From 8b276b59ccf983517a0d40f8a3ac243a104d4c16 Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Mon, 29 Nov 2021 19:11:44 +0000 Subject: include: trace: Add new scmi_xfer_response_wait event Having a new step to trace SCMI stack while it waits for synchronous responses is useful to analyze system performance when changing waiting mode between polling and interrupt completion. Link: https://lore.kernel.org/r/20211129191156.29322-5-cristian.marussi@arm.com Reviewed-by: Florian Fainelli Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/trace/events/scmi.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include') diff --git a/include/trace/events/scmi.h b/include/trace/events/scmi.h index f3a4b4d60714..cee4b2b64ae4 100644 --- a/include/trace/events/scmi.h +++ b/include/trace/events/scmi.h @@ -33,6 +33,34 @@ TRACE_EVENT(scmi_xfer_begin, __entry->seq, __entry->poll) ); +TRACE_EVENT(scmi_xfer_response_wait, + TP_PROTO(int transfer_id, u8 msg_id, u8 protocol_id, u16 seq, + u32 timeout, bool poll), + TP_ARGS(transfer_id, msg_id, protocol_id, seq, timeout, poll), + + TP_STRUCT__entry( + __field(int, transfer_id) + __field(u8, msg_id) + __field(u8, protocol_id) + __field(u16, seq) + __field(u32, timeout) + __field(bool, poll) + ), + + TP_fast_assign( + __entry->transfer_id = transfer_id; + __entry->msg_id = msg_id; + __entry->protocol_id = protocol_id; + __entry->seq = seq; + __entry->timeout = timeout; + __entry->poll = poll; + ), + + TP_printk("transfer_id=%d msg_id=%u protocol_id=%u seq=%u tmo_ms=%u poll=%u", + __entry->transfer_id, __entry->msg_id, __entry->protocol_id, + __entry->seq, __entry->timeout, __entry->poll) +); + TRACE_EVENT(scmi_xfer_end, TP_PROTO(int transfer_id, u8 msg_id, u8 protocol_id, u16 seq, int status), -- cgit v1.2.3 From 7e28d0b26759846485978ada860ef4a427e06c8f Mon Sep 17 00:00:00 2001 From: Tejas Upadhyay Date: Fri, 10 Dec 2021 10:48:02 +0530 Subject: drm/i915/adl-n: Enable ADL-N platform Adding PCI device ids and enabling ADL-N platform. ADL-N from i915 point of view is subplatform of ADL-P. BSpec: 68397 Changes since V2: - Added version log history Changes since V1: - replace IS_ALDERLAKE_N with IS_ADLP_N - Jani Nikula Signed-off-by: Tejas Upadhyay Reviewed-by: Anusha Srivatsa Acked-by: Thomas Gleixner Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20211210051802.4063958-1-tejaskumarx.surendrakumar.upadhyay@intel.com --- include/drm/i915_pciids.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h index baf3d1d3d566..533890dc9da1 100644 --- a/include/drm/i915_pciids.h +++ b/include/drm/i915_pciids.h @@ -666,6 +666,12 @@ INTEL_VGA_DEVICE(0x46C2, info), \ INTEL_VGA_DEVICE(0x46C3, info) +/* ADL-N */ +#define INTEL_ADLN_IDS(info) \ + INTEL_VGA_DEVICE(0x46D0, info), \ + INTEL_VGA_DEVICE(0x46D1, info), \ + INTEL_VGA_DEVICE(0x46D2, info) + /* RPL-S */ #define INTEL_RPLS_IDS(info) \ INTEL_VGA_DEVICE(0xA780, info), \ -- cgit v1.2.3 From 69255e746890274e887ba36a403019380cde0b48 Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Mon, 20 Dec 2021 19:56:41 +0000 Subject: firmware: arm_scmi: Add support for atomic transports An SCMI transport can be configured as .atomic_enabled in order to signal to the SCMI core that all its TX path is executed in atomic context and that, when requested, polling mode should be used while waiting for command responses. When a specific platform configuration had properly configured such a transport as .atomic_enabled, the SCMI core will also take care not to sleep in the corresponding RX path while waiting for a response if that specific command transaction was requested as atomic using polling mode. Asynchronous commands should not be used in an atomic context and so a warning is emitted if polling was requested for an asynchronous command. Add also a method to check, from the SCMI drivers, if the underlying SCMI transport is currently configured to support atomic transactions: this will be used by upper layers to determine if atomic requests can be supported at all on this SCMI instance. Link: https://lore.kernel.org/r/20211220195646.44498-7-cristian.marussi@arm.com Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 80e781c51ddc..9f895cb81818 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -612,6 +612,13 @@ struct scmi_notify_ops { * @devm_protocol_get: devres managed method to acquire a protocol and get specific * operations and a dedicated protocol handler * @devm_protocol_put: devres managed method to release a protocol + * @is_transport_atomic: method to check if the underlying transport for this + * instance handle is configured to support atomic + * transactions for commands. + * Some users of the SCMI stack in the upper layers could + * be interested to know if they can assume SCMI + * command transactions associated to this handle will + * never sleep and act accordingly. * @notify_ops: pointer to set of notifications related operations */ struct scmi_handle { @@ -622,6 +629,7 @@ struct scmi_handle { (*devm_protocol_get)(struct scmi_device *sdev, u8 proto, struct scmi_protocol_handle **ph); void (*devm_protocol_put)(struct scmi_device *sdev, u8 proto); + bool (*is_transport_atomic)(const struct scmi_handle *handle); const struct scmi_notify_ops *notify_ops; }; -- cgit v1.2.3 From 6844a28885183a5a2af92a8d315a59f7a0e668b9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Tue, 21 Dec 2021 21:37:54 +0200 Subject: drm/dbi: Use a static inline stub for mipi_dbi_debugfs_init() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replace the slightly odd "#define NULL" thing with a standard static inline stub. Cc: Noralf Trønnes Cc: Sam Ravnborg Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20211221193754.12287-2-ville.syrjala@linux.intel.com Reviewed-by: Jani Nikula --- include/drm/drm_mipi_dbi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_mipi_dbi.h b/include/drm/drm_mipi_dbi.h index 05e194958265..6fe13cce2670 100644 --- a/include/drm/drm_mipi_dbi.h +++ b/include/drm/drm_mipi_dbi.h @@ -194,7 +194,7 @@ int mipi_dbi_buf_copy(void *dst, struct drm_framebuffer *fb, #ifdef CONFIG_DEBUG_FS void mipi_dbi_debugfs_init(struct drm_minor *minor); #else -#define mipi_dbi_debugfs_init NULL +static inline void mipi_dbi_debugfs_init(struct drm_minor *minor) {} #endif #endif /* __LINUX_MIPI_DBI_H */ -- cgit v1.2.3 From 825ca9ed1c9f5516b30292bb1c7ab648c2a01b92 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Tue, 21 Dec 2021 21:37:53 +0200 Subject: drm: Always include the debugfs dentry in drm_crtc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Remove the counterproductive CONFIG_DEBUG_FS ifdef and just include the debugfs dentry in drm_crtc always. This way we don't need annoying ifdefs in the actual code with DEBUGFS=n. Also we don't have these ifdefs around any of the other debugfs dentries either so can't see why drm_crtc should be special. This fixes the i915 DEBUGFS=n build because I assumed the dentry would always be there. Cc: Jani Nikula Reported-by: Nathan Chancellor Tested-by: Nathan Chancellor Fixes: e74c6aa955ca ("drm/i915/fbc: Register per-crtc debugfs files") Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20211221193754.12287-1-ville.syrjala@linux.intel.com Reviewed-by: Jani Nikula Acked-by: Daniel Vetter --- include/drm/drm_crtc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h index 13eeba2a750a..4d01b4d89775 100644 --- a/include/drm/drm_crtc.h +++ b/include/drm/drm_crtc.h @@ -1135,14 +1135,12 @@ struct drm_crtc { */ spinlock_t commit_lock; -#ifdef CONFIG_DEBUG_FS /** * @debugfs_entry: * * Debugfs directory for this CRTC. */ struct dentry *debugfs_entry; -#endif /** * @crc: -- cgit v1.2.3 From 5f4f958a0d9dfd7a569c56e76840e39b0c434378 Mon Sep 17 00:00:00 2001 From: Antonio Borneo Date: Sat, 18 Dec 2021 22:50:53 +0100 Subject: drm/bridge/synopsys: dsi: extend the prototype of mode_valid() To evaluate the validity of a video mode, some additional internal value has to be passed to the platform implementation. Extend the prototype of mode_valid(). Signed-off-by: Antonio Borneo Reviewed-by: Philippe Cornu Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20211218215055.212421-2-antonio.borneo@foss.st.com --- include/drm/bridge/dw_mipi_dsi.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/bridge/dw_mipi_dsi.h b/include/drm/bridge/dw_mipi_dsi.h index bda8aa7c2280..5286a53a1875 100644 --- a/include/drm/bridge/dw_mipi_dsi.h +++ b/include/drm/bridge/dw_mipi_dsi.h @@ -51,7 +51,9 @@ struct dw_mipi_dsi_plat_data { unsigned int max_data_lanes; enum drm_mode_status (*mode_valid)(void *priv_data, - const struct drm_display_mode *mode); + const struct drm_display_mode *mode, + unsigned long mode_flags, + u32 lanes, u32 format); const struct dw_mipi_dsi_phy_ops *phy_ops; const struct dw_mipi_dsi_host_ops *host_ops; -- cgit v1.2.3 From 91d8531393be96b4a088290cc67233b2e6ab072f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jos=C3=A9=20Exp=C3=B3sito?= Date: Sun, 26 Dec 2021 12:24:59 +0100 Subject: drm/plane: Fix typo in format_mod_supported documentation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix minor typo: "valdiate" -> "validate". Signed-off-by: José Expósito Reviewed-by: Simon Ser Signed-off-by: Simon Ser Link: https://patchwork.freedesktop.org/patch/msgid/20211226112503.31771-3-jose.exposito89@gmail.com --- include/drm/drm_plane.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h index 0c1102dc4d88..06759badf99f 100644 --- a/include/drm/drm_plane.h +++ b/include/drm/drm_plane.h @@ -516,7 +516,7 @@ struct drm_plane_funcs { * This optional hook is used for the DRM to determine if the given * format/modifier combination is valid for the plane. This allows the * DRM to generate the correct format bitmask (which formats apply to - * which modifier), and to valdiate modifiers at atomic_check time. + * which modifier), and to validate modifiers at atomic_check time. * * If not present, then any modifier in the plane's modifier * list is allowed with any of the plane's formats. -- cgit v1.2.3 From 30598d925d466c53c4c218a58f80e043cfe9b085 Mon Sep 17 00:00:00 2001 From: Rajat Jain Date: Fri, 7 Jan 2022 11:02:06 -0800 Subject: drm/privacy_screen: Add drvdata in drm_privacy_screen Allow a privacy screen provider to stash its private data pointer in the drm_privacy_screen, and update the drm_privacy_screen_register() call to accept that. Also introduce a *_get_drvdata() so that it can retrieved back when needed. This also touches the IBM Thinkpad platform driver, the only user of privacy screen today, to pass NULL for now to the updated API. Signed-off-by: Rajat Jain Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Link: https://patchwork.freedesktop.org/patch/msgid/20220107190208.95479-1-rajatja@google.com --- include/drm/drm_privacy_screen_driver.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_privacy_screen_driver.h b/include/drm/drm_privacy_screen_driver.h index 24591b607675..4ef246d5706f 100644 --- a/include/drm/drm_privacy_screen_driver.h +++ b/include/drm/drm_privacy_screen_driver.h @@ -73,10 +73,21 @@ struct drm_privacy_screen { * for more info. */ enum drm_privacy_screen_status hw_state; + /** + * @drvdata: Private data owned by the privacy screen provider + */ + void *drvdata; }; +static inline +void *drm_privacy_screen_get_drvdata(struct drm_privacy_screen *priv) +{ + return priv->drvdata; +} + struct drm_privacy_screen *drm_privacy_screen_register( - struct device *parent, const struct drm_privacy_screen_ops *ops); + struct device *parent, const struct drm_privacy_screen_ops *ops, + void *data); void drm_privacy_screen_unregister(struct drm_privacy_screen *priv); void drm_privacy_screen_call_notifier_chain(struct drm_privacy_screen *priv); -- cgit v1.2.3 From a9e4fb51425f680f191bb65c2778cea31bf058c7 Mon Sep 17 00:00:00 2001 From: Alyssa Rosenzweig Date: Sun, 9 Jan 2022 11:37:04 -0500 Subject: drm/panfrost: Update create_bo flags comment Update a comment stating create_bo took no flags, since it now takes a bit mask of optional flags NOEXEC and HEAP. Signed-off-by: Alyssa Rosenzweig Reviewed-by: Steven Price Signed-off-by: Steven Price Link: https://patchwork.freedesktop.org/patch/msgid/20220109163704.2564-1-alyssa.rosenzweig@collabora.com --- include/uapi/drm/panfrost_drm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/drm/panfrost_drm.h b/include/uapi/drm/panfrost_drm.h index 061e700dd06c..9e40277d8185 100644 --- a/include/uapi/drm/panfrost_drm.h +++ b/include/uapi/drm/panfrost_drm.h @@ -84,14 +84,14 @@ struct drm_panfrost_wait_bo { __s64 timeout_ns; /* absolute */ }; +/* Valid flags to pass to drm_panfrost_create_bo */ #define PANFROST_BO_NOEXEC 1 #define PANFROST_BO_HEAP 2 /** * struct drm_panfrost_create_bo - ioctl argument for creating Panfrost BOs. * - * There are currently no values for the flags argument, but it may be - * used in a future extension. + * The flags argument is a bit mask of PANFROST_BO_* flags. */ struct drm_panfrost_create_bo { __u32 size; -- cgit v1.2.3 From e8c1f36157ce0bf8c150059c3f9f573c13a186df Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Mon, 10 Jan 2022 16:33:05 -0800 Subject: dma-buf-map: Fix dot vs comma in example Fix typo: separate arguments with comma rather than dot. Signed-off-by: Lucas De Marchi Signed-off-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20220111003305.1214667-1-lucas.demarchi@intel.com --- include/linux/dma-buf-map.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/dma-buf-map.h b/include/linux/dma-buf-map.h index 278d489e4bdd..19fa0b5ae5ec 100644 --- a/include/linux/dma-buf-map.h +++ b/include/linux/dma-buf-map.h @@ -52,13 +52,13 @@ * * struct dma_buf_map map = DMA_BUF_MAP_INIT_VADDR(0xdeadbeaf); * - * dma_buf_map_set_vaddr(&map. 0xdeadbeaf); + * dma_buf_map_set_vaddr(&map, 0xdeadbeaf); * * To set an address in I/O memory, use dma_buf_map_set_vaddr_iomem(). * * .. code-block:: c * - * dma_buf_map_set_vaddr_iomem(&map. 0xdeadbeaf); + * dma_buf_map_set_vaddr_iomem(&map, 0xdeadbeaf); * * Instances of struct dma_buf_map do not have to be cleaned up, but * can be cleared to NULL with dma_buf_map_clear(). Cleared mappings -- cgit v1.2.3 From 39feb6e726e7b36327e4c82239669bf86dd59544 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Wed, 15 Dec 2021 10:51:14 +0100 Subject: firmware: raspberrypi: Add RPI_FIRMWARE_NOTIFY_DISPLAY_DONE The RPI_FIRMWARE_NOTIFY_DISPLAY_DONE firmware call allows to tell the firmware the kernel is in charge of the display now and the firmware can free whatever resources it was using. Acked-by: Nicolas Saenz Julienne Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20211215095117.176435-2-maxime@cerno.tech --- include/soc/bcm2835/raspberrypi-firmware.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/soc/bcm2835/raspberrypi-firmware.h b/include/soc/bcm2835/raspberrypi-firmware.h index 73ad784fca96..811ea668c4a1 100644 --- a/include/soc/bcm2835/raspberrypi-firmware.h +++ b/include/soc/bcm2835/raspberrypi-firmware.h @@ -91,6 +91,7 @@ enum rpi_firmware_property_tag { RPI_FIRMWARE_GET_POE_HAT_VAL = 0x00030049, RPI_FIRMWARE_SET_POE_HAT_VAL = 0x00030050, RPI_FIRMWARE_NOTIFY_XHCI_RESET = 0x00030058, + RPI_FIRMWARE_NOTIFY_DISPLAY_DONE = 0x00030066, /* Dispmanx TAGS */ RPI_FIRMWARE_FRAMEBUFFER_ALLOCATE = 0x00040001, -- cgit v1.2.3 From 55a9c00021e2393393a26e0833fd66e73d630117 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Tue, 4 Jan 2022 20:48:56 +0200 Subject: drm/dp: note that DPCD 0x2002-0x2003 match 0x200-0x201 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit DP_SINK_COUNT_ESI and DP_DEVICE_SERVICE_IRQ_VECTOR_ESI0 have the same contents as DP_SINK_COUNT and DP_DEVICE_SERVICE_IRQ_VECTOR, respectively. Signed-off-by: Jani Nikula Reviewed-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20220104184857.784563-1-jani.nikula@intel.com --- include/drm/drm_dp_helper.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 8b2ed4199284..16d6da3a129f 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -1038,11 +1038,8 @@ struct drm_panel; #define DP_SIDEBAND_MSG_UP_REQ_BASE 0x1600 /* 1.2 MST */ /* DPRX Event Status Indicator */ -#define DP_SINK_COUNT_ESI 0x2002 /* 1.2 */ -/* 0-5 sink count */ -# define DP_SINK_COUNT_CP_READY (1 << 6) - -#define DP_DEVICE_SERVICE_IRQ_VECTOR_ESI0 0x2003 /* 1.2 */ +#define DP_SINK_COUNT_ESI 0x2002 /* same as 0x200 */ +#define DP_DEVICE_SERVICE_IRQ_VECTOR_ESI0 0x2003 /* same as 0x201 */ #define DP_DEVICE_SERVICE_IRQ_VECTOR_ESI1 0x2004 /* 1.2 */ # define DP_RX_GTC_MSTR_REQ_STATUS_CHANGE (1 << 0) -- cgit v1.2.3 From d72d84aea4d57a735d8cfbade32ed323f47a5941 Mon Sep 17 00:00:00 2001 From: Guchun Chen Date: Fri, 14 Jan 2022 16:37:42 +0800 Subject: locking/rwsem: drop redundant semicolon of down_write_nest_lock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Otherwise, braces are needed when using it. Signed-off-by: Guchun Chen Acked-by: Christian König Acked-by: Peter Zijlstra (Intel) Link: https://patchwork.freedesktop.org/patch/msgid/20220114083742.6219-1-guchun.chen@amd.com Signed-off-by: Christian König --- include/linux/rwsem.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index f9348769e558..efa5c324369a 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -230,7 +230,7 @@ extern void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map * do { \ typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ _down_write_nest_lock(sem, &(nest_lock)->dep_map); \ -} while (0); +} while (0) /* * Take/release a lock when not the owner will release it. -- cgit v1.2.3 From c4381d0ee81930097e94e55d1c23f85798ffd093 Mon Sep 17 00:00:00 2001 From: Bokun Zhang Date: Wed, 12 Jan 2022 10:34:11 -0500 Subject: drm/amdgpu: Add interface to load SRIOV cap FW - Add interface to load SRIOV cap FW. If the FW does not exist, simply skip this FW loading routine. This FW will only be loaded under SRIOV. Other driver configuration will not be affected. By adding this interface, it will make us easier to prepare SRIOV Linux guest driver for different users. - Update sysfs interface to read cap FW version. - Refactor PSP FW loading routine under SRIOV to use a unified SWITCH statement instead of using IF statement - Remove redundant amdgpu_sriov_vf() check in FW loading routine Acked-by: Monk Liu Acked-by: Guchun Chen Signed-off-by: Bokun Zhang Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 0b94ec7b73e7..be4f9111f478 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -728,6 +728,8 @@ struct drm_amdgpu_cs_chunk_data { #define AMDGPU_INFO_FW_DMCUB 0x14 /* Subquery id: Query TOC firmware version */ #define AMDGPU_INFO_FW_TOC 0x15 + /* Subquery id: Query CAP firmware version */ + #define AMDGPU_INFO_FW_CAP 0x16 /* number of bytes moved for TTM migration */ #define AMDGPU_INFO_NUM_BYTES_MOVED 0x0f -- cgit v1.2.3 From 5b529e8d9c387a34ca2b8008dc65f55d539b3ef6 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 14 Jan 2022 12:45:34 +0100 Subject: drm/dp: Move public DisplayPort headers into dp/ Move all public DisplayPort headers into dp/ and update users. No functional changes. v3: * rebased onto latest drm-tip Signed-off-by: Thomas Zimmermann Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220114114535.29157-5-tzimmermann@suse.de --- include/drm/dp/drm_dp_dual_mode_helper.h | 121 ++ include/drm/dp/drm_dp_helper.h | 2358 ++++++++++++++++++++++++++++++ include/drm/dp/drm_dp_mst_helper.h | 972 ++++++++++++ include/drm/drm_dp_dual_mode_helper.h | 121 -- include/drm/drm_dp_helper.h | 2358 ------------------------------ include/drm/drm_dp_mst_helper.h | 972 ------------ include/drm/drm_dsc.h | 2 +- 7 files changed, 3452 insertions(+), 3452 deletions(-) create mode 100644 include/drm/dp/drm_dp_dual_mode_helper.h create mode 100644 include/drm/dp/drm_dp_helper.h create mode 100644 include/drm/dp/drm_dp_mst_helper.h delete mode 100644 include/drm/drm_dp_dual_mode_helper.h delete mode 100644 include/drm/drm_dp_helper.h delete mode 100644 include/drm/drm_dp_mst_helper.h (limited to 'include') diff --git a/include/drm/dp/drm_dp_dual_mode_helper.h b/include/drm/dp/drm_dp_dual_mode_helper.h new file mode 100644 index 000000000000..7ee482265087 --- /dev/null +++ b/include/drm/dp/drm_dp_dual_mode_helper.h @@ -0,0 +1,121 @@ +/* + * Copyright © 2016 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#ifndef DRM_DP_DUAL_MODE_HELPER_H +#define DRM_DP_DUAL_MODE_HELPER_H + +#include + +/* + * Optional for type 1 DVI adaptors + * Mandatory for type 1 HDMI and type 2 adaptors + */ +#define DP_DUAL_MODE_HDMI_ID 0x00 /* 00-0f */ +#define DP_DUAL_MODE_HDMI_ID_LEN 16 +/* + * Optional for type 1 adaptors + * Mandatory for type 2 adaptors + */ +#define DP_DUAL_MODE_ADAPTOR_ID 0x10 +#define DP_DUAL_MODE_REV_MASK 0x07 +#define DP_DUAL_MODE_REV_TYPE2 0x00 +#define DP_DUAL_MODE_TYPE_MASK 0xf0 +#define DP_DUAL_MODE_TYPE_TYPE2 0xa0 +/* This field is marked reserved in dual mode spec, used in LSPCON */ +#define DP_DUAL_MODE_TYPE_HAS_DPCD 0x08 +#define DP_DUAL_MODE_IEEE_OUI 0x11 /* 11-13*/ +#define DP_DUAL_IEEE_OUI_LEN 3 +#define DP_DUAL_DEVICE_ID 0x14 /* 14-19 */ +#define DP_DUAL_DEVICE_ID_LEN 6 +#define DP_DUAL_MODE_HARDWARE_REV 0x1a +#define DP_DUAL_MODE_FIRMWARE_MAJOR_REV 0x1b +#define DP_DUAL_MODE_FIRMWARE_MINOR_REV 0x1c +#define DP_DUAL_MODE_MAX_TMDS_CLOCK 0x1d +#define DP_DUAL_MODE_I2C_SPEED_CAP 0x1e +#define DP_DUAL_MODE_TMDS_OEN 0x20 +#define DP_DUAL_MODE_TMDS_DISABLE 0x01 +#define DP_DUAL_MODE_HDMI_PIN_CTRL 0x21 +#define DP_DUAL_MODE_CEC_ENABLE 0x01 +#define DP_DUAL_MODE_I2C_SPEED_CTRL 0x22 + +/* LSPCON specific registers, defined by MCA */ +#define DP_DUAL_MODE_LSPCON_MODE_CHANGE 0x40 +#define DP_DUAL_MODE_LSPCON_CURRENT_MODE 0x41 +#define DP_DUAL_MODE_LSPCON_MODE_PCON 0x1 + +struct drm_device; +struct i2c_adapter; + +ssize_t drm_dp_dual_mode_read(struct i2c_adapter *adapter, + u8 offset, void *buffer, size_t size); +ssize_t drm_dp_dual_mode_write(struct i2c_adapter *adapter, + u8 offset, const void *buffer, size_t size); + +/** + * enum drm_lspcon_mode + * @DRM_LSPCON_MODE_INVALID: No LSPCON. + * @DRM_LSPCON_MODE_LS: Level shifter mode of LSPCON + * which drives DP++ to HDMI 1.4 conversion. + * @DRM_LSPCON_MODE_PCON: Protocol converter mode of LSPCON + * which drives DP++ to HDMI 2.0 active conversion. + */ +enum drm_lspcon_mode { + DRM_LSPCON_MODE_INVALID, + DRM_LSPCON_MODE_LS, + DRM_LSPCON_MODE_PCON, +}; + +/** + * enum drm_dp_dual_mode_type - Type of the DP dual mode adaptor + * @DRM_DP_DUAL_MODE_NONE: No DP dual mode adaptor + * @DRM_DP_DUAL_MODE_UNKNOWN: Could be either none or type 1 DVI adaptor + * @DRM_DP_DUAL_MODE_TYPE1_DVI: Type 1 DVI adaptor + * @DRM_DP_DUAL_MODE_TYPE1_HDMI: Type 1 HDMI adaptor + * @DRM_DP_DUAL_MODE_TYPE2_DVI: Type 2 DVI adaptor + * @DRM_DP_DUAL_MODE_TYPE2_HDMI: Type 2 HDMI adaptor + * @DRM_DP_DUAL_MODE_LSPCON: Level shifter / protocol converter + */ +enum drm_dp_dual_mode_type { + DRM_DP_DUAL_MODE_NONE, + DRM_DP_DUAL_MODE_UNKNOWN, + DRM_DP_DUAL_MODE_TYPE1_DVI, + DRM_DP_DUAL_MODE_TYPE1_HDMI, + DRM_DP_DUAL_MODE_TYPE2_DVI, + DRM_DP_DUAL_MODE_TYPE2_HDMI, + DRM_DP_DUAL_MODE_LSPCON, +}; + +enum drm_dp_dual_mode_type +drm_dp_dual_mode_detect(const struct drm_device *dev, struct i2c_adapter *adapter); +int drm_dp_dual_mode_max_tmds_clock(const struct drm_device *dev, enum drm_dp_dual_mode_type type, + struct i2c_adapter *adapter); +int drm_dp_dual_mode_get_tmds_output(const struct drm_device *dev, enum drm_dp_dual_mode_type type, + struct i2c_adapter *adapter, bool *enabled); +int drm_dp_dual_mode_set_tmds_output(const struct drm_device *dev, enum drm_dp_dual_mode_type type, + struct i2c_adapter *adapter, bool enable); +const char *drm_dp_get_dual_mode_type_name(enum drm_dp_dual_mode_type type); + +int drm_lspcon_get_mode(const struct drm_device *dev, struct i2c_adapter *adapter, + enum drm_lspcon_mode *current_mode); +int drm_lspcon_set_mode(const struct drm_device *dev, struct i2c_adapter *adapter, + enum drm_lspcon_mode reqd_mode); +#endif diff --git a/include/drm/dp/drm_dp_helper.h b/include/drm/dp/drm_dp_helper.h new file mode 100644 index 000000000000..16d6da3a129f --- /dev/null +++ b/include/drm/dp/drm_dp_helper.h @@ -0,0 +1,2358 @@ +/* + * Copyright © 2008 Keith Packard + * + * Permission to use, copy, modify, distribute, and sell this software and its + * documentation for any purpose is hereby granted without fee, provided that + * the above copyright notice appear in all copies and that both that copyright + * notice and this permission notice appear in supporting documentation, and + * that the name of the copyright holders not be used in advertising or + * publicity pertaining to distribution of the software without specific, + * written prior permission. The copyright holders make no representations + * about the suitability of this software for any purpose. It is provided "as + * is" without express or implied warranty. + * + * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, + * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO + * EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT OR + * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, + * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER + * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE + * OF THIS SOFTWARE. + */ + +#ifndef _DRM_DP_HELPER_H_ +#define _DRM_DP_HELPER_H_ + +#include +#include +#include +#include + +struct drm_device; +struct drm_dp_aux; +struct drm_panel; + +/* + * Unless otherwise noted, all values are from the DP 1.1a spec. Note that + * DP and DPCD versions are independent. Differences from 1.0 are not noted, + * 1.0 devices basically don't exist in the wild. + * + * Abbreviations, in chronological order: + * + * eDP: Embedded DisplayPort version 1 + * DPI: DisplayPort Interoperability Guideline v1.1a + * 1.2: DisplayPort 1.2 + * MST: Multistream Transport - part of DP 1.2a + * + * 1.2 formally includes both eDP and DPI definitions. + */ + +/* MSA (Main Stream Attribute) MISC bits (as MISC1<<8|MISC0) */ +#define DP_MSA_MISC_SYNC_CLOCK (1 << 0) +#define DP_MSA_MISC_INTERLACE_VTOTAL_EVEN (1 << 8) +#define DP_MSA_MISC_STEREO_NO_3D (0 << 9) +#define DP_MSA_MISC_STEREO_PROG_RIGHT_EYE (1 << 9) +#define DP_MSA_MISC_STEREO_PROG_LEFT_EYE (3 << 9) +/* bits per component for non-RAW */ +#define DP_MSA_MISC_6_BPC (0 << 5) +#define DP_MSA_MISC_8_BPC (1 << 5) +#define DP_MSA_MISC_10_BPC (2 << 5) +#define DP_MSA_MISC_12_BPC (3 << 5) +#define DP_MSA_MISC_16_BPC (4 << 5) +/* bits per component for RAW */ +#define DP_MSA_MISC_RAW_6_BPC (1 << 5) +#define DP_MSA_MISC_RAW_7_BPC (2 << 5) +#define DP_MSA_MISC_RAW_8_BPC (3 << 5) +#define DP_MSA_MISC_RAW_10_BPC (4 << 5) +#define DP_MSA_MISC_RAW_12_BPC (5 << 5) +#define DP_MSA_MISC_RAW_14_BPC (6 << 5) +#define DP_MSA_MISC_RAW_16_BPC (7 << 5) +/* pixel encoding/colorimetry format */ +#define _DP_MSA_MISC_COLOR(misc1_7, misc0_21, misc0_3, misc0_4) \ + ((misc1_7) << 15 | (misc0_4) << 4 | (misc0_3) << 3 | ((misc0_21) << 1)) +#define DP_MSA_MISC_COLOR_RGB _DP_MSA_MISC_COLOR(0, 0, 0, 0) +#define DP_MSA_MISC_COLOR_CEA_RGB _DP_MSA_MISC_COLOR(0, 0, 1, 0) +#define DP_MSA_MISC_COLOR_RGB_WIDE_FIXED _DP_MSA_MISC_COLOR(0, 3, 0, 0) +#define DP_MSA_MISC_COLOR_RGB_WIDE_FLOAT _DP_MSA_MISC_COLOR(0, 3, 0, 1) +#define DP_MSA_MISC_COLOR_Y_ONLY _DP_MSA_MISC_COLOR(1, 0, 0, 0) +#define DP_MSA_MISC_COLOR_RAW _DP_MSA_MISC_COLOR(1, 1, 0, 0) +#define DP_MSA_MISC_COLOR_YCBCR_422_BT601 _DP_MSA_MISC_COLOR(0, 1, 1, 0) +#define DP_MSA_MISC_COLOR_YCBCR_422_BT709 _DP_MSA_MISC_COLOR(0, 1, 1, 1) +#define DP_MSA_MISC_COLOR_YCBCR_444_BT601 _DP_MSA_MISC_COLOR(0, 2, 1, 0) +#define DP_MSA_MISC_COLOR_YCBCR_444_BT709 _DP_MSA_MISC_COLOR(0, 2, 1, 1) +#define DP_MSA_MISC_COLOR_XVYCC_422_BT601 _DP_MSA_MISC_COLOR(0, 1, 0, 0) +#define DP_MSA_MISC_COLOR_XVYCC_422_BT709 _DP_MSA_MISC_COLOR(0, 1, 0, 1) +#define DP_MSA_MISC_COLOR_XVYCC_444_BT601 _DP_MSA_MISC_COLOR(0, 2, 0, 0) +#define DP_MSA_MISC_COLOR_XVYCC_444_BT709 _DP_MSA_MISC_COLOR(0, 2, 0, 1) +#define DP_MSA_MISC_COLOR_OPRGB _DP_MSA_MISC_COLOR(0, 0, 1, 1) +#define DP_MSA_MISC_COLOR_DCI_P3 _DP_MSA_MISC_COLOR(0, 3, 1, 0) +#define DP_MSA_MISC_COLOR_COLOR_PROFILE _DP_MSA_MISC_COLOR(0, 3, 1, 1) +#define DP_MSA_MISC_COLOR_VSC_SDP (1 << 14) + +#define DP_AUX_MAX_PAYLOAD_BYTES 16 + +#define DP_AUX_I2C_WRITE 0x0 +#define DP_AUX_I2C_READ 0x1 +#define DP_AUX_I2C_WRITE_STATUS_UPDATE 0x2 +#define DP_AUX_I2C_MOT 0x4 +#define DP_AUX_NATIVE_WRITE 0x8 +#define DP_AUX_NATIVE_READ 0x9 + +#define DP_AUX_NATIVE_REPLY_ACK (0x0 << 0) +#define DP_AUX_NATIVE_REPLY_NACK (0x1 << 0) +#define DP_AUX_NATIVE_REPLY_DEFER (0x2 << 0) +#define DP_AUX_NATIVE_REPLY_MASK (0x3 << 0) + +#define DP_AUX_I2C_REPLY_ACK (0x0 << 2) +#define DP_AUX_I2C_REPLY_NACK (0x1 << 2) +#define DP_AUX_I2C_REPLY_DEFER (0x2 << 2) +#define DP_AUX_I2C_REPLY_MASK (0x3 << 2) + +/* DPCD Field Address Mapping */ + +/* Receiver Capability */ +#define DP_DPCD_REV 0x000 +# define DP_DPCD_REV_10 0x10 +# define DP_DPCD_REV_11 0x11 +# define DP_DPCD_REV_12 0x12 +# define DP_DPCD_REV_13 0x13 +# define DP_DPCD_REV_14 0x14 + +#define DP_MAX_LINK_RATE 0x001 + +#define DP_MAX_LANE_COUNT 0x002 +# define DP_MAX_LANE_COUNT_MASK 0x1f +# define DP_TPS3_SUPPORTED (1 << 6) /* 1.2 */ +# define DP_ENHANCED_FRAME_CAP (1 << 7) + +#define DP_MAX_DOWNSPREAD 0x003 +# define DP_MAX_DOWNSPREAD_0_5 (1 << 0) +# define DP_STREAM_REGENERATION_STATUS_CAP (1 << 1) /* 2.0 */ +# define DP_NO_AUX_HANDSHAKE_LINK_TRAINING (1 << 6) +# define DP_TPS4_SUPPORTED (1 << 7) + +#define DP_NORP 0x004 + +#define DP_DOWNSTREAMPORT_PRESENT 0x005 +# define DP_DWN_STRM_PORT_PRESENT (1 << 0) +# define DP_DWN_STRM_PORT_TYPE_MASK 0x06 +# define DP_DWN_STRM_PORT_TYPE_DP (0 << 1) +# define DP_DWN_STRM_PORT_TYPE_ANALOG (1 << 1) +# define DP_DWN_STRM_PORT_TYPE_TMDS (2 << 1) +# define DP_DWN_STRM_PORT_TYPE_OTHER (3 << 1) +# define DP_FORMAT_CONVERSION (1 << 3) +# define DP_DETAILED_CAP_INFO_AVAILABLE (1 << 4) /* DPI */ + +#define DP_MAIN_LINK_CHANNEL_CODING 0x006 +# define DP_CAP_ANSI_8B10B (1 << 0) +# define DP_CAP_ANSI_128B132B (1 << 1) /* 2.0 */ + +#define DP_DOWN_STREAM_PORT_COUNT 0x007 +# define DP_PORT_COUNT_MASK 0x0f +# define DP_MSA_TIMING_PAR_IGNORED (1 << 6) /* eDP */ +# define DP_OUI_SUPPORT (1 << 7) + +#define DP_RECEIVE_PORT_0_CAP_0 0x008 +# define DP_LOCAL_EDID_PRESENT (1 << 1) +# define DP_ASSOCIATED_TO_PRECEDING_PORT (1 << 2) + +#define DP_RECEIVE_PORT_0_BUFFER_SIZE 0x009 + +#define DP_RECEIVE_PORT_1_CAP_0 0x00a +#define DP_RECEIVE_PORT_1_BUFFER_SIZE 0x00b + +#define DP_I2C_SPEED_CAP 0x00c /* DPI */ +# define DP_I2C_SPEED_1K 0x01 +# define DP_I2C_SPEED_5K 0x02 +# define DP_I2C_SPEED_10K 0x04 +# define DP_I2C_SPEED_100K 0x08 +# define DP_I2C_SPEED_400K 0x10 +# define DP_I2C_SPEED_1M 0x20 + +#define DP_EDP_CONFIGURATION_CAP 0x00d /* XXX 1.2? */ +# define DP_ALTERNATE_SCRAMBLER_RESET_CAP (1 << 0) +# define DP_FRAMING_CHANGE_CAP (1 << 1) +# define DP_DPCD_DISPLAY_CONTROL_CAPABLE (1 << 3) /* edp v1.2 or higher */ + +#define DP_TRAINING_AUX_RD_INTERVAL 0x00e /* XXX 1.2? */ +# define DP_TRAINING_AUX_RD_MASK 0x7F /* DP 1.3 */ +# define DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT (1 << 7) /* DP 1.3 */ + +#define DP_ADAPTER_CAP 0x00f /* 1.2 */ +# define DP_FORCE_LOAD_SENSE_CAP (1 << 0) +# define DP_ALTERNATE_I2C_PATTERN_CAP (1 << 1) + +#define DP_SUPPORTED_LINK_RATES 0x010 /* eDP 1.4 */ +# define DP_MAX_SUPPORTED_RATES 8 /* 16-bit little-endian */ + +/* Multiple stream transport */ +#define DP_FAUX_CAP 0x020 /* 1.2 */ +# define DP_FAUX_CAP_1 (1 << 0) + +#define DP_SINK_VIDEO_FALLBACK_FORMATS 0x020 /* 2.0 */ +# define DP_FALLBACK_1024x768_60HZ_24BPP (1 << 0) +# define DP_FALLBACK_1280x720_60HZ_24BPP (1 << 1) +# define DP_FALLBACK_1920x1080_60HZ_24BPP (1 << 2) + +#define DP_MSTM_CAP 0x021 /* 1.2 */ +# define DP_MST_CAP (1 << 0) +# define DP_SINGLE_STREAM_SIDEBAND_MSG (1 << 1) /* 2.0 */ + +#define DP_NUMBER_OF_AUDIO_ENDPOINTS 0x022 /* 1.2 */ + +/* AV_SYNC_DATA_BLOCK 1.2 */ +#define DP_AV_GRANULARITY 0x023 +# define DP_AG_FACTOR_MASK (0xf << 0) +# define DP_AG_FACTOR_3MS (0 << 0) +# define DP_AG_FACTOR_2MS (1 << 0) +# define DP_AG_FACTOR_1MS (2 << 0) +# define DP_AG_FACTOR_500US (3 << 0) +# define DP_AG_FACTOR_200US (4 << 0) +# define DP_AG_FACTOR_100US (5 << 0) +# define DP_AG_FACTOR_10US (6 << 0) +# define DP_AG_FACTOR_1US (7 << 0) +# define DP_VG_FACTOR_MASK (0xf << 4) +# define DP_VG_FACTOR_3MS (0 << 4) +# define DP_VG_FACTOR_2MS (1 << 4) +# define DP_VG_FACTOR_1MS (2 << 4) +# define DP_VG_FACTOR_500US (3 << 4) +# define DP_VG_FACTOR_200US (4 << 4) +# define DP_VG_FACTOR_100US (5 << 4) + +#define DP_AUD_DEC_LAT0 0x024 +#define DP_AUD_DEC_LAT1 0x025 + +#define DP_AUD_PP_LAT0 0x026 +#define DP_AUD_PP_LAT1 0x027 + +#define DP_VID_INTER_LAT 0x028 + +#define DP_VID_PROG_LAT 0x029 + +#define DP_REP_LAT 0x02a + +#define DP_AUD_DEL_INS0 0x02b +#define DP_AUD_DEL_INS1 0x02c +#define DP_AUD_DEL_INS2 0x02d +/* End of AV_SYNC_DATA_BLOCK */ + +#define DP_RECEIVER_ALPM_CAP 0x02e /* eDP 1.4 */ +# define DP_ALPM_CAP (1 << 0) + +#define DP_SINK_DEVICE_AUX_FRAME_SYNC_CAP 0x02f /* eDP 1.4 */ +# define DP_AUX_FRAME_SYNC_CAP (1 << 0) + +#define DP_GUID 0x030 /* 1.2 */ + +#define DP_DSC_SUPPORT 0x060 /* DP 1.4 */ +# define DP_DSC_DECOMPRESSION_IS_SUPPORTED (1 << 0) + +#define DP_DSC_REV 0x061 +# define DP_DSC_MAJOR_MASK (0xf << 0) +# define DP_DSC_MINOR_MASK (0xf << 4) +# define DP_DSC_MAJOR_SHIFT 0 +# define DP_DSC_MINOR_SHIFT 4 + +#define DP_DSC_RC_BUF_BLK_SIZE 0x062 +# define DP_DSC_RC_BUF_BLK_SIZE_1 0x0 +# define DP_DSC_RC_BUF_BLK_SIZE_4 0x1 +# define DP_DSC_RC_BUF_BLK_SIZE_16 0x2 +# define DP_DSC_RC_BUF_BLK_SIZE_64 0x3 + +#define DP_DSC_RC_BUF_SIZE 0x063 + +#define DP_DSC_SLICE_CAP_1 0x064 +# define DP_DSC_1_PER_DP_DSC_SINK (1 << 0) +# define DP_DSC_2_PER_DP_DSC_SINK (1 << 1) +# define DP_DSC_4_PER_DP_DSC_SINK (1 << 3) +# define DP_DSC_6_PER_DP_DSC_SINK (1 << 4) +# define DP_DSC_8_PER_DP_DSC_SINK (1 << 5) +# define DP_DSC_10_PER_DP_DSC_SINK (1 << 6) +# define DP_DSC_12_PER_DP_DSC_SINK (1 << 7) + +#define DP_DSC_LINE_BUF_BIT_DEPTH 0x065 +# define DP_DSC_LINE_BUF_BIT_DEPTH_MASK (0xf << 0) +# define DP_DSC_LINE_BUF_BIT_DEPTH_9 0x0 +# define DP_DSC_LINE_BUF_BIT_DEPTH_10 0x1 +# define DP_DSC_LINE_BUF_BIT_DEPTH_11 0x2 +# define DP_DSC_LINE_BUF_BIT_DEPTH_12 0x3 +# define DP_DSC_LINE_BUF_BIT_DEPTH_13 0x4 +# define DP_DSC_LINE_BUF_BIT_DEPTH_14 0x5 +# define DP_DSC_LINE_BUF_BIT_DEPTH_15 0x6 +# define DP_DSC_LINE_BUF_BIT_DEPTH_16 0x7 +# define DP_DSC_LINE_BUF_BIT_DEPTH_8 0x8 + +#define DP_DSC_BLK_PREDICTION_SUPPORT 0x066 +# define DP_DSC_BLK_PREDICTION_IS_SUPPORTED (1 << 0) + +#define DP_DSC_MAX_BITS_PER_PIXEL_LOW 0x067 /* eDP 1.4 */ + +#define DP_DSC_MAX_BITS_PER_PIXEL_HI 0x068 /* eDP 1.4 */ +# define DP_DSC_MAX_BITS_PER_PIXEL_HI_MASK (0x3 << 0) +# define DP_DSC_MAX_BITS_PER_PIXEL_HI_SHIFT 8 + +#define DP_DSC_DEC_COLOR_FORMAT_CAP 0x069 +# define DP_DSC_RGB (1 << 0) +# define DP_DSC_YCbCr444 (1 << 1) +# define DP_DSC_YCbCr422_Simple (1 << 2) +# define DP_DSC_YCbCr422_Native (1 << 3) +# define DP_DSC_YCbCr420_Native (1 << 4) + +#define DP_DSC_DEC_COLOR_DEPTH_CAP 0x06A +# define DP_DSC_8_BPC (1 << 1) +# define DP_DSC_10_BPC (1 << 2) +# define DP_DSC_12_BPC (1 << 3) + +#define DP_DSC_PEAK_THROUGHPUT 0x06B +# define DP_DSC_THROUGHPUT_MODE_0_MASK (0xf << 0) +# define DP_DSC_THROUGHPUT_MODE_0_SHIFT 0 +# define DP_DSC_THROUGHPUT_MODE_0_UNSUPPORTED 0 +# define DP_DSC_THROUGHPUT_MODE_0_340 (1 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_400 (2 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_450 (3 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_500 (4 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_550 (5 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_600 (6 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_650 (7 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_700 (8 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_750 (9 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_800 (10 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_850 (11 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_900 (12 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_950 (13 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_1000 (14 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_170 (15 << 0) /* 1.4a */ +# define DP_DSC_THROUGHPUT_MODE_1_MASK (0xf << 4) +# define DP_DSC_THROUGHPUT_MODE_1_SHIFT 4 +# define DP_DSC_THROUGHPUT_MODE_1_UNSUPPORTED 0 +# define DP_DSC_THROUGHPUT_MODE_1_340 (1 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_400 (2 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_450 (3 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_500 (4 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_550 (5 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_600 (6 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_650 (7 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_700 (8 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_750 (9 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_800 (10 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_850 (11 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_900 (12 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_950 (13 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_1000 (14 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_170 (15 << 4) + +#define DP_DSC_MAX_SLICE_WIDTH 0x06C +#define DP_DSC_MIN_SLICE_WIDTH_VALUE 2560 +#define DP_DSC_SLICE_WIDTH_MULTIPLIER 320 + +#define DP_DSC_SLICE_CAP_2 0x06D +# define DP_DSC_16_PER_DP_DSC_SINK (1 << 0) +# define DP_DSC_20_PER_DP_DSC_SINK (1 << 1) +# define DP_DSC_24_PER_DP_DSC_SINK (1 << 2) + +#define DP_DSC_BITS_PER_PIXEL_INC 0x06F +# define DP_DSC_BITS_PER_PIXEL_1_16 0x0 +# define DP_DSC_BITS_PER_PIXEL_1_8 0x1 +# define DP_DSC_BITS_PER_PIXEL_1_4 0x2 +# define DP_DSC_BITS_PER_PIXEL_1_2 0x3 +# define DP_DSC_BITS_PER_PIXEL_1 0x4 + +#define DP_PSR_SUPPORT 0x070 /* XXX 1.2? */ +# define DP_PSR_IS_SUPPORTED 1 +# define DP_PSR2_IS_SUPPORTED 2 /* eDP 1.4 */ +# define DP_PSR2_WITH_Y_COORD_IS_SUPPORTED 3 /* eDP 1.4a */ + +#define DP_PSR_CAPS 0x071 /* XXX 1.2? */ +# define DP_PSR_NO_TRAIN_ON_EXIT 1 +# define DP_PSR_SETUP_TIME_330 (0 << 1) +# define DP_PSR_SETUP_TIME_275 (1 << 1) +# define DP_PSR_SETUP_TIME_220 (2 << 1) +# define DP_PSR_SETUP_TIME_165 (3 << 1) +# define DP_PSR_SETUP_TIME_110 (4 << 1) +# define DP_PSR_SETUP_TIME_55 (5 << 1) +# define DP_PSR_SETUP_TIME_0 (6 << 1) +# define DP_PSR_SETUP_TIME_MASK (7 << 1) +# define DP_PSR_SETUP_TIME_SHIFT 1 +# define DP_PSR2_SU_Y_COORDINATE_REQUIRED (1 << 4) /* eDP 1.4a */ +# define DP_PSR2_SU_GRANULARITY_REQUIRED (1 << 5) /* eDP 1.4b */ + +#define DP_PSR2_SU_X_GRANULARITY 0x072 /* eDP 1.4b */ +#define DP_PSR2_SU_Y_GRANULARITY 0x074 /* eDP 1.4b */ + +/* + * 0x80-0x8f describe downstream port capabilities, but there are two layouts + * based on whether DP_DETAILED_CAP_INFO_AVAILABLE was set. If it was not, + * each port's descriptor is one byte wide. If it was set, each port's is + * four bytes wide, starting with the one byte from the base info. As of + * DP interop v1.1a only VGA defines additional detail. + */ + +/* offset 0 */ +#define DP_DOWNSTREAM_PORT_0 0x80 +# define DP_DS_PORT_TYPE_MASK (7 << 0) +# define DP_DS_PORT_TYPE_DP 0 +# define DP_DS_PORT_TYPE_VGA 1 +# define DP_DS_PORT_TYPE_DVI 2 +# define DP_DS_PORT_TYPE_HDMI 3 +# define DP_DS_PORT_TYPE_NON_EDID 4 +# define DP_DS_PORT_TYPE_DP_DUALMODE 5 +# define DP_DS_PORT_TYPE_WIRELESS 6 +# define DP_DS_PORT_HPD (1 << 3) +# define DP_DS_NON_EDID_MASK (0xf << 4) +# define DP_DS_NON_EDID_720x480i_60 (1 << 4) +# define DP_DS_NON_EDID_720x480i_50 (2 << 4) +# define DP_DS_NON_EDID_1920x1080i_60 (3 << 4) +# define DP_DS_NON_EDID_1920x1080i_50 (4 << 4) +# define DP_DS_NON_EDID_1280x720_60 (5 << 4) +# define DP_DS_NON_EDID_1280x720_50 (7 << 4) +/* offset 1 for VGA is maximum megapixels per second / 8 */ +/* offset 1 for DVI/HDMI is maximum TMDS clock in Mbps / 2.5 */ +/* offset 2 for VGA/DVI/HDMI */ +# define DP_DS_MAX_BPC_MASK (3 << 0) +# define DP_DS_8BPC 0 +# define DP_DS_10BPC 1 +# define DP_DS_12BPC 2 +# define DP_DS_16BPC 3 +/* HDMI2.1 PCON FRL CONFIGURATION */ +# define DP_PCON_MAX_FRL_BW (7 << 2) +# define DP_PCON_MAX_0GBPS (0 << 2) +# define DP_PCON_MAX_9GBPS (1 << 2) +# define DP_PCON_MAX_18GBPS (2 << 2) +# define DP_PCON_MAX_24GBPS (3 << 2) +# define DP_PCON_MAX_32GBPS (4 << 2) +# define DP_PCON_MAX_40GBPS (5 << 2) +# define DP_PCON_MAX_48GBPS (6 << 2) +# define DP_PCON_SOURCE_CTL_MODE (1 << 5) + +/* offset 3 for DVI */ +# define DP_DS_DVI_DUAL_LINK (1 << 1) +# define DP_DS_DVI_HIGH_COLOR_DEPTH (1 << 2) +/* offset 3 for HDMI */ +# define DP_DS_HDMI_FRAME_SEQ_TO_FRAME_PACK (1 << 0) +# define DP_DS_HDMI_YCBCR422_PASS_THROUGH (1 << 1) +# define DP_DS_HDMI_YCBCR420_PASS_THROUGH (1 << 2) +# define DP_DS_HDMI_YCBCR444_TO_422_CONV (1 << 3) +# define DP_DS_HDMI_YCBCR444_TO_420_CONV (1 << 4) + +/* + * VESA DP-to-HDMI PCON Specification adds caps for colorspace + * conversion in DFP cap DPCD 83h. Sec6.1 Table-3. + * Based on the available support the source can enable + * color conversion by writing into PROTOCOL_COVERTER_CONTROL_2 + * DPCD 3052h. + */ +# define DP_DS_HDMI_BT601_RGB_YCBCR_CONV (1 << 5) +# define DP_DS_HDMI_BT709_RGB_YCBCR_CONV (1 << 6) +# define DP_DS_HDMI_BT2020_RGB_YCBCR_CONV (1 << 7) + +#define DP_MAX_DOWNSTREAM_PORTS 0x10 + +/* DP Forward error Correction Registers */ +#define DP_FEC_CAPABILITY 0x090 /* 1.4 */ +# define DP_FEC_CAPABLE (1 << 0) +# define DP_FEC_UNCORR_BLK_ERROR_COUNT_CAP (1 << 1) +# define DP_FEC_CORR_BLK_ERROR_COUNT_CAP (1 << 2) +# define DP_FEC_BIT_ERROR_COUNT_CAP (1 << 3) +#define DP_FEC_CAPABILITY_1 0x091 /* 2.0 */ + +/* DP-HDMI2.1 PCON DSC ENCODER SUPPORT */ +#define DP_PCON_DSC_ENCODER_CAP_SIZE 0xC /* 0x9E - 0x92 */ +#define DP_PCON_DSC_ENCODER 0x092 +# define DP_PCON_DSC_ENCODER_SUPPORTED (1 << 0) +# define DP_PCON_DSC_PPS_ENC_OVERRIDE (1 << 1) + +/* DP-HDMI2.1 PCON DSC Version */ +#define DP_PCON_DSC_VERSION 0x093 +# define DP_PCON_DSC_MAJOR_MASK (0xF << 0) +# define DP_PCON_DSC_MINOR_MASK (0xF << 4) +# define DP_PCON_DSC_MAJOR_SHIFT 0 +# define DP_PCON_DSC_MINOR_SHIFT 4 + +/* DP-HDMI2.1 PCON DSC RC Buffer block size */ +#define DP_PCON_DSC_RC_BUF_BLK_INFO 0x094 +# define DP_PCON_DSC_RC_BUF_BLK_SIZE (0x3 << 0) +# define DP_PCON_DSC_RC_BUF_BLK_1KB 0 +# define DP_PCON_DSC_RC_BUF_BLK_4KB 1 +# define DP_PCON_DSC_RC_BUF_BLK_16KB 2 +# define DP_PCON_DSC_RC_BUF_BLK_64KB 3 + +/* DP-HDMI2.1 PCON DSC RC Buffer size */ +#define DP_PCON_DSC_RC_BUF_SIZE 0x095 + +/* DP-HDMI2.1 PCON DSC Slice capabilities-1 */ +#define DP_PCON_DSC_SLICE_CAP_1 0x096 +# define DP_PCON_DSC_1_PER_DSC_ENC (0x1 << 0) +# define DP_PCON_DSC_2_PER_DSC_ENC (0x1 << 1) +# define DP_PCON_DSC_4_PER_DSC_ENC (0x1 << 3) +# define DP_PCON_DSC_6_PER_DSC_ENC (0x1 << 4) +# define DP_PCON_DSC_8_PER_DSC_ENC (0x1 << 5) +# define DP_PCON_DSC_10_PER_DSC_ENC (0x1 << 6) +# define DP_PCON_DSC_12_PER_DSC_ENC (0x1 << 7) + +#define DP_PCON_DSC_BUF_BIT_DEPTH 0x097 +# define DP_PCON_DSC_BIT_DEPTH_MASK (0xF << 0) +# define DP_PCON_DSC_DEPTH_9_BITS 0 +# define DP_PCON_DSC_DEPTH_10_BITS 1 +# define DP_PCON_DSC_DEPTH_11_BITS 2 +# define DP_PCON_DSC_DEPTH_12_BITS 3 +# define DP_PCON_DSC_DEPTH_13_BITS 4 +# define DP_PCON_DSC_DEPTH_14_BITS 5 +# define DP_PCON_DSC_DEPTH_15_BITS 6 +# define DP_PCON_DSC_DEPTH_16_BITS 7 +# define DP_PCON_DSC_DEPTH_8_BITS 8 + +#define DP_PCON_DSC_BLOCK_PREDICTION 0x098 +# define DP_PCON_DSC_BLOCK_PRED_SUPPORT (0x1 << 0) + +#define DP_PCON_DSC_ENC_COLOR_FMT_CAP 0x099 +# define DP_PCON_DSC_ENC_RGB (0x1 << 0) +# define DP_PCON_DSC_ENC_YUV444 (0x1 << 1) +# define DP_PCON_DSC_ENC_YUV422_S (0x1 << 2) +# define DP_PCON_DSC_ENC_YUV422_N (0x1 << 3) +# define DP_PCON_DSC_ENC_YUV420_N (0x1 << 4) + +#define DP_PCON_DSC_ENC_COLOR_DEPTH_CAP 0x09A +# define DP_PCON_DSC_ENC_8BPC (0x1 << 1) +# define DP_PCON_DSC_ENC_10BPC (0x1 << 2) +# define DP_PCON_DSC_ENC_12BPC (0x1 << 3) + +#define DP_PCON_DSC_MAX_SLICE_WIDTH 0x09B + +/* DP-HDMI2.1 PCON DSC Slice capabilities-2 */ +#define DP_PCON_DSC_SLICE_CAP_2 0x09C +# define DP_PCON_DSC_16_PER_DSC_ENC (0x1 << 0) +# define DP_PCON_DSC_20_PER_DSC_ENC (0x1 << 1) +# define DP_PCON_DSC_24_PER_DSC_ENC (0x1 << 2) + +/* DP-HDMI2.1 PCON HDMI TX Encoder Bits/pixel increment */ +#define DP_PCON_DSC_BPP_INCR 0x09E +# define DP_PCON_DSC_BPP_INCR_MASK (0x7 << 0) +# define DP_PCON_DSC_ONE_16TH_BPP 0 +# define DP_PCON_DSC_ONE_8TH_BPP 1 +# define DP_PCON_DSC_ONE_4TH_BPP 2 +# define DP_PCON_DSC_ONE_HALF_BPP 3 +# define DP_PCON_DSC_ONE_BPP 4 + +/* DP Extended DSC Capabilities */ +#define DP_DSC_BRANCH_OVERALL_THROUGHPUT_0 0x0a0 /* DP 1.4a SCR */ +#define DP_DSC_BRANCH_OVERALL_THROUGHPUT_1 0x0a1 +#define DP_DSC_BRANCH_MAX_LINE_WIDTH 0x0a2 + +/* DFP Capability Extension */ +#define DP_DFP_CAPABILITY_EXTENSION_SUPPORT 0x0a3 /* 2.0 */ + +/* Link Configuration */ +#define DP_LINK_BW_SET 0x100 +# define DP_LINK_RATE_TABLE 0x00 /* eDP 1.4 */ +# define DP_LINK_BW_1_62 0x06 +# define DP_LINK_BW_2_7 0x0a +# define DP_LINK_BW_5_4 0x14 /* 1.2 */ +# define DP_LINK_BW_8_1 0x1e /* 1.4 */ +# define DP_LINK_BW_10 0x01 /* 2.0 128b/132b Link Layer */ +# define DP_LINK_BW_13_5 0x04 /* 2.0 128b/132b Link Layer */ +# define DP_LINK_BW_20 0x02 /* 2.0 128b/132b Link Layer */ + +#define DP_LANE_COUNT_SET 0x101 +# define DP_LANE_COUNT_MASK 0x0f +# define DP_LANE_COUNT_ENHANCED_FRAME_EN (1 << 7) + +#define DP_TRAINING_PATTERN_SET 0x102 +# define DP_TRAINING_PATTERN_DISABLE 0 +# define DP_TRAINING_PATTERN_1 1 +# define DP_TRAINING_PATTERN_2 2 +# define DP_TRAINING_PATTERN_3 3 /* 1.2 */ +# define DP_TRAINING_PATTERN_4 7 /* 1.4 */ +# define DP_TRAINING_PATTERN_MASK 0x3 +# define DP_TRAINING_PATTERN_MASK_1_4 0xf + +/* DPCD 1.1 only. For DPCD >= 1.2 see per-lane DP_LINK_QUAL_LANEn_SET */ +# define DP_LINK_QUAL_PATTERN_11_DISABLE (0 << 2) +# define DP_LINK_QUAL_PATTERN_11_D10_2 (1 << 2) +# define DP_LINK_QUAL_PATTERN_11_ERROR_RATE (2 << 2) +# define DP_LINK_QUAL_PATTERN_11_PRBS7 (3 << 2) +# define DP_LINK_QUAL_PATTERN_11_MASK (3 << 2) + +# define DP_RECOVERED_CLOCK_OUT_EN (1 << 4) +# define DP_LINK_SCRAMBLING_DISABLE (1 << 5) + +# define DP_SYMBOL_ERROR_COUNT_BOTH (0 << 6) +# define DP_SYMBOL_ERROR_COUNT_DISPARITY (1 << 6) +# define DP_SYMBOL_ERROR_COUNT_SYMBOL (2 << 6) +# define DP_SYMBOL_ERROR_COUNT_MASK (3 << 6) + +#define DP_TRAINING_LANE0_SET 0x103 +#define DP_TRAINING_LANE1_SET 0x104 +#define DP_TRAINING_LANE2_SET 0x105 +#define DP_TRAINING_LANE3_SET 0x106 + +# define DP_TRAIN_VOLTAGE_SWING_MASK 0x3 +# define DP_TRAIN_VOLTAGE_SWING_SHIFT 0 +# define DP_TRAIN_MAX_SWING_REACHED (1 << 2) +# define DP_TRAIN_VOLTAGE_SWING_LEVEL_0 (0 << 0) +# define DP_TRAIN_VOLTAGE_SWING_LEVEL_1 (1 << 0) +# define DP_TRAIN_VOLTAGE_SWING_LEVEL_2 (2 << 0) +# define DP_TRAIN_VOLTAGE_SWING_LEVEL_3 (3 << 0) + +# define DP_TRAIN_PRE_EMPHASIS_MASK (3 << 3) +# define DP_TRAIN_PRE_EMPH_LEVEL_0 (0 << 3) +# define DP_TRAIN_PRE_EMPH_LEVEL_1 (1 << 3) +# define DP_TRAIN_PRE_EMPH_LEVEL_2 (2 << 3) +# define DP_TRAIN_PRE_EMPH_LEVEL_3 (3 << 3) + +# define DP_TRAIN_PRE_EMPHASIS_SHIFT 3 +# define DP_TRAIN_MAX_PRE_EMPHASIS_REACHED (1 << 5) + +# define DP_TX_FFE_PRESET_VALUE_MASK (0xf << 0) /* 2.0 128b/132b Link Layer */ + +#define DP_DOWNSPREAD_CTRL 0x107 +# define DP_SPREAD_AMP_0_5 (1 << 4) +# define DP_MSA_TIMING_PAR_IGNORE_EN (1 << 7) /* eDP */ + +#define DP_MAIN_LINK_CHANNEL_CODING_SET 0x108 +# define DP_SET_ANSI_8B10B (1 << 0) +# define DP_SET_ANSI_128B132B (1 << 1) + +#define DP_I2C_SPEED_CONTROL_STATUS 0x109 /* DPI */ +/* bitmask as for DP_I2C_SPEED_CAP */ + +#define DP_EDP_CONFIGURATION_SET 0x10a /* XXX 1.2? */ +# define DP_ALTERNATE_SCRAMBLER_RESET_ENABLE (1 << 0) +# define DP_FRAMING_CHANGE_ENABLE (1 << 1) +# define DP_PANEL_SELF_TEST_ENABLE (1 << 7) + +#define DP_LINK_QUAL_LANE0_SET 0x10b /* DPCD >= 1.2 */ +#define DP_LINK_QUAL_LANE1_SET 0x10c +#define DP_LINK_QUAL_LANE2_SET 0x10d +#define DP_LINK_QUAL_LANE3_SET 0x10e +# define DP_LINK_QUAL_PATTERN_DISABLE 0 +# define DP_LINK_QUAL_PATTERN_D10_2 1 +# define DP_LINK_QUAL_PATTERN_ERROR_RATE 2 +# define DP_LINK_QUAL_PATTERN_PRBS7 3 +# define DP_LINK_QUAL_PATTERN_80BIT_CUSTOM 4 +# define DP_LINK_QUAL_PATTERN_CP2520_PAT_1 5 +# define DP_LINK_QUAL_PATTERN_CP2520_PAT_2 6 +# define DP_LINK_QUAL_PATTERN_CP2520_PAT_3 7 +/* DP 2.0 UHBR10, UHBR13.5, UHBR20 */ +# define DP_LINK_QUAL_PATTERN_128B132B_TPS1 0x08 +# define DP_LINK_QUAL_PATTERN_128B132B_TPS2 0x10 +# define DP_LINK_QUAL_PATTERN_PRSBS9 0x18 +# define DP_LINK_QUAL_PATTERN_PRSBS11 0x20 +# define DP_LINK_QUAL_PATTERN_PRSBS15 0x28 +# define DP_LINK_QUAL_PATTERN_PRSBS23 0x30 +# define DP_LINK_QUAL_PATTERN_PRSBS31 0x38 +# define DP_LINK_QUAL_PATTERN_CUSTOM 0x40 +# define DP_LINK_QUAL_PATTERN_SQUARE 0x48 + +#define DP_TRAINING_LANE0_1_SET2 0x10f +#define DP_TRAINING_LANE2_3_SET2 0x110 +# define DP_LANE02_POST_CURSOR2_SET_MASK (3 << 0) +# define DP_LANE02_MAX_POST_CURSOR2_REACHED (1 << 2) +# define DP_LANE13_POST_CURSOR2_SET_MASK (3 << 4) +# define DP_LANE13_MAX_POST_CURSOR2_REACHED (1 << 6) + +#define DP_MSTM_CTRL 0x111 /* 1.2 */ +# define DP_MST_EN (1 << 0) +# define DP_UP_REQ_EN (1 << 1) +# define DP_UPSTREAM_IS_SRC (1 << 2) + +#define DP_AUDIO_DELAY0 0x112 /* 1.2 */ +#define DP_AUDIO_DELAY1 0x113 +#define DP_AUDIO_DELAY2 0x114 + +#define DP_LINK_RATE_SET 0x115 /* eDP 1.4 */ +# define DP_LINK_RATE_SET_SHIFT 0 +# define DP_LINK_RATE_SET_MASK (7 << 0) + +#define DP_RECEIVER_ALPM_CONFIG 0x116 /* eDP 1.4 */ +# define DP_ALPM_ENABLE (1 << 0) +# define DP_ALPM_LOCK_ERROR_IRQ_HPD_ENABLE (1 << 1) + +#define DP_SINK_DEVICE_AUX_FRAME_SYNC_CONF 0x117 /* eDP 1.4 */ +# define DP_AUX_FRAME_SYNC_ENABLE (1 << 0) +# define DP_IRQ_HPD_ENABLE (1 << 1) + +#define DP_UPSTREAM_DEVICE_DP_PWR_NEED 0x118 /* 1.2 */ +# define DP_PWR_NOT_NEEDED (1 << 0) + +#define DP_FEC_CONFIGURATION 0x120 /* 1.4 */ +# define DP_FEC_READY (1 << 0) +# define DP_FEC_ERR_COUNT_SEL_MASK (7 << 1) +# define DP_FEC_ERR_COUNT_DIS (0 << 1) +# define DP_FEC_UNCORR_BLK_ERROR_COUNT (1 << 1) +# define DP_FEC_CORR_BLK_ERROR_COUNT (2 << 1) +# define DP_FEC_BIT_ERROR_COUNT (3 << 1) +# define DP_FEC_LANE_SELECT_MASK (3 << 4) +# define DP_FEC_LANE_0_SELECT (0 << 4) +# define DP_FEC_LANE_1_SELECT (1 << 4) +# define DP_FEC_LANE_2_SELECT (2 << 4) +# define DP_FEC_LANE_3_SELECT (3 << 4) + +#define DP_AUX_FRAME_SYNC_VALUE 0x15c /* eDP 1.4 */ +# define DP_AUX_FRAME_SYNC_VALID (1 << 0) + +#define DP_DSC_ENABLE 0x160 /* DP 1.4 */ +# define DP_DECOMPRESSION_EN (1 << 0) +#define DP_DSC_CONFIGURATION 0x161 /* DP 2.0 */ + +#define DP_PSR_EN_CFG 0x170 /* XXX 1.2? */ +# define DP_PSR_ENABLE BIT(0) +# define DP_PSR_MAIN_LINK_ACTIVE BIT(1) +# define DP_PSR_CRC_VERIFICATION BIT(2) +# define DP_PSR_FRAME_CAPTURE BIT(3) +# define DP_PSR_SU_REGION_SCANLINE_CAPTURE BIT(4) /* eDP 1.4a */ +# define DP_PSR_IRQ_HPD_WITH_CRC_ERRORS BIT(5) /* eDP 1.4a */ +# define DP_PSR_ENABLE_PSR2 BIT(6) /* eDP 1.4a */ + +#define DP_ADAPTER_CTRL 0x1a0 +# define DP_ADAPTER_CTRL_FORCE_LOAD_SENSE (1 << 0) + +#define DP_BRANCH_DEVICE_CTRL 0x1a1 +# define DP_BRANCH_DEVICE_IRQ_HPD (1 << 0) + +#define DP_PAYLOAD_ALLOCATE_SET 0x1c0 +#define DP_PAYLOAD_ALLOCATE_START_TIME_SLOT 0x1c1 +#define DP_PAYLOAD_ALLOCATE_TIME_SLOT_COUNT 0x1c2 + +/* Link/Sink Device Status */ +#define DP_SINK_COUNT 0x200 +/* prior to 1.2 bit 7 was reserved mbz */ +# define DP_GET_SINK_COUNT(x) ((((x) & 0x80) >> 1) | ((x) & 0x3f)) +# define DP_SINK_CP_READY (1 << 6) + +#define DP_DEVICE_SERVICE_IRQ_VECTOR 0x201 +# define DP_REMOTE_CONTROL_COMMAND_PENDING (1 << 0) +# define DP_AUTOMATED_TEST_REQUEST (1 << 1) +# define DP_CP_IRQ (1 << 2) +# define DP_MCCS_IRQ (1 << 3) +# define DP_DOWN_REP_MSG_RDY (1 << 4) /* 1.2 MST */ +# define DP_UP_REQ_MSG_RDY (1 << 5) /* 1.2 MST */ +# define DP_SINK_SPECIFIC_IRQ (1 << 6) + +#define DP_LANE0_1_STATUS 0x202 +#define DP_LANE2_3_STATUS 0x203 +# define DP_LANE_CR_DONE (1 << 0) +# define DP_LANE_CHANNEL_EQ_DONE (1 << 1) +# define DP_LANE_SYMBOL_LOCKED (1 << 2) + +#define DP_CHANNEL_EQ_BITS (DP_LANE_CR_DONE | \ + DP_LANE_CHANNEL_EQ_DONE | \ + DP_LANE_SYMBOL_LOCKED) + +#define DP_LANE_ALIGN_STATUS_UPDATED 0x204 + +#define DP_INTERLANE_ALIGN_DONE (1 << 0) +#define DP_DOWNSTREAM_PORT_STATUS_CHANGED (1 << 6) +#define DP_LINK_STATUS_UPDATED (1 << 7) + +#define DP_SINK_STATUS 0x205 +# define DP_RECEIVE_PORT_0_STATUS (1 << 0) +# define DP_RECEIVE_PORT_1_STATUS (1 << 1) +# define DP_STREAM_REGENERATION_STATUS (1 << 2) /* 2.0 */ +# define DP_INTRA_HOP_AUX_REPLY_INDICATION (1 << 3) /* 2.0 */ + +#define DP_ADJUST_REQUEST_LANE0_1 0x206 +#define DP_ADJUST_REQUEST_LANE2_3 0x207 +# define DP_ADJUST_VOLTAGE_SWING_LANE0_MASK 0x03 +# define DP_ADJUST_VOLTAGE_SWING_LANE0_SHIFT 0 +# define DP_ADJUST_PRE_EMPHASIS_LANE0_MASK 0x0c +# define DP_ADJUST_PRE_EMPHASIS_LANE0_SHIFT 2 +# define DP_ADJUST_VOLTAGE_SWING_LANE1_MASK 0x30 +# define DP_ADJUST_VOLTAGE_SWING_LANE1_SHIFT 4 +# define DP_ADJUST_PRE_EMPHASIS_LANE1_MASK 0xc0 +# define DP_ADJUST_PRE_EMPHASIS_LANE1_SHIFT 6 + +/* DP 2.0 128b/132b Link Layer */ +# define DP_ADJUST_TX_FFE_PRESET_LANE0_MASK (0xf << 0) +# define DP_ADJUST_TX_FFE_PRESET_LANE0_SHIFT 0 +# define DP_ADJUST_TX_FFE_PRESET_LANE1_MASK (0xf << 4) +# define DP_ADJUST_TX_FFE_PRESET_LANE1_SHIFT 4 + +#define DP_ADJUST_REQUEST_POST_CURSOR2 0x20c +# define DP_ADJUST_POST_CURSOR2_LANE0_MASK 0x03 +# define DP_ADJUST_POST_CURSOR2_LANE0_SHIFT 0 +# define DP_ADJUST_POST_CURSOR2_LANE1_MASK 0x0c +# define DP_ADJUST_POST_CURSOR2_LANE1_SHIFT 2 +# define DP_ADJUST_POST_CURSOR2_LANE2_MASK 0x30 +# define DP_ADJUST_POST_CURSOR2_LANE2_SHIFT 4 +# define DP_ADJUST_POST_CURSOR2_LANE3_MASK 0xc0 +# define DP_ADJUST_POST_CURSOR2_LANE3_SHIFT 6 + +#define DP_TEST_REQUEST 0x218 +# define DP_TEST_LINK_TRAINING (1 << 0) +# define DP_TEST_LINK_VIDEO_PATTERN (1 << 1) +# define DP_TEST_LINK_EDID_READ (1 << 2) +# define DP_TEST_LINK_PHY_TEST_PATTERN (1 << 3) /* DPCD >= 1.1 */ +# define DP_TEST_LINK_FAUX_PATTERN (1 << 4) /* DPCD >= 1.2 */ +# define DP_TEST_LINK_AUDIO_PATTERN (1 << 5) /* DPCD >= 1.2 */ +# define DP_TEST_LINK_AUDIO_DISABLED_VIDEO (1 << 6) /* DPCD >= 1.2 */ + +#define DP_TEST_LINK_RATE 0x219 +# define DP_LINK_RATE_162 (0x6) +# define DP_LINK_RATE_27 (0xa) + +#define DP_TEST_LANE_COUNT 0x220 + +#define DP_TEST_PATTERN 0x221 +# define DP_NO_TEST_PATTERN 0x0 +# define DP_COLOR_RAMP 0x1 +# define DP_BLACK_AND_WHITE_VERTICAL_LINES 0x2 +# define DP_COLOR_SQUARE 0x3 + +#define DP_TEST_H_TOTAL_HI 0x222 +#define DP_TEST_H_TOTAL_LO 0x223 + +#define DP_TEST_V_TOTAL_HI 0x224 +#define DP_TEST_V_TOTAL_LO 0x225 + +#define DP_TEST_H_START_HI 0x226 +#define DP_TEST_H_START_LO 0x227 + +#define DP_TEST_V_START_HI 0x228 +#define DP_TEST_V_START_LO 0x229 + +#define DP_TEST_HSYNC_HI 0x22A +# define DP_TEST_HSYNC_POLARITY (1 << 7) +# define DP_TEST_HSYNC_WIDTH_HI_MASK (127 << 0) +#define DP_TEST_HSYNC_WIDTH_LO 0x22B + +#define DP_TEST_VSYNC_HI 0x22C +# define DP_TEST_VSYNC_POLARITY (1 << 7) +# define DP_TEST_VSYNC_WIDTH_HI_MASK (127 << 0) +#define DP_TEST_VSYNC_WIDTH_LO 0x22D + +#define DP_TEST_H_WIDTH_HI 0x22E +#define DP_TEST_H_WIDTH_LO 0x22F + +#define DP_TEST_V_HEIGHT_HI 0x230 +#define DP_TEST_V_HEIGHT_LO 0x231 + +#define DP_TEST_MISC0 0x232 +# define DP_TEST_SYNC_CLOCK (1 << 0) +# define DP_TEST_COLOR_FORMAT_MASK (3 << 1) +# define DP_TEST_COLOR_FORMAT_SHIFT 1 +# define DP_COLOR_FORMAT_RGB (0 << 1) +# define DP_COLOR_FORMAT_YCbCr422 (1 << 1) +# define DP_COLOR_FORMAT_YCbCr444 (2 << 1) +# define DP_TEST_DYNAMIC_RANGE_VESA (0 << 3) +# define DP_TEST_DYNAMIC_RANGE_CEA (1 << 3) +# define DP_TEST_YCBCR_COEFFICIENTS (1 << 4) +# define DP_YCBCR_COEFFICIENTS_ITU601 (0 << 4) +# define DP_YCBCR_COEFFICIENTS_ITU709 (1 << 4) +# define DP_TEST_BIT_DEPTH_MASK (7 << 5) +# define DP_TEST_BIT_DEPTH_SHIFT 5 +# define DP_TEST_BIT_DEPTH_6 (0 << 5) +# define DP_TEST_BIT_DEPTH_8 (1 << 5) +# define DP_TEST_BIT_DEPTH_10 (2 << 5) +# define DP_TEST_BIT_DEPTH_12 (3 << 5) +# define DP_TEST_BIT_DEPTH_16 (4 << 5) + +#define DP_TEST_MISC1 0x233 +# define DP_TEST_REFRESH_DENOMINATOR (1 << 0) +# define DP_TEST_INTERLACED (1 << 1) + +#define DP_TEST_REFRESH_RATE_NUMERATOR 0x234 + +#define DP_TEST_MISC0 0x232 + +#define DP_TEST_CRC_R_CR 0x240 +#define DP_TEST_CRC_G_Y 0x242 +#define DP_TEST_CRC_B_CB 0x244 + +#define DP_TEST_SINK_MISC 0x246 +# define DP_TEST_CRC_SUPPORTED (1 << 5) +# define DP_TEST_COUNT_MASK 0xf + +#define DP_PHY_TEST_PATTERN 0x248 +# define DP_PHY_TEST_PATTERN_SEL_MASK 0x7 +# define DP_PHY_TEST_PATTERN_NONE 0x0 +# define DP_PHY_TEST_PATTERN_D10_2 0x1 +# define DP_PHY_TEST_PATTERN_ERROR_COUNT 0x2 +# define DP_PHY_TEST_PATTERN_PRBS7 0x3 +# define DP_PHY_TEST_PATTERN_80BIT_CUSTOM 0x4 +# define DP_PHY_TEST_PATTERN_CP2520 0x5 + +#define DP_PHY_SQUARE_PATTERN 0x249 + +#define DP_TEST_HBR2_SCRAMBLER_RESET 0x24A +#define DP_TEST_80BIT_CUSTOM_PATTERN_7_0 0x250 +#define DP_TEST_80BIT_CUSTOM_PATTERN_15_8 0x251 +#define DP_TEST_80BIT_CUSTOM_PATTERN_23_16 0x252 +#define DP_TEST_80BIT_CUSTOM_PATTERN_31_24 0x253 +#define DP_TEST_80BIT_CUSTOM_PATTERN_39_32 0x254 +#define DP_TEST_80BIT_CUSTOM_PATTERN_47_40 0x255 +#define DP_TEST_80BIT_CUSTOM_PATTERN_55_48 0x256 +#define DP_TEST_80BIT_CUSTOM_PATTERN_63_56 0x257 +#define DP_TEST_80BIT_CUSTOM_PATTERN_71_64 0x258 +#define DP_TEST_80BIT_CUSTOM_PATTERN_79_72 0x259 + +#define DP_TEST_RESPONSE 0x260 +# define DP_TEST_ACK (1 << 0) +# define DP_TEST_NAK (1 << 1) +# define DP_TEST_EDID_CHECKSUM_WRITE (1 << 2) + +#define DP_TEST_EDID_CHECKSUM 0x261 + +#define DP_TEST_SINK 0x270 +# define DP_TEST_SINK_START (1 << 0) +#define DP_TEST_AUDIO_MODE 0x271 +#define DP_TEST_AUDIO_PATTERN_TYPE 0x272 +#define DP_TEST_AUDIO_PERIOD_CH1 0x273 +#define DP_TEST_AUDIO_PERIOD_CH2 0x274 +#define DP_TEST_AUDIO_PERIOD_CH3 0x275 +#define DP_TEST_AUDIO_PERIOD_CH4 0x276 +#define DP_TEST_AUDIO_PERIOD_CH5 0x277 +#define DP_TEST_AUDIO_PERIOD_CH6 0x278 +#define DP_TEST_AUDIO_PERIOD_CH7 0x279 +#define DP_TEST_AUDIO_PERIOD_CH8 0x27A + +#define DP_FEC_STATUS 0x280 /* 1.4 */ +# define DP_FEC_DECODE_EN_DETECTED (1 << 0) +# define DP_FEC_DECODE_DIS_DETECTED (1 << 1) + +#define DP_FEC_ERROR_COUNT_LSB 0x0281 /* 1.4 */ + +#define DP_FEC_ERROR_COUNT_MSB 0x0282 /* 1.4 */ +# define DP_FEC_ERROR_COUNT_MASK 0x7F +# define DP_FEC_ERR_COUNT_VALID (1 << 7) + +#define DP_PAYLOAD_TABLE_UPDATE_STATUS 0x2c0 /* 1.2 MST */ +# define DP_PAYLOAD_TABLE_UPDATED (1 << 0) +# define DP_PAYLOAD_ACT_HANDLED (1 << 1) + +#define DP_VC_PAYLOAD_ID_SLOT_1 0x2c1 /* 1.2 MST */ +/* up to ID_SLOT_63 at 0x2ff */ + +/* Source Device-specific */ +#define DP_SOURCE_OUI 0x300 + +/* Sink Device-specific */ +#define DP_SINK_OUI 0x400 + +/* Branch Device-specific */ +#define DP_BRANCH_OUI 0x500 +#define DP_BRANCH_ID 0x503 +#define DP_BRANCH_REVISION_START 0x509 +#define DP_BRANCH_HW_REV 0x509 +#define DP_BRANCH_SW_REV 0x50A + +/* Link/Sink Device Power Control */ +#define DP_SET_POWER 0x600 +# define DP_SET_POWER_D0 0x1 +# define DP_SET_POWER_D3 0x2 +# define DP_SET_POWER_MASK 0x3 +# define DP_SET_POWER_D3_AUX_ON 0x5 + +/* eDP-specific */ +#define DP_EDP_DPCD_REV 0x700 /* eDP 1.2 */ +# define DP_EDP_11 0x00 +# define DP_EDP_12 0x01 +# define DP_EDP_13 0x02 +# define DP_EDP_14 0x03 +# define DP_EDP_14a 0x04 /* eDP 1.4a */ +# define DP_EDP_14b 0x05 /* eDP 1.4b */ + +#define DP_EDP_GENERAL_CAP_1 0x701 +# define DP_EDP_TCON_BACKLIGHT_ADJUSTMENT_CAP (1 << 0) +# define DP_EDP_BACKLIGHT_PIN_ENABLE_CAP (1 << 1) +# define DP_EDP_BACKLIGHT_AUX_ENABLE_CAP (1 << 2) +# define DP_EDP_PANEL_SELF_TEST_PIN_ENABLE_CAP (1 << 3) +# define DP_EDP_PANEL_SELF_TEST_AUX_ENABLE_CAP (1 << 4) +# define DP_EDP_FRC_ENABLE_CAP (1 << 5) +# define DP_EDP_COLOR_ENGINE_CAP (1 << 6) +# define DP_EDP_SET_POWER_CAP (1 << 7) + +#define DP_EDP_BACKLIGHT_ADJUSTMENT_CAP 0x702 +# define DP_EDP_BACKLIGHT_BRIGHTNESS_PWM_PIN_CAP (1 << 0) +# define DP_EDP_BACKLIGHT_BRIGHTNESS_AUX_SET_CAP (1 << 1) +# define DP_EDP_BACKLIGHT_BRIGHTNESS_BYTE_COUNT (1 << 2) +# define DP_EDP_BACKLIGHT_AUX_PWM_PRODUCT_CAP (1 << 3) +# define DP_EDP_BACKLIGHT_FREQ_PWM_PIN_PASSTHRU_CAP (1 << 4) +# define DP_EDP_BACKLIGHT_FREQ_AUX_SET_CAP (1 << 5) +# define DP_EDP_DYNAMIC_BACKLIGHT_CAP (1 << 6) +# define DP_EDP_VBLANK_BACKLIGHT_UPDATE_CAP (1 << 7) + +#define DP_EDP_GENERAL_CAP_2 0x703 +# define DP_EDP_OVERDRIVE_ENGINE_ENABLED (1 << 0) + +#define DP_EDP_GENERAL_CAP_3 0x704 /* eDP 1.4 */ +# define DP_EDP_X_REGION_CAP_MASK (0xf << 0) +# define DP_EDP_X_REGION_CAP_SHIFT 0 +# define DP_EDP_Y_REGION_CAP_MASK (0xf << 4) +# define DP_EDP_Y_REGION_CAP_SHIFT 4 + +#define DP_EDP_DISPLAY_CONTROL_REGISTER 0x720 +# define DP_EDP_BACKLIGHT_ENABLE (1 << 0) +# define DP_EDP_BLACK_VIDEO_ENABLE (1 << 1) +# define DP_EDP_FRC_ENABLE (1 << 2) +# define DP_EDP_COLOR_ENGINE_ENABLE (1 << 3) +# define DP_EDP_VBLANK_BACKLIGHT_UPDATE_ENABLE (1 << 7) + +#define DP_EDP_BACKLIGHT_MODE_SET_REGISTER 0x721 +# define DP_EDP_BACKLIGHT_CONTROL_MODE_MASK (3 << 0) +# define DP_EDP_BACKLIGHT_CONTROL_MODE_PWM (0 << 0) +# define DP_EDP_BACKLIGHT_CONTROL_MODE_PRESET (1 << 0) +# define DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD (2 << 0) +# define DP_EDP_BACKLIGHT_CONTROL_MODE_PRODUCT (3 << 0) +# define DP_EDP_BACKLIGHT_FREQ_PWM_PIN_PASSTHRU_ENABLE (1 << 2) +# define DP_EDP_BACKLIGHT_FREQ_AUX_SET_ENABLE (1 << 3) +# define DP_EDP_DYNAMIC_BACKLIGHT_ENABLE (1 << 4) +# define DP_EDP_REGIONAL_BACKLIGHT_ENABLE (1 << 5) +# define DP_EDP_UPDATE_REGION_BRIGHTNESS (1 << 6) /* eDP 1.4 */ + +#define DP_EDP_BACKLIGHT_BRIGHTNESS_MSB 0x722 +#define DP_EDP_BACKLIGHT_BRIGHTNESS_LSB 0x723 + +#define DP_EDP_PWMGEN_BIT_COUNT 0x724 +#define DP_EDP_PWMGEN_BIT_COUNT_CAP_MIN 0x725 +#define DP_EDP_PWMGEN_BIT_COUNT_CAP_MAX 0x726 +# define DP_EDP_PWMGEN_BIT_COUNT_MASK (0x1f << 0) + +#define DP_EDP_BACKLIGHT_CONTROL_STATUS 0x727 + +#define DP_EDP_BACKLIGHT_FREQ_SET 0x728 +# define DP_EDP_BACKLIGHT_FREQ_BASE_KHZ 27000 + +#define DP_EDP_BACKLIGHT_FREQ_CAP_MIN_MSB 0x72a +#define DP_EDP_BACKLIGHT_FREQ_CAP_MIN_MID 0x72b +#define DP_EDP_BACKLIGHT_FREQ_CAP_MIN_LSB 0x72c + +#define DP_EDP_BACKLIGHT_FREQ_CAP_MAX_MSB 0x72d +#define DP_EDP_BACKLIGHT_FREQ_CAP_MAX_MID 0x72e +#define DP_EDP_BACKLIGHT_FREQ_CAP_MAX_LSB 0x72f + +#define DP_EDP_DBC_MINIMUM_BRIGHTNESS_SET 0x732 +#define DP_EDP_DBC_MAXIMUM_BRIGHTNESS_SET 0x733 + +#define DP_EDP_REGIONAL_BACKLIGHT_BASE 0x740 /* eDP 1.4 */ +#define DP_EDP_REGIONAL_BACKLIGHT_0 0x741 /* eDP 1.4 */ + +#define DP_EDP_MSO_LINK_CAPABILITIES 0x7a4 /* eDP 1.4 */ +# define DP_EDP_MSO_NUMBER_OF_LINKS_MASK (7 << 0) +# define DP_EDP_MSO_NUMBER_OF_LINKS_SHIFT 0 +# define DP_EDP_MSO_INDEPENDENT_LINK_BIT (1 << 3) + +/* Sideband MSG Buffers */ +#define DP_SIDEBAND_MSG_DOWN_REQ_BASE 0x1000 /* 1.2 MST */ +#define DP_SIDEBAND_MSG_UP_REP_BASE 0x1200 /* 1.2 MST */ +#define DP_SIDEBAND_MSG_DOWN_REP_BASE 0x1400 /* 1.2 MST */ +#define DP_SIDEBAND_MSG_UP_REQ_BASE 0x1600 /* 1.2 MST */ + +/* DPRX Event Status Indicator */ +#define DP_SINK_COUNT_ESI 0x2002 /* same as 0x200 */ +#define DP_DEVICE_SERVICE_IRQ_VECTOR_ESI0 0x2003 /* same as 0x201 */ + +#define DP_DEVICE_SERVICE_IRQ_VECTOR_ESI1 0x2004 /* 1.2 */ +# define DP_RX_GTC_MSTR_REQ_STATUS_CHANGE (1 << 0) +# define DP_LOCK_ACQUISITION_REQUEST (1 << 1) +# define DP_CEC_IRQ (1 << 2) + +#define DP_LINK_SERVICE_IRQ_VECTOR_ESI0 0x2005 /* 1.2 */ +# define RX_CAP_CHANGED (1 << 0) +# define LINK_STATUS_CHANGED (1 << 1) +# define STREAM_STATUS_CHANGED (1 << 2) +# define HDMI_LINK_STATUS_CHANGED (1 << 3) +# define CONNECTED_OFF_ENTRY_REQUESTED (1 << 4) + +#define DP_PSR_ERROR_STATUS 0x2006 /* XXX 1.2? */ +# define DP_PSR_LINK_CRC_ERROR (1 << 0) +# define DP_PSR_RFB_STORAGE_ERROR (1 << 1) +# define DP_PSR_VSC_SDP_UNCORRECTABLE_ERROR (1 << 2) /* eDP 1.4 */ + +#define DP_PSR_ESI 0x2007 /* XXX 1.2? */ +# define DP_PSR_CAPS_CHANGE (1 << 0) + +#define DP_PSR_STATUS 0x2008 /* XXX 1.2? */ +# define DP_PSR_SINK_INACTIVE 0 +# define DP_PSR_SINK_ACTIVE_SRC_SYNCED 1 +# define DP_PSR_SINK_ACTIVE_RFB 2 +# define DP_PSR_SINK_ACTIVE_SINK_SYNCED 3 +# define DP_PSR_SINK_ACTIVE_RESYNC 4 +# define DP_PSR_SINK_INTERNAL_ERROR 7 +# define DP_PSR_SINK_STATE_MASK 0x07 + +#define DP_SYNCHRONIZATION_LATENCY_IN_SINK 0x2009 /* edp 1.4 */ +# define DP_MAX_RESYNC_FRAME_COUNT_MASK (0xf << 0) +# define DP_MAX_RESYNC_FRAME_COUNT_SHIFT 0 +# define DP_LAST_ACTUAL_SYNCHRONIZATION_LATENCY_MASK (0xf << 4) +# define DP_LAST_ACTUAL_SYNCHRONIZATION_LATENCY_SHIFT 4 + +#define DP_LAST_RECEIVED_PSR_SDP 0x200a /* eDP 1.2 */ +# define DP_PSR_STATE_BIT (1 << 0) /* eDP 1.2 */ +# define DP_UPDATE_RFB_BIT (1 << 1) /* eDP 1.2 */ +# define DP_CRC_VALID_BIT (1 << 2) /* eDP 1.2 */ +# define DP_SU_VALID (1 << 3) /* eDP 1.4 */ +# define DP_FIRST_SCAN_LINE_SU_REGION (1 << 4) /* eDP 1.4 */ +# define DP_LAST_SCAN_LINE_SU_REGION (1 << 5) /* eDP 1.4 */ +# define DP_Y_COORDINATE_VALID (1 << 6) /* eDP 1.4a */ + +#define DP_RECEIVER_ALPM_STATUS 0x200b /* eDP 1.4 */ +# define DP_ALPM_LOCK_TIMEOUT_ERROR (1 << 0) + +#define DP_LANE0_1_STATUS_ESI 0x200c /* status same as 0x202 */ +#define DP_LANE2_3_STATUS_ESI 0x200d /* status same as 0x203 */ +#define DP_LANE_ALIGN_STATUS_UPDATED_ESI 0x200e /* status same as 0x204 */ +#define DP_SINK_STATUS_ESI 0x200f /* status same as 0x205 */ + +/* Extended Receiver Capability: See DP_DPCD_REV for definitions */ +#define DP_DP13_DPCD_REV 0x2200 + +#define DP_DPRX_FEATURE_ENUMERATION_LIST 0x2210 /* DP 1.3 */ +# define DP_GTC_CAP (1 << 0) /* DP 1.3 */ +# define DP_SST_SPLIT_SDP_CAP (1 << 1) /* DP 1.4 */ +# define DP_AV_SYNC_CAP (1 << 2) /* DP 1.3 */ +# define DP_VSC_SDP_EXT_FOR_COLORIMETRY_SUPPORTED (1 << 3) /* DP 1.3 */ +# define DP_VSC_EXT_VESA_SDP_SUPPORTED (1 << 4) /* DP 1.4 */ +# define DP_VSC_EXT_VESA_SDP_CHAINING_SUPPORTED (1 << 5) /* DP 1.4 */ +# define DP_VSC_EXT_CEA_SDP_SUPPORTED (1 << 6) /* DP 1.4 */ +# define DP_VSC_EXT_CEA_SDP_CHAINING_SUPPORTED (1 << 7) /* DP 1.4 */ + +#define DP_128B132B_SUPPORTED_LINK_RATES 0x2215 /* 2.0 */ +# define DP_UHBR10 (1 << 0) +# define DP_UHBR20 (1 << 1) +# define DP_UHBR13_5 (1 << 2) + +#define DP_128B132B_TRAINING_AUX_RD_INTERVAL 0x2216 /* 2.0 */ +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_MASK 0x7f +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_400_US 0x00 +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_4_MS 0x01 +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_8_MS 0x02 +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_12_MS 0x03 +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_16_MS 0x04 +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_32_MS 0x05 +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_64_MS 0x06 + +#define DP_TEST_264BIT_CUSTOM_PATTERN_7_0 0x2230 +#define DP_TEST_264BIT_CUSTOM_PATTERN_263_256 0x2250 + +/* DSC Extended Capability Branch Total DSC Resources */ +#define DP_DSC_SUPPORT_AND_DSC_DECODER_COUNT 0x2260 /* 2.0 */ +# define DP_DSC_DECODER_COUNT_MASK (0b111 << 5) +# define DP_DSC_DECODER_COUNT_SHIFT 5 +#define DP_DSC_MAX_SLICE_COUNT_AND_AGGREGATION_0 0x2270 /* 2.0 */ +# define DP_DSC_DECODER_0_MAXIMUM_SLICE_COUNT_MASK (1 << 0) +# define DP_DSC_DECODER_0_AGGREGATION_SUPPORT_MASK (0b111 << 1) +# define DP_DSC_DECODER_0_AGGREGATION_SUPPORT_SHIFT 1 + +/* Protocol Converter Extension */ +/* HDMI CEC tunneling over AUX DP 1.3 section 5.3.3.3.1 DPCD 1.4+ */ +#define DP_CEC_TUNNELING_CAPABILITY 0x3000 +# define DP_CEC_TUNNELING_CAPABLE (1 << 0) +# define DP_CEC_SNOOPING_CAPABLE (1 << 1) +# define DP_CEC_MULTIPLE_LA_CAPABLE (1 << 2) + +#define DP_CEC_TUNNELING_CONTROL 0x3001 +# define DP_CEC_TUNNELING_ENABLE (1 << 0) +# define DP_CEC_SNOOPING_ENABLE (1 << 1) + +#define DP_CEC_RX_MESSAGE_INFO 0x3002 +# define DP_CEC_RX_MESSAGE_LEN_MASK (0xf << 0) +# define DP_CEC_RX_MESSAGE_LEN_SHIFT 0 +# define DP_CEC_RX_MESSAGE_HPD_STATE (1 << 4) +# define DP_CEC_RX_MESSAGE_HPD_LOST (1 << 5) +# define DP_CEC_RX_MESSAGE_ACKED (1 << 6) +# define DP_CEC_RX_MESSAGE_ENDED (1 << 7) + +#define DP_CEC_TX_MESSAGE_INFO 0x3003 +# define DP_CEC_TX_MESSAGE_LEN_MASK (0xf << 0) +# define DP_CEC_TX_MESSAGE_LEN_SHIFT 0 +# define DP_CEC_TX_RETRY_COUNT_MASK (0x7 << 4) +# define DP_CEC_TX_RETRY_COUNT_SHIFT 4 +# define DP_CEC_TX_MESSAGE_SEND (1 << 7) + +#define DP_CEC_TUNNELING_IRQ_FLAGS 0x3004 +# define DP_CEC_RX_MESSAGE_INFO_VALID (1 << 0) +# define DP_CEC_RX_MESSAGE_OVERFLOW (1 << 1) +# define DP_CEC_TX_MESSAGE_SENT (1 << 4) +# define DP_CEC_TX_LINE_ERROR (1 << 5) +# define DP_CEC_TX_ADDRESS_NACK_ERROR (1 << 6) +# define DP_CEC_TX_DATA_NACK_ERROR (1 << 7) + +#define DP_CEC_LOGICAL_ADDRESS_MASK 0x300E /* 0x300F word */ +# define DP_CEC_LOGICAL_ADDRESS_0 (1 << 0) +# define DP_CEC_LOGICAL_ADDRESS_1 (1 << 1) +# define DP_CEC_LOGICAL_ADDRESS_2 (1 << 2) +# define DP_CEC_LOGICAL_ADDRESS_3 (1 << 3) +# define DP_CEC_LOGICAL_ADDRESS_4 (1 << 4) +# define DP_CEC_LOGICAL_ADDRESS_5 (1 << 5) +# define DP_CEC_LOGICAL_ADDRESS_6 (1 << 6) +# define DP_CEC_LOGICAL_ADDRESS_7 (1 << 7) +#define DP_CEC_LOGICAL_ADDRESS_MASK_2 0x300F /* 0x300E word */ +# define DP_CEC_LOGICAL_ADDRESS_8 (1 << 0) +# define DP_CEC_LOGICAL_ADDRESS_9 (1 << 1) +# define DP_CEC_LOGICAL_ADDRESS_10 (1 << 2) +# define DP_CEC_LOGICAL_ADDRESS_11 (1 << 3) +# define DP_CEC_LOGICAL_ADDRESS_12 (1 << 4) +# define DP_CEC_LOGICAL_ADDRESS_13 (1 << 5) +# define DP_CEC_LOGICAL_ADDRESS_14 (1 << 6) +# define DP_CEC_LOGICAL_ADDRESS_15 (1 << 7) + +#define DP_CEC_RX_MESSAGE_BUFFER 0x3010 +#define DP_CEC_TX_MESSAGE_BUFFER 0x3020 +#define DP_CEC_MESSAGE_BUFFER_LENGTH 0x10 + +/* PCON CONFIGURE-1 FRL FOR HDMI SINK */ +#define DP_PCON_HDMI_LINK_CONFIG_1 0x305A +# define DP_PCON_ENABLE_MAX_FRL_BW (7 << 0) +# define DP_PCON_ENABLE_MAX_BW_0GBPS 0 +# define DP_PCON_ENABLE_MAX_BW_9GBPS 1 +# define DP_PCON_ENABLE_MAX_BW_18GBPS 2 +# define DP_PCON_ENABLE_MAX_BW_24GBPS 3 +# define DP_PCON_ENABLE_MAX_BW_32GBPS 4 +# define DP_PCON_ENABLE_MAX_BW_40GBPS 5 +# define DP_PCON_ENABLE_MAX_BW_48GBPS 6 +# define DP_PCON_ENABLE_SOURCE_CTL_MODE (1 << 3) +# define DP_PCON_ENABLE_CONCURRENT_LINK (1 << 4) +# define DP_PCON_ENABLE_SEQUENTIAL_LINK (0 << 4) +# define DP_PCON_ENABLE_LINK_FRL_MODE (1 << 5) +# define DP_PCON_ENABLE_HPD_READY (1 << 6) +# define DP_PCON_ENABLE_HDMI_LINK (1 << 7) + +/* PCON CONFIGURE-2 FRL FOR HDMI SINK */ +#define DP_PCON_HDMI_LINK_CONFIG_2 0x305B +# define DP_PCON_MAX_LINK_BW_MASK (0x3F << 0) +# define DP_PCON_FRL_BW_MASK_9GBPS (1 << 0) +# define DP_PCON_FRL_BW_MASK_18GBPS (1 << 1) +# define DP_PCON_FRL_BW_MASK_24GBPS (1 << 2) +# define DP_PCON_FRL_BW_MASK_32GBPS (1 << 3) +# define DP_PCON_FRL_BW_MASK_40GBPS (1 << 4) +# define DP_PCON_FRL_BW_MASK_48GBPS (1 << 5) +# define DP_PCON_FRL_LINK_TRAIN_EXTENDED (1 << 6) +# define DP_PCON_FRL_LINK_TRAIN_NORMAL (0 << 6) + +/* PCON HDMI LINK STATUS */ +#define DP_PCON_HDMI_TX_LINK_STATUS 0x303B +# define DP_PCON_HDMI_TX_LINK_ACTIVE (1 << 0) +# define DP_PCON_FRL_READY (1 << 1) + +/* PCON HDMI POST FRL STATUS */ +#define DP_PCON_HDMI_POST_FRL_STATUS 0x3036 +# define DP_PCON_HDMI_LINK_MODE (1 << 0) +# define DP_PCON_HDMI_MODE_TMDS 0 +# define DP_PCON_HDMI_MODE_FRL 1 +# define DP_PCON_HDMI_FRL_TRAINED_BW (0x3F << 1) +# define DP_PCON_FRL_TRAINED_BW_9GBPS (1 << 1) +# define DP_PCON_FRL_TRAINED_BW_18GBPS (1 << 2) +# define DP_PCON_FRL_TRAINED_BW_24GBPS (1 << 3) +# define DP_PCON_FRL_TRAINED_BW_32GBPS (1 << 4) +# define DP_PCON_FRL_TRAINED_BW_40GBPS (1 << 5) +# define DP_PCON_FRL_TRAINED_BW_48GBPS (1 << 6) + +#define DP_PROTOCOL_CONVERTER_CONTROL_0 0x3050 /* DP 1.3 */ +# define DP_HDMI_DVI_OUTPUT_CONFIG (1 << 0) /* DP 1.3 */ +#define DP_PROTOCOL_CONVERTER_CONTROL_1 0x3051 /* DP 1.3 */ +# define DP_CONVERSION_TO_YCBCR420_ENABLE (1 << 0) /* DP 1.3 */ +# define DP_HDMI_EDID_PROCESSING_DISABLE (1 << 1) /* DP 1.4 */ +# define DP_HDMI_AUTONOMOUS_SCRAMBLING_DISABLE (1 << 2) /* DP 1.4 */ +# define DP_HDMI_FORCE_SCRAMBLING (1 << 3) /* DP 1.4 */ +#define DP_PROTOCOL_CONVERTER_CONTROL_2 0x3052 /* DP 1.3 */ +# define DP_CONVERSION_TO_YCBCR422_ENABLE (1 << 0) /* DP 1.3 */ +# define DP_PCON_ENABLE_DSC_ENCODER (1 << 1) +# define DP_PCON_ENCODER_PPS_OVERRIDE_MASK (0x3 << 2) +# define DP_PCON_ENC_PPS_OVERRIDE_DISABLED 0 +# define DP_PCON_ENC_PPS_OVERRIDE_EN_PARAMS 1 +# define DP_PCON_ENC_PPS_OVERRIDE_EN_BUFFER 2 +# define DP_CONVERSION_RGB_YCBCR_MASK (7 << 4) +# define DP_CONVERSION_BT601_RGB_YCBCR_ENABLE (1 << 4) +# define DP_CONVERSION_BT709_RGB_YCBCR_ENABLE (1 << 5) +# define DP_CONVERSION_BT2020_RGB_YCBCR_ENABLE (1 << 6) + +/* PCON Downstream HDMI ERROR Status per Lane */ +#define DP_PCON_HDMI_ERROR_STATUS_LN0 0x3037 +#define DP_PCON_HDMI_ERROR_STATUS_LN1 0x3038 +#define DP_PCON_HDMI_ERROR_STATUS_LN2 0x3039 +#define DP_PCON_HDMI_ERROR_STATUS_LN3 0x303A +# define DP_PCON_HDMI_ERROR_COUNT_MASK (0x7 << 0) +# define DP_PCON_HDMI_ERROR_COUNT_THREE_PLUS (1 << 0) +# define DP_PCON_HDMI_ERROR_COUNT_TEN_PLUS (1 << 1) +# define DP_PCON_HDMI_ERROR_COUNT_HUNDRED_PLUS (1 << 2) + +/* PCON HDMI CONFIG PPS Override Buffer + * Valid Offsets to be added to Base : 0-127 + */ +#define DP_PCON_HDMI_PPS_OVERRIDE_BASE 0x3100 + +/* PCON HDMI CONFIG PPS Override Parameter: Slice height + * Offset-0 8LSBs of the Slice height. + * Offset-1 8MSBs of the Slice height. + */ +#define DP_PCON_HDMI_PPS_OVRD_SLICE_HEIGHT 0x3180 + +/* PCON HDMI CONFIG PPS Override Parameter: Slice width + * Offset-0 8LSBs of the Slice width. + * Offset-1 8MSBs of the Slice width. + */ +#define DP_PCON_HDMI_PPS_OVRD_SLICE_WIDTH 0x3182 + +/* PCON HDMI CONFIG PPS Override Parameter: bits_per_pixel + * Offset-0 8LSBs of the bits_per_pixel. + * Offset-1 2MSBs of the bits_per_pixel. + */ +#define DP_PCON_HDMI_PPS_OVRD_BPP 0x3184 + +/* HDCP 1.3 and HDCP 2.2 */ +#define DP_AUX_HDCP_BKSV 0x68000 +#define DP_AUX_HDCP_RI_PRIME 0x68005 +#define DP_AUX_HDCP_AKSV 0x68007 +#define DP_AUX_HDCP_AN 0x6800C +#define DP_AUX_HDCP_V_PRIME(h) (0x68014 + h * 4) +#define DP_AUX_HDCP_BCAPS 0x68028 +# define DP_BCAPS_REPEATER_PRESENT BIT(1) +# define DP_BCAPS_HDCP_CAPABLE BIT(0) +#define DP_AUX_HDCP_BSTATUS 0x68029 +# define DP_BSTATUS_REAUTH_REQ BIT(3) +# define DP_BSTATUS_LINK_FAILURE BIT(2) +# define DP_BSTATUS_R0_PRIME_READY BIT(1) +# define DP_BSTATUS_READY BIT(0) +#define DP_AUX_HDCP_BINFO 0x6802A +#define DP_AUX_HDCP_KSV_FIFO 0x6802C +#define DP_AUX_HDCP_AINFO 0x6803B + +/* DP HDCP2.2 parameter offsets in DPCD address space */ +#define DP_HDCP_2_2_REG_RTX_OFFSET 0x69000 +#define DP_HDCP_2_2_REG_TXCAPS_OFFSET 0x69008 +#define DP_HDCP_2_2_REG_CERT_RX_OFFSET 0x6900B +#define DP_HDCP_2_2_REG_RRX_OFFSET 0x69215 +#define DP_HDCP_2_2_REG_RX_CAPS_OFFSET 0x6921D +#define DP_HDCP_2_2_REG_EKPUB_KM_OFFSET 0x69220 +#define DP_HDCP_2_2_REG_EKH_KM_WR_OFFSET 0x692A0 +#define DP_HDCP_2_2_REG_M_OFFSET 0x692B0 +#define DP_HDCP_2_2_REG_HPRIME_OFFSET 0x692C0 +#define DP_HDCP_2_2_REG_EKH_KM_RD_OFFSET 0x692E0 +#define DP_HDCP_2_2_REG_RN_OFFSET 0x692F0 +#define DP_HDCP_2_2_REG_LPRIME_OFFSET 0x692F8 +#define DP_HDCP_2_2_REG_EDKEY_KS_OFFSET 0x69318 +#define DP_HDCP_2_2_REG_RIV_OFFSET 0x69328 +#define DP_HDCP_2_2_REG_RXINFO_OFFSET 0x69330 +#define DP_HDCP_2_2_REG_SEQ_NUM_V_OFFSET 0x69332 +#define DP_HDCP_2_2_REG_VPRIME_OFFSET 0x69335 +#define DP_HDCP_2_2_REG_RECV_ID_LIST_OFFSET 0x69345 +#define DP_HDCP_2_2_REG_V_OFFSET 0x693E0 +#define DP_HDCP_2_2_REG_SEQ_NUM_M_OFFSET 0x693F0 +#define DP_HDCP_2_2_REG_K_OFFSET 0x693F3 +#define DP_HDCP_2_2_REG_STREAM_ID_TYPE_OFFSET 0x693F5 +#define DP_HDCP_2_2_REG_MPRIME_OFFSET 0x69473 +#define DP_HDCP_2_2_REG_RXSTATUS_OFFSET 0x69493 +#define DP_HDCP_2_2_REG_STREAM_TYPE_OFFSET 0x69494 +#define DP_HDCP_2_2_REG_DBG_OFFSET 0x69518 + +/* LTTPR: Link Training (LT)-tunable PHY Repeaters */ +#define DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV 0xf0000 /* 1.3 */ +#define DP_MAX_LINK_RATE_PHY_REPEATER 0xf0001 /* 1.4a */ +#define DP_PHY_REPEATER_CNT 0xf0002 /* 1.3 */ +#define DP_PHY_REPEATER_MODE 0xf0003 /* 1.3 */ +#define DP_MAX_LANE_COUNT_PHY_REPEATER 0xf0004 /* 1.4a */ +#define DP_Repeater_FEC_CAPABILITY 0xf0004 /* 1.4 */ +#define DP_PHY_REPEATER_EXTENDED_WAIT_TIMEOUT 0xf0005 /* 1.4a */ +#define DP_MAIN_LINK_CHANNEL_CODING_PHY_REPEATER 0xf0006 /* 2.0 */ +# define DP_PHY_REPEATER_128B132B_SUPPORTED (1 << 0) +/* See DP_128B132B_SUPPORTED_LINK_RATES for values */ +#define DP_PHY_REPEATER_128B132B_RATES 0xf0007 /* 2.0 */ + +enum drm_dp_phy { + DP_PHY_DPRX, + + DP_PHY_LTTPR1, + DP_PHY_LTTPR2, + DP_PHY_LTTPR3, + DP_PHY_LTTPR4, + DP_PHY_LTTPR5, + DP_PHY_LTTPR6, + DP_PHY_LTTPR7, + DP_PHY_LTTPR8, + + DP_MAX_LTTPR_COUNT = DP_PHY_LTTPR8, +}; + +#define DP_PHY_LTTPR(i) (DP_PHY_LTTPR1 + (i)) + +#define __DP_LTTPR1_BASE 0xf0010 /* 1.3 */ +#define __DP_LTTPR2_BASE 0xf0060 /* 1.3 */ +#define DP_LTTPR_BASE(dp_phy) \ + (__DP_LTTPR1_BASE + (__DP_LTTPR2_BASE - __DP_LTTPR1_BASE) * \ + ((dp_phy) - DP_PHY_LTTPR1)) + +#define DP_LTTPR_REG(dp_phy, lttpr1_reg) \ + (DP_LTTPR_BASE(dp_phy) - DP_LTTPR_BASE(DP_PHY_LTTPR1) + (lttpr1_reg)) + +#define DP_TRAINING_PATTERN_SET_PHY_REPEATER1 0xf0010 /* 1.3 */ +#define DP_TRAINING_PATTERN_SET_PHY_REPEATER(dp_phy) \ + DP_LTTPR_REG(dp_phy, DP_TRAINING_PATTERN_SET_PHY_REPEATER1) + +#define DP_TRAINING_LANE0_SET_PHY_REPEATER1 0xf0011 /* 1.3 */ +#define DP_TRAINING_LANE0_SET_PHY_REPEATER(dp_phy) \ + DP_LTTPR_REG(dp_phy, DP_TRAINING_LANE0_SET_PHY_REPEATER1) + +#define DP_TRAINING_LANE1_SET_PHY_REPEATER1 0xf0012 /* 1.3 */ +#define DP_TRAINING_LANE2_SET_PHY_REPEATER1 0xf0013 /* 1.3 */ +#define DP_TRAINING_LANE3_SET_PHY_REPEATER1 0xf0014 /* 1.3 */ +#define DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1 0xf0020 /* 1.4a */ +#define DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER(dp_phy) \ + DP_LTTPR_REG(dp_phy, DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1) + +#define DP_TRANSMITTER_CAPABILITY_PHY_REPEATER1 0xf0021 /* 1.4a */ +# define DP_VOLTAGE_SWING_LEVEL_3_SUPPORTED BIT(0) +# define DP_PRE_EMPHASIS_LEVEL_3_SUPPORTED BIT(1) + +#define DP_128B132B_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1 0xf0022 /* 2.0 */ +#define DP_128B132B_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER(dp_phy) \ + DP_LTTPR_REG(dp_phy, DP_128B132B_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1) +/* see DP_128B132B_TRAINING_AUX_RD_INTERVAL for values */ + +#define DP_LANE0_1_STATUS_PHY_REPEATER1 0xf0030 /* 1.3 */ +#define DP_LANE0_1_STATUS_PHY_REPEATER(dp_phy) \ + DP_LTTPR_REG(dp_phy, DP_LANE0_1_STATUS_PHY_REPEATER1) + +#define DP_LANE2_3_STATUS_PHY_REPEATER1 0xf0031 /* 1.3 */ + +#define DP_LANE_ALIGN_STATUS_UPDATED_PHY_REPEATER1 0xf0032 /* 1.3 */ +#define DP_ADJUST_REQUEST_LANE0_1_PHY_REPEATER1 0xf0033 /* 1.3 */ +#define DP_ADJUST_REQUEST_LANE2_3_PHY_REPEATER1 0xf0034 /* 1.3 */ +#define DP_SYMBOL_ERROR_COUNT_LANE0_PHY_REPEATER1 0xf0035 /* 1.3 */ +#define DP_SYMBOL_ERROR_COUNT_LANE1_PHY_REPEATER1 0xf0037 /* 1.3 */ +#define DP_SYMBOL_ERROR_COUNT_LANE2_PHY_REPEATER1 0xf0039 /* 1.3 */ +#define DP_SYMBOL_ERROR_COUNT_LANE3_PHY_REPEATER1 0xf003b /* 1.3 */ + +#define __DP_FEC1_BASE 0xf0290 /* 1.4 */ +#define __DP_FEC2_BASE 0xf0298 /* 1.4 */ +#define DP_FEC_BASE(dp_phy) \ + (__DP_FEC1_BASE + ((__DP_FEC2_BASE - __DP_FEC1_BASE) * \ + ((dp_phy) - DP_PHY_LTTPR1))) + +#define DP_FEC_REG(dp_phy, fec1_reg) \ + (DP_FEC_BASE(dp_phy) - DP_FEC_BASE(DP_PHY_LTTPR1) + fec1_reg) + +#define DP_FEC_STATUS_PHY_REPEATER1 0xf0290 /* 1.4 */ +#define DP_FEC_STATUS_PHY_REPEATER(dp_phy) \ + DP_FEC_REG(dp_phy, DP_FEC_STATUS_PHY_REPEATER1) + +#define DP_FEC_ERROR_COUNT_PHY_REPEATER1 0xf0291 /* 1.4 */ +#define DP_FEC_CAPABILITY_PHY_REPEATER1 0xf0294 /* 1.4a */ + +#define DP_LTTPR_MAX_ADD 0xf02ff /* 1.4 */ + +#define DP_DPCD_MAX_ADD 0xfffff /* 1.4 */ + +/* Repeater modes */ +#define DP_PHY_REPEATER_MODE_TRANSPARENT 0x55 /* 1.3 */ +#define DP_PHY_REPEATER_MODE_NON_TRANSPARENT 0xaa /* 1.3 */ + +/* DP HDCP message start offsets in DPCD address space */ +#define DP_HDCP_2_2_AKE_INIT_OFFSET DP_HDCP_2_2_REG_RTX_OFFSET +#define DP_HDCP_2_2_AKE_SEND_CERT_OFFSET DP_HDCP_2_2_REG_CERT_RX_OFFSET +#define DP_HDCP_2_2_AKE_NO_STORED_KM_OFFSET DP_HDCP_2_2_REG_EKPUB_KM_OFFSET +#define DP_HDCP_2_2_AKE_STORED_KM_OFFSET DP_HDCP_2_2_REG_EKH_KM_WR_OFFSET +#define DP_HDCP_2_2_AKE_SEND_HPRIME_OFFSET DP_HDCP_2_2_REG_HPRIME_OFFSET +#define DP_HDCP_2_2_AKE_SEND_PAIRING_INFO_OFFSET \ + DP_HDCP_2_2_REG_EKH_KM_RD_OFFSET +#define DP_HDCP_2_2_LC_INIT_OFFSET DP_HDCP_2_2_REG_RN_OFFSET +#define DP_HDCP_2_2_LC_SEND_LPRIME_OFFSET DP_HDCP_2_2_REG_LPRIME_OFFSET +#define DP_HDCP_2_2_SKE_SEND_EKS_OFFSET DP_HDCP_2_2_REG_EDKEY_KS_OFFSET +#define DP_HDCP_2_2_REP_SEND_RECVID_LIST_OFFSET DP_HDCP_2_2_REG_RXINFO_OFFSET +#define DP_HDCP_2_2_REP_SEND_ACK_OFFSET DP_HDCP_2_2_REG_V_OFFSET +#define DP_HDCP_2_2_REP_STREAM_MANAGE_OFFSET DP_HDCP_2_2_REG_SEQ_NUM_M_OFFSET +#define DP_HDCP_2_2_REP_STREAM_READY_OFFSET DP_HDCP_2_2_REG_MPRIME_OFFSET + +#define HDCP_2_2_DP_RXSTATUS_LEN 1 +#define HDCP_2_2_DP_RXSTATUS_READY(x) ((x) & BIT(0)) +#define HDCP_2_2_DP_RXSTATUS_H_PRIME(x) ((x) & BIT(1)) +#define HDCP_2_2_DP_RXSTATUS_PAIRING(x) ((x) & BIT(2)) +#define HDCP_2_2_DP_RXSTATUS_REAUTH_REQ(x) ((x) & BIT(3)) +#define HDCP_2_2_DP_RXSTATUS_LINK_FAILED(x) ((x) & BIT(4)) + +/* DP 1.2 Sideband message defines */ +/* peer device type - DP 1.2a Table 2-92 */ +#define DP_PEER_DEVICE_NONE 0x0 +#define DP_PEER_DEVICE_SOURCE_OR_SST 0x1 +#define DP_PEER_DEVICE_MST_BRANCHING 0x2 +#define DP_PEER_DEVICE_SST_SINK 0x3 +#define DP_PEER_DEVICE_DP_LEGACY_CONV 0x4 + +/* DP 1.2 MST sideband request names DP 1.2a Table 2-80 */ +#define DP_GET_MSG_TRANSACTION_VERSION 0x00 /* DP 1.3 */ +#define DP_LINK_ADDRESS 0x01 +#define DP_CONNECTION_STATUS_NOTIFY 0x02 +#define DP_ENUM_PATH_RESOURCES 0x10 +#define DP_ALLOCATE_PAYLOAD 0x11 +#define DP_QUERY_PAYLOAD 0x12 +#define DP_RESOURCE_STATUS_NOTIFY 0x13 +#define DP_CLEAR_PAYLOAD_ID_TABLE 0x14 +#define DP_REMOTE_DPCD_READ 0x20 +#define DP_REMOTE_DPCD_WRITE 0x21 +#define DP_REMOTE_I2C_READ 0x22 +#define DP_REMOTE_I2C_WRITE 0x23 +#define DP_POWER_UP_PHY 0x24 +#define DP_POWER_DOWN_PHY 0x25 +#define DP_SINK_EVENT_NOTIFY 0x30 +#define DP_QUERY_STREAM_ENC_STATUS 0x38 +#define DP_QUERY_STREAM_ENC_STATUS_STATE_NO_EXIST 0 +#define DP_QUERY_STREAM_ENC_STATUS_STATE_INACTIVE 1 +#define DP_QUERY_STREAM_ENC_STATUS_STATE_ACTIVE 2 + +/* DP 1.2 MST sideband reply types */ +#define DP_SIDEBAND_REPLY_ACK 0x00 +#define DP_SIDEBAND_REPLY_NAK 0x01 + +/* DP 1.2 MST sideband nak reasons - table 2.84 */ +#define DP_NAK_WRITE_FAILURE 0x01 +#define DP_NAK_INVALID_READ 0x02 +#define DP_NAK_CRC_FAILURE 0x03 +#define DP_NAK_BAD_PARAM 0x04 +#define DP_NAK_DEFER 0x05 +#define DP_NAK_LINK_FAILURE 0x06 +#define DP_NAK_NO_RESOURCES 0x07 +#define DP_NAK_DPCD_FAIL 0x08 +#define DP_NAK_I2C_NAK 0x09 +#define DP_NAK_ALLOCATE_FAIL 0x0a + +#define MODE_I2C_START 1 +#define MODE_I2C_WRITE 2 +#define MODE_I2C_READ 4 +#define MODE_I2C_STOP 8 + +/* DP 1.2 MST PORTs - Section 2.5.1 v1.2a spec */ +#define DP_MST_PHYSICAL_PORT_0 0 +#define DP_MST_LOGICAL_PORT_0 8 + +#define DP_LINK_CONSTANT_N_VALUE 0x8000 +#define DP_LINK_STATUS_SIZE 6 +bool drm_dp_channel_eq_ok(const u8 link_status[DP_LINK_STATUS_SIZE], + int lane_count); +bool drm_dp_clock_recovery_ok(const u8 link_status[DP_LINK_STATUS_SIZE], + int lane_count); +u8 drm_dp_get_adjust_request_voltage(const u8 link_status[DP_LINK_STATUS_SIZE], + int lane); +u8 drm_dp_get_adjust_request_pre_emphasis(const u8 link_status[DP_LINK_STATUS_SIZE], + int lane); +u8 drm_dp_get_adjust_tx_ffe_preset(const u8 link_status[DP_LINK_STATUS_SIZE], + int lane); +u8 drm_dp_get_adjust_request_post_cursor(const u8 link_status[DP_LINK_STATUS_SIZE], + unsigned int lane); + +#define DP_BRANCH_OUI_HEADER_SIZE 0xc +#define DP_RECEIVER_CAP_SIZE 0xf +#define DP_DSC_RECEIVER_CAP_SIZE 0xf +#define EDP_PSR_RECEIVER_CAP_SIZE 2 +#define EDP_DISPLAY_CTL_CAP_SIZE 3 +#define DP_LTTPR_COMMON_CAP_SIZE 8 +#define DP_LTTPR_PHY_CAP_SIZE 3 + +int drm_dp_read_clock_recovery_delay(struct drm_dp_aux *aux, const u8 dpcd[DP_RECEIVER_CAP_SIZE], + enum drm_dp_phy dp_phy, bool uhbr); +int drm_dp_read_channel_eq_delay(struct drm_dp_aux *aux, const u8 dpcd[DP_RECEIVER_CAP_SIZE], + enum drm_dp_phy dp_phy, bool uhbr); + +void drm_dp_link_train_clock_recovery_delay(const struct drm_dp_aux *aux, + const u8 dpcd[DP_RECEIVER_CAP_SIZE]); +void drm_dp_lttpr_link_train_clock_recovery_delay(void); +void drm_dp_link_train_channel_eq_delay(const struct drm_dp_aux *aux, + const u8 dpcd[DP_RECEIVER_CAP_SIZE]); +void drm_dp_lttpr_link_train_channel_eq_delay(const struct drm_dp_aux *aux, + const u8 caps[DP_LTTPR_PHY_CAP_SIZE]); + +u8 drm_dp_link_rate_to_bw_code(int link_rate); +int drm_dp_bw_code_to_link_rate(u8 link_bw); + +#define DP_SDP_AUDIO_TIMESTAMP 0x01 +#define DP_SDP_AUDIO_STREAM 0x02 +#define DP_SDP_EXTENSION 0x04 /* DP 1.1 */ +#define DP_SDP_AUDIO_COPYMANAGEMENT 0x05 /* DP 1.2 */ +#define DP_SDP_ISRC 0x06 /* DP 1.2 */ +#define DP_SDP_VSC 0x07 /* DP 1.2 */ +#define DP_SDP_CAMERA_GENERIC(i) (0x08 + (i)) /* 0-7, DP 1.3 */ +#define DP_SDP_PPS 0x10 /* DP 1.4 */ +#define DP_SDP_VSC_EXT_VESA 0x20 /* DP 1.4 */ +#define DP_SDP_VSC_EXT_CEA 0x21 /* DP 1.4 */ +/* 0x80+ CEA-861 infoframe types */ + +/** + * struct dp_sdp_header - DP secondary data packet header + * @HB0: Secondary Data Packet ID + * @HB1: Secondary Data Packet Type + * @HB2: Secondary Data Packet Specific header, Byte 0 + * @HB3: Secondary Data packet Specific header, Byte 1 + */ +struct dp_sdp_header { + u8 HB0; + u8 HB1; + u8 HB2; + u8 HB3; +} __packed; + +#define EDP_SDP_HEADER_REVISION_MASK 0x1F +#define EDP_SDP_HEADER_VALID_PAYLOAD_BYTES 0x1F +#define DP_SDP_PPS_HEADER_PAYLOAD_BYTES_MINUS_1 0x7F + +/** + * struct dp_sdp - DP secondary data packet + * @sdp_header: DP secondary data packet header + * @db: DP secondaray data packet data blocks + * VSC SDP Payload for PSR + * db[0]: Stereo Interface + * db[1]: 0 - PSR State; 1 - Update RFB; 2 - CRC Valid + * db[2]: CRC value bits 7:0 of the R or Cr component + * db[3]: CRC value bits 15:8 of the R or Cr component + * db[4]: CRC value bits 7:0 of the G or Y component + * db[5]: CRC value bits 15:8 of the G or Y component + * db[6]: CRC value bits 7:0 of the B or Cb component + * db[7]: CRC value bits 15:8 of the B or Cb component + * db[8] - db[31]: Reserved + * VSC SDP Payload for Pixel Encoding/Colorimetry Format + * db[0] - db[15]: Reserved + * db[16]: Pixel Encoding and Colorimetry Formats + * db[17]: Dynamic Range and Component Bit Depth + * db[18]: Content Type + * db[19] - db[31]: Reserved + */ +struct dp_sdp { + struct dp_sdp_header sdp_header; + u8 db[32]; +} __packed; + +#define EDP_VSC_PSR_STATE_ACTIVE (1<<0) +#define EDP_VSC_PSR_UPDATE_RFB (1<<1) +#define EDP_VSC_PSR_CRC_VALUES_VALID (1<<2) + +/** + * enum dp_pixelformat - drm DP Pixel encoding formats + * + * This enum is used to indicate DP VSC SDP Pixel encoding formats. + * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through + * DB18] + * + * @DP_PIXELFORMAT_RGB: RGB pixel encoding format + * @DP_PIXELFORMAT_YUV444: YCbCr 4:4:4 pixel encoding format + * @DP_PIXELFORMAT_YUV422: YCbCr 4:2:2 pixel encoding format + * @DP_PIXELFORMAT_YUV420: YCbCr 4:2:0 pixel encoding format + * @DP_PIXELFORMAT_Y_ONLY: Y Only pixel encoding format + * @DP_PIXELFORMAT_RAW: RAW pixel encoding format + * @DP_PIXELFORMAT_RESERVED: Reserved pixel encoding format + */ +enum dp_pixelformat { + DP_PIXELFORMAT_RGB = 0, + DP_PIXELFORMAT_YUV444 = 0x1, + DP_PIXELFORMAT_YUV422 = 0x2, + DP_PIXELFORMAT_YUV420 = 0x3, + DP_PIXELFORMAT_Y_ONLY = 0x4, + DP_PIXELFORMAT_RAW = 0x5, + DP_PIXELFORMAT_RESERVED = 0x6, +}; + +/** + * enum dp_colorimetry - drm DP Colorimetry formats + * + * This enum is used to indicate DP VSC SDP Colorimetry formats. + * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through + * DB18] and a name of enum member follows DRM_MODE_COLORIMETRY definition. + * + * @DP_COLORIMETRY_DEFAULT: sRGB (IEC 61966-2-1) or + * ITU-R BT.601 colorimetry format + * @DP_COLORIMETRY_RGB_WIDE_FIXED: RGB wide gamut fixed point colorimetry format + * @DP_COLORIMETRY_BT709_YCC: ITU-R BT.709 colorimetry format + * @DP_COLORIMETRY_RGB_WIDE_FLOAT: RGB wide gamut floating point + * (scRGB (IEC 61966-2-2)) colorimetry format + * @DP_COLORIMETRY_XVYCC_601: xvYCC601 colorimetry format + * @DP_COLORIMETRY_OPRGB: OpRGB colorimetry format + * @DP_COLORIMETRY_XVYCC_709: xvYCC709 colorimetry format + * @DP_COLORIMETRY_DCI_P3_RGB: DCI-P3 (SMPTE RP 431-2) colorimetry format + * @DP_COLORIMETRY_SYCC_601: sYCC601 colorimetry format + * @DP_COLORIMETRY_RGB_CUSTOM: RGB Custom Color Profile colorimetry format + * @DP_COLORIMETRY_OPYCC_601: opYCC601 colorimetry format + * @DP_COLORIMETRY_BT2020_RGB: ITU-R BT.2020 R' G' B' colorimetry format + * @DP_COLORIMETRY_BT2020_CYCC: ITU-R BT.2020 Y'c C'bc C'rc colorimetry format + * @DP_COLORIMETRY_BT2020_YCC: ITU-R BT.2020 Y' C'b C'r colorimetry format + */ +enum dp_colorimetry { + DP_COLORIMETRY_DEFAULT = 0, + DP_COLORIMETRY_RGB_WIDE_FIXED = 0x1, + DP_COLORIMETRY_BT709_YCC = 0x1, + DP_COLORIMETRY_RGB_WIDE_FLOAT = 0x2, + DP_COLORIMETRY_XVYCC_601 = 0x2, + DP_COLORIMETRY_OPRGB = 0x3, + DP_COLORIMETRY_XVYCC_709 = 0x3, + DP_COLORIMETRY_DCI_P3_RGB = 0x4, + DP_COLORIMETRY_SYCC_601 = 0x4, + DP_COLORIMETRY_RGB_CUSTOM = 0x5, + DP_COLORIMETRY_OPYCC_601 = 0x5, + DP_COLORIMETRY_BT2020_RGB = 0x6, + DP_COLORIMETRY_BT2020_CYCC = 0x6, + DP_COLORIMETRY_BT2020_YCC = 0x7, +}; + +/** + * enum dp_dynamic_range - drm DP Dynamic Range + * + * This enum is used to indicate DP VSC SDP Dynamic Range. + * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through + * DB18] + * + * @DP_DYNAMIC_RANGE_VESA: VESA range + * @DP_DYNAMIC_RANGE_CTA: CTA range + */ +enum dp_dynamic_range { + DP_DYNAMIC_RANGE_VESA = 0, + DP_DYNAMIC_RANGE_CTA = 1, +}; + +/** + * enum dp_content_type - drm DP Content Type + * + * This enum is used to indicate DP VSC SDP Content Types. + * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through + * DB18] + * CTA-861-G defines content types and expected processing by a sink device + * + * @DP_CONTENT_TYPE_NOT_DEFINED: Not defined type + * @DP_CONTENT_TYPE_GRAPHICS: Graphics type + * @DP_CONTENT_TYPE_PHOTO: Photo type + * @DP_CONTENT_TYPE_VIDEO: Video type + * @DP_CONTENT_TYPE_GAME: Game type + */ +enum dp_content_type { + DP_CONTENT_TYPE_NOT_DEFINED = 0x00, + DP_CONTENT_TYPE_GRAPHICS = 0x01, + DP_CONTENT_TYPE_PHOTO = 0x02, + DP_CONTENT_TYPE_VIDEO = 0x03, + DP_CONTENT_TYPE_GAME = 0x04, +}; + +/** + * struct drm_dp_vsc_sdp - drm DP VSC SDP + * + * This structure represents a DP VSC SDP of drm + * It is based on DP 1.4 spec [Table 2-116: VSC SDP Header Bytes] and + * [Table 2-117: VSC SDP Payload for DB16 through DB18] + * + * @sdp_type: secondary-data packet type + * @revision: revision number + * @length: number of valid data bytes + * @pixelformat: pixel encoding format + * @colorimetry: colorimetry format + * @bpc: bit per color + * @dynamic_range: dynamic range information + * @content_type: CTA-861-G defines content types and expected processing by a sink device + */ +struct drm_dp_vsc_sdp { + unsigned char sdp_type; + unsigned char revision; + unsigned char length; + enum dp_pixelformat pixelformat; + enum dp_colorimetry colorimetry; + int bpc; + enum dp_dynamic_range dynamic_range; + enum dp_content_type content_type; +}; + +void drm_dp_vsc_sdp_log(const char *level, struct device *dev, + const struct drm_dp_vsc_sdp *vsc); + +int drm_dp_psr_setup_time(const u8 psr_cap[EDP_PSR_RECEIVER_CAP_SIZE]); + +static inline int +drm_dp_max_link_rate(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return drm_dp_bw_code_to_link_rate(dpcd[DP_MAX_LINK_RATE]); +} + +static inline u8 +drm_dp_max_lane_count(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return dpcd[DP_MAX_LANE_COUNT] & DP_MAX_LANE_COUNT_MASK; +} + +static inline bool +drm_dp_enhanced_frame_cap(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return dpcd[DP_DPCD_REV] >= 0x11 && + (dpcd[DP_MAX_LANE_COUNT] & DP_ENHANCED_FRAME_CAP); +} + +static inline bool +drm_dp_fast_training_cap(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return dpcd[DP_DPCD_REV] >= 0x11 && + (dpcd[DP_MAX_DOWNSPREAD] & DP_NO_AUX_HANDSHAKE_LINK_TRAINING); +} + +static inline bool +drm_dp_tps3_supported(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return dpcd[DP_DPCD_REV] >= 0x12 && + dpcd[DP_MAX_LANE_COUNT] & DP_TPS3_SUPPORTED; +} + +static inline bool +drm_dp_tps4_supported(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return dpcd[DP_DPCD_REV] >= 0x14 && + dpcd[DP_MAX_DOWNSPREAD] & DP_TPS4_SUPPORTED; +} + +static inline u8 +drm_dp_training_pattern_mask(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return (dpcd[DP_DPCD_REV] >= 0x14) ? DP_TRAINING_PATTERN_MASK_1_4 : + DP_TRAINING_PATTERN_MASK; +} + +static inline bool +drm_dp_is_branch(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_PRESENT; +} + +/* DP/eDP DSC support */ +u8 drm_dp_dsc_sink_max_slice_count(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE], + bool is_edp); +u8 drm_dp_dsc_sink_line_buf_depth(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]); +int drm_dp_dsc_sink_supported_input_bpcs(const u8 dsc_dpc[DP_DSC_RECEIVER_CAP_SIZE], + u8 dsc_bpc[3]); + +static inline bool +drm_dp_sink_supports_dsc(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]) +{ + return dsc_dpcd[DP_DSC_SUPPORT - DP_DSC_SUPPORT] & + DP_DSC_DECOMPRESSION_IS_SUPPORTED; +} + +static inline u16 +drm_edp_dsc_sink_output_bpp(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]) +{ + return dsc_dpcd[DP_DSC_MAX_BITS_PER_PIXEL_LOW - DP_DSC_SUPPORT] | + (dsc_dpcd[DP_DSC_MAX_BITS_PER_PIXEL_HI - DP_DSC_SUPPORT] & + DP_DSC_MAX_BITS_PER_PIXEL_HI_MASK << + DP_DSC_MAX_BITS_PER_PIXEL_HI_SHIFT); +} + +static inline u32 +drm_dp_dsc_sink_max_slice_width(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]) +{ + /* Max Slicewidth = Number of Pixels * 320 */ + return dsc_dpcd[DP_DSC_MAX_SLICE_WIDTH - DP_DSC_SUPPORT] * + DP_DSC_SLICE_WIDTH_MULTIPLIER; +} + +/* Forward Error Correction Support on DP 1.4 */ +static inline bool +drm_dp_sink_supports_fec(const u8 fec_capable) +{ + return fec_capable & DP_FEC_CAPABLE; +} + +static inline bool +drm_dp_channel_coding_supported(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return dpcd[DP_MAIN_LINK_CHANNEL_CODING] & DP_CAP_ANSI_8B10B; +} + +static inline bool +drm_dp_alternate_scrambler_reset_cap(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return dpcd[DP_EDP_CONFIGURATION_CAP] & + DP_ALTERNATE_SCRAMBLER_RESET_CAP; +} + +/* Ignore MSA timing for Adaptive Sync support on DP 1.4 */ +static inline bool +drm_dp_sink_can_do_video_without_timing_msa(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return dpcd[DP_DOWN_STREAM_PORT_COUNT] & + DP_MSA_TIMING_PAR_IGNORED; +} + +/** + * drm_edp_backlight_supported() - Check an eDP DPCD for VESA backlight support + * @edp_dpcd: The DPCD to check + * + * Note that currently this function will return %false for panels which support various DPCD + * backlight features but which require the brightness be set through PWM, and don't support setting + * the brightness level via the DPCD. + * + * Returns: %True if @edp_dpcd indicates that VESA backlight controls are supported, %false + * otherwise + */ +static inline bool +drm_edp_backlight_supported(const u8 edp_dpcd[EDP_DISPLAY_CTL_CAP_SIZE]) +{ + return !!(edp_dpcd[1] & DP_EDP_TCON_BACKLIGHT_ADJUSTMENT_CAP); +} + +/* + * DisplayPort AUX channel + */ + +/** + * struct drm_dp_aux_msg - DisplayPort AUX channel transaction + * @address: address of the (first) register to access + * @request: contains the type of transaction (see DP_AUX_* macros) + * @reply: upon completion, contains the reply type of the transaction + * @buffer: pointer to a transmission or reception buffer + * @size: size of @buffer + */ +struct drm_dp_aux_msg { + unsigned int address; + u8 request; + u8 reply; + void *buffer; + size_t size; +}; + +struct cec_adapter; +struct edid; +struct drm_connector; + +/** + * struct drm_dp_aux_cec - DisplayPort CEC-Tunneling-over-AUX + * @lock: mutex protecting this struct + * @adap: the CEC adapter for CEC-Tunneling-over-AUX support. + * @connector: the connector this CEC adapter is associated with + * @unregister_work: unregister the CEC adapter + */ +struct drm_dp_aux_cec { + struct mutex lock; + struct cec_adapter *adap; + struct drm_connector *connector; + struct delayed_work unregister_work; +}; + +/** + * struct drm_dp_aux - DisplayPort AUX channel + * + * An AUX channel can also be used to transport I2C messages to a sink. A + * typical application of that is to access an EDID that's present in the sink + * device. The @transfer() function can also be used to execute such + * transactions. The drm_dp_aux_register() function registers an I2C adapter + * that can be passed to drm_probe_ddc(). Upon removal, drivers should call + * drm_dp_aux_unregister() to remove the I2C adapter. The I2C adapter uses long + * transfers by default; if a partial response is received, the adapter will + * drop down to the size given by the partial response for this transaction + * only. + */ +struct drm_dp_aux { + /** + * @name: user-visible name of this AUX channel and the + * I2C-over-AUX adapter. + * + * It's also used to specify the name of the I2C adapter. If set + * to %NULL, dev_name() of @dev will be used. + */ + const char *name; + + /** + * @ddc: I2C adapter that can be used for I2C-over-AUX + * communication + */ + struct i2c_adapter ddc; + + /** + * @dev: pointer to struct device that is the parent for this + * AUX channel. + */ + struct device *dev; + + /** + * @drm_dev: pointer to the &drm_device that owns this AUX channel. + * Beware, this may be %NULL before drm_dp_aux_register() has been + * called. + * + * It should be set to the &drm_device that will be using this AUX + * channel as early as possible. For many graphics drivers this should + * happen before drm_dp_aux_init(), however it's perfectly fine to set + * this field later so long as it's assigned before calling + * drm_dp_aux_register(). + */ + struct drm_device *drm_dev; + + /** + * @crtc: backpointer to the crtc that is currently using this + * AUX channel + */ + struct drm_crtc *crtc; + + /** + * @hw_mutex: internal mutex used for locking transfers. + * + * Note that if the underlying hardware is shared among multiple + * channels, the driver needs to do additional locking to + * prevent concurrent access. + */ + struct mutex hw_mutex; + + /** + * @crc_work: worker that captures CRCs for each frame + */ + struct work_struct crc_work; + + /** + * @crc_count: counter of captured frame CRCs + */ + u8 crc_count; + + /** + * @transfer: transfers a message representing a single AUX + * transaction. + * + * This is a hardware-specific implementation of how + * transactions are executed that the drivers must provide. + * + * A pointer to a &drm_dp_aux_msg structure describing the + * transaction is passed into this function. Upon success, the + * implementation should return the number of payload bytes that + * were transferred, or a negative error-code on failure. + * + * Helpers will propagate these errors, with the exception of + * the %-EBUSY error, which causes a transaction to be retried. + * On a short, helpers will return %-EPROTO to make it simpler + * to check for failure. + * + * The @transfer() function must only modify the reply field of + * the &drm_dp_aux_msg structure. The retry logic and i2c + * helpers assume this is the case. + * + * Also note that this callback can be called no matter the + * state @dev is in. Drivers that need that device to be powered + * to perform this operation will first need to make sure it's + * been properly enabled. + */ + ssize_t (*transfer)(struct drm_dp_aux *aux, + struct drm_dp_aux_msg *msg); + + /** + * @i2c_nack_count: Counts I2C NACKs, used for DP validation. + */ + unsigned i2c_nack_count; + /** + * @i2c_defer_count: Counts I2C DEFERs, used for DP validation. + */ + unsigned i2c_defer_count; + /** + * @cec: struct containing fields used for CEC-Tunneling-over-AUX. + */ + struct drm_dp_aux_cec cec; + /** + * @is_remote: Is this AUX CH actually using sideband messaging. + */ + bool is_remote; +}; + +ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset, + void *buffer, size_t size); +ssize_t drm_dp_dpcd_write(struct drm_dp_aux *aux, unsigned int offset, + void *buffer, size_t size); + +/** + * drm_dp_dpcd_readb() - read a single byte from the DPCD + * @aux: DisplayPort AUX channel + * @offset: address of the register to read + * @valuep: location where the value of the register will be stored + * + * Returns the number of bytes transferred (1) on success, or a negative + * error code on failure. + */ +static inline ssize_t drm_dp_dpcd_readb(struct drm_dp_aux *aux, + unsigned int offset, u8 *valuep) +{ + return drm_dp_dpcd_read(aux, offset, valuep, 1); +} + +/** + * drm_dp_dpcd_writeb() - write a single byte to the DPCD + * @aux: DisplayPort AUX channel + * @offset: address of the register to write + * @value: value to write to the register + * + * Returns the number of bytes transferred (1) on success, or a negative + * error code on failure. + */ +static inline ssize_t drm_dp_dpcd_writeb(struct drm_dp_aux *aux, + unsigned int offset, u8 value) +{ + return drm_dp_dpcd_write(aux, offset, &value, 1); +} + +int drm_dp_read_dpcd_caps(struct drm_dp_aux *aux, + u8 dpcd[DP_RECEIVER_CAP_SIZE]); + +int drm_dp_dpcd_read_link_status(struct drm_dp_aux *aux, + u8 status[DP_LINK_STATUS_SIZE]); + +int drm_dp_dpcd_read_phy_link_status(struct drm_dp_aux *aux, + enum drm_dp_phy dp_phy, + u8 link_status[DP_LINK_STATUS_SIZE]); + +bool drm_dp_send_real_edid_checksum(struct drm_dp_aux *aux, + u8 real_edid_checksum); + +int drm_dp_read_downstream_info(struct drm_dp_aux *aux, + const u8 dpcd[DP_RECEIVER_CAP_SIZE], + u8 downstream_ports[DP_MAX_DOWNSTREAM_PORTS]); +bool drm_dp_downstream_is_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], u8 type); +bool drm_dp_downstream_is_tmds(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], + const struct edid *edid); +int drm_dp_downstream_max_dotclock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]); +int drm_dp_downstream_max_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], + const struct edid *edid); +int drm_dp_downstream_min_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], + const struct edid *edid); +int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], + const struct edid *edid); +bool drm_dp_downstream_420_passthrough(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]); +bool drm_dp_downstream_444_to_420_conversion(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]); +struct drm_display_mode *drm_dp_downstream_mode(struct drm_device *dev, + const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]); +int drm_dp_downstream_id(struct drm_dp_aux *aux, char id[6]); +void drm_dp_downstream_debug(struct seq_file *m, + const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], + const struct edid *edid, + struct drm_dp_aux *aux); +enum drm_mode_subconnector +drm_dp_subconnector_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]); +void drm_dp_set_subconnector_property(struct drm_connector *connector, + enum drm_connector_status status, + const u8 *dpcd, + const u8 port_cap[4]); + +struct drm_dp_desc; +bool drm_dp_read_sink_count_cap(struct drm_connector *connector, + const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const struct drm_dp_desc *desc); +int drm_dp_read_sink_count(struct drm_dp_aux *aux); + +int drm_dp_read_lttpr_common_caps(struct drm_dp_aux *aux, + u8 caps[DP_LTTPR_COMMON_CAP_SIZE]); +int drm_dp_read_lttpr_phy_caps(struct drm_dp_aux *aux, + enum drm_dp_phy dp_phy, + u8 caps[DP_LTTPR_PHY_CAP_SIZE]); +int drm_dp_lttpr_count(const u8 cap[DP_LTTPR_COMMON_CAP_SIZE]); +int drm_dp_lttpr_max_link_rate(const u8 caps[DP_LTTPR_COMMON_CAP_SIZE]); +int drm_dp_lttpr_max_lane_count(const u8 caps[DP_LTTPR_COMMON_CAP_SIZE]); +bool drm_dp_lttpr_voltage_swing_level_3_supported(const u8 caps[DP_LTTPR_PHY_CAP_SIZE]); +bool drm_dp_lttpr_pre_emphasis_level_3_supported(const u8 caps[DP_LTTPR_PHY_CAP_SIZE]); + +void drm_dp_remote_aux_init(struct drm_dp_aux *aux); +void drm_dp_aux_init(struct drm_dp_aux *aux); +int drm_dp_aux_register(struct drm_dp_aux *aux); +void drm_dp_aux_unregister(struct drm_dp_aux *aux); + +int drm_dp_start_crc(struct drm_dp_aux *aux, struct drm_crtc *crtc); +int drm_dp_stop_crc(struct drm_dp_aux *aux); + +struct drm_dp_dpcd_ident { + u8 oui[3]; + u8 device_id[6]; + u8 hw_rev; + u8 sw_major_rev; + u8 sw_minor_rev; +} __packed; + +/** + * struct drm_dp_desc - DP branch/sink device descriptor + * @ident: DP device identification from DPCD 0x400 (sink) or 0x500 (branch). + * @quirks: Quirks; use drm_dp_has_quirk() to query for the quirks. + */ +struct drm_dp_desc { + struct drm_dp_dpcd_ident ident; + u32 quirks; +}; + +int drm_dp_read_desc(struct drm_dp_aux *aux, struct drm_dp_desc *desc, + bool is_branch); + +/** + * enum drm_dp_quirk - Display Port sink/branch device specific quirks + * + * Display Port sink and branch devices in the wild have a variety of bugs, try + * to collect them here. The quirks are shared, but it's up to the drivers to + * implement workarounds for them. + */ +enum drm_dp_quirk { + /** + * @DP_DPCD_QUIRK_CONSTANT_N: + * + * The device requires main link attributes Mvid and Nvid to be limited + * to 16 bits. So will give a constant value (0x8000) for compatability. + */ + DP_DPCD_QUIRK_CONSTANT_N, + /** + * @DP_DPCD_QUIRK_NO_PSR: + * + * The device does not support PSR even if reports that it supports or + * driver still need to implement proper handling for such device. + */ + DP_DPCD_QUIRK_NO_PSR, + /** + * @DP_DPCD_QUIRK_NO_SINK_COUNT: + * + * The device does not set SINK_COUNT to a non-zero value. + * The driver should ignore SINK_COUNT during detection. Note that + * drm_dp_read_sink_count_cap() automatically checks for this quirk. + */ + DP_DPCD_QUIRK_NO_SINK_COUNT, + /** + * @DP_DPCD_QUIRK_DSC_WITHOUT_VIRTUAL_DPCD: + * + * The device supports MST DSC despite not supporting Virtual DPCD. + * The DSC caps can be read from the physical aux instead. + */ + DP_DPCD_QUIRK_DSC_WITHOUT_VIRTUAL_DPCD, + /** + * @DP_DPCD_QUIRK_CAN_DO_MAX_LINK_RATE_3_24_GBPS: + * + * The device supports a link rate of 3.24 Gbps (multiplier 0xc) despite + * the DP_MAX_LINK_RATE register reporting a lower max multiplier. + */ + DP_DPCD_QUIRK_CAN_DO_MAX_LINK_RATE_3_24_GBPS, +}; + +/** + * drm_dp_has_quirk() - does the DP device have a specific quirk + * @desc: Device descriptor filled by drm_dp_read_desc() + * @quirk: Quirk to query for + * + * Return true if DP device identified by @desc has @quirk. + */ +static inline bool +drm_dp_has_quirk(const struct drm_dp_desc *desc, enum drm_dp_quirk quirk) +{ + return desc->quirks & BIT(quirk); +} + +/** + * struct drm_edp_backlight_info - Probed eDP backlight info struct + * @pwmgen_bit_count: The pwmgen bit count + * @pwm_freq_pre_divider: The PWM frequency pre-divider value being used for this backlight, if any + * @max: The maximum backlight level that may be set + * @lsb_reg_used: Do we also write values to the DP_EDP_BACKLIGHT_BRIGHTNESS_LSB register? + * @aux_enable: Does the panel support the AUX enable cap? + * @aux_set: Does the panel support setting the brightness through AUX? + * + * This structure contains various data about an eDP backlight, which can be populated by using + * drm_edp_backlight_init(). + */ +struct drm_edp_backlight_info { + u8 pwmgen_bit_count; + u8 pwm_freq_pre_divider; + u16 max; + + bool lsb_reg_used : 1; + bool aux_enable : 1; + bool aux_set : 1; +}; + +int +drm_edp_backlight_init(struct drm_dp_aux *aux, struct drm_edp_backlight_info *bl, + u16 driver_pwm_freq_hz, const u8 edp_dpcd[EDP_DISPLAY_CTL_CAP_SIZE], + u16 *current_level, u8 *current_mode); +int drm_edp_backlight_set_level(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl, + u16 level); +int drm_edp_backlight_enable(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl, + u16 level); +int drm_edp_backlight_disable(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl); + +#if IS_ENABLED(CONFIG_DRM_KMS_HELPER) && (IS_BUILTIN(CONFIG_BACKLIGHT_CLASS_DEVICE) || \ + (IS_MODULE(CONFIG_DRM_KMS_HELPER) && IS_MODULE(CONFIG_BACKLIGHT_CLASS_DEVICE))) + +int drm_panel_dp_aux_backlight(struct drm_panel *panel, struct drm_dp_aux *aux); + +#else + +static inline int drm_panel_dp_aux_backlight(struct drm_panel *panel, + struct drm_dp_aux *aux) +{ + return 0; +} + +#endif + +#ifdef CONFIG_DRM_DP_CEC +void drm_dp_cec_irq(struct drm_dp_aux *aux); +void drm_dp_cec_register_connector(struct drm_dp_aux *aux, + struct drm_connector *connector); +void drm_dp_cec_unregister_connector(struct drm_dp_aux *aux); +void drm_dp_cec_set_edid(struct drm_dp_aux *aux, const struct edid *edid); +void drm_dp_cec_unset_edid(struct drm_dp_aux *aux); +#else +static inline void drm_dp_cec_irq(struct drm_dp_aux *aux) +{ +} + +static inline void +drm_dp_cec_register_connector(struct drm_dp_aux *aux, + struct drm_connector *connector) +{ +} + +static inline void drm_dp_cec_unregister_connector(struct drm_dp_aux *aux) +{ +} + +static inline void drm_dp_cec_set_edid(struct drm_dp_aux *aux, + const struct edid *edid) +{ +} + +static inline void drm_dp_cec_unset_edid(struct drm_dp_aux *aux) +{ +} + +#endif + +/** + * struct drm_dp_phy_test_params - DP Phy Compliance parameters + * @link_rate: Requested Link rate from DPCD 0x219 + * @num_lanes: Number of lanes requested by sing through DPCD 0x220 + * @phy_pattern: DP Phy test pattern from DPCD 0x248 + * @hbr2_reset: DP HBR2_COMPLIANCE_SCRAMBLER_RESET from DCPD 0x24A and 0x24B + * @custom80: DP Test_80BIT_CUSTOM_PATTERN from DPCDs 0x250 through 0x259 + * @enhanced_frame_cap: flag for enhanced frame capability. + */ +struct drm_dp_phy_test_params { + int link_rate; + u8 num_lanes; + u8 phy_pattern; + u8 hbr2_reset[2]; + u8 custom80[10]; + bool enhanced_frame_cap; +}; + +int drm_dp_get_phy_test_pattern(struct drm_dp_aux *aux, + struct drm_dp_phy_test_params *data); +int drm_dp_set_phy_test_pattern(struct drm_dp_aux *aux, + struct drm_dp_phy_test_params *data, u8 dp_rev); +int drm_dp_get_pcon_max_frl_bw(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]); +int drm_dp_pcon_frl_prepare(struct drm_dp_aux *aux, bool enable_frl_ready_hpd); +bool drm_dp_pcon_is_frl_ready(struct drm_dp_aux *aux); +int drm_dp_pcon_frl_configure_1(struct drm_dp_aux *aux, int max_frl_gbps, + u8 frl_mode); +int drm_dp_pcon_frl_configure_2(struct drm_dp_aux *aux, int max_frl_mask, + u8 frl_type); +int drm_dp_pcon_reset_frl_config(struct drm_dp_aux *aux); +int drm_dp_pcon_frl_enable(struct drm_dp_aux *aux); + +bool drm_dp_pcon_hdmi_link_active(struct drm_dp_aux *aux); +int drm_dp_pcon_hdmi_link_mode(struct drm_dp_aux *aux, u8 *frl_trained_mask); +void drm_dp_pcon_hdmi_frl_link_error_count(struct drm_dp_aux *aux, + struct drm_connector *connector); +bool drm_dp_pcon_enc_is_dsc_1_2(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]); +int drm_dp_pcon_dsc_max_slices(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]); +int drm_dp_pcon_dsc_max_slice_width(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]); +int drm_dp_pcon_dsc_bpp_incr(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]); +int drm_dp_pcon_pps_default(struct drm_dp_aux *aux); +int drm_dp_pcon_pps_override_buf(struct drm_dp_aux *aux, u8 pps_buf[128]); +int drm_dp_pcon_pps_override_param(struct drm_dp_aux *aux, u8 pps_param[6]); +bool drm_dp_downstream_rgb_to_ycbcr_conversion(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], u8 color_spc); +int drm_dp_pcon_convert_rgb_to_ycbcr(struct drm_dp_aux *aux, u8 color_spc); + +#endif /* _DRM_DP_HELPER_H_ */ diff --git a/include/drm/dp/drm_dp_mst_helper.h b/include/drm/dp/drm_dp_mst_helper.h new file mode 100644 index 000000000000..08276eb8c187 --- /dev/null +++ b/include/drm/dp/drm_dp_mst_helper.h @@ -0,0 +1,972 @@ +/* + * Copyright © 2014 Red Hat. + * + * Permission to use, copy, modify, distribute, and sell this software and its + * documentation for any purpose is hereby granted without fee, provided that + * the above copyright notice appear in all copies and that both that copyright + * notice and this permission notice appear in supporting documentation, and + * that the name of the copyright holders not be used in advertising or + * publicity pertaining to distribution of the software without specific, + * written prior permission. The copyright holders make no representations + * about the suitability of this software for any purpose. It is provided "as + * is" without express or implied warranty. + * + * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, + * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO + * EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT OR + * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, + * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER + * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE + * OF THIS SOFTWARE. + */ +#ifndef _DRM_DP_MST_HELPER_H_ +#define _DRM_DP_MST_HELPER_H_ + +#include +#include +#include + +#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) +#include +#include + +enum drm_dp_mst_topology_ref_type { + DRM_DP_MST_TOPOLOGY_REF_GET, + DRM_DP_MST_TOPOLOGY_REF_PUT, +}; + +struct drm_dp_mst_topology_ref_history { + struct drm_dp_mst_topology_ref_entry { + enum drm_dp_mst_topology_ref_type type; + int count; + ktime_t ts_nsec; + depot_stack_handle_t backtrace; + } *entries; + int len; +}; +#endif /* IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) */ + +struct drm_dp_mst_branch; + +/** + * struct drm_dp_vcpi - Virtual Channel Payload Identifier + * @vcpi: Virtual channel ID. + * @pbn: Payload Bandwidth Number for this channel + * @aligned_pbn: PBN aligned with slot size + * @num_slots: number of slots for this PBN + */ +struct drm_dp_vcpi { + int vcpi; + int pbn; + int aligned_pbn; + int num_slots; +}; + +/** + * struct drm_dp_mst_port - MST port + * @port_num: port number + * @input: if this port is an input port. Protected by + * &drm_dp_mst_topology_mgr.base.lock. + * @mcs: message capability status - DP 1.2 spec. Protected by + * &drm_dp_mst_topology_mgr.base.lock. + * @ddps: DisplayPort Device Plug Status - DP 1.2. Protected by + * &drm_dp_mst_topology_mgr.base.lock. + * @pdt: Peer Device Type. Protected by + * &drm_dp_mst_topology_mgr.base.lock. + * @ldps: Legacy Device Plug Status. Protected by + * &drm_dp_mst_topology_mgr.base.lock. + * @dpcd_rev: DPCD revision of device on this port. Protected by + * &drm_dp_mst_topology_mgr.base.lock. + * @num_sdp_streams: Number of simultaneous streams. Protected by + * &drm_dp_mst_topology_mgr.base.lock. + * @num_sdp_stream_sinks: Number of stream sinks. Protected by + * &drm_dp_mst_topology_mgr.base.lock. + * @full_pbn: Max possible bandwidth for this port. Protected by + * &drm_dp_mst_topology_mgr.base.lock. + * @next: link to next port on this branch device + * @aux: i2c aux transport to talk to device connected to this port, protected + * by &drm_dp_mst_topology_mgr.base.lock. + * @parent: branch device parent of this port + * @vcpi: Virtual Channel Payload info for this port. + * @connector: DRM connector this port is connected to. Protected by + * &drm_dp_mst_topology_mgr.base.lock. + * @mgr: topology manager this port lives under. + * + * This structure represents an MST port endpoint on a device somewhere + * in the MST topology. + */ +struct drm_dp_mst_port { + /** + * @topology_kref: refcount for this port's lifetime in the topology, + * only the DP MST helpers should need to touch this + */ + struct kref topology_kref; + + /** + * @malloc_kref: refcount for the memory allocation containing this + * structure. See drm_dp_mst_get_port_malloc() and + * drm_dp_mst_put_port_malloc(). + */ + struct kref malloc_kref; + +#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) + /** + * @topology_ref_history: A history of each topology + * reference/dereference. See CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS. + */ + struct drm_dp_mst_topology_ref_history topology_ref_history; +#endif + + u8 port_num; + bool input; + bool mcs; + bool ddps; + u8 pdt; + bool ldps; + u8 dpcd_rev; + u8 num_sdp_streams; + u8 num_sdp_stream_sinks; + uint16_t full_pbn; + struct list_head next; + /** + * @mstb: the branch device connected to this port, if there is one. + * This should be considered protected for reading by + * &drm_dp_mst_topology_mgr.lock. There are two exceptions to this: + * &drm_dp_mst_topology_mgr.up_req_work and + * &drm_dp_mst_topology_mgr.work, which do not grab + * &drm_dp_mst_topology_mgr.lock during reads but are the only + * updaters of this list and are protected from writing concurrently + * by &drm_dp_mst_topology_mgr.probe_lock. + */ + struct drm_dp_mst_branch *mstb; + struct drm_dp_aux aux; /* i2c bus for this port? */ + struct drm_dp_mst_branch *parent; + + struct drm_dp_vcpi vcpi; + struct drm_connector *connector; + struct drm_dp_mst_topology_mgr *mgr; + + /** + * @cached_edid: for DP logical ports - make tiling work by ensuring + * that the EDID for all connectors is read immediately. + */ + struct edid *cached_edid; + /** + * @has_audio: Tracks whether the sink connector to this port is + * audio-capable. + */ + bool has_audio; + + /** + * @fec_capable: bool indicating if FEC can be supported up to that + * point in the MST topology. + */ + bool fec_capable; +}; + +/* sideband msg header - not bit struct */ +struct drm_dp_sideband_msg_hdr { + u8 lct; + u8 lcr; + u8 rad[8]; + bool broadcast; + bool path_msg; + u8 msg_len; + bool somt; + bool eomt; + bool seqno; +}; + +struct drm_dp_sideband_msg_rx { + u8 chunk[48]; + u8 msg[256]; + u8 curchunk_len; + u8 curchunk_idx; /* chunk we are parsing now */ + u8 curchunk_hdrlen; + u8 curlen; /* total length of the msg */ + bool have_somt; + bool have_eomt; + struct drm_dp_sideband_msg_hdr initial_hdr; +}; + +/** + * struct drm_dp_mst_branch - MST branch device. + * @rad: Relative Address to talk to this branch device. + * @lct: Link count total to talk to this branch device. + * @num_ports: number of ports on the branch. + * @port_parent: pointer to the port parent, NULL if toplevel. + * @mgr: topology manager for this branch device. + * @link_address_sent: if a link address message has been sent to this device yet. + * @guid: guid for DP 1.2 branch device. port under this branch can be + * identified by port #. + * + * This structure represents an MST branch device, there is one + * primary branch device at the root, along with any other branches connected + * to downstream port of parent branches. + */ +struct drm_dp_mst_branch { + /** + * @topology_kref: refcount for this branch device's lifetime in the + * topology, only the DP MST helpers should need to touch this + */ + struct kref topology_kref; + + /** + * @malloc_kref: refcount for the memory allocation containing this + * structure. See drm_dp_mst_get_mstb_malloc() and + * drm_dp_mst_put_mstb_malloc(). + */ + struct kref malloc_kref; + +#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) + /** + * @topology_ref_history: A history of each topology + * reference/dereference. See CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS. + */ + struct drm_dp_mst_topology_ref_history topology_ref_history; +#endif + + /** + * @destroy_next: linked-list entry used by + * drm_dp_delayed_destroy_work() + */ + struct list_head destroy_next; + + u8 rad[8]; + u8 lct; + int num_ports; + + /** + * @ports: the list of ports on this branch device. This should be + * considered protected for reading by &drm_dp_mst_topology_mgr.lock. + * There are two exceptions to this: + * &drm_dp_mst_topology_mgr.up_req_work and + * &drm_dp_mst_topology_mgr.work, which do not grab + * &drm_dp_mst_topology_mgr.lock during reads but are the only + * updaters of this list and are protected from updating the list + * concurrently by @drm_dp_mst_topology_mgr.probe_lock + */ + struct list_head ports; + + struct drm_dp_mst_port *port_parent; + struct drm_dp_mst_topology_mgr *mgr; + + bool link_address_sent; + + /* global unique identifier to identify branch devices */ + u8 guid[16]; +}; + + +struct drm_dp_nak_reply { + u8 guid[16]; + u8 reason; + u8 nak_data; +}; + +struct drm_dp_link_address_ack_reply { + u8 guid[16]; + u8 nports; + struct drm_dp_link_addr_reply_port { + bool input_port; + u8 peer_device_type; + u8 port_number; + bool mcs; + bool ddps; + bool legacy_device_plug_status; + u8 dpcd_revision; + u8 peer_guid[16]; + u8 num_sdp_streams; + u8 num_sdp_stream_sinks; + } ports[16]; +}; + +struct drm_dp_remote_dpcd_read_ack_reply { + u8 port_number; + u8 num_bytes; + u8 bytes[255]; +}; + +struct drm_dp_remote_dpcd_write_ack_reply { + u8 port_number; +}; + +struct drm_dp_remote_dpcd_write_nak_reply { + u8 port_number; + u8 reason; + u8 bytes_written_before_failure; +}; + +struct drm_dp_remote_i2c_read_ack_reply { + u8 port_number; + u8 num_bytes; + u8 bytes[255]; +}; + +struct drm_dp_remote_i2c_read_nak_reply { + u8 port_number; + u8 nak_reason; + u8 i2c_nak_transaction; +}; + +struct drm_dp_remote_i2c_write_ack_reply { + u8 port_number; +}; + +struct drm_dp_query_stream_enc_status_ack_reply { + /* Bit[23:16]- Stream Id */ + u8 stream_id; + + /* Bit[15]- Signed */ + bool reply_signed; + + /* Bit[10:8]- Stream Output Sink Type */ + bool unauthorizable_device_present; + bool legacy_device_present; + bool query_capable_device_present; + + /* Bit[12:11]- Stream Output CP Type */ + bool hdcp_1x_device_present; + bool hdcp_2x_device_present; + + /* Bit[4]- Stream Authentication */ + bool auth_completed; + + /* Bit[3]- Stream Encryption */ + bool encryption_enabled; + + /* Bit[2]- Stream Repeater Function Present */ + bool repeater_present; + + /* Bit[1:0]- Stream State */ + u8 state; +}; + +#define DRM_DP_MAX_SDP_STREAMS 16 +struct drm_dp_allocate_payload { + u8 port_number; + u8 number_sdp_streams; + u8 vcpi; + u16 pbn; + u8 sdp_stream_sink[DRM_DP_MAX_SDP_STREAMS]; +}; + +struct drm_dp_allocate_payload_ack_reply { + u8 port_number; + u8 vcpi; + u16 allocated_pbn; +}; + +struct drm_dp_connection_status_notify { + u8 guid[16]; + u8 port_number; + bool legacy_device_plug_status; + bool displayport_device_plug_status; + bool message_capability_status; + bool input_port; + u8 peer_device_type; +}; + +struct drm_dp_remote_dpcd_read { + u8 port_number; + u32 dpcd_address; + u8 num_bytes; +}; + +struct drm_dp_remote_dpcd_write { + u8 port_number; + u32 dpcd_address; + u8 num_bytes; + u8 *bytes; +}; + +#define DP_REMOTE_I2C_READ_MAX_TRANSACTIONS 4 +struct drm_dp_remote_i2c_read { + u8 num_transactions; + u8 port_number; + struct drm_dp_remote_i2c_read_tx { + u8 i2c_dev_id; + u8 num_bytes; + u8 *bytes; + u8 no_stop_bit; + u8 i2c_transaction_delay; + } transactions[DP_REMOTE_I2C_READ_MAX_TRANSACTIONS]; + u8 read_i2c_device_id; + u8 num_bytes_read; +}; + +struct drm_dp_remote_i2c_write { + u8 port_number; + u8 write_i2c_device_id; + u8 num_bytes; + u8 *bytes; +}; + +struct drm_dp_query_stream_enc_status { + u8 stream_id; + u8 client_id[7]; /* 56-bit nonce */ + u8 stream_event; + bool valid_stream_event; + u8 stream_behavior; + u8 valid_stream_behavior; +}; + +/* this covers ENUM_RESOURCES, POWER_DOWN_PHY, POWER_UP_PHY */ +struct drm_dp_port_number_req { + u8 port_number; +}; + +struct drm_dp_enum_path_resources_ack_reply { + u8 port_number; + bool fec_capable; + u16 full_payload_bw_number; + u16 avail_payload_bw_number; +}; + +/* covers POWER_DOWN_PHY, POWER_UP_PHY */ +struct drm_dp_port_number_rep { + u8 port_number; +}; + +struct drm_dp_query_payload { + u8 port_number; + u8 vcpi; +}; + +struct drm_dp_resource_status_notify { + u8 port_number; + u8 guid[16]; + u16 available_pbn; +}; + +struct drm_dp_query_payload_ack_reply { + u8 port_number; + u16 allocated_pbn; +}; + +struct drm_dp_sideband_msg_req_body { + u8 req_type; + union ack_req { + struct drm_dp_connection_status_notify conn_stat; + struct drm_dp_port_number_req port_num; + struct drm_dp_resource_status_notify resource_stat; + + struct drm_dp_query_payload query_payload; + struct drm_dp_allocate_payload allocate_payload; + + struct drm_dp_remote_dpcd_read dpcd_read; + struct drm_dp_remote_dpcd_write dpcd_write; + + struct drm_dp_remote_i2c_read i2c_read; + struct drm_dp_remote_i2c_write i2c_write; + + struct drm_dp_query_stream_enc_status enc_status; + } u; +}; + +struct drm_dp_sideband_msg_reply_body { + u8 reply_type; + u8 req_type; + union ack_replies { + struct drm_dp_nak_reply nak; + struct drm_dp_link_address_ack_reply link_addr; + struct drm_dp_port_number_rep port_number; + + struct drm_dp_enum_path_resources_ack_reply path_resources; + struct drm_dp_allocate_payload_ack_reply allocate_payload; + struct drm_dp_query_payload_ack_reply query_payload; + + struct drm_dp_remote_dpcd_read_ack_reply remote_dpcd_read_ack; + struct drm_dp_remote_dpcd_write_ack_reply remote_dpcd_write_ack; + struct drm_dp_remote_dpcd_write_nak_reply remote_dpcd_write_nack; + + struct drm_dp_remote_i2c_read_ack_reply remote_i2c_read_ack; + struct drm_dp_remote_i2c_read_nak_reply remote_i2c_read_nack; + struct drm_dp_remote_i2c_write_ack_reply remote_i2c_write_ack; + + struct drm_dp_query_stream_enc_status_ack_reply enc_status; + } u; +}; + +/* msg is queued to be put into a slot */ +#define DRM_DP_SIDEBAND_TX_QUEUED 0 +/* msg has started transmitting on a slot - still on msgq */ +#define DRM_DP_SIDEBAND_TX_START_SEND 1 +/* msg has finished transmitting on a slot - removed from msgq only in slot */ +#define DRM_DP_SIDEBAND_TX_SENT 2 +/* msg has received a response - removed from slot */ +#define DRM_DP_SIDEBAND_TX_RX 3 +#define DRM_DP_SIDEBAND_TX_TIMEOUT 4 + +struct drm_dp_sideband_msg_tx { + u8 msg[256]; + u8 chunk[48]; + u8 cur_offset; + u8 cur_len; + struct drm_dp_mst_branch *dst; + struct list_head next; + int seqno; + int state; + bool path_msg; + struct drm_dp_sideband_msg_reply_body reply; +}; + +/* sideband msg handler */ +struct drm_dp_mst_topology_mgr; +struct drm_dp_mst_topology_cbs { + /* create a connector for a port */ + struct drm_connector *(*add_connector)(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port, const char *path); + /* + * Checks for any pending MST interrupts, passing them to MST core for + * processing, the same way an HPD IRQ pulse handler would do this. + * If provided MST core calls this callback from a poll-waiting loop + * when waiting for MST down message replies. The driver is expected + * to guard against a race between this callback and the driver's HPD + * IRQ pulse handler. + */ + void (*poll_hpd_irq)(struct drm_dp_mst_topology_mgr *mgr); +}; + +#define DP_MAX_PAYLOAD (sizeof(unsigned long) * 8) + +#define DP_PAYLOAD_LOCAL 1 +#define DP_PAYLOAD_REMOTE 2 +#define DP_PAYLOAD_DELETE_LOCAL 3 + +struct drm_dp_payload { + int payload_state; + int start_slot; + int num_slots; + int vcpi; +}; + +#define to_dp_mst_topology_state(x) container_of(x, struct drm_dp_mst_topology_state, base) + +struct drm_dp_vcpi_allocation { + struct drm_dp_mst_port *port; + int vcpi; + int pbn; + bool dsc_enabled; + struct list_head next; +}; + +struct drm_dp_mst_topology_state { + struct drm_private_state base; + struct list_head vcpis; + struct drm_dp_mst_topology_mgr *mgr; + u8 total_avail_slots; + u8 start_slot; +}; + +#define to_dp_mst_topology_mgr(x) container_of(x, struct drm_dp_mst_topology_mgr, base) + +/** + * struct drm_dp_mst_topology_mgr - DisplayPort MST manager + * + * This struct represents the toplevel displayport MST topology manager. + * There should be one instance of this for every MST capable DP connector + * on the GPU. + */ +struct drm_dp_mst_topology_mgr { + /** + * @base: Base private object for atomic + */ + struct drm_private_obj base; + + /** + * @dev: device pointer for adding i2c devices etc. + */ + struct drm_device *dev; + /** + * @cbs: callbacks for connector addition and destruction. + */ + const struct drm_dp_mst_topology_cbs *cbs; + /** + * @max_dpcd_transaction_bytes: maximum number of bytes to read/write + * in one go. + */ + int max_dpcd_transaction_bytes; + /** + * @aux: AUX channel for the DP MST connector this topolgy mgr is + * controlling. + */ + struct drm_dp_aux *aux; + /** + * @max_payloads: maximum number of payloads the GPU can generate. + */ + int max_payloads; + /** + * @max_lane_count: maximum number of lanes the GPU can drive. + */ + int max_lane_count; + /** + * @max_link_rate: maximum link rate per lane GPU can output, in kHz. + */ + int max_link_rate; + /** + * @conn_base_id: DRM connector ID this mgr is connected to. Only used + * to build the MST connector path value. + */ + int conn_base_id; + + /** + * @up_req_recv: Message receiver state for up requests. + */ + struct drm_dp_sideband_msg_rx up_req_recv; + + /** + * @down_rep_recv: Message receiver state for replies to down + * requests. + */ + struct drm_dp_sideband_msg_rx down_rep_recv; + + /** + * @lock: protects @mst_state, @mst_primary, @dpcd, and + * @payload_id_table_cleared. + */ + struct mutex lock; + + /** + * @probe_lock: Prevents @work and @up_req_work, the only writers of + * &drm_dp_mst_port.mstb and &drm_dp_mst_branch.ports, from racing + * while they update the topology. + */ + struct mutex probe_lock; + + /** + * @mst_state: If this manager is enabled for an MST capable port. False + * if no MST sink/branch devices is connected. + */ + bool mst_state : 1; + + /** + * @payload_id_table_cleared: Whether or not we've cleared the payload + * ID table for @mst_primary. Protected by @lock. + */ + bool payload_id_table_cleared : 1; + + /** + * @mst_primary: Pointer to the primary/first branch device. + */ + struct drm_dp_mst_branch *mst_primary; + + /** + * @dpcd: Cache of DPCD for primary port. + */ + u8 dpcd[DP_RECEIVER_CAP_SIZE]; + /** + * @sink_count: Sink count from DEVICE_SERVICE_IRQ_VECTOR_ESI0. + */ + u8 sink_count; + /** + * @pbn_div: PBN to slots divisor. + */ + int pbn_div; + + /** + * @funcs: Atomic helper callbacks + */ + const struct drm_private_state_funcs *funcs; + + /** + * @qlock: protects @tx_msg_downq and &drm_dp_sideband_msg_tx.state + */ + struct mutex qlock; + + /** + * @tx_msg_downq: List of pending down requests + */ + struct list_head tx_msg_downq; + + /** + * @payload_lock: Protect payload information. + */ + struct mutex payload_lock; + /** + * @proposed_vcpis: Array of pointers for the new VCPI allocation. The + * VCPI structure itself is &drm_dp_mst_port.vcpi, and the size of + * this array is determined by @max_payloads. + */ + struct drm_dp_vcpi **proposed_vcpis; + /** + * @payloads: Array of payloads. The size of this array is determined + * by @max_payloads. + */ + struct drm_dp_payload *payloads; + /** + * @payload_mask: Elements of @payloads actually in use. Since + * reallocation of active outputs isn't possible gaps can be created by + * disabling outputs out of order compared to how they've been enabled. + */ + unsigned long payload_mask; + /** + * @vcpi_mask: Similar to @payload_mask, but for @proposed_vcpis. + */ + unsigned long vcpi_mask; + + /** + * @tx_waitq: Wait to queue stall for the tx worker. + */ + wait_queue_head_t tx_waitq; + /** + * @work: Probe work. + */ + struct work_struct work; + /** + * @tx_work: Sideband transmit worker. This can nest within the main + * @work worker for each transaction @work launches. + */ + struct work_struct tx_work; + + /** + * @destroy_port_list: List of to be destroyed connectors. + */ + struct list_head destroy_port_list; + /** + * @destroy_branch_device_list: List of to be destroyed branch + * devices. + */ + struct list_head destroy_branch_device_list; + /** + * @delayed_destroy_lock: Protects @destroy_port_list and + * @destroy_branch_device_list. + */ + struct mutex delayed_destroy_lock; + + /** + * @delayed_destroy_wq: Workqueue used for delayed_destroy_work items. + * A dedicated WQ makes it possible to drain any requeued work items + * on it. + */ + struct workqueue_struct *delayed_destroy_wq; + + /** + * @delayed_destroy_work: Work item to destroy MST port and branch + * devices, needed to avoid locking inversion. + */ + struct work_struct delayed_destroy_work; + + /** + * @up_req_list: List of pending up requests from the topology that + * need to be processed, in chronological order. + */ + struct list_head up_req_list; + /** + * @up_req_lock: Protects @up_req_list + */ + struct mutex up_req_lock; + /** + * @up_req_work: Work item to process up requests received from the + * topology. Needed to avoid blocking hotplug handling and sideband + * transmissions. + */ + struct work_struct up_req_work; + +#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) + /** + * @topology_ref_history_lock: protects + * &drm_dp_mst_port.topology_ref_history and + * &drm_dp_mst_branch.topology_ref_history. + */ + struct mutex topology_ref_history_lock; +#endif +}; + +int drm_dp_mst_topology_mgr_init(struct drm_dp_mst_topology_mgr *mgr, + struct drm_device *dev, struct drm_dp_aux *aux, + int max_dpcd_transaction_bytes, + int max_payloads, + int max_lane_count, int max_link_rate, + int conn_base_id); + +void drm_dp_mst_topology_mgr_destroy(struct drm_dp_mst_topology_mgr *mgr); + +bool drm_dp_read_mst_cap(struct drm_dp_aux *aux, const u8 dpcd[DP_RECEIVER_CAP_SIZE]); +int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool mst_state); + +int drm_dp_mst_hpd_irq(struct drm_dp_mst_topology_mgr *mgr, u8 *esi, bool *handled); + + +int +drm_dp_mst_detect_port(struct drm_connector *connector, + struct drm_modeset_acquire_ctx *ctx, + struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_port *port); + +struct edid *drm_dp_mst_get_edid(struct drm_connector *connector, struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port); + +int drm_dp_get_vc_payload_bw(const struct drm_dp_mst_topology_mgr *mgr, + int link_rate, int link_lane_count); + +int drm_dp_calc_pbn_mode(int clock, int bpp, bool dsc); + +bool drm_dp_mst_allocate_vcpi(struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_port *port, int pbn, int slots); + +int drm_dp_mst_get_vcpi_slots(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port); + + +void drm_dp_mst_reset_vcpi_slots(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port); + +void drm_dp_mst_update_slots(struct drm_dp_mst_topology_state *mst_state, uint8_t link_encoding_cap); + +void drm_dp_mst_deallocate_vcpi(struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_port *port); + + +int drm_dp_find_vcpi_slots(struct drm_dp_mst_topology_mgr *mgr, + int pbn); + + +int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr, int start_slot); + + +int drm_dp_update_payload_part2(struct drm_dp_mst_topology_mgr *mgr); + +int drm_dp_check_act_status(struct drm_dp_mst_topology_mgr *mgr); + +void drm_dp_mst_dump_topology(struct seq_file *m, + struct drm_dp_mst_topology_mgr *mgr); + +void drm_dp_mst_topology_mgr_suspend(struct drm_dp_mst_topology_mgr *mgr); +int __must_check +drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr, + bool sync); + +ssize_t drm_dp_mst_dpcd_read(struct drm_dp_aux *aux, + unsigned int offset, void *buffer, size_t size); +ssize_t drm_dp_mst_dpcd_write(struct drm_dp_aux *aux, + unsigned int offset, void *buffer, size_t size); + +int drm_dp_mst_connector_late_register(struct drm_connector *connector, + struct drm_dp_mst_port *port); +void drm_dp_mst_connector_early_unregister(struct drm_connector *connector, + struct drm_dp_mst_port *port); + +struct drm_dp_mst_topology_state *drm_atomic_get_mst_topology_state(struct drm_atomic_state *state, + struct drm_dp_mst_topology_mgr *mgr); +int __must_check +drm_dp_atomic_find_vcpi_slots(struct drm_atomic_state *state, + struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_port *port, int pbn, + int pbn_div); +int drm_dp_mst_atomic_enable_dsc(struct drm_atomic_state *state, + struct drm_dp_mst_port *port, + int pbn, int pbn_div, + bool enable); +int __must_check +drm_dp_mst_add_affected_dsc_crtcs(struct drm_atomic_state *state, + struct drm_dp_mst_topology_mgr *mgr); +int __must_check +drm_dp_atomic_release_vcpi_slots(struct drm_atomic_state *state, + struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_port *port); +int drm_dp_send_power_updown_phy(struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_port *port, bool power_up); +int drm_dp_send_query_stream_enc_status(struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_port *port, + struct drm_dp_query_stream_enc_status_ack_reply *status); +int __must_check drm_dp_mst_atomic_check(struct drm_atomic_state *state); + +void drm_dp_mst_get_port_malloc(struct drm_dp_mst_port *port); +void drm_dp_mst_put_port_malloc(struct drm_dp_mst_port *port); + +struct drm_dp_aux *drm_dp_mst_dsc_aux_for_port(struct drm_dp_mst_port *port); + +extern const struct drm_private_state_funcs drm_dp_mst_topology_state_funcs; + +/** + * __drm_dp_mst_state_iter_get - private atomic state iterator function for + * macro-internal use + * @state: &struct drm_atomic_state pointer + * @mgr: pointer to the &struct drm_dp_mst_topology_mgr iteration cursor + * @old_state: optional pointer to the old &struct drm_dp_mst_topology_state + * iteration cursor + * @new_state: optional pointer to the new &struct drm_dp_mst_topology_state + * iteration cursor + * @i: int iteration cursor, for macro-internal use + * + * Used by for_each_oldnew_mst_mgr_in_state(), + * for_each_old_mst_mgr_in_state(), and for_each_new_mst_mgr_in_state(). Don't + * call this directly. + * + * Returns: + * True if the current &struct drm_private_obj is a &struct + * drm_dp_mst_topology_mgr, false otherwise. + */ +static inline bool +__drm_dp_mst_state_iter_get(struct drm_atomic_state *state, + struct drm_dp_mst_topology_mgr **mgr, + struct drm_dp_mst_topology_state **old_state, + struct drm_dp_mst_topology_state **new_state, + int i) +{ + struct __drm_private_objs_state *objs_state = &state->private_objs[i]; + + if (objs_state->ptr->funcs != &drm_dp_mst_topology_state_funcs) + return false; + + *mgr = to_dp_mst_topology_mgr(objs_state->ptr); + if (old_state) + *old_state = to_dp_mst_topology_state(objs_state->old_state); + if (new_state) + *new_state = to_dp_mst_topology_state(objs_state->new_state); + + return true; +} + +/** + * for_each_oldnew_mst_mgr_in_state - iterate over all DP MST topology + * managers in an atomic update + * @__state: &struct drm_atomic_state pointer + * @mgr: &struct drm_dp_mst_topology_mgr iteration cursor + * @old_state: &struct drm_dp_mst_topology_state iteration cursor for the old + * state + * @new_state: &struct drm_dp_mst_topology_state iteration cursor for the new + * state + * @__i: int iteration cursor, for macro-internal use + * + * This iterates over all DRM DP MST topology managers in an atomic update, + * tracking both old and new state. This is useful in places where the state + * delta needs to be considered, for example in atomic check functions. + */ +#define for_each_oldnew_mst_mgr_in_state(__state, mgr, old_state, new_state, __i) \ + for ((__i) = 0; (__i) < (__state)->num_private_objs; (__i)++) \ + for_each_if(__drm_dp_mst_state_iter_get((__state), &(mgr), &(old_state), &(new_state), (__i))) + +/** + * for_each_old_mst_mgr_in_state - iterate over all DP MST topology managers + * in an atomic update + * @__state: &struct drm_atomic_state pointer + * @mgr: &struct drm_dp_mst_topology_mgr iteration cursor + * @old_state: &struct drm_dp_mst_topology_state iteration cursor for the old + * state + * @__i: int iteration cursor, for macro-internal use + * + * This iterates over all DRM DP MST topology managers in an atomic update, + * tracking only the old state. This is useful in disable functions, where we + * need the old state the hardware is still in. + */ +#define for_each_old_mst_mgr_in_state(__state, mgr, old_state, __i) \ + for ((__i) = 0; (__i) < (__state)->num_private_objs; (__i)++) \ + for_each_if(__drm_dp_mst_state_iter_get((__state), &(mgr), &(old_state), NULL, (__i))) + +/** + * for_each_new_mst_mgr_in_state - iterate over all DP MST topology managers + * in an atomic update + * @__state: &struct drm_atomic_state pointer + * @mgr: &struct drm_dp_mst_topology_mgr iteration cursor + * @new_state: &struct drm_dp_mst_topology_state iteration cursor for the new + * state + * @__i: int iteration cursor, for macro-internal use + * + * This iterates over all DRM DP MST topology managers in an atomic update, + * tracking only the new state. This is useful in enable functions, where we + * need the new state the hardware should be in when the atomic commit + * operation has completed. + */ +#define for_each_new_mst_mgr_in_state(__state, mgr, new_state, __i) \ + for ((__i) = 0; (__i) < (__state)->num_private_objs; (__i)++) \ + for_each_if(__drm_dp_mst_state_iter_get((__state), &(mgr), NULL, &(new_state), (__i))) + +#endif diff --git a/include/drm/drm_dp_dual_mode_helper.h b/include/drm/drm_dp_dual_mode_helper.h deleted file mode 100644 index 7ee482265087..000000000000 --- a/include/drm/drm_dp_dual_mode_helper.h +++ /dev/null @@ -1,121 +0,0 @@ -/* - * Copyright © 2016 Intel Corporation - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - */ - -#ifndef DRM_DP_DUAL_MODE_HELPER_H -#define DRM_DP_DUAL_MODE_HELPER_H - -#include - -/* - * Optional for type 1 DVI adaptors - * Mandatory for type 1 HDMI and type 2 adaptors - */ -#define DP_DUAL_MODE_HDMI_ID 0x00 /* 00-0f */ -#define DP_DUAL_MODE_HDMI_ID_LEN 16 -/* - * Optional for type 1 adaptors - * Mandatory for type 2 adaptors - */ -#define DP_DUAL_MODE_ADAPTOR_ID 0x10 -#define DP_DUAL_MODE_REV_MASK 0x07 -#define DP_DUAL_MODE_REV_TYPE2 0x00 -#define DP_DUAL_MODE_TYPE_MASK 0xf0 -#define DP_DUAL_MODE_TYPE_TYPE2 0xa0 -/* This field is marked reserved in dual mode spec, used in LSPCON */ -#define DP_DUAL_MODE_TYPE_HAS_DPCD 0x08 -#define DP_DUAL_MODE_IEEE_OUI 0x11 /* 11-13*/ -#define DP_DUAL_IEEE_OUI_LEN 3 -#define DP_DUAL_DEVICE_ID 0x14 /* 14-19 */ -#define DP_DUAL_DEVICE_ID_LEN 6 -#define DP_DUAL_MODE_HARDWARE_REV 0x1a -#define DP_DUAL_MODE_FIRMWARE_MAJOR_REV 0x1b -#define DP_DUAL_MODE_FIRMWARE_MINOR_REV 0x1c -#define DP_DUAL_MODE_MAX_TMDS_CLOCK 0x1d -#define DP_DUAL_MODE_I2C_SPEED_CAP 0x1e -#define DP_DUAL_MODE_TMDS_OEN 0x20 -#define DP_DUAL_MODE_TMDS_DISABLE 0x01 -#define DP_DUAL_MODE_HDMI_PIN_CTRL 0x21 -#define DP_DUAL_MODE_CEC_ENABLE 0x01 -#define DP_DUAL_MODE_I2C_SPEED_CTRL 0x22 - -/* LSPCON specific registers, defined by MCA */ -#define DP_DUAL_MODE_LSPCON_MODE_CHANGE 0x40 -#define DP_DUAL_MODE_LSPCON_CURRENT_MODE 0x41 -#define DP_DUAL_MODE_LSPCON_MODE_PCON 0x1 - -struct drm_device; -struct i2c_adapter; - -ssize_t drm_dp_dual_mode_read(struct i2c_adapter *adapter, - u8 offset, void *buffer, size_t size); -ssize_t drm_dp_dual_mode_write(struct i2c_adapter *adapter, - u8 offset, const void *buffer, size_t size); - -/** - * enum drm_lspcon_mode - * @DRM_LSPCON_MODE_INVALID: No LSPCON. - * @DRM_LSPCON_MODE_LS: Level shifter mode of LSPCON - * which drives DP++ to HDMI 1.4 conversion. - * @DRM_LSPCON_MODE_PCON: Protocol converter mode of LSPCON - * which drives DP++ to HDMI 2.0 active conversion. - */ -enum drm_lspcon_mode { - DRM_LSPCON_MODE_INVALID, - DRM_LSPCON_MODE_LS, - DRM_LSPCON_MODE_PCON, -}; - -/** - * enum drm_dp_dual_mode_type - Type of the DP dual mode adaptor - * @DRM_DP_DUAL_MODE_NONE: No DP dual mode adaptor - * @DRM_DP_DUAL_MODE_UNKNOWN: Could be either none or type 1 DVI adaptor - * @DRM_DP_DUAL_MODE_TYPE1_DVI: Type 1 DVI adaptor - * @DRM_DP_DUAL_MODE_TYPE1_HDMI: Type 1 HDMI adaptor - * @DRM_DP_DUAL_MODE_TYPE2_DVI: Type 2 DVI adaptor - * @DRM_DP_DUAL_MODE_TYPE2_HDMI: Type 2 HDMI adaptor - * @DRM_DP_DUAL_MODE_LSPCON: Level shifter / protocol converter - */ -enum drm_dp_dual_mode_type { - DRM_DP_DUAL_MODE_NONE, - DRM_DP_DUAL_MODE_UNKNOWN, - DRM_DP_DUAL_MODE_TYPE1_DVI, - DRM_DP_DUAL_MODE_TYPE1_HDMI, - DRM_DP_DUAL_MODE_TYPE2_DVI, - DRM_DP_DUAL_MODE_TYPE2_HDMI, - DRM_DP_DUAL_MODE_LSPCON, -}; - -enum drm_dp_dual_mode_type -drm_dp_dual_mode_detect(const struct drm_device *dev, struct i2c_adapter *adapter); -int drm_dp_dual_mode_max_tmds_clock(const struct drm_device *dev, enum drm_dp_dual_mode_type type, - struct i2c_adapter *adapter); -int drm_dp_dual_mode_get_tmds_output(const struct drm_device *dev, enum drm_dp_dual_mode_type type, - struct i2c_adapter *adapter, bool *enabled); -int drm_dp_dual_mode_set_tmds_output(const struct drm_device *dev, enum drm_dp_dual_mode_type type, - struct i2c_adapter *adapter, bool enable); -const char *drm_dp_get_dual_mode_type_name(enum drm_dp_dual_mode_type type); - -int drm_lspcon_get_mode(const struct drm_device *dev, struct i2c_adapter *adapter, - enum drm_lspcon_mode *current_mode); -int drm_lspcon_set_mode(const struct drm_device *dev, struct i2c_adapter *adapter, - enum drm_lspcon_mode reqd_mode); -#endif diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h deleted file mode 100644 index 16d6da3a129f..000000000000 --- a/include/drm/drm_dp_helper.h +++ /dev/null @@ -1,2358 +0,0 @@ -/* - * Copyright © 2008 Keith Packard - * - * Permission to use, copy, modify, distribute, and sell this software and its - * documentation for any purpose is hereby granted without fee, provided that - * the above copyright notice appear in all copies and that both that copyright - * notice and this permission notice appear in supporting documentation, and - * that the name of the copyright holders not be used in advertising or - * publicity pertaining to distribution of the software without specific, - * written prior permission. The copyright holders make no representations - * about the suitability of this software for any purpose. It is provided "as - * is" without express or implied warranty. - * - * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, - * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO - * EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT OR - * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, - * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER - * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE - * OF THIS SOFTWARE. - */ - -#ifndef _DRM_DP_HELPER_H_ -#define _DRM_DP_HELPER_H_ - -#include -#include -#include -#include - -struct drm_device; -struct drm_dp_aux; -struct drm_panel; - -/* - * Unless otherwise noted, all values are from the DP 1.1a spec. Note that - * DP and DPCD versions are independent. Differences from 1.0 are not noted, - * 1.0 devices basically don't exist in the wild. - * - * Abbreviations, in chronological order: - * - * eDP: Embedded DisplayPort version 1 - * DPI: DisplayPort Interoperability Guideline v1.1a - * 1.2: DisplayPort 1.2 - * MST: Multistream Transport - part of DP 1.2a - * - * 1.2 formally includes both eDP and DPI definitions. - */ - -/* MSA (Main Stream Attribute) MISC bits (as MISC1<<8|MISC0) */ -#define DP_MSA_MISC_SYNC_CLOCK (1 << 0) -#define DP_MSA_MISC_INTERLACE_VTOTAL_EVEN (1 << 8) -#define DP_MSA_MISC_STEREO_NO_3D (0 << 9) -#define DP_MSA_MISC_STEREO_PROG_RIGHT_EYE (1 << 9) -#define DP_MSA_MISC_STEREO_PROG_LEFT_EYE (3 << 9) -/* bits per component for non-RAW */ -#define DP_MSA_MISC_6_BPC (0 << 5) -#define DP_MSA_MISC_8_BPC (1 << 5) -#define DP_MSA_MISC_10_BPC (2 << 5) -#define DP_MSA_MISC_12_BPC (3 << 5) -#define DP_MSA_MISC_16_BPC (4 << 5) -/* bits per component for RAW */ -#define DP_MSA_MISC_RAW_6_BPC (1 << 5) -#define DP_MSA_MISC_RAW_7_BPC (2 << 5) -#define DP_MSA_MISC_RAW_8_BPC (3 << 5) -#define DP_MSA_MISC_RAW_10_BPC (4 << 5) -#define DP_MSA_MISC_RAW_12_BPC (5 << 5) -#define DP_MSA_MISC_RAW_14_BPC (6 << 5) -#define DP_MSA_MISC_RAW_16_BPC (7 << 5) -/* pixel encoding/colorimetry format */ -#define _DP_MSA_MISC_COLOR(misc1_7, misc0_21, misc0_3, misc0_4) \ - ((misc1_7) << 15 | (misc0_4) << 4 | (misc0_3) << 3 | ((misc0_21) << 1)) -#define DP_MSA_MISC_COLOR_RGB _DP_MSA_MISC_COLOR(0, 0, 0, 0) -#define DP_MSA_MISC_COLOR_CEA_RGB _DP_MSA_MISC_COLOR(0, 0, 1, 0) -#define DP_MSA_MISC_COLOR_RGB_WIDE_FIXED _DP_MSA_MISC_COLOR(0, 3, 0, 0) -#define DP_MSA_MISC_COLOR_RGB_WIDE_FLOAT _DP_MSA_MISC_COLOR(0, 3, 0, 1) -#define DP_MSA_MISC_COLOR_Y_ONLY _DP_MSA_MISC_COLOR(1, 0, 0, 0) -#define DP_MSA_MISC_COLOR_RAW _DP_MSA_MISC_COLOR(1, 1, 0, 0) -#define DP_MSA_MISC_COLOR_YCBCR_422_BT601 _DP_MSA_MISC_COLOR(0, 1, 1, 0) -#define DP_MSA_MISC_COLOR_YCBCR_422_BT709 _DP_MSA_MISC_COLOR(0, 1, 1, 1) -#define DP_MSA_MISC_COLOR_YCBCR_444_BT601 _DP_MSA_MISC_COLOR(0, 2, 1, 0) -#define DP_MSA_MISC_COLOR_YCBCR_444_BT709 _DP_MSA_MISC_COLOR(0, 2, 1, 1) -#define DP_MSA_MISC_COLOR_XVYCC_422_BT601 _DP_MSA_MISC_COLOR(0, 1, 0, 0) -#define DP_MSA_MISC_COLOR_XVYCC_422_BT709 _DP_MSA_MISC_COLOR(0, 1, 0, 1) -#define DP_MSA_MISC_COLOR_XVYCC_444_BT601 _DP_MSA_MISC_COLOR(0, 2, 0, 0) -#define DP_MSA_MISC_COLOR_XVYCC_444_BT709 _DP_MSA_MISC_COLOR(0, 2, 0, 1) -#define DP_MSA_MISC_COLOR_OPRGB _DP_MSA_MISC_COLOR(0, 0, 1, 1) -#define DP_MSA_MISC_COLOR_DCI_P3 _DP_MSA_MISC_COLOR(0, 3, 1, 0) -#define DP_MSA_MISC_COLOR_COLOR_PROFILE _DP_MSA_MISC_COLOR(0, 3, 1, 1) -#define DP_MSA_MISC_COLOR_VSC_SDP (1 << 14) - -#define DP_AUX_MAX_PAYLOAD_BYTES 16 - -#define DP_AUX_I2C_WRITE 0x0 -#define DP_AUX_I2C_READ 0x1 -#define DP_AUX_I2C_WRITE_STATUS_UPDATE 0x2 -#define DP_AUX_I2C_MOT 0x4 -#define DP_AUX_NATIVE_WRITE 0x8 -#define DP_AUX_NATIVE_READ 0x9 - -#define DP_AUX_NATIVE_REPLY_ACK (0x0 << 0) -#define DP_AUX_NATIVE_REPLY_NACK (0x1 << 0) -#define DP_AUX_NATIVE_REPLY_DEFER (0x2 << 0) -#define DP_AUX_NATIVE_REPLY_MASK (0x3 << 0) - -#define DP_AUX_I2C_REPLY_ACK (0x0 << 2) -#define DP_AUX_I2C_REPLY_NACK (0x1 << 2) -#define DP_AUX_I2C_REPLY_DEFER (0x2 << 2) -#define DP_AUX_I2C_REPLY_MASK (0x3 << 2) - -/* DPCD Field Address Mapping */ - -/* Receiver Capability */ -#define DP_DPCD_REV 0x000 -# define DP_DPCD_REV_10 0x10 -# define DP_DPCD_REV_11 0x11 -# define DP_DPCD_REV_12 0x12 -# define DP_DPCD_REV_13 0x13 -# define DP_DPCD_REV_14 0x14 - -#define DP_MAX_LINK_RATE 0x001 - -#define DP_MAX_LANE_COUNT 0x002 -# define DP_MAX_LANE_COUNT_MASK 0x1f -# define DP_TPS3_SUPPORTED (1 << 6) /* 1.2 */ -# define DP_ENHANCED_FRAME_CAP (1 << 7) - -#define DP_MAX_DOWNSPREAD 0x003 -# define DP_MAX_DOWNSPREAD_0_5 (1 << 0) -# define DP_STREAM_REGENERATION_STATUS_CAP (1 << 1) /* 2.0 */ -# define DP_NO_AUX_HANDSHAKE_LINK_TRAINING (1 << 6) -# define DP_TPS4_SUPPORTED (1 << 7) - -#define DP_NORP 0x004 - -#define DP_DOWNSTREAMPORT_PRESENT 0x005 -# define DP_DWN_STRM_PORT_PRESENT (1 << 0) -# define DP_DWN_STRM_PORT_TYPE_MASK 0x06 -# define DP_DWN_STRM_PORT_TYPE_DP (0 << 1) -# define DP_DWN_STRM_PORT_TYPE_ANALOG (1 << 1) -# define DP_DWN_STRM_PORT_TYPE_TMDS (2 << 1) -# define DP_DWN_STRM_PORT_TYPE_OTHER (3 << 1) -# define DP_FORMAT_CONVERSION (1 << 3) -# define DP_DETAILED_CAP_INFO_AVAILABLE (1 << 4) /* DPI */ - -#define DP_MAIN_LINK_CHANNEL_CODING 0x006 -# define DP_CAP_ANSI_8B10B (1 << 0) -# define DP_CAP_ANSI_128B132B (1 << 1) /* 2.0 */ - -#define DP_DOWN_STREAM_PORT_COUNT 0x007 -# define DP_PORT_COUNT_MASK 0x0f -# define DP_MSA_TIMING_PAR_IGNORED (1 << 6) /* eDP */ -# define DP_OUI_SUPPORT (1 << 7) - -#define DP_RECEIVE_PORT_0_CAP_0 0x008 -# define DP_LOCAL_EDID_PRESENT (1 << 1) -# define DP_ASSOCIATED_TO_PRECEDING_PORT (1 << 2) - -#define DP_RECEIVE_PORT_0_BUFFER_SIZE 0x009 - -#define DP_RECEIVE_PORT_1_CAP_0 0x00a -#define DP_RECEIVE_PORT_1_BUFFER_SIZE 0x00b - -#define DP_I2C_SPEED_CAP 0x00c /* DPI */ -# define DP_I2C_SPEED_1K 0x01 -# define DP_I2C_SPEED_5K 0x02 -# define DP_I2C_SPEED_10K 0x04 -# define DP_I2C_SPEED_100K 0x08 -# define DP_I2C_SPEED_400K 0x10 -# define DP_I2C_SPEED_1M 0x20 - -#define DP_EDP_CONFIGURATION_CAP 0x00d /* XXX 1.2? */ -# define DP_ALTERNATE_SCRAMBLER_RESET_CAP (1 << 0) -# define DP_FRAMING_CHANGE_CAP (1 << 1) -# define DP_DPCD_DISPLAY_CONTROL_CAPABLE (1 << 3) /* edp v1.2 or higher */ - -#define DP_TRAINING_AUX_RD_INTERVAL 0x00e /* XXX 1.2? */ -# define DP_TRAINING_AUX_RD_MASK 0x7F /* DP 1.3 */ -# define DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT (1 << 7) /* DP 1.3 */ - -#define DP_ADAPTER_CAP 0x00f /* 1.2 */ -# define DP_FORCE_LOAD_SENSE_CAP (1 << 0) -# define DP_ALTERNATE_I2C_PATTERN_CAP (1 << 1) - -#define DP_SUPPORTED_LINK_RATES 0x010 /* eDP 1.4 */ -# define DP_MAX_SUPPORTED_RATES 8 /* 16-bit little-endian */ - -/* Multiple stream transport */ -#define DP_FAUX_CAP 0x020 /* 1.2 */ -# define DP_FAUX_CAP_1 (1 << 0) - -#define DP_SINK_VIDEO_FALLBACK_FORMATS 0x020 /* 2.0 */ -# define DP_FALLBACK_1024x768_60HZ_24BPP (1 << 0) -# define DP_FALLBACK_1280x720_60HZ_24BPP (1 << 1) -# define DP_FALLBACK_1920x1080_60HZ_24BPP (1 << 2) - -#define DP_MSTM_CAP 0x021 /* 1.2 */ -# define DP_MST_CAP (1 << 0) -# define DP_SINGLE_STREAM_SIDEBAND_MSG (1 << 1) /* 2.0 */ - -#define DP_NUMBER_OF_AUDIO_ENDPOINTS 0x022 /* 1.2 */ - -/* AV_SYNC_DATA_BLOCK 1.2 */ -#define DP_AV_GRANULARITY 0x023 -# define DP_AG_FACTOR_MASK (0xf << 0) -# define DP_AG_FACTOR_3MS (0 << 0) -# define DP_AG_FACTOR_2MS (1 << 0) -# define DP_AG_FACTOR_1MS (2 << 0) -# define DP_AG_FACTOR_500US (3 << 0) -# define DP_AG_FACTOR_200US (4 << 0) -# define DP_AG_FACTOR_100US (5 << 0) -# define DP_AG_FACTOR_10US (6 << 0) -# define DP_AG_FACTOR_1US (7 << 0) -# define DP_VG_FACTOR_MASK (0xf << 4) -# define DP_VG_FACTOR_3MS (0 << 4) -# define DP_VG_FACTOR_2MS (1 << 4) -# define DP_VG_FACTOR_1MS (2 << 4) -# define DP_VG_FACTOR_500US (3 << 4) -# define DP_VG_FACTOR_200US (4 << 4) -# define DP_VG_FACTOR_100US (5 << 4) - -#define DP_AUD_DEC_LAT0 0x024 -#define DP_AUD_DEC_LAT1 0x025 - -#define DP_AUD_PP_LAT0 0x026 -#define DP_AUD_PP_LAT1 0x027 - -#define DP_VID_INTER_LAT 0x028 - -#define DP_VID_PROG_LAT 0x029 - -#define DP_REP_LAT 0x02a - -#define DP_AUD_DEL_INS0 0x02b -#define DP_AUD_DEL_INS1 0x02c -#define DP_AUD_DEL_INS2 0x02d -/* End of AV_SYNC_DATA_BLOCK */ - -#define DP_RECEIVER_ALPM_CAP 0x02e /* eDP 1.4 */ -# define DP_ALPM_CAP (1 << 0) - -#define DP_SINK_DEVICE_AUX_FRAME_SYNC_CAP 0x02f /* eDP 1.4 */ -# define DP_AUX_FRAME_SYNC_CAP (1 << 0) - -#define DP_GUID 0x030 /* 1.2 */ - -#define DP_DSC_SUPPORT 0x060 /* DP 1.4 */ -# define DP_DSC_DECOMPRESSION_IS_SUPPORTED (1 << 0) - -#define DP_DSC_REV 0x061 -# define DP_DSC_MAJOR_MASK (0xf << 0) -# define DP_DSC_MINOR_MASK (0xf << 4) -# define DP_DSC_MAJOR_SHIFT 0 -# define DP_DSC_MINOR_SHIFT 4 - -#define DP_DSC_RC_BUF_BLK_SIZE 0x062 -# define DP_DSC_RC_BUF_BLK_SIZE_1 0x0 -# define DP_DSC_RC_BUF_BLK_SIZE_4 0x1 -# define DP_DSC_RC_BUF_BLK_SIZE_16 0x2 -# define DP_DSC_RC_BUF_BLK_SIZE_64 0x3 - -#define DP_DSC_RC_BUF_SIZE 0x063 - -#define DP_DSC_SLICE_CAP_1 0x064 -# define DP_DSC_1_PER_DP_DSC_SINK (1 << 0) -# define DP_DSC_2_PER_DP_DSC_SINK (1 << 1) -# define DP_DSC_4_PER_DP_DSC_SINK (1 << 3) -# define DP_DSC_6_PER_DP_DSC_SINK (1 << 4) -# define DP_DSC_8_PER_DP_DSC_SINK (1 << 5) -# define DP_DSC_10_PER_DP_DSC_SINK (1 << 6) -# define DP_DSC_12_PER_DP_DSC_SINK (1 << 7) - -#define DP_DSC_LINE_BUF_BIT_DEPTH 0x065 -# define DP_DSC_LINE_BUF_BIT_DEPTH_MASK (0xf << 0) -# define DP_DSC_LINE_BUF_BIT_DEPTH_9 0x0 -# define DP_DSC_LINE_BUF_BIT_DEPTH_10 0x1 -# define DP_DSC_LINE_BUF_BIT_DEPTH_11 0x2 -# define DP_DSC_LINE_BUF_BIT_DEPTH_12 0x3 -# define DP_DSC_LINE_BUF_BIT_DEPTH_13 0x4 -# define DP_DSC_LINE_BUF_BIT_DEPTH_14 0x5 -# define DP_DSC_LINE_BUF_BIT_DEPTH_15 0x6 -# define DP_DSC_LINE_BUF_BIT_DEPTH_16 0x7 -# define DP_DSC_LINE_BUF_BIT_DEPTH_8 0x8 - -#define DP_DSC_BLK_PREDICTION_SUPPORT 0x066 -# define DP_DSC_BLK_PREDICTION_IS_SUPPORTED (1 << 0) - -#define DP_DSC_MAX_BITS_PER_PIXEL_LOW 0x067 /* eDP 1.4 */ - -#define DP_DSC_MAX_BITS_PER_PIXEL_HI 0x068 /* eDP 1.4 */ -# define DP_DSC_MAX_BITS_PER_PIXEL_HI_MASK (0x3 << 0) -# define DP_DSC_MAX_BITS_PER_PIXEL_HI_SHIFT 8 - -#define DP_DSC_DEC_COLOR_FORMAT_CAP 0x069 -# define DP_DSC_RGB (1 << 0) -# define DP_DSC_YCbCr444 (1 << 1) -# define DP_DSC_YCbCr422_Simple (1 << 2) -# define DP_DSC_YCbCr422_Native (1 << 3) -# define DP_DSC_YCbCr420_Native (1 << 4) - -#define DP_DSC_DEC_COLOR_DEPTH_CAP 0x06A -# define DP_DSC_8_BPC (1 << 1) -# define DP_DSC_10_BPC (1 << 2) -# define DP_DSC_12_BPC (1 << 3) - -#define DP_DSC_PEAK_THROUGHPUT 0x06B -# define DP_DSC_THROUGHPUT_MODE_0_MASK (0xf << 0) -# define DP_DSC_THROUGHPUT_MODE_0_SHIFT 0 -# define DP_DSC_THROUGHPUT_MODE_0_UNSUPPORTED 0 -# define DP_DSC_THROUGHPUT_MODE_0_340 (1 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_400 (2 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_450 (3 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_500 (4 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_550 (5 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_600 (6 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_650 (7 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_700 (8 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_750 (9 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_800 (10 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_850 (11 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_900 (12 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_950 (13 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_1000 (14 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_170 (15 << 0) /* 1.4a */ -# define DP_DSC_THROUGHPUT_MODE_1_MASK (0xf << 4) -# define DP_DSC_THROUGHPUT_MODE_1_SHIFT 4 -# define DP_DSC_THROUGHPUT_MODE_1_UNSUPPORTED 0 -# define DP_DSC_THROUGHPUT_MODE_1_340 (1 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_400 (2 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_450 (3 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_500 (4 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_550 (5 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_600 (6 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_650 (7 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_700 (8 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_750 (9 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_800 (10 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_850 (11 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_900 (12 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_950 (13 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_1000 (14 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_170 (15 << 4) - -#define DP_DSC_MAX_SLICE_WIDTH 0x06C -#define DP_DSC_MIN_SLICE_WIDTH_VALUE 2560 -#define DP_DSC_SLICE_WIDTH_MULTIPLIER 320 - -#define DP_DSC_SLICE_CAP_2 0x06D -# define DP_DSC_16_PER_DP_DSC_SINK (1 << 0) -# define DP_DSC_20_PER_DP_DSC_SINK (1 << 1) -# define DP_DSC_24_PER_DP_DSC_SINK (1 << 2) - -#define DP_DSC_BITS_PER_PIXEL_INC 0x06F -# define DP_DSC_BITS_PER_PIXEL_1_16 0x0 -# define DP_DSC_BITS_PER_PIXEL_1_8 0x1 -# define DP_DSC_BITS_PER_PIXEL_1_4 0x2 -# define DP_DSC_BITS_PER_PIXEL_1_2 0x3 -# define DP_DSC_BITS_PER_PIXEL_1 0x4 - -#define DP_PSR_SUPPORT 0x070 /* XXX 1.2? */ -# define DP_PSR_IS_SUPPORTED 1 -# define DP_PSR2_IS_SUPPORTED 2 /* eDP 1.4 */ -# define DP_PSR2_WITH_Y_COORD_IS_SUPPORTED 3 /* eDP 1.4a */ - -#define DP_PSR_CAPS 0x071 /* XXX 1.2? */ -# define DP_PSR_NO_TRAIN_ON_EXIT 1 -# define DP_PSR_SETUP_TIME_330 (0 << 1) -# define DP_PSR_SETUP_TIME_275 (1 << 1) -# define DP_PSR_SETUP_TIME_220 (2 << 1) -# define DP_PSR_SETUP_TIME_165 (3 << 1) -# define DP_PSR_SETUP_TIME_110 (4 << 1) -# define DP_PSR_SETUP_TIME_55 (5 << 1) -# define DP_PSR_SETUP_TIME_0 (6 << 1) -# define DP_PSR_SETUP_TIME_MASK (7 << 1) -# define DP_PSR_SETUP_TIME_SHIFT 1 -# define DP_PSR2_SU_Y_COORDINATE_REQUIRED (1 << 4) /* eDP 1.4a */ -# define DP_PSR2_SU_GRANULARITY_REQUIRED (1 << 5) /* eDP 1.4b */ - -#define DP_PSR2_SU_X_GRANULARITY 0x072 /* eDP 1.4b */ -#define DP_PSR2_SU_Y_GRANULARITY 0x074 /* eDP 1.4b */ - -/* - * 0x80-0x8f describe downstream port capabilities, but there are two layouts - * based on whether DP_DETAILED_CAP_INFO_AVAILABLE was set. If it was not, - * each port's descriptor is one byte wide. If it was set, each port's is - * four bytes wide, starting with the one byte from the base info. As of - * DP interop v1.1a only VGA defines additional detail. - */ - -/* offset 0 */ -#define DP_DOWNSTREAM_PORT_0 0x80 -# define DP_DS_PORT_TYPE_MASK (7 << 0) -# define DP_DS_PORT_TYPE_DP 0 -# define DP_DS_PORT_TYPE_VGA 1 -# define DP_DS_PORT_TYPE_DVI 2 -# define DP_DS_PORT_TYPE_HDMI 3 -# define DP_DS_PORT_TYPE_NON_EDID 4 -# define DP_DS_PORT_TYPE_DP_DUALMODE 5 -# define DP_DS_PORT_TYPE_WIRELESS 6 -# define DP_DS_PORT_HPD (1 << 3) -# define DP_DS_NON_EDID_MASK (0xf << 4) -# define DP_DS_NON_EDID_720x480i_60 (1 << 4) -# define DP_DS_NON_EDID_720x480i_50 (2 << 4) -# define DP_DS_NON_EDID_1920x1080i_60 (3 << 4) -# define DP_DS_NON_EDID_1920x1080i_50 (4 << 4) -# define DP_DS_NON_EDID_1280x720_60 (5 << 4) -# define DP_DS_NON_EDID_1280x720_50 (7 << 4) -/* offset 1 for VGA is maximum megapixels per second / 8 */ -/* offset 1 for DVI/HDMI is maximum TMDS clock in Mbps / 2.5 */ -/* offset 2 for VGA/DVI/HDMI */ -# define DP_DS_MAX_BPC_MASK (3 << 0) -# define DP_DS_8BPC 0 -# define DP_DS_10BPC 1 -# define DP_DS_12BPC 2 -# define DP_DS_16BPC 3 -/* HDMI2.1 PCON FRL CONFIGURATION */ -# define DP_PCON_MAX_FRL_BW (7 << 2) -# define DP_PCON_MAX_0GBPS (0 << 2) -# define DP_PCON_MAX_9GBPS (1 << 2) -# define DP_PCON_MAX_18GBPS (2 << 2) -# define DP_PCON_MAX_24GBPS (3 << 2) -# define DP_PCON_MAX_32GBPS (4 << 2) -# define DP_PCON_MAX_40GBPS (5 << 2) -# define DP_PCON_MAX_48GBPS (6 << 2) -# define DP_PCON_SOURCE_CTL_MODE (1 << 5) - -/* offset 3 for DVI */ -# define DP_DS_DVI_DUAL_LINK (1 << 1) -# define DP_DS_DVI_HIGH_COLOR_DEPTH (1 << 2) -/* offset 3 for HDMI */ -# define DP_DS_HDMI_FRAME_SEQ_TO_FRAME_PACK (1 << 0) -# define DP_DS_HDMI_YCBCR422_PASS_THROUGH (1 << 1) -# define DP_DS_HDMI_YCBCR420_PASS_THROUGH (1 << 2) -# define DP_DS_HDMI_YCBCR444_TO_422_CONV (1 << 3) -# define DP_DS_HDMI_YCBCR444_TO_420_CONV (1 << 4) - -/* - * VESA DP-to-HDMI PCON Specification adds caps for colorspace - * conversion in DFP cap DPCD 83h. Sec6.1 Table-3. - * Based on the available support the source can enable - * color conversion by writing into PROTOCOL_COVERTER_CONTROL_2 - * DPCD 3052h. - */ -# define DP_DS_HDMI_BT601_RGB_YCBCR_CONV (1 << 5) -# define DP_DS_HDMI_BT709_RGB_YCBCR_CONV (1 << 6) -# define DP_DS_HDMI_BT2020_RGB_YCBCR_CONV (1 << 7) - -#define DP_MAX_DOWNSTREAM_PORTS 0x10 - -/* DP Forward error Correction Registers */ -#define DP_FEC_CAPABILITY 0x090 /* 1.4 */ -# define DP_FEC_CAPABLE (1 << 0) -# define DP_FEC_UNCORR_BLK_ERROR_COUNT_CAP (1 << 1) -# define DP_FEC_CORR_BLK_ERROR_COUNT_CAP (1 << 2) -# define DP_FEC_BIT_ERROR_COUNT_CAP (1 << 3) -#define DP_FEC_CAPABILITY_1 0x091 /* 2.0 */ - -/* DP-HDMI2.1 PCON DSC ENCODER SUPPORT */ -#define DP_PCON_DSC_ENCODER_CAP_SIZE 0xC /* 0x9E - 0x92 */ -#define DP_PCON_DSC_ENCODER 0x092 -# define DP_PCON_DSC_ENCODER_SUPPORTED (1 << 0) -# define DP_PCON_DSC_PPS_ENC_OVERRIDE (1 << 1) - -/* DP-HDMI2.1 PCON DSC Version */ -#define DP_PCON_DSC_VERSION 0x093 -# define DP_PCON_DSC_MAJOR_MASK (0xF << 0) -# define DP_PCON_DSC_MINOR_MASK (0xF << 4) -# define DP_PCON_DSC_MAJOR_SHIFT 0 -# define DP_PCON_DSC_MINOR_SHIFT 4 - -/* DP-HDMI2.1 PCON DSC RC Buffer block size */ -#define DP_PCON_DSC_RC_BUF_BLK_INFO 0x094 -# define DP_PCON_DSC_RC_BUF_BLK_SIZE (0x3 << 0) -# define DP_PCON_DSC_RC_BUF_BLK_1KB 0 -# define DP_PCON_DSC_RC_BUF_BLK_4KB 1 -# define DP_PCON_DSC_RC_BUF_BLK_16KB 2 -# define DP_PCON_DSC_RC_BUF_BLK_64KB 3 - -/* DP-HDMI2.1 PCON DSC RC Buffer size */ -#define DP_PCON_DSC_RC_BUF_SIZE 0x095 - -/* DP-HDMI2.1 PCON DSC Slice capabilities-1 */ -#define DP_PCON_DSC_SLICE_CAP_1 0x096 -# define DP_PCON_DSC_1_PER_DSC_ENC (0x1 << 0) -# define DP_PCON_DSC_2_PER_DSC_ENC (0x1 << 1) -# define DP_PCON_DSC_4_PER_DSC_ENC (0x1 << 3) -# define DP_PCON_DSC_6_PER_DSC_ENC (0x1 << 4) -# define DP_PCON_DSC_8_PER_DSC_ENC (0x1 << 5) -# define DP_PCON_DSC_10_PER_DSC_ENC (0x1 << 6) -# define DP_PCON_DSC_12_PER_DSC_ENC (0x1 << 7) - -#define DP_PCON_DSC_BUF_BIT_DEPTH 0x097 -# define DP_PCON_DSC_BIT_DEPTH_MASK (0xF << 0) -# define DP_PCON_DSC_DEPTH_9_BITS 0 -# define DP_PCON_DSC_DEPTH_10_BITS 1 -# define DP_PCON_DSC_DEPTH_11_BITS 2 -# define DP_PCON_DSC_DEPTH_12_BITS 3 -# define DP_PCON_DSC_DEPTH_13_BITS 4 -# define DP_PCON_DSC_DEPTH_14_BITS 5 -# define DP_PCON_DSC_DEPTH_15_BITS 6 -# define DP_PCON_DSC_DEPTH_16_BITS 7 -# define DP_PCON_DSC_DEPTH_8_BITS 8 - -#define DP_PCON_DSC_BLOCK_PREDICTION 0x098 -# define DP_PCON_DSC_BLOCK_PRED_SUPPORT (0x1 << 0) - -#define DP_PCON_DSC_ENC_COLOR_FMT_CAP 0x099 -# define DP_PCON_DSC_ENC_RGB (0x1 << 0) -# define DP_PCON_DSC_ENC_YUV444 (0x1 << 1) -# define DP_PCON_DSC_ENC_YUV422_S (0x1 << 2) -# define DP_PCON_DSC_ENC_YUV422_N (0x1 << 3) -# define DP_PCON_DSC_ENC_YUV420_N (0x1 << 4) - -#define DP_PCON_DSC_ENC_COLOR_DEPTH_CAP 0x09A -# define DP_PCON_DSC_ENC_8BPC (0x1 << 1) -# define DP_PCON_DSC_ENC_10BPC (0x1 << 2) -# define DP_PCON_DSC_ENC_12BPC (0x1 << 3) - -#define DP_PCON_DSC_MAX_SLICE_WIDTH 0x09B - -/* DP-HDMI2.1 PCON DSC Slice capabilities-2 */ -#define DP_PCON_DSC_SLICE_CAP_2 0x09C -# define DP_PCON_DSC_16_PER_DSC_ENC (0x1 << 0) -# define DP_PCON_DSC_20_PER_DSC_ENC (0x1 << 1) -# define DP_PCON_DSC_24_PER_DSC_ENC (0x1 << 2) - -/* DP-HDMI2.1 PCON HDMI TX Encoder Bits/pixel increment */ -#define DP_PCON_DSC_BPP_INCR 0x09E -# define DP_PCON_DSC_BPP_INCR_MASK (0x7 << 0) -# define DP_PCON_DSC_ONE_16TH_BPP 0 -# define DP_PCON_DSC_ONE_8TH_BPP 1 -# define DP_PCON_DSC_ONE_4TH_BPP 2 -# define DP_PCON_DSC_ONE_HALF_BPP 3 -# define DP_PCON_DSC_ONE_BPP 4 - -/* DP Extended DSC Capabilities */ -#define DP_DSC_BRANCH_OVERALL_THROUGHPUT_0 0x0a0 /* DP 1.4a SCR */ -#define DP_DSC_BRANCH_OVERALL_THROUGHPUT_1 0x0a1 -#define DP_DSC_BRANCH_MAX_LINE_WIDTH 0x0a2 - -/* DFP Capability Extension */ -#define DP_DFP_CAPABILITY_EXTENSION_SUPPORT 0x0a3 /* 2.0 */ - -/* Link Configuration */ -#define DP_LINK_BW_SET 0x100 -# define DP_LINK_RATE_TABLE 0x00 /* eDP 1.4 */ -# define DP_LINK_BW_1_62 0x06 -# define DP_LINK_BW_2_7 0x0a -# define DP_LINK_BW_5_4 0x14 /* 1.2 */ -# define DP_LINK_BW_8_1 0x1e /* 1.4 */ -# define DP_LINK_BW_10 0x01 /* 2.0 128b/132b Link Layer */ -# define DP_LINK_BW_13_5 0x04 /* 2.0 128b/132b Link Layer */ -# define DP_LINK_BW_20 0x02 /* 2.0 128b/132b Link Layer */ - -#define DP_LANE_COUNT_SET 0x101 -# define DP_LANE_COUNT_MASK 0x0f -# define DP_LANE_COUNT_ENHANCED_FRAME_EN (1 << 7) - -#define DP_TRAINING_PATTERN_SET 0x102 -# define DP_TRAINING_PATTERN_DISABLE 0 -# define DP_TRAINING_PATTERN_1 1 -# define DP_TRAINING_PATTERN_2 2 -# define DP_TRAINING_PATTERN_3 3 /* 1.2 */ -# define DP_TRAINING_PATTERN_4 7 /* 1.4 */ -# define DP_TRAINING_PATTERN_MASK 0x3 -# define DP_TRAINING_PATTERN_MASK_1_4 0xf - -/* DPCD 1.1 only. For DPCD >= 1.2 see per-lane DP_LINK_QUAL_LANEn_SET */ -# define DP_LINK_QUAL_PATTERN_11_DISABLE (0 << 2) -# define DP_LINK_QUAL_PATTERN_11_D10_2 (1 << 2) -# define DP_LINK_QUAL_PATTERN_11_ERROR_RATE (2 << 2) -# define DP_LINK_QUAL_PATTERN_11_PRBS7 (3 << 2) -# define DP_LINK_QUAL_PATTERN_11_MASK (3 << 2) - -# define DP_RECOVERED_CLOCK_OUT_EN (1 << 4) -# define DP_LINK_SCRAMBLING_DISABLE (1 << 5) - -# define DP_SYMBOL_ERROR_COUNT_BOTH (0 << 6) -# define DP_SYMBOL_ERROR_COUNT_DISPARITY (1 << 6) -# define DP_SYMBOL_ERROR_COUNT_SYMBOL (2 << 6) -# define DP_SYMBOL_ERROR_COUNT_MASK (3 << 6) - -#define DP_TRAINING_LANE0_SET 0x103 -#define DP_TRAINING_LANE1_SET 0x104 -#define DP_TRAINING_LANE2_SET 0x105 -#define DP_TRAINING_LANE3_SET 0x106 - -# define DP_TRAIN_VOLTAGE_SWING_MASK 0x3 -# define DP_TRAIN_VOLTAGE_SWING_SHIFT 0 -# define DP_TRAIN_MAX_SWING_REACHED (1 << 2) -# define DP_TRAIN_VOLTAGE_SWING_LEVEL_0 (0 << 0) -# define DP_TRAIN_VOLTAGE_SWING_LEVEL_1 (1 << 0) -# define DP_TRAIN_VOLTAGE_SWING_LEVEL_2 (2 << 0) -# define DP_TRAIN_VOLTAGE_SWING_LEVEL_3 (3 << 0) - -# define DP_TRAIN_PRE_EMPHASIS_MASK (3 << 3) -# define DP_TRAIN_PRE_EMPH_LEVEL_0 (0 << 3) -# define DP_TRAIN_PRE_EMPH_LEVEL_1 (1 << 3) -# define DP_TRAIN_PRE_EMPH_LEVEL_2 (2 << 3) -# define DP_TRAIN_PRE_EMPH_LEVEL_3 (3 << 3) - -# define DP_TRAIN_PRE_EMPHASIS_SHIFT 3 -# define DP_TRAIN_MAX_PRE_EMPHASIS_REACHED (1 << 5) - -# define DP_TX_FFE_PRESET_VALUE_MASK (0xf << 0) /* 2.0 128b/132b Link Layer */ - -#define DP_DOWNSPREAD_CTRL 0x107 -# define DP_SPREAD_AMP_0_5 (1 << 4) -# define DP_MSA_TIMING_PAR_IGNORE_EN (1 << 7) /* eDP */ - -#define DP_MAIN_LINK_CHANNEL_CODING_SET 0x108 -# define DP_SET_ANSI_8B10B (1 << 0) -# define DP_SET_ANSI_128B132B (1 << 1) - -#define DP_I2C_SPEED_CONTROL_STATUS 0x109 /* DPI */ -/* bitmask as for DP_I2C_SPEED_CAP */ - -#define DP_EDP_CONFIGURATION_SET 0x10a /* XXX 1.2? */ -# define DP_ALTERNATE_SCRAMBLER_RESET_ENABLE (1 << 0) -# define DP_FRAMING_CHANGE_ENABLE (1 << 1) -# define DP_PANEL_SELF_TEST_ENABLE (1 << 7) - -#define DP_LINK_QUAL_LANE0_SET 0x10b /* DPCD >= 1.2 */ -#define DP_LINK_QUAL_LANE1_SET 0x10c -#define DP_LINK_QUAL_LANE2_SET 0x10d -#define DP_LINK_QUAL_LANE3_SET 0x10e -# define DP_LINK_QUAL_PATTERN_DISABLE 0 -# define DP_LINK_QUAL_PATTERN_D10_2 1 -# define DP_LINK_QUAL_PATTERN_ERROR_RATE 2 -# define DP_LINK_QUAL_PATTERN_PRBS7 3 -# define DP_LINK_QUAL_PATTERN_80BIT_CUSTOM 4 -# define DP_LINK_QUAL_PATTERN_CP2520_PAT_1 5 -# define DP_LINK_QUAL_PATTERN_CP2520_PAT_2 6 -# define DP_LINK_QUAL_PATTERN_CP2520_PAT_3 7 -/* DP 2.0 UHBR10, UHBR13.5, UHBR20 */ -# define DP_LINK_QUAL_PATTERN_128B132B_TPS1 0x08 -# define DP_LINK_QUAL_PATTERN_128B132B_TPS2 0x10 -# define DP_LINK_QUAL_PATTERN_PRSBS9 0x18 -# define DP_LINK_QUAL_PATTERN_PRSBS11 0x20 -# define DP_LINK_QUAL_PATTERN_PRSBS15 0x28 -# define DP_LINK_QUAL_PATTERN_PRSBS23 0x30 -# define DP_LINK_QUAL_PATTERN_PRSBS31 0x38 -# define DP_LINK_QUAL_PATTERN_CUSTOM 0x40 -# define DP_LINK_QUAL_PATTERN_SQUARE 0x48 - -#define DP_TRAINING_LANE0_1_SET2 0x10f -#define DP_TRAINING_LANE2_3_SET2 0x110 -# define DP_LANE02_POST_CURSOR2_SET_MASK (3 << 0) -# define DP_LANE02_MAX_POST_CURSOR2_REACHED (1 << 2) -# define DP_LANE13_POST_CURSOR2_SET_MASK (3 << 4) -# define DP_LANE13_MAX_POST_CURSOR2_REACHED (1 << 6) - -#define DP_MSTM_CTRL 0x111 /* 1.2 */ -# define DP_MST_EN (1 << 0) -# define DP_UP_REQ_EN (1 << 1) -# define DP_UPSTREAM_IS_SRC (1 << 2) - -#define DP_AUDIO_DELAY0 0x112 /* 1.2 */ -#define DP_AUDIO_DELAY1 0x113 -#define DP_AUDIO_DELAY2 0x114 - -#define DP_LINK_RATE_SET 0x115 /* eDP 1.4 */ -# define DP_LINK_RATE_SET_SHIFT 0 -# define DP_LINK_RATE_SET_MASK (7 << 0) - -#define DP_RECEIVER_ALPM_CONFIG 0x116 /* eDP 1.4 */ -# define DP_ALPM_ENABLE (1 << 0) -# define DP_ALPM_LOCK_ERROR_IRQ_HPD_ENABLE (1 << 1) - -#define DP_SINK_DEVICE_AUX_FRAME_SYNC_CONF 0x117 /* eDP 1.4 */ -# define DP_AUX_FRAME_SYNC_ENABLE (1 << 0) -# define DP_IRQ_HPD_ENABLE (1 << 1) - -#define DP_UPSTREAM_DEVICE_DP_PWR_NEED 0x118 /* 1.2 */ -# define DP_PWR_NOT_NEEDED (1 << 0) - -#define DP_FEC_CONFIGURATION 0x120 /* 1.4 */ -# define DP_FEC_READY (1 << 0) -# define DP_FEC_ERR_COUNT_SEL_MASK (7 << 1) -# define DP_FEC_ERR_COUNT_DIS (0 << 1) -# define DP_FEC_UNCORR_BLK_ERROR_COUNT (1 << 1) -# define DP_FEC_CORR_BLK_ERROR_COUNT (2 << 1) -# define DP_FEC_BIT_ERROR_COUNT (3 << 1) -# define DP_FEC_LANE_SELECT_MASK (3 << 4) -# define DP_FEC_LANE_0_SELECT (0 << 4) -# define DP_FEC_LANE_1_SELECT (1 << 4) -# define DP_FEC_LANE_2_SELECT (2 << 4) -# define DP_FEC_LANE_3_SELECT (3 << 4) - -#define DP_AUX_FRAME_SYNC_VALUE 0x15c /* eDP 1.4 */ -# define DP_AUX_FRAME_SYNC_VALID (1 << 0) - -#define DP_DSC_ENABLE 0x160 /* DP 1.4 */ -# define DP_DECOMPRESSION_EN (1 << 0) -#define DP_DSC_CONFIGURATION 0x161 /* DP 2.0 */ - -#define DP_PSR_EN_CFG 0x170 /* XXX 1.2? */ -# define DP_PSR_ENABLE BIT(0) -# define DP_PSR_MAIN_LINK_ACTIVE BIT(1) -# define DP_PSR_CRC_VERIFICATION BIT(2) -# define DP_PSR_FRAME_CAPTURE BIT(3) -# define DP_PSR_SU_REGION_SCANLINE_CAPTURE BIT(4) /* eDP 1.4a */ -# define DP_PSR_IRQ_HPD_WITH_CRC_ERRORS BIT(5) /* eDP 1.4a */ -# define DP_PSR_ENABLE_PSR2 BIT(6) /* eDP 1.4a */ - -#define DP_ADAPTER_CTRL 0x1a0 -# define DP_ADAPTER_CTRL_FORCE_LOAD_SENSE (1 << 0) - -#define DP_BRANCH_DEVICE_CTRL 0x1a1 -# define DP_BRANCH_DEVICE_IRQ_HPD (1 << 0) - -#define DP_PAYLOAD_ALLOCATE_SET 0x1c0 -#define DP_PAYLOAD_ALLOCATE_START_TIME_SLOT 0x1c1 -#define DP_PAYLOAD_ALLOCATE_TIME_SLOT_COUNT 0x1c2 - -/* Link/Sink Device Status */ -#define DP_SINK_COUNT 0x200 -/* prior to 1.2 bit 7 was reserved mbz */ -# define DP_GET_SINK_COUNT(x) ((((x) & 0x80) >> 1) | ((x) & 0x3f)) -# define DP_SINK_CP_READY (1 << 6) - -#define DP_DEVICE_SERVICE_IRQ_VECTOR 0x201 -# define DP_REMOTE_CONTROL_COMMAND_PENDING (1 << 0) -# define DP_AUTOMATED_TEST_REQUEST (1 << 1) -# define DP_CP_IRQ (1 << 2) -# define DP_MCCS_IRQ (1 << 3) -# define DP_DOWN_REP_MSG_RDY (1 << 4) /* 1.2 MST */ -# define DP_UP_REQ_MSG_RDY (1 << 5) /* 1.2 MST */ -# define DP_SINK_SPECIFIC_IRQ (1 << 6) - -#define DP_LANE0_1_STATUS 0x202 -#define DP_LANE2_3_STATUS 0x203 -# define DP_LANE_CR_DONE (1 << 0) -# define DP_LANE_CHANNEL_EQ_DONE (1 << 1) -# define DP_LANE_SYMBOL_LOCKED (1 << 2) - -#define DP_CHANNEL_EQ_BITS (DP_LANE_CR_DONE | \ - DP_LANE_CHANNEL_EQ_DONE | \ - DP_LANE_SYMBOL_LOCKED) - -#define DP_LANE_ALIGN_STATUS_UPDATED 0x204 - -#define DP_INTERLANE_ALIGN_DONE (1 << 0) -#define DP_DOWNSTREAM_PORT_STATUS_CHANGED (1 << 6) -#define DP_LINK_STATUS_UPDATED (1 << 7) - -#define DP_SINK_STATUS 0x205 -# define DP_RECEIVE_PORT_0_STATUS (1 << 0) -# define DP_RECEIVE_PORT_1_STATUS (1 << 1) -# define DP_STREAM_REGENERATION_STATUS (1 << 2) /* 2.0 */ -# define DP_INTRA_HOP_AUX_REPLY_INDICATION (1 << 3) /* 2.0 */ - -#define DP_ADJUST_REQUEST_LANE0_1 0x206 -#define DP_ADJUST_REQUEST_LANE2_3 0x207 -# define DP_ADJUST_VOLTAGE_SWING_LANE0_MASK 0x03 -# define DP_ADJUST_VOLTAGE_SWING_LANE0_SHIFT 0 -# define DP_ADJUST_PRE_EMPHASIS_LANE0_MASK 0x0c -# define DP_ADJUST_PRE_EMPHASIS_LANE0_SHIFT 2 -# define DP_ADJUST_VOLTAGE_SWING_LANE1_MASK 0x30 -# define DP_ADJUST_VOLTAGE_SWING_LANE1_SHIFT 4 -# define DP_ADJUST_PRE_EMPHASIS_LANE1_MASK 0xc0 -# define DP_ADJUST_PRE_EMPHASIS_LANE1_SHIFT 6 - -/* DP 2.0 128b/132b Link Layer */ -# define DP_ADJUST_TX_FFE_PRESET_LANE0_MASK (0xf << 0) -# define DP_ADJUST_TX_FFE_PRESET_LANE0_SHIFT 0 -# define DP_ADJUST_TX_FFE_PRESET_LANE1_MASK (0xf << 4) -# define DP_ADJUST_TX_FFE_PRESET_LANE1_SHIFT 4 - -#define DP_ADJUST_REQUEST_POST_CURSOR2 0x20c -# define DP_ADJUST_POST_CURSOR2_LANE0_MASK 0x03 -# define DP_ADJUST_POST_CURSOR2_LANE0_SHIFT 0 -# define DP_ADJUST_POST_CURSOR2_LANE1_MASK 0x0c -# define DP_ADJUST_POST_CURSOR2_LANE1_SHIFT 2 -# define DP_ADJUST_POST_CURSOR2_LANE2_MASK 0x30 -# define DP_ADJUST_POST_CURSOR2_LANE2_SHIFT 4 -# define DP_ADJUST_POST_CURSOR2_LANE3_MASK 0xc0 -# define DP_ADJUST_POST_CURSOR2_LANE3_SHIFT 6 - -#define DP_TEST_REQUEST 0x218 -# define DP_TEST_LINK_TRAINING (1 << 0) -# define DP_TEST_LINK_VIDEO_PATTERN (1 << 1) -# define DP_TEST_LINK_EDID_READ (1 << 2) -# define DP_TEST_LINK_PHY_TEST_PATTERN (1 << 3) /* DPCD >= 1.1 */ -# define DP_TEST_LINK_FAUX_PATTERN (1 << 4) /* DPCD >= 1.2 */ -# define DP_TEST_LINK_AUDIO_PATTERN (1 << 5) /* DPCD >= 1.2 */ -# define DP_TEST_LINK_AUDIO_DISABLED_VIDEO (1 << 6) /* DPCD >= 1.2 */ - -#define DP_TEST_LINK_RATE 0x219 -# define DP_LINK_RATE_162 (0x6) -# define DP_LINK_RATE_27 (0xa) - -#define DP_TEST_LANE_COUNT 0x220 - -#define DP_TEST_PATTERN 0x221 -# define DP_NO_TEST_PATTERN 0x0 -# define DP_COLOR_RAMP 0x1 -# define DP_BLACK_AND_WHITE_VERTICAL_LINES 0x2 -# define DP_COLOR_SQUARE 0x3 - -#define DP_TEST_H_TOTAL_HI 0x222 -#define DP_TEST_H_TOTAL_LO 0x223 - -#define DP_TEST_V_TOTAL_HI 0x224 -#define DP_TEST_V_TOTAL_LO 0x225 - -#define DP_TEST_H_START_HI 0x226 -#define DP_TEST_H_START_LO 0x227 - -#define DP_TEST_V_START_HI 0x228 -#define DP_TEST_V_START_LO 0x229 - -#define DP_TEST_HSYNC_HI 0x22A -# define DP_TEST_HSYNC_POLARITY (1 << 7) -# define DP_TEST_HSYNC_WIDTH_HI_MASK (127 << 0) -#define DP_TEST_HSYNC_WIDTH_LO 0x22B - -#define DP_TEST_VSYNC_HI 0x22C -# define DP_TEST_VSYNC_POLARITY (1 << 7) -# define DP_TEST_VSYNC_WIDTH_HI_MASK (127 << 0) -#define DP_TEST_VSYNC_WIDTH_LO 0x22D - -#define DP_TEST_H_WIDTH_HI 0x22E -#define DP_TEST_H_WIDTH_LO 0x22F - -#define DP_TEST_V_HEIGHT_HI 0x230 -#define DP_TEST_V_HEIGHT_LO 0x231 - -#define DP_TEST_MISC0 0x232 -# define DP_TEST_SYNC_CLOCK (1 << 0) -# define DP_TEST_COLOR_FORMAT_MASK (3 << 1) -# define DP_TEST_COLOR_FORMAT_SHIFT 1 -# define DP_COLOR_FORMAT_RGB (0 << 1) -# define DP_COLOR_FORMAT_YCbCr422 (1 << 1) -# define DP_COLOR_FORMAT_YCbCr444 (2 << 1) -# define DP_TEST_DYNAMIC_RANGE_VESA (0 << 3) -# define DP_TEST_DYNAMIC_RANGE_CEA (1 << 3) -# define DP_TEST_YCBCR_COEFFICIENTS (1 << 4) -# define DP_YCBCR_COEFFICIENTS_ITU601 (0 << 4) -# define DP_YCBCR_COEFFICIENTS_ITU709 (1 << 4) -# define DP_TEST_BIT_DEPTH_MASK (7 << 5) -# define DP_TEST_BIT_DEPTH_SHIFT 5 -# define DP_TEST_BIT_DEPTH_6 (0 << 5) -# define DP_TEST_BIT_DEPTH_8 (1 << 5) -# define DP_TEST_BIT_DEPTH_10 (2 << 5) -# define DP_TEST_BIT_DEPTH_12 (3 << 5) -# define DP_TEST_BIT_DEPTH_16 (4 << 5) - -#define DP_TEST_MISC1 0x233 -# define DP_TEST_REFRESH_DENOMINATOR (1 << 0) -# define DP_TEST_INTERLACED (1 << 1) - -#define DP_TEST_REFRESH_RATE_NUMERATOR 0x234 - -#define DP_TEST_MISC0 0x232 - -#define DP_TEST_CRC_R_CR 0x240 -#define DP_TEST_CRC_G_Y 0x242 -#define DP_TEST_CRC_B_CB 0x244 - -#define DP_TEST_SINK_MISC 0x246 -# define DP_TEST_CRC_SUPPORTED (1 << 5) -# define DP_TEST_COUNT_MASK 0xf - -#define DP_PHY_TEST_PATTERN 0x248 -# define DP_PHY_TEST_PATTERN_SEL_MASK 0x7 -# define DP_PHY_TEST_PATTERN_NONE 0x0 -# define DP_PHY_TEST_PATTERN_D10_2 0x1 -# define DP_PHY_TEST_PATTERN_ERROR_COUNT 0x2 -# define DP_PHY_TEST_PATTERN_PRBS7 0x3 -# define DP_PHY_TEST_PATTERN_80BIT_CUSTOM 0x4 -# define DP_PHY_TEST_PATTERN_CP2520 0x5 - -#define DP_PHY_SQUARE_PATTERN 0x249 - -#define DP_TEST_HBR2_SCRAMBLER_RESET 0x24A -#define DP_TEST_80BIT_CUSTOM_PATTERN_7_0 0x250 -#define DP_TEST_80BIT_CUSTOM_PATTERN_15_8 0x251 -#define DP_TEST_80BIT_CUSTOM_PATTERN_23_16 0x252 -#define DP_TEST_80BIT_CUSTOM_PATTERN_31_24 0x253 -#define DP_TEST_80BIT_CUSTOM_PATTERN_39_32 0x254 -#define DP_TEST_80BIT_CUSTOM_PATTERN_47_40 0x255 -#define DP_TEST_80BIT_CUSTOM_PATTERN_55_48 0x256 -#define DP_TEST_80BIT_CUSTOM_PATTERN_63_56 0x257 -#define DP_TEST_80BIT_CUSTOM_PATTERN_71_64 0x258 -#define DP_TEST_80BIT_CUSTOM_PATTERN_79_72 0x259 - -#define DP_TEST_RESPONSE 0x260 -# define DP_TEST_ACK (1 << 0) -# define DP_TEST_NAK (1 << 1) -# define DP_TEST_EDID_CHECKSUM_WRITE (1 << 2) - -#define DP_TEST_EDID_CHECKSUM 0x261 - -#define DP_TEST_SINK 0x270 -# define DP_TEST_SINK_START (1 << 0) -#define DP_TEST_AUDIO_MODE 0x271 -#define DP_TEST_AUDIO_PATTERN_TYPE 0x272 -#define DP_TEST_AUDIO_PERIOD_CH1 0x273 -#define DP_TEST_AUDIO_PERIOD_CH2 0x274 -#define DP_TEST_AUDIO_PERIOD_CH3 0x275 -#define DP_TEST_AUDIO_PERIOD_CH4 0x276 -#define DP_TEST_AUDIO_PERIOD_CH5 0x277 -#define DP_TEST_AUDIO_PERIOD_CH6 0x278 -#define DP_TEST_AUDIO_PERIOD_CH7 0x279 -#define DP_TEST_AUDIO_PERIOD_CH8 0x27A - -#define DP_FEC_STATUS 0x280 /* 1.4 */ -# define DP_FEC_DECODE_EN_DETECTED (1 << 0) -# define DP_FEC_DECODE_DIS_DETECTED (1 << 1) - -#define DP_FEC_ERROR_COUNT_LSB 0x0281 /* 1.4 */ - -#define DP_FEC_ERROR_COUNT_MSB 0x0282 /* 1.4 */ -# define DP_FEC_ERROR_COUNT_MASK 0x7F -# define DP_FEC_ERR_COUNT_VALID (1 << 7) - -#define DP_PAYLOAD_TABLE_UPDATE_STATUS 0x2c0 /* 1.2 MST */ -# define DP_PAYLOAD_TABLE_UPDATED (1 << 0) -# define DP_PAYLOAD_ACT_HANDLED (1 << 1) - -#define DP_VC_PAYLOAD_ID_SLOT_1 0x2c1 /* 1.2 MST */ -/* up to ID_SLOT_63 at 0x2ff */ - -/* Source Device-specific */ -#define DP_SOURCE_OUI 0x300 - -/* Sink Device-specific */ -#define DP_SINK_OUI 0x400 - -/* Branch Device-specific */ -#define DP_BRANCH_OUI 0x500 -#define DP_BRANCH_ID 0x503 -#define DP_BRANCH_REVISION_START 0x509 -#define DP_BRANCH_HW_REV 0x509 -#define DP_BRANCH_SW_REV 0x50A - -/* Link/Sink Device Power Control */ -#define DP_SET_POWER 0x600 -# define DP_SET_POWER_D0 0x1 -# define DP_SET_POWER_D3 0x2 -# define DP_SET_POWER_MASK 0x3 -# define DP_SET_POWER_D3_AUX_ON 0x5 - -/* eDP-specific */ -#define DP_EDP_DPCD_REV 0x700 /* eDP 1.2 */ -# define DP_EDP_11 0x00 -# define DP_EDP_12 0x01 -# define DP_EDP_13 0x02 -# define DP_EDP_14 0x03 -# define DP_EDP_14a 0x04 /* eDP 1.4a */ -# define DP_EDP_14b 0x05 /* eDP 1.4b */ - -#define DP_EDP_GENERAL_CAP_1 0x701 -# define DP_EDP_TCON_BACKLIGHT_ADJUSTMENT_CAP (1 << 0) -# define DP_EDP_BACKLIGHT_PIN_ENABLE_CAP (1 << 1) -# define DP_EDP_BACKLIGHT_AUX_ENABLE_CAP (1 << 2) -# define DP_EDP_PANEL_SELF_TEST_PIN_ENABLE_CAP (1 << 3) -# define DP_EDP_PANEL_SELF_TEST_AUX_ENABLE_CAP (1 << 4) -# define DP_EDP_FRC_ENABLE_CAP (1 << 5) -# define DP_EDP_COLOR_ENGINE_CAP (1 << 6) -# define DP_EDP_SET_POWER_CAP (1 << 7) - -#define DP_EDP_BACKLIGHT_ADJUSTMENT_CAP 0x702 -# define DP_EDP_BACKLIGHT_BRIGHTNESS_PWM_PIN_CAP (1 << 0) -# define DP_EDP_BACKLIGHT_BRIGHTNESS_AUX_SET_CAP (1 << 1) -# define DP_EDP_BACKLIGHT_BRIGHTNESS_BYTE_COUNT (1 << 2) -# define DP_EDP_BACKLIGHT_AUX_PWM_PRODUCT_CAP (1 << 3) -# define DP_EDP_BACKLIGHT_FREQ_PWM_PIN_PASSTHRU_CAP (1 << 4) -# define DP_EDP_BACKLIGHT_FREQ_AUX_SET_CAP (1 << 5) -# define DP_EDP_DYNAMIC_BACKLIGHT_CAP (1 << 6) -# define DP_EDP_VBLANK_BACKLIGHT_UPDATE_CAP (1 << 7) - -#define DP_EDP_GENERAL_CAP_2 0x703 -# define DP_EDP_OVERDRIVE_ENGINE_ENABLED (1 << 0) - -#define DP_EDP_GENERAL_CAP_3 0x704 /* eDP 1.4 */ -# define DP_EDP_X_REGION_CAP_MASK (0xf << 0) -# define DP_EDP_X_REGION_CAP_SHIFT 0 -# define DP_EDP_Y_REGION_CAP_MASK (0xf << 4) -# define DP_EDP_Y_REGION_CAP_SHIFT 4 - -#define DP_EDP_DISPLAY_CONTROL_REGISTER 0x720 -# define DP_EDP_BACKLIGHT_ENABLE (1 << 0) -# define DP_EDP_BLACK_VIDEO_ENABLE (1 << 1) -# define DP_EDP_FRC_ENABLE (1 << 2) -# define DP_EDP_COLOR_ENGINE_ENABLE (1 << 3) -# define DP_EDP_VBLANK_BACKLIGHT_UPDATE_ENABLE (1 << 7) - -#define DP_EDP_BACKLIGHT_MODE_SET_REGISTER 0x721 -# define DP_EDP_BACKLIGHT_CONTROL_MODE_MASK (3 << 0) -# define DP_EDP_BACKLIGHT_CONTROL_MODE_PWM (0 << 0) -# define DP_EDP_BACKLIGHT_CONTROL_MODE_PRESET (1 << 0) -# define DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD (2 << 0) -# define DP_EDP_BACKLIGHT_CONTROL_MODE_PRODUCT (3 << 0) -# define DP_EDP_BACKLIGHT_FREQ_PWM_PIN_PASSTHRU_ENABLE (1 << 2) -# define DP_EDP_BACKLIGHT_FREQ_AUX_SET_ENABLE (1 << 3) -# define DP_EDP_DYNAMIC_BACKLIGHT_ENABLE (1 << 4) -# define DP_EDP_REGIONAL_BACKLIGHT_ENABLE (1 << 5) -# define DP_EDP_UPDATE_REGION_BRIGHTNESS (1 << 6) /* eDP 1.4 */ - -#define DP_EDP_BACKLIGHT_BRIGHTNESS_MSB 0x722 -#define DP_EDP_BACKLIGHT_BRIGHTNESS_LSB 0x723 - -#define DP_EDP_PWMGEN_BIT_COUNT 0x724 -#define DP_EDP_PWMGEN_BIT_COUNT_CAP_MIN 0x725 -#define DP_EDP_PWMGEN_BIT_COUNT_CAP_MAX 0x726 -# define DP_EDP_PWMGEN_BIT_COUNT_MASK (0x1f << 0) - -#define DP_EDP_BACKLIGHT_CONTROL_STATUS 0x727 - -#define DP_EDP_BACKLIGHT_FREQ_SET 0x728 -# define DP_EDP_BACKLIGHT_FREQ_BASE_KHZ 27000 - -#define DP_EDP_BACKLIGHT_FREQ_CAP_MIN_MSB 0x72a -#define DP_EDP_BACKLIGHT_FREQ_CAP_MIN_MID 0x72b -#define DP_EDP_BACKLIGHT_FREQ_CAP_MIN_LSB 0x72c - -#define DP_EDP_BACKLIGHT_FREQ_CAP_MAX_MSB 0x72d -#define DP_EDP_BACKLIGHT_FREQ_CAP_MAX_MID 0x72e -#define DP_EDP_BACKLIGHT_FREQ_CAP_MAX_LSB 0x72f - -#define DP_EDP_DBC_MINIMUM_BRIGHTNESS_SET 0x732 -#define DP_EDP_DBC_MAXIMUM_BRIGHTNESS_SET 0x733 - -#define DP_EDP_REGIONAL_BACKLIGHT_BASE 0x740 /* eDP 1.4 */ -#define DP_EDP_REGIONAL_BACKLIGHT_0 0x741 /* eDP 1.4 */ - -#define DP_EDP_MSO_LINK_CAPABILITIES 0x7a4 /* eDP 1.4 */ -# define DP_EDP_MSO_NUMBER_OF_LINKS_MASK (7 << 0) -# define DP_EDP_MSO_NUMBER_OF_LINKS_SHIFT 0 -# define DP_EDP_MSO_INDEPENDENT_LINK_BIT (1 << 3) - -/* Sideband MSG Buffers */ -#define DP_SIDEBAND_MSG_DOWN_REQ_BASE 0x1000 /* 1.2 MST */ -#define DP_SIDEBAND_MSG_UP_REP_BASE 0x1200 /* 1.2 MST */ -#define DP_SIDEBAND_MSG_DOWN_REP_BASE 0x1400 /* 1.2 MST */ -#define DP_SIDEBAND_MSG_UP_REQ_BASE 0x1600 /* 1.2 MST */ - -/* DPRX Event Status Indicator */ -#define DP_SINK_COUNT_ESI 0x2002 /* same as 0x200 */ -#define DP_DEVICE_SERVICE_IRQ_VECTOR_ESI0 0x2003 /* same as 0x201 */ - -#define DP_DEVICE_SERVICE_IRQ_VECTOR_ESI1 0x2004 /* 1.2 */ -# define DP_RX_GTC_MSTR_REQ_STATUS_CHANGE (1 << 0) -# define DP_LOCK_ACQUISITION_REQUEST (1 << 1) -# define DP_CEC_IRQ (1 << 2) - -#define DP_LINK_SERVICE_IRQ_VECTOR_ESI0 0x2005 /* 1.2 */ -# define RX_CAP_CHANGED (1 << 0) -# define LINK_STATUS_CHANGED (1 << 1) -# define STREAM_STATUS_CHANGED (1 << 2) -# define HDMI_LINK_STATUS_CHANGED (1 << 3) -# define CONNECTED_OFF_ENTRY_REQUESTED (1 << 4) - -#define DP_PSR_ERROR_STATUS 0x2006 /* XXX 1.2? */ -# define DP_PSR_LINK_CRC_ERROR (1 << 0) -# define DP_PSR_RFB_STORAGE_ERROR (1 << 1) -# define DP_PSR_VSC_SDP_UNCORRECTABLE_ERROR (1 << 2) /* eDP 1.4 */ - -#define DP_PSR_ESI 0x2007 /* XXX 1.2? */ -# define DP_PSR_CAPS_CHANGE (1 << 0) - -#define DP_PSR_STATUS 0x2008 /* XXX 1.2? */ -# define DP_PSR_SINK_INACTIVE 0 -# define DP_PSR_SINK_ACTIVE_SRC_SYNCED 1 -# define DP_PSR_SINK_ACTIVE_RFB 2 -# define DP_PSR_SINK_ACTIVE_SINK_SYNCED 3 -# define DP_PSR_SINK_ACTIVE_RESYNC 4 -# define DP_PSR_SINK_INTERNAL_ERROR 7 -# define DP_PSR_SINK_STATE_MASK 0x07 - -#define DP_SYNCHRONIZATION_LATENCY_IN_SINK 0x2009 /* edp 1.4 */ -# define DP_MAX_RESYNC_FRAME_COUNT_MASK (0xf << 0) -# define DP_MAX_RESYNC_FRAME_COUNT_SHIFT 0 -# define DP_LAST_ACTUAL_SYNCHRONIZATION_LATENCY_MASK (0xf << 4) -# define DP_LAST_ACTUAL_SYNCHRONIZATION_LATENCY_SHIFT 4 - -#define DP_LAST_RECEIVED_PSR_SDP 0x200a /* eDP 1.2 */ -# define DP_PSR_STATE_BIT (1 << 0) /* eDP 1.2 */ -# define DP_UPDATE_RFB_BIT (1 << 1) /* eDP 1.2 */ -# define DP_CRC_VALID_BIT (1 << 2) /* eDP 1.2 */ -# define DP_SU_VALID (1 << 3) /* eDP 1.4 */ -# define DP_FIRST_SCAN_LINE_SU_REGION (1 << 4) /* eDP 1.4 */ -# define DP_LAST_SCAN_LINE_SU_REGION (1 << 5) /* eDP 1.4 */ -# define DP_Y_COORDINATE_VALID (1 << 6) /* eDP 1.4a */ - -#define DP_RECEIVER_ALPM_STATUS 0x200b /* eDP 1.4 */ -# define DP_ALPM_LOCK_TIMEOUT_ERROR (1 << 0) - -#define DP_LANE0_1_STATUS_ESI 0x200c /* status same as 0x202 */ -#define DP_LANE2_3_STATUS_ESI 0x200d /* status same as 0x203 */ -#define DP_LANE_ALIGN_STATUS_UPDATED_ESI 0x200e /* status same as 0x204 */ -#define DP_SINK_STATUS_ESI 0x200f /* status same as 0x205 */ - -/* Extended Receiver Capability: See DP_DPCD_REV for definitions */ -#define DP_DP13_DPCD_REV 0x2200 - -#define DP_DPRX_FEATURE_ENUMERATION_LIST 0x2210 /* DP 1.3 */ -# define DP_GTC_CAP (1 << 0) /* DP 1.3 */ -# define DP_SST_SPLIT_SDP_CAP (1 << 1) /* DP 1.4 */ -# define DP_AV_SYNC_CAP (1 << 2) /* DP 1.3 */ -# define DP_VSC_SDP_EXT_FOR_COLORIMETRY_SUPPORTED (1 << 3) /* DP 1.3 */ -# define DP_VSC_EXT_VESA_SDP_SUPPORTED (1 << 4) /* DP 1.4 */ -# define DP_VSC_EXT_VESA_SDP_CHAINING_SUPPORTED (1 << 5) /* DP 1.4 */ -# define DP_VSC_EXT_CEA_SDP_SUPPORTED (1 << 6) /* DP 1.4 */ -# define DP_VSC_EXT_CEA_SDP_CHAINING_SUPPORTED (1 << 7) /* DP 1.4 */ - -#define DP_128B132B_SUPPORTED_LINK_RATES 0x2215 /* 2.0 */ -# define DP_UHBR10 (1 << 0) -# define DP_UHBR20 (1 << 1) -# define DP_UHBR13_5 (1 << 2) - -#define DP_128B132B_TRAINING_AUX_RD_INTERVAL 0x2216 /* 2.0 */ -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_MASK 0x7f -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_400_US 0x00 -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_4_MS 0x01 -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_8_MS 0x02 -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_12_MS 0x03 -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_16_MS 0x04 -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_32_MS 0x05 -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_64_MS 0x06 - -#define DP_TEST_264BIT_CUSTOM_PATTERN_7_0 0x2230 -#define DP_TEST_264BIT_CUSTOM_PATTERN_263_256 0x2250 - -/* DSC Extended Capability Branch Total DSC Resources */ -#define DP_DSC_SUPPORT_AND_DSC_DECODER_COUNT 0x2260 /* 2.0 */ -# define DP_DSC_DECODER_COUNT_MASK (0b111 << 5) -# define DP_DSC_DECODER_COUNT_SHIFT 5 -#define DP_DSC_MAX_SLICE_COUNT_AND_AGGREGATION_0 0x2270 /* 2.0 */ -# define DP_DSC_DECODER_0_MAXIMUM_SLICE_COUNT_MASK (1 << 0) -# define DP_DSC_DECODER_0_AGGREGATION_SUPPORT_MASK (0b111 << 1) -# define DP_DSC_DECODER_0_AGGREGATION_SUPPORT_SHIFT 1 - -/* Protocol Converter Extension */ -/* HDMI CEC tunneling over AUX DP 1.3 section 5.3.3.3.1 DPCD 1.4+ */ -#define DP_CEC_TUNNELING_CAPABILITY 0x3000 -# define DP_CEC_TUNNELING_CAPABLE (1 << 0) -# define DP_CEC_SNOOPING_CAPABLE (1 << 1) -# define DP_CEC_MULTIPLE_LA_CAPABLE (1 << 2) - -#define DP_CEC_TUNNELING_CONTROL 0x3001 -# define DP_CEC_TUNNELING_ENABLE (1 << 0) -# define DP_CEC_SNOOPING_ENABLE (1 << 1) - -#define DP_CEC_RX_MESSAGE_INFO 0x3002 -# define DP_CEC_RX_MESSAGE_LEN_MASK (0xf << 0) -# define DP_CEC_RX_MESSAGE_LEN_SHIFT 0 -# define DP_CEC_RX_MESSAGE_HPD_STATE (1 << 4) -# define DP_CEC_RX_MESSAGE_HPD_LOST (1 << 5) -# define DP_CEC_RX_MESSAGE_ACKED (1 << 6) -# define DP_CEC_RX_MESSAGE_ENDED (1 << 7) - -#define DP_CEC_TX_MESSAGE_INFO 0x3003 -# define DP_CEC_TX_MESSAGE_LEN_MASK (0xf << 0) -# define DP_CEC_TX_MESSAGE_LEN_SHIFT 0 -# define DP_CEC_TX_RETRY_COUNT_MASK (0x7 << 4) -# define DP_CEC_TX_RETRY_COUNT_SHIFT 4 -# define DP_CEC_TX_MESSAGE_SEND (1 << 7) - -#define DP_CEC_TUNNELING_IRQ_FLAGS 0x3004 -# define DP_CEC_RX_MESSAGE_INFO_VALID (1 << 0) -# define DP_CEC_RX_MESSAGE_OVERFLOW (1 << 1) -# define DP_CEC_TX_MESSAGE_SENT (1 << 4) -# define DP_CEC_TX_LINE_ERROR (1 << 5) -# define DP_CEC_TX_ADDRESS_NACK_ERROR (1 << 6) -# define DP_CEC_TX_DATA_NACK_ERROR (1 << 7) - -#define DP_CEC_LOGICAL_ADDRESS_MASK 0x300E /* 0x300F word */ -# define DP_CEC_LOGICAL_ADDRESS_0 (1 << 0) -# define DP_CEC_LOGICAL_ADDRESS_1 (1 << 1) -# define DP_CEC_LOGICAL_ADDRESS_2 (1 << 2) -# define DP_CEC_LOGICAL_ADDRESS_3 (1 << 3) -# define DP_CEC_LOGICAL_ADDRESS_4 (1 << 4) -# define DP_CEC_LOGICAL_ADDRESS_5 (1 << 5) -# define DP_CEC_LOGICAL_ADDRESS_6 (1 << 6) -# define DP_CEC_LOGICAL_ADDRESS_7 (1 << 7) -#define DP_CEC_LOGICAL_ADDRESS_MASK_2 0x300F /* 0x300E word */ -# define DP_CEC_LOGICAL_ADDRESS_8 (1 << 0) -# define DP_CEC_LOGICAL_ADDRESS_9 (1 << 1) -# define DP_CEC_LOGICAL_ADDRESS_10 (1 << 2) -# define DP_CEC_LOGICAL_ADDRESS_11 (1 << 3) -# define DP_CEC_LOGICAL_ADDRESS_12 (1 << 4) -# define DP_CEC_LOGICAL_ADDRESS_13 (1 << 5) -# define DP_CEC_LOGICAL_ADDRESS_14 (1 << 6) -# define DP_CEC_LOGICAL_ADDRESS_15 (1 << 7) - -#define DP_CEC_RX_MESSAGE_BUFFER 0x3010 -#define DP_CEC_TX_MESSAGE_BUFFER 0x3020 -#define DP_CEC_MESSAGE_BUFFER_LENGTH 0x10 - -/* PCON CONFIGURE-1 FRL FOR HDMI SINK */ -#define DP_PCON_HDMI_LINK_CONFIG_1 0x305A -# define DP_PCON_ENABLE_MAX_FRL_BW (7 << 0) -# define DP_PCON_ENABLE_MAX_BW_0GBPS 0 -# define DP_PCON_ENABLE_MAX_BW_9GBPS 1 -# define DP_PCON_ENABLE_MAX_BW_18GBPS 2 -# define DP_PCON_ENABLE_MAX_BW_24GBPS 3 -# define DP_PCON_ENABLE_MAX_BW_32GBPS 4 -# define DP_PCON_ENABLE_MAX_BW_40GBPS 5 -# define DP_PCON_ENABLE_MAX_BW_48GBPS 6 -# define DP_PCON_ENABLE_SOURCE_CTL_MODE (1 << 3) -# define DP_PCON_ENABLE_CONCURRENT_LINK (1 << 4) -# define DP_PCON_ENABLE_SEQUENTIAL_LINK (0 << 4) -# define DP_PCON_ENABLE_LINK_FRL_MODE (1 << 5) -# define DP_PCON_ENABLE_HPD_READY (1 << 6) -# define DP_PCON_ENABLE_HDMI_LINK (1 << 7) - -/* PCON CONFIGURE-2 FRL FOR HDMI SINK */ -#define DP_PCON_HDMI_LINK_CONFIG_2 0x305B -# define DP_PCON_MAX_LINK_BW_MASK (0x3F << 0) -# define DP_PCON_FRL_BW_MASK_9GBPS (1 << 0) -# define DP_PCON_FRL_BW_MASK_18GBPS (1 << 1) -# define DP_PCON_FRL_BW_MASK_24GBPS (1 << 2) -# define DP_PCON_FRL_BW_MASK_32GBPS (1 << 3) -# define DP_PCON_FRL_BW_MASK_40GBPS (1 << 4) -# define DP_PCON_FRL_BW_MASK_48GBPS (1 << 5) -# define DP_PCON_FRL_LINK_TRAIN_EXTENDED (1 << 6) -# define DP_PCON_FRL_LINK_TRAIN_NORMAL (0 << 6) - -/* PCON HDMI LINK STATUS */ -#define DP_PCON_HDMI_TX_LINK_STATUS 0x303B -# define DP_PCON_HDMI_TX_LINK_ACTIVE (1 << 0) -# define DP_PCON_FRL_READY (1 << 1) - -/* PCON HDMI POST FRL STATUS */ -#define DP_PCON_HDMI_POST_FRL_STATUS 0x3036 -# define DP_PCON_HDMI_LINK_MODE (1 << 0) -# define DP_PCON_HDMI_MODE_TMDS 0 -# define DP_PCON_HDMI_MODE_FRL 1 -# define DP_PCON_HDMI_FRL_TRAINED_BW (0x3F << 1) -# define DP_PCON_FRL_TRAINED_BW_9GBPS (1 << 1) -# define DP_PCON_FRL_TRAINED_BW_18GBPS (1 << 2) -# define DP_PCON_FRL_TRAINED_BW_24GBPS (1 << 3) -# define DP_PCON_FRL_TRAINED_BW_32GBPS (1 << 4) -# define DP_PCON_FRL_TRAINED_BW_40GBPS (1 << 5) -# define DP_PCON_FRL_TRAINED_BW_48GBPS (1 << 6) - -#define DP_PROTOCOL_CONVERTER_CONTROL_0 0x3050 /* DP 1.3 */ -# define DP_HDMI_DVI_OUTPUT_CONFIG (1 << 0) /* DP 1.3 */ -#define DP_PROTOCOL_CONVERTER_CONTROL_1 0x3051 /* DP 1.3 */ -# define DP_CONVERSION_TO_YCBCR420_ENABLE (1 << 0) /* DP 1.3 */ -# define DP_HDMI_EDID_PROCESSING_DISABLE (1 << 1) /* DP 1.4 */ -# define DP_HDMI_AUTONOMOUS_SCRAMBLING_DISABLE (1 << 2) /* DP 1.4 */ -# define DP_HDMI_FORCE_SCRAMBLING (1 << 3) /* DP 1.4 */ -#define DP_PROTOCOL_CONVERTER_CONTROL_2 0x3052 /* DP 1.3 */ -# define DP_CONVERSION_TO_YCBCR422_ENABLE (1 << 0) /* DP 1.3 */ -# define DP_PCON_ENABLE_DSC_ENCODER (1 << 1) -# define DP_PCON_ENCODER_PPS_OVERRIDE_MASK (0x3 << 2) -# define DP_PCON_ENC_PPS_OVERRIDE_DISABLED 0 -# define DP_PCON_ENC_PPS_OVERRIDE_EN_PARAMS 1 -# define DP_PCON_ENC_PPS_OVERRIDE_EN_BUFFER 2 -# define DP_CONVERSION_RGB_YCBCR_MASK (7 << 4) -# define DP_CONVERSION_BT601_RGB_YCBCR_ENABLE (1 << 4) -# define DP_CONVERSION_BT709_RGB_YCBCR_ENABLE (1 << 5) -# define DP_CONVERSION_BT2020_RGB_YCBCR_ENABLE (1 << 6) - -/* PCON Downstream HDMI ERROR Status per Lane */ -#define DP_PCON_HDMI_ERROR_STATUS_LN0 0x3037 -#define DP_PCON_HDMI_ERROR_STATUS_LN1 0x3038 -#define DP_PCON_HDMI_ERROR_STATUS_LN2 0x3039 -#define DP_PCON_HDMI_ERROR_STATUS_LN3 0x303A -# define DP_PCON_HDMI_ERROR_COUNT_MASK (0x7 << 0) -# define DP_PCON_HDMI_ERROR_COUNT_THREE_PLUS (1 << 0) -# define DP_PCON_HDMI_ERROR_COUNT_TEN_PLUS (1 << 1) -# define DP_PCON_HDMI_ERROR_COUNT_HUNDRED_PLUS (1 << 2) - -/* PCON HDMI CONFIG PPS Override Buffer - * Valid Offsets to be added to Base : 0-127 - */ -#define DP_PCON_HDMI_PPS_OVERRIDE_BASE 0x3100 - -/* PCON HDMI CONFIG PPS Override Parameter: Slice height - * Offset-0 8LSBs of the Slice height. - * Offset-1 8MSBs of the Slice height. - */ -#define DP_PCON_HDMI_PPS_OVRD_SLICE_HEIGHT 0x3180 - -/* PCON HDMI CONFIG PPS Override Parameter: Slice width - * Offset-0 8LSBs of the Slice width. - * Offset-1 8MSBs of the Slice width. - */ -#define DP_PCON_HDMI_PPS_OVRD_SLICE_WIDTH 0x3182 - -/* PCON HDMI CONFIG PPS Override Parameter: bits_per_pixel - * Offset-0 8LSBs of the bits_per_pixel. - * Offset-1 2MSBs of the bits_per_pixel. - */ -#define DP_PCON_HDMI_PPS_OVRD_BPP 0x3184 - -/* HDCP 1.3 and HDCP 2.2 */ -#define DP_AUX_HDCP_BKSV 0x68000 -#define DP_AUX_HDCP_RI_PRIME 0x68005 -#define DP_AUX_HDCP_AKSV 0x68007 -#define DP_AUX_HDCP_AN 0x6800C -#define DP_AUX_HDCP_V_PRIME(h) (0x68014 + h * 4) -#define DP_AUX_HDCP_BCAPS 0x68028 -# define DP_BCAPS_REPEATER_PRESENT BIT(1) -# define DP_BCAPS_HDCP_CAPABLE BIT(0) -#define DP_AUX_HDCP_BSTATUS 0x68029 -# define DP_BSTATUS_REAUTH_REQ BIT(3) -# define DP_BSTATUS_LINK_FAILURE BIT(2) -# define DP_BSTATUS_R0_PRIME_READY BIT(1) -# define DP_BSTATUS_READY BIT(0) -#define DP_AUX_HDCP_BINFO 0x6802A -#define DP_AUX_HDCP_KSV_FIFO 0x6802C -#define DP_AUX_HDCP_AINFO 0x6803B - -/* DP HDCP2.2 parameter offsets in DPCD address space */ -#define DP_HDCP_2_2_REG_RTX_OFFSET 0x69000 -#define DP_HDCP_2_2_REG_TXCAPS_OFFSET 0x69008 -#define DP_HDCP_2_2_REG_CERT_RX_OFFSET 0x6900B -#define DP_HDCP_2_2_REG_RRX_OFFSET 0x69215 -#define DP_HDCP_2_2_REG_RX_CAPS_OFFSET 0x6921D -#define DP_HDCP_2_2_REG_EKPUB_KM_OFFSET 0x69220 -#define DP_HDCP_2_2_REG_EKH_KM_WR_OFFSET 0x692A0 -#define DP_HDCP_2_2_REG_M_OFFSET 0x692B0 -#define DP_HDCP_2_2_REG_HPRIME_OFFSET 0x692C0 -#define DP_HDCP_2_2_REG_EKH_KM_RD_OFFSET 0x692E0 -#define DP_HDCP_2_2_REG_RN_OFFSET 0x692F0 -#define DP_HDCP_2_2_REG_LPRIME_OFFSET 0x692F8 -#define DP_HDCP_2_2_REG_EDKEY_KS_OFFSET 0x69318 -#define DP_HDCP_2_2_REG_RIV_OFFSET 0x69328 -#define DP_HDCP_2_2_REG_RXINFO_OFFSET 0x69330 -#define DP_HDCP_2_2_REG_SEQ_NUM_V_OFFSET 0x69332 -#define DP_HDCP_2_2_REG_VPRIME_OFFSET 0x69335 -#define DP_HDCP_2_2_REG_RECV_ID_LIST_OFFSET 0x69345 -#define DP_HDCP_2_2_REG_V_OFFSET 0x693E0 -#define DP_HDCP_2_2_REG_SEQ_NUM_M_OFFSET 0x693F0 -#define DP_HDCP_2_2_REG_K_OFFSET 0x693F3 -#define DP_HDCP_2_2_REG_STREAM_ID_TYPE_OFFSET 0x693F5 -#define DP_HDCP_2_2_REG_MPRIME_OFFSET 0x69473 -#define DP_HDCP_2_2_REG_RXSTATUS_OFFSET 0x69493 -#define DP_HDCP_2_2_REG_STREAM_TYPE_OFFSET 0x69494 -#define DP_HDCP_2_2_REG_DBG_OFFSET 0x69518 - -/* LTTPR: Link Training (LT)-tunable PHY Repeaters */ -#define DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV 0xf0000 /* 1.3 */ -#define DP_MAX_LINK_RATE_PHY_REPEATER 0xf0001 /* 1.4a */ -#define DP_PHY_REPEATER_CNT 0xf0002 /* 1.3 */ -#define DP_PHY_REPEATER_MODE 0xf0003 /* 1.3 */ -#define DP_MAX_LANE_COUNT_PHY_REPEATER 0xf0004 /* 1.4a */ -#define DP_Repeater_FEC_CAPABILITY 0xf0004 /* 1.4 */ -#define DP_PHY_REPEATER_EXTENDED_WAIT_TIMEOUT 0xf0005 /* 1.4a */ -#define DP_MAIN_LINK_CHANNEL_CODING_PHY_REPEATER 0xf0006 /* 2.0 */ -# define DP_PHY_REPEATER_128B132B_SUPPORTED (1 << 0) -/* See DP_128B132B_SUPPORTED_LINK_RATES for values */ -#define DP_PHY_REPEATER_128B132B_RATES 0xf0007 /* 2.0 */ - -enum drm_dp_phy { - DP_PHY_DPRX, - - DP_PHY_LTTPR1, - DP_PHY_LTTPR2, - DP_PHY_LTTPR3, - DP_PHY_LTTPR4, - DP_PHY_LTTPR5, - DP_PHY_LTTPR6, - DP_PHY_LTTPR7, - DP_PHY_LTTPR8, - - DP_MAX_LTTPR_COUNT = DP_PHY_LTTPR8, -}; - -#define DP_PHY_LTTPR(i) (DP_PHY_LTTPR1 + (i)) - -#define __DP_LTTPR1_BASE 0xf0010 /* 1.3 */ -#define __DP_LTTPR2_BASE 0xf0060 /* 1.3 */ -#define DP_LTTPR_BASE(dp_phy) \ - (__DP_LTTPR1_BASE + (__DP_LTTPR2_BASE - __DP_LTTPR1_BASE) * \ - ((dp_phy) - DP_PHY_LTTPR1)) - -#define DP_LTTPR_REG(dp_phy, lttpr1_reg) \ - (DP_LTTPR_BASE(dp_phy) - DP_LTTPR_BASE(DP_PHY_LTTPR1) + (lttpr1_reg)) - -#define DP_TRAINING_PATTERN_SET_PHY_REPEATER1 0xf0010 /* 1.3 */ -#define DP_TRAINING_PATTERN_SET_PHY_REPEATER(dp_phy) \ - DP_LTTPR_REG(dp_phy, DP_TRAINING_PATTERN_SET_PHY_REPEATER1) - -#define DP_TRAINING_LANE0_SET_PHY_REPEATER1 0xf0011 /* 1.3 */ -#define DP_TRAINING_LANE0_SET_PHY_REPEATER(dp_phy) \ - DP_LTTPR_REG(dp_phy, DP_TRAINING_LANE0_SET_PHY_REPEATER1) - -#define DP_TRAINING_LANE1_SET_PHY_REPEATER1 0xf0012 /* 1.3 */ -#define DP_TRAINING_LANE2_SET_PHY_REPEATER1 0xf0013 /* 1.3 */ -#define DP_TRAINING_LANE3_SET_PHY_REPEATER1 0xf0014 /* 1.3 */ -#define DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1 0xf0020 /* 1.4a */ -#define DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER(dp_phy) \ - DP_LTTPR_REG(dp_phy, DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1) - -#define DP_TRANSMITTER_CAPABILITY_PHY_REPEATER1 0xf0021 /* 1.4a */ -# define DP_VOLTAGE_SWING_LEVEL_3_SUPPORTED BIT(0) -# define DP_PRE_EMPHASIS_LEVEL_3_SUPPORTED BIT(1) - -#define DP_128B132B_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1 0xf0022 /* 2.0 */ -#define DP_128B132B_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER(dp_phy) \ - DP_LTTPR_REG(dp_phy, DP_128B132B_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1) -/* see DP_128B132B_TRAINING_AUX_RD_INTERVAL for values */ - -#define DP_LANE0_1_STATUS_PHY_REPEATER1 0xf0030 /* 1.3 */ -#define DP_LANE0_1_STATUS_PHY_REPEATER(dp_phy) \ - DP_LTTPR_REG(dp_phy, DP_LANE0_1_STATUS_PHY_REPEATER1) - -#define DP_LANE2_3_STATUS_PHY_REPEATER1 0xf0031 /* 1.3 */ - -#define DP_LANE_ALIGN_STATUS_UPDATED_PHY_REPEATER1 0xf0032 /* 1.3 */ -#define DP_ADJUST_REQUEST_LANE0_1_PHY_REPEATER1 0xf0033 /* 1.3 */ -#define DP_ADJUST_REQUEST_LANE2_3_PHY_REPEATER1 0xf0034 /* 1.3 */ -#define DP_SYMBOL_ERROR_COUNT_LANE0_PHY_REPEATER1 0xf0035 /* 1.3 */ -#define DP_SYMBOL_ERROR_COUNT_LANE1_PHY_REPEATER1 0xf0037 /* 1.3 */ -#define DP_SYMBOL_ERROR_COUNT_LANE2_PHY_REPEATER1 0xf0039 /* 1.3 */ -#define DP_SYMBOL_ERROR_COUNT_LANE3_PHY_REPEATER1 0xf003b /* 1.3 */ - -#define __DP_FEC1_BASE 0xf0290 /* 1.4 */ -#define __DP_FEC2_BASE 0xf0298 /* 1.4 */ -#define DP_FEC_BASE(dp_phy) \ - (__DP_FEC1_BASE + ((__DP_FEC2_BASE - __DP_FEC1_BASE) * \ - ((dp_phy) - DP_PHY_LTTPR1))) - -#define DP_FEC_REG(dp_phy, fec1_reg) \ - (DP_FEC_BASE(dp_phy) - DP_FEC_BASE(DP_PHY_LTTPR1) + fec1_reg) - -#define DP_FEC_STATUS_PHY_REPEATER1 0xf0290 /* 1.4 */ -#define DP_FEC_STATUS_PHY_REPEATER(dp_phy) \ - DP_FEC_REG(dp_phy, DP_FEC_STATUS_PHY_REPEATER1) - -#define DP_FEC_ERROR_COUNT_PHY_REPEATER1 0xf0291 /* 1.4 */ -#define DP_FEC_CAPABILITY_PHY_REPEATER1 0xf0294 /* 1.4a */ - -#define DP_LTTPR_MAX_ADD 0xf02ff /* 1.4 */ - -#define DP_DPCD_MAX_ADD 0xfffff /* 1.4 */ - -/* Repeater modes */ -#define DP_PHY_REPEATER_MODE_TRANSPARENT 0x55 /* 1.3 */ -#define DP_PHY_REPEATER_MODE_NON_TRANSPARENT 0xaa /* 1.3 */ - -/* DP HDCP message start offsets in DPCD address space */ -#define DP_HDCP_2_2_AKE_INIT_OFFSET DP_HDCP_2_2_REG_RTX_OFFSET -#define DP_HDCP_2_2_AKE_SEND_CERT_OFFSET DP_HDCP_2_2_REG_CERT_RX_OFFSET -#define DP_HDCP_2_2_AKE_NO_STORED_KM_OFFSET DP_HDCP_2_2_REG_EKPUB_KM_OFFSET -#define DP_HDCP_2_2_AKE_STORED_KM_OFFSET DP_HDCP_2_2_REG_EKH_KM_WR_OFFSET -#define DP_HDCP_2_2_AKE_SEND_HPRIME_OFFSET DP_HDCP_2_2_REG_HPRIME_OFFSET -#define DP_HDCP_2_2_AKE_SEND_PAIRING_INFO_OFFSET \ - DP_HDCP_2_2_REG_EKH_KM_RD_OFFSET -#define DP_HDCP_2_2_LC_INIT_OFFSET DP_HDCP_2_2_REG_RN_OFFSET -#define DP_HDCP_2_2_LC_SEND_LPRIME_OFFSET DP_HDCP_2_2_REG_LPRIME_OFFSET -#define DP_HDCP_2_2_SKE_SEND_EKS_OFFSET DP_HDCP_2_2_REG_EDKEY_KS_OFFSET -#define DP_HDCP_2_2_REP_SEND_RECVID_LIST_OFFSET DP_HDCP_2_2_REG_RXINFO_OFFSET -#define DP_HDCP_2_2_REP_SEND_ACK_OFFSET DP_HDCP_2_2_REG_V_OFFSET -#define DP_HDCP_2_2_REP_STREAM_MANAGE_OFFSET DP_HDCP_2_2_REG_SEQ_NUM_M_OFFSET -#define DP_HDCP_2_2_REP_STREAM_READY_OFFSET DP_HDCP_2_2_REG_MPRIME_OFFSET - -#define HDCP_2_2_DP_RXSTATUS_LEN 1 -#define HDCP_2_2_DP_RXSTATUS_READY(x) ((x) & BIT(0)) -#define HDCP_2_2_DP_RXSTATUS_H_PRIME(x) ((x) & BIT(1)) -#define HDCP_2_2_DP_RXSTATUS_PAIRING(x) ((x) & BIT(2)) -#define HDCP_2_2_DP_RXSTATUS_REAUTH_REQ(x) ((x) & BIT(3)) -#define HDCP_2_2_DP_RXSTATUS_LINK_FAILED(x) ((x) & BIT(4)) - -/* DP 1.2 Sideband message defines */ -/* peer device type - DP 1.2a Table 2-92 */ -#define DP_PEER_DEVICE_NONE 0x0 -#define DP_PEER_DEVICE_SOURCE_OR_SST 0x1 -#define DP_PEER_DEVICE_MST_BRANCHING 0x2 -#define DP_PEER_DEVICE_SST_SINK 0x3 -#define DP_PEER_DEVICE_DP_LEGACY_CONV 0x4 - -/* DP 1.2 MST sideband request names DP 1.2a Table 2-80 */ -#define DP_GET_MSG_TRANSACTION_VERSION 0x00 /* DP 1.3 */ -#define DP_LINK_ADDRESS 0x01 -#define DP_CONNECTION_STATUS_NOTIFY 0x02 -#define DP_ENUM_PATH_RESOURCES 0x10 -#define DP_ALLOCATE_PAYLOAD 0x11 -#define DP_QUERY_PAYLOAD 0x12 -#define DP_RESOURCE_STATUS_NOTIFY 0x13 -#define DP_CLEAR_PAYLOAD_ID_TABLE 0x14 -#define DP_REMOTE_DPCD_READ 0x20 -#define DP_REMOTE_DPCD_WRITE 0x21 -#define DP_REMOTE_I2C_READ 0x22 -#define DP_REMOTE_I2C_WRITE 0x23 -#define DP_POWER_UP_PHY 0x24 -#define DP_POWER_DOWN_PHY 0x25 -#define DP_SINK_EVENT_NOTIFY 0x30 -#define DP_QUERY_STREAM_ENC_STATUS 0x38 -#define DP_QUERY_STREAM_ENC_STATUS_STATE_NO_EXIST 0 -#define DP_QUERY_STREAM_ENC_STATUS_STATE_INACTIVE 1 -#define DP_QUERY_STREAM_ENC_STATUS_STATE_ACTIVE 2 - -/* DP 1.2 MST sideband reply types */ -#define DP_SIDEBAND_REPLY_ACK 0x00 -#define DP_SIDEBAND_REPLY_NAK 0x01 - -/* DP 1.2 MST sideband nak reasons - table 2.84 */ -#define DP_NAK_WRITE_FAILURE 0x01 -#define DP_NAK_INVALID_READ 0x02 -#define DP_NAK_CRC_FAILURE 0x03 -#define DP_NAK_BAD_PARAM 0x04 -#define DP_NAK_DEFER 0x05 -#define DP_NAK_LINK_FAILURE 0x06 -#define DP_NAK_NO_RESOURCES 0x07 -#define DP_NAK_DPCD_FAIL 0x08 -#define DP_NAK_I2C_NAK 0x09 -#define DP_NAK_ALLOCATE_FAIL 0x0a - -#define MODE_I2C_START 1 -#define MODE_I2C_WRITE 2 -#define MODE_I2C_READ 4 -#define MODE_I2C_STOP 8 - -/* DP 1.2 MST PORTs - Section 2.5.1 v1.2a spec */ -#define DP_MST_PHYSICAL_PORT_0 0 -#define DP_MST_LOGICAL_PORT_0 8 - -#define DP_LINK_CONSTANT_N_VALUE 0x8000 -#define DP_LINK_STATUS_SIZE 6 -bool drm_dp_channel_eq_ok(const u8 link_status[DP_LINK_STATUS_SIZE], - int lane_count); -bool drm_dp_clock_recovery_ok(const u8 link_status[DP_LINK_STATUS_SIZE], - int lane_count); -u8 drm_dp_get_adjust_request_voltage(const u8 link_status[DP_LINK_STATUS_SIZE], - int lane); -u8 drm_dp_get_adjust_request_pre_emphasis(const u8 link_status[DP_LINK_STATUS_SIZE], - int lane); -u8 drm_dp_get_adjust_tx_ffe_preset(const u8 link_status[DP_LINK_STATUS_SIZE], - int lane); -u8 drm_dp_get_adjust_request_post_cursor(const u8 link_status[DP_LINK_STATUS_SIZE], - unsigned int lane); - -#define DP_BRANCH_OUI_HEADER_SIZE 0xc -#define DP_RECEIVER_CAP_SIZE 0xf -#define DP_DSC_RECEIVER_CAP_SIZE 0xf -#define EDP_PSR_RECEIVER_CAP_SIZE 2 -#define EDP_DISPLAY_CTL_CAP_SIZE 3 -#define DP_LTTPR_COMMON_CAP_SIZE 8 -#define DP_LTTPR_PHY_CAP_SIZE 3 - -int drm_dp_read_clock_recovery_delay(struct drm_dp_aux *aux, const u8 dpcd[DP_RECEIVER_CAP_SIZE], - enum drm_dp_phy dp_phy, bool uhbr); -int drm_dp_read_channel_eq_delay(struct drm_dp_aux *aux, const u8 dpcd[DP_RECEIVER_CAP_SIZE], - enum drm_dp_phy dp_phy, bool uhbr); - -void drm_dp_link_train_clock_recovery_delay(const struct drm_dp_aux *aux, - const u8 dpcd[DP_RECEIVER_CAP_SIZE]); -void drm_dp_lttpr_link_train_clock_recovery_delay(void); -void drm_dp_link_train_channel_eq_delay(const struct drm_dp_aux *aux, - const u8 dpcd[DP_RECEIVER_CAP_SIZE]); -void drm_dp_lttpr_link_train_channel_eq_delay(const struct drm_dp_aux *aux, - const u8 caps[DP_LTTPR_PHY_CAP_SIZE]); - -u8 drm_dp_link_rate_to_bw_code(int link_rate); -int drm_dp_bw_code_to_link_rate(u8 link_bw); - -#define DP_SDP_AUDIO_TIMESTAMP 0x01 -#define DP_SDP_AUDIO_STREAM 0x02 -#define DP_SDP_EXTENSION 0x04 /* DP 1.1 */ -#define DP_SDP_AUDIO_COPYMANAGEMENT 0x05 /* DP 1.2 */ -#define DP_SDP_ISRC 0x06 /* DP 1.2 */ -#define DP_SDP_VSC 0x07 /* DP 1.2 */ -#define DP_SDP_CAMERA_GENERIC(i) (0x08 + (i)) /* 0-7, DP 1.3 */ -#define DP_SDP_PPS 0x10 /* DP 1.4 */ -#define DP_SDP_VSC_EXT_VESA 0x20 /* DP 1.4 */ -#define DP_SDP_VSC_EXT_CEA 0x21 /* DP 1.4 */ -/* 0x80+ CEA-861 infoframe types */ - -/** - * struct dp_sdp_header - DP secondary data packet header - * @HB0: Secondary Data Packet ID - * @HB1: Secondary Data Packet Type - * @HB2: Secondary Data Packet Specific header, Byte 0 - * @HB3: Secondary Data packet Specific header, Byte 1 - */ -struct dp_sdp_header { - u8 HB0; - u8 HB1; - u8 HB2; - u8 HB3; -} __packed; - -#define EDP_SDP_HEADER_REVISION_MASK 0x1F -#define EDP_SDP_HEADER_VALID_PAYLOAD_BYTES 0x1F -#define DP_SDP_PPS_HEADER_PAYLOAD_BYTES_MINUS_1 0x7F - -/** - * struct dp_sdp - DP secondary data packet - * @sdp_header: DP secondary data packet header - * @db: DP secondaray data packet data blocks - * VSC SDP Payload for PSR - * db[0]: Stereo Interface - * db[1]: 0 - PSR State; 1 - Update RFB; 2 - CRC Valid - * db[2]: CRC value bits 7:0 of the R or Cr component - * db[3]: CRC value bits 15:8 of the R or Cr component - * db[4]: CRC value bits 7:0 of the G or Y component - * db[5]: CRC value bits 15:8 of the G or Y component - * db[6]: CRC value bits 7:0 of the B or Cb component - * db[7]: CRC value bits 15:8 of the B or Cb component - * db[8] - db[31]: Reserved - * VSC SDP Payload for Pixel Encoding/Colorimetry Format - * db[0] - db[15]: Reserved - * db[16]: Pixel Encoding and Colorimetry Formats - * db[17]: Dynamic Range and Component Bit Depth - * db[18]: Content Type - * db[19] - db[31]: Reserved - */ -struct dp_sdp { - struct dp_sdp_header sdp_header; - u8 db[32]; -} __packed; - -#define EDP_VSC_PSR_STATE_ACTIVE (1<<0) -#define EDP_VSC_PSR_UPDATE_RFB (1<<1) -#define EDP_VSC_PSR_CRC_VALUES_VALID (1<<2) - -/** - * enum dp_pixelformat - drm DP Pixel encoding formats - * - * This enum is used to indicate DP VSC SDP Pixel encoding formats. - * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through - * DB18] - * - * @DP_PIXELFORMAT_RGB: RGB pixel encoding format - * @DP_PIXELFORMAT_YUV444: YCbCr 4:4:4 pixel encoding format - * @DP_PIXELFORMAT_YUV422: YCbCr 4:2:2 pixel encoding format - * @DP_PIXELFORMAT_YUV420: YCbCr 4:2:0 pixel encoding format - * @DP_PIXELFORMAT_Y_ONLY: Y Only pixel encoding format - * @DP_PIXELFORMAT_RAW: RAW pixel encoding format - * @DP_PIXELFORMAT_RESERVED: Reserved pixel encoding format - */ -enum dp_pixelformat { - DP_PIXELFORMAT_RGB = 0, - DP_PIXELFORMAT_YUV444 = 0x1, - DP_PIXELFORMAT_YUV422 = 0x2, - DP_PIXELFORMAT_YUV420 = 0x3, - DP_PIXELFORMAT_Y_ONLY = 0x4, - DP_PIXELFORMAT_RAW = 0x5, - DP_PIXELFORMAT_RESERVED = 0x6, -}; - -/** - * enum dp_colorimetry - drm DP Colorimetry formats - * - * This enum is used to indicate DP VSC SDP Colorimetry formats. - * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through - * DB18] and a name of enum member follows DRM_MODE_COLORIMETRY definition. - * - * @DP_COLORIMETRY_DEFAULT: sRGB (IEC 61966-2-1) or - * ITU-R BT.601 colorimetry format - * @DP_COLORIMETRY_RGB_WIDE_FIXED: RGB wide gamut fixed point colorimetry format - * @DP_COLORIMETRY_BT709_YCC: ITU-R BT.709 colorimetry format - * @DP_COLORIMETRY_RGB_WIDE_FLOAT: RGB wide gamut floating point - * (scRGB (IEC 61966-2-2)) colorimetry format - * @DP_COLORIMETRY_XVYCC_601: xvYCC601 colorimetry format - * @DP_COLORIMETRY_OPRGB: OpRGB colorimetry format - * @DP_COLORIMETRY_XVYCC_709: xvYCC709 colorimetry format - * @DP_COLORIMETRY_DCI_P3_RGB: DCI-P3 (SMPTE RP 431-2) colorimetry format - * @DP_COLORIMETRY_SYCC_601: sYCC601 colorimetry format - * @DP_COLORIMETRY_RGB_CUSTOM: RGB Custom Color Profile colorimetry format - * @DP_COLORIMETRY_OPYCC_601: opYCC601 colorimetry format - * @DP_COLORIMETRY_BT2020_RGB: ITU-R BT.2020 R' G' B' colorimetry format - * @DP_COLORIMETRY_BT2020_CYCC: ITU-R BT.2020 Y'c C'bc C'rc colorimetry format - * @DP_COLORIMETRY_BT2020_YCC: ITU-R BT.2020 Y' C'b C'r colorimetry format - */ -enum dp_colorimetry { - DP_COLORIMETRY_DEFAULT = 0, - DP_COLORIMETRY_RGB_WIDE_FIXED = 0x1, - DP_COLORIMETRY_BT709_YCC = 0x1, - DP_COLORIMETRY_RGB_WIDE_FLOAT = 0x2, - DP_COLORIMETRY_XVYCC_601 = 0x2, - DP_COLORIMETRY_OPRGB = 0x3, - DP_COLORIMETRY_XVYCC_709 = 0x3, - DP_COLORIMETRY_DCI_P3_RGB = 0x4, - DP_COLORIMETRY_SYCC_601 = 0x4, - DP_COLORIMETRY_RGB_CUSTOM = 0x5, - DP_COLORIMETRY_OPYCC_601 = 0x5, - DP_COLORIMETRY_BT2020_RGB = 0x6, - DP_COLORIMETRY_BT2020_CYCC = 0x6, - DP_COLORIMETRY_BT2020_YCC = 0x7, -}; - -/** - * enum dp_dynamic_range - drm DP Dynamic Range - * - * This enum is used to indicate DP VSC SDP Dynamic Range. - * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through - * DB18] - * - * @DP_DYNAMIC_RANGE_VESA: VESA range - * @DP_DYNAMIC_RANGE_CTA: CTA range - */ -enum dp_dynamic_range { - DP_DYNAMIC_RANGE_VESA = 0, - DP_DYNAMIC_RANGE_CTA = 1, -}; - -/** - * enum dp_content_type - drm DP Content Type - * - * This enum is used to indicate DP VSC SDP Content Types. - * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through - * DB18] - * CTA-861-G defines content types and expected processing by a sink device - * - * @DP_CONTENT_TYPE_NOT_DEFINED: Not defined type - * @DP_CONTENT_TYPE_GRAPHICS: Graphics type - * @DP_CONTENT_TYPE_PHOTO: Photo type - * @DP_CONTENT_TYPE_VIDEO: Video type - * @DP_CONTENT_TYPE_GAME: Game type - */ -enum dp_content_type { - DP_CONTENT_TYPE_NOT_DEFINED = 0x00, - DP_CONTENT_TYPE_GRAPHICS = 0x01, - DP_CONTENT_TYPE_PHOTO = 0x02, - DP_CONTENT_TYPE_VIDEO = 0x03, - DP_CONTENT_TYPE_GAME = 0x04, -}; - -/** - * struct drm_dp_vsc_sdp - drm DP VSC SDP - * - * This structure represents a DP VSC SDP of drm - * It is based on DP 1.4 spec [Table 2-116: VSC SDP Header Bytes] and - * [Table 2-117: VSC SDP Payload for DB16 through DB18] - * - * @sdp_type: secondary-data packet type - * @revision: revision number - * @length: number of valid data bytes - * @pixelformat: pixel encoding format - * @colorimetry: colorimetry format - * @bpc: bit per color - * @dynamic_range: dynamic range information - * @content_type: CTA-861-G defines content types and expected processing by a sink device - */ -struct drm_dp_vsc_sdp { - unsigned char sdp_type; - unsigned char revision; - unsigned char length; - enum dp_pixelformat pixelformat; - enum dp_colorimetry colorimetry; - int bpc; - enum dp_dynamic_range dynamic_range; - enum dp_content_type content_type; -}; - -void drm_dp_vsc_sdp_log(const char *level, struct device *dev, - const struct drm_dp_vsc_sdp *vsc); - -int drm_dp_psr_setup_time(const u8 psr_cap[EDP_PSR_RECEIVER_CAP_SIZE]); - -static inline int -drm_dp_max_link_rate(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return drm_dp_bw_code_to_link_rate(dpcd[DP_MAX_LINK_RATE]); -} - -static inline u8 -drm_dp_max_lane_count(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return dpcd[DP_MAX_LANE_COUNT] & DP_MAX_LANE_COUNT_MASK; -} - -static inline bool -drm_dp_enhanced_frame_cap(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return dpcd[DP_DPCD_REV] >= 0x11 && - (dpcd[DP_MAX_LANE_COUNT] & DP_ENHANCED_FRAME_CAP); -} - -static inline bool -drm_dp_fast_training_cap(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return dpcd[DP_DPCD_REV] >= 0x11 && - (dpcd[DP_MAX_DOWNSPREAD] & DP_NO_AUX_HANDSHAKE_LINK_TRAINING); -} - -static inline bool -drm_dp_tps3_supported(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return dpcd[DP_DPCD_REV] >= 0x12 && - dpcd[DP_MAX_LANE_COUNT] & DP_TPS3_SUPPORTED; -} - -static inline bool -drm_dp_tps4_supported(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return dpcd[DP_DPCD_REV] >= 0x14 && - dpcd[DP_MAX_DOWNSPREAD] & DP_TPS4_SUPPORTED; -} - -static inline u8 -drm_dp_training_pattern_mask(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return (dpcd[DP_DPCD_REV] >= 0x14) ? DP_TRAINING_PATTERN_MASK_1_4 : - DP_TRAINING_PATTERN_MASK; -} - -static inline bool -drm_dp_is_branch(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_PRESENT; -} - -/* DP/eDP DSC support */ -u8 drm_dp_dsc_sink_max_slice_count(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE], - bool is_edp); -u8 drm_dp_dsc_sink_line_buf_depth(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]); -int drm_dp_dsc_sink_supported_input_bpcs(const u8 dsc_dpc[DP_DSC_RECEIVER_CAP_SIZE], - u8 dsc_bpc[3]); - -static inline bool -drm_dp_sink_supports_dsc(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]) -{ - return dsc_dpcd[DP_DSC_SUPPORT - DP_DSC_SUPPORT] & - DP_DSC_DECOMPRESSION_IS_SUPPORTED; -} - -static inline u16 -drm_edp_dsc_sink_output_bpp(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]) -{ - return dsc_dpcd[DP_DSC_MAX_BITS_PER_PIXEL_LOW - DP_DSC_SUPPORT] | - (dsc_dpcd[DP_DSC_MAX_BITS_PER_PIXEL_HI - DP_DSC_SUPPORT] & - DP_DSC_MAX_BITS_PER_PIXEL_HI_MASK << - DP_DSC_MAX_BITS_PER_PIXEL_HI_SHIFT); -} - -static inline u32 -drm_dp_dsc_sink_max_slice_width(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]) -{ - /* Max Slicewidth = Number of Pixels * 320 */ - return dsc_dpcd[DP_DSC_MAX_SLICE_WIDTH - DP_DSC_SUPPORT] * - DP_DSC_SLICE_WIDTH_MULTIPLIER; -} - -/* Forward Error Correction Support on DP 1.4 */ -static inline bool -drm_dp_sink_supports_fec(const u8 fec_capable) -{ - return fec_capable & DP_FEC_CAPABLE; -} - -static inline bool -drm_dp_channel_coding_supported(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return dpcd[DP_MAIN_LINK_CHANNEL_CODING] & DP_CAP_ANSI_8B10B; -} - -static inline bool -drm_dp_alternate_scrambler_reset_cap(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return dpcd[DP_EDP_CONFIGURATION_CAP] & - DP_ALTERNATE_SCRAMBLER_RESET_CAP; -} - -/* Ignore MSA timing for Adaptive Sync support on DP 1.4 */ -static inline bool -drm_dp_sink_can_do_video_without_timing_msa(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return dpcd[DP_DOWN_STREAM_PORT_COUNT] & - DP_MSA_TIMING_PAR_IGNORED; -} - -/** - * drm_edp_backlight_supported() - Check an eDP DPCD for VESA backlight support - * @edp_dpcd: The DPCD to check - * - * Note that currently this function will return %false for panels which support various DPCD - * backlight features but which require the brightness be set through PWM, and don't support setting - * the brightness level via the DPCD. - * - * Returns: %True if @edp_dpcd indicates that VESA backlight controls are supported, %false - * otherwise - */ -static inline bool -drm_edp_backlight_supported(const u8 edp_dpcd[EDP_DISPLAY_CTL_CAP_SIZE]) -{ - return !!(edp_dpcd[1] & DP_EDP_TCON_BACKLIGHT_ADJUSTMENT_CAP); -} - -/* - * DisplayPort AUX channel - */ - -/** - * struct drm_dp_aux_msg - DisplayPort AUX channel transaction - * @address: address of the (first) register to access - * @request: contains the type of transaction (see DP_AUX_* macros) - * @reply: upon completion, contains the reply type of the transaction - * @buffer: pointer to a transmission or reception buffer - * @size: size of @buffer - */ -struct drm_dp_aux_msg { - unsigned int address; - u8 request; - u8 reply; - void *buffer; - size_t size; -}; - -struct cec_adapter; -struct edid; -struct drm_connector; - -/** - * struct drm_dp_aux_cec - DisplayPort CEC-Tunneling-over-AUX - * @lock: mutex protecting this struct - * @adap: the CEC adapter for CEC-Tunneling-over-AUX support. - * @connector: the connector this CEC adapter is associated with - * @unregister_work: unregister the CEC adapter - */ -struct drm_dp_aux_cec { - struct mutex lock; - struct cec_adapter *adap; - struct drm_connector *connector; - struct delayed_work unregister_work; -}; - -/** - * struct drm_dp_aux - DisplayPort AUX channel - * - * An AUX channel can also be used to transport I2C messages to a sink. A - * typical application of that is to access an EDID that's present in the sink - * device. The @transfer() function can also be used to execute such - * transactions. The drm_dp_aux_register() function registers an I2C adapter - * that can be passed to drm_probe_ddc(). Upon removal, drivers should call - * drm_dp_aux_unregister() to remove the I2C adapter. The I2C adapter uses long - * transfers by default; if a partial response is received, the adapter will - * drop down to the size given by the partial response for this transaction - * only. - */ -struct drm_dp_aux { - /** - * @name: user-visible name of this AUX channel and the - * I2C-over-AUX adapter. - * - * It's also used to specify the name of the I2C adapter. If set - * to %NULL, dev_name() of @dev will be used. - */ - const char *name; - - /** - * @ddc: I2C adapter that can be used for I2C-over-AUX - * communication - */ - struct i2c_adapter ddc; - - /** - * @dev: pointer to struct device that is the parent for this - * AUX channel. - */ - struct device *dev; - - /** - * @drm_dev: pointer to the &drm_device that owns this AUX channel. - * Beware, this may be %NULL before drm_dp_aux_register() has been - * called. - * - * It should be set to the &drm_device that will be using this AUX - * channel as early as possible. For many graphics drivers this should - * happen before drm_dp_aux_init(), however it's perfectly fine to set - * this field later so long as it's assigned before calling - * drm_dp_aux_register(). - */ - struct drm_device *drm_dev; - - /** - * @crtc: backpointer to the crtc that is currently using this - * AUX channel - */ - struct drm_crtc *crtc; - - /** - * @hw_mutex: internal mutex used for locking transfers. - * - * Note that if the underlying hardware is shared among multiple - * channels, the driver needs to do additional locking to - * prevent concurrent access. - */ - struct mutex hw_mutex; - - /** - * @crc_work: worker that captures CRCs for each frame - */ - struct work_struct crc_work; - - /** - * @crc_count: counter of captured frame CRCs - */ - u8 crc_count; - - /** - * @transfer: transfers a message representing a single AUX - * transaction. - * - * This is a hardware-specific implementation of how - * transactions are executed that the drivers must provide. - * - * A pointer to a &drm_dp_aux_msg structure describing the - * transaction is passed into this function. Upon success, the - * implementation should return the number of payload bytes that - * were transferred, or a negative error-code on failure. - * - * Helpers will propagate these errors, with the exception of - * the %-EBUSY error, which causes a transaction to be retried. - * On a short, helpers will return %-EPROTO to make it simpler - * to check for failure. - * - * The @transfer() function must only modify the reply field of - * the &drm_dp_aux_msg structure. The retry logic and i2c - * helpers assume this is the case. - * - * Also note that this callback can be called no matter the - * state @dev is in. Drivers that need that device to be powered - * to perform this operation will first need to make sure it's - * been properly enabled. - */ - ssize_t (*transfer)(struct drm_dp_aux *aux, - struct drm_dp_aux_msg *msg); - - /** - * @i2c_nack_count: Counts I2C NACKs, used for DP validation. - */ - unsigned i2c_nack_count; - /** - * @i2c_defer_count: Counts I2C DEFERs, used for DP validation. - */ - unsigned i2c_defer_count; - /** - * @cec: struct containing fields used for CEC-Tunneling-over-AUX. - */ - struct drm_dp_aux_cec cec; - /** - * @is_remote: Is this AUX CH actually using sideband messaging. - */ - bool is_remote; -}; - -ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset, - void *buffer, size_t size); -ssize_t drm_dp_dpcd_write(struct drm_dp_aux *aux, unsigned int offset, - void *buffer, size_t size); - -/** - * drm_dp_dpcd_readb() - read a single byte from the DPCD - * @aux: DisplayPort AUX channel - * @offset: address of the register to read - * @valuep: location where the value of the register will be stored - * - * Returns the number of bytes transferred (1) on success, or a negative - * error code on failure. - */ -static inline ssize_t drm_dp_dpcd_readb(struct drm_dp_aux *aux, - unsigned int offset, u8 *valuep) -{ - return drm_dp_dpcd_read(aux, offset, valuep, 1); -} - -/** - * drm_dp_dpcd_writeb() - write a single byte to the DPCD - * @aux: DisplayPort AUX channel - * @offset: address of the register to write - * @value: value to write to the register - * - * Returns the number of bytes transferred (1) on success, or a negative - * error code on failure. - */ -static inline ssize_t drm_dp_dpcd_writeb(struct drm_dp_aux *aux, - unsigned int offset, u8 value) -{ - return drm_dp_dpcd_write(aux, offset, &value, 1); -} - -int drm_dp_read_dpcd_caps(struct drm_dp_aux *aux, - u8 dpcd[DP_RECEIVER_CAP_SIZE]); - -int drm_dp_dpcd_read_link_status(struct drm_dp_aux *aux, - u8 status[DP_LINK_STATUS_SIZE]); - -int drm_dp_dpcd_read_phy_link_status(struct drm_dp_aux *aux, - enum drm_dp_phy dp_phy, - u8 link_status[DP_LINK_STATUS_SIZE]); - -bool drm_dp_send_real_edid_checksum(struct drm_dp_aux *aux, - u8 real_edid_checksum); - -int drm_dp_read_downstream_info(struct drm_dp_aux *aux, - const u8 dpcd[DP_RECEIVER_CAP_SIZE], - u8 downstream_ports[DP_MAX_DOWNSTREAM_PORTS]); -bool drm_dp_downstream_is_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4], u8 type); -bool drm_dp_downstream_is_tmds(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4], - const struct edid *edid); -int drm_dp_downstream_max_dotclock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4]); -int drm_dp_downstream_max_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4], - const struct edid *edid); -int drm_dp_downstream_min_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4], - const struct edid *edid); -int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4], - const struct edid *edid); -bool drm_dp_downstream_420_passthrough(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4]); -bool drm_dp_downstream_444_to_420_conversion(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4]); -struct drm_display_mode *drm_dp_downstream_mode(struct drm_device *dev, - const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4]); -int drm_dp_downstream_id(struct drm_dp_aux *aux, char id[6]); -void drm_dp_downstream_debug(struct seq_file *m, - const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4], - const struct edid *edid, - struct drm_dp_aux *aux); -enum drm_mode_subconnector -drm_dp_subconnector_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4]); -void drm_dp_set_subconnector_property(struct drm_connector *connector, - enum drm_connector_status status, - const u8 *dpcd, - const u8 port_cap[4]); - -struct drm_dp_desc; -bool drm_dp_read_sink_count_cap(struct drm_connector *connector, - const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const struct drm_dp_desc *desc); -int drm_dp_read_sink_count(struct drm_dp_aux *aux); - -int drm_dp_read_lttpr_common_caps(struct drm_dp_aux *aux, - u8 caps[DP_LTTPR_COMMON_CAP_SIZE]); -int drm_dp_read_lttpr_phy_caps(struct drm_dp_aux *aux, - enum drm_dp_phy dp_phy, - u8 caps[DP_LTTPR_PHY_CAP_SIZE]); -int drm_dp_lttpr_count(const u8 cap[DP_LTTPR_COMMON_CAP_SIZE]); -int drm_dp_lttpr_max_link_rate(const u8 caps[DP_LTTPR_COMMON_CAP_SIZE]); -int drm_dp_lttpr_max_lane_count(const u8 caps[DP_LTTPR_COMMON_CAP_SIZE]); -bool drm_dp_lttpr_voltage_swing_level_3_supported(const u8 caps[DP_LTTPR_PHY_CAP_SIZE]); -bool drm_dp_lttpr_pre_emphasis_level_3_supported(const u8 caps[DP_LTTPR_PHY_CAP_SIZE]); - -void drm_dp_remote_aux_init(struct drm_dp_aux *aux); -void drm_dp_aux_init(struct drm_dp_aux *aux); -int drm_dp_aux_register(struct drm_dp_aux *aux); -void drm_dp_aux_unregister(struct drm_dp_aux *aux); - -int drm_dp_start_crc(struct drm_dp_aux *aux, struct drm_crtc *crtc); -int drm_dp_stop_crc(struct drm_dp_aux *aux); - -struct drm_dp_dpcd_ident { - u8 oui[3]; - u8 device_id[6]; - u8 hw_rev; - u8 sw_major_rev; - u8 sw_minor_rev; -} __packed; - -/** - * struct drm_dp_desc - DP branch/sink device descriptor - * @ident: DP device identification from DPCD 0x400 (sink) or 0x500 (branch). - * @quirks: Quirks; use drm_dp_has_quirk() to query for the quirks. - */ -struct drm_dp_desc { - struct drm_dp_dpcd_ident ident; - u32 quirks; -}; - -int drm_dp_read_desc(struct drm_dp_aux *aux, struct drm_dp_desc *desc, - bool is_branch); - -/** - * enum drm_dp_quirk - Display Port sink/branch device specific quirks - * - * Display Port sink and branch devices in the wild have a variety of bugs, try - * to collect them here. The quirks are shared, but it's up to the drivers to - * implement workarounds for them. - */ -enum drm_dp_quirk { - /** - * @DP_DPCD_QUIRK_CONSTANT_N: - * - * The device requires main link attributes Mvid and Nvid to be limited - * to 16 bits. So will give a constant value (0x8000) for compatability. - */ - DP_DPCD_QUIRK_CONSTANT_N, - /** - * @DP_DPCD_QUIRK_NO_PSR: - * - * The device does not support PSR even if reports that it supports or - * driver still need to implement proper handling for such device. - */ - DP_DPCD_QUIRK_NO_PSR, - /** - * @DP_DPCD_QUIRK_NO_SINK_COUNT: - * - * The device does not set SINK_COUNT to a non-zero value. - * The driver should ignore SINK_COUNT during detection. Note that - * drm_dp_read_sink_count_cap() automatically checks for this quirk. - */ - DP_DPCD_QUIRK_NO_SINK_COUNT, - /** - * @DP_DPCD_QUIRK_DSC_WITHOUT_VIRTUAL_DPCD: - * - * The device supports MST DSC despite not supporting Virtual DPCD. - * The DSC caps can be read from the physical aux instead. - */ - DP_DPCD_QUIRK_DSC_WITHOUT_VIRTUAL_DPCD, - /** - * @DP_DPCD_QUIRK_CAN_DO_MAX_LINK_RATE_3_24_GBPS: - * - * The device supports a link rate of 3.24 Gbps (multiplier 0xc) despite - * the DP_MAX_LINK_RATE register reporting a lower max multiplier. - */ - DP_DPCD_QUIRK_CAN_DO_MAX_LINK_RATE_3_24_GBPS, -}; - -/** - * drm_dp_has_quirk() - does the DP device have a specific quirk - * @desc: Device descriptor filled by drm_dp_read_desc() - * @quirk: Quirk to query for - * - * Return true if DP device identified by @desc has @quirk. - */ -static inline bool -drm_dp_has_quirk(const struct drm_dp_desc *desc, enum drm_dp_quirk quirk) -{ - return desc->quirks & BIT(quirk); -} - -/** - * struct drm_edp_backlight_info - Probed eDP backlight info struct - * @pwmgen_bit_count: The pwmgen bit count - * @pwm_freq_pre_divider: The PWM frequency pre-divider value being used for this backlight, if any - * @max: The maximum backlight level that may be set - * @lsb_reg_used: Do we also write values to the DP_EDP_BACKLIGHT_BRIGHTNESS_LSB register? - * @aux_enable: Does the panel support the AUX enable cap? - * @aux_set: Does the panel support setting the brightness through AUX? - * - * This structure contains various data about an eDP backlight, which can be populated by using - * drm_edp_backlight_init(). - */ -struct drm_edp_backlight_info { - u8 pwmgen_bit_count; - u8 pwm_freq_pre_divider; - u16 max; - - bool lsb_reg_used : 1; - bool aux_enable : 1; - bool aux_set : 1; -}; - -int -drm_edp_backlight_init(struct drm_dp_aux *aux, struct drm_edp_backlight_info *bl, - u16 driver_pwm_freq_hz, const u8 edp_dpcd[EDP_DISPLAY_CTL_CAP_SIZE], - u16 *current_level, u8 *current_mode); -int drm_edp_backlight_set_level(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl, - u16 level); -int drm_edp_backlight_enable(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl, - u16 level); -int drm_edp_backlight_disable(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl); - -#if IS_ENABLED(CONFIG_DRM_KMS_HELPER) && (IS_BUILTIN(CONFIG_BACKLIGHT_CLASS_DEVICE) || \ - (IS_MODULE(CONFIG_DRM_KMS_HELPER) && IS_MODULE(CONFIG_BACKLIGHT_CLASS_DEVICE))) - -int drm_panel_dp_aux_backlight(struct drm_panel *panel, struct drm_dp_aux *aux); - -#else - -static inline int drm_panel_dp_aux_backlight(struct drm_panel *panel, - struct drm_dp_aux *aux) -{ - return 0; -} - -#endif - -#ifdef CONFIG_DRM_DP_CEC -void drm_dp_cec_irq(struct drm_dp_aux *aux); -void drm_dp_cec_register_connector(struct drm_dp_aux *aux, - struct drm_connector *connector); -void drm_dp_cec_unregister_connector(struct drm_dp_aux *aux); -void drm_dp_cec_set_edid(struct drm_dp_aux *aux, const struct edid *edid); -void drm_dp_cec_unset_edid(struct drm_dp_aux *aux); -#else -static inline void drm_dp_cec_irq(struct drm_dp_aux *aux) -{ -} - -static inline void -drm_dp_cec_register_connector(struct drm_dp_aux *aux, - struct drm_connector *connector) -{ -} - -static inline void drm_dp_cec_unregister_connector(struct drm_dp_aux *aux) -{ -} - -static inline void drm_dp_cec_set_edid(struct drm_dp_aux *aux, - const struct edid *edid) -{ -} - -static inline void drm_dp_cec_unset_edid(struct drm_dp_aux *aux) -{ -} - -#endif - -/** - * struct drm_dp_phy_test_params - DP Phy Compliance parameters - * @link_rate: Requested Link rate from DPCD 0x219 - * @num_lanes: Number of lanes requested by sing through DPCD 0x220 - * @phy_pattern: DP Phy test pattern from DPCD 0x248 - * @hbr2_reset: DP HBR2_COMPLIANCE_SCRAMBLER_RESET from DCPD 0x24A and 0x24B - * @custom80: DP Test_80BIT_CUSTOM_PATTERN from DPCDs 0x250 through 0x259 - * @enhanced_frame_cap: flag for enhanced frame capability. - */ -struct drm_dp_phy_test_params { - int link_rate; - u8 num_lanes; - u8 phy_pattern; - u8 hbr2_reset[2]; - u8 custom80[10]; - bool enhanced_frame_cap; -}; - -int drm_dp_get_phy_test_pattern(struct drm_dp_aux *aux, - struct drm_dp_phy_test_params *data); -int drm_dp_set_phy_test_pattern(struct drm_dp_aux *aux, - struct drm_dp_phy_test_params *data, u8 dp_rev); -int drm_dp_get_pcon_max_frl_bw(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4]); -int drm_dp_pcon_frl_prepare(struct drm_dp_aux *aux, bool enable_frl_ready_hpd); -bool drm_dp_pcon_is_frl_ready(struct drm_dp_aux *aux); -int drm_dp_pcon_frl_configure_1(struct drm_dp_aux *aux, int max_frl_gbps, - u8 frl_mode); -int drm_dp_pcon_frl_configure_2(struct drm_dp_aux *aux, int max_frl_mask, - u8 frl_type); -int drm_dp_pcon_reset_frl_config(struct drm_dp_aux *aux); -int drm_dp_pcon_frl_enable(struct drm_dp_aux *aux); - -bool drm_dp_pcon_hdmi_link_active(struct drm_dp_aux *aux); -int drm_dp_pcon_hdmi_link_mode(struct drm_dp_aux *aux, u8 *frl_trained_mask); -void drm_dp_pcon_hdmi_frl_link_error_count(struct drm_dp_aux *aux, - struct drm_connector *connector); -bool drm_dp_pcon_enc_is_dsc_1_2(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]); -int drm_dp_pcon_dsc_max_slices(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]); -int drm_dp_pcon_dsc_max_slice_width(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]); -int drm_dp_pcon_dsc_bpp_incr(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]); -int drm_dp_pcon_pps_default(struct drm_dp_aux *aux); -int drm_dp_pcon_pps_override_buf(struct drm_dp_aux *aux, u8 pps_buf[128]); -int drm_dp_pcon_pps_override_param(struct drm_dp_aux *aux, u8 pps_param[6]); -bool drm_dp_downstream_rgb_to_ycbcr_conversion(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4], u8 color_spc); -int drm_dp_pcon_convert_rgb_to_ycbcr(struct drm_dp_aux *aux, u8 color_spc); - -#endif /* _DRM_DP_HELPER_H_ */ diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h deleted file mode 100644 index 78044ac5b59b..000000000000 --- a/include/drm/drm_dp_mst_helper.h +++ /dev/null @@ -1,972 +0,0 @@ -/* - * Copyright © 2014 Red Hat. - * - * Permission to use, copy, modify, distribute, and sell this software and its - * documentation for any purpose is hereby granted without fee, provided that - * the above copyright notice appear in all copies and that both that copyright - * notice and this permission notice appear in supporting documentation, and - * that the name of the copyright holders not be used in advertising or - * publicity pertaining to distribution of the software without specific, - * written prior permission. The copyright holders make no representations - * about the suitability of this software for any purpose. It is provided "as - * is" without express or implied warranty. - * - * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, - * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO - * EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT OR - * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, - * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER - * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE - * OF THIS SOFTWARE. - */ -#ifndef _DRM_DP_MST_HELPER_H_ -#define _DRM_DP_MST_HELPER_H_ - -#include -#include -#include - -#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) -#include -#include - -enum drm_dp_mst_topology_ref_type { - DRM_DP_MST_TOPOLOGY_REF_GET, - DRM_DP_MST_TOPOLOGY_REF_PUT, -}; - -struct drm_dp_mst_topology_ref_history { - struct drm_dp_mst_topology_ref_entry { - enum drm_dp_mst_topology_ref_type type; - int count; - ktime_t ts_nsec; - depot_stack_handle_t backtrace; - } *entries; - int len; -}; -#endif /* IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) */ - -struct drm_dp_mst_branch; - -/** - * struct drm_dp_vcpi - Virtual Channel Payload Identifier - * @vcpi: Virtual channel ID. - * @pbn: Payload Bandwidth Number for this channel - * @aligned_pbn: PBN aligned with slot size - * @num_slots: number of slots for this PBN - */ -struct drm_dp_vcpi { - int vcpi; - int pbn; - int aligned_pbn; - int num_slots; -}; - -/** - * struct drm_dp_mst_port - MST port - * @port_num: port number - * @input: if this port is an input port. Protected by - * &drm_dp_mst_topology_mgr.base.lock. - * @mcs: message capability status - DP 1.2 spec. Protected by - * &drm_dp_mst_topology_mgr.base.lock. - * @ddps: DisplayPort Device Plug Status - DP 1.2. Protected by - * &drm_dp_mst_topology_mgr.base.lock. - * @pdt: Peer Device Type. Protected by - * &drm_dp_mst_topology_mgr.base.lock. - * @ldps: Legacy Device Plug Status. Protected by - * &drm_dp_mst_topology_mgr.base.lock. - * @dpcd_rev: DPCD revision of device on this port. Protected by - * &drm_dp_mst_topology_mgr.base.lock. - * @num_sdp_streams: Number of simultaneous streams. Protected by - * &drm_dp_mst_topology_mgr.base.lock. - * @num_sdp_stream_sinks: Number of stream sinks. Protected by - * &drm_dp_mst_topology_mgr.base.lock. - * @full_pbn: Max possible bandwidth for this port. Protected by - * &drm_dp_mst_topology_mgr.base.lock. - * @next: link to next port on this branch device - * @aux: i2c aux transport to talk to device connected to this port, protected - * by &drm_dp_mst_topology_mgr.base.lock. - * @parent: branch device parent of this port - * @vcpi: Virtual Channel Payload info for this port. - * @connector: DRM connector this port is connected to. Protected by - * &drm_dp_mst_topology_mgr.base.lock. - * @mgr: topology manager this port lives under. - * - * This structure represents an MST port endpoint on a device somewhere - * in the MST topology. - */ -struct drm_dp_mst_port { - /** - * @topology_kref: refcount for this port's lifetime in the topology, - * only the DP MST helpers should need to touch this - */ - struct kref topology_kref; - - /** - * @malloc_kref: refcount for the memory allocation containing this - * structure. See drm_dp_mst_get_port_malloc() and - * drm_dp_mst_put_port_malloc(). - */ - struct kref malloc_kref; - -#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) - /** - * @topology_ref_history: A history of each topology - * reference/dereference. See CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS. - */ - struct drm_dp_mst_topology_ref_history topology_ref_history; -#endif - - u8 port_num; - bool input; - bool mcs; - bool ddps; - u8 pdt; - bool ldps; - u8 dpcd_rev; - u8 num_sdp_streams; - u8 num_sdp_stream_sinks; - uint16_t full_pbn; - struct list_head next; - /** - * @mstb: the branch device connected to this port, if there is one. - * This should be considered protected for reading by - * &drm_dp_mst_topology_mgr.lock. There are two exceptions to this: - * &drm_dp_mst_topology_mgr.up_req_work and - * &drm_dp_mst_topology_mgr.work, which do not grab - * &drm_dp_mst_topology_mgr.lock during reads but are the only - * updaters of this list and are protected from writing concurrently - * by &drm_dp_mst_topology_mgr.probe_lock. - */ - struct drm_dp_mst_branch *mstb; - struct drm_dp_aux aux; /* i2c bus for this port? */ - struct drm_dp_mst_branch *parent; - - struct drm_dp_vcpi vcpi; - struct drm_connector *connector; - struct drm_dp_mst_topology_mgr *mgr; - - /** - * @cached_edid: for DP logical ports - make tiling work by ensuring - * that the EDID for all connectors is read immediately. - */ - struct edid *cached_edid; - /** - * @has_audio: Tracks whether the sink connector to this port is - * audio-capable. - */ - bool has_audio; - - /** - * @fec_capable: bool indicating if FEC can be supported up to that - * point in the MST topology. - */ - bool fec_capable; -}; - -/* sideband msg header - not bit struct */ -struct drm_dp_sideband_msg_hdr { - u8 lct; - u8 lcr; - u8 rad[8]; - bool broadcast; - bool path_msg; - u8 msg_len; - bool somt; - bool eomt; - bool seqno; -}; - -struct drm_dp_sideband_msg_rx { - u8 chunk[48]; - u8 msg[256]; - u8 curchunk_len; - u8 curchunk_idx; /* chunk we are parsing now */ - u8 curchunk_hdrlen; - u8 curlen; /* total length of the msg */ - bool have_somt; - bool have_eomt; - struct drm_dp_sideband_msg_hdr initial_hdr; -}; - -/** - * struct drm_dp_mst_branch - MST branch device. - * @rad: Relative Address to talk to this branch device. - * @lct: Link count total to talk to this branch device. - * @num_ports: number of ports on the branch. - * @port_parent: pointer to the port parent, NULL if toplevel. - * @mgr: topology manager for this branch device. - * @link_address_sent: if a link address message has been sent to this device yet. - * @guid: guid for DP 1.2 branch device. port under this branch can be - * identified by port #. - * - * This structure represents an MST branch device, there is one - * primary branch device at the root, along with any other branches connected - * to downstream port of parent branches. - */ -struct drm_dp_mst_branch { - /** - * @topology_kref: refcount for this branch device's lifetime in the - * topology, only the DP MST helpers should need to touch this - */ - struct kref topology_kref; - - /** - * @malloc_kref: refcount for the memory allocation containing this - * structure. See drm_dp_mst_get_mstb_malloc() and - * drm_dp_mst_put_mstb_malloc(). - */ - struct kref malloc_kref; - -#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) - /** - * @topology_ref_history: A history of each topology - * reference/dereference. See CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS. - */ - struct drm_dp_mst_topology_ref_history topology_ref_history; -#endif - - /** - * @destroy_next: linked-list entry used by - * drm_dp_delayed_destroy_work() - */ - struct list_head destroy_next; - - u8 rad[8]; - u8 lct; - int num_ports; - - /** - * @ports: the list of ports on this branch device. This should be - * considered protected for reading by &drm_dp_mst_topology_mgr.lock. - * There are two exceptions to this: - * &drm_dp_mst_topology_mgr.up_req_work and - * &drm_dp_mst_topology_mgr.work, which do not grab - * &drm_dp_mst_topology_mgr.lock during reads but are the only - * updaters of this list and are protected from updating the list - * concurrently by @drm_dp_mst_topology_mgr.probe_lock - */ - struct list_head ports; - - struct drm_dp_mst_port *port_parent; - struct drm_dp_mst_topology_mgr *mgr; - - bool link_address_sent; - - /* global unique identifier to identify branch devices */ - u8 guid[16]; -}; - - -struct drm_dp_nak_reply { - u8 guid[16]; - u8 reason; - u8 nak_data; -}; - -struct drm_dp_link_address_ack_reply { - u8 guid[16]; - u8 nports; - struct drm_dp_link_addr_reply_port { - bool input_port; - u8 peer_device_type; - u8 port_number; - bool mcs; - bool ddps; - bool legacy_device_plug_status; - u8 dpcd_revision; - u8 peer_guid[16]; - u8 num_sdp_streams; - u8 num_sdp_stream_sinks; - } ports[16]; -}; - -struct drm_dp_remote_dpcd_read_ack_reply { - u8 port_number; - u8 num_bytes; - u8 bytes[255]; -}; - -struct drm_dp_remote_dpcd_write_ack_reply { - u8 port_number; -}; - -struct drm_dp_remote_dpcd_write_nak_reply { - u8 port_number; - u8 reason; - u8 bytes_written_before_failure; -}; - -struct drm_dp_remote_i2c_read_ack_reply { - u8 port_number; - u8 num_bytes; - u8 bytes[255]; -}; - -struct drm_dp_remote_i2c_read_nak_reply { - u8 port_number; - u8 nak_reason; - u8 i2c_nak_transaction; -}; - -struct drm_dp_remote_i2c_write_ack_reply { - u8 port_number; -}; - -struct drm_dp_query_stream_enc_status_ack_reply { - /* Bit[23:16]- Stream Id */ - u8 stream_id; - - /* Bit[15]- Signed */ - bool reply_signed; - - /* Bit[10:8]- Stream Output Sink Type */ - bool unauthorizable_device_present; - bool legacy_device_present; - bool query_capable_device_present; - - /* Bit[12:11]- Stream Output CP Type */ - bool hdcp_1x_device_present; - bool hdcp_2x_device_present; - - /* Bit[4]- Stream Authentication */ - bool auth_completed; - - /* Bit[3]- Stream Encryption */ - bool encryption_enabled; - - /* Bit[2]- Stream Repeater Function Present */ - bool repeater_present; - - /* Bit[1:0]- Stream State */ - u8 state; -}; - -#define DRM_DP_MAX_SDP_STREAMS 16 -struct drm_dp_allocate_payload { - u8 port_number; - u8 number_sdp_streams; - u8 vcpi; - u16 pbn; - u8 sdp_stream_sink[DRM_DP_MAX_SDP_STREAMS]; -}; - -struct drm_dp_allocate_payload_ack_reply { - u8 port_number; - u8 vcpi; - u16 allocated_pbn; -}; - -struct drm_dp_connection_status_notify { - u8 guid[16]; - u8 port_number; - bool legacy_device_plug_status; - bool displayport_device_plug_status; - bool message_capability_status; - bool input_port; - u8 peer_device_type; -}; - -struct drm_dp_remote_dpcd_read { - u8 port_number; - u32 dpcd_address; - u8 num_bytes; -}; - -struct drm_dp_remote_dpcd_write { - u8 port_number; - u32 dpcd_address; - u8 num_bytes; - u8 *bytes; -}; - -#define DP_REMOTE_I2C_READ_MAX_TRANSACTIONS 4 -struct drm_dp_remote_i2c_read { - u8 num_transactions; - u8 port_number; - struct drm_dp_remote_i2c_read_tx { - u8 i2c_dev_id; - u8 num_bytes; - u8 *bytes; - u8 no_stop_bit; - u8 i2c_transaction_delay; - } transactions[DP_REMOTE_I2C_READ_MAX_TRANSACTIONS]; - u8 read_i2c_device_id; - u8 num_bytes_read; -}; - -struct drm_dp_remote_i2c_write { - u8 port_number; - u8 write_i2c_device_id; - u8 num_bytes; - u8 *bytes; -}; - -struct drm_dp_query_stream_enc_status { - u8 stream_id; - u8 client_id[7]; /* 56-bit nonce */ - u8 stream_event; - bool valid_stream_event; - u8 stream_behavior; - u8 valid_stream_behavior; -}; - -/* this covers ENUM_RESOURCES, POWER_DOWN_PHY, POWER_UP_PHY */ -struct drm_dp_port_number_req { - u8 port_number; -}; - -struct drm_dp_enum_path_resources_ack_reply { - u8 port_number; - bool fec_capable; - u16 full_payload_bw_number; - u16 avail_payload_bw_number; -}; - -/* covers POWER_DOWN_PHY, POWER_UP_PHY */ -struct drm_dp_port_number_rep { - u8 port_number; -}; - -struct drm_dp_query_payload { - u8 port_number; - u8 vcpi; -}; - -struct drm_dp_resource_status_notify { - u8 port_number; - u8 guid[16]; - u16 available_pbn; -}; - -struct drm_dp_query_payload_ack_reply { - u8 port_number; - u16 allocated_pbn; -}; - -struct drm_dp_sideband_msg_req_body { - u8 req_type; - union ack_req { - struct drm_dp_connection_status_notify conn_stat; - struct drm_dp_port_number_req port_num; - struct drm_dp_resource_status_notify resource_stat; - - struct drm_dp_query_payload query_payload; - struct drm_dp_allocate_payload allocate_payload; - - struct drm_dp_remote_dpcd_read dpcd_read; - struct drm_dp_remote_dpcd_write dpcd_write; - - struct drm_dp_remote_i2c_read i2c_read; - struct drm_dp_remote_i2c_write i2c_write; - - struct drm_dp_query_stream_enc_status enc_status; - } u; -}; - -struct drm_dp_sideband_msg_reply_body { - u8 reply_type; - u8 req_type; - union ack_replies { - struct drm_dp_nak_reply nak; - struct drm_dp_link_address_ack_reply link_addr; - struct drm_dp_port_number_rep port_number; - - struct drm_dp_enum_path_resources_ack_reply path_resources; - struct drm_dp_allocate_payload_ack_reply allocate_payload; - struct drm_dp_query_payload_ack_reply query_payload; - - struct drm_dp_remote_dpcd_read_ack_reply remote_dpcd_read_ack; - struct drm_dp_remote_dpcd_write_ack_reply remote_dpcd_write_ack; - struct drm_dp_remote_dpcd_write_nak_reply remote_dpcd_write_nack; - - struct drm_dp_remote_i2c_read_ack_reply remote_i2c_read_ack; - struct drm_dp_remote_i2c_read_nak_reply remote_i2c_read_nack; - struct drm_dp_remote_i2c_write_ack_reply remote_i2c_write_ack; - - struct drm_dp_query_stream_enc_status_ack_reply enc_status; - } u; -}; - -/* msg is queued to be put into a slot */ -#define DRM_DP_SIDEBAND_TX_QUEUED 0 -/* msg has started transmitting on a slot - still on msgq */ -#define DRM_DP_SIDEBAND_TX_START_SEND 1 -/* msg has finished transmitting on a slot - removed from msgq only in slot */ -#define DRM_DP_SIDEBAND_TX_SENT 2 -/* msg has received a response - removed from slot */ -#define DRM_DP_SIDEBAND_TX_RX 3 -#define DRM_DP_SIDEBAND_TX_TIMEOUT 4 - -struct drm_dp_sideband_msg_tx { - u8 msg[256]; - u8 chunk[48]; - u8 cur_offset; - u8 cur_len; - struct drm_dp_mst_branch *dst; - struct list_head next; - int seqno; - int state; - bool path_msg; - struct drm_dp_sideband_msg_reply_body reply; -}; - -/* sideband msg handler */ -struct drm_dp_mst_topology_mgr; -struct drm_dp_mst_topology_cbs { - /* create a connector for a port */ - struct drm_connector *(*add_connector)(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port, const char *path); - /* - * Checks for any pending MST interrupts, passing them to MST core for - * processing, the same way an HPD IRQ pulse handler would do this. - * If provided MST core calls this callback from a poll-waiting loop - * when waiting for MST down message replies. The driver is expected - * to guard against a race between this callback and the driver's HPD - * IRQ pulse handler. - */ - void (*poll_hpd_irq)(struct drm_dp_mst_topology_mgr *mgr); -}; - -#define DP_MAX_PAYLOAD (sizeof(unsigned long) * 8) - -#define DP_PAYLOAD_LOCAL 1 -#define DP_PAYLOAD_REMOTE 2 -#define DP_PAYLOAD_DELETE_LOCAL 3 - -struct drm_dp_payload { - int payload_state; - int start_slot; - int num_slots; - int vcpi; -}; - -#define to_dp_mst_topology_state(x) container_of(x, struct drm_dp_mst_topology_state, base) - -struct drm_dp_vcpi_allocation { - struct drm_dp_mst_port *port; - int vcpi; - int pbn; - bool dsc_enabled; - struct list_head next; -}; - -struct drm_dp_mst_topology_state { - struct drm_private_state base; - struct list_head vcpis; - struct drm_dp_mst_topology_mgr *mgr; - u8 total_avail_slots; - u8 start_slot; -}; - -#define to_dp_mst_topology_mgr(x) container_of(x, struct drm_dp_mst_topology_mgr, base) - -/** - * struct drm_dp_mst_topology_mgr - DisplayPort MST manager - * - * This struct represents the toplevel displayport MST topology manager. - * There should be one instance of this for every MST capable DP connector - * on the GPU. - */ -struct drm_dp_mst_topology_mgr { - /** - * @base: Base private object for atomic - */ - struct drm_private_obj base; - - /** - * @dev: device pointer for adding i2c devices etc. - */ - struct drm_device *dev; - /** - * @cbs: callbacks for connector addition and destruction. - */ - const struct drm_dp_mst_topology_cbs *cbs; - /** - * @max_dpcd_transaction_bytes: maximum number of bytes to read/write - * in one go. - */ - int max_dpcd_transaction_bytes; - /** - * @aux: AUX channel for the DP MST connector this topolgy mgr is - * controlling. - */ - struct drm_dp_aux *aux; - /** - * @max_payloads: maximum number of payloads the GPU can generate. - */ - int max_payloads; - /** - * @max_lane_count: maximum number of lanes the GPU can drive. - */ - int max_lane_count; - /** - * @max_link_rate: maximum link rate per lane GPU can output, in kHz. - */ - int max_link_rate; - /** - * @conn_base_id: DRM connector ID this mgr is connected to. Only used - * to build the MST connector path value. - */ - int conn_base_id; - - /** - * @up_req_recv: Message receiver state for up requests. - */ - struct drm_dp_sideband_msg_rx up_req_recv; - - /** - * @down_rep_recv: Message receiver state for replies to down - * requests. - */ - struct drm_dp_sideband_msg_rx down_rep_recv; - - /** - * @lock: protects @mst_state, @mst_primary, @dpcd, and - * @payload_id_table_cleared. - */ - struct mutex lock; - - /** - * @probe_lock: Prevents @work and @up_req_work, the only writers of - * &drm_dp_mst_port.mstb and &drm_dp_mst_branch.ports, from racing - * while they update the topology. - */ - struct mutex probe_lock; - - /** - * @mst_state: If this manager is enabled for an MST capable port. False - * if no MST sink/branch devices is connected. - */ - bool mst_state : 1; - - /** - * @payload_id_table_cleared: Whether or not we've cleared the payload - * ID table for @mst_primary. Protected by @lock. - */ - bool payload_id_table_cleared : 1; - - /** - * @mst_primary: Pointer to the primary/first branch device. - */ - struct drm_dp_mst_branch *mst_primary; - - /** - * @dpcd: Cache of DPCD for primary port. - */ - u8 dpcd[DP_RECEIVER_CAP_SIZE]; - /** - * @sink_count: Sink count from DEVICE_SERVICE_IRQ_VECTOR_ESI0. - */ - u8 sink_count; - /** - * @pbn_div: PBN to slots divisor. - */ - int pbn_div; - - /** - * @funcs: Atomic helper callbacks - */ - const struct drm_private_state_funcs *funcs; - - /** - * @qlock: protects @tx_msg_downq and &drm_dp_sideband_msg_tx.state - */ - struct mutex qlock; - - /** - * @tx_msg_downq: List of pending down requests - */ - struct list_head tx_msg_downq; - - /** - * @payload_lock: Protect payload information. - */ - struct mutex payload_lock; - /** - * @proposed_vcpis: Array of pointers for the new VCPI allocation. The - * VCPI structure itself is &drm_dp_mst_port.vcpi, and the size of - * this array is determined by @max_payloads. - */ - struct drm_dp_vcpi **proposed_vcpis; - /** - * @payloads: Array of payloads. The size of this array is determined - * by @max_payloads. - */ - struct drm_dp_payload *payloads; - /** - * @payload_mask: Elements of @payloads actually in use. Since - * reallocation of active outputs isn't possible gaps can be created by - * disabling outputs out of order compared to how they've been enabled. - */ - unsigned long payload_mask; - /** - * @vcpi_mask: Similar to @payload_mask, but for @proposed_vcpis. - */ - unsigned long vcpi_mask; - - /** - * @tx_waitq: Wait to queue stall for the tx worker. - */ - wait_queue_head_t tx_waitq; - /** - * @work: Probe work. - */ - struct work_struct work; - /** - * @tx_work: Sideband transmit worker. This can nest within the main - * @work worker for each transaction @work launches. - */ - struct work_struct tx_work; - - /** - * @destroy_port_list: List of to be destroyed connectors. - */ - struct list_head destroy_port_list; - /** - * @destroy_branch_device_list: List of to be destroyed branch - * devices. - */ - struct list_head destroy_branch_device_list; - /** - * @delayed_destroy_lock: Protects @destroy_port_list and - * @destroy_branch_device_list. - */ - struct mutex delayed_destroy_lock; - - /** - * @delayed_destroy_wq: Workqueue used for delayed_destroy_work items. - * A dedicated WQ makes it possible to drain any requeued work items - * on it. - */ - struct workqueue_struct *delayed_destroy_wq; - - /** - * @delayed_destroy_work: Work item to destroy MST port and branch - * devices, needed to avoid locking inversion. - */ - struct work_struct delayed_destroy_work; - - /** - * @up_req_list: List of pending up requests from the topology that - * need to be processed, in chronological order. - */ - struct list_head up_req_list; - /** - * @up_req_lock: Protects @up_req_list - */ - struct mutex up_req_lock; - /** - * @up_req_work: Work item to process up requests received from the - * topology. Needed to avoid blocking hotplug handling and sideband - * transmissions. - */ - struct work_struct up_req_work; - -#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) - /** - * @topology_ref_history_lock: protects - * &drm_dp_mst_port.topology_ref_history and - * &drm_dp_mst_branch.topology_ref_history. - */ - struct mutex topology_ref_history_lock; -#endif -}; - -int drm_dp_mst_topology_mgr_init(struct drm_dp_mst_topology_mgr *mgr, - struct drm_device *dev, struct drm_dp_aux *aux, - int max_dpcd_transaction_bytes, - int max_payloads, - int max_lane_count, int max_link_rate, - int conn_base_id); - -void drm_dp_mst_topology_mgr_destroy(struct drm_dp_mst_topology_mgr *mgr); - -bool drm_dp_read_mst_cap(struct drm_dp_aux *aux, const u8 dpcd[DP_RECEIVER_CAP_SIZE]); -int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool mst_state); - -int drm_dp_mst_hpd_irq(struct drm_dp_mst_topology_mgr *mgr, u8 *esi, bool *handled); - - -int -drm_dp_mst_detect_port(struct drm_connector *connector, - struct drm_modeset_acquire_ctx *ctx, - struct drm_dp_mst_topology_mgr *mgr, - struct drm_dp_mst_port *port); - -struct edid *drm_dp_mst_get_edid(struct drm_connector *connector, struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port); - -int drm_dp_get_vc_payload_bw(const struct drm_dp_mst_topology_mgr *mgr, - int link_rate, int link_lane_count); - -int drm_dp_calc_pbn_mode(int clock, int bpp, bool dsc); - -bool drm_dp_mst_allocate_vcpi(struct drm_dp_mst_topology_mgr *mgr, - struct drm_dp_mst_port *port, int pbn, int slots); - -int drm_dp_mst_get_vcpi_slots(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port); - - -void drm_dp_mst_reset_vcpi_slots(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port); - -void drm_dp_mst_update_slots(struct drm_dp_mst_topology_state *mst_state, uint8_t link_encoding_cap); - -void drm_dp_mst_deallocate_vcpi(struct drm_dp_mst_topology_mgr *mgr, - struct drm_dp_mst_port *port); - - -int drm_dp_find_vcpi_slots(struct drm_dp_mst_topology_mgr *mgr, - int pbn); - - -int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr, int start_slot); - - -int drm_dp_update_payload_part2(struct drm_dp_mst_topology_mgr *mgr); - -int drm_dp_check_act_status(struct drm_dp_mst_topology_mgr *mgr); - -void drm_dp_mst_dump_topology(struct seq_file *m, - struct drm_dp_mst_topology_mgr *mgr); - -void drm_dp_mst_topology_mgr_suspend(struct drm_dp_mst_topology_mgr *mgr); -int __must_check -drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr, - bool sync); - -ssize_t drm_dp_mst_dpcd_read(struct drm_dp_aux *aux, - unsigned int offset, void *buffer, size_t size); -ssize_t drm_dp_mst_dpcd_write(struct drm_dp_aux *aux, - unsigned int offset, void *buffer, size_t size); - -int drm_dp_mst_connector_late_register(struct drm_connector *connector, - struct drm_dp_mst_port *port); -void drm_dp_mst_connector_early_unregister(struct drm_connector *connector, - struct drm_dp_mst_port *port); - -struct drm_dp_mst_topology_state *drm_atomic_get_mst_topology_state(struct drm_atomic_state *state, - struct drm_dp_mst_topology_mgr *mgr); -int __must_check -drm_dp_atomic_find_vcpi_slots(struct drm_atomic_state *state, - struct drm_dp_mst_topology_mgr *mgr, - struct drm_dp_mst_port *port, int pbn, - int pbn_div); -int drm_dp_mst_atomic_enable_dsc(struct drm_atomic_state *state, - struct drm_dp_mst_port *port, - int pbn, int pbn_div, - bool enable); -int __must_check -drm_dp_mst_add_affected_dsc_crtcs(struct drm_atomic_state *state, - struct drm_dp_mst_topology_mgr *mgr); -int __must_check -drm_dp_atomic_release_vcpi_slots(struct drm_atomic_state *state, - struct drm_dp_mst_topology_mgr *mgr, - struct drm_dp_mst_port *port); -int drm_dp_send_power_updown_phy(struct drm_dp_mst_topology_mgr *mgr, - struct drm_dp_mst_port *port, bool power_up); -int drm_dp_send_query_stream_enc_status(struct drm_dp_mst_topology_mgr *mgr, - struct drm_dp_mst_port *port, - struct drm_dp_query_stream_enc_status_ack_reply *status); -int __must_check drm_dp_mst_atomic_check(struct drm_atomic_state *state); - -void drm_dp_mst_get_port_malloc(struct drm_dp_mst_port *port); -void drm_dp_mst_put_port_malloc(struct drm_dp_mst_port *port); - -struct drm_dp_aux *drm_dp_mst_dsc_aux_for_port(struct drm_dp_mst_port *port); - -extern const struct drm_private_state_funcs drm_dp_mst_topology_state_funcs; - -/** - * __drm_dp_mst_state_iter_get - private atomic state iterator function for - * macro-internal use - * @state: &struct drm_atomic_state pointer - * @mgr: pointer to the &struct drm_dp_mst_topology_mgr iteration cursor - * @old_state: optional pointer to the old &struct drm_dp_mst_topology_state - * iteration cursor - * @new_state: optional pointer to the new &struct drm_dp_mst_topology_state - * iteration cursor - * @i: int iteration cursor, for macro-internal use - * - * Used by for_each_oldnew_mst_mgr_in_state(), - * for_each_old_mst_mgr_in_state(), and for_each_new_mst_mgr_in_state(). Don't - * call this directly. - * - * Returns: - * True if the current &struct drm_private_obj is a &struct - * drm_dp_mst_topology_mgr, false otherwise. - */ -static inline bool -__drm_dp_mst_state_iter_get(struct drm_atomic_state *state, - struct drm_dp_mst_topology_mgr **mgr, - struct drm_dp_mst_topology_state **old_state, - struct drm_dp_mst_topology_state **new_state, - int i) -{ - struct __drm_private_objs_state *objs_state = &state->private_objs[i]; - - if (objs_state->ptr->funcs != &drm_dp_mst_topology_state_funcs) - return false; - - *mgr = to_dp_mst_topology_mgr(objs_state->ptr); - if (old_state) - *old_state = to_dp_mst_topology_state(objs_state->old_state); - if (new_state) - *new_state = to_dp_mst_topology_state(objs_state->new_state); - - return true; -} - -/** - * for_each_oldnew_mst_mgr_in_state - iterate over all DP MST topology - * managers in an atomic update - * @__state: &struct drm_atomic_state pointer - * @mgr: &struct drm_dp_mst_topology_mgr iteration cursor - * @old_state: &struct drm_dp_mst_topology_state iteration cursor for the old - * state - * @new_state: &struct drm_dp_mst_topology_state iteration cursor for the new - * state - * @__i: int iteration cursor, for macro-internal use - * - * This iterates over all DRM DP MST topology managers in an atomic update, - * tracking both old and new state. This is useful in places where the state - * delta needs to be considered, for example in atomic check functions. - */ -#define for_each_oldnew_mst_mgr_in_state(__state, mgr, old_state, new_state, __i) \ - for ((__i) = 0; (__i) < (__state)->num_private_objs; (__i)++) \ - for_each_if(__drm_dp_mst_state_iter_get((__state), &(mgr), &(old_state), &(new_state), (__i))) - -/** - * for_each_old_mst_mgr_in_state - iterate over all DP MST topology managers - * in an atomic update - * @__state: &struct drm_atomic_state pointer - * @mgr: &struct drm_dp_mst_topology_mgr iteration cursor - * @old_state: &struct drm_dp_mst_topology_state iteration cursor for the old - * state - * @__i: int iteration cursor, for macro-internal use - * - * This iterates over all DRM DP MST topology managers in an atomic update, - * tracking only the old state. This is useful in disable functions, where we - * need the old state the hardware is still in. - */ -#define for_each_old_mst_mgr_in_state(__state, mgr, old_state, __i) \ - for ((__i) = 0; (__i) < (__state)->num_private_objs; (__i)++) \ - for_each_if(__drm_dp_mst_state_iter_get((__state), &(mgr), &(old_state), NULL, (__i))) - -/** - * for_each_new_mst_mgr_in_state - iterate over all DP MST topology managers - * in an atomic update - * @__state: &struct drm_atomic_state pointer - * @mgr: &struct drm_dp_mst_topology_mgr iteration cursor - * @new_state: &struct drm_dp_mst_topology_state iteration cursor for the new - * state - * @__i: int iteration cursor, for macro-internal use - * - * This iterates over all DRM DP MST topology managers in an atomic update, - * tracking only the new state. This is useful in enable functions, where we - * need the new state the hardware should be in when the atomic commit - * operation has completed. - */ -#define for_each_new_mst_mgr_in_state(__state, mgr, new_state, __i) \ - for ((__i) = 0; (__i) < (__state)->num_private_objs; (__i)++) \ - for_each_if(__drm_dp_mst_state_iter_get((__state), &(mgr), NULL, &(new_state), (__i))) - -#endif diff --git a/include/drm/drm_dsc.h b/include/drm/drm_dsc.h index cf43561e60fa..ca022e960dcc 100644 --- a/include/drm/drm_dsc.h +++ b/include/drm/drm_dsc.h @@ -8,7 +8,7 @@ #ifndef DRM_DSC_H_ #define DRM_DSC_H_ -#include +#include /* VESA Display Stream Compression DSC 1.2 constants */ #define DSC_NUM_BUF_RANGES 15 -- cgit v1.2.3 From 032a125904995985334766911de9e26ee2bbd646 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 14 Jan 2022 12:45:35 +0100 Subject: drm/dp: Move DisplayPort AUX bus helpers into dp/ Move drm_dp_aux_bus.c and its header file into the DP subdirectory and update all users. No functional changes. Signed-off-by: Thomas Zimmermann Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220114114535.29157-6-tzimmermann@suse.de --- include/drm/dp/drm_dp_aux_bus.h | 57 +++++++++++++++++++++++++++++++++++++++++ include/drm/drm_dp_aux_bus.h | 57 ----------------------------------------- 2 files changed, 57 insertions(+), 57 deletions(-) create mode 100644 include/drm/dp/drm_dp_aux_bus.h delete mode 100644 include/drm/drm_dp_aux_bus.h (limited to 'include') diff --git a/include/drm/dp/drm_dp_aux_bus.h b/include/drm/dp/drm_dp_aux_bus.h new file mode 100644 index 000000000000..4f19b20b1dd6 --- /dev/null +++ b/include/drm/dp/drm_dp_aux_bus.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2021 Google Inc. + * + * The DP AUX bus is used for devices that are connected over a DisplayPort + * AUX bus. The devices on the far side of the bus are referred to as + * endpoints in this code. + */ + +#ifndef _DP_AUX_BUS_H_ +#define _DP_AUX_BUS_H_ + +#include +#include + +/** + * struct dp_aux_ep_device - Main dev structure for DP AUX endpoints + * + * This is used to instantiate devices that are connected via a DP AUX + * bus. Usually the device is a panel, but conceivable other devices could + * be hooked up there. + */ +struct dp_aux_ep_device { + /** @dev: The normal dev pointer */ + struct device dev; + /** @aux: Pointer to the aux bus */ + struct drm_dp_aux *aux; +}; + +struct dp_aux_ep_driver { + int (*probe)(struct dp_aux_ep_device *aux_ep); + void (*remove)(struct dp_aux_ep_device *aux_ep); + void (*shutdown)(struct dp_aux_ep_device *aux_ep); + struct device_driver driver; +}; + +static inline struct dp_aux_ep_device *to_dp_aux_ep_dev(struct device *dev) +{ + return container_of(dev, struct dp_aux_ep_device, dev); +} + +static inline struct dp_aux_ep_driver *to_dp_aux_ep_drv(struct device_driver *drv) +{ + return container_of(drv, struct dp_aux_ep_driver, driver); +} + +int of_dp_aux_populate_ep_devices(struct drm_dp_aux *aux); +void of_dp_aux_depopulate_ep_devices(struct drm_dp_aux *aux); +int devm_of_dp_aux_populate_ep_devices(struct drm_dp_aux *aux); + +#define dp_aux_dp_driver_register(aux_ep_drv) \ + __dp_aux_dp_driver_register(aux_ep_drv, THIS_MODULE) +int __dp_aux_dp_driver_register(struct dp_aux_ep_driver *aux_ep_drv, + struct module *owner); +void dp_aux_dp_driver_unregister(struct dp_aux_ep_driver *aux_ep_drv); + +#endif /* _DP_AUX_BUS_H_ */ diff --git a/include/drm/drm_dp_aux_bus.h b/include/drm/drm_dp_aux_bus.h deleted file mode 100644 index 4f19b20b1dd6..000000000000 --- a/include/drm/drm_dp_aux_bus.h +++ /dev/null @@ -1,57 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright 2021 Google Inc. - * - * The DP AUX bus is used for devices that are connected over a DisplayPort - * AUX bus. The devices on the far side of the bus are referred to as - * endpoints in this code. - */ - -#ifndef _DP_AUX_BUS_H_ -#define _DP_AUX_BUS_H_ - -#include -#include - -/** - * struct dp_aux_ep_device - Main dev structure for DP AUX endpoints - * - * This is used to instantiate devices that are connected via a DP AUX - * bus. Usually the device is a panel, but conceivable other devices could - * be hooked up there. - */ -struct dp_aux_ep_device { - /** @dev: The normal dev pointer */ - struct device dev; - /** @aux: Pointer to the aux bus */ - struct drm_dp_aux *aux; -}; - -struct dp_aux_ep_driver { - int (*probe)(struct dp_aux_ep_device *aux_ep); - void (*remove)(struct dp_aux_ep_device *aux_ep); - void (*shutdown)(struct dp_aux_ep_device *aux_ep); - struct device_driver driver; -}; - -static inline struct dp_aux_ep_device *to_dp_aux_ep_dev(struct device *dev) -{ - return container_of(dev, struct dp_aux_ep_device, dev); -} - -static inline struct dp_aux_ep_driver *to_dp_aux_ep_drv(struct device_driver *drv) -{ - return container_of(drv, struct dp_aux_ep_driver, driver); -} - -int of_dp_aux_populate_ep_devices(struct drm_dp_aux *aux); -void of_dp_aux_depopulate_ep_devices(struct drm_dp_aux *aux); -int devm_of_dp_aux_populate_ep_devices(struct drm_dp_aux *aux); - -#define dp_aux_dp_driver_register(aux_ep_drv) \ - __dp_aux_dp_driver_register(aux_ep_drv, THIS_MODULE) -int __dp_aux_dp_driver_register(struct dp_aux_ep_driver *aux_ep_drv, - struct module *owner); -void dp_aux_dp_driver_unregister(struct dp_aux_ep_driver *aux_ep_drv); - -#endif /* _DP_AUX_BUS_H_ */ -- cgit v1.2.3 From dee872e124e8d5de22b68c58f6f6c3f5e8889160 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 14 Jan 2022 22:09:45 +0530 Subject: bpf: Populate kfunc BTF ID sets in struct btf This patch prepares the kernel to support putting all kinds of kfunc BTF ID sets in the struct btf itself. The various kernel subsystems will make register_btf_kfunc_id_set call in the initcalls (for built-in code and modules). The 'hook' is one of the many program types, e.g. XDP and TC/SCHED_CLS, STRUCT_OPS, and 'types' are check (allowed or not), acquire, release, and ret_null (with PTR_TO_BTF_ID_OR_NULL return type). A maximum of BTF_KFUNC_SET_MAX_CNT (32) kfunc BTF IDs are permitted in a set of certain hook and type for vmlinux sets, since they are allocated on demand, and otherwise set as NULL. Module sets can only be registered once per hook and type, hence they are directly assigned. A new btf_kfunc_id_set_contains function is exposed for use in verifier, this new method is faster than the existing list searching method, and is also automatic. It also lets other code not care whether the set is unallocated or not. Note that module code can only do single register_btf_kfunc_id_set call per hook. This is why sorting is only done for in-kernel vmlinux sets, because there might be multiple sets for the same hook and type that must be concatenated, hence sorting them is required to ensure bsearch in btf_id_set_contains continues to work correctly. Next commit will update the kernel users to make use of this infrastructure. Finally, add __maybe_unused annotation for BTF ID macros for the !CONFIG_DEBUG_INFO_BTF case, so that they don't produce warnings during build time. The previous patch is also needed to provide synchronization against initialization for module BTF's kfunc_set_tab introduced here, as described below: The kfunc_set_tab pointer in struct btf is write-once (if we consider the registration phase (comprised of multiple register_btf_kfunc_id_set calls) as a single operation). In this sense, once it has been fully prepared, it isn't modified, only used for lookup (from the verifier context). For btf_vmlinux, it is initialized fully during the do_initcalls phase, which happens fairly early in the boot process, before any processes are present. This also eliminates the possibility of bpf_check being called at that point, thus relieving us of ensuring any synchronization between the registration and lookup function (btf_kfunc_id_set_contains). However, the case for module BTF is a bit tricky. The BTF is parsed, prepared, and published from the MODULE_STATE_COMING notifier callback. After this, the module initcalls are invoked, where our registration function will be called to populate the kfunc_set_tab for module BTF. At this point, BTF may be available to userspace while its corresponding module is still intializing. A BTF fd can then be passed to verifier using bpf syscall (e.g. for kfunc call insn). Hence, there is a race window where verifier may concurrently try to lookup the kfunc_set_tab. To prevent this race, we must ensure the operations are serialized, or waiting for the __init functions to complete. In the earlier registration API, this race was alleviated as verifier bpf_check_mod_kfunc_call didn't find the kfunc BTF ID until it was added by the registration function (called usually at the end of module __init function after all module resources have been initialized). If the verifier made the check_kfunc_call before kfunc BTF ID was added to the list, it would fail verification (saying call isn't allowed). The access to list was protected using a mutex. Now, it would still fail verification, but for a different reason (returning ENXIO due to the failed btf_try_get_module call in add_kfunc_call), because if the __init call is in progress the module will be in the middle of MODULE_STATE_COMING -> MODULE_STATE_LIVE transition, and the BTF_MODULE_LIVE flag for btf_module instance will not be set, so the btf_try_get_module call will fail. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220114163953.1455836-3-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/btf.h | 39 +++++++++++++++++++++++++++++++++++++++ include/linux/btf_ids.h | 13 +++++++------ 2 files changed, 46 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/btf.h b/include/linux/btf.h index 0c74348cbc9d..c451f8e2612a 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -12,11 +12,33 @@ #define BTF_TYPE_EMIT(type) ((void)(type *)0) #define BTF_TYPE_EMIT_ENUM(enum_val) ((void)enum_val) +enum btf_kfunc_type { + BTF_KFUNC_TYPE_CHECK, + BTF_KFUNC_TYPE_ACQUIRE, + BTF_KFUNC_TYPE_RELEASE, + BTF_KFUNC_TYPE_RET_NULL, + BTF_KFUNC_TYPE_MAX, +}; + struct btf; struct btf_member; struct btf_type; union bpf_attr; struct btf_show; +struct btf_id_set; + +struct btf_kfunc_id_set { + struct module *owner; + union { + struct { + struct btf_id_set *check_set; + struct btf_id_set *acquire_set; + struct btf_id_set *release_set; + struct btf_id_set *ret_null_set; + }; + struct btf_id_set *sets[BTF_KFUNC_TYPE_MAX]; + }; +}; extern const struct file_operations btf_fops; @@ -307,6 +329,11 @@ const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); struct btf *btf_parse_vmlinux(void); struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog); +bool btf_kfunc_id_set_contains(const struct btf *btf, + enum bpf_prog_type prog_type, + enum btf_kfunc_type type, u32 kfunc_btf_id); +int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, + const struct btf_kfunc_id_set *s); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) @@ -318,6 +345,18 @@ static inline const char *btf_name_by_offset(const struct btf *btf, { return NULL; } +static inline bool btf_kfunc_id_set_contains(const struct btf *btf, + enum bpf_prog_type prog_type, + enum btf_kfunc_type type, + u32 kfunc_btf_id) +{ + return false; +} +static inline int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, + const struct btf_kfunc_id_set *s) +{ + return 0; +} #endif struct kfunc_btf_id_set { diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 919c0fde1c51..bc5d9cc34e4c 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -11,6 +11,7 @@ struct btf_id_set { #ifdef CONFIG_DEBUG_INFO_BTF #include /* for __PASTE */ +#include /* for __maybe_unused */ /* * Following macros help to define lists of BTF IDs placed @@ -146,14 +147,14 @@ extern struct btf_id_set name; #else -#define BTF_ID_LIST(name) static u32 name[5]; +#define BTF_ID_LIST(name) static u32 __maybe_unused name[5]; #define BTF_ID(prefix, name) #define BTF_ID_UNUSED -#define BTF_ID_LIST_GLOBAL(name, n) u32 name[n]; -#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1]; -#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 name[1]; -#define BTF_SET_START(name) static struct btf_id_set name = { 0 }; -#define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 }; +#define BTF_ID_LIST_GLOBAL(name, n) u32 __maybe_unused name[n]; +#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 __maybe_unused name[1]; +#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 __maybe_unused name[1]; +#define BTF_SET_START(name) static struct btf_id_set __maybe_unused name = { 0 }; +#define BTF_SET_START_GLOBAL(name) static struct btf_id_set __maybe_unused name = { 0 }; #define BTF_SET_END(name) #endif /* CONFIG_DEBUG_INFO_BTF */ -- cgit v1.2.3 From b202d84422223b7222cba5031d182f20b37e146e Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 14 Jan 2022 22:09:46 +0530 Subject: bpf: Remove check_kfunc_call callback and old kfunc BTF ID API Completely remove the old code for check_kfunc_call to help it work with modules, and also the callback itself. The previous commit adds infrastructure to register all sets and put them in vmlinux or module BTF, and concatenates all related sets organized by the hook and the type. Once populated, these sets remain immutable for the lifetime of the struct btf. Also, since we don't need the 'owner' module anywhere when doing check_kfunc_call, drop the 'btf_modp' module parameter from find_kfunc_desc_btf. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220114163953.1455836-4-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 8 -------- include/linux/btf.h | 44 -------------------------------------------- 2 files changed, 52 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6e947cd91152..6d7346c54d83 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -573,7 +573,6 @@ struct bpf_verifier_ops { const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id); - bool (*check_kfunc_call)(u32 kfunc_btf_id, struct module *owner); }; struct bpf_prog_offload_ops { @@ -1719,7 +1718,6 @@ int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); -bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, struct module *owner); bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); @@ -1971,12 +1969,6 @@ static inline int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, return -ENOTSUPP; } -static inline bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, - struct module *owner) -{ - return false; -} - static inline void bpf_map_put(struct bpf_map *map) { } diff --git a/include/linux/btf.h b/include/linux/btf.h index c451f8e2612a..b12cfe3b12bb 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -359,48 +359,4 @@ static inline int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, } #endif -struct kfunc_btf_id_set { - struct list_head list; - struct btf_id_set *set; - struct module *owner; -}; - -struct kfunc_btf_id_list { - struct list_head list; - struct mutex mutex; -}; - -#ifdef CONFIG_DEBUG_INFO_BTF_MODULES -void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s); -void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s); -bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, - struct module *owner); - -extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list; -extern struct kfunc_btf_id_list prog_test_kfunc_list; -#else -static inline void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s) -{ -} -static inline void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s) -{ -} -static inline bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, - u32 kfunc_id, struct module *owner) -{ - return false; -} - -static struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list __maybe_unused; -static struct kfunc_btf_id_list prog_test_kfunc_list __maybe_unused; -#endif - -#define DEFINE_KFUNC_BTF_ID_SET(set, name) \ - struct kfunc_btf_id_set name = { LIST_HEAD_INIT(name.list), (set), \ - THIS_MODULE } - #endif -- cgit v1.2.3 From d583691c47dc0424ebe926000339a6d6cd590ff7 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 14 Jan 2022 22:09:47 +0530 Subject: bpf: Introduce mem, size argument pair support for kfunc BPF helpers can associate two adjacent arguments together to pass memory of certain size, using ARG_PTR_TO_MEM and ARG_CONST_SIZE arguments. Since we don't use bpf_func_proto for kfunc, we need to leverage BTF to implement similar support. The ARG_CONST_SIZE processing for helpers is refactored into a common check_mem_size_reg helper that is shared with kfunc as well. kfunc ptr_to_mem support follows logic similar to global functions, where verification is done as if pointer is not null, even when it may be null. This leads to a simple to follow rule for writing kfunc: always check the argument pointer for NULL, except when it is PTR_TO_CTX. Also, the PTR_TO_CTX case is also only safe when the helper expecting pointer to program ctx is not exposed to other programs where same struct is not ctx type. In that case, the type check will fall through to other cases and would permit passing other types of pointers, possibly NULL at runtime. Currently, we require the size argument to be suffixed with "__sz" in the parameter name. This information is then recorded in kernel BTF and verified during function argument checking. In the future we can use BTF tagging instead, and modify the kernel function definitions. This will be a purely kernel-side change. This allows us to have some form of backwards compatibility for structures that are passed in to the kernel function with their size, and allow variable length structures to be passed in if they are accompanied by a size parameter. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220114163953.1455836-5-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 143401d4c9d9..857fd687bdc2 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -521,6 +521,8 @@ bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt); int check_ctx_reg(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno); +int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + u32 regno); int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, u32 mem_size); -- cgit v1.2.3 From 5c073f26f9dc78a6c8194b23eac7537c9692c7d7 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 14 Jan 2022 22:09:48 +0530 Subject: bpf: Add reference tracking support to kfunc This patch adds verifier support for PTR_TO_BTF_ID return type of kfunc to be a reference, by reusing acquire_reference_state/release_reference support for existing in-kernel bpf helpers. We make use of the three kfunc types: - BTF_KFUNC_TYPE_ACQUIRE Return true if kfunc_btf_id is an acquire kfunc. This will acquire_reference_state for the returned PTR_TO_BTF_ID (this is the only allow return value). Note that acquire kfunc must always return a PTR_TO_BTF_ID{_OR_NULL}, otherwise the program is rejected. - BTF_KFUNC_TYPE_RELEASE Return true if kfunc_btf_id is a release kfunc. This will release the reference to the passed in PTR_TO_BTF_ID which has a reference state (from earlier acquire kfunc). The btf_check_func_arg_match returns the regno (of argument register, hence > 0) if the kfunc is a release kfunc, and a proper referenced PTR_TO_BTF_ID is being passed to it. This is similar to how helper call check uses bpf_call_arg_meta to store the ref_obj_id that is later used to release the reference. Similar to in-kernel helper, we only allow passing one referenced PTR_TO_BTF_ID as an argument. It can also be passed in to normal kfunc, but in case of release kfunc there must always be one PTR_TO_BTF_ID argument that is referenced. - BTF_KFUNC_TYPE_RET_NULL For kfunc returning PTR_TO_BTF_ID, tells if it can be NULL, hence force caller to mark the pointer not null (using check) before accessing it. Note that taking into account the case fixed by commit 93c230e3f5bd ("bpf: Enforce id generation for all may-be-null register type") we assign a non-zero id for mark_ptr_or_null_reg logic. Later, if more return types are supported by kfunc, which have a _OR_NULL variant, it might be better to move this id generation under a common reg_type_may_be_null check, similar to the case in the commit. Referenced PTR_TO_BTF_ID is currently only limited to kfunc, but can be extended in the future to other BPF helpers as well. For now, we can rely on the btf_struct_ids_match check to ensure we get the pointer to the expected struct type. In the future, care needs to be taken to avoid ambiguity for reference PTR_TO_BTF_ID passed to release function, in case multiple candidates can release same BTF ID. e.g. there might be two release kfuncs (or kfunc and helper): foo(struct abc *p); bar(struct abc *p); ... such that both release a PTR_TO_BTF_ID with btf_id of struct abc. In this case we would need to track the acquire function corresponding to the release function to avoid type confusion, and store this information in the register state so that an incorrect program can be rejected. This is not a problem right now, hence it is left as an exercise for the future patch introducing such a case in the kernel. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220114163953.1455836-6-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 857fd687bdc2..ac4797155412 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -566,4 +566,9 @@ static inline u32 type_flag(u32 type) return type & ~BPF_BASE_TYPE_MASK; } +static inline enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog) +{ + return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type; +} + #endif /* _LINUX_BPF_VERIFIER_H */ -- cgit v1.2.3 From b4c2b9593a1c4c3a718370e34af28e817fd5e5c6 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 14 Jan 2022 22:09:49 +0530 Subject: net/netfilter: Add unstable CT lookup helpers for XDP and TC-BPF This change adds conntrack lookup helpers using the unstable kfunc call interface for the XDP and TC-BPF hooks. The primary usecase is implementing a synproxy in XDP, see Maxim's patchset [0]. Export get_net_ns_by_id as nf_conntrack_bpf.c needs to call it. This object is only built when CONFIG_DEBUG_INFO_BTF_MODULES is enabled. [0]: https://lore.kernel.org/bpf/20211019144655.3483197-1-maximmi@nvidia.com Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220114163953.1455836-7-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/net/netfilter/nf_conntrack_bpf.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100644 include/net/netfilter/nf_conntrack_bpf.h (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_bpf.h b/include/net/netfilter/nf_conntrack_bpf.h new file mode 100644 index 000000000000..a473b56842c5 --- /dev/null +++ b/include/net/netfilter/nf_conntrack_bpf.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _NF_CONNTRACK_BPF_H +#define _NF_CONNTRACK_BPF_H + +#include +#include + +#if (IS_BUILTIN(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \ + (IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) + +extern int register_nf_conntrack_bpf(void); + +#else + +static inline int register_nf_conntrack_bpf(void) +{ + return 0; +} + +#endif + +#endif /* _NF_CONNTRACK_BPF_H */ -- cgit v1.2.3 From 6387a3c4b0c45a3932cc06daaf15727e7f83be43 Mon Sep 17 00:00:00 2001 From: Arunpravin Date: Tue, 18 Jan 2022 16:14:59 +0530 Subject: drm: move the buddy allocator from i915 into common drm MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move the base i915 buddy allocator code into drm - Move i915_buddy.h to include/drm - Move i915_buddy.c to drm root folder - Rename "i915" string with "drm" string wherever applicable - Rename "I915" string with "DRM" string wherever applicable - Fix header file dependencies - Fix alignment issues - add Makefile support for drm buddy - export functions and write kerneldoc description - Remove i915 selftest config check condition as buddy selftest will be moved to drm selftest folder cleanup i915 buddy references in i915 driver module and replace with drm buddy v2: - include header file in alphabetical order(Thomas) - merged changes listed in the body section into a single patch to keep the build intact(Christian, Jani) v3: - make drm buddy a separate module(Thomas, Christian) v4: - Fix build error reported by kernel test robot - removed i915 buddy selftest from i915_mock_selftests.h to avoid build error - removed selftests/i915_buddy.c file as we create a new set of buddy test cases in drm/selftests folder v5: - Fix merge conflict issue v6: - replace drm_buddy_mm structure name as drm_buddy(Thomas, Christian) - replace drm_buddy_alloc() function name as drm_buddy_alloc_blocks() (Thomas) - replace drm_buddy_free() function name as drm_buddy_free_block() (Thomas) - export drm_buddy_free_block() function - fix multiple instances of KMEM_CACHE() entry v7: - fix warnings reported by kernel test robot - modify the license(Christian) v8: - fix warnings reported by kernel test robot Signed-off-by: Arunpravin Acked-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20220118104504.2349-1-Arunpravin.PaneerSelvam@amd.com Signed-off-by: Christian König --- include/drm/drm_buddy.h | 150 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 150 insertions(+) create mode 100644 include/drm/drm_buddy.h (limited to 'include') diff --git a/include/drm/drm_buddy.h b/include/drm/drm_buddy.h new file mode 100644 index 000000000000..f524db152413 --- /dev/null +++ b/include/drm/drm_buddy.h @@ -0,0 +1,150 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ + +#ifndef __DRM_BUDDY_H__ +#define __DRM_BUDDY_H__ + +#include +#include +#include +#include + +#include + +#define range_overflows(start, size, max) ({ \ + typeof(start) start__ = (start); \ + typeof(size) size__ = (size); \ + typeof(max) max__ = (max); \ + (void)(&start__ == &size__); \ + (void)(&start__ == &max__); \ + start__ >= max__ || size__ > max__ - start__; \ +}) + +struct drm_buddy_block { +#define DRM_BUDDY_HEADER_OFFSET GENMASK_ULL(63, 12) +#define DRM_BUDDY_HEADER_STATE GENMASK_ULL(11, 10) +#define DRM_BUDDY_ALLOCATED (1 << 10) +#define DRM_BUDDY_FREE (2 << 10) +#define DRM_BUDDY_SPLIT (3 << 10) +/* Free to be used, if needed in the future */ +#define DRM_BUDDY_HEADER_UNUSED GENMASK_ULL(9, 6) +#define DRM_BUDDY_HEADER_ORDER GENMASK_ULL(5, 0) + u64 header; + + struct drm_buddy_block *left; + struct drm_buddy_block *right; + struct drm_buddy_block *parent; + + void *private; /* owned by creator */ + + /* + * While the block is allocated by the user through drm_buddy_alloc*, + * the user has ownership of the link, for example to maintain within + * a list, if so desired. As soon as the block is freed with + * drm_buddy_free* ownership is given back to the mm. + */ + struct list_head link; + struct list_head tmp_link; +}; + +/* Order-zero must be at least PAGE_SIZE */ +#define DRM_BUDDY_MAX_ORDER (63 - PAGE_SHIFT) + +/* + * Binary Buddy System. + * + * Locking should be handled by the user, a simple mutex around + * drm_buddy_alloc* and drm_buddy_free* should suffice. + */ +struct drm_buddy { + /* Maintain a free list for each order. */ + struct list_head *free_list; + + /* + * Maintain explicit binary tree(s) to track the allocation of the + * address space. This gives us a simple way of finding a buddy block + * and performing the potentially recursive merge step when freeing a + * block. Nodes are either allocated or free, in which case they will + * also exist on the respective free list. + */ + struct drm_buddy_block **roots; + + /* + * Anything from here is public, and remains static for the lifetime of + * the mm. Everything above is considered do-not-touch. + */ + unsigned int n_roots; + unsigned int max_order; + + /* Must be at least PAGE_SIZE */ + u64 chunk_size; + u64 size; + u64 avail; +}; + +static inline u64 +drm_buddy_block_offset(struct drm_buddy_block *block) +{ + return block->header & DRM_BUDDY_HEADER_OFFSET; +} + +static inline unsigned int +drm_buddy_block_order(struct drm_buddy_block *block) +{ + return block->header & DRM_BUDDY_HEADER_ORDER; +} + +static inline unsigned int +drm_buddy_block_state(struct drm_buddy_block *block) +{ + return block->header & DRM_BUDDY_HEADER_STATE; +} + +static inline bool +drm_buddy_block_is_allocated(struct drm_buddy_block *block) +{ + return drm_buddy_block_state(block) == DRM_BUDDY_ALLOCATED; +} + +static inline bool +drm_buddy_block_is_free(struct drm_buddy_block *block) +{ + return drm_buddy_block_state(block) == DRM_BUDDY_FREE; +} + +static inline bool +drm_buddy_block_is_split(struct drm_buddy_block *block) +{ + return drm_buddy_block_state(block) == DRM_BUDDY_SPLIT; +} + +static inline u64 +drm_buddy_block_size(struct drm_buddy *mm, + struct drm_buddy_block *block) +{ + return mm->chunk_size << drm_buddy_block_order(block); +} + +int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size); + +void drm_buddy_fini(struct drm_buddy *mm); + +struct drm_buddy_block * +drm_buddy_alloc_blocks(struct drm_buddy *mm, unsigned int order); + +int drm_buddy_alloc_range(struct drm_buddy *mm, + struct list_head *blocks, + u64 start, u64 size); + +void drm_buddy_free_block(struct drm_buddy *mm, struct drm_buddy_block *block); + +void drm_buddy_free_list(struct drm_buddy *mm, struct list_head *objects); + +void drm_buddy_print(struct drm_buddy *mm, struct drm_printer *p); +void drm_buddy_block_print(struct drm_buddy *mm, + struct drm_buddy_block *block, + struct drm_printer *p); + +#endif -- cgit v1.2.3 From 75ab2b3633ccddd8f7bdf6c76f9ab3f9b2fc5d9d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Thu, 28 Oct 2021 13:19:22 +0200 Subject: dma-buf: drop excl_fence parameter from dma_resv_get_fences MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Returning the exclusive fence separately is no longer used. Instead add a write parameter to indicate the use case. Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20211207123411.167006-4-christian.koenig@amd.com --- include/linux/dma-resv.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index eebf04325b34..a715df97b31a 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -458,8 +458,8 @@ void dma_resv_fini(struct dma_resv *obj); int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences); void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence); void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence); -int dma_resv_get_fences(struct dma_resv *obj, struct dma_fence **pfence_excl, - unsigned *pshared_count, struct dma_fence ***pshared); +int dma_resv_get_fences(struct dma_resv *obj, bool write, + unsigned int *num_fences, struct dma_fence ***fences); int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src); long dma_resv_wait_timeout(struct dma_resv *obj, bool wait_all, bool intr, unsigned long timeout); -- cgit v1.2.3 From 52506b099e1baa204b56b170f40f680ffcabb4c1 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Wed, 22 Dec 2021 09:28:22 +0100 Subject: drm: Provide PCI module-init macros Provide helper macros to register PCI-based DRM drivers. The new macros behave like module_pci_driver() with an additional test if DRM modesetting has been enabled. Signed-off-by: Thomas Zimmermann Reviewed-by: Javier Martinez Canillas Signed-off-by: Javier Martinez Canillas Link: https://patchwork.freedesktop.org/patch/msgid/20211222082831.196562-2-javierm@redhat.com --- include/drm/drm_module.h | 95 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 95 insertions(+) create mode 100644 include/drm/drm_module.h (limited to 'include') diff --git a/include/drm/drm_module.h b/include/drm/drm_module.h new file mode 100644 index 000000000000..eb3fd7bcbec9 --- /dev/null +++ b/include/drm/drm_module.h @@ -0,0 +1,95 @@ +/* SPDX-License-Identifier: MIT */ + +#ifndef DRM_MODULE_H +#define DRM_MODULE_H + +#include + +#include + +/** + * DOC: overview + * + * This library provides helpers registering DRM drivers during module + * initialization and shutdown. The provided helpers act like bus-specific + * module helpers, such as module_pci_driver(), but respect additional + * parameters that control DRM driver registration. + * + * Below is an example of initializing a DRM driver for a device on the + * PCI bus. + * + * .. code-block:: c + * + * struct pci_driver my_pci_drv = { + * }; + * + * drm_module_pci_driver(my_pci_drv); + * + * The generated code will test if DRM drivers are enabled and register + * the PCI driver my_pci_drv. For more complex module initialization, you + * can still use module_init() and module_exit() in your driver. + */ + +/* + * PCI drivers + */ + +static inline int __init drm_pci_register_driver(struct pci_driver *pci_drv) +{ + if (drm_firmware_drivers_only()) + return -ENODEV; + + return pci_register_driver(pci_drv); +} + +/** + * drm_module_pci_driver - Register a DRM driver for PCI-based devices + * @__pci_drv: the PCI driver structure + * + * Registers a DRM driver for devices on the PCI bus. The helper + * macro behaves like module_pci_driver() but tests the state of + * drm_firmware_drivers_only(). For more complex module initialization, + * use module_init() and module_exit() directly. + * + * Each module may only use this macro once. Calling it replaces + * module_init() and module_exit(). + */ +#define drm_module_pci_driver(__pci_drv) \ + module_driver(__pci_drv, drm_pci_register_driver, pci_unregister_driver) + +static inline int __init +drm_pci_register_driver_if_modeset(struct pci_driver *pci_drv, int modeset) +{ + if (drm_firmware_drivers_only() && modeset == -1) + return -ENODEV; + if (modeset == 0) + return -ENODEV; + + return pci_register_driver(pci_drv); +} + +static inline void __exit +drm_pci_unregister_driver_if_modeset(struct pci_driver *pci_drv, int modeset) +{ + pci_unregister_driver(pci_drv); +} + +/** + * drm_module_pci_driver_if_modeset - Register a DRM driver for PCI-based devices + * @__pci_drv: the PCI driver structure + * @__modeset: an additional parameter that disables the driver + * + * This macro is deprecated and only provided for existing drivers. For + * new drivers, use drm_module_pci_driver(). + * + * Registers a DRM driver for devices on the PCI bus. The helper macro + * behaves like drm_module_pci_driver() with an additional driver-specific + * flag. If __modeset is 0, the driver has been disabled, if __modeset is + * -1 the driver state depends on the global DRM state. For all other + * values, the PCI driver has been enabled. The default should be -1. + */ +#define drm_module_pci_driver_if_modeset(__pci_drv, __modeset) \ + module_driver(__pci_drv, drm_pci_register_driver_if_modeset, \ + drm_pci_unregister_driver_if_modeset, __modeset) + +#endif -- cgit v1.2.3 From 09f137c320633d08b263c54c0782e91d55a6c09f Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Wed, 22 Dec 2021 09:28:27 +0100 Subject: drm: Provide platform module-init macro Provide a helper macro to register platform DRM drivers. The new macro behaves like module_platform_driver() with an additional test if DRM modesetting has been enabled. Signed-off-by: Javier Martinez Canillas Acked-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20211222082831.196562-7-javierm@redhat.com --- include/drm/drm_module.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include') diff --git a/include/drm/drm_module.h b/include/drm/drm_module.h index eb3fd7bcbec9..4db1ae03d9a5 100644 --- a/include/drm/drm_module.h +++ b/include/drm/drm_module.h @@ -4,6 +4,7 @@ #define DRM_MODULE_H #include +#include #include @@ -92,4 +93,33 @@ drm_pci_unregister_driver_if_modeset(struct pci_driver *pci_drv, int modeset) module_driver(__pci_drv, drm_pci_register_driver_if_modeset, \ drm_pci_unregister_driver_if_modeset, __modeset) +/* + * Platform drivers + */ + +static inline int __init +drm_platform_driver_register(struct platform_driver *platform_drv) +{ + if (drm_firmware_drivers_only()) + return -ENODEV; + + return platform_driver_register(platform_drv); +} + +/** + * drm_module_platform_driver - Register a DRM driver for platform devices + * @__platform_drv: the platform driver structure + * + * Registers a DRM driver for devices on the platform bus. The helper + * macro behaves like module_platform_driver() but tests the state of + * drm_firmware_drivers_only(). For more complex module initialization, + * use module_init() and module_exit() directly. + * + * Each module may only use this macro once. Calling it replaces + * module_init() and module_exit(). + */ +#define drm_module_platform_driver(__platform_drv) \ + module_driver(__platform_drv, drm_platform_driver_register, \ + platform_driver_unregister) + #endif -- cgit v1.2.3 From e40fbbf0572c5e41dc87ad79001748ed399ce32d Mon Sep 17 00:00:00 2001 From: Usama Arif Date: Wed, 19 Jan 2022 11:44:40 +0000 Subject: uapi/bpf: Add missing description and returns for helper documentation Both description and returns section will become mandatory for helpers and syscalls in a later commit to generate man pages. This commit also adds in the documentation that BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN for anyone searching for the syscall in the generated man pages. Signed-off-by: Usama Arif Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220119114442.1452088-1-usama.arif@bytedance.com --- include/uapi/linux/bpf.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b0383d371b9a..a9c96c21330a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -330,6 +330,8 @@ union bpf_iter_link_info { * *ctx_out*, *data_in* and *data_out* must be NULL. * *repeat* must be zero. * + * BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN. + * * Return * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. @@ -1775,6 +1777,8 @@ union bpf_attr { * 0 on success, or a negative error in case of failure. * * u64 bpf_get_current_pid_tgid(void) + * Description + * Get the current pid and tgid. * Return * A 64-bit integer containing the current tgid and pid, and * created as such: @@ -1782,6 +1786,8 @@ union bpf_attr { * *current_task*\ **->pid**. * * u64 bpf_get_current_uid_gid(void) + * Description + * Get the current uid and gid. * Return * A 64-bit integer containing the current GID and UID, and * created as such: *current_gid* **<< 32 \|** *current_uid*. @@ -2256,6 +2262,8 @@ union bpf_attr { * The 32-bit hash. * * u64 bpf_get_current_task(void) + * Description + * Get the current task. * Return * A pointer to the current task struct. * @@ -2369,6 +2377,8 @@ union bpf_attr { * indicate that the hash is outdated and to trigger a * recalculation the next time the kernel tries to access this * hash or when the **bpf_get_hash_recalc**\ () helper is called. + * Return + * void. * * long bpf_get_numa_node_id(void) * Description @@ -2466,6 +2476,8 @@ union bpf_attr { * A 8-byte long unique number or 0 if *sk* is NULL. * * u32 bpf_get_socket_uid(struct sk_buff *skb) + * Description + * Get the owner UID of the socked associated to *skb*. * Return * The owner UID of the socket associated to *skb*. If the socket * is **NULL**, or if it is not a full socket (i.e. if it is a @@ -3240,6 +3252,9 @@ union bpf_attr { * The id is returned or 0 in case the id could not be retrieved. * * u64 bpf_get_current_cgroup_id(void) + * Description + * Get the current cgroup id based on the cgroup within which + * the current task is running. * Return * A 64-bit integer containing the current cgroup id based * on the cgroup within which the current task is running. -- cgit v1.2.3 From f10d059661968b01ef61a8b516775f95a18ab8ae Mon Sep 17 00:00:00 2001 From: YiFei Zhu Date: Thu, 16 Dec 2021 02:04:25 +0000 Subject: bpf: Make BPF_PROG_RUN_ARRAY return -err instead of allow boolean Right now BPF_PROG_RUN_ARRAY and related macros return 1 or 0 for whether the prog array allows or rejects whatever is being hooked. The caller of these macros then return -EPERM or continue processing based on thw macro's return value. Unforunately this is inflexible, since -EPERM is the only err that can be returned. This patch should be a no-op; it prepares for the next patch. The returning of the -EPERM is moved to inside the macros, so the outer functions are directly returning what the macros returned if they are non-zero. Signed-off-by: YiFei Zhu Reviewed-by: Stanislav Fomichev Link: https://lore.kernel.org/r/788abcdca55886d1f43274c918eaa9f792a9f33b.1639619851.git.zhuyifei@google.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6d7346c54d83..83da1764fcfe 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1277,7 +1277,7 @@ static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx) typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx); -static __always_inline u32 +static __always_inline int BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, const void *ctx, bpf_prog_run_fn run_prog, u32 *ret_flags) @@ -1287,7 +1287,7 @@ BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_cg_run_ctx run_ctx; - u32 ret = 1; + int ret = 0; u32 func_ret; migrate_disable(); @@ -1298,7 +1298,8 @@ BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; func_ret = run_prog(prog, ctx); - ret &= (func_ret & 1); + if (!(func_ret & 1)) + ret = -EPERM; *(ret_flags) |= (func_ret >> 1); item++; } @@ -1308,7 +1309,7 @@ BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, return ret; } -static __always_inline u32 +static __always_inline int BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, const void *ctx, bpf_prog_run_fn run_prog) { @@ -1317,7 +1318,7 @@ BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_cg_run_ctx run_ctx; - u32 ret = 1; + int ret = 0; migrate_disable(); rcu_read_lock(); @@ -1326,7 +1327,8 @@ BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; - ret &= run_prog(prog, ctx); + if (!run_prog(prog, ctx)) + ret = -EPERM; item++; } bpf_reset_run_ctx(old_run_ctx); @@ -1394,7 +1396,7 @@ out: u32 _ret; \ _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, &_flags); \ _cn = _flags & BPF_RET_SET_CN; \ - if (_ret) \ + if (!_ret) \ _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ else \ _ret = (_cn ? NET_XMIT_DROP : -EPERM); \ -- cgit v1.2.3 From c4dcfdd406aa2167396ac215e351e5e4dfd7efe3 Mon Sep 17 00:00:00 2001 From: YiFei Zhu Date: Thu, 16 Dec 2021 02:04:26 +0000 Subject: bpf: Move getsockopt retval to struct bpf_cg_run_ctx The retval value is moved to struct bpf_cg_run_ctx for ease of access in different prog types with different context structs layouts. The helper implementation (to be added in a later patch in the series) can simply perform a container_of from current->bpf_ctx to retrieve bpf_cg_run_ctx. Unfortunately, there is no easy way to access the current task_struct via the verifier BPF bytecode rewrite, aside from possibly calling a helper, so a pointer to current task is added to struct bpf_sockopt_kern so that the rewritten BPF bytecode can access struct bpf_cg_run_ctx with an indirection. For backward compatibility, if a getsockopt program rejects a syscall by returning 0, an -EPERM will be generated, by having the BPF_PROG_RUN_ARRAY_CG family macros automatically set the retval to -EPERM. Unlike prior to this patch, this -EPERM will be visible to ctx->retval for any other hooks down the line in the prog array. Additionally, the restriction that getsockopt filters can only set the retval to 0 is removed, considering that certain getsockopt implementations may return optlen. Filters are now able to set the value arbitrarily. Signed-off-by: YiFei Zhu Reviewed-by: Stanislav Fomichev Link: https://lore.kernel.org/r/73b0325f5c29912ccea7ea57ec1ed4d388fc1d37.1639619851.git.zhuyifei@google.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 20 +++++++++++--------- include/linux/filter.h | 5 ++++- 2 files changed, 15 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 83da1764fcfe..7b0c11f414d0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1245,6 +1245,7 @@ struct bpf_run_ctx {}; struct bpf_cg_run_ctx { struct bpf_run_ctx run_ctx; const struct bpf_prog_array_item *prog_item; + int retval; }; struct bpf_trace_run_ctx { @@ -1280,16 +1281,16 @@ typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx); static __always_inline int BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, const void *ctx, bpf_prog_run_fn run_prog, - u32 *ret_flags) + int retval, u32 *ret_flags) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_cg_run_ctx run_ctx; - int ret = 0; u32 func_ret; + run_ctx.retval = retval; migrate_disable(); rcu_read_lock(); array = rcu_dereference(array_rcu); @@ -1299,27 +1300,28 @@ BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, run_ctx.prog_item = item; func_ret = run_prog(prog, ctx); if (!(func_ret & 1)) - ret = -EPERM; + run_ctx.retval = -EPERM; *(ret_flags) |= (func_ret >> 1); item++; } bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); migrate_enable(); - return ret; + return run_ctx.retval; } static __always_inline int BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, - const void *ctx, bpf_prog_run_fn run_prog) + const void *ctx, bpf_prog_run_fn run_prog, + int retval) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_cg_run_ctx run_ctx; - int ret = 0; + run_ctx.retval = retval; migrate_disable(); rcu_read_lock(); array = rcu_dereference(array_rcu); @@ -1328,13 +1330,13 @@ BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; if (!run_prog(prog, ctx)) - ret = -EPERM; + run_ctx.retval = -EPERM; item++; } bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); migrate_enable(); - return ret; + return run_ctx.retval; } static __always_inline u32 @@ -1394,7 +1396,7 @@ out: u32 _flags = 0; \ bool _cn; \ u32 _ret; \ - _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, &_flags); \ + _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, 0, &_flags); \ _cn = _flags & BPF_RET_SET_CN; \ if (!_ret) \ _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ diff --git a/include/linux/filter.h b/include/linux/filter.h index 71fa57b88bfc..d23e999dc032 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1356,7 +1356,10 @@ struct bpf_sockopt_kern { s32 level; s32 optname; s32 optlen; - s32 retval; + /* for retval in struct bpf_cg_run_ctx */ + struct task_struct *current_task; + /* Temporary "register" for indirect stores to ppos. */ + u64 tmp_reg; }; int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len); -- cgit v1.2.3 From b44123b4a3dcad4664d3a0f72c011ffd4c9c4d93 Mon Sep 17 00:00:00 2001 From: YiFei Zhu Date: Thu, 16 Dec 2021 02:04:27 +0000 Subject: bpf: Add cgroup helpers bpf_{get,set}_retval to get/set syscall return value The helpers continue to use int for retval because all the hooks are int-returning rather than long-returning. The return value of bpf_set_retval is int for future-proofing, in case in the future there may be errors trying to set the retval. After the previous patch, if a program rejects a syscall by returning 0, an -EPERM will be generated no matter if the retval is already set to -err. This patch change it being forced only if retval is not -err. This is because we want to support, for example, invoking bpf_set_retval(-EINVAL) and return 0, and have the syscall return value be -EINVAL not -EPERM. For BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY, the prior behavior is that, if the return value is NET_XMIT_DROP, the packet is silently dropped. We preserve this behavior for backward compatibility reasons, so even if an errno is set, the errno does not return to caller. However, setting a non-err to retval cannot propagate so this is not allowed and we return a -EFAULT in that case. Signed-off-by: YiFei Zhu Reviewed-by: Stanislav Fomichev Link: https://lore.kernel.org/r/b4013fd5d16bed0b01977c1fafdeae12e1de61fb.1639619851.git.zhuyifei@google.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 10 ++++++---- include/uapi/linux/bpf.h | 18 ++++++++++++++++++ 2 files changed, 24 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7b0c11f414d0..dce54eb0aae8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1299,7 +1299,7 @@ BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; func_ret = run_prog(prog, ctx); - if (!(func_ret & 1)) + if (!(func_ret & 1) && !IS_ERR_VALUE((long)run_ctx.retval)) run_ctx.retval = -EPERM; *(ret_flags) |= (func_ret >> 1); item++; @@ -1329,7 +1329,7 @@ BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; - if (!run_prog(prog, ctx)) + if (!run_prog(prog, ctx) && !IS_ERR_VALUE((long)run_ctx.retval)) run_ctx.retval = -EPERM; item++; } @@ -1389,7 +1389,7 @@ out: * 0: NET_XMIT_SUCCESS skb should be transmitted * 1: NET_XMIT_DROP skb should be dropped and cn * 2: NET_XMIT_CN skb should be transmitted and cn - * 3: -EPERM skb should be dropped + * 3: -err skb should be dropped */ #define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \ ({ \ @@ -1398,10 +1398,12 @@ out: u32 _ret; \ _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, 0, &_flags); \ _cn = _flags & BPF_RET_SET_CN; \ + if (_ret && !IS_ERR_VALUE((long)_ret)) \ + _ret = -EFAULT; \ if (!_ret) \ _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ else \ - _ret = (_cn ? NET_XMIT_DROP : -EPERM); \ + _ret = (_cn ? NET_XMIT_DROP : _ret); \ _ret; \ }) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a9c96c21330a..fe2272defcd9 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5033,6 +5033,22 @@ union bpf_attr { * * Return * The number of arguments of the traced function. + * + * int bpf_get_retval(void) + * Description + * Get the syscall's return value that will be returned to userspace. + * + * This helper is currently supported by cgroup programs only. + * Return + * The syscall's return value. + * + * int bpf_set_retval(int retval) + * Description + * Set the syscall's return value that will be returned to userspace. + * + * This helper is currently supported by cgroup programs only. + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5221,6 +5237,8 @@ union bpf_attr { FN(get_func_arg), \ FN(get_func_ret), \ FN(get_func_arg_cnt), \ + FN(get_retval), \ + FN(set_retval), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 6f043b5969a4d6d385ca429388ded37e30e0d179 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Thu, 20 Jan 2022 11:48:56 +0200 Subject: drm/locking: fix drm_modeset_acquire_ctx kernel-doc The stack_depot member was added without kernel-doc, leading to below warning. Fix it. ./include/drm/drm_modeset_lock.h:74: warning: Function parameter or member 'stack_depot' not described in 'drm_modeset_acquire_ctx' Reported-by: Stephen Rothwell Fixes: cd06ab2fd48f ("drm/locking: add backtrace for locking contended locks without backoff") Signed-off-by: Jani Nikula Reviewed-by: Daniel Vetter Tested-by: Stephen Rothwell Link: https://patchwork.freedesktop.org/patch/msgid/20220120094856.3004147-1-jani.nikula@intel.com --- include/drm/drm_modeset_lock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/drm/drm_modeset_lock.h b/include/drm/drm_modeset_lock.h index b84693fbd2b5..ec4f543c3d95 100644 --- a/include/drm/drm_modeset_lock.h +++ b/include/drm/drm_modeset_lock.h @@ -34,6 +34,7 @@ struct drm_modeset_lock; * struct drm_modeset_acquire_ctx - locking context (see ww_acquire_ctx) * @ww_ctx: base acquire ctx * @contended: used internally for -EDEADLK handling + * @stack_depot: used internally for contention debugging * @locked: list of held locks * @trylock_only: trylock mode used in atomic contexts/panic notifiers * @interruptible: whether interruptible locking should be used. -- cgit v1.2.3 From 3368aa357f3ba133ae65fc26c04d24a1447a3903 Mon Sep 17 00:00:00 2001 From: Manish Mandlik Date: Tue, 11 Jan 2022 08:14:25 -0800 Subject: Bluetooth: msft: Handle MSFT Monitor Device Event Whenever the controller starts/stops monitoring a bt device, it sends MSFT Monitor Device event. Add handler to read this vendor event. Test performed: - Verified by logs that the MSFT Monitor Device event is received from the controller whenever it starts/stops monitoring a device. Signed-off-by: Manish Mandlik Reviewed-by: Miao-chen Chou Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 586f69d084a2..639fb9f57ae7 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -258,6 +258,15 @@ struct adv_info { #define HCI_ADV_TX_POWER_NO_PREFERENCE 0x7F +struct monitored_device { + struct list_head list; + + bdaddr_t bdaddr; + __u8 addr_type; + __u16 handle; + bool notified; +}; + struct adv_pattern { struct list_head list; __u8 ad_type; @@ -591,6 +600,8 @@ struct hci_dev { struct delayed_work interleave_scan; + struct list_head monitored_devices; + #if IS_ENABLED(CONFIG_BT_LEDS) struct led_trigger *power_led; #endif -- cgit v1.2.3 From 8d7f167752c3e4c45a39e76ffa6f7209413d3fa6 Mon Sep 17 00:00:00 2001 From: Manish Mandlik Date: Tue, 11 Jan 2022 08:14:26 -0800 Subject: Bluetooth: mgmt: Add MGMT Adv Monitor Device Found/Lost events This patch introduces two new MGMT events for notifying the bluetoothd whenever the controller starts/stops monitoring a device. Test performed: - Verified by logs that the MSFT Monitor Device is received from the controller and the bluetoothd is notified whenever the controller starts/stops monitoring a device. Signed-off-by: Manish Mandlik Reviewed-by: Miao-chen Chou Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 3 +++ include/net/bluetooth/mgmt.h | 16 ++++++++++++++++ 2 files changed, 19 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 639fb9f57ae7..21eadb113a31 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -601,6 +601,7 @@ struct hci_dev { struct delayed_work interleave_scan; struct list_head monitored_devices; + bool advmon_pend_notify; #if IS_ENABLED(CONFIG_BT_LEDS) struct led_trigger *power_led; @@ -1858,6 +1859,8 @@ void mgmt_adv_monitor_removed(struct hci_dev *hdev, u16 handle); int mgmt_phy_configuration_changed(struct hci_dev *hdev, struct sock *skip); int mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev, u8 status); int mgmt_remove_adv_monitor_complete(struct hci_dev *hdev, u8 status); +void mgmt_adv_monitor_device_lost(struct hci_dev *hdev, u16 handle, + bdaddr_t *bdaddr, u8 addr_type); u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, u16 to_multiplier); diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 107b25deae68..99266f7aebdc 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -1104,3 +1104,19 @@ struct mgmt_ev_controller_resume { #define MGMT_WAKE_REASON_NON_BT_WAKE 0x0 #define MGMT_WAKE_REASON_UNEXPECTED 0x1 #define MGMT_WAKE_REASON_REMOTE_WAKE 0x2 + +#define MGMT_EV_ADV_MONITOR_DEVICE_FOUND 0x002f +struct mgmt_ev_adv_monitor_device_found { + __le16 monitor_handle; + struct mgmt_addr_info addr; + __s8 rssi; + __le32 flags; + __le16 eir_len; + __u8 eir[0]; +} __packed; + +#define MGMT_EV_ADV_MONITOR_DEVICE_LOST 0x0030 +struct mgmt_ev_adv_monitor_device_lost { + __le16 monitor_handle; + struct mgmt_addr_info addr; +} __packed; -- cgit v1.2.3 From 748cd5729ac7421091316e32dcdffb0578563880 Mon Sep 17 00:00:00 2001 From: Di Zhu Date: Wed, 19 Jan 2022 09:40:04 +0800 Subject: bpf: support BPF_PROG_QUERY for progs attached to sockmap Right now there is no way to query whether BPF programs are attached to a sockmap or not. we can use the standard interface in libbpf to query, such as: bpf_prog_query(mapFd, BPF_SK_SKB_STREAM_PARSER, 0, NULL, ...); the mapFd is the fd of sockmap. Signed-off-by: Di Zhu Acked-by: Yonghong Song Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/r/20220119014005.1209-1-zhudi2@huawei.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index dce54eb0aae8..80e3387ea3af 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2069,6 +2069,9 @@ int bpf_prog_test_run_syscall(struct bpf_prog *prog, int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); +int sock_map_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr); + void sock_map_unhash(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else @@ -2122,6 +2125,12 @@ static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void { return -EOPNOTSUPP; } + +static inline int sock_map_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EINVAL; +} #endif /* CONFIG_BPF_SYSCALL */ #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ -- cgit v1.2.3 From d16697cb6261d4cc23422e6b1cb2759df8aa76d0 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 21 Jan 2022 11:09:44 +0100 Subject: net: skbuff: add size metadata to skb_shared_info for xdp Introduce xdp_frags_size field in skb_shared_info data structure to store xdp_buff/xdp_frame frame paged size (xdp_frags_size will be used in xdp frags support). In order to not increase skb_shared_info size we will use a hole due to skb_shared_info alignment. Acked-by: Toke Hoiland-Jorgensen Acked-by: John Fastabend Acked-by: Jesper Dangaard Brouer Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/8a849819a3e0a143d540f78a3a5add76e17e980d.1642758637.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bf11e1fbd69b..8131d0de7559 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -557,6 +557,7 @@ struct skb_shared_info { * Warning : all fields before dataref are cleared in __alloc_skb() */ atomic_t dataref; + unsigned int xdp_frags_size; /* Intermediate layers must ensure that destructor_arg * remains valid until skb destructor */ -- cgit v1.2.3 From 2e88d4ff03013937028f5397268b21e10cf68713 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 21 Jan 2022 11:09:45 +0100 Subject: xdp: introduce flags field in xdp_buff/xdp_frame Introduce flags field in xdp_frame and xdp_buffer data structures to define additional buffer features. At the moment the only supported buffer feature is frags bit (XDP_FLAGS_HAS_FRAGS). frags bit is used to specify if this is a linear buffer (XDP_FLAGS_HAS_FRAGS not set) or a frags frame (XDP_FLAGS_HAS_FRAGS set). In the latter case the driver is expected to initialize the skb_shared_info structure at the end of the first buffer to link together subsequent buffers belonging to the same frame. Acked-by: Toke Hoiland-Jorgensen Acked-by: John Fastabend Acked-by: Jesper Dangaard Brouer Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/e389f14f3a162c0a5bc6a2e1aa8dd01a90be117d.1642758637.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/net/xdp.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include') diff --git a/include/net/xdp.h b/include/net/xdp.h index 8f0812e4996d..485e9495a690 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -66,6 +66,10 @@ struct xdp_txq_info { struct net_device *dev; }; +enum xdp_buff_flags { + XDP_FLAGS_HAS_FRAGS = BIT(0), /* non-linear xdp buff */ +}; + struct xdp_buff { void *data; void *data_end; @@ -74,13 +78,30 @@ struct xdp_buff { struct xdp_rxq_info *rxq; struct xdp_txq_info *txq; u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/ + u32 flags; /* supported values defined in xdp_buff_flags */ }; +static __always_inline bool xdp_buff_has_frags(struct xdp_buff *xdp) +{ + return !!(xdp->flags & XDP_FLAGS_HAS_FRAGS); +} + +static __always_inline void xdp_buff_set_frags_flag(struct xdp_buff *xdp) +{ + xdp->flags |= XDP_FLAGS_HAS_FRAGS; +} + +static __always_inline void xdp_buff_clear_frags_flag(struct xdp_buff *xdp) +{ + xdp->flags &= ~XDP_FLAGS_HAS_FRAGS; +} + static __always_inline void xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq) { xdp->frame_sz = frame_sz; xdp->rxq = rxq; + xdp->flags = 0; } static __always_inline void @@ -122,8 +143,14 @@ struct xdp_frame { */ struct xdp_mem_info mem; struct net_device *dev_rx; /* used by cpumap */ + u32 flags; /* supported values defined in xdp_buff_flags */ }; +static __always_inline bool xdp_frame_has_frags(struct xdp_frame *frame) +{ + return !!(frame->flags & XDP_FLAGS_HAS_FRAGS); +} + #define XDP_BULK_QUEUE_SIZE 16 struct xdp_frame_bulk { int count; @@ -180,6 +207,7 @@ void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) xdp->data_end = frame->data + frame->len; xdp->data_meta = frame->data - frame->metasize; xdp->frame_sz = frame->frame_sz; + xdp->flags = frame->flags; } static inline @@ -206,6 +234,7 @@ int xdp_update_frame_from_buff(struct xdp_buff *xdp, xdp_frame->headroom = headroom - sizeof(*xdp_frame); xdp_frame->metasize = metasize; xdp_frame->frame_sz = xdp->frame_sz; + xdp_frame->flags = xdp->flags; return 0; } -- cgit v1.2.3 From d65a1906b31246492449eafe9cace188cb59e26c Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 21 Jan 2022 11:09:48 +0100 Subject: net: xdp: add xdp_update_skb_shared_info utility routine Introduce xdp_update_skb_shared_info routine to update frags array metadata in skb_shared_info data structure converting to a skb from a xdp_buff or xdp_frame. According to the current skb_shared_info architecture in xdp_frame/xdp_buff and to the xdp frags support, there is no need to run skb_add_rx_frag() and reset frags array converting the buffer to a skb since the frag array will be in the same position for xdp_buff/xdp_frame and for the skb, we just need to update memory metadata. Introduce XDP_FLAGS_PF_MEMALLOC flag in xdp_buff_flags in order to mark the xdp_buff or xdp_frame as under memory-pressure if pages of the frags array are under memory pressure. Doing so we can avoid looping over all fragments in xdp_update_skb_shared_info routine. The driver is expected to set the flag constructing the xdp_buffer using xdp_buff_set_frag_pfmemalloc utility routine. Rely on xdp_update_skb_shared_info in __xdp_build_skb_from_frame routine converting the non-linear xdp_frame to a skb after performing a XDP_REDIRECT. Acked-by: Toke Hoiland-Jorgensen Acked-by: John Fastabend Acked-by: Jesper Dangaard Brouer Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/bfd23fb8a8d7438724f7819c567cdf99ffd6226f.1642758637.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/net/xdp.h | 33 ++++++++++++++++++++++++++++++++- 1 file changed, 32 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/xdp.h b/include/net/xdp.h index 485e9495a690..1f8641ec658e 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -67,7 +67,10 @@ struct xdp_txq_info { }; enum xdp_buff_flags { - XDP_FLAGS_HAS_FRAGS = BIT(0), /* non-linear xdp buff */ + XDP_FLAGS_HAS_FRAGS = BIT(0), /* non-linear xdp buff */ + XDP_FLAGS_FRAGS_PF_MEMALLOC = BIT(1), /* xdp paged memory is under + * pressure + */ }; struct xdp_buff { @@ -96,6 +99,16 @@ static __always_inline void xdp_buff_clear_frags_flag(struct xdp_buff *xdp) xdp->flags &= ~XDP_FLAGS_HAS_FRAGS; } +static __always_inline bool xdp_buff_is_frag_pfmemalloc(struct xdp_buff *xdp) +{ + return !!(xdp->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); +} + +static __always_inline void xdp_buff_set_frag_pfmemalloc(struct xdp_buff *xdp) +{ + xdp->flags |= XDP_FLAGS_FRAGS_PF_MEMALLOC; +} + static __always_inline void xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq) { @@ -151,6 +164,11 @@ static __always_inline bool xdp_frame_has_frags(struct xdp_frame *frame) return !!(frame->flags & XDP_FLAGS_HAS_FRAGS); } +static __always_inline bool xdp_frame_is_frag_pfmemalloc(struct xdp_frame *frame) +{ + return !!(frame->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); +} + #define XDP_BULK_QUEUE_SIZE 16 struct xdp_frame_bulk { int count; @@ -186,6 +204,19 @@ static inline void xdp_scrub_frame(struct xdp_frame *frame) frame->dev_rx = NULL; } +static inline void +xdp_update_skb_shared_info(struct sk_buff *skb, u8 nr_frags, + unsigned int size, unsigned int truesize, + bool pfmemalloc) +{ + skb_shinfo(skb)->nr_frags = nr_frags; + + skb->len += size; + skb->data_len += size; + skb->truesize += truesize; + skb->pfmemalloc |= pfmemalloc; +} + /* Avoids inlining WARN macro in fast-path */ void xdp_warn(const char *msg, const char *func, const int line); #define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__) -- cgit v1.2.3 From 7c48cb0176c6d6d3b55029f7ff4ffa05faee6446 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 21 Jan 2022 11:09:50 +0100 Subject: xdp: add frags support to xdp_return_{buff/frame} Take into account if the received xdp_buff/xdp_frame is non-linear recycling/returning the frame memory to the allocator or into xdp_frame_bulk. Acked-by: Toke Hoiland-Jorgensen Acked-by: John Fastabend Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/a961069febc868508ce1bdf5e53a343eb4e57cb2.1642758637.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/net/xdp.h | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/xdp.h b/include/net/xdp.h index 1f8641ec658e..8463dea8b4db 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -306,10 +306,24 @@ void __xdp_release_frame(void *data, struct xdp_mem_info *mem); static inline void xdp_release_frame(struct xdp_frame *xdpf) { struct xdp_mem_info *mem = &xdpf->mem; + struct skb_shared_info *sinfo; + int i; /* Curr only page_pool needs this */ - if (mem->type == MEM_TYPE_PAGE_POOL) - __xdp_release_frame(xdpf->data, mem); + if (mem->type != MEM_TYPE_PAGE_POOL) + return; + + if (likely(!xdp_frame_has_frags(xdpf))) + goto out; + + sinfo = xdp_get_shared_info_from_frame(xdpf); + for (i = 0; i < sinfo->nr_frags; i++) { + struct page *page = skb_frag_page(&sinfo->frags[i]); + + __xdp_release_frame(page_address(page), mem); + } +out: + __xdp_release_frame(xdpf->data, mem); } int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, -- cgit v1.2.3 From c2f2cdbeffda7b153c19e0f3d73149c41026c0db Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 21 Jan 2022 11:09:52 +0100 Subject: bpf: introduce BPF_F_XDP_HAS_FRAGS flag in prog_flags loading the ebpf program Introduce BPF_F_XDP_HAS_FRAGS and the related field in bpf_prog_aux in order to notify the driver the loaded program support xdp frags. Acked-by: Toke Hoiland-Jorgensen Acked-by: John Fastabend Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/db2e8075b7032a356003f407d1b0deb99adaa0ed.1642758637.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 5 +++++ 2 files changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 80e3387ea3af..e93ed028a030 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -933,6 +933,7 @@ struct bpf_prog_aux { bool func_proto_unreliable; bool sleepable; bool tail_call_reachable; + bool xdp_has_frags; struct hlist_node tramp_hlist; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index fe2272defcd9..945649c67e03 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1113,6 +1113,11 @@ enum bpf_link_type { */ #define BPF_F_SLEEPABLE (1U << 4) +/* If BPF_F_XDP_HAS_FRAGS is used in BPF_PROG_LOAD command, the loaded program + * fully support xdp frags. + */ +#define BPF_F_XDP_HAS_FRAGS (1U << 5) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * -- cgit v1.2.3 From 0165cc817075cf701e4289838f1d925ff1911b3e Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 21 Jan 2022 11:09:54 +0100 Subject: bpf: introduce bpf_xdp_get_buff_len helper Introduce bpf_xdp_get_buff_len helper in order to return the xdp buffer total size (linear and paged area) Acked-by: Toke Hoiland-Jorgensen Acked-by: John Fastabend Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/aac9ac3504c84026cf66a3c71b7c5ae89bc991be.1642758637.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/net/xdp.h | 14 ++++++++++++++ include/uapi/linux/bpf.h | 7 +++++++ 2 files changed, 21 insertions(+) (limited to 'include') diff --git a/include/net/xdp.h b/include/net/xdp.h index 8463dea8b4db..52b593321956 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -145,6 +145,20 @@ xdp_get_shared_info_from_buff(struct xdp_buff *xdp) return (struct skb_shared_info *)xdp_data_hard_end(xdp); } +static __always_inline unsigned int xdp_get_buff_len(struct xdp_buff *xdp) +{ + unsigned int len = xdp->data_end - xdp->data; + struct skb_shared_info *sinfo; + + if (likely(!xdp_buff_has_frags(xdp))) + goto out; + + sinfo = xdp_get_shared_info_from_buff(xdp); + len += sinfo->xdp_frags_size; +out: + return len; +} + struct xdp_frame { void *data; u16 len; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 945649c67e03..5a28772063f6 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5054,6 +5054,12 @@ union bpf_attr { * This helper is currently supported by cgroup programs only. * Return * 0 on success, or a negative error in case of failure. + * + * u64 bpf_xdp_get_buff_len(struct xdp_buff *xdp_md) + * Description + * Get the total size of a given xdp buff (linear and paged area) + * Return + * The total size of a given xdp buffer. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5244,6 +5250,7 @@ union bpf_attr { FN(get_func_arg_cnt), \ FN(get_retval), \ FN(set_retval), \ + FN(xdp_get_buff_len), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From bf25146a5595269810b1f47d048f114c5ff9f544 Mon Sep 17 00:00:00 2001 From: Eelco Chaudron Date: Fri, 21 Jan 2022 11:09:55 +0100 Subject: bpf: add frags support to the bpf_xdp_adjust_tail() API This change adds support for tail growing and shrinking for XDP frags. When called on a non-linear packet with a grow request, it will work on the last fragment of the packet. So the maximum grow size is the last fragments tailroom, i.e. no new buffer will be allocated. A XDP frags capable driver is expected to set frag_size in xdp_rxq_info data structure to notify the XDP core the fragment size. frag_size set to 0 is interpreted by the XDP core as tail growing is not allowed. Introduce __xdp_rxq_info_reg utility routine to initialize frag_size field. When shrinking, it will work from the last fragment, all the way down to the base buffer depending on the shrinking size. It's important to mention that once you shrink down the fragment(s) are freed, so you can not grow again to the original size. Acked-by: Toke Hoiland-Jorgensen Acked-by: John Fastabend Acked-by: Jakub Kicinski Co-developed-by: Lorenzo Bianconi Signed-off-by: Lorenzo Bianconi Signed-off-by: Eelco Chaudron Link: https://lore.kernel.org/r/eabda3485dda4f2f158b477729337327e609461d.1642758637.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/net/xdp.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/xdp.h b/include/net/xdp.h index 52b593321956..b7721c3e4d1f 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -60,6 +60,7 @@ struct xdp_rxq_info { u32 reg_state; struct xdp_mem_info mem; unsigned int napi_id; + u32 frag_size; } ____cacheline_aligned; /* perf critical, avoid false-sharing */ struct xdp_txq_info { @@ -304,6 +305,8 @@ struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp) return xdp_frame; } +void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, + struct xdp_buff *xdp); void xdp_return_frame(struct xdp_frame *xdpf); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf); void xdp_return_buff(struct xdp_buff *xdp); @@ -340,8 +343,17 @@ out: __xdp_release_frame(xdpf->data, mem); } -int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, - struct net_device *dev, u32 queue_index, unsigned int napi_id); +int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, + struct net_device *dev, u32 queue_index, + unsigned int napi_id, u32 frag_size); +static inline int +xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, + struct net_device *dev, u32 queue_index, + unsigned int napi_id) +{ + return __xdp_rxq_info_reg(xdp_rxq, dev, queue_index, napi_id, 0); +} + void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq); void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq); -- cgit v1.2.3 From f45d5b6ce2e835834c94b8b700787984f02cd662 Mon Sep 17 00:00:00 2001 From: Toke Hoiland-Jorgensen Date: Fri, 21 Jan 2022 11:10:02 +0100 Subject: bpf: generalise tail call map compatibility check The check for tail call map compatibility ensures that tail calls only happen between maps of the same type. To ensure backwards compatibility for XDP frags we need a similar type of check for cpumap and devmap programs, so move the state from bpf_array_aux into bpf_map, add xdp_has_frags to the check, and apply the same check to cpumap and devmap. Acked-by: John Fastabend Co-developed-by: Lorenzo Bianconi Signed-off-by: Lorenzo Bianconi Signed-off-by: Toke Hoiland-Jorgensen Link: https://lore.kernel.org/r/f19fd97c0328a39927f3ad03e1ca6b43fd53cdfd.1642758637.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 30 +++++++++++++++++++----------- 1 file changed, 19 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e93ed028a030..e8ec8d2f2fe3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -194,6 +194,17 @@ struct bpf_map { struct work_struct work; struct mutex freeze_mutex; atomic64_t writecnt; + /* 'Ownership' of program-containing map is claimed by the first program + * that is going to use this map or by the first program which FD is + * stored in the map to make sure that all callers and callees have the + * same prog type, JITed flag and xdp_has_frags flag. + */ + struct { + spinlock_t lock; + enum bpf_prog_type type; + bool jited; + bool xdp_has_frags; + } owner; }; static inline bool map_value_has_spin_lock(const struct bpf_map *map) @@ -994,16 +1005,6 @@ struct bpf_prog_aux { }; struct bpf_array_aux { - /* 'Ownership' of prog array is claimed by the first program that - * is going to use this map or by the first program which FD is - * stored in the map to make sure that all callers and callees have - * the same prog type and JITed flag. - */ - struct { - spinlock_t lock; - enum bpf_prog_type type; - bool jited; - } owner; /* Programs with direct jumps into programs part of this array. */ struct list_head poke_progs; struct bpf_map *map; @@ -1178,7 +1179,14 @@ struct bpf_event_entry { struct rcu_head rcu; }; -bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); +static inline bool map_type_contains_progs(struct bpf_map *map) +{ + return map->map_type == BPF_MAP_TYPE_PROG_ARRAY || + map->map_type == BPF_MAP_TYPE_DEVMAP || + map->map_type == BPF_MAP_TYPE_CPUMAP; +} + +bool bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp); int bpf_prog_calc_tag(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); -- cgit v1.2.3 From 3f364222d032eea6b245780e845ad213dab28cdd Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 21 Jan 2022 11:10:03 +0100 Subject: net: xdp: introduce bpf_xdp_pointer utility routine Similar to skb_header_pointer, introduce bpf_xdp_pointer utility routine to return a pointer to a given position in the xdp_buff if the requested area (offset + len) is contained in a contiguous memory area otherwise it will be copied in a bounce buffer provided by the caller. Similar to the tc counterpart, introduce the two following xdp helpers: - bpf_xdp_load_bytes - bpf_xdp_store_bytes Reviewed-by: Eelco Chaudron Acked-by: Toke Hoiland-Jorgensen Acked-by: John Fastabend Acked-by: Jakub Kicinski Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/ab285c1efdd5b7a9d361348b1e7d3ef49f6382b3.1642758637.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 5a28772063f6..16a7574292a5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5060,6 +5060,22 @@ union bpf_attr { * Get the total size of a given xdp buff (linear and paged area) * Return * The total size of a given xdp buffer. + * + * long bpf_xdp_load_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * This helper is provided as an easy way to load data from a + * xdp buffer. It can be used to load *len* bytes from *offset* from + * the frame associated to *xdp_md*, into the buffer pointed by + * *buf*. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_xdp_store_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * Store *len* bytes from buffer *buf* into the frame + * associated to *xdp_md*, at *offset*. + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5251,6 +5267,8 @@ union bpf_attr { FN(get_retval), \ FN(set_retval), \ FN(xdp_get_buff_len), \ + FN(xdp_load_bytes), \ + FN(xdp_store_bytes), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 96489c1c0b53131b0e1ec33e2060538379ad6152 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 16 Dec 2021 12:16:38 +0100 Subject: mtd: nand: ecc: Add infrastructure to support hardware engines Add the necessary helpers to register/unregister hardware ECC engines that will be called from ECC engine drivers. Also add helpers to get the right engine from the user perspective. Keep a reference of the in use ECC engine in order to prevent modules to be unloaded. Put the reference when the engine gets retired. A static list of hardware (only) ECC engines is setup to keep track of the registered engines. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20211216111654.238086-13-miquel.raynal@bootlin.com --- include/linux/mtd/nand.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 32fc7edf65b3..4ddd20fe9c9e 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -263,12 +263,36 @@ struct nand_ecc_engine_ops { struct nand_page_io_req *req); }; +/** + * enum nand_ecc_engine_integration - How the NAND ECC engine is integrated + * @NAND_ECC_ENGINE_INTEGRATION_INVALID: Invalid value + * @NAND_ECC_ENGINE_INTEGRATION_PIPELINED: Pipelined engine, performs on-the-fly + * correction, does not need to copy + * data around + * @NAND_ECC_ENGINE_INTEGRATION_EXTERNAL: External engine, needs to bring the + * data into its own area before use + */ +enum nand_ecc_engine_integration { + NAND_ECC_ENGINE_INTEGRATION_INVALID, + NAND_ECC_ENGINE_INTEGRATION_PIPELINED, + NAND_ECC_ENGINE_INTEGRATION_EXTERNAL, +}; + /** * struct nand_ecc_engine - ECC engine abstraction for NAND devices + * @dev: Host device + * @node: Private field for registration time * @ops: ECC engine operations + * @integration: How the engine is integrated with the host + * (only relevant on %NAND_ECC_ENGINE_TYPE_ON_HOST engines) + * @priv: Private data */ struct nand_ecc_engine { + struct device *dev; + struct list_head node; struct nand_ecc_engine_ops *ops; + enum nand_ecc_engine_integration integration; + void *priv; }; void of_get_nand_ecc_user_config(struct nand_device *nand); @@ -279,8 +303,12 @@ int nand_ecc_prepare_io_req(struct nand_device *nand, int nand_ecc_finish_io_req(struct nand_device *nand, struct nand_page_io_req *req); bool nand_ecc_is_strong_enough(struct nand_device *nand); +int nand_ecc_register_on_host_hw_engine(struct nand_ecc_engine *engine); +int nand_ecc_unregister_on_host_hw_engine(struct nand_ecc_engine *engine); struct nand_ecc_engine *nand_ecc_get_sw_engine(struct nand_device *nand); struct nand_ecc_engine *nand_ecc_get_on_die_hw_engine(struct nand_device *nand); +struct nand_ecc_engine *nand_ecc_get_on_host_hw_engine(struct nand_device *nand); +void nand_ecc_put_on_host_hw_engine(struct nand_device *nand); #if IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING) struct nand_ecc_engine *nand_ecc_sw_hamming_get_engine(void); -- cgit v1.2.3 From cda32a618debd3fad8e42757b198719ae180f8f4 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 16 Dec 2021 12:16:39 +0100 Subject: mtd: nand: Add a new helper to retrieve the ECC context Introduce nand_to_ecc_ctx() which will allow to easily jump to the private pointer of an ECC context given a NAND device. This is very handy, from the prepare or finish ECC hook, to get the internal context out of the NAND device object. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20211216111654.238086-14-miquel.raynal@bootlin.com --- include/linux/mtd/nand.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 4ddd20fe9c9e..b617efa0a881 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -990,6 +990,11 @@ int nanddev_markbad(struct nand_device *nand, const struct nand_pos *pos); int nanddev_ecc_engine_init(struct nand_device *nand); void nanddev_ecc_engine_cleanup(struct nand_device *nand); +static inline void *nand_to_ecc_ctx(struct nand_device *nand) +{ + return nand->ecc.ctx.priv; +} + /* BBT related functions */ enum nand_bbt_block_status { NAND_BBT_BLOCK_STATUS_UNKNOWN, -- cgit v1.2.3 From 02d1d0e4dfc3fdc5aa05b78e7def00dc1e62257e Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 7 Jan 2022 10:46:11 -0800 Subject: mtd: rawnand: brcmnand: Add platform data structure for BCMA Update the BCMA's chipcommon nand flash driver to detect which chip-select is used and pass that information via platform data to the brcmnand driver. Make sure that the brcmnand platform data structure is always at the beginning of the platform data of the "nflash" device created by BCMA to allow brcmnand to safely de-reference it. Signed-off-by: Florian Fainelli Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20220107184614.2670254-7-f.fainelli@gmail.com --- include/linux/bcma/bcma_driver_chipcommon.h | 5 +++++ include/linux/platform_data/brcmnand.h | 12 ++++++++++++ 2 files changed, 17 insertions(+) create mode 100644 include/linux/platform_data/brcmnand.h (limited to 'include') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index d35b9206096d..e3314f746bfa 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -3,6 +3,7 @@ #define LINUX_BCMA_DRIVER_CC_H_ #include +#include #include /** ChipCommon core registers. **/ @@ -599,6 +600,10 @@ struct bcma_sflash { #ifdef CONFIG_BCMA_NFLASH struct bcma_nflash { + /* Must be the fist member for the brcmnand driver to + * de-reference that structure. + */ + struct brcmnand_platform_data brcmnand_info; bool present; bool boot; /* This is the flash the SoC boots from */ }; diff --git a/include/linux/platform_data/brcmnand.h b/include/linux/platform_data/brcmnand.h new file mode 100644 index 000000000000..8b8777985dce --- /dev/null +++ b/include/linux/platform_data/brcmnand.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef BRCMNAND_PLAT_DATA_H +#define BRCMNAND_PLAT_DATA_H + +struct brcmnand_platform_data { + int chip_select; + const char * const *part_probe_types; + unsigned int ecc_stepsize; + unsigned int ecc_strength; +}; + +#endif /* BRCMNAND_PLAT_DATA_H */ -- cgit v1.2.3 From 1e73d7f689c7a8fa13f78fe8d6be908fdceef17a Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 15 Dec 2021 16:13:35 +0100 Subject: iio: core: Fix the kernel doc regarding the currentmode iio_dev entry This is an internal variable, which should be accessed in a very sporadic way and in no case changed by any device driver. Signed-off-by: Miquel Raynal Reviewed-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20211215151344.163036-2-miquel.raynal@bootlin.com Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 07025d6b3de1..faf00f2c0be6 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -489,7 +489,7 @@ struct iio_buffer_setup_ops { /** * struct iio_dev - industrial I/O device * @modes: [DRIVER] operating modes supported by device - * @currentmode: [DRIVER] current operating mode + * @currentmode: [INTERN] current operating mode * @dev: [DRIVER] device structure, should be assigned a parent * and owner * @buffer: [DRIVER] any buffer present -- cgit v1.2.3 From da5936770517aef8b28888f1123fa654c78cc2f9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Sat, 22 Jan 2022 14:09:04 +0100 Subject: adis: simplify 'adis_update_bits' macros MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There's no need to use '__builtin_choose_expr' to choose the right call to 'adis_update_bits_base()'. We can change the 'BUILD_BUG_ON()' condition so that it makes sure only the supported sizes are passed in. With that, we can just use 'sizeof(val)' as the size argument of 'adis_update_bits_base()'. Signed-off-by: Nuno Sá Link: https://lore.kernel.org/r/20220122130905.99-2-nuno.sa@analog.com Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 7c02f5292eea..11754f97d8bb 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -381,10 +381,8 @@ static inline int adis_update_bits_base(struct adis *adis, unsigned int reg, * @val can lead to undesired behavior if the register to update is 16bit. */ #define adis_update_bits(adis, reg, mask, val) ({ \ - BUILD_BUG_ON(sizeof(val) == 1 || sizeof(val) == 8); \ - __builtin_choose_expr(sizeof(val) == 4, \ - adis_update_bits_base(adis, reg, mask, val, 4), \ - adis_update_bits_base(adis, reg, mask, val, 2)); \ + BUILD_BUG_ON(sizeof(val) != 2 && sizeof(val) != 4); \ + adis_update_bits_base(adis, reg, mask, val, sizeof(val)); \ }) /** @@ -399,10 +397,8 @@ static inline int adis_update_bits_base(struct adis *adis, unsigned int reg, * @val can lead to undesired behavior if the register to update is 16bit. */ #define __adis_update_bits(adis, reg, mask, val) ({ \ - BUILD_BUG_ON(sizeof(val) == 1 || sizeof(val) == 8); \ - __builtin_choose_expr(sizeof(val) == 4, \ - __adis_update_bits_base(adis, reg, mask, val, 4), \ - __adis_update_bits_base(adis, reg, mask, val, 2)); \ + BUILD_BUG_ON(sizeof(val) != 2 && sizeof(val) != 4); \ + __adis_update_bits_base(adis, reg, mask, val, sizeof(val)); \ }) int adis_enable_irq(struct adis *adis, bool enable); -- cgit v1.2.3 From c39010ea6ba13bdf0003bd353e1d4c663aaac0a8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Sat, 22 Jan 2022 14:09:05 +0100 Subject: iio: adis: stylistic changes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Minor stylistic changes to address checkptach complains when called with '--strict'. Signed-off-by: Nuno Sá Link: https://lore.kernel.org/r/20220122130905.99-3-nuno.sa@analog.com Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 48 +++++++++++++++++++++++--------------------- 1 file changed, 25 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 11754f97d8bb..515ca09764fe 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -32,6 +32,7 @@ struct adis_timeout { u16 sw_reset_ms; u16 self_test_ms; }; + /** * struct adis_data - ADIS chip variant specific data * @read_delay: SPI delay for read operations in us @@ -45,7 +46,7 @@ struct adis_timeout { * @self_test_mask: Bitmask of supported self-test operations * @self_test_reg: Register address to request self test command * @self_test_no_autoclear: True if device's self-test needs clear of ctrl reg - * @status_error_msgs: Array of error messgaes + * @status_error_msgs: Array of error messages * @status_error_mask: Bitmask of errors supported by the device * @timeouts: Chip specific delays * @enable_irq: Hook for ADIS devices that have a special IRQ enable/disable @@ -130,12 +131,12 @@ struct adis { unsigned long irq_flag; void *buffer; - uint8_t tx[10] ____cacheline_aligned; - uint8_t rx[4]; + u8 tx[10] ____cacheline_aligned; + u8 rx[4]; }; int adis_init(struct adis *adis, struct iio_dev *indio_dev, - struct spi_device *spi, const struct adis_data *data); + struct spi_device *spi, const struct adis_data *data); int __adis_reset(struct adis *adis); /** @@ -156,9 +157,9 @@ static inline int adis_reset(struct adis *adis) } int __adis_write_reg(struct adis *adis, unsigned int reg, - unsigned int val, unsigned int size); + unsigned int val, unsigned int size); int __adis_read_reg(struct adis *adis, unsigned int reg, - unsigned int *val, unsigned int size); + unsigned int *val, unsigned int size); /** * __adis_write_reg_8() - Write single byte to a register (unlocked) @@ -167,7 +168,7 @@ int __adis_read_reg(struct adis *adis, unsigned int reg, * @value: The value to write */ static inline int __adis_write_reg_8(struct adis *adis, unsigned int reg, - uint8_t val) + u8 val) { return __adis_write_reg(adis, reg, val, 1); } @@ -179,7 +180,7 @@ static inline int __adis_write_reg_8(struct adis *adis, unsigned int reg, * @value: Value to be written */ static inline int __adis_write_reg_16(struct adis *adis, unsigned int reg, - uint16_t val) + u16 val) { return __adis_write_reg(adis, reg, val, 2); } @@ -191,7 +192,7 @@ static inline int __adis_write_reg_16(struct adis *adis, unsigned int reg, * @value: Value to be written */ static inline int __adis_write_reg_32(struct adis *adis, unsigned int reg, - uint32_t val) + u32 val) { return __adis_write_reg(adis, reg, val, 4); } @@ -203,7 +204,7 @@ static inline int __adis_write_reg_32(struct adis *adis, unsigned int reg, * @val: The value read back from the device */ static inline int __adis_read_reg_16(struct adis *adis, unsigned int reg, - uint16_t *val) + u16 *val) { unsigned int tmp; int ret; @@ -222,7 +223,7 @@ static inline int __adis_read_reg_16(struct adis *adis, unsigned int reg, * @val: The value read back from the device */ static inline int __adis_read_reg_32(struct adis *adis, unsigned int reg, - uint32_t *val) + u32 *val) { unsigned int tmp; int ret; @@ -242,7 +243,7 @@ static inline int __adis_read_reg_32(struct adis *adis, unsigned int reg, * @size: The size of the @value (in bytes) */ static inline int adis_write_reg(struct adis *adis, unsigned int reg, - unsigned int val, unsigned int size) + unsigned int val, unsigned int size) { int ret; @@ -261,7 +262,7 @@ static inline int adis_write_reg(struct adis *adis, unsigned int reg, * @size: The size of the @val buffer */ static int adis_read_reg(struct adis *adis, unsigned int reg, - unsigned int *val, unsigned int size) + unsigned int *val, unsigned int size) { int ret; @@ -279,7 +280,7 @@ static int adis_read_reg(struct adis *adis, unsigned int reg, * @value: The value to write */ static inline int adis_write_reg_8(struct adis *adis, unsigned int reg, - uint8_t val) + u8 val) { return adis_write_reg(adis, reg, val, 1); } @@ -291,7 +292,7 @@ static inline int adis_write_reg_8(struct adis *adis, unsigned int reg, * @value: Value to be written */ static inline int adis_write_reg_16(struct adis *adis, unsigned int reg, - uint16_t val) + u16 val) { return adis_write_reg(adis, reg, val, 2); } @@ -303,7 +304,7 @@ static inline int adis_write_reg_16(struct adis *adis, unsigned int reg, * @value: Value to be written */ static inline int adis_write_reg_32(struct adis *adis, unsigned int reg, - uint32_t val) + u32 val) { return adis_write_reg(adis, reg, val, 4); } @@ -315,7 +316,7 @@ static inline int adis_write_reg_32(struct adis *adis, unsigned int reg, * @val: The value read back from the device */ static inline int adis_read_reg_16(struct adis *adis, unsigned int reg, - uint16_t *val) + u16 *val) { unsigned int tmp; int ret; @@ -334,7 +335,7 @@ static inline int adis_read_reg_16(struct adis *adis, unsigned int reg, * @val: The value read back from the device */ static inline int adis_read_reg_32(struct adis *adis, unsigned int reg, - uint32_t *val) + u32 *val) { unsigned int tmp; int ret; @@ -439,8 +440,8 @@ static inline void adis_dev_unlock(struct adis *adis) } int adis_single_conversion(struct iio_dev *indio_dev, - const struct iio_chan_spec *chan, unsigned int error_mask, - int *val); + const struct iio_chan_spec *chan, + unsigned int error_mask, int *val); #define ADIS_VOLTAGE_CHAN(addr, si, chan, name, info_all, bits) { \ .type = IIO_VOLTAGE, \ @@ -489,7 +490,7 @@ int adis_single_conversion(struct iio_dev *indio_dev, .modified = 1, \ .channel2 = IIO_MOD_ ## mod, \ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \ - info_sep, \ + (info_sep), \ .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), \ .info_mask_shared_by_all = info_all, \ .address = (addr), \ @@ -523,7 +524,7 @@ devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev, int devm_adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev); int adis_update_scan_mode(struct iio_dev *indio_dev, - const unsigned long *scan_mask); + const unsigned long *scan_mask); #else /* CONFIG_IIO_BUFFER */ @@ -547,7 +548,8 @@ static inline int devm_adis_probe_trigger(struct adis *adis, #ifdef CONFIG_DEBUG_FS int adis_debugfs_reg_access(struct iio_dev *indio_dev, - unsigned int reg, unsigned int writeval, unsigned int *readval); + unsigned int reg, unsigned int writeval, + unsigned int *readval); #else -- cgit v1.2.3 From 7a3b3dc3bb2eeac4adf8b01b1b6b519bcbc48cfc Mon Sep 17 00:00:00 2001 From: Benjamin Gaignard Date: Fri, 7 Jan 2022 16:54:54 +0100 Subject: media: hevc: Remove RPS named flags Marking a picture as long-term reference is valid for DPB but not for RPS. Change flag name to match with the description in HEVC spec chapter "8.3.2 Decoding process for reference picture set". PocStCurrBefore, PocStCurrAfter, PocLtCurr lists could be built by the kernel from the DPB entries struct v4l2_hevc_dpb_entry, using the information in the rps field. This way RPS flags becomes useless and are removed. This patch breaks the staging HEVC API because it introduces a new flag, changes a field name in v4l2_hevc_dpb_entry structure and removes V4L2_HEVC_DPB_ENTRY_RPS_* flags. [hverkuil: fixed some typos] Signed-off-by: Benjamin Gaignard Reviewed-by: Jernej Skrabec Reviewed-by: Ezequiel Garcia Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/hevc-ctrls.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/media/hevc-ctrls.h b/include/media/hevc-ctrls.h index ef63bc205756..01ccda48d8c5 100644 --- a/include/media/hevc-ctrls.h +++ b/include/media/hevc-ctrls.h @@ -127,15 +127,13 @@ struct v4l2_ctrl_hevc_pps { __u64 flags; }; -#define V4L2_HEVC_DPB_ENTRY_RPS_ST_CURR_BEFORE 0x01 -#define V4L2_HEVC_DPB_ENTRY_RPS_ST_CURR_AFTER 0x02 -#define V4L2_HEVC_DPB_ENTRY_RPS_LT_CURR 0x03 +#define V4L2_HEVC_DPB_ENTRY_LONG_TERM_REFERENCE 0x01 #define V4L2_HEVC_DPB_ENTRIES_NUM_MAX 16 struct v4l2_hevc_dpb_entry { __u64 timestamp; - __u8 rps; + __u8 flags; __u8 field_pic; __u16 pic_order_cnt[2]; __u8 padding[2]; -- cgit v1.2.3 From d49a14a946db0a8e0713aa43034879f967ab75e2 Mon Sep 17 00:00:00 2001 From: Sean Young Date: Thu, 13 Jan 2022 12:29:01 +0100 Subject: media: lirc: simplify gap calculation When a driver reports a timeout, no more IR activity will be reported until the next pulse. A space is inserted between the timeout and the next pulse, based on ktime. The timeout reports already a duration, so this duration should not be added to the gap. Otherwise there is no change to the functionality. Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab --- include/media/rc-core.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/media/rc-core.h b/include/media/rc-core.h index ab9d3b7cd799..33b3f7fcf92e 100644 --- a/include/media/rc-core.h +++ b/include/media/rc-core.h @@ -130,9 +130,7 @@ struct lirc_fh { * @tx_resolution: resolution (in us) of output sampler * @lirc_dev: lirc device * @lirc_cdev: lirc char cdev - * @gap_start: time when gap starts - * @gap_duration: duration of initial gap - * @gap: true if we're in a gap + * @gap_start: start time for gap after timeout if non-zero * @lirc_fh_lock: protects lirc_fh list * @lirc_fh: list of open files * @registered: set to true by rc_register_device(), false by @@ -201,8 +199,6 @@ struct rc_dev { struct device lirc_dev; struct cdev lirc_cdev; ktime_t gap_start; - u64 gap_duration; - bool gap; spinlock_t lirc_fh_lock; struct list_head lirc_fh; #endif -- cgit v1.2.3 From 1dafede34dda19fc2878724145dc16c0b51dc174 Mon Sep 17 00:00:00 2001 From: Keyon Jie Date: Thu, 20 Jan 2022 17:15:28 -0600 Subject: ASoC: SOF: add _D3_PERSISTENT flag to fw_ready message MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a bit definition to the fw_ready message, to denote if the FW supports the IMR (Isolated Memory Region) restoring feature. If the bit is set, the driver can skip downloading the firmware again during system resume or runtime resume. Bump the ABI version to 3.19 to make it aligned with FW side. Reviewed-by: Ranjani Sridharan Reviewed-by: Péter Ujfalusi Signed-off-by: Keyon Jie Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20220120231532.196926-2-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof/info.h | 1 + include/uapi/sound/sof/abi.h | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/sof/info.h b/include/sound/sof/info.h index 0b7101aef596..65e86e4e9fd8 100644 --- a/include/sound/sof/info.h +++ b/include/sound/sof/info.h @@ -25,6 +25,7 @@ #define SOF_IPC_INFO_LOCKS BIT(1) #define SOF_IPC_INFO_LOCKSV BIT(2) #define SOF_IPC_INFO_GDB BIT(3) +#define SOF_IPC_INFO_D3_PERSISTENT BIT(4) /* extended data types that can be appended onto end of sof_ipc_fw_ready */ enum sof_ipc_ext_data { diff --git a/include/uapi/sound/sof/abi.h b/include/uapi/sound/sof/abi.h index fe2cfae94b45..f4232d289a22 100644 --- a/include/uapi/sound/sof/abi.h +++ b/include/uapi/sound/sof/abi.h @@ -26,7 +26,7 @@ /* SOF ABI version major, minor and patch numbers */ #define SOF_ABI_MAJOR 3 -#define SOF_ABI_MINOR 18 +#define SOF_ABI_MINOR 19 #define SOF_ABI_PATCH 0 /* SOF ABI version number. Format within 32bit word is MMmmmppp */ -- cgit v1.2.3 From 85f856f790b5fd427cb31b3f62755713174da0aa Mon Sep 17 00:00:00 2001 From: Ariel D'Alessandro Date: Mon, 17 Jan 2022 10:21:05 -0300 Subject: ASoC: Rename tlv320aic31xx-micbias.h as tlv320aic31xx.h Let's use a more generic name, so other definitions for tlv320aic31xx can be included. Signed-off-by: Ariel D'Alessandro Acked-by: Rob Herring Link: https://lore.kernel.org/r/20220117132109.283365-2-ariel.dalessandro@collabora.com Signed-off-by: Mark Brown --- include/dt-bindings/sound/tlv320aic31xx-micbias.h | 9 --------- include/dt-bindings/sound/tlv320aic31xx.h | 9 +++++++++ 2 files changed, 9 insertions(+), 9 deletions(-) delete mode 100644 include/dt-bindings/sound/tlv320aic31xx-micbias.h create mode 100644 include/dt-bindings/sound/tlv320aic31xx.h (limited to 'include') diff --git a/include/dt-bindings/sound/tlv320aic31xx-micbias.h b/include/dt-bindings/sound/tlv320aic31xx-micbias.h deleted file mode 100644 index c6895a18a455..000000000000 --- a/include/dt-bindings/sound/tlv320aic31xx-micbias.h +++ /dev/null @@ -1,9 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __DT_TLV320AIC31XX_MICBIAS_H -#define __DT_TLV320AIC31XX_MICBIAS_H - -#define MICBIAS_2_0V 1 -#define MICBIAS_2_5V 2 -#define MICBIAS_AVDDV 3 - -#endif /* __DT_TLV320AIC31XX_MICBIAS_H */ diff --git a/include/dt-bindings/sound/tlv320aic31xx.h b/include/dt-bindings/sound/tlv320aic31xx.h new file mode 100644 index 000000000000..3a845fbba992 --- /dev/null +++ b/include/dt-bindings/sound/tlv320aic31xx.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __DT_TLV320AIC31XX_H +#define __DT_TLV320AIC31XX_H + +#define MICBIAS_2_0V 1 +#define MICBIAS_2_5V 2 +#define MICBIAS_AVDDV 3 + +#endif /* __DT_TLV320AIC31XX_H */ -- cgit v1.2.3 From 6045ffd366283236f0de79c8a0e98ae766e9a8f9 Mon Sep 17 00:00:00 2001 From: Ariel D'Alessandro Date: Mon, 17 Jan 2022 10:21:06 -0300 Subject: ASoC: tlv320aic31xx: Define PLL clock inputs Add constants for the different PLL clock inputs in tlv320aic31xx. Signed-off-by: Ariel D'Alessandro Link: https://lore.kernel.org/r/20220117132109.283365-3-ariel.dalessandro@collabora.com Signed-off-by: Mark Brown --- include/dt-bindings/sound/tlv320aic31xx.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/sound/tlv320aic31xx.h b/include/dt-bindings/sound/tlv320aic31xx.h index 3a845fbba992..4a80238ab250 100644 --- a/include/dt-bindings/sound/tlv320aic31xx.h +++ b/include/dt-bindings/sound/tlv320aic31xx.h @@ -6,4 +6,9 @@ #define MICBIAS_2_5V 2 #define MICBIAS_AVDDV 3 +#define PLL_CLKIN_MCLK 0x00 +#define PLL_CLKIN_BCLK 0x01 +#define PLL_CLKIN_GPIO1 0x02 +#define PLL_CLKIN_DIN 0x03 + #endif /* __DT_TLV320AIC31XX_H */ -- cgit v1.2.3 From f1ba938e4f98941dc2b77795062e49444ec1fee1 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 19 Jan 2022 00:09:13 +0100 Subject: spi: s3c64xx: Delete unused boardfile helpers The helpers to use SPI host 1 and 2 are unused in the kernel and taking up space and maintenance hours. New systems should use device tree and not this, so delete the code. Cc: linux-samsung-soc@vger.kernel.org Cc: Krzysztof Kozlowski Cc: Sylwester Nawrocki Signed-off-by: Linus Walleij Reviewed-by: Sam Protsenko Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220118230915.157797-1-linus.walleij@linaro.org Signed-off-by: Mark Brown --- include/linux/platform_data/spi-s3c64xx.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/spi-s3c64xx.h b/include/linux/platform_data/spi-s3c64xx.h index 773daf7915a3..19d690f34670 100644 --- a/include/linux/platform_data/spi-s3c64xx.h +++ b/include/linux/platform_data/spi-s3c64xx.h @@ -52,17 +52,9 @@ struct s3c64xx_spi_info { */ extern void s3c64xx_spi0_set_platdata(int (*cfg_gpio)(void), int src_clk_nr, int num_cs); -extern void s3c64xx_spi1_set_platdata(int (*cfg_gpio)(void), int src_clk_nr, - int num_cs); -extern void s3c64xx_spi2_set_platdata(int (*cfg_gpio)(void), int src_clk_nr, - int num_cs); /* defined by architecture to configure gpio */ extern int s3c64xx_spi0_cfg_gpio(void); -extern int s3c64xx_spi1_cfg_gpio(void); -extern int s3c64xx_spi2_cfg_gpio(void); extern struct s3c64xx_spi_info s3c64xx_spi0_pdata; -extern struct s3c64xx_spi_info s3c64xx_spi1_pdata; -extern struct s3c64xx_spi_info s3c64xx_spi2_pdata; #endif /*__SPI_S3C64XX_H */ -- cgit v1.2.3 From 3b5529ae7f3578da633e8ae2ec0715a55a248f9f Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 19 Jan 2022 00:09:14 +0100 Subject: spi: s3c64xx: Drop custom gpio setup argument The SPI0 platform population function was taking a custom gpio setup callback but the only user pass NULL as argument so drop this argument. Cc: linux-samsung-soc@vger.kernel.org Cc: Krzysztof Kozlowski Cc: Sylwester Nawrocki Signed-off-by: Linus Walleij Reviewed-by: Krzysztof Kozlowski Reviewed-by: Sam Protsenko Link: https://lore.kernel.org/r/20220118230915.157797-2-linus.walleij@linaro.org Signed-off-by: Mark Brown --- include/linux/platform_data/spi-s3c64xx.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/spi-s3c64xx.h b/include/linux/platform_data/spi-s3c64xx.h index 19d690f34670..10890a4b55b9 100644 --- a/include/linux/platform_data/spi-s3c64xx.h +++ b/include/linux/platform_data/spi-s3c64xx.h @@ -43,15 +43,13 @@ struct s3c64xx_spi_info { /** * s3c64xx_spi_set_platdata - SPI Controller configure callback by the board * initialization code. - * @cfg_gpio: Pointer to gpio setup function. * @src_clk_nr: Clock the SPI controller is to use to generate SPI clocks. * @num_cs: Number of elements in the 'cs' array. * * Call this from machine init code for each SPI Controller that * has some chips attached to it. */ -extern void s3c64xx_spi0_set_platdata(int (*cfg_gpio)(void), int src_clk_nr, - int num_cs); +extern void s3c64xx_spi0_set_platdata(int src_clk_nr, int num_cs); /* defined by architecture to configure gpio */ extern int s3c64xx_spi0_cfg_gpio(void); -- cgit v1.2.3 From a45cf3cc72dd9cfde9db8af32cdf9c431f53f9bc Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 19 Jan 2022 00:09:15 +0100 Subject: spi: s3c64xx: Convert to use GPIO descriptors Convert the S3C64xx SPI host to use GPIO descriptors. Provide GPIO descriptor tables for the one user with CS 0 and 1. Cc: linux-samsung-soc@vger.kernel.org Cc: Sylwester Nawrocki Reviewed-by: Krzysztof Kozlowski Reviewed-by: Sam Protsenko Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20220118230915.157797-3-linus.walleij@linaro.org Signed-off-by: Mark Brown --- include/linux/platform_data/spi-s3c64xx.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/spi-s3c64xx.h b/include/linux/platform_data/spi-s3c64xx.h index 10890a4b55b9..5df1ace6d2c9 100644 --- a/include/linux/platform_data/spi-s3c64xx.h +++ b/include/linux/platform_data/spi-s3c64xx.h @@ -16,7 +16,6 @@ struct platform_device; * struct s3c64xx_spi_csinfo - ChipSelect description * @fb_delay: Slave specific feedback delay. * Refer to FB_CLK_SEL register definition in SPI chapter. - * @line: Custom 'identity' of the CS line. * * This is per SPI-Slave Chipselect information. * Allocate and initialize one in machine init code and make the @@ -24,7 +23,6 @@ struct platform_device; */ struct s3c64xx_spi_csinfo { u8 fb_delay; - unsigned line; }; /** -- cgit v1.2.3 From 7f2a3cf4e6077a1525092f114be7819e505773a1 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 19 Jan 2022 01:09:14 +0100 Subject: spi: s3c24xx: Convert to GPIO descriptors This driver has a bunch of custom oldstyle GPIO number-passing fields and a custom set-up callback. The good thing is: nothing in the kernel is using it. Convert the driver to use GPIO descriptors with a SPI_MASTER_GPIO_SS flag so that the local CS callback also get invoked as the hardware needs this. New users of this driver can provide GPIO descriptor tables like the other converted drivers. Cc: linux-samsung-soc@vger.kernel.org Cc: Krzysztof Kozlowski Cc: Sylwester Nawrocki Signed-off-by: Linus Walleij Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220119000914.192553-1-linus.walleij@linaro.org Signed-off-by: Mark Brown --- include/linux/spi/s3c24xx.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/spi/s3c24xx.h b/include/linux/spi/s3c24xx.h index 440a71593162..9b8bb22d5b0c 100644 --- a/include/linux/spi/s3c24xx.h +++ b/include/linux/spi/s3c24xx.h @@ -10,14 +10,9 @@ #define __LINUX_SPI_S3C24XX_H __FILE__ struct s3c2410_spi_info { - int pin_cs; /* simple gpio cs */ unsigned int num_cs; /* total chipselects */ int bus_num; /* bus number to use. */ - unsigned int use_fiq:1; /* use fiq */ - - void (*gpio_setup)(struct s3c2410_spi_info *spi, int enable); - void (*set_cs)(struct s3c2410_spi_info *spi, int cs, int pol); }; extern int s3c24xx_set_fiq(unsigned int irq, u32 *ack_ptr, bool on); -- cgit v1.2.3 From 5ca2ab4598179a2690a38420f3fde9f2ad79d55c Mon Sep 17 00:00:00 2001 From: Robert Hancock Date: Thu, 20 Jan 2022 13:58:32 -0600 Subject: ASoC: simple-card-utils: Add new system-clock-fixed flag Add a new system-clock-fixed flag, which can be used to specify that the driver cannot or should not allow the clock frequency of the mapped clock to be modified. This behavior is also implied if the system-clock-frequency parameter is set explicitly - the flag is meant for cases where a clock is mapped to the DAI but which is, or should be treated as, fixed. When mclk-fs is also specified, this causes a PCM constraint to be added which enforces that only the corresponding valid sample rate can be used. Signed-off-by: Robert Hancock Link: https://lore.kernel.org/r/20220120195832.1742271-7-robert.hancock@calian.com Signed-off-by: Mark Brown --- include/sound/simple_card_utils.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h index df430f1c2a10..5ee269c59aac 100644 --- a/include/sound/simple_card_utils.h +++ b/include/sound/simple_card_utils.h @@ -25,6 +25,7 @@ struct asoc_simple_dai { unsigned int tx_slot_mask; unsigned int rx_slot_mask; struct clk *clk; + bool clk_fixed; }; struct asoc_simple_data { -- cgit v1.2.3 From 2145bb687e3fdb128066872fd952f4563d89177e Mon Sep 17 00:00:00 2001 From: Daire McNamara Date: Thu, 16 Dec 2021 14:00:21 +0000 Subject: dt-bindings: clk: microchip: Add Microchip PolarFire host binding Add device tree bindings for the Microchip PolarFire system clock controller Signed-off-by: Daire McNamara Signed-off-by: Conor Dooley Reviewed-by: Geert Uytterhoeven Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20211216140022.16146-2-conor.dooley@microchip.com Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/microchip,mpfs-clock.h | 45 ++++++++++++++++++++++++ 1 file changed, 45 insertions(+) create mode 100644 include/dt-bindings/clock/microchip,mpfs-clock.h (limited to 'include') diff --git a/include/dt-bindings/clock/microchip,mpfs-clock.h b/include/dt-bindings/clock/microchip,mpfs-clock.h new file mode 100644 index 000000000000..73f2a9324857 --- /dev/null +++ b/include/dt-bindings/clock/microchip,mpfs-clock.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Daire McNamara, + * Copyright (C) 2020 Microchip Technology Inc. All rights reserved. + */ + +#ifndef _DT_BINDINGS_CLK_MICROCHIP_MPFS_H_ +#define _DT_BINDINGS_CLK_MICROCHIP_MPFS_H_ + +#define CLK_CPU 0 +#define CLK_AXI 1 +#define CLK_AHB 2 + +#define CLK_ENVM 3 +#define CLK_MAC0 4 +#define CLK_MAC1 5 +#define CLK_MMC 6 +#define CLK_TIMER 7 +#define CLK_MMUART0 8 +#define CLK_MMUART1 9 +#define CLK_MMUART2 10 +#define CLK_MMUART3 11 +#define CLK_MMUART4 12 +#define CLK_SPI0 13 +#define CLK_SPI1 14 +#define CLK_I2C0 15 +#define CLK_I2C1 16 +#define CLK_CAN0 17 +#define CLK_CAN1 18 +#define CLK_USB 19 +#define CLK_RESERVED 20 +#define CLK_RTC 21 +#define CLK_QSPI 22 +#define CLK_GPIO0 23 +#define CLK_GPIO1 24 +#define CLK_GPIO2 25 +#define CLK_DDRC 26 +#define CLK_FIC0 27 +#define CLK_FIC1 28 +#define CLK_FIC2 29 +#define CLK_FIC3 30 +#define CLK_ATHENA 31 +#define CLK_CFM 32 + +#endif /* _DT_BINDINGS_CLK_MICROCHIP_MPFS_H_ */ -- cgit v1.2.3 From ea2be22f3d37b1e77fbfe46cd6536eab667107ec Mon Sep 17 00:00:00 2001 From: Zixun LI Date: Tue, 11 Jan 2022 14:20:50 +0000 Subject: clk: at91: allow setting PMC_AUDIOPINCK clock parents via DT Make AUDIOPINCK accessible via phandle to select it as peripheral clock parent using assigned-clock-parents in DT where available. Signed-off-by: Zixun LI Reviewed-by: Claudiu Beznea Link: https://lore.kernel.org/r/20220111142051.37957-1-admin@hifiphile.com Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/at91.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/clock/at91.h b/include/dt-bindings/clock/at91.h index 98e1b2ab6403..573cf8c25eb4 100644 --- a/include/dt-bindings/clock/at91.h +++ b/include/dt-bindings/clock/at91.h @@ -24,6 +24,7 @@ #define PMC_PLLACK 7 #define PMC_PLLBCK 8 #define PMC_AUDIOPLLCK 9 +#define PMC_AUDIOPINCK 10 /* SAMA7G5 */ #define PMC_CPUPLL (PMC_MAIN + 1) -- cgit v1.2.3 From a5ab04af49434aef532bf6cd4baa08a13665d608 Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Tue, 11 Jan 2022 14:53:10 +0200 Subject: clk: at91: sama7g5: Allow MCK1 to be exported and referenced in DT MCK1 feeds the External Bus Interface (EBI). EBI's clock rate is used to translate EBI's timmings to SMC timings, thus we need to handle MCK1 in the EBI driver. Allow MCK1 to be referenced as a PMC_TYPE_CORE clock from phandle in DT. Signed-off-by: Tudor Ambarus Link: https://lore.kernel.org/r/20220111125310.902856-1-tudor.ambarus@microchip.com Reviewed-by: Claudiu Beznea Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/at91.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/clock/at91.h b/include/dt-bindings/clock/at91.h index 573cf8c25eb4..3e3972a814c1 100644 --- a/include/dt-bindings/clock/at91.h +++ b/include/dt-bindings/clock/at91.h @@ -36,6 +36,7 @@ #define PMC_AUDIOIOPLL (PMC_MAIN + 7) #define PMC_ETHPLL (PMC_MAIN + 8) #define PMC_CPU (PMC_MAIN + 9) +#define PMC_MCK1 (PMC_MAIN + 10) #ifndef AT91_PMC_MOSCS #define AT91_PMC_MOSCS 0 /* MOSCS Flag */ -- cgit v1.2.3 From d5ebaa7c5f6f688959e8d40840b2249ede63b8ed Mon Sep 17 00:00:00 2001 From: Soenke Huster Date: Sun, 23 Jan 2022 15:06:24 +0100 Subject: Bluetooth: hci_event: Ignore multiple conn complete events When one of the three connection complete events is received multiple times for the same handle, the device is registered multiple times which leads to memory corruptions. Therefore, consequent events for a single connection are ignored. The conn->state can hold different values, therefore HCI_CONN_HANDLE_UNSET is introduced to identify new connections. To make sure the events do not contain this or another invalid handle HCI_CONN_HANDLE_MAX and checks are introduced. Buglink: https://bugzilla.kernel.org/show_bug.cgi?id=215497 Signed-off-by: Soenke Huster Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 21eadb113a31..f5caff1ddb29 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -303,6 +303,9 @@ struct adv_monitor { #define HCI_MAX_SHORT_NAME_LENGTH 10 +#define HCI_CONN_HANDLE_UNSET 0xffff +#define HCI_CONN_HANDLE_MAX 0x0eff + /* Min encryption key size to match with SMP */ #define HCI_MIN_ENC_KEY_SIZE 7 -- cgit v1.2.3 From 376040e47334c6dc6a939a32197acceb00fe4acf Mon Sep 17 00:00:00 2001 From: Kenny Yu Date: Mon, 24 Jan 2022 10:54:01 -0800 Subject: bpf: Add bpf_copy_from_user_task() helper This adds a helper for bpf programs to read the memory of other tasks. As an example use case at Meta, we are using a bpf task iterator program and this new helper to print C++ async stack traces for all threads of a given process. Signed-off-by: Kenny Yu Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20220124185403.468466-3-kennyyu@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 11 +++++++++++ 2 files changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8c92c974bd12..394305a5e02f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2243,6 +2243,7 @@ extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto; extern const struct bpf_func_proto bpf_find_vma_proto; extern const struct bpf_func_proto bpf_loop_proto; extern const struct bpf_func_proto bpf_strncmp_proto; +extern const struct bpf_func_proto bpf_copy_from_user_task_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 16a7574292a5..4a2f7041ebae 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5076,6 +5076,16 @@ union bpf_attr { * associated to *xdp_md*, at *offset*. * Return * 0 on success, or a negative error in case of failure. + * + * long bpf_copy_from_user_task(void *dst, u32 size, const void *user_ptr, struct task_struct *tsk, u64 flags) + * Description + * Read *size* bytes from user space address *user_ptr* in *tsk*'s + * address space, and stores the data in *dst*. *flags* is not + * used yet and is provided for future extensibility. This helper + * can only be used by sleepable programs. + * Return + * 0 on success, or a negative error in case of failure. On error + * *dst* buffer is zeroed out. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5269,6 +5279,7 @@ union bpf_attr { FN(xdp_get_buff_len), \ FN(xdp_load_bytes), \ FN(xdp_store_bytes), \ + FN(copy_from_user_task), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 4fd5e720b709b87f67809a871fde9fb6cb910f28 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 24 Jan 2022 23:16:33 +0100 Subject: drm/docs: Document where the C8 color lut is stored MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Also add notes that for atomic drivers it's really somewhere else and no longer in struct drm_crtc. Maybe we should put a bigger warning here that this is confusing, since the pixel format is a plane property, but the GAMMA_LUT property is on the crtc. But I think we can fix this if/when someone finds a need for a per-plane CLUT, since I'm not sure such hw even exists. I'm also not sure whether even hardware with a CLUT and a full color correction pipeline with degamm/cgm/gamma exists. Motivated by comments from Geert that we have a gap here. v2: More names for color luts (Laurent). Reviewed-by: Alex Deucher Cc: Laurent Pinchart Reviewed-by: Laurent Pinchart Cc: Geert Uytterhoeven Cc: Ville Syrjälä Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Thomas Zimmermann Cc: David Airlie Cc: Daniel Vetter Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220124221633.952374-1-daniel.vetter@ffwll.ch --- include/drm/drm_crtc.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h index 13eeba2a750a..f9f9af8b5448 100644 --- a/include/drm/drm_crtc.h +++ b/include/drm/drm_crtc.h @@ -285,6 +285,10 @@ struct drm_crtc_state { * Lookup table for converting pixel data after the color conversion * matrix @ctm. See drm_crtc_enable_color_mgmt(). The blob (if not * NULL) is an array of &struct drm_color_lut. + * + * Note that for mostly historical reasons stemming from Xorg heritage, + * this is also used to store the color map (also sometimes color lut, + * CLUT or color palette) for indexed formats like DRM_FORMAT_C8. */ struct drm_property_blob *gamma_lut; @@ -1075,12 +1079,18 @@ struct drm_crtc { /** * @gamma_size: Size of legacy gamma ramp reported to userspace. Set up * by calling drm_mode_crtc_set_gamma_size(). + * + * Note that atomic drivers need to instead use + * &drm_crtc_state.gamma_lut. See drm_crtc_enable_color_mgmt(). */ uint32_t gamma_size; /** * @gamma_store: Gamma ramp values used by the legacy SETGAMMA and * GETGAMMA IOCTls. Set up by calling drm_mode_crtc_set_gamma_size(). + * + * Note that atomic drivers need to instead use + * &drm_crtc_state.gamma_lut. See drm_crtc_enable_color_mgmt(). */ uint16_t *gamma_store; -- cgit v1.2.3 From 4a46e5d251a39e7c10493743ac89a31f6f3ce5b5 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Thu, 20 Jan 2022 16:16:10 +0100 Subject: drm/edid: Rename drm_hdmi_avi_infoframe_colorspace to _colorimetry MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The drm_hdmi_avi_infoframe_colorspace() function actually sets the colorimetry and extended_colorimetry fields in the hdmi_avi_infoframe structure with DRM_MODE_COLORIMETRY_* values. To make things worse, the hdmi_avi_infoframe structure also has a colorspace field used to signal whether an RGB or YUV output is being used. Let's remove the inconsistency and allow for the colorspace usage by renaming the function. Reviewed-by: Ville Syrjälä Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20220120151625.594595-2-maxime@cerno.tech --- include/drm/drm_edid.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h index 18f6c700f6d0..144c495b99c4 100644 --- a/include/drm/drm_edid.h +++ b/include/drm/drm_edid.h @@ -401,8 +401,8 @@ drm_hdmi_vendor_infoframe_from_display_mode(struct hdmi_vendor_infoframe *frame, const struct drm_display_mode *mode); void -drm_hdmi_avi_infoframe_colorspace(struct hdmi_avi_infoframe *frame, - const struct drm_connector_state *conn_state); +drm_hdmi_avi_infoframe_colorimetry(struct hdmi_avi_infoframe *frame, + const struct drm_connector_state *conn_state); void drm_hdmi_avi_infoframe_bars(struct hdmi_avi_infoframe *frame, -- cgit v1.2.3 From 4adc33f36d80489339f1b43dfeee96bb9ea8e459 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Thu, 20 Jan 2022 16:16:12 +0100 Subject: drm/edid: Split deep color modes between RGB and YUV444 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The current code assumes that the RGB444 and YUV444 formats are the same, but the HDMI 2.0 specification states that: The three DC_XXbit bits above only indicate support for RGB 4:4:4 at that pixel size. Support for YCBCR 4:4:4 in Deep Color modes is indicated with the DC_Y444 bit. If DC_Y444 is set, then YCBCR 4:4:4 is supported for all modes indicated by the DC_XXbit flags. So if we have YUV444 support and any DC_XXbit flag set but the DC_Y444 flag isn't, we'll assume that we support that deep colour mode for YUV444 which breaks the specification. In order to fix this, let's split the edid_hdmi_dc_modes field in struct drm_display_info into two fields, one for RGB444 and one for YUV444. Suggested-by: Ville Syrjälä Fixes: d0c94692e0a3 ("drm/edid: Parse and handle HDMI deep color modes.") Signed-off-by: Maxime Ripard Reviewed-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20220120151625.594595-4-maxime@cerno.tech --- include/drm/drm_connector.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index b501d0badaea..eaf0ef5f1843 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -592,10 +592,16 @@ struct drm_display_info { bool rgb_quant_range_selectable; /** - * @edid_hdmi_dc_modes: Mask of supported hdmi deep color modes. Even - * more stuff redundant with @bus_formats. + * @edid_hdmi_dc_rgb444_modes: Mask of supported hdmi deep color modes + * in RGB 4:4:4. Even more stuff redundant with @bus_formats. */ - u8 edid_hdmi_dc_modes; + u8 edid_hdmi_rgb444_dc_modes; + + /** + * @edid_hdmi_dc_ycbcr444_modes: Mask of supported hdmi deep color + * modes in YCbCr 4:4:4. Even more stuff redundant with @bus_formats. + */ + u8 edid_hdmi_ycbcr444_dc_modes; /** * @cea_rev: CEA revision of the HDMI sink. -- cgit v1.2.3 From c03d0b52ff71d580ee235463c7ca9eac31351dcd Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Thu, 20 Jan 2022 16:16:13 +0100 Subject: drm/connector: Fix typo in output format MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The HDMI specification mentions YCbCr everywhere, but our enums have YCrCb. Let's rename it to match. Signed-off-by: Maxime Ripard Reviewed-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20220120151625.594595-5-maxime@cerno.tech --- include/drm/drm_connector.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index eaf0ef5f1843..64cf5f88c05b 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -522,9 +522,9 @@ struct drm_display_info { enum subpixel_order subpixel_order; #define DRM_COLOR_FORMAT_RGB444 (1<<0) -#define DRM_COLOR_FORMAT_YCRCB444 (1<<1) -#define DRM_COLOR_FORMAT_YCRCB422 (1<<2) -#define DRM_COLOR_FORMAT_YCRCB420 (1<<3) +#define DRM_COLOR_FORMAT_YCBCR444 (1<<1) +#define DRM_COLOR_FORMAT_YCBCR422 (1<<2) +#define DRM_COLOR_FORMAT_YCBCR420 (1<<3) /** * @panel_orientation: Read only connector property for built-in panels, -- cgit v1.2.3 From d507204d3c5cc57d9a8bdf0a477615bb59ea1611 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 24 Jan 2022 12:24:52 -0800 Subject: tcp/dccp: add tw->tw_bslot We want to allow inet_twsk_kill() working even if netns has been dismantled/freed, to get rid of inet_twsk_purge(). This patch adds tw->tw_bslot to cache the bind bucket slot so that inet_twsk_kill() no longer needs to dereference twsk_net(tw) Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_timewait_sock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index dfd919b3119e..c221fe2b77dd 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -72,6 +72,7 @@ struct inet_timewait_sock { tw_tos : 8; u32 tw_txhash; u32 tw_priority; + u32 tw_bslot; /* bind bucket slot */ struct timer_list tw_timer; struct inet_bind_bucket *tw_tb; }; -- cgit v1.2.3 From 27dd35e02235902933626469a1c9198612d72564 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 24 Jan 2022 12:24:53 -0800 Subject: tcp/dccp: no longer use twsk_net(tw) from tw_timer_handler() We will soon get rid of inet_twsk_purge(). This means that tw_timer_handler() might fire after a netns has been dismantled/freed. Instead of adding a function (and data structure) to find a netns from tw->tw_net_cookie, just update the SNMP counters a bit earlier, when the netns is known to be alive. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_timewait_sock.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index c221fe2b77dd..b323db969b8b 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -65,10 +65,9 @@ struct inet_timewait_sock { /* these three are in inet_sock */ __be16 tw_sport; /* And these are ours. */ - unsigned int tw_kill : 1, - tw_transparent : 1, + unsigned int tw_transparent : 1, tw_flowlabel : 20, - tw_pad : 2, /* 2 bits hole */ + tw_pad : 3, /* 3 bits hole */ tw_tos : 8; u32 tw_txhash; u32 tw_priority; -- cgit v1.2.3 From 0dad4087a86a2cbe177404dc73f18ada26a2c390 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 24 Jan 2022 12:24:54 -0800 Subject: tcp/dccp: get rid of inet_twsk_purge() Prior patches in the series made sure tw_timer_handler() can be fired after netns has been dismantled/freed. We no longer have to scan a potentially big TCP ehash table at netns dismantle. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_timewait_sock.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index b323db969b8b..463ae5d33eb0 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -110,8 +110,6 @@ static inline void inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo void inet_twsk_deschedule_put(struct inet_timewait_sock *tw); -void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family); - static inline struct net *twsk_net(const struct inet_timewait_sock *twsk) { -- cgit v1.2.3 From a15c89c703d43490ea68ea4516553d4ea4f6b1e1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 24 Jan 2022 12:24:55 -0800 Subject: ipv4: do not use per netns icmp sockets Back in linux-2.6.25 (commit 4a6ad7a141cb "[NETNS]: Make icmp_sk per namespace."), we added private per-cpu/per-netns ipv4 icmp sockets. This adds memory and cpu costs, which do not seem needed. Now typical servers have 256 or more cores, this adds considerable tax to netns users. icmp sockets are used from BH context, are not receiving packets, and do not store any persistent state but the 'struct net' pointer. icmp_xmit_lock() already makes sure to lock the chosen per-cpu socket. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 78557643526e..639a31638159 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -70,7 +70,6 @@ struct netns_ipv4 { struct hlist_head *fib_table_hash; struct sock *fibnl; - struct sock * __percpu *icmp_sk; struct sock *mc_autojoin_sk; struct inet_peer_base *peers; -- cgit v1.2.3 From 6a17b961ec19cd61ca646a6655ab93e8f6fe15c0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 24 Jan 2022 12:24:56 -0800 Subject: ipv6: do not use per netns icmp sockets Back in linux-2.6.25 (commit 98c6d1b261e7 "[NETNS]: Make icmpv6_sk per namespace.", we added private per-cpu/per-netns ipv6 icmp sockets. This adds memory and cpu costs, which do not seem needed. Now typical servers have 256 or more cores, this adds considerable tax to netns users. icmp sockets are used from BH context, are not receiving packets, and do not store any persistent state but the 'struct net' pointer. icmpv6_xmit_lock() already makes sure to lock the chosen per-cpu socket. This patch has a considerable impact on the number of netns that the worker thread in cleanup_net() can dismantle per second, because ip6mr_sk_done() is no longer called, meaning we no longer acquire the rtnl mutex, competing with other threads adding new netns. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/netns/ipv6.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index a4b550380316..30cdfc4e1615 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -88,7 +88,6 @@ struct netns_ipv6 { struct fib6_table *fib6_local_tbl; struct fib_rules_ops *fib6_rules_ops; #endif - struct sock * __percpu *icmp_sk; struct sock *ndisc_sk; struct sock *tcp_sk; struct sock *igmp_sk; -- cgit v1.2.3 From 37ba017dcc3b1123206808979834655ddcf93251 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 24 Jan 2022 12:24:57 -0800 Subject: ipv4/tcp: do not use per netns ctl sockets TCP ipv4 uses per-cpu/per-netns ctl sockets in order to send RST and some ACK packets (on behalf of TIMEWAIT sockets). This adds memory and cpu costs, which do not seem needed. Now typical servers have 256 or more cores, this adds considerable tax to netns users. tcp sockets are used from BH context, are not receiving packets, and do not store any persistent state but the 'struct net' pointer in order to be able to use IPv4 output functions. Note that I attempted a related change in the past, that had to be hot-fixed in commit bdbbb8527b6f ("ipv4: tcp: get rid of ugly unicast_sock") This patch could very well surface old bugs, on layers not taking care of sk->sk_kern_sock properly. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 639a31638159..22b4c6df1d2b 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -73,7 +73,6 @@ struct netns_ipv4 { struct sock *mc_autojoin_sk; struct inet_peer_base *peers; - struct sock * __percpu *tcp_sk; struct fqdir *fqdir; u8 sysctl_icmp_echo_ignore_all; -- cgit v1.2.3 From ae57857b9b6341096ddfd9c0cf26fb640c561160 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 11 Jan 2022 16:55:25 +0100 Subject: ACPICA: Use uintptr_t and offsetof() in Linux kernel builds To avoid "performing pointer subtraction with a null pointer has undefined behavior" compiler warnings, use uintptr_t and offsetof() that are always available during Linux kernel builds to define acpi_uintptr_t and the ACPI_TO_INTEGER() and ACPI_OFFSET() macros. Based on earlier proposal from Arnd Bergmann. Link: https://lore.kernel.org/linux-acpi/20210927121338.938994-1-arnd@kernel.org Signed-off-by: Rafael J. Wysocki Reviewed-by: Arnd Bergmann --- include/acpi/actypes.h | 4 ++++ include/acpi/platform/aclinux.h | 5 +++++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index 69e89d572b9e..02c1fa16e638 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -507,8 +507,12 @@ typedef u64 acpi_integer; /* Pointer/Integer type conversions */ #define ACPI_TO_POINTER(i) ACPI_CAST_PTR (void, (acpi_size) (i)) +#ifndef ACPI_TO_INTEGER #define ACPI_TO_INTEGER(p) ACPI_PTR_DIFF (p, (void *) 0) +#endif +#ifndef ACPI_OFFSET #define ACPI_OFFSET(d, f) ACPI_PTR_DIFF (&(((d *) 0)->f), (void *) 0) +#endif #define ACPI_PTR_TO_PHYSADDR(i) ACPI_TO_INTEGER(i) /* Optimizations for 4-character (32-bit) acpi_name manipulation */ diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h index b3ffb9bbf664..cec41e004ecf 100644 --- a/include/acpi/platform/aclinux.h +++ b/include/acpi/platform/aclinux.h @@ -114,6 +114,11 @@ #define acpi_raw_spinlock raw_spinlock_t * #define acpi_cpu_flags unsigned long +#define acpi_uintptr_t uintptr_t + +#define ACPI_TO_INTEGER(p) ((uintptr_t)(p)) +#define ACPI_OFFSET(d, f) offsetof(d, f) + /* Use native linux version of acpi_os_allocate_zeroed */ #define USE_NATIVE_ALLOCATE_ZEROED -- cgit v1.2.3 From 4fdacef8ac5a5382eeb1bc6fc2632d71a09d52cd Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Thu, 13 Jan 2022 08:59:27 -0800 Subject: kunit: move check if assertion passed into the macros Currently the code always calls kunit_do_assertion() even though it does nothing when `pass` is true. This change moves the `if(!(pass))` check into the macro instead and renames the function to kunit_do_failed_assertion(). I feel this a bit easier to read and understand. This has the potential upside of avoiding a function call that does nothing most of the time (assuming your tests are passing) but comes with the downside of generating a bit more code and branches. We try to mitigate the branches by tagging them with `unlikely()`. This also means we don't have to initialize structs that we don't need, which will become a tiny bit more expensive if we switch over to using static variables to try and reduce stack usage. (There's runtime code to check if the variable has been initialized yet or not). Signed-off-by: Daniel Latypov Reviewed-by: Brendan Higgins Reviewed-by: David Gow Signed-off-by: Shuah Khan --- include/kunit/test.h | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index b26400731c02..12cabd15449a 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -12,6 +12,7 @@ #include #include +#include #include #include #include @@ -770,18 +771,18 @@ void __printf(2, 3) kunit_log_append(char *log, const char *fmt, ...); */ #define KUNIT_SUCCEED(test) do {} while (0) -void kunit_do_assertion(struct kunit *test, - struct kunit_assert *assert, - bool pass, - const char *fmt, ...); +void kunit_do_failed_assertion(struct kunit *test, + struct kunit_assert *assert, + const char *fmt, ...); #define KUNIT_ASSERTION(test, pass, assert_class, INITIALIZER, fmt, ...) do { \ - struct assert_class __assertion = INITIALIZER; \ - kunit_do_assertion(test, \ - &__assertion.assert, \ - pass, \ - fmt, \ - ##__VA_ARGS__); \ + if (unlikely(!(pass))) { \ + struct assert_class __assertion = INITIALIZER; \ + kunit_do_failed_assertion(test, \ + &__assertion.assert, \ + fmt, \ + ##__VA_ARGS__); \ + } \ } while (0) -- cgit v1.2.3 From a91e9ade402c48ee35cd1e4b671e3938db798d17 Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Thu, 13 Jan 2022 08:59:28 -0800 Subject: kunit: drop unused kunit* field in kunit_assert The `struct kunit* test` field in kunit_assert is unused. Note: string_stream needs it, but it has its own `test` field. I assume `test` in `kunit_assert` predates this and was leftover after some refactoring. This patch removes the field and cleans up the macros to avoid needlessly passing around `test`. Signed-off-by: Daniel Latypov Reviewed-by: Brendan Higgins Reviewed-by: David Gow Signed-off-by: Shuah Khan --- include/kunit/assert.h | 45 +++++++++++++-------------------------------- include/kunit/test.h | 14 +++++--------- 2 files changed, 18 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/include/kunit/assert.h b/include/kunit/assert.h index ccbc36c0b02f..f568166ef034 100644 --- a/include/kunit/assert.h +++ b/include/kunit/assert.h @@ -30,7 +30,6 @@ enum kunit_assert_type { /** * struct kunit_assert - Data for printing a failed assertion or expectation. - * @test: the test case this expectation/assertion is associated with. * @type: the type (either an expectation or an assertion) of this kunit_assert. * @line: the source code line number that the expectation/assertion is at. * @file: the file path of the source file that the expectation/assertion is in. @@ -41,7 +40,6 @@ enum kunit_assert_type { * format a string to a user reporting the failure. */ struct kunit_assert { - struct kunit *test; enum kunit_assert_type type; int line; const char *file; @@ -60,14 +58,12 @@ struct kunit_assert { /** * KUNIT_INIT_ASSERT_STRUCT() - Initializer for a &struct kunit_assert. - * @kunit: The test case that this expectation/assertion is associated with. * @assert_type: The type (assertion or expectation) of this kunit_assert. * @fmt: The formatting function which builds a string out of this kunit_assert. * * The base initializer for a &struct kunit_assert. */ -#define KUNIT_INIT_ASSERT_STRUCT(kunit, assert_type, fmt) { \ - .test = kunit, \ +#define KUNIT_INIT_ASSERT_STRUCT(assert_type, fmt) { \ .type = assert_type, \ .file = __FILE__, \ .line = __LINE__, \ @@ -96,15 +92,13 @@ void kunit_fail_assert_format(const struct kunit_assert *assert, /** * KUNIT_INIT_FAIL_ASSERT_STRUCT() - Initializer for &struct kunit_fail_assert. - * @test: The test case that this expectation/assertion is associated with. * @type: The type (assertion or expectation) of this kunit_assert. * * Initializes a &struct kunit_fail_assert. Intended to be used in * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. */ -#define KUNIT_INIT_FAIL_ASSERT_STRUCT(test, type) { \ - .assert = KUNIT_INIT_ASSERT_STRUCT(test, \ - type, \ +#define KUNIT_INIT_FAIL_ASSERT_STRUCT(type) { \ + .assert = KUNIT_INIT_ASSERT_STRUCT(type, \ kunit_fail_assert_format) \ } @@ -129,7 +123,6 @@ void kunit_unary_assert_format(const struct kunit_assert *assert, /** * KUNIT_INIT_UNARY_ASSERT_STRUCT() - Initializes &struct kunit_unary_assert. - * @test: The test case that this expectation/assertion is associated with. * @type: The type (assertion or expectation) of this kunit_assert. * @cond: A string representation of the expression asserted true or false. * @expect_true: True if of type KUNIT_{EXPECT|ASSERT}_TRUE, false otherwise. @@ -137,9 +130,8 @@ void kunit_unary_assert_format(const struct kunit_assert *assert, * Initializes a &struct kunit_unary_assert. Intended to be used in * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. */ -#define KUNIT_INIT_UNARY_ASSERT_STRUCT(test, type, cond, expect_true) { \ - .assert = KUNIT_INIT_ASSERT_STRUCT(test, \ - type, \ +#define KUNIT_INIT_UNARY_ASSERT_STRUCT(type, cond, expect_true) { \ + .assert = KUNIT_INIT_ASSERT_STRUCT(type, \ kunit_unary_assert_format), \ .condition = cond, \ .expected_true = expect_true \ @@ -167,7 +159,6 @@ void kunit_ptr_not_err_assert_format(const struct kunit_assert *assert, /** * KUNIT_INIT_PTR_NOT_ERR_ASSERT_STRUCT() - Initializes a * &struct kunit_ptr_not_err_assert. - * @test: The test case that this expectation/assertion is associated with. * @type: The type (assertion or expectation) of this kunit_assert. * @txt: A string representation of the expression passed to the expectation. * @val: The actual evaluated pointer value of the expression. @@ -175,9 +166,8 @@ void kunit_ptr_not_err_assert_format(const struct kunit_assert *assert, * Initializes a &struct kunit_ptr_not_err_assert. Intended to be used in * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. */ -#define KUNIT_INIT_PTR_NOT_ERR_STRUCT(test, type, txt, val) { \ - .assert = KUNIT_INIT_ASSERT_STRUCT(test, \ - type, \ +#define KUNIT_INIT_PTR_NOT_ERR_STRUCT(type, txt, val) { \ + .assert = KUNIT_INIT_ASSERT_STRUCT(type, \ kunit_ptr_not_err_assert_format), \ .text = txt, \ .value = val \ @@ -212,7 +202,6 @@ void kunit_binary_assert_format(const struct kunit_assert *assert, /** * KUNIT_INIT_BINARY_ASSERT_STRUCT() - Initializes a * &struct kunit_binary_assert. - * @test: The test case that this expectation/assertion is associated with. * @type: The type (assertion or expectation) of this kunit_assert. * @op_str: A string representation of the comparison operator (e.g. "=="). * @left_str: A string representation of the expression in the left slot. @@ -223,15 +212,13 @@ void kunit_binary_assert_format(const struct kunit_assert *assert, * Initializes a &struct kunit_binary_assert. Intended to be used in * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. */ -#define KUNIT_INIT_BINARY_ASSERT_STRUCT(test, \ - type, \ +#define KUNIT_INIT_BINARY_ASSERT_STRUCT(type, \ op_str, \ left_str, \ left_val, \ right_str, \ right_val) { \ - .assert = KUNIT_INIT_ASSERT_STRUCT(test, \ - type, \ + .assert = KUNIT_INIT_ASSERT_STRUCT(type, \ kunit_binary_assert_format), \ .operation = op_str, \ .left_text = left_str, \ @@ -269,7 +256,6 @@ void kunit_binary_ptr_assert_format(const struct kunit_assert *assert, /** * KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT() - Initializes a * &struct kunit_binary_ptr_assert. - * @test: The test case that this expectation/assertion is associated with. * @type: The type (assertion or expectation) of this kunit_assert. * @op_str: A string representation of the comparison operator (e.g. "=="). * @left_str: A string representation of the expression in the left slot. @@ -280,15 +266,13 @@ void kunit_binary_ptr_assert_format(const struct kunit_assert *assert, * Initializes a &struct kunit_binary_ptr_assert. Intended to be used in * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. */ -#define KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT(test, \ - type, \ +#define KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT(type, \ op_str, \ left_str, \ left_val, \ right_str, \ right_val) { \ - .assert = KUNIT_INIT_ASSERT_STRUCT(test, \ - type, \ + .assert = KUNIT_INIT_ASSERT_STRUCT(type, \ kunit_binary_ptr_assert_format), \ .operation = op_str, \ .left_text = left_str, \ @@ -326,7 +310,6 @@ void kunit_binary_str_assert_format(const struct kunit_assert *assert, /** * KUNIT_INIT_BINARY_STR_ASSERT_STRUCT() - Initializes a * &struct kunit_binary_str_assert. - * @test: The test case that this expectation/assertion is associated with. * @type: The type (assertion or expectation) of this kunit_assert. * @op_str: A string representation of the comparison operator (e.g. "=="). * @left_str: A string representation of the expression in the left slot. @@ -337,15 +320,13 @@ void kunit_binary_str_assert_format(const struct kunit_assert *assert, * Initializes a &struct kunit_binary_str_assert. Intended to be used in * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. */ -#define KUNIT_INIT_BINARY_STR_ASSERT_STRUCT(test, \ - type, \ +#define KUNIT_INIT_BINARY_STR_ASSERT_STRUCT(type, \ op_str, \ left_str, \ left_val, \ right_str, \ right_val) { \ - .assert = KUNIT_INIT_ASSERT_STRUCT(test, \ - type, \ + .assert = KUNIT_INIT_ASSERT_STRUCT(type, \ kunit_binary_str_assert_format), \ .operation = op_str, \ .left_text = left_str, \ diff --git a/include/kunit/test.h b/include/kunit/test.h index 12cabd15449a..25ea3bce6663 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -790,7 +790,7 @@ void kunit_do_failed_assertion(struct kunit *test, KUNIT_ASSERTION(test, \ false, \ kunit_fail_assert, \ - KUNIT_INIT_FAIL_ASSERT_STRUCT(test, assert_type), \ + KUNIT_INIT_FAIL_ASSERT_STRUCT(assert_type), \ fmt, \ ##__VA_ARGS__) @@ -820,8 +820,7 @@ void kunit_do_failed_assertion(struct kunit *test, KUNIT_ASSERTION(test, \ !!(condition) == !!expected_true, \ kunit_unary_assert, \ - KUNIT_INIT_UNARY_ASSERT_STRUCT(test, \ - assert_type, \ + KUNIT_INIT_UNARY_ASSERT_STRUCT(assert_type, \ #condition, \ expected_true), \ fmt, \ @@ -879,8 +878,7 @@ do { \ KUNIT_ASSERTION(test, \ __left op __right, \ assert_class, \ - ASSERT_CLASS_INIT(test, \ - assert_type, \ + ASSERT_CLASS_INIT(assert_type, \ #op, \ #left, \ __left, \ @@ -1234,8 +1232,7 @@ do { \ KUNIT_ASSERTION(test, \ strcmp(__left, __right) op 0, \ kunit_binary_str_assert, \ - KUNIT_INIT_BINARY_STR_ASSERT_STRUCT(test, \ - assert_type, \ + KUNIT_INIT_BINARY_STR_ASSERT_STRUCT(assert_type, \ #op, \ #left, \ __left, \ @@ -1294,8 +1291,7 @@ do { \ KUNIT_ASSERTION(test, \ !IS_ERR_OR_NULL(__ptr), \ kunit_ptr_not_err_assert, \ - KUNIT_INIT_PTR_NOT_ERR_STRUCT(test, \ - assert_type, \ + KUNIT_INIT_PTR_NOT_ERR_STRUCT(assert_type, \ #ptr, \ __ptr), \ fmt, \ -- cgit v1.2.3 From 21957f90b28f6bc118c055e3e564d45f6e4df45d Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Thu, 13 Jan 2022 08:59:30 -0800 Subject: kunit: split out part of kunit_assert into a static const This is per Linus's suggestion in [1]. The issue there is that every KUNIT_EXPECT/KUNIT_ASSERT puts a kunit_assert object onto the stack. Normally we rely on compilers to elide this, but when that doesn't work out, this blows up the stack usage of kunit test functions. We can move some data off the stack by making it static. This change introduces a new `struct kunit_loc` to hold the file and line number and then just passing assert_type (EXPECT or ASSERT) as an argument. In [1], it was suggested to also move out the format string as well, but users could theoretically craft a format string at runtime, so we can't. This change leaves a copy of `assert_type` in kunit_assert for now because cleaning up all the macros to not pass it around is a bit more involved. Here's an example of the expanded code for KUNIT_FAIL(): if (__builtin_expect(!!(!(false)), 0)) { static const struct kunit_loc loc = { .file = ... }; struct kunit_fail_assert __assertion = { .assert = { .type ... }; kunit_do_failed_assertion(test, &loc, KUNIT_EXPECTATION, &__assertion.assert, ...); }; [1] https://groups.google.com/g/kunit-dev/c/i3fZXgvBrfA/m/VULQg1z6BAAJ Signed-off-by: Daniel Latypov Suggested-by: Linus Torvalds Reviewed-by: David Gow Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- include/kunit/assert.h | 25 +++++++++++++++++-------- include/kunit/test.h | 12 +++++++++++- 2 files changed, 28 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/kunit/assert.h b/include/kunit/assert.h index f568166ef034..0da1bbdd1ee8 100644 --- a/include/kunit/assert.h +++ b/include/kunit/assert.h @@ -28,11 +28,21 @@ enum kunit_assert_type { KUNIT_EXPECTATION, }; +/** + * struct kunit_loc - Identifies the source location of a line of code. + * @line: the line number in the file. + * @file: the file name. + */ +struct kunit_loc { + int line; + const char *file; +}; + +#define KUNIT_CURRENT_LOC { .file = __FILE__, .line = __LINE__ } + /** * struct kunit_assert - Data for printing a failed assertion or expectation. * @type: the type (either an expectation or an assertion) of this kunit_assert. - * @line: the source code line number that the expectation/assertion is at. - * @file: the file path of the source file that the expectation/assertion is in. * @message: an optional message to provide additional context. * @format: a function which formats the data in this kunit_assert to a string. * @@ -40,9 +50,9 @@ enum kunit_assert_type { * format a string to a user reporting the failure. */ struct kunit_assert { + // TODO(dlatypov@google.com): delete this unused field when we've + // updated all the related KUNIT_INIT_ASSERT* macros. enum kunit_assert_type type; - int line; - const char *file; struct va_format message; void (*format)(const struct kunit_assert *assert, struct string_stream *stream); @@ -65,14 +75,13 @@ struct kunit_assert { */ #define KUNIT_INIT_ASSERT_STRUCT(assert_type, fmt) { \ .type = assert_type, \ - .file = __FILE__, \ - .line = __LINE__, \ .message = KUNIT_INIT_VA_FMT_NULL, \ .format = fmt \ } -void kunit_base_assert_format(const struct kunit_assert *assert, - struct string_stream *stream); +void kunit_assert_prologue(const struct kunit_loc *loc, + enum kunit_assert_type type, + struct string_stream *stream); void kunit_assert_print_msg(const struct kunit_assert *assert, struct string_stream *stream); diff --git a/include/kunit/test.h b/include/kunit/test.h index 25ea3bce6663..7b752175e614 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -772,13 +772,18 @@ void __printf(2, 3) kunit_log_append(char *log, const char *fmt, ...); #define KUNIT_SUCCEED(test) do {} while (0) void kunit_do_failed_assertion(struct kunit *test, + const struct kunit_loc *loc, + enum kunit_assert_type type, struct kunit_assert *assert, const char *fmt, ...); -#define KUNIT_ASSERTION(test, pass, assert_class, INITIALIZER, fmt, ...) do { \ +#define KUNIT_ASSERTION(test, assert_type, pass, assert_class, INITIALIZER, fmt, ...) do { \ if (unlikely(!(pass))) { \ + static const struct kunit_loc loc = KUNIT_CURRENT_LOC; \ struct assert_class __assertion = INITIALIZER; \ kunit_do_failed_assertion(test, \ + &loc, \ + assert_type, \ &__assertion.assert, \ fmt, \ ##__VA_ARGS__); \ @@ -788,6 +793,7 @@ void kunit_do_failed_assertion(struct kunit *test, #define KUNIT_FAIL_ASSERTION(test, assert_type, fmt, ...) \ KUNIT_ASSERTION(test, \ + assert_type, \ false, \ kunit_fail_assert, \ KUNIT_INIT_FAIL_ASSERT_STRUCT(assert_type), \ @@ -818,6 +824,7 @@ void kunit_do_failed_assertion(struct kunit *test, fmt, \ ...) \ KUNIT_ASSERTION(test, \ + assert_type, \ !!(condition) == !!expected_true, \ kunit_unary_assert, \ KUNIT_INIT_UNARY_ASSERT_STRUCT(assert_type, \ @@ -876,6 +883,7 @@ do { \ typeof(right) __right = (right); \ \ KUNIT_ASSERTION(test, \ + assert_type, \ __left op __right, \ assert_class, \ ASSERT_CLASS_INIT(assert_type, \ @@ -1230,6 +1238,7 @@ do { \ const char *__right = (right); \ \ KUNIT_ASSERTION(test, \ + assert_type, \ strcmp(__left, __right) op 0, \ kunit_binary_str_assert, \ KUNIT_INIT_BINARY_STR_ASSERT_STRUCT(assert_type, \ @@ -1289,6 +1298,7 @@ do { \ typeof(ptr) __ptr = (ptr); \ \ KUNIT_ASSERTION(test, \ + assert_type, \ !IS_ERR_OR_NULL(__ptr), \ kunit_ptr_not_err_assert, \ KUNIT_INIT_PTR_NOT_ERR_STRUCT(assert_type, \ -- cgit v1.2.3 From 05a7da89c15ddb3fc7618a16f5941eca68fc441c Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Thu, 13 Jan 2022 08:59:31 -0800 Subject: kunit: drop unused assert_type from kunit_assert and clean up macros This field has been split out from kunit_assert to make the struct less heavy along with the filename and line number. This change drops the assert_type field and cleans up all the macros that were plumbing assert_type into kunit_assert. Signed-off-by: Daniel Latypov Reviewed-by: David Gow Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- include/kunit/assert.h | 48 ++++++++++++++---------------------------------- include/kunit/test.h | 14 +++++--------- 2 files changed, 19 insertions(+), 43 deletions(-) (limited to 'include') diff --git a/include/kunit/assert.h b/include/kunit/assert.h index 0da1bbdd1ee8..f2b3ae5cc2de 100644 --- a/include/kunit/assert.h +++ b/include/kunit/assert.h @@ -42,7 +42,6 @@ struct kunit_loc { /** * struct kunit_assert - Data for printing a failed assertion or expectation. - * @type: the type (either an expectation or an assertion) of this kunit_assert. * @message: an optional message to provide additional context. * @format: a function which formats the data in this kunit_assert to a string. * @@ -50,9 +49,6 @@ struct kunit_loc { * format a string to a user reporting the failure. */ struct kunit_assert { - // TODO(dlatypov@google.com): delete this unused field when we've - // updated all the related KUNIT_INIT_ASSERT* macros. - enum kunit_assert_type type; struct va_format message; void (*format)(const struct kunit_assert *assert, struct string_stream *stream); @@ -68,13 +64,11 @@ struct kunit_assert { /** * KUNIT_INIT_ASSERT_STRUCT() - Initializer for a &struct kunit_assert. - * @assert_type: The type (assertion or expectation) of this kunit_assert. * @fmt: The formatting function which builds a string out of this kunit_assert. * * The base initializer for a &struct kunit_assert. */ -#define KUNIT_INIT_ASSERT_STRUCT(assert_type, fmt) { \ - .type = assert_type, \ +#define KUNIT_INIT_ASSERT_STRUCT(fmt) { \ .message = KUNIT_INIT_VA_FMT_NULL, \ .format = fmt \ } @@ -100,15 +94,13 @@ void kunit_fail_assert_format(const struct kunit_assert *assert, struct string_stream *stream); /** - * KUNIT_INIT_FAIL_ASSERT_STRUCT() - Initializer for &struct kunit_fail_assert. - * @type: The type (assertion or expectation) of this kunit_assert. + * KUNIT_INIT_FAIL_ASSERT_STRUCT - Initializer for &struct kunit_fail_assert. * * Initializes a &struct kunit_fail_assert. Intended to be used in * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. */ -#define KUNIT_INIT_FAIL_ASSERT_STRUCT(type) { \ - .assert = KUNIT_INIT_ASSERT_STRUCT(type, \ - kunit_fail_assert_format) \ +#define KUNIT_INIT_FAIL_ASSERT_STRUCT { \ + .assert = KUNIT_INIT_ASSERT_STRUCT(kunit_fail_assert_format) \ } /** @@ -132,16 +124,14 @@ void kunit_unary_assert_format(const struct kunit_assert *assert, /** * KUNIT_INIT_UNARY_ASSERT_STRUCT() - Initializes &struct kunit_unary_assert. - * @type: The type (assertion or expectation) of this kunit_assert. * @cond: A string representation of the expression asserted true or false. * @expect_true: True if of type KUNIT_{EXPECT|ASSERT}_TRUE, false otherwise. * * Initializes a &struct kunit_unary_assert. Intended to be used in * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. */ -#define KUNIT_INIT_UNARY_ASSERT_STRUCT(type, cond, expect_true) { \ - .assert = KUNIT_INIT_ASSERT_STRUCT(type, \ - kunit_unary_assert_format), \ +#define KUNIT_INIT_UNARY_ASSERT_STRUCT(cond, expect_true) { \ + .assert = KUNIT_INIT_ASSERT_STRUCT(kunit_unary_assert_format), \ .condition = cond, \ .expected_true = expect_true \ } @@ -168,16 +158,14 @@ void kunit_ptr_not_err_assert_format(const struct kunit_assert *assert, /** * KUNIT_INIT_PTR_NOT_ERR_ASSERT_STRUCT() - Initializes a * &struct kunit_ptr_not_err_assert. - * @type: The type (assertion or expectation) of this kunit_assert. * @txt: A string representation of the expression passed to the expectation. * @val: The actual evaluated pointer value of the expression. * * Initializes a &struct kunit_ptr_not_err_assert. Intended to be used in * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. */ -#define KUNIT_INIT_PTR_NOT_ERR_STRUCT(type, txt, val) { \ - .assert = KUNIT_INIT_ASSERT_STRUCT(type, \ - kunit_ptr_not_err_assert_format), \ +#define KUNIT_INIT_PTR_NOT_ERR_STRUCT(txt, val) { \ + .assert = KUNIT_INIT_ASSERT_STRUCT(kunit_ptr_not_err_assert_format), \ .text = txt, \ .value = val \ } @@ -211,7 +199,6 @@ void kunit_binary_assert_format(const struct kunit_assert *assert, /** * KUNIT_INIT_BINARY_ASSERT_STRUCT() - Initializes a * &struct kunit_binary_assert. - * @type: The type (assertion or expectation) of this kunit_assert. * @op_str: A string representation of the comparison operator (e.g. "=="). * @left_str: A string representation of the expression in the left slot. * @left_val: The actual evaluated value of the expression in the left slot. @@ -221,14 +208,12 @@ void kunit_binary_assert_format(const struct kunit_assert *assert, * Initializes a &struct kunit_binary_assert. Intended to be used in * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. */ -#define KUNIT_INIT_BINARY_ASSERT_STRUCT(type, \ - op_str, \ +#define KUNIT_INIT_BINARY_ASSERT_STRUCT(op_str, \ left_str, \ left_val, \ right_str, \ right_val) { \ - .assert = KUNIT_INIT_ASSERT_STRUCT(type, \ - kunit_binary_assert_format), \ + .assert = KUNIT_INIT_ASSERT_STRUCT(kunit_binary_assert_format), \ .operation = op_str, \ .left_text = left_str, \ .left_value = left_val, \ @@ -275,14 +260,12 @@ void kunit_binary_ptr_assert_format(const struct kunit_assert *assert, * Initializes a &struct kunit_binary_ptr_assert. Intended to be used in * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. */ -#define KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT(type, \ - op_str, \ +#define KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT(op_str, \ left_str, \ left_val, \ right_str, \ right_val) { \ - .assert = KUNIT_INIT_ASSERT_STRUCT(type, \ - kunit_binary_ptr_assert_format), \ + .assert = KUNIT_INIT_ASSERT_STRUCT(kunit_binary_ptr_assert_format), \ .operation = op_str, \ .left_text = left_str, \ .left_value = left_val, \ @@ -319,7 +302,6 @@ void kunit_binary_str_assert_format(const struct kunit_assert *assert, /** * KUNIT_INIT_BINARY_STR_ASSERT_STRUCT() - Initializes a * &struct kunit_binary_str_assert. - * @type: The type (assertion or expectation) of this kunit_assert. * @op_str: A string representation of the comparison operator (e.g. "=="). * @left_str: A string representation of the expression in the left slot. * @left_val: The actual evaluated value of the expression in the left slot. @@ -329,14 +311,12 @@ void kunit_binary_str_assert_format(const struct kunit_assert *assert, * Initializes a &struct kunit_binary_str_assert. Intended to be used in * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. */ -#define KUNIT_INIT_BINARY_STR_ASSERT_STRUCT(type, \ - op_str, \ +#define KUNIT_INIT_BINARY_STR_ASSERT_STRUCT(op_str, \ left_str, \ left_val, \ right_str, \ right_val) { \ - .assert = KUNIT_INIT_ASSERT_STRUCT(type, \ - kunit_binary_str_assert_format), \ + .assert = KUNIT_INIT_ASSERT_STRUCT(kunit_binary_str_assert_format), \ .operation = op_str, \ .left_text = left_str, \ .left_value = left_val, \ diff --git a/include/kunit/test.h b/include/kunit/test.h index 7b752175e614..5964af750d93 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -796,7 +796,7 @@ void kunit_do_failed_assertion(struct kunit *test, assert_type, \ false, \ kunit_fail_assert, \ - KUNIT_INIT_FAIL_ASSERT_STRUCT(assert_type), \ + KUNIT_INIT_FAIL_ASSERT_STRUCT, \ fmt, \ ##__VA_ARGS__) @@ -827,8 +827,7 @@ void kunit_do_failed_assertion(struct kunit *test, assert_type, \ !!(condition) == !!expected_true, \ kunit_unary_assert, \ - KUNIT_INIT_UNARY_ASSERT_STRUCT(assert_type, \ - #condition, \ + KUNIT_INIT_UNARY_ASSERT_STRUCT(#condition, \ expected_true), \ fmt, \ ##__VA_ARGS__) @@ -886,8 +885,7 @@ do { \ assert_type, \ __left op __right, \ assert_class, \ - ASSERT_CLASS_INIT(assert_type, \ - #op, \ + ASSERT_CLASS_INIT(#op, \ #left, \ __left, \ #right, \ @@ -1241,8 +1239,7 @@ do { \ assert_type, \ strcmp(__left, __right) op 0, \ kunit_binary_str_assert, \ - KUNIT_INIT_BINARY_STR_ASSERT_STRUCT(assert_type, \ - #op, \ + KUNIT_INIT_BINARY_STR_ASSERT_STRUCT(#op, \ #left, \ __left, \ #right, \ @@ -1301,8 +1298,7 @@ do { \ assert_type, \ !IS_ERR_OR_NULL(__ptr), \ kunit_ptr_not_err_assert, \ - KUNIT_INIT_PTR_NOT_ERR_STRUCT(assert_type, \ - #ptr, \ + KUNIT_INIT_PTR_NOT_ERR_STRUCT(#ptr, \ __ptr), \ fmt, \ ##__VA_ARGS__); \ -- cgit v1.2.3 From 6709d0fe55933d3ac944f3cdd5b66d9786092f90 Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Tue, 18 Jan 2022 14:35:02 -0800 Subject: kunit: make KUNIT_EXPECT_EQ() use KUNIT_EXPECT_EQ_MSG(), etc. There's quite a few macros in play for KUnit assertions. The current macro chain looks like: KUNIT_EXPECT_EQ => KUNIT_BINARY_EQ_ASSERTION => KUNIT_BINARY_EQ_MSG_ASSERTION KUNIT_EXPECT_EQ_MSG => KUNIT_BINARY_EQ_MSG_ASSERTION KUNIT_ASSERT_EQ => KUNIT_BINARY_EQ_ASSERTION => KUNIT_BINARY_EQ_MSG_ASSERTION KUNIT_ASSERT_EQ_MSG => KUNIT_BINARY_EQ_MSG_ASSERTION After this change: KUNIT_EXPECT_EQ => KUNIT_EXPECT_EQ_MSG => KUNIT_BINARY_EQ_MSG_ASSERTION KUNIT_ASSERT_EQ => KUNIT_ASSERT_EQ_MSG => KUNIT_BINARY_EQ_MSG_ASSERTION and we can drop the intermediate KUNIT_BINARY_EQ_ASSERTION. This change does this for all the other macros as well. Signed-off-by: Daniel Latypov Reviewed-by: David Gow Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- include/kunit/test.h | 168 ++++++++------------------------------------------- 1 file changed, 26 insertions(+), 142 deletions(-) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index 5964af750d93..b032dd6816d2 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -840,9 +840,6 @@ void kunit_do_failed_assertion(struct kunit *test, fmt, \ ##__VA_ARGS__) -#define KUNIT_TRUE_ASSERTION(test, assert_type, condition) \ - KUNIT_TRUE_MSG_ASSERTION(test, assert_type, condition, NULL) - #define KUNIT_FALSE_MSG_ASSERTION(test, assert_type, condition, fmt, ...) \ KUNIT_UNARY_ASSERTION(test, \ assert_type, \ @@ -851,9 +848,6 @@ void kunit_do_failed_assertion(struct kunit *test, fmt, \ ##__VA_ARGS__) -#define KUNIT_FALSE_ASSERTION(test, assert_type, condition) \ - KUNIT_FALSE_MSG_ASSERTION(test, assert_type, condition, NULL) - /* * A factory macro for defining the assertions and expectations for the basic * comparisons defined for the built in types. @@ -1000,13 +994,6 @@ do { \ fmt, \ ##__VA_ARGS__) -#define KUNIT_BINARY_EQ_ASSERTION(test, assert_type, left, right) \ - KUNIT_BINARY_EQ_MSG_ASSERTION(test, \ - assert_type, \ - left, \ - right, \ - NULL) - #define KUNIT_BINARY_PTR_EQ_MSG_ASSERTION(test, \ assert_type, \ left, \ @@ -1022,13 +1009,6 @@ do { \ fmt, \ ##__VA_ARGS__) -#define KUNIT_BINARY_PTR_EQ_ASSERTION(test, assert_type, left, right) \ - KUNIT_BINARY_PTR_EQ_MSG_ASSERTION(test, \ - assert_type, \ - left, \ - right, \ - NULL) - #define KUNIT_BINARY_NE_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\ KUNIT_BASE_NE_MSG_ASSERTION(test, \ kunit_binary_assert, \ @@ -1039,13 +1019,6 @@ do { \ fmt, \ ##__VA_ARGS__) -#define KUNIT_BINARY_NE_ASSERTION(test, assert_type, left, right) \ - KUNIT_BINARY_NE_MSG_ASSERTION(test, \ - assert_type, \ - left, \ - right, \ - NULL) - #define KUNIT_BINARY_PTR_NE_MSG_ASSERTION(test, \ assert_type, \ left, \ @@ -1061,13 +1034,6 @@ do { \ fmt, \ ##__VA_ARGS__) -#define KUNIT_BINARY_PTR_NE_ASSERTION(test, assert_type, left, right) \ - KUNIT_BINARY_PTR_NE_MSG_ASSERTION(test, \ - assert_type, \ - left, \ - right, \ - NULL) - #define KUNIT_BINARY_LT_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\ KUNIT_BASE_LT_MSG_ASSERTION(test, \ kunit_binary_assert, \ @@ -1078,13 +1044,6 @@ do { \ fmt, \ ##__VA_ARGS__) -#define KUNIT_BINARY_LT_ASSERTION(test, assert_type, left, right) \ - KUNIT_BINARY_LT_MSG_ASSERTION(test, \ - assert_type, \ - left, \ - right, \ - NULL) - #define KUNIT_BINARY_PTR_LT_MSG_ASSERTION(test, \ assert_type, \ left, \ @@ -1100,13 +1059,6 @@ do { \ fmt, \ ##__VA_ARGS__) -#define KUNIT_BINARY_PTR_LT_ASSERTION(test, assert_type, left, right) \ - KUNIT_BINARY_PTR_LT_MSG_ASSERTION(test, \ - assert_type, \ - left, \ - right, \ - NULL) - #define KUNIT_BINARY_LE_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\ KUNIT_BASE_LE_MSG_ASSERTION(test, \ kunit_binary_assert, \ @@ -1117,13 +1069,6 @@ do { \ fmt, \ ##__VA_ARGS__) -#define KUNIT_BINARY_LE_ASSERTION(test, assert_type, left, right) \ - KUNIT_BINARY_LE_MSG_ASSERTION(test, \ - assert_type, \ - left, \ - right, \ - NULL) - #define KUNIT_BINARY_PTR_LE_MSG_ASSERTION(test, \ assert_type, \ left, \ @@ -1139,13 +1084,6 @@ do { \ fmt, \ ##__VA_ARGS__) -#define KUNIT_BINARY_PTR_LE_ASSERTION(test, assert_type, left, right) \ - KUNIT_BINARY_PTR_LE_MSG_ASSERTION(test, \ - assert_type, \ - left, \ - right, \ - NULL) - #define KUNIT_BINARY_GT_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\ KUNIT_BASE_GT_MSG_ASSERTION(test, \ kunit_binary_assert, \ @@ -1156,13 +1094,6 @@ do { \ fmt, \ ##__VA_ARGS__) -#define KUNIT_BINARY_GT_ASSERTION(test, assert_type, left, right) \ - KUNIT_BINARY_GT_MSG_ASSERTION(test, \ - assert_type, \ - left, \ - right, \ - NULL) - #define KUNIT_BINARY_PTR_GT_MSG_ASSERTION(test, \ assert_type, \ left, \ @@ -1178,13 +1109,6 @@ do { \ fmt, \ ##__VA_ARGS__) -#define KUNIT_BINARY_PTR_GT_ASSERTION(test, assert_type, left, right) \ - KUNIT_BINARY_PTR_GT_MSG_ASSERTION(test, \ - assert_type, \ - left, \ - right, \ - NULL) - #define KUNIT_BINARY_GE_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\ KUNIT_BASE_GE_MSG_ASSERTION(test, \ kunit_binary_assert, \ @@ -1195,13 +1119,6 @@ do { \ fmt, \ ##__VA_ARGS__) -#define KUNIT_BINARY_GE_ASSERTION(test, assert_type, left, right) \ - KUNIT_BINARY_GE_MSG_ASSERTION(test, \ - assert_type, \ - left, \ - right, \ - NULL) - #define KUNIT_BINARY_PTR_GE_MSG_ASSERTION(test, \ assert_type, \ left, \ @@ -1217,13 +1134,6 @@ do { \ fmt, \ ##__VA_ARGS__) -#define KUNIT_BINARY_PTR_GE_ASSERTION(test, assert_type, left, right) \ - KUNIT_BINARY_PTR_GE_MSG_ASSERTION(test, \ - assert_type, \ - left, \ - right, \ - NULL) - #define KUNIT_BINARY_STR_ASSERTION(test, \ assert_type, \ left, \ @@ -1260,13 +1170,6 @@ do { \ fmt, \ ##__VA_ARGS__) -#define KUNIT_BINARY_STR_EQ_ASSERTION(test, assert_type, left, right) \ - KUNIT_BINARY_STR_EQ_MSG_ASSERTION(test, \ - assert_type, \ - left, \ - right, \ - NULL) - #define KUNIT_BINARY_STR_NE_MSG_ASSERTION(test, \ assert_type, \ left, \ @@ -1279,13 +1182,6 @@ do { \ fmt, \ ##__VA_ARGS__) -#define KUNIT_BINARY_STR_NE_ASSERTION(test, assert_type, left, right) \ - KUNIT_BINARY_STR_NE_MSG_ASSERTION(test, \ - assert_type, \ - left, \ - right, \ - NULL) - #define KUNIT_PTR_NOT_ERR_OR_NULL_MSG_ASSERTION(test, \ assert_type, \ ptr, \ @@ -1304,12 +1200,6 @@ do { \ ##__VA_ARGS__); \ } while (0) -#define KUNIT_PTR_NOT_ERR_OR_NULL_ASSERTION(test, assert_type, ptr) \ - KUNIT_PTR_NOT_ERR_OR_NULL_MSG_ASSERTION(test, \ - assert_type, \ - ptr, \ - NULL) - /** * KUNIT_EXPECT_TRUE() - Causes a test failure when the expression is not true. * @test: The test context object. @@ -1322,7 +1212,7 @@ do { \ * *expectation failure*. */ #define KUNIT_EXPECT_TRUE(test, condition) \ - KUNIT_TRUE_ASSERTION(test, KUNIT_EXPECTATION, condition) + KUNIT_EXPECT_TRUE_MSG(test, condition, NULL) #define KUNIT_EXPECT_TRUE_MSG(test, condition, fmt, ...) \ KUNIT_TRUE_MSG_ASSERTION(test, \ @@ -1341,7 +1231,7 @@ do { \ * KUNIT_EXPECT_TRUE() for more information. */ #define KUNIT_EXPECT_FALSE(test, condition) \ - KUNIT_FALSE_ASSERTION(test, KUNIT_EXPECTATION, condition) + KUNIT_EXPECT_FALSE_MSG(test, condition, NULL) #define KUNIT_EXPECT_FALSE_MSG(test, condition, fmt, ...) \ KUNIT_FALSE_MSG_ASSERTION(test, \ @@ -1362,7 +1252,7 @@ do { \ * more information. */ #define KUNIT_EXPECT_EQ(test, left, right) \ - KUNIT_BINARY_EQ_ASSERTION(test, KUNIT_EXPECTATION, left, right) + KUNIT_EXPECT_EQ_MSG(test, left, right, NULL) #define KUNIT_EXPECT_EQ_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_EQ_MSG_ASSERTION(test, \ @@ -1384,10 +1274,7 @@ do { \ * more information. */ #define KUNIT_EXPECT_PTR_EQ(test, left, right) \ - KUNIT_BINARY_PTR_EQ_ASSERTION(test, \ - KUNIT_EXPECTATION, \ - left, \ - right) + KUNIT_EXPECT_PTR_EQ_MSG(test, left, right, NULL) #define KUNIT_EXPECT_PTR_EQ_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_PTR_EQ_MSG_ASSERTION(test, \ @@ -1409,7 +1296,7 @@ do { \ * more information. */ #define KUNIT_EXPECT_NE(test, left, right) \ - KUNIT_BINARY_NE_ASSERTION(test, KUNIT_EXPECTATION, left, right) + KUNIT_EXPECT_NE_MSG(test, left, right, NULL) #define KUNIT_EXPECT_NE_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_NE_MSG_ASSERTION(test, \ @@ -1431,10 +1318,7 @@ do { \ * more information. */ #define KUNIT_EXPECT_PTR_NE(test, left, right) \ - KUNIT_BINARY_PTR_NE_ASSERTION(test, \ - KUNIT_EXPECTATION, \ - left, \ - right) + KUNIT_EXPECT_PTR_NE_MSG(test, left, right, NULL) #define KUNIT_EXPECT_PTR_NE_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_PTR_NE_MSG_ASSERTION(test, \ @@ -1456,7 +1340,7 @@ do { \ * more information. */ #define KUNIT_EXPECT_LT(test, left, right) \ - KUNIT_BINARY_LT_ASSERTION(test, KUNIT_EXPECTATION, left, right) + KUNIT_EXPECT_LT_MSG(test, left, right, NULL) #define KUNIT_EXPECT_LT_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_LT_MSG_ASSERTION(test, \ @@ -1478,7 +1362,7 @@ do { \ * more information. */ #define KUNIT_EXPECT_LE(test, left, right) \ - KUNIT_BINARY_LE_ASSERTION(test, KUNIT_EXPECTATION, left, right) + KUNIT_EXPECT_LE_MSG(test, left, right, NULL) #define KUNIT_EXPECT_LE_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_LE_MSG_ASSERTION(test, \ @@ -1500,7 +1384,7 @@ do { \ * more information. */ #define KUNIT_EXPECT_GT(test, left, right) \ - KUNIT_BINARY_GT_ASSERTION(test, KUNIT_EXPECTATION, left, right) + KUNIT_EXPECT_GT_MSG(test, left, right, NULL) #define KUNIT_EXPECT_GT_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_GT_MSG_ASSERTION(test, \ @@ -1522,7 +1406,7 @@ do { \ * more information. */ #define KUNIT_EXPECT_GE(test, left, right) \ - KUNIT_BINARY_GE_ASSERTION(test, KUNIT_EXPECTATION, left, right) + KUNIT_EXPECT_GE_MSG(test, left, right, NULL) #define KUNIT_EXPECT_GE_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_GE_MSG_ASSERTION(test, \ @@ -1544,7 +1428,7 @@ do { \ * for more information. */ #define KUNIT_EXPECT_STREQ(test, left, right) \ - KUNIT_BINARY_STR_EQ_ASSERTION(test, KUNIT_EXPECTATION, left, right) + KUNIT_EXPECT_STREQ_MSG(test, left, right, NULL) #define KUNIT_EXPECT_STREQ_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_STR_EQ_MSG_ASSERTION(test, \ @@ -1566,7 +1450,7 @@ do { \ * for more information. */ #define KUNIT_EXPECT_STRNEQ(test, left, right) \ - KUNIT_BINARY_STR_NE_ASSERTION(test, KUNIT_EXPECTATION, left, right) + KUNIT_EXPECT_STRNEQ_MSG(test, left, right, NULL) #define KUNIT_EXPECT_STRNEQ_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_STR_NE_MSG_ASSERTION(test, \ @@ -1587,7 +1471,7 @@ do { \ * more information. */ #define KUNIT_EXPECT_NOT_ERR_OR_NULL(test, ptr) \ - KUNIT_PTR_NOT_ERR_OR_NULL_ASSERTION(test, KUNIT_EXPECTATION, ptr) + KUNIT_EXPECT_NOT_ERR_OR_NULL_MSG(test, ptr, NULL) #define KUNIT_EXPECT_NOT_ERR_OR_NULL_MSG(test, ptr, fmt, ...) \ KUNIT_PTR_NOT_ERR_OR_NULL_MSG_ASSERTION(test, \ @@ -1611,7 +1495,7 @@ do { \ * this is otherwise known as an *assertion failure*. */ #define KUNIT_ASSERT_TRUE(test, condition) \ - KUNIT_TRUE_ASSERTION(test, KUNIT_ASSERTION, condition) + KUNIT_ASSERT_TRUE_MSG(test, condition, NULL) #define KUNIT_ASSERT_TRUE_MSG(test, condition, fmt, ...) \ KUNIT_TRUE_MSG_ASSERTION(test, \ @@ -1630,7 +1514,7 @@ do { \ * (see KUNIT_ASSERT_TRUE()) when the assertion is not met. */ #define KUNIT_ASSERT_FALSE(test, condition) \ - KUNIT_FALSE_ASSERTION(test, KUNIT_ASSERTION, condition) + KUNIT_ASSERT_FALSE_MSG(test, condition, NULL) #define KUNIT_ASSERT_FALSE_MSG(test, condition, fmt, ...) \ KUNIT_FALSE_MSG_ASSERTION(test, \ @@ -1650,7 +1534,7 @@ do { \ * failure (see KUNIT_ASSERT_TRUE()) when the assertion is not met. */ #define KUNIT_ASSERT_EQ(test, left, right) \ - KUNIT_BINARY_EQ_ASSERTION(test, KUNIT_ASSERTION, left, right) + KUNIT_ASSERT_EQ_MSG(test, left, right, NULL) #define KUNIT_ASSERT_EQ_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_EQ_MSG_ASSERTION(test, \ @@ -1671,7 +1555,7 @@ do { \ * failure (see KUNIT_ASSERT_TRUE()) when the assertion is not met. */ #define KUNIT_ASSERT_PTR_EQ(test, left, right) \ - KUNIT_BINARY_PTR_EQ_ASSERTION(test, KUNIT_ASSERTION, left, right) + KUNIT_ASSERT_PTR_EQ_MSG(test, left, right, NULL) #define KUNIT_ASSERT_PTR_EQ_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_PTR_EQ_MSG_ASSERTION(test, \ @@ -1692,7 +1576,7 @@ do { \ * failure (see KUNIT_ASSERT_TRUE()) when the assertion is not met. */ #define KUNIT_ASSERT_NE(test, left, right) \ - KUNIT_BINARY_NE_ASSERTION(test, KUNIT_ASSERTION, left, right) + KUNIT_ASSERT_NE_MSG(test, left, right, NULL) #define KUNIT_ASSERT_NE_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_NE_MSG_ASSERTION(test, \ @@ -1714,7 +1598,7 @@ do { \ * failure (see KUNIT_ASSERT_TRUE()) when the assertion is not met. */ #define KUNIT_ASSERT_PTR_NE(test, left, right) \ - KUNIT_BINARY_PTR_NE_ASSERTION(test, KUNIT_ASSERTION, left, right) + KUNIT_ASSERT_PTR_NE_MSG(test, left, right, NULL) #define KUNIT_ASSERT_PTR_NE_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_PTR_NE_MSG_ASSERTION(test, \ @@ -1735,7 +1619,7 @@ do { \ * is not met. */ #define KUNIT_ASSERT_LT(test, left, right) \ - KUNIT_BINARY_LT_ASSERTION(test, KUNIT_ASSERTION, left, right) + KUNIT_ASSERT_LT_MSG(test, left, right, NULL) #define KUNIT_ASSERT_LT_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_LT_MSG_ASSERTION(test, \ @@ -1756,7 +1640,7 @@ do { \ * KUNIT_ASSERT_TRUE()) when the assertion is not met. */ #define KUNIT_ASSERT_LE(test, left, right) \ - KUNIT_BINARY_LE_ASSERTION(test, KUNIT_ASSERTION, left, right) + KUNIT_ASSERT_LE_MSG(test, left, right, NULL) #define KUNIT_ASSERT_LE_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_LE_MSG_ASSERTION(test, \ @@ -1778,7 +1662,7 @@ do { \ * is not met. */ #define KUNIT_ASSERT_GT(test, left, right) \ - KUNIT_BINARY_GT_ASSERTION(test, KUNIT_ASSERTION, left, right) + KUNIT_ASSERT_GT_MSG(test, left, right, NULL) #define KUNIT_ASSERT_GT_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_GT_MSG_ASSERTION(test, \ @@ -1800,7 +1684,7 @@ do { \ * is not met. */ #define KUNIT_ASSERT_GE(test, left, right) \ - KUNIT_BINARY_GE_ASSERTION(test, KUNIT_ASSERTION, left, right) + KUNIT_ASSERT_GE_MSG(test, left, right, NULL) #define KUNIT_ASSERT_GE_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_GE_MSG_ASSERTION(test, \ @@ -1821,7 +1705,7 @@ do { \ * assertion failure (see KUNIT_ASSERT_TRUE()) when the assertion is not met. */ #define KUNIT_ASSERT_STREQ(test, left, right) \ - KUNIT_BINARY_STR_EQ_ASSERTION(test, KUNIT_ASSERTION, left, right) + KUNIT_ASSERT_STREQ_MSG(test, left, right, NULL) #define KUNIT_ASSERT_STREQ_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_STR_EQ_MSG_ASSERTION(test, \ @@ -1843,7 +1727,7 @@ do { \ * for more information. */ #define KUNIT_ASSERT_STRNEQ(test, left, right) \ - KUNIT_BINARY_STR_NE_ASSERTION(test, KUNIT_ASSERTION, left, right) + KUNIT_ASSERT_STRNEQ_MSG(test, left, right, NULL) #define KUNIT_ASSERT_STRNEQ_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_STR_NE_MSG_ASSERTION(test, \ @@ -1864,7 +1748,7 @@ do { \ * KUNIT_ASSERT_TRUE()) when the assertion is not met. */ #define KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr) \ - KUNIT_PTR_NOT_ERR_OR_NULL_ASSERTION(test, KUNIT_ASSERTION, ptr) + KUNIT_ASSERT_NOT_ERR_OR_NULL_MSG(test, ptr, NULL) #define KUNIT_ASSERT_NOT_ERR_OR_NULL_MSG(test, ptr, fmt, ...) \ KUNIT_PTR_NOT_ERR_OR_NULL_MSG_ASSERTION(test, \ -- cgit v1.2.3 From c5855907d388321c1089023489e49ba9a5e9afc7 Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Tue, 18 Jan 2022 14:35:03 -0800 Subject: kunit: drop unused intermediate macros for ptr inequality checks We have the intermediate macros for KUNIT_EXPECT_PTR_GT() and friends, but these macros don't exist. I can see niche usecases for these macros existing, but since we've been fine without them for so long, let's drop this dead code. Users can instead cast the pointers and use the other GT/LT macros. Signed-off-by: Daniel Latypov Reviewed-by: David Gow Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- include/kunit/test.h | 60 ---------------------------------------------------- 1 file changed, 60 deletions(-) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index b032dd6816d2..c021945a75e3 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -1044,21 +1044,6 @@ do { \ fmt, \ ##__VA_ARGS__) -#define KUNIT_BINARY_PTR_LT_MSG_ASSERTION(test, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ...) \ - KUNIT_BASE_LT_MSG_ASSERTION(test, \ - kunit_binary_ptr_assert, \ - KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) - #define KUNIT_BINARY_LE_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\ KUNIT_BASE_LE_MSG_ASSERTION(test, \ kunit_binary_assert, \ @@ -1069,21 +1054,6 @@ do { \ fmt, \ ##__VA_ARGS__) -#define KUNIT_BINARY_PTR_LE_MSG_ASSERTION(test, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ...) \ - KUNIT_BASE_LE_MSG_ASSERTION(test, \ - kunit_binary_ptr_assert, \ - KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) - #define KUNIT_BINARY_GT_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\ KUNIT_BASE_GT_MSG_ASSERTION(test, \ kunit_binary_assert, \ @@ -1094,21 +1064,6 @@ do { \ fmt, \ ##__VA_ARGS__) -#define KUNIT_BINARY_PTR_GT_MSG_ASSERTION(test, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ...) \ - KUNIT_BASE_GT_MSG_ASSERTION(test, \ - kunit_binary_ptr_assert, \ - KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) - #define KUNIT_BINARY_GE_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\ KUNIT_BASE_GE_MSG_ASSERTION(test, \ kunit_binary_assert, \ @@ -1119,21 +1074,6 @@ do { \ fmt, \ ##__VA_ARGS__) -#define KUNIT_BINARY_PTR_GE_MSG_ASSERTION(test, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ...) \ - KUNIT_BASE_GE_MSG_ASSERTION(test, \ - kunit_binary_ptr_assert, \ - KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) - #define KUNIT_BINARY_STR_ASSERTION(test, \ assert_type, \ left, \ -- cgit v1.2.3 From 955df7d85e58b8090f1fd2d10b4b2713e99b552c Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Tue, 18 Jan 2022 14:35:04 -0800 Subject: kunit: reduce layering in string assertion macros The current macro chain looks like: KUNIT_EXPECT_STREQ => KUNIT_EXPECT_STREQ_MSG => KUNIT_BINARY_STR_EQ_MSG_ASSERTION => KUNIT_BINARY_STR_ASSERTION. KUNIT_ASSERT_STREQ => KUNIT_ASSERT_STREQ_MSG => KUNIT_BINARY_STR_EQ_MSG_ASSERTION => KUNIT_BINARY_STR_ASSERTION. After this change: KUNIT_EXPECT_STREQ => KUNIT_EXPECT_STREQ_MSG => KUNIT_BINARY_STR_ASSERTION. KUNIT_ASSERT_STREQ => KUNIT_ASSERT_STREQ_MSG => KUNIT_BINARY_STR_ASSERTION. All the intermediate macro did was pass in "==" or "!=", so it seems better to just drop them at the cost of a bit more copy-paste. Signed-off-by: Daniel Latypov Reviewed-by: David Gow Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- include/kunit/test.h | 68 ++++++++++++++++------------------------------------ 1 file changed, 20 insertions(+), 48 deletions(-) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index c021945a75e3..d5dc1ef68bfe 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -1098,30 +1098,6 @@ do { \ ##__VA_ARGS__); \ } while (0) -#define KUNIT_BINARY_STR_EQ_MSG_ASSERTION(test, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ...) \ - KUNIT_BINARY_STR_ASSERTION(test, \ - assert_type, \ - left, ==, right, \ - fmt, \ - ##__VA_ARGS__) - -#define KUNIT_BINARY_STR_NE_MSG_ASSERTION(test, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ...) \ - KUNIT_BINARY_STR_ASSERTION(test, \ - assert_type, \ - left, !=, right, \ - fmt, \ - ##__VA_ARGS__) - #define KUNIT_PTR_NOT_ERR_OR_NULL_MSG_ASSERTION(test, \ assert_type, \ ptr, \ @@ -1371,12 +1347,11 @@ do { \ KUNIT_EXPECT_STREQ_MSG(test, left, right, NULL) #define KUNIT_EXPECT_STREQ_MSG(test, left, right, fmt, ...) \ - KUNIT_BINARY_STR_EQ_MSG_ASSERTION(test, \ - KUNIT_EXPECTATION, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) + KUNIT_BINARY_STR_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, ==, right, \ + fmt, \ + ##__VA_ARGS__) /** * KUNIT_EXPECT_STRNEQ() - Expects that strings @left and @right are not equal. @@ -1393,12 +1368,11 @@ do { \ KUNIT_EXPECT_STRNEQ_MSG(test, left, right, NULL) #define KUNIT_EXPECT_STRNEQ_MSG(test, left, right, fmt, ...) \ - KUNIT_BINARY_STR_NE_MSG_ASSERTION(test, \ - KUNIT_EXPECTATION, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) + KUNIT_BINARY_STR_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, !=, right, \ + fmt, \ + ##__VA_ARGS__) /** * KUNIT_EXPECT_NOT_ERR_OR_NULL() - Expects that @ptr is not null and not err. @@ -1648,12 +1622,11 @@ do { \ KUNIT_ASSERT_STREQ_MSG(test, left, right, NULL) #define KUNIT_ASSERT_STREQ_MSG(test, left, right, fmt, ...) \ - KUNIT_BINARY_STR_EQ_MSG_ASSERTION(test, \ - KUNIT_ASSERTION, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) + KUNIT_BINARY_STR_ASSERTION(test, \ + KUNIT_ASSERTION, \ + left, ==, right, \ + fmt, \ + ##__VA_ARGS__) /** * KUNIT_ASSERT_STRNEQ() - Expects that strings @left and @right are not equal. @@ -1670,12 +1643,11 @@ do { \ KUNIT_ASSERT_STRNEQ_MSG(test, left, right, NULL) #define KUNIT_ASSERT_STRNEQ_MSG(test, left, right, fmt, ...) \ - KUNIT_BINARY_STR_NE_MSG_ASSERTION(test, \ - KUNIT_ASSERTION, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) + KUNIT_BINARY_STR_ASSERTION(test, \ + KUNIT_ASSERTION, \ + left, !=, right, \ + fmt, \ + ##__VA_ARGS__) /** * KUNIT_ASSERT_NOT_ERR_OR_NULL() - Assertion that @ptr is not null and not err. -- cgit v1.2.3 From 40f39777ce4f8e65ca16c10f1b895bbe8306a42f Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Tue, 18 Jan 2022 14:35:05 -0800 Subject: kunit: decrease macro layering for integer asserts Introduce a KUNIT_BINARY_INT_ASSERTION for the likes of KUNIT_EXPECT_LT. This is analagous to KUNIT_BINARY_STR_ASSERTION. Note: this patch leaves the EQ/NE macros untouched since those share some intermediate macros for the pointer-based macros. The current macro chain looks like: KUNIT_EXPECT_LT_MSG => KUNIT_BASE_LT_MSG_ASSERTION => KUNIT_BASE_BINARY_ASSERTION KUNIT_EXPECT_GT_MSG => KUNIT_BASE_GT_MSG_ASSERTION => KUNIT_BASE_BINARY_ASSERTION After this change: KUNIT_EXPECT_LT_MSG => KUNIT_BINARY_INT_ASSERTION => KUNIT_BASE_BINARY_ASSERTION KUNIT_EXPECT_GT_MSG => KUNIT_BINARY_INT_ASSERTION => KUNIT_BASE_BINARY_ASSERTION I.e. we've traded all the unique intermediary macros for a single shared KUNIT_BINARY_INT_ASSERTION. The only difference is that users of KUNIT_BINARY_INT_ASSERTION also need to pass the operation (==, <, etc.). Signed-off-by: Daniel Latypov Reviewed-by: David Gow Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- include/kunit/test.h | 199 +++++++++++++-------------------------------------- 1 file changed, 51 insertions(+), 148 deletions(-) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index d5dc1ef68bfe..48cf520b69ce 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -920,77 +920,28 @@ do { \ fmt, \ ##__VA_ARGS__) -#define KUNIT_BASE_LT_MSG_ASSERTION(test, \ - assert_class, \ - ASSERT_CLASS_INIT, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ...) \ - KUNIT_BASE_BINARY_ASSERTION(test, \ - assert_class, \ - ASSERT_CLASS_INIT, \ - assert_type, \ - left, <, right, \ - fmt, \ - ##__VA_ARGS__) - -#define KUNIT_BASE_LE_MSG_ASSERTION(test, \ - assert_class, \ - ASSERT_CLASS_INIT, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ...) \ - KUNIT_BASE_BINARY_ASSERTION(test, \ - assert_class, \ - ASSERT_CLASS_INIT, \ - assert_type, \ - left, <=, right, \ - fmt, \ - ##__VA_ARGS__) - -#define KUNIT_BASE_GT_MSG_ASSERTION(test, \ - assert_class, \ - ASSERT_CLASS_INIT, \ +#define KUNIT_BINARY_EQ_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\ + KUNIT_BASE_EQ_MSG_ASSERTION(test, \ + kunit_binary_assert, \ + KUNIT_INIT_BINARY_ASSERT_STRUCT, \ assert_type, \ left, \ right, \ fmt, \ - ...) \ - KUNIT_BASE_BINARY_ASSERTION(test, \ - assert_class, \ - ASSERT_CLASS_INIT, \ - assert_type, \ - left, >, right, \ - fmt, \ ##__VA_ARGS__) -#define KUNIT_BASE_GE_MSG_ASSERTION(test, \ - assert_class, \ - ASSERT_CLASS_INIT, \ - assert_type, \ - left, \ - right, \ - fmt, \ +#define KUNIT_BINARY_INT_ASSERTION(test, \ + assert_type, \ + left, \ + op, \ + right, \ + fmt, \ ...) \ KUNIT_BASE_BINARY_ASSERTION(test, \ - assert_class, \ - ASSERT_CLASS_INIT, \ - assert_type, \ - left, >=, right, \ - fmt, \ - ##__VA_ARGS__) - -#define KUNIT_BINARY_EQ_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\ - KUNIT_BASE_EQ_MSG_ASSERTION(test, \ kunit_binary_assert, \ KUNIT_INIT_BINARY_ASSERT_STRUCT, \ assert_type, \ - left, \ - right, \ + left, op, right, \ fmt, \ ##__VA_ARGS__) @@ -1034,46 +985,6 @@ do { \ fmt, \ ##__VA_ARGS__) -#define KUNIT_BINARY_LT_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\ - KUNIT_BASE_LT_MSG_ASSERTION(test, \ - kunit_binary_assert, \ - KUNIT_INIT_BINARY_ASSERT_STRUCT, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) - -#define KUNIT_BINARY_LE_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\ - KUNIT_BASE_LE_MSG_ASSERTION(test, \ - kunit_binary_assert, \ - KUNIT_INIT_BINARY_ASSERT_STRUCT, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) - -#define KUNIT_BINARY_GT_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\ - KUNIT_BASE_GT_MSG_ASSERTION(test, \ - kunit_binary_assert, \ - KUNIT_INIT_BINARY_ASSERT_STRUCT, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) - -#define KUNIT_BINARY_GE_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\ - KUNIT_BASE_GE_MSG_ASSERTION(test, \ - kunit_binary_assert, \ - KUNIT_INIT_BINARY_ASSERT_STRUCT, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) - #define KUNIT_BINARY_STR_ASSERTION(test, \ assert_type, \ left, \ @@ -1259,12 +1170,11 @@ do { \ KUNIT_EXPECT_LT_MSG(test, left, right, NULL) #define KUNIT_EXPECT_LT_MSG(test, left, right, fmt, ...) \ - KUNIT_BINARY_LT_MSG_ASSERTION(test, \ - KUNIT_EXPECTATION, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) + KUNIT_BINARY_INT_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, <, right, \ + fmt, \ + ##__VA_ARGS__) /** * KUNIT_EXPECT_LE() - Expects that @left is less than or equal to @right. @@ -1281,12 +1191,11 @@ do { \ KUNIT_EXPECT_LE_MSG(test, left, right, NULL) #define KUNIT_EXPECT_LE_MSG(test, left, right, fmt, ...) \ - KUNIT_BINARY_LE_MSG_ASSERTION(test, \ - KUNIT_EXPECTATION, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) + KUNIT_BINARY_INT_ASSERTION(test, \ + KUNIT_ASSERTION, \ + left, <=, right, \ + fmt, \ + ##__VA_ARGS__) /** * KUNIT_EXPECT_GT() - An expectation that @left is greater than @right. @@ -1303,12 +1212,11 @@ do { \ KUNIT_EXPECT_GT_MSG(test, left, right, NULL) #define KUNIT_EXPECT_GT_MSG(test, left, right, fmt, ...) \ - KUNIT_BINARY_GT_MSG_ASSERTION(test, \ - KUNIT_EXPECTATION, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) + KUNIT_BINARY_INT_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, >, right, \ + fmt, \ + ##__VA_ARGS__) /** * KUNIT_EXPECT_GE() - Expects that @left is greater than or equal to @right. @@ -1325,12 +1233,11 @@ do { \ KUNIT_EXPECT_GE_MSG(test, left, right, NULL) #define KUNIT_EXPECT_GE_MSG(test, left, right, fmt, ...) \ - KUNIT_BINARY_GE_MSG_ASSERTION(test, \ - KUNIT_EXPECTATION, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) + KUNIT_BINARY_INT_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, >=, right, \ + fmt, \ + ##__VA_ARGS__) /** * KUNIT_EXPECT_STREQ() - Expects that strings @left and @right are equal. @@ -1536,12 +1443,11 @@ do { \ KUNIT_ASSERT_LT_MSG(test, left, right, NULL) #define KUNIT_ASSERT_LT_MSG(test, left, right, fmt, ...) \ - KUNIT_BINARY_LT_MSG_ASSERTION(test, \ - KUNIT_ASSERTION, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) + KUNIT_BINARY_INT_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, <, right, \ + fmt, \ + ##__VA_ARGS__) /** * KUNIT_ASSERT_LE() - An assertion that @left is less than or equal to @right. * @test: The test context object. @@ -1557,12 +1463,11 @@ do { \ KUNIT_ASSERT_LE_MSG(test, left, right, NULL) #define KUNIT_ASSERT_LE_MSG(test, left, right, fmt, ...) \ - KUNIT_BINARY_LE_MSG_ASSERTION(test, \ - KUNIT_ASSERTION, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) + KUNIT_BINARY_INT_ASSERTION(test, \ + KUNIT_ASSERTION, \ + left, <=, right, \ + fmt, \ + ##__VA_ARGS__) /** * KUNIT_ASSERT_GT() - An assertion that @left is greater than @right. @@ -1579,12 +1484,11 @@ do { \ KUNIT_ASSERT_GT_MSG(test, left, right, NULL) #define KUNIT_ASSERT_GT_MSG(test, left, right, fmt, ...) \ - KUNIT_BINARY_GT_MSG_ASSERTION(test, \ - KUNIT_ASSERTION, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) + KUNIT_BINARY_INT_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, >, right, \ + fmt, \ + ##__VA_ARGS__) /** * KUNIT_ASSERT_GE() - Assertion that @left is greater than or equal to @right. @@ -1601,12 +1505,11 @@ do { \ KUNIT_ASSERT_GE_MSG(test, left, right, NULL) #define KUNIT_ASSERT_GE_MSG(test, left, right, fmt, ...) \ - KUNIT_BINARY_GE_MSG_ASSERTION(test, \ - KUNIT_ASSERTION, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) + KUNIT_BINARY_INT_ASSERTION(test, \ + KUNIT_ASSERTION, \ + left, >=, right, \ + fmt, \ + ##__VA_ARGS__) /** * KUNIT_ASSERT_STREQ() - An assertion that strings @left and @right are equal. -- cgit v1.2.3 From 6125a5c70acddd9fc1fb7329047a254c74d0173c Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Tue, 18 Jan 2022 14:35:06 -0800 Subject: kunit: decrease macro layering for EQ/NE asserts Introduce KUNIT_BINARY_PTR_ASSERTION to match KUNIT_BINARY_INT_ASSERTION and make KUNIT_EXPECT_EQ and KUNIT_EXPECT_PTREQ use these instead of shared intermediate macros that only remove the need to type "==" or "!=". The current macro chain looks like: KUNIT_EXPECT_EQ_MSG => KUNIT_BINARY_EQ_MSG_ASSERTION => KUNIT_BASE_EQ_MSG_ASSERTION => KUNIT_BASE_BINARY_ASSERTION KUNIT_EXPECT_PTR_EQ_MSG => KUNIT_BINARY_PTR_EQ_MSG_ASSERTION => KUNIT_BASE_EQ_MSG_ASSERTION => KUNIT_BASE_BINARY_ASSERTION After this change: KUNIT_EXPECT_EQ_MSG => KUNIT_BINARY_INT_ASSERTION => KUNIT_BASE_BINARY_ASSERTION KUNIT_EXPECT_PTR_EQ_MSG => KUNIT_BINARY_PTR_ASSERTION => KUNIT_BASE_BINARY_ASSERTION Signed-off-by: Daniel Latypov Reviewed-by: David Gow Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- include/kunit/test.h | 173 +++++++++++++++------------------------------------ 1 file changed, 49 insertions(+), 124 deletions(-) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index 48cf520b69ce..bf82c313223b 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -888,48 +888,6 @@ do { \ ##__VA_ARGS__); \ } while (0) -#define KUNIT_BASE_EQ_MSG_ASSERTION(test, \ - assert_class, \ - ASSERT_CLASS_INIT, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ...) \ - KUNIT_BASE_BINARY_ASSERTION(test, \ - assert_class, \ - ASSERT_CLASS_INIT, \ - assert_type, \ - left, ==, right, \ - fmt, \ - ##__VA_ARGS__) - -#define KUNIT_BASE_NE_MSG_ASSERTION(test, \ - assert_class, \ - ASSERT_CLASS_INIT, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ...) \ - KUNIT_BASE_BINARY_ASSERTION(test, \ - assert_class, \ - ASSERT_CLASS_INIT, \ - assert_type, \ - left, !=, right, \ - fmt, \ - ##__VA_ARGS__) - -#define KUNIT_BINARY_EQ_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\ - KUNIT_BASE_EQ_MSG_ASSERTION(test, \ - kunit_binary_assert, \ - KUNIT_INIT_BINARY_ASSERT_STRUCT, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) - #define KUNIT_BINARY_INT_ASSERTION(test, \ assert_type, \ left, \ @@ -945,43 +903,18 @@ do { \ fmt, \ ##__VA_ARGS__) -#define KUNIT_BINARY_PTR_EQ_MSG_ASSERTION(test, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ...) \ - KUNIT_BASE_EQ_MSG_ASSERTION(test, \ - kunit_binary_ptr_assert, \ - KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) - -#define KUNIT_BINARY_NE_MSG_ASSERTION(test, assert_type, left, right, fmt, ...)\ - KUNIT_BASE_NE_MSG_ASSERTION(test, \ - kunit_binary_assert, \ - KUNIT_INIT_BINARY_ASSERT_STRUCT, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) - -#define KUNIT_BINARY_PTR_NE_MSG_ASSERTION(test, \ - assert_type, \ - left, \ - right, \ - fmt, \ - ...) \ - KUNIT_BASE_NE_MSG_ASSERTION(test, \ +#define KUNIT_BINARY_PTR_ASSERTION(test, \ + assert_type, \ + left, \ + op, \ + right, \ + fmt, \ + ...) \ + KUNIT_BASE_BINARY_ASSERTION(test, \ kunit_binary_ptr_assert, \ KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT, \ assert_type, \ - left, \ - right, \ + left, op, right, \ fmt, \ ##__VA_ARGS__) @@ -1082,12 +1015,11 @@ do { \ KUNIT_EXPECT_EQ_MSG(test, left, right, NULL) #define KUNIT_EXPECT_EQ_MSG(test, left, right, fmt, ...) \ - KUNIT_BINARY_EQ_MSG_ASSERTION(test, \ - KUNIT_EXPECTATION, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) + KUNIT_BINARY_INT_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, ==, right, \ + fmt, \ + ##__VA_ARGS__) /** * KUNIT_EXPECT_PTR_EQ() - Expects that pointers @left and @right are equal. @@ -1104,12 +1036,11 @@ do { \ KUNIT_EXPECT_PTR_EQ_MSG(test, left, right, NULL) #define KUNIT_EXPECT_PTR_EQ_MSG(test, left, right, fmt, ...) \ - KUNIT_BINARY_PTR_EQ_MSG_ASSERTION(test, \ - KUNIT_EXPECTATION, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) + KUNIT_BINARY_PTR_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, ==, right, \ + fmt, \ + ##__VA_ARGS__) /** * KUNIT_EXPECT_NE() - An expectation that @left and @right are not equal. @@ -1126,12 +1057,11 @@ do { \ KUNIT_EXPECT_NE_MSG(test, left, right, NULL) #define KUNIT_EXPECT_NE_MSG(test, left, right, fmt, ...) \ - KUNIT_BINARY_NE_MSG_ASSERTION(test, \ - KUNIT_EXPECTATION, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) + KUNIT_BINARY_INT_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, !=, right, \ + fmt, \ + ##__VA_ARGS__) /** * KUNIT_EXPECT_PTR_NE() - Expects that pointers @left and @right are not equal. @@ -1148,12 +1078,11 @@ do { \ KUNIT_EXPECT_PTR_NE_MSG(test, left, right, NULL) #define KUNIT_EXPECT_PTR_NE_MSG(test, left, right, fmt, ...) \ - KUNIT_BINARY_PTR_NE_MSG_ASSERTION(test, \ - KUNIT_EXPECTATION, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) + KUNIT_BINARY_PTR_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + left, !=, right, \ + fmt, \ + ##__VA_ARGS__) /** * KUNIT_EXPECT_LT() - An expectation that @left is less than @right. @@ -1358,12 +1287,11 @@ do { \ KUNIT_ASSERT_EQ_MSG(test, left, right, NULL) #define KUNIT_ASSERT_EQ_MSG(test, left, right, fmt, ...) \ - KUNIT_BINARY_EQ_MSG_ASSERTION(test, \ - KUNIT_ASSERTION, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) + KUNIT_BINARY_INT_ASSERTION(test, \ + KUNIT_ASSERTION, \ + left, ==, right, \ + fmt, \ + ##__VA_ARGS__) /** * KUNIT_ASSERT_PTR_EQ() - Asserts that pointers @left and @right are equal. @@ -1379,12 +1307,11 @@ do { \ KUNIT_ASSERT_PTR_EQ_MSG(test, left, right, NULL) #define KUNIT_ASSERT_PTR_EQ_MSG(test, left, right, fmt, ...) \ - KUNIT_BINARY_PTR_EQ_MSG_ASSERTION(test, \ - KUNIT_ASSERTION, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) + KUNIT_BINARY_PTR_ASSERTION(test, \ + KUNIT_ASSERTION, \ + left, ==, right, \ + fmt, \ + ##__VA_ARGS__) /** * KUNIT_ASSERT_NE() - An assertion that @left and @right are not equal. @@ -1400,12 +1327,11 @@ do { \ KUNIT_ASSERT_NE_MSG(test, left, right, NULL) #define KUNIT_ASSERT_NE_MSG(test, left, right, fmt, ...) \ - KUNIT_BINARY_NE_MSG_ASSERTION(test, \ - KUNIT_ASSERTION, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) + KUNIT_BINARY_INT_ASSERTION(test, \ + KUNIT_ASSERTION, \ + left, !=, right, \ + fmt, \ + ##__VA_ARGS__) /** * KUNIT_ASSERT_PTR_NE() - Asserts that pointers @left and @right are not equal. @@ -1422,12 +1348,11 @@ do { \ KUNIT_ASSERT_PTR_NE_MSG(test, left, right, NULL) #define KUNIT_ASSERT_PTR_NE_MSG(test, left, right, fmt, ...) \ - KUNIT_BINARY_PTR_NE_MSG_ASSERTION(test, \ - KUNIT_ASSERTION, \ - left, \ - right, \ - fmt, \ - ##__VA_ARGS__) + KUNIT_BINARY_PTR_ASSERTION(test, \ + KUNIT_ASSERTION, \ + left, !=, right, \ + fmt, \ + ##__VA_ARGS__) /** * KUNIT_ASSERT_LT() - An assertion that @left is less than @right. * @test: The test context object. -- cgit v1.2.3 From acb13ea0baf8db8d05a3910c06e997c90825faad Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Thu, 13 Jan 2022 16:53:56 +0100 Subject: asm-generic/bitops: Always inline all bit manipulation helpers Make it consistent with the atomic/atomic-instrumented.h helpers. And defconfig size is actually going down! text data bss dec hex filename 22352096 8213152 1917164 32482412 1efa46c vmlinux.x86-64.defconfig.before 22350551 8213184 1917164 32480899 1ef9e83 vmlinux.x86-64.defconfig.after Suggested-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov Signed-off-by: Peter Zijlstra (Intel) Acked-by: Marco Elver Link: https://lore.kernel.org/r/20220113155357.4706-2-bp@alien8.de --- include/asm-generic/bitops/instrumented-atomic.h | 12 ++++++------ include/asm-generic/bitops/instrumented-non-atomic.h | 16 ++++++++-------- 2 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/asm-generic/bitops/instrumented-atomic.h b/include/asm-generic/bitops/instrumented-atomic.h index c90192b1c755..4225a8ca9c1a 100644 --- a/include/asm-generic/bitops/instrumented-atomic.h +++ b/include/asm-generic/bitops/instrumented-atomic.h @@ -23,7 +23,7 @@ * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ -static inline void set_bit(long nr, volatile unsigned long *addr) +static __always_inline void set_bit(long nr, volatile unsigned long *addr) { instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); arch_set_bit(nr, addr); @@ -36,7 +36,7 @@ static inline void set_bit(long nr, volatile unsigned long *addr) * * This is a relaxed atomic operation (no implied memory barriers). */ -static inline void clear_bit(long nr, volatile unsigned long *addr) +static __always_inline void clear_bit(long nr, volatile unsigned long *addr) { instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); arch_clear_bit(nr, addr); @@ -52,7 +52,7 @@ static inline void clear_bit(long nr, volatile unsigned long *addr) * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ -static inline void change_bit(long nr, volatile unsigned long *addr) +static __always_inline void change_bit(long nr, volatile unsigned long *addr) { instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); arch_change_bit(nr, addr); @@ -65,7 +65,7 @@ static inline void change_bit(long nr, volatile unsigned long *addr) * * This is an atomic fully-ordered operation (implied full memory barrier). */ -static inline bool test_and_set_bit(long nr, volatile unsigned long *addr) +static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr) { kcsan_mb(); instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); @@ -79,7 +79,7 @@ static inline bool test_and_set_bit(long nr, volatile unsigned long *addr) * * This is an atomic fully-ordered operation (implied full memory barrier). */ -static inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) +static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) { kcsan_mb(); instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); @@ -93,7 +93,7 @@ static inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) * * This is an atomic fully-ordered operation (implied full memory barrier). */ -static inline bool test_and_change_bit(long nr, volatile unsigned long *addr) +static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr) { kcsan_mb(); instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); diff --git a/include/asm-generic/bitops/instrumented-non-atomic.h b/include/asm-generic/bitops/instrumented-non-atomic.h index 37363d570b9b..7ab1ecc37782 100644 --- a/include/asm-generic/bitops/instrumented-non-atomic.h +++ b/include/asm-generic/bitops/instrumented-non-atomic.h @@ -22,7 +22,7 @@ * region of memory concurrently, the effect may be that only one operation * succeeds. */ -static inline void __set_bit(long nr, volatile unsigned long *addr) +static __always_inline void __set_bit(long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___set_bit(nr, addr); @@ -37,7 +37,7 @@ static inline void __set_bit(long nr, volatile unsigned long *addr) * region of memory concurrently, the effect may be that only one operation * succeeds. */ -static inline void __clear_bit(long nr, volatile unsigned long *addr) +static __always_inline void __clear_bit(long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___clear_bit(nr, addr); @@ -52,13 +52,13 @@ static inline void __clear_bit(long nr, volatile unsigned long *addr) * region of memory concurrently, the effect may be that only one operation * succeeds. */ -static inline void __change_bit(long nr, volatile unsigned long *addr) +static __always_inline void __change_bit(long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___change_bit(nr, addr); } -static inline void __instrument_read_write_bitop(long nr, volatile unsigned long *addr) +static __always_inline void __instrument_read_write_bitop(long nr, volatile unsigned long *addr) { if (IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC)) { /* @@ -90,7 +90,7 @@ static inline void __instrument_read_write_bitop(long nr, volatile unsigned long * This operation is non-atomic. If two instances of this operation race, one * can appear to succeed but actually fail. */ -static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr) +static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_set_bit(nr, addr); @@ -104,7 +104,7 @@ static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr) * This operation is non-atomic. If two instances of this operation race, one * can appear to succeed but actually fail. */ -static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr) +static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_clear_bit(nr, addr); @@ -118,7 +118,7 @@ static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr) * This operation is non-atomic. If two instances of this operation race, one * can appear to succeed but actually fail. */ -static inline bool __test_and_change_bit(long nr, volatile unsigned long *addr) +static __always_inline bool __test_and_change_bit(long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_change_bit(nr, addr); @@ -129,7 +129,7 @@ static inline bool __test_and_change_bit(long nr, volatile unsigned long *addr) * @nr: bit number to test * @addr: Address to start counting from */ -static inline bool test_bit(long nr, const volatile unsigned long *addr) +static __always_inline bool test_bit(long nr, const volatile unsigned long *addr) { instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long)); return arch_test_bit(nr, addr); -- cgit v1.2.3 From 1dc01abad6544cb9d884071b626b706e37aa9601 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Thu, 13 Jan 2022 16:53:57 +0100 Subject: cpumask: Always inline helpers which use bit manipulation functions Former are always inlined so do that for the latter too, for consistency. Size impact is a whopping 5 bytes increase! :-) text data bss dec hex filename 22350551 8213184 1917164 32480899 1ef9e83 vmlinux.x86-64.defconfig.before 22350556 8213152 1917164 32480872 1ef9e68 vmlinux.x86-64.defconfig.after Signed-off-by: Borislav Petkov Signed-off-by: Peter Zijlstra (Intel) Acked-by: Marco Elver Link: https://lore.kernel.org/r/20220113155357.4706-3-bp@alien8.de --- include/linux/cpumask.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 64dae70d31f5..6b06c698cd2a 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -341,12 +341,12 @@ extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ -static inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) +static __always_inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } -static inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) +static __always_inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { __set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } @@ -357,12 +357,12 @@ static inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ -static inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp) +static __always_inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp) { clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } -static inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) +static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) { __clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } @@ -374,7 +374,7 @@ static inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) * * Returns 1 if @cpu is set in @cpumask, else returns 0 */ -static inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask) +static __always_inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask) { return test_bit(cpumask_check(cpu), cpumask_bits((cpumask))); } @@ -388,7 +388,7 @@ static inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask) * * test_and_set_bit wrapper for cpumasks. */ -static inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) +static __always_inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) { return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } @@ -402,7 +402,7 @@ static inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) * * test_and_clear_bit wrapper for cpumasks. */ -static inline int cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) +static __always_inline int cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) { return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } -- cgit v1.2.3 From 68643c3735102177139237fd6656085eac403b69 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Tue, 25 Jan 2022 10:33:29 +0100 Subject: dt-bindings: clock: cs2000-cp: document aux-output-source This new optional property can be used to control the function of the auxiliary output pin. Introduce a new dt-bindings include file that contains the numerical values. Signed-off-by: Daniel Mack Acked-by: Rob Herring Link: https://lore.kernel.org/r/20220125093336.226787-3-daniel@zonque.org Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/cirrus,cs2000-cp.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 include/dt-bindings/clock/cirrus,cs2000-cp.h (limited to 'include') diff --git a/include/dt-bindings/clock/cirrus,cs2000-cp.h b/include/dt-bindings/clock/cirrus,cs2000-cp.h new file mode 100644 index 000000000000..fe3ac71750a8 --- /dev/null +++ b/include/dt-bindings/clock/cirrus,cs2000-cp.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (C) 2021 Daniel Mack + */ + +#ifndef __DT_BINDINGS_CS2000CP_CLK_H +#define __DT_BINDINGS_CS2000CP_CLK_H + +#define CS2000CP_AUX_OUTPUT_REF_CLK 0 +#define CS2000CP_AUX_OUTPUT_CLK_IN 1 +#define CS2000CP_AUX_OUTPUT_CLK_OUT 2 +#define CS2000CP_AUX_OUTPUT_PLL_LOCK 3 + +#endif /* __DT_BINDINGS_CS2000CP_CLK_H */ -- cgit v1.2.3 From d6dc675377261472adda696da456b4ebcc5bb9d9 Mon Sep 17 00:00:00 2001 From: Alim Akhtar Date: Mon, 24 Jan 2022 19:46:30 +0530 Subject: dt-bindings: clock: Add bindings definitions for FSD CMU blocks Clock controller driver of FSD platform is designed to have separate instances for each particular CMU. So clock IDs in this bindings header also start from 1 for each CMU block. Cc: linux-fsd@tesla.com Reported-by: kernel test robot [robot: reported missing #endif] Signed-off-by: Pankaj Dubey Signed-off-by: Alim Akhtar Reviewed-by: Krzysztof Kozlowski Acked-by: Stephen Boyd Acked-by: Sylwester Nawrocki Link: https://lore.kernel.org/r/20220124141644.71052-3-alim.akhtar@samsung.com Signed-off-by: Krzysztof Kozlowski --- include/dt-bindings/clock/fsd-clk.h | 150 ++++++++++++++++++++++++++++++++++++ 1 file changed, 150 insertions(+) create mode 100644 include/dt-bindings/clock/fsd-clk.h (limited to 'include') diff --git a/include/dt-bindings/clock/fsd-clk.h b/include/dt-bindings/clock/fsd-clk.h new file mode 100644 index 000000000000..c8a2af1dd1ad --- /dev/null +++ b/include/dt-bindings/clock/fsd-clk.h @@ -0,0 +1,150 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2017 - 2022: Samsung Electronics Co., Ltd. + * https://www.samsung.com + * Copyright (c) 2017-2022 Tesla, Inc. + * https://www.tesla.com + * + * The constants defined in this header are being used in dts + * and fsd platform driver. + */ + +#ifndef _DT_BINDINGS_CLOCK_FSD_H +#define _DT_BINDINGS_CLOCK_FSD_H + +/* CMU */ +#define DOUT_CMU_PLL_SHARED0_DIV4 1 +#define DOUT_CMU_PERIC_SHARED1DIV36 2 +#define DOUT_CMU_PERIC_SHARED0DIV3_TBUCLK 3 +#define DOUT_CMU_PERIC_SHARED0DIV20 4 +#define DOUT_CMU_PERIC_SHARED1DIV4_DMACLK 5 +#define DOUT_CMU_PLL_SHARED0_DIV6 6 +#define DOUT_CMU_FSYS0_SHARED1DIV4 7 +#define DOUT_CMU_FSYS0_SHARED0DIV4 8 +#define DOUT_CMU_FSYS1_SHARED0DIV8 9 +#define DOUT_CMU_FSYS1_SHARED0DIV4 10 +#define CMU_CPUCL_SWITCH_GATE 11 +#define DOUT_CMU_IMEM_TCUCLK 12 +#define DOUT_CMU_IMEM_ACLK 13 +#define DOUT_CMU_IMEM_DMACLK 14 +#define GAT_CMU_FSYS0_SHARED0DIV4 15 +#define CMU_NR_CLK 16 + +/* PERIC */ +#define PERIC_SCLK_UART0 1 +#define PERIC_PCLK_UART0 2 +#define PERIC_SCLK_UART1 3 +#define PERIC_PCLK_UART1 4 +#define PERIC_DMA0_IPCLKPORT_ACLK 5 +#define PERIC_DMA1_IPCLKPORT_ACLK 6 +#define PERIC_PWM0_IPCLKPORT_I_PCLK_S0 7 +#define PERIC_PWM1_IPCLKPORT_I_PCLK_S0 8 +#define PERIC_PCLK_SPI0 9 +#define PERIC_SCLK_SPI0 10 +#define PERIC_PCLK_SPI1 11 +#define PERIC_SCLK_SPI1 12 +#define PERIC_PCLK_SPI2 13 +#define PERIC_SCLK_SPI2 14 +#define PERIC_PCLK_TDM0 15 +#define PERIC_PCLK_HSI2C0 16 +#define PERIC_PCLK_HSI2C1 17 +#define PERIC_PCLK_HSI2C2 18 +#define PERIC_PCLK_HSI2C3 19 +#define PERIC_PCLK_HSI2C4 20 +#define PERIC_PCLK_HSI2C5 21 +#define PERIC_PCLK_HSI2C6 22 +#define PERIC_PCLK_HSI2C7 23 +#define PERIC_MCAN0_IPCLKPORT_CCLK 24 +#define PERIC_MCAN0_IPCLKPORT_PCLK 25 +#define PERIC_MCAN1_IPCLKPORT_CCLK 26 +#define PERIC_MCAN1_IPCLKPORT_PCLK 27 +#define PERIC_MCAN2_IPCLKPORT_CCLK 28 +#define PERIC_MCAN2_IPCLKPORT_PCLK 29 +#define PERIC_MCAN3_IPCLKPORT_CCLK 30 +#define PERIC_MCAN3_IPCLKPORT_PCLK 31 +#define PERIC_PCLK_ADCIF 32 +#define PERIC_EQOS_TOP_IPCLKPORT_CLK_PTP_REF_I 33 +#define PERIC_EQOS_TOP_IPCLKPORT_ACLK_I 34 +#define PERIC_EQOS_TOP_IPCLKPORT_HCLK_I 35 +#define PERIC_EQOS_TOP_IPCLKPORT_RGMII_CLK_I 36 +#define PERIC_EQOS_TOP_IPCLKPORT_CLK_RX_I 37 +#define PERIC_BUS_D_PERIC_IPCLKPORT_EQOSCLK 38 +#define PERIC_BUS_P_PERIC_IPCLKPORT_EQOSCLK 39 +#define PERIC_HCLK_TDM0 40 +#define PERIC_PCLK_TDM1 41 +#define PERIC_HCLK_TDM1 42 +#define PERIC_EQOS_PHYRXCLK_MUX 43 +#define PERIC_EQOS_PHYRXCLK 44 +#define PERIC_DOUT_RGMII_CLK 45 +#define PERIC_NR_CLK 46 + +/* FSYS0 */ +#define UFS0_MPHY_REFCLK_IXTAL24 1 +#define UFS0_MPHY_REFCLK_IXTAL26 2 +#define UFS1_MPHY_REFCLK_IXTAL24 3 +#define UFS1_MPHY_REFCLK_IXTAL26 4 +#define UFS0_TOP0_HCLK_BUS 5 +#define UFS0_TOP0_ACLK 6 +#define UFS0_TOP0_CLK_UNIPRO 7 +#define UFS0_TOP0_FMP_CLK 8 +#define UFS1_TOP1_HCLK_BUS 9 +#define UFS1_TOP1_ACLK 10 +#define UFS1_TOP1_CLK_UNIPRO 11 +#define UFS1_TOP1_FMP_CLK 12 +#define PCIE_SUBCTRL_INST0_DBI_ACLK_SOC 13 +#define PCIE_SUBCTRL_INST0_AUX_CLK_SOC 14 +#define PCIE_SUBCTRL_INST0_MSTR_ACLK_SOC 15 +#define PCIE_SUBCTRL_INST0_SLV_ACLK_SOC 16 +#define FSYS0_EQOS_TOP0_IPCLKPORT_CLK_PTP_REF_I 17 +#define FSYS0_EQOS_TOP0_IPCLKPORT_ACLK_I 18 +#define FSYS0_EQOS_TOP0_IPCLKPORT_HCLK_I 19 +#define FSYS0_EQOS_TOP0_IPCLKPORT_RGMII_CLK_I 20 +#define FSYS0_EQOS_TOP0_IPCLKPORT_CLK_RX_I 21 +#define FSYS0_DOUT_FSYS0_PERIBUS_GRP 22 +#define FSYS0_NR_CLK 23 + +/* FSYS1 */ +#define PCIE_LINK0_IPCLKPORT_DBI_ACLK 1 +#define PCIE_LINK0_IPCLKPORT_AUX_ACLK 2 +#define PCIE_LINK0_IPCLKPORT_MSTR_ACLK 3 +#define PCIE_LINK0_IPCLKPORT_SLV_ACLK 4 +#define PCIE_LINK1_IPCLKPORT_DBI_ACLK 5 +#define PCIE_LINK1_IPCLKPORT_AUX_ACLK 6 +#define PCIE_LINK1_IPCLKPORT_MSTR_ACLK 7 +#define PCIE_LINK1_IPCLKPORT_SLV_ACLK 8 +#define FSYS1_NR_CLK 9 + +/* IMEM */ +#define IMEM_DMA0_IPCLKPORT_ACLK 1 +#define IMEM_DMA1_IPCLKPORT_ACLK 2 +#define IMEM_WDT0_IPCLKPORT_PCLK 3 +#define IMEM_WDT1_IPCLKPORT_PCLK 4 +#define IMEM_WDT2_IPCLKPORT_PCLK 5 +#define IMEM_MCT_PCLK 6 +#define IMEM_TMU_CPU0_IPCLKPORT_I_CLK_TS 7 +#define IMEM_TMU_CPU2_IPCLKPORT_I_CLK_TS 8 +#define IMEM_TMU_TOP_IPCLKPORT_I_CLK_TS 9 +#define IMEM_TMU_GPU_IPCLKPORT_I_CLK_TS 10 +#define IMEM_TMU_GT_IPCLKPORT_I_CLK_TS 11 +#define IMEM_NR_CLK 12 + +/* MFC */ +#define MFC_MFC_IPCLKPORT_ACLK 1 +#define MFC_NR_CLK 2 + +/* CAM_CSI */ +#define CAM_CSI0_0_IPCLKPORT_I_ACLK 1 +#define CAM_CSI0_1_IPCLKPORT_I_ACLK 2 +#define CAM_CSI0_2_IPCLKPORT_I_ACLK 3 +#define CAM_CSI0_3_IPCLKPORT_I_ACLK 4 +#define CAM_CSI1_0_IPCLKPORT_I_ACLK 5 +#define CAM_CSI1_1_IPCLKPORT_I_ACLK 6 +#define CAM_CSI1_2_IPCLKPORT_I_ACLK 7 +#define CAM_CSI1_3_IPCLKPORT_I_ACLK 8 +#define CAM_CSI2_0_IPCLKPORT_I_ACLK 9 +#define CAM_CSI2_1_IPCLKPORT_I_ACLK 10 +#define CAM_CSI2_2_IPCLKPORT_I_ACLK 11 +#define CAM_CSI2_3_IPCLKPORT_I_ACLK 12 +#define CAM_CSI_NR_CLK 13 + +#endif /*_DT_BINDINGS_CLOCK_FSD_H */ -- cgit v1.2.3 From be6ec5b7026620b931e0fa9287d24ad2cd2ab9b6 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Wed, 26 Jan 2022 10:25:55 +0000 Subject: net: xpcs: add support for retrieving supported interface modes Add a function to the xpcs driver to retrieve the supported PHY interface modes, which can be used by drivers to fill in phylink's supported_interfaces mask. We validate the interface bit index to ensure that it fits within the bitmap as xpcs lists PHY_INTERFACE_MODE_MAX in an entry. Tested-by: Wong Vee Khee # Intel EHL Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- include/linux/pcs/pcs-xpcs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index add077a81b21..3126a4924d92 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -33,6 +33,7 @@ int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, unsigned int mode); void xpcs_validate(struct dw_xpcs *xpcs, unsigned long *supported, struct phylink_link_state *state); +void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces); int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable); struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, -- cgit v1.2.3 From fe70fb74b56407c1a5be347258082f8abbe7956d Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Wed, 26 Jan 2022 10:26:10 +0000 Subject: net: stmmac/xpcs: convert to pcs_validate() stmmac explicitly calls the xpcs driver to validate the ethtool linkmodes. This is no longer necessary as phylink now supports validation through a PCS method. Convert both drivers to use this new mechanism. Tested-by: Wong Vee Khee # Intel EHL Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- include/linux/pcs/pcs-xpcs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 3126a4924d92..266eb26fb029 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -31,8 +31,6 @@ void xpcs_link_up(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, int speed, int duplex); int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, unsigned int mode); -void xpcs_validate(struct dw_xpcs *xpcs, unsigned long *supported, - struct phylink_link_state *state); void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces); int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable); -- cgit v1.2.3 From f383b0770612838e78986231710c0a3afee4db42 Mon Sep 17 00:00:00 2001 From: Sergio Paracuellos Date: Mon, 10 Jan 2022 12:49:27 +0100 Subject: dt-bindings: reset: add dt binding header for Mediatek MT7621 resets MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add dt binding header for resets lines in Mediatek MT7621 SoCs. Acked-by: Rob Herring Tested-by: Arınç ÜNAL Signed-off-by: Sergio Paracuellos Link: https://lore.kernel.org/r/20220110114930.1406665-2-sergio.paracuellos@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/dt-bindings/reset/mt7621-reset.h | 37 ++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) create mode 100644 include/dt-bindings/reset/mt7621-reset.h (limited to 'include') diff --git a/include/dt-bindings/reset/mt7621-reset.h b/include/dt-bindings/reset/mt7621-reset.h new file mode 100644 index 000000000000..7572c6b41453 --- /dev/null +++ b/include/dt-bindings/reset/mt7621-reset.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2021 Sergio Paracuellos + * Author: Sergio Paracuellos + */ + +#ifndef DT_BINDING_MT7621_RESET_H +#define DT_BINDING_MT7621_RESET_H + +#define MT7621_RST_SYS 0 +#define MT7621_RST_MCM 2 +#define MT7621_RST_HSDMA 5 +#define MT7621_RST_FE 6 +#define MT7621_RST_SPDIFTX 7 +#define MT7621_RST_TIMER 8 +#define MT7621_RST_INT 9 +#define MT7621_RST_MC 10 +#define MT7621_RST_PCM 11 +#define MT7621_RST_PIO 13 +#define MT7621_RST_GDMA 14 +#define MT7621_RST_NFI 15 +#define MT7621_RST_I2C 16 +#define MT7621_RST_I2S 17 +#define MT7621_RST_SPI 18 +#define MT7621_RST_UART1 19 +#define MT7621_RST_UART2 20 +#define MT7621_RST_UART3 21 +#define MT7621_RST_ETH 23 +#define MT7621_RST_PCIE0 24 +#define MT7621_RST_PCIE1 25 +#define MT7621_RST_PCIE2 26 +#define MT7621_RST_AUX_STCK 28 +#define MT7621_RST_CRYPTO 29 +#define MT7621_RST_SDXC 30 +#define MT7621_RST_PPE 31 + +#endif /* DT_BINDING_MT7621_RESET_H */ -- cgit v1.2.3 From 4e2a44c1408b6a6a46122704511234f68cf012b8 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Mon, 24 Jan 2022 08:14:22 +0100 Subject: tty: add kfifo to tty_port Define a kfifo inside struct tty_port. We use DECLARE_KFIFO_PTR and let the preexisting tty_port::xmit_buf be also the buffer for the kfifo. And handle the initialization/decomissioning along with xmit_buf, i.e. in tty_port_alloc_xmit_buf() and tty_port_free_xmit_buf(), respectively. This allows for kfifo use in drivers which opt-in, while others still may use the old xmit_buf. mxser will be the first user in the next few patches. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20220124071430.14907-4-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_port.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/tty_port.h b/include/linux/tty_port.h index d3ea9ed0b98e..58e9619116b7 100644 --- a/include/linux/tty_port.h +++ b/include/linux/tty_port.h @@ -2,6 +2,7 @@ #ifndef _LINUX_TTY_PORT_H #define _LINUX_TTY_PORT_H +#include #include #include #include @@ -67,6 +68,7 @@ extern const struct tty_port_client_operations tty_port_default_client_ops; * @mutex: locking, for open, shutdown and other port operations * @buf_mutex: @xmit_buf alloc lock * @xmit_buf: optional xmit buffer used by some drivers + * @xmit_fifo: optional xmit buffer used by some drivers * @close_delay: delay in jiffies to wait when closing the port * @closing_wait: delay in jiffies for output to be sent before closing * @drain_delay: set to zero if no pure time based drain is needed else set to @@ -110,6 +112,7 @@ struct tty_port { struct mutex mutex; struct mutex buf_mutex; unsigned char *xmit_buf; + DECLARE_KFIFO_PTR(xmit_fifo, unsigned char); unsigned int close_delay; unsigned int closing_wait; int drain_delay; -- cgit v1.2.3 From de3688e469b08be958914674e8b01cb0cea42388 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Fri, 9 Jul 2021 15:18:39 +0200 Subject: drm/ttm: add ttm_resource_fini v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Make sure we call the common cleanup function in all implementations of the resource manager. v2: fix missing case in i915, rudimentary kerneldoc, should be filled in more when we add more functionality Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220124122514.1832-2-christian.koenig@amd.com --- include/drm/ttm/ttm_resource.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index 5952051091cd..df1f06b7b504 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -261,6 +261,9 @@ ttm_resource_manager_cleanup(struct ttm_resource_manager *man) void ttm_resource_init(struct ttm_buffer_object *bo, const struct ttm_place *place, struct ttm_resource *res); +void ttm_resource_fini(struct ttm_resource_manager *man, + struct ttm_resource *res); + int ttm_resource_alloc(struct ttm_buffer_object *bo, const struct ttm_place *place, struct ttm_resource **res); -- cgit v1.2.3 From 3f268ef06f8cf3c481dbd5843d564f5170c6df54 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Mon, 30 Aug 2021 09:22:06 +0200 Subject: drm/ttm: add back a reference to the bdev to the res manager MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It is simply a lot cleaner to have this around instead of adding the device throughout the call chain. Signed-off-by: Christian König Reviewed-by: Huang Rui Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220124122514.1832-3-christian.koenig@amd.com --- include/drm/ttm/ttm_resource.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index df1f06b7b504..6bf37383002b 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -105,11 +105,11 @@ struct ttm_resource_manager_func { * @use_type: The memory type is enabled. * @use_tt: If a TT object should be used for the backing store. * @size: Size of the managed region. + * @bdev: ttm device this manager belongs to * @func: structure pointer implementing the range manager. See above * @move_lock: lock for move fence - * static information. bdev::driver::io_mem_free is never used. - * @lru: The lru list for this memory type. * @move: The fence of the last pipelined move operation. + * @lru: The lru list for this memory type. * * This structure is used to identify and manage memory types for a device. */ @@ -119,20 +119,21 @@ struct ttm_resource_manager { */ bool use_type; bool use_tt; + struct ttm_device *bdev; uint64_t size; const struct ttm_resource_manager_func *func; spinlock_t move_lock; /* - * Protected by the global->lru_lock. + * Protected by @move_lock. */ - - struct list_head lru[TTM_MAX_BO_PRIORITY]; + struct dma_fence *move; /* - * Protected by @move_lock. + * Protected by the global->lru_lock. */ - struct dma_fence *move; + + struct list_head lru[TTM_MAX_BO_PRIORITY]; }; /** @@ -272,6 +273,7 @@ bool ttm_resource_compat(struct ttm_resource *res, struct ttm_placement *placement); void ttm_resource_manager_init(struct ttm_resource_manager *man, + struct ttm_device *bdev, unsigned long p_size); int ttm_resource_manager_evict_all(struct ttm_device *bdev, -- cgit v1.2.3 From fda8d552c9c7783d4b29aeb6350d7404b31cdbff Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Thu, 15 Jul 2021 14:17:19 +0200 Subject: drm/ttm: add a weak BO reference to the resource v3 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Keep track for which BO a resource was allocated. This is necessary to move the LRU handling into the resources. A bit problematic is i915 since it tries to use the resource interface without a BO which is illegal from the conceptional point of view. v2: Document that this is a weak reference and add a workaround for i915 v3: further document that this is protected by ttm_device::lru_lock and clarify the i915 workaround Signed-off-by: Christian König Acked-by: Huang Rui Link: https://patchwork.freedesktop.org/patch/msgid/20220124122514.1832-4-christian.koenig@amd.com --- include/drm/ttm/ttm_resource.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index 6bf37383002b..69eea9d6399b 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -161,6 +161,7 @@ struct ttm_bus_placement { * @mem_type: Resource type of the allocation. * @placement: Placement flags. * @bus: Placement on io bus accessible to the CPU + * @bo: weak reference to the BO, protected by ttm_device::lru_lock * * Structure indicating the placement and space resources used by a * buffer object. @@ -171,6 +172,7 @@ struct ttm_resource { uint32_t mem_type; uint32_t placement; struct ttm_bus_placement bus; + struct ttm_buffer_object *bo; }; /** @@ -271,6 +273,8 @@ int ttm_resource_alloc(struct ttm_buffer_object *bo, void ttm_resource_free(struct ttm_buffer_object *bo, struct ttm_resource **res); bool ttm_resource_compat(struct ttm_resource *res, struct ttm_placement *placement); +void ttm_resource_set_bo(struct ttm_resource *res, + struct ttm_buffer_object *bo); void ttm_resource_manager_init(struct ttm_resource_manager *man, struct ttm_device *bdev, -- cgit v1.2.3 From 597568e8df046ebf349c706b281a711297ab20fb Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Tue, 25 Jan 2022 13:50:07 +0800 Subject: misc: rtsx: Rework runtime power management flow Commit 5b4258f6721f ("misc: rtsx: rts5249 support runtime PM") uses "rtd3_work" and "idle_work" to manage it's own runtime PM state machine. When its child device, rtsx_pci_sdmmc, uses runtime PM refcount correctly, all the additional works can be managed by generic runtime PM helpers. So consolidate "idle_work" and "rtd3_work" into generic runtime idle callback and runtime suspend callback, respectively. Fixes: 5b4258f6721f ("misc: rtsx: rts5249 support runtime PM") Cc: Ricky WU Tested-by: Ricky WU Signed-off-by: Kai-Heng Feng Link: https://lore.kernel.org/r/20220125055010.1866563-2-kai.heng.feng@canonical.com Signed-off-by: Greg Kroah-Hartman --- include/linux/rtsx_pci.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h index 4ab7bfc675f1..89b7d34e25b6 100644 --- a/include/linux/rtsx_pci.h +++ b/include/linux/rtsx_pci.h @@ -1201,8 +1201,6 @@ struct rtsx_pcr { unsigned int card_exist; struct delayed_work carddet_work; - struct delayed_work idle_work; - struct delayed_work rtd3_work; spinlock_t lock; struct mutex pcr_mutex; @@ -1212,7 +1210,6 @@ struct rtsx_pcr { unsigned int cur_clock; bool remove_pci; bool msi_en; - bool is_runtime_suspended; #define EXTRA_CAPS_SD_SDR50 (1 << 0) #define EXTRA_CAPS_SD_SDR104 (1 << 1) -- cgit v1.2.3 From 71732e24609b5a7af96efc89aebde55f76c1de3e Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Tue, 25 Jan 2022 13:50:09 +0800 Subject: misc: rtsx: Quiesce rts5249 on system suspend Set more registers in force_power_down callback to avoid S3 wakeup from hotplugging cards. This is originally written by Ricky WU. Link: https://lore.kernel.org/lkml/c4525b4738f94483b9b8f8571fc80646@realtek.com/ Cc: Ricky WU Tested-by: Ricky WU Signed-off-by: Kai-Heng Feng Link: https://lore.kernel.org/r/20220125055010.1866563-4-kai.heng.feng@canonical.com Signed-off-by: Greg Kroah-Hartman --- include/linux/rtsx_pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h index 89b7d34e25b6..3d780b44e678 100644 --- a/include/linux/rtsx_pci.h +++ b/include/linux/rtsx_pci.h @@ -1095,7 +1095,7 @@ struct pcr_ops { unsigned int (*cd_deglitch)(struct rtsx_pcr *pcr); int (*conv_clk_and_div_n)(int clk, int dir); void (*fetch_vendor_settings)(struct rtsx_pcr *pcr); - void (*force_power_down)(struct rtsx_pcr *pcr, u8 pm_state); + void (*force_power_down)(struct rtsx_pcr *pcr, u8 pm_state, bool runtime); void (*stop_cmd)(struct rtsx_pcr *pcr); void (*set_aspm)(struct rtsx_pcr *pcr, bool enable); -- cgit v1.2.3 From fbb8295248e1d6f576d444309fcf79356008eac1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 26 Jan 2022 10:07:14 -0800 Subject: tcp: allocate tcp_death_row outside of struct netns_ipv4 I forgot tcp had per netns tracking of timewait sockets, and their sysctl to change the limit. After 0dad4087a86a ("tcp/dccp: get rid of inet_twsk_purge()"), whole struct net can be freed before last tw socket is freed. We need to allocate a separate struct inet_timewait_death_row object per netns. tw_count becomes a refcount and gains associated debugging infrastructure. BUG: KASAN: use-after-free in inet_twsk_kill+0x358/0x3c0 net/ipv4/inet_timewait_sock.c:46 Read of size 8 at addr ffff88807d5f9f40 by task kworker/1:7/3690 CPU: 1 PID: 3690 Comm: kworker/1:7 Not tainted 5.16.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: events pwq_unbound_release_workfn Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_address_description.constprop.0.cold+0x8d/0x336 mm/kasan/report.c:255 __kasan_report mm/kasan/report.c:442 [inline] kasan_report.cold+0x83/0xdf mm/kasan/report.c:459 inet_twsk_kill+0x358/0x3c0 net/ipv4/inet_timewait_sock.c:46 call_timer_fn+0x1a5/0x6b0 kernel/time/timer.c:1421 expire_timers kernel/time/timer.c:1466 [inline] __run_timers.part.0+0x67c/0xa30 kernel/time/timer.c:1734 __run_timers kernel/time/timer.c:1715 [inline] run_timer_softirq+0xb3/0x1d0 kernel/time/timer.c:1747 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558 invoke_softirq kernel/softirq.c:432 [inline] __irq_exit_rcu+0x123/0x180 kernel/softirq.c:637 irq_exit_rcu+0x5/0x20 kernel/softirq.c:649 sysvec_apic_timer_interrupt+0x93/0xc0 arch/x86/kernel/apic/apic.c:1097 asm_sysvec_apic_timer_interrupt+0x12/0x20 arch/x86/include/asm/idtentry.h:638 RIP: 0010:lockdep_unregister_key+0x1c9/0x250 kernel/locking/lockdep.c:6328 Code: 00 00 00 48 89 ee e8 46 fd ff ff 4c 89 f7 e8 5e c9 ff ff e8 09 cc ff ff 9c 58 f6 c4 02 75 26 41 f7 c4 00 02 00 00 74 01 fb 5b <5d> 41 5c 41 5d 41 5e 41 5f e9 19 4a 08 00 0f 0b 5b 5d 41 5c 41 5d RSP: 0018:ffffc90004077cb8 EFLAGS: 00000206 RAX: 0000000000000046 RBX: ffff88807b61b498 RCX: 0000000000000001 RDX: dffffc0000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffff888077027128 R08: 0000000000000001 R09: ffffffff8f1ea4fc R10: fffffbfff1ff93ee R11: 000000000000af1e R12: 0000000000000246 R13: 0000000000000000 R14: ffffffff8ffc89b8 R15: ffffffff90157fb0 wq_unregister_lockdep kernel/workqueue.c:3508 [inline] pwq_unbound_release_workfn+0x254/0x340 kernel/workqueue.c:3746 process_one_work+0x9ac/0x1650 kernel/workqueue.c:2307 worker_thread+0x657/0x1110 kernel/workqueue.c:2454 kthread+0x2e9/0x3a0 kernel/kthread.c:377 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:295 Allocated by task 3635: kasan_save_stack+0x1e/0x50 mm/kasan/common.c:38 kasan_set_track mm/kasan/common.c:46 [inline] set_alloc_info mm/kasan/common.c:437 [inline] __kasan_slab_alloc+0x90/0xc0 mm/kasan/common.c:470 kasan_slab_alloc include/linux/kasan.h:260 [inline] slab_post_alloc_hook mm/slab.h:732 [inline] slab_alloc_node mm/slub.c:3230 [inline] slab_alloc mm/slub.c:3238 [inline] kmem_cache_alloc+0x202/0x3a0 mm/slub.c:3243 kmem_cache_zalloc include/linux/slab.h:705 [inline] net_alloc net/core/net_namespace.c:407 [inline] copy_net_ns+0x125/0x760 net/core/net_namespace.c:462 create_new_namespaces+0x3f6/0xb20 kernel/nsproxy.c:110 unshare_nsproxy_namespaces+0xc1/0x1f0 kernel/nsproxy.c:226 ksys_unshare+0x445/0x920 kernel/fork.c:3048 __do_sys_unshare kernel/fork.c:3119 [inline] __se_sys_unshare kernel/fork.c:3117 [inline] __x64_sys_unshare+0x2d/0x40 kernel/fork.c:3117 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae The buggy address belongs to the object at ffff88807d5f9a80 which belongs to the cache net_namespace of size 6528 The buggy address is located 1216 bytes inside of 6528-byte region [ffff88807d5f9a80, ffff88807d5fb400) The buggy address belongs to the page: page:ffffea0001f57e00 refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff88807d5f9a80 pfn:0x7d5f8 head:ffffea0001f57e00 order:3 compound_mapcount:0 compound_pincount:0 memcg:ffff888070023001 flags: 0xfff00000010200(slab|head|node=0|zone=1|lastcpupid=0x7ff) raw: 00fff00000010200 ffff888010dd4f48 ffffea0001404e08 ffff8880118fd000 raw: ffff88807d5f9a80 0000000000040002 00000001ffffffff ffff888070023001 page dumped because: kasan: bad access detected page_owner tracks the page as allocated page last allocated via order 3, migratetype Unmovable, gfp_mask 0xd20c0(__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC), pid 3634, ts 119694798460, free_ts 119693556950 prep_new_page mm/page_alloc.c:2434 [inline] get_page_from_freelist+0xa72/0x2f50 mm/page_alloc.c:4165 __alloc_pages+0x1b2/0x500 mm/page_alloc.c:5389 alloc_pages+0x1aa/0x310 mm/mempolicy.c:2271 alloc_slab_page mm/slub.c:1799 [inline] allocate_slab mm/slub.c:1944 [inline] new_slab+0x28a/0x3b0 mm/slub.c:2004 ___slab_alloc+0x87c/0xe90 mm/slub.c:3018 __slab_alloc.constprop.0+0x4d/0xa0 mm/slub.c:3105 slab_alloc_node mm/slub.c:3196 [inline] slab_alloc mm/slub.c:3238 [inline] kmem_cache_alloc+0x35c/0x3a0 mm/slub.c:3243 kmem_cache_zalloc include/linux/slab.h:705 [inline] net_alloc net/core/net_namespace.c:407 [inline] copy_net_ns+0x125/0x760 net/core/net_namespace.c:462 create_new_namespaces+0x3f6/0xb20 kernel/nsproxy.c:110 unshare_nsproxy_namespaces+0xc1/0x1f0 kernel/nsproxy.c:226 ksys_unshare+0x445/0x920 kernel/fork.c:3048 __do_sys_unshare kernel/fork.c:3119 [inline] __se_sys_unshare kernel/fork.c:3117 [inline] __x64_sys_unshare+0x2d/0x40 kernel/fork.c:3117 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae page last free stack trace: reset_page_owner include/linux/page_owner.h:24 [inline] free_pages_prepare mm/page_alloc.c:1352 [inline] free_pcp_prepare+0x374/0x870 mm/page_alloc.c:1404 free_unref_page_prepare mm/page_alloc.c:3325 [inline] free_unref_page+0x19/0x690 mm/page_alloc.c:3404 skb_free_head net/core/skbuff.c:655 [inline] skb_release_data+0x65d/0x790 net/core/skbuff.c:677 skb_release_all net/core/skbuff.c:742 [inline] __kfree_skb net/core/skbuff.c:756 [inline] consume_skb net/core/skbuff.c:914 [inline] consume_skb+0xc2/0x160 net/core/skbuff.c:908 skb_free_datagram+0x1b/0x1f0 net/core/datagram.c:325 netlink_recvmsg+0x636/0xea0 net/netlink/af_netlink.c:1998 sock_recvmsg_nosec net/socket.c:948 [inline] sock_recvmsg net/socket.c:966 [inline] sock_recvmsg net/socket.c:962 [inline] ____sys_recvmsg+0x2c4/0x600 net/socket.c:2632 ___sys_recvmsg+0x127/0x200 net/socket.c:2674 __sys_recvmsg+0xe2/0x1a0 net/socket.c:2704 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae Memory state around the buggy address: ffff88807d5f9e00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88807d5f9e80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff88807d5f9f00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff88807d5f9f80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88807d5fa000: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: 0dad4087a86a ("tcp/dccp: get rid of inet_twsk_purge()") Signed-off-by: Eric Dumazet Reported-by: syzbot Reported-by: Paolo Abeni Tested-by: Paolo Abeni Link: https://lore.kernel.org/r/20220126180714.845362-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/net/netns/ipv4.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 22b4c6df1d2b..94568e022001 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -31,18 +31,16 @@ struct ping_group_range { struct inet_hashinfo; struct inet_timewait_death_row { - atomic_t tw_count; - char tw_pad[L1_CACHE_BYTES - sizeof(atomic_t)]; + refcount_t tw_refcount; - struct inet_hashinfo *hashinfo; + struct inet_hashinfo *hashinfo ____cacheline_aligned_in_smp; int sysctl_max_tw_buckets; }; struct tcp_fastopen_context; struct netns_ipv4 { - /* Please keep tcp_death_row at first field in netns_ipv4 */ - struct inet_timewait_death_row tcp_death_row ____cacheline_aligned_in_smp; + struct inet_timewait_death_row *tcp_death_row; #ifdef CONFIG_SYSCTL struct ctl_table_header *forw_hdr; -- cgit v1.2.3 From 8033c6c2fed235b3d571b5a5ede302b752bc5c7d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 26 Jan 2022 10:54:12 -0800 Subject: bpf: remove unused static inlines Remove two dead stubs, sk_msg_clear_meta() was never used, use of xskq_cons_is_full() got replaced by xsk_tx_writeable() in v5.10. Signed-off-by: Jakub Kicinski Link: https://lore.kernel.org/r/20220126185412.2776254-1-kuba@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 10 ---------- include/linux/skmsg.h | 5 ----- 2 files changed, 15 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 394305a5e02f..2344f793c4dc 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1875,11 +1875,6 @@ static inline int bpf_obj_get_user(const char __user *pathname, int flags) return -EOPNOTSUPP; } -static inline bool dev_map_can_have_prog(struct bpf_map *map) -{ - return false; -} - static inline void __dev_flush(void) { } @@ -1943,11 +1938,6 @@ static inline int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, return -EOPNOTSUPP; } -static inline bool cpu_map_prog_allowed(struct bpf_map *map) -{ - return false; -} - static inline struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type) { diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 18a717fe62eb..ddde5f620901 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -171,11 +171,6 @@ static inline u32 sk_msg_iter_dist(u32 start, u32 end) #define sk_msg_iter_next(msg, which) \ sk_msg_iter_var_next(msg->sg.which) -static inline void sk_msg_clear_meta(struct sk_msg *msg) -{ - memset(&msg->sg, 0, offsetofend(struct sk_msg_sg, copy)); -} - static inline void sk_msg_init(struct sk_msg *msg) { BUILD_BUG_ON(ARRAY_SIZE(msg->sg.data) - 1 != NR_MSG_FRAG_IDS); -- cgit v1.2.3 From 27599aacbaefcbf2af7b06b0029459bbf682000d Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Tue, 25 Jan 2022 10:12:18 +0100 Subject: fbdev: Hot-unplug firmware fb devices on forced removal Hot-unplug all firmware-framebuffer devices as part of removing them via remove_conflicting_framebuffers() et al. Releases all memory regions to be acquired by native drivers. Firmware, such as EFI, install a framebuffer while posting the computer. After removing the firmware-framebuffer device from fbdev, a native driver takes over the hardware and the firmware framebuffer becomes invalid. Firmware-framebuffer drivers, specifically simplefb, don't release their device from Linux' device hierarchy. It still owns the firmware framebuffer and blocks the native drivers from loading. This has been observed in the vmwgfx driver. [1] Initiating a device removal (i.e., hot unplug) as part of remove_conflicting_framebuffers() removes the underlying device and returns the memory range to the system. [1] https://lore.kernel.org/dri-devel/20220117180359.18114-1-zack@kde.org/ v2: * rename variable 'dev' to 'device' (Javier) Signed-off-by: Thomas Zimmermann Reported-by: Zack Rusin Reviewed-by: Javier Martinez Canillas Reviewed-by: Zack Rusin Reviewed-by: Hans de Goede CC: stable@vger.kernel.org # v5.11+ Link: https://patchwork.freedesktop.org/patch/msgid/20220125091222.21457-2-tzimmermann@suse.de --- include/linux/fb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fb.h b/include/linux/fb.h index 6f3db99ab990..ac294fc4c07b 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -502,6 +502,7 @@ struct fb_info { } *apertures; bool skip_vt_switch; /* no VT switch on suspend/resume required */ + bool forced_out; /* set when being removed by another driver */ }; static inline struct apertures_struct *alloc_apertures(unsigned int max_num) { -- cgit v1.2.3 From ec2444530612a886b406e2830d7f314d1a07d4bb Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Wed, 19 Jan 2022 14:39:39 -0800 Subject: psi: Fix "no previous prototype" warnings when CONFIG_CGROUPS=n When CONFIG_CGROUPS is disabled psi code generates the following warnings: kernel/sched/psi.c:1112:21: warning: no previous prototype for 'psi_trigger_create' [-Wmissing-prototypes] 1112 | struct psi_trigger *psi_trigger_create(struct psi_group *group, | ^~~~~~~~~~~~~~~~~~ kernel/sched/psi.c:1182:6: warning: no previous prototype for 'psi_trigger_destroy' [-Wmissing-prototypes] 1182 | void psi_trigger_destroy(struct psi_trigger *t) | ^~~~~~~~~~~~~~~~~~~ kernel/sched/psi.c:1249:10: warning: no previous prototype for 'psi_trigger_poll' [-Wmissing-prototypes] 1249 | __poll_t psi_trigger_poll(void **trigger_ptr, | ^~~~~~~~~~~~~~~~ Change declarations of these functions in the header to provide the prototypes even when they are unused. Fixes: 0e94682b73bf ("psi: introduce psi monitor") Reported-by: kernel test robot Signed-off-by: Suren Baghdasaryan Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20220119223940.787748-2-surenb@google.com --- include/linux/psi.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/psi.h b/include/linux/psi.h index a70ca833c6d7..827970278d62 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -25,18 +25,17 @@ void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags); int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); - -#ifdef CONFIG_CGROUPS -int psi_cgroup_alloc(struct cgroup *cgrp); -void psi_cgroup_free(struct cgroup *cgrp); -void cgroup_move_task(struct task_struct *p, struct css_set *to); - struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, size_t nbytes, enum psi_res res); void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *t); __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, poll_table *wait); + +#ifdef CONFIG_CGROUPS +int psi_cgroup_alloc(struct cgroup *cgrp); +void psi_cgroup_free(struct cgroup *cgrp); +void cgroup_move_task(struct task_struct *p, struct css_set *to); #endif #else /* CONFIG_PSI */ -- cgit v1.2.3 From 2e9589ff809e9232f689acd51da73390e135146a Mon Sep 17 00:00:00 2001 From: xu xin Date: Wed, 26 Jan 2022 07:10:58 +0000 Subject: ipv4: Namespaceify min_adv_mss sysctl knob Different netns has different requirement on the setting of min_adv_mss sysctl which the advertised MSS will be never lower than. Enable min_adv_mss to be configured per network namespace. Signed-off-by: xu xin Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 94568e022001..f0687867b5cd 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -83,6 +83,7 @@ struct netns_ipv4 { u32 ip_rt_min_pmtu; int ip_rt_mtu_expires; + int ip_rt_min_advmss; struct local_ports ip_local_ports; -- cgit v1.2.3 From bd5daba2d02479729526d35de85807aadf6fba20 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 26 Jan 2022 11:10:55 -0800 Subject: mii: remove mii_lpa_to_linkmode_lpa_sgmii() The only caller of mii_lpa_to_linkmode_lpa_sgmii() disappeared in v5.10. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/mii.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include') diff --git a/include/linux/mii.h b/include/linux/mii.h index 12ea29e04293..b8a1a17a87dd 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -387,23 +387,6 @@ mii_lpa_mod_linkmode_lpa_sgmii(unsigned long *lp_advertising, u32 lpa) speed_duplex == LPA_SGMII_10FULL); } -/** - * mii_lpa_to_linkmode_adv_sgmii - * @advertising: pointer to destination link mode. - * @lpa: value of the MII_LPA register - * - * A small helper function that translates MII_ADVERTISE bits - * to linkmode advertisement settings when in SGMII mode. - * Clears the old value of advertising. - */ -static inline void mii_lpa_to_linkmode_lpa_sgmii(unsigned long *lp_advertising, - u32 lpa) -{ - linkmode_zero(lp_advertising); - - mii_lpa_mod_linkmode_lpa_sgmii(lp_advertising, lpa); -} - /** * mii_adv_mod_linkmode_adv_t * @advertising:pointer to destination link mode. -- cgit v1.2.3 From b1755400b4be33dbd286272b153579631be2e2ca Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 26 Jan 2022 11:10:57 -0800 Subject: net: remove net_invalid_timestamp() No callers since v3.15. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 8131d0de7559..60bd2347708c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3899,11 +3899,6 @@ static inline ktime_t net_timedelta(ktime_t t) return ktime_sub(ktime_get_real(), t); } -static inline ktime_t net_invalid_timestamp(void) -{ - return 0; -} - static inline u8 skb_metadata_len(const struct sk_buff *skb) { return skb_shinfo(skb)->meta_len; -- cgit v1.2.3 From 08dfa5a19e1f4344ce5d3a5eed4c5529adafe0dc Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 26 Jan 2022 11:10:58 -0800 Subject: net: remove linkmode_change_bit() No callers since v5.7, the initial use case seems pretty esoteric so removing this should not harm the completeness of the API. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/linkmode.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index f8397f300fcd..15e0e0209da4 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -66,11 +66,6 @@ static inline void linkmode_mod_bit(int nr, volatile unsigned long *addr, linkmode_clear_bit(nr, addr); } -static inline void linkmode_change_bit(int nr, volatile unsigned long *addr) -{ - __change_bit(nr, addr); -} - static inline int linkmode_test_bit(int nr, const volatile unsigned long *addr) { return test_bit(nr, addr); -- cgit v1.2.3 From 8b0fdcdc3a7d44aff907f0103f5ffb86b12bfe71 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 26 Jan 2022 11:10:59 -0800 Subject: net: remove bond_slave_has_mac_rcu() No caller since v3.16. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/bonding.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include') diff --git a/include/net/bonding.h b/include/net/bonding.h index 83cfd2d70247..7dead855a72d 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -698,20 +698,6 @@ static inline struct slave *bond_slave_has_mac(struct bonding *bond, return NULL; } -/* Caller must hold rcu_read_lock() for read */ -static inline struct slave *bond_slave_has_mac_rcu(struct bonding *bond, - const u8 *mac) -{ - struct list_head *iter; - struct slave *tmp; - - bond_for_each_slave_rcu(bond, tmp, iter) - if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) - return tmp; - - return NULL; -} - /* Caller must hold rcu_read_lock() for read */ static inline bool bond_slave_has_mac_rx(struct bonding *bond, const u8 *mac) { -- cgit v1.2.3 From 560e08eda7969c3ef0639ab05f718be03a49d387 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 26 Jan 2022 11:11:00 -0800 Subject: net: ax25: remove route refcount Nothing takes the refcount since v4.9. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/ax25.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include') diff --git a/include/net/ax25.h b/include/net/ax25.h index 526e49589197..cb628c5d7c5b 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -187,18 +187,12 @@ typedef struct { typedef struct ax25_route { struct ax25_route *next; - refcount_t refcount; ax25_address callsign; struct net_device *dev; ax25_digi *digipeat; char ip_mode; } ax25_route; -static inline void ax25_hold_route(ax25_route *ax25_rt) -{ - refcount_inc(&ax25_rt->refcount); -} - void __ax25_put_route(ax25_route *ax25_rt); extern rwlock_t ax25_route_lock; @@ -213,12 +207,6 @@ static inline void ax25_route_lock_unuse(void) read_unlock(&ax25_route_lock); } -static inline void ax25_put_route(ax25_route *ax25_rt) -{ - if (refcount_dec_and_test(&ax25_rt->refcount)) - __ax25_put_route(ax25_rt); -} - typedef struct { char slave; /* slave_mode? */ struct timer_list slave_timer; /* timeout timer */ -- cgit v1.2.3 From 8b2d546e23bb3588f897089368b5f09e49f7762d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 26 Jan 2022 11:11:02 -0800 Subject: ipv6: remove inet6_rsk() and tcp_twsk_ipv6only() The stubs under !CONFIG_IPV6 were missed when real functions got deleted ca. v3.13. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/ipv6.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index a59d25f19385..1e0f8a31f3de 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -371,19 +371,12 @@ static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk) return NULL; } -static inline struct inet6_request_sock * - inet6_rsk(const struct request_sock *rsk) -{ - return NULL; -} - static inline struct raw6_sock *raw6_sk(const struct sock *sk) { return NULL; } #define inet6_rcv_saddr(__sk) NULL -#define tcp_twsk_ipv6only(__sk) 0 #define inet_v6_ipv6only(__sk) 0 #endif /* IS_ENABLED(CONFIG_IPV6) */ #endif /* _IPV6_H */ -- cgit v1.2.3 From cc81df835c25b108248bad24021a21e77cbb84ac Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 26 Jan 2022 11:11:04 -0800 Subject: udp: remove inner_udp_hdr() Not used since added in v3.8. Signed-off-by: Jakub Kicinski Acked-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/udp.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/udp.h b/include/linux/udp.h index ae66dadd8543..254a2654400f 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -23,11 +23,6 @@ static inline struct udphdr *udp_hdr(const struct sk_buff *skb) return (struct udphdr *)skb_transport_header(skb); } -static inline struct udphdr *inner_udp_hdr(const struct sk_buff *skb) -{ - return (struct udphdr *)skb_inner_transport_header(skb); -} - #define UDP_HTABLE_SIZE_MIN (CONFIG_BASE_SMALL ? 128 : 256) static inline u32 udp_hashfn(const struct net *net, u32 num, u32 mask) -- cgit v1.2.3 From 937fca918aacf54f1c9cb00d16d4e999a0569be0 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 26 Jan 2022 11:11:05 -0800 Subject: udplite: remove udplite_csum_outgoing() Not used since v4.0. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/udplite.h | 43 ------------------------------------------- 1 file changed, 43 deletions(-) (limited to 'include') diff --git a/include/net/udplite.h b/include/net/udplite.h index 9185e45b997f..a3c53110d30b 100644 --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -70,49 +70,6 @@ static inline int udplite_checksum_init(struct sk_buff *skb, struct udphdr *uh) return 0; } -/* Slow-path computation of checksum. Socket is locked. */ -static inline __wsum udplite_csum_outgoing(struct sock *sk, struct sk_buff *skb) -{ - const struct udp_sock *up = udp_sk(skb->sk); - int cscov = up->len; - __wsum csum = 0; - - if (up->pcflag & UDPLITE_SEND_CC) { - /* - * Sender has set `partial coverage' option on UDP-Lite socket. - * The special case "up->pcslen == 0" signifies full coverage. - */ - if (up->pcslen < up->len) { - if (0 < up->pcslen) - cscov = up->pcslen; - udp_hdr(skb)->len = htons(up->pcslen); - } - /* - * NOTE: Causes for the error case `up->pcslen > up->len': - * (i) Application error (will not be penalized). - * (ii) Payload too big for send buffer: data is split - * into several packets, each with its own header. - * In this case (e.g. last segment), coverage may - * exceed packet length. - * Since packets with coverage length > packet length are - * illegal, we fall back to the defaults here. - */ - } - - skb->ip_summed = CHECKSUM_NONE; /* no HW support for checksumming */ - - skb_queue_walk(&sk->sk_write_queue, skb) { - const int off = skb_transport_offset(skb); - const int len = skb->len - off; - - csum = skb_checksum(skb, off, (cscov > len)? len : cscov, csum); - - if ((cscov -= len) <= 0) - break; - } - return csum; -} - /* Fast-path computation of checksum. Socket may not be locked. */ static inline __wsum udplite_csum(struct sk_buff *skb) { -- cgit v1.2.3 From d59a67f2f3f39012271ed3d11c338706a011c5c2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 26 Jan 2022 11:11:06 -0800 Subject: netlink: remove nl_set_extack_cookie_u32() Not used since v5.10. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netlink.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 1ec631838af9..bda1c385cffb 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -135,15 +135,6 @@ static inline void nl_set_extack_cookie_u64(struct netlink_ext_ack *extack, extack->cookie_len = sizeof(cookie); } -static inline void nl_set_extack_cookie_u32(struct netlink_ext_ack *extack, - u32 cookie) -{ - if (!extack) - return; - memcpy(extack->cookie, &cookie, sizeof(cookie)); - extack->cookie_len = sizeof(cookie); -} - void netlink_kernel_release(struct sock *sk); int __netlink_change_ngroups(struct sock *sk, unsigned int groups); int netlink_change_ngroups(struct sock *sk, unsigned int groups); -- cgit v1.2.3 From 98b608629746946ecc6cda70bf0fd047785a1197 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 26 Jan 2022 11:11:07 -0800 Subject: net: sched: remove psched_tdiff_bounded() Not used since v3.9. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/pkt_sched.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 9e7b21c0b3a6..44a35531952e 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -63,12 +63,6 @@ static inline psched_time_t psched_get_time(void) return PSCHED_NS2TICKS(ktime_get_ns()); } -static inline psched_tdiff_t -psched_tdiff_bounded(psched_time_t tv1, psched_time_t tv2, psched_time_t bound) -{ - return min(tv1 - tv2, bound); -} - struct qdisc_watchdog { u64 last_expires; struct hrtimer timer; -- cgit v1.2.3 From a459bc9a3a68f2975ee6661fb9c86126a5636b25 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 26 Jan 2022 11:11:08 -0800 Subject: net: sched: remove qdisc_qlen_cpu() Never used since it was added in v5.2. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/sch_generic.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 472843eedbae..9bab396c1f3b 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -518,11 +518,6 @@ static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) BUILD_BUG_ON(sizeof(qcb->data) < sz); } -static inline int qdisc_qlen_cpu(const struct Qdisc *q) -{ - return this_cpu_ptr(q->cpu_qstats)->qlen; -} - static inline int qdisc_qlen(const struct Qdisc *q) { return q->q.qlen; -- cgit v1.2.3 From d1bc532e99becf104635ed4da6fefa306f452321 Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Tue, 25 Jan 2022 17:04:43 +0100 Subject: i40e: xsk: Move tmp desc array from driver to pool Move desc_array from the driver to the pool. The reason behind this is that we can then reuse this array as a temporary storage for descriptors in all zero-copy drivers that use the batched interface. This will make it easier to add batching to more drivers. i40e is the only driver that has a batched Tx zero-copy implementation, so no need to touch any other driver. Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Reviewed-by: Alexander Lobakin Link: https://lore.kernel.org/bpf/20220125160446.78976-6-maciej.fijalkowski@intel.com --- include/net/xdp_sock_drv.h | 5 ++--- include/net/xsk_buff_pool.h | 1 + 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 443d45951564..4aa031849668 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -13,7 +13,7 @@ void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries); bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc); -u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, struct xdp_desc *desc, u32 max); +u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max); void xsk_tx_release(struct xsk_buff_pool *pool); struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev, u16 queue_id); @@ -142,8 +142,7 @@ static inline bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, return false; } -static inline u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, struct xdp_desc *desc, - u32 max) +static inline u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max) { return 0; } diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index ddeefc4a1040..5554ee75e7da 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -60,6 +60,7 @@ struct xsk_buff_pool { */ dma_addr_t *dma_pages; struct xdp_buff_xsk *heads; + struct xdp_desc *tx_descs; u64 chunk_mask; u64 addrs_cnt; u32 free_list_cnt; -- cgit v1.2.3 From 46531a30364bd483bfa1b041c15d42a196e77e93 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 27 Jan 2022 14:09:13 +0000 Subject: cgroup/bpf: fast path skb BPF filtering Even though there is a static key protecting from overhead from cgroup-bpf skb filtering when there is nothing attached, in many cases it's not enough as registering a filter for one type will ruin the fast path for all others. It's observed in production servers I've looked at but also in laptops, where registration is done during init by systemd or something else. Add a per-socket fast path check guarding from such overhead. This affects both receive and transmit paths of TCP, UDP and other protocols. It showed ~1% tx/s improvement in small payload UDP send benchmarks using a real NIC and in a server environment and the number jumps to 2-3% for preemtible kernels. Reviewed-by: Stanislav Fomichev Signed-off-by: Pavel Begunkov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/r/d8c58857113185a764927a46f4b5a058d36d3ec3.1643292455.git.asml.silence@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf-cgroup.h | 24 ++++++++++++++++++++---- include/linux/bpf.h | 13 +++++++++++++ 2 files changed, 33 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index b525d8cdc25b..88a51b242adc 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -8,6 +8,7 @@ #include #include #include +#include #include struct sock; @@ -165,11 +166,23 @@ int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, void *value, u64 flags); +/* Opportunistic check to see whether we have any BPF program attached*/ +static inline bool cgroup_bpf_sock_enabled(struct sock *sk, + enum cgroup_bpf_attach_type type) +{ + struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); + struct bpf_prog_array *array; + + array = rcu_access_pointer(cgrp->bpf.effective[type]); + return array != &bpf_empty_prog_array.hdr; +} + /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */ #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(CGROUP_INET_INGRESS)) \ + if (cgroup_bpf_enabled(CGROUP_INET_INGRESS) && \ + cgroup_bpf_sock_enabled(sk, CGROUP_INET_INGRESS)) \ __ret = __cgroup_bpf_run_filter_skb(sk, skb, \ CGROUP_INET_INGRESS); \ \ @@ -181,7 +194,8 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_INET_EGRESS) && sk && sk == skb->sk) { \ typeof(sk) __sk = sk_to_full_sk(sk); \ - if (sk_fullsock(__sk)) \ + if (sk_fullsock(__sk) && \ + cgroup_bpf_sock_enabled(__sk, CGROUP_INET_EGRESS)) \ __ret = __cgroup_bpf_run_filter_skb(__sk, skb, \ CGROUP_INET_EGRESS); \ } \ @@ -347,7 +361,8 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, kernel_optval) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(CGROUP_SETSOCKOPT)) \ + if (cgroup_bpf_enabled(CGROUP_SETSOCKOPT) && \ + cgroup_bpf_sock_enabled(sock, CGROUP_SETSOCKOPT)) \ __ret = __cgroup_bpf_run_filter_setsockopt(sock, level, \ optname, optval, \ optlen, \ @@ -367,7 +382,8 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, max_optlen, retval) \ ({ \ int __ret = retval; \ - if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT)) \ + if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT) && \ + cgroup_bpf_sock_enabled(sock, CGROUP_GETSOCKOPT)) \ if (!(sock)->sk_prot->bpf_bypass_getsockopt || \ !INDIRECT_CALL_INET_1((sock)->sk_prot->bpf_bypass_getsockopt, \ tcp_bpf_bypass_getsockopt, \ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2344f793c4dc..e3b82ce51445 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1233,6 +1233,19 @@ struct bpf_prog_array { struct bpf_prog_array_item items[]; }; +struct bpf_empty_prog_array { + struct bpf_prog_array hdr; + struct bpf_prog *null_prog; +}; + +/* to avoid allocating empty bpf_prog_array for cgroups that + * don't have bpf program attached use one global 'bpf_empty_prog_array' + * It will not be modified the caller of bpf_prog_array_alloc() + * (since caller requested prog_cnt == 0) + * that pointer should be 'freed' by bpf_prog_array_free() + */ +extern struct bpf_empty_prog_array bpf_empty_prog_array; + struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); void bpf_prog_array_free(struct bpf_prog_array *progs); int bpf_prog_array_length(struct bpf_prog_array *progs); -- cgit v1.2.3 From 7472d5a642c94a0ee1882ff3038de72ffe803a01 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 27 Jan 2022 07:46:00 -0800 Subject: compiler_types: define __user as __attribute__((btf_type_tag("user"))) The __user attribute is currently mainly used by sparse for type checking. The attribute indicates whether a memory access is in user memory address space or not. Such information is important during tracing kernel internal functions or data structures as accessing user memory often has different mechanisms compared to accessing kernel memory. For example, the perf-probe needs explicit command line specification to indicate a particular argument or string in user-space memory ([1], [2], [3]). Currently, vmlinux BTF is available in kernel with many distributions. If __user attribute information is available in vmlinux BTF, the explicit user memory access information from users will not be necessary as the kernel can figure it out by itself with vmlinux BTF. Besides the above possible use for perf/probe, another use case is for bpf verifier. Currently, for bpf BPF_PROG_TYPE_TRACING type of bpf programs, users can write direct code like p->m1->m2 and "p" could be a function parameter. Without __user information in BTF, the verifier will assume p->m1 accessing kernel memory and will generate normal loads. Let us say "p" actually tagged with __user in the source code. In such cases, p->m1 is actually accessing user memory and direct load is not right and may produce incorrect result. For such cases, bpf_probe_read_user() will be the correct way to read p->m1. To support encoding __user information in BTF, a new attribute __attribute__((btf_type_tag(""))) is implemented in clang ([4]). For example, if we have #define __user __attribute__((btf_type_tag("user"))) during kernel compilation, the attribute "user" information will be preserved in dwarf. After pahole converting dwarf to BTF, __user information will be available in vmlinux BTF. The following is an example with latest upstream clang (clang14) and pahole 1.23: [$ ~] cat test.c #define __user __attribute__((btf_type_tag("user"))) int foo(int __user *arg) { return *arg; } [$ ~] clang -O2 -g -c test.c [$ ~] pahole -JV test.o ... [1] INT int size=4 nr_bits=32 encoding=SIGNED [2] TYPE_TAG user type_id=1 [3] PTR (anon) type_id=2 [4] FUNC_PROTO (anon) return=1 args=(3 arg) [5] FUNC foo type_id=4 [$ ~] You can see for the function argument "int __user *arg", its type is described as PTR -> TYPE_TAG(user) -> INT The kernel can use this information for bpf verification or other use cases. Current btf_type_tag is only supported in clang (>= clang14) and pahole (>= 1.23). gcc support is also proposed and under development ([5]). [1] http://lkml.kernel.org/r/155789874562.26965.10836126971405890891.stgit@devnote2 [2] http://lkml.kernel.org/r/155789872187.26965.4468456816590888687.stgit@devnote2 [3] http://lkml.kernel.org/r/155789871009.26965.14167558859557329331.stgit@devnote2 [4] https://reviews.llvm.org/D111199 [5] https://lore.kernel.org/bpf/0cbeb2fb-1a18-f690-e360-24b1c90c2a91@fb.com/ Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20220127154600.652613-1-yhs@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/compiler_types.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3c1795fdb568..3f31ff400432 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -31,6 +31,9 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } # define __kernel # ifdef STRUCTLEAK_PLUGIN # define __user __attribute__((user)) +# elif defined(CONFIG_DEBUG_INFO_BTF) && defined(CONFIG_PAHOLE_HAS_BTF_TAG) && \ + __has_attribute(btf_type_tag) +# define __user __attribute__((btf_type_tag("user"))) # else # define __user # endif -- cgit v1.2.3 From c6f1bfe89ac95dc829dcb4ed54780da134ac5fce Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 27 Jan 2022 07:46:06 -0800 Subject: bpf: reject program if a __user tagged memory accessed in kernel way BPF verifier supports direct memory access for BPF_PROG_TYPE_TRACING type of bpf programs, e.g., a->b. If "a" is a pointer pointing to kernel memory, bpf verifier will allow user to write code in C like a->b and the verifier will translate it to a kernel load properly. If "a" is a pointer to user memory, it is expected that bpf developer should be bpf_probe_read_user() helper to get the value a->b. Without utilizing BTF __user tagging information, current verifier will assume that a->b is a kernel memory access and this may generate incorrect result. Now BTF contains __user information, it can check whether the pointer points to a user memory or not. If it is, the verifier can reject the program and force users to use bpf_probe_read_user() helper explicitly. In the future, we can easily extend btf_add_space for other address space tagging, for example, rcu/percpu etc. Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20220127154606.654961-1-yhs@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 9 ++++++--- include/linux/btf.h | 5 +++++ 2 files changed, 11 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e3b82ce51445..6eb0b180d33b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -332,7 +332,10 @@ enum bpf_type_flag { */ MEM_ALLOC = BIT(2 + BPF_BASE_TYPE_BITS), - __BPF_TYPE_LAST_FLAG = MEM_ALLOC, + /* MEM is in user address space. */ + MEM_USER = BIT(3 + BPF_BASE_TYPE_BITS), + + __BPF_TYPE_LAST_FLAG = MEM_USER, }; /* Max number of base types. */ @@ -588,7 +591,7 @@ struct bpf_verifier_ops { const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, - u32 *next_btf_id); + u32 *next_btf_id, enum bpf_type_flag *flag); }; struct bpf_prog_offload_ops { @@ -1780,7 +1783,7 @@ static inline bool bpf_tracing_btf_ctx_access(int off, int size, int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, - u32 *next_btf_id); + u32 *next_btf_id, enum bpf_type_flag *flag); bool btf_struct_ids_match(struct bpf_verifier_log *log, const struct btf *btf, u32 id, int off, const struct btf *need_btf, u32 need_type_id); diff --git a/include/linux/btf.h b/include/linux/btf.h index b12cfe3b12bb..f6c43dd513fa 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -238,6 +238,11 @@ static inline bool btf_type_is_var(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_VAR; } +static inline bool btf_type_is_type_tag(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_TYPE_TAG; +} + /* union is only a special case of struct: * all its offsetof(member) == 0 */ -- cgit v1.2.3 From 9059b04b4108be71397941f4665d5aa79783125a Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Sun, 9 Jan 2022 21:46:34 +0200 Subject: net/mlx5: Remove unused TIR modify bitmask enums struct mlx5_ifc_modify_tir_bitmask_bits is used for the bitmask of MODIFY_TIR operations. Remove the unused bitmask enums. Signed-off-by: Tariq Toukan Reviewed-by: Gal Pressman Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 598ac3bcc901..27145c4d6820 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -63,13 +63,6 @@ enum { MLX5_EVENT_TYPE_CODING_FPGA_QP_ERROR = 0x21 }; -enum { - MLX5_MODIFY_TIR_BITMASK_LRO = 0x0, - MLX5_MODIFY_TIR_BITMASK_INDIRECT_TABLE = 0x1, - MLX5_MODIFY_TIR_BITMASK_HASH = 0x2, - MLX5_MODIFY_TIR_BITMASK_TUNNELED_OFFLOAD_EN = 0x3 -}; - enum { MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE = 0x0, MLX5_SET_HCA_CAP_OP_MOD_ODP = 0x2, -- cgit v1.2.3 From 8cda7a4f96e435be2fd074009d69521d973d7d31 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 7 Jan 2022 17:57:33 -0500 Subject: drm/amdgpu/UAPI: add new CTX OP to get/set stable pstates Add a new CTX ioctl operation to set stable pstates for profiling. When creating traces for tools like RGP or using SPM or doing performance profiling, it's required to enable a special stable profiling power state on the GPU. These profiling states set fixed clocks and disable certain other power features like powergating which may impact the results. Historically, these profiling pstates were enabled via sysfs, but this adds an interface to enable it via the CTX ioctl from the application. Since the power state is global only one application can set it at a time, so if multiple applications try and use it only the first will get it, the ioctl will return -EBUSY for others. The sysfs interface will override whatever has been set by this interface. Mesa MR: https://gitlab.freedesktop.org/mesa/drm/-/merge_requests/207 v2: don't default r = 0; v3: rebase on Evan's PM cleanup Reviewed-by: Evan Quan Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index be4f9111f478..76b580d10a52 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -206,6 +206,8 @@ union drm_amdgpu_bo_list { #define AMDGPU_CTX_OP_FREE_CTX 2 #define AMDGPU_CTX_OP_QUERY_STATE 3 #define AMDGPU_CTX_OP_QUERY_STATE2 4 +#define AMDGPU_CTX_OP_GET_STABLE_PSTATE 5 +#define AMDGPU_CTX_OP_SET_STABLE_PSTATE 6 /* GPU reset status */ #define AMDGPU_CTX_NO_RESET 0 @@ -238,10 +240,18 @@ union drm_amdgpu_bo_list { #define AMDGPU_CTX_PRIORITY_HIGH 512 #define AMDGPU_CTX_PRIORITY_VERY_HIGH 1023 +/* select a stable profiling pstate for perfmon tools */ +#define AMDGPU_CTX_STABLE_PSTATE_FLAGS_MASK 0xf +#define AMDGPU_CTX_STABLE_PSTATE_NONE 0 +#define AMDGPU_CTX_STABLE_PSTATE_STANDARD 1 +#define AMDGPU_CTX_STABLE_PSTATE_MIN_SCLK 2 +#define AMDGPU_CTX_STABLE_PSTATE_MIN_MCLK 3 +#define AMDGPU_CTX_STABLE_PSTATE_PEAK 4 + struct drm_amdgpu_ctx_in { /** AMDGPU_CTX_OP_* */ __u32 op; - /** For future use, no flags defined so far */ + /** Flags */ __u32 flags; __u32 ctx_id; /** AMDGPU_CTX_PRIORITY_* */ @@ -262,6 +272,11 @@ union drm_amdgpu_ctx_out { /** Reset status since the last call of the ioctl. */ __u32 reset_status; } state; + + struct { + __u32 flags; + __u32 _pad; + } pstate; }; union drm_amdgpu_ctx { -- cgit v1.2.3 From f37a4cc6bb0ba08c2d9fd7d18a1da87161cbb7f9 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 27 Jan 2022 00:36:28 +0000 Subject: udp6: pass flow in ip6_make_skb together with cork Another preparation patch. inet_cork_full already contains a field for iflow, so we can avoid passing a separate struct iflow6 into __ip6_append_data() and ip6_make_skb(), and use the flow stored in inet_cork_full. Make sure callers set cork->fl, i.e. we init it in ip6_append_data() and before calling ip6_make_skb(). Signed-off-by: Pavel Begunkov Reviewed-by: Willem de Bruijn Signed-off-by: Jakub Kicinski --- include/net/ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 3afcb128e064..5e0b56d66724 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1020,7 +1020,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, - struct ipcm6_cookie *ipc6, struct flowi6 *fl6, + struct ipcm6_cookie *ipc6, struct rt6_info *rt, unsigned int flags, struct inet_cork_full *cork); -- cgit v1.2.3 From 31ed2261e88fbd1eb62fc870ef2c6b2cf2951336 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 27 Jan 2022 00:36:31 +0000 Subject: ipv6: partially inline ipv6_fixup_options Inline a part of ipv6_fixup_options() to avoid extra overhead on function call if opt is NULL. Signed-off-by: Pavel Begunkov Reviewed-by: Willem de Bruijn Signed-off-by: Jakub Kicinski --- include/net/ipv6.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 5e0b56d66724..082f30256f59 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -437,8 +437,16 @@ struct ipv6_txoptions *ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, int newtype, struct ipv6_opt_hdr *newopt); -struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space, - struct ipv6_txoptions *opt); +struct ipv6_txoptions *__ipv6_fixup_options(struct ipv6_txoptions *opt_space, + struct ipv6_txoptions *opt); + +static inline struct ipv6_txoptions * +ipv6_fixup_options(struct ipv6_txoptions *opt_space, struct ipv6_txoptions *opt) +{ + if (!opt) + return NULL; + return __ipv6_fixup_options(opt_space, opt); +} bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, const struct inet6_skb_parm *opt); -- cgit v1.2.3 From eb90686d5d10fef9cadd9c0eb30f3fee66d2b2a5 Mon Sep 17 00:00:00 2001 From: Tianjia Zhang Date: Fri, 7 Jan 2022 20:06:55 +0800 Subject: crypto: sm3 - create SM3 stand-alone library Stand-alone implementation of the SM3 algorithm. It is designed to have as little dependencies as possible. In other cases you should generally use the hash APIs from include/crypto/hash.h. Especially when hashing large amounts of data as those APIs may be hw-accelerated. In the new SM3 stand-alone library, sm3_transform() has also been optimized, instead of simply using the code in sm3_generic. Signed-off-by: Tianjia Zhang Reviewed-by: Gilad Ben-Yossef Signed-off-by: Herbert Xu --- include/crypto/sm3.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include') diff --git a/include/crypto/sm3.h b/include/crypto/sm3.h index 42ea21289ba9..b5fb6d1bf247 100644 --- a/include/crypto/sm3.h +++ b/include/crypto/sm3.h @@ -1,5 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Common values for SM3 algorithm + * + * Copyright (C) 2017 ARM Limited or its affiliates. + * Copyright (C) 2017 Gilad Ben-Yossef + * Copyright (C) 2021 Tianjia Zhang */ #ifndef _CRYPTO_SM3_H @@ -39,4 +44,31 @@ extern int crypto_sm3_final(struct shash_desc *desc, u8 *out); extern int crypto_sm3_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *hash); + +/* + * Stand-alone implementation of the SM3 algorithm. It is designed to + * have as little dependencies as possible so it can be used in the + * kexec_file purgatory. In other cases you should generally use the + * hash APIs from include/crypto/hash.h. Especially when hashing large + * amounts of data as those APIs may be hw-accelerated. + * + * For details see lib/crypto/sm3.c + */ + +static inline void sm3_init(struct sm3_state *sctx) +{ + sctx->state[0] = SM3_IVA; + sctx->state[1] = SM3_IVB; + sctx->state[2] = SM3_IVC; + sctx->state[3] = SM3_IVD; + sctx->state[4] = SM3_IVE; + sctx->state[5] = SM3_IVF; + sctx->state[6] = SM3_IVG; + sctx->state[7] = SM3_IVH; + sctx->count = 0; +} + +void sm3_update(struct sm3_state *sctx, const u8 *data, unsigned int len); +void sm3_final(struct sm3_state *sctx, u8 *out); + #endif -- cgit v1.2.3 From b4784a45ea69577f21f89898c71127774a090a2a Mon Sep 17 00:00:00 2001 From: Tianjia Zhang Date: Fri, 7 Jan 2022 20:06:58 +0800 Subject: crypto: sm3 - make dependent on sm3 library SM3 generic library is stand-alone implementation, it is necessary making the sm3-generic implementation to depends on SM3 library. The functions crypto_sm3_*() provided by sm3_generic is no longer exported. Signed-off-by: Tianjia Zhang Signed-off-by: Herbert Xu --- include/crypto/sm3.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/crypto/sm3.h b/include/crypto/sm3.h index b5fb6d1bf247..1f021ad0533f 100644 --- a/include/crypto/sm3.h +++ b/include/crypto/sm3.h @@ -35,16 +35,6 @@ struct sm3_state { u8 buffer[SM3_BLOCK_SIZE]; }; -struct shash_desc; - -extern int crypto_sm3_update(struct shash_desc *desc, const u8 *data, - unsigned int len); - -extern int crypto_sm3_final(struct shash_desc *desc, u8 *out); - -extern int crypto_sm3_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *hash); - /* * Stand-alone implementation of the SM3 algorithm. It is designed to * have as little dependencies as possible so it can be used in the -- cgit v1.2.3 From c265a3a6690b093e542aceb4a7bf8bf6c577e42b Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 25 Jan 2022 13:25:40 +0100 Subject: net: mac802154: Explain the use of ieee802154_wake/stop_queue() It is not straightforward to the newcomer that a single skb can currently be sent at a time and that the internal process is to stop the queue when processing a frame before re-enabling it. Make this clear by documenting the ieee802154_wake/stop_queue() helpers. Signed-off-by: Miquel Raynal Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20220125122540.855604-4-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt --- include/net/mac802154.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/net/mac802154.h b/include/net/mac802154.h index d524ffb9eb25..2c3bbc6645ba 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -464,6 +464,12 @@ void ieee802154_rx_irqsafe(struct ieee802154_hw *hw, struct sk_buff *skb, * ieee802154_wake_queue - wake ieee802154 queue * @hw: pointer as obtained from ieee802154_alloc_hw(). * + * Tranceivers usually have either one transmit framebuffer or one framebuffer + * for both transmitting and receiving. Hence, the core currently only handles + * one frame at a time for each phy, which means we had to stop the queue to + * avoid new skb to come during the transmission. The queue then needs to be + * woken up after the operation. + * * Drivers should use this function instead of netif_wake_queue. */ void ieee802154_wake_queue(struct ieee802154_hw *hw); @@ -472,6 +478,12 @@ void ieee802154_wake_queue(struct ieee802154_hw *hw); * ieee802154_stop_queue - stop ieee802154 queue * @hw: pointer as obtained from ieee802154_alloc_hw(). * + * Tranceivers usually have either one transmit framebuffer or one framebuffer + * for both transmitting and receiving. Hence, the core currently only handles + * one frame at a time for each phy, which means we need to tell upper layers to + * stop giving us new skbs while we are busy with the transmitted one. The queue + * must then be stopped before transmitting. + * * Drivers should use this function instead of netif_stop_queue. */ void ieee802154_stop_queue(struct ieee802154_hw *hw); -- cgit v1.2.3 From dbd171df8cc02a7c286779a048082624fc4dce8e Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Mon, 17 Jan 2022 08:05:08 +0100 Subject: media: memory: mtk-smi: Get rid of mtk_smi_larb_get/put After adding device_link between the iommu consumer and smi-larb, the pm_runtime_get(_sync) of smi-larb and smi-common will be called automatically. we can get rid of mtk_smi_larb_get/put. Signed-off-by: Yong Wu Reviewed-by: Evan Green Acked-by: Krzysztof Kozlowski Acked-by: Matthias Brugger Reviewed-by: Dafna Hirschfeld Tested-by: Frank Wunderlich # BPI-R2/MT7623 Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/soc/mediatek/smi.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include') diff --git a/include/soc/mediatek/smi.h b/include/soc/mediatek/smi.h index 15e3397cec58..11f7d6b59642 100644 --- a/include/soc/mediatek/smi.h +++ b/include/soc/mediatek/smi.h @@ -19,26 +19,6 @@ struct mtk_smi_larb_iommu { unsigned char bank[32]; }; -/* - * mtk_smi_larb_get: Enable the power domain and clocks for this local arbiter. - * It also initialize some basic setting(like iommu). - * mtk_smi_larb_put: Disable the power domain and clocks for this local arbiter. - * Both should be called in non-atomic context. - * - * Returns 0 if successful, negative on failure. - */ -int mtk_smi_larb_get(struct device *larbdev); -void mtk_smi_larb_put(struct device *larbdev); - -#else - -static inline int mtk_smi_larb_get(struct device *larbdev) -{ - return 0; -} - -static inline void mtk_smi_larb_put(struct device *larbdev) { } - #endif #endif -- cgit v1.2.3 From b5b3d10ef638fcadc56609961875bf157a92aaa4 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 27 Jan 2022 08:33:49 -0800 Subject: net: mii: remove mii_lpa_mod_linkmode_lpa_sgmii() Vladimir points out that since we removed mii_lpa_to_linkmode_lpa_sgmii(), mii_lpa_mod_linkmode_lpa_sgmii() is also no longer called. Suggested-by: Vladimir Oltean Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/mii.h | 33 --------------------------------- 1 file changed, 33 deletions(-) (limited to 'include') diff --git a/include/linux/mii.h b/include/linux/mii.h index b8a1a17a87dd..5ee13083cec7 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -354,39 +354,6 @@ static inline u32 mii_adv_to_ethtool_adv_x(u32 adv) return result; } -/** - * mii_lpa_mod_linkmode_adv_sgmii - * @lp_advertising: pointer to destination link mode. - * @lpa: value of the MII_LPA register - * - * A small helper function that translates MII_LPA bits to - * linkmode advertisement settings for SGMII. - * Leaves other bits unchanged. - */ -static inline void -mii_lpa_mod_linkmode_lpa_sgmii(unsigned long *lp_advertising, u32 lpa) -{ - u32 speed_duplex = lpa & LPA_SGMII_DPX_SPD_MASK; - - linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, lp_advertising, - speed_duplex == LPA_SGMII_1000HALF); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, lp_advertising, - speed_duplex == LPA_SGMII_1000FULL); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, lp_advertising, - speed_duplex == LPA_SGMII_100HALF); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, lp_advertising, - speed_duplex == LPA_SGMII_100FULL); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, lp_advertising, - speed_duplex == LPA_SGMII_10HALF); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, lp_advertising, - speed_duplex == LPA_SGMII_10FULL); -} - /** * mii_adv_mod_linkmode_adv_t * @advertising:pointer to destination link mode. -- cgit v1.2.3 From 9690ae60429020f38e4aa2540c306f27eb021bc0 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 27 Jan 2022 10:42:59 -0800 Subject: ethtool: add header/data split indication For applications running on a mix of platforms it's useful to have a clear indication whether host's NIC supports the geometry requirements of TCP zero-copy. TCP zero-copy Rx requires data to be neatly placed into memory pages. Most NICs can't do that. This patch is adding GET support only, since the NICs I work with either always have the feature enabled or enable it whenever MTU is set to jumbo. In other words I don't need SET. But adding set should be trivial. (The only note on SET is that we will likely want the setting to be "sticky" and use 0 / `unknown` to reset it back to driver default.) Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/ethtool.h | 2 ++ include/uapi/linux/ethtool_netlink.h | 7 +++++++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 11efc45de66a..e0853f48b75e 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -70,9 +70,11 @@ enum { /** * struct kernel_ethtool_ringparam - RX/TX ring configuration * @rx_buf_len: Current length of buffers on the rx ring. + * @tcp_data_split: Scatter packet headers and data to separate buffers */ struct kernel_ethtool_ringparam { u32 rx_buf_len; + u8 tcp_data_split; }; /** diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index cca6e474a085..417d4280d7b5 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -318,6 +318,12 @@ enum { /* RINGS */ +enum { + ETHTOOL_TCP_DATA_SPLIT_UNKNOWN = 0, + ETHTOOL_TCP_DATA_SPLIT_DISABLED, + ETHTOOL_TCP_DATA_SPLIT_ENABLED, +}; + enum { ETHTOOL_A_RINGS_UNSPEC, ETHTOOL_A_RINGS_HEADER, /* nest - _A_HEADER_* */ @@ -330,6 +336,7 @@ enum { ETHTOOL_A_RINGS_RX_JUMBO, /* u32 */ ETHTOOL_A_RINGS_TX, /* u32 */ ETHTOOL_A_RINGS_RX_BUF_LEN, /* u32 */ + ETHTOOL_A_RINGS_TCP_DATA_SPLIT, /* u8 */ /* add new constants above here */ __ETHTOOL_A_RINGS_CNT, -- cgit v1.2.3 From 6cdef8a6ee748ec522aabee049633b16b4115f73 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 27 Jan 2022 12:09:35 -0800 Subject: SUNRPC: add netns refcount tracker to struct svc_xprt struct svc_xprt holds a long lived reference to a netns, it is worth tracking it. Signed-off-by: Eric Dumazet Acked-by: Chuck Lever Signed-off-by: David S. Miller --- include/linux/sunrpc/svc_xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 571f605bc91e..382af90320ac 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -88,6 +88,7 @@ struct svc_xprt { struct list_head xpt_users; /* callbacks on free */ struct net *xpt_net; + netns_tracker ns_tracker; const struct cred *xpt_cred; struct rpc_xprt *xpt_bc_xprt; /* NFSv4.1 backchannel */ struct rpc_xprt_switch *xpt_bc_xps; /* NFSv4.1 backchannel */ -- cgit v1.2.3 From b9a0d6d143ec63132beff04802578c499083f87c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 27 Jan 2022 12:09:37 -0800 Subject: SUNRPC: add netns refcount tracker to struct rpc_xprt Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/sunrpc/xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 955ea4d7af0b..3cdc8d878d81 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -284,6 +284,7 @@ struct rpc_xprt { } stat; struct net *xprt_net; + netns_tracker ns_tracker; const char *servername; const char *address_strings[RPC_DISPLAY_MAX]; #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) -- cgit v1.2.3 From a299299963aeba13bac88020e5f8fd293fbe10b2 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Mon, 3 Jan 2022 17:24:09 +0100 Subject: media: v4l2-subdev: Drop .set_mbus_config() operation The .set_mbus_config() operation is deprecated, and nothing in the kernel uses it. Drop it. Signed-off-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-mediabus.h | 15 +++++++-------- include/media/v4l2-subdev.h | 13 ------------- 2 files changed, 7 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-mediabus.h b/include/media/v4l2-mediabus.h index 841e190aedd9..96af9cedacde 100644 --- a/include/media/v4l2-mediabus.h +++ b/include/media/v4l2-mediabus.h @@ -15,15 +15,14 @@ * How to use the V4L2_MBUS_* flags: * Flags are defined for each of the possible states and values of a media * bus configuration parameter. One and only one bit of each group of flags - * shall be set by the users of the v4l2_subdev_pad_ops.get_mbus_config and - * v4l2_subdev_pad_ops.set_mbus_config operations to ensure that no - * conflicting settings are specified when reporting and setting the media bus - * configuration with the two operations respectively. For example, it is - * invalid to set or clear both the V4L2_MBUS_HSYNC_ACTIVE_HIGH and the + * shall be set by the users of the v4l2_subdev_pad_ops.get_mbus_config + * operation to ensure that no conflicting settings are specified when + * reporting the media bus configuration. For example, it is invalid to set or + * clear both the V4L2_MBUS_HSYNC_ACTIVE_HIGH and the * V4L2_MBUS_HSYNC_ACTIVE_LOW flag at the same time. Instead either flag - * V4L2_MBUS_HSYNC_ACTIVE_HIGH or flag V4L2_MBUS_HSYNC_ACTIVE_LOW shall be - * set. The same is true for the V4L2_MBUS_CSI2_1/2/3/4_LANE flags group: only - * one of these four bits shall be set. + * V4L2_MBUS_HSYNC_ACTIVE_HIGH or flag V4L2_MBUS_HSYNC_ACTIVE_LOW shall be set. + * The same is true for the V4L2_MBUS_CSI2_1/2/3/4_LANE flags group: only one + * of these four bits shall be set. * * TODO: replace the existing V4L2_MBUS_* flags with structures of fields * to avoid conflicting settings. diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index 95ec18c2f49c..6c153b33bb04 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -715,17 +715,6 @@ struct v4l2_subdev_state { * this operation as close as possible to stream on time. The * operation shall fail if the pad index it has been called on * is not valid or in case of unrecoverable failures. - * - * @set_mbus_config: set the media bus configuration of a remote sub-device. - * This operations is intended to allow, in combination with - * the get_mbus_config operation, the negotiation of media bus - * configuration parameters between media sub-devices. The - * operation shall not fail if the requested configuration is - * not supported, but the driver shall update the content of - * the %config argument to reflect what has been actually - * applied to the hardware. The operation shall fail if the - * pad index it has been called on is not valid or in case of - * unrecoverable failures. */ struct v4l2_subdev_pad_ops { int (*init_cfg)(struct v4l2_subdev *sd, @@ -768,8 +757,6 @@ struct v4l2_subdev_pad_ops { struct v4l2_mbus_frame_desc *fd); int (*get_mbus_config)(struct v4l2_subdev *sd, unsigned int pad, struct v4l2_mbus_config *config); - int (*set_mbus_config)(struct v4l2_subdev *sd, unsigned int pad, - struct v4l2_mbus_config *config); }; /** -- cgit v1.2.3 From 94d964e58ad6ba907c4169be99267ef517796614 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Mon, 3 Jan 2022 17:24:10 +0100 Subject: media: v4l2-fwnode: Move bus config structure to v4l2_mediabus.h To prepare for usage of the v4l2_fwnode_bus_* data structures to describe bus configuration in the subdev .get_mbus_config() operation, rename the structures with a v4l2_mbus_config_ prefix instead of v4l2_fwnode_bus_, and move them to v4l2_mediabus.h. Signed-off-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-fwnode.h | 61 +++++-------------------------------------- include/media/v4l2-mediabus.h | 49 ++++++++++++++++++++++++++++++++++ 2 files changed, 55 insertions(+), 55 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-fwnode.h b/include/media/v4l2-fwnode.h index 9c97f1dbd1c6..feb132df45a3 100644 --- a/include/media/v4l2-fwnode.h +++ b/include/media/v4l2-fwnode.h @@ -25,68 +25,19 @@ struct fwnode_handle; struct v4l2_async_notifier; struct v4l2_async_subdev; -#define V4L2_FWNODE_CSI2_MAX_DATA_LANES 8 - -/** - * struct v4l2_fwnode_bus_mipi_csi2 - MIPI CSI-2 bus data structure - * @flags: media bus (V4L2_MBUS_*) flags - * @data_lanes: an array of physical data lane indexes - * @clock_lane: physical lane index of the clock lane - * @num_data_lanes: number of data lanes - * @lane_polarities: polarity of the lanes. The order is the same of - * the physical lanes. - */ -struct v4l2_fwnode_bus_mipi_csi2 { - unsigned int flags; - unsigned char data_lanes[V4L2_FWNODE_CSI2_MAX_DATA_LANES]; - unsigned char clock_lane; - unsigned char num_data_lanes; - bool lane_polarities[1 + V4L2_FWNODE_CSI2_MAX_DATA_LANES]; -}; - -/** - * struct v4l2_fwnode_bus_parallel - parallel data bus data structure - * @flags: media bus (V4L2_MBUS_*) flags - * @bus_width: bus width in bits - * @data_shift: data shift in bits - */ -struct v4l2_fwnode_bus_parallel { - unsigned int flags; - unsigned char bus_width; - unsigned char data_shift; -}; - -/** - * struct v4l2_fwnode_bus_mipi_csi1 - CSI-1/CCP2 data bus structure - * @clock_inv: polarity of clock/strobe signal - * false - not inverted, true - inverted - * @strobe: false - data/clock, true - data/strobe - * @lane_polarity: the polarities of the clock (index 0) and data lanes - * index (1) - * @data_lane: the number of the data lane - * @clock_lane: the number of the clock lane - */ -struct v4l2_fwnode_bus_mipi_csi1 { - unsigned char clock_inv:1; - unsigned char strobe:1; - bool lane_polarity[2]; - unsigned char data_lane; - unsigned char clock_lane; -}; - /** * struct v4l2_fwnode_endpoint - the endpoint data structure * @base: fwnode endpoint of the v4l2_fwnode * @bus_type: bus type * @bus: bus configuration data structure - * @bus.parallel: embedded &struct v4l2_fwnode_bus_parallel. + * @bus.parallel: embedded &struct v4l2_mbus_config_parallel. * Used if the bus is parallel. - * @bus.mipi_csi1: embedded &struct v4l2_fwnode_bus_mipi_csi1. + * @bus.mipi_csi1: embedded &struct v4l2_mbus_config_mipi_csi1. * Used if the bus is MIPI Alliance's Camera Serial * Interface version 1 (MIPI CSI1) or Standard * Mobile Imaging Architecture's Compact Camera Port 2 * (SMIA CCP2). - * @bus.mipi_csi2: embedded &struct v4l2_fwnode_bus_mipi_csi2. + * @bus.mipi_csi2: embedded &struct v4l2_mbus_config_mipi_csi2. * Used if the bus is MIPI Alliance's Camera Serial * Interface version 2 (MIPI CSI2). * @link_frequencies: array of supported link frequencies @@ -100,9 +51,9 @@ struct v4l2_fwnode_endpoint { */ enum v4l2_mbus_type bus_type; struct { - struct v4l2_fwnode_bus_parallel parallel; - struct v4l2_fwnode_bus_mipi_csi1 mipi_csi1; - struct v4l2_fwnode_bus_mipi_csi2 mipi_csi2; + struct v4l2_mbus_config_parallel parallel; + struct v4l2_mbus_config_mipi_csi1 mipi_csi1; + struct v4l2_mbus_config_mipi_csi2 mipi_csi2; } bus; u64 *link_frequencies; unsigned int nr_of_link_frequencies; diff --git a/include/media/v4l2-mediabus.h b/include/media/v4l2-mediabus.h index 96af9cedacde..9c4970fbd8ea 100644 --- a/include/media/v4l2-mediabus.h +++ b/include/media/v4l2-mediabus.h @@ -92,6 +92,55 @@ V4L2_MBUS_CSI2_CHANNEL_2 | \ V4L2_MBUS_CSI2_CHANNEL_3) +#define V4L2_MBUS_CSI2_MAX_DATA_LANES 8 + +/** + * struct v4l2_mbus_config_mipi_csi2 - MIPI CSI-2 data bus configuration + * @flags: media bus (V4L2_MBUS_*) flags + * @data_lanes: an array of physical data lane indexes + * @clock_lane: physical lane index of the clock lane + * @num_data_lanes: number of data lanes + * @lane_polarities: polarity of the lanes. The order is the same of + * the physical lanes. + */ +struct v4l2_mbus_config_mipi_csi2 { + unsigned int flags; + unsigned char data_lanes[V4L2_MBUS_CSI2_MAX_DATA_LANES]; + unsigned char clock_lane; + unsigned char num_data_lanes; + bool lane_polarities[1 + V4L2_MBUS_CSI2_MAX_DATA_LANES]; +}; + +/** + * struct v4l2_mbus_config_parallel - parallel data bus configuration + * @flags: media bus (V4L2_MBUS_*) flags + * @bus_width: bus width in bits + * @data_shift: data shift in bits + */ +struct v4l2_mbus_config_parallel { + unsigned int flags; + unsigned char bus_width; + unsigned char data_shift; +}; + +/** + * struct v4l2_mbus_config_mipi_csi1 - CSI-1/CCP2 data bus configuration + * @clock_inv: polarity of clock/strobe signal + * false - not inverted, true - inverted + * @strobe: false - data/clock, true - data/strobe + * @lane_polarity: the polarities of the clock (index 0) and data lanes + * index (1) + * @data_lane: the number of the data lane + * @clock_lane: the number of the clock lane + */ +struct v4l2_mbus_config_mipi_csi1 { + unsigned char clock_inv:1; + unsigned char strobe:1; + bool lane_polarity[2]; + unsigned char data_lane; + unsigned char clock_lane; +}; + /** * enum v4l2_mbus_type - media bus type * @V4L2_MBUS_UNKNOWN: unknown bus type, no V4L2 mediabus configuration -- cgit v1.2.3 From b2a90f4fcb146d0e033203ab646f0fd22cfa947f Mon Sep 17 00:00:00 2001 From: Sean Young Date: Thu, 13 Jan 2022 11:20:22 +0100 Subject: media: lirc: remove unused lirc features These features have never been implemented by any lirc driver, including staging or out of tree drivers. The ioctls for these feaures were removed in commit d55f09abe24b ("[media] lirc.h: remove several unused ioctls"). So, we can safely remove them. Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/lirc.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/lirc.h b/include/uapi/linux/lirc.h index 9919f2062b14..a1f9c26ea537 100644 --- a/include/uapi/linux/lirc.h +++ b/include/uapi/linux/lirc.h @@ -72,11 +72,9 @@ #define LIRC_CAN_SET_REC_CARRIER (LIRC_CAN_SET_SEND_CARRIER << 16) #define LIRC_CAN_SET_REC_DUTY_CYCLE (LIRC_CAN_SET_SEND_DUTY_CYCLE << 16) -#define LIRC_CAN_SET_REC_DUTY_CYCLE_RANGE 0x40000000 #define LIRC_CAN_SET_REC_CARRIER_RANGE 0x80000000 #define LIRC_CAN_GET_REC_RESOLUTION 0x20000000 #define LIRC_CAN_SET_REC_TIMEOUT 0x10000000 -#define LIRC_CAN_SET_REC_FILTER 0x08000000 #define LIRC_CAN_MEASURE_CARRIER 0x02000000 #define LIRC_CAN_USE_WIDEBAND_RECEIVER 0x04000000 @@ -84,8 +82,6 @@ #define LIRC_CAN_SEND(x) ((x)&LIRC_CAN_SEND_MASK) #define LIRC_CAN_REC(x) ((x)&LIRC_CAN_REC_MASK) -#define LIRC_CAN_NOTIFY_DECODE 0x01000000 - /*** IOCTL commands for lirc driver ***/ #define LIRC_GET_FEATURES _IOR('i', 0x00000000, __u32) -- cgit v1.2.3 From 950170d6d2a5d3c0c959696d2440e5c8dfd02896 Mon Sep 17 00:00:00 2001 From: Sean Young Date: Sat, 15 Jan 2022 11:12:35 +0100 Subject: media: rc-core: rename ir_raw_event_reset to ir_raw_event_overflow The driver report a reset event when the hardware reports and overflow. There is no reason to have a generic "reset" event. Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab --- include/media/rc-core.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/media/rc-core.h b/include/media/rc-core.h index 33b3f7fcf92e..803349599c27 100644 --- a/include/media/rc-core.h +++ b/include/media/rc-core.h @@ -298,7 +298,7 @@ struct ir_raw_event { u8 duty_cycle; unsigned pulse:1; - unsigned reset:1; + unsigned overflow:1; unsigned timeout:1; unsigned carrier_report:1; }; @@ -321,9 +321,9 @@ int ir_raw_encode_scancode(enum rc_proto protocol, u32 scancode, struct ir_raw_event *events, unsigned int max); int ir_raw_encode_carrier(enum rc_proto protocol); -static inline void ir_raw_event_reset(struct rc_dev *dev) +static inline void ir_raw_event_overflow(struct rc_dev *dev) { - ir_raw_event_store(dev, &((struct ir_raw_event) { .reset = true })); + ir_raw_event_store(dev, &((struct ir_raw_event) { .overflow = true })); dev->idle = true; ir_raw_event_handle(dev); } -- cgit v1.2.3 From 68a99f6a0ebfe9101ea79ba5af1c407a5ad4f629 Mon Sep 17 00:00:00 2001 From: Sean Young Date: Sat, 15 Jan 2022 11:19:11 +0100 Subject: media: lirc: report ir receiver overflow If the driver reports that the hardware had an overflow, report this to userspace. It would be nice to know when this happens, and not just get a long space. This change has been tested with lircd, ir-ctl, and ir-keytable. Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/lirc.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/lirc.h b/include/uapi/linux/lirc.h index a1f9c26ea537..21c69a6a100d 100644 --- a/include/uapi/linux/lirc.h +++ b/include/uapi/linux/lirc.h @@ -16,14 +16,16 @@ #define LIRC_MODE2_PULSE 0x01000000 #define LIRC_MODE2_FREQUENCY 0x02000000 #define LIRC_MODE2_TIMEOUT 0x03000000 +#define LIRC_MODE2_OVERFLOW 0x04000000 #define LIRC_VALUE_MASK 0x00FFFFFF #define LIRC_MODE2_MASK 0xFF000000 -#define LIRC_SPACE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_SPACE) -#define LIRC_PULSE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_PULSE) -#define LIRC_FREQUENCY(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_FREQUENCY) -#define LIRC_TIMEOUT(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_TIMEOUT) +#define LIRC_SPACE(val) (((val) & LIRC_VALUE_MASK) | LIRC_MODE2_SPACE) +#define LIRC_PULSE(val) (((val) & LIRC_VALUE_MASK) | LIRC_MODE2_PULSE) +#define LIRC_FREQUENCY(val) (((val) & LIRC_VALUE_MASK) | LIRC_MODE2_FREQUENCY) +#define LIRC_TIMEOUT(val) (((val) & LIRC_VALUE_MASK) | LIRC_MODE2_TIMEOUT) +#define LIRC_OVERFLOW(val) (((val) & LIRC_VALUE_MASK) | LIRC_MODE2_OVERFLOW) #define LIRC_VALUE(val) ((val)&LIRC_VALUE_MASK) #define LIRC_MODE2(val) ((val)&LIRC_MODE2_MASK) @@ -32,6 +34,7 @@ #define LIRC_IS_PULSE(val) (LIRC_MODE2(val) == LIRC_MODE2_PULSE) #define LIRC_IS_FREQUENCY(val) (LIRC_MODE2(val) == LIRC_MODE2_FREQUENCY) #define LIRC_IS_TIMEOUT(val) (LIRC_MODE2(val) == LIRC_MODE2_TIMEOUT) +#define LIRC_IS_OVERFLOW(val) (LIRC_MODE2(val) == LIRC_MODE2_OVERFLOW) /* used heavily by lirc userspace */ #define lirc_t int -- cgit v1.2.3 From ca0acb511c21738b32386ce0f85c284b351d919e Mon Sep 17 00:00:00 2001 From: Akhil R Date: Fri, 28 Jan 2022 17:14:25 +0530 Subject: device property: Add fwnode_irq_get_byname Add fwnode_irq_get_byname() to get an interrupt by name from either ACPI table or Device Tree, whichever is used for enumeration. In the ACPI case, this allow us to use 'interrupt-names' in _DSD which can be mapped to Interrupt() resource by index. The implementation is similar to 'interrupt-names' in the Device Tree. Signed-off-by: Akhil R Reviewed-by: Andy Shevchenko Acked-by: Rafael J. Wysocki Signed-off-by: Wolfram Sang --- include/linux/property.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/property.h b/include/linux/property.h index 7399a0b45f98..95d56a562b6a 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -121,6 +121,7 @@ struct fwnode_handle *fwnode_handle_get(struct fwnode_handle *fwnode); void fwnode_handle_put(struct fwnode_handle *fwnode); int fwnode_irq_get(const struct fwnode_handle *fwnode, unsigned int index); +int fwnode_irq_get_byname(const struct fwnode_handle *fwnode, const char *name); void __iomem *fwnode_iomap(struct fwnode_handle *fwnode, int index); -- cgit v1.2.3 From a263a84088f689bf0c1552a510b25d0bcc45fcae Mon Sep 17 00:00:00 2001 From: Akhil R Date: Fri, 28 Jan 2022 17:14:27 +0530 Subject: i2c: smbus: Use device_*() functions instead of of_*() Change of_*() functions to device_*() for firmware agnostic usage. This allows to have the smbus_alert interrupt without any changes in the controller drivers using the ACPI table. Signed-off-by: Akhil R Reviewed-by: Andy Shevchenko Signed-off-by: Wolfram Sang --- include/linux/i2c-smbus.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/i2c-smbus.h b/include/linux/i2c-smbus.h index 1ef421818d3a..95cf902e0bda 100644 --- a/include/linux/i2c-smbus.h +++ b/include/linux/i2c-smbus.h @@ -30,10 +30,10 @@ struct i2c_client *i2c_new_smbus_alert_device(struct i2c_adapter *adapter, struct i2c_smbus_alert_setup *setup); int i2c_handle_smbus_alert(struct i2c_client *ara); -#if IS_ENABLED(CONFIG_I2C_SMBUS) && IS_ENABLED(CONFIG_OF) -int of_i2c_setup_smbus_alert(struct i2c_adapter *adap); +#if IS_ENABLED(CONFIG_I2C_SMBUS) +int i2c_setup_smbus_alert(struct i2c_adapter *adap); #else -static inline int of_i2c_setup_smbus_alert(struct i2c_adapter *adap) +static inline int i2c_setup_smbus_alert(struct i2c_adapter *adap) { return 0; } -- cgit v1.2.3 From a81595729be6561d25ae64d5bbae059058234363 Mon Sep 17 00:00:00 2001 From: Giulio Benetti Date: Tue, 11 Jan 2022 16:54:11 -0500 Subject: dt-bindings: imx: Add clock binding for i.MXRT1050 Add the clock binding doc for i.MXRT1050. Signed-off-by: Giulio Benetti Signed-off-by: Jesse Taube [Jesse: added clocks from IMXRT1050_CLK_IPG_PDOF to IMXRT1050_CLK_DMA_MUX and moved IMXRT1050_CLK_END on] Acked-by: Stephen Boyd Link: https://lore.kernel.org/r/20220111215415.2075257-4-Mr.Bossman075@gmail.com Signed-off-by: Abel Vesa --- include/dt-bindings/clock/imxrt1050-clock.h | 72 +++++++++++++++++++++++++++++ 1 file changed, 72 insertions(+) create mode 100644 include/dt-bindings/clock/imxrt1050-clock.h (limited to 'include') diff --git a/include/dt-bindings/clock/imxrt1050-clock.h b/include/dt-bindings/clock/imxrt1050-clock.h new file mode 100644 index 000000000000..93bef0832d16 --- /dev/null +++ b/include/dt-bindings/clock/imxrt1050-clock.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR MIT) */ +/* + * Copyright(C) 2019 + * Author(s): Giulio Benetti + */ + +#ifndef __DT_BINDINGS_CLOCK_IMXRT1050_H +#define __DT_BINDINGS_CLOCK_IMXRT1050_H + +#define IMXRT1050_CLK_DUMMY 0 +#define IMXRT1050_CLK_CKIL 1 +#define IMXRT1050_CLK_CKIH 2 +#define IMXRT1050_CLK_OSC 3 +#define IMXRT1050_CLK_PLL2_PFD0_352M 4 +#define IMXRT1050_CLK_PLL2_PFD1_594M 5 +#define IMXRT1050_CLK_PLL2_PFD2_396M 6 +#define IMXRT1050_CLK_PLL3_PFD0_720M 7 +#define IMXRT1050_CLK_PLL3_PFD1_664_62M 8 +#define IMXRT1050_CLK_PLL3_PFD2_508_24M 9 +#define IMXRT1050_CLK_PLL3_PFD3_454_74M 10 +#define IMXRT1050_CLK_PLL2_198M 11 +#define IMXRT1050_CLK_PLL3_120M 12 +#define IMXRT1050_CLK_PLL3_80M 13 +#define IMXRT1050_CLK_PLL3_60M 14 +#define IMXRT1050_CLK_PLL1_BYPASS 15 +#define IMXRT1050_CLK_PLL2_BYPASS 16 +#define IMXRT1050_CLK_PLL3_BYPASS 17 +#define IMXRT1050_CLK_PLL5_BYPASS 19 +#define IMXRT1050_CLK_PLL1_REF_SEL 20 +#define IMXRT1050_CLK_PLL2_REF_SEL 21 +#define IMXRT1050_CLK_PLL3_REF_SEL 22 +#define IMXRT1050_CLK_PLL5_REF_SEL 23 +#define IMXRT1050_CLK_PRE_PERIPH_SEL 24 +#define IMXRT1050_CLK_PERIPH_SEL 25 +#define IMXRT1050_CLK_SEMC_ALT_SEL 26 +#define IMXRT1050_CLK_SEMC_SEL 27 +#define IMXRT1050_CLK_USDHC1_SEL 28 +#define IMXRT1050_CLK_USDHC2_SEL 29 +#define IMXRT1050_CLK_LPUART_SEL 30 +#define IMXRT1050_CLK_LCDIF_SEL 31 +#define IMXRT1050_CLK_VIDEO_POST_DIV_SEL 32 +#define IMXRT1050_CLK_VIDEO_DIV 33 +#define IMXRT1050_CLK_ARM_PODF 34 +#define IMXRT1050_CLK_LPUART_PODF 35 +#define IMXRT1050_CLK_USDHC1_PODF 36 +#define IMXRT1050_CLK_USDHC2_PODF 37 +#define IMXRT1050_CLK_SEMC_PODF 38 +#define IMXRT1050_CLK_AHB_PODF 39 +#define IMXRT1050_CLK_LCDIF_PRED 40 +#define IMXRT1050_CLK_LCDIF_PODF 41 +#define IMXRT1050_CLK_USDHC1 42 +#define IMXRT1050_CLK_USDHC2 43 +#define IMXRT1050_CLK_LPUART1 44 +#define IMXRT1050_CLK_SEMC 45 +#define IMXRT1050_CLK_LCDIF_APB 46 +#define IMXRT1050_CLK_PLL1_ARM 47 +#define IMXRT1050_CLK_PLL2_SYS 48 +#define IMXRT1050_CLK_PLL3_USB_OTG 49 +#define IMXRT1050_CLK_PLL4_AUDIO 50 +#define IMXRT1050_CLK_PLL5_VIDEO 51 +#define IMXRT1050_CLK_PLL6_ENET 52 +#define IMXRT1050_CLK_PLL7_USB_HOST 53 +#define IMXRT1050_CLK_LCDIF_PIX 54 +#define IMXRT1050_CLK_USBOH3 55 +#define IMXRT1050_CLK_IPG_PDOF 56 +#define IMXRT1050_CLK_PER_CLK_SEL 57 +#define IMXRT1050_CLK_PER_PDOF 58 +#define IMXRT1050_CLK_DMA 59 +#define IMXRT1050_CLK_DMA_MUX 60 +#define IMXRT1050_CLK_END 61 + +#endif /* __DT_BINDINGS_CLOCK_IMXRT1050_H */ -- cgit v1.2.3 From 4f0e30407ef6f2075b8e86d54be42e787087cd61 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 28 Jan 2022 08:06:54 -0800 Subject: ipv4: drop fragmentation code from ip_options_build() Since v2.5.44 and addition of ip_options_fragment() ip_options_build() does not render headers for fragments directly. @is_frag is always 0. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/ip.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index b51bae43b0dd..fdbab0c00fca 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -712,7 +712,7 @@ int ip_forward(struct sk_buff *skb); */ void ip_options_build(struct sk_buff *skb, struct ip_options *opt, - __be32 daddr, struct rtable *rt, int is_frag); + __be32 daddr, struct rtable *rt); int __ip_options_echo(struct net *net, struct ip_options *dopt, struct sk_buff *skb, const struct ip_options *sopt); -- cgit v1.2.3 From 1713a8de4a3bf7d7d2d5759c895e486885fd1cc3 Mon Sep 17 00:00:00 2001 From: Qianggui Song Date: Thu, 13 Jan 2022 11:10:42 +0800 Subject: dt-bindings: gpio: Add a header file for Amlogic Meson S4 Add a new dt-binding header file which documents the detail pin names. Reviewed-by: Martin Blumenstingl Acked-by: Rob Herring Signed-off-by: Qianggui Song Link: https://lore.kernel.org/r/20220113031044.2665-3-qianggui.song@amlogic.com Signed-off-by: Linus Walleij --- include/dt-bindings/gpio/meson-s4-gpio.h | 99 ++++++++++++++++++++++++++++++++ 1 file changed, 99 insertions(+) create mode 100644 include/dt-bindings/gpio/meson-s4-gpio.h (limited to 'include') diff --git a/include/dt-bindings/gpio/meson-s4-gpio.h b/include/dt-bindings/gpio/meson-s4-gpio.h new file mode 100644 index 000000000000..35aee21b94f1 --- /dev/null +++ b/include/dt-bindings/gpio/meson-s4-gpio.h @@ -0,0 +1,99 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR MIT) */ +/* + * Copyright (c) 2021 Amlogic, Inc. All rights reserved. + * Author: Qianggui Song + */ + +#ifndef _DT_BINDINGS_MESON_S4_GPIO_H +#define _DT_BINDINGS_MESON_S4_GPIO_H + +#define GPIOB_0 0 +#define GPIOB_1 1 +#define GPIOB_2 2 +#define GPIOB_3 3 +#define GPIOB_4 4 +#define GPIOB_5 5 +#define GPIOB_6 6 +#define GPIOB_7 7 +#define GPIOB_8 8 +#define GPIOB_9 9 +#define GPIOB_10 10 +#define GPIOB_11 11 +#define GPIOB_12 12 +#define GPIOB_13 13 + +#define GPIOC_0 14 +#define GPIOC_1 15 +#define GPIOC_2 16 +#define GPIOC_3 17 +#define GPIOC_4 18 +#define GPIOC_5 19 +#define GPIOC_6 20 +#define GPIOC_7 21 + +#define GPIOE_0 22 +#define GPIOE_1 23 + +#define GPIOD_0 24 +#define GPIOD_1 25 +#define GPIOD_2 26 +#define GPIOD_3 27 +#define GPIOD_4 28 +#define GPIOD_5 29 +#define GPIOD_6 30 +#define GPIOD_7 31 +#define GPIOD_8 32 +#define GPIOD_9 33 +#define GPIOD_10 34 +#define GPIOD_11 35 + +#define GPIOH_0 36 +#define GPIOH_1 37 +#define GPIOH_2 38 +#define GPIOH_3 39 +#define GPIOH_4 40 +#define GPIOH_5 41 +#define GPIOH_6 42 +#define GPIOH_7 43 +#define GPIOH_8 44 +#define GPIOH_9 45 +#define GPIOH_10 46 +#define GPIOH_11 47 + +#define GPIOX_0 48 +#define GPIOX_1 49 +#define GPIOX_2 50 +#define GPIOX_3 51 +#define GPIOX_4 52 +#define GPIOX_5 53 +#define GPIOX_6 54 +#define GPIOX_7 55 +#define GPIOX_8 56 +#define GPIOX_9 57 +#define GPIOX_10 58 +#define GPIOX_11 59 +#define GPIOX_12 60 +#define GPIOX_13 61 +#define GPIOX_14 62 +#define GPIOX_15 63 +#define GPIOX_16 64 +#define GPIOX_17 65 +#define GPIOX_18 66 +#define GPIOX_19 67 + +#define GPIOZ_0 68 +#define GPIOZ_1 69 +#define GPIOZ_2 70 +#define GPIOZ_3 71 +#define GPIOZ_4 72 +#define GPIOZ_5 73 +#define GPIOZ_6 74 +#define GPIOZ_7 75 +#define GPIOZ_8 76 +#define GPIOZ_9 77 +#define GPIOZ_10 78 +#define GPIOZ_11 79 +#define GPIOZ_12 80 + +#define GPIO_TEST_N 81 +#endif /* _DT_BINDINGS_MESON_S4_GPIO_H */ -- cgit v1.2.3 From 340407d214e4566c8a5d6997b7ca5ec21c7077a8 Mon Sep 17 00:00:00 2001 From: Wells Lu Date: Sun, 16 Jan 2022 22:52:13 +0800 Subject: dt-bindings: pinctrl: Add dt-bindings for Sunplus SP7021 Add dt-bindings header files and documentation for Sunplus SP7021 SoC. Signed-off-by: Wells Lu Link: https://lore.kernel.org/r/1642344734-27229-2-git-send-email-wellslutw@gmail.com Signed-off-by: Linus Walleij --- include/dt-bindings/pinctrl/sppctl-sp7021.h | 179 ++++++++++++++++++++++++++++ include/dt-bindings/pinctrl/sppctl.h | 31 +++++ 2 files changed, 210 insertions(+) create mode 100644 include/dt-bindings/pinctrl/sppctl-sp7021.h create mode 100644 include/dt-bindings/pinctrl/sppctl.h (limited to 'include') diff --git a/include/dt-bindings/pinctrl/sppctl-sp7021.h b/include/dt-bindings/pinctrl/sppctl-sp7021.h new file mode 100644 index 000000000000..629aa9b5ffbc --- /dev/null +++ b/include/dt-bindings/pinctrl/sppctl-sp7021.h @@ -0,0 +1,179 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Sunplus SP7021 dt-bindings Pinctrl header file + * Copyright (C) Sunplus Tech/Tibbo Tech. + * Author: Dvorkin Dmitry + */ + +#ifndef __DT_BINDINGS_PINCTRL_SPPCTL_SP7021_H__ +#define __DT_BINDINGS_PINCTRL_SPPCTL_SP7021_H__ + +#include + +/* + * Please don't change the order of the following defines. + * They are based on order of 'hardware' control register + * defined in MOON2 ~ MOON3 registers. + */ +#define MUXF_GPIO 0 +#define MUXF_IOP 1 +#define MUXF_L2SW_CLK_OUT 2 +#define MUXF_L2SW_MAC_SMI_MDC 3 +#define MUXF_L2SW_LED_FLASH0 4 +#define MUXF_L2SW_LED_FLASH1 5 +#define MUXF_L2SW_LED_ON0 6 +#define MUXF_L2SW_LED_ON1 7 +#define MUXF_L2SW_MAC_SMI_MDIO 8 +#define MUXF_L2SW_P0_MAC_RMII_TXEN 9 +#define MUXF_L2SW_P0_MAC_RMII_TXD0 10 +#define MUXF_L2SW_P0_MAC_RMII_TXD1 11 +#define MUXF_L2SW_P0_MAC_RMII_CRSDV 12 +#define MUXF_L2SW_P0_MAC_RMII_RXD0 13 +#define MUXF_L2SW_P0_MAC_RMII_RXD1 14 +#define MUXF_L2SW_P0_MAC_RMII_RXER 15 +#define MUXF_L2SW_P1_MAC_RMII_TXEN 16 +#define MUXF_L2SW_P1_MAC_RMII_TXD0 17 +#define MUXF_L2SW_P1_MAC_RMII_TXD1 18 +#define MUXF_L2SW_P1_MAC_RMII_CRSDV 19 +#define MUXF_L2SW_P1_MAC_RMII_RXD0 20 +#define MUXF_L2SW_P1_MAC_RMII_RXD1 21 +#define MUXF_L2SW_P1_MAC_RMII_RXER 22 +#define MUXF_DAISY_MODE 23 +#define MUXF_SDIO_CLK 24 +#define MUXF_SDIO_CMD 25 +#define MUXF_SDIO_D0 26 +#define MUXF_SDIO_D1 27 +#define MUXF_SDIO_D2 28 +#define MUXF_SDIO_D3 29 +#define MUXF_PWM0 30 +#define MUXF_PWM1 31 +#define MUXF_PWM2 32 +#define MUXF_PWM3 33 +#define MUXF_PWM4 34 +#define MUXF_PWM5 35 +#define MUXF_PWM6 36 +#define MUXF_PWM7 37 +#define MUXF_ICM0_D 38 +#define MUXF_ICM1_D 39 +#define MUXF_ICM2_D 40 +#define MUXF_ICM3_D 41 +#define MUXF_ICM0_CLK 42 +#define MUXF_ICM1_CLK 43 +#define MUXF_ICM2_CLK 44 +#define MUXF_ICM3_CLK 45 +#define MUXF_SPIM0_INT 46 +#define MUXF_SPIM0_CLK 47 +#define MUXF_SPIM0_EN 48 +#define MUXF_SPIM0_DO 49 +#define MUXF_SPIM0_DI 50 +#define MUXF_SPIM1_INT 51 +#define MUXF_SPIM1_CLK 52 +#define MUXF_SPIM1_EN 53 +#define MUXF_SPIM1_DO 54 +#define MUXF_SPIM1_DI 55 +#define MUXF_SPIM2_INT 56 +#define MUXF_SPIM2_CLK 57 +#define MUXF_SPIM2_EN 58 +#define MUXF_SPIM2_DO 59 +#define MUXF_SPIM2_DI 60 +#define MUXF_SPIM3_INT 61 +#define MUXF_SPIM3_CLK 62 +#define MUXF_SPIM3_EN 63 +#define MUXF_SPIM3_DO 64 +#define MUXF_SPIM3_DI 65 +#define MUXF_SPI0S_INT 66 +#define MUXF_SPI0S_CLK 67 +#define MUXF_SPI0S_EN 68 +#define MUXF_SPI0S_DO 69 +#define MUXF_SPI0S_DI 70 +#define MUXF_SPI1S_INT 71 +#define MUXF_SPI1S_CLK 72 +#define MUXF_SPI1S_EN 73 +#define MUXF_SPI1S_DO 74 +#define MUXF_SPI1S_DI 75 +#define MUXF_SPI2S_INT 76 +#define MUXF_SPI2S_CLK 77 +#define MUXF_SPI2S_EN 78 +#define MUXF_SPI2S_DO 79 +#define MUXF_SPI2S_DI 80 +#define MUXF_SPI3S_INT 81 +#define MUXF_SPI3S_CLK 82 +#define MUXF_SPI3S_EN 83 +#define MUXF_SPI3S_DO 84 +#define MUXF_SPI3S_DI 85 +#define MUXF_I2CM0_CLK 86 +#define MUXF_I2CM0_DAT 87 +#define MUXF_I2CM1_CLK 88 +#define MUXF_I2CM1_DAT 89 +#define MUXF_I2CM2_CLK 90 +#define MUXF_I2CM2_DAT 91 +#define MUXF_I2CM3_CLK 92 +#define MUXF_I2CM3_DAT 93 +#define MUXF_UA1_TX 94 +#define MUXF_UA1_RX 95 +#define MUXF_UA1_CTS 96 +#define MUXF_UA1_RTS 97 +#define MUXF_UA2_TX 98 +#define MUXF_UA2_RX 99 +#define MUXF_UA2_CTS 100 +#define MUXF_UA2_RTS 101 +#define MUXF_UA3_TX 102 +#define MUXF_UA3_RX 103 +#define MUXF_UA3_CTS 104 +#define MUXF_UA3_RTS 105 +#define MUXF_UA4_TX 106 +#define MUXF_UA4_RX 107 +#define MUXF_UA4_CTS 108 +#define MUXF_UA4_RTS 109 +#define MUXF_TIMER0_INT 110 +#define MUXF_TIMER1_INT 111 +#define MUXF_TIMER2_INT 112 +#define MUXF_TIMER3_INT 113 +#define MUXF_GPIO_INT0 114 +#define MUXF_GPIO_INT1 115 +#define MUXF_GPIO_INT2 116 +#define MUXF_GPIO_INT3 117 +#define MUXF_GPIO_INT4 118 +#define MUXF_GPIO_INT5 119 +#define MUXF_GPIO_INT6 120 +#define MUXF_GPIO_INT7 121 + +/* + * Please don't change the order of the following defines. + * They are based on order of items in array 'sppctl_list_funcs' + * in Sunplus pinctrl driver. + */ +#define GROP_SPI_FLASH 122 +#define GROP_SPI_FLASH_4BIT 123 +#define GROP_SPI_NAND 124 +#define GROP_CARD0_EMMC 125 +#define GROP_SD_CARD 126 +#define GROP_UA0 127 +#define GROP_ACHIP_DEBUG 128 +#define GROP_ACHIP_UA2AXI 129 +#define GROP_FPGA_IFX 130 +#define GROP_HDMI_TX 131 +#define GROP_AUD_EXT_ADC_IFX0 132 +#define GROP_AUD_EXT_DAC_IFX0 133 +#define GROP_SPDIF_RX 134 +#define GROP_SPDIF_TX 135 +#define GROP_TDMTX_IFX0 136 +#define GROP_TDMRX_IFX0 137 +#define GROP_PDMRX_IFX0 138 +#define GROP_PCM_IEC_TX 139 +#define GROP_LCDIF 140 +#define GROP_DVD_DSP_DEBUG 141 +#define GROP_I2C_DEBUG 142 +#define GROP_I2C_SLAVE 143 +#define GROP_WAKEUP 144 +#define GROP_UART2AXI 145 +#define GROP_USB0_I2C 146 +#define GROP_USB1_I2C 147 +#define GROP_USB0_OTG 148 +#define GROP_USB1_OTG 149 +#define GROP_UPHY0_DEBUG 150 +#define GROP_UPHY1_DEBUG 151 +#define GROP_UPHY0_EXT 152 +#define GROP_PROBE_PORT 153 + +#endif diff --git a/include/dt-bindings/pinctrl/sppctl.h b/include/dt-bindings/pinctrl/sppctl.h new file mode 100644 index 000000000000..50557265dbfc --- /dev/null +++ b/include/dt-bindings/pinctrl/sppctl.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Sunplus dt-bindings Pinctrl header file + * Copyright (C) Sunplus Tech / Tibbo Tech. + * Author: Dvorkin Dmitry + */ + +#ifndef __DT_BINDINGS_PINCTRL_SPPCTL_H__ +#define __DT_BINDINGS_PINCTRL_SPPCTL_H__ + +#define IOP_G_MASTE (0x01 << 0) +#define IOP_G_FIRST (0x01 << 1) + +#define SPPCTL_PCTL_G_PMUX (0x00 | IOP_G_MASTE) +#define SPPCTL_PCTL_G_GPIO (IOP_G_FIRST | IOP_G_MASTE) +#define SPPCTL_PCTL_G_IOPP (IOP_G_FIRST | 0x00) + +#define SPPCTL_PCTL_L_OUT (0x01 << 0) /* Output LOW */ +#define SPPCTL_PCTL_L_OU1 (0x01 << 1) /* Output HIGH */ +#define SPPCTL_PCTL_L_INV (0x01 << 2) /* Input Invert */ +#define SPPCTL_PCTL_L_ONV (0x01 << 3) /* Output Invert */ +#define SPPCTL_PCTL_L_ODR (0x01 << 4) /* Output Open Drain */ + +/* + * pack into 32-bit value: + * pin# (8bit), typ (8bit), function (8bit), flag (8bit) + */ +#define SPPCTL_IOPAD(pin, typ, fun, flg) (((pin) << 24) | ((typ) << 16) | \ + ((fun) << 8) | (flg)) + +#endif -- cgit v1.2.3 From e820a33748b5e22cecafddf919a7d8679949deb1 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 26 Jan 2022 15:53:50 +0200 Subject: math.h: Introduce data types for fractional numbers Introduce a macro to produce data types like struct TYPE_fract { __TYPE numerator; __TYPE denominator; }; to be used in the code wherever it's needed. In the following changes convert some users to it. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20220126135353.24007-1-andriy.shevchenko@linux.intel.com Signed-off-by: Jonathan Cameron --- include/linux/math.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/math.h b/include/linux/math.h index 53674a327e39..439b8f0b9ebd 100644 --- a/include/linux/math.h +++ b/include/linux/math.h @@ -2,6 +2,7 @@ #ifndef _LINUX_MATH_H #define _LINUX_MATH_H +#include #include #include @@ -106,6 +107,17 @@ } \ ) +#define __STRUCT_FRACT(type) \ +struct type##_fract { \ + __##type numerator; \ + __##type denominator; \ +}; +__STRUCT_FRACT(s16) +__STRUCT_FRACT(u16) +__STRUCT_FRACT(s32) +__STRUCT_FRACT(u32) +#undef __STRUCT_FRACT + /* * Multiplies an integer by a fraction, while avoiding unnecessary * overflow or loss of precision. -- cgit v1.2.3 From a5e9b2ddbbc789f34be2333263232435d8edf57c Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 26 Jan 2022 15:53:53 +0200 Subject: iio: adc: qcom-vadc-common: Re-use generic struct u32_fract Instead of custom data type re-use generic struct u32_fract. No changes intended. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20220126135353.24007-4-andriy.shevchenko@linux.intel.com Signed-off-by: Jonathan Cameron --- include/linux/iio/adc/qcom-vadc-common.h | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/iio/adc/qcom-vadc-common.h b/include/linux/iio/adc/qcom-vadc-common.h index 33f60f43e1aa..ce78d4804994 100644 --- a/include/linux/iio/adc/qcom-vadc-common.h +++ b/include/linux/iio/adc/qcom-vadc-common.h @@ -6,6 +6,7 @@ #ifndef QCOM_VADC_COMMON_H #define QCOM_VADC_COMMON_H +#include #include #define VADC_CONV_TIME_MIN_US 2000 @@ -79,16 +80,6 @@ struct vadc_linear_graph { s32 gnd; }; -/** - * struct vadc_prescale_ratio - Represent scaling ratio for ADC input. - * @num: the inverse numerator of the gain applied to the input channel. - * @den: the inverse denominator of the gain applied to the input channel. - */ -struct vadc_prescale_ratio { - u32 num; - u32 den; -}; - /** * enum vadc_scale_fn_type - Scaling function to convert ADC code to * physical scaled units for the channel. @@ -144,12 +135,12 @@ struct adc5_data { int qcom_vadc_scale(enum vadc_scale_fn_type scaletype, const struct vadc_linear_graph *calib_graph, - const struct vadc_prescale_ratio *prescale, + const struct u32_fract *prescale, bool absolute, u16 adc_code, int *result_mdec); struct qcom_adc5_scale_type { - int (*scale_fn)(const struct vadc_prescale_ratio *prescale, + int (*scale_fn)(const struct u32_fract *prescale, const struct adc5_data *data, u16 adc_code, int *result); }; -- cgit v1.2.3 From 73c105ad2a3e142d81fc59761ce8353d0b211b8f Mon Sep 17 00:00:00 2001 From: Sergey Shtylyov Date: Fri, 28 Jan 2022 21:32:40 +0300 Subject: phy: make phy_set_max_speed() *void* After following the call tree of phy_set_max_speed(), it became clear that this function never returns anything but 0, so we can change its result type to *void* and drop the result checks from the three drivers that actually bothered to do it... Found by Linux Verification Center (linuxtesting.org) with the SVACE static analysis tool. Signed-off-by: Sergey Shtylyov Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index 6de8d7a90d78..cd08cf1a8b0d 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1661,7 +1661,7 @@ int phy_disable_interrupts(struct phy_device *phydev); void phy_request_interrupt(struct phy_device *phydev); void phy_free_interrupt(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); -int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); +void phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); void phy_advertise_supported(struct phy_device *phydev); void phy_support_sym_pause(struct phy_device *phydev); -- cgit v1.2.3 From 47ed9442b2ecfcdc72889667236d6c59b6a3337e Mon Sep 17 00:00:00 2001 From: David Ahern Date: Fri, 28 Jan 2022 16:53:47 -0700 Subject: ipv4: Make ip_idents_reserve static ip_idents_reserve is only used in net/ipv4/route.c. Make it static and remove the export. Signed-off-by: David Ahern Cc: Eric Dumazet Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index fdbab0c00fca..3984f2c39c4b 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -517,7 +517,6 @@ void ip_dst_metrics_put(struct dst_entry *dst) kfree(p); } -u32 ip_idents_reserve(u32 hash, int segs); void __ip_select_ident(struct net *net, struct iphdr *iph, int segs); static inline void ip_select_ident_segs(struct net *net, struct sk_buff *skb, -- cgit v1.2.3 From 13e906e50a8cf6033f22c03c4d772e36a9e02c6b Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Thu, 27 Jan 2022 12:01:07 -0800 Subject: component: Replace most references to 'master' with 'aggregate device' Remove most references to 'master' in the code and replace them with some form of 'aggregate device'. This better reflects the reality of what this code does, i.e. an aggregate device that represents a device like a GPU card once some set of devices that make up the aggregate device probe and register with the component framework. Cc: Daniel Vetter Cc: Greg Kroah-Hartman Cc: Laurent Pinchart Cc: "Rafael J. Wysocki" Cc: Rob Clark Cc: Russell King Cc: Saravana Kannan Signed-off-by: Stephen Boyd Link: https://lore.kernel.org/r/20220127200141.1295328-2-swboyd@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/component.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/component.h b/include/linux/component.h index 16de18f473d7..7012569c6546 100644 --- a/include/linux/component.h +++ b/include/linux/component.h @@ -38,10 +38,10 @@ int component_add_typed(struct device *dev, const struct component_ops *ops, int subcomponent); void component_del(struct device *, const struct component_ops *); -int component_bind_all(struct device *master, void *master_data); -void component_unbind_all(struct device *master, void *master_data); +int component_bind_all(struct device *parent, void *data); +void component_unbind_all(struct device *parent, void *data); -struct master; +struct aggregate_device; /** * struct component_master_ops - callback for the aggregate driver @@ -89,22 +89,22 @@ struct component_match; int component_master_add_with_match(struct device *, const struct component_master_ops *, struct component_match *); -void component_match_add_release(struct device *master, +void component_match_add_release(struct device *parent, struct component_match **matchptr, void (*release)(struct device *, void *), int (*compare)(struct device *, void *), void *compare_data); -void component_match_add_typed(struct device *master, +void component_match_add_typed(struct device *parent, struct component_match **matchptr, int (*compare_typed)(struct device *, int, void *), void *compare_data); /** * component_match_add - add a component match entry - * @master: device with the aggregate driver + * @parent: device with the aggregate driver * @matchptr: pointer to the list of component matches * @compare: compare function to match against all components * @compare_data: opaque pointer passed to the @compare function * - * Adds a new component match to the list stored in @matchptr, which the @master + * Adds a new component match to the list stored in @matchptr, which the @parent * aggregate driver needs to function. The list of component matches pointed to * by @matchptr must be initialized to NULL before adding the first match. This * only matches against components added with component_add(). @@ -114,11 +114,11 @@ void component_match_add_typed(struct device *master, * * See also component_match_add_release() and component_match_add_typed(). */ -static inline void component_match_add(struct device *master, +static inline void component_match_add(struct device *parent, struct component_match **matchptr, int (*compare)(struct device *, void *), void *compare_data) { - component_match_add_release(master, matchptr, NULL, compare, + component_match_add_release(parent, matchptr, NULL, compare, compare_data); } -- cgit v1.2.3 From e187013abeb4c2a7ec8a4bb978844c7e92a1a6ec Mon Sep 17 00:00:00 2001 From: Akhmat Karakotov Date: Mon, 31 Jan 2022 16:31:21 +0300 Subject: txhash: Make rethinking txhash behavior configurable via sysctl Add a per ns sysctl that controls the txhash rethink behavior: net.core.txrehash. When enabled, the same behavior is retained, when disabled, rethink is not performed. Sysctl is enabled by default. Signed-off-by: Akhmat Karakotov Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/netns/core.h | 1 + include/net/sock.h | 34 +++++++++++++++++++++------------- include/uapi/linux/socket.h | 3 +++ 3 files changed, 25 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/net/netns/core.h b/include/net/netns/core.h index 552bc25b1933..388244e315e7 100644 --- a/include/net/netns/core.h +++ b/include/net/netns/core.h @@ -10,6 +10,7 @@ struct netns_core { struct ctl_table_header *sysctl_hdr; int sysctl_somaxconn; + u8 sysctl_txrehash; #ifdef CONFIG_PROC_FS struct prot_inuse __percpu *prot_inuse; diff --git a/include/net/sock.h b/include/net/sock.h index ff9b508d9c5f..0540e1b2aeb0 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -587,6 +587,18 @@ static inline bool sk_user_data_is_nocopy(const struct sock *sk) __tmp | SK_USER_DATA_NOCOPY); \ }) +static inline +struct net *sock_net(const struct sock *sk) +{ + return read_pnet(&sk->sk_net); +} + +static inline +void sock_net_set(struct sock *sk, struct net *net) +{ + write_pnet(&sk->sk_net, net); +} + /* * SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK * or not whether his port will be reused by someone else. SK_FORCE_REUSE @@ -2054,10 +2066,18 @@ static inline void sk_set_txhash(struct sock *sk) static inline bool sk_rethink_txhash(struct sock *sk) { - if (sk->sk_txhash) { + u8 rehash; + + if (!sk->sk_txhash) + return false; + + rehash = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); + + if (rehash) { sk_set_txhash(sk); return true; } + return false; } @@ -2704,18 +2724,6 @@ static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb) __kfree_skb(skb); } -static inline -struct net *sock_net(const struct sock *sk) -{ - return read_pnet(&sk->sk_net); -} - -static inline -void sock_net_set(struct sock *sk, struct net *net) -{ - write_pnet(&sk->sk_net, net); -} - static inline bool skb_sk_is_prefetched(struct sk_buff *skb) { diff --git a/include/uapi/linux/socket.h b/include/uapi/linux/socket.h index eb0a9a5b6e71..0accd6102ece 100644 --- a/include/uapi/linux/socket.h +++ b/include/uapi/linux/socket.h @@ -31,4 +31,7 @@ struct __kernel_sockaddr_storage { #define SOCK_BUF_LOCK_MASK (SOCK_SNDBUF_LOCK | SOCK_RCVBUF_LOCK) +#define SOCK_TXREHASH_DISABLED 0 +#define SOCK_TXREHASH_ENABLED 1 + #endif /* _UAPI_LINUX_SOCKET_H */ -- cgit v1.2.3 From 26859240e4ee701e0379f08634957adaff67e43a Mon Sep 17 00:00:00 2001 From: Akhmat Karakotov Date: Mon, 31 Jan 2022 16:31:22 +0300 Subject: txhash: Add socket option to control TX hash rethink behavior Add the SO_TXREHASH socket option to control hash rethink behavior per socket. When default mode is set, sockets disable rehash at initialization and use sysctl option when entering listen state. setsockopt() overrides default behavior. Signed-off-by: Akhmat Karakotov Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 12 +++--------- include/uapi/asm-generic/socket.h | 2 ++ include/uapi/linux/socket.h | 1 + 3 files changed, 6 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 0540e1b2aeb0..d6c13f0fba40 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -316,6 +316,7 @@ struct sk_filter; * @sk_rcvtimeo: %SO_RCVTIMEO setting * @sk_sndtimeo: %SO_SNDTIMEO setting * @sk_txhash: computed flow hash for use on transmit + * @sk_txrehash: enable TX hash rethink * @sk_filter: socket filtering instructions * @sk_timer: sock cleanup timer * @sk_stamp: time stamp of last packet received @@ -491,6 +492,7 @@ struct sock { u32 sk_ack_backlog; u32 sk_max_ack_backlog; kuid_t sk_uid; + u8 sk_txrehash; #ifdef CONFIG_NET_RX_BUSY_POLL u8 sk_prefer_busy_poll; u16 sk_busy_poll_budget; @@ -2066,18 +2068,10 @@ static inline void sk_set_txhash(struct sock *sk) static inline bool sk_rethink_txhash(struct sock *sk) { - u8 rehash; - - if (!sk->sk_txhash) - return false; - - rehash = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); - - if (rehash) { + if (sk->sk_txhash && sk->sk_txrehash == SOCK_TXREHASH_ENABLED) { sk_set_txhash(sk); return true; } - return false; } diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index c77a1313b3b0..467ca2f28760 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -128,6 +128,8 @@ #define SO_RESERVE_MEM 73 +#define SO_TXREHASH 74 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/include/uapi/linux/socket.h b/include/uapi/linux/socket.h index 0accd6102ece..51d6bb2f6765 100644 --- a/include/uapi/linux/socket.h +++ b/include/uapi/linux/socket.h @@ -31,6 +31,7 @@ struct __kernel_sockaddr_storage { #define SOCK_BUF_LOCK_MASK (SOCK_SNDBUF_LOCK | SOCK_RCVBUF_LOCK) +#define SOCK_TXREHASH_DEFAULT ((u8)-1) #define SOCK_TXREHASH_DISABLED 0 #define SOCK_TXREHASH_ENABLED 1 -- cgit v1.2.3 From 31455bbda2081af83f72bb4636348b12b82c37c1 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 25 Jan 2022 01:58:36 +0100 Subject: spi: pxa2xx_spi: Convert to use GPIO descriptors This converts the PXA2xx SPI driver to use GPIO descriptors exclusively to retrieve GPIO chip select lines. The device tree and ACPI paths of the driver already use descriptors, hence ->use_gpio_descriptors is already set and this codepath is well tested. Convert all the PXA boards providing chip select GPIOs as platform data and drop the old GPIO chipselect handling in favor of the core managing it exclusively. Cc: Marek Vasut Cc: Daniel Mack Cc: Haojian Zhuang Cc: Robert Jarzmik Cc: linux-arm-kernel@lists.infradead.org Acked-by: Jonathan Cameron Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20220125005836.494807-1-linus.walleij@linaro.org Signed-off-by: Mark Brown --- include/linux/spi/pxa2xx_spi.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h index ca74dce36706..4658e7801b42 100644 --- a/include/linux/spi/pxa2xx_spi.h +++ b/include/linux/spi/pxa2xx_spi.h @@ -42,7 +42,6 @@ struct pxa2xx_spi_chip { u8 rx_threshold; u8 dma_burst_size; u32 timeout; - int gpio_cs; }; #if defined(CONFIG_ARCH_PXA) || defined(CONFIG_ARCH_MMP) -- cgit v1.2.3 From 6419abb80e82c603bbec6d7f5af6c2f79fa5c4ae Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Tue, 25 Jan 2022 13:00:09 -0800 Subject: kunit: remove va_format from kunit_assert The concern is that having a lot of redundant fields in kunit_assert can blow up stack usage if the compiler doesn't optimize them away [1]. The comment on this field implies that it was meant to be initialized when the expect/assert was declared, but this only happens when we run kunit_do_failed_assertion(). We don't need to access it outside of that function, so move it out of the struct and make it a local variable there. This change also takes the chance to reduce the number of macros by inlining the now simplified KUNIT_INIT_ASSERT_STRUCT() macro. [1] https://groups.google.com/g/kunit-dev/c/i3fZXgvBrfA/m/VULQg1z6BAAJ Signed-off-by: Daniel Latypov Reviewed-by: David Gow Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- include/kunit/assert.h | 43 +++++++++++++------------------------------ 1 file changed, 13 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/kunit/assert.h b/include/kunit/assert.h index f2b3ae5cc2de..0b3704db54b6 100644 --- a/include/kunit/assert.h +++ b/include/kunit/assert.h @@ -42,44 +42,21 @@ struct kunit_loc { /** * struct kunit_assert - Data for printing a failed assertion or expectation. - * @message: an optional message to provide additional context. * @format: a function which formats the data in this kunit_assert to a string. * * Represents a failed expectation/assertion. Contains all the data necessary to * format a string to a user reporting the failure. */ struct kunit_assert { - struct va_format message; void (*format)(const struct kunit_assert *assert, + const struct va_format *message, struct string_stream *stream); }; -/** - * KUNIT_INIT_VA_FMT_NULL - Default initializer for struct va_format. - * - * Used inside a struct initialization block to initialize struct va_format to - * default values where fmt and va are null. - */ -#define KUNIT_INIT_VA_FMT_NULL { .fmt = NULL, .va = NULL } - -/** - * KUNIT_INIT_ASSERT_STRUCT() - Initializer for a &struct kunit_assert. - * @fmt: The formatting function which builds a string out of this kunit_assert. - * - * The base initializer for a &struct kunit_assert. - */ -#define KUNIT_INIT_ASSERT_STRUCT(fmt) { \ - .message = KUNIT_INIT_VA_FMT_NULL, \ - .format = fmt \ -} - void kunit_assert_prologue(const struct kunit_loc *loc, enum kunit_assert_type type, struct string_stream *stream); -void kunit_assert_print_msg(const struct kunit_assert *assert, - struct string_stream *stream); - /** * struct kunit_fail_assert - Represents a plain fail expectation/assertion. * @assert: The parent of this type. @@ -91,6 +68,7 @@ struct kunit_fail_assert { }; void kunit_fail_assert_format(const struct kunit_assert *assert, + const struct va_format *message, struct string_stream *stream); /** @@ -100,7 +78,7 @@ void kunit_fail_assert_format(const struct kunit_assert *assert, * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. */ #define KUNIT_INIT_FAIL_ASSERT_STRUCT { \ - .assert = KUNIT_INIT_ASSERT_STRUCT(kunit_fail_assert_format) \ + .assert = { .format = kunit_fail_assert_format }, \ } /** @@ -120,6 +98,7 @@ struct kunit_unary_assert { }; void kunit_unary_assert_format(const struct kunit_assert *assert, + const struct va_format *message, struct string_stream *stream); /** @@ -131,7 +110,7 @@ void kunit_unary_assert_format(const struct kunit_assert *assert, * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. */ #define KUNIT_INIT_UNARY_ASSERT_STRUCT(cond, expect_true) { \ - .assert = KUNIT_INIT_ASSERT_STRUCT(kunit_unary_assert_format), \ + .assert = { .format = kunit_unary_assert_format }, \ .condition = cond, \ .expected_true = expect_true \ } @@ -153,6 +132,7 @@ struct kunit_ptr_not_err_assert { }; void kunit_ptr_not_err_assert_format(const struct kunit_assert *assert, + const struct va_format *message, struct string_stream *stream); /** @@ -165,7 +145,7 @@ void kunit_ptr_not_err_assert_format(const struct kunit_assert *assert, * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. */ #define KUNIT_INIT_PTR_NOT_ERR_STRUCT(txt, val) { \ - .assert = KUNIT_INIT_ASSERT_STRUCT(kunit_ptr_not_err_assert_format), \ + .assert = { .format = kunit_ptr_not_err_assert_format }, \ .text = txt, \ .value = val \ } @@ -194,6 +174,7 @@ struct kunit_binary_assert { }; void kunit_binary_assert_format(const struct kunit_assert *assert, + const struct va_format *message, struct string_stream *stream); /** @@ -213,7 +194,7 @@ void kunit_binary_assert_format(const struct kunit_assert *assert, left_val, \ right_str, \ right_val) { \ - .assert = KUNIT_INIT_ASSERT_STRUCT(kunit_binary_assert_format), \ + .assert = { .format = kunit_binary_assert_format }, \ .operation = op_str, \ .left_text = left_str, \ .left_value = left_val, \ @@ -245,6 +226,7 @@ struct kunit_binary_ptr_assert { }; void kunit_binary_ptr_assert_format(const struct kunit_assert *assert, + const struct va_format *message, struct string_stream *stream); /** @@ -265,7 +247,7 @@ void kunit_binary_ptr_assert_format(const struct kunit_assert *assert, left_val, \ right_str, \ right_val) { \ - .assert = KUNIT_INIT_ASSERT_STRUCT(kunit_binary_ptr_assert_format), \ + .assert = { .format = kunit_binary_ptr_assert_format }, \ .operation = op_str, \ .left_text = left_str, \ .left_value = left_val, \ @@ -297,6 +279,7 @@ struct kunit_binary_str_assert { }; void kunit_binary_str_assert_format(const struct kunit_assert *assert, + const struct va_format *message, struct string_stream *stream); /** @@ -316,7 +299,7 @@ void kunit_binary_str_assert_format(const struct kunit_assert *assert, left_val, \ right_str, \ right_val) { \ - .assert = KUNIT_INIT_ASSERT_STRUCT(kunit_binary_str_assert_format), \ + .assert = { .format = kunit_binary_str_assert_format }, \ .operation = op_str, \ .left_text = left_str, \ .left_value = left_val, \ -- cgit v1.2.3 From 064ff292aca500d6b911dca6abe1ece22620d475 Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Tue, 25 Jan 2022 13:00:10 -0800 Subject: kunit: consolidate KUNIT_INIT_BINARY_ASSERT_STRUCT macros We currently have 2 other versions of KUNIT_INIT_BINARY_ASSERT_STRUCT. The only differences are that * the format funcition they pass is different * the types of left_val/right_val should be different (integral, pointer, string). The latter doesn't actually matter since these macros are just plumbing them along to KUNIT_ASSERTION where they will get type checked. So combine them all into a single KUNIT_INIT_BINARY_ASSERT_STRUCT that now also takes the format function as a parameter. Signed-off-by: Daniel Latypov Reviewed-by: David Gow Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- include/kunit/assert.h | 68 ++++++++------------------------------------------ include/kunit/test.h | 20 ++++++++------- 2 files changed, 22 insertions(+), 66 deletions(-) (limited to 'include') diff --git a/include/kunit/assert.h b/include/kunit/assert.h index 0b3704db54b6..649bfac9f406 100644 --- a/include/kunit/assert.h +++ b/include/kunit/assert.h @@ -178,23 +178,28 @@ void kunit_binary_assert_format(const struct kunit_assert *assert, struct string_stream *stream); /** - * KUNIT_INIT_BINARY_ASSERT_STRUCT() - Initializes a - * &struct kunit_binary_assert. + * KUNIT_INIT_BINARY_ASSERT_STRUCT() - Initializes a binary assert like + * kunit_binary_assert, kunit_binary_ptr_assert, etc. + * + * @format_func: a function which formats the assert to a string. * @op_str: A string representation of the comparison operator (e.g. "=="). * @left_str: A string representation of the expression in the left slot. * @left_val: The actual evaluated value of the expression in the left slot. * @right_str: A string representation of the expression in the right slot. * @right_val: The actual evaluated value of the expression in the right slot. * - * Initializes a &struct kunit_binary_assert. Intended to be used in - * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. + * Initializes a binary assert like kunit_binary_assert, + * kunit_binary_ptr_assert, etc. This relies on these structs having the same + * fields but with different types for left_val/right_val. + * This is ultimately used by binary assertion macros like KUNIT_EXPECT_EQ, etc. */ -#define KUNIT_INIT_BINARY_ASSERT_STRUCT(op_str, \ +#define KUNIT_INIT_BINARY_ASSERT_STRUCT(format_func, \ + op_str, \ left_str, \ left_val, \ right_str, \ right_val) { \ - .assert = { .format = kunit_binary_assert_format }, \ + .assert = { .format = format_func }, \ .operation = op_str, \ .left_text = left_str, \ .left_value = left_val, \ @@ -229,32 +234,6 @@ void kunit_binary_ptr_assert_format(const struct kunit_assert *assert, const struct va_format *message, struct string_stream *stream); -/** - * KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT() - Initializes a - * &struct kunit_binary_ptr_assert. - * @type: The type (assertion or expectation) of this kunit_assert. - * @op_str: A string representation of the comparison operator (e.g. "=="). - * @left_str: A string representation of the expression in the left slot. - * @left_val: The actual evaluated value of the expression in the left slot. - * @right_str: A string representation of the expression in the right slot. - * @right_val: The actual evaluated value of the expression in the right slot. - * - * Initializes a &struct kunit_binary_ptr_assert. Intended to be used in - * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. - */ -#define KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT(op_str, \ - left_str, \ - left_val, \ - right_str, \ - right_val) { \ - .assert = { .format = kunit_binary_ptr_assert_format }, \ - .operation = op_str, \ - .left_text = left_str, \ - .left_value = left_val, \ - .right_text = right_str, \ - .right_value = right_val \ -} - /** * struct kunit_binary_str_assert - An expectation/assertion that compares two * string values (for example, KUNIT_EXPECT_STREQ(test, foo, "bar")). @@ -282,29 +261,4 @@ void kunit_binary_str_assert_format(const struct kunit_assert *assert, const struct va_format *message, struct string_stream *stream); -/** - * KUNIT_INIT_BINARY_STR_ASSERT_STRUCT() - Initializes a - * &struct kunit_binary_str_assert. - * @op_str: A string representation of the comparison operator (e.g. "=="). - * @left_str: A string representation of the expression in the left slot. - * @left_val: The actual evaluated value of the expression in the left slot. - * @right_str: A string representation of the expression in the right slot. - * @right_val: The actual evaluated value of the expression in the right slot. - * - * Initializes a &struct kunit_binary_str_assert. Intended to be used in - * KUNIT_EXPECT_* and KUNIT_ASSERT_* macros. - */ -#define KUNIT_INIT_BINARY_STR_ASSERT_STRUCT(op_str, \ - left_str, \ - left_val, \ - right_str, \ - right_val) { \ - .assert = { .format = kunit_binary_str_assert_format }, \ - .operation = op_str, \ - .left_text = left_str, \ - .left_value = left_val, \ - .right_text = right_str, \ - .right_value = right_val \ -} - #endif /* _KUNIT_ASSERT_H */ diff --git a/include/kunit/test.h b/include/kunit/test.h index bf82c313223b..a93dfb8ff393 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -864,7 +864,7 @@ void kunit_do_failed_assertion(struct kunit *test, */ #define KUNIT_BASE_BINARY_ASSERTION(test, \ assert_class, \ - ASSERT_CLASS_INIT, \ + format_func, \ assert_type, \ left, \ op, \ @@ -879,11 +879,12 @@ do { \ assert_type, \ __left op __right, \ assert_class, \ - ASSERT_CLASS_INIT(#op, \ - #left, \ - __left, \ - #right, \ - __right), \ + KUNIT_INIT_BINARY_ASSERT_STRUCT(format_func, \ + #op, \ + #left, \ + __left, \ + #right, \ + __right), \ fmt, \ ##__VA_ARGS__); \ } while (0) @@ -897,7 +898,7 @@ do { \ ...) \ KUNIT_BASE_BINARY_ASSERTION(test, \ kunit_binary_assert, \ - KUNIT_INIT_BINARY_ASSERT_STRUCT, \ + kunit_binary_assert_format, \ assert_type, \ left, op, right, \ fmt, \ @@ -912,7 +913,7 @@ do { \ ...) \ KUNIT_BASE_BINARY_ASSERTION(test, \ kunit_binary_ptr_assert, \ - KUNIT_INIT_BINARY_PTR_ASSERT_STRUCT, \ + kunit_binary_ptr_assert_format, \ assert_type, \ left, op, right, \ fmt, \ @@ -933,7 +934,8 @@ do { \ assert_type, \ strcmp(__left, __right) op 0, \ kunit_binary_str_assert, \ - KUNIT_INIT_BINARY_STR_ASSERT_STRUCT(#op, \ + KUNIT_INIT_BINARY_ASSERT_STRUCT(kunit_binary_str_assert_format,\ + #op, \ #left, \ __left, \ #right, \ -- cgit v1.2.3 From 2b6861e2372bac68861c54372f68f6016a7484fc Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Tue, 25 Jan 2022 13:00:11 -0800 Subject: kunit: factor out str constants from binary assertion structs If the compiler doesn't optimize them away, each kunit assertion (use of KUNIT_EXPECT_EQ, etc.) can use 88 bytes of stack space in the worst and most common case. This has led to compiler warnings and a suggestion from Linus to move data from the structs into static const's where possible [1]. This builds upon [2] which did so for the base struct kunit_assert type. That only reduced sizeof(struct kunit_binary_assert) from 88 to 64. Given these are by far the most commonly used asserts, this patch factors out the textual representations of the operands and comparator into another static const, saving 16 more bytes. In detail, KUNIT_EXPECT_EQ(test, 2 + 2, 5) yields the following struct (struct kunit_binary_assert) { .assert = , .operation = "==", .left_text = "2 + 2", .left_value = 4, .right_text = "5", .right_value = 5, } After this change static const struct kunit_binary_assert_text __text = { .operation = "==", .left_text = "2 + 2", .right_text = "5", }; (struct kunit_binary_assert) { .assert = , .text = &__text, .left_value = 4, .right_value = 5, } This also DRYs the code a bit more since these str fields were repeated for the string and pointer versions of kunit_binary_assert. Note: we could name the kunit_binary_assert_text fields left/right instead of left_text/right_text. But that would require changing the macros a bit since they have args called "left" and "right" which would be substituted in `.left = #left` as `.2 + 2 = \"2 + 2\"`. [1] https://groups.google.com/g/kunit-dev/c/i3fZXgvBrfA/m/VULQg1z6BAAJ [2] https://lore.kernel.org/linux-kselftest/20220113165931.451305-6-dlatypov@google.com/ Signed-off-by: Daniel Latypov Reviewed-by: David Gow Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- include/kunit/assert.h | 49 ++++++++++++++++++++++--------------------------- include/kunit/test.h | 20 +++++++++++++------- 2 files changed, 35 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/include/kunit/assert.h b/include/kunit/assert.h index 649bfac9f406..4b52e12c2ae8 100644 --- a/include/kunit/assert.h +++ b/include/kunit/assert.h @@ -150,14 +150,25 @@ void kunit_ptr_not_err_assert_format(const struct kunit_assert *assert, .value = val \ } +/** + * struct kunit_binary_assert_text - holds strings for &struct + * kunit_binary_assert and friends to try and make the structs smaller. + * @operation: A string representation of the comparison operator (e.g. "=="). + * @left_text: A string representation of the left expression (e.g. "2+2"). + * @right_text: A string representation of the right expression (e.g. "2+2"). + */ +struct kunit_binary_assert_text { + const char *operation; + const char *left_text; + const char *right_text; +}; + /** * struct kunit_binary_assert - An expectation/assertion that compares two * non-pointer values (for example, KUNIT_EXPECT_EQ(test, 1 + 1, 2)). * @assert: The parent of this type. - * @operation: A string representation of the comparison operator (e.g. "=="). - * @left_text: A string representation of the expression in the left slot. + * @text: Holds the textual representations of the operands and op (e.g. "=="). * @left_value: The actual evaluated value of the expression in the left slot. - * @right_text: A string representation of the expression in the right slot. * @right_value: The actual evaluated value of the expression in the right slot. * * Represents an expectation/assertion that compares two non-pointer values. For @@ -166,10 +177,8 @@ void kunit_ptr_not_err_assert_format(const struct kunit_assert *assert, */ struct kunit_binary_assert { struct kunit_assert assert; - const char *operation; - const char *left_text; + const struct kunit_binary_assert_text *text; long long left_value; - const char *right_text; long long right_value; }; @@ -182,10 +191,8 @@ void kunit_binary_assert_format(const struct kunit_assert *assert, * kunit_binary_assert, kunit_binary_ptr_assert, etc. * * @format_func: a function which formats the assert to a string. - * @op_str: A string representation of the comparison operator (e.g. "=="). - * @left_str: A string representation of the expression in the left slot. + * @text_: Pointer to a kunit_binary_assert_text. * @left_val: The actual evaluated value of the expression in the left slot. - * @right_str: A string representation of the expression in the right slot. * @right_val: The actual evaluated value of the expression in the right slot. * * Initializes a binary assert like kunit_binary_assert, @@ -194,16 +201,12 @@ void kunit_binary_assert_format(const struct kunit_assert *assert, * This is ultimately used by binary assertion macros like KUNIT_EXPECT_EQ, etc. */ #define KUNIT_INIT_BINARY_ASSERT_STRUCT(format_func, \ - op_str, \ - left_str, \ + text_, \ left_val, \ - right_str, \ right_val) { \ .assert = { .format = format_func }, \ - .operation = op_str, \ - .left_text = left_str, \ + .text = text_, \ .left_value = left_val, \ - .right_text = right_str, \ .right_value = right_val \ } @@ -211,10 +214,8 @@ void kunit_binary_assert_format(const struct kunit_assert *assert, * struct kunit_binary_ptr_assert - An expectation/assertion that compares two * pointer values (for example, KUNIT_EXPECT_PTR_EQ(test, foo, bar)). * @assert: The parent of this type. - * @operation: A string representation of the comparison operator (e.g. "=="). - * @left_text: A string representation of the expression in the left slot. + * @text: Holds the textual representations of the operands and op (e.g. "=="). * @left_value: The actual evaluated value of the expression in the left slot. - * @right_text: A string representation of the expression in the right slot. * @right_value: The actual evaluated value of the expression in the right slot. * * Represents an expectation/assertion that compares two pointer values. For @@ -223,10 +224,8 @@ void kunit_binary_assert_format(const struct kunit_assert *assert, */ struct kunit_binary_ptr_assert { struct kunit_assert assert; - const char *operation; - const char *left_text; + const struct kunit_binary_assert_text *text; const void *left_value; - const char *right_text; const void *right_value; }; @@ -238,10 +237,8 @@ void kunit_binary_ptr_assert_format(const struct kunit_assert *assert, * struct kunit_binary_str_assert - An expectation/assertion that compares two * string values (for example, KUNIT_EXPECT_STREQ(test, foo, "bar")). * @assert: The parent of this type. - * @operation: A string representation of the comparison operator (e.g. "=="). - * @left_text: A string representation of the expression in the left slot. + * @text: Holds the textual representations of the operands and comparator. * @left_value: The actual evaluated value of the expression in the left slot. - * @right_text: A string representation of the expression in the right slot. * @right_value: The actual evaluated value of the expression in the right slot. * * Represents an expectation/assertion that compares two string values. For @@ -250,10 +247,8 @@ void kunit_binary_ptr_assert_format(const struct kunit_assert *assert, */ struct kunit_binary_str_assert { struct kunit_assert assert; - const char *operation; - const char *left_text; + const struct kunit_binary_assert_text *text; const char *left_value; - const char *right_text; const char *right_value; }; diff --git a/include/kunit/test.h b/include/kunit/test.h index a93dfb8ff393..088ff394ae94 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -874,16 +874,19 @@ void kunit_do_failed_assertion(struct kunit *test, do { \ typeof(left) __left = (left); \ typeof(right) __right = (right); \ + static const struct kunit_binary_assert_text __text = { \ + .operation = #op, \ + .left_text = #left, \ + .right_text = #right, \ + }; \ \ KUNIT_ASSERTION(test, \ assert_type, \ __left op __right, \ assert_class, \ KUNIT_INIT_BINARY_ASSERT_STRUCT(format_func, \ - #op, \ - #left, \ + &__text, \ __left, \ - #right, \ __right), \ fmt, \ ##__VA_ARGS__); \ @@ -928,17 +931,20 @@ do { \ ...) \ do { \ const char *__left = (left); \ - const char *__right = (right); \ + const char *__right = (right); \ + static const struct kunit_binary_assert_text __text = { \ + .operation = #op, \ + .left_text = #left, \ + .right_text = #right, \ + }; \ \ KUNIT_ASSERTION(test, \ assert_type, \ strcmp(__left, __right) op 0, \ kunit_binary_str_assert, \ KUNIT_INIT_BINARY_ASSERT_STRUCT(kunit_binary_str_assert_format,\ - #op, \ - #left, \ + &__text, \ __left, \ - #right, \ __right), \ fmt, \ ##__VA_ARGS__); \ -- cgit v1.2.3 From c2741453478badf571ef020d160053e8d5e1ba94 Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Thu, 27 Jan 2022 13:52:22 -0800 Subject: kunit: cleanup assertion macro internal variables All the operands should be tagged `const`. We're only assigning them to variables so that we can compare them (e.g. check if left == right, etc.) and avoid evaluating expressions multiple times. There's no need for them to be mutable. Also rename the helper variable `loc` to `__loc` like we do with `__assertion` and `__strs` to avoid potential name collisions with user code. Signed-off-by: Daniel Latypov Reviewed-by: David Gow Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- include/kunit/test.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index 088ff394ae94..00b9ff7783ab 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -779,10 +779,10 @@ void kunit_do_failed_assertion(struct kunit *test, #define KUNIT_ASSERTION(test, assert_type, pass, assert_class, INITIALIZER, fmt, ...) do { \ if (unlikely(!(pass))) { \ - static const struct kunit_loc loc = KUNIT_CURRENT_LOC; \ + static const struct kunit_loc __loc = KUNIT_CURRENT_LOC; \ struct assert_class __assertion = INITIALIZER; \ kunit_do_failed_assertion(test, \ - &loc, \ + &__loc, \ assert_type, \ &__assertion.assert, \ fmt, \ @@ -872,8 +872,8 @@ void kunit_do_failed_assertion(struct kunit *test, fmt, \ ...) \ do { \ - typeof(left) __left = (left); \ - typeof(right) __right = (right); \ + const typeof(left) __left = (left); \ + const typeof(right) __right = (right); \ static const struct kunit_binary_assert_text __text = { \ .operation = #op, \ .left_text = #left, \ @@ -956,7 +956,7 @@ do { \ fmt, \ ...) \ do { \ - typeof(ptr) __ptr = (ptr); \ + const typeof(ptr) __ptr = (ptr); \ \ KUNIT_ASSERTION(test, \ assert_type, \ -- cgit v1.2.3 From 4421a582718ab81608d8486734c18083b822390d Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Sun, 30 Jan 2022 12:55:17 +0100 Subject: bpf: Make dst_port field in struct bpf_sock 16-bit wide Menglong Dong reports that the documentation for the dst_port field in struct bpf_sock is inaccurate and confusing. From the BPF program PoV, the field is a zero-padded 16-bit integer in network byte order. The value appears to the BPF user as if laid out in memory as so: offsetof(struct bpf_sock, dst_port) + 0 + 8 +16 0x00 +24 0x00 32-, 16-, and 8-bit wide loads from the field are all allowed, but only if the offset into the field is 0. 32-bit wide loads from dst_port are especially confusing. The loaded value, after converting to host byte order with bpf_ntohl(dst_port), contains the port number in the upper 16-bits. Remove the confusion by splitting the field into two 16-bit fields. For backward compatibility, allow 32-bit wide loads from offsetof(struct bpf_sock, dst_port). While at it, allow loads 8-bit loads at offset [0] and [1] from dst_port. Reported-by: Menglong Dong Signed-off-by: Jakub Sitnicki Link: https://lore.kernel.org/r/20220130115518.213259-2-jakub@cloudflare.com Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4a2f7041ebae..a7f0ddedac1f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5574,7 +5574,8 @@ struct bpf_sock { __u32 src_ip4; __u32 src_ip6[4]; __u32 src_port; /* host byte order */ - __u32 dst_port; /* network byte order */ + __be16 dst_port; /* network byte order */ + __u16 :16; /* zero padding */ __u32 dst_ip4; __u32 dst_ip6[4]; __u32 state; -- cgit v1.2.3 From 2af104290da5e4858e8caefa068827d7392c6a09 Mon Sep 17 00:00:00 2001 From: Tomohito Esaki Date: Fri, 28 Jan 2022 15:08:34 +0900 Subject: drm: introduce fb_modifiers_not_supported flag in mode_config If only linear modifier is advertised, since there are many drivers that only linear supported, the DRM core should handle this rather than open-coding in every driver. However, there are legacy drivers such as radeon that do not support modifiers but infer the actual layout of the underlying buffer. Therefore, a new flag fb_modifiers_not_supported is introduced for these legacy drivers, and allow_fb_modifiers is replaced with this new flag. v3: - change the order as follows: 1. add fb_modifiers_not_supported flag 2. add default modifiers 3. remove allow_fb_modifiers flag - add a conditional disable in amdgpu_dm_plane_init() v4: - modify kernel docs v5: - modify kernel docs Signed-off-by: Tomohito Esaki Acked-by: Harry Wentland Reviewed-by: Andy Shevchenko Reviewed-by: Laurent Pinchart Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220128060836.11216-2-etom@igel.co.jp --- include/drm/drm_mode_config.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h index 91ca575a78de..4a93dac91cf9 100644 --- a/include/drm/drm_mode_config.h +++ b/include/drm/drm_mode_config.h @@ -933,6 +933,16 @@ struct drm_mode_config { */ bool allow_fb_modifiers; + /** + * @fb_modifiers_not_supported: + * + * When this flag is set, the DRM device will not expose modifier + * support to userspace. This is only used by legacy drivers that infer + * the buffer layout through heuristics without using modifiers. New + * drivers shall not set fhis flag. + */ + bool fb_modifiers_not_supported; + /** * @normalize_zpos: * -- cgit v1.2.3 From 8be576837b6e62b2ad0de2f9ba31cef618fa2891 Mon Sep 17 00:00:00 2001 From: Tomohito Esaki Date: Fri, 28 Jan 2022 15:08:35 +0900 Subject: drm: add support modifiers for drivers whose planes only support linear layout The LINEAR modifier is advertised as default if a driver doesn't specify modifiers. v2: - rebase to the latest master branch (5.16.0+) + "drm/plane: Make format_mod_supported truly optional" patch [1] [1] https://patchwork.freedesktop.org/patch/467940/?series=98255&rev=3 v3: - change the order as follows: 1. add fb_modifiers_not_supported flag 2. add default modifiers 3. remove allow_fb_modifiers flag v5: - change default_modifiers array from non-static to static - remove terminator in default_modifiers array - use ARRAY_SIZE to get the format_modifier_count - update sanity check in plane init func to use the fb_modifiers_not_supported - modify kernel docs Signed-off-by: Tomohito Esaki Reviewed-by: Andy Shevchenko Reviewed-by: Laurent Pinchart Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220128060836.11216-3-etom@igel.co.jp --- include/drm/drm_plane.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h index 06759badf99f..2628c7cde2da 100644 --- a/include/drm/drm_plane.h +++ b/include/drm/drm_plane.h @@ -803,6 +803,9 @@ void *__drmm_universal_plane_alloc(struct drm_device *dev, * * The @drm_plane_funcs.destroy hook must be NULL. * + * Drivers that only support the DRM_FORMAT_MOD_LINEAR modifier support may set + * @format_modifiers to NULL. The plane will advertise the linear modifier. + * * Returns: * Pointer to new plane, or ERR_PTR on failure. */ -- cgit v1.2.3 From 3d082157a24216ca084082ce421a37d14ecfcfad Mon Sep 17 00:00:00 2001 From: Tomohito Esaki Date: Fri, 28 Jan 2022 15:08:36 +0900 Subject: drm: remove allow_fb_modifiers The allow_fb_modifiers flag is unnecessary since it has been replaced with fb_modifiers_not_supported flag. v3: - change the order as follows: 1. add fb_modifiers_not_supported flag 2. add default modifiers 3. remove allow_fb_modifiers flag v5: - keep a sanity check in plane init func Signed-off-by: Tomohito Esaki Reviewed-by: Andy Shevchenko Reviewed-by: Laurent Pinchart Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220128060836.11216-4-etom@igel.co.jp --- include/drm/drm_mode_config.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include') diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h index 4a93dac91cf9..6b5e01295348 100644 --- a/include/drm/drm_mode_config.h +++ b/include/drm/drm_mode_config.h @@ -917,22 +917,6 @@ struct drm_mode_config { */ bool async_page_flip; - /** - * @allow_fb_modifiers: - * - * Whether the driver supports fb modifiers in the ADDFB2.1 ioctl call. - * Note that drivers should not set this directly, it is automatically - * set in drm_universal_plane_init(). - * - * IMPORTANT: - * - * If this is set the driver must fill out the full implicit modifier - * information in their &drm_mode_config_funcs.fb_create hook for legacy - * userspace which does not set modifiers. Otherwise the GETFB2 ioctl is - * broken for modifier aware userspace. - */ - bool allow_fb_modifiers; - /** * @fb_modifiers_not_supported: * -- cgit v1.2.3 From d80976d9ffd9d7f89a26134a299b236910477f3b Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Tue, 30 Nov 2021 16:27:55 +0100 Subject: dma-resv: some doc polish for iterators MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Hammer it a bit more in that iterators can be restarted and when that matters, plus suggest to prefer the locked version whenver. Also delete the two leftover kerneldoc for static functions plus sprinkle some more links while at it. v2: Keep some comments (Christian) Reviewed-by: Christian König Signed-off-by: Daniel Vetter Cc: Sumit Semwal Cc: "Christian König" Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20211130152756.1388106-1-daniel.vetter@ffwll.ch --- include/linux/dma-resv.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index a715df97b31a..afdfdfac729f 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -153,6 +153,13 @@ struct dma_resv { * struct dma_resv_iter - current position into the dma_resv fences * * Don't touch this directly in the driver, use the accessor function instead. + * + * IMPORTANT + * + * When using the lockless iterators like dma_resv_iter_next_unlocked() or + * dma_resv_for_each_fence_unlocked() beware that the iterator can be restarted. + * Code which accumulates statistics or similar needs to check for this with + * dma_resv_iter_is_restarted(). */ struct dma_resv_iter { /** @obj: The dma_resv object we iterate over */ @@ -243,7 +250,11 @@ static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor) * &dma_resv.lock and using RCU instead. The cursor needs to be initialized * with dma_resv_iter_begin() and cleaned up with dma_resv_iter_end(). Inside * the iterator a reference to the dma_fence is held and the RCU lock dropped. - * When the dma_resv is modified the iteration starts over again. + * + * Beware that the iterator can be restarted when the struct dma_resv for + * @cursor is modified. Code which accumulates statistics or similar needs to + * check for this with dma_resv_iter_is_restarted(). For this reason prefer the + * lock iterator dma_resv_for_each_fence() whenever possible. */ #define dma_resv_for_each_fence_unlocked(cursor, fence) \ for (fence = dma_resv_iter_first_unlocked(cursor); \ -- cgit v1.2.3 From 943515090ec67f81f6f93febfddb8c9118357e97 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Wed, 8 Dec 2021 09:34:22 +0100 Subject: firmware: qcom: scm: Add function to set the maximum IOMMU pool size This is not necessary for basic functionality of the IOMMU, but it's an optimization that tells to the TZ what's the maximum mappable size for the secure IOMMUs, so that it can optimize the data structures in the TZ itself. Signed-off-by: AngeloGioacchino Del Regno [Marijn: ported from 5.3 to the unified architecture in 5.11] Signed-off-by: Marijn Suijten Reviewed-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20211208083423.22037-3-marijn.suijten@somainline.org --- include/linux/qcom_scm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index 81cad9e1e412..8a065f8660c1 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -83,6 +83,7 @@ extern bool qcom_scm_restore_sec_cfg_available(void); extern int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare); extern int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size); extern int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare); +extern int qcom_scm_iommu_set_cp_pool_size(u32 spare, u32 size); extern int qcom_scm_mem_protect_video_var(u32 cp_start, u32 cp_size, u32 cp_nonpixel_start, u32 cp_nonpixel_size); -- cgit v1.2.3 From 071a13332de894cb3c38b17c82350f1e4167c023 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Wed, 8 Dec 2021 09:34:23 +0100 Subject: firmware: qcom: scm: Add function to set IOMMU pagetable addressing Add a function to change the IOMMU pagetable addressing to AArch32 LPAE or AArch64. If doing that, then this must be done for each IOMMU context (not necessarily at the same time). Signed-off-by: AngeloGioacchino Del Regno [Marijn: ported from 5.3 to the unified architecture in 5.11] Signed-off-by: Marijn Suijten Reviewed-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20211208083423.22037-4-marijn.suijten@somainline.org --- include/linux/qcom_scm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index 8a065f8660c1..ca4a88d7cbdc 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -108,6 +108,7 @@ extern bool qcom_scm_hdcp_available(void); extern int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, u32 *resp); +extern int qcom_scm_iommu_set_pt_format(u32 sec_id, u32 ctx_num, u32 pt_fmt); extern int qcom_scm_qsmmu500_wait_safe_toggle(bool en); extern int qcom_scm_lmh_dcvsh(u32 payload_fn, u32 payload_reg, u32 payload_val, -- cgit v1.2.3 From 6d3ac94bae21de6b6a1d81596752428960012816 Mon Sep 17 00:00:00 2001 From: Yang Guang Date: Fri, 14 Jan 2022 08:11:02 +0800 Subject: ssb: fix boolreturn.cocci warning The coccinelle report ./include/linux/ssb/ssb_driver_gige.h:98:8-9: WARNING: return of 0/1 in function 'ssb_gige_must_flush_posted_writes' with return type bool Return statements in functions returning bool should use true/false instead of 1/0. Reported-by: Zeal Robot Signed-off-by: Yang Guang Signed-off-by: David Yang Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/fa4f1fa737e715eb62a85229ac5f12bae21145cf.1642065490.git.davidcomponentone@gmail.com --- include/linux/ssb/ssb_driver_gige.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ssb/ssb_driver_gige.h b/include/linux/ssb/ssb_driver_gige.h index 15ba0df1ee0d..28c145a51e57 100644 --- a/include/linux/ssb/ssb_driver_gige.h +++ b/include/linux/ssb/ssb_driver_gige.h @@ -95,7 +95,7 @@ static inline bool ssb_gige_must_flush_posted_writes(struct pci_dev *pdev) struct ssb_gige *dev = pdev_to_ssb_gige(pdev); if (dev) return (dev->dev->bus->chip_id == 0x4785); - return 0; + return false; } /* Get the device MAC address */ -- cgit v1.2.3 From 2220af8ca61ae67de4ec3deec1c6395a2f65b9fd Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 1 Feb 2022 14:06:47 +0100 Subject: power: supply: core: Refactor power_supply_set_input_current_limit_from_supplier() Some (USB) charger ICs have variants with USB D+ and D- pins to do their own builtin charger-type detection, like e.g. the bq24190 and bq25890 and also variants which lack this functionality, e.g. the bq24192 and bq25892. In case the charger-type; and thus the input-current-limit detection is done outside the charger IC then we need some way to communicate this to the charger IC. In the past extcon was used for this, but if the external detection does e.g. full USB PD negotiation then the extcon cable-types do not convey enough information. For these setups it was decided to model the external charging "brick" and the parameters negotiated with it as a power_supply class-device itself; and power_supply_set_input_current_limit_from_supplier() was introduced to allow drivers to get the input-current-limit this way. But in some cases psy drivers may want to know other properties, e.g. the bq25892 can do "quick-charge" negotiation by pulsing its current draw, but this should only be done if the usb_type psy-property of its supplier is set to DCP (and device-properties indicate the board allows higher voltages). Instead of adding extra helper functions for each property which a psy-driver wants to query from its supplier, refactor power_supply_set_input_current_limit_from_supplier() into a more generic power_supply_get_property_from_supplier() function. Reviewed-by: Andy Shevchenko Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index e218041cc000..006111917d1a 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -597,8 +597,9 @@ power_supply_temp2resist_simple(struct power_supply_resistance_temp_table *table int table_len, int temp); extern void power_supply_changed(struct power_supply *psy); extern int power_supply_am_i_supplied(struct power_supply *psy); -extern int power_supply_set_input_current_limit_from_supplier( - struct power_supply *psy); +int power_supply_get_property_from_supplier(struct power_supply *psy, + enum power_supply_property psp, + union power_supply_propval *val); extern int power_supply_set_battery_charged(struct power_supply *psy); #ifdef CONFIG_POWER_SUPPLY -- cgit v1.2.3 From 79d35365a5858466ff7b37aaf1fcf11b683b9442 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 1 Feb 2022 14:06:56 +0100 Subject: power: supply: bq25890: Add support for registering the Vbus boost converter as a regulator The bq25890_charger code supports enabling/disabling the boost converter based on usb-phy notifications. But the usb-phy framework is not used on all boards/platforms. At support for registering the Vbus boost converter as a standard regulator when there is no usb-phy on the board. Also add support for providing regulator_init_data through platform_data for use on boards where device-tree is not used and the platform code must thus provide the regulator_init_data. Reviewed-by: Andy Shevchenko Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel --- include/linux/power/bq25890_charger.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) create mode 100644 include/linux/power/bq25890_charger.h (limited to 'include') diff --git a/include/linux/power/bq25890_charger.h b/include/linux/power/bq25890_charger.h new file mode 100644 index 000000000000..c706ddb77a08 --- /dev/null +++ b/include/linux/power/bq25890_charger.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Platform data for the TI bq25890 battery charger driver. + */ + +#ifndef _BQ25890_CHARGER_H_ +#define _BQ25890_CHARGER_H_ + +struct regulator_init_data; + +struct bq25890_platform_data { + const struct regulator_init_data *regulator_init_data; +}; + +#endif -- cgit v1.2.3 From 3afcbe09470091ca8a8048ef7c96701839a70961 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 1 Feb 2022 14:07:00 +0100 Subject: mfd: intel_soc_pmic_chtwc: Add cht_wc_model data to struct intel_soc_pmic Tablet / laptop designs using an Intel Cherry Trail x86 main SoC with an Intel Whiskey Cove PMIC do not use a single standard setup for the charger, fuel-gauge and other chips surrounding the PMIC / charging+data USB port. Unlike what is normal on x86 this diversity in designs is not handled by the ACPI tables. On 2 of the 3 known designs there are no standard (PNP0C0A) ACPI battery devices and on the 3th design the ACPI battery device does not work under Linux due to it requiring non-standard and undocumented ACPI behavior. So to make things work under Linux we use native charger and fuel-gauge drivers on these devices, re-using the native drivers used on ARM boards with the same charger / fuel-gauge ICs. This requires various MFD-cell drivers for the CHT-WC PMIC cells to know which model they are exactly running on so that they can e.g. instantiate an I2C-client for the right model charger-IC (the charger is connected to an I2C-controller which is part of the PMIC). Rather then duplicating DMI-id matching to check which model we are running on in each MFD-cell driver, add a check for this to the shared drivers/mfd/intel_soc_pmic_chtwc.c code by using a DMI table for all 3 known models: 1. The GPD Win and GPD Pocket mini-laptops, these are really 2 models but the Pocket re-uses the GPD Win's design in a different housing: The WC PMIC is connected to a TI BQ24292i charger, paired with a Maxim MAX17047 fuelgauge + a FUSB302 USB Type-C Controller + a PI3USB30532 USB switch, for a fully functional Type-C port. 2. The Xiaomi Mi Pad 2: The WC PMIC is connected to a TI BQ25890 charger, paired with a TI BQ27520 fuelgauge, using the TI BQ25890 for BC1.2 charger type detection, for a USB-2 only Type-C port without PD. 3. The Lenovo Yoga Book YB1-X90 / Lenovo Yoga Book YB1-X91 series: The WC PMIC is connected to a TI BQ25892 charger, paired with a TI BQ27542 fuelgauge, using the WC PMIC for BC1.2 charger type detection and using the BQ25892's Mediatek Pump Express+ (1.0) support to enable charging with up to 12V through a micro-USB port. Reviewed-by: Andy Shevchenko Acked-by: Lee Jones Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel --- include/linux/mfd/intel_soc_pmic.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/intel_soc_pmic.h b/include/linux/mfd/intel_soc_pmic.h index 6a88e34cb955..945bde1fe55c 100644 --- a/include/linux/mfd/intel_soc_pmic.h +++ b/include/linux/mfd/intel_soc_pmic.h @@ -13,6 +13,13 @@ #include +enum intel_cht_wc_models { + INTEL_CHT_WC_UNKNOWN, + INTEL_CHT_WC_GPD_WIN_POCKET, + INTEL_CHT_WC_XIAOMI_MIPAD2, + INTEL_CHT_WC_LENOVO_YOGABOOK1, +}; + /** * struct intel_soc_pmic - Intel SoC PMIC data * @irq: Master interrupt number of the parent PMIC device @@ -39,6 +46,7 @@ struct intel_soc_pmic { struct regmap_irq_chip_data *irq_chip_data_crit; struct device *dev; struct intel_scu_ipc_dev *scu; + enum intel_cht_wc_models cht_wc_model; }; int intel_soc_pmic_exec_mipi_pmic_seq_element(u16 i2c_address, u32 reg_address, -- cgit v1.2.3 From ab28e944197fa78e6af7c4a0ffd6bba9a5bbacf0 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Mon, 31 Jan 2022 15:01:11 -0800 Subject: topology/sysfs: Add PPIN in sysfs under cpu topology PPIN is the Protected Processor Identification Number. This is used to identify the socket as a Field Replaceable Unit (FRU). Existing code only displays this when reporting errors. But this makes it inconvenient for large clusters to use it for its intended purpose of inventory control. Add ppin to /sys/devices/system/cpu/cpu*/topology to make what is already available using RDMSR more easily accessible. Make the file read only for root in case there are still people concerned about making a unique system "serial number" available. Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Acked-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20220131230111.2004669-6-tony.luck@intel.com --- include/linux/topology.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/topology.h b/include/linux/topology.h index a6e201758ae9..f19bc3626297 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -211,6 +211,9 @@ static inline int cpu_to_mem(int cpu) #ifndef topology_drawer_id #define topology_drawer_id(cpu) ((void)(cpu), -1) #endif +#ifndef topology_ppin +#define topology_ppin(cpu) ((void)(cpu), 0ull) +#endif #ifndef topology_sibling_cpumask #define topology_sibling_cpumask(cpu) cpumask_of(cpu) #endif -- cgit v1.2.3 From 90b2433edb6d995bd23d6adde753095b4ab26104 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ma=C3=ADra=20Canal?= Date: Mon, 31 Jan 2022 15:22:42 -0300 Subject: seq_file: fix NULL pointer arithmetic warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Implement conditional logic in order to replace NULL pointer arithmetic. The use of NULL pointer arithmetic was pointed out by clang with the following warning: fs/kernfs/file.c:128:15: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] return NULL + !*ppos; ~~~~ ^ fs/seq_file.c:559:14: warning: performing pointer arithmetic on a null pointer has undefined behavior [-Wnull-pointer-arithmetic] return NULL + (*pos == 0); Signed-off-by: Maíra Canal Signed-off-by: Al Viro --- include/linux/seq_file.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 88cc16444b43..60820ab511d2 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -162,6 +162,7 @@ int seq_dentry(struct seq_file *, struct dentry *, const char *); int seq_path_root(struct seq_file *m, const struct path *path, const struct path *root, const char *esc); +void *single_start(struct seq_file *, loff_t *); int single_open(struct file *, int (*)(struct seq_file *, void *), void *); int single_open_size(struct file *, int (*)(struct seq_file *, void *), void *, size_t); int single_release(struct inode *, struct file *); -- cgit v1.2.3 From e3dc1399506f894110667ee5c66a6a70f06f3348 Mon Sep 17 00:00:00 2001 From: Stefan Binding Date: Fri, 21 Jan 2022 17:24:23 +0000 Subject: spi: Make spi_alloc_device and spi_add_device public again This functions were previously made private since they were not used. However, these functions will be needed again. Partial revert of commit da21fde0fdb3 ("spi: Make several public functions private to spi.c") Signed-off-by: Stefan Binding Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20220121172431.6876-2-sbinding@opensource.cirrus.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 7ab3fed7b804..0346a3ff27fd 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -1452,7 +1452,19 @@ spi_register_board_info(struct spi_board_info const *info, unsigned n) * use spi_new_device() to describe each device. You can also call * spi_unregister_device() to start making that device vanish, but * normally that would be handled by spi_unregister_controller(). + * + * You can also use spi_alloc_device() and spi_add_device() to use a two + * stage registration sequence for each spi_device. This gives the caller + * some more control over the spi_device structure before it is registered, + * but requires that caller to initialize fields that would otherwise + * be defined using the board info. */ +extern struct spi_device * +spi_alloc_device(struct spi_controller *ctlr); + +extern int +spi_add_device(struct spi_device *spi); + extern struct spi_device * spi_new_device(struct spi_controller *, struct spi_board_info *); -- cgit v1.2.3 From 000bee0ed70af79e610444096fb453430220960f Mon Sep 17 00:00:00 2001 From: Stefan Binding Date: Fri, 21 Jan 2022 17:24:24 +0000 Subject: spi: Create helper API to lookup ACPI info for spi device This can then be used to find a spi resource inside an ACPI node, and allocate a spi device. Signed-off-by: Stefan Binding Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20220121172431.6876-3-sbinding@opensource.cirrus.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 0346a3ff27fd..d159cef12f1a 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -16,6 +16,7 @@ #include #include +#include struct dma_chan; struct software_node; @@ -759,6 +760,11 @@ extern int devm_spi_register_controller(struct device *dev, struct spi_controller *ctlr); extern void spi_unregister_controller(struct spi_controller *ctlr); +#if IS_ENABLED(CONFIG_ACPI) +extern struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr, + struct acpi_device *adev); +#endif + /* * SPI resource management while processing a SPI message */ -- cgit v1.2.3 From 87e59b36e5e26122efd55d77adb9fac827987db0 Mon Sep 17 00:00:00 2001 From: Stefan Binding Date: Fri, 21 Jan 2022 17:24:25 +0000 Subject: spi: Support selection of the index of the ACPI Spi Resource before alloc If a node contains more than one SPI resource it may be necessary to use an index to select which one you want to allocate a spi device for. Signed-off-by: Stefan Binding Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20220121172431.6876-4-sbinding@opensource.cirrus.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index d159cef12f1a..e5bbb9cbd3d7 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -762,7 +762,8 @@ extern void spi_unregister_controller(struct spi_controller *ctlr); #if IS_ENABLED(CONFIG_ACPI) extern struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr, - struct acpi_device *adev); + struct acpi_device *adev, + int index); #endif /* -- cgit v1.2.3 From e612af7acef2459f1afd885f4107748995a05963 Mon Sep 17 00:00:00 2001 From: Stefan Binding Date: Fri, 21 Jan 2022 17:24:26 +0000 Subject: spi: Add API to count spi acpi resources Some ACPI nodes may have more than one Spi Resource. To be able to handle these case, its necessary to have a way of counting these resources. Signed-off-by: Stefan Binding Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20220121172431.6876-5-sbinding@opensource.cirrus.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index e5bbb9cbd3d7..394b4241d989 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -764,6 +764,7 @@ extern void spi_unregister_controller(struct spi_controller *ctlr); extern struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr, struct acpi_device *adev, int index); +int acpi_spi_count_resources(struct acpi_device *adev); #endif /* -- cgit v1.2.3 From 02b2a91c6f0d57df687e666b475849a54f295a12 Mon Sep 17 00:00:00 2001 From: David Girault Date: Tue, 1 Feb 2022 19:09:56 +0100 Subject: net: ieee802154: Provide a kdoc to the address structure Give this structure a header to better explain its content. Signed-off-by: David Girault [miquel.raynal@bootlin.com: Isolate this change from a bigger commit and reword the comment] Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/r/20220201180956.93581-1-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt --- include/net/cfg802154.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 6ed07844eb24..833672d6fbe4 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -227,6 +227,16 @@ static inline void wpan_phy_net_set(struct wpan_phy *wpan_phy, struct net *net) write_pnet(&wpan_phy->_net, net); } +/** + * struct ieee802154_addr - IEEE802.15.4 device address + * @mode: Address mode from frame header. Can be one of: + * - @IEEE802154_ADDR_NONE + * - @IEEE802154_ADDR_SHORT + * - @IEEE802154_ADDR_LONG + * @pan_id: The PAN ID this address belongs to + * @short_addr: address if @mode is @IEEE802154_ADDR_SHORT + * @extended_addr: address if @mode is @IEEE802154_ADDR_LONG + */ struct ieee802154_addr { u8 mode; __le16 pan_id; -- cgit v1.2.3 From 4decd2e54b61686787f36b727d2772e067a46ea5 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Wed, 26 Jan 2022 21:10:03 +0000 Subject: dt-bindings: clock: Add R9A07G054 CPG Clock and Reset Definitions Define RZ/V2L (R9A07G054) Clock Pulse Generator Core Clock and module clock outputs, as listed in Table 7.1.4.2 ("Clock List r1.0") and also add Reset definitions referring to registers CPG_RST_* in Section 7.2.3 ("Register configuration") of the RZ/V2L Hardware User's Manual (Rev. 1.00, Nov. 2021). Signed-off-by: Biju Das Signed-off-by: Lad Prabhakar Acked-by: Rob Herring Link: https://lore.kernel.org/r/20220126211003.6675-1-prabhakar.mahadev-lad.rj@bp.renesas.com Signed-off-by: Geert Uytterhoeven --- include/dt-bindings/clock/r9a07g054-cpg.h | 229 ++++++++++++++++++++++++++++++ 1 file changed, 229 insertions(+) create mode 100644 include/dt-bindings/clock/r9a07g054-cpg.h (limited to 'include') diff --git a/include/dt-bindings/clock/r9a07g054-cpg.h b/include/dt-bindings/clock/r9a07g054-cpg.h new file mode 100644 index 000000000000..43f4dbda872c --- /dev/null +++ b/include/dt-bindings/clock/r9a07g054-cpg.h @@ -0,0 +1,229 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + * + * Copyright (C) 2022 Renesas Electronics Corp. + */ +#ifndef __DT_BINDINGS_CLOCK_R9A07G054_CPG_H__ +#define __DT_BINDINGS_CLOCK_R9A07G054_CPG_H__ + +#include + +/* R9A07G054 CPG Core Clocks */ +#define R9A07G054_CLK_I 0 +#define R9A07G054_CLK_I2 1 +#define R9A07G054_CLK_G 2 +#define R9A07G054_CLK_S0 3 +#define R9A07G054_CLK_S1 4 +#define R9A07G054_CLK_SPI0 5 +#define R9A07G054_CLK_SPI1 6 +#define R9A07G054_CLK_SD0 7 +#define R9A07G054_CLK_SD1 8 +#define R9A07G054_CLK_M0 9 +#define R9A07G054_CLK_M1 10 +#define R9A07G054_CLK_M2 11 +#define R9A07G054_CLK_M3 12 +#define R9A07G054_CLK_M4 13 +#define R9A07G054_CLK_HP 14 +#define R9A07G054_CLK_TSU 15 +#define R9A07G054_CLK_ZT 16 +#define R9A07G054_CLK_P0 17 +#define R9A07G054_CLK_P1 18 +#define R9A07G054_CLK_P2 19 +#define R9A07G054_CLK_AT 20 +#define R9A07G054_OSCCLK 21 +#define R9A07G054_CLK_P0_DIV2 22 +#define R9A07G054_CLK_DRP_M 23 +#define R9A07G054_CLK_DRP_D 24 +#define R9A07G054_CLK_DRP_A 25 + +/* R9A07G054 Module Clocks */ +#define R9A07G054_CA55_SCLK 0 +#define R9A07G054_CA55_PCLK 1 +#define R9A07G054_CA55_ATCLK 2 +#define R9A07G054_CA55_GICCLK 3 +#define R9A07G054_CA55_PERICLK 4 +#define R9A07G054_CA55_ACLK 5 +#define R9A07G054_CA55_TSCLK 6 +#define R9A07G054_GIC600_GICCLK 7 +#define R9A07G054_IA55_CLK 8 +#define R9A07G054_IA55_PCLK 9 +#define R9A07G054_MHU_PCLK 10 +#define R9A07G054_SYC_CNT_CLK 11 +#define R9A07G054_DMAC_ACLK 12 +#define R9A07G054_DMAC_PCLK 13 +#define R9A07G054_OSTM0_PCLK 14 +#define R9A07G054_OSTM1_PCLK 15 +#define R9A07G054_OSTM2_PCLK 16 +#define R9A07G054_MTU_X_MCK_MTU3 17 +#define R9A07G054_POE3_CLKM_POE 18 +#define R9A07G054_GPT_PCLK 19 +#define R9A07G054_POEG_A_CLKP 20 +#define R9A07G054_POEG_B_CLKP 21 +#define R9A07G054_POEG_C_CLKP 22 +#define R9A07G054_POEG_D_CLKP 23 +#define R9A07G054_WDT0_PCLK 24 +#define R9A07G054_WDT0_CLK 25 +#define R9A07G054_WDT1_PCLK 26 +#define R9A07G054_WDT1_CLK 27 +#define R9A07G054_WDT2_PCLK 28 +#define R9A07G054_WDT2_CLK 29 +#define R9A07G054_SPI_CLK2 30 +#define R9A07G054_SPI_CLK 31 +#define R9A07G054_SDHI0_IMCLK 32 +#define R9A07G054_SDHI0_IMCLK2 33 +#define R9A07G054_SDHI0_CLK_HS 34 +#define R9A07G054_SDHI0_ACLK 35 +#define R9A07G054_SDHI1_IMCLK 36 +#define R9A07G054_SDHI1_IMCLK2 37 +#define R9A07G054_SDHI1_CLK_HS 38 +#define R9A07G054_SDHI1_ACLK 39 +#define R9A07G054_GPU_CLK 40 +#define R9A07G054_GPU_AXI_CLK 41 +#define R9A07G054_GPU_ACE_CLK 42 +#define R9A07G054_ISU_ACLK 43 +#define R9A07G054_ISU_PCLK 44 +#define R9A07G054_H264_CLK_A 45 +#define R9A07G054_H264_CLK_P 46 +#define R9A07G054_CRU_SYSCLK 47 +#define R9A07G054_CRU_VCLK 48 +#define R9A07G054_CRU_PCLK 49 +#define R9A07G054_CRU_ACLK 50 +#define R9A07G054_MIPI_DSI_PLLCLK 51 +#define R9A07G054_MIPI_DSI_SYSCLK 52 +#define R9A07G054_MIPI_DSI_ACLK 53 +#define R9A07G054_MIPI_DSI_PCLK 54 +#define R9A07G054_MIPI_DSI_VCLK 55 +#define R9A07G054_MIPI_DSI_LPCLK 56 +#define R9A07G054_LCDC_CLK_A 57 +#define R9A07G054_LCDC_CLK_P 58 +#define R9A07G054_LCDC_CLK_D 59 +#define R9A07G054_SSI0_PCLK2 60 +#define R9A07G054_SSI0_PCLK_SFR 61 +#define R9A07G054_SSI1_PCLK2 62 +#define R9A07G054_SSI1_PCLK_SFR 63 +#define R9A07G054_SSI2_PCLK2 64 +#define R9A07G054_SSI2_PCLK_SFR 65 +#define R9A07G054_SSI3_PCLK2 66 +#define R9A07G054_SSI3_PCLK_SFR 67 +#define R9A07G054_SRC_CLKP 68 +#define R9A07G054_USB_U2H0_HCLK 69 +#define R9A07G054_USB_U2H1_HCLK 70 +#define R9A07G054_USB_U2P_EXR_CPUCLK 71 +#define R9A07G054_USB_PCLK 72 +#define R9A07G054_ETH0_CLK_AXI 73 +#define R9A07G054_ETH0_CLK_CHI 74 +#define R9A07G054_ETH1_CLK_AXI 75 +#define R9A07G054_ETH1_CLK_CHI 76 +#define R9A07G054_I2C0_PCLK 77 +#define R9A07G054_I2C1_PCLK 78 +#define R9A07G054_I2C2_PCLK 79 +#define R9A07G054_I2C3_PCLK 80 +#define R9A07G054_SCIF0_CLK_PCK 81 +#define R9A07G054_SCIF1_CLK_PCK 82 +#define R9A07G054_SCIF2_CLK_PCK 83 +#define R9A07G054_SCIF3_CLK_PCK 84 +#define R9A07G054_SCIF4_CLK_PCK 85 +#define R9A07G054_SCI0_CLKP 86 +#define R9A07G054_SCI1_CLKP 87 +#define R9A07G054_IRDA_CLKP 88 +#define R9A07G054_RSPI0_CLKB 89 +#define R9A07G054_RSPI1_CLKB 90 +#define R9A07G054_RSPI2_CLKB 91 +#define R9A07G054_CANFD_PCLK 92 +#define R9A07G054_GPIO_HCLK 93 +#define R9A07G054_ADC_ADCLK 94 +#define R9A07G054_ADC_PCLK 95 +#define R9A07G054_TSU_PCLK 96 +#define R9A07G054_STPAI_INITCLK 97 +#define R9A07G054_STPAI_ACLK 98 +#define R9A07G054_STPAI_MCLK 99 +#define R9A07G054_STPAI_DCLKIN 100 +#define R9A07G054_STPAI_ACLK_DRP 101 + +/* R9A07G054 Resets */ +#define R9A07G054_CA55_RST_1_0 0 +#define R9A07G054_CA55_RST_1_1 1 +#define R9A07G054_CA55_RST_3_0 2 +#define R9A07G054_CA55_RST_3_1 3 +#define R9A07G054_CA55_RST_4 4 +#define R9A07G054_CA55_RST_5 5 +#define R9A07G054_CA55_RST_6 6 +#define R9A07G054_CA55_RST_7 7 +#define R9A07G054_CA55_RST_8 8 +#define R9A07G054_CA55_RST_9 9 +#define R9A07G054_CA55_RST_10 10 +#define R9A07G054_CA55_RST_11 11 +#define R9A07G054_CA55_RST_12 12 +#define R9A07G054_GIC600_GICRESET_N 13 +#define R9A07G054_GIC600_DBG_GICRESET_N 14 +#define R9A07G054_IA55_RESETN 15 +#define R9A07G054_MHU_RESETN 16 +#define R9A07G054_DMAC_ARESETN 17 +#define R9A07G054_DMAC_RST_ASYNC 18 +#define R9A07G054_SYC_RESETN 19 +#define R9A07G054_OSTM0_PRESETZ 20 +#define R9A07G054_OSTM1_PRESETZ 21 +#define R9A07G054_OSTM2_PRESETZ 22 +#define R9A07G054_MTU_X_PRESET_MTU3 23 +#define R9A07G054_POE3_RST_M_REG 24 +#define R9A07G054_GPT_RST_C 25 +#define R9A07G054_POEG_A_RST 26 +#define R9A07G054_POEG_B_RST 27 +#define R9A07G054_POEG_C_RST 28 +#define R9A07G054_POEG_D_RST 29 +#define R9A07G054_WDT0_PRESETN 30 +#define R9A07G054_WDT1_PRESETN 31 +#define R9A07G054_WDT2_PRESETN 32 +#define R9A07G054_SPI_RST 33 +#define R9A07G054_SDHI0_IXRST 34 +#define R9A07G054_SDHI1_IXRST 35 +#define R9A07G054_GPU_RESETN 36 +#define R9A07G054_GPU_AXI_RESETN 37 +#define R9A07G054_GPU_ACE_RESETN 38 +#define R9A07G054_ISU_ARESETN 39 +#define R9A07G054_ISU_PRESETN 40 +#define R9A07G054_H264_X_RESET_VCP 41 +#define R9A07G054_H264_CP_PRESET_P 42 +#define R9A07G054_CRU_CMN_RSTB 43 +#define R9A07G054_CRU_PRESETN 44 +#define R9A07G054_CRU_ARESETN 45 +#define R9A07G054_MIPI_DSI_CMN_RSTB 46 +#define R9A07G054_MIPI_DSI_ARESET_N 47 +#define R9A07G054_MIPI_DSI_PRESET_N 48 +#define R9A07G054_LCDC_RESET_N 49 +#define R9A07G054_SSI0_RST_M2_REG 50 +#define R9A07G054_SSI1_RST_M2_REG 51 +#define R9A07G054_SSI2_RST_M2_REG 52 +#define R9A07G054_SSI3_RST_M2_REG 53 +#define R9A07G054_SRC_RST 54 +#define R9A07G054_USB_U2H0_HRESETN 55 +#define R9A07G054_USB_U2H1_HRESETN 56 +#define R9A07G054_USB_U2P_EXL_SYSRST 57 +#define R9A07G054_USB_PRESETN 58 +#define R9A07G054_ETH0_RST_HW_N 59 +#define R9A07G054_ETH1_RST_HW_N 60 +#define R9A07G054_I2C0_MRST 61 +#define R9A07G054_I2C1_MRST 62 +#define R9A07G054_I2C2_MRST 63 +#define R9A07G054_I2C3_MRST 64 +#define R9A07G054_SCIF0_RST_SYSTEM_N 65 +#define R9A07G054_SCIF1_RST_SYSTEM_N 66 +#define R9A07G054_SCIF2_RST_SYSTEM_N 67 +#define R9A07G054_SCIF3_RST_SYSTEM_N 68 +#define R9A07G054_SCIF4_RST_SYSTEM_N 69 +#define R9A07G054_SCI0_RST 70 +#define R9A07G054_SCI1_RST 71 +#define R9A07G054_IRDA_RST 72 +#define R9A07G054_RSPI0_RST 73 +#define R9A07G054_RSPI1_RST 74 +#define R9A07G054_RSPI2_RST 75 +#define R9A07G054_CANFD_RSTP_N 76 +#define R9A07G054_CANFD_RSTC_N 77 +#define R9A07G054_GPIO_RSTN 78 +#define R9A07G054_GPIO_PORT_RESETN 79 +#define R9A07G054_GPIO_SPARE_RESETN 80 +#define R9A07G054_ADC_PRESETN 81 +#define R9A07G054_ADC_ADRST_N 82 +#define R9A07G054_TSU_PRESETN 83 +#define R9A07G054_STPAI_ARESETN 84 + +#endif /* __DT_BINDINGS_CLOCK_R9A07G054_CPG_H__ */ -- cgit v1.2.3 From bfdf4e6208051ed7165b2e92035b4bf11f43eb63 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Thu, 27 Jan 2022 10:27:20 -0500 Subject: rseq: Remove broken uapi field layout on 32-bit little endian The rseq rseq_cs.ptr.{ptr32,padding} uapi endianness handling is entirely wrong on 32-bit little endian: a preprocessor logic mistake wrongly uses the big endian field layout on 32-bit little endian architectures. Fortunately, those ptr32 accessors were never used within the kernel, and only meant as a convenience for user-space. Remove those and replace the whole rseq_cs union by a __u64 type, as this is the only thing really needed to express the ABI. Document how 32-bit architectures are meant to interact with this field. Fixes: ec9c82e03a74 ("rseq: uapi: Declare rseq_cs field as union, update includes") Signed-off-by: Mathieu Desnoyers Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20220127152720.25898-1-mathieu.desnoyers@efficios.com --- include/uapi/linux/rseq.h | 20 ++++---------------- 1 file changed, 4 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h index 9a402fdb60e9..77ee207623a9 100644 --- a/include/uapi/linux/rseq.h +++ b/include/uapi/linux/rseq.h @@ -105,23 +105,11 @@ struct rseq { * Read and set by the kernel. Set by user-space with single-copy * atomicity semantics. This field should only be updated by the * thread which registered this data structure. Aligned on 64-bit. + * + * 32-bit architectures should update the low order bits of the + * rseq_cs field, leaving the high order bits initialized to 0. */ - union { - __u64 ptr64; -#ifdef __LP64__ - __u64 ptr; -#else - struct { -#if (defined(__BYTE_ORDER) && (__BYTE_ORDER == __BIG_ENDIAN)) || defined(__BIG_ENDIAN) - __u32 padding; /* Initialized to zero. */ - __u32 ptr32; -#else /* LITTLE */ - __u32 ptr32; - __u32 padding; /* Initialized to zero. */ -#endif /* ENDIAN */ - } ptr; -#endif - } rseq_cs; + __u64 rseq_cs; /* * Restartable sequences flags field. -- cgit v1.2.3 From c8eaf6ac76f40f6c59fc7d056e2e08c4a57ea9c7 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Fri, 28 Jan 2022 17:50:25 +0800 Subject: sched: move autogroup sysctls into its own file move autogroup sysctls to autogroup.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20220128095025.8745-1-nizhen@uniontech.com --- include/linux/sched/sysctl.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index c19dd5a2c05c..3f2b70f8d32c 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -45,10 +45,6 @@ extern unsigned int sysctl_sched_uclamp_util_min_rt_default; extern unsigned int sysctl_sched_cfs_bandwidth_slice; #endif -#ifdef CONFIG_SCHED_AUTOGROUP -extern unsigned int sysctl_sched_autogroup_enabled; -#endif - extern int sysctl_sched_rr_timeslice; extern int sched_rr_timeslice; -- cgit v1.2.3 From 295ab96f478d0fa56393e85406f19a867e26ce22 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 2 Feb 2022 01:03:20 +0100 Subject: net: dsa: provide switch operations for tracking the master state Certain drivers may need to send management traffic to the switch for things like register access, FDB dump, etc, to accelerate what their slow bus (SPI, I2C, MDIO) can already do. Ethernet is faster (especially in bulk transactions) but is also more unreliable, since the user may decide to bring the DSA master down (or not bring it up), therefore severing the link between the host and the attached switch. Drivers needing Ethernet-based register access already should have fallback logic to the slow bus if the Ethernet method fails, but that fallback may be based on a timeout, and the I/O to the switch may slow down to a halt if the master is down, because every Ethernet packet will have to time out. The driver also doesn't have the option to turn off Ethernet-based I/O momentarily, because it wouldn't know when to turn it back on. Which is where this change comes in. By tracking NETDEV_CHANGE, NETDEV_UP and NETDEV_GOING_DOWN events on the DSA master, we should know the exact interval of time during which this interface is reliably available for traffic. Provide this information to switches so they can use it as they wish. An helper is added dsa_port_master_is_operational() to check if a master port is operational. Signed-off-by: Vladimir Oltean Signed-off-by: Ansuel Smith Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/net/dsa.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 57b3e4e7413b..43c4153ef53a 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -278,6 +278,10 @@ struct dsa_port { u8 devlink_port_setup:1; + /* Master state bits, valid only on CPU ports */ + u8 master_admin_up:1; + u8 master_oper_up:1; + u8 setup:1; struct device_node *dn; @@ -478,6 +482,12 @@ static inline bool dsa_port_is_unused(struct dsa_port *dp) return dp->type == DSA_PORT_TYPE_UNUSED; } +static inline bool dsa_port_master_is_operational(struct dsa_port *dp) +{ + return dsa_port_is_cpu(dp) && dp->master_admin_up && + dp->master_oper_up; +} + static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED; @@ -1036,6 +1046,13 @@ struct dsa_switch_ops { int (*tag_8021q_vlan_add)(struct dsa_switch *ds, int port, u16 vid, u16 flags); int (*tag_8021q_vlan_del)(struct dsa_switch *ds, int port, u16 vid); + + /* + * DSA master tracking operations + */ + void (*master_state_change)(struct dsa_switch *ds, + const struct net_device *master, + bool operational); }; #define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \ -- cgit v1.2.3 From 3ec762fb13c7e7273800b94c80db1c2cc37590d1 Mon Sep 17 00:00:00 2001 From: Ansuel Smith Date: Wed, 2 Feb 2022 01:03:23 +0100 Subject: net: dsa: tag_qca: move define to include linux/dsa Move tag_qca define to include dir linux/dsa as the qca8k require access to the tagger define to support in-band mdio read/write using ethernet packet. Signed-off-by: Ansuel Smith Reviewed-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/tag_qca.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 include/linux/dsa/tag_qca.h (limited to 'include') diff --git a/include/linux/dsa/tag_qca.h b/include/linux/dsa/tag_qca.h new file mode 100644 index 000000000000..c02d2d39ff4a --- /dev/null +++ b/include/linux/dsa/tag_qca.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __TAG_QCA_H +#define __TAG_QCA_H + +#define QCA_HDR_LEN 2 +#define QCA_HDR_VERSION 0x2 + +#define QCA_HDR_RECV_VERSION GENMASK(15, 14) +#define QCA_HDR_RECV_PRIORITY GENMASK(13, 11) +#define QCA_HDR_RECV_TYPE GENMASK(10, 6) +#define QCA_HDR_RECV_FRAME_IS_TAGGED BIT(3) +#define QCA_HDR_RECV_SOURCE_PORT GENMASK(2, 0) + +#define QCA_HDR_XMIT_VERSION GENMASK(15, 14) +#define QCA_HDR_XMIT_PRIORITY GENMASK(13, 11) +#define QCA_HDR_XMIT_CONTROL GENMASK(10, 8) +#define QCA_HDR_XMIT_FROM_CPU BIT(7) +#define QCA_HDR_XMIT_DP_BIT GENMASK(6, 0) + +#endif /* __TAG_QCA_H */ -- cgit v1.2.3 From c2ee8181fddb293d296477f60b3eb4fa3ce4e1a6 Mon Sep 17 00:00:00 2001 From: Ansuel Smith Date: Wed, 2 Feb 2022 01:03:25 +0100 Subject: net: dsa: tag_qca: add define for handling mgmt Ethernet packet Add all the required define to prepare support for mgmt read/write in Ethernet packet. Any packet of this type has to be dropped as the only use of these special packet is receive ack for an mgmt write request or receive data for an mgmt read request. A struct is used that emulates the Ethernet header but is used for a different purpose. Signed-off-by: Ansuel Smith Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/tag_qca.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) (limited to 'include') diff --git a/include/linux/dsa/tag_qca.h b/include/linux/dsa/tag_qca.h index c02d2d39ff4a..f366422ab7a0 100644 --- a/include/linux/dsa/tag_qca.h +++ b/include/linux/dsa/tag_qca.h @@ -12,10 +12,54 @@ #define QCA_HDR_RECV_FRAME_IS_TAGGED BIT(3) #define QCA_HDR_RECV_SOURCE_PORT GENMASK(2, 0) +/* Packet type for recv */ +#define QCA_HDR_RECV_TYPE_NORMAL 0x0 +#define QCA_HDR_RECV_TYPE_MIB 0x1 +#define QCA_HDR_RECV_TYPE_RW_REG_ACK 0x2 + #define QCA_HDR_XMIT_VERSION GENMASK(15, 14) #define QCA_HDR_XMIT_PRIORITY GENMASK(13, 11) #define QCA_HDR_XMIT_CONTROL GENMASK(10, 8) #define QCA_HDR_XMIT_FROM_CPU BIT(7) #define QCA_HDR_XMIT_DP_BIT GENMASK(6, 0) +/* Packet type for xmit */ +#define QCA_HDR_XMIT_TYPE_NORMAL 0x0 +#define QCA_HDR_XMIT_TYPE_RW_REG 0x1 + +/* Check code for a valid mgmt packet. Switch will ignore the packet + * with this wrong. + */ +#define QCA_HDR_MGMT_CHECK_CODE_VAL 0x5 + +/* Specific define for in-band MDIO read/write with Ethernet packet */ +#define QCA_HDR_MGMT_SEQ_LEN 4 /* 4 byte for the seq */ +#define QCA_HDR_MGMT_COMMAND_LEN 4 /* 4 byte for the command */ +#define QCA_HDR_MGMT_DATA1_LEN 4 /* First 4 byte for the mdio data */ +#define QCA_HDR_MGMT_HEADER_LEN (QCA_HDR_MGMT_SEQ_LEN + \ + QCA_HDR_MGMT_COMMAND_LEN + \ + QCA_HDR_MGMT_DATA1_LEN) + +#define QCA_HDR_MGMT_DATA2_LEN 12 /* Other 12 byte for the mdio data */ +#define QCA_HDR_MGMT_PADDING_LEN 34 /* Padding to reach the min Ethernet packet */ + +#define QCA_HDR_MGMT_PKT_LEN (QCA_HDR_MGMT_HEADER_LEN + \ + QCA_HDR_LEN + \ + QCA_HDR_MGMT_DATA2_LEN + \ + QCA_HDR_MGMT_PADDING_LEN) + +#define QCA_HDR_MGMT_SEQ_NUM GENMASK(31, 0) /* 63, 32 */ +#define QCA_HDR_MGMT_CHECK_CODE GENMASK(31, 29) /* 31, 29 */ +#define QCA_HDR_MGMT_CMD BIT(28) /* 28 */ +#define QCA_HDR_MGMT_LENGTH GENMASK(23, 20) /* 23, 20 */ +#define QCA_HDR_MGMT_ADDR GENMASK(18, 0) /* 18, 0 */ + +/* Special struct emulating a Ethernet header */ +struct qca_mgmt_ethhdr { + u32 command; /* command bit 31:0 */ + u32 seq; /* seq 63:32 */ + u32 mdio_data; /* first 4byte mdio */ + __be16 hdr; /* qca hdr */ +} __packed; + #endif /* __TAG_QCA_H */ -- cgit v1.2.3 From 18be654a4345f7d937b4bfbad74bea8093e3a93c Mon Sep 17 00:00:00 2001 From: Ansuel Smith Date: Wed, 2 Feb 2022 01:03:26 +0100 Subject: net: dsa: tag_qca: add define for handling MIB packet Add struct to correctly parse a mib Ethernet packet. Signed-off-by: Ansuel Smith Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/tag_qca.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/dsa/tag_qca.h b/include/linux/dsa/tag_qca.h index f366422ab7a0..1fff57f2937b 100644 --- a/include/linux/dsa/tag_qca.h +++ b/include/linux/dsa/tag_qca.h @@ -62,4 +62,14 @@ struct qca_mgmt_ethhdr { __be16 hdr; /* qca hdr */ } __packed; +enum mdio_cmd { + MDIO_WRITE = 0x0, + MDIO_READ +}; + +struct mib_ethhdr { + u32 data[3]; /* first 3 mib counter */ + __be16 hdr; /* qca hdr */ +} __packed; + #endif /* __TAG_QCA_H */ -- cgit v1.2.3 From 31eb6b4386ad91930417e3f5c8157a4b5e31cbd5 Mon Sep 17 00:00:00 2001 From: Ansuel Smith Date: Wed, 2 Feb 2022 01:03:27 +0100 Subject: net: dsa: tag_qca: add support for handling mgmt and MIB Ethernet packet Add connect/disconnect helper to assign private struct to the DSA switch. Add support for Ethernet mgmt and MIB if the DSA driver provide an handler to correctly parse and elaborate the data. Signed-off-by: Ansuel Smith Reviewed-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/dsa/tag_qca.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/dsa/tag_qca.h b/include/linux/dsa/tag_qca.h index 1fff57f2937b..4359fb0221cf 100644 --- a/include/linux/dsa/tag_qca.h +++ b/include/linux/dsa/tag_qca.h @@ -72,4 +72,11 @@ struct mib_ethhdr { __be16 hdr; /* qca hdr */ } __packed; +struct qca_tagger_data { + void (*rw_reg_ack_handler)(struct dsa_switch *ds, + struct sk_buff *skb); + void (*mib_autocast_handler)(struct dsa_switch *ds, + struct sk_buff *skb); +}; + #endif /* __TAG_QCA_H */ -- cgit v1.2.3 From 5903123f662ed18483f05cac3f9e800a074c29ff Mon Sep 17 00:00:00 2001 From: Akhmat Karakotov Date: Fri, 28 Jan 2022 22:26:21 +0300 Subject: tcp: Use BPF timeout setting for SYN ACK RTO When setting RTO through BPF program, some SYN ACK packets were unaffected and continued to use TCP_TIMEOUT_INIT constant. This patch adds timeout option to struct request_sock. Option is initialized with TCP_TIMEOUT_INIT and is reassigned through BPF using tcp_timeout_init call. SYN ACK retransmits now use newly added timeout option. Signed-off-by: Akhmat Karakotov Acked-by: Martin KaFai Lau v2: - Add timeout option to struct request_sock. Do not call tcp_timeout_init on every syn ack retransmit. v3: - Use unsigned long for min. Bound tcp_timeout_init to TCP_RTO_MAX. v4: - Refactor duplicate code by adding reqsk_timeout function. Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 8 ++++++++ include/net/request_sock.h | 2 ++ include/net/tcp.h | 2 +- 3 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 4ad47d9f9d27..3908296d103f 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -285,6 +285,14 @@ static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req); +static inline unsigned long +reqsk_timeout(struct request_sock *req, unsigned long max_timeout) +{ + u64 timeout = (u64)req->timeout << req->num_timeout; + + return (unsigned long)min_t(u64, timeout, max_timeout); +} + static inline void inet_csk_prepare_for_destroy_sock(struct sock *sk) { /* The below has to be done to allow calling inet_csk_destroy_sock */ diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 29e41ff3ec93..144c39db9898 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -70,6 +70,7 @@ struct request_sock { struct saved_syn *saved_syn; u32 secid; u32 peer_secid; + u32 timeout; }; static inline struct request_sock *inet_reqsk(const struct sock *sk) @@ -104,6 +105,7 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, sk_node_init(&req_to_sk(req)->sk_node); sk_tx_queue_clear(req_to_sk(req)); req->saved_syn = NULL; + req->timeout = 0; req->num_timeout = 0; req->num_retrans = 0; req->sk = NULL; diff --git a/include/net/tcp.h b/include/net/tcp.h index b9fc978fb2ca..eff2487d972d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2358,7 +2358,7 @@ static inline u32 tcp_timeout_init(struct sock *sk) if (timeout <= 0) timeout = TCP_TIMEOUT_INIT; - return timeout; + return min_t(int, timeout, TCP_RTO_MAX); } static inline u32 tcp_rwnd_init_bpf(struct sock *sk) -- cgit v1.2.3 From 926597ffce0e3e2f785475df18e1636194209910 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Jan 2022 10:39:11 +0100 Subject: block: move disk_{block,unblock,flush}_events to blk.h No need to have these declarations in a public header. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20220124093913.742411-2-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/genhd.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 6906a45bc761..504f9a6674ac 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -185,9 +185,6 @@ static inline int bdev_read_only(struct block_device *bdev) return bdev->bd_read_only || get_disk_ro(bdev->bd_disk); } -extern void disk_block_events(struct gendisk *disk); -extern void disk_unblock_events(struct gendisk *disk); -extern void disk_flush_events(struct gendisk *disk, unsigned int mask); bool set_capacity_and_notify(struct gendisk *disk, sector_t size); bool disk_force_media_change(struct gendisk *disk, unsigned int events); -- cgit v1.2.3 From e7243285c0fc87054990fcde630583586ff8ed5f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Jan 2022 10:39:12 +0100 Subject: block: move blk_drop_partitions to blk.h No need to have this declaration in a public header. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20220124093913.742411-3-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/genhd.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 504f9a6674ac..aa4bd985dbe5 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -219,7 +219,6 @@ static inline u64 sb_bdev_nr_blocks(struct super_block *sb) } int bdev_disk_changed(struct gendisk *disk, bool invalidate); -void blk_drop_partitions(struct gendisk *disk); struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, struct lock_class_key *lkclass); -- cgit v1.2.3 From 322cbb50de711814c42fb088f6d31901502c711a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Jan 2022 10:39:13 +0100 Subject: block: remove genhd.h There is no good reason to keep genhd.h separate from the main blkdev.h header that includes it. So fold the contents of genhd.h into blkdev.h and remove genhd.h entirely. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20220124093913.742411-4-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 273 ++++++++++++++++++++++++++++++++++++++++++- include/linux/genhd.h | 287 ---------------------------------------------- include/linux/part_stat.h | 2 +- 3 files changed, 271 insertions(+), 291 deletions(-) delete mode 100644 include/linux/genhd.h (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f35aea98bc35..99a4384bb8a5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1,9 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* + * Portions Copyright (C) 1992 Drew Eckhardt + */ #ifndef _LINUX_BLKDEV_H #define _LINUX_BLKDEV_H -#include -#include +#include +#include +#include #include #include #include @@ -12,11 +16,15 @@ #include #include #include +#include #include #include #include +#include #include #include +#include +#include struct module; struct request_queue; @@ -33,6 +41,10 @@ struct blk_queue_stats; struct blk_stat_callback; struct blk_crypto_profile; +extern const struct device_type disk_type; +extern struct device_type part_type; +extern struct class block_class; + /* Must be consistent with blk_mq_poll_stats_bkt() */ #define BLK_MQ_POLL_STATS_BKTS 16 @@ -45,6 +57,144 @@ struct blk_crypto_profile; */ #define BLKCG_MAX_POLS 6 +#define DISK_MAX_PARTS 256 +#define DISK_NAME_LEN 32 + +#define PARTITION_META_INFO_VOLNAMELTH 64 +/* + * Enough for the string representation of any kind of UUID plus NULL. + * EFI UUID is 36 characters. MSDOS UUID is 11 characters. + */ +#define PARTITION_META_INFO_UUIDLTH (UUID_STRING_LEN + 1) + +struct partition_meta_info { + char uuid[PARTITION_META_INFO_UUIDLTH]; + u8 volname[PARTITION_META_INFO_VOLNAMELTH]; +}; + +/** + * DOC: genhd capability flags + * + * ``GENHD_FL_REMOVABLE``: indicates that the block device gives access to + * removable media. When set, the device remains present even when media is not + * inserted. Shall not be set for devices which are removed entirely when the + * media is removed. + * + * ``GENHD_FL_HIDDEN``: the block device is hidden; it doesn't produce events, + * doesn't appear in sysfs, and can't be opened from userspace or using + * blkdev_get*. Used for the underlying components of multipath devices. + * + * ``GENHD_FL_NO_PART``: partition support is disabled. The kernel will not + * scan for partitions from add_disk, and users can't add partitions manually. + * + */ +enum { + GENHD_FL_REMOVABLE = 1 << 0, + GENHD_FL_HIDDEN = 1 << 1, + GENHD_FL_NO_PART = 1 << 2, +}; + +enum { + DISK_EVENT_MEDIA_CHANGE = 1 << 0, /* media changed */ + DISK_EVENT_EJECT_REQUEST = 1 << 1, /* eject requested */ +}; + +enum { + /* Poll even if events_poll_msecs is unset */ + DISK_EVENT_FLAG_POLL = 1 << 0, + /* Forward events to udev */ + DISK_EVENT_FLAG_UEVENT = 1 << 1, + /* Block event polling when open for exclusive write */ + DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE = 1 << 2, +}; + +struct disk_events; +struct badblocks; + +struct blk_integrity { + const struct blk_integrity_profile *profile; + unsigned char flags; + unsigned char tuple_size; + unsigned char interval_exp; + unsigned char tag_size; +}; + +struct gendisk { + /* + * major/first_minor/minors should not be set by any new driver, the + * block core will take care of allocating them automatically. + */ + int major; + int first_minor; + int minors; + + char disk_name[DISK_NAME_LEN]; /* name of major driver */ + + unsigned short events; /* supported events */ + unsigned short event_flags; /* flags related to event processing */ + + struct xarray part_tbl; + struct block_device *part0; + + const struct block_device_operations *fops; + struct request_queue *queue; + void *private_data; + + int flags; + unsigned long state; +#define GD_NEED_PART_SCAN 0 +#define GD_READ_ONLY 1 +#define GD_DEAD 2 +#define GD_NATIVE_CAPACITY 3 + + struct mutex open_mutex; /* open/close mutex */ + unsigned open_partitions; /* number of open partitions */ + + struct backing_dev_info *bdi; + struct kobject *slave_dir; +#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED + struct list_head slave_bdevs; +#endif + struct timer_rand_state *random; + atomic_t sync_io; /* RAID */ + struct disk_events *ev; +#ifdef CONFIG_BLK_DEV_INTEGRITY + struct kobject integrity_kobj; +#endif /* CONFIG_BLK_DEV_INTEGRITY */ +#if IS_ENABLED(CONFIG_CDROM) + struct cdrom_device_info *cdi; +#endif + int node_id; + struct badblocks *bb; + struct lockdep_map lockdep_map; + u64 diskseq; +}; + +static inline bool disk_live(struct gendisk *disk) +{ + return !inode_unhashed(disk->part0->bd_inode); +} + +/* + * The gendisk is refcounted by the part0 block_device, and the bd_device + * therein is also used for device model presentation in sysfs. + */ +#define dev_to_disk(device) \ + (dev_to_bdev(device)->bd_disk) +#define disk_to_dev(disk) \ + (&((disk)->part0->bd_device)) + +#if IS_REACHABLE(CONFIG_CDROM) +#define disk_to_cdi(disk) ((disk)->cdi) +#else +#define disk_to_cdi(disk) NULL +#endif + +static inline dev_t disk_devt(struct gendisk *disk) +{ + return MKDEV(disk->major, disk->first_minor); +} + static inline int blk_validate_block_size(unsigned long bsize) { if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize)) @@ -596,6 +746,118 @@ static inline unsigned int blk_queue_depth(struct request_queue *q) #define for_each_bio(_bio) \ for (; _bio; _bio = _bio->bi_next) +int __must_check device_add_disk(struct device *parent, struct gendisk *disk, + const struct attribute_group **groups); +static inline int __must_check add_disk(struct gendisk *disk) +{ + return device_add_disk(NULL, disk, NULL); +} +void del_gendisk(struct gendisk *gp); +void invalidate_disk(struct gendisk *disk); +void set_disk_ro(struct gendisk *disk, bool read_only); +void disk_uevent(struct gendisk *disk, enum kobject_action action); + +static inline int get_disk_ro(struct gendisk *disk) +{ + return disk->part0->bd_read_only || + test_bit(GD_READ_ONLY, &disk->state); +} + +static inline int bdev_read_only(struct block_device *bdev) +{ + return bdev->bd_read_only || get_disk_ro(bdev->bd_disk); +} + +bool set_capacity_and_notify(struct gendisk *disk, sector_t size); +bool disk_force_media_change(struct gendisk *disk, unsigned int events); + +void add_disk_randomness(struct gendisk *disk) __latent_entropy; +void rand_initialize_disk(struct gendisk *disk); + +static inline sector_t get_start_sect(struct block_device *bdev) +{ + return bdev->bd_start_sect; +} + +static inline sector_t bdev_nr_sectors(struct block_device *bdev) +{ + return bdev->bd_nr_sectors; +} + +static inline loff_t bdev_nr_bytes(struct block_device *bdev) +{ + return (loff_t)bdev_nr_sectors(bdev) << SECTOR_SHIFT; +} + +static inline sector_t get_capacity(struct gendisk *disk) +{ + return bdev_nr_sectors(disk->part0); +} + +static inline u64 sb_bdev_nr_blocks(struct super_block *sb) +{ + return bdev_nr_sectors(sb->s_bdev) >> + (sb->s_blocksize_bits - SECTOR_SHIFT); +} + +int bdev_disk_changed(struct gendisk *disk, bool invalidate); + +struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, + struct lock_class_key *lkclass); +void put_disk(struct gendisk *disk); +struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass); + +/** + * blk_alloc_disk - allocate a gendisk structure + * @node_id: numa node to allocate on + * + * Allocate and pre-initialize a gendisk structure for use with BIO based + * drivers. + * + * Context: can sleep + */ +#define blk_alloc_disk(node_id) \ +({ \ + static struct lock_class_key __key; \ + \ + __blk_alloc_disk(node_id, &__key); \ +}) +void blk_cleanup_disk(struct gendisk *disk); + +int __register_blkdev(unsigned int major, const char *name, + void (*probe)(dev_t devt)); +#define register_blkdev(major, name) \ + __register_blkdev(major, name, NULL) +void unregister_blkdev(unsigned int major, const char *name); + +bool bdev_check_media_change(struct block_device *bdev); +int __invalidate_device(struct block_device *bdev, bool kill_dirty); +void set_capacity(struct gendisk *disk, sector_t size); + +#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED +int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); +void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk); +int bd_register_pending_holders(struct gendisk *disk); +#else +static inline int bd_link_disk_holder(struct block_device *bdev, + struct gendisk *disk) +{ + return 0; +} +static inline void bd_unlink_disk_holder(struct block_device *bdev, + struct gendisk *disk) +{ +} +static inline int bd_register_pending_holders(struct gendisk *disk) +{ + return 0; +} +#endif /* CONFIG_BLOCK_HOLDER_DEPRECATED */ + +dev_t part_devt(struct gendisk *disk, u8 partno); +void inc_diskseq(struct gendisk *disk); +dev_t blk_lookup_devt(const char *name, int partno); +void blk_request_module(dev_t devt); extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); @@ -1311,6 +1573,7 @@ void invalidate_bdev(struct block_device *bdev); int sync_blockdev(struct block_device *bdev); int sync_blockdev_nowait(struct block_device *bdev); void sync_bdevs(bool wait); +void printk_all_partitions(void); #else static inline void invalidate_bdev(struct block_device *bdev) { @@ -1326,7 +1589,11 @@ static inline int sync_blockdev_nowait(struct block_device *bdev) static inline void sync_bdevs(bool wait) { } -#endif +static inline void printk_all_partitions(void) +{ +} +#endif /* CONFIG_BLOCK */ + int fsync_bdev(struct block_device *bdev); int freeze_bdev(struct block_device *bdev); diff --git a/include/linux/genhd.h b/include/linux/genhd.h deleted file mode 100644 index aa4bd985dbe5..000000000000 --- a/include/linux/genhd.h +++ /dev/null @@ -1,287 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_GENHD_H -#define _LINUX_GENHD_H - -/* - * genhd.h Copyright (C) 1992 Drew Eckhardt - * Generic hard disk header file by - * Drew Eckhardt - * - * - */ - -#include -#include -#include -#include -#include -#include - -extern const struct device_type disk_type; -extern struct device_type part_type; -extern struct class block_class; - -#define DISK_MAX_PARTS 256 -#define DISK_NAME_LEN 32 - -#define PARTITION_META_INFO_VOLNAMELTH 64 -/* - * Enough for the string representation of any kind of UUID plus NULL. - * EFI UUID is 36 characters. MSDOS UUID is 11 characters. - */ -#define PARTITION_META_INFO_UUIDLTH (UUID_STRING_LEN + 1) - -struct partition_meta_info { - char uuid[PARTITION_META_INFO_UUIDLTH]; - u8 volname[PARTITION_META_INFO_VOLNAMELTH]; -}; - -/** - * DOC: genhd capability flags - * - * ``GENHD_FL_REMOVABLE``: indicates that the block device gives access to - * removable media. When set, the device remains present even when media is not - * inserted. Shall not be set for devices which are removed entirely when the - * media is removed. - * - * ``GENHD_FL_HIDDEN``: the block device is hidden; it doesn't produce events, - * doesn't appear in sysfs, and can't be opened from userspace or using - * blkdev_get*. Used for the underlying components of multipath devices. - * - * ``GENHD_FL_NO_PART``: partition support is disabled. The kernel will not - * scan for partitions from add_disk, and users can't add partitions manually. - * - */ -enum { - GENHD_FL_REMOVABLE = 1 << 0, - GENHD_FL_HIDDEN = 1 << 1, - GENHD_FL_NO_PART = 1 << 2, -}; - -enum { - DISK_EVENT_MEDIA_CHANGE = 1 << 0, /* media changed */ - DISK_EVENT_EJECT_REQUEST = 1 << 1, /* eject requested */ -}; - -enum { - /* Poll even if events_poll_msecs is unset */ - DISK_EVENT_FLAG_POLL = 1 << 0, - /* Forward events to udev */ - DISK_EVENT_FLAG_UEVENT = 1 << 1, - /* Block event polling when open for exclusive write */ - DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE = 1 << 2, -}; - -struct disk_events; -struct badblocks; - -struct blk_integrity { - const struct blk_integrity_profile *profile; - unsigned char flags; - unsigned char tuple_size; - unsigned char interval_exp; - unsigned char tag_size; -}; - -struct gendisk { - /* - * major/first_minor/minors should not be set by any new driver, the - * block core will take care of allocating them automatically. - */ - int major; - int first_minor; - int minors; - - char disk_name[DISK_NAME_LEN]; /* name of major driver */ - - unsigned short events; /* supported events */ - unsigned short event_flags; /* flags related to event processing */ - - struct xarray part_tbl; - struct block_device *part0; - - const struct block_device_operations *fops; - struct request_queue *queue; - void *private_data; - - int flags; - unsigned long state; -#define GD_NEED_PART_SCAN 0 -#define GD_READ_ONLY 1 -#define GD_DEAD 2 -#define GD_NATIVE_CAPACITY 3 - - struct mutex open_mutex; /* open/close mutex */ - unsigned open_partitions; /* number of open partitions */ - - struct backing_dev_info *bdi; - struct kobject *slave_dir; -#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED - struct list_head slave_bdevs; -#endif - struct timer_rand_state *random; - atomic_t sync_io; /* RAID */ - struct disk_events *ev; -#ifdef CONFIG_BLK_DEV_INTEGRITY - struct kobject integrity_kobj; -#endif /* CONFIG_BLK_DEV_INTEGRITY */ -#if IS_ENABLED(CONFIG_CDROM) - struct cdrom_device_info *cdi; -#endif - int node_id; - struct badblocks *bb; - struct lockdep_map lockdep_map; - u64 diskseq; -}; - -static inline bool disk_live(struct gendisk *disk) -{ - return !inode_unhashed(disk->part0->bd_inode); -} - -/* - * The gendisk is refcounted by the part0 block_device, and the bd_device - * therein is also used for device model presentation in sysfs. - */ -#define dev_to_disk(device) \ - (dev_to_bdev(device)->bd_disk) -#define disk_to_dev(disk) \ - (&((disk)->part0->bd_device)) - -#if IS_REACHABLE(CONFIG_CDROM) -#define disk_to_cdi(disk) ((disk)->cdi) -#else -#define disk_to_cdi(disk) NULL -#endif - -static inline dev_t disk_devt(struct gendisk *disk) -{ - return MKDEV(disk->major, disk->first_minor); -} - -void disk_uevent(struct gendisk *disk, enum kobject_action action); - -/* block/genhd.c */ -int __must_check device_add_disk(struct device *parent, struct gendisk *disk, - const struct attribute_group **groups); -static inline int __must_check add_disk(struct gendisk *disk) -{ - return device_add_disk(NULL, disk, NULL); -} -extern void del_gendisk(struct gendisk *gp); - -void invalidate_disk(struct gendisk *disk); - -void set_disk_ro(struct gendisk *disk, bool read_only); - -static inline int get_disk_ro(struct gendisk *disk) -{ - return disk->part0->bd_read_only || - test_bit(GD_READ_ONLY, &disk->state); -} - -static inline int bdev_read_only(struct block_device *bdev) -{ - return bdev->bd_read_only || get_disk_ro(bdev->bd_disk); -} - -bool set_capacity_and_notify(struct gendisk *disk, sector_t size); -bool disk_force_media_change(struct gendisk *disk, unsigned int events); - -/* drivers/char/random.c */ -extern void add_disk_randomness(struct gendisk *disk) __latent_entropy; -extern void rand_initialize_disk(struct gendisk *disk); - -static inline sector_t get_start_sect(struct block_device *bdev) -{ - return bdev->bd_start_sect; -} - -static inline sector_t bdev_nr_sectors(struct block_device *bdev) -{ - return bdev->bd_nr_sectors; -} - -static inline loff_t bdev_nr_bytes(struct block_device *bdev) -{ - return (loff_t)bdev_nr_sectors(bdev) << SECTOR_SHIFT; -} - -static inline sector_t get_capacity(struct gendisk *disk) -{ - return bdev_nr_sectors(disk->part0); -} - -static inline u64 sb_bdev_nr_blocks(struct super_block *sb) -{ - return bdev_nr_sectors(sb->s_bdev) >> - (sb->s_blocksize_bits - SECTOR_SHIFT); -} - -int bdev_disk_changed(struct gendisk *disk, bool invalidate); - -struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, - struct lock_class_key *lkclass); -extern void put_disk(struct gendisk *disk); -struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass); - -/** - * blk_alloc_disk - allocate a gendisk structure - * @node_id: numa node to allocate on - * - * Allocate and pre-initialize a gendisk structure for use with BIO based - * drivers. - * - * Context: can sleep - */ -#define blk_alloc_disk(node_id) \ -({ \ - static struct lock_class_key __key; \ - \ - __blk_alloc_disk(node_id, &__key); \ -}) -void blk_cleanup_disk(struct gendisk *disk); - -int __register_blkdev(unsigned int major, const char *name, - void (*probe)(dev_t devt)); -#define register_blkdev(major, name) \ - __register_blkdev(major, name, NULL) -void unregister_blkdev(unsigned int major, const char *name); - -bool bdev_check_media_change(struct block_device *bdev); -int __invalidate_device(struct block_device *bdev, bool kill_dirty); -void set_capacity(struct gendisk *disk, sector_t size); - -#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED -int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); -void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk); -int bd_register_pending_holders(struct gendisk *disk); -#else -static inline int bd_link_disk_holder(struct block_device *bdev, - struct gendisk *disk) -{ - return 0; -} -static inline void bd_unlink_disk_holder(struct block_device *bdev, - struct gendisk *disk) -{ -} -static inline int bd_register_pending_holders(struct gendisk *disk) -{ - return 0; -} -#endif /* CONFIG_BLOCK_HOLDER_DEPRECATED */ - -dev_t part_devt(struct gendisk *disk, u8 partno); -void inc_diskseq(struct gendisk *disk); -dev_t blk_lookup_devt(const char *name, int partno); -void blk_request_module(dev_t devt); -#ifdef CONFIG_BLOCK -void printk_all_partitions(void); -#else /* CONFIG_BLOCK */ -static inline void printk_all_partitions(void) -{ -} -#endif /* CONFIG_BLOCK */ - -#endif /* _LINUX_GENHD_H */ diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h index 6f7949b2fd8d..abeba356bc3f 100644 --- a/include/linux/part_stat.h +++ b/include/linux/part_stat.h @@ -2,7 +2,7 @@ #ifndef _LINUX_PART_STAT_H #define _LINUX_PART_STAT_H -#include +#include #include struct disk_stats { -- cgit v1.2.3 From 0a3140ea0fae377c9eaa031b7db1670ae422ed47 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Mon, 24 Jan 2022 10:11:02 +0100 Subject: block: pass a block_device and opf to blk_next_bio All callers need to set the block_device and operation, so lift that into the common code. Signed-off-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220124091107.642561-15-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/bio.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 117d7f248ac9..edeae54074ed 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -790,6 +790,7 @@ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb) bio->bi_opf |= REQ_NOWAIT; } -struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp); +struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev, + unsigned int nr_pages, unsigned int opf, gfp_t gfp); #endif /* __LINUX_BIO_H */ -- cgit v1.2.3 From 609be1066731fea86436f5f91022f82e592ab456 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Jan 2022 10:11:03 +0100 Subject: block: pass a block_device and opf to bio_alloc_bioset Pass the block_device and operation that we plan to use this bio for to bio_alloc_bioset to optimize the assigment. NULL/0 can be passed, both for the passthrough case on a raw request_queue and to temporarily avoid refactoring some nasty code. Also move the gfp_mask argument after the nr_vecs argument for a much more logical calling convention matching what most of the kernel does. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220124091107.642561-16-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/bio.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index edeae54074ed..2f63ae9a71e1 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -405,8 +405,9 @@ extern void bioset_exit(struct bio_set *); extern int biovec_init_pool(mempool_t *pool, int pool_entries); extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src); -struct bio *bio_alloc_bioset(gfp_t gfp, unsigned short nr_iovecs, - struct bio_set *bs); +struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, + unsigned int opf, gfp_t gfp_mask, + struct bio_set *bs); struct bio *bio_alloc_kiocb(struct kiocb *kiocb, unsigned short nr_vecs, struct bio_set *bs); struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs); @@ -419,7 +420,7 @@ extern struct bio_set fs_bio_set; static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned short nr_iovecs) { - return bio_alloc_bioset(gfp_mask, nr_iovecs, &fs_bio_set); + return bio_alloc_bioset(NULL, nr_iovecs, 0, gfp_mask, &fs_bio_set); } void submit_bio(struct bio *bio); -- cgit v1.2.3 From b77c88c2100ce6a5ec8126c13599b5a7f6663e32 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Jan 2022 10:11:04 +0100 Subject: block: pass a block_device and opf to bio_alloc_kiocb Pass the block_device and operation that we plan to use this bio for to bio_alloc_kiocb to optimize the assigment. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220124091107.642561-17-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/bio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 2f63ae9a71e1..5c5ada2ebb27 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -408,8 +408,8 @@ extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src); struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, unsigned int opf, gfp_t gfp_mask, struct bio_set *bs); -struct bio *bio_alloc_kiocb(struct kiocb *kiocb, unsigned short nr_vecs, - struct bio_set *bs); +struct bio *bio_alloc_kiocb(struct kiocb *kiocb, struct block_device *bdev, + unsigned short nr_vecs, unsigned int opf, struct bio_set *bs); struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs); extern void bio_put(struct bio *); -- cgit v1.2.3 From 07888c665b405b1cd3577ddebfeb74f4717a84c4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Jan 2022 10:11:05 +0100 Subject: block: pass a block_device and opf to bio_alloc Pass the block_device and operation that we plan to use this bio for to bio_alloc to optimize the assignment. NULL/0 can be passed, both for the passthrough case on a raw request_queue and to temporarily avoid refactoring some nasty code. Also move the gfp_mask argument after the nr_vecs argument for a much more logical calling convention matching what most of the kernel does. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220124091107.642561-18-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/bio.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 5c5ada2ebb27..be6ac92913d4 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -418,9 +418,10 @@ extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *); extern struct bio_set fs_bio_set; -static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned short nr_iovecs) +static inline struct bio *bio_alloc(struct block_device *bdev, + unsigned short nr_vecs, unsigned int opf, gfp_t gfp_mask) { - return bio_alloc_bioset(NULL, nr_iovecs, 0, gfp_mask, &fs_bio_set); + return bio_alloc_bioset(bdev, nr_vecs, opf, gfp_mask, &fs_bio_set); } void submit_bio(struct bio *bio); -- cgit v1.2.3 From 49add4966d79244013fce35f95c6833fae82b8b1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Jan 2022 10:11:06 +0100 Subject: block: pass a block_device and opf to bio_init Pass the block_device that we plan to use this bio for and the operation to bio_init to optimize the assignment. A NULL block_device can be passed, both for the passthrough case on a raw request_queue and to temporarily avoid refactoring some nasty code. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220124091107.642561-19-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/bio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index be6ac92913d4..41bedf727f59 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -456,8 +456,8 @@ static inline int bio_iov_vecs_to_alloc(struct iov_iter *iter, int max_segs) struct request_queue; extern int submit_bio_wait(struct bio *bio); -extern void bio_init(struct bio *bio, struct bio_vec *table, - unsigned short max_vecs); +void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table, + unsigned short max_vecs, unsigned int opf); extern void bio_uninit(struct bio *); extern void bio_reset(struct bio *); void bio_chain(struct bio *, struct bio *); -- cgit v1.2.3 From a7c50c940477bae89fb2b4f51bd969a2d95d7512 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 24 Jan 2022 10:11:07 +0100 Subject: block: pass a block_device and opf to bio_reset Pass the block_device that we plan to use this bio for and the operation to bio_reset to optimize the assigment. A NULL block_device can be passed, both for the passthrough case on a raw request_queue and to temporarily avoid refactoring some nasty code. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220124091107.642561-20-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/bio.h | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 41bedf727f59..18cfe5bb41ea 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -459,7 +459,7 @@ extern int submit_bio_wait(struct bio *bio); void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table, unsigned short max_vecs, unsigned int opf); extern void bio_uninit(struct bio *); -extern void bio_reset(struct bio *); +void bio_reset(struct bio *bio, struct block_device *bdev, unsigned int opf); void bio_chain(struct bio *, struct bio *); int bio_add_page(struct bio *, struct page *, unsigned len, unsigned off); @@ -517,13 +517,6 @@ static inline void bio_set_dev(struct bio *bio, struct block_device *bdev) bio_associate_blkg(bio); } -static inline void bio_copy_dev(struct bio *dst, struct bio *src) -{ - bio_clear_flag(dst, BIO_REMAPPED); - dst->bi_bdev = src->bi_bdev; - bio_clone_blkg_association(dst, src); -} - /* * BIO list management for use by remapping drivers (e.g. DM or MD) and loop. * -- cgit v1.2.3 From b1f866b013e6e5583f2f0bf4a61d13eddb9a1799 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 27 Jan 2022 08:05:48 +0100 Subject: block: remove blk_needs_flush_plug blk_needs_flush_plug fails to account for the cb_list, which needs flushing as well. Remove it and just check if there is a plug instead of poking into the internals of the plug structure. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220127070549.1377856-1-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 99a4384bb8a5..f902a1c2fac0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1055,14 +1055,6 @@ extern void blk_finish_plug(struct blk_plug *); void blk_flush_plug(struct blk_plug *plug, bool from_schedule); -static inline bool blk_needs_flush_plug(struct task_struct *tsk) -{ - struct blk_plug *plug = tsk->plug; - - return plug && - (plug->mq_list || !list_empty(&plug->cb_list)); -} - int blkdev_issue_flush(struct block_device *bdev); long nr_blockdev_pages(void); #else /* CONFIG_BLOCK */ @@ -1086,11 +1078,6 @@ static inline void blk_flush_plug(struct blk_plug *plug, bool async) { } -static inline bool blk_needs_flush_plug(struct task_struct *tsk) -{ - return false; -} - static inline int blkdev_issue_flush(struct block_device *bdev) { return 0; -- cgit v1.2.3 From aa8dcccaf32bfdc09f2aff089d5d60c37da5b7b5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 27 Jan 2022 08:05:49 +0100 Subject: block: check that there is a plug in blk_flush_plug Rename blk_flush_plug to __blk_flush_plug and add a wrapper that includes the NULL check instead of open coding that check everywhere. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220127070549.1377856-2-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f902a1c2fac0..654163d3b903 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1053,7 +1053,12 @@ extern void blk_start_plug(struct blk_plug *); extern void blk_start_plug_nr_ios(struct blk_plug *, unsigned short); extern void blk_finish_plug(struct blk_plug *); -void blk_flush_plug(struct blk_plug *plug, bool from_schedule); +void __blk_flush_plug(struct blk_plug *plug, bool from_schedule); +static inline void blk_flush_plug(struct blk_plug *plug, bool async) +{ + if (plug) + __blk_flush_plug(plug, async); +} int blkdev_issue_flush(struct block_device *bdev); long nr_blockdev_pages(void); -- cgit v1.2.3 From b42c1fc3d55e077d36718ad9800d89100b2aff81 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 27 Jan 2022 07:41:25 +0100 Subject: block: fix the kerneldoc for bio_end_io_acct Document the actually existing parameter name. Reported-by: Stephen Rothwell Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220127064125.1314347-1-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 654163d3b903..3bfc75a2a450 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1520,7 +1520,7 @@ void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, /** * bio_end_io_acct - end I/O accounting for bio based drivers * @bio: bio to end account for - * @start: start time returned by bio_start_io_acct() + * @start_time: start time returned by bio_start_io_acct() */ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) { -- cgit v1.2.3 From 043cfff99a18933fda2fb2e163daee73cc07910b Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Thu, 23 Dec 2021 17:23:00 +0100 Subject: firmware: ti_sci: Fix compilation failure when CONFIG_TI_SCI_PROTOCOL is not defined Remove an extra ";" which breaks compilation. Fixes: 53bf2b0e4e4c ("firmware: ti_sci: Add support for getting resource with subtype") Signed-off-by: Christophe JAILLET Signed-off-by: Nishanth Menon Link: https://lore.kernel.org/r/e6c3cb793e1a6a2a0ae2528d5a5650dfe6a4b6ff.1640276505.git.christophe.jaillet@wanadoo.fr --- include/linux/soc/ti/ti_sci_protocol.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h index 0aad7009b50e..bd0d11af76c5 100644 --- a/include/linux/soc/ti/ti_sci_protocol.h +++ b/include/linux/soc/ti/ti_sci_protocol.h @@ -645,7 +645,7 @@ devm_ti_sci_get_of_resource(const struct ti_sci_handle *handle, static inline struct ti_sci_resource * devm_ti_sci_get_resource(const struct ti_sci_handle *handle, struct device *dev, - u32 dev_id, u32 sub_type); + u32 dev_id, u32 sub_type) { return ERR_PTR(-EINVAL); } -- cgit v1.2.3 From 52cc6ffc0ab2c61a76127b9347567fc97c15582f Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 31 Jan 2022 08:40:01 -0800 Subject: page_pool: Refactor page_pool to enable fragmenting after allocation This change is meant to permit a driver to perform "fragmenting" of the page from within the driver instead of the current model which requires pre-partitioning the page. The main motivation behind this is to support use cases where the page will be split up by the driver after DMA instead of before. With this change it becomes possible to start using page pool to replace some of the existing use cases where multiple references were being used for a single page, but the number needed was unknown as the size could be dynamic. For example, with this code it would be possible to do something like the following to handle allocation: page = page_pool_alloc_pages(); if (!page) return NULL; page_pool_fragment_page(page, DRIVER_PAGECNT_BIAS_MAX); rx_buf->page = page; rx_buf->pagecnt_bias = DRIVER_PAGECNT_BIAS_MAX; Then we would process a received buffer by handling it with: rx_buf->pagecnt_bias--; Once the page has been fully consumed we could then flush the remaining instances with: if (page_pool_defrag_page(page, rx_buf->pagecnt_bias)) continue; page_pool_put_defragged_page(pool, page -1, !!budget); The general idea is that we want to have the ability to allocate a page with excess fragment count and then trim off the unneeded fragments. Signed-off-by: Alexander Duyck Reviewed-by: Ilias Apalodimas Signed-off-by: David S. Miller --- include/net/page_pool.h | 82 +++++++++++++++++++++++++++++++------------------ 1 file changed, 52 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 79a805542d0f..97c3c19872ff 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -201,21 +201,67 @@ static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data, } #endif -void page_pool_put_page(struct page_pool *pool, struct page *page, - unsigned int dma_sync_size, bool allow_direct); +void page_pool_put_defragged_page(struct page_pool *pool, struct page *page, + unsigned int dma_sync_size, + bool allow_direct); -/* Same as above but will try to sync the entire area pool->max_len */ -static inline void page_pool_put_full_page(struct page_pool *pool, - struct page *page, bool allow_direct) +static inline void page_pool_fragment_page(struct page *page, long nr) +{ + atomic_long_set(&page->pp_frag_count, nr); +} + +static inline long page_pool_defrag_page(struct page *page, long nr) +{ + long ret; + + /* If nr == pp_frag_count then we have cleared all remaining + * references to the page. No need to actually overwrite it, instead + * we can leave this to be overwritten by the calling function. + * + * The main advantage to doing this is that an atomic_read is + * generally a much cheaper operation than an atomic update, + * especially when dealing with a page that may be partitioned + * into only 2 or 3 pieces. + */ + if (atomic_long_read(&page->pp_frag_count) == nr) + return 0; + + ret = atomic_long_sub_return(nr, &page->pp_frag_count); + WARN_ON(ret < 0); + return ret; +} + +static inline bool page_pool_is_last_frag(struct page_pool *pool, + struct page *page) +{ + /* If fragments aren't enabled or count is 0 we were the last user */ + return !(pool->p.flags & PP_FLAG_PAGE_FRAG) || + (page_pool_defrag_page(page, 1) == 0); +} + +static inline void page_pool_put_page(struct page_pool *pool, + struct page *page, + unsigned int dma_sync_size, + bool allow_direct) { /* When page_pool isn't compiled-in, net/core/xdp.c doesn't * allow registering MEM_TYPE_PAGE_POOL, but shield linker. */ #ifdef CONFIG_PAGE_POOL - page_pool_put_page(pool, page, -1, allow_direct); + if (!page_pool_is_last_frag(pool, page)) + return; + + page_pool_put_defragged_page(pool, page, dma_sync_size, allow_direct); #endif } +/* Same as above but will try to sync the entire area pool->max_len */ +static inline void page_pool_put_full_page(struct page_pool *pool, + struct page *page, bool allow_direct) +{ + page_pool_put_page(pool, page, -1, allow_direct); +} + /* Same as above but the caller must guarantee safe context. e.g NAPI */ static inline void page_pool_recycle_direct(struct page_pool *pool, struct page *page) @@ -243,30 +289,6 @@ static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr) page->dma_addr_upper = upper_32_bits(addr); } -static inline void page_pool_set_frag_count(struct page *page, long nr) -{ - atomic_long_set(&page->pp_frag_count, nr); -} - -static inline long page_pool_atomic_sub_frag_count_return(struct page *page, - long nr) -{ - long ret; - - /* As suggested by Alexander, atomic_long_read() may cover up the - * reference count errors, so avoid calling atomic_long_read() in - * the cases of freeing or draining the page_frags, where we would - * not expect it to match or that are slowpath anyway. - */ - if (__builtin_constant_p(nr) && - atomic_long_read(&page->pp_frag_count) == nr) - return 0; - - ret = atomic_long_sub_return(nr, &page->pp_frag_count); - WARN_ON(ret < 0); - return ret; -} - static inline bool is_page_pool_compiled_in(void) { #ifdef CONFIG_PAGE_POOL -- cgit v1.2.3 From 7af4a361a62f59b44ec301f21090823365dd0244 Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Thu, 3 Feb 2022 11:16:53 +0100 Subject: net: dsa: mv88e6xxx: Improve isolation of standalone ports Clear MapDA on standalone ports to bypass any ATU lookup that might point the packet in the wrong direction. This means that all packets are flooded using the PVT config. So make sure that standalone ports are only allowed to communicate with the local upstream port. Here is a scenario in which this is needed: CPU | .----. .---0---. | .--0--. | sw0 | | | sw1 | '-1-2-3-' | '-1-2-' '---' - sw0p1 and sw1p1 are bridged - sw0p2 and sw1p2 are in standalone mode - Learning must be enabled on sw0p3 in order for hardware forwarding to work properly between bridged ports 1. A packet with SA :aa comes in on sw1p2 1a. Egresses sw1p0 1b. Ingresses sw0p3, ATU adds an entry for :aa towards port 3 1c. Egresses sw0p0 2. A packet with DA :aa comes in on sw0p2 2a. If an ATU lookup is done at this point, the packet will be incorrectly forwarded towards sw0p3. With this change in place, the ATU is bypassed and the packet is forwarded in accordance with the PVT, which only contains the CPU port. Signed-off-by: Tobias Waldekranz Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/dsa.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 43c4153ef53a..6e5ef62a7dce 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -591,6 +591,18 @@ static inline bool dsa_is_upstream_port(struct dsa_switch *ds, int port) return port == dsa_upstream_port(ds, port); } +/* Return the local port used to reach the CPU port */ +static inline unsigned int dsa_switch_upstream_port(struct dsa_switch *ds) +{ + struct dsa_port *dp; + + dsa_switch_for_each_available_port(dp, ds) { + return dsa_upstream_port(ds, dp->index); + } + + return ds->num_ports; +} + /* Return true if @upstream_ds is an upstream switch of @downstream_ds, meaning * that the routing port from @downstream_ds to @upstream_ds is also the port * which @downstream_ds uses to reach its dedicated CPU. -- cgit v1.2.3 From d352b20f4174a6bd998992329b773ab513232880 Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Thu, 3 Feb 2022 11:16:56 +0100 Subject: net: dsa: mv88e6xxx: Improve multichip isolation of standalone ports Given that standalone ports are now configured to bypass the ATU and forward all frames towards the upstream port, extend the ATU bypass to multichip systems. Load VID 0 (standalone) into the VTU with the policy bit set. Since VID 4095 (bridged) is already loaded, we now know that all VIDs in use are always available in all VTUs. Therefore, we can safely enable 802.1Q on DSA ports. Setting the DSA ports' VTU policy to TRAP means that all incoming frames on VID 0 will be classified as MGMT - as a result, the ATU is bypassed on all subsequent switches. With this isolation in place, we are able to support configurations that are simultaneously very quirky and very useful. Quirky because it involves looping cables between local switchports like in this example: CPU | .------. .---0---. | .----0----. | sw0 | | | sw1 | '-1-2-3-' | '-1-2-3-4-' $ @ '---' $ @ % % We have three physically looped pairs ($, @, and %). This is very useful because it allows us to run the kernel's kselftests for the bridge on mv88e6xxx hardware. Signed-off-by: Tobias Waldekranz Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/dsa.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 6e5ef62a7dce..ca8c14b547b4 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -591,6 +591,12 @@ static inline bool dsa_is_upstream_port(struct dsa_switch *ds, int port) return port == dsa_upstream_port(ds, port); } +/* Return true if this is a DSA port leading away from the CPU */ +static inline bool dsa_is_downstream_port(struct dsa_switch *ds, int port) +{ + return dsa_is_dsa_port(ds, port) && !dsa_is_upstream_port(ds, port); +} + /* Return the local port used to reach the CPU port */ static inline unsigned int dsa_switch_upstream_port(struct dsa_switch *ds) { -- cgit v1.2.3 From dca384a3bf5af1c781cfa6aec63904bdb5018c36 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Wed, 2 Feb 2022 10:43:40 +0100 Subject: drm/connector: Fix typo in documentation Commit 4adc33f36d80 ("drm/edid: Split deep color modes between RGB and YUV444") introduced two new variables in struct drm_display_info and their documentation, but the documentation part had a typo resulting in a doc build warning. Fixes: 4adc33f36d80 ("drm/edid: Split deep color modes between RGB and YUV444") Reported-by: Stephen Rothwell Signed-off-by: Maxime Ripard Reviewed-by: Simon Ser Link: https://patchwork.freedesktop.org/patch/msgid/20220202094340.875190-1-maxime@cerno.tech --- include/drm/drm_connector.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index 64cf5f88c05b..5e36eb3df66f 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -592,13 +592,13 @@ struct drm_display_info { bool rgb_quant_range_selectable; /** - * @edid_hdmi_dc_rgb444_modes: Mask of supported hdmi deep color modes + * @edid_hdmi_rgb444_dc_modes: Mask of supported hdmi deep color modes * in RGB 4:4:4. Even more stuff redundant with @bus_formats. */ u8 edid_hdmi_rgb444_dc_modes; /** - * @edid_hdmi_dc_ycbcr444_modes: Mask of supported hdmi deep color + * @edid_hdmi_ycbcr444_dc_modes: Mask of supported hdmi deep color * modes in YCbCr 4:4:4. Even more stuff redundant with @bus_formats. */ u8 edid_hdmi_ycbcr444_dc_modes; -- cgit v1.2.3 From bb747becf8084ebbbb8986f7927057034d5c3329 Mon Sep 17 00:00:00 2001 From: Akhil R Date: Mon, 24 Jan 2022 16:48:14 +0530 Subject: dt-bindings: Add headers for Tegra234 I2C Add dt-bindings header files for I2C controllers for Tegra234 Signed-off-by: Akhil R Signed-off-by: Thierry Reding --- include/dt-bindings/clock/tegra234-clock.h | 19 ++++++++++++++++++- include/dt-bindings/reset/tegra234-reset.h | 8 ++++++++ 2 files changed, 26 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/clock/tegra234-clock.h b/include/dt-bindings/clock/tegra234-clock.h index 8d7e66e1b6ef..dc524e6e8d66 100644 --- a/include/dt-bindings/clock/tegra234-clock.h +++ b/include/dt-bindings/clock/tegra234-clock.h @@ -20,6 +20,24 @@ #define TEGRA234_CLK_EMC 31U /** @brief output of gate CLK_ENB_FUSE */ #define TEGRA234_CLK_FUSE 40U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_I2C1 */ +#define TEGRA234_CLK_I2C1 48U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_I2C2 */ +#define TEGRA234_CLK_I2C2 49U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_I2C3 */ +#define TEGRA234_CLK_I2C3 50U +/** output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_I2C4 */ +#define TEGRA234_CLK_I2C4 51U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_I2C6 */ +#define TEGRA234_CLK_I2C6 52U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_I2C7 */ +#define TEGRA234_CLK_I2C7 53U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_I2C8 */ +#define TEGRA234_CLK_I2C8 54U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_I2C9 */ +#define TEGRA234_CLK_I2C9 55U +/** @brief PLLP clk output */ +#define TEGRA234_CLK_PLLP_OUT0 102U /** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_SDMMC4 */ #define TEGRA234_CLK_SDMMC4 123U /** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_UARTA */ @@ -30,5 +48,4 @@ #define TEGRA234_CLK_PLLC4 237U /** @brief 32K input clock provided by PMIC */ #define TEGRA234_CLK_CLK_32K 289U - #endif diff --git a/include/dt-bindings/reset/tegra234-reset.h b/include/dt-bindings/reset/tegra234-reset.h index 50e13bced642..29632598fe11 100644 --- a/include/dt-bindings/reset/tegra234-reset.h +++ b/include/dt-bindings/reset/tegra234-reset.h @@ -10,6 +10,14 @@ * @brief Identifiers for Resets controllable by firmware * @{ */ +#define TEGRA234_RESET_I2C1 24U +#define TEGRA234_RESET_I2C2 29U +#define TEGRA234_RESET_I2C3 30U +#define TEGRA234_RESET_I2C4 31U +#define TEGRA234_RESET_I2C6 32U +#define TEGRA234_RESET_I2C7 33U +#define TEGRA234_RESET_I2C8 34U +#define TEGRA234_RESET_I2C9 35U #define TEGRA234_RESET_SDMMC4 85U #define TEGRA234_RESET_UARTA 100U -- cgit v1.2.3 From 38eb21a5fcd2ae482c8377ccb75c265037ef538f Mon Sep 17 00:00:00 2001 From: Akhil R Date: Mon, 24 Jan 2022 16:48:16 +0530 Subject: dt-bindings: Add headers for Tegra234 PWM Add dt-bindings header files for PWM of Tegra234 Signed-off-by: Akhil R Signed-off-by: Thierry Reding --- include/dt-bindings/clock/tegra234-clock.h | 16 ++++++++++++++++ include/dt-bindings/reset/tegra234-reset.h | 8 ++++++++ 2 files changed, 24 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/clock/tegra234-clock.h b/include/dt-bindings/clock/tegra234-clock.h index dc524e6e8d66..2529e7ec0bf4 100644 --- a/include/dt-bindings/clock/tegra234-clock.h +++ b/include/dt-bindings/clock/tegra234-clock.h @@ -38,6 +38,22 @@ #define TEGRA234_CLK_I2C9 55U /** @brief PLLP clk output */ #define TEGRA234_CLK_PLLP_OUT0 102U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_PWM1 */ +#define TEGRA234_CLK_PWM1 105U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_PWM2 */ +#define TEGRA234_CLK_PWM2 106U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_PWM3 */ +#define TEGRA234_CLK_PWM3 107U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_PWM4 */ +#define TEGRA234_CLK_PWM4 108U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_PWM5 */ +#define TEGRA234_CLK_PWM5 109U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_PWM6 */ +#define TEGRA234_CLK_PWM6 110U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_PWM7 */ +#define TEGRA234_CLK_PWM7 111U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_PWM8 */ +#define TEGRA234_CLK_PWM8 112U /** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_SDMMC4 */ #define TEGRA234_CLK_SDMMC4 123U /** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_UARTA */ diff --git a/include/dt-bindings/reset/tegra234-reset.h b/include/dt-bindings/reset/tegra234-reset.h index 29632598fe11..ba390b86361d 100644 --- a/include/dt-bindings/reset/tegra234-reset.h +++ b/include/dt-bindings/reset/tegra234-reset.h @@ -18,6 +18,14 @@ #define TEGRA234_RESET_I2C7 33U #define TEGRA234_RESET_I2C8 34U #define TEGRA234_RESET_I2C9 35U +#define TEGRA234_RESET_PWM1 68U +#define TEGRA234_RESET_PWM2 69U +#define TEGRA234_RESET_PWM3 70U +#define TEGRA234_RESET_PWM4 71U +#define TEGRA234_RESET_PWM5 72U +#define TEGRA234_RESET_PWM6 73U +#define TEGRA234_RESET_PWM7 74U +#define TEGRA234_RESET_PWM8 75U #define TEGRA234_RESET_SDMMC4 85U #define TEGRA234_RESET_UARTA 100U -- cgit v1.2.3 From e4b1eb24ce5a696ef7229f9926ff34d7502f0582 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Thu, 27 Jan 2022 11:34:53 -0800 Subject: thermal: netlink: Add a new event to notify CPU capabilities change Add a new netlink event to notify change in CPU capabilities in terms of performance and efficiency. Firmware may change CPU capabilities as a result of thermal events in the system or to account for changes in the TDP (thermal design power) level. This notification type will allow user space to avoid running workloads on certain CPUs or proactively adjust power limits to avoid future events. The netlink message consists of a nested attribute (THERMAL_GENL_ATTR_CPU_CAPABILITY) with three attributes: * THERMAL_GENL_ATTR_CPU_CAPABILITY_ID (type u32): -- logical CPU number * THERMAL_GENL_ATTR_CPU_CAPABILITY_PERFORMANCE (type u32): -- Scaled performance from 0-1023 * THERMAL_GENL_ATTR_CPU_CAPABILITY_EFFICIENCY (type u32): -- Scaled efficiency from 0-1023 Reviewed-by: Len Brown Signed-off-by: Srinivas Pandruvada Signed-off-by: Rafael J. Wysocki --- include/uapi/linux/thermal.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/thermal.h b/include/uapi/linux/thermal.h index 9aa2fedfa309..fc78bf3aead7 100644 --- a/include/uapi/linux/thermal.h +++ b/include/uapi/linux/thermal.h @@ -44,7 +44,10 @@ enum thermal_genl_attr { THERMAL_GENL_ATTR_CDEV_MAX_STATE, THERMAL_GENL_ATTR_CDEV_NAME, THERMAL_GENL_ATTR_GOV_NAME, - + THERMAL_GENL_ATTR_CPU_CAPABILITY, + THERMAL_GENL_ATTR_CPU_CAPABILITY_ID, + THERMAL_GENL_ATTR_CPU_CAPABILITY_PERFORMANCE, + THERMAL_GENL_ATTR_CPU_CAPABILITY_EFFICIENCY, __THERMAL_GENL_ATTR_MAX, }; #define THERMAL_GENL_ATTR_MAX (__THERMAL_GENL_ATTR_MAX - 1) @@ -71,6 +74,7 @@ enum thermal_genl_event { THERMAL_GENL_EVENT_CDEV_DELETE, /* Cdev unbound */ THERMAL_GENL_EVENT_CDEV_STATE_UPDATE, /* Cdev state updated */ THERMAL_GENL_EVENT_TZ_GOV_CHANGE, /* Governor policy changed */ + THERMAL_GENL_EVENT_CPU_CAPABILITY_CHANGE, /* CPU capability changed */ __THERMAL_GENL_EVENT_MAX, }; #define THERMAL_GENL_EVENT_MAX (__THERMAL_GENL_EVENT_MAX - 1) -- cgit v1.2.3 From 22f56b8e890d4e2835951b437bb6eeebfd1cb18b Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 3 Feb 2022 16:01:39 -0500 Subject: XArray: Include bitmap.h from xarray.h xas_find_chunk() calls find_next_bit(), which is defined in find.h, included from bitmap.h. Inside the kernel, this isn't a problem because bitmap.h is included from cpumask.h which is dragged in (eventually) by gfp.h. When building the test-suite, that doesn't happen, so we need to include bitmap.h explicitly. Fixes: 4ade0818cf04 ("tools: sync tools/bitmap with mother linux") Reported-by: Liam Howlett Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/xarray.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index d6d5da6ed735..66e28bc1a023 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -9,6 +9,7 @@ * See Documentation/core-api/xarray.rst for how to use the XArray. */ +#include #include #include #include -- cgit v1.2.3 From 00edb2bac29f2e9c1674e85479fa5e3aa8cc648f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 26 Jan 2022 10:55:44 -0800 Subject: i40e: remove enum i40e_client_state It's not used. Signed-off-by: Jakub Kicinski Reviewed-by: Jesse Brandeburg Tested-by: Gurucharan G Signed-off-by: Tony Nguyen --- include/linux/net/intel/i40e_client.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h index 6b3267b49755..ed42bd5f639f 100644 --- a/include/linux/net/intel/i40e_client.h +++ b/include/linux/net/intel/i40e_client.h @@ -26,11 +26,6 @@ struct i40e_client_version { u8 rsvd; }; -enum i40e_client_state { - __I40E_CLIENT_NULL, - __I40E_CLIENT_REGISTERED -}; - enum i40e_client_instance_state { __I40E_CLIENT_INSTANCE_NONE, __I40E_CLIENT_INSTANCE_OPENED, @@ -190,11 +185,6 @@ struct i40e_client { const struct i40e_client_ops *ops; /* client ops provided by the client */ }; -static inline bool i40e_client_is_registered(struct i40e_client *client) -{ - return test_bit(__I40E_CLIENT_REGISTERED, &client->state); -} - void i40e_client_device_register(struct i40e_info *ldev, struct i40e_client *client); void i40e_client_device_unregister(struct i40e_info *ldev); -- cgit v1.2.3 From 3a99f121fe0bfa4b65ff74d9e980018caf54c2d4 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Thu, 27 Jan 2022 18:55:01 -0800 Subject: firmware: qcom: scm: Introduce pas_metadata context Starting with Qualcomm SM8450, some new security enhancements has been done in the secure world, which results in the requirement to keep the metadata segment accessible by the secure world from init_image() until auth_and_reset(). Introduce a "PAS metadata context" object that can be passed to init_image() for tracking the mapped memory and a related release function for client drivers to release the mapping once either auth_and_reset() has been invoked or in error handling paths on the way there. Signed-off-by: Bjorn Andersson Reviewed-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20220128025513.97188-2-bjorn.andersson@linaro.org --- include/linux/qcom_scm.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index ca4a88d7cbdc..681748619890 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -68,8 +68,16 @@ extern int qcom_scm_set_warm_boot_addr(void *entry, const cpumask_t *cpus); extern void qcom_scm_cpu_power_down(u32 flags); extern int qcom_scm_set_remote_state(u32 state, u32 id); +struct qcom_scm_pas_metadata { + void *ptr; + dma_addr_t phys; + ssize_t size; +}; + extern int qcom_scm_pas_init_image(u32 peripheral, const void *metadata, - size_t size); + size_t size, + struct qcom_scm_pas_metadata *ctx); +void qcom_scm_pas_metadata_release(struct qcom_scm_pas_metadata *ctx); extern int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr, phys_addr_t size); extern int qcom_scm_pas_auth_and_reset(u32 peripheral); -- cgit v1.2.3 From 8bd42e2341a7857010001f08ee1729ced3b0e394 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Thu, 27 Jan 2022 18:55:03 -0800 Subject: soc: qcom: mdt_loader: Allow hash segment to be split out It's been observed that some firmware found in a Qualcomm SM8450 device has the hash table in a separate .bNN file. Use the newly extracted helper function to load this segment from the separate file, if it's determined that the hashes are not part of the already loaded firmware. In order to do this, the function needs access to the firmware basename and to provide more useful error messages a struct device to associate the errors with. Signed-off-by: Bjorn Andersson Reviewed-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20220128025513.97188-4-bjorn.andersson@linaro.org --- include/linux/soc/qcom/mdt_loader.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/soc/qcom/mdt_loader.h b/include/linux/soc/qcom/mdt_loader.h index afd47217996b..46bdb7bace9a 100644 --- a/include/linux/soc/qcom/mdt_loader.h +++ b/include/linux/soc/qcom/mdt_loader.h @@ -23,7 +23,8 @@ int qcom_mdt_load_no_init(struct device *dev, const struct firmware *fw, const char *fw_name, int pas_id, void *mem_region, phys_addr_t mem_phys, size_t mem_size, phys_addr_t *reloc_base); -void *qcom_mdt_read_metadata(const struct firmware *fw, size_t *data_len); +void *qcom_mdt_read_metadata(const struct firmware *fw, size_t *data_len, + const char *fw_name, struct device *dev); #else /* !IS_ENABLED(CONFIG_QCOM_MDT_LOADER) */ @@ -51,7 +52,8 @@ static inline int qcom_mdt_load_no_init(struct device *dev, } static inline void *qcom_mdt_read_metadata(const struct firmware *fw, - size_t *data_len) + size_t *data_len, const char *fw_name, + struct device *dev) { return ERR_PTR(-ENODEV); } -- cgit v1.2.3 From b794eecb2af77145d36b9c28f056e242add9c4b2 Mon Sep 17 00:00:00 2001 From: Dave Ertman Date: Tue, 23 Nov 2021 10:25:36 -0800 Subject: ice: add support for DSCP QoS for IDC The ice driver provides QoS information to auxiliary drivers through the exported function ice_get_qos_params. This function doesn't currently support L3 DSCP QoS. Add the necessary defines, structure elements and code to support DSCP QoS through the IIDC functions. Signed-off-by: Dave Ertman Signed-off-by: Shiraz Saleem Signed-off-by: Tony Nguyen --- include/linux/net/intel/iidc.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/net/intel/iidc.h b/include/linux/net/intel/iidc.h index 1289593411d3..1c1332e4df26 100644 --- a/include/linux/net/intel/iidc.h +++ b/include/linux/net/intel/iidc.h @@ -32,6 +32,8 @@ enum iidc_rdma_protocol { }; #define IIDC_MAX_USER_PRIORITY 8 +#define IIDC_MAX_DSCP_MAPPING 64 +#define IIDC_DSCP_PFC_MODE 0x1 /* Struct to hold per RDMA Qset info */ struct iidc_rdma_qset_params { @@ -60,6 +62,8 @@ struct iidc_qos_params { u8 vport_relative_bw; u8 vport_priority_type; u8 num_tc; + u8 pfc_mode; + u8 dscp_map[IIDC_MAX_DSCP_MAPPING]; }; struct iidc_event { -- cgit v1.2.3 From f4e526ff7e38e27bb87d53131d227a6fd6f73ab5 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Thu, 27 Jan 2022 18:55:08 -0800 Subject: soc: qcom: mdt_loader: Extract PAS operations Rather than passing a boolean to indicate if the PAS operations should be performed from within __mdt_load(), extract them to their own helper function. This will allow clients to invoke this directly, with some qcom_scm_pas_metadata context that they later needs to release, without further having to complicate the prototype of qcom_mdt_load(). Signed-off-by: Bjorn Andersson Reviewed-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20220128025513.97188-9-bjorn.andersson@linaro.org --- include/linux/soc/qcom/mdt_loader.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/soc/qcom/mdt_loader.h b/include/linux/soc/qcom/mdt_loader.h index 46bdb7bace9a..9e8e60421192 100644 --- a/include/linux/soc/qcom/mdt_loader.h +++ b/include/linux/soc/qcom/mdt_loader.h @@ -10,10 +10,14 @@ struct device; struct firmware; +struct qcom_scm_pas_metadata; #if IS_ENABLED(CONFIG_QCOM_MDT_LOADER) ssize_t qcom_mdt_get_size(const struct firmware *fw); +int qcom_mdt_pas_init(struct device *dev, const struct firmware *fw, + const char *fw_name, int pas_id, phys_addr_t mem_phys, + struct qcom_scm_pas_metadata *pas_metadata_ctx); int qcom_mdt_load(struct device *dev, const struct firmware *fw, const char *fw_name, int pas_id, void *mem_region, phys_addr_t mem_phys, size_t mem_size, @@ -33,6 +37,13 @@ static inline ssize_t qcom_mdt_get_size(const struct firmware *fw) return -ENODEV; } +static inline int qcom_mdt_pas_init(struct device *dev, const struct firmware *fw, + const char *fw_name, int pas_id, phys_addr_t mem_phys, + struct qcom_scm_pas_metadata *pas_metadata_ctx) +{ + return -ENODEV; +} + static inline int qcom_mdt_load(struct device *dev, const struct firmware *fw, const char *fw_name, int pas_id, void *mem_region, phys_addr_t mem_phys, -- cgit v1.2.3 From 52beb1fc237d67cdc64277dc90047767a6fc52d7 Mon Sep 17 00:00:00 2001 From: Stephan Gerhold Date: Wed, 1 Dec 2021 14:05:04 +0100 Subject: firmware: qcom: scm: Drop cpumask parameter from set_boot_addr() qcom_scm_set_cold/warm_boot_addr() currently take a cpumask parameter, but it's not very useful because at the end we always set the same entry address for all CPUs. This also allows speeding up probe of cpuidle-qcom-spm a bit because only one SCM call needs to be made to the TrustZone firmware, instead of one per CPU. The main reason for this change is that it allows implementing the "multi-cluster" variant of the set_boot_addr() call more easily without having to rely on functions that break in certain build configurations or that are not exported to modules. Signed-off-by: Stephan Gerhold Acked-by: Daniel Lezcano Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20211201130505.257379-4-stephan@gerhold.net --- include/linux/qcom_scm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index 681748619890..f8335644a01a 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -63,8 +63,8 @@ enum qcom_scm_ice_cipher { extern bool qcom_scm_is_available(void); -extern int qcom_scm_set_cold_boot_addr(void *entry, const cpumask_t *cpus); -extern int qcom_scm_set_warm_boot_addr(void *entry, const cpumask_t *cpus); +extern int qcom_scm_set_cold_boot_addr(void *entry); +extern int qcom_scm_set_warm_boot_addr(void *entry); extern void qcom_scm_cpu_power_down(u32 flags); extern int qcom_scm_set_remote_state(u32 state, u32 id); -- cgit v1.2.3 From 2651bf680bc2ad9a078b7222b0873145ab4ece07 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 3 Feb 2022 11:28:25 -0800 Subject: block: introduce BLK_STS_OFFLINE Currently, drivers reports BLK_STS_IOERR for devices that are not full online or being removed. This behavior could cause confusion for users, as they are not really I/O errors from the device. Solve this issue with a new state BLK_STS_OFFLINE, which reports "device offline error" in dmesg instead of "I/O error". EIO is intentionally kept to not change user visible return value. Signed-off-by: Song Liu Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20220203192827.1370270-2-song@kernel.org Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index fe065c394fff..5561e58d158a 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -153,6 +153,13 @@ typedef u8 __bitwise blk_status_t; */ #define BLK_STS_ZONE_ACTIVE_RESOURCE ((__force blk_status_t)16) +/* + * BLK_STS_OFFLINE is returned from the driver when the target device is offline + * or is being taken offline. This could help differentiate the case where a + * device is intentionally being shut down from a real I/O error. + */ +#define BLK_STS_OFFLINE ((__force blk_status_t)17) + /** * blk_path_error - returns true if error may be path related * @error: status the request was completed with -- cgit v1.2.3 From 8b5413647262dda8d8d0e07e14ea1de9ac7cf0b2 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Mon, 17 Jan 2022 21:56:13 +0100 Subject: netfilter: nfqueue: enable to get skb->priority This info could be useful to improve traffic analysis. Signed-off-by: Nicolas Dichtel Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nfnetlink_queue.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nfnetlink_queue.h b/include/uapi/linux/netfilter/nfnetlink_queue.h index aed90c4df0c8..ef7c97f21a15 100644 --- a/include/uapi/linux/netfilter/nfnetlink_queue.h +++ b/include/uapi/linux/netfilter/nfnetlink_queue.h @@ -61,6 +61,7 @@ enum nfqnl_attr_type { NFQA_SECCTX, /* security context string */ NFQA_VLAN, /* nested attribute: packet vlan info */ NFQA_L2HDR, /* full L2 header */ + NFQA_PRIORITY, /* skb->priority */ __NFQA_MAX }; -- cgit v1.2.3 From bb62a765b1b5597d32a426096aa78d2a8eb6b091 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 20 Jan 2022 13:06:59 +0100 Subject: netfilter: conntrack: make all extensions 8-byte alignned All extensions except one need 8 byte alignment, so just make that the default. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_extend.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index c7515d82ab06..705a4487f023 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -49,7 +49,7 @@ enum nf_ct_ext_id { struct nf_ct_ext { u8 offset[NF_CT_EXT_NUM]; u8 len; - char data[]; + char data[] __aligned(8); }; static inline bool __nf_ct_ext_exist(const struct nf_ct_ext *ext, u8 id) @@ -83,10 +83,7 @@ struct nf_ct_ext_type { void (*destroy)(struct nf_conn *ct); enum nf_ct_ext_id id; - - /* Length and min alignment. */ u8 len; - u8 align; }; int nf_ct_extend_register(const struct nf_ct_ext_type *type); -- cgit v1.2.3 From 5f31edc0676b55cd6baf5ba119d1881f3fbadee1 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 20 Jan 2022 13:07:00 +0100 Subject: netfilter: conntrack: move extension sizes into core No need to specify this in the registration modules, we already collect all sizes for build-time checks on the maximum combined size. After this change, all extensions except nat have no meaningful content in their nf_ct_ext_type struct definition. Next patch handles nat, this will then allow to remove the dynamic register api completely. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_extend.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 705a4487f023..87d818414092 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -83,7 +83,6 @@ struct nf_ct_ext_type { void (*destroy)(struct nf_conn *ct); enum nf_ct_ext_id id; - u8 len; }; int nf_ct_extend_register(const struct nf_ct_ext_type *type); -- cgit v1.2.3 From 1bc91a5ddf3eaea0e0ea957cccf3abdcfcace00e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 20 Jan 2022 13:07:01 +0100 Subject: netfilter: conntrack: handle ->destroy hook via nat_ops instead The nat module already exposes a few functions to the conntrack core. Move the nat extension destroy hook to it. After this, no conntrack extension needs a destroy hook. 'struct nf_ct_ext_type' and the register/unregister api can be removed in a followup patch. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 1 + include/net/netfilter/nf_conntrack_extend.h | 3 --- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 15e71bfff726..c2c6f332fb90 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -379,6 +379,7 @@ struct nf_nat_hook { unsigned int (*manip_pkt)(struct sk_buff *skb, struct nf_conn *ct, enum nf_nat_manip_type mtype, enum ip_conntrack_dir dir); + void (*remove_nat_bysrc)(struct nf_conn *ct); }; extern const struct nf_nat_hook __rcu *nf_nat_hook; diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 87d818414092..343f9194423a 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -79,9 +79,6 @@ void nf_ct_ext_destroy(struct nf_conn *ct); void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp); struct nf_ct_ext_type { - /* Destroys relationships (can be NULL). */ - void (*destroy)(struct nf_conn *ct); - enum nf_ct_ext_id id; }; -- cgit v1.2.3 From 1015c3de23eedb8ac5a163165434484df44cfe00 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 20 Jan 2022 13:07:02 +0100 Subject: netfilter: conntrack: remove extension register api These no longer register/unregister a meaningful structure so remove it. Cc: Paul Blakey Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_acct.h | 1 - include/net/netfilter/nf_conntrack_ecache.h | 13 ------------- include/net/netfilter/nf_conntrack_extend.h | 9 --------- include/net/netfilter/nf_conntrack_labels.h | 3 --- include/net/netfilter/nf_conntrack_seqadj.h | 3 --- include/net/netfilter/nf_conntrack_timeout.h | 12 ------------ include/net/netfilter/nf_conntrack_timestamp.h | 13 ------------- 7 files changed, 54 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_acct.h b/include/net/netfilter/nf_conntrack_acct.h index 7f44a771530e..4b2b7f8914ea 100644 --- a/include/net/netfilter/nf_conntrack_acct.h +++ b/include/net/netfilter/nf_conntrack_acct.h @@ -78,7 +78,6 @@ static inline void nf_ct_acct_update(struct nf_conn *ct, u32 dir, void nf_conntrack_acct_pernet_init(struct net *net); -int nf_conntrack_acct_init(void); void nf_conntrack_acct_fini(void); #endif /* _NF_CONNTRACK_ACCT_H */ diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index d932e22edcb4..16bcff809b18 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -166,9 +166,6 @@ void nf_conntrack_ecache_work(struct net *net, enum nf_ct_ecache_state state); void nf_conntrack_ecache_pernet_init(struct net *net); void nf_conntrack_ecache_pernet_fini(struct net *net); -int nf_conntrack_ecache_init(void); -void nf_conntrack_ecache_fini(void); - static inline bool nf_conntrack_ecache_dwork_pending(const struct net *net) { return net->ct.ecache_dwork_pending; @@ -194,16 +191,6 @@ static inline void nf_conntrack_ecache_pernet_init(struct net *net) static inline void nf_conntrack_ecache_pernet_fini(struct net *net) { } - -static inline int nf_conntrack_ecache_init(void) -{ - return 0; -} - -static inline void nf_conntrack_ecache_fini(void) -{ -} - static inline bool nf_conntrack_ecache_dwork_pending(const struct net *net) { return false; } #endif /* CONFIG_NF_CONNTRACK_EVENTS */ #endif /*_NF_CONNTRACK_ECACHE_H*/ diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 343f9194423a..96635ad2acc7 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -72,16 +72,7 @@ static inline void *__nf_ct_ext_find(const struct nf_conn *ct, u8 id) #define nf_ct_ext_find(ext, id) \ ((id##_TYPE *)__nf_ct_ext_find((ext), (id))) -/* Destroy all relationships */ -void nf_ct_ext_destroy(struct nf_conn *ct); - /* Add this type, returns pointer to data or NULL. */ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp); -struct nf_ct_ext_type { - enum nf_ct_ext_id id; -}; - -int nf_ct_extend_register(const struct nf_ct_ext_type *type); -void nf_ct_extend_unregister(const struct nf_ct_ext_type *type); #endif /* _NF_CONNTRACK_EXTEND_H */ diff --git a/include/net/netfilter/nf_conntrack_labels.h b/include/net/netfilter/nf_conntrack_labels.h index ba916411c4e1..3c23298e68ca 100644 --- a/include/net/netfilter/nf_conntrack_labels.h +++ b/include/net/netfilter/nf_conntrack_labels.h @@ -45,12 +45,9 @@ int nf_connlabels_replace(struct nf_conn *ct, #ifdef CONFIG_NF_CONNTRACK_LABELS int nf_conntrack_labels_init(void); -void nf_conntrack_labels_fini(void); int nf_connlabels_get(struct net *net, unsigned int bit); void nf_connlabels_put(struct net *net); #else -static inline int nf_conntrack_labels_init(void) { return 0; } -static inline void nf_conntrack_labels_fini(void) {} static inline int nf_connlabels_get(struct net *net, unsigned int bit) { return 0; } static inline void nf_connlabels_put(struct net *net) {} #endif diff --git a/include/net/netfilter/nf_conntrack_seqadj.h b/include/net/netfilter/nf_conntrack_seqadj.h index 0a10b50537ae..883c414b768e 100644 --- a/include/net/netfilter/nf_conntrack_seqadj.h +++ b/include/net/netfilter/nf_conntrack_seqadj.h @@ -42,7 +42,4 @@ int nf_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int protoff); s32 nf_ct_seq_offset(const struct nf_conn *ct, enum ip_conntrack_dir, u32 seq); -int nf_conntrack_seqadj_init(void); -void nf_conntrack_seqadj_fini(void); - #endif /* _NF_CONNTRACK_SEQADJ_H */ diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h index 659b0ea25b4d..db507e4a65bb 100644 --- a/include/net/netfilter/nf_conntrack_timeout.h +++ b/include/net/netfilter/nf_conntrack_timeout.h @@ -89,23 +89,11 @@ static inline unsigned int *nf_ct_timeout_lookup(const struct nf_conn *ct) } #ifdef CONFIG_NF_CONNTRACK_TIMEOUT -int nf_conntrack_timeout_init(void); -void nf_conntrack_timeout_fini(void); void nf_ct_untimeout(struct net *net, struct nf_ct_timeout *timeout); int nf_ct_set_timeout(struct net *net, struct nf_conn *ct, u8 l3num, u8 l4num, const char *timeout_name); void nf_ct_destroy_timeout(struct nf_conn *ct); #else -static inline int nf_conntrack_timeout_init(void) -{ - return 0; -} - -static inline void nf_conntrack_timeout_fini(void) -{ - return; -} - static inline int nf_ct_set_timeout(struct net *net, struct nf_conn *ct, u8 l3num, u8 l4num, const char *timeout_name) diff --git a/include/net/netfilter/nf_conntrack_timestamp.h b/include/net/netfilter/nf_conntrack_timestamp.h index 820ea34b6029..57138d974a9f 100644 --- a/include/net/netfilter/nf_conntrack_timestamp.h +++ b/include/net/netfilter/nf_conntrack_timestamp.h @@ -40,21 +40,8 @@ struct nf_conn_tstamp *nf_ct_tstamp_ext_add(struct nf_conn *ct, gfp_t gfp) #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP void nf_conntrack_tstamp_pernet_init(struct net *net); - -int nf_conntrack_tstamp_init(void); -void nf_conntrack_tstamp_fini(void); #else static inline void nf_conntrack_tstamp_pernet_init(struct net *net) {} - -static inline int nf_conntrack_tstamp_init(void) -{ - return 0; -} - -static inline void nf_conntrack_tstamp_fini(void) -{ - return; -} #endif /* CONFIG_NF_CONNTRACK_TIMESTAMP */ #endif /* _NF_CONNTRACK_TSTAMP_H */ -- cgit v1.2.3 From 20ff32024624102596f2b4083a17a97ca71d6cd8 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 20 Jan 2022 16:09:13 +0100 Subject: netfilter: conntrack: pptp: use single option structure Instead of exposing the four hooks individually use a sinle hook ops structure. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_pptp.h | 38 +++++++++++++---------------- 1 file changed, 17 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/nf_conntrack_pptp.h b/include/linux/netfilter/nf_conntrack_pptp.h index a28aa289afdc..c3bdb4370938 100644 --- a/include/linux/netfilter/nf_conntrack_pptp.h +++ b/include/linux/netfilter/nf_conntrack_pptp.h @@ -300,26 +300,22 @@ union pptp_ctrl_union { struct PptpSetLinkInfo setlink; }; -extern int -(*nf_nat_pptp_hook_outbound)(struct sk_buff *skb, - struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned int protoff, - struct PptpControlHeader *ctlh, - union pptp_ctrl_union *pptpReq); - -extern int -(*nf_nat_pptp_hook_inbound)(struct sk_buff *skb, - struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned int protoff, - struct PptpControlHeader *ctlh, - union pptp_ctrl_union *pptpReq); - -extern void -(*nf_nat_pptp_hook_exp_gre)(struct nf_conntrack_expect *exp_orig, - struct nf_conntrack_expect *exp_reply); - -extern void -(*nf_nat_pptp_hook_expectfn)(struct nf_conn *ct, - struct nf_conntrack_expect *exp); +struct nf_nat_pptp_hook { + int (*outbound)(struct sk_buff *skb, + struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, + struct PptpControlHeader *ctlh, + union pptp_ctrl_union *pptpReq); + int (*inbound)(struct sk_buff *skb, + struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, + struct PptpControlHeader *ctlh, + union pptp_ctrl_union *pptpReq); + void (*exp_gre)(struct nf_conntrack_expect *exp_orig, + struct nf_conntrack_expect *exp_reply); + void (*expectfn)(struct nf_conn *ct, + struct nf_conntrack_expect *exp); +}; +extern const struct nf_nat_pptp_hook __rcu *nf_nat_pptp_hook; #endif /* _NF_CONNTRACK_PPTP_H */ -- cgit v1.2.3 From b93235e68921b9acd38ee309953a3a9808105289 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 2 Feb 2022 14:20:31 -0800 Subject: tls: cap the output scatter list to something reasonable TLS recvmsg() passes user pages as destination for decrypt. The decrypt operation is repeated record by record, each record being 16kB, max. TLS allocates an sg_table and uses iov_iter_get_pages() to populate it with enough pages to fit the decrypted record. Even though we decrypt a single message at a time we size the sg_table based on the entire length of the iovec. This leads to unnecessarily large allocations, risking triggering OOM conditions. Use iov_iter_truncate() / iov_iter_reexpand() to construct a "capped" version of iov_iter_npages(). Alternatively we could parametrize iov_iter_npages() to take the size as arg instead of using i->count, or do something else.. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/uio.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/linux/uio.h b/include/linux/uio.h index 1198a2bfc9bf..739285fe5a2f 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -273,6 +273,23 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) i->count = count; } +static inline int +iov_iter_npages_cap(struct iov_iter *i, int maxpages, size_t max_bytes) +{ + size_t shorted = 0; + int npages; + + if (iov_iter_count(i) > max_bytes) { + shorted = iov_iter_count(i) - max_bytes; + iov_iter_truncate(i, max_bytes); + } + npages = iov_iter_npages(i, INT_MAX); + if (shorted) + iov_iter_reexpand(i, iov_iter_count(i) + shorted); + + return npages; +} + struct csum_state { __wsum csum; size_t off; -- cgit v1.2.3 From 56b4b5abcdab6daf71c5536fca2772f178590e06 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 2 Feb 2022 17:01:06 +0100 Subject: block: clone crypto and integrity data in __bio_clone_fast __bio_clone_fast should also clone integrity and crypto data, as a clone without those is incomplete. Right now the only caller that can actually support crypto and integrity data (dm) does it manually for the one callchain that supports these, but we better do it properly in the core. Note that all callers except for the above mentioned one also don't need to handle failure at all, given that the integrity and crypto clones are based on mempool allocations that won't fail for sleeping allocations. Signed-off-by: Christoph Hellwig Reviewed-by: Mike Snitzer Link: https://lore.kernel.org/r/20220202160109.108149-11-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/bio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 18cfe5bb41ea..b814361c957b 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -413,7 +413,7 @@ struct bio *bio_alloc_kiocb(struct kiocb *kiocb, struct block_device *bdev, struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs); extern void bio_put(struct bio *); -extern void __bio_clone_fast(struct bio *, struct bio *); +int __bio_clone_fast(struct bio *bio, struct bio *bio_src, gfp_t gfp); extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *); extern struct bio_set fs_bio_set; -- cgit v1.2.3 From abfc426d1b2fb2176df59851a64223b58ddae7e7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 2 Feb 2022 17:01:09 +0100 Subject: block: pass a block_device to bio_clone_fast Pass a block_device to bio_clone_fast and __bio_clone_fast and give the functions more suitable names. Signed-off-by: Christoph Hellwig Reviewed-by: Mike Snitzer Link: https://lore.kernel.org/r/20220202160109.108149-14-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/bio.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index b814361c957b..7523aba4ddf7 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -413,8 +413,10 @@ struct bio *bio_alloc_kiocb(struct kiocb *kiocb, struct block_device *bdev, struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs); extern void bio_put(struct bio *); -int __bio_clone_fast(struct bio *bio, struct bio *bio_src, gfp_t gfp); -extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *); +struct bio *bio_alloc_clone(struct block_device *bdev, struct bio *bio_src, + gfp_t gfp, struct bio_set *bs); +int bio_init_clone(struct block_device *bdev, struct bio *bio, + struct bio *bio_src, gfp_t gfp); extern struct bio_set fs_bio_set; -- cgit v1.2.3 From 916acbf6b4b9262df7de1d2b6208a4efa209a88f Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 3 Feb 2022 16:45:21 +0200 Subject: serial: core: Fix the definition name in the comment of UPF_* flags From day 1 the UPF_LAST_USER wasn't defined, a specific number of the last bit for userspace. Instead the code always relies on ASYNCB_LAST_USER. Fix comment accordingly. Fixes: 904326ecac02 ("tty,serial: Unify UPF_* and ASYNC_* flag definitions") Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20220203144521.16457-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index c58cc142d23f..31f7fe527395 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -171,7 +171,7 @@ struct uart_port { * assigned from the serial_struct flags in uart_set_info() * [for bit definitions in the UPF_CHANGE_MASK] * - * Bits [0..UPF_LAST_USER] are userspace defined/visible/changeable + * Bits [0..ASYNCB_LAST_USER] are userspace defined/visible/changeable * The remaining bits are serial-core specific and not modifiable by * userspace. */ -- cgit v1.2.3 From 84564481bc4520c47e7fe9c594c0523d81e6a97a Mon Sep 17 00:00:00 2001 From: Aswath Govindraju Date: Fri, 7 Jan 2022 08:44:25 +0100 Subject: mux: Add support for reading mux state from consumer DT node In some cases, we might need to provide the state of the mux to be set for the operation of a given peripheral. Therefore, pass this information using mux-states property. Link: https://lore.kernel.org/lkml/20211123081222.27979-1-a-govindraju@ti.com Signed-off-by: Aswath Govindraju Signed-off-by: Peter Rosin (minor edits) Link: https://lore.kernel.org/r/aac25be8-9515-a980-f7cb-709938c84822@axentia.se Signed-off-by: Greg Kroah-Hartman --- include/linux/mux/consumer.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/mux/consumer.h b/include/linux/mux/consumer.h index 7a09b040ac39..2e25c838f831 100644 --- a/include/linux/mux/consumer.h +++ b/include/linux/mux/consumer.h @@ -14,14 +14,19 @@ struct device; struct mux_control; +struct mux_state; unsigned int mux_control_states(struct mux_control *mux); int __must_check mux_control_select_delay(struct mux_control *mux, unsigned int state, unsigned int delay_us); +int __must_check mux_state_select_delay(struct mux_state *mstate, + unsigned int delay_us); int __must_check mux_control_try_select_delay(struct mux_control *mux, unsigned int state, unsigned int delay_us); +int __must_check mux_state_try_select_delay(struct mux_state *mstate, + unsigned int delay_us); static inline int __must_check mux_control_select(struct mux_control *mux, unsigned int state) @@ -29,18 +34,31 @@ static inline int __must_check mux_control_select(struct mux_control *mux, return mux_control_select_delay(mux, state, 0); } +static inline int __must_check mux_state_select(struct mux_state *mstate) +{ + return mux_state_select_delay(mstate, 0); +} + static inline int __must_check mux_control_try_select(struct mux_control *mux, unsigned int state) { return mux_control_try_select_delay(mux, state, 0); } +static inline int __must_check mux_state_try_select(struct mux_state *mstate) +{ + return mux_state_try_select_delay(mstate, 0); +} + int mux_control_deselect(struct mux_control *mux); +int mux_state_deselect(struct mux_state *mstate); struct mux_control *mux_control_get(struct device *dev, const char *mux_name); void mux_control_put(struct mux_control *mux); struct mux_control *devm_mux_control_get(struct device *dev, const char *mux_name); +struct mux_state *devm_mux_state_get(struct device *dev, + const char *mux_name); #endif /* _LINUX_MUX_CONSUMER_H */ -- cgit v1.2.3 From bb6e8c28414335a551da5973d44cc537f7abe65a Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Wed, 12 Jan 2022 08:00:53 -0800 Subject: firmware_loader: simplfy builtin or module check The existing check is outdated and confuses developers. Use the already existing IS_REACHABLE() defined on kconfig.h which makes the intention much clearer. Cc: Randy Dunlap Cc: Masahiro Yamada Reported-by: Borislav Petkov Reported-by: Greg Kroah-Hartman Suggested-by: Masahiro Yamada Signed-off-by: Luis Chamberlain Ackd-by: Randy Dunlap Link: https://lore.kernel.org/r/20220112160053.723795-1-mcgrof@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/firmware.h b/include/linux/firmware.h index 3b057dfc8284..ec2ccfebef65 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -34,7 +34,7 @@ static inline bool firmware_request_builtin(struct firmware *fw, } #endif -#if defined(CONFIG_FW_LOADER) || (defined(CONFIG_FW_LOADER_MODULE) && defined(MODULE)) +#if IS_REACHABLE(CONFIG_FW_LOADER) int request_firmware(const struct firmware **fw, const char *name, struct device *device); int firmware_request_nowarn(const struct firmware **fw, const char *name, -- cgit v1.2.3 From bed89478934a9803d1a4d97574dcc30e509aa972 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 2 Feb 2022 10:49:38 +0200 Subject: ieee80211: fix -Wcast-qual warnings When enabling -Wcast-qual e.g. via W=3, we get a lot of warnings from this file, whenever it's included. Since the fixes are simple, just do that. Signed-off-by: Johannes Berg Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20220202104617.79ec4a4bab29.I8177a0c79d656c552e22c88931d8da06f2977896@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 559b6c644938..60ee7b3f58e7 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2427,7 +2427,7 @@ struct ieee80211_tx_pwr_env { static inline u8 ieee80211_he_oper_size(const u8 *he_oper_ie) { - struct ieee80211_he_operation *he_oper = (void *)he_oper_ie; + const struct ieee80211_he_operation *he_oper = (const void *)he_oper_ie; u8 oper_len = sizeof(struct ieee80211_he_operation); u32 he_oper_params; @@ -2460,7 +2460,7 @@ ieee80211_he_oper_size(const u8 *he_oper_ie) static inline const struct ieee80211_he_6ghz_oper * ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) { - const u8 *ret = (void *)&he_oper->optional; + const u8 *ret = (const void *)&he_oper->optional; u32 he_oper_params; if (!he_oper) @@ -2475,7 +2475,7 @@ ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS) ret++; - return (void *)ret; + return (const void *)ret; } /* HE Spatial Reuse defines */ @@ -2496,7 +2496,7 @@ ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) static inline u8 ieee80211_he_spr_size(const u8 *he_spr_ie) { - struct ieee80211_he_spr *he_spr = (void *)he_spr_ie; + const struct ieee80211_he_spr *he_spr = (const void *)he_spr_ie; u8 spr_len = sizeof(struct ieee80211_he_spr); u8 he_spr_params; -- cgit v1.2.3 From 7e367b06f16b3d22e884af55117601d2a73fca03 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 2 Feb 2022 10:49:39 +0200 Subject: cfg80211: fix -Wcast-qual warnings When enabling -Wcast-qual e.g. via W=3, we get a lot of warnings from this file, whenever it's included. Since the fixes are simple, just do that. Signed-off-by: Johannes Berg Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20220202104617.6a1d52213019.I92d82e7251cf712faa43fd09db3142327a3bce3d@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index d19e48f9fdc6..f6db085ff3df 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2604,7 +2604,7 @@ const struct element *ieee80211_bss_get_elem(struct cfg80211_bss *bss, u8 id); */ static inline const u8 *ieee80211_bss_get_ie(struct cfg80211_bss *bss, u8 id) { - return (void *)ieee80211_bss_get_elem(bss, id); + return (const void *)ieee80211_bss_get_elem(bss, id); } @@ -5970,9 +5970,9 @@ cfg80211_find_ie_match(u8 eid, const u8 *ies, unsigned int len, (!match_len && match_offset))) return NULL; - return (void *)cfg80211_find_elem_match(eid, ies, len, - match, match_len, - match_offset ? + return (const void *)cfg80211_find_elem_match(eid, ies, len, + match, match_len, + match_offset ? match_offset - 2 : 0); } @@ -6099,7 +6099,7 @@ static inline const u8 * cfg80211_find_vendor_ie(unsigned int oui, int oui_type, const u8 *ies, unsigned int len) { - return (void *)cfg80211_find_vendor_elem(oui, oui_type, ies, len); + return (const void *)cfg80211_find_vendor_elem(oui, oui_type, ies, len); } /** -- cgit v1.2.3 From 5beb53d6ba4f39743d057e756db22bd8c079fc21 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 2 Feb 2022 10:49:40 +0200 Subject: ieee80211: radiotap: fix -Wcast-qual warnings When enabling -Wcast-qual e.g. via W=3, we get a lot of warnings from this file, whenever it's included. Since the fixes are simple, just do that. Signed-off-by: Johannes Berg Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20220202104617.cc733aeb1a18.I03396e1bf7a1af364cbd0916037f65d800035039@changeid Signed-off-by: Johannes Berg --- include/net/ieee80211_radiotap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index 11630351c978..598f53d2a3a0 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -1,6 +1,6 @@ /* * Copyright (c) 2017 Intel Deutschland GmbH - * Copyright (c) 2018-2019 Intel Corporation + * Copyright (c) 2018-2019, 2021 Intel Corporation * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -365,7 +365,7 @@ enum ieee80211_radiotap_zero_len_psdu_type { */ static inline u16 ieee80211_get_radiotap_len(const char *data) { - struct ieee80211_radiotap_header *hdr = (void *)data; + const struct ieee80211_radiotap_header *hdr = (const void *)data; return get_unaligned_le16(&hdr->it_len); } -- cgit v1.2.3 From ea5907db2a9ccf37fdb6d1e67bcb620c1fea10f8 Mon Sep 17 00:00:00 2001 From: Avraham Stern Date: Wed, 2 Feb 2022 10:49:47 +0200 Subject: mac80211: fix struct ieee80211_tx_info size The size of the status_driver_data field was not adjusted when the is_valid_ack_signal field was added. Since the size of struct ieee80211_tx_info is limited, replace the is_valid_ack_signal field with a flags field, and adjust the struct size accordingly. Signed-off-by: Avraham Stern Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20220202104617.0ff363d4fa56.I45792c0187034a6d0e1c99a7db741996ef7caba3@changeid Signed-off-by: Johannes Berg --- include/net/mac80211.h | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index c50221d7e82c..bd6912d0292b 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -7,7 +7,7 @@ * Copyright 2007-2010 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018 - 2021 Intel Corporation + * Copyright (C) 2018 - 2022 Intel Corporation */ #ifndef MAC80211_H @@ -883,6 +883,17 @@ enum mac80211_tx_control_flags { IEEE80211_TX_CTRL_DONT_REORDER = BIT(8), }; +/** + * enum mac80211_tx_status_flags - flags to describe transmit status + * + * @IEEE80211_TX_STATUS_ACK_SIGNAL_VALID: ACK signal is valid + * + * These flags are used in tx_info->status.flags. + */ +enum mac80211_tx_status_flags { + IEEE80211_TX_STATUS_ACK_SIGNAL_VALID = BIT(0), +}; + /* * This definition is used as a mask to clear all temporary flags, which are * set by the tx handlers for each transmission attempt by the mac80211 stack. @@ -1046,7 +1057,7 @@ ieee80211_rate_get_vht_nss(const struct ieee80211_tx_rate *rate) * @status.antenna: (legacy, kept only for iwlegacy) * @status.tx_time: airtime consumed for transmission; note this is only * used for WMM AC, not for airtime fairness - * @status.is_valid_ack_signal: ACK signal is valid + * @status.flags: status flags, see &enum mac80211_tx_status_flags * @status.status_driver_data: driver use area * @ack: union part for pure ACK data * @ack.cookie: cookie for the ACK @@ -1099,8 +1110,8 @@ struct ieee80211_tx_info { u8 ampdu_len; u8 antenna; u16 tx_time; - bool is_valid_ack_signal; - void *status_driver_data[19 / sizeof(void *)]; + u8 flags; + void *status_driver_data[18 / sizeof(void *)]; } status; struct { struct ieee80211_tx_rate driver_rates[ -- cgit v1.2.3 From b9794a822281944ef3de5b1812a94cbdb8134320 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Fri, 28 Jan 2022 17:35:33 +0100 Subject: powercap/drivers/dtpm: Convert the init table section to a simple array The init table section is freed after the system booted. However the next changes will make per module the DTPM description, so the table won't be accessible when the module is loaded. In order to fix that, we should move the table to the data section where there are very few entries and that makes strange to add it there. The main goal of the table was to keep self-encapsulated code and we can keep it almost as it by using an array instead. Suggested-by: Ulf Hansson Reviewed-by: Ulf Hansson Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20220128163537.212248-2-daniel.lezcano@linaro.org --- include/asm-generic/vmlinux.lds.h | 11 ----------- include/linux/dtpm.h | 24 +++--------------------- 2 files changed, 3 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 42f3866bca69..2a10db2f0bc5 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -321,16 +321,6 @@ #define THERMAL_TABLE(name) #endif -#ifdef CONFIG_DTPM -#define DTPM_TABLE() \ - . = ALIGN(8); \ - __dtpm_table = .; \ - KEEP(*(__dtpm_table)) \ - __dtpm_table_end = .; -#else -#define DTPM_TABLE() -#endif - #define KERNEL_DTB() \ STRUCT_ALIGN(); \ __dtb_start = .; \ @@ -723,7 +713,6 @@ ACPI_PROBE_TABLE(irqchip) \ ACPI_PROBE_TABLE(timer) \ THERMAL_TABLE(governor) \ - DTPM_TABLE() \ EARLYCON_TABLE() \ LSM_TABLE() \ EARLY_LSM_TABLE() \ diff --git a/include/linux/dtpm.h b/include/linux/dtpm.h index d37e5d06a357..506048158a50 100644 --- a/include/linux/dtpm.h +++ b/include/linux/dtpm.h @@ -32,29 +32,11 @@ struct dtpm_ops { void (*release)(struct dtpm *); }; -typedef int (*dtpm_init_t)(void); - -struct dtpm_descr { - dtpm_init_t init; +struct dtpm_subsys_ops { + const char *name; + int (*init)(void); }; -/* Init section thermal table */ -extern struct dtpm_descr __dtpm_table[]; -extern struct dtpm_descr __dtpm_table_end[]; - -#define DTPM_TABLE_ENTRY(name, __init) \ - static struct dtpm_descr __dtpm_table_entry_##name \ - __used __section("__dtpm_table") = { \ - .init = __init, \ - } - -#define DTPM_DECLARE(name, init) DTPM_TABLE_ENTRY(name, init) - -#define for_each_dtpm_table(__dtpm) \ - for (__dtpm = __dtpm_table; \ - __dtpm < __dtpm_table_end; \ - __dtpm++) - static inline struct dtpm *to_dtpm(struct powercap_zone *zone) { return container_of(zone, struct dtpm, zone); -- cgit v1.2.3 From 3759ec678e8944dc2ea70cab77a300408f78ae27 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Fri, 28 Jan 2022 17:35:34 +0100 Subject: powercap/drivers/dtpm: Add hierarchy creation The DTPM framework is available but without a way to configure it. This change provides a way to create a hierarchy of DTPM node where the power consumption reflects the sum of the children's power consumption. It is up to the platform to specify an array of dtpm nodes where each element has a pointer to its parent, except the top most one. The type of the node gives the indication of which initialization callback to call. At this time, we can create a virtual node, where its purpose is to be a parent in the hierarchy, and a DT node where the name describes its path. In order to ensure a nice self-encapsulation, the DTPM subsys array contains a couple of initialization functions, one to setup the DTPM backend and one to initialize it up. With this approach, the DTPM framework has a very few material to export. Signed-off-by: Daniel Lezcano Reviewed-by: Ulf Hansson Link: https://lore.kernel.org/r/20220128163537.212248-3-daniel.lezcano@linaro.org --- include/linux/dtpm.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/dtpm.h b/include/linux/dtpm.h index 506048158a50..f7a25c70dd4c 100644 --- a/include/linux/dtpm.h +++ b/include/linux/dtpm.h @@ -32,9 +32,23 @@ struct dtpm_ops { void (*release)(struct dtpm *); }; +struct device_node; + struct dtpm_subsys_ops { const char *name; int (*init)(void); + int (*setup)(struct dtpm *, struct device_node *); +}; + +enum DTPM_NODE_TYPE { + DTPM_NODE_VIRTUAL = 0, + DTPM_NODE_DT, +}; + +struct dtpm_node { + enum DTPM_NODE_TYPE type; + const char *name; + struct dtpm_node *parent; }; static inline struct dtpm *to_dtpm(struct powercap_zone *zone) @@ -52,4 +66,5 @@ void dtpm_unregister(struct dtpm *dtpm); int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent); +int dtpm_create_hierarchy(struct of_device_id *dtpm_match_table); #endif -- cgit v1.2.3 From ae26508651272695a3ab353f75ab9a8daf3da324 Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Sun, 23 Jan 2022 20:45:06 +0800 Subject: cpufreq: Move to_gov_attr_set() to cpufreq.h So it can be reused by other codes. Signed-off-by: Kevin Hao Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 1ab29e61b078..f0dfc0b260ec 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -658,6 +658,11 @@ struct gov_attr_set { /* sysfs ops for cpufreq governors */ extern const struct sysfs_ops governor_sysfs_ops; +static inline struct gov_attr_set *to_gov_attr_set(struct kobject *kobj) +{ + return container_of(kobj, struct gov_attr_set, kobj); +} + void gov_attr_set_init(struct gov_attr_set *attr_set, struct list_head *list_node); void gov_attr_set_get(struct gov_attr_set *attr_set, struct list_head *list_node); unsigned int gov_attr_set_put(struct gov_attr_set *attr_set, struct list_head *list_node); -- cgit v1.2.3 From e70e13e7d4ab8f932f49db1c9500b30a34a6d420 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Fri, 4 Feb 2022 01:55:18 +0100 Subject: bpf: Implement bpf_core_types_are_compat(). Adopt libbpf's bpf_core_types_are_compat() for kernel duty by adding explicit recursion limit of 2 which is enough to handle 2 levels of function prototypes. Signed-off-by: Matteo Croce Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220204005519.60361-2-mcroce@linux.microsoft.com --- include/linux/btf.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/btf.h b/include/linux/btf.h index f6c43dd513fa..36bc09b8e890 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -327,6 +327,11 @@ static inline const struct btf_var_secinfo *btf_type_var_secinfo( return (const struct btf_var_secinfo *)(t + 1); } +static inline struct btf_param *btf_params(const struct btf_type *t) +{ + return (struct btf_param *)(t + 1); +} + #ifdef CONFIG_BPF_SYSCALL struct bpf_prog; -- cgit v1.2.3 From c78b8b20e34920231eda02fb40c7aca7d88be837 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 3 Feb 2022 15:12:40 -0800 Subject: net: don't include ndisc.h from ipv6.h Nothing in ipv6.h needs ndisc.h, drop it. Link: https://lore.kernel.org/r/20220203043457.2222388-1-kuba@kernel.org Acked-by: Jeremy Kerr Acked-by: Stefan Schmidt Link: https://lore.kernel.org/r/20220203231240.2297588-1-kuba@kernel.org Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- include/net/ipv6.h | 1 - include/net/ipv6_frag.h | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 082f30256f59..cda1f205f391 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #include diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h index 0a4779175a52..5052c66e22d2 100644 --- a/include/net/ipv6_frag.h +++ b/include/net/ipv6_frag.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _IPV6_FRAG_H #define _IPV6_FRAG_H +#include #include #include #include -- cgit v1.2.3 From be847673cfffce8bb6e9ed6ae186081280c58831 Mon Sep 17 00:00:00 2001 From: Justin Iurman Date: Wed, 2 Feb 2022 15:25:53 +0100 Subject: uapi: ioam: Insertion frequency Add the insertion frequency uapi for IOAM lwtunnels. Signed-off-by: Justin Iurman Signed-off-by: Jakub Kicinski --- include/uapi/linux/ioam6_iptunnel.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/ioam6_iptunnel.h b/include/uapi/linux/ioam6_iptunnel.h index 829ffdfcacca..38f6a8fdfd34 100644 --- a/include/uapi/linux/ioam6_iptunnel.h +++ b/include/uapi/linux/ioam6_iptunnel.h @@ -41,6 +41,15 @@ enum { /* IOAM Trace Header */ IOAM6_IPTUNNEL_TRACE, /* struct ioam6_trace_hdr */ + /* Insertion frequency: + * "k over n" packets (0 < k <= n) + * [0.0001% ... 100%] + */ +#define IOAM6_IPTUNNEL_FREQ_MIN 1 +#define IOAM6_IPTUNNEL_FREQ_MAX 1000000 + IOAM6_IPTUNNEL_FREQ_K, /* u32 */ + IOAM6_IPTUNNEL_FREQ_N, /* u32 */ + __IOAM6_IPTUNNEL_MAX, }; -- cgit v1.2.3 From 35d39fecbc242150af5587506e58ec1f8541fb68 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Thu, 3 Feb 2022 10:44:30 +0200 Subject: net/sched: Enable tc skb ext allocation on chain miss only when needed Currently tc skb extension is used to send miss info from tc to ovs datapath module, and driver to tc. For the tc to ovs miss it is currently always allocated even if it will not be used by ovs datapath (as it depends on a requested feature). Export the static key which is used by openvswitch module to guard this code path as well, so it will be skipped if ovs datapath doesn't need it. Enable this code path once ovs datapath needs it. Signed-off-by: Paul Blakey Reviewed-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 676cb8ea9e15..a3b57a93228a 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -1028,4 +1028,15 @@ struct tc_fifo_qopt_offload { }; }; +#ifdef CONFIG_NET_CLS_ACT +DECLARE_STATIC_KEY_FALSE(tc_skb_ext_tc); +void tc_skb_ext_tc_enable(void); +void tc_skb_ext_tc_disable(void); +#define tc_skb_ext_tc_enabled() static_branch_unlikely(&tc_skb_ext_tc) +#else /* CONFIG_NET_CLS_ACT */ +static inline void tc_skb_ext_tc_enable(void) { } +static inline void tc_skb_ext_tc_disable(void) { } +#define tc_skb_ext_tc_enabled() false +#endif + #endif -- cgit v1.2.3 From de5a1f3ce4c862150dc442530dba19e1d1dc6bc2 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 4 Feb 2022 12:28:37 +0100 Subject: net: gro: minor optimization for dev_gro_receive() While inspecting some perf report, I noticed that the compiler emits suboptimal code for the napi CB initialization, fetching and storing multiple times the memory for flags bitfield. This is with gcc 10.3.1, but I observed the same with older compiler versions. We can help the compiler to do a nicer work clearing several fields at once using an u32 alias. The generated code is quite smaller, with the same number of conditional. Before: objdump -t net/core/gro.o | grep " F .text" 0000000000000bb0 l F .text 0000000000000357 dev_gro_receive After: 0000000000000bb0 l F .text 000000000000033c dev_gro_receive v1 -> v2: - use struct_group (Alexander and Alex) RFC -> v1: - use __struct_group to delimit the zeroed area (Alexander) Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/net/gro.h | 52 ++++++++++++++++++++++++++++------------------------ 1 file changed, 28 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/net/gro.h b/include/net/gro.h index 8f75802d50fd..a765fedda5c4 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -29,46 +29,50 @@ struct napi_gro_cb { /* Number of segments aggregated. */ u16 count; - /* Start offset for remote checksum offload */ - u16 gro_remcsum_start; + /* Used in ipv6_gro_receive() and foo-over-udp */ + u16 proto; /* jiffies when first packet was created/queued */ unsigned long age; - /* Used in ipv6_gro_receive() and foo-over-udp */ - u16 proto; + /* portion of the cb set to zero at every gro iteration */ + struct_group(zeroed, + + /* Start offset for remote checksum offload */ + u16 gro_remcsum_start; - /* This is non-zero if the packet may be of the same flow. */ - u8 same_flow:1; + /* This is non-zero if the packet may be of the same flow. */ + u8 same_flow:1; - /* Used in tunnel GRO receive */ - u8 encap_mark:1; + /* Used in tunnel GRO receive */ + u8 encap_mark:1; - /* GRO checksum is valid */ - u8 csum_valid:1; + /* GRO checksum is valid */ + u8 csum_valid:1; - /* Number of checksums via CHECKSUM_UNNECESSARY */ - u8 csum_cnt:3; + /* Number of checksums via CHECKSUM_UNNECESSARY */ + u8 csum_cnt:3; - /* Free the skb? */ - u8 free:2; + /* Free the skb? */ + u8 free:2; #define NAPI_GRO_FREE 1 #define NAPI_GRO_FREE_STOLEN_HEAD 2 - /* Used in foo-over-udp, set in udp[46]_gro_receive */ - u8 is_ipv6:1; + /* Used in foo-over-udp, set in udp[46]_gro_receive */ + u8 is_ipv6:1; - /* Used in GRE, set in fou/gue_gro_receive */ - u8 is_fou:1; + /* Used in GRE, set in fou/gue_gro_receive */ + u8 is_fou:1; - /* Used to determine if flush_id can be ignored */ - u8 is_atomic:1; + /* Used to determine if flush_id can be ignored */ + u8 is_atomic:1; - /* Number of gro_receive callbacks this packet already went through */ - u8 recursion_counter:4; + /* Number of gro_receive callbacks this packet already went through */ + u8 recursion_counter:4; - /* GRO is done by frag_list pointer chaining. */ - u8 is_flist:1; + /* GRO is done by frag_list pointer chaining. */ + u8 is_flist:1; + ); /* used to support CHECKSUM_COMPLETE for tunneling protocols */ __wsum csum; -- cgit v1.2.3 From 0463e320421b313db320bbcf2928ebf49f556b67 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Fri, 4 Feb 2022 11:42:10 +0000 Subject: net: phylink: remove phylink_set_10g_modes() phylink_set_10g_modes() is no longer used with the conversion of drivers to phylink_generic_validate(), so we can remove it. Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- include/linux/phylink.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 713a0c928b7c..cca149f78d35 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -582,7 +582,6 @@ int phylink_speed_up(struct phylink *pl); #define phylink_test(bm, mode) __phylink_do_bit(test_bit, bm, mode) void phylink_set_port_modes(unsigned long *bits); -void phylink_set_10g_modes(unsigned long *mask); void phylink_helper_basex_speed(struct phylink_link_state *state); void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state, -- cgit v1.2.3 From 145c7a793838add5e004e7d49a67654dc7eba147 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 4 Feb 2022 12:15:45 -0800 Subject: ipv6: make mc_forwarding atomic This fixes minor data-races in ip6_mc_input() and batadv_mcast_mla_rtr_flags_softif_get_ipv6() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 1e0f8a31f3de..16870f86c74d 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -51,7 +51,7 @@ struct ipv6_devconf { __s32 use_optimistic; #endif #ifdef CONFIG_IPV6_MROUTE - __s32 mc_forwarding; + atomic_t mc_forwarding; #endif __s32 disable_ipv6; __s32 drop_unicast_in_l2_multicast; -- cgit v1.2.3 From e3ececfe668facd87d920b608349a32607060e66 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 4 Feb 2022 14:42:35 -0800 Subject: ref_tracker: implement use-after-free detection Whenever ref_tracker_dir_init() is called, mark the struct ref_tracker_dir as dead. Test the dead status from ref_tracker_alloc() and ref_tracker_free() This should detect buggy dev_put()/dev_hold() happening too late in netdevice dismantle process. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/ref_tracker.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/ref_tracker.h b/include/linux/ref_tracker.h index 60f3453be23e..a443abda937d 100644 --- a/include/linux/ref_tracker.h +++ b/include/linux/ref_tracker.h @@ -13,6 +13,7 @@ struct ref_tracker_dir { spinlock_t lock; unsigned int quarantine_avail; refcount_t untracked; + bool dead; struct list_head list; /* List of active trackers */ struct list_head quarantine; /* List of dead trackers */ #endif @@ -26,6 +27,7 @@ static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir, INIT_LIST_HEAD(&dir->quarantine); spin_lock_init(&dir->lock); dir->quarantine_avail = quarantine_count; + dir->dead = false; refcount_set(&dir->untracked, 1); stack_depot_init(); } -- cgit v1.2.3 From 8fd5522f44dcd7f05454ddc4f16d0f821b676cd9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 4 Feb 2022 14:42:36 -0800 Subject: ref_tracker: add a count of untracked references We are still chasing a netdev refcount imbalance, and we suspect we have one rogue dev_put() that is consuming a reference taken from a dev_hold_track() To detect this case, allow ref_tracker_alloc() and ref_tracker_free() to be called with a NULL @trackerp parameter, and use a dedicated refcount_t just for them. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/ref_tracker.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/ref_tracker.h b/include/linux/ref_tracker.h index a443abda937d..9ca353ab712b 100644 --- a/include/linux/ref_tracker.h +++ b/include/linux/ref_tracker.h @@ -13,6 +13,7 @@ struct ref_tracker_dir { spinlock_t lock; unsigned int quarantine_avail; refcount_t untracked; + refcount_t no_tracker; bool dead; struct list_head list; /* List of active trackers */ struct list_head quarantine; /* List of dead trackers */ @@ -29,6 +30,7 @@ static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir, dir->quarantine_avail = quarantine_count; dir->dead = false; refcount_set(&dir->untracked, 1); + refcount_set(&dir->no_tracker, 1); stack_depot_init(); } -- cgit v1.2.3 From 4c6c11ea0f7b00a1894803efe980dfaf3b074886 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 4 Feb 2022 14:42:37 -0800 Subject: net: refine dev_put()/dev_hold() debugging We are still chasing some syzbot reports where we think a rogue dev_put() is called with no corresponding prior dev_hold(). Unfortunately it eats a reference on dev->dev_refcnt taken by innocent dev_hold_track(), meaning that the refcount saturation splat comes too late to be useful. Make sure that 'not tracked' dev_put() and dev_hold() better use CONFIG_NET_DEV_REFCNT_TRACKER=y debug infrastructure: Prior patch in the series allowed ref_tracker_alloc() and ref_tracker_free() to be called with a NULL @trackerp parameter, and to use a separate refcount only to detect too many put() even in the following case: dev_hold_track(dev, tracker_1, GFP_ATOMIC); dev_hold(dev); dev_put(dev); dev_put(dev); // Should complain loudly here. dev_put_track(dev, tracker_1); // instead of here Add clarification about netdev_tracker_alloc() role. v2: I replaced the dev_put() in linkwatch_do_dev() with __dev_put() because callers called netdev_tracker_free(). Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 69 +++++++++++++++++++++++++++++++---------------- 1 file changed, 46 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e490b84732d1..3fb6fb67ed77 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3817,14 +3817,7 @@ extern unsigned int netdev_budget_usecs; /* Called by rtnetlink.c:rtnl_unlock() */ void netdev_run_todo(void); -/** - * dev_put - release reference to device - * @dev: network device - * - * Release reference to device to allow it to be freed. - * Try using dev_put_track() instead. - */ -static inline void dev_put(struct net_device *dev) +static inline void __dev_put(struct net_device *dev) { if (dev) { #ifdef CONFIG_PCPU_DEV_REFCNT @@ -3835,14 +3828,7 @@ static inline void dev_put(struct net_device *dev) } } -/** - * dev_hold - get reference to device - * @dev: network device - * - * Hold reference to device to keep it from being freed. - * Try using dev_hold_track() instead. - */ -static inline void dev_hold(struct net_device *dev) +static inline void __dev_hold(struct net_device *dev) { if (dev) { #ifdef CONFIG_PCPU_DEV_REFCNT @@ -3853,11 +3839,24 @@ static inline void dev_hold(struct net_device *dev) } } +static inline void __netdev_tracker_alloc(struct net_device *dev, + netdevice_tracker *tracker, + gfp_t gfp) +{ +#ifdef CONFIG_NET_DEV_REFCNT_TRACKER + ref_tracker_alloc(&dev->refcnt_tracker, tracker, gfp); +#endif +} + +/* netdev_tracker_alloc() can upgrade a prior untracked reference + * taken by dev_get_by_name()/dev_get_by_index() to a tracked one. + */ static inline void netdev_tracker_alloc(struct net_device *dev, netdevice_tracker *tracker, gfp_t gfp) { #ifdef CONFIG_NET_DEV_REFCNT_TRACKER - ref_tracker_alloc(&dev->refcnt_tracker, tracker, gfp); + refcount_dec(&dev->refcnt_tracker.no_tracker); + __netdev_tracker_alloc(dev, tracker, gfp); #endif } @@ -3873,8 +3872,8 @@ static inline void dev_hold_track(struct net_device *dev, netdevice_tracker *tracker, gfp_t gfp) { if (dev) { - dev_hold(dev); - netdev_tracker_alloc(dev, tracker, gfp); + __dev_hold(dev); + __netdev_tracker_alloc(dev, tracker, gfp); } } @@ -3883,10 +3882,34 @@ static inline void dev_put_track(struct net_device *dev, { if (dev) { netdev_tracker_free(dev, tracker); - dev_put(dev); + __dev_put(dev); } } +/** + * dev_hold - get reference to device + * @dev: network device + * + * Hold reference to device to keep it from being freed. + * Try using dev_hold_track() instead. + */ +static inline void dev_hold(struct net_device *dev) +{ + dev_hold_track(dev, NULL, GFP_ATOMIC); +} + +/** + * dev_put - release reference to device + * @dev: network device + * + * Release reference to device to allow it to be freed. + * Try using dev_put_track() instead. + */ +static inline void dev_put(struct net_device *dev) +{ + dev_put_track(dev, NULL); +} + static inline void dev_replace_track(struct net_device *odev, struct net_device *ndev, netdevice_tracker *tracker, @@ -3895,11 +3918,11 @@ static inline void dev_replace_track(struct net_device *odev, if (odev) netdev_tracker_free(odev, tracker); - dev_hold(ndev); - dev_put(odev); + __dev_hold(ndev); + __dev_put(odev); if (ndev) - netdev_tracker_alloc(ndev, tracker, gfp); + __netdev_tracker_alloc(ndev, tracker, gfp); } /* Carrier loss detection, dial on demand. The functions netif_carrier_on -- cgit v1.2.3 From 5a8fb33e530512ee67a11b30f3451a4f030f4b01 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 4 Feb 2022 20:56:14 -0800 Subject: skmsg: convert struct sk_msg_sg::copy to a bitmap We have plans for increasing MAX_SKB_FRAGS, but sk_msg_sg::copy is currently an unsigned long, limiting MAX_SKB_FRAGS to 30 on 32bit arches. Convert it to a bitmap, as Jakub suggested. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skmsg.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 18a717fe62eb..1ff68a88c58d 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -29,7 +29,7 @@ struct sk_msg_sg { u32 end; u32 size; u32 copybreak; - unsigned long copy; + DECLARE_BITMAP(copy, MAX_MSG_FRAGS + 2); /* The extra two elements: * 1) used for chaining the front and sections when the list becomes * partitioned (e.g. end < start). The crypto APIs require the @@ -38,7 +38,6 @@ struct sk_msg_sg { */ struct scatterlist data[MAX_MSG_FRAGS + 2]; }; -static_assert(BITS_PER_LONG >= NR_MSG_FRAG_IDS); /* UAPI in filter.c depends on struct sk_msg_sg being first element. */ struct sk_msg { @@ -234,7 +233,7 @@ static inline void sk_msg_compute_data_pointers(struct sk_msg *msg) { struct scatterlist *sge = sk_msg_elem(msg, msg->sg.start); - if (test_bit(msg->sg.start, &msg->sg.copy)) { + if (test_bit(msg->sg.start, msg->sg.copy)) { msg->data = NULL; msg->data_end = NULL; } else { @@ -253,7 +252,7 @@ static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page, sg_set_page(sge, page, len, offset); sg_unmark_end(sge); - __set_bit(msg->sg.end, &msg->sg.copy); + __set_bit(msg->sg.end, msg->sg.copy); msg->sg.size += len; sk_msg_iter_next(msg, end); } @@ -262,9 +261,9 @@ static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state) { do { if (copy_state) - __set_bit(i, &msg->sg.copy); + __set_bit(i, msg->sg.copy); else - __clear_bit(i, &msg->sg.copy); + __clear_bit(i, msg->sg.copy); sk_msg_iter_var_next(i); if (i == msg->sg.end) break; -- cgit v1.2.3 From 9c1be1935fb68b2413796cdc03d019b8cf35ab51 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 5 Feb 2022 09:01:25 -0800 Subject: net: initialize init_net earlier While testing a patch that will follow later ("net: add netns refcount tracker to struct nsproxy") I found that devtmpfs_init() was called before init_net was initialized. This is a bug, because devtmpfs_setup() calls ksys_unshare(CLONE_NEWNS); This has the effect of increasing init_net refcount, which will be later overwritten to 1, as part of setup_net(&init_net) We had too many prior patches [1] trying to work around the root cause. Really, make sure init_net is in BSS section, and that net_ns_init() is called earlier at boot time. Note that another patch ("vfs: add netns refcount tracker to struct fs_context") also will need net_ns_init() being called before vfs_caches_init() As a bonus, this patch saves around 4KB in .data section. [1] f8c46cb39079 ("netns: do not call pernet ops for not yet set up init_net namespace") b5082df8019a ("net: Initialise init_net.count to 1") 734b65417b24 ("net: Statically initialize init_net.dev_base_head") v2: fixed a build error reported by kernel build bots (CONFIG_NET=n) Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/net_namespace.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 5b61c462e534..374cc7b260fc 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -513,4 +513,10 @@ static inline void fnhe_genid_bump(struct net *net) atomic_inc(&net->fnhe_genid); } +#ifdef CONFIG_NET +void net_ns_init(void); +#else +static inline void net_ns_init(void) {} +#endif + #endif /* __NET_NET_NAMESPACE_H */ -- cgit v1.2.3 From a3574119826d9a4ef807fb973cf5150c3b90da43 Mon Sep 17 00:00:00 2001 From: Simon Ser Date: Thu, 3 Feb 2022 13:38:06 +0000 Subject: drm: document struct drm_mode_fb_cmd2 Follow-up for the DRM_IOCTL_MODE_GETFB2 docs. v2: (Daniel Stone) - Replace fourcc.org with drm_fourcc.h because this is the authoritative source and the website may have mismatches. - Drop assumption that offsets will generally be 0. - Mention that unused entries must be zero'ed out. v3: (Pekka) - Mention that a handle can be re-used - Add unit for pitches/offsets Signed-off-by: Simon Ser Reviewed-by: Daniel Vetter Acked-by: Pekka Paalanen Cc: Daniel Stone Reviewed-by: Daniel Stone Link: https://patchwork.freedesktop.org/patch/msgid/20220203133753.261507-1-contact@emersion.fr --- include/uapi/drm/drm_mode.h | 88 ++++++++++++++++++++++++++++++--------------- 1 file changed, 60 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h index e1e351682872..0a0d56a6158e 100644 --- a/include/uapi/drm/drm_mode.h +++ b/include/uapi/drm/drm_mode.h @@ -663,41 +663,73 @@ struct drm_mode_fb_cmd { #define DRM_MODE_FB_INTERLACED (1<<0) /* for interlaced framebuffers */ #define DRM_MODE_FB_MODIFIERS (1<<1) /* enables ->modifer[] */ +/** + * struct drm_mode_fb_cmd2 - Frame-buffer metadata. + * + * This struct holds frame-buffer metadata. There are two ways to use it: + * + * - User-space can fill this struct and perform a &DRM_IOCTL_MODE_ADDFB2 + * ioctl to register a new frame-buffer. The new frame-buffer object ID will + * be set by the kernel in @fb_id. + * - User-space can set @fb_id and perform a &DRM_IOCTL_MODE_GETFB2 ioctl to + * fetch metadata about an existing frame-buffer. + * + * In case of planar formats, this struct allows up to 4 buffer objects with + * offsets and pitches per plane. The pitch and offset order is dictated by the + * format FourCC as defined by ``drm_fourcc.h``, e.g. NV12 is described as: + * + * YUV 4:2:0 image with a plane of 8 bit Y samples followed by an + * interleaved U/V plane containing 8 bit 2x2 subsampled colour difference + * samples. + * + * So it would consist of a Y plane at ``offsets[0]`` and a UV plane at + * ``offsets[1]``. + * + * To accommodate tiled, compressed, etc formats, a modifier can be specified. + * For more information see the "Format Modifiers" section. Note that even + * though it looks like we have a modifier per-plane, we in fact do not. The + * modifier for each plane must be identical. Thus all combinations of + * different data layouts for multi-plane formats must be enumerated as + * separate modifiers. + * + * All of the entries in @handles, @pitches, @offsets and @modifier must be + * zero when unused. Warning, for @offsets and @modifier zero can't be used to + * figure out whether the entry is used or not since it's a valid value (a zero + * offset is common, and a zero modifier is &DRM_FORMAT_MOD_LINEAR). + */ struct drm_mode_fb_cmd2 { + /** @fb_id: Object ID of the frame-buffer. */ __u32 fb_id; + /** @width: Width of the frame-buffer. */ __u32 width; + /** @height: Height of the frame-buffer. */ __u32 height; - __u32 pixel_format; /* fourcc code from drm_fourcc.h */ - __u32 flags; /* see above flags */ + /** + * @pixel_format: FourCC format code, see ``DRM_FORMAT_*`` constants in + * ``drm_fourcc.h``. + */ + __u32 pixel_format; + /** + * @flags: Frame-buffer flags (see &DRM_MODE_FB_INTERLACED and + * &DRM_MODE_FB_MODIFIERS). + */ + __u32 flags; - /* - * In case of planar formats, this ioctl allows up to 4 - * buffer objects with offsets and pitches per plane. - * The pitch and offset order is dictated by the fourcc, - * e.g. NV12 (https://fourcc.org/yuv.php#NV12) is described as: - * - * YUV 4:2:0 image with a plane of 8 bit Y samples - * followed by an interleaved U/V plane containing - * 8 bit 2x2 subsampled colour difference samples. - * - * So it would consist of Y as offsets[0] and UV as - * offsets[1]. Note that offsets[0] will generally - * be 0 (but this is not required). - * - * To accommodate tiled, compressed, etc formats, a - * modifier can be specified. The default value of zero - * indicates "native" format as specified by the fourcc. - * Vendor specific modifier token. Note that even though - * it looks like we have a modifier per-plane, we in fact - * do not. The modifier for each plane must be identical. - * Thus all combinations of different data layouts for - * multi plane formats must be enumerated as separate - * modifiers. + /** + * @handles: GEM buffer handle, one per plane. Set to 0 if the plane is + * unused. The same handle can be used for multiple planes. */ __u32 handles[4]; - __u32 pitches[4]; /* pitch for each plane */ - __u32 offsets[4]; /* offset of each plane */ - __u64 modifier[4]; /* ie, tiling, compress */ + /** @pitches: Pitch (aka. stride) in bytes, one per plane. */ + __u32 pitches[4]; + /** @offsets: Offset into the buffer in bytes, one per plane. */ + __u32 offsets[4]; + /** + * @modifier: Format modifier, one per plane. See ``DRM_FORMAT_MOD_*`` + * constants in ``drm_fourcc.h``. All planes must use the same + * modifier. Ignored unless &DRM_MODE_FB_MODIFIERS is set in @flags. + */ + __u64 modifier[4]; }; #define DRM_MODE_FB_DIRTY_ANNOTATE_COPY 0x01 -- cgit v1.2.3 From 88590b369354092183bcba04e2368010c462557f Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sat, 5 Feb 2022 15:47:33 +0800 Subject: net: skb_drop_reason: add document for drop reasons Add document for following existing drop reasons: SKB_DROP_REASON_NOT_SPECIFIED SKB_DROP_REASON_NO_SOCKET SKB_DROP_REASON_PKT_TOO_SMALL SKB_DROP_REASON_TCP_CSUM SKB_DROP_REASON_SOCKET_FILTER SKB_DROP_REASON_UDP_CSUM Signed-off-by: Menglong Dong Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a27bcc4f7e9a..f04e3a1f4455 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -314,12 +314,12 @@ struct sk_buff; * used to translate the reason to string. */ enum skb_drop_reason { - SKB_DROP_REASON_NOT_SPECIFIED, - SKB_DROP_REASON_NO_SOCKET, - SKB_DROP_REASON_PKT_TOO_SMALL, - SKB_DROP_REASON_TCP_CSUM, - SKB_DROP_REASON_SOCKET_FILTER, - SKB_DROP_REASON_UDP_CSUM, + SKB_DROP_REASON_NOT_SPECIFIED, /* drop reason is not specified */ + SKB_DROP_REASON_NO_SOCKET, /* socket not found */ + SKB_DROP_REASON_PKT_TOO_SMALL, /* packet size is too small */ + SKB_DROP_REASON_TCP_CSUM, /* TCP checksum error */ + SKB_DROP_REASON_SOCKET_FILTER, /* dropped by socket filter */ + SKB_DROP_REASON_UDP_CSUM, /* UDP checksum error */ SKB_DROP_REASON_MAX, }; -- cgit v1.2.3 From 2df3041ba3be950376e8c25a8f6da22f7fcc765c Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sat, 5 Feb 2022 15:47:34 +0800 Subject: net: netfilter: use kfree_drop_reason() for NF_DROP Replace kfree_skb() with kfree_skb_reason() in nf_hook_slow() when skb is dropped by reason of NF_DROP. Following new drop reasons are introduced: SKB_DROP_REASON_NETFILTER_DROP Signed-off-by: Menglong Dong Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + include/trace/events/skb.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f04e3a1f4455..9060159b4375 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -320,6 +320,7 @@ enum skb_drop_reason { SKB_DROP_REASON_TCP_CSUM, /* TCP checksum error */ SKB_DROP_REASON_SOCKET_FILTER, /* dropped by socket filter */ SKB_DROP_REASON_UDP_CSUM, /* UDP checksum error */ + SKB_DROP_REASON_NETFILTER_DROP, /* dropped by netfilter */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index a8a64b97504d..3d89f7b09a43 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -16,6 +16,7 @@ EM(SKB_DROP_REASON_TCP_CSUM, TCP_CSUM) \ EM(SKB_DROP_REASON_SOCKET_FILTER, SOCKET_FILTER) \ EM(SKB_DROP_REASON_UDP_CSUM, UDP_CSUM) \ + EM(SKB_DROP_REASON_NETFILTER_DROP, NETFILTER_DROP) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From 33cba42985c8144eef78d618fc1e51aaa074b169 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sat, 5 Feb 2022 15:47:35 +0800 Subject: net: ipv4: use kfree_skb_reason() in ip_rcv_core() Replace kfree_skb() with kfree_skb_reason() in ip_rcv_core(). Three new drop reasons are introduced: SKB_DROP_REASON_OTHERHOST SKB_DROP_REASON_IP_CSUM SKB_DROP_REASON_IP_INHDR Signed-off-by: Menglong Dong Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 9 +++++++++ include/trace/events/skb.h | 3 +++ 2 files changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9060159b4375..8e82130b3c52 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -321,6 +321,15 @@ enum skb_drop_reason { SKB_DROP_REASON_SOCKET_FILTER, /* dropped by socket filter */ SKB_DROP_REASON_UDP_CSUM, /* UDP checksum error */ SKB_DROP_REASON_NETFILTER_DROP, /* dropped by netfilter */ + SKB_DROP_REASON_OTHERHOST, /* packet don't belong to current + * host (interface is in promisc + * mode) + */ + SKB_DROP_REASON_IP_CSUM, /* IP checksum error */ + SKB_DROP_REASON_IP_INHDR, /* there is something wrong with + * IP header (see + * IPSTATS_MIB_INHDRERRORS) + */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 3d89f7b09a43..f2b1778485f0 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -17,6 +17,9 @@ EM(SKB_DROP_REASON_SOCKET_FILTER, SOCKET_FILTER) \ EM(SKB_DROP_REASON_UDP_CSUM, UDP_CSUM) \ EM(SKB_DROP_REASON_NETFILTER_DROP, NETFILTER_DROP) \ + EM(SKB_DROP_REASON_OTHERHOST, OTHERHOST) \ + EM(SKB_DROP_REASON_IP_CSUM, IP_CSUM) \ + EM(SKB_DROP_REASON_IP_INHDR, IP_INHDR) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From c1f166d1f7eef212096a98b22f5acf92f9af353d Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sat, 5 Feb 2022 15:47:36 +0800 Subject: net: ipv4: use kfree_skb_reason() in ip_rcv_finish_core() Replace kfree_skb() with kfree_skb_reason() in ip_rcv_finish_core(), following drop reasons are introduced: SKB_DROP_REASON_IP_RPFILTER SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST Signed-off-by: Menglong Dong Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 9 +++++++++ include/trace/events/skb.h | 3 +++ 2 files changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 8e82130b3c52..4baba45f223d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -330,6 +330,15 @@ enum skb_drop_reason { * IP header (see * IPSTATS_MIB_INHDRERRORS) */ + SKB_DROP_REASON_IP_RPFILTER, /* IP rpfilter validate failed. + * see the document for rp_filter + * in ip-sysctl.rst for more + * information + */ + SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST, /* destination address of L2 + * is multicast, but L3 is + * unicast. + */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index f2b1778485f0..485a1d3034a4 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -20,6 +20,9 @@ EM(SKB_DROP_REASON_OTHERHOST, OTHERHOST) \ EM(SKB_DROP_REASON_IP_CSUM, IP_CSUM) \ EM(SKB_DROP_REASON_IP_INHDR, IP_INHDR) \ + EM(SKB_DROP_REASON_IP_RPFILTER, IP_RPFILTER) \ + EM(SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST, \ + UNICAST_IN_L2_MULTICAST) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From 10580c4791902571777603cb980414892dd5f149 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sat, 5 Feb 2022 15:47:37 +0800 Subject: net: ipv4: use kfree_skb_reason() in ip_protocol_deliver_rcu() Replace kfree_skb() with kfree_skb_reason() in ip_protocol_deliver_rcu(). Following new drop reasons are introduced: SKB_DROP_REASON_XFRM_POLICY SKB_DROP_REASON_IP_NOPROTO Signed-off-by: Menglong Dong Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 ++ include/trace/events/skb.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4baba45f223d..2a64afa97910 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -339,6 +339,8 @@ enum skb_drop_reason { * is multicast, but L3 is * unicast. */ + SKB_DROP_REASON_XFRM_POLICY, /* xfrm policy check failed */ + SKB_DROP_REASON_IP_NOPROTO, /* no support for IP protocol */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 485a1d3034a4..985e481c092d 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -23,6 +23,8 @@ EM(SKB_DROP_REASON_IP_RPFILTER, IP_RPFILTER) \ EM(SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST, \ UNICAST_IN_L2_MULTICAST) \ + EM(SKB_DROP_REASON_XFRM_POLICY, XFRM_POLICY) \ + EM(SKB_DROP_REASON_IP_NOPROTO, IP_NOPROTO) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From 08d4c0370c400fa6ef2194f9ee2e8dccc4a7ab39 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sat, 5 Feb 2022 15:47:39 +0800 Subject: net: udp: use kfree_skb_reason() in __udp_queue_rcv_skb() Replace kfree_skb() with kfree_skb_reason() in __udp_queue_rcv_skb(). Following new drop reasons are introduced: SKB_DROP_REASON_SOCKET_RCVBUFF SKB_DROP_REASON_PROTO_MEM Signed-off-by: Menglong Dong Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 +++++ include/trace/events/skb.h | 2 ++ 2 files changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2a64afa97910..a5adbf6b51e8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -341,6 +341,11 @@ enum skb_drop_reason { */ SKB_DROP_REASON_XFRM_POLICY, /* xfrm policy check failed */ SKB_DROP_REASON_IP_NOPROTO, /* no support for IP protocol */ + SKB_DROP_REASON_SOCKET_RCVBUFF, /* socket receive buff is full */ + SKB_DROP_REASON_PROTO_MEM, /* proto memory limition, such as + * udp packet drop out of + * udp_memory_allocated. + */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 985e481c092d..cfcfd26399f7 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -25,6 +25,8 @@ UNICAST_IN_L2_MULTICAST) \ EM(SKB_DROP_REASON_XFRM_POLICY, XFRM_POLICY) \ EM(SKB_DROP_REASON_IP_NOPROTO, IP_NOPROTO) \ + EM(SKB_DROP_REASON_SOCKET_RCVBUFF, SOCKET_RCVBUFF) \ + EM(SKB_DROP_REASON_PROTO_MEM, PROTO_MEM) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From ad5e35f58384179bbd3cdb349904e150f364c4f3 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 28 Jan 2022 12:34:14 +0100 Subject: mtd: Replace the expert mode symbols with a single helper Reduce the number of exported symbols by replacing: - mtd_expert_analysis_warning (the error string) - mtd_expert_analysis_mode (the boolean) with a single helper: - mtd_check_expert_analysis_mode Calling this helper will both check/return the content of the internal boolean -which is not exported anymore- and as well conditionally WARN_ONCE() the user, like it was done before. While on this function, make the error string local to the helper and set it const. Only export this helper when CONFIG_DEBUG_FS is defined to limit the growth of the Linux kernel size only for a debug feature on production kernels. Mechanically update all the consumers. Suggested-by: Geert Uytterhoeven Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20220128113414.1121924-1-miquel.raynal@bootlin.com --- include/linux/mtd/mtd.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 1ffa933121f6..1b3fc8c71ab3 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -711,7 +711,11 @@ static inline int mtd_is_bitflip_or_eccerr(int err) { unsigned mtd_mmap_capabilities(struct mtd_info *mtd); -extern char *mtd_expert_analysis_warning; -extern bool mtd_expert_analysis_mode; +#ifdef CONFIG_DEBUG_FS +bool mtd_check_expert_analysis_mode(void); +#else +static inline bool mtd_check_expert_analysis_mode(void) { return false; } +#endif + #endif /* __MTD_MTD_H__ */ -- cgit v1.2.3 From 74703b13f9d2ef286ef588f29295a2fd30b5f295 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 1 Nov 2021 19:58:42 +0000 Subject: dt-bindings: apple,aic: Add CPU PMU per-cpu pseudo-interrupts Advertise the two pseudo-interrupts that tied to the two PMU flavours present in the Apple M1 SoC. We choose the expose two different pseudo-interrupts to the OS as the e-core PMU is obviously different from the p-core one, effectively presenting two different devices. Acked-by: Rob Herring Reviewed-by: Hector Martin Signed-off-by: Marc Zyngier --- include/dt-bindings/interrupt-controller/apple-aic.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/interrupt-controller/apple-aic.h b/include/dt-bindings/interrupt-controller/apple-aic.h index 604f2bb30ac0..bf3aac0e5491 100644 --- a/include/dt-bindings/interrupt-controller/apple-aic.h +++ b/include/dt-bindings/interrupt-controller/apple-aic.h @@ -11,5 +11,7 @@ #define AIC_TMR_HV_VIRT 1 #define AIC_TMR_GUEST_PHYS 2 #define AIC_TMR_GUEST_VIRT 3 +#define AIC_CPU_PMU_E 4 +#define AIC_CPU_PMU_P 5 #endif -- cgit v1.2.3 From ea4692c75e1c63926e4fb0728f5775ef0d733888 Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Wed, 26 Jan 2022 01:39:41 -0800 Subject: lib/string_helpers: Consolidate string helpers implementation There are a few implementations of string helpers in the tree like yesno() that just returns "yes" or "no" depending on a boolean argument. Those are helpful to output strings to the user or log. In order to consolidate them, prefix all of them str_ prefix to make it clear what they are about and avoid symbol clashes. Taking the commoon `val ? "yes" : "no"` implementation, quite a few users of open coded yesno() could later be converted to the new function: $ git grep '?\s*"yes"\s*' | wc -l 286 $ git grep '?\s*"no"\s*' | wc -l 20 The inlined function should keep the const strings local to each compilation unit, the same way it's now, thus not changing the current behavior. Signed-off-by: Lucas De Marchi Reviewed-by: Andy Shevchenko Acked-by: Jani Nikula Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220126093951.1470898-2-lucas.demarchi@intel.com --- include/linux/string_helpers.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index 7a22921c9db7..4d72258d42fd 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -106,4 +106,24 @@ void kfree_strarray(char **array, size_t n); char **devm_kasprintf_strarray(struct device *dev, const char *prefix, size_t n); +static inline const char *str_yes_no(bool v) +{ + return v ? "yes" : "no"; +} + +static inline const char *str_on_off(bool v) +{ + return v ? "on" : "off"; +} + +static inline const char *str_enable_disable(bool v) +{ + return v ? "enable" : "disable"; +} + +static inline const char *str_enabled_disabled(bool v) +{ + return v ? "enabled" : "disabled"; +} + #endif -- cgit v1.2.3 From 3698807094ecae945436921325f5c309d1123f11 Mon Sep 17 00:00:00 2001 From: Rajneesh Bhardwaj Date: Tue, 24 Aug 2021 16:13:41 -0400 Subject: drm/amdkfd: CRIU Introduce Checkpoint-Restore APIs Checkpoint-Restore in userspace (CRIU) is a powerful tool that can snapshot a running process and later restore it on same or a remote machine but expects the processes that have a device file (e.g. GPU) associated with them, provide necessary driver support to assist CRIU and its extensible plugin interface. Thus, In order to support the Checkpoint-Restore of any ROCm process, the AMD Radeon Open Compute Kernel driver, needs to provide a set of new APIs that provide necessary VRAM metadata and its contents to a userspace component (CRIU plugin) that can store it in form of image files. This introduces some new ioctls which will be used to checkpoint-Restore any KFD bound user process. KFD only allows ioctl calls from the same process that opened the KFD file descriptor. Since these ioctls are expected to be called from a KFD criu plugin which has elevated ptrace attached privileges and CAP_CHECKPOINT_RESTORE capabilities attached with the file descriptors so modify KFD to allow such calls. (API redesigned by David Yat Sin) Suggested-by: Felix Kuehling Reviewed-by: Felix Kuehling Signed-off-by: David Yat Sin Signed-off-by: Rajneesh Bhardwaj Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 81 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 80 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index af96af174dc4..49429a6c42fc 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -468,6 +468,82 @@ struct kfd_ioctl_smi_events_args { __u32 anon_fd; /* from KFD */ }; +/************************************************************************************************** + * CRIU IOCTLs (Checkpoint Restore In Userspace) + * + * When checkpointing a process, the userspace application will perform: + * 1. PROCESS_INFO op to determine current process information. This pauses execution and evicts + * all the queues. + * 2. CHECKPOINT op to checkpoint process contents (BOs, queues, events, svm-ranges) + * 3. UNPAUSE op to un-evict all the queues + * + * When restoring a process, the CRIU userspace application will perform: + * + * 1. RESTORE op to restore process contents + * 2. RESUME op to start the process + * + * Note: Queues are forced into an evicted state after a successful PROCESS_INFO. User + * application needs to perform an UNPAUSE operation after calling PROCESS_INFO. + */ + +enum kfd_criu_op { + KFD_CRIU_OP_PROCESS_INFO, + KFD_CRIU_OP_CHECKPOINT, + KFD_CRIU_OP_UNPAUSE, + KFD_CRIU_OP_RESTORE, + KFD_CRIU_OP_RESUME, +}; + +/** + * kfd_ioctl_criu_args - Arguments perform CRIU operation + * @devices: [in/out] User pointer to memory location for devices information. + * This is an array of type kfd_criu_device_bucket. + * @bos: [in/out] User pointer to memory location for BOs information + * This is an array of type kfd_criu_bo_bucket. + * @priv_data: [in/out] User pointer to memory location for private data + * @priv_data_size: [in/out] Size of priv_data in bytes + * @num_devices: [in/out] Number of GPUs used by process. Size of @devices array. + * @num_bos [in/out] Number of BOs used by process. Size of @bos array. + * @num_objects: [in/out] Number of objects used by process. Objects are opaque to + * user application. + * @pid: [in/out] PID of the process being checkpointed + * @op [in] Type of operation (kfd_criu_op) + * + * Return: 0 on success, -errno on failure + */ +struct kfd_ioctl_criu_args { + __u64 devices; /* Used during ops: CHECKPOINT, RESTORE */ + __u64 bos; /* Used during ops: CHECKPOINT, RESTORE */ + __u64 priv_data; /* Used during ops: CHECKPOINT, RESTORE */ + __u64 priv_data_size; /* Used during ops: PROCESS_INFO, RESTORE */ + __u32 num_devices; /* Used during ops: PROCESS_INFO, RESTORE */ + __u32 num_bos; /* Used during ops: PROCESS_INFO, RESTORE */ + __u32 num_objects; /* Used during ops: PROCESS_INFO, RESTORE */ + __u32 pid; /* Used during ops: PROCESS_INFO, RESUME */ + __u32 op; +}; + +struct kfd_criu_device_bucket { + __u32 user_gpu_id; + __u32 actual_gpu_id; + __u32 drm_fd; + __u32 pad; +}; + +struct kfd_criu_bo_bucket { + __u64 addr; + __u64 size; + __u64 offset; + __u64 restored_offset; /* During restore, updated offset for BO */ + __u32 gpu_id; /* This is the user_gpu_id */ + __u32 alloc_flags; + __u32 dmabuf_fd; + __u32 pad; +}; + +/* CRIU IOCTLs - END */ +/**************************************************************************************************/ + /* Register offset inside the remapped mmio page */ enum kfd_mmio_remap { @@ -742,7 +818,10 @@ struct kfd_ioctl_set_xnack_mode_args { #define AMDKFD_IOC_SET_XNACK_MODE \ AMDKFD_IOWR(0x21, struct kfd_ioctl_set_xnack_mode_args) +#define AMDKFD_IOC_CRIU_OP \ + AMDKFD_IOWR(0x22, struct kfd_ioctl_criu_args) + #define AMDKFD_COMMAND_START 0x01 -#define AMDKFD_COMMAND_END 0x22 +#define AMDKFD_COMMAND_END 0x23 #endif -- cgit v1.2.3 From 692996f2bef7aa1737e07554255ba0d9a73fb750 Mon Sep 17 00:00:00 2001 From: Rajneesh Bhardwaj Date: Tue, 18 Jan 2022 01:47:58 -0500 Subject: drm/amdkfd: Bump up KFD API version for CRIU - Change KFD minor version to 7 for CRIU Proposed userspace changes: https://github.com/RadeonOpenCompute/criu Reviewed-by: Felix Kuehling Signed-off-by: Rajneesh Bhardwaj Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 49429a6c42fc..e6a56c146920 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -32,9 +32,10 @@ * - 1.4 - Indicate new SRAM EDC bit in device properties * - 1.5 - Add SVM API * - 1.6 - Query clear flags in SVM get_attr API + * - 1.7 - Checkpoint Restore (CRIU) API */ #define KFD_IOCTL_MAJOR_VERSION 1 -#define KFD_IOCTL_MINOR_VERSION 6 +#define KFD_IOCTL_MINOR_VERSION 7 struct kfd_ioctl_get_version_args { __u32 major_version; /* from KFD */ -- cgit v1.2.3 From 7938f4218168ae9fc4bdddb15976f9ebbae41999 Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Fri, 4 Feb 2022 09:05:41 -0800 Subject: dma-buf-map: Rename to iosys-map MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rename struct dma_buf_map to struct iosys_map and corresponding APIs. Over time dma-buf-map grew up to more functionality than the one used by dma-buf: in fact it's just a shim layer to abstract system memory, that can be accessed via regular load and store, from IO memory that needs to be acessed via arch helpers. The idea is to extend this API so it can fulfill other needs, internal to a single driver. Example: in the i915 driver it's desired to share the implementation for integrated graphics, which uses mostly system memory, with discrete graphics, which may need to access IO memory. The conversion was mostly done with the following semantic patch: @r1@ @@ - struct dma_buf_map + struct iosys_map @r2@ @@ ( - DMA_BUF_MAP_INIT_VADDR + IOSYS_MAP_INIT_VADDR | - dma_buf_map_set_vaddr + iosys_map_set_vaddr | - dma_buf_map_set_vaddr_iomem + iosys_map_set_vaddr_iomem | - dma_buf_map_is_equal + iosys_map_is_equal | - dma_buf_map_is_null + iosys_map_is_null | - dma_buf_map_is_set + iosys_map_is_set | - dma_buf_map_clear + iosys_map_clear | - dma_buf_map_memcpy_to + iosys_map_memcpy_to | - dma_buf_map_incr + iosys_map_incr ) @@ @@ - #include + #include Then some files had their includes adjusted and some comments were update to remove mentions to dma-buf-map. Since this is not specific to dma-buf anymore, move the documentation to the "Bus-Independent Device Accesses" section. v2: - Squash patches v3: - Fix wrong removal of dma-buf.h from MAINTAINERS - Move documentation from dma-buf.rst to device-io.rst v4: - Change documentation title and level Signed-off-by: Lucas De Marchi Acked-by: Christian König Acked-by: Sumit Semwal Acked-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20220204170541.829227-1-lucas.demarchi@intel.com --- include/drm/drm_cache.h | 6 +- include/drm/drm_client.h | 7 +- include/drm/drm_gem.h | 6 +- include/drm/drm_gem_atomic_helper.h | 6 +- include/drm/drm_gem_cma_helper.h | 6 +- include/drm/drm_gem_framebuffer_helper.h | 8 +- include/drm/drm_gem_shmem_helper.h | 12 +- include/drm/drm_gem_ttm_helper.h | 6 +- include/drm/drm_gem_vram_helper.h | 9 +- include/drm/drm_prime.h | 6 +- include/drm/ttm/ttm_bo_api.h | 10 +- include/drm/ttm/ttm_kmap_iter.h | 10 +- include/drm/ttm/ttm_resource.h | 6 +- include/linux/dma-buf-map.h | 266 ------------------------------- include/linux/dma-buf.h | 12 +- include/linux/iosys-map.h | 257 +++++++++++++++++++++++++++++ 16 files changed, 316 insertions(+), 317 deletions(-) delete mode 100644 include/linux/dma-buf-map.h create mode 100644 include/linux/iosys-map.h (limited to 'include') diff --git a/include/drm/drm_cache.h b/include/drm/drm_cache.h index cc9de1632dd3..22deb216b59c 100644 --- a/include/drm/drm_cache.h +++ b/include/drm/drm_cache.h @@ -35,7 +35,7 @@ #include -struct dma_buf_map; +struct iosys_map; void drm_clflush_pages(struct page *pages[], unsigned long num_pages); void drm_clflush_sg(struct sg_table *st); @@ -74,7 +74,7 @@ static inline bool drm_arch_can_wc_memory(void) void drm_memcpy_init_early(void); -void drm_memcpy_from_wc(struct dma_buf_map *dst, - const struct dma_buf_map *src, +void drm_memcpy_from_wc(struct iosys_map *dst, + const struct iosys_map *src, unsigned long len); #endif diff --git a/include/drm/drm_client.h b/include/drm/drm_client.h index f07f2fb02e75..4fc8018eddda 100644 --- a/include/drm/drm_client.h +++ b/include/drm/drm_client.h @@ -3,7 +3,7 @@ #ifndef _DRM_CLIENT_H_ #define _DRM_CLIENT_H_ -#include +#include #include #include #include @@ -144,7 +144,7 @@ struct drm_client_buffer { /** * @map: Virtual address for the buffer */ - struct dma_buf_map map; + struct iosys_map map; /** * @fb: DRM framebuffer @@ -156,7 +156,8 @@ struct drm_client_buffer * drm_client_framebuffer_create(struct drm_client_dev *client, u32 width, u32 height, u32 format); void drm_client_framebuffer_delete(struct drm_client_buffer *buffer); int drm_client_framebuffer_flush(struct drm_client_buffer *buffer, struct drm_rect *rect); -int drm_client_buffer_vmap(struct drm_client_buffer *buffer, struct dma_buf_map *map); +int drm_client_buffer_vmap(struct drm_client_buffer *buffer, + struct iosys_map *map); void drm_client_buffer_vunmap(struct drm_client_buffer *buffer); int drm_client_modeset_create(struct drm_client_dev *client); diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h index 35e7f44c2a75..e2941cee14b6 100644 --- a/include/drm/drm_gem.h +++ b/include/drm/drm_gem.h @@ -39,7 +39,7 @@ #include -struct dma_buf_map; +struct iosys_map; struct drm_gem_object; /** @@ -139,7 +139,7 @@ struct drm_gem_object_funcs { * * This callback is optional. */ - int (*vmap)(struct drm_gem_object *obj, struct dma_buf_map *map); + int (*vmap)(struct drm_gem_object *obj, struct iosys_map *map); /** * @vunmap: @@ -149,7 +149,7 @@ struct drm_gem_object_funcs { * * This callback is optional. */ - void (*vunmap)(struct drm_gem_object *obj, struct dma_buf_map *map); + void (*vunmap)(struct drm_gem_object *obj, struct iosys_map *map); /** * @mmap: diff --git a/include/drm/drm_gem_atomic_helper.h b/include/drm/drm_gem_atomic_helper.h index 0b1e2dd2ac3f..6e3319e9001a 100644 --- a/include/drm/drm_gem_atomic_helper.h +++ b/include/drm/drm_gem_atomic_helper.h @@ -3,7 +3,7 @@ #ifndef __DRM_GEM_ATOMIC_HELPER_H__ #define __DRM_GEM_ATOMIC_HELPER_H__ -#include +#include #include #include @@ -59,7 +59,7 @@ struct drm_shadow_plane_state { * The memory mappings stored in map should be established in the plane's * prepare_fb callback and removed in the cleanup_fb callback. */ - struct dma_buf_map map[DRM_FORMAT_MAX_PLANES]; + struct iosys_map map[DRM_FORMAT_MAX_PLANES]; /** * @data: Address of each framebuffer BO's data @@ -67,7 +67,7 @@ struct drm_shadow_plane_state { * The address of the data stored in each mapping. This is different * for framebuffers with non-zero offset fields. */ - struct dma_buf_map data[DRM_FORMAT_MAX_PLANES]; + struct iosys_map data[DRM_FORMAT_MAX_PLANES]; }; /** diff --git a/include/drm/drm_gem_cma_helper.h b/include/drm/drm_gem_cma_helper.h index adb507a9dbf0..fbda4ce5d5fb 100644 --- a/include/drm/drm_gem_cma_helper.h +++ b/include/drm/drm_gem_cma_helper.h @@ -38,7 +38,8 @@ void drm_gem_cma_free(struct drm_gem_cma_object *cma_obj); void drm_gem_cma_print_info(const struct drm_gem_cma_object *cma_obj, struct drm_printer *p, unsigned int indent); struct sg_table *drm_gem_cma_get_sg_table(struct drm_gem_cma_object *cma_obj); -int drm_gem_cma_vmap(struct drm_gem_cma_object *cma_obj, struct dma_buf_map *map); +int drm_gem_cma_vmap(struct drm_gem_cma_object *cma_obj, + struct iosys_map *map); int drm_gem_cma_mmap(struct drm_gem_cma_object *cma_obj, struct vm_area_struct *vma); extern const struct vm_operations_struct drm_gem_cma_vm_ops; @@ -106,7 +107,8 @@ static inline struct sg_table *drm_gem_cma_object_get_sg_table(struct drm_gem_ob * Returns: * 0 on success or a negative error code on failure. */ -static inline int drm_gem_cma_object_vmap(struct drm_gem_object *obj, struct dma_buf_map *map) +static inline int drm_gem_cma_object_vmap(struct drm_gem_object *obj, + struct iosys_map *map) { struct drm_gem_cma_object *cma_obj = to_drm_gem_cma_obj(obj); diff --git a/include/drm/drm_gem_framebuffer_helper.h b/include/drm/drm_gem_framebuffer_helper.h index 905727719ead..1091e4fa08cb 100644 --- a/include/drm/drm_gem_framebuffer_helper.h +++ b/include/drm/drm_gem_framebuffer_helper.h @@ -2,7 +2,7 @@ #define __DRM_GEM_FB_HELPER_H__ #include -#include +#include #include @@ -40,10 +40,10 @@ drm_gem_fb_create_with_dirty(struct drm_device *dev, struct drm_file *file, const struct drm_mode_fb_cmd2 *mode_cmd); int drm_gem_fb_vmap(struct drm_framebuffer *fb, - struct dma_buf_map map[static DRM_FORMAT_MAX_PLANES], - struct dma_buf_map data[DRM_FORMAT_MAX_PLANES]); + struct iosys_map map[static DRM_FORMAT_MAX_PLANES], + struct iosys_map data[DRM_FORMAT_MAX_PLANES]); void drm_gem_fb_vunmap(struct drm_framebuffer *fb, - struct dma_buf_map map[static DRM_FORMAT_MAX_PLANES]); + struct iosys_map map[static DRM_FORMAT_MAX_PLANES]); int drm_gem_fb_begin_cpu_access(struct drm_framebuffer *fb, enum dma_data_direction dir); void drm_gem_fb_end_cpu_access(struct drm_framebuffer *fb, enum dma_data_direction dir); diff --git a/include/drm/drm_gem_shmem_helper.h b/include/drm/drm_gem_shmem_helper.h index 311d66c9cf4b..68347b63fc71 100644 --- a/include/drm/drm_gem_shmem_helper.h +++ b/include/drm/drm_gem_shmem_helper.h @@ -113,8 +113,10 @@ int drm_gem_shmem_get_pages(struct drm_gem_shmem_object *shmem); void drm_gem_shmem_put_pages(struct drm_gem_shmem_object *shmem); int drm_gem_shmem_pin(struct drm_gem_shmem_object *shmem); void drm_gem_shmem_unpin(struct drm_gem_shmem_object *shmem); -int drm_gem_shmem_vmap(struct drm_gem_shmem_object *shmem, struct dma_buf_map *map); -void drm_gem_shmem_vunmap(struct drm_gem_shmem_object *shmem, struct dma_buf_map *map); +int drm_gem_shmem_vmap(struct drm_gem_shmem_object *shmem, + struct iosys_map *map); +void drm_gem_shmem_vunmap(struct drm_gem_shmem_object *shmem, + struct iosys_map *map); int drm_gem_shmem_mmap(struct drm_gem_shmem_object *shmem, struct vm_area_struct *vma); int drm_gem_shmem_madvise(struct drm_gem_shmem_object *shmem, int madv); @@ -226,7 +228,8 @@ static inline struct sg_table *drm_gem_shmem_object_get_sg_table(struct drm_gem_ * Returns: * 0 on success or a negative error code on failure. */ -static inline int drm_gem_shmem_object_vmap(struct drm_gem_object *obj, struct dma_buf_map *map) +static inline int drm_gem_shmem_object_vmap(struct drm_gem_object *obj, + struct iosys_map *map) { struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); @@ -241,7 +244,8 @@ static inline int drm_gem_shmem_object_vmap(struct drm_gem_object *obj, struct d * This function wraps drm_gem_shmem_vunmap(). Drivers that employ the shmem helpers should * use it as their &drm_gem_object_funcs.vunmap handler. */ -static inline void drm_gem_shmem_object_vunmap(struct drm_gem_object *obj, struct dma_buf_map *map) +static inline void drm_gem_shmem_object_vunmap(struct drm_gem_object *obj, + struct iosys_map *map) { struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); diff --git a/include/drm/drm_gem_ttm_helper.h b/include/drm/drm_gem_ttm_helper.h index 78040f6cc6f3..4c003b4f173e 100644 --- a/include/drm/drm_gem_ttm_helper.h +++ b/include/drm/drm_gem_ttm_helper.h @@ -10,7 +10,7 @@ #include #include -struct dma_buf_map; +struct iosys_map; #define drm_gem_ttm_of_gem(gem_obj) \ container_of(gem_obj, struct ttm_buffer_object, base) @@ -18,9 +18,9 @@ struct dma_buf_map; void drm_gem_ttm_print_info(struct drm_printer *p, unsigned int indent, const struct drm_gem_object *gem); int drm_gem_ttm_vmap(struct drm_gem_object *gem, - struct dma_buf_map *map); + struct iosys_map *map); void drm_gem_ttm_vunmap(struct drm_gem_object *gem, - struct dma_buf_map *map); + struct iosys_map *map); int drm_gem_ttm_mmap(struct drm_gem_object *gem, struct vm_area_struct *vma); diff --git a/include/drm/drm_gem_vram_helper.h b/include/drm/drm_gem_vram_helper.h index b4ce27a72773..c083a1d71cf4 100644 --- a/include/drm/drm_gem_vram_helper.h +++ b/include/drm/drm_gem_vram_helper.h @@ -12,7 +12,7 @@ #include #include -#include +#include struct drm_mode_create_dumb; struct drm_plane; @@ -51,7 +51,7 @@ struct vm_area_struct; */ struct drm_gem_vram_object { struct ttm_buffer_object bo; - struct dma_buf_map map; + struct iosys_map map; /** * @vmap_use_count: @@ -97,8 +97,9 @@ void drm_gem_vram_put(struct drm_gem_vram_object *gbo); s64 drm_gem_vram_offset(struct drm_gem_vram_object *gbo); int drm_gem_vram_pin(struct drm_gem_vram_object *gbo, unsigned long pl_flag); int drm_gem_vram_unpin(struct drm_gem_vram_object *gbo); -int drm_gem_vram_vmap(struct drm_gem_vram_object *gbo, struct dma_buf_map *map); -void drm_gem_vram_vunmap(struct drm_gem_vram_object *gbo, struct dma_buf_map *map); +int drm_gem_vram_vmap(struct drm_gem_vram_object *gbo, struct iosys_map *map); +void drm_gem_vram_vunmap(struct drm_gem_vram_object *gbo, + struct iosys_map *map); int drm_gem_vram_fill_create_dumb(struct drm_file *file, struct drm_device *dev, diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h index 54f2c58305d2..2a1d01e5b56b 100644 --- a/include/drm/drm_prime.h +++ b/include/drm/drm_prime.h @@ -54,7 +54,7 @@ struct device; struct dma_buf_export_info; struct dma_buf; struct dma_buf_attachment; -struct dma_buf_map; +struct iosys_map; enum dma_data_direction; @@ -83,8 +83,8 @@ struct sg_table *drm_gem_map_dma_buf(struct dma_buf_attachment *attach, void drm_gem_unmap_dma_buf(struct dma_buf_attachment *attach, struct sg_table *sgt, enum dma_data_direction dir); -int drm_gem_dmabuf_vmap(struct dma_buf *dma_buf, struct dma_buf_map *map); -void drm_gem_dmabuf_vunmap(struct dma_buf *dma_buf, struct dma_buf_map *map); +int drm_gem_dmabuf_vmap(struct dma_buf *dma_buf, struct iosys_map *map); +void drm_gem_dmabuf_vunmap(struct dma_buf *dma_buf, struct iosys_map *map); int drm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma); int drm_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *vma); diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index c17b2df9178b..155b19ee12fb 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -47,7 +47,7 @@ struct ttm_global; struct ttm_device; -struct dma_buf_map; +struct iosys_map; struct drm_mm_node; @@ -481,17 +481,17 @@ void ttm_bo_kunmap(struct ttm_bo_kmap_obj *map); * ttm_bo_vmap * * @bo: The buffer object. - * @map: pointer to a struct dma_buf_map representing the map. + * @map: pointer to a struct iosys_map representing the map. * * Sets up a kernel virtual mapping, using ioremap or vmap to the * data in the buffer object. The parameter @map returns the virtual - * address as struct dma_buf_map. Unmap the buffer with ttm_bo_vunmap(). + * address as struct iosys_map. Unmap the buffer with ttm_bo_vunmap(). * * Returns * -ENOMEM: Out of memory. * -EINVAL: Invalid range. */ -int ttm_bo_vmap(struct ttm_buffer_object *bo, struct dma_buf_map *map); +int ttm_bo_vmap(struct ttm_buffer_object *bo, struct iosys_map *map); /** * ttm_bo_vunmap @@ -501,7 +501,7 @@ int ttm_bo_vmap(struct ttm_buffer_object *bo, struct dma_buf_map *map); * * Unmaps a kernel map set up by ttm_bo_vmap(). */ -void ttm_bo_vunmap(struct ttm_buffer_object *bo, struct dma_buf_map *map); +void ttm_bo_vunmap(struct ttm_buffer_object *bo, struct iosys_map *map); /** * ttm_bo_mmap_obj - mmap memory backed by a ttm buffer object. diff --git a/include/drm/ttm/ttm_kmap_iter.h b/include/drm/ttm/ttm_kmap_iter.h index 8bb00fd39d6c..cc5c09a211b4 100644 --- a/include/drm/ttm/ttm_kmap_iter.h +++ b/include/drm/ttm/ttm_kmap_iter.h @@ -8,7 +8,7 @@ #include struct ttm_kmap_iter; -struct dma_buf_map; +struct iosys_map; /** * struct ttm_kmap_iter_ops - Ops structure for a struct @@ -24,22 +24,22 @@ struct ttm_kmap_iter_ops { * kmap_local semantics. * @res_iter: Pointer to the struct ttm_kmap_iter representing * the resource. - * @dmap: The struct dma_buf_map holding the virtual address after + * @dmap: The struct iosys_map holding the virtual address after * the operation. * @i: The location within the resource to map. PAGE_SIZE granularity. */ void (*map_local)(struct ttm_kmap_iter *res_iter, - struct dma_buf_map *dmap, pgoff_t i); + struct iosys_map *dmap, pgoff_t i); /** * unmap_local() - Unmap a PAGE_SIZE part of the resource previously * mapped using kmap_local. * @res_iter: Pointer to the struct ttm_kmap_iter representing * the resource. - * @dmap: The struct dma_buf_map holding the virtual address after + * @dmap: The struct iosys_map holding the virtual address after * the operation. */ void (*unmap_local)(struct ttm_kmap_iter *res_iter, - struct dma_buf_map *dmap); + struct iosys_map *dmap); bool maps_tt; }; diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index 5952051091cd..6eae09e382d2 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -27,7 +27,7 @@ #include #include -#include +#include #include #include #include @@ -41,7 +41,7 @@ struct ttm_resource; struct ttm_place; struct ttm_buffer_object; struct ttm_placement; -struct dma_buf_map; +struct iosys_map; struct io_mapping; struct sg_table; struct scatterlist; @@ -207,7 +207,7 @@ struct ttm_kmap_iter_iomap { */ struct ttm_kmap_iter_linear_io { struct ttm_kmap_iter base; - struct dma_buf_map dmap; + struct iosys_map dmap; bool needs_unmap; }; diff --git a/include/linux/dma-buf-map.h b/include/linux/dma-buf-map.h deleted file mode 100644 index 278d489e4bdd..000000000000 --- a/include/linux/dma-buf-map.h +++ /dev/null @@ -1,266 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Pointer to dma-buf-mapped memory, plus helpers. - */ - -#ifndef __DMA_BUF_MAP_H__ -#define __DMA_BUF_MAP_H__ - -#include -#include - -/** - * DOC: overview - * - * Calling dma-buf's vmap operation returns a pointer to the buffer's memory. - * Depending on the location of the buffer, users may have to access it with - * I/O operations or memory load/store operations. For example, copying to - * system memory could be done with memcpy(), copying to I/O memory would be - * done with memcpy_toio(). - * - * .. code-block:: c - * - * void *vaddr = ...; // pointer to system memory - * memcpy(vaddr, src, len); - * - * void *vaddr_iomem = ...; // pointer to I/O memory - * memcpy_toio(vaddr, _iomem, src, len); - * - * When using dma-buf's vmap operation, the returned pointer is encoded as - * :c:type:`struct dma_buf_map `. - * :c:type:`struct dma_buf_map ` stores the buffer's address in - * system or I/O memory and a flag that signals the required method of - * accessing the buffer. Use the returned instance and the helper functions - * to access the buffer's memory in the correct way. - * - * The type :c:type:`struct dma_buf_map ` and its helpers are - * actually independent from the dma-buf infrastructure. When sharing buffers - * among devices, drivers have to know the location of the memory to access - * the buffers in a safe way. :c:type:`struct dma_buf_map ` - * solves this problem for dma-buf and its users. If other drivers or - * sub-systems require similar functionality, the type could be generalized - * and moved to a more prominent header file. - * - * Open-coding access to :c:type:`struct dma_buf_map ` is - * considered bad style. Rather then accessing its fields directly, use one - * of the provided helper functions, or implement your own. For example, - * instances of :c:type:`struct dma_buf_map ` can be initialized - * statically with DMA_BUF_MAP_INIT_VADDR(), or at runtime with - * dma_buf_map_set_vaddr(). These helpers will set an address in system memory. - * - * .. code-block:: c - * - * struct dma_buf_map map = DMA_BUF_MAP_INIT_VADDR(0xdeadbeaf); - * - * dma_buf_map_set_vaddr(&map. 0xdeadbeaf); - * - * To set an address in I/O memory, use dma_buf_map_set_vaddr_iomem(). - * - * .. code-block:: c - * - * dma_buf_map_set_vaddr_iomem(&map. 0xdeadbeaf); - * - * Instances of struct dma_buf_map do not have to be cleaned up, but - * can be cleared to NULL with dma_buf_map_clear(). Cleared mappings - * always refer to system memory. - * - * .. code-block:: c - * - * dma_buf_map_clear(&map); - * - * Test if a mapping is valid with either dma_buf_map_is_set() or - * dma_buf_map_is_null(). - * - * .. code-block:: c - * - * if (dma_buf_map_is_set(&map) != dma_buf_map_is_null(&map)) - * // always true - * - * Instances of :c:type:`struct dma_buf_map ` can be compared - * for equality with dma_buf_map_is_equal(). Mappings the point to different - * memory spaces, system or I/O, are never equal. That's even true if both - * spaces are located in the same address space, both mappings contain the - * same address value, or both mappings refer to NULL. - * - * .. code-block:: c - * - * struct dma_buf_map sys_map; // refers to system memory - * struct dma_buf_map io_map; // refers to I/O memory - * - * if (dma_buf_map_is_equal(&sys_map, &io_map)) - * // always false - * - * A set up instance of struct dma_buf_map can be used to access or manipulate - * the buffer memory. Depending on the location of the memory, the provided - * helpers will pick the correct operations. Data can be copied into the memory - * with dma_buf_map_memcpy_to(). The address can be manipulated with - * dma_buf_map_incr(). - * - * .. code-block:: c - * - * const void *src = ...; // source buffer - * size_t len = ...; // length of src - * - * dma_buf_map_memcpy_to(&map, src, len); - * dma_buf_map_incr(&map, len); // go to first byte after the memcpy - */ - -/** - * struct dma_buf_map - Pointer to vmap'ed dma-buf memory. - * @vaddr_iomem: The buffer's address if in I/O memory - * @vaddr: The buffer's address if in system memory - * @is_iomem: True if the dma-buf memory is located in I/O - * memory, or false otherwise. - */ -struct dma_buf_map { - union { - void __iomem *vaddr_iomem; - void *vaddr; - }; - bool is_iomem; -}; - -/** - * DMA_BUF_MAP_INIT_VADDR - Initializes struct dma_buf_map to an address in system memory - * @vaddr_: A system-memory address - */ -#define DMA_BUF_MAP_INIT_VADDR(vaddr_) \ - { \ - .vaddr = (vaddr_), \ - .is_iomem = false, \ - } - -/** - * dma_buf_map_set_vaddr - Sets a dma-buf mapping structure to an address in system memory - * @map: The dma-buf mapping structure - * @vaddr: A system-memory address - * - * Sets the address and clears the I/O-memory flag. - */ -static inline void dma_buf_map_set_vaddr(struct dma_buf_map *map, void *vaddr) -{ - map->vaddr = vaddr; - map->is_iomem = false; -} - -/** - * dma_buf_map_set_vaddr_iomem - Sets a dma-buf mapping structure to an address in I/O memory - * @map: The dma-buf mapping structure - * @vaddr_iomem: An I/O-memory address - * - * Sets the address and the I/O-memory flag. - */ -static inline void dma_buf_map_set_vaddr_iomem(struct dma_buf_map *map, - void __iomem *vaddr_iomem) -{ - map->vaddr_iomem = vaddr_iomem; - map->is_iomem = true; -} - -/** - * dma_buf_map_is_equal - Compares two dma-buf mapping structures for equality - * @lhs: The dma-buf mapping structure - * @rhs: A dma-buf mapping structure to compare with - * - * Two dma-buf mapping structures are equal if they both refer to the same type of memory - * and to the same address within that memory. - * - * Returns: - * True is both structures are equal, or false otherwise. - */ -static inline bool dma_buf_map_is_equal(const struct dma_buf_map *lhs, - const struct dma_buf_map *rhs) -{ - if (lhs->is_iomem != rhs->is_iomem) - return false; - else if (lhs->is_iomem) - return lhs->vaddr_iomem == rhs->vaddr_iomem; - else - return lhs->vaddr == rhs->vaddr; -} - -/** - * dma_buf_map_is_null - Tests for a dma-buf mapping to be NULL - * @map: The dma-buf mapping structure - * - * Depending on the state of struct dma_buf_map.is_iomem, tests if the - * mapping is NULL. - * - * Returns: - * True if the mapping is NULL, or false otherwise. - */ -static inline bool dma_buf_map_is_null(const struct dma_buf_map *map) -{ - if (map->is_iomem) - return !map->vaddr_iomem; - return !map->vaddr; -} - -/** - * dma_buf_map_is_set - Tests is the dma-buf mapping has been set - * @map: The dma-buf mapping structure - * - * Depending on the state of struct dma_buf_map.is_iomem, tests if the - * mapping has been set. - * - * Returns: - * True if the mapping is been set, or false otherwise. - */ -static inline bool dma_buf_map_is_set(const struct dma_buf_map *map) -{ - return !dma_buf_map_is_null(map); -} - -/** - * dma_buf_map_clear - Clears a dma-buf mapping structure - * @map: The dma-buf mapping structure - * - * Clears all fields to zero; including struct dma_buf_map.is_iomem. So - * mapping structures that were set to point to I/O memory are reset for - * system memory. Pointers are cleared to NULL. This is the default. - */ -static inline void dma_buf_map_clear(struct dma_buf_map *map) -{ - if (map->is_iomem) { - map->vaddr_iomem = NULL; - map->is_iomem = false; - } else { - map->vaddr = NULL; - } -} - -/** - * dma_buf_map_memcpy_to - Memcpy into dma-buf mapping - * @dst: The dma-buf mapping structure - * @src: The source buffer - * @len: The number of byte in src - * - * Copies data into a dma-buf mapping. The source buffer is in system - * memory. Depending on the buffer's location, the helper picks the correct - * method of accessing the memory. - */ -static inline void dma_buf_map_memcpy_to(struct dma_buf_map *dst, const void *src, size_t len) -{ - if (dst->is_iomem) - memcpy_toio(dst->vaddr_iomem, src, len); - else - memcpy(dst->vaddr, src, len); -} - -/** - * dma_buf_map_incr - Increments the address stored in a dma-buf mapping - * @map: The dma-buf mapping structure - * @incr: The number of bytes to increment - * - * Increments the address stored in a dma-buf mapping. Depending on the - * buffer's location, the correct value will be updated. - */ -static inline void dma_buf_map_incr(struct dma_buf_map *map, size_t incr) -{ - if (map->is_iomem) - map->vaddr_iomem += incr; - else - map->vaddr += incr; -} - -#endif /* __DMA_BUF_MAP_H__ */ diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 7ab50076e7a6..2097760e8e95 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -13,7 +13,7 @@ #ifndef __DMA_BUF_H__ #define __DMA_BUF_H__ -#include +#include #include #include #include @@ -283,8 +283,8 @@ struct dma_buf_ops { */ int (*mmap)(struct dma_buf *, struct vm_area_struct *vma); - int (*vmap)(struct dma_buf *dmabuf, struct dma_buf_map *map); - void (*vunmap)(struct dma_buf *dmabuf, struct dma_buf_map *map); + int (*vmap)(struct dma_buf *dmabuf, struct iosys_map *map); + void (*vunmap)(struct dma_buf *dmabuf, struct iosys_map *map); }; /** @@ -347,7 +347,7 @@ struct dma_buf { * @vmap_ptr: * The current vmap ptr if @vmapping_counter > 0. Protected by @lock. */ - struct dma_buf_map vmap_ptr; + struct iosys_map vmap_ptr; /** * @exp_name: @@ -628,6 +628,6 @@ int dma_buf_end_cpu_access(struct dma_buf *dma_buf, int dma_buf_mmap(struct dma_buf *, struct vm_area_struct *, unsigned long); -int dma_buf_vmap(struct dma_buf *dmabuf, struct dma_buf_map *map); -void dma_buf_vunmap(struct dma_buf *dmabuf, struct dma_buf_map *map); +int dma_buf_vmap(struct dma_buf *dmabuf, struct iosys_map *map); +void dma_buf_vunmap(struct dma_buf *dmabuf, struct iosys_map *map); #endif /* __DMA_BUF_H__ */ diff --git a/include/linux/iosys-map.h b/include/linux/iosys-map.h new file mode 100644 index 000000000000..f4186f91caa6 --- /dev/null +++ b/include/linux/iosys-map.h @@ -0,0 +1,257 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Pointer abstraction for IO/system memory + */ + +#ifndef __IOSYS_MAP_H__ +#define __IOSYS_MAP_H__ + +#include +#include + +/** + * DOC: overview + * + * When accessing a memory region, depending on its location, users may have to + * access it with I/O operations or memory load/store operations. For example, + * copying to system memory could be done with memcpy(), copying to I/O memory + * would be done with memcpy_toio(). + * + * .. code-block:: c + * + * void *vaddr = ...; // pointer to system memory + * memcpy(vaddr, src, len); + * + * void *vaddr_iomem = ...; // pointer to I/O memory + * memcpy_toio(vaddr, _iomem, src, len); + * + * The user of such pointer may not have information about the mapping of that + * region or may want to have a single code path to handle operations on that + * buffer, regardless if it's located in system or IO memory. The type + * :c:type:`struct iosys_map ` and its helpers abstract that so the + * buffer can be passed around to other drivers or have separate duties inside + * the same driver for allocation, read and write operations. + * + * Open-coding access to :c:type:`struct iosys_map ` is considered + * bad style. Rather then accessing its fields directly, use one of the provided + * helper functions, or implement your own. For example, instances of + * :c:type:`struct iosys_map ` can be initialized statically with + * IOSYS_MAP_INIT_VADDR(), or at runtime with iosys_map_set_vaddr(). These + * helpers will set an address in system memory. + * + * .. code-block:: c + * + * struct iosys_map map = IOSYS_MAP_INIT_VADDR(0xdeadbeaf); + * + * iosys_map_set_vaddr(&map, 0xdeadbeaf); + * + * To set an address in I/O memory, use iosys_map_set_vaddr_iomem(). + * + * .. code-block:: c + * + * iosys_map_set_vaddr_iomem(&map, 0xdeadbeaf); + * + * Instances of struct iosys_map do not have to be cleaned up, but + * can be cleared to NULL with iosys_map_clear(). Cleared mappings + * always refer to system memory. + * + * .. code-block:: c + * + * iosys_map_clear(&map); + * + * Test if a mapping is valid with either iosys_map_is_set() or + * iosys_map_is_null(). + * + * .. code-block:: c + * + * if (iosys_map_is_set(&map) != iosys_map_is_null(&map)) + * // always true + * + * Instances of :c:type:`struct iosys_map ` can be compared for + * equality with iosys_map_is_equal(). Mappings that point to different memory + * spaces, system or I/O, are never equal. That's even true if both spaces are + * located in the same address space, both mappings contain the same address + * value, or both mappings refer to NULL. + * + * .. code-block:: c + * + * struct iosys_map sys_map; // refers to system memory + * struct iosys_map io_map; // refers to I/O memory + * + * if (iosys_map_is_equal(&sys_map, &io_map)) + * // always false + * + * A set up instance of struct iosys_map can be used to access or manipulate the + * buffer memory. Depending on the location of the memory, the provided helpers + * will pick the correct operations. Data can be copied into the memory with + * iosys_map_memcpy_to(). The address can be manipulated with iosys_map_incr(). + * + * .. code-block:: c + * + * const void *src = ...; // source buffer + * size_t len = ...; // length of src + * + * iosys_map_memcpy_to(&map, src, len); + * iosys_map_incr(&map, len); // go to first byte after the memcpy + */ + +/** + * struct iosys_map - Pointer to IO/system memory + * @vaddr_iomem: The buffer's address if in I/O memory + * @vaddr: The buffer's address if in system memory + * @is_iomem: True if the buffer is located in I/O memory, or false + * otherwise. + */ +struct iosys_map { + union { + void __iomem *vaddr_iomem; + void *vaddr; + }; + bool is_iomem; +}; + +/** + * IOSYS_MAP_INIT_VADDR - Initializes struct iosys_map to an address in system memory + * @vaddr_: A system-memory address + */ +#define IOSYS_MAP_INIT_VADDR(vaddr_) \ + { \ + .vaddr = (vaddr_), \ + .is_iomem = false, \ + } + +/** + * iosys_map_set_vaddr - Sets a iosys mapping structure to an address in system memory + * @map: The iosys_map structure + * @vaddr: A system-memory address + * + * Sets the address and clears the I/O-memory flag. + */ +static inline void iosys_map_set_vaddr(struct iosys_map *map, void *vaddr) +{ + map->vaddr = vaddr; + map->is_iomem = false; +} + +/** + * iosys_map_set_vaddr_iomem - Sets a iosys mapping structure to an address in I/O memory + * @map: The iosys_map structure + * @vaddr_iomem: An I/O-memory address + * + * Sets the address and the I/O-memory flag. + */ +static inline void iosys_map_set_vaddr_iomem(struct iosys_map *map, + void __iomem *vaddr_iomem) +{ + map->vaddr_iomem = vaddr_iomem; + map->is_iomem = true; +} + +/** + * iosys_map_is_equal - Compares two iosys mapping structures for equality + * @lhs: The iosys_map structure + * @rhs: A iosys_map structure to compare with + * + * Two iosys mapping structures are equal if they both refer to the same type of memory + * and to the same address within that memory. + * + * Returns: + * True is both structures are equal, or false otherwise. + */ +static inline bool iosys_map_is_equal(const struct iosys_map *lhs, + const struct iosys_map *rhs) +{ + if (lhs->is_iomem != rhs->is_iomem) + return false; + else if (lhs->is_iomem) + return lhs->vaddr_iomem == rhs->vaddr_iomem; + else + return lhs->vaddr == rhs->vaddr; +} + +/** + * iosys_map_is_null - Tests for a iosys mapping to be NULL + * @map: The iosys_map structure + * + * Depending on the state of struct iosys_map.is_iomem, tests if the + * mapping is NULL. + * + * Returns: + * True if the mapping is NULL, or false otherwise. + */ +static inline bool iosys_map_is_null(const struct iosys_map *map) +{ + if (map->is_iomem) + return !map->vaddr_iomem; + return !map->vaddr; +} + +/** + * iosys_map_is_set - Tests if the iosys mapping has been set + * @map: The iosys_map structure + * + * Depending on the state of struct iosys_map.is_iomem, tests if the + * mapping has been set. + * + * Returns: + * True if the mapping is been set, or false otherwise. + */ +static inline bool iosys_map_is_set(const struct iosys_map *map) +{ + return !iosys_map_is_null(map); +} + +/** + * iosys_map_clear - Clears a iosys mapping structure + * @map: The iosys_map structure + * + * Clears all fields to zero, including struct iosys_map.is_iomem, so + * mapping structures that were set to point to I/O memory are reset for + * system memory. Pointers are cleared to NULL. This is the default. + */ +static inline void iosys_map_clear(struct iosys_map *map) +{ + if (map->is_iomem) { + map->vaddr_iomem = NULL; + map->is_iomem = false; + } else { + map->vaddr = NULL; + } +} + +/** + * iosys_map_memcpy_to - Memcpy into iosys mapping + * @dst: The iosys_map structure + * @src: The source buffer + * @len: The number of byte in src + * + * Copies data into a iosys mapping. The source buffer is in system + * memory. Depending on the buffer's location, the helper picks the correct + * method of accessing the memory. + */ +static inline void iosys_map_memcpy_to(struct iosys_map *dst, const void *src, + size_t len) +{ + if (dst->is_iomem) + memcpy_toio(dst->vaddr_iomem, src, len); + else + memcpy(dst->vaddr, src, len); +} + +/** + * iosys_map_incr - Increments the address stored in a iosys mapping + * @map: The iosys_map structure + * @incr: The number of bytes to increment + * + * Increments the address stored in a iosys mapping. Depending on the + * buffer's location, the correct value will be updated. + */ +static inline void iosys_map_incr(struct iosys_map *map, size_t incr) +{ + if (map->is_iomem) + map->vaddr_iomem += incr; + else + map->vaddr += incr; +} + +#endif /* __IOSYS_MAP_H__ */ -- cgit v1.2.3 From 3486bedd99196ecdfe99c0ab5b67ad3c47e8a8fa Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 4 Feb 2022 10:57:35 -0800 Subject: bpf: Use bytes instead of pages for bpf_jit_[charge|uncharge]_modmem This enables sub-page memory charge and allocation. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220204185742.271030-3-song@kernel.org --- include/linux/bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6eb0b180d33b..366f88afd56b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -846,8 +846,8 @@ void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym); void bpf_image_ksym_del(struct bpf_ksym *ksym); void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); -int bpf_jit_charge_modmem(u32 pages); -void bpf_jit_uncharge_modmem(u32 pages); +int bpf_jit_charge_modmem(u32 size); +void bpf_jit_uncharge_modmem(u32 size); bool bpf_prog_has_trampoline(const struct bpf_prog *prog); #else static inline int bpf_trampoline_link_prog(struct bpf_prog *prog, -- cgit v1.2.3 From ed2d9e1a26cca963ff5ed3b76326d70f7d8201a9 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 4 Feb 2022 10:57:36 -0800 Subject: bpf: Use size instead of pages in bpf_binary_header This is necessary to charge sub page memory for the BPF program. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220204185742.271030-4-song@kernel.org --- include/linux/filter.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index d23e999dc032..5855eb474c62 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -548,7 +548,7 @@ struct sock_fprog_kern { #define BPF_IMAGE_ALIGNMENT 8 struct bpf_binary_header { - u32 pages; + u32 size; u8 image[] __aligned(BPF_IMAGE_ALIGNMENT); }; @@ -886,8 +886,8 @@ static inline void bpf_prog_lock_ro(struct bpf_prog *fp) static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { set_vm_flush_reset_perms(hdr); - set_memory_ro((unsigned long)hdr, hdr->pages); - set_memory_x((unsigned long)hdr, hdr->pages); + set_memory_ro((unsigned long)hdr, hdr->size >> PAGE_SHIFT); + set_memory_x((unsigned long)hdr, hdr->size >> PAGE_SHIFT); } static inline struct bpf_binary_header * -- cgit v1.2.3 From ebc1415d9b4f043cef5a1fb002ec316e32167e7a Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 4 Feb 2022 10:57:39 -0800 Subject: bpf: Introduce bpf_arch_text_copy This will be used to copy JITed text to RO protected module memory. On x86, bpf_arch_text_copy is implemented with text_poke_copy. bpf_arch_text_copy returns pointer to dst on success, and ERR_PTR(errno) on errors. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220204185742.271030-7-song@kernel.org --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 366f88afd56b..ea0d7fd4a410 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2362,6 +2362,8 @@ enum bpf_text_poke_type { int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2); +void *bpf_arch_text_copy(void *dst, void *src, size_t len); + struct btf_id_set; bool btf_id_set_contains(const struct btf_id_set *set, u32 id); -- cgit v1.2.3 From 33c9805860e584b194199cab1a1e81f4e6395408 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 4 Feb 2022 10:57:41 -0800 Subject: bpf: Introduce bpf_jit_binary_pack_[alloc|finalize|free] This is the jit binary allocator built on top of bpf_prog_pack. bpf_prog_pack allocates RO memory, which cannot be used directly by the JIT engine. Therefore, a temporary rw buffer is allocated for the JIT engine. Once JIT is done, bpf_jit_binary_pack_finalize is used to copy the program to the RO memory. bpf_jit_binary_pack_alloc reserves 16 bytes of extra space for illegal instructions, which is small than the 128 bytes space reserved by bpf_jit_binary_alloc. This change is necessary for bpf_jit_binary_hdr to find the correct header. Also, flag use_bpf_prog_pack is added to differentiate a program allocated by bpf_jit_binary_pack_alloc. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220204185742.271030-9-song@kernel.org --- include/linux/bpf.h | 1 + include/linux/filter.h | 21 ++++++++++++--------- 2 files changed, 13 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ea0d7fd4a410..2fc7e5c5ef41 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -953,6 +953,7 @@ struct bpf_prog_aux { bool sleepable; bool tail_call_reachable; bool xdp_has_frags; + bool use_bpf_prog_pack; struct hlist_node tramp_hlist; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; diff --git a/include/linux/filter.h b/include/linux/filter.h index 5855eb474c62..1cb1af917617 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -890,15 +890,6 @@ static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) set_memory_x((unsigned long)hdr, hdr->size >> PAGE_SHIFT); } -static inline struct bpf_binary_header * -bpf_jit_binary_hdr(const struct bpf_prog *fp) -{ - unsigned long real_start = (unsigned long)fp->bpf_func; - unsigned long addr = real_start & PAGE_MASK; - - return (void *)addr; -} - int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); static inline int sk_filter(struct sock *sk, struct sk_buff *skb) { @@ -1068,6 +1059,18 @@ void *bpf_jit_alloc_exec(unsigned long size); void bpf_jit_free_exec(void *addr); void bpf_jit_free(struct bpf_prog *fp); +struct bpf_binary_header * +bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **ro_image, + unsigned int alignment, + struct bpf_binary_header **rw_hdr, + u8 **rw_image, + bpf_jit_fill_hole_t bpf_fill_ill_insns); +int bpf_jit_binary_pack_finalize(struct bpf_prog *prog, + struct bpf_binary_header *ro_header, + struct bpf_binary_header *rw_header); +void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header, + struct bpf_binary_header *rw_header); + int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke); -- cgit v1.2.3 From a410a0cf98854a698a519bfbeb604145da384c0e Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 4 Feb 2022 14:58:11 +0100 Subject: ipv6: Define dscp_t and stop taking ECN bits into account in fib6-rules MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Define a dscp_t type and its appropriate helpers that ensure ECN bits are not taken into account when handling DSCP. Use this new type to replace the tclass field of struct fib6_rule, so that fib6-rules don't get influenced by ECN bits anymore. Before this patch, fib6-rules didn't make any distinction between the DSCP and ECN bits. Therefore, rules specifying a DSCP (tos or dsfield options in iproute2) stopped working as soon a packets had at least one of its ECN bits set (as a work around one could create four rules for each DSCP value to match, one for each possible ECN value). After this patch fib6-rules only compare the DSCP bits. ECN doesn't influence the result anymore. Also, fib6-rules now must have the ECN bits cleared or they will be rejected. Signed-off-by: Guillaume Nault Acked-by: David Ahern Reviewed-by: Toke Høiland-Jørgensen Signed-off-by: Jakub Kicinski --- include/net/inet_dscp.h | 57 +++++++++++++++++++++++++++++++++++++++++++++++++ include/net/ipv6.h | 6 ++++++ 2 files changed, 63 insertions(+) create mode 100644 include/net/inet_dscp.h (limited to 'include') diff --git a/include/net/inet_dscp.h b/include/net/inet_dscp.h new file mode 100644 index 000000000000..72f250dffada --- /dev/null +++ b/include/net/inet_dscp.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * inet_dscp.h: helpers for handling differentiated services codepoints (DSCP) + * + * DSCP is defined in RFC 2474: + * + * 0 1 2 3 4 5 6 7 + * +---+---+---+---+---+---+---+---+ + * | DSCP | CU | + * +---+---+---+---+---+---+---+---+ + * + * DSCP: differentiated services codepoint + * CU: currently unused + * + * The whole DSCP + CU bits form the DS field. + * The DS field is also commonly called TOS or Traffic Class (for IPv6). + * + * Note: the CU bits are now used for Explicit Congestion Notification + * (RFC 3168). + */ + +#ifndef _INET_DSCP_H +#define _INET_DSCP_H + +#include + +/* Special type for storing DSCP values. + * + * A dscp_t variable stores a DS field with the CU (ECN) bits cleared. + * Using dscp_t allows to strictly separate DSCP and ECN bits, thus avoiding + * bugs where ECN bits are erroneously taken into account during FIB lookups + * or policy routing. + * + * Note: to get the real DSCP value contained in a dscp_t variable one would + * have to do a bit shift after calling inet_dscp_to_dsfield(). We could have + * a helper for that, but there's currently no users. + */ +typedef u8 __bitwise dscp_t; + +#define INET_DSCP_MASK 0xfc + +static inline dscp_t inet_dsfield_to_dscp(__u8 dsfield) +{ + return (__force dscp_t)(dsfield & INET_DSCP_MASK); +} + +static inline __u8 inet_dscp_to_dsfield(dscp_t dscp) +{ + return (__force __u8)dscp; +} + +static inline bool inet_validate_dscp(__u8 val) +{ + return !(val & ~INET_DSCP_MASK); +} + +#endif /* _INET_DSCP_H */ diff --git a/include/net/ipv6.h b/include/net/ipv6.h index cda1f205f391..f693784e1419 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -974,6 +975,11 @@ static inline u8 ip6_tclass(__be32 flowinfo) return ntohl(flowinfo & IPV6_TCLASS_MASK) >> IPV6_TCLASS_SHIFT; } +static inline dscp_t ip6_dscp(__be32 flowinfo) +{ + return inet_dsfield_to_dscp(ip6_tclass(flowinfo)); +} + static inline __be32 ip6_make_flowinfo(unsigned int tclass, __be32 flowlabel) { return htonl(tclass << IPV6_TCLASS_SHIFT) | flowlabel; -- cgit v1.2.3 From f55fbb6afb8d701e3185e31e73f5ea9503a66744 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 4 Feb 2022 14:58:16 +0100 Subject: ipv4: Reject routes specifying ECN bits in rtm_tos MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use the new dscp_t type to replace the fc_tos field of fib_config, to ensure IPv4 routes aren't influenced by ECN bits when configured with non-zero rtm_tos. Before this patch, IPv4 routes specifying an rtm_tos with some of the ECN bits set were accepted. However they wouldn't work (never match) as IPv4 normally clears the ECN bits with IPTOS_RT_MASK before doing a FIB lookup (although a few buggy code paths don't). After this patch, IPv4 routes specifying an rtm_tos with any ECN bit set is rejected. Note: IPv6 routes ignore rtm_tos altogether, any rtm_tos is accepted, but treated as if it were 0. Signed-off-by: Guillaume Nault Acked-by: David Ahern Reviewed-by: Toke Høiland-Jørgensen Signed-off-by: Jakub Kicinski --- include/net/ip_fib.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index c4297704bbcb..6a82bcb8813b 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -24,7 +25,7 @@ struct fib_config { u8 fc_dst_len; - u8 fc_tos; + dscp_t fc_dscp; u8 fc_protocol; u8 fc_scope; u8 fc_type; -- cgit v1.2.3 From b84b6ec0f9767c82d0cfe5b2ac2c41de6b3d37e8 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 3 Feb 2022 21:29:25 +0100 Subject: scsi: core: Add scsi_done_direct() for immediate completion Add scsi_done_direct() which behaves like scsi_done() except that it invokes blk_mq_complete_request_direct() in order to complete the request. Callers from process context can complete the request directly instead waking ksoftirqd. Link: https://lore.kernel.org/r/Yfw7JaszshmfYa1d@flow Reviewed-by: Bart Van Assche Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Martin K. Petersen --- include/scsi/scsi_cmnd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index 6794d7322cbd..ff1c4b51f7ae 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -168,6 +168,7 @@ static inline struct scsi_driver *scsi_cmd_to_driver(struct scsi_cmnd *cmd) } void scsi_done(struct scsi_cmnd *cmd); +void scsi_done_direct(struct scsi_cmnd *cmd); extern void scsi_finish_command(struct scsi_cmnd *cmd); -- cgit v1.2.3 From 976b6d97c62347df3e686f60a5f455bb8ed6ea23 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Wed, 19 Jan 2022 11:17:32 +0100 Subject: dma-buf: consolidate dma_fence subclass checking MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Consolidate the wrapper functions to check for dma_fence subclasses in the dma_fence header. This makes it easier to document and also check the different requirements for fence containers in the subclasses. Signed-off-by: Christian König Reviewed-by: Thomas Hellström Link: https://patchwork.freedesktop.org/patch/msgid/20220204100429.2049-2-christian.koenig@amd.com --- include/linux/dma-fence-array.h | 15 +-------------- include/linux/dma-fence-chain.h | 3 +-- include/linux/dma-fence.h | 38 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 40 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/linux/dma-fence-array.h b/include/linux/dma-fence-array.h index 303dd712220f..fec374f69e12 100644 --- a/include/linux/dma-fence-array.h +++ b/include/linux/dma-fence-array.h @@ -45,19 +45,6 @@ struct dma_fence_array { struct irq_work work; }; -extern const struct dma_fence_ops dma_fence_array_ops; - -/** - * dma_fence_is_array - check if a fence is from the array subsclass - * @fence: fence to test - * - * Return true if it is a dma_fence_array and false otherwise. - */ -static inline bool dma_fence_is_array(struct dma_fence *fence) -{ - return fence->ops == &dma_fence_array_ops; -} - /** * to_dma_fence_array - cast a fence to a dma_fence_array * @fence: fence to cast to a dma_fence_array @@ -68,7 +55,7 @@ static inline bool dma_fence_is_array(struct dma_fence *fence) static inline struct dma_fence_array * to_dma_fence_array(struct dma_fence *fence) { - if (fence->ops != &dma_fence_array_ops) + if (!fence || !dma_fence_is_array(fence)) return NULL; return container_of(fence, struct dma_fence_array, base); diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index 54fe3443fd2c..ee906b659694 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -49,7 +49,6 @@ struct dma_fence_chain { spinlock_t lock; }; -extern const struct dma_fence_ops dma_fence_chain_ops; /** * to_dma_fence_chain - cast a fence to a dma_fence_chain @@ -61,7 +60,7 @@ extern const struct dma_fence_ops dma_fence_chain_ops; static inline struct dma_fence_chain * to_dma_fence_chain(struct dma_fence *fence) { - if (!fence || fence->ops != &dma_fence_chain_ops) + if (!fence || !dma_fence_is_chain(fence)) return NULL; return container_of(fence, struct dma_fence_chain, base); diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 1ea691753bd3..775cdc0b4f24 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -587,4 +587,42 @@ struct dma_fence *dma_fence_get_stub(void); struct dma_fence *dma_fence_allocate_private_stub(void); u64 dma_fence_context_alloc(unsigned num); +extern const struct dma_fence_ops dma_fence_array_ops; +extern const struct dma_fence_ops dma_fence_chain_ops; + +/** + * dma_fence_is_array - check if a fence is from the array subclass + * @fence: the fence to test + * + * Return true if it is a dma_fence_array and false otherwise. + */ +static inline bool dma_fence_is_array(struct dma_fence *fence) +{ + return fence->ops == &dma_fence_array_ops; +} + +/** + * dma_fence_is_chain - check if a fence is from the chain subclass + * @fence: the fence to test + * + * Return true if it is a dma_fence_chain and false otherwise. + */ +static inline bool dma_fence_is_chain(struct dma_fence *fence) +{ + return fence->ops == &dma_fence_chain_ops; +} + +/** + * dma_fence_is_container - check if a fence is a container for other fences + * @fence: the fence to test + * + * Return true if this fence is a container for other fences, false otherwise. + * This is important since we can't build up large fence structure or otherwise + * we run into recursion during operation on those fences. + */ +static inline bool dma_fence_is_container(struct dma_fence *fence) +{ + return dma_fence_is_array(fence) || dma_fence_is_chain(fence); +} + #endif /* __LINUX_DMA_FENCE_H */ -- cgit v1.2.3 From 18f5fad275efef015226ee4f90eae34d8f44aa5e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Thu, 20 Jan 2022 11:42:40 +0100 Subject: dma-buf: add dma_fence_chain_contained helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It's a reoccurring pattern that we need to extract the fence from a dma_fence_chain object. Add a helper for this. Signed-off-by: Christian König Reviewed-by: Thomas Hellström Link: https://patchwork.freedesktop.org/patch/msgid/20220204100429.2049-6-christian.koenig@amd.com --- include/linux/dma-fence-chain.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index ee906b659694..10d51bcdf7b7 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -66,6 +66,21 @@ to_dma_fence_chain(struct dma_fence *fence) return container_of(fence, struct dma_fence_chain, base); } +/** + * dma_fence_chain_contained - return the contained fence + * @fence: the fence to test + * + * If the fence is a dma_fence_chain the function returns the fence contained + * inside the chain object, otherwise it returns the fence itself. + */ +static inline struct dma_fence * +dma_fence_chain_contained(struct dma_fence *fence) +{ + struct dma_fence_chain *chain = to_dma_fence_chain(fence); + + return chain ? chain->fence : fence; +} + /** * dma_fence_chain_alloc * -- cgit v1.2.3 From 5913eb45d036288babb67e97b210233537ef7b90 Mon Sep 17 00:00:00 2001 From: Alistair Francis Date: Mon, 24 Jan 2022 22:10:04 +1000 Subject: mfd: simple-mfd-i2c: Enable support for the silergy,sy7636a Signed-off-by: Alistair Francis Signed-off-by: Lee Jones --- include/linux/mfd/sy7636a.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) create mode 100644 include/linux/mfd/sy7636a.h (limited to 'include') diff --git a/include/linux/mfd/sy7636a.h b/include/linux/mfd/sy7636a.h new file mode 100644 index 000000000000..22f03b2f851e --- /dev/null +++ b/include/linux/mfd/sy7636a.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Functions to access SY3686A power management chip. + * + * Copyright (C) 2021 reMarkable AS - http://www.remarkable.com/ + */ + +#ifndef __MFD_SY7636A_H +#define __MFD_SY7636A_H + +#define SY7636A_REG_OPERATION_MODE_CRL 0x00 +/* It is set if a gpio is used to control the regulator */ +#define SY7636A_OPERATION_MODE_CRL_VCOMCTL BIT(6) +#define SY7636A_OPERATION_MODE_CRL_ONOFF BIT(7) +#define SY7636A_REG_VCOM_ADJUST_CTRL_L 0x01 +#define SY7636A_REG_VCOM_ADJUST_CTRL_H 0x02 +#define SY7636A_REG_VCOM_ADJUST_CTRL_MASK 0x01ff +#define SY7636A_REG_VLDO_VOLTAGE_ADJULST_CTRL 0x03 +#define SY7636A_REG_POWER_ON_DELAY_TIME 0x06 +#define SY7636A_REG_FAULT_FLAG 0x07 +#define SY7636A_FAULT_FLAG_PG BIT(0) +#define SY7636A_REG_TERMISTOR_READOUT 0x08 + +#define SY7636A_REG_MAX 0x08 + +#define VCOM_ADJUST_CTRL_MASK 0x1ff +// Used to shift the high byte +#define VCOM_ADJUST_CTRL_SHIFT 8 +// Used to scale from VCOM_ADJUST_CTRL to mv +#define VCOM_ADJUST_CTRL_SCAL 10000 + +#define FAULT_FLAG_SHIFT 1 + +#endif /* __LINUX_MFD_SY7636A_H */ -- cgit v1.2.3 From fac608138c6136126faadafa5554cc0bbabf3c44 Mon Sep 17 00:00:00 2001 From: Jorgen Hansen Date: Mon, 7 Feb 2022 02:27:18 -0800 Subject: VMCI: dma dg: whitespace formatting change for vmci register defines Update formatting of existing register defines in preparation for adding additional register definitions for the VMCI device. Reviewed-by: Vishnu Dasa Signed-off-by: Jorgen Hansen Link: https://lore.kernel.org/r/20220207102725.2742-2-jhansen@vmware.com Signed-off-by: Greg Kroah-Hartman --- include/linux/vmw_vmci_defs.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/vmw_vmci_defs.h b/include/linux/vmw_vmci_defs.h index e36cb114c188..9911ecfc18ba 100644 --- a/include/linux/vmw_vmci_defs.h +++ b/include/linux/vmw_vmci_defs.h @@ -12,15 +12,15 @@ #include /* Register offsets. */ -#define VMCI_STATUS_ADDR 0x00 -#define VMCI_CONTROL_ADDR 0x04 -#define VMCI_ICR_ADDR 0x08 -#define VMCI_IMR_ADDR 0x0c -#define VMCI_DATA_OUT_ADDR 0x10 -#define VMCI_DATA_IN_ADDR 0x14 -#define VMCI_CAPS_ADDR 0x18 -#define VMCI_RESULT_LOW_ADDR 0x1c -#define VMCI_RESULT_HIGH_ADDR 0x20 +#define VMCI_STATUS_ADDR 0x00 +#define VMCI_CONTROL_ADDR 0x04 +#define VMCI_ICR_ADDR 0x08 +#define VMCI_IMR_ADDR 0x0c +#define VMCI_DATA_OUT_ADDR 0x10 +#define VMCI_DATA_IN_ADDR 0x14 +#define VMCI_CAPS_ADDR 0x18 +#define VMCI_RESULT_LOW_ADDR 0x1c +#define VMCI_RESULT_HIGH_ADDR 0x20 /* Max number of devices. */ #define VMCI_MAX_DEVICES 1 -- cgit v1.2.3 From e283a0e8b7ea83915e988ed059384af166b444c0 Mon Sep 17 00:00:00 2001 From: Jorgen Hansen Date: Mon, 7 Feb 2022 02:27:19 -0800 Subject: VMCI: dma dg: add MMIO access to registers Detect the support for MMIO access through examination of the length of the region requested in BAR1. If it is 256KB, the VMCI device supports MMIO access to registers. If MMIO access is supported, map the area of the region used for MMIO access (64KB size at offset 128KB). Add wrapper functions for accessing 32 bit register accesses through either MMIO or IO ports based on device configuration. Sending and receiving datagrams through iowrite8_rep/ioread8_rep is left unchanged for now, and will be addressed in a later change. Reviewed-by: Vishnu Dasa Signed-off-by: Jorgen Hansen Link: https://lore.kernel.org/r/20220207102725.2742-3-jhansen@vmware.com Signed-off-by: Greg Kroah-Hartman --- include/linux/vmw_vmci_defs.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/vmw_vmci_defs.h b/include/linux/vmw_vmci_defs.h index 9911ecfc18ba..8fc00e2685cf 100644 --- a/include/linux/vmw_vmci_defs.h +++ b/include/linux/vmw_vmci_defs.h @@ -82,6 +82,18 @@ enum { */ #define VMCI_MAX_PINNED_QP_MEMORY ((size_t)(32 * 1024)) +/* + * The version of the VMCI device that supports MMIO access to registers + * requests 256KB for BAR1 whereas the version of VMCI that supports + * MSI/MSI-X only requests 8KB. The layout of the larger 256KB region is: + * - the first 128KB are used for MSI/MSI-X. + * - the following 64KB are used for MMIO register access. + * - the remaining 64KB are unused. + */ +#define VMCI_WITH_MMIO_ACCESS_BAR_SIZE ((size_t)(256 * 1024)) +#define VMCI_MMIO_ACCESS_OFFSET ((size_t)(128 * 1024)) +#define VMCI_MMIO_ACCESS_SIZE ((size_t)(64 * 1024)) + /* * We have a fixed set of resource IDs available in the VMX. * This allows us to have a very simple implementation since we statically -- cgit v1.2.3 From eed2298d936087a1c85e0fa6f7170028e4f4fded Mon Sep 17 00:00:00 2001 From: Jorgen Hansen Date: Mon, 7 Feb 2022 02:27:20 -0800 Subject: VMCI: dma dg: detect DMA datagram capability Detect the VMCI DMA datagram capability, and if present, ack it to the device. Reviewed-by: Vishnu Dasa Signed-off-by: Jorgen Hansen Link: https://lore.kernel.org/r/20220207102725.2742-4-jhansen@vmware.com Signed-off-by: Greg Kroah-Hartman --- include/linux/vmw_vmci_defs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/vmw_vmci_defs.h b/include/linux/vmw_vmci_defs.h index 8fc00e2685cf..1ce2cffdc3ae 100644 --- a/include/linux/vmw_vmci_defs.h +++ b/include/linux/vmw_vmci_defs.h @@ -39,6 +39,7 @@ #define VMCI_CAPS_DATAGRAM BIT(2) #define VMCI_CAPS_NOTIFICATIONS BIT(3) #define VMCI_CAPS_PPN64 BIT(4) +#define VMCI_CAPS_DMA_DATAGRAM BIT(5) /* Interrupt Cause register bits. */ #define VMCI_ICR_DATAGRAM BIT(0) -- cgit v1.2.3 From 8cb520bea1470ca205980fbf030ed1f472f4af2f Mon Sep 17 00:00:00 2001 From: Jorgen Hansen Date: Mon, 7 Feb 2022 02:27:21 -0800 Subject: VMCI: dma dg: set OS page size Tell the device the page size used by the OS. Reviewed-by: Vishnu Dasa Signed-off-by: Jorgen Hansen Link: https://lore.kernel.org/r/20220207102725.2742-5-jhansen@vmware.com Signed-off-by: Greg Kroah-Hartman --- include/linux/vmw_vmci_defs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/vmw_vmci_defs.h b/include/linux/vmw_vmci_defs.h index 1ce2cffdc3ae..4167779469fd 100644 --- a/include/linux/vmw_vmci_defs.h +++ b/include/linux/vmw_vmci_defs.h @@ -21,6 +21,7 @@ #define VMCI_CAPS_ADDR 0x18 #define VMCI_RESULT_LOW_ADDR 0x1c #define VMCI_RESULT_HIGH_ADDR 0x20 +#define VMCI_GUEST_PAGE_SHIFT 0x34 /* Max number of devices. */ #define VMCI_MAX_DEVICES 1 -- cgit v1.2.3 From cc68f2177fcbfe2dbe5e9514789b96ba5995ec1e Mon Sep 17 00:00:00 2001 From: Jorgen Hansen Date: Mon, 7 Feb 2022 02:27:22 -0800 Subject: VMCI: dma dg: register dummy IRQ handlers for DMA datagrams Register dummy interrupt handlers for DMA datagrams in preparation for DMA datagram receive operations. Reviewed-by: Vishnu Dasa Signed-off-by: Jorgen Hansen Link: https://lore.kernel.org/r/20220207102725.2742-6-jhansen@vmware.com Signed-off-by: Greg Kroah-Hartman --- include/linux/vmw_vmci_defs.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/vmw_vmci_defs.h b/include/linux/vmw_vmci_defs.h index 4167779469fd..2b70c024dacb 100644 --- a/include/linux/vmw_vmci_defs.h +++ b/include/linux/vmw_vmci_defs.h @@ -45,13 +45,22 @@ /* Interrupt Cause register bits. */ #define VMCI_ICR_DATAGRAM BIT(0) #define VMCI_ICR_NOTIFICATION BIT(1) +#define VMCI_ICR_DMA_DATAGRAM BIT(2) /* Interrupt Mask register bits. */ #define VMCI_IMR_DATAGRAM BIT(0) #define VMCI_IMR_NOTIFICATION BIT(1) +#define VMCI_IMR_DMA_DATAGRAM BIT(2) -/* Maximum MSI/MSI-X interrupt vectors in the device. */ -#define VMCI_MAX_INTRS 2 +/* + * Maximum MSI/MSI-X interrupt vectors in the device. + * If VMCI_CAPS_DMA_DATAGRAM is supported by the device, + * VMCI_MAX_INTRS_DMA_DATAGRAM vectors are available, + * otherwise only VMCI_MAX_INTRS_NOTIFICATION. + */ +#define VMCI_MAX_INTRS_NOTIFICATION 2 +#define VMCI_MAX_INTRS_DMA_DATAGRAM 3 +#define VMCI_MAX_INTRS VMCI_MAX_INTRS_DMA_DATAGRAM /* * Supported interrupt vectors. There is one for each ICR value above, @@ -60,6 +69,7 @@ enum { VMCI_INTR_DATAGRAM = 0, VMCI_INTR_NOTIFICATION = 1, + VMCI_INTR_DMA_DATAGRAM = 2, }; /* -- cgit v1.2.3 From 5ee109828e73bbe4213c373988608d8f33e03d78 Mon Sep 17 00:00:00 2001 From: Jorgen Hansen Date: Mon, 7 Feb 2022 02:27:23 -0800 Subject: VMCI: dma dg: allocate send and receive buffers for DMA datagrams If DMA datagrams are used, allocate send and receive buffers in coherent DMA memory. This is done in preparation for the send and receive datagram operations, where the buffers are used for the exchange of data between driver and device. Reviewed-by: Vishnu Dasa Signed-off-by: Jorgen Hansen Link: https://lore.kernel.org/r/20220207102725.2742-7-jhansen@vmware.com Signed-off-by: Greg Kroah-Hartman --- include/linux/vmw_vmci_defs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/vmw_vmci_defs.h b/include/linux/vmw_vmci_defs.h index 2b70c024dacb..8bc37d8244a8 100644 --- a/include/linux/vmw_vmci_defs.h +++ b/include/linux/vmw_vmci_defs.h @@ -21,6 +21,10 @@ #define VMCI_CAPS_ADDR 0x18 #define VMCI_RESULT_LOW_ADDR 0x1c #define VMCI_RESULT_HIGH_ADDR 0x20 +#define VMCI_DATA_OUT_LOW_ADDR 0x24 +#define VMCI_DATA_OUT_HIGH_ADDR 0x28 +#define VMCI_DATA_IN_LOW_ADDR 0x2c +#define VMCI_DATA_IN_HIGH_ADDR 0x30 #define VMCI_GUEST_PAGE_SHIFT 0x34 /* Max number of devices. */ -- cgit v1.2.3 From 22aa5c7f323022477b70e044eb00e6bfea9498e8 Mon Sep 17 00:00:00 2001 From: Jorgen Hansen Date: Mon, 7 Feb 2022 02:27:24 -0800 Subject: VMCI: dma dg: add support for DMA datagrams sends Use DMA based send operation from the transmit buffer instead of the iowrite8_rep based datagram send when DMA datagrams are supported. The outgoing datagram is sent as inline data in the VMCI transmit buffer. Once the header has been configured, the send is initiated by writing the lower 32 bit of the buffer base address to the VMCI_DATA_OUT_LOW_ADDR register. Only then will the device process the header and the datagram itself. Following that, the driver busy waits (it isn't possible to sleep on the send path) for the header busy flag to change - indicating that the send is complete. Reviewed-by: Vishnu Dasa Signed-off-by: Jorgen Hansen Link: https://lore.kernel.org/r/20220207102725.2742-8-jhansen@vmware.com Signed-off-by: Greg Kroah-Hartman --- include/linux/vmw_vmci_defs.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include') diff --git a/include/linux/vmw_vmci_defs.h b/include/linux/vmw_vmci_defs.h index 8bc37d8244a8..6fb663b36f72 100644 --- a/include/linux/vmw_vmci_defs.h +++ b/include/linux/vmw_vmci_defs.h @@ -110,6 +110,40 @@ enum { #define VMCI_MMIO_ACCESS_OFFSET ((size_t)(128 * 1024)) #define VMCI_MMIO_ACCESS_SIZE ((size_t)(64 * 1024)) +/* + * For VMCI devices supporting the VMCI_CAPS_DMA_DATAGRAM capability, the + * sending and receiving of datagrams can be performed using DMA to/from + * a driver allocated buffer. + * Sending and receiving will be handled as follows: + * - when sending datagrams, the driver initializes the buffer where the + * data part will refer to the outgoing VMCI datagram, sets the busy flag + * to 1 and writes the address of the buffer to VMCI_DATA_OUT_HIGH_ADDR + * and VMCI_DATA_OUT_LOW_ADDR. Writing to VMCI_DATA_OUT_LOW_ADDR triggers + * the device processing of the buffer. When the device has processed the + * buffer, it will write the result value to the buffer and then clear the + * busy flag. + * - when receiving datagrams, the driver initializes the buffer where the + * data part will describe the receive buffer, clears the busy flag and + * writes the address of the buffer to VMCI_DATA_IN_HIGH_ADDR and + * VMCI_DATA_IN_LOW_ADDR. Writing to VMCI_DATA_IN_LOW_ADDR triggers the + * device processing of the buffer. The device will copy as many available + * datagrams into the buffer as possible, and then sets the busy flag. + * When the busy flag is set, the driver will process the datagrams in the + * buffer. + */ +struct vmci_data_in_out_header { + uint32_t busy; + uint32_t opcode; + uint32_t size; + uint32_t rsvd; + uint64_t result; +}; + +struct vmci_sg_elem { + uint64_t addr; + uint64_t size; +}; + /* * We have a fixed set of resource IDs available in the VMX. * This allows us to have a very simple implementation since we statically -- cgit v1.2.3 From 2f04aa69ab5c5c40d2e3e51fd73ce2ecb651e9ba Mon Sep 17 00:00:00 2001 From: Vincent Whitchurch Date: Fri, 4 Feb 2022 16:52:40 +0100 Subject: regulator: Add bindings for TPS62864x Add bindings for the TPS62864/TPS6286/TPS62868/TPS62869 voltage regulators. Signed-off-by: Vincent Whitchurch Link: https://lore.kernel.org/r/20220204155241.576342-2-vincent.whitchurch@axis.com Signed-off-by: Mark Brown --- include/dt-bindings/regulator/ti,tps62864.h | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 include/dt-bindings/regulator/ti,tps62864.h (limited to 'include') diff --git a/include/dt-bindings/regulator/ti,tps62864.h b/include/dt-bindings/regulator/ti,tps62864.h new file mode 100644 index 000000000000..8db31f23d956 --- /dev/null +++ b/include/dt-bindings/regulator/ti,tps62864.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ + +#ifndef _DT_BINDINGS_REGULATOR_TI_TPS62864_H +#define _DT_BINDINGS_REGULATOR_TI_TPS62864_H + +#define TPS62864_MODE_NORMAL 0 +#define TPS62864_MODE_FPWM 1 + +#endif -- cgit v1.2.3 From 3301bc53358a0eb0a0db65fd7a513cd4cb50c83a Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 10 Jan 2022 15:29:45 +0800 Subject: lib/sbitmap: kill 'depth' from sbitmap_word Only the last sbitmap_word can have different depth, and all the others must have same depth of 1U << sb->shift, so not necessary to store it in sbitmap_word, and it can be retrieved easily and efficiently by adding one internal helper of __map_depth(sb, index). Remove 'depth' field from sbitmap_word, then the annotation of ____cacheline_aligned_in_smp for 'word' isn't needed any more. Not see performance effect when running high parallel IOPS test on null_blk. This way saves us one cacheline(usually 64 words) per each sbitmap_word. Cc: Martin Wilck Signed-off-by: Ming Lei Reviewed-by: Martin Wilck Reviewed-by: John Garry Link: https://lore.kernel.org/r/20220110072945.347535-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- include/linux/sbitmap.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index 95df357ec009..df3b584b0f0c 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -27,15 +27,10 @@ struct seq_file; * struct sbitmap_word - Word in a &struct sbitmap. */ struct sbitmap_word { - /** - * @depth: Number of bits being used in @word/@cleared - */ - unsigned long depth; - /** * @word: word holding free bits */ - unsigned long word ____cacheline_aligned_in_smp; + unsigned long word; /** * @cleared: word holding cleared bits @@ -164,6 +159,14 @@ struct sbitmap_queue { int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, gfp_t flags, int node, bool round_robin, bool alloc_hint); +/* sbitmap internal helper */ +static inline unsigned int __map_depth(const struct sbitmap *sb, int index) +{ + if (index == sb->map_nr - 1) + return sb->depth - (index << sb->shift); + return 1U << sb->shift; +} + /** * sbitmap_free() - Free memory used by a &struct sbitmap. * @sb: Bitmap to free. @@ -251,7 +254,7 @@ static inline void __sbitmap_for_each_set(struct sbitmap *sb, while (scanned < sb->depth) { unsigned long word; unsigned int depth = min_t(unsigned int, - sb->map[index].depth - nr, + __map_depth(sb, index) - nr, sb->depth - scanned); scanned += depth; -- cgit v1.2.3 From 3f607293b74d6acb06571a774a500143c1f0ed2c Mon Sep 17 00:00:00 2001 From: John Garry Date: Tue, 8 Feb 2022 20:07:04 +0800 Subject: sbitmap: Delete old sbitmap_queue_get_shallow() Since __sbitmap_queue_get_shallow() was introduced in commit c05e66733788 ("sbitmap: add sbitmap_get_shallow() operation"), it has not been used. Delete __sbitmap_queue_get_shallow() and rename public __sbitmap_queue_get_shallow() -> sbitmap_queue_get_shallow() as it is odd to have public __foo but no foo at all. Signed-off-by: John Garry Link: https://lore.kernel.org/r/1644322024-105340-1-git-send-email-john.garry@huawei.com Signed-off-by: Jens Axboe --- include/linux/sbitmap.h | 34 ++++------------------------------ 1 file changed, 4 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index df3b584b0f0c..dffeb8281c2d 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -135,7 +135,7 @@ struct sbitmap_queue { /** * @min_shallow_depth: The minimum shallow depth which may be passed to - * sbitmap_queue_get_shallow() or __sbitmap_queue_get_shallow(). + * sbitmap_queue_get_shallow() */ unsigned int min_shallow_depth; }; @@ -463,7 +463,7 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags, unsigned int *offset); /** - * __sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct + * sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct * sbitmap_queue, limiting the depth used from each word, with preemption * already disabled. * @sbq: Bitmap queue to allocate from. @@ -475,8 +475,8 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags, * * Return: Non-negative allocated bit number if successful, -1 otherwise. */ -int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, - unsigned int shallow_depth); +int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, + unsigned int shallow_depth); /** * sbitmap_queue_get() - Try to allocate a free bit from a &struct @@ -498,32 +498,6 @@ static inline int sbitmap_queue_get(struct sbitmap_queue *sbq, return nr; } -/** - * sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct - * sbitmap_queue, limiting the depth used from each word. - * @sbq: Bitmap queue to allocate from. - * @cpu: Output parameter; will contain the CPU we ran on (e.g., to be passed to - * sbitmap_queue_clear()). - * @shallow_depth: The maximum number of bits to allocate from a single word. - * See sbitmap_get_shallow(). - * - * If you call this, make sure to call sbitmap_queue_min_shallow_depth() after - * initializing @sbq. - * - * Return: Non-negative allocated bit number if successful, -1 otherwise. - */ -static inline int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, - unsigned int *cpu, - unsigned int shallow_depth) -{ - int nr; - - *cpu = get_cpu(); - nr = __sbitmap_queue_get_shallow(sbq, shallow_depth); - put_cpu(); - return nr; -} - /** * sbitmap_queue_min_shallow_depth() - Inform a &struct sbitmap_queue of the * minimum shallow depth that will be used. -- cgit v1.2.3 From dfefa04a90cf9a20090cfa096153d64f95b7e33f Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Tue, 8 Feb 2022 01:27:05 +0000 Subject: KVM: arm64: Drop unused param from kvm_psci_version() kvm_psci_version() consumes a pointer to struct kvm in addition to a vcpu pointer. Drop the kvm pointer as it is unused. While the comment suggests the explicit kvm pointer was useful for calling from hyp, there exist no such callsite in hyp. Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220208012705.640444-1-oupton@google.com --- include/kvm/arm_psci.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h index 5b58bd2fe088..297645edcaff 100644 --- a/include/kvm/arm_psci.h +++ b/include/kvm/arm_psci.h @@ -16,11 +16,7 @@ #define KVM_ARM_PSCI_LATEST KVM_ARM_PSCI_1_0 -/* - * We need the KVM pointer independently from the vcpu as we can call - * this from HYP, and need to apply kern_hyp_va on it... - */ -static inline int kvm_psci_version(struct kvm_vcpu *vcpu, struct kvm *kvm) +static inline int kvm_psci_version(struct kvm_vcpu *vcpu) { /* * Our PSCI implementation stays the same across versions from -- cgit v1.2.3 From 2093057ab879da1070c851b9e07126eaa86d0dfc Mon Sep 17 00:00:00 2001 From: Alexandru Elisei Date: Thu, 27 Jan 2022 16:17:55 +0000 Subject: perf: Fix wrong name in comment for struct perf_cpu_context Commit 0793a61d4df8 ("performance counters: core code") added the perf subsystem (then called Performance Counters) to Linux, creating the struct perf_cpu_context. The comment for the struct referred to it as a "struct perf_counter_cpu_context". Commit cdd6c482c9ff ("perf: Do the big rename: Performance Counters -> Performance Events") changed the comment to refer to a "struct perf_event_cpu_context", which was still the wrong name for the struct. Change the comment to say "struct perf_cpu_context". CC: Thomas Gleixner CC: Ingo Molnar Signed-off-by: Alexandru Elisei Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220127161759.53553-3-alexandru.elisei@arm.com --- include/linux/perf_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 733649184b27..af97dd427501 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -864,7 +864,7 @@ struct perf_event_context { #define PERF_NR_CONTEXTS 4 /** - * struct perf_event_cpu_context - per cpu event context structure + * struct perf_cpu_context - per cpu event context structure */ struct perf_cpu_context { struct perf_event_context ctx; -- cgit v1.2.3 From db858060b1a788fba03711793dcaff19ea43286c Mon Sep 17 00:00:00 2001 From: Alexandru Elisei Date: Thu, 27 Jan 2022 16:17:57 +0000 Subject: KVM: arm64: Keep a list of probed PMUs The ARM PMU driver calls kvm_host_pmu_init() after probing to tell KVM that a hardware PMU is available for guest emulation. Heterogeneous systems can have more than one PMU present, and the callback gets called multiple times, once for each of them. Keep track of all the PMUs available to KVM, as they're going to be needed later. Reviewed-by: Reiji Watanabe Signed-off-by: Alexandru Elisei Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220127161759.53553-5-alexandru.elisei@arm.com --- include/kvm/arm_pmu.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index f9ed4c171d7b..20193416d214 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -29,6 +29,11 @@ struct kvm_pmu { struct irq_work overflow_work; }; +struct arm_pmu_entry { + struct list_head entry; + struct arm_pmu *arm_pmu; +}; + DECLARE_STATIC_KEY_FALSE(kvm_arm_pmu_available); static __always_inline bool kvm_arm_support_pmu_v3(void) -- cgit v1.2.3 From 0cabb47af3cfaeb6007ba3868379bbd4daee64cc Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 10 Dec 2021 16:25:20 -0800 Subject: rcu: Refactor rcu_barrier() empty-list handling This commit saves a few lines by checking first for an empty callback list. If the callback list is empty, then that CPU is taken care of, regardless of its online or nocb state. Also simplify tracing accordingly and fold a few lines together. Signed-off-by: Paul E. McKenney --- include/trace/events/rcu.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index 670e41783edd..90b2fb0292cb 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -794,16 +794,15 @@ TRACE_EVENT_RCU(rcu_torture_read, * Tracepoint for rcu_barrier() execution. The string "s" describes * the rcu_barrier phase: * "Begin": rcu_barrier() started. + * "CB": An rcu_barrier_callback() invoked a callback, not the last. * "EarlyExit": rcu_barrier() piggybacked, thus early exit. * "Inc1": rcu_barrier() piggyback check counter incremented. - * "OfflineNoCBQ": rcu_barrier() found offline no-CBs CPU with callbacks. - * "OnlineQ": rcu_barrier() found online CPU with callbacks. - * "OnlineNQ": rcu_barrier() found online CPU, no callbacks. + * "Inc2": rcu_barrier() piggyback check counter incremented. * "IRQ": An rcu_barrier_callback() callback posted on remote CPU. * "IRQNQ": An rcu_barrier_callback() callback found no callbacks. - * "CB": An rcu_barrier_callback() invoked a callback, not the last. * "LastCB": An rcu_barrier_callback() invoked the last callback. - * "Inc2": rcu_barrier() piggyback check counter incremented. + * "NQ": rcu_barrier() found a CPU with no callbacks. + * "OnlineQ": rcu_barrier() found online CPU with callbacks. * The "cpu" argument is the CPU or -1 if meaningless, the "cnt" argument * is the count of remaining callbacks, and "done" is the piggybacking count. */ -- cgit v1.2.3 From c6c89783eba05a5e159b07cfd8c68d841cc5de42 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 28 Jan 2022 15:39:36 -0800 Subject: fscrypt: add functions for direct I/O support Encrypted files traditionally haven't supported DIO, due to the need to encrypt/decrypt the data. However, when the encryption is implemented using inline encryption (blk-crypto) instead of the traditional filesystem-layer encryption, it is straightforward to support DIO. In preparation for supporting this, add the following functions: - fscrypt_dio_supported() checks whether a DIO request is supported as far as encryption is concerned. Encrypted files will only support DIO when inline encryption is used and the I/O request is properly aligned; this function checks these preconditions. - fscrypt_limit_io_blocks() limits the length of a bio to avoid crossing a place in the file that a bio with an encryption context cannot cross due to a DUN discontiguity. This function is needed by filesystems that use the iomap DIO implementation (which operates directly on logical ranges, so it won't use fscrypt_mergeable_bio()) and that support FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32. Co-developed-by: Satya Tangirala Signed-off-by: Satya Tangirala Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220128233940.79464-2-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fscrypt.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 91ea9477e9bd..50d92d805bd8 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -714,6 +714,10 @@ bool fscrypt_mergeable_bio(struct bio *bio, const struct inode *inode, bool fscrypt_mergeable_bio_bh(struct bio *bio, const struct buffer_head *next_bh); +bool fscrypt_dio_supported(struct kiocb *iocb, struct iov_iter *iter); + +u64 fscrypt_limit_io_blocks(const struct inode *inode, u64 lblk, u64 nr_blocks); + #else /* CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ static inline bool __fscrypt_inode_uses_inline_crypto(const struct inode *inode) @@ -742,6 +746,20 @@ static inline bool fscrypt_mergeable_bio_bh(struct bio *bio, { return true; } + +static inline bool fscrypt_dio_supported(struct kiocb *iocb, + struct iov_iter *iter) +{ + const struct inode *inode = file_inode(iocb->ki_filp); + + return !fscrypt_needs_contents_encryption(inode); +} + +static inline u64 fscrypt_limit_io_blocks(const struct inode *inode, u64 lblk, + u64 nr_blocks) +{ + return nr_blocks; +} #endif /* !CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ /** -- cgit v1.2.3 From b2309a71c1f2fc841feb184195b2e46b2e139bf4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 7 Feb 2022 10:41:07 -0800 Subject: net: add dev->dev_registered_tracker Convert one dev_hold()/dev_put() pair in register_netdevice() and unregister_netdevice_many() to dev_hold_track() and dev_put_track(). This would allow to detect a rogue dev_put() a bit earlier. Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20220207184107.1401096-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3fb6fb67ed77..5f6e2c0b0c90 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1948,6 +1948,8 @@ enum netdev_ml_priv_type { * @dev_addr_shadow: Copy of @dev_addr to catch direct writes. * @linkwatch_dev_tracker: refcount tracker used by linkwatch. * @watchdog_dev_tracker: refcount tracker used by watchdog. + * @dev_registered_tracker: tracker for reference held while + * registered * * FIXME: cleanup struct net_device such that network protocol info * moves out. @@ -2282,6 +2284,7 @@ struct net_device { u8 dev_addr_shadow[MAX_ADDR_LEN]; netdevice_tracker linkwatch_dev_tracker; netdevice_tracker watchdog_dev_tracker; + netdevice_tracker dev_registered_tracker; }; #define to_net_dev(d) container_of(d, struct net_device, dev) -- cgit v1.2.3 From 21a216a8fc630161e69eaf02cbebdd1816ff1a13 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 7 Feb 2022 20:50:28 -0800 Subject: ipv6/addrconf: allocate a per netns hash table Add a per netns hash table and a dedicated spinlock, first step to get rid of the global inet6_addr_lst[] one. Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- include/net/netns/ipv6.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 30cdfc4e1615..755f12001c8b 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -92,6 +92,10 @@ struct netns_ipv6 { struct sock *tcp_sk; struct sock *igmp_sk; struct sock *mc_autojoin_sk; + + struct hlist_head *inet6_addr_lst; + spinlock_t addrconf_hash_lock; + #ifdef CONFIG_IPV6_MROUTE #ifndef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES struct mr_table *mrt6; -- cgit v1.2.3 From 8805d13ff1b2bef6a7bb8a005d2441763286dd7a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 7 Feb 2022 20:50:29 -0800 Subject: ipv6/addrconf: use one delayed work per netns Next step for using per netns inet6_addr_lst is to have per netns work item to ultimately call addrconf_verify_rtnl() and addrconf_verify() with a new 'struct net*' argument. Everything is still using the global inet6_addr_lst[] table. Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- include/net/netns/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 755f12001c8b..d145f1966682 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -95,6 +95,7 @@ struct netns_ipv6 { struct hlist_head *inet6_addr_lst; spinlock_t addrconf_hash_lock; + struct delayed_work addr_chk_work; #ifdef CONFIG_IPV6_MROUTE #ifndef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES -- cgit v1.2.3 From c7d9a6751a5fcebc87feee9b999b40078ed9fb43 Mon Sep 17 00:00:00 2001 From: Luiz Angelo Daros de Luca Date: Tue, 8 Feb 2022 02:32:10 -0300 Subject: net: dsa: typo in comment Signed-off-by: Luiz Angelo Daros de Luca Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20220208053210.14831-1-luizluca@gmail.com Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index ca8c14b547b4..fd1f62a6e0a8 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -1281,7 +1281,7 @@ module_exit(dsa_tag_driver_module_exit) /** * module_dsa_tag_drivers() - Helper macro for registering DSA tag * drivers - * @__ops_array: Array of tag driver strucutres + * @__ops_array: Array of tag driver structures * * Helper macro for DSA tag drivers which do not do anything special * in module init/exit. Each module may only use this macro once, and -- cgit v1.2.3 From 6523d3b2ffa238ac033c34a726617061d6a744aa Mon Sep 17 00:00:00 2001 From: Iwona Winiarska Date: Tue, 8 Feb 2022 16:36:30 +0100 Subject: peci: Add core infrastructure Intel processors provide access for various services designed to support processor and DRAM thermal management, platform manageability and processor interface tuning and diagnostics. Those services are available via the Platform Environment Control Interface (PECI) that provides a communication channel between the processor and the Baseboard Management Controller (BMC) or other platform management device. This change introduces PECI subsystem by adding the initial core module and API for controller drivers. Co-developed-by: Jason M Bills Co-developed-by: Jae Hyun Yoo Reviewed-by: Pierre-Louis Bossart Acked-by: Joel Stanley Signed-off-by: Jason M Bills Signed-off-by: Jae Hyun Yoo Signed-off-by: Iwona Winiarska Link: https://lore.kernel.org/r/20220208153639.255278-5-iwona.winiarska@intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/peci.h | 99 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 99 insertions(+) create mode 100644 include/linux/peci.h (limited to 'include') diff --git a/include/linux/peci.h b/include/linux/peci.h new file mode 100644 index 000000000000..26e0a4e73b50 --- /dev/null +++ b/include/linux/peci.h @@ -0,0 +1,99 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2018-2021 Intel Corporation */ + +#ifndef __LINUX_PECI_H +#define __LINUX_PECI_H + +#include +#include +#include +#include + +/* + * Currently we don't support any PECI command over 32 bytes. + */ +#define PECI_REQUEST_MAX_BUF_SIZE 32 + +struct peci_controller; +struct peci_request; + +/** + * struct peci_controller_ops - PECI controller specific methods + * @xfer: PECI transfer function + * + * PECI controllers may have different hardware interfaces - the drivers + * implementing PECI controllers can use this structure to abstract away those + * differences by exposing a common interface for PECI core. + */ +struct peci_controller_ops { + int (*xfer)(struct peci_controller *controller, u8 addr, struct peci_request *req); +}; + +/** + * struct peci_controller - PECI controller + * @dev: device object to register PECI controller to the device model + * @ops: pointer to device specific controller operations + * @bus_lock: lock used to protect multiple callers + * @id: PECI controller ID + * + * PECI controllers usually connect to their drivers using non-PECI bus, + * such as the platform bus. + * Each PECI controller can communicate with one or more PECI devices. + */ +struct peci_controller { + struct device dev; + struct peci_controller_ops *ops; + struct mutex bus_lock; /* held for the duration of xfer */ + u8 id; +}; + +struct peci_controller *devm_peci_controller_add(struct device *parent, + struct peci_controller_ops *ops); + +static inline struct peci_controller *to_peci_controller(void *d) +{ + return container_of(d, struct peci_controller, dev); +} + +/** + * struct peci_device - PECI device + * @dev: device object to register PECI device to the device model + * @controller: manages the bus segment hosting this PECI device + * @addr: address used on the PECI bus connected to the parent controller + * + * A peci_device identifies a single device (i.e. CPU) connected to a PECI bus. + * The behaviour exposed to the rest of the system is defined by the PECI driver + * managing the device. + */ +struct peci_device { + struct device dev; + u8 addr; +}; + +static inline struct peci_device *to_peci_device(struct device *d) +{ + return container_of(d, struct peci_device, dev); +} + +/** + * struct peci_request - PECI request + * @device: PECI device to which the request is sent + * @tx: TX buffer specific data + * @tx.buf: TX buffer + * @tx.len: transfer data length in bytes + * @rx: RX buffer specific data + * @rx.buf: RX buffer + * @rx.len: received data length in bytes + * + * A peci_request represents a request issued by PECI originator (TX) and + * a response received from PECI responder (RX). + */ +struct peci_request { + struct peci_device *device; + struct { + u8 buf[PECI_REQUEST_MAX_BUF_SIZE]; + u8 len; + } rx, tx; +}; + +#endif /* __LINUX_PECI_H */ -- cgit v1.2.3 From 52857e6828e260b16ac569578705f83cf2a71ac1 Mon Sep 17 00:00:00 2001 From: Iwona Winiarska Date: Tue, 8 Feb 2022 16:36:32 +0100 Subject: peci: Add device detection Since PECI devices are discoverable, we can dynamically detect devices that are actually available in the system. This change complements the earlier implementation by rescanning PECI bus to detect available devices. For this purpose, it also introduces the minimal API for PECI requests. Reviewed-by: Pierre-Louis Bossart Acked-by: Joel Stanley Signed-off-by: Iwona Winiarska Link: https://lore.kernel.org/r/20220208153639.255278-7-iwona.winiarska@intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/peci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/peci.h b/include/linux/peci.h index 26e0a4e73b50..7e35673f3786 100644 --- a/include/linux/peci.h +++ b/include/linux/peci.h @@ -60,6 +60,7 @@ static inline struct peci_controller *to_peci_controller(void *d) * @dev: device object to register PECI device to the device model * @controller: manages the bus segment hosting this PECI device * @addr: address used on the PECI bus connected to the parent controller + * @deleted: indicates that PECI device was already deleted * * A peci_device identifies a single device (i.e. CPU) connected to a PECI bus. * The behaviour exposed to the rest of the system is defined by the PECI driver @@ -68,6 +69,7 @@ static inline struct peci_controller *to_peci_controller(void *d) struct peci_device { struct device dev; u8 addr; + bool deleted; }; static inline struct peci_device *to_peci_device(struct device *d) -- cgit v1.2.3 From 6b8145b054b27319dddaad4abbb5184e343375da Mon Sep 17 00:00:00 2001 From: Iwona Winiarska Date: Tue, 8 Feb 2022 16:36:34 +0100 Subject: peci: Add support for PECI device drivers Add support for PECI device drivers, which unlike PECI controller drivers are actually able to provide functionalities to userspace. Also, extend peci_request API to allow querying more details about PECI device (e.g. model/family), that's going to be used to find a compatible peci_driver. Reviewed-by: Pierre-Louis Bossart Acked-by: Joel Stanley Signed-off-by: Iwona Winiarska Link: https://lore.kernel.org/r/20220208153639.255278-9-iwona.winiarska@intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/peci.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/linux/peci.h b/include/linux/peci.h index 7e35673f3786..4eda423ba10c 100644 --- a/include/linux/peci.h +++ b/include/linux/peci.h @@ -14,6 +14,14 @@ */ #define PECI_REQUEST_MAX_BUF_SIZE 32 +#define PECI_PCS_PKG_ID 0 /* Package Identifier Read */ +#define PECI_PKG_ID_CPU_ID 0x0000 /* CPUID Info */ +#define PECI_PKG_ID_PLATFORM_ID 0x0001 /* Platform ID */ +#define PECI_PKG_ID_DEVICE_ID 0x0002 /* Uncore Device ID */ +#define PECI_PKG_ID_MAX_THREAD_ID 0x0003 /* Max Thread ID */ +#define PECI_PKG_ID_MICROCODE_REV 0x0004 /* CPU Microcode Update Revision */ +#define PECI_PKG_ID_MCA_ERROR_LOG 0x0005 /* Machine Check Status */ + struct peci_controller; struct peci_request; @@ -59,6 +67,11 @@ static inline struct peci_controller *to_peci_controller(void *d) * struct peci_device - PECI device * @dev: device object to register PECI device to the device model * @controller: manages the bus segment hosting this PECI device + * @info: PECI device characteristics + * @info.family: device family + * @info.model: device model + * @info.peci_revision: PECI revision supported by the PECI device + * @info.socket_id: the socket ID represented by the PECI device * @addr: address used on the PECI bus connected to the parent controller * @deleted: indicates that PECI device was already deleted * @@ -68,6 +81,12 @@ static inline struct peci_controller *to_peci_controller(void *d) */ struct peci_device { struct device dev; + struct { + u16 family; + u8 model; + u8 peci_revision; + u8 socket_id; + } info; u8 addr; bool deleted; }; -- cgit v1.2.3 From 93e1821c80f9460c8931dc4bc090ede794f966cd Mon Sep 17 00:00:00 2001 From: Iwona Winiarska Date: Tue, 8 Feb 2022 16:36:35 +0100 Subject: peci: Add peci-cpu driver PECI is an interface that may be used by different types of devices. Add a peci-cpu driver compatible with Intel processors. The driver is responsible for handling auxiliary devices that can subsequently be used by other drivers (e.g. hwmons). Reviewed-by: Pierre-Louis Bossart Acked-by: Joel Stanley Signed-off-by: Iwona Winiarska Link: https://lore.kernel.org/r/20220208153639.255278-10-iwona.winiarska@intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/peci-cpu.h | 40 ++++++++++++++++++++++++++++++++++++++++ include/linux/peci.h | 8 -------- 2 files changed, 40 insertions(+), 8 deletions(-) create mode 100644 include/linux/peci-cpu.h (limited to 'include') diff --git a/include/linux/peci-cpu.h b/include/linux/peci-cpu.h new file mode 100644 index 000000000000..ff8ae9c26c80 --- /dev/null +++ b/include/linux/peci-cpu.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2021 Intel Corporation */ + +#ifndef __LINUX_PECI_CPU_H +#define __LINUX_PECI_CPU_H + +#include + +#include "../../arch/x86/include/asm/intel-family.h" + +#define PECI_PCS_PKG_ID 0 /* Package Identifier Read */ +#define PECI_PKG_ID_CPU_ID 0x0000 /* CPUID Info */ +#define PECI_PKG_ID_PLATFORM_ID 0x0001 /* Platform ID */ +#define PECI_PKG_ID_DEVICE_ID 0x0002 /* Uncore Device ID */ +#define PECI_PKG_ID_MAX_THREAD_ID 0x0003 /* Max Thread ID */ +#define PECI_PKG_ID_MICROCODE_REV 0x0004 /* CPU Microcode Update Revision */ +#define PECI_PKG_ID_MCA_ERROR_LOG 0x0005 /* Machine Check Status */ +#define PECI_PCS_MODULE_TEMP 9 /* Per Core DTS Temperature Read */ +#define PECI_PCS_THERMAL_MARGIN 10 /* DTS thermal margin */ +#define PECI_PCS_DDR_DIMM_TEMP 14 /* DDR DIMM Temperature */ +#define PECI_PCS_TEMP_TARGET 16 /* Temperature Target Read */ +#define PECI_PCS_TDP_UNITS 30 /* Units for power/energy registers */ + +struct peci_device; + +int peci_temp_read(struct peci_device *device, s16 *temp_raw); + +int peci_pcs_read(struct peci_device *device, u8 index, + u16 param, u32 *data); + +int peci_pci_local_read(struct peci_device *device, u8 bus, u8 dev, + u8 func, u16 reg, u32 *data); + +int peci_ep_pci_local_read(struct peci_device *device, u8 seg, + u8 bus, u8 dev, u8 func, u16 reg, u32 *data); + +int peci_mmio_read(struct peci_device *device, u8 bar, u8 seg, + u8 bus, u8 dev, u8 func, u64 address, u32 *data); + +#endif /* __LINUX_PECI_CPU_H */ diff --git a/include/linux/peci.h b/include/linux/peci.h index 4eda423ba10c..06e6ef935297 100644 --- a/include/linux/peci.h +++ b/include/linux/peci.h @@ -14,14 +14,6 @@ */ #define PECI_REQUEST_MAX_BUF_SIZE 32 -#define PECI_PCS_PKG_ID 0 /* Package Identifier Read */ -#define PECI_PKG_ID_CPU_ID 0x0000 /* CPUID Info */ -#define PECI_PKG_ID_PLATFORM_ID 0x0001 /* Platform ID */ -#define PECI_PKG_ID_DEVICE_ID 0x0002 /* Uncore Device ID */ -#define PECI_PKG_ID_MAX_THREAD_ID 0x0003 /* Max Thread ID */ -#define PECI_PKG_ID_MICROCODE_REV 0x0004 /* CPU Microcode Update Revision */ -#define PECI_PKG_ID_MCA_ERROR_LOG 0x0005 /* Machine Check Status */ - struct peci_controller; struct peci_request; -- cgit v1.2.3 From 8cba323437a49a45756d661f500b324fc2d486fe Mon Sep 17 00:00:00 2001 From: Sean Nyekjaer Date: Tue, 8 Feb 2022 09:52:13 +0100 Subject: mtd: rawnand: protect access to rawnand devices while in suspend Prevent rawnand access while in a suspended state. Commit 013e6292aaf5 ("mtd: rawnand: Simplify the locking") allows the rawnand layer to return errors rather than waiting in a blocking wait. Tested on a iMX6ULL. Fixes: 013e6292aaf5 ("mtd: rawnand: Simplify the locking") Signed-off-by: Sean Nyekjaer Reviewed-by: Boris Brezillon Cc: stable@vger.kernel.org Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20220208085213.1838273-1-sean@geanix.com --- include/linux/mtd/rawnand.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 5b88cd51fadb..dcf90144d70b 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1240,6 +1240,7 @@ struct nand_secure_region { * @lock: Lock protecting the suspended field. Also used to serialize accesses * to the NAND device * @suspended: Set to 1 when the device is suspended, 0 when it's not + * @resume_wq: wait queue to sleep if rawnand is in suspended state. * @cur_cs: Currently selected target. -1 means no target selected, otherwise we * should always have cur_cs >= 0 && cur_cs < nanddev_ntargets(). * NAND Controller drivers should not modify this value, but they're @@ -1294,6 +1295,7 @@ struct nand_chip { /* Internals */ struct mutex lock; unsigned int suspended : 1; + wait_queue_head_t resume_wq; int cur_cs; int read_retries; struct nand_secure_region *secure_regions; -- cgit v1.2.3 From 5145abeb0649acf810a32e63bd762e617a9b3309 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 16 Dec 2021 12:16:41 +0100 Subject: mtd: nand: ecc: Provide a helper to retrieve a pilelined engine device In a pipelined engine situation, we might either have the host which internally has support for error correction, or have it using an external hardware block for this purpose. In the former case, the host is also the ECC engine. In the latter case, it is not. In order to get the right pointers on the right devices (for example: in order to devm_* allocate variables), let's introduce this helper which can safely be called by pipelined ECC engines in order to retrieve the right device structure. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20211216111654.238086-16-miquel.raynal@bootlin.com --- include/linux/mtd/nand.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index b617efa0a881..615b3e3a3920 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -309,6 +309,7 @@ struct nand_ecc_engine *nand_ecc_get_sw_engine(struct nand_device *nand); struct nand_ecc_engine *nand_ecc_get_on_die_hw_engine(struct nand_device *nand); struct nand_ecc_engine *nand_ecc_get_on_host_hw_engine(struct nand_device *nand); void nand_ecc_put_on_host_hw_engine(struct nand_device *nand); +struct device *nand_ecc_get_engine_dev(struct device *host); #if IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING) struct nand_ecc_engine *nand_ecc_sw_hamming_get_engine(void); -- cgit v1.2.3 From 4398693a9e24bcab0b99ea219073917991d0792b Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Tue, 8 Feb 2022 11:48:31 +0100 Subject: gpiolib: make struct comments into real kernel docs We have several comments that start with '/**' but don't conform to the kernel doc standard. Add proper detailed descriptions for the affected definitions and move the docs from the forward declarations to the struct definitions where applicable. Reported-by: Randy Dunlap Signed-off-by: Bartosz Golaszewski Reviewed-by: Andy Shevchenko Tested-by: Randy Dunlap --- include/linux/gpio/consumer.h | 35 ++++++++++++++++------------------- 1 file changed, 16 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 3ad67b4a72be..c3aa8b330e1c 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -8,27 +8,16 @@ #include struct device; - -/** - * Opaque descriptor for a GPIO. These are obtained using gpiod_get() and are - * preferable to the old integer-based handles. - * - * Contrary to integers, a pointer to a gpio_desc is guaranteed to be valid - * until the GPIO is released. - */ struct gpio_desc; - -/** - * Opaque descriptor for a structure of GPIO array attributes. This structure - * is attached to struct gpiod_descs obtained from gpiod_get_array() and can be - * passed back to get/set array functions in order to activate fast processing - * path if applicable. - */ struct gpio_array; /** - * Struct containing an array of descriptors that can be obtained using - * gpiod_get_array(). + * struct gpio_descs - Struct containing an array of descriptors that can be + * obtained using gpiod_get_array() + * + * @info: Pointer to the opaque gpio_array structure + * @ndescs: Number of held descriptors + * @desc: Array of pointers to GPIO descriptors */ struct gpio_descs { struct gpio_array *info; @@ -43,8 +32,16 @@ struct gpio_descs { #define GPIOD_FLAGS_BIT_NONEXCLUSIVE BIT(4) /** - * Optional flags that can be passed to one of gpiod_* to configure direction - * and output value. These values cannot be OR'd. + * enum gpiod_flags - Optional flags that can be passed to one of gpiod_* to + * configure direction and output value. These values + * cannot be OR'd. + * + * @GPIOD_ASIS: Don't change anything + * @GPIOD_IN: Set lines to input mode + * @GPIOD_OUT_LOW: Set lines to output and drive them low + * @GPIOD_OUT_HIGH: Set lines to output and drive them high + * @GPIOD_OUT_LOW_OPEN_DRAIN: Set lines to open-drain output and drive them low + * @GPIOD_OUT_HIGH_OPEN_DRAIN: Set lines to open-drain output and drive them high */ enum gpiod_flags { GPIOD_ASIS = 0, -- cgit v1.2.3 From 8dd8678e42b5a8bbd3e2c49cda76c743318c56b0 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 5 Feb 2022 13:00:04 +0100 Subject: netfilter: ecache: don't use nf_conn spinlock For updating eache missed value we can use cmpxchg. This also avoids need to disable BH. kernel robot reported build failure on v1 because not all arches support cmpxchg for u16, so extend this to u32. This doesn't increase struct size, existing padding is used. Reported-by: kernel test robot Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_ecache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 16bcff809b18..6c4c490a3e34 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -21,10 +21,10 @@ enum nf_ct_ecache_state { struct nf_conntrack_ecache { unsigned long cache; /* bitops want long */ - u16 missed; /* missed events */ u16 ctmask; /* bitmask of ct events to be delivered */ u16 expmask; /* bitmask of expect events to be delivered */ enum nf_ct_ecache_state state:8;/* ecache state */ + u32 missed; /* missed events */ u32 portid; /* netlink portid of destroyer */ }; -- cgit v1.2.3 From 7afa38831aee2ca2f41b22747ed8545e1887aaa9 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 8 Feb 2022 12:29:47 +0100 Subject: netfilter: cttimeout: use option structure Instead of two exported functions, export a single option structure. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_timeout.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h index db507e4a65bb..3ea94f6f3844 100644 --- a/include/net/netfilter/nf_conntrack_timeout.h +++ b/include/net/netfilter/nf_conntrack_timeout.h @@ -108,8 +108,12 @@ static inline void nf_ct_destroy_timeout(struct nf_conn *ct) #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_NF_CONNTRACK_TIMEOUT -extern struct nf_ct_timeout *(*nf_ct_timeout_find_get_hook)(struct net *net, const char *name); -extern void (*nf_ct_timeout_put_hook)(struct nf_ct_timeout *timeout); +struct nf_ct_timeout_hooks { + struct nf_ct_timeout *(*timeout_find_get)(struct net *net, const char *name); + void (*timeout_put)(struct nf_ct_timeout *timeout); +}; + +extern const struct nf_ct_timeout_hooks *nf_ct_timeout_hook; #endif #endif /* _NF_CONNTRACK_TIMEOUT_H */ -- cgit v1.2.3 From 23f68d462984bfda47c7bf663dca347e8e3df549 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 7 Feb 2022 19:25:08 +0100 Subject: netfilter: nft_cmp: optimize comparison for 16-bytes Allow up to 16-byte comparisons with a new cmp fast version. Use two 64-bit words and calculate the mask representing the bits to be compared. Make sure the comparison is 64-bit aligned and avoid out-of-bound memory access on registers. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables_core.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index b6fb1fdff9b2..0ea7c55cea4d 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -42,6 +42,14 @@ struct nft_cmp_fast_expr { bool inv; }; +struct nft_cmp16_fast_expr { + struct nft_data data; + struct nft_data mask; + u8 sreg; + u8 len; + bool inv; +}; + struct nft_immediate_expr { struct nft_data data; u8 dreg; @@ -59,6 +67,7 @@ static inline u32 nft_cmp_fast_mask(unsigned int len) } extern const struct nft_expr_ops nft_cmp_fast_ops; +extern const struct nft_expr_ops nft_cmp16_fast_ops; struct nft_payload { enum nft_payload_bases base:8; -- cgit v1.2.3 From 8069b22d656f6e1922352bff90ab78e6fab73779 Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Wed, 9 Feb 2022 12:05:55 +0800 Subject: mctp: Add helper for address match checking Currently, we have a couple of paths that check that an EID matches, or the match value is MCTP_ADDR_ANY. Rather than open coding this, add a little helper. Signed-off-by: Jeremy Kerr Signed-off-by: David S. Miller --- include/net/mctp.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/mctp.h b/include/net/mctp.h index 7e35ec79b909..706d329dd8e8 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -45,6 +45,11 @@ static inline bool mctp_address_ok(mctp_eid_t eid) return eid >= 8 && eid < 255; } +static inline bool mctp_address_matches(mctp_eid_t match, mctp_eid_t eid) +{ + return match == eid || match == MCTP_ADDR_ANY; +} + static inline struct mctp_hdr *mctp_hdr(struct sk_buff *skb) { return (struct mctp_hdr *)skb_network_header(skb); -- cgit v1.2.3 From 63ed1aab3d40aa61aaa66819bdce9377ac7f40fa Mon Sep 17 00:00:00 2001 From: Matt Johnston Date: Wed, 9 Feb 2022 12:05:57 +0800 Subject: mctp: Add SIOCMCTP{ALLOC,DROP}TAG ioctls for tag control This change adds a couple of new ioctls for mctp sockets: SIOCMCTPALLOCTAG and SIOCMCTPDROPTAG. These ioctls provide facilities for explicit allocation / release of tags, overriding the automatic allocate-on-send/release-on-reply and timeout behaviours. This allows userspace more control over messages that may not fit a simple request/response model. In order to indicate a pre-allocated tag to the sendmsg() syscall, we introduce a new flag to the struct sockaddr_mctp.smctp_tag value: MCTP_TAG_PREALLOC. Additional changes from Jeremy Kerr . Contains a fix that was: Reported-by: kernel test robot Signed-off-by: Matt Johnston Signed-off-by: Jeremy Kerr Signed-off-by: David S. Miller --- include/net/mctp.h | 11 ++++++++++- include/trace/events/mctp.h | 5 ++++- include/uapi/linux/mctp.h | 18 ++++++++++++++++++ 3 files changed, 32 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/mctp.h b/include/net/mctp.h index 706d329dd8e8..e80a4baf8379 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -126,7 +126,7 @@ struct mctp_sock { */ struct mctp_sk_key { mctp_eid_t peer_addr; - mctp_eid_t local_addr; + mctp_eid_t local_addr; /* MCTP_ADDR_ANY for local owned tags */ __u8 tag; /* incoming tag match; invert TO for local */ /* we hold a ref to sk when set */ @@ -163,6 +163,12 @@ struct mctp_sk_key { */ unsigned long dev_flow_state; struct mctp_dev *dev; + + /* a tag allocated with SIOCMCTPALLOCTAG ioctl will not expire + * automatically on timeout or response, instead SIOCMCTPDROPTAG + * is used. + */ + bool manual_alloc; }; struct mctp_skb_cb { @@ -239,6 +245,9 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, struct sk_buff *skb, mctp_eid_t daddr, u8 req_tag); void mctp_key_unref(struct mctp_sk_key *key); +struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk, + mctp_eid_t daddr, mctp_eid_t saddr, + bool manual, u8 *tagp); /* routing <--> device interface */ unsigned int mctp_default_net(struct net *net); diff --git a/include/trace/events/mctp.h b/include/trace/events/mctp.h index 175b057c507f..165cf25f77a7 100644 --- a/include/trace/events/mctp.h +++ b/include/trace/events/mctp.h @@ -15,6 +15,7 @@ enum { MCTP_TRACE_KEY_REPLIED, MCTP_TRACE_KEY_INVALIDATED, MCTP_TRACE_KEY_CLOSED, + MCTP_TRACE_KEY_DROPPED, }; #endif /* __TRACE_MCTP_ENUMS */ @@ -22,6 +23,7 @@ TRACE_DEFINE_ENUM(MCTP_TRACE_KEY_TIMEOUT); TRACE_DEFINE_ENUM(MCTP_TRACE_KEY_REPLIED); TRACE_DEFINE_ENUM(MCTP_TRACE_KEY_INVALIDATED); TRACE_DEFINE_ENUM(MCTP_TRACE_KEY_CLOSED); +TRACE_DEFINE_ENUM(MCTP_TRACE_KEY_DROPPED); TRACE_EVENT(mctp_key_acquire, TP_PROTO(const struct mctp_sk_key *key), @@ -66,7 +68,8 @@ TRACE_EVENT(mctp_key_release, { MCTP_TRACE_KEY_TIMEOUT, "timeout" }, { MCTP_TRACE_KEY_REPLIED, "replied" }, { MCTP_TRACE_KEY_INVALIDATED, "invalidated" }, - { MCTP_TRACE_KEY_CLOSED, "closed" }) + { MCTP_TRACE_KEY_CLOSED, "closed" }, + { MCTP_TRACE_KEY_DROPPED, "dropped" }) ) ); diff --git a/include/uapi/linux/mctp.h b/include/uapi/linux/mctp.h index 07b0318716fc..154ab56651f1 100644 --- a/include/uapi/linux/mctp.h +++ b/include/uapi/linux/mctp.h @@ -44,7 +44,25 @@ struct sockaddr_mctp_ext { #define MCTP_TAG_MASK 0x07 #define MCTP_TAG_OWNER 0x08 +#define MCTP_TAG_PREALLOC 0x10 #define MCTP_OPT_ADDR_EXT 1 +#define SIOCMCTPALLOCTAG (SIOCPROTOPRIVATE + 0) +#define SIOCMCTPDROPTAG (SIOCPROTOPRIVATE + 1) + +struct mctp_ioc_tag_ctl { + mctp_eid_t peer_addr; + + /* For SIOCMCTPALLOCTAG: must be passed as zero, kernel will + * populate with the allocated tag value. Returned tag value will + * always have TO and PREALLOC set. + * + * For SIOCMCTPDROPTAG: userspace provides tag value to drop, from + * a prior SIOCMCTPALLOCTAG call (and so must have TO and PREALLOC set). + */ + __u8 tag; + __u16 flags; +}; + #endif /* __UAPI_MCTP_H */ -- cgit v1.2.3 From a0386bba70934d42f586eaf68b21d5eeaffa7bd0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 23 Jan 2022 18:52:01 +0100 Subject: spi: make remove callback a void function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The value returned by an spi driver's remove function is mostly ignored. (Only an error message is printed if the value is non-zero that the error is ignored.) So change the prototype of the remove function to return no value. This way driver authors are not tempted to assume that passing an error to the upper layer is a good idea. All drivers are adapted accordingly. There is no intended change of behaviour, all callbacks were prepared to return 0 before. Signed-off-by: Uwe Kleine-König Acked-by: Marc Kleine-Budde Acked-by: Andy Shevchenko Reviewed-by: Geert Uytterhoeven Acked-by: Jérôme Pouiller Acked-by: Miquel Raynal Acked-by: Jonathan Cameron Acked-by: Claudius Heine Acked-by: Stefan Schmidt Acked-by: Alexandre Belloni Acked-by: Ulf Hansson # For MMC Acked-by: Marcus Folkesson Acked-by: Łukasz Stelmach Acked-by: Lee Jones Link: https://lore.kernel.org/r/20220123175201.34839-6-u.kleine-koenig@pengutronix.de Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 7ab3fed7b804..c84e61b99c7b 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -280,7 +280,7 @@ struct spi_message; struct spi_driver { const struct spi_device_id *id_table; int (*probe)(struct spi_device *spi); - int (*remove)(struct spi_device *spi); + void (*remove)(struct spi_device *spi); void (*shutdown)(struct spi_device *spi); struct device_driver driver; }; -- cgit v1.2.3 From 1f8863bfb5ca500ea1c7669b16b1931ba27fce20 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 1 Feb 2022 12:02:59 +0000 Subject: genirq: Allow the PM device to originate from irq domain As a preparation to moving the reference to the device used for runtime power management, add a new 'dev' field to the irqdomain structure for that exact purpose. The irq_chip_pm_{get,put}() helpers are made aware of the dual location via a new private helper. No functional change intended. Signed-off-by: Marc Zyngier Reviewed-by: Geert Uytterhoeven Tested-by: Geert Uytterhoeven Tested-by: Tony Lindgren Acked-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20220201120310.878267-2-maz@kernel.org --- include/linux/irqdomain.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index d476405802e9..be25a33293e5 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -151,6 +151,8 @@ struct irq_domain_chip_generic; * @gc: Pointer to a list of generic chips. There is a helper function for * setting up one or more generic chips for interrupt controllers * drivers using the generic chip library which uses this pointer. + * @dev: Pointer to a device that the domain represent, and that will be + * used for power management purposes. * @parent: Pointer to parent irq_domain to support hierarchy irq_domains * * Revmap data, used internally by irq_domain @@ -171,6 +173,7 @@ struct irq_domain { struct fwnode_handle *fwnode; enum irq_domain_bus_token bus_token; struct irq_domain_chip_generic *gc; + struct device *dev; #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY struct irq_domain *parent; #endif @@ -226,6 +229,13 @@ static inline struct device_node *irq_domain_get_of_node(struct irq_domain *d) return to_of_node(d->fwnode); } +static inline void irq_domain_set_pm_device(struct irq_domain *d, + struct device *dev) +{ + if (d) + d->dev = dev; +} + #ifdef CONFIG_IRQ_DOMAIN struct fwnode_handle *__irq_domain_alloc_fwnode(unsigned int type, int id, const char *name, phys_addr_t *pa); -- cgit v1.2.3 From 9a69e2b385f443f244a7e8b8bcafe5ccfb0866b4 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Wed, 9 Feb 2022 19:43:32 +0100 Subject: bpf: Make remote_port field in struct bpf_sk_lookup 16-bit wide remote_port is another case of a BPF context field documented as a 32-bit value in network byte order for which the BPF context access converter generates a load of a zero-padded 16-bit integer in network byte order. First such case was dst_port in bpf_sock which got addressed in commit 4421a582718a ("bpf: Make dst_port field in struct bpf_sock 16-bit wide"). Loading 4-bytes from the remote_port offset and converting the value with bpf_ntohl() leads to surprising results, as the expected value is shifted by 16 bits. Reduce the confusion by splitting the field in two - a 16-bit field holding a big-endian integer, and a 16-bit zero-padding anonymous field that follows it. Suggested-by: Alexei Starovoitov Signed-off-by: Jakub Sitnicki Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220209184333.654927-2-jakub@cloudflare.com --- include/uapi/linux/bpf.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a7f0ddedac1f..afe3d0d7f5f2 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6453,7 +6453,8 @@ struct bpf_sk_lookup { __u32 protocol; /* IP protocol (IPPROTO_TCP, IPPROTO_UDP) */ __u32 remote_ip4; /* Network byte order */ __u32 remote_ip6[4]; /* Network byte order */ - __u32 remote_port; /* Network byte order */ + __be16 remote_port; /* Network byte order */ + __u16 :16; /* Zero padding */ __u32 local_ip4; /* Network byte order */ __u32 local_ip6[4]; /* Network byte order */ __u32 local_port; /* Host byte order */ -- cgit v1.2.3 From 5bdd3eb253544b1e80f904e1205699d0a126d2d6 Mon Sep 17 00:00:00 2001 From: Mukul Joshi Date: Fri, 4 Feb 2022 11:58:32 -0500 Subject: drm/amdkfd: Remove unused old debugger implementation Cleanup the kfd code by removing the unused old debugger implementation. The address watch was only ever implemented in the upstream driver for GFXv7 (Kaveri). The user mode tools runtime using this API was never open-sourced. Work on the old debugger prototype that used this API has been discontinued years ago. Only a small piece of resetting wavefronts is kept and is moved to kfd_device_queue_manager.c. Signed-off-by: Mukul Joshi Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index e6a56c146920..6e4268f5e482 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -756,16 +756,16 @@ struct kfd_ioctl_set_xnack_mode_args { #define AMDKFD_IOC_WAIT_EVENTS \ AMDKFD_IOWR(0x0C, struct kfd_ioctl_wait_events_args) -#define AMDKFD_IOC_DBG_REGISTER \ +#define AMDKFD_IOC_DBG_REGISTER_DEPRECATED \ AMDKFD_IOW(0x0D, struct kfd_ioctl_dbg_register_args) -#define AMDKFD_IOC_DBG_UNREGISTER \ +#define AMDKFD_IOC_DBG_UNREGISTER_DEPRECATED \ AMDKFD_IOW(0x0E, struct kfd_ioctl_dbg_unregister_args) -#define AMDKFD_IOC_DBG_ADDRESS_WATCH \ +#define AMDKFD_IOC_DBG_ADDRESS_WATCH_DEPRECATED \ AMDKFD_IOW(0x0F, struct kfd_ioctl_dbg_address_watch_args) -#define AMDKFD_IOC_DBG_WAVE_CONTROL \ +#define AMDKFD_IOC_DBG_WAVE_CONTROL_DEPRECATED \ AMDKFD_IOW(0x10, struct kfd_ioctl_dbg_wave_control_args) #define AMDKFD_IOC_SET_SCRATCH_BACKING_VA \ -- cgit v1.2.3 From 5cad527d5ffa9a1c4731bb9c97d2ee93f8960d50 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Wed, 9 Feb 2022 14:08:38 +0800 Subject: net: drop_monitor: support drop reason In the commit c504e5c2f964 ("net: skb: introduce kfree_skb_reason()") drop reason is introduced to the tracepoint of kfree_skb. Therefore, drop_monitor is able to report the drop reason to users by netlink. The drop reasons are reported as string to users, which is exactly the same as what we do when reporting it to ftrace. Signed-off-by: Menglong Dong Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20220209060838.55513-1-imagedong@tencent.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/net_dropmon.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/net_dropmon.h b/include/uapi/linux/net_dropmon.h index 66048cc5d7b3..1bbea8f0681e 100644 --- a/include/uapi/linux/net_dropmon.h +++ b/include/uapi/linux/net_dropmon.h @@ -93,6 +93,7 @@ enum net_dm_attr { NET_DM_ATTR_SW_DROPS, /* flag */ NET_DM_ATTR_HW_DROPS, /* flag */ NET_DM_ATTR_FLOW_ACTION_COOKIE, /* binary */ + NET_DM_ATTR_REASON, /* string */ __NET_DM_ATTR_MAX, NET_DM_ATTR_MAX = __NET_DM_ATTR_MAX - 1 -- cgit v1.2.3 From 70e038f89b467995708207fb57bbf46aec32dc2c Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 16 Dec 2021 12:16:42 +0100 Subject: mtd: nand: mxic-ecc: Support SPI pipelined mode Introduce the support for another possible configuration: the ECC engine may work as DMA master (pipelined) and move itself the data to/from the NAND chip into the buffer, applying the necessary corrections/computations on the fly. This driver offers an ECC engine implementation that must be instatiated from a SPI controller driver. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20211216111654.238086-17-miquel.raynal@bootlin.com --- include/linux/mtd/nand-ecc-mxic.h | 49 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) create mode 100644 include/linux/mtd/nand-ecc-mxic.h (limited to 'include') diff --git a/include/linux/mtd/nand-ecc-mxic.h b/include/linux/mtd/nand-ecc-mxic.h new file mode 100644 index 000000000000..f3aa1ac82aed --- /dev/null +++ b/include/linux/mtd/nand-ecc-mxic.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright © 2019 Macronix + * Author: Miquèl Raynal + * + * Header for the Macronix external ECC engine. + */ + +#ifndef __MTD_NAND_ECC_MXIC_H__ +#define __MTD_NAND_ECC_MXIC_H__ + +#include +#include + +struct mxic_ecc_engine; + +#if IS_ENABLED(CONFIG_MTD_NAND_ECC_MXIC) + +struct nand_ecc_engine_ops *mxic_ecc_get_pipelined_ops(void); +struct nand_ecc_engine *mxic_ecc_get_pipelined_engine(struct platform_device *spi_pdev); +void mxic_ecc_put_pipelined_engine(struct nand_ecc_engine *eng); +int mxic_ecc_process_data_pipelined(struct nand_ecc_engine *eng, + unsigned int direction, dma_addr_t dirmap); + +#else /* !CONFIG_MTD_NAND_ECC_MXIC */ + +static inline struct nand_ecc_engine_ops *mxic_ecc_get_pipelined_ops(void) +{ + return NULL; +} + +static inline struct nand_ecc_engine * +mxic_ecc_get_pipelined_engine(struct platform_device *spi_pdev) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void mxic_ecc_put_pipelined_engine(struct nand_ecc_engine *eng) {} + +static inline int mxic_ecc_process_data_pipelined(struct nand_ecc_engine *eng, + unsigned int direction, + dma_addr_t dirmap) +{ + return -EOPNOTSUPP; +} + +#endif /* CONFIG_MTD_NAND_ECC_MXIC */ + +#endif /* __MTD_NAND_ECC_MXIC_H__ */ -- cgit v1.2.3 From 4a3cc7fb6e63bcfdedec25364738f1493345bd20 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 27 Jan 2022 10:17:56 +0100 Subject: spi: spi-mem: Introduce a capability structure Create a spi_controller_mem_caps structure and put it within the spi_controller structure close to the spi_controller_mem_ops strucure. So far the only field in this structure is the support for dtr operations, but soon we will add another parameter. Also create a helper to parse the capabilities and check if the requested capability has been set or not. Signed-off-by: Miquel Raynal Reviewed-by: Pratyush Yadav Reviewed-by: Boris Brezillon Reviewed-by: Tudor Ambarus Reviewed-by: Mark Brown Link: https://lore.kernel.org/linux-mtd/20220127091808.1043392-2-miquel.raynal@bootlin.com --- include/linux/spi/spi-mem.h | 11 +++++++++++ include/linux/spi/spi.h | 3 +++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 85e2ff7b840d..38e5d45c9842 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -285,6 +285,17 @@ struct spi_controller_mem_ops { unsigned long timeout_ms); }; +/** + * struct spi_controller_mem_caps - SPI memory controller capabilities + * @dtr: Supports DTR operations + */ +struct spi_controller_mem_caps { + bool dtr; +}; + +#define spi_mem_controller_is_capable(ctlr, cap) \ + ((ctlr)->mem_caps && (ctlr)->mem_caps->cap) + /** * struct spi_mem_driver - SPI memory driver * @spidrv: inherit from a SPI driver diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 7ab3fed7b804..cf99a1ee0e74 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -23,6 +23,7 @@ struct ptp_system_timestamp; struct spi_controller; struct spi_transfer; struct spi_controller_mem_ops; +struct spi_controller_mem_caps; /* * INTERFACES between SPI master-side drivers and SPI slave protocol handlers, @@ -415,6 +416,7 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @mem_ops: optimized/dedicated operations for interactions with SPI memory. * This field is optional and should only be implemented if the * controller has native support for memory like operations. + * @mem_caps: controller capabilities for the handling of memory operations. * @unprepare_message: undo any work done by prepare_message(). * @slave_abort: abort the ongoing transfer request on an SPI slave controller * @cs_gpios: LEGACY: array of GPIO descs to use as chip select lines; one per @@ -639,6 +641,7 @@ struct spi_controller { /* Optimized handlers for SPI memory-like operations. */ const struct spi_controller_mem_ops *mem_ops; + const struct spi_controller_mem_caps *mem_caps; /* gpio chip select */ int *cs_gpios; -- cgit v1.2.3 From 9a15efc5d5e6b5beaed0883e5bdcd0b1384c1b20 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 27 Jan 2022 10:18:00 +0100 Subject: spi: spi-mem: Kill the spi_mem_dtr_supports_op() helper Now that spi_mem_default_supports_op() has access to the static controller capabilities (relating to memory operations), and now that these capabilities have been filled by the relevant controllers, there is no need for a specific helper checking only DTR operations, so let's just kill spi_mem_dtr_supports_op() and simply use spi_mem_default_supports_op() instead. Signed-off-by: Miquel Raynal Reviewed-by: Pratyush Yadav Reviewed-by: Boris Brezillon Reviewed-by: Tudor Ambarus Link: https://lore.kernel.org/linux-mtd/20220127091808.1043392-6-miquel.raynal@bootlin.com --- include/linux/spi/spi-mem.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 38e5d45c9842..4a1bfe689872 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -330,10 +330,6 @@ void spi_controller_dma_unmap_mem_op_data(struct spi_controller *ctlr, bool spi_mem_default_supports_op(struct spi_mem *mem, const struct spi_mem_op *op); - -bool spi_mem_dtr_supports_op(struct spi_mem *mem, - const struct spi_mem_op *op); - #else static inline int spi_controller_dma_map_mem_op_data(struct spi_controller *ctlr, @@ -356,13 +352,6 @@ bool spi_mem_default_supports_op(struct spi_mem *mem, { return false; } - -static inline -bool spi_mem_dtr_supports_op(struct spi_mem *mem, - const struct spi_mem_op *op) -{ - return false; -} #endif /* CONFIG_SPI_MEM */ int spi_mem_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op); -- cgit v1.2.3 From a433c2cbd75ab76f277364f44e76f32c7df306e7 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 27 Jan 2022 10:18:01 +0100 Subject: spi: spi-mem: Add an ecc parameter to the spi_mem_op structure Soon the SPI-NAND core will need a way to request a SPI controller to enable ECC support for a given operation. This is because of the pipelined integration of certain ECC engines, which are directly managed by the SPI controller itself. Introduce a spi_mem_op additional field for this purpose: ecc. So far this field is left unset and checked to be false by all the SPI controller drivers in their ->supports_op() hook, as they all call spi_mem_default_supports_op(). Signed-off-by: Miquel Raynal Acked-by: Pratyush Yadav Reviewed-by: Boris Brezillon Reviewed-by: Tudor Ambarus Link: https://lore.kernel.org/linux-mtd/20220127091808.1043392-7-miquel.raynal@bootlin.com --- include/linux/spi/spi-mem.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 4a1bfe689872..2ba044d0d5e5 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -89,6 +89,7 @@ enum spi_mem_data_dir { * @dummy.dtr: whether the dummy bytes should be sent in DTR mode or not * @data.buswidth: number of IO lanes used to send/receive the data * @data.dtr: whether the data should be sent in DTR mode or not + * @data.ecc: whether error correction is required or not * @data.dir: direction of the transfer * @data.nbytes: number of data bytes to send/receive. Can be zero if the * operation does not involve transferring data @@ -119,6 +120,7 @@ struct spi_mem_op { struct { u8 buswidth; u8 dtr : 1; + u8 ecc : 1; enum spi_mem_data_dir dir; unsigned int nbytes; union { @@ -288,9 +290,11 @@ struct spi_controller_mem_ops { /** * struct spi_controller_mem_caps - SPI memory controller capabilities * @dtr: Supports DTR operations + * @ecc: Supports operations with error correction */ struct spi_controller_mem_caps { bool dtr; + bool ecc; }; #define spi_mem_controller_is_capable(ctlr, cap) \ -- cgit v1.2.3 From f9d7c7265bcff7d9a17425a8cddf702e8fe159c2 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 27 Jan 2022 10:18:03 +0100 Subject: mtd: spinand: Create direct mapping descriptors for ECC operations In order for pipelined ECC engines to be able to enable/disable the ECC engine only when needed and avoid races when future parallel-operations will be supported, we need to provide the information about the use of the ECC engine in the direct mapping hooks. As direct mapping configurations are meant to be static, it is best to create two new mappings: one for regular 'raw' accesses and one for accesses involving correction. It is up to the driver to use or not the new ECC enable boolean contained in the spi-mem operation. As dirmaps are not free (they consume a few pages of MMIO address space) and because these extra entries are only meant to be used by pipelined engines, let's limit their use to this specific type of engine and save a bit of memory with all the other setups. Signed-off-by: Miquel Raynal Reviewed-by: Boris Brezillon Link: https://lore.kernel.org/linux-mtd/20220127091808.1043392-9-miquel.raynal@bootlin.com --- include/linux/mtd/spinand.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 6988956b8492..3aa28240a77f 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -389,6 +389,8 @@ struct spinand_info { struct spinand_dirmap { struct spi_mem_dirmap_desc *wdesc; struct spi_mem_dirmap_desc *rdesc; + struct spi_mem_dirmap_desc *wdesc_ecc; + struct spi_mem_dirmap_desc *rdesc_ecc; }; /** -- cgit v1.2.3 From 00360ebae483e603d55ec9a7231b787cb80ffe13 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 2 Feb 2022 15:45:36 +0100 Subject: spi: mxic: Add support for pipelined ECC operations Some SPI-NAND chips do not have a proper on-die ECC engine providing error correction/detection. This is particularly an issue on embedded devices with limited resources because all the computations must happen in software, unless an external hardware engine is provided. These external engines are new and can be of two categories: external or pipelined. Macronix is providing both, the former being already supported. The second, however, is very SoC implementation dependent and must be instantiated by the SPI host controller directly. An entire subsystem has been contributed to support these engines which makes the insertion into another subsystem such as SPI quite straightforward without the need for a lot of specific functions. Signed-off-by: Miquel Raynal Reviewed-by: Mark Brown Link: https://lore.kernel.org/linux-mtd/20220202144536.393792-1-miquel.raynal@bootlin.com --- include/linux/mtd/nand-ecc-mxic.h | 2 +- include/linux/mtd/nand.h | 15 +++++++++++++++ 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mtd/nand-ecc-mxic.h b/include/linux/mtd/nand-ecc-mxic.h index f3aa1ac82aed..b125926e458c 100644 --- a/include/linux/mtd/nand-ecc-mxic.h +++ b/include/linux/mtd/nand-ecc-mxic.h @@ -14,7 +14,7 @@ struct mxic_ecc_engine; -#if IS_ENABLED(CONFIG_MTD_NAND_ECC_MXIC) +#if IS_ENABLED(CONFIG_MTD_NAND_ECC_MXIC) && IS_REACHABLE(CONFIG_MTD_NAND_CORE) struct nand_ecc_engine_ops *mxic_ecc_get_pipelined_ops(void); struct nand_ecc_engine *mxic_ecc_get_pipelined_engine(struct platform_device *spi_pdev); diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 615b3e3a3920..c3693bb87b4c 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -303,8 +303,23 @@ int nand_ecc_prepare_io_req(struct nand_device *nand, int nand_ecc_finish_io_req(struct nand_device *nand, struct nand_page_io_req *req); bool nand_ecc_is_strong_enough(struct nand_device *nand); + +#if IS_REACHABLE(CONFIG_MTD_NAND_CORE) int nand_ecc_register_on_host_hw_engine(struct nand_ecc_engine *engine); int nand_ecc_unregister_on_host_hw_engine(struct nand_ecc_engine *engine); +#else +static inline int +nand_ecc_register_on_host_hw_engine(struct nand_ecc_engine *engine) +{ + return -ENOTSUPP; +} +static inline int +nand_ecc_unregister_on_host_hw_engine(struct nand_ecc_engine *engine) +{ + return -ENOTSUPP; +} +#endif + struct nand_ecc_engine *nand_ecc_get_sw_engine(struct nand_device *nand); struct nand_ecc_engine *nand_ecc_get_on_die_hw_engine(struct nand_device *nand); struct nand_ecc_engine *nand_ecc_get_on_host_hw_engine(struct nand_device *nand); -- cgit v1.2.3 From beb0622138cd2848dec06b0651a988c39d099574 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 1 Feb 2022 12:03:10 +0000 Subject: genirq: Kill irq_chip::parent_device Now that noone is using irq_chip::parent_device in the tree, get rid of it. Signed-off-by: Marc Zyngier Acked-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20220201120310.878267-13-maz@kernel.org --- include/linux/irq.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index 848e1e12c5c6..2cb2e2ac2703 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -456,7 +456,6 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) /** * struct irq_chip - hardware interrupt chip descriptor * - * @parent_device: pointer to parent device for irqchip * @name: name for /proc/interrupts * @irq_startup: start up the interrupt (defaults to ->enable if NULL) * @irq_shutdown: shut down the interrupt (defaults to ->disable if NULL) @@ -503,7 +502,6 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) * @flags: chip specific flags */ struct irq_chip { - struct device *parent_device; const char *name; unsigned int (*irq_startup)(struct irq_data *data); void (*irq_shutdown)(struct irq_data *data); -- cgit v1.2.3 From 731cddce6dd110fb2cdee34eddb48599e7251517 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 1 Feb 2022 19:06:27 +0100 Subject: net: mac802154: Convert the symbol duration into nanoseconds Tdsym is often given in the spec as pretty small numbers in microseconds and hence was reflected in the code as symbol_duration and was stored as a u8. Actually, for UWB PHYs, the symbol duration is given in nanoseconds and are as precise as picoseconds. In order to handle better these PHYs, change the type of symbol_duration to u32 and store this value in nanoseconds. All the users of this variable are updated in a mechanical way. Signed-off-by: Miquel Raynal Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20220201180629.93410-3-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt --- include/net/cfg802154.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 833672d6fbe4..92d4f178caca 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -203,8 +203,8 @@ struct wpan_phy { /* PHY depended MAC PIB values */ - /* 802.15.4 acronym: Tdsym in usec */ - u8 symbol_duration; + /* 802.15.4 acronym: Tdsym in nsec */ + u32 symbol_duration; /* lifs and sifs periods timing */ u16 lifs_period; u16 sifs_period; -- cgit v1.2.3 From 781830c800ddd19566846c634de09fadf37eafde Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 1 Feb 2022 19:06:28 +0100 Subject: net: mac802154: Set durations automatically As depicted in the IEEE 802.15.4 specification, modulation/bands are tight to a number of page/channels so we can for most of them derive the durations automatically. The two locations that must call this new helper to set the variou symbol durations are: - when manually requesting a channel change though the netlink interface - at PHY creation, once the device driver has set the default page/channel If an information is missing, the symbol duration is not touched, a debug message is eventually printed. This keeps the compatibility with the unconverted drivers for which it was too complicated for me to find their precise information. If they initially provided a symbol duration, it would be kept. If they don't, the symbol duration value is left untouched. Once the symbol duration derived, the lifs and sifs durations are updated as well. Signed-off-by: Miquel Raynal Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20220201180629.93410-4-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt --- include/net/cfg802154.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 92d4f178caca..85f9e8417688 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -415,4 +415,6 @@ static inline const char *wpan_phy_name(struct wpan_phy *phy) return dev_name(&phy->dev); } +void ieee802154_configure_durations(struct wpan_phy *phy); + #endif /* __NET_CFG802154_H */ -- cgit v1.2.3 From 5fdc1242453e2ae88b2cdb607e4eda6b687f084c Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Thu, 10 Feb 2022 17:05:18 +0200 Subject: ASoC: SOF: Move the definition of enum sof_dsp_power_states to global header Move the enum sof_dsp_power_states to include/sound/sof.h to be accessible outside of the core SOF stack. Signed-off-by: Peter Ujfalusi Reviewed-by: Kai Vehmanen Reviewed-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Link: https://lore.kernel.org/r/20220210150525.30756-3-peter.ujfalusi@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/sound/sof.h b/include/sound/sof.h index 813680ab9aad..7cdfc954df12 100644 --- a/include/sound/sof.h +++ b/include/sound/sof.h @@ -39,6 +39,14 @@ enum sof_fw_state { SOF_FW_CRASHED, }; +/* DSP power states */ +enum sof_dsp_power_states { + SOF_DSP_PM_D0, + SOF_DSP_PM_D1, + SOF_DSP_PM_D2, + SOF_DSP_PM_D3, +}; + /* * SOF Platform data. */ -- cgit v1.2.3 From ede6c39c4f9068cbeb4036448c45fff5393e0432 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 9 Feb 2022 18:59:32 -0800 Subject: net: make net->dev_unreg_count atomic Having to acquire rtnl from netdev_run_todo() for every dismantled device is not desirable when/if rtnl is under stress. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/net_namespace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 374cc7b260fc..c4f5601f6e32 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -63,7 +63,7 @@ struct net { */ spinlock_t rules_mod_lock; - unsigned int dev_unreg_count; + atomic_t dev_unreg_count; unsigned int dev_base_seq; /* protected by rtnl_mutex */ int ifindex; -- cgit v1.2.3 From bd1ba5732bb954c31e2be07e8ee1397a910835e4 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 7 Dec 2021 22:09:20 +0000 Subject: KVM: x86: Get the number of Hyper-V sparse banks from the VARHEAD field Get the number of sparse banks from the VARHEAD field, which the guest is required to provide as "The size of a variable header, in QWORDS.", where the variable header is: Variable Header Bytes = {Total Header Bytes - sizeof(Fixed Header)} rounded up to nearest multiple of 8 Variable HeaderSize = Variable Header Bytes / 8 In other words, the VARHEAD should match the number of sparse banks. Keep the manual count as a sanity check, but otherwise rely on the field so as to more closely align with the logic defined in the TLFS and to allow for future cleanups. Tweak the tracepoint output to use "rep_cnt" instead of simply "cnt" now that there is also "var_cnt". Signed-off-by: Sean Christopherson Reviewed-by: Vitaly Kuznetsov Message-Id: <20211207220926.718794-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- include/asm-generic/hyperv-tlfs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h index 8f97c2927bee..b8babc4d3fe4 100644 --- a/include/asm-generic/hyperv-tlfs.h +++ b/include/asm-generic/hyperv-tlfs.h @@ -183,6 +183,7 @@ enum HV_GENERIC_SET_FORMAT { #define HV_HYPERCALL_RESULT_MASK GENMASK_ULL(15, 0) #define HV_HYPERCALL_FAST_BIT BIT(16) #define HV_HYPERCALL_VARHEAD_OFFSET 17 +#define HV_HYPERCALL_VARHEAD_MASK GENMASK_ULL(26, 17) #define HV_HYPERCALL_REP_COMP_OFFSET 32 #define HV_HYPERCALL_REP_COMP_1 BIT_ULL(32) #define HV_HYPERCALL_REP_COMP_MASK GENMASK_ULL(43, 32) -- cgit v1.2.3 From 413af6601f7613c07d8c36b57e184d7841ace43a Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 7 Dec 2021 22:09:26 +0000 Subject: KVM: x86: Add checks for reserved-to-zero Hyper-V hypercall fields Add checks for the three fields in Hyper-V's hypercall params that must be zero. Per the TLFS, HV_STATUS_INVALID_HYPERCALL_INPUT is returned if "A reserved bit in the specified hypercall input value is non-zero." Note, some versions of the TLFS have an off-by-one bug for the last reserved field, and define it as being bits 64:60. See https://github.com/MicrosoftDocs/Virtualization-Documentation/pull/1682. Signed-off-by: Sean Christopherson Reviewed-by: Vitaly Kuznetsov Message-Id: <20211207220926.718794-9-seanjc@google.com> Signed-off-by: Paolo Bonzini --- include/asm-generic/hyperv-tlfs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h index b8babc4d3fe4..fdce7a4cfc6f 100644 --- a/include/asm-generic/hyperv-tlfs.h +++ b/include/asm-generic/hyperv-tlfs.h @@ -184,11 +184,17 @@ enum HV_GENERIC_SET_FORMAT { #define HV_HYPERCALL_FAST_BIT BIT(16) #define HV_HYPERCALL_VARHEAD_OFFSET 17 #define HV_HYPERCALL_VARHEAD_MASK GENMASK_ULL(26, 17) +#define HV_HYPERCALL_RSVD0_MASK GENMASK_ULL(31, 27) #define HV_HYPERCALL_REP_COMP_OFFSET 32 #define HV_HYPERCALL_REP_COMP_1 BIT_ULL(32) #define HV_HYPERCALL_REP_COMP_MASK GENMASK_ULL(43, 32) +#define HV_HYPERCALL_RSVD1_MASK GENMASK_ULL(47, 44) #define HV_HYPERCALL_REP_START_OFFSET 48 #define HV_HYPERCALL_REP_START_MASK GENMASK_ULL(59, 48) +#define HV_HYPERCALL_RSVD2_MASK GENMASK_ULL(63, 60) +#define HV_HYPERCALL_RSVD_MASK (HV_HYPERCALL_RSVD0_MASK | \ + HV_HYPERCALL_RSVD1_MASK | \ + HV_HYPERCALL_RSVD2_MASK) /* hypercall status code */ #define HV_STATUS_SUCCESS 0 -- cgit v1.2.3 From 27c196c7b73cb70bbed3a9df46563bab60e63415 Mon Sep 17 00:00:00 2001 From: Terry Bowman Date: Wed, 9 Feb 2022 11:27:09 -0600 Subject: kernel/resource: Introduce request_mem_region_muxed() Support for requesting muxed memory region is implemented but not currently callable as a macro. Add the request muxed memory region macro. MMIO memory accesses can be synchronized using request_mem_region() which is already available. This call will return failure if the resource is busy. The 'muxed' version of this macro will handle a busy resource by using a wait queue to retry until the resource is available. Signed-off-by: Terry Bowman Reviewed-by: Andy Shevchenko Signed-off-by: Wolfram Sang --- include/linux/ioport.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 8359c50f9988..ec5f71f7135b 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -262,6 +262,8 @@ resource_union(struct resource *r1, struct resource *r2, struct resource *r) #define request_muxed_region(start,n,name) __request_region(&ioport_resource, (start), (n), (name), IORESOURCE_MUXED) #define __request_mem_region(start,n,name, excl) __request_region(&iomem_resource, (start), (n), (name), excl) #define request_mem_region(start,n,name) __request_region(&iomem_resource, (start), (n), (name), 0) +#define request_mem_region_muxed(start, n, name) \ + __request_region(&iomem_resource, (start), (n), (name), IORESOURCE_MUXED) #define request_mem_region_exclusive(start,n,name) \ __request_region(&iomem_resource, (start), (n), (name), IORESOURCE_EXCLUSIVE) #define rename_region(region, newname) do { (region)->name = (newname); } while (0) -- cgit v1.2.3 From 85cedb4e0c9d3b08c28e164e592b3a329e3dd5fa Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Wed, 9 Feb 2022 19:45:07 +0100 Subject: dt-bindings: clock: Add qualcomm QCM2290 DISPCC bindings Add device tree bindings for display clock controller on QCM2290 SoCs. Signed-off-by: Loic Poulain Reviewed-by: Bjorn Andersson Reviewed-by: Rob Herring Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/1644432308-21099-1-git-send-email-loic.poulain@linaro.org --- include/dt-bindings/clock/qcom,dispcc-qcm2290.h | 34 +++++++++++++++++++++++++ 1 file changed, 34 insertions(+) create mode 100644 include/dt-bindings/clock/qcom,dispcc-qcm2290.h (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,dispcc-qcm2290.h b/include/dt-bindings/clock/qcom,dispcc-qcm2290.h new file mode 100644 index 000000000000..1db513d6b3ee --- /dev/null +++ b/include/dt-bindings/clock/qcom,dispcc-qcm2290.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2019, The Linux Foundation. All rights reserved. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_DISP_CC_QCM2290_H +#define _DT_BINDINGS_CLK_QCOM_DISP_CC_QCM2290_H + +/* DISP_CC clocks */ +#define DISP_CC_PLL0 0 +#define DISP_CC_MDSS_AHB_CLK 1 +#define DISP_CC_MDSS_AHB_CLK_SRC 2 +#define DISP_CC_MDSS_BYTE0_CLK 3 +#define DISP_CC_MDSS_BYTE0_CLK_SRC 4 +#define DISP_CC_MDSS_BYTE0_DIV_CLK_SRC 5 +#define DISP_CC_MDSS_BYTE0_INTF_CLK 6 +#define DISP_CC_MDSS_ESC0_CLK 7 +#define DISP_CC_MDSS_ESC0_CLK_SRC 8 +#define DISP_CC_MDSS_MDP_CLK 9 +#define DISP_CC_MDSS_MDP_CLK_SRC 10 +#define DISP_CC_MDSS_MDP_LUT_CLK 11 +#define DISP_CC_MDSS_NON_GDSC_AHB_CLK 12 +#define DISP_CC_MDSS_PCLK0_CLK 13 +#define DISP_CC_MDSS_PCLK0_CLK_SRC 14 +#define DISP_CC_MDSS_VSYNC_CLK 15 +#define DISP_CC_MDSS_VSYNC_CLK_SRC 16 +#define DISP_CC_SLEEP_CLK 17 +#define DISP_CC_SLEEP_CLK_SRC 18 +#define DISP_CC_XO_CLK 19 +#define DISP_CC_XO_CLK_SRC 20 + +#define MDSS_GDSC 0 + +#endif -- cgit v1.2.3 From 8008e7902f28eb9e5459b21d375b3e5b4090efff Mon Sep 17 00:00:00 2001 From: Sai Prakash Ranjan Date: Fri, 28 Jan 2022 13:17:09 +0530 Subject: soc: qcom: llcc: Update the logic for version info extraction LLCC HW version info is made up of major, branch, minor and echo version bits each of which are 8bits. Several features in newer LLCC HW are based on the full version rather than just major or minor versions such as write-subcache enable which is applicable for versions v2.0.0.0 and later, also upcoming write-subcache cacheable for SM8450 SoC which is only present in versions v2.1.0.0 and later, so it makes it easier and cleaner to just directly compare with the full version than adding additional major/branch/ minor/echo version checks. So remove the earlier major version check and add full version check for those features. Signed-off-by: Sai Prakash Ranjan Tested-by: Vinod Koul Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/a82d7c32348c51fcc2b63e220d91b318bf706c83.1643355594.git.quic_saipraka@quicinc.com --- include/linux/soc/qcom/llcc-qcom.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index 9e8fd92c96b7..beecf00b707d 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -83,7 +83,7 @@ struct llcc_edac_reg_data { * @bitmap: Bit map to track the active slice ids * @offsets: Pointer to the bank offsets array * @ecc_irq: interrupt for llcc cache error detection and reporting - * @major_version: Indicates the LLCC major version + * @version: Indicates the LLCC version */ struct llcc_drv_data { struct regmap *regmap; @@ -96,7 +96,7 @@ struct llcc_drv_data { unsigned long *bitmap; u32 *offsets; int ecc_irq; - u32 major_version; + u32 version; }; #if IS_ENABLED(CONFIG_QCOM_LLCC) -- cgit v1.2.3 From a6e9d7ef252c44a4f33b4403cd367430697dd9be Mon Sep 17 00:00:00 2001 From: Sai Prakash Ranjan Date: Fri, 28 Jan 2022 13:17:13 +0530 Subject: soc: qcom: llcc: Add configuration data for SM8450 SoC Add LLCC configuration data for SM8450 SoC. Signed-off-by: Sai Prakash Ranjan Tested-by: Vinod Koul Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/fec944cb8f2a4a70785903c6bfec629c6f31b6a4.1643355594.git.quic_saipraka@quicinc.com --- include/linux/soc/qcom/llcc-qcom.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index beecf00b707d..0bc21ee58fac 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -35,7 +35,12 @@ #define LLCC_WRCACHE 31 #define LLCC_CVPFW 32 #define LLCC_CPUSS1 33 +#define LLCC_CAMEXP0 34 +#define LLCC_CPUMTE 35 #define LLCC_CPUHWT 36 +#define LLCC_MDMCLAD2 37 +#define LLCC_CAMEXP1 38 +#define LLCC_AENPU 45 /** * struct llcc_slice_desc - Cache slice descriptor -- cgit v1.2.3 From 7a7b1414ea9a3641672be768afe16f583f0b76e7 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Tue, 25 Jan 2022 11:11:19 -0600 Subject: dt-bindings: power: imx8mq: add defines for VPU blk-ctrl domains This adds the defines for the power domains provided by the VPU blk-ctrl on the i.MX8MQ. Signed-off-by: Lucas Stach Acked-by: Rob Herring Signed-off-by: Adam Ford Signed-off-by: Shawn Guo --- include/dt-bindings/power/imx8mq-power.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/power/imx8mq-power.h b/include/dt-bindings/power/imx8mq-power.h index 8a513bd9166e..9f7d0f1e7c32 100644 --- a/include/dt-bindings/power/imx8mq-power.h +++ b/include/dt-bindings/power/imx8mq-power.h @@ -18,4 +18,7 @@ #define IMX8M_POWER_DOMAIN_MIPI_CSI2 9 #define IMX8M_POWER_DOMAIN_PCIE2 10 +#define IMX8MQ_VPUBLK_PD_G1 0 +#define IMX8MQ_VPUBLK_PD_G2 1 + #endif -- cgit v1.2.3 From 7f5a08c79df35e68f1a43033450c5050f12bc155 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 18 Jan 2022 12:43:15 -0800 Subject: user_events: Add minimal support for trace_event into ftrace Minimal support for interacting with dynamic events, trace_event and ftrace. Core outline of flow between user process, ioctl and trace_event APIs. User mode processes that wish to use trace events to get data into ftrace, perf, eBPF, etc are limited to uprobes today. The user events features enables an ABI for user mode processes to create and write to trace events that are isolated from kernel level trace events. This enables a faster path for tracing from user mode data as well as opens managed code to participate in trace events, where stub locations are dynamic. User processes often want to trace only when it's useful. To enable this a set of pages are mapped into the user process space that indicate the current state of the user events that have been registered. User processes can check if their event is hooked to a trace/probe, and if it is, emit the event data out via the write() syscall. Two new files are introduced into tracefs to accomplish this: user_events_status - This file is mmap'd into participating user mode processes to indicate event status. user_events_data - This file is opened and register/delete ioctl's are issued to create/open/delete trace events that can be used for tracing. The typical scenario is on process start to mmap user_events_status. Processes then register the events they plan to use via the REG ioctl. The ioctl reads and updates the passed in user_reg struct. The status_index of the struct is used to know the byte in the status page to check for that event. The write_index of the struct is used to describe that event when writing out to the fd that was used for the ioctl call. The data must always include this index first when writing out data for an event. Data can be written either by write() or by writev(). For example, in memory: int index; char data[]; Psuedo code example of typical usage: struct user_reg reg; int page_fd = open("user_events_status", O_RDWR); char *page_data = mmap(NULL, PAGE_SIZE, PROT_READ, MAP_SHARED, page_fd, 0); close(page_fd); int data_fd = open("user_events_data", O_RDWR); reg.size = sizeof(reg); reg.name_args = (__u64)"test"; ioctl(data_fd, DIAG_IOCSREG, ®); int status_id = reg.status_index; int write_id = reg.write_index; struct iovec io[2]; io[0].iov_base = &write_id; io[0].iov_len = sizeof(write_id); io[1].iov_base = payload; io[1].iov_len = sizeof(payload); if (page_data[status_id]) writev(data_fd, io, 2); User events are also exposed via the dynamic_events tracefs file for both create and delete. Current status is exposed via the user_events_status tracefs file. Simple example to register a user event via dynamic_events: echo u:test >> dynamic_events cat dynamic_events u:test If an event is hooked to a probe, the probe hooked shows up: echo 1 > events/user_events/test/enable cat user_events_status 1:test # Used by ftrace Active: 1 Busy: 1 Max: 4096 If an event is not hooked to a probe, no probe status shows up: echo 0 > events/user_events/test/enable cat user_events_status 1:test Active: 1 Busy: 0 Max: 4096 Users can describe the trace event format via the following format: name[:FLAG1[,FLAG2...] [field1[;field2...]] Each field has the following format: type name Example for char array with a size of 20 named msg: echo 'u:detailed char[20] msg' >> dynamic_events cat dynamic_events u:detailed char[20] msg Data offsets are based on the data written out via write() and will be updated to reflect the correct offset in the trace_event fields. For dynamic data it is recommended to use the new __rel_loc data type. This type will be the same as __data_loc, but the offset is relative to this entry. This allows user_events to not worry about what common fields are being inserted before the data. The above format is valid for both the ioctl and the dynamic_events file. Link: https://lkml.kernel.org/r/20220118204326.2169-2-beaub@linux.microsoft.com Acked-by: Masami Hiramatsu Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- include/uapi/linux/user_events.h | 116 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 116 insertions(+) create mode 100644 include/uapi/linux/user_events.h (limited to 'include') diff --git a/include/uapi/linux/user_events.h b/include/uapi/linux/user_events.h new file mode 100644 index 000000000000..e570840571e1 --- /dev/null +++ b/include/uapi/linux/user_events.h @@ -0,0 +1,116 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright (c) 2021, Microsoft Corporation. + * + * Authors: + * Beau Belgrave + */ +#ifndef _UAPI_LINUX_USER_EVENTS_H +#define _UAPI_LINUX_USER_EVENTS_H + +#include +#include + +#ifdef __KERNEL__ +#include +#else +#include +#endif + +#define USER_EVENTS_SYSTEM "user_events" +#define USER_EVENTS_PREFIX "u:" + +/* Bits 0-6 are for known probe types, Bit 7 is for unknown probes */ +#define EVENT_BIT_FTRACE 0 +#define EVENT_BIT_PERF 1 +#define EVENT_BIT_OTHER 7 + +#define EVENT_STATUS_FTRACE (1 << EVENT_BIT_FTRACE) +#define EVENT_STATUS_PERF (1 << EVENT_BIT_PERF) +#define EVENT_STATUS_OTHER (1 << EVENT_BIT_OTHER) + +/* Create dynamic location entry within a 32-bit value */ +#define DYN_LOC(offset, size) ((size) << 16 | (offset)) + +/* Use raw iterator for attached BPF program(s), no affect on ftrace/perf */ +#define FLAG_BPF_ITER (1 << 0) + +/* + * Describes an event registration and stores the results of the registration. + * This structure is passed to the DIAG_IOCSREG ioctl, callers at a minimum + * must set the size and name_args before invocation. + */ +struct user_reg { + + /* Input: Size of the user_reg structure being used */ + __u32 size; + + /* Input: Pointer to string with event name, description and flags */ + __u64 name_args; + + /* Output: Byte index of the event within the status page */ + __u32 status_index; + + /* Output: Index of the event to use when writing data */ + __u32 write_index; +}; + +#define DIAG_IOC_MAGIC '*' + +/* Requests to register a user_event */ +#define DIAG_IOCSREG _IOWR(DIAG_IOC_MAGIC, 0, struct user_reg*) + +/* Requests to delete a user_event */ +#define DIAG_IOCSDEL _IOW(DIAG_IOC_MAGIC, 1, char*) + +/* Data type that was passed to the BPF program */ +enum { + /* Data resides in kernel space */ + USER_BPF_DATA_KERNEL, + + /* Data resides in user space */ + USER_BPF_DATA_USER, + + /* Data is a pointer to a user_bpf_iter structure */ + USER_BPF_DATA_ITER, +}; + +/* + * Describes an iovec iterator that BPF programs can use to access data for + * a given user_event write() / writev() call. + */ +struct user_bpf_iter { + + /* Offset of the data within the first iovec */ + __u32 iov_offset; + + /* Number of iovec structures */ + __u32 nr_segs; + + /* Pointer to iovec structures */ + const struct iovec *iov; +}; + +/* Context that BPF programs receive when attached to a user_event */ +struct user_bpf_context { + + /* Data type being passed (see union below) */ + __u32 data_type; + + /* Length of the data */ + __u32 data_len; + + /* Pointer to data, varies by data type */ + union { + /* Kernel data (data_type == USER_BPF_DATA_KERNEL) */ + void *kdata; + + /* User data (data_type == USER_BPF_DATA_USER) */ + void *udata; + + /* Direct iovec (data_type == USER_BPF_DATA_ITER) */ + struct user_bpf_iter *iter; + }; +}; + +#endif /* _UAPI_LINUX_USER_EVENTS_H */ -- cgit v1.2.3 From 0f4b58423f3500ee3e3159fbbd6c41a6e6f920d4 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Thu, 3 Feb 2022 11:03:50 +0200 Subject: drm/dp: add drm_dp_128b132b_read_aux_rd_interval() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The DP 2.0 errata changes DP_128B132B_TRAINING_AUX_RD_INTERVAL (DPCD 0x2216) completely. Add a new function to read that. Follow-up will need to clean up existing functions. v2: fix reversed interpretation of bit 7 meaning (Uma) Cc: Uma Shankar Cc: Ville Syrjälä Signed-off-by: Jani Nikula Reviewed-by: Ville Syrjälä Acked-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/22f6637194c9edb22b6a84be82dd385550dbb958.1643878928.git.jani.nikula@intel.com --- include/drm/drm_dp_helper.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 30359e434c3f..629ac2272e55 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -1115,6 +1115,7 @@ struct drm_panel; # define DP_UHBR13_5 (1 << 2) #define DP_128B132B_TRAINING_AUX_RD_INTERVAL 0x2216 /* 2.0 */ +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_1MS_UNIT (1 << 7) # define DP_128B132B_TRAINING_AUX_RD_INTERVAL_MASK 0x7f # define DP_128B132B_TRAINING_AUX_RD_INTERVAL_400_US 0x00 # define DP_128B132B_TRAINING_AUX_RD_INTERVAL_4_MS 0x01 @@ -1552,6 +1553,8 @@ void drm_dp_link_train_channel_eq_delay(const struct drm_dp_aux *aux, void drm_dp_lttpr_link_train_channel_eq_delay(const struct drm_dp_aux *aux, const u8 caps[DP_LTTPR_PHY_CAP_SIZE]); +int drm_dp_128b132b_read_aux_rd_interval(struct drm_dp_aux *aux); + u8 drm_dp_link_rate_to_bw_code(int link_rate); int drm_dp_bw_code_to_link_rate(u8 link_bw); -- cgit v1.2.3 From 0192c25c03cd2feaeaadae375fe6aadff788939a Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Thu, 3 Feb 2022 11:03:51 +0200 Subject: drm/dp: add 128b/132b link status helpers from DP 2.0 E11 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The DP 2.0 errata redefines link training. There are some new status bits, and some of the old ones need to be checked independently. Add helpers to do this. Cc: Uma Shankar Cc: Ville Syrjälä Signed-off-by: Jani Nikula Reviewed-by: Ville Syrjälä Acked-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/5a46260d1f171fed46d0ab8fe4b6499abd65ce24.1643878928.git.jani.nikula@intel.com --- include/drm/drm_dp_helper.h | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 629ac2272e55..c9ca38941514 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -738,11 +738,13 @@ struct drm_panel; DP_LANE_CHANNEL_EQ_DONE | \ DP_LANE_SYMBOL_LOCKED) -#define DP_LANE_ALIGN_STATUS_UPDATED 0x204 - -#define DP_INTERLANE_ALIGN_DONE (1 << 0) -#define DP_DOWNSTREAM_PORT_STATUS_CHANGED (1 << 6) -#define DP_LINK_STATUS_UPDATED (1 << 7) +#define DP_LANE_ALIGN_STATUS_UPDATED 0x204 +#define DP_INTERLANE_ALIGN_DONE (1 << 0) +#define DP_128B132B_DPRX_EQ_INTERLANE_ALIGN_DONE (1 << 2) /* 2.0 E11 */ +#define DP_128B132B_DPRX_CDS_INTERLANE_ALIGN_DONE (1 << 3) /* 2.0 E11 */ +#define DP_128B132B_LT_FAILED (1 << 4) /* 2.0 E11 */ +#define DP_DOWNSTREAM_PORT_STATUS_CHANGED (1 << 6) +#define DP_LINK_STATUS_UPDATED (1 << 7) #define DP_SINK_STATUS 0x205 # define DP_RECEIVE_PORT_0_STATUS (1 << 0) @@ -1554,6 +1556,13 @@ void drm_dp_lttpr_link_train_channel_eq_delay(const struct drm_dp_aux *aux, const u8 caps[DP_LTTPR_PHY_CAP_SIZE]); int drm_dp_128b132b_read_aux_rd_interval(struct drm_dp_aux *aux); +bool drm_dp_128b132b_lane_channel_eq_done(const u8 link_status[DP_LINK_STATUS_SIZE], + int lane_count); +bool drm_dp_128b132b_lane_symbol_locked(const u8 link_status[DP_LINK_STATUS_SIZE], + int lane_count); +bool drm_dp_128b132b_eq_interlane_align_done(const u8 link_status[DP_LINK_STATUS_SIZE]); +bool drm_dp_128b132b_cds_interlane_align_done(const u8 link_status[DP_LINK_STATUS_SIZE]); +bool drm_dp_128b132b_link_training_failed(const u8 link_status[DP_LINK_STATUS_SIZE]); u8 drm_dp_link_rate_to_bw_code(int link_rate); int drm_dp_bw_code_to_link_rate(u8 link_bw); -- cgit v1.2.3 From 427153ef63a82a4d51c6046e2457787127f4d6d7 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Thu, 3 Feb 2022 11:03:52 +0200 Subject: drm/dp: add some new DPCD macros from DP 2.0 E11 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add some of the new additions from DP 2.0 E11. Cc: Uma Shankar Cc: Ville Syrjälä Signed-off-by: Jani Nikula Reviewed-by: Ville Syrjälä Acked-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/ec9c1b94858de36b9f4ef6c197effa4ca667afc3.1643878928.git.jani.nikula@intel.com --- include/drm/drm_dp_helper.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index c9ca38941514..c48bf958a967 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -560,6 +560,7 @@ struct drm_panel; # define DP_TRAINING_PATTERN_DISABLE 0 # define DP_TRAINING_PATTERN_1 1 # define DP_TRAINING_PATTERN_2 2 +# define DP_TRAINING_PATTERN_2_CDS 3 /* 2.0 E11 */ # define DP_TRAINING_PATTERN_3 3 /* 1.2 */ # define DP_TRAINING_PATTERN_4 7 /* 1.4 */ # define DP_TRAINING_PATTERN_MASK 0x3 @@ -1353,6 +1354,7 @@ struct drm_panel; # define DP_PHY_REPEATER_128B132B_SUPPORTED (1 << 0) /* See DP_128B132B_SUPPORTED_LINK_RATES for values */ #define DP_PHY_REPEATER_128B132B_RATES 0xf0007 /* 2.0 */ +#define DP_PHY_REPEATER_EQ_DONE 0xf0008 /* 2.0 E11 */ enum drm_dp_phy { DP_PHY_DPRX, -- cgit v1.2.3 From 297565aa22cfa80ab0f88c3569693aea0b6afb6d Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Sat, 5 Feb 2022 16:23:45 +0100 Subject: lib/xor: make xor prototypes more friendly to compiler vectorization Modern compilers are perfectly capable of extracting parallelism from the XOR routines, provided that the prototypes reflect the nature of the input accurately, in particular, the fact that the input vectors are expected not to overlap. This is not documented explicitly, but is implied by the interchangeability of the various C routines, some of which use temporary variables while others don't: this means that these routines only behave identically for non-overlapping inputs. So let's decorate these input vectors with the __restrict modifier, which informs the compiler that there is no overlap. While at it, make the input-only vectors pointer-to-const as well. Tested-by: Nathan Chancellor Signed-off-by: Ard Biesheuvel Reviewed-by: Nick Desaulniers Link: https://github.com/ClangBuiltLinux/linux/issues/563 Signed-off-by: Herbert Xu --- include/asm-generic/xor.h | 84 +++++++++++++++++++++++++++++++---------------- include/linux/raid/xor.h | 21 ++++++++---- 2 files changed, 70 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/include/asm-generic/xor.h b/include/asm-generic/xor.h index b62a2a56a4d4..44509d48fca2 100644 --- a/include/asm-generic/xor.h +++ b/include/asm-generic/xor.h @@ -8,7 +8,8 @@ #include static void -xor_8regs_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) +xor_8regs_2(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2) { long lines = bytes / (sizeof (long)) / 8; @@ -27,8 +28,9 @@ xor_8regs_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) } static void -xor_8regs_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3) +xor_8regs_3(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3) { long lines = bytes / (sizeof (long)) / 8; @@ -48,8 +50,10 @@ xor_8regs_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_8regs_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4) +xor_8regs_4(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4) { long lines = bytes / (sizeof (long)) / 8; @@ -70,8 +74,11 @@ xor_8regs_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_8regs_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4, unsigned long *p5) +xor_8regs_5(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4, + const unsigned long * __restrict p5) { long lines = bytes / (sizeof (long)) / 8; @@ -93,7 +100,8 @@ xor_8regs_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_32regs_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) +xor_32regs_2(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2) { long lines = bytes / (sizeof (long)) / 8; @@ -129,8 +137,9 @@ xor_32regs_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) } static void -xor_32regs_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3) +xor_32regs_3(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3) { long lines = bytes / (sizeof (long)) / 8; @@ -175,8 +184,10 @@ xor_32regs_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_32regs_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4) +xor_32regs_4(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4) { long lines = bytes / (sizeof (long)) / 8; @@ -230,8 +241,11 @@ xor_32regs_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_32regs_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4, unsigned long *p5) +xor_32regs_5(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4, + const unsigned long * __restrict p5) { long lines = bytes / (sizeof (long)) / 8; @@ -294,7 +308,8 @@ xor_32regs_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_8regs_p_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) +xor_8regs_p_2(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2) { long lines = bytes / (sizeof (long)) / 8 - 1; prefetchw(p1); @@ -320,8 +335,9 @@ xor_8regs_p_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) } static void -xor_8regs_p_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3) +xor_8regs_p_3(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3) { long lines = bytes / (sizeof (long)) / 8 - 1; prefetchw(p1); @@ -350,8 +366,10 @@ xor_8regs_p_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_8regs_p_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4) +xor_8regs_p_4(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4) { long lines = bytes / (sizeof (long)) / 8 - 1; @@ -384,8 +402,11 @@ xor_8regs_p_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_8regs_p_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4, unsigned long *p5) +xor_8regs_p_5(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4, + const unsigned long * __restrict p5) { long lines = bytes / (sizeof (long)) / 8 - 1; @@ -421,7 +442,8 @@ xor_8regs_p_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_32regs_p_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) +xor_32regs_p_2(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2) { long lines = bytes / (sizeof (long)) / 8 - 1; @@ -466,8 +488,9 @@ xor_32regs_p_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) } static void -xor_32regs_p_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3) +xor_32regs_p_3(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3) { long lines = bytes / (sizeof (long)) / 8 - 1; @@ -523,8 +546,10 @@ xor_32regs_p_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_32regs_p_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4) +xor_32regs_p_4(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4) { long lines = bytes / (sizeof (long)) / 8 - 1; @@ -591,8 +616,11 @@ xor_32regs_p_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_32regs_p_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4, unsigned long *p5) +xor_32regs_p_5(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4, + const unsigned long * __restrict p5) { long lines = bytes / (sizeof (long)) / 8 - 1; diff --git a/include/linux/raid/xor.h b/include/linux/raid/xor.h index 2a9fee8ddae3..51b811b62322 100644 --- a/include/linux/raid/xor.h +++ b/include/linux/raid/xor.h @@ -11,13 +11,20 @@ struct xor_block_template { struct xor_block_template *next; const char *name; int speed; - void (*do_2)(unsigned long, unsigned long *, unsigned long *); - void (*do_3)(unsigned long, unsigned long *, unsigned long *, - unsigned long *); - void (*do_4)(unsigned long, unsigned long *, unsigned long *, - unsigned long *, unsigned long *); - void (*do_5)(unsigned long, unsigned long *, unsigned long *, - unsigned long *, unsigned long *, unsigned long *); + void (*do_2)(unsigned long, unsigned long * __restrict, + const unsigned long * __restrict); + void (*do_3)(unsigned long, unsigned long * __restrict, + const unsigned long * __restrict, + const unsigned long * __restrict); + void (*do_4)(unsigned long, unsigned long * __restrict, + const unsigned long * __restrict, + const unsigned long * __restrict, + const unsigned long * __restrict); + void (*do_5)(unsigned long, unsigned long * __restrict, + const unsigned long * __restrict, + const unsigned long * __restrict, + const unsigned long * __restrict, + const unsigned long * __restrict); }; #endif -- cgit v1.2.3 From dc1b4df09acdca7a89806b28f235cd6d8dcd3d24 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 7 Feb 2022 10:19:43 +0000 Subject: atomics: Fix atomic64_{read_acquire,set_release} fallbacks Arnd reports that on 32-bit architectures, the fallbacks for atomic64_read_acquire() and atomic64_set_release() are broken as they use smp_load_acquire() and smp_store_release() respectively, which do not work on types larger than the native word size. Since those contain compiletime_assert_atomic_type(), any attempt to use those fallbacks will result in a build-time error. e.g. with the following added to arch/arm/kernel/setup.c: | void test_atomic64(atomic64_t *v) | { | atomic64_set_release(v, 5); | atomic64_read_acquire(v); | } The compiler will complain as follows: | In file included from : | In function 'arch_atomic64_set_release', | inlined from 'test_atomic64' at ./include/linux/atomic/atomic-instrumented.h:669:2: | ././include/linux/compiler_types.h:346:38: error: call to '__compiletime_assert_9' declared with attribute error: Need native word sized stores/loads for atomicity. | 346 | _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__) | | ^ | ././include/linux/compiler_types.h:327:4: note: in definition of macro '__compiletime_assert' | 327 | prefix ## suffix(); \ | | ^~~~~~ | ././include/linux/compiler_types.h:346:2: note: in expansion of macro '_compiletime_assert' | 346 | _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__) | | ^~~~~~~~~~~~~~~~~~~ | ././include/linux/compiler_types.h:349:2: note: in expansion of macro 'compiletime_assert' | 349 | compiletime_assert(__native_word(t), \ | | ^~~~~~~~~~~~~~~~~~ | ./include/asm-generic/barrier.h:133:2: note: in expansion of macro 'compiletime_assert_atomic_type' | 133 | compiletime_assert_atomic_type(*p); \ | | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ | ./include/asm-generic/barrier.h:164:55: note: in expansion of macro '__smp_store_release' | 164 | #define smp_store_release(p, v) do { kcsan_release(); __smp_store_release(p, v); } while (0) | | ^~~~~~~~~~~~~~~~~~~ | ./include/linux/atomic/atomic-arch-fallback.h:1270:2: note: in expansion of macro 'smp_store_release' | 1270 | smp_store_release(&(v)->counter, i); | | ^~~~~~~~~~~~~~~~~ | make[2]: *** [scripts/Makefile.build:288: arch/arm/kernel/setup.o] Error 1 | make[1]: *** [scripts/Makefile.build:550: arch/arm/kernel] Error 2 | make: *** [Makefile:1831: arch/arm] Error 2 Fix this by only using smp_load_acquire() and smp_store_release() for native atomic types, and otherwise falling back to the regular barriers necessary for acquire/release semantics, as we do in the more generic acquire and release fallbacks. Since the fallback templates are used to generate the atomic64_*() and atomic_*() operations, the __native_word() check is added to both. For the atomic_*() operations, which are always 32-bit, the __native_word() check is redundant but not harmful, as it is always true. For the example above this works as expected on 32-bit, e.g. for arm multi_v7_defconfig: | : | push {r4, r5} | dmb ish | pldw [r0] | mov r2, #5 | mov r3, #0 | ldrexd r4, [r0] | strexd r4, r2, [r0] | teq r4, #0 | bne 484 | ldrexd r2, [r0] | dmb ish | pop {r4, r5} | bx lr ... and also on 64-bit, e.g. for arm64 defconfig: | : | bti c | paciasp | mov x1, #0x5 | stlr x1, [x0] | ldar x0, [x0] | autiasp | ret Reported-by: Arnd Bergmann Signed-off-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Ard Biesheuvel Reviewed-by: Boqun Feng Link: https://lore.kernel.org/r/20220207101943.439825-1-mark.rutland@arm.com --- include/linux/atomic/atomic-arch-fallback.h | 38 +++++++++++++++++++++++++---- 1 file changed, 33 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index a3dba31df01e..6db58d180866 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -151,7 +151,16 @@ static __always_inline int arch_atomic_read_acquire(const atomic_t *v) { - return smp_load_acquire(&(v)->counter); + int ret; + + if (__native_word(atomic_t)) { + ret = smp_load_acquire(&(v)->counter); + } else { + ret = arch_atomic_read(v); + __atomic_acquire_fence(); + } + + return ret; } #define arch_atomic_read_acquire arch_atomic_read_acquire #endif @@ -160,7 +169,12 @@ arch_atomic_read_acquire(const atomic_t *v) static __always_inline void arch_atomic_set_release(atomic_t *v, int i) { - smp_store_release(&(v)->counter, i); + if (__native_word(atomic_t)) { + smp_store_release(&(v)->counter, i); + } else { + __atomic_release_fence(); + arch_atomic_set(v, i); + } } #define arch_atomic_set_release arch_atomic_set_release #endif @@ -1258,7 +1272,16 @@ arch_atomic_dec_if_positive(atomic_t *v) static __always_inline s64 arch_atomic64_read_acquire(const atomic64_t *v) { - return smp_load_acquire(&(v)->counter); + s64 ret; + + if (__native_word(atomic64_t)) { + ret = smp_load_acquire(&(v)->counter); + } else { + ret = arch_atomic64_read(v); + __atomic_acquire_fence(); + } + + return ret; } #define arch_atomic64_read_acquire arch_atomic64_read_acquire #endif @@ -1267,7 +1290,12 @@ arch_atomic64_read_acquire(const atomic64_t *v) static __always_inline void arch_atomic64_set_release(atomic64_t *v, s64 i) { - smp_store_release(&(v)->counter, i); + if (__native_word(atomic64_t)) { + smp_store_release(&(v)->counter, i); + } else { + __atomic_release_fence(); + arch_atomic64_set(v, i); + } } #define arch_atomic64_set_release arch_atomic64_set_release #endif @@ -2358,4 +2386,4 @@ arch_atomic64_dec_if_positive(atomic64_t *v) #endif #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// cca554917d7ea73d5e3e7397dd70c484cad9b2c4 +// 8e2cc06bc0d2c0967d2f8424762bd48555ee40ae -- cgit v1.2.3 From 9983a9d577db415c41099a20a5637ab25dd3c240 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 8 Feb 2022 18:08:02 +0100 Subject: locking/local_lock: Make the empty local_lock_*() function a macro. It has been said that local_lock() does not add any overhead compared to preempt_disable() in a !LOCKDEP configuration. A micro benchmark showed an unexpected result which can be reduced to the fact that local_lock() was not entirely optimized away. In the !LOCKDEP configuration local_lock_acquire() is an empty static inline function. On x86 the this_cpu_ptr() argument of that function is fully evaluated leading to an additional mov+add instructions which are not needed and not used. Replace the static inline function with a macro. The typecheck() macro ensures that the argument is of proper type while the resulting disassembly shows no traces of this_cpu_ptr(). Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Waiman Long Link: https://lkml.kernel.org/r/YgKjciR60fZft2l4@linutronix.de --- include/linux/local_lock_internal.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index 975e33b793a7..6d635e8306d6 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -44,9 +44,9 @@ static inline void local_lock_debug_init(local_lock_t *l) } #else /* CONFIG_DEBUG_LOCK_ALLOC */ # define LOCAL_LOCK_DEBUG_INIT(lockname) -static inline void local_lock_acquire(local_lock_t *l) { } -static inline void local_lock_release(local_lock_t *l) { } -static inline void local_lock_debug_init(local_lock_t *l) { } +# define local_lock_acquire(__ll) do { typecheck(local_lock_t *, __ll); } while (0) +# define local_lock_release(__ll) do { typecheck(local_lock_t *, __ll); } while (0) +# define local_lock_debug_init(__ll) do { typecheck(local_lock_t *, __ll); } while (0) #endif /* !CONFIG_DEBUG_LOCK_ALLOC */ #define INIT_LOCAL_LOCK(lockname) { LOCAL_LOCK_DEBUG_INIT(lockname) } -- cgit v1.2.3 From 48b6190a00425a1bebac9f7ae4b338a1e20f50f3 Mon Sep 17 00:00:00 2001 From: "D. Wythe" Date: Thu, 10 Feb 2022 17:11:36 +0800 Subject: net/smc: Limit SMC visits when handshake workqueue congested This patch intends to provide a mechanism to put constraint on SMC connections visit according to the pressure of SMC handshake process. At present, frequent visits will cause the incoming connections to be backlogged in SMC handshake queue, raise the connections established time. Which is quite unacceptable for those applications who base on short lived connections. There are two ways to implement this mechanism: 1. Put limitation after TCP established. 2. Put limitation before TCP established. In the first way, we need to wait and receive CLC messages that the client will potentially send, and then actively reply with a decline message, in a sense, which is also a sort of SMC handshake, affect the connections established time on its way. In the second way, the only problem is that we need to inject SMC logic into TCP when it is about to reply the incoming SYN, since we already do that, it's seems not a problem anymore. And advantage is obvious, few additional processes are required to complete the constraint. This patch use the second way. After this patch, connections who beyond constraint will not informed any SMC indication, and SMC will not be involved in any of its subsequent processes. Link: https://lore.kernel.org/all/1641301961-59331-1-git-send-email-alibuda@linux.alibaba.com/ Signed-off-by: D. Wythe Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 78b91bb92f0d..1168302b7927 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -394,6 +394,7 @@ struct tcp_sock { bool is_mptcp; #endif #if IS_ENABLED(CONFIG_SMC) + bool (*smc_hs_congested)(const struct sock *sk); bool syn_smc; /* SYN includes SMC */ #endif -- cgit v1.2.3 From a6a6fe27bab48f0d09a64b051e7bde432fcae081 Mon Sep 17 00:00:00 2001 From: "D. Wythe" Date: Thu, 10 Feb 2022 17:11:37 +0800 Subject: net/smc: Dynamic control handshake limitation by socket options This patch aims to add dynamic control for SMC handshake limitation for every smc sockets, in production environment, it is possible for the same applications to handle different service types, and may have different opinion on SMC handshake limitation. This patch try socket options to complete it, since we don't have socket option level for SMC yet, which requires us to implement it at the same time. This patch does the following: - add new socket option level: SOL_SMC. - add new SMC socket option: SMC_LIMIT_HS. - provide getter/setter for SMC socket options. Link: https://lore.kernel.org/all/20f504f961e1a803f85d64229ad84260434203bd.1644323503.git.alibuda@linux.alibaba.com/ Signed-off-by: D. Wythe Signed-off-by: David S. Miller --- include/linux/socket.h | 1 + include/uapi/linux/smc.h | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/socket.h b/include/linux/socket.h index 8ef26d89ef49..6f85f5d957ef 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -366,6 +366,7 @@ struct ucred { #define SOL_XDP 283 #define SOL_MPTCP 284 #define SOL_MCTP 285 +#define SOL_SMC 286 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index 6c2874fd2c00..343e7450c3a3 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -284,4 +284,8 @@ enum { __SMC_NLA_SEID_TABLE_MAX, SMC_NLA_SEID_TABLE_MAX = __SMC_NLA_SEID_TABLE_MAX - 1 }; + +/* SMC socket options */ +#define SMC_LIMIT_HS 1 /* constraint on smc handshake */ + #endif /* _UAPI_LINUX_SMC_H */ -- cgit v1.2.3 From f9496b7c1b48ce02cd17a3ee88b1e049c689a222 Mon Sep 17 00:00:00 2001 From: "D. Wythe" Date: Thu, 10 Feb 2022 17:11:38 +0800 Subject: net/smc: Add global configure for handshake limitation by netlink Although we can control SMC handshake limitation through socket options, which means that applications who need it must modify their code. It's quite troublesome for many existing applications. This patch modifies the global default value of SMC handshake limitation through netlink, providing a way to put constraint on handshake without modifies any code for applications. Suggested-by: Tony Lu Signed-off-by: D. Wythe Reviewed-by: Tony Lu Signed-off-by: David S. Miller --- include/net/netns/smc.h | 2 ++ include/uapi/linux/smc.h | 11 +++++++++++ 2 files changed, 13 insertions(+) (limited to 'include') diff --git a/include/net/netns/smc.h b/include/net/netns/smc.h index ea8a9cf2619b..47b166684fd8 100644 --- a/include/net/netns/smc.h +++ b/include/net/netns/smc.h @@ -12,5 +12,7 @@ struct netns_smc { /* protect fback_rsn */ struct mutex mutex_fback_rsn; struct smc_stats_rsn *fback_rsn; + + bool limit_smc_hs; /* constraint on handshake */ }; #endif diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index 343e7450c3a3..693f549f6966 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -59,6 +59,9 @@ enum { SMC_NETLINK_DUMP_SEID, SMC_NETLINK_ENABLE_SEID, SMC_NETLINK_DISABLE_SEID, + SMC_NETLINK_DUMP_HS_LIMITATION, + SMC_NETLINK_ENABLE_HS_LIMITATION, + SMC_NETLINK_DISABLE_HS_LIMITATION, }; /* SMC_GENL_FAMILY top level attributes */ @@ -285,6 +288,14 @@ enum { SMC_NLA_SEID_TABLE_MAX = __SMC_NLA_SEID_TABLE_MAX - 1 }; +/* SMC_NETLINK_HS_LIMITATION attributes */ +enum { + SMC_NLA_HS_LIMITATION_UNSPEC, + SMC_NLA_HS_LIMITATION_ENABLED, /* u8 */ + __SMC_NLA_HS_LIMITATION_MAX, + SMC_NLA_HS_LIMITATION_MAX = __SMC_NLA_HS_LIMITATION_MAX - 1 +}; + /* SMC socket options */ #define SMC_LIMIT_HS 1 /* constraint on smc handshake */ -- cgit v1.2.3 From 2d4feb2c1ba728fe53d6f80705b2d7e5c5b666a5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 10 Feb 2022 13:42:28 -0800 Subject: ipv6: get rid of net->ipv6.rt6_stats->fib_rt_uncache This counter has never been visible, there is little point trying to maintain it. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 40ae8f1b18e5..32c83bb68879 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -367,9 +367,8 @@ struct rt6_statistics { __u32 fib_rt_cache; /* cached rt entries in exception table */ __u32 fib_discarded_routes; /* total number of routes delete */ - /* The following stats are not protected by any lock */ + /* The following stat is not protected by any lock */ atomic_t fib_rt_alloc; /* total number of routes alloced */ - atomic_t fib_rt_uncache; /* rt entries in uncached list */ }; #define RTN_TL_ROOT 0x0001 -- cgit v1.2.3 From bad03efd11dfa6f039fe494207996c482e9364d0 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Wed, 9 Feb 2022 07:01:33 -0800 Subject: ALSA: cleanup double word in comment Remove the second 'device'. Signed-off-by: Tom Rix Link: https://lore.kernel.org/r/20220209150133.2291856-1-trix@redhat.com Signed-off-by: Takashi Iwai --- include/sound/hda_verbs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/hda_verbs.h b/include/sound/hda_verbs.h index e36b77531c5c..006d358acce2 100644 --- a/include/sound/hda_verbs.h +++ b/include/sound/hda_verbs.h @@ -461,7 +461,7 @@ enum { #define AC_DE_ELDV (1<<1) #define AC_DE_IA (1<<2) -/* device device types (0x0-0xf) */ +/* device types (0x0-0xf) */ enum { AC_JACK_LINE_OUT, AC_JACK_SPEAKER, -- cgit v1.2.3 From d5869fdc189f0f12a954a48d58a48104a2f5d044 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Thu, 10 Feb 2022 14:52:22 -0800 Subject: block: introduce block_rq_error tracepoint Currently, rasdaemon uses the existing tracepoint block_rq_complete and filters out non-error cases in order to capture block disk errors. But there are a few problems with this approach: 1. Even kernel trace filter could do the filtering work, there is still some overhead after we enable this tracepoint. 2. The filter is merely based on errno, which does not align with kernel logic to check the errors for print_req_error(). 3. block_rq_complete only provides dev major and minor to identify the block device, it is not convenient to use in user-space. So introduce a new tracepoint block_rq_error just for the error case. With this patch, rasdaemon could switch to block_rq_error. Since the new tracepoint has the similar implementation with block_rq_complete, so move the existing code from TRACE_EVENT block_rq_complete() into new event class block_rq_completion(). Then add event for block_rq_complete and block_rq_err respectively from the newly created event class per the suggestion from Chaitanya Kulkarni. Cc: Jens Axboe Cc: Christoph Hellwig Reviewed-by: Steven Rostedt Signed-off-by: Cong Wang Signed-off-by: Chaitanya Kulkarni Signed-off-by: Yang Shi Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220210225222.260069-1-shy828301@gmail.com Signed-off-by: Jens Axboe --- include/trace/events/block.h | 49 ++++++++++++++++++++++++++++++++------------ 1 file changed, 36 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 27170e40e8c9..7f4dfbdf12a6 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -100,19 +100,7 @@ TRACE_EVENT(block_rq_requeue, __entry->nr_sector, 0) ); -/** - * block_rq_complete - block IO operation completed by device driver - * @rq: block operations request - * @error: status code - * @nr_bytes: number of completed bytes - * - * The block_rq_complete tracepoint event indicates that some portion - * of operation request has been completed by the device driver. If - * the @rq->bio is %NULL, then there is absolutely no additional work to - * do for the request. If @rq->bio is non-NULL then there is - * additional work required to complete the request. - */ -TRACE_EVENT(block_rq_complete, +DECLARE_EVENT_CLASS(block_rq_completion, TP_PROTO(struct request *rq, blk_status_t error, unsigned int nr_bytes), @@ -144,6 +132,41 @@ TRACE_EVENT(block_rq_complete, __entry->nr_sector, __entry->error) ); +/** + * block_rq_complete - block IO operation completed by device driver + * @rq: block operations request + * @error: status code + * @nr_bytes: number of completed bytes + * + * The block_rq_complete tracepoint event indicates that some portion + * of operation request has been completed by the device driver. If + * the @rq->bio is %NULL, then there is absolutely no additional work to + * do for the request. If @rq->bio is non-NULL then there is + * additional work required to complete the request. + */ +DEFINE_EVENT(block_rq_completion, block_rq_complete, + + TP_PROTO(struct request *rq, blk_status_t error, unsigned int nr_bytes), + + TP_ARGS(rq, error, nr_bytes) +); + +/** + * block_rq_error - block IO operation error reported by device driver + * @rq: block operations request + * @error: status code + * @nr_bytes: number of completed bytes + * + * The block_rq_error tracepoint event indicates that some portion + * of operation request has failed as reported by the device driver. + */ +DEFINE_EVENT(block_rq_completion, block_rq_error, + + TP_PROTO(struct request *rq, blk_status_t error, unsigned int nr_bytes), + + TP_ARGS(rq, error, nr_bytes) +); + DECLARE_EVENT_CLASS(block_rq, TP_PROTO(struct request *rq), -- cgit v1.2.3 From 0e51e2ab49a99bc5077760aa083dfa1c3bf9899b Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 11 Feb 2022 18:11:47 +0800 Subject: block: remove THROTL_IOPS_MAX No one uses THROTL_IOPS_MAX any more, so remove it. Signed-off-by: Ming Lei Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220211101149.2368042-2-ming.lei@redhat.com Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index b4de2010fba5..bdc49bd4eef0 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -28,8 +28,6 @@ /* percpu_counter batch for blkg_[rw]stats, per-cpu drift doesn't matter */ #define BLKG_STAT_CPU_BATCH (INT_MAX / 2) -/* Max limits for throttle policy */ -#define THROTL_IOPS_MAX UINT_MAX #define FC_APPID_LEN 129 -- cgit v1.2.3 From 672fdcf0e7de3b1e39416ac85abf178f023271f1 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 11 Feb 2022 18:11:49 +0800 Subject: block: partition include/linux/blk-cgroup.h Partition include/linux/blk-cgroup.h into two parts: one is public part, the other is block layer private part. Suggested by Christoph Hellwig. Signed-off-by: Ming Lei Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220211101149.2368042-4-ming.lei@redhat.com Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 459 +-------------------------------------------- 1 file changed, 5 insertions(+), 454 deletions(-) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index bdc49bd4eef0..f2ad8ed8f777 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -25,12 +25,8 @@ #include #include -/* percpu_counter batch for blkg_[rw]stats, per-cpu drift doesn't matter */ -#define BLKG_STAT_CPU_BATCH (INT_MAX / 2) - #define FC_APPID_LEN 129 - #ifdef CONFIG_BLK_CGROUP enum blkg_iostat_type { @@ -42,6 +38,7 @@ enum blkg_iostat_type { }; struct blkcg_gq; +struct blkg_policy_data; struct blkcg { struct cgroup_subsys_state css; @@ -74,36 +71,6 @@ struct blkg_iostat_set { struct blkg_iostat last; }; -/* - * A blkcg_gq (blkg) is association between a block cgroup (blkcg) and a - * request_queue (q). This is used by blkcg policies which need to track - * information per blkcg - q pair. - * - * There can be multiple active blkcg policies and each blkg:policy pair is - * represented by a blkg_policy_data which is allocated and freed by each - * policy's pd_alloc/free_fn() methods. A policy can allocate private data - * area by allocating larger data structure which embeds blkg_policy_data - * at the beginning. - */ -struct blkg_policy_data { - /* the blkg and policy id this per-policy data belongs to */ - struct blkcg_gq *blkg; - int plid; -}; - -/* - * Policies that need to keep per-blkcg data which is independent from any - * request_queue associated to it should implement cpd_alloc/free_fn() - * methods. A policy can allocate private data area by allocating larger - * data structure which embeds blkcg_policy_data at the beginning. - * cpd_init() is invoked to let each policy handle per-blkcg data. - */ -struct blkcg_policy_data { - /* the blkcg and policy id this per-policy data belongs to */ - struct blkcg *blkcg; - int plid; -}; - /* association between a blk cgroup and a request queue */ struct blkcg_gq { /* Pointer to the associated request_queue */ @@ -139,120 +106,17 @@ struct blkcg_gq { struct rcu_head rcu_head; }; -typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp); -typedef void (blkcg_pol_init_cpd_fn)(struct blkcg_policy_data *cpd); -typedef void (blkcg_pol_free_cpd_fn)(struct blkcg_policy_data *cpd); -typedef void (blkcg_pol_bind_cpd_fn)(struct blkcg_policy_data *cpd); -typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(gfp_t gfp, - struct request_queue *q, struct blkcg *blkcg); -typedef void (blkcg_pol_init_pd_fn)(struct blkg_policy_data *pd); -typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd); -typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd); -typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd); -typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd); -typedef bool (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, - struct seq_file *s); - -struct blkcg_policy { - int plid; - /* cgroup files for the policy */ - struct cftype *dfl_cftypes; - struct cftype *legacy_cftypes; - - /* operations */ - blkcg_pol_alloc_cpd_fn *cpd_alloc_fn; - blkcg_pol_init_cpd_fn *cpd_init_fn; - blkcg_pol_free_cpd_fn *cpd_free_fn; - blkcg_pol_bind_cpd_fn *cpd_bind_fn; - - blkcg_pol_alloc_pd_fn *pd_alloc_fn; - blkcg_pol_init_pd_fn *pd_init_fn; - blkcg_pol_online_pd_fn *pd_online_fn; - blkcg_pol_offline_pd_fn *pd_offline_fn; - blkcg_pol_free_pd_fn *pd_free_fn; - blkcg_pol_reset_pd_stats_fn *pd_reset_stats_fn; - blkcg_pol_stat_pd_fn *pd_stat_fn; -}; - -extern struct blkcg blkcg_root; extern struct cgroup_subsys_state * const blkcg_root_css; -extern bool blkcg_debug_stats; - -struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, - struct request_queue *q, bool update_hint); -int blkcg_init_queue(struct request_queue *q); -void blkcg_exit_queue(struct request_queue *q); - -/* Blkio controller policy registration */ -int blkcg_policy_register(struct blkcg_policy *pol); -void blkcg_policy_unregister(struct blkcg_policy *pol); -int blkcg_activate_policy(struct request_queue *q, - const struct blkcg_policy *pol); -void blkcg_deactivate_policy(struct request_queue *q, - const struct blkcg_policy *pol); - -const char *blkg_dev_name(struct blkcg_gq *blkg); -void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, - u64 (*prfill)(struct seq_file *, - struct blkg_policy_data *, int), - const struct blkcg_policy *pol, int data, - bool show_total); -u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v); - -struct blkg_conf_ctx { - struct block_device *bdev; - struct blkcg_gq *blkg; - char *body; -}; - -struct block_device *blkcg_conf_open_bdev(char **inputp); -int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, - char *input, struct blkg_conf_ctx *ctx); -void blkg_conf_finish(struct blkg_conf_ctx *ctx); -/** - * blkcg_css - find the current css - * - * Find the css associated with either the kthread or the current task. - * This may return a dying css, so it is up to the caller to use tryget logic - * to confirm it is alive and well. - */ -static inline struct cgroup_subsys_state *blkcg_css(void) -{ - struct cgroup_subsys_state *css; - - css = kthread_blkcg(); - if (css) - return css; - return task_css(current, io_cgrp_id); -} +void blkcg_destroy_blkgs(struct blkcg *blkcg); +void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); +void blkcg_maybe_throttle_current(void); static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) { return css ? container_of(css, struct blkcg, css) : NULL; } -/** - * __bio_blkcg - internal, inconsistent version to get blkcg - * - * DO NOT USE. - * This function is inconsistent and consequently is dangerous to use. The - * first part of the function returns a blkcg where a reference is owned by the - * bio. This means it does not need to be rcu protected as it cannot go away - * with the bio owning a reference to it. However, the latter potentially gets - * it from task_css(). This can race against task migration and the cgroup - * dying. It is also semantically different as it must be called rcu protected - * and is susceptible to failure when trying to get a reference to it. - * Therefore, it is not ok to assume that *_get() will always succeed on the - * blkcg returned here. - */ -static inline struct blkcg *__bio_blkcg(struct bio *bio) -{ - if (bio && bio->bi_blkg) - return bio->bi_blkg->blkcg; - return css_to_blkcg(blkcg_css()); -} - /** * bio_blkcg - grab the blkcg associated with a bio * @bio: target bio @@ -288,22 +152,6 @@ static inline bool blk_cgroup_congested(void) return ret; } -/** - * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg - * @return: true if this bio needs to be submitted with the root blkg context. - * - * In order to avoid priority inversions we sometimes need to issue a bio as if - * it were attached to the root blkg, and then backcharge to the actual owning - * blkg. The idea is we do bio_blkcg() to look up the actual context for the - * bio and attach the appropriate blkg to the bio. Then we call this helper and - * if it is true run with the root blkg for that queue and then do any - * backcharging to the originating cgroup once the io is complete. - */ -static inline bool bio_issue_as_root_blkg(struct bio *bio) -{ - return (bio->bi_opf & (REQ_META | REQ_SWAP)) != 0; -} - /** * blkcg_parent - get the parent of a blkcg * @blkcg: blkcg of interest @@ -315,96 +163,6 @@ static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) return css_to_blkcg(blkcg->css.parent); } -/** - * __blkg_lookup - internal version of blkg_lookup() - * @blkcg: blkcg of interest - * @q: request_queue of interest - * @update_hint: whether to update lookup hint with the result or not - * - * This is internal version and shouldn't be used by policy - * implementations. Looks up blkgs for the @blkcg - @q pair regardless of - * @q's bypass state. If @update_hint is %true, the caller should be - * holding @q->queue_lock and lookup hint is updated on success. - */ -static inline struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, - struct request_queue *q, - bool update_hint) -{ - struct blkcg_gq *blkg; - - if (blkcg == &blkcg_root) - return q->root_blkg; - - blkg = rcu_dereference(blkcg->blkg_hint); - if (blkg && blkg->q == q) - return blkg; - - return blkg_lookup_slowpath(blkcg, q, update_hint); -} - -/** - * blkg_lookup - lookup blkg for the specified blkcg - q pair - * @blkcg: blkcg of interest - * @q: request_queue of interest - * - * Lookup blkg for the @blkcg - @q pair. This function should be called - * under RCU read lock. - */ -static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, - struct request_queue *q) -{ - WARN_ON_ONCE(!rcu_read_lock_held()); - return __blkg_lookup(blkcg, q, false); -} - -/** - * blk_queue_root_blkg - return blkg for the (blkcg_root, @q) pair - * @q: request_queue of interest - * - * Lookup blkg for @q at the root level. See also blkg_lookup(). - */ -static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q) -{ - return q->root_blkg; -} - -/** - * blkg_to_pdata - get policy private data - * @blkg: blkg of interest - * @pol: policy of interest - * - * Return pointer to private data associated with the @blkg-@pol pair. - */ -static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, - struct blkcg_policy *pol) -{ - return blkg ? blkg->pd[pol->plid] : NULL; -} - -static inline struct blkcg_policy_data *blkcg_to_cpd(struct blkcg *blkcg, - struct blkcg_policy *pol) -{ - return blkcg ? blkcg->cpd[pol->plid] : NULL; -} - -/** - * pdata_to_blkg - get blkg associated with policy private data - * @pd: policy private data of interest - * - * @pd is policy private data. Determine the blkg it's associated with. - */ -static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) -{ - return pd ? pd->blkg : NULL; -} - -static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd) -{ - return cpd ? cpd->blkcg : NULL; -} - -extern void blkcg_destroy_blkgs(struct blkcg *blkcg); - /** * blkcg_pin_online - pin online state * @blkcg: blkcg of interest @@ -437,231 +195,24 @@ static inline void blkcg_unpin_online(struct blkcg *blkcg) } while (blkcg); } -/** - * blkg_path - format cgroup path of blkg - * @blkg: blkg of interest - * @buf: target buffer - * @buflen: target buffer length - * - * Format the path of the cgroup of @blkg into @buf. - */ -static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen) -{ - return cgroup_path(blkg->blkcg->css.cgroup, buf, buflen); -} - -/** - * blkg_get - get a blkg reference - * @blkg: blkg to get - * - * The caller should be holding an existing reference. - */ -static inline void blkg_get(struct blkcg_gq *blkg) -{ - percpu_ref_get(&blkg->refcnt); -} - -/** - * blkg_tryget - try and get a blkg reference - * @blkg: blkg to get - * - * This is for use when doing an RCU lookup of the blkg. We may be in the midst - * of freeing this blkg, so we can only use it if the refcnt is not zero. - */ -static inline bool blkg_tryget(struct blkcg_gq *blkg) -{ - return blkg && percpu_ref_tryget(&blkg->refcnt); -} - -/** - * blkg_put - put a blkg reference - * @blkg: blkg to put - */ -static inline void blkg_put(struct blkcg_gq *blkg) -{ - percpu_ref_put(&blkg->refcnt); -} - -/** - * blkg_for_each_descendant_pre - pre-order walk of a blkg's descendants - * @d_blkg: loop cursor pointing to the current descendant - * @pos_css: used for iteration - * @p_blkg: target blkg to walk descendants of - * - * Walk @c_blkg through the descendants of @p_blkg. Must be used with RCU - * read locked. If called under either blkcg or queue lock, the iteration - * is guaranteed to include all and only online blkgs. The caller may - * update @pos_css by calling css_rightmost_descendant() to skip subtree. - * @p_blkg is included in the iteration and the first node to be visited. - */ -#define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg) \ - css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css) \ - if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ - (p_blkg)->q, false))) - -/** - * blkg_for_each_descendant_post - post-order walk of a blkg's descendants - * @d_blkg: loop cursor pointing to the current descendant - * @pos_css: used for iteration - * @p_blkg: target blkg to walk descendants of - * - * Similar to blkg_for_each_descendant_pre() but performs post-order - * traversal instead. Synchronization rules are the same. @p_blkg is - * included in the iteration and the last node to be visited. - */ -#define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg) \ - css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css) \ - if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ - (p_blkg)->q, false))) - -bool __blkcg_punt_bio_submit(struct bio *bio); - -static inline bool blkcg_punt_bio_submit(struct bio *bio) -{ - if (bio->bi_opf & REQ_CGROUP_PUNT) - return __blkcg_punt_bio_submit(bio); - else - return false; -} - -static inline void blkcg_bio_issue_init(struct bio *bio) -{ - bio_issue_init(&bio->bi_issue, bio_sectors(bio)); -} - -static inline void blkcg_use_delay(struct blkcg_gq *blkg) -{ - if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0)) - return; - if (atomic_add_return(1, &blkg->use_delay) == 1) - atomic_inc(&blkg->blkcg->css.cgroup->congestion_count); -} - -static inline int blkcg_unuse_delay(struct blkcg_gq *blkg) -{ - int old = atomic_read(&blkg->use_delay); - - if (WARN_ON_ONCE(old < 0)) - return 0; - if (old == 0) - return 0; - - /* - * We do this song and dance because we can race with somebody else - * adding or removing delay. If we just did an atomic_dec we'd end up - * negative and we'd already be in trouble. We need to subtract 1 and - * then check to see if we were the last delay so we can drop the - * congestion count on the cgroup. - */ - while (old) { - int cur = atomic_cmpxchg(&blkg->use_delay, old, old - 1); - if (cur == old) - break; - old = cur; - } - - if (old == 0) - return 0; - if (old == 1) - atomic_dec(&blkg->blkcg->css.cgroup->congestion_count); - return 1; -} - -/** - * blkcg_set_delay - Enable allocator delay mechanism with the specified delay amount - * @blkg: target blkg - * @delay: delay duration in nsecs - * - * When enabled with this function, the delay is not decayed and must be - * explicitly cleared with blkcg_clear_delay(). Must not be mixed with - * blkcg_[un]use_delay() and blkcg_add_delay() usages. - */ -static inline void blkcg_set_delay(struct blkcg_gq *blkg, u64 delay) -{ - int old = atomic_read(&blkg->use_delay); - - /* We only want 1 person setting the congestion count for this blkg. */ - if (!old && atomic_cmpxchg(&blkg->use_delay, old, -1) == old) - atomic_inc(&blkg->blkcg->css.cgroup->congestion_count); - - atomic64_set(&blkg->delay_nsec, delay); -} - -/** - * blkcg_clear_delay - Disable allocator delay mechanism - * @blkg: target blkg - * - * Disable use_delay mechanism. See blkcg_set_delay(). - */ -static inline void blkcg_clear_delay(struct blkcg_gq *blkg) -{ - int old = atomic_read(&blkg->use_delay); - - /* We only want 1 person clearing the congestion count for this blkg. */ - if (old && atomic_cmpxchg(&blkg->use_delay, old, 0) == old) - atomic_dec(&blkg->blkcg->css.cgroup->congestion_count); -} - -void blk_cgroup_bio_start(struct bio *bio); -void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta); -void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); -void blkcg_maybe_throttle_current(void); #else /* CONFIG_BLK_CGROUP */ struct blkcg { }; -struct blkg_policy_data { -}; - -struct blkcg_policy_data { -}; - struct blkcg_gq { }; -struct blkcg_policy { -}; - #define blkcg_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL)) static inline void blkcg_maybe_throttle_current(void) { } static inline bool blk_cgroup_congested(void) { return false; } #ifdef CONFIG_BLOCK - static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { } - -static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } -static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q) -{ return NULL; } -static inline int blkcg_init_queue(struct request_queue *q) { return 0; } -static inline void blkcg_exit_queue(struct request_queue *q) { } -static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; } -static inline void blkcg_policy_unregister(struct blkcg_policy *pol) { } -static inline int blkcg_activate_policy(struct request_queue *q, - const struct blkcg_policy *pol) { return 0; } -static inline void blkcg_deactivate_policy(struct request_queue *q, - const struct blkcg_policy *pol) { } - -static inline struct blkcg *__bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } +#endif /* CONFIG_BLOCK */ -static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, - struct blkcg_policy *pol) { return NULL; } -static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) { return NULL; } -static inline char *blkg_path(struct blkcg_gq *blkg) { return NULL; } -static inline void blkg_get(struct blkcg_gq *blkg) { } -static inline void blkg_put(struct blkcg_gq *blkg) { } - -static inline bool blkcg_punt_bio_submit(struct bio *bio) { return false; } -static inline void blkcg_bio_issue_init(struct bio *bio) { } -static inline void blk_cgroup_bio_start(struct bio *bio) { } - -#define blk_queue_for_each_rl(rl, q) \ - for ((rl) = &(q)->root_rl; (rl); (rl) = NULL) - -#endif /* CONFIG_BLOCK */ #endif /* CONFIG_BLK_CGROUP */ #ifdef CONFIG_BLK_CGROUP_FC_APPID -- cgit v1.2.3 From 03e4383c7ce36ac400489c8fe84724470a8251e9 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 7 Feb 2022 22:12:31 -0800 Subject: scsi: ibmvscsis: Silence -Warray-bounds warning Instead of doing a cast to storage that is too small, add a union for the high 64 bits. Silences the warnings under -Warray-bounds: drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c: In function 'ibmvscsis_send_messages': drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c:1934:44: error: array subscript 'struct viosrp_crq[0]' is partly outside array bounds of 'u64[1]' {aka 'long long unsigned int[1]'} [-Werror=array-bounds] 1934 | crq->valid = VALID_CMD_RESP_EL; | ^~ drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c:1875:13: note: while referencing 'msg_hi' 1875 | u64 msg_hi = 0; | ^~~~~~ There is no change to the resulting binary instructions. Link: https://lore.kernel.org/lkml/20220125142430.75c3160e@canb.auug.org.au Link: https://lore.kernel.org/r/20220208061231.3429486-1-keescook@chromium.org Cc: Michael Cyr Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: Tyrel Datwyler Cc: linux-scsi@vger.kernel.org Cc: target-devel@vger.kernel.org Reported-by: Stephen Rothwell Reviewed-by: Tyrel Datwyler Signed-off-by: Kees Cook Signed-off-by: Martin K. Petersen --- include/scsi/viosrp.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/scsi/viosrp.h b/include/scsi/viosrp.h index c978133c83e3..6c5559d2b285 100644 --- a/include/scsi/viosrp.h +++ b/include/scsi/viosrp.h @@ -70,12 +70,17 @@ enum viosrp_crq_status { }; struct viosrp_crq { - u8 valid; /* used by RPA */ - u8 format; /* SCSI vs out-of-band */ - u8 reserved; - u8 status; /* non-scsi failure? (e.g. DMA failure) */ - __be16 timeout; /* in seconds */ - __be16 IU_length; /* in bytes */ + union { + __be64 high; /* High 64 bits */ + struct { + u8 valid; /* used by RPA */ + u8 format; /* SCSI vs out-of-band */ + u8 reserved; + u8 status; /* non-scsi failure? (e.g. DMA failure) */ + __be16 timeout; /* in seconds */ + __be16 IU_length; /* in bytes */ + }; + }; __be64 IU_data_ptr; /* the TCE for transferring data */ }; -- cgit v1.2.3 From 26fc0ea74fcb9b76b41f5e9b89728cd1c01559cd Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 10 Feb 2022 18:43:24 +0800 Subject: scsi: libsas: Drop SAS_TASK_AT_INITIATOR This flag is now only ever set, so delete it. This also avoids a use-after-free in the pm8001 queue path, as reported in the following: https://lore.kernel.org/linux-scsi/c3cb7228-254e-9584-182b-007ac5e6fe0a@huawei.com/T/#m28c94c6d3ff582ec4a9fa54819180740e8bd4cfb https://lore.kernel.org/linux-scsi/0cc0c435-b4f2-9c76-258d-865ba50a29dd@huawei.com/ [mkp: checkpatch + two SAS_TASK_AT_INITIATOR references] Link: https://lore.kernel.org/r/1644489804-85730-3-git-send-email-john.garry@huawei.com Reviewed-by: Damien Le Moal Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 698f2032807b..549232d66b40 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -617,7 +617,6 @@ struct sas_task_slow { #define SAS_TASK_STATE_DONE 2 #define SAS_TASK_STATE_ABORTED 4 #define SAS_TASK_NEED_DEV_RESET 8 -#define SAS_TASK_AT_INITIATOR 16 extern struct sas_task *sas_alloc_task(gfp_t flags); extern struct sas_task *sas_alloc_slow_task(gfp_t flags); -- cgit v1.2.3 From 26d4a969dd0516da2d25e1e4dc5632853c774c17 Mon Sep 17 00:00:00 2001 From: Xiang Chen Date: Fri, 11 Feb 2022 14:42:55 +0800 Subject: scsi: libsas: Use void for sas_discover_event() return code The callers of function sas_discover_event() do not check its return value. The function also only ever returns 0, so use void instead. Link: https://lore.kernel.org/r/1644561778-183074-2-git-send-email-chenxiang66@hisilicon.com Reviewed-by: John Garry Signed-off-by: Xiang Chen Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 549232d66b40..fad328d3a551 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -684,7 +684,7 @@ int sas_ex_revalidate_domain(struct domain_device *); void sas_unregister_domain_devices(struct asd_sas_port *port, int gone); void sas_init_disc(struct sas_discovery *disc, struct asd_sas_port *); -int sas_discover_event(struct asd_sas_port *, enum discover_event ev); +void sas_discover_event(struct asd_sas_port *, enum discover_event ev); int sas_discover_sata(struct domain_device *); int sas_discover_end_dev(struct domain_device *); -- cgit v1.2.3 From 3a20e64281fd481f59c5c188d60632ef1d3264ea Mon Sep 17 00:00:00 2001 From: Xiang Chen Date: Fri, 11 Feb 2022 14:42:57 +0800 Subject: scsi: libsas: Remove unused parameter for function sas_ata_eh() Input parameter work_q is not unused in function sas_ata_eh(), so remove it. Link: https://lore.kernel.org/r/1644561778-183074-4-git-send-email-chenxiang66@hisilicon.com Reviewed-by: John Garry Signed-off-by: Xiang Chen Signed-off-by: Martin K. Petersen --- include/scsi/sas_ata.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/scsi/sas_ata.h b/include/scsi/sas_ata.h index 416c9c47d0e7..21e7c10c6295 100644 --- a/include/scsi/sas_ata.h +++ b/include/scsi/sas_ata.h @@ -25,8 +25,7 @@ int sas_get_ata_info(struct domain_device *dev, struct ex_phy *phy); int sas_ata_init(struct domain_device *dev); void sas_ata_task_abort(struct sas_task *task); void sas_ata_strategy_handler(struct Scsi_Host *shost); -void sas_ata_eh(struct Scsi_Host *shost, struct list_head *work_q, - struct list_head *done_q); +void sas_ata_eh(struct Scsi_Host *shost, struct list_head *work_q); void sas_ata_schedule_reset(struct domain_device *dev); void sas_ata_wait_eh(struct domain_device *dev); void sas_probe_sata(struct asd_sas_port *port); @@ -52,8 +51,7 @@ static inline void sas_ata_strategy_handler(struct Scsi_Host *shost) { } -static inline void sas_ata_eh(struct Scsi_Host *shost, struct list_head *work_q, - struct list_head *done_q) +static inline void sas_ata_eh(struct Scsi_Host *shost, struct list_head *work_q) { } -- cgit v1.2.3 From 23406e4d1f1e4653ec16b546d9480268ef284634 Mon Sep 17 00:00:00 2001 From: Xiang Chen Date: Fri, 11 Feb 2022 14:42:58 +0800 Subject: scsi: Remove unused member cmd_pool for structure scsi_host_template After commit e9c787e65c0c ("scsi: allocate scsi_cmnd structures as part of struct request"), the member cmd_pool in structure scsi_host_template is not used, so remove it. Link: https://lore.kernel.org/r/1644561778-183074-5-git-send-email-chenxiang66@hisilicon.com Reviewed-by: John Garry Signed-off-by: Xiang Chen Signed-off-by: Martin K. Petersen --- include/scsi/scsi_host.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index 72e1a347baa6..667d889b92b5 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -16,7 +16,6 @@ struct completion; struct module; struct scsi_cmnd; struct scsi_device; -struct scsi_host_cmd_pool; struct scsi_target; struct Scsi_Host; struct scsi_transport_template; @@ -493,8 +492,6 @@ struct scsi_host_template { */ u64 vendor_id; - struct scsi_host_cmd_pool *cmd_pool; - /* Delay for runtime autosuspend */ int rpm_autosuspend_delay; }; -- cgit v1.2.3 From e496132ebedd870b67f1f6d2428f9bb9d7ae27fd Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 8 Feb 2022 09:43:34 +0000 Subject: sched/fair: Adjust the allowed NUMA imbalance when SD_NUMA spans multiple LLCs Commit 7d2b5dd0bcc4 ("sched/numa: Allow a floating imbalance between NUMA nodes") allowed an imbalance between NUMA nodes such that communicating tasks would not be pulled apart by the load balancer. This works fine when there is a 1:1 relationship between LLC and node but can be suboptimal for multiple LLCs if independent tasks prematurely use CPUs sharing cache. Zen* has multiple LLCs per node with local memory channels and due to the allowed imbalance, it's far harder to tune some workloads to run optimally than it is on hardware that has 1 LLC per node. This patch allows an imbalance to exist up to the point where LLCs should be balanced between nodes. On a Zen3 machine running STREAM parallelised with OMP to have on instance per LLC the results and without binding, the results are 5.17.0-rc0 5.17.0-rc0 vanilla sched-numaimb-v6 MB/sec copy-16 162596.94 ( 0.00%) 580559.74 ( 257.05%) MB/sec scale-16 136901.28 ( 0.00%) 374450.52 ( 173.52%) MB/sec add-16 157300.70 ( 0.00%) 564113.76 ( 258.62%) MB/sec triad-16 151446.88 ( 0.00%) 564304.24 ( 272.61%) STREAM can use directives to force the spread if the OpenMP is new enough but that doesn't help if an application uses threads and it's not known in advance how many threads will be created. Coremark is a CPU and cache intensive benchmark parallelised with threads. When running with 1 thread per core, the vanilla kernel allows threads to contend on cache. With the patch; 5.17.0-rc0 5.17.0-rc0 vanilla sched-numaimb-v5 Min Score-16 368239.36 ( 0.00%) 389816.06 ( 5.86%) Hmean Score-16 388607.33 ( 0.00%) 427877.08 * 10.11%* Max Score-16 408945.69 ( 0.00%) 481022.17 ( 17.62%) Stddev Score-16 15247.04 ( 0.00%) 24966.82 ( -63.75%) CoeffVar Score-16 3.92 ( 0.00%) 5.82 ( -48.48%) It can also make a big difference for semi-realistic workloads like specjbb which can execute arbitrary numbers of threads without advance knowledge of how they should be placed. Even in cases where the average performance is neutral, the results are more stable. 5.17.0-rc0 5.17.0-rc0 vanilla sched-numaimb-v6 Hmean tput-1 71631.55 ( 0.00%) 73065.57 ( 2.00%) Hmean tput-8 582758.78 ( 0.00%) 556777.23 ( -4.46%) Hmean tput-16 1020372.75 ( 0.00%) 1009995.26 ( -1.02%) Hmean tput-24 1416430.67 ( 0.00%) 1398700.11 ( -1.25%) Hmean tput-32 1687702.72 ( 0.00%) 1671357.04 ( -0.97%) Hmean tput-40 1798094.90 ( 0.00%) 2015616.46 * 12.10%* Hmean tput-48 1972731.77 ( 0.00%) 2333233.72 ( 18.27%) Hmean tput-56 2386872.38 ( 0.00%) 2759483.38 ( 15.61%) Hmean tput-64 2909475.33 ( 0.00%) 2925074.69 ( 0.54%) Hmean tput-72 2585071.36 ( 0.00%) 2962443.97 ( 14.60%) Hmean tput-80 2994387.24 ( 0.00%) 3015980.59 ( 0.72%) Hmean tput-88 3061408.57 ( 0.00%) 3010296.16 ( -1.67%) Hmean tput-96 3052394.82 ( 0.00%) 2784743.41 ( -8.77%) Hmean tput-104 2997814.76 ( 0.00%) 2758184.50 ( -7.99%) Hmean tput-112 2955353.29 ( 0.00%) 2859705.09 ( -3.24%) Hmean tput-120 2889770.71 ( 0.00%) 2764478.46 ( -4.34%) Hmean tput-128 2871713.84 ( 0.00%) 2750136.73 ( -4.23%) Stddev tput-1 5325.93 ( 0.00%) 2002.53 ( 62.40%) Stddev tput-8 6630.54 ( 0.00%) 10905.00 ( -64.47%) Stddev tput-16 25608.58 ( 0.00%) 6851.16 ( 73.25%) Stddev tput-24 12117.69 ( 0.00%) 4227.79 ( 65.11%) Stddev tput-32 27577.16 ( 0.00%) 8761.05 ( 68.23%) Stddev tput-40 59505.86 ( 0.00%) 2048.49 ( 96.56%) Stddev tput-48 168330.30 ( 0.00%) 93058.08 ( 44.72%) Stddev tput-56 219540.39 ( 0.00%) 30687.02 ( 86.02%) Stddev tput-64 121750.35 ( 0.00%) 9617.36 ( 92.10%) Stddev tput-72 223387.05 ( 0.00%) 34081.13 ( 84.74%) Stddev tput-80 128198.46 ( 0.00%) 22565.19 ( 82.40%) Stddev tput-88 136665.36 ( 0.00%) 27905.97 ( 79.58%) Stddev tput-96 111925.81 ( 0.00%) 99615.79 ( 11.00%) Stddev tput-104 146455.96 ( 0.00%) 28861.98 ( 80.29%) Stddev tput-112 88740.49 ( 0.00%) 58288.23 ( 34.32%) Stddev tput-120 186384.86 ( 0.00%) 45812.03 ( 75.42%) Stddev tput-128 78761.09 ( 0.00%) 57418.48 ( 27.10%) Similarly, for embarassingly parallel problems like NPB-ep, there are improvements due to better spreading across LLC when the machine is not fully utilised. vanilla sched-numaimb-v6 Min ep.D 31.79 ( 0.00%) 26.11 ( 17.87%) Amean ep.D 31.86 ( 0.00%) 26.17 * 17.86%* Stddev ep.D 0.07 ( 0.00%) 0.05 ( 24.41%) CoeffVar ep.D 0.22 ( 0.00%) 0.20 ( 7.97%) Max ep.D 31.93 ( 0.00%) 26.21 ( 17.91%) Signed-off-by: Mel Gorman Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Gautham R. Shenoy Tested-by: K Prateek Nayak Link: https://lore.kernel.org/r/20220208094334.16379-3-mgorman@techsingularity.net --- include/linux/sched/topology.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 8054641c0a7b..56cffe42abbc 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -93,6 +93,7 @@ struct sched_domain { unsigned int busy_factor; /* less balancing by factor if busy */ unsigned int imbalance_pct; /* No balance until over watermark */ unsigned int cache_nice_tries; /* Leave cache hot tasks for # tries */ + unsigned int imb_numa_nr; /* Nr running tasks that allows a NUMA imbalance */ int nohz_idle; /* NOHZ IDLE status */ int flags; /* See SD_* */ -- cgit v1.2.3 From 6d240170811aad7330e6d0b3857fb0d4d9c82b56 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Mon, 7 Feb 2022 10:05:40 +0800 Subject: firmware: imx: add get resource owner api Add resource owner management API, this API could be used to check whether M4 is under control of Linux. Signed-off-by: Peng Fan Signed-off-by: Shawn Guo --- include/linux/firmware/imx/svc/rm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/firmware/imx/svc/rm.h b/include/linux/firmware/imx/svc/rm.h index 456b6a59d29b..31456f897aa9 100644 --- a/include/linux/firmware/imx/svc/rm.h +++ b/include/linux/firmware/imx/svc/rm.h @@ -59,11 +59,16 @@ enum imx_sc_rm_func { #if IS_ENABLED(CONFIG_IMX_SCU) bool imx_sc_rm_is_resource_owned(struct imx_sc_ipc *ipc, u16 resource); +int imx_sc_rm_get_resource_owner(struct imx_sc_ipc *ipc, u16 resource, u8 *pt); #else static inline bool imx_sc_rm_is_resource_owned(struct imx_sc_ipc *ipc, u16 resource) { return true; } +static inline int imx_sc_rm_get_resource_owner(struct imx_sc_ipc *ipc, u16 resource, u8 *pt) +{ + return -EOPNOTSUPP; +} #endif #endif -- cgit v1.2.3 From 3e96dcfb96e80d2f7f1edb6a1ac81b12de996fa8 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 11 Feb 2022 23:32:27 +0100 Subject: ARM: ixp4xx: Delete the Goramo MLR boardfile MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This board is replaced with the corresponding device tree. Also delete dangling platform data file only used by this boardfile and nothing else. Cc: Krzysztof Hałasa Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20220211223238.648934-3-linus.walleij@linaro.org Signed-off-by: Linus Walleij --- include/linux/platform_data/wan_ixp4xx_hss.h | 17 ----------------- 1 file changed, 17 deletions(-) delete mode 100644 include/linux/platform_data/wan_ixp4xx_hss.h (limited to 'include') diff --git a/include/linux/platform_data/wan_ixp4xx_hss.h b/include/linux/platform_data/wan_ixp4xx_hss.h deleted file mode 100644 index d525a0feb9e1..000000000000 --- a/include/linux/platform_data/wan_ixp4xx_hss.h +++ /dev/null @@ -1,17 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PLATFORM_DATA_WAN_IXP4XX_HSS_H -#define __PLATFORM_DATA_WAN_IXP4XX_HSS_H - -#include - -/* Information about built-in HSS (synchronous serial) interfaces */ -struct hss_plat_info { - int (*set_clock)(int port, unsigned int clock_type); - int (*open)(int port, void *pdev, - void (*set_carrier_cb)(void *pdev, int carrier)); - void (*close)(int port, void *pdev); - u8 txreadyq; - u32 timer_freq; -}; - -#endif -- cgit v1.2.3 From b50113cbdd1340c31e85e4cfc5f5e81ce9cbb2aa Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 11 Feb 2022 23:32:31 +0100 Subject: soc: ixp4xx: Add features from regmap helper If we want to read the CFG2 register on the expansion bus and apply the inversion and check for some hardcoded versions this helper comes in handy. Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20220211223238.648934-7-linus.walleij@linaro.org Signed-off-by: Linus Walleij --- include/linux/soc/ixp4xx/cpu.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include') diff --git a/include/linux/soc/ixp4xx/cpu.h b/include/linux/soc/ixp4xx/cpu.h index 88bd8de0e803..48c2e241ac83 100644 --- a/include/linux/soc/ixp4xx/cpu.h +++ b/include/linux/soc/ixp4xx/cpu.h @@ -9,6 +9,7 @@ #define __SOC_IXP4XX_CPU_H__ #include +#include #ifdef CONFIG_ARM #include #endif @@ -23,6 +24,9 @@ #define IXP46X_PROCESSOR_ID_VALUE 0x69054200 /* including IXP455 */ #define IXP46X_PROCESSOR_ID_MASK 0xfffffff0 +/* Feature register in the expansion bus controller */ +#define IXP4XX_EXP_CNFG2 0x2c + /* "fuse" bits of IXP_EXP_CFG2 */ /* All IXP4xx CPUs */ #define IXP4XX_FEATURE_RCOMP (1 << 0) @@ -89,6 +93,22 @@ u32 ixp4xx_read_feature_bits(void); void ixp4xx_write_feature_bits(u32 value); +static inline u32 cpu_ixp4xx_features(struct regmap *rmap) +{ + u32 val; + + regmap_read(rmap, IXP4XX_EXP_CNFG2, &val); + /* For some reason this register is inverted */ + val = ~val; + if (cpu_is_ixp42x_rev_a0()) + return IXP42X_FEATURE_MASK & ~(IXP4XX_FEATURE_RCOMP | + IXP4XX_FEATURE_AES); + if (cpu_is_ixp42x()) + return val & IXP42X_FEATURE_MASK; + if (cpu_is_ixp43x()) + return val & IXP43X_FEATURE_MASK; + return val & IXP46X_FEATURE_MASK; +} #else #define cpu_is_ixp42x_rev_a0() 0 #define cpu_is_ixp42x() 0 @@ -101,6 +121,10 @@ static inline u32 ixp4xx_read_feature_bits(void) static inline void ixp4xx_write_feature_bits(u32 value) { } +static inline u32 cpu_ixp4xx_features(struct regmap *rmap) +{ + return 0; +} #endif #endif /* _ASM_ARCH_CPU_H */ -- cgit v1.2.3 From 8754a7e61c766fbc533c627b56ff181550dca00e Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 11 Feb 2022 23:32:32 +0100 Subject: soc: ixp4xx-npe: Access syscon regs using regmap If we access the syscon (expansion bus config registers) using the syscon regmap instead of relying on direct accessor functions, we do not need to call this static code in the machine (arch/arm/mach-ixp4xx/common.c) which makes things less dependent on custom machine-dependent code. Look up the syscon regmap and handle the error: this will make deferred probe work with relation to the syscon. Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20220211223238.648934-8-linus.walleij@linaro.org Signed-off-by: Linus Walleij --- include/linux/soc/ixp4xx/npe.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/soc/ixp4xx/npe.h b/include/linux/soc/ixp4xx/npe.h index 2a91f465d456..9efeac777da1 100644 --- a/include/linux/soc/ixp4xx/npe.h +++ b/include/linux/soc/ixp4xx/npe.h @@ -3,6 +3,7 @@ #define __IXP4XX_NPE_H #include +#include extern const char *npe_names[]; @@ -17,6 +18,7 @@ struct npe_regs { struct npe { struct npe_regs __iomem *regs; + struct regmap *rmap; int id; int valid; }; -- cgit v1.2.3 From c8200f4e7267545a384fb86a4630f76958ab9df6 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 11 Feb 2022 23:32:33 +0100 Subject: net: ixp4xx_eth: Drop platform data support All IXP4xx platforms are converted to device tree, the platform data path is no longer used. Drop the code and custom include, confine the driver in its own file. Depend on OF and remove ifdefs around this, as we are all probing from OF now. Cc: David S. Miller Cc: Jakub Kicinski Cc: netdev@vger.kernel.org Signed-off-by: Linus Walleij Acked-by: Jakub Kicinski Link: https://lore.kernel.org/r/20220211223238.648934-9-linus.walleij@linaro.org Signed-off-by: Linus Walleij --- include/linux/platform_data/eth_ixp4xx.h | 21 --------------------- 1 file changed, 21 deletions(-) delete mode 100644 include/linux/platform_data/eth_ixp4xx.h (limited to 'include') diff --git a/include/linux/platform_data/eth_ixp4xx.h b/include/linux/platform_data/eth_ixp4xx.h deleted file mode 100644 index 114b0940729f..000000000000 --- a/include/linux/platform_data/eth_ixp4xx.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PLATFORM_DATA_ETH_IXP4XX -#define __PLATFORM_DATA_ETH_IXP4XX - -#include - -#define IXP4XX_ETH_NPEA 0x00 -#define IXP4XX_ETH_NPEB 0x10 -#define IXP4XX_ETH_NPEC 0x20 - -/* Information about built-in Ethernet MAC interfaces */ -struct eth_plat_info { - u8 phy; /* MII PHY ID, 0 - 31 */ - u8 rxq; /* configurable, currently 0 - 31 only */ - u8 txreadyq; - u8 hwaddr[6]; - u8 npe; /* NPE instance used by this interface */ - bool has_mdio; /* If this instance has an MDIO bus */ -}; - -#endif -- cgit v1.2.3 From 3059dfa52c07a9b6d770e87dc21b68f4295239c5 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 11 Feb 2022 23:32:35 +0100 Subject: ARM: ixp4xx: Remove feature bit accessors We switched users of the accessors over to using syscon to inspect the bits, or removed the need for checking them. Delete these accessors. Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20220211223238.648934-11-linus.walleij@linaro.org Signed-off-by: Linus Walleij --- include/linux/soc/ixp4xx/cpu.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/linux/soc/ixp4xx/cpu.h b/include/linux/soc/ixp4xx/cpu.h index 48c2e241ac83..f526ac33afea 100644 --- a/include/linux/soc/ixp4xx/cpu.h +++ b/include/linux/soc/ixp4xx/cpu.h @@ -90,9 +90,6 @@ IXP43X_PROCESSOR_ID_VALUE) #define cpu_is_ixp46x() ((read_cpuid_id() & IXP46X_PROCESSOR_ID_MASK) == \ IXP46X_PROCESSOR_ID_VALUE) - -u32 ixp4xx_read_feature_bits(void); -void ixp4xx_write_feature_bits(u32 value); static inline u32 cpu_ixp4xx_features(struct regmap *rmap) { u32 val; @@ -114,13 +111,6 @@ static inline u32 cpu_ixp4xx_features(struct regmap *rmap) #define cpu_is_ixp42x() 0 #define cpu_is_ixp43x() 0 #define cpu_is_ixp46x() 0 -static inline u32 ixp4xx_read_feature_bits(void) -{ - return 0; -} -static inline void ixp4xx_write_feature_bits(u32 value) -{ -} static inline u32 cpu_ixp4xx_features(struct regmap *rmap) { return 0; -- cgit v1.2.3 From f5c54f77b07b278cfde4a654e111c39996ac8b5b Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Fri, 4 Feb 2022 09:30:13 +0100 Subject: cpumask: Add a x86-specific cpumask_clear_cpu() helper Add a x86-specific cpumask_clear_cpu() helper which will be used in places where the explicit KASAN-instrumentation in the *_bit() helpers is unwanted. Also, always inline two more cpumask generic helpers. allyesconfig: text data bss dec hex filename 190553143 159425889 32076404 382055436 16c5b40c vmlinux.before 190551812 159424945 32076404 382053161 16c5ab29 vmlinux.after Signed-off-by: Borislav Petkov Acked-by: Marco Elver Link: https://lore.kernel.org/r/20220204083015.17317-2-bp@alien8.de --- include/linux/cpumask.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 6b06c698cd2a..fe29ac7cc469 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -102,7 +102,7 @@ extern atomic_t __num_online_cpus; extern cpumask_t cpus_booted_once_mask; -static inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits) +static __always_inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits) { #ifdef CONFIG_DEBUG_PER_CPU_MAPS WARN_ON_ONCE(cpu >= bits); @@ -110,7 +110,7 @@ static inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits) } /* verify cpu argument to cpumask_* operators */ -static inline unsigned int cpumask_check(unsigned int cpu) +static __always_inline unsigned int cpumask_check(unsigned int cpu) { cpu_max_bits_warn(cpu, nr_cpumask_bits); return cpu; -- cgit v1.2.3 From 39d01d9c4522c4ac9e0f041eaaf7cee670a6a574 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Mon, 7 Feb 2022 20:25:40 +0100 Subject: dt-bindings: power: add defines for i.MX8MP power domain This adds the DT defines for the GPC power domains found on the i.MX8MP SoC. Signed-off-by: Lucas Stach Acked-by: Rob Herring Signed-off-by: Shawn Guo --- include/dt-bindings/power/imx8mp-power.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) create mode 100644 include/dt-bindings/power/imx8mp-power.h (limited to 'include') diff --git a/include/dt-bindings/power/imx8mp-power.h b/include/dt-bindings/power/imx8mp-power.h new file mode 100644 index 000000000000..7c67689e4faf --- /dev/null +++ b/include/dt-bindings/power/imx8mp-power.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ +/* + * Copyright (C) 2020 Pengutronix, Sascha Hauer + */ + +#ifndef __DT_BINDINGS_IMX8MP_POWER_DOMAIN_POWER_H__ +#define __DT_BINDINGS_IMX8MP_POWER_DOMAIN_POWER_H__ + +#define IMX8MP_POWER_DOMAIN_MIPI_PHY1 0 +#define IMX8MP_POWER_DOMAIN_PCIE_PHY 1 +#define IMX8MP_POWER_DOMAIN_USB1_PHY 2 +#define IMX8MP_POWER_DOMAIN_USB2_PHY 3 +#define IMX8MP_POWER_DOMAIN_MLMIX 4 +#define IMX8MP_POWER_DOMAIN_AUDIOMIX 5 +#define IMX8MP_POWER_DOMAIN_GPU2D 6 +#define IMX8MP_POWER_DOMAIN_GPUMIX 7 +#define IMX8MP_POWER_DOMAIN_VPUMIX 8 +#define IMX8MP_POWER_DOMAIN_GPU3D 9 +#define IMX8MP_POWER_DOMAIN_MEDIAMIX 10 +#define IMX8MP_POWER_DOMAIN_VPU_G1 11 +#define IMX8MP_POWER_DOMAIN_VPU_G2 12 +#define IMX8MP_POWER_DOMAIN_VPU_VC8000E 13 +#define IMX8MP_POWER_DOMAIN_HDMIMIX 14 +#define IMX8MP_POWER_DOMAIN_HDMI_PHY 15 +#define IMX8MP_POWER_DOMAIN_MIPI_PHY2 16 +#define IMX8MP_POWER_DOMAIN_HSIOMIX 17 +#define IMX8MP_POWER_DOMAIN_MEDIAMIX_ISPDWP 18 + +#endif -- cgit v1.2.3 From 38294f6158b8f8af8afa82f98ca9db3a8021f020 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Mon, 7 Feb 2022 20:25:42 +0100 Subject: dt-bindings: power: imx8mp: add defines for HSIO blk-ctrl domains This adds the defines for the power domains provided by the HSIO blk-ctrl on the i.MX8MP. Signed-off-by: Lucas Stach Acked-by: Rob Herring Signed-off-by: Shawn Guo --- include/dt-bindings/power/imx8mp-power.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/power/imx8mp-power.h b/include/dt-bindings/power/imx8mp-power.h index 7c67689e4faf..9f90c40a2c6c 100644 --- a/include/dt-bindings/power/imx8mp-power.h +++ b/include/dt-bindings/power/imx8mp-power.h @@ -26,4 +26,10 @@ #define IMX8MP_POWER_DOMAIN_HSIOMIX 17 #define IMX8MP_POWER_DOMAIN_MEDIAMIX_ISPDWP 18 +#define IMX8MP_HSIOBLK_PD_USB 0 +#define IMX8MP_HSIOBLK_PD_USB_PHY1 1 +#define IMX8MP_HSIOBLK_PD_USB_PHY2 2 +#define IMX8MP_HSIOBLK_PD_PCIE 3 +#define IMX8MP_HSIOBLK_PD_PCIE_PHY 4 + #endif -- cgit v1.2.3 From 2618a0dae09ef37728dab89ff60418cbe25ae6bd Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Sat, 12 Feb 2022 09:14:49 -0800 Subject: etherdevice: Adjust ether_addr* prototypes to silence -Wstringop-overead MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With GCC 12, -Wstringop-overread was warning about an implicit cast from char[6] to char[8]. However, the extra 2 bytes are always thrown away, alignment doesn't matter, and the risk of hitting the edge of unallocated memory has been accepted, so this prototype can just be converted to a regular char *. Silences: net/core/dev.c: In function ‘bpf_prog_run_generic_xdp’: net/core/dev.c:4618:21: warning: ‘ether_addr_equal_64bits’ reading 8 bytes from a region of size 6 [-Wstringop-overread] 4618 | orig_host = ether_addr_equal_64bits(eth->h_dest, > skb->dev->dev_addr); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ net/core/dev.c:4618:21: note: referencing argument 1 of type ‘const u8[8]’ {aka ‘const unsigned char[8]’} net/core/dev.c:4618:21: note: referencing argument 2 of type ‘const u8[8]’ {aka ‘const unsigned char[8]’} In file included from net/core/dev.c:91: include/linux/etherdevice.h:375:20: note: in a call to function ‘ether_addr_equal_64bits’ 375 | static inline bool ether_addr_equal_64bits(const u8 addr1[6+2], | ^~~~~~~~~~~~~~~~~~~~~~~ Reported-by: Marc Kleine-Budde Tested-by: Marc Kleine-Budde Link: https://lore.kernel.org/netdev/20220212090811.uuzk6d76agw2vv73@pengutronix.de Cc: Jakub Kicinski Cc: "David S. Miller" Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 2ad71cc90b37..92b10e67d5f8 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -134,7 +134,7 @@ static inline bool is_multicast_ether_addr(const u8 *addr) #endif } -static inline bool is_multicast_ether_addr_64bits(const u8 addr[6+2]) +static inline bool is_multicast_ether_addr_64bits(const u8 *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 #ifdef __BIG_ENDIAN @@ -372,8 +372,7 @@ static inline bool ether_addr_equal(const u8 *addr1, const u8 *addr2) * Please note that alignment of addr1 & addr2 are only guaranteed to be 16 bits. */ -static inline bool ether_addr_equal_64bits(const u8 addr1[6+2], - const u8 addr2[6+2]) +static inline bool ether_addr_equal_64bits(const u8 *addr1, const u8 *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 u64 fold = (*(const u64 *)addr1) ^ (*(const u64 *)addr2); -- cgit v1.2.3 From 845301001308aab8fb7902548f6c3256d28b8c48 Mon Sep 17 00:00:00 2001 From: Daisuke Nojiri Date: Wed, 26 Jan 2022 10:04:10 -0800 Subject: power: supply: PCHG: Use MKBP for device event handling This change makes the PCHG driver receive device events through MKBP protocol since CrOS EC switched to deliver all peripheral charge events to the MKBP protocol. This will unify PCHG event handling on X86 and ARM. Signed-off-by: Daisuke Nojiri Signed-off-by: Sebastian Reichel --- include/linux/platform_data/cros_ec_commands.h | 64 ++++++++++++++++++++++++++ 1 file changed, 64 insertions(+) (limited to 'include') diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 271bd87bff0a..95e7e5667291 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -3386,6 +3386,9 @@ enum ec_mkbp_event { /* Send an incoming CEC message to the AP */ EC_MKBP_EVENT_CEC_MESSAGE = 9, + /* Peripheral device charger event */ + EC_MKBP_EVENT_PCHG = 12, + /* Number of MKBP events */ EC_MKBP_EVENT_COUNT, }; @@ -5527,6 +5530,67 @@ enum pchg_state { [PCHG_STATE_CONNECTED] = "CONNECTED", \ } +/* + * Update firmware of peripheral chip + */ +#define EC_CMD_PCHG_UPDATE 0x0136 + +/* Port number is encoded in bit[28:31]. */ +#define EC_MKBP_PCHG_PORT_SHIFT 28 +/* Utility macro for converting MKBP event to port number. */ +#define EC_MKBP_PCHG_EVENT_TO_PORT(e) (((e) >> EC_MKBP_PCHG_PORT_SHIFT) & 0xf) +/* Utility macro for extracting event bits. */ +#define EC_MKBP_PCHG_EVENT_MASK(e) ((e) \ + & GENMASK(EC_MKBP_PCHG_PORT_SHIFT-1, 0)) + +#define EC_MKBP_PCHG_UPDATE_OPENED BIT(0) +#define EC_MKBP_PCHG_WRITE_COMPLETE BIT(1) +#define EC_MKBP_PCHG_UPDATE_CLOSED BIT(2) +#define EC_MKBP_PCHG_UPDATE_ERROR BIT(3) +#define EC_MKBP_PCHG_DEVICE_EVENT BIT(4) + +enum ec_pchg_update_cmd { + /* Reset chip to normal mode. */ + EC_PCHG_UPDATE_CMD_RESET_TO_NORMAL = 0, + /* Reset and put a chip in update (a.k.a. download) mode. */ + EC_PCHG_UPDATE_CMD_OPEN, + /* Write a block of data containing FW image. */ + EC_PCHG_UPDATE_CMD_WRITE, + /* Close update session. */ + EC_PCHG_UPDATE_CMD_CLOSE, + /* End of commands */ + EC_PCHG_UPDATE_CMD_COUNT, +}; + +struct ec_params_pchg_update { + /* PCHG port number */ + uint8_t port; + /* enum ec_pchg_update_cmd */ + uint8_t cmd; + /* Padding */ + uint8_t reserved0; + uint8_t reserved1; + /* Version of new firmware */ + uint32_t version; + /* CRC32 of new firmware */ + uint32_t crc32; + /* Address in chip memory where is written to */ + uint32_t addr; + /* Size of */ + uint32_t size; + /* Partial data of new firmware */ + uint8_t data[]; +} __ec_align4; + +BUILD_ASSERT(EC_PCHG_UPDATE_CMD_COUNT + < BIT(sizeof(((struct ec_params_pchg_update *)0)->cmd)*8)); + +struct ec_response_pchg_update { + /* Block size */ + uint32_t block_size; +} __ec_align4; + + /*****************************************************************************/ /* Voltage regulator controls */ -- cgit v1.2.3 From f68f2ff91512c199ec24883001245912afc17873 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 20 Apr 2021 23:22:52 -0700 Subject: fortify: Detect struct member overflows in memcpy() at compile-time memcpy() is dead; long live memcpy() tl;dr: In order to eliminate a large class of common buffer overflow flaws that continue to persist in the kernel, have memcpy() (under CONFIG_FORTIFY_SOURCE) perform bounds checking of the destination struct member when they have a known size. This would have caught all of the memcpy()-related buffer write overflow flaws identified in at least the last three years. Background and analysis: While stack-based buffer overflow flaws are largely mitigated by stack canaries (and similar) features, heap-based buffer overflow flaws continue to regularly appear in the kernel. Many classes of heap buffer overflows are mitigated by FORTIFY_SOURCE when using the strcpy() family of functions, but a significant number remain exposed through the memcpy() family of functions. At its core, FORTIFY_SOURCE uses the compiler's __builtin_object_size() internal[0] to determine the available size at a target address based on the compile-time known structure layout details. It operates in two modes: outer bounds (0) and inner bounds (1). In mode 0, the size of the enclosing structure is used. In mode 1, the size of the specific field is used. For example: struct object { u16 scalar1; /* 2 bytes */ char array[6]; /* 6 bytes */ u64 scalar2; /* 8 bytes */ u32 scalar3; /* 4 bytes */ u32 scalar4; /* 4 bytes */ } instance; __builtin_object_size(instance.array, 0) == 22, since the remaining size of the enclosing structure starting from "array" is 22 bytes (6 + 8 + 4 + 4). __builtin_object_size(instance.array, 1) == 6, since the remaining size of the specific field "array" is 6 bytes. The initial implementation of FORTIFY_SOURCE used mode 0 because there were many cases of both strcpy() and memcpy() functions being used to write (or read) across multiple fields in a structure. For example, it would catch this, which is writing 2 bytes beyond the end of "instance": memcpy(&instance.array, data, 25); While this didn't protect against overwriting adjacent fields in a given structure, it would at least stop overflows from reaching beyond the end of the structure into neighboring memory, and provided a meaningful mitigation of a subset of buffer overflow flaws. However, many desirable targets remain within the enclosing structure (for example function pointers). As it happened, there were very few cases of strcpy() family functions intentionally writing beyond the end of a string buffer. Once all known cases were removed from the kernel, the strcpy() family was tightened[1] to use mode 1, providing greater mitigation coverage. What remains is switching memcpy() to mode 1 as well, but making the switch is much more difficult because of how frustrating it can be to find existing "normal" uses of memcpy() that expect to write (or read) across multiple fields. The root cause of the problem is that the C language lacks a common pattern to indicate the intent of an author's use of memcpy(), and is further complicated by the available compile-time and run-time mitigation behaviors. The FORTIFY_SOURCE mitigation comes in two halves: the compile-time half, when both the buffer size _and_ the length of the copy is known, and the run-time half, when only the buffer size is known. If neither size is known, there is no bounds checking possible. At compile-time when the compiler sees that a length will always exceed a known buffer size, a warning can be deterministically emitted. For the run-time half, the length is tested against the known size of the buffer, and the overflowing operation is detected. (The performance overhead for these tests is virtually zero.) It is relatively easy to find compile-time false-positives since a warning is always generated. Fixing the false positives, however, can be very time-consuming as there are hundreds of instances. While it's possible some over-read conditions could lead to kernel memory exposures, the bulk of the risk comes from the run-time flaws where the length of a write may end up being attacker-controlled and lead to an overflow. Many of the compile-time false-positives take a form similar to this: memcpy(&instance.scalar2, data, sizeof(instance.scalar2) + sizeof(instance.scalar3)); and the run-time ones are similar, but lack a constant expression for the size of the copy: memcpy(instance.array, data, length); The former is meant to cover multiple fields (though its style has been frowned upon more recently), but has been technically legal. Both lack any expressivity in the C language about the author's _intent_ in a way that a compiler can check when the length isn't known at compile time. A comment doesn't work well because what's needed is something a compiler can directly reason about. Is a given memcpy() call expected to overflow into neighbors? Is it not? By using the new struct_group() macro, this intent can be much more easily encoded. It is not as easy to find the run-time false-positives since the code path to exercise a seemingly out-of-bounds condition that is actually expected may not be trivially reachable. Tightening the restrictions to block an operation for a false positive will either potentially create a greater flaw (if a copy is truncated by the mitigation), or destabilize the kernel (e.g. with a BUG()), making things completely useless for the end user. As a result, tightening the memcpy() restriction (when there is a reasonable level of uncertainty of the number of false positives), needs to first WARN() with no truncation. (Though any sufficiently paranoid end-user can always opt to set the panic_on_warn=1 sysctl.) Once enough development time has passed, the mitigation can be further intensified. (Note that this patch is only the compile-time checking step, which is a prerequisite to doing run-time checking, which will come in future patches.) Given the potential frustrations of weeding out all the false positives when tightening the run-time checks, it is reasonable to wonder if these changes would actually add meaningful protection. Looking at just the last three years, there are 23 identified flaws with a CVE that mention "buffer overflow", and 11 are memcpy()-related buffer overflows. (For the remaining 12: 7 are array index overflows that would be mitigated by systems built with CONFIG_UBSAN_BOUNDS=y: CVE-2019-0145, CVE-2019-14835, CVE-2019-14896, CVE-2019-14897, CVE-2019-14901, CVE-2019-17666, CVE-2021-28952. 2 are miscalculated allocation sizes which could be mitigated with memory tagging: CVE-2019-16746, CVE-2019-2181. 1 is an iovec buffer bug maybe mitigated by memory tagging: CVE-2020-10742. 1 is a type confusion bug mitigated by stack canaries: CVE-2020-10942. 1 is a string handling logic bug with no mitigation I'm aware of: CVE-2021-28972.) At my last count on an x86_64 allmodconfig build, there are 35,294 calls to memcpy(). With callers instrumented to report all places where the buffer size is known but the length remains unknown (i.e. a run-time bounds check is added), we can count how many new run-time bounds checks are added when the destination and source arguments of memcpy() are changed to use "mode 1" bounds checking: 1,276. This means for the future run-time checking, there is a worst-case upper bounds of 3.6% false positives to fix. In addition, there were around 150 new compile-time warnings to evaluate and fix (which have now been fixed). With this instrumentation it's also possible to compare the places where the known 11 memcpy() flaw overflows manifested against the resulting list of potential new run-time bounds checks, as a measure of potential efficacy of the tightened mitigation. Much to my surprise, horror, and delight, all 11 flaws would have been detected by the newly added run-time bounds checks, making this a distinctly clear mitigation improvement: 100% coverage for known memcpy() flaws, with a possible 2 orders of magnitude gain in coverage over existing but undiscovered run-time dynamic length flaws (i.e. 1265 newly covered sites in addition to the 11 known), against only <4% of all memcpy() callers maybe gaining a false positive run-time check, with only about 150 new compile-time instances needing evaluation. Specifically these would have been mitigated: CVE-2020-24490 https://git.kernel.org/linus/a2ec905d1e160a33b2e210e45ad30445ef26ce0e CVE-2020-12654 https://git.kernel.org/linus/3a9b153c5591548612c3955c9600a98150c81875 CVE-2020-12653 https://git.kernel.org/linus/b70261a288ea4d2f4ac7cd04be08a9f0f2de4f4d CVE-2019-14895 https://git.kernel.org/linus/3d94a4a8373bf5f45cf5f939e88b8354dbf2311b CVE-2019-14816 https://git.kernel.org/linus/7caac62ed598a196d6ddf8d9c121e12e082cac3a CVE-2019-14815 https://git.kernel.org/linus/7caac62ed598a196d6ddf8d9c121e12e082cac3a CVE-2019-14814 https://git.kernel.org/linus/7caac62ed598a196d6ddf8d9c121e12e082cac3a CVE-2019-10126 https://git.kernel.org/linus/69ae4f6aac1578575126319d3f55550e7e440449 CVE-2019-9500 https://git.kernel.org/linus/1b5e2423164b3670e8bc9174e4762d297990deff no-CVE-yet https://git.kernel.org/linus/130f634da1af649205f4a3dd86cbe5c126b57914 no-CVE-yet https://git.kernel.org/linus/d10a87a3535cce2b890897914f5d0d83df669c63 To accelerate the review of potential run-time false positives, it's also worth noting that it is possible to partially automate checking by examining the memcpy() buffer argument to check for the destination struct member having a neighboring array member. It is reasonable to expect that the vast majority of run-time false positives would look like the already evaluated and fixed compile-time false positives, where the most common pattern is neighboring arrays. (And, FWIW, many of the compile-time fixes were actual bugs, so it is reasonable to assume we'll have similar cases of actual bugs getting fixed for run-time checks.) Implementation: Tighten the memcpy() destination buffer size checking to use the actual ("mode 1") target buffer size as the bounds check instead of their enclosing structure's ("mode 0") size. Use a common inline for memcpy() (and memmove() in a following patch), since all the tests are the same. All new cross-field memcpy() uses must use the struct_group() macro or similar to target a specific range of fields, so that FORTIFY_SOURCE can reason about the size and safety of the copy. For now, cross-member "mode 1" _read_ detection at compile-time will be limited to W=1 builds, since it is, unfortunately, very common. As the priority is solving write overflows, read overflows will be part of a future phase (and can be fixed in parallel, for anyone wanting to look at W=1 build output). For run-time, the "mode 0" size checking and mitigation is left unchanged, with "mode 1" to be added in stages. In this patch, no new run-time checks are added. Future patches will first bounds-check writes, and only perform a WARN() for now. This way any missed run-time false positives can be flushed out over the coming several development cycles, but system builders who have tested their workloads to be WARN()-free can enable the panic_on_warn=1 sysctl to immediately gain a mitigation against this class of buffer overflows. Once that is under way, run-time bounds-checking of reads can be similarly enabled. Related classes of flaws that will remain unmitigated: - memcpy() with flexible array structures, as the compiler does not currently have visibility into the size of the trailing flexible array. These can be fixed in the future by refactoring such cases to use a new set of flexible array structure helpers to perform the common serialization/deserialization code patterns doing allocation and/or copying. - memcpy() with raw pointers (e.g. void *, char *, etc), or otherwise having their buffer size unknown at compile time, have no good mitigation beyond memory tagging (and even that would only protect against inter-object overflow, not intra-object neighboring field overflows), or refactoring. Some kind of "fat pointer" solution is likely needed to gain proper size-of-buffer awareness. (e.g. see struct membuf) - type confusion where a higher level type's allocation size does not match the resulting cast type eventually passed to a deeper memcpy() call where the compiler cannot see the true type. In theory, greater static analysis could catch these, and the use of -Warray-bounds will help find some of these. [0] https://gcc.gnu.org/onlinedocs/gcc/Object-Size-Checking.html [1] https://git.kernel.org/linus/6a39e62abbafd1d58d1722f40c7d26ef379c6a2f Signed-off-by: Kees Cook --- include/linux/fortify-string.h | 109 ++++++++++++++++++++++++++++++++++++----- 1 file changed, 97 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index a6cd6815f249..f578d00403ad 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -8,7 +8,9 @@ void fortify_panic(const char *name) __noreturn __cold; void __read_overflow(void) __compiletime_error("detected read beyond size of object (1st parameter)"); void __read_overflow2(void) __compiletime_error("detected read beyond size of object (2nd parameter)"); +void __read_overflow2_field(size_t avail, size_t wanted) __compiletime_warning("detected read beyond size of field (2nd parameter); maybe use struct_group()?"); void __write_overflow(void) __compiletime_error("detected write beyond size of object (1st parameter)"); +void __write_overflow_field(size_t avail, size_t wanted) __compiletime_warning("detected write beyond size of field (1st parameter); maybe use struct_group()?"); #define __compiletime_strlen(p) \ ({ \ @@ -209,22 +211,105 @@ __FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size) return __underlying_memset(p, c, size); } -__FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) +/* + * To make sure the compiler can enforce protection against buffer overflows, + * memcpy(), memmove(), and memset() must not be used beyond individual + * struct members. If you need to copy across multiple members, please use + * struct_group() to create a named mirror of an anonymous struct union. + * (e.g. see struct sk_buff.) Read overflow checking is currently only + * done when a write overflow is also present, or when building with W=1. + * + * Mitigation coverage matrix + * Bounds checking at: + * +-------+-------+-------+-------+ + * | Compile time | Run time | + * memcpy() argument sizes: | write | read | write | read | + * dest source length +-------+-------+-------+-------+ + * memcpy(known, known, constant) | y | y | n/a | n/a | + * memcpy(known, unknown, constant) | y | n | n/a | V | + * memcpy(known, known, dynamic) | n | n | B | B | + * memcpy(known, unknown, dynamic) | n | n | B | V | + * memcpy(unknown, known, constant) | n | y | V | n/a | + * memcpy(unknown, unknown, constant) | n | n | V | V | + * memcpy(unknown, known, dynamic) | n | n | V | B | + * memcpy(unknown, unknown, dynamic) | n | n | V | V | + * +-------+-------+-------+-------+ + * + * y = perform deterministic compile-time bounds checking + * n = cannot perform deterministic compile-time bounds checking + * n/a = no run-time bounds checking needed since compile-time deterministic + * B = can perform run-time bounds checking (currently unimplemented) + * V = vulnerable to run-time overflow (will need refactoring to solve) + * + */ +__FORTIFY_INLINE void fortify_memcpy_chk(__kernel_size_t size, + const size_t p_size, + const size_t q_size, + const size_t p_size_field, + const size_t q_size_field, + const char *func) { - size_t p_size = __builtin_object_size(p, 0); - size_t q_size = __builtin_object_size(q, 0); - if (__builtin_constant_p(size)) { - if (p_size < size) + /* + * Length argument is a constant expression, so we + * can perform compile-time bounds checking where + * buffer sizes are known. + */ + + /* Error when size is larger than enclosing struct. */ + if (p_size > p_size_field && p_size < size) __write_overflow(); - if (q_size < size) + if (q_size > q_size_field && q_size < size) __read_overflow2(); + + /* Warn when write size argument larger than dest field. */ + if (p_size_field < size) + __write_overflow_field(p_size_field, size); + /* + * Warn for source field over-read when building with W=1 + * or when an over-write happened, so both can be fixed at + * the same time. + */ + if ((IS_ENABLED(KBUILD_EXTRA_WARN1) || p_size_field < size) && + q_size_field < size) + __read_overflow2_field(q_size_field, size); } - if (p_size < size || q_size < size) - fortify_panic(__func__); - return __underlying_memcpy(p, q, size); + /* + * At this point, length argument may not be a constant expression, + * so run-time bounds checking can be done where buffer sizes are + * known. (This is not an "else" because the above checks may only + * be compile-time warnings, and we want to still warn for run-time + * overflows.) + */ + + /* + * Always stop accesses beyond the struct that contains the + * field, when the buffer's remaining size is known. + * (The -1 test is to optimize away checks where the buffer + * lengths are unknown.) + */ + if ((p_size != (size_t)(-1) && p_size < size) || + (q_size != (size_t)(-1) && q_size < size)) + fortify_panic(func); } +#define __fortify_memcpy_chk(p, q, size, p_size, q_size, \ + p_size_field, q_size_field, op) ({ \ + size_t __fortify_size = (size_t)(size); \ + fortify_memcpy_chk(__fortify_size, p_size, q_size, \ + p_size_field, q_size_field, #op); \ + __underlying_##op(p, q, __fortify_size); \ +}) + +/* + * __builtin_object_size() must be captured here to avoid evaluating argument + * side-effects further into the macro layers. + */ +#define memcpy(p, q, s) __fortify_memcpy_chk(p, q, s, \ + __builtin_object_size(p, 0), __builtin_object_size(q, 0), \ + __builtin_object_size(p, 1), __builtin_object_size(q, 1), \ + memcpy) + __FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); @@ -304,13 +389,14 @@ __FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp) return __real_kmemdup(p, size, gfp); } -/* defined after fortified strlen and memcpy to reuse them */ +/* Defined after fortified strlen to reuse it. */ __FORTIFY_INLINE char *strcpy(char *p, const char *q) { size_t p_size = __builtin_object_size(p, 1); size_t q_size = __builtin_object_size(q, 1); size_t size; + /* If neither buffer size is known, immediately give up. */ if (p_size == (size_t)-1 && q_size == (size_t)-1) return __underlying_strcpy(p, q); size = strlen(q) + 1; @@ -320,14 +406,13 @@ __FORTIFY_INLINE char *strcpy(char *p, const char *q) /* Run-time check for dynamic size overflow. */ if (p_size < size) fortify_panic(__func__); - memcpy(p, q, size); + __underlying_memcpy(p, q, size); return p; } /* Don't use these outside the FORITFY_SOURCE implementation */ #undef __underlying_memchr #undef __underlying_memcmp -#undef __underlying_memcpy #undef __underlying_memmove #undef __underlying_memset #undef __underlying_strcat -- cgit v1.2.3 From 938a000e3f9bead24ea753286b3e4d2423275c9e Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 16 Jun 2021 14:48:19 -0700 Subject: fortify: Detect struct member overflows in memmove() at compile-time As done for memcpy(), also update memmove() to use the same tightened compile-time checks under CONFIG_FORTIFY_SOURCE. Signed-off-by: Kees Cook --- include/linux/fortify-string.h | 21 ++++----------------- 1 file changed, 4 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index f578d00403ad..098d8a322a7a 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -309,22 +309,10 @@ __FORTIFY_INLINE void fortify_memcpy_chk(__kernel_size_t size, __builtin_object_size(p, 0), __builtin_object_size(q, 0), \ __builtin_object_size(p, 1), __builtin_object_size(q, 1), \ memcpy) - -__FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - size_t q_size = __builtin_object_size(q, 0); - - if (__builtin_constant_p(size)) { - if (p_size < size) - __write_overflow(); - if (q_size < size) - __read_overflow2(); - } - if (p_size < size || q_size < size) - fortify_panic(__func__); - return __underlying_memmove(p, q, size); -} +#define memmove(p, q, s) __fortify_memcpy_chk(p, q, s, \ + __builtin_object_size(p, 0), __builtin_object_size(q, 0), \ + __builtin_object_size(p, 1), __builtin_object_size(q, 1), \ + memmove) extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); __FORTIFY_INLINE void *memscan(void *p, int c, __kernel_size_t size) @@ -413,7 +401,6 @@ __FORTIFY_INLINE char *strcpy(char *p, const char *q) /* Don't use these outside the FORITFY_SOURCE implementation */ #undef __underlying_memchr #undef __underlying_memcmp -#undef __underlying_memmove #undef __underlying_memset #undef __underlying_strcat #undef __underlying_strcpy -- cgit v1.2.3 From 28e77cc1c0686621a4d416f599cee5ab369daa0a Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 16 Jun 2021 14:42:23 -0700 Subject: fortify: Detect struct member overflows in memset() at compile-time As done for memcpy(), also update memset() to use the same tightened compile-time bounds checking under CONFIG_FORTIFY_SOURCE. Signed-off-by: Kees Cook --- include/linux/fortify-string.h | 54 +++++++++++++++++++++++++++++++++++------- 1 file changed, 46 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 098d8a322a7a..53123712bb3b 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -200,17 +200,56 @@ __FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) return p; } -__FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size) +__FORTIFY_INLINE void fortify_memset_chk(__kernel_size_t size, + const size_t p_size, + const size_t p_size_field) { - size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size)) { + /* + * Length argument is a constant expression, so we + * can perform compile-time bounds checking where + * buffer sizes are known. + */ - if (__builtin_constant_p(size) && p_size < size) - __write_overflow(); - if (p_size < size) - fortify_panic(__func__); - return __underlying_memset(p, c, size); + /* Error when size is larger than enclosing struct. */ + if (p_size > p_size_field && p_size < size) + __write_overflow(); + + /* Warn when write size is larger than dest field. */ + if (p_size_field < size) + __write_overflow_field(p_size_field, size); + } + /* + * At this point, length argument may not be a constant expression, + * so run-time bounds checking can be done where buffer sizes are + * known. (This is not an "else" because the above checks may only + * be compile-time warnings, and we want to still warn for run-time + * overflows.) + */ + + /* + * Always stop accesses beyond the struct that contains the + * field, when the buffer's remaining size is known. + * (The -1 test is to optimize away checks where the buffer + * lengths are unknown.) + */ + if (p_size != (size_t)(-1) && p_size < size) + fortify_panic("memset"); } +#define __fortify_memset_chk(p, c, size, p_size, p_size_field) ({ \ + size_t __fortify_size = (size_t)(size); \ + fortify_memset_chk(__fortify_size, p_size, p_size_field), \ + __underlying_memset(p, c, __fortify_size); \ +}) + +/* + * __builtin_object_size() must be captured here to avoid evaluating argument + * side-effects further into the macro layers. + */ +#define memset(p, c, s) __fortify_memset_chk(p, c, s, \ + __builtin_object_size(p, 0), __builtin_object_size(p, 1)) + /* * To make sure the compiler can enforce protection against buffer overflows, * memcpy(), memmove(), and memset() must not be used beyond individual @@ -401,7 +440,6 @@ __FORTIFY_INLINE char *strcpy(char *p, const char *q) /* Don't use these outside the FORITFY_SOURCE implementation */ #undef __underlying_memchr #undef __underlying_memcmp -#undef __underlying_memset #undef __underlying_strcat #undef __underlying_strcpy #undef __underlying_strlen -- cgit v1.2.3 From f361143141362485b39eb40bb4910e3f4219180f Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 8 Feb 2022 14:53:43 -0800 Subject: fortify: Replace open-coded __gnu_inline attribute Replace open-coded gnu_inline attribute with the normal kernel convention for attributes: __gnu_inline Signed-off-by: Kees Cook Reviewed-by: Nick Desaulniers Link: https://lore.kernel.org/r/20220208225350.1331628-2-keescook@chromium.org --- include/linux/fortify-string.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 53123712bb3b..439aad24ab3b 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -2,7 +2,7 @@ #ifndef _LINUX_FORTIFY_STRING_H_ #define _LINUX_FORTIFY_STRING_H_ -#define __FORTIFY_INLINE extern __always_inline __attribute__((gnu_inline)) +#define __FORTIFY_INLINE extern __always_inline __gnu_inline #define __RENAME(x) __asm__(#x) void fortify_panic(const char *name) __noreturn __cold; -- cgit v1.2.3 From f0202b8ca48cef152d4cdf775f39be6d3b372e1e Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 8 Feb 2022 14:53:44 -0800 Subject: Compiler Attributes: Add __pass_object_size for Clang In order to gain greater visibility to type information when using __builtin_object_size(), Clang has a function attribute "pass_object_size" that will make size information available for marked arguments in a function by way of implicit additional function arguments that are then wired up the __builtin_object_size(). This is needed to implement FORTIFY_SOURCE in Clang, as a workaround to Clang's __builtin_object_size() having limited visibility[1] into types across function calls (even inlines). This attribute has an additional benefit that it can be used even on non-inline functions to gain argument size information. [1] https://github.com/llvm/llvm-project/issues/53516 Cc: Nick Desaulniers Cc: Nathan Chancellor Cc: llvm@lists.linux.dev Reviewed-by: Miguel Ojeda Signed-off-by: Kees Cook Reviewed-by: Nick Desaulniers Link: https://lore.kernel.org/r/20220208225350.1331628-3-keescook@chromium.org --- include/linux/compiler_attributes.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 37e260020221..d0c503772061 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -263,6 +263,20 @@ */ #define __packed __attribute__((__packed__)) +/* + * Note: the "type" argument should match any __builtin_object_size(p, type) usage. + * + * Optional: not supported by gcc. + * Optional: not supported by icc. + * + * clang: https://clang.llvm.org/docs/AttributeReference.html#pass-object-size-pass-dynamic-object-size + */ +#if __has_attribute(__pass_object_size__) +# define __pass_object_size(type) __attribute__((__pass_object_size__(type))) +#else +# define __pass_object_size(type) +#endif + /* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-pure-function-attribute */ -- cgit v1.2.3 From d694dbaefd6fa6bdde84b704779eab53942753a5 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 8 Feb 2022 14:53:45 -0800 Subject: Compiler Attributes: Add __overloadable for Clang In order for FORTIFY_SOURCE to use __pass_object_size on an "extern inline" function, as all the fortified string functions are, the functions must be marked as being overloadable (i.e. different prototypes due to the implicitly injected object size arguments). This allows the __pass_object_size versions to take precedence. Cc: Nathan Chancellor Cc: llvm@lists.linux.dev Reviewed-by: Miguel Ojeda Reviewed-by: Nick Desaulniers Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220208225350.1331628-4-keescook@chromium.org --- include/linux/compiler_attributes.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index d0c503772061..dcaf55f5d1ae 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -257,6 +257,18 @@ */ #define __noreturn __attribute__((__noreturn__)) +/* + * Optional: not supported by gcc. + * Optional: not supported by icc. + * + * clang: https://clang.llvm.org/docs/AttributeReference.html#overloadable + */ +#if __has_attribute(__overloadable__) +# define __overloadable __attribute__((__overloadable__)) +#else +# define __overloadable +#endif + /* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-packed-type-attribute * clang: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-packed-variable-attribute -- cgit v1.2.3 From 1c7f4e5c1b6c9d9b508007c141dca77cab9434b4 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 8 Feb 2022 14:53:46 -0800 Subject: Compiler Attributes: Add __diagnose_as for Clang Clang will perform various compile-time diagnostics on uses of various functions (e.g. simple bounds-checking on strcpy(), etc). These diagnostics can be assigned to other functions (for example, new implementations of the string functions under CONFIG_FORTIFY_SOURCE) using the "diagnose_as_builtin" attribute. This allows those functions to retain their compile-time diagnostic warnings. Cc: Nathan Chancellor Cc: llvm@lists.linux.dev Reviewed-by: Miguel Ojeda Reviewed-by: Nick Desaulniers Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220208225350.1331628-5-keescook@chromium.org --- include/linux/compiler_attributes.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index dcaf55f5d1ae..445e80517cab 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -100,6 +100,19 @@ # define __copy(symbol) #endif +/* + * Optional: not supported by gcc + * Optional: only supported since clang >= 14.0 + * Optional: not supported by icc + * + * clang: https://clang.llvm.org/docs/AttributeReference.html#diagnose_as_builtin + */ +#if __has_attribute(__diagnose_as_builtin__) +# define __diagnose_as(builtin...) __attribute__((__diagnose_as_builtin__(builtin))) +#else +# define __diagnose_as(builtin...) +#endif + /* * Don't. Just don't. See commit 771c035372a0 ("deprecate the '__deprecated' * attribute warnings entirely and for good") for more information. -- cgit v1.2.3 From 0a2b782a00f33e7d06dc43d099fa071ae97bee77 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 8 Feb 2022 14:53:47 -0800 Subject: fortify: Make pointer arguments const In preparation for using Clang's __pass_object_size attribute, make all the pointer arguments to the fortified string functions const. Nothing was changing their values anyway, so this added requirement (needed by __pass_object_size) requires no code changes and has no impact on the binary instruction output. Signed-off-by: Kees Cook Reviewed-by: Nick Desaulniers Link: https://lore.kernel.org/r/20220208225350.1331628-6-keescook@chromium.org --- include/linux/fortify-string.h | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 439aad24ab3b..f874ada4b9af 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -50,7 +50,7 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) #define __underlying_strncpy __builtin_strncpy #endif -__FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) +__FORTIFY_INLINE char *strncpy(char * const p, const char *q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 1); @@ -61,7 +61,7 @@ __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) return __underlying_strncpy(p, q, size); } -__FORTIFY_INLINE char *strcat(char *p, const char *q) +__FORTIFY_INLINE char *strcat(char * const p, const char *q) { size_t p_size = __builtin_object_size(p, 1); @@ -73,7 +73,7 @@ __FORTIFY_INLINE char *strcat(char *p, const char *q) } extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); -__FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) +__FORTIFY_INLINE __kernel_size_t strnlen(const char * const p, __kernel_size_t maxlen) { size_t p_size = __builtin_object_size(p, 1); size_t p_len = __compiletime_strlen(p); @@ -94,7 +94,7 @@ __FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) } /* defined after fortified strnlen to reuse it. */ -__FORTIFY_INLINE __kernel_size_t strlen(const char *p) +__FORTIFY_INLINE __kernel_size_t strlen(const char * const p) { __kernel_size_t ret; size_t p_size = __builtin_object_size(p, 1); @@ -110,7 +110,7 @@ __FORTIFY_INLINE __kernel_size_t strlen(const char *p) /* defined after fortified strlen to reuse it */ extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); -__FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) +__FORTIFY_INLINE size_t strlcpy(char * const p, const char * const q, size_t size) { size_t p_size = __builtin_object_size(p, 1); size_t q_size = __builtin_object_size(q, 1); @@ -137,7 +137,7 @@ __FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) /* defined after fortified strnlen to reuse it */ extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy); -__FORTIFY_INLINE ssize_t strscpy(char *p, const char *q, size_t size) +__FORTIFY_INLINE ssize_t strscpy(char * const p, const char * const q, size_t size) { size_t len; /* Use string size rather than possible enclosing struct size. */ @@ -183,7 +183,7 @@ __FORTIFY_INLINE ssize_t strscpy(char *p, const char *q, size_t size) } /* defined after fortified strlen and strnlen to reuse them */ -__FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) +__FORTIFY_INLINE char *strncat(char * const p, const char * const q, __kernel_size_t count) { size_t p_len, copy_len; size_t p_size = __builtin_object_size(p, 1); @@ -354,7 +354,7 @@ __FORTIFY_INLINE void fortify_memcpy_chk(__kernel_size_t size, memmove) extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); -__FORTIFY_INLINE void *memscan(void *p, int c, __kernel_size_t size) +__FORTIFY_INLINE void *memscan(void * const p, int c, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); @@ -365,7 +365,7 @@ __FORTIFY_INLINE void *memscan(void *p, int c, __kernel_size_t size) return __real_memscan(p, c, size); } -__FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) +__FORTIFY_INLINE int memcmp(const void * const p, const void * const q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); @@ -381,7 +381,7 @@ __FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) return __underlying_memcmp(p, q, size); } -__FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) +__FORTIFY_INLINE void *memchr(const void * const p, int c, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); @@ -393,7 +393,7 @@ __FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) } void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); -__FORTIFY_INLINE void *memchr_inv(const void *p, int c, size_t size) +__FORTIFY_INLINE void *memchr_inv(const void * const p, int c, size_t size) { size_t p_size = __builtin_object_size(p, 0); @@ -405,7 +405,7 @@ __FORTIFY_INLINE void *memchr_inv(const void *p, int c, size_t size) } extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup); -__FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp) +__FORTIFY_INLINE void *kmemdup(const void * const p, size_t size, gfp_t gfp) { size_t p_size = __builtin_object_size(p, 0); @@ -417,7 +417,7 @@ __FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp) } /* Defined after fortified strlen to reuse it. */ -__FORTIFY_INLINE char *strcpy(char *p, const char *q) +__FORTIFY_INLINE char *strcpy(char * const p, const char * const q) { size_t p_size = __builtin_object_size(p, 1); size_t q_size = __builtin_object_size(q, 1); -- cgit v1.2.3 From 92df138a8d663cefebc3124041253677a53c92cf Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 8 Feb 2022 14:53:48 -0800 Subject: fortify: Use __diagnose_as() for better diagnostic coverage In preparation for using Clang's __pass_object_size, add __diagnose_as() attributes to mark the functions as being the same as the indicated builtins. When __daignose_as() is available, Clang will have a more complete ability to apply its own diagnostic analysis to callers of these functions, as if they were the builtins themselves. Without __diagnose_as, Clang's compile time diagnostic messages won't be as precise as they could be, but at least users of older toolchains will still benefit from having fortified routines. Signed-off-by: Kees Cook Reviewed-by: Nick Desaulniers Link: https://lore.kernel.org/r/20220208225350.1331628-7-keescook@chromium.org --- include/linux/fortify-string.h | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index f874ada4b9af..db1ad1c1c79a 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -50,7 +50,8 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) #define __underlying_strncpy __builtin_strncpy #endif -__FORTIFY_INLINE char *strncpy(char * const p, const char *q, __kernel_size_t size) +__FORTIFY_INLINE __diagnose_as(__builtin_strncpy, 1, 2, 3) +char *strncpy(char * const p, const char *q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 1); @@ -61,7 +62,8 @@ __FORTIFY_INLINE char *strncpy(char * const p, const char *q, __kernel_size_t si return __underlying_strncpy(p, q, size); } -__FORTIFY_INLINE char *strcat(char * const p, const char *q) +__FORTIFY_INLINE __diagnose_as(__builtin_strcat, 1, 2) +char *strcat(char * const p, const char *q) { size_t p_size = __builtin_object_size(p, 1); @@ -94,7 +96,8 @@ __FORTIFY_INLINE __kernel_size_t strnlen(const char * const p, __kernel_size_t m } /* defined after fortified strnlen to reuse it. */ -__FORTIFY_INLINE __kernel_size_t strlen(const char * const p) +__FORTIFY_INLINE __diagnose_as(__builtin_strlen, 1) +__kernel_size_t strlen(const char * const p) { __kernel_size_t ret; size_t p_size = __builtin_object_size(p, 1); @@ -183,7 +186,8 @@ __FORTIFY_INLINE ssize_t strscpy(char * const p, const char * const q, size_t si } /* defined after fortified strlen and strnlen to reuse them */ -__FORTIFY_INLINE char *strncat(char * const p, const char * const q, __kernel_size_t count) +__FORTIFY_INLINE __diagnose_as(__builtin_strncat, 1, 2, 3) +char *strncat(char * const p, const char * const q, __kernel_size_t count) { size_t p_len, copy_len; size_t p_size = __builtin_object_size(p, 1); @@ -365,7 +369,8 @@ __FORTIFY_INLINE void *memscan(void * const p, int c, __kernel_size_t size) return __real_memscan(p, c, size); } -__FORTIFY_INLINE int memcmp(const void * const p, const void * const q, __kernel_size_t size) +__FORTIFY_INLINE __diagnose_as(__builtin_memcmp, 1, 2, 3) +int memcmp(const void * const p, const void * const q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); @@ -381,7 +386,8 @@ __FORTIFY_INLINE int memcmp(const void * const p, const void * const q, __kernel return __underlying_memcmp(p, q, size); } -__FORTIFY_INLINE void *memchr(const void * const p, int c, __kernel_size_t size) +__FORTIFY_INLINE __diagnose_as(__builtin_memchr, 1, 2, 3) +void *memchr(const void * const p, int c, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); @@ -417,7 +423,8 @@ __FORTIFY_INLINE void *kmemdup(const void * const p, size_t size, gfp_t gfp) } /* Defined after fortified strlen to reuse it. */ -__FORTIFY_INLINE char *strcpy(char * const p, const char * const q) +__FORTIFY_INLINE __diagnose_as(__builtin_strcpy, 1, 2) +char *strcpy(char * const p, const char * const q) { size_t p_size = __builtin_object_size(p, 1); size_t q_size = __builtin_object_size(q, 1); -- cgit v1.2.3 From 67ebc3ab446230c77fe3b545a9d8a11cac1cfb6e Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 8 Feb 2022 14:53:49 -0800 Subject: fortify: Make sure strlen() may still be used as a constant expression In preparation for enabling Clang FORTIFY_SOURCE support, redefine strlen() as a macro that tests for being a constant expression so that strlen() can still be used in static initializers, which is lost when adding __pass_object_size and __overloadable. An example of this usage can be seen here: https://lore.kernel.org/all/202201252321.dRmWZ8wW-lkp@intel.com/ Notably, this constant expression feature of strlen() is not available for architectures that build with -ffreestanding. This means the kernel currently does not universally expect strlen() to be used this way, but since there _are_ some build configurations that depend on it, retain the characteristic for Clang FORTIFY_SOURCE builds too. Signed-off-by: Kees Cook Reviewed-by: Nick Desaulniers Link: https://lore.kernel.org/r/20220208225350.1331628-8-keescook@chromium.org --- include/linux/fortify-string.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index db1ad1c1c79a..f77cf22e2d60 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -2,6 +2,8 @@ #ifndef _LINUX_FORTIFY_STRING_H_ #define _LINUX_FORTIFY_STRING_H_ +#include + #define __FORTIFY_INLINE extern __always_inline __gnu_inline #define __RENAME(x) __asm__(#x) @@ -95,9 +97,16 @@ __FORTIFY_INLINE __kernel_size_t strnlen(const char * const p, __kernel_size_t m return ret; } -/* defined after fortified strnlen to reuse it. */ +/* + * Defined after fortified strnlen to reuse it. However, it must still be + * possible for strlen() to be used on compile-time strings for use in + * static initializers (i.e. as a constant expression). + */ +#define strlen(p) \ + __builtin_choose_expr(__is_constexpr(__builtin_strlen(p)), \ + __builtin_strlen(p), __fortify_strlen(p)) __FORTIFY_INLINE __diagnose_as(__builtin_strlen, 1) -__kernel_size_t strlen(const char * const p) +__kernel_size_t __fortify_strlen(const char * const p) { __kernel_size_t ret; size_t p_size = __builtin_object_size(p, 1); -- cgit v1.2.3 From 281d0c962752fb40866dd8d4cade68656f34bd1f Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 8 Feb 2022 14:53:50 -0800 Subject: fortify: Add Clang support Enable FORTIFY_SOURCE support for Clang: Use the new __pass_object_size and __overloadable attributes so that Clang will have appropriate visibility into argument sizes such that __builtin_object_size(p, 1) will behave correctly. Additional details available here: https://github.com/llvm/llvm-project/issues/53516 https://github.com/ClangBuiltLinux/linux/issues/1401 A bug with __builtin_constant_p() of globally defined variables was fixed in Clang 13 (and backported to 12.0.1), so FORTIFY support must depend on that version or later. Additional details here: https://bugs.llvm.org/show_bug.cgi?id=41459 commit a52f8a59aef4 ("fortify: Explicitly disable Clang support") A bug with Clang's -mregparm=3 and -m32 makes some builtins unusable, so removing -ffreestanding (to gain the needed libcall optimizations with Clang) cannot be done. Without the libcall optimizations, Clang cannot provide appropriate FORTIFY coverage, so it must be disabled for CONFIG_X86_32. Additional details here; https://github.com/llvm/llvm-project/issues/53645 Cc: Miguel Ojeda Cc: Nick Desaulniers Cc: Nathan Chancellor Cc: George Burgess IV Cc: llvm@lists.linux.dev Signed-off-by: Kees Cook Reviewed-by: Nick Desaulniers Link: https://lore.kernel.org/r/20220208225350.1331628-9-keescook@chromium.org --- include/linux/fortify-string.h | 40 ++++++++++++++++++++++++++-------------- 1 file changed, 26 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index f77cf22e2d60..295637a66c46 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -4,7 +4,7 @@ #include -#define __FORTIFY_INLINE extern __always_inline __gnu_inline +#define __FORTIFY_INLINE extern __always_inline __gnu_inline __overloadable #define __RENAME(x) __asm__(#x) void fortify_panic(const char *name) __noreturn __cold; @@ -52,8 +52,17 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) #define __underlying_strncpy __builtin_strncpy #endif +/* + * Clang's use of __builtin_object_size() within inlines needs hinting via + * __pass_object_size(). The preference is to only ever use type 1 (member + * size, rather than struct size), but there remain some stragglers using + * type 0 that will be converted in the future. + */ +#define POS __pass_object_size(1) +#define POS0 __pass_object_size(0) + __FORTIFY_INLINE __diagnose_as(__builtin_strncpy, 1, 2, 3) -char *strncpy(char * const p, const char *q, __kernel_size_t size) +char *strncpy(char * const POS p, const char *q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 1); @@ -65,7 +74,7 @@ char *strncpy(char * const p, const char *q, __kernel_size_t size) } __FORTIFY_INLINE __diagnose_as(__builtin_strcat, 1, 2) -char *strcat(char * const p, const char *q) +char *strcat(char * const POS p, const char *q) { size_t p_size = __builtin_object_size(p, 1); @@ -77,7 +86,7 @@ char *strcat(char * const p, const char *q) } extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); -__FORTIFY_INLINE __kernel_size_t strnlen(const char * const p, __kernel_size_t maxlen) +__FORTIFY_INLINE __kernel_size_t strnlen(const char * const POS p, __kernel_size_t maxlen) { size_t p_size = __builtin_object_size(p, 1); size_t p_len = __compiletime_strlen(p); @@ -106,7 +115,7 @@ __FORTIFY_INLINE __kernel_size_t strnlen(const char * const p, __kernel_size_t m __builtin_choose_expr(__is_constexpr(__builtin_strlen(p)), \ __builtin_strlen(p), __fortify_strlen(p)) __FORTIFY_INLINE __diagnose_as(__builtin_strlen, 1) -__kernel_size_t __fortify_strlen(const char * const p) +__kernel_size_t __fortify_strlen(const char * const POS p) { __kernel_size_t ret; size_t p_size = __builtin_object_size(p, 1); @@ -122,7 +131,7 @@ __kernel_size_t __fortify_strlen(const char * const p) /* defined after fortified strlen to reuse it */ extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); -__FORTIFY_INLINE size_t strlcpy(char * const p, const char * const q, size_t size) +__FORTIFY_INLINE size_t strlcpy(char * const POS p, const char * const POS q, size_t size) { size_t p_size = __builtin_object_size(p, 1); size_t q_size = __builtin_object_size(q, 1); @@ -149,7 +158,7 @@ __FORTIFY_INLINE size_t strlcpy(char * const p, const char * const q, size_t siz /* defined after fortified strnlen to reuse it */ extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy); -__FORTIFY_INLINE ssize_t strscpy(char * const p, const char * const q, size_t size) +__FORTIFY_INLINE ssize_t strscpy(char * const POS p, const char * const POS q, size_t size) { size_t len; /* Use string size rather than possible enclosing struct size. */ @@ -196,7 +205,7 @@ __FORTIFY_INLINE ssize_t strscpy(char * const p, const char * const q, size_t si /* defined after fortified strlen and strnlen to reuse them */ __FORTIFY_INLINE __diagnose_as(__builtin_strncat, 1, 2, 3) -char *strncat(char * const p, const char * const q, __kernel_size_t count) +char *strncat(char * const POS p, const char * const POS q, __kernel_size_t count) { size_t p_len, copy_len; size_t p_size = __builtin_object_size(p, 1); @@ -367,7 +376,7 @@ __FORTIFY_INLINE void fortify_memcpy_chk(__kernel_size_t size, memmove) extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); -__FORTIFY_INLINE void *memscan(void * const p, int c, __kernel_size_t size) +__FORTIFY_INLINE void *memscan(void * const POS0 p, int c, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); @@ -379,7 +388,7 @@ __FORTIFY_INLINE void *memscan(void * const p, int c, __kernel_size_t size) } __FORTIFY_INLINE __diagnose_as(__builtin_memcmp, 1, 2, 3) -int memcmp(const void * const p, const void * const q, __kernel_size_t size) +int memcmp(const void * const POS0 p, const void * const POS0 q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); @@ -396,7 +405,7 @@ int memcmp(const void * const p, const void * const q, __kernel_size_t size) } __FORTIFY_INLINE __diagnose_as(__builtin_memchr, 1, 2, 3) -void *memchr(const void * const p, int c, __kernel_size_t size) +void *memchr(const void * const POS0 p, int c, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); @@ -408,7 +417,7 @@ void *memchr(const void * const p, int c, __kernel_size_t size) } void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); -__FORTIFY_INLINE void *memchr_inv(const void * const p, int c, size_t size) +__FORTIFY_INLINE void *memchr_inv(const void * const POS0 p, int c, size_t size) { size_t p_size = __builtin_object_size(p, 0); @@ -420,7 +429,7 @@ __FORTIFY_INLINE void *memchr_inv(const void * const p, int c, size_t size) } extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup); -__FORTIFY_INLINE void *kmemdup(const void * const p, size_t size, gfp_t gfp) +__FORTIFY_INLINE void *kmemdup(const void * const POS0 p, size_t size, gfp_t gfp) { size_t p_size = __builtin_object_size(p, 0); @@ -433,7 +442,7 @@ __FORTIFY_INLINE void *kmemdup(const void * const p, size_t size, gfp_t gfp) /* Defined after fortified strlen to reuse it. */ __FORTIFY_INLINE __diagnose_as(__builtin_strcpy, 1, 2) -char *strcpy(char * const p, const char * const q) +char *strcpy(char * const POS p, const char * const POS q) { size_t p_size = __builtin_object_size(p, 1); size_t q_size = __builtin_object_size(q, 1); @@ -462,4 +471,7 @@ char *strcpy(char * const p, const char * const q) #undef __underlying_strncat #undef __underlying_strncpy +#undef POS +#undef POS0 + #endif /* _LINUX_FORTIFY_STRING_H_ */ -- cgit v1.2.3 From d315bdbfebd517cf5efabf666c8099e027ef666f Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Wed, 9 Feb 2022 16:56:33 +0100 Subject: drm/gem-shmem: Set vm_ops in static initializer Initialize default vm_ops in static initialization of the GEM SHMEM funcs, instead of the mmap code. It's simply better style. GEM helpers will later set a VMA's vm_ops from the default automatically. v2: * also update the drivers that build upon GEM SHMEM Signed-off-by: Thomas Zimmermann Reviewed-by: Steven Price Reviewed-by: Chia-I Wu Link: https://patchwork.freedesktop.org/patch/msgid/20220209155634.3994-2-tzimmermann@suse.de --- include/drm/drm_gem_shmem_helper.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/drm/drm_gem_shmem_helper.h b/include/drm/drm_gem_shmem_helper.h index 311d66c9cf4b..08e7846e8abc 100644 --- a/include/drm/drm_gem_shmem_helper.h +++ b/include/drm/drm_gem_shmem_helper.h @@ -135,6 +135,8 @@ struct sg_table *drm_gem_shmem_get_pages_sgt(struct drm_gem_shmem_object *shmem) void drm_gem_shmem_print_info(const struct drm_gem_shmem_object *shmem, struct drm_printer *p, unsigned int indent); +extern const struct vm_operations_struct drm_gem_shmem_vm_ops; + /* * GEM object functions */ -- cgit v1.2.3 From cd149eff8d2201a63c074a6d9d03e52926aa535d Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 9 Feb 2022 15:27:04 +0300 Subject: mtd: spi-nor: intel-spi: Disable write protection only if asked Currently the driver tries to disable the BIOS write protection automatically even if this is not what the user wants. For this reason modify the driver so that by default it does not touch the write protection. Only if specifically asked by the user (setting writeable=1 command line parameter) the driver tries to disable the BIOS write protection. Signed-off-by: Mika Westerberg Reviewed-by: Andy Shevchenko Reviewed-by: Mauro Lima Reviewed-by: Tudor Ambarus Acked-by: Lee Jones Link: https://lore.kernel.org/r/20220209122706.42439-2-mika.westerberg@linux.intel.com Signed-off-by: Mark Brown --- include/linux/platform_data/x86/intel-spi.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/x86/intel-spi.h b/include/linux/platform_data/x86/intel-spi.h index 7f53a5c6f35e..7dda3f690465 100644 --- a/include/linux/platform_data/x86/intel-spi.h +++ b/include/linux/platform_data/x86/intel-spi.h @@ -19,11 +19,13 @@ enum intel_spi_type { /** * struct intel_spi_boardinfo - Board specific data for Intel SPI driver * @type: Type which this controller is compatible with - * @writeable: The chip is writeable + * @set_writeable: Try to make the chip writeable (optional) + * @data: Data to be passed to @set_writeable can be %NULL */ struct intel_spi_boardinfo { enum intel_spi_type type; - bool writeable; + bool (*set_writeable)(void __iomem *base, void *data); + void *data; }; #endif /* INTEL_SPI_PDATA_H */ -- cgit v1.2.3 From e23e5a05d1fd9479586c40ffbcc056b3e34ef816 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 9 Feb 2022 15:27:05 +0300 Subject: mtd: spi-nor: intel-spi: Convert to SPI MEM The preferred way to implement SPI-NOR controller drivers is through SPI subsubsystem utilizing the SPI MEM core functions. This converts the Intel SPI flash controller driver over the SPI MEM by moving the driver from SPI-NOR subsystem to SPI subsystem and in one go make it use the SPI MEM functions. The driver name will be changed from intel-spi to spi-intel to match the convention used in the SPI subsystem. Signed-off-by: Mika Westerberg Reviewed-by: Andy Shevchenko Reviewed-by: Mauro Lima Reviewed-by: Boris Brezillon Acked-by: Lee Jones Acked-by: Pratyush Yadav Reviewed-by: Tudor Ambarus Link: https://lore.kernel.org/r/20220209122706.42439-3-mika.westerberg@linux.intel.com Signed-off-by: Mark Brown --- include/linux/mfd/lpc_ich.h | 2 +- include/linux/platform_data/x86/intel-spi.h | 31 ----------------------------- include/linux/platform_data/x86/spi-intel.h | 31 +++++++++++++++++++++++++++++ 3 files changed, 32 insertions(+), 32 deletions(-) delete mode 100644 include/linux/platform_data/x86/intel-spi.h create mode 100644 include/linux/platform_data/x86/spi-intel.h (limited to 'include') diff --git a/include/linux/mfd/lpc_ich.h b/include/linux/mfd/lpc_ich.h index 39967a5eca6d..ea4a4b1b246a 100644 --- a/include/linux/mfd/lpc_ich.h +++ b/include/linux/mfd/lpc_ich.h @@ -8,7 +8,7 @@ #ifndef LPC_ICH_H #define LPC_ICH_H -#include +#include /* GPIO resources */ #define ICH_RES_GPIO 0 diff --git a/include/linux/platform_data/x86/intel-spi.h b/include/linux/platform_data/x86/intel-spi.h deleted file mode 100644 index 7dda3f690465..000000000000 --- a/include/linux/platform_data/x86/intel-spi.h +++ /dev/null @@ -1,31 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Intel PCH/PCU SPI flash driver. - * - * Copyright (C) 2016, Intel Corporation - * Author: Mika Westerberg - */ - -#ifndef INTEL_SPI_PDATA_H -#define INTEL_SPI_PDATA_H - -enum intel_spi_type { - INTEL_SPI_BYT = 1, - INTEL_SPI_LPT, - INTEL_SPI_BXT, - INTEL_SPI_CNL, -}; - -/** - * struct intel_spi_boardinfo - Board specific data for Intel SPI driver - * @type: Type which this controller is compatible with - * @set_writeable: Try to make the chip writeable (optional) - * @data: Data to be passed to @set_writeable can be %NULL - */ -struct intel_spi_boardinfo { - enum intel_spi_type type; - bool (*set_writeable)(void __iomem *base, void *data); - void *data; -}; - -#endif /* INTEL_SPI_PDATA_H */ diff --git a/include/linux/platform_data/x86/spi-intel.h b/include/linux/platform_data/x86/spi-intel.h new file mode 100644 index 000000000000..a512ec37abbb --- /dev/null +++ b/include/linux/platform_data/x86/spi-intel.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Intel PCH/PCU SPI flash driver. + * + * Copyright (C) 2016, Intel Corporation + * Author: Mika Westerberg + */ + +#ifndef SPI_INTEL_PDATA_H +#define SPI_INTEL_PDATA_H + +enum intel_spi_type { + INTEL_SPI_BYT = 1, + INTEL_SPI_LPT, + INTEL_SPI_BXT, + INTEL_SPI_CNL, +}; + +/** + * struct intel_spi_boardinfo - Board specific data for Intel SPI driver + * @type: Type which this controller is compatible with + * @set_writeable: Try to make the chip writeable (optional) + * @data: Data to be passed to @set_writeable can be %NULL + */ +struct intel_spi_boardinfo { + enum intel_spi_type type; + bool (*set_writeable)(void __iomem *base, void *data); + void *data; +}; + +#endif /* SPI_INTEL_PDATA_H */ -- cgit v1.2.3 From f48dc6b9664963107e500aecfc2f4df27dc5afb6 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 11 Feb 2022 00:19:54 +0100 Subject: spi: Retire legacy GPIO handling All drivers using GPIOs as chip select have been rewritten to use GPIO descriptors passing the ->use_gpio_descriptors flag. Retire the code and fields used by the legacy GPIO API. Do not drop the ->use_gpio_descriptors flag: it now only indicates that we want to use GPIOs in addition to native chip selects. Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20220210231954.807904-1-linus.walleij@linaro.org Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index c3746ff35691..579d71cdf6fa 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -137,9 +137,6 @@ extern int spi_delay_exec(struct spi_delay *_delay, struct spi_transfer *xfer); * for driver coldplugging, and in uevents used for hotplugging * @driver_override: If the name of a driver is written to this attribute, then * the device will bind to the named driver and only the named driver. - * @cs_gpio: LEGACY: gpio number of the chipselect line (optional, -ENOENT when - * not using a GPIO line) use cs_gpiod in new drivers by opting in on - * the spi_master. * @cs_gpiod: gpio descriptor of the chipselect line (optional, NULL when * not using a GPIO line) * @word_delay: delay to be inserted between consecutive @@ -186,7 +183,6 @@ struct spi_device { void *controller_data; char modalias[SPI_NAME_SIZE]; const char *driver_override; - int cs_gpio; /* LEGACY: chip select gpio */ struct gpio_desc *cs_gpiod; /* chip select gpio desc */ struct spi_delay word_delay; /* inter-word delay */ /* CS delays */ @@ -418,17 +414,12 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * controller has native support for memory like operations. * @unprepare_message: undo any work done by prepare_message(). * @slave_abort: abort the ongoing transfer request on an SPI slave controller - * @cs_gpios: LEGACY: array of GPIO descs to use as chip select lines; one per - * CS number. Any individual value may be -ENOENT for CS lines that - * are not GPIOs (driven by the SPI controller itself). Use the cs_gpiods - * in new drivers. * @cs_gpiods: Array of GPIO descs to use as chip select lines; one per CS * number. Any individual value may be NULL for CS lines that * are not GPIOs (driven by the SPI controller itself). * @use_gpio_descriptors: Turns on the code in the SPI core to parse and grab - * GPIO descriptors rather than using global GPIO numbers grabbed by the - * driver. This will fill in @cs_gpiods and @cs_gpios should not be used, - * and SPI devices will have the cs_gpiod assigned rather than cs_gpio. + * GPIO descriptors. This will fill in @cs_gpiods and SPI devices will have + * the cs_gpiod assigned if a GPIO line is found for the chipselect. * @unused_native_cs: When cs_gpiods is used, spi_register_controller() will * fill in this field with the first unused native CS, to be used by SPI * controller drivers that need to drive a native CS when using GPIO CS. @@ -642,7 +633,6 @@ struct spi_controller { const struct spi_controller_mem_ops *mem_ops; /* gpio chip select */ - int *cs_gpios; struct gpio_desc **cs_gpiods; bool use_gpio_descriptors; s8 unused_native_cs; -- cgit v1.2.3 From 1de785a58035031f81a43c42f355fa1db510dc36 Mon Sep 17 00:00:00 2001 From: Jeff LaBundy Date: Sun, 23 Jan 2022 13:01:05 -0600 Subject: mfd: iqs62x: Provide device revision to sub-devices Individual sub-devices may elect to make decisions based on the specific revision of silicon encountered at probe. This data is already read from the device, but is not retained. Pass this data on to the sub-devices by adding the software and hardware numbers (registers 0x01 and 0x02, respectively) to the iqs62x_core struct. Signed-off-by: Jeff LaBundy Signed-off-by: Lee Jones --- include/linux/mfd/iqs62x.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/iqs62x.h b/include/linux/mfd/iqs62x.h index 5ced55eae11b..ffc86010af74 100644 --- a/include/linux/mfd/iqs62x.h +++ b/include/linux/mfd/iqs62x.h @@ -14,6 +14,11 @@ #define IQS624_PROD_NUM 0x43 #define IQS625_PROD_NUM 0x4E +#define IQS620_HW_NUM_V0 0x82 +#define IQS620_HW_NUM_V1 IQS620_HW_NUM_V0 +#define IQS620_HW_NUM_V2 IQS620_HW_NUM_V0 +#define IQS620_HW_NUM_V3 0x92 + #define IQS621_ALS_FLAGS 0x16 #define IQS622_ALS_FLAGS 0x14 @@ -129,6 +134,8 @@ struct iqs62x_core { struct completion fw_done; enum iqs62x_ui_sel ui_sel; unsigned long event_cache; + u8 sw_num; + u8 hw_num; }; extern const struct iqs62x_event_desc iqs62x_events[IQS62X_NUM_EVENTS]; -- cgit v1.2.3 From 65c53595bc2a14e77b455c8a12fc2631cbe43868 Mon Sep 17 00:00:00 2001 From: Colin Foster Date: Sun, 13 Feb 2022 11:12:52 -0800 Subject: net: ocelot: align macros for consistency In the ocelot.h file, several read / write macros were split across multiple lines, while others weren't. Split all macros that exceed the 80 character column width and match the style of the rest of the file. Signed-off-by: Colin Foster Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 44 +++++++++++++++++++++++++++++--------------- 1 file changed, 29 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 5c3a3597f1d2..1dbf8aff861c 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -742,25 +742,39 @@ struct ocelot_policer { u32 burst; /* bytes */ }; -#define ocelot_read_ix(ocelot, reg, gi, ri) __ocelot_read_ix(ocelot, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri)) -#define ocelot_read_gix(ocelot, reg, gi) __ocelot_read_ix(ocelot, reg, reg##_GSZ * (gi)) -#define ocelot_read_rix(ocelot, reg, ri) __ocelot_read_ix(ocelot, reg, reg##_RSZ * (ri)) -#define ocelot_read(ocelot, reg) __ocelot_read_ix(ocelot, reg, 0) - -#define ocelot_write_ix(ocelot, val, reg, gi, ri) __ocelot_write_ix(ocelot, val, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri)) -#define ocelot_write_gix(ocelot, val, reg, gi) __ocelot_write_ix(ocelot, val, reg, reg##_GSZ * (gi)) -#define ocelot_write_rix(ocelot, val, reg, ri) __ocelot_write_ix(ocelot, val, reg, reg##_RSZ * (ri)) +#define ocelot_read_ix(ocelot, reg, gi, ri) \ + __ocelot_read_ix(ocelot, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri)) +#define ocelot_read_gix(ocelot, reg, gi) \ + __ocelot_read_ix(ocelot, reg, reg##_GSZ * (gi)) +#define ocelot_read_rix(ocelot, reg, ri) \ + __ocelot_read_ix(ocelot, reg, reg##_RSZ * (ri)) +#define ocelot_read(ocelot, reg) \ + __ocelot_read_ix(ocelot, reg, 0) + +#define ocelot_write_ix(ocelot, val, reg, gi, ri) \ + __ocelot_write_ix(ocelot, val, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri)) +#define ocelot_write_gix(ocelot, val, reg, gi) \ + __ocelot_write_ix(ocelot, val, reg, reg##_GSZ * (gi)) +#define ocelot_write_rix(ocelot, val, reg, ri) \ + __ocelot_write_ix(ocelot, val, reg, reg##_RSZ * (ri)) #define ocelot_write(ocelot, val, reg) __ocelot_write_ix(ocelot, val, reg, 0) -#define ocelot_rmw_ix(ocelot, val, m, reg, gi, ri) __ocelot_rmw_ix(ocelot, val, m, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri)) -#define ocelot_rmw_gix(ocelot, val, m, reg, gi) __ocelot_rmw_ix(ocelot, val, m, reg, reg##_GSZ * (gi)) -#define ocelot_rmw_rix(ocelot, val, m, reg, ri) __ocelot_rmw_ix(ocelot, val, m, reg, reg##_RSZ * (ri)) +#define ocelot_rmw_ix(ocelot, val, m, reg, gi, ri) \ + __ocelot_rmw_ix(ocelot, val, m, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri)) +#define ocelot_rmw_gix(ocelot, val, m, reg, gi) \ + __ocelot_rmw_ix(ocelot, val, m, reg, reg##_GSZ * (gi)) +#define ocelot_rmw_rix(ocelot, val, m, reg, ri) \ + __ocelot_rmw_ix(ocelot, val, m, reg, reg##_RSZ * (ri)) #define ocelot_rmw(ocelot, val, m, reg) __ocelot_rmw_ix(ocelot, val, m, reg, 0) -#define ocelot_field_write(ocelot, reg, val) regmap_field_write((ocelot)->regfields[(reg)], (val)) -#define ocelot_field_read(ocelot, reg, val) regmap_field_read((ocelot)->regfields[(reg)], (val)) -#define ocelot_fields_write(ocelot, id, reg, val) regmap_fields_write((ocelot)->regfields[(reg)], (id), (val)) -#define ocelot_fields_read(ocelot, id, reg, val) regmap_fields_read((ocelot)->regfields[(reg)], (id), (val)) +#define ocelot_field_write(ocelot, reg, val) \ + regmap_field_write((ocelot)->regfields[(reg)], (val)) +#define ocelot_field_read(ocelot, reg, val) \ + regmap_field_read((ocelot)->regfields[(reg)], (val)) +#define ocelot_fields_write(ocelot, id, reg, val) \ + regmap_fields_write((ocelot)->regfields[(reg)], (id), (val)) +#define ocelot_fields_read(ocelot, id, reg, val) \ + regmap_fields_read((ocelot)->regfields[(reg)], (id), (val)) #define ocelot_target_read_ix(ocelot, target, reg, gi, ri) \ __ocelot_target_read_ix(ocelot, target, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri)) -- cgit v1.2.3 From 40f3a5c81555880a437dfd3301826074dff18138 Mon Sep 17 00:00:00 2001 From: Colin Foster Date: Sun, 13 Feb 2022 11:12:53 -0800 Subject: net: mscc: ocelot: add ability to perform bulk reads Regmap supports bulk register reads. Ocelot does not. This patch adds support for Ocelot to invoke bulk regmap reads. That will allow any driver that performs consecutive reads over memory regions to optimize that access. Signed-off-by: Colin Foster Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 1dbf8aff861c..6687ba35eaf3 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -742,6 +742,9 @@ struct ocelot_policer { u32 burst; /* bytes */ }; +#define ocelot_bulk_read_rix(ocelot, reg, ri, buf, count) \ + __ocelot_bulk_read_ix(ocelot, reg, reg##_RSZ * (ri), buf, count) + #define ocelot_read_ix(ocelot, reg, gi, ri) \ __ocelot_read_ix(ocelot, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri)) #define ocelot_read_gix(ocelot, reg, gi) \ @@ -798,6 +801,8 @@ struct ocelot_policer { u32 ocelot_port_readl(struct ocelot_port *port, u32 reg); void ocelot_port_writel(struct ocelot_port *port, u32 val, u32 reg); void ocelot_port_rmwl(struct ocelot_port *port, u32 val, u32 mask, u32 reg); +int __ocelot_bulk_read_ix(struct ocelot *ocelot, u32 reg, u32 offset, void *buf, + int count); u32 __ocelot_read_ix(struct ocelot *ocelot, u32 reg, u32 offset); void __ocelot_write_ix(struct ocelot *ocelot, u32 val, u32 reg, u32 offset); void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 mask, u32 reg, -- cgit v1.2.3 From d87b1c08f38a2ce40cf559df36c107a2e6c16a8f Mon Sep 17 00:00:00 2001 From: Colin Foster Date: Sun, 13 Feb 2022 11:12:54 -0800 Subject: net: mscc: ocelot: use bulk reads for stats Create and utilize bulk regmap reads instead of single access for gathering stats. The background reading of statistics happens frequently, and over a few contiguous memory regions. High speed PCIe buses and MMIO access will probably see negligible performance increase. Lower speed buses like SPI and I2C could see significant performance increase, since the bus configuration and register access times account for a large percentage of data transfer time. Signed-off-by: Colin Foster Reviewed-by: Vladimir Oltean Tested-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 6687ba35eaf3..cacb103e4bad 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -540,6 +540,13 @@ struct ocelot_stat_layout { char name[ETH_GSTRING_LEN]; }; +struct ocelot_stats_region { + struct list_head node; + u32 offset; + int count; + u32 *buf; +}; + enum ocelot_tag_prefix { OCELOT_TAG_PREFIX_DISABLED = 0, OCELOT_TAG_PREFIX_NONE, @@ -671,6 +678,7 @@ struct ocelot { struct regmap_field *regfields[REGFIELD_MAX]; const u32 *const *map; const struct ocelot_stat_layout *stats_layout; + struct list_head stats_regions; unsigned int num_stats; u32 pool_size[OCELOT_SB_NUM][OCELOT_SB_POOL_NUM]; -- cgit v1.2.3 From 90d4aa20c8cc76f5baecd423b5dc289b899ebc42 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Mon, 14 Feb 2022 07:28:38 +0100 Subject: drm/ttm: fix resource manager size type and description MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Leave the man->size units as driver defined. Signed-off-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20220214093439.2989-1-christian.koenig@amd.com Reviewed-by: Matthew Auld --- include/drm/ttm/ttm_resource.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index 69eea9d6399b..555a11fb8a7f 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -278,7 +278,7 @@ void ttm_resource_set_bo(struct ttm_resource *res, void ttm_resource_manager_init(struct ttm_resource_manager *man, struct ttm_device *bdev, - unsigned long p_size); + uint64_t size); int ttm_resource_manager_evict_all(struct ttm_device *bdev, struct ttm_resource_manager *man); -- cgit v1.2.3 From 0e05fc49c358cb49e59ce8d6ecda652951335e1e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Mon, 12 Jul 2021 14:05:01 +0200 Subject: drm/ttm: add common accounting to the resource mgr v3 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It makes sense to have this in the common manager for debugging and accounting of how much resources are used. v2: cleanup kerneldoc a bit v3: drop the atomic, update counter under lock instead Signed-off-by: Christian König Reviewed-by: Huang Rui (v1) Reviewed-by: Matthew Auld Tested-by: Bas Nieuwenhuizen Link: https://patchwork.freedesktop.org/patch/msgid/20220214093439.2989-2-christian.koenig@amd.com --- include/drm/ttm/ttm_resource.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index 555a11fb8a7f..323c14a30c6b 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -27,6 +27,7 @@ #include #include +#include #include #include #include @@ -130,10 +131,15 @@ struct ttm_resource_manager { struct dma_fence *move; /* - * Protected by the global->lru_lock. + * Protected by the bdev->lru_lock. */ - struct list_head lru[TTM_MAX_BO_PRIORITY]; + + /** + * @usage: How much of the resources are used, protected by the + * bdev->lru_lock. + */ + uint64_t usage; }; /** @@ -283,6 +289,7 @@ void ttm_resource_manager_init(struct ttm_resource_manager *man, int ttm_resource_manager_evict_all(struct ttm_device *bdev, struct ttm_resource_manager *man); +uint64_t ttm_resource_manager_usage(struct ttm_resource_manager *man); void ttm_resource_manager_debug(struct ttm_resource_manager *man, struct drm_printer *p); -- cgit v1.2.3 From baebdf48c360080710f80699eea3affbb13d6c65 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Sat, 12 Feb 2022 00:38:38 +0100 Subject: net: dev: Makes sure netif_rx() can be invoked in any context. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Dave suggested a while ago (eleven years by now) "Let's make netif_rx() work in all contexts and get rid of netif_rx_ni()". Eric agreed and pointed out that modern devices should use netif_receive_skb() to avoid the overhead. In the meantime someone added another variant, netif_rx_any_context(), which behaves as suggested. netif_rx() must be invoked with disabled bottom halves to ensure that pending softirqs, which were raised within the function, are handled. netif_rx_ni() can be invoked only from process context (bottom halves must be enabled) because the function handles pending softirqs without checking if bottom halves were disabled or not. netif_rx_any_context() invokes on the former functions by checking in_interrupts(). netif_rx() could be taught to handle both cases (disabled and enabled bottom halves) by simply disabling bottom halves while invoking netif_rx_internal(). The local_bh_enable() invocation will then invoke pending softirqs only if the BH-disable counter drops to zero. Eric is concerned about the overhead of BH-disable+enable especially in regard to the loopback driver. As critical as this driver is, it will receive a shortcut to avoid the additional overhead which is not needed. Add a local_bh_disable() section in netif_rx() to ensure softirqs are handled if needed. Provide __netif_rx() which does not disable BH and has a lockdep assert to ensure that interrupts are disabled. Use this shortcut in the loopback driver and in drivers/net/*.c. Make netif_rx_ni() and netif_rx_any_context() invoke netif_rx() so they can be removed once they are no more users left. Link: https://lkml.kernel.org/r/20100415.020246.218622820.davem@davemloft.net Signed-off-by: Sebastian Andrzej Siewior Reviewed-by: Eric Dumazet Reviewed-by: Toke Høiland-Jørgensen Signed-off-by: David S. Miller --- include/linux/netdevice.h | 14 ++++++++++++-- include/trace/events/net.h | 14 -------------- 2 files changed, 12 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5f6e2c0b0c90..e99db8341da5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3672,8 +3672,18 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog); int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb); int netif_rx(struct sk_buff *skb); -int netif_rx_ni(struct sk_buff *skb); -int netif_rx_any_context(struct sk_buff *skb); +int __netif_rx(struct sk_buff *skb); + +static inline int netif_rx_ni(struct sk_buff *skb) +{ + return netif_rx(skb); +} + +static inline int netif_rx_any_context(struct sk_buff *skb) +{ + return netif_rx(skb); +} + int netif_receive_skb(struct sk_buff *skb); int netif_receive_skb_core(struct sk_buff *skb); void netif_receive_skb_list_internal(struct list_head *head); diff --git a/include/trace/events/net.h b/include/trace/events/net.h index 78c448c6ab4c..032b431b987b 100644 --- a/include/trace/events/net.h +++ b/include/trace/events/net.h @@ -260,13 +260,6 @@ DEFINE_EVENT(net_dev_rx_verbose_template, netif_rx_entry, TP_ARGS(skb) ); -DEFINE_EVENT(net_dev_rx_verbose_template, netif_rx_ni_entry, - - TP_PROTO(const struct sk_buff *skb), - - TP_ARGS(skb) -); - DECLARE_EVENT_CLASS(net_dev_rx_exit_template, TP_PROTO(int ret), @@ -312,13 +305,6 @@ DEFINE_EVENT(net_dev_rx_exit_template, netif_rx_exit, TP_ARGS(ret) ); -DEFINE_EVENT(net_dev_rx_exit_template, netif_rx_ni_exit, - - TP_PROTO(int ret), - - TP_ARGS(ret) -); - DEFINE_EVENT(net_dev_rx_exit_template, netif_receive_skb_list_exit, TP_PROTO(int ret), -- cgit v1.2.3 From 76f05d88623e559eb9fc41db9fb911e67fab0e7a Mon Sep 17 00:00:00 2001 From: M Chetan Kumar Date: Mon, 14 Feb 2022 12:46:52 +0530 Subject: net: wwan: debugfs obtained dev reference not dropped WWAN driver call's wwan_get_debugfs_dir() to obtain WWAN debugfs dir entry. As part of this procedure it returns a reference to a found device. Since there is no debugfs interface available at WWAN subsystem, it is not possible to drop dev reference post debugfs use. This leads to side effects like post wwan driver load and reload the wwan instance gets increment from wwanX to wwanX+1. A new debugfs interface is added in wwan subsystem so that wwan driver can drop the obtained dev reference post debugfs use. void wwan_put_debugfs_dir(struct dentry *dir) Signed-off-by: M Chetan Kumar Signed-off-by: David S. Miller --- include/linux/wwan.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/wwan.h b/include/linux/wwan.h index afb3334ec8c5..5ce2acf444fb 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -174,11 +174,13 @@ void wwan_unregister_ops(struct device *parent); #ifdef CONFIG_WWAN_DEBUGFS struct dentry *wwan_get_debugfs_dir(struct device *parent); +void wwan_put_debugfs_dir(struct dentry *dir); #else static inline struct dentry *wwan_get_debugfs_dir(struct device *parent) { return ERR_PTR(-ENODEV); } +static inline void wwan_put_debugfs_dir(struct dentry *dir) {} #endif #endif /* __WWAN_H */ -- cgit v1.2.3 From 32e92d9f6f876721cc4f565f8369d542b6266380 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 3 Feb 2022 17:59:20 +0800 Subject: iommu/iova: Separate out rcache init Currently the rcache structures are allocated for all IOVA domains, even if they do not use "fast" alloc+free interface. This is wasteful of memory. In addition, fails in init_iova_rcaches() are not handled safely, which is less than ideal. Make "fast" users call a separate rcache init explicitly, which includes error checking. Signed-off-by: John Garry Reviewed-by: Robin Murphy Acked-by: Michael S. Tsirkin Link: https://lore.kernel.org/r/1643882360-241739-1-git-send-email-john.garry@huawei.com Signed-off-by: Joerg Roedel --- include/linux/iova.h | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/iova.h b/include/linux/iova.h index cea79cb9f26c..320a70e40233 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -21,18 +21,8 @@ struct iova { unsigned long pfn_lo; /* Lowest allocated pfn */ }; -struct iova_magazine; -struct iova_cpu_rcache; -#define IOVA_RANGE_CACHE_MAX_SIZE 6 /* log of max cached IOVA range size (in pages) */ -#define MAX_GLOBAL_MAGS 32 /* magazines per bin */ - -struct iova_rcache { - spinlock_t lock; - unsigned long depot_size; - struct iova_magazine *depot[MAX_GLOBAL_MAGS]; - struct iova_cpu_rcache __percpu *cpu_rcaches; -}; +struct iova_rcache; /* holds all the iova translations for a domain */ struct iova_domain { @@ -46,7 +36,7 @@ struct iova_domain { unsigned long max32_alloc_size; /* Size of last failed allocation */ struct iova anchor; /* rbtree lookup anchor */ - struct iova_rcache rcaches[IOVA_RANGE_CACHE_MAX_SIZE]; /* IOVA range caches */ + struct iova_rcache *rcaches; struct hlist_node cpuhp_dead; }; @@ -102,6 +92,7 @@ struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo, unsigned long pfn_hi); void init_iova_domain(struct iova_domain *iovad, unsigned long granule, unsigned long start_pfn); +int iova_domain_init_rcaches(struct iova_domain *iovad); struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn); void put_iova_domain(struct iova_domain *iovad); #else -- cgit v1.2.3 From e9e9feebcbc14b174fef862842f8cc9a388e1db3 Mon Sep 17 00:00:00 2001 From: Janis Schoetterl-Glausch Date: Fri, 11 Feb 2022 19:22:10 +0100 Subject: KVM: s390: Add optional storage key checking to MEMOP IOCTL User space needs a mechanism to perform key checked accesses when emulating instructions. The key can be passed as an additional argument. Having an additional argument is flexible, as user space can pass the guest PSW's key, in order to make an access the same way the CPU would, or pass another key if necessary. Signed-off-by: Janis Schoetterl-Glausch Reviewed-by: Claudio Imbrenda Reviewed-by: Christian Borntraeger Reviewed-by: Janosch Frank Link: https://lore.kernel.org/r/20220211182215.2730017-6-scgl@linux.ibm.com Signed-off-by: Christian Borntraeger --- include/uapi/linux/kvm.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 5191b57e1562..4566f429db2c 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -562,7 +562,10 @@ struct kvm_s390_mem_op { __u32 op; /* type of operation */ __u64 buf; /* buffer in userspace */ union { - __u8 ar; /* the access register number */ + struct { + __u8 ar; /* the access register number */ + __u8 key; /* access key, ignored if flag unset */ + }; __u32 sida_offset; /* offset into the sida */ __u8 reserved[32]; /* should be set to 0 */ }; @@ -575,6 +578,7 @@ struct kvm_s390_mem_op { /* flags for kvm_s390_mem_op->flags */ #define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) #define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) +#define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2) /* for KVM_INTERRUPT */ struct kvm_interrupt { -- cgit v1.2.3 From ef11c9463ae006302ce170a401854a48ea0532ca Mon Sep 17 00:00:00 2001 From: Janis Schoetterl-Glausch Date: Fri, 11 Feb 2022 19:22:11 +0100 Subject: KVM: s390: Add vm IOCTL for key checked guest absolute memory access Channel I/O honors storage keys and is performed on absolute memory. For I/O emulation user space therefore needs to be able to do key checked accesses. The vm IOCTL supports read/write accesses, as well as checking if an access would succeed. Unlike relying on KVM_S390_GET_SKEYS for key checking would, the vm IOCTL performs the check in lockstep with the read or write, by, ultimately, mapping the access to move instructions that support key protection checking with a supplied key. Fetch and storage protection override are not applicable to absolute accesses and so are not applied as they are when using the vcpu memop. Signed-off-by: Janis Schoetterl-Glausch Reviewed-by: Christian Borntraeger Link: https://lore.kernel.org/r/20220211182215.2730017-7-scgl@linux.ibm.com Signed-off-by: Christian Borntraeger --- include/uapi/linux/kvm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 4566f429db2c..4bc7623def87 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -575,6 +575,8 @@ struct kvm_s390_mem_op { #define KVM_S390_MEMOP_LOGICAL_WRITE 1 #define KVM_S390_MEMOP_SIDA_READ 2 #define KVM_S390_MEMOP_SIDA_WRITE 3 +#define KVM_S390_MEMOP_ABSOLUTE_READ 4 +#define KVM_S390_MEMOP_ABSOLUTE_WRITE 5 /* flags for kvm_s390_mem_op->flags */ #define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) #define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) -- cgit v1.2.3 From d004079edc166ff19605475211305923c708b4d5 Mon Sep 17 00:00:00 2001 From: Janis Schoetterl-Glausch Date: Fri, 11 Feb 2022 19:22:13 +0100 Subject: KVM: s390: Add capability for storage key extension of MEM_OP IOCTL Availability of the KVM_CAP_S390_MEM_OP_EXTENSION capability signals that: * The vcpu MEM_OP IOCTL supports storage key checking. * The vm MEM_OP IOCTL exists. Signed-off-by: Janis Schoetterl-Glausch Reviewed-by: Janosch Frank Reviewed-by: Christian Borntraeger Link: https://lore.kernel.org/r/20220211182215.2730017-9-scgl@linux.ibm.com Signed-off-by: Christian Borntraeger --- include/uapi/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 4bc7623def87..08756eeea065 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1140,6 +1140,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_VM_GPA_BITS 207 #define KVM_CAP_XSAVE2 208 #define KVM_CAP_SYS_ATTRIBUTES 209 +#define KVM_CAP_S390_MEM_OP_EXTENSION 210 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 5e35d0eb472b48ac9c8ef7017753b8a1f765aa01 Mon Sep 17 00:00:00 2001 From: Janis Schoetterl-Glausch Date: Fri, 11 Feb 2022 19:22:14 +0100 Subject: KVM: s390: Update api documentation for memop ioctl Document all currently existing operations, flags and explain under which circumstances they are available. Document the recently introduced absolute operations and the storage key protection flag, as well as the existing SIDA operations. Signed-off-by: Janis Schoetterl-Glausch Reviewed-by: Janosch Frank Link: https://lore.kernel.org/r/20220211182215.2730017-10-scgl@linux.ibm.com Signed-off-by: Christian Borntraeger --- include/uapi/linux/kvm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 08756eeea065..dbc550bbd9fa 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -567,7 +567,7 @@ struct kvm_s390_mem_op { __u8 key; /* access key, ignored if flag unset */ }; __u32 sida_offset; /* offset into the sida */ - __u8 reserved[32]; /* should be set to 0 */ + __u8 reserved[32]; /* ignored */ }; }; /* types for kvm_s390_mem_op->op */ -- cgit v1.2.3 From b2638e56c2ced2ca258d22f939c47327b189e00c Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 3 Feb 2022 14:56:13 +0200 Subject: device property: Don't split fwnode_get_irq*() APIs in the code New fwnode_get_irq_byname() landed after an unrelated function by ordering. Move fwnode_iomap(), so fwnode_get_irq*() APIs will go together. No functional change intended. Signed-off-by: Andy Shevchenko Reviewed-by: Sakari Ailus Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/property.h b/include/linux/property.h index 95d56a562b6a..4cd4b326941f 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -123,8 +123,6 @@ void fwnode_handle_put(struct fwnode_handle *fwnode); int fwnode_irq_get(const struct fwnode_handle *fwnode, unsigned int index); int fwnode_irq_get_byname(const struct fwnode_handle *fwnode, const char *name); -void __iomem *fwnode_iomap(struct fwnode_handle *fwnode, int index); - unsigned int device_get_child_node_count(struct device *dev); static inline bool device_property_read_bool(struct device *dev, @@ -388,8 +386,10 @@ enum dev_dma_attr device_get_dma_attr(struct device *dev); const void *device_get_match_data(struct device *dev); int device_get_phy_mode(struct device *dev); - int fwnode_get_phy_mode(struct fwnode_handle *fwnode); + +void __iomem *fwnode_iomap(struct fwnode_handle *fwnode, int index); + struct fwnode_handle *fwnode_graph_get_next_endpoint( const struct fwnode_handle *fwnode, struct fwnode_handle *prev); struct fwnode_handle * -- cgit v1.2.3 From 7a853c2d5951419fdf3c1c9d2b6f5a38f6a6857d Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Mon, 7 Feb 2022 15:02:45 -0800 Subject: mm: Change CONFIG option for mm->pasid field This currently depends on CONFIG_IOMMU_SUPPORT. But it is only needed when CONFIG_IOMMU_SVA option is enabled. Change the CONFIG guards around definition and initialization of mm->pasid field. Suggested-by: Jacob Pan Signed-off-by: Fenghua Yu Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Reviewed-by: Thomas Gleixner Reviewed-by: Lu Baolu Link: https://lore.kernel.org/r/20220207230254.3342514-3-fenghua.yu@intel.com --- include/linux/mm_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5140e5feb486..c5cbfd7915ad 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -631,7 +631,7 @@ struct mm_struct { #endif struct work_struct async_put_work; -#ifdef CONFIG_IOMMU_SUPPORT +#ifdef CONFIG_IOMMU_SVA u32 pasid; #endif } __randomize_layout; -- cgit v1.2.3 From 150154aae4311e7e6458903baecdc8fffe981ed3 Mon Sep 17 00:00:00 2001 From: "Uladzislau Rezki (Sony)" Date: Wed, 1 Dec 2021 10:20:53 +0100 Subject: rcu: Fix description of kvfree_rcu() The kvfree_rcu() header comment's description of the "ptr" parameter is unclear, therefore rephrase it to make it clear that it is a pointer to the memory to eventually be passed to kvfree(). Reported-by: Steven Rostedt Signed-off-by: Uladzislau Rezki (Sony) Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 88b42eb46406..9d7df8d36af0 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -924,7 +924,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * * kvfree_rcu(ptr); * - * where @ptr is a pointer to kvfree(). + * where @ptr is the pointer to be freed by kvfree(). * * Please note, head-less way of freeing is permitted to * use from a context that has to follow might_sleep() -- cgit v1.2.3 From 58d4292bd037b01fbb940a5170817f7d40caa9d5 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 14 Jan 2022 16:07:28 -0800 Subject: rcu: Uninline multi-use function: finish_rcuwait() This is a rarely used function, so uninlining its 3 instructions is probably a win or a wash - but the main motivation is to make independent of task_struct details. Signed-off-by: Ingo Molnar Signed-off-by: Paul E. McKenney --- include/linux/rcuwait.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h index 61c56cca95c4..8052d34da782 100644 --- a/include/linux/rcuwait.h +++ b/include/linux/rcuwait.h @@ -47,11 +47,7 @@ static inline void prepare_to_rcuwait(struct rcuwait *w) rcu_assign_pointer(w->task, current); } -static inline void finish_rcuwait(struct rcuwait *w) -{ - rcu_assign_pointer(w->task, NULL); - __set_current_state(TASK_RUNNING); -} +extern void finish_rcuwait(struct rcuwait *w); #define rcuwait_wait_event(w, condition, state) \ ({ \ -- cgit v1.2.3 From e6339d3b443c436c3b8f45eefec2212a8c07065d Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 14 Jan 2022 16:16:55 -0800 Subject: rcu: Remove __read_mostly annotations from rcu_scheduler_active externs Remove the __read_mostly attributes from the rcu_scheduler_active extern declarations, because these attributes are ignored for prototypes and we'd have to include the full header to gain this functionally pointless attribute defined. Signed-off-by: Ingo Molnar Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 2 +- include/linux/rcutree.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 9d7df8d36af0..e7c39c200e2b 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -84,7 +84,7 @@ static inline int rcu_preempt_depth(void) /* Internal to kernel */ void rcu_init(void); -extern int rcu_scheduler_active __read_mostly; +extern int rcu_scheduler_active; void rcu_sched_clock_irq(int user); void rcu_report_dead(unsigned int cpu); void rcutree_migrate_callbacks(int cpu); diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 53209d669400..76665db179fa 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -62,7 +62,7 @@ static inline void rcu_irq_exit_check_preempt(void) { } void exit_rcu(void); void rcu_scheduler_starting(void); -extern int rcu_scheduler_active __read_mostly; +extern int rcu_scheduler_active; void rcu_end_inkernel_boot(void); bool rcu_inkernel_boot_has_ended(void); bool rcu_is_watching(void); -- cgit v1.2.3 From 7a5fbc9bcba5325a45297a4ba00091f39a63a1ed Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Mon, 7 Feb 2022 15:02:46 -0800 Subject: iommu/ioasid: Introduce a helper to check for valid PASIDs Define a pasid_valid() helper to check if a given PASID is valid. [ bp: Massage commit message. ] Suggested-by: Ashok Raj Suggested-by: Jacob Pan Signed-off-by: Fenghua Yu Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Reviewed-by: Thomas Gleixner Reviewed-by: Lu Baolu Link: https://lore.kernel.org/r/20220207230254.3342514-4-fenghua.yu@intel.com --- include/linux/ioasid.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h index e9dacd4b9f6b..2237f64dbaae 100644 --- a/include/linux/ioasid.h +++ b/include/linux/ioasid.h @@ -41,6 +41,10 @@ void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, int ioasid_register_allocator(struct ioasid_allocator_ops *allocator); void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator); int ioasid_set_data(ioasid_t ioasid, void *data); +static inline bool pasid_valid(ioasid_t ioasid) +{ + return ioasid != INVALID_IOASID; +} #else /* !CONFIG_IOASID */ static inline ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, @@ -78,5 +82,10 @@ static inline int ioasid_set_data(ioasid_t ioasid, void *data) return -ENOTSUPP; } +static inline bool pasid_valid(ioasid_t ioasid) +{ + return false; +} + #endif /* CONFIG_IOASID */ #endif /* __LINUX_IOASID_H */ -- cgit v1.2.3 From a6cbd44093ef305b02ad5f80ed54abf0148a696c Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Mon, 7 Feb 2022 15:02:47 -0800 Subject: kernel/fork: Initialize mm's PASID A new mm doesn't have a PASID yet when it's created. Initialize the mm's PASID on fork() or for init_mm to INVALID_IOASID (-1). INIT_PASID (0) is reserved for kernel legacy DMA PASID. It cannot be allocated to a user process. Initializing the process's PASID to 0 may cause confusion that's why the process uses the reserved kernel legacy DMA PASID. Initializing the PASID to INVALID_IOASID (-1) explicitly tells the process doesn't have a valid PASID yet. Even though the only user of mm_pasid_init() is in fork.c, define it in as the first of three mm/pasid life cycle functions (init/set/drop) to keep these all together. Suggested-by: Dave Hansen Signed-off-by: Fenghua Yu Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Reviewed-by: Thomas Gleixner Link: https://lore.kernel.org/r/20220207230254.3342514-5-fenghua.yu@intel.com --- include/linux/sched/mm.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index aa5f09ca5bcf..c74d1edbac2f 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -8,6 +8,7 @@ #include #include #include +#include /* * Routines for handling mm_structs @@ -433,4 +434,13 @@ static inline void membarrier_update_current_mm(struct mm_struct *next_mm) } #endif +#ifdef CONFIG_IOMMU_SVA +static inline void mm_pasid_init(struct mm_struct *mm) +{ + mm->pasid = INVALID_IOASID; +} +#else +static inline void mm_pasid_init(struct mm_struct *mm) {} +#endif + #endif /* _LINUX_SCHED_MM_H */ -- cgit v1.2.3 From 8cb37a5974a48569aab8a1736d21399fddbdbdb2 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Mon, 31 Jan 2022 10:05:20 +0100 Subject: stack: Introduce CONFIG_RANDOMIZE_KSTACK_OFFSET The randomize_kstack_offset feature is unconditionally compiled in when the architecture supports it. To add constraints on compiler versions, we require a dedicated Kconfig variable. Therefore, introduce RANDOMIZE_KSTACK_OFFSET. Furthermore, this option is now also configurable by EXPERT kernels: while the feature is supposed to have zero performance overhead when disabled, due to its use of static branches, there are few cases where giving a distribution the option to disable the feature entirely makes sense. For example, in very resource constrained environments, which would never enable the feature to begin with, in which case the additional kernel code size increase would be redundant. Signed-off-by: Marco Elver Reviewed-by: Nathan Chancellor Acked-by: Peter Zijlstra (Intel) Acked-by: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220131090521.1947110-1-elver@google.com --- include/linux/randomize_kstack.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h index bebc911161b6..91f1b990a3c3 100644 --- a/include/linux/randomize_kstack.h +++ b/include/linux/randomize_kstack.h @@ -2,6 +2,7 @@ #ifndef _LINUX_RANDOMIZE_KSTACK_H #define _LINUX_RANDOMIZE_KSTACK_H +#ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET #include #include #include @@ -50,5 +51,9 @@ void *__builtin_alloca(size_t size); raw_cpu_write(kstack_offset, offset); \ } \ } while (0) +#else /* CONFIG_RANDOMIZE_KSTACK_OFFSET */ +#define add_random_kstack_offset() do { } while (0) +#define choose_random_kstack_offset(rand) do { } while (0) +#endif /* CONFIG_RANDOMIZE_KSTACK_OFFSET */ #endif -- cgit v1.2.3 From efa90c11f62e6b7252fb75efe2787056872a627c Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Mon, 31 Jan 2022 10:05:21 +0100 Subject: stack: Constrain and fix stack offset randomization with Clang builds All supported versions of Clang perform auto-init of __builtin_alloca() when stack auto-init is on (CONFIG_INIT_STACK_ALL_{ZERO,PATTERN}). add_random_kstack_offset() uses __builtin_alloca() to add a stack offset. This means, when CONFIG_INIT_STACK_ALL_{ZERO,PATTERN} is enabled, add_random_kstack_offset() will auto-init that unused portion of the stack used to add an offset. There are several problems with this: 1. These offsets can be as large as 1023 bytes. Performing memset() on them isn't exactly cheap, and this is done on every syscall entry. 2. Architectures adding add_random_kstack_offset() to syscall entry implemented in C require them to be 'noinstr' (e.g. see x86 and s390). The potential problem here is that a call to memset may occur, which is not noinstr. A x86_64 defconfig kernel with Clang 11 and CONFIG_VMLINUX_VALIDATION shows: | vmlinux.o: warning: objtool: do_syscall_64()+0x9d: call to memset() leaves .noinstr.text section | vmlinux.o: warning: objtool: do_int80_syscall_32()+0xab: call to memset() leaves .noinstr.text section | vmlinux.o: warning: objtool: __do_fast_syscall_32()+0xe2: call to memset() leaves .noinstr.text section | vmlinux.o: warning: objtool: fixup_bad_iret()+0x2f: call to memset() leaves .noinstr.text section Clang 14 (unreleased) will introduce a way to skip alloca initialization via __builtin_alloca_uninitialized() (https://reviews.llvm.org/D115440). Constrain RANDOMIZE_KSTACK_OFFSET to only be enabled if no stack auto-init is enabled, the compiler is GCC, or Clang is version 14+. Use __builtin_alloca_uninitialized() if the compiler provides it, as is done by Clang 14. Link: https://lkml.kernel.org/r/YbHTKUjEejZCLyhX@elver.google.com Fixes: 39218ff4c625 ("stack: Optionally randomize kernel stack offset each syscall") Signed-off-by: Marco Elver Reviewed-by: Nathan Chancellor Acked-by: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220131090521.1947110-2-elver@google.com --- include/linux/randomize_kstack.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h index 91f1b990a3c3..1468caf001c0 100644 --- a/include/linux/randomize_kstack.h +++ b/include/linux/randomize_kstack.h @@ -17,8 +17,20 @@ DECLARE_PER_CPU(u32, kstack_offset); * alignment. Also, since this use is being explicitly masked to a max of * 10 bits, stack-clash style attacks are unlikely. For more details see * "VLAs" in Documentation/process/deprecated.rst + * + * The normal __builtin_alloca() is initialized with INIT_STACK_ALL (currently + * only with Clang and not GCC). Initializing the unused area on each syscall + * entry is expensive, and generating an implicit call to memset() may also be + * problematic (such as in noinstr functions). Therefore, if the compiler + * supports it (which it should if it initializes allocas), always use the + * "uninitialized" variant of the builtin. */ -void *__builtin_alloca(size_t size); +#if __has_builtin(__builtin_alloca_uninitialized) +#define __kstack_alloca __builtin_alloca_uninitialized +#else +#define __kstack_alloca __builtin_alloca +#endif + /* * Use, at most, 10 bits of entropy. We explicitly cap this to keep the * "VLA" from being unbounded (see above). 10 bits leaves enough room for @@ -37,7 +49,7 @@ void *__builtin_alloca(size_t size); if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \ &randomize_kstack_offset)) { \ u32 offset = raw_cpu_read(kstack_offset); \ - u8 *ptr = __builtin_alloca(KSTACK_OFFSET_MAX(offset)); \ + u8 *ptr = __kstack_alloca(KSTACK_OFFSET_MAX(offset)); \ /* Keep allocation even after "ptr" loses scope. */ \ asm volatile("" :: "r"(ptr) : "memory"); \ } \ -- cgit v1.2.3 From 481153991c410e322383490527c20b0c41dbf652 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Thu, 10 Feb 2022 22:33:41 +0100 Subject: i2c: don't expose function which is only used internally MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit i2c_setup_smbus_alert() is only needed within the I2C core, so no need to expose it to other modules. Signed-off-by: Wolfram Sang Reviewed-by: Niklas Söderlund Signed-off-by: Wolfram Sang --- include/linux/i2c-smbus.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/i2c-smbus.h b/include/linux/i2c-smbus.h index 95cf902e0bda..ced1c6ead52a 100644 --- a/include/linux/i2c-smbus.h +++ b/include/linux/i2c-smbus.h @@ -30,14 +30,6 @@ struct i2c_client *i2c_new_smbus_alert_device(struct i2c_adapter *adapter, struct i2c_smbus_alert_setup *setup); int i2c_handle_smbus_alert(struct i2c_client *ara); -#if IS_ENABLED(CONFIG_I2C_SMBUS) -int i2c_setup_smbus_alert(struct i2c_adapter *adap); -#else -static inline int i2c_setup_smbus_alert(struct i2c_adapter *adap) -{ - return 0; -} -#endif #if IS_ENABLED(CONFIG_I2C_SMBUS) && IS_ENABLED(CONFIG_I2C_SLAVE) struct i2c_client *i2c_new_slave_host_notify_device(struct i2c_adapter *adapter); void i2c_free_slave_host_notify_device(struct i2c_client *client); -- cgit v1.2.3 From 701fac40384f07197b106136012804c3cae0b3de Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Mon, 7 Feb 2022 15:02:48 -0800 Subject: iommu/sva: Assign a PASID to mm on PASID allocation and free it on mm exit PASIDs are process-wide. It was attempted to use refcounted PASIDs to free them when the last thread drops the refcount. This turned out to be complex and error prone. Given the fact that the PASID space is 20 bits, which allows up to 1M processes to have a PASID associated concurrently, PASID resource exhaustion is not a realistic concern. Therefore, it was decided to simplify the approach and stick with lazy on demand PASID allocation, but drop the eager free approach and make an allocated PASID's lifetime bound to the lifetime of the process. Get rid of the refcounting mechanisms and replace/rename the interfaces to reflect this new approach. [ bp: Massage commit message. ] Suggested-by: Dave Hansen Signed-off-by: Fenghua Yu Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Reviewed-by: Lu Baolu Reviewed-by: Jacob Pan Reviewed-by: Thomas Gleixner Acked-by: Joerg Roedel Link: https://lore.kernel.org/r/20220207230254.3342514-6-fenghua.yu@intel.com --- include/linux/ioasid.h | 12 ++---------- include/linux/sched/mm.h | 16 ++++++++++++++++ 2 files changed, 18 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h index 2237f64dbaae..af1c9d62e642 100644 --- a/include/linux/ioasid.h +++ b/include/linux/ioasid.h @@ -34,8 +34,7 @@ struct ioasid_allocator_ops { #if IS_ENABLED(CONFIG_IOASID) ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, void *private); -void ioasid_get(ioasid_t ioasid); -bool ioasid_put(ioasid_t ioasid); +void ioasid_free(ioasid_t ioasid); void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, bool (*getter)(void *)); int ioasid_register_allocator(struct ioasid_allocator_ops *allocator); @@ -53,14 +52,7 @@ static inline ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, return INVALID_IOASID; } -static inline void ioasid_get(ioasid_t ioasid) -{ -} - -static inline bool ioasid_put(ioasid_t ioasid) -{ - return false; -} +static inline void ioasid_free(ioasid_t ioasid) { } static inline void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, bool (*getter)(void *)) diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index c74d1edbac2f..a80356e9dc69 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -439,8 +439,24 @@ static inline void mm_pasid_init(struct mm_struct *mm) { mm->pasid = INVALID_IOASID; } + +/* Associate a PASID with an mm_struct: */ +static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) +{ + mm->pasid = pasid; +} + +static inline void mm_pasid_drop(struct mm_struct *mm) +{ + if (pasid_valid(mm->pasid)) { + ioasid_free(mm->pasid); + mm->pasid = INVALID_IOASID; + } +} #else static inline void mm_pasid_init(struct mm_struct *mm) {} +static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) {} +static inline void mm_pasid_drop(struct mm_struct *mm) {} #endif #endif /* _LINUX_SCHED_MM_H */ -- cgit v1.2.3 From a3d29e8291b622780eb6e4e3eeaf2b24ec78fd43 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 7 Feb 2022 15:02:50 -0800 Subject: sched: Define and initialize a flag to identify valid PASID in the task Add a new single bit field to the task structure to track whether this task has initialized the IA32_PASID MSR to the mm's PASID. Initialize the field to zero when creating a new task with fork/clone. Signed-off-by: Peter Zijlstra Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Reviewed-by: Thomas Gleixner Link: https://lore.kernel.org/r/20220207230254.3342514-8-fenghua.yu@intel.com --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 75ba8aa60248..4e5de3aed410 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -938,6 +938,9 @@ struct task_struct { /* Recursion prevention for eventfd_signal() */ unsigned in_eventfd_signal:1; #endif +#ifdef CONFIG_IOMMU_SVA + unsigned pasid_activated:1; +#endif unsigned long atomic_flags; /* Flags requiring atomic access. */ -- cgit v1.2.3 From 45ec846c1cd11835a29c85645065115dd791aa45 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 9 Feb 2022 16:25:58 +0000 Subject: irqdomain: Let irq_domain_set_{info,hwirq_and_chip} take a const irq_chip In order to let a const irqchip be fed to the irqchip layer, adjust the various prototypes. An extra cast in irq_domain_set_hwirq_and_chip() is required to avoid a warning. Signed-off-by: Marc Zyngier Acked-by: Linus Walleij Link: https://lore.kernel.org/r/20220209162607.1118325-2-maz@kernel.org --- include/linux/irqdomain.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index be25a33293e5..00d577f90883 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -479,7 +479,8 @@ int irq_destroy_ipi(unsigned int irq, const struct cpumask *dest); extern struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain, unsigned int virq); extern void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq, struct irq_chip *chip, + irq_hw_number_t hwirq, + const struct irq_chip *chip, void *chip_data, irq_flow_handler_t handler, void *handler_data, const char *handler_name); extern void irq_domain_reset_irq_data(struct irq_data *irq_data); @@ -522,7 +523,7 @@ extern int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain, extern int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, unsigned int virq, irq_hw_number_t hwirq, - struct irq_chip *chip, + const struct irq_chip *chip, void *chip_data); extern void irq_domain_free_irqs_common(struct irq_domain *domain, unsigned int virq, -- cgit v1.2.3 From 393e1280f765661cf39785e967676a4e57324126 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 9 Feb 2022 16:25:59 +0000 Subject: genirq: Allow irq_chip registration functions to take a const irq_chip In order to let a const irqchip be fed to the irqchip layer, adjust the various prototypes. An extra cast in irq_set_chip()() is required to avoid a warning. Signed-off-by: Marc Zyngier Acked-by: Linus Walleij Link: https://lore.kernel.org/r/20220209162607.1118325-3-maz@kernel.org --- include/linux/irq.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index 2cb2e2ac2703..f92788ccdba2 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -710,10 +710,11 @@ extern struct irq_chip no_irq_chip; extern struct irq_chip dummy_irq_chip; extern void -irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip, +irq_set_chip_and_handler_name(unsigned int irq, const struct irq_chip *chip, irq_flow_handler_t handle, const char *name); -static inline void irq_set_chip_and_handler(unsigned int irq, struct irq_chip *chip, +static inline void irq_set_chip_and_handler(unsigned int irq, + const struct irq_chip *chip, irq_flow_handler_t handle) { irq_set_chip_and_handler_name(irq, chip, handle, NULL); @@ -803,7 +804,7 @@ static inline void irq_set_percpu_devid_flags(unsigned int irq) } /* Set/get chip/data for an IRQ: */ -extern int irq_set_chip(unsigned int irq, struct irq_chip *chip); +extern int irq_set_chip(unsigned int irq, const struct irq_chip *chip); extern int irq_set_handler_data(unsigned int irq, void *data); extern int irq_set_chip_data(unsigned int irq, void *data); extern int irq_set_irq_type(unsigned int irq, unsigned int type); -- cgit v1.2.3 From 3fb212a042fbd8eccbb2af1852e03ed7757b9600 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 9 Feb 2022 16:26:04 +0000 Subject: irqchip/versatile-fpga: Switch to dynamic chip name output Move the name output to the relevant callback, which allows us some nice cleanups (mostly owing to the fact that the driver is now DT only. We also drop a random include directive from the ftintc010 driver. Signed-off-by: Marc Zyngier Reviewed-by: Linus Walleij Acked-by: Linus Walleij Link: https://lore.kernel.org/r/20220209162607.1118325-8-maz@kernel.org --- include/linux/irqchip/versatile-fpga.h | 14 -------------- 1 file changed, 14 deletions(-) delete mode 100644 include/linux/irqchip/versatile-fpga.h (limited to 'include') diff --git a/include/linux/irqchip/versatile-fpga.h b/include/linux/irqchip/versatile-fpga.h deleted file mode 100644 index a978fc8c7996..000000000000 --- a/include/linux/irqchip/versatile-fpga.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef PLAT_FPGA_IRQ_H -#define PLAT_FPGA_IRQ_H - -struct device_node; -struct pt_regs; - -void fpga_handle_irq(struct pt_regs *regs); -void fpga_irq_init(void __iomem *, const char *, int, int, u32, - struct device_node *node); -int fpga_irq_of_init(struct device_node *node, - struct device_node *parent); - -#endif -- cgit v1.2.3 From 5e50f5d4ff31e95599d695df1f0a4e7d2d6fef99 Mon Sep 17 00:00:00 2001 From: Ondrej Mosnacek Date: Sat, 12 Feb 2022 18:59:21 +0100 Subject: security: add sctp_assoc_established hook security_sctp_assoc_established() is added to replace security_inet_conn_established() called in sctp_sf_do_5_1E_ca(), so that asoc can be accessed in security subsystem and save the peer secid to asoc->peer_secid. Fixes: 72e89f50084c ("security: Add support for SCTP security hooks") Reported-by: Prashanth Prahlad Based-on-patch-by: Xin Long Reviewed-by: Xin Long Tested-by: Richard Haines Signed-off-by: Ondrej Mosnacek Signed-off-by: Paul Moore --- include/linux/lsm_hook_defs.h | 2 ++ include/linux/lsm_hooks.h | 5 +++++ include/linux/security.h | 8 ++++++++ 3 files changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index a5a724c308d8..45931d81ccc3 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -332,6 +332,8 @@ LSM_HOOK(int, 0, sctp_bind_connect, struct sock *sk, int optname, struct sockaddr *address, int addrlen) LSM_HOOK(void, LSM_RET_VOID, sctp_sk_clone, struct sctp_association *asoc, struct sock *sk, struct sock *newsk) +LSM_HOOK(int, 0, sctp_assoc_established, struct sctp_association *asoc, + struct sk_buff *skb) #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 3bf5c658bc44..419b5febc3ca 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1046,6 +1046,11 @@ * @asoc pointer to current sctp association structure. * @sk pointer to current sock structure. * @newsk pointer to new sock structure. + * @sctp_assoc_established: + * Passes the @asoc and @chunk->skb of the association COOKIE_ACK packet + * to the security module. + * @asoc pointer to sctp association structure. + * @skb pointer to skbuff of association packet. * * Security hooks for Infiniband * diff --git a/include/linux/security.h b/include/linux/security.h index 6d72772182c8..25b3ef71f495 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1422,6 +1422,8 @@ int security_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen); void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk); +int security_sctp_assoc_established(struct sctp_association *asoc, + struct sk_buff *skb); #else /* CONFIG_SECURITY_NETWORK */ static inline int security_unix_stream_connect(struct sock *sock, @@ -1641,6 +1643,12 @@ static inline void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *newsk) { } + +static inline int security_sctp_assoc_established(struct sctp_association *asoc, + struct sk_buff *skb) +{ + return 0; +} #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND -- cgit v1.2.3 From 8487614a8a8a70d44957a11693dbefd8350f402c Mon Sep 17 00:00:00 2001 From: Samuel Holland Date: Wed, 2 Feb 2022 20:17:32 -0600 Subject: dt-bindings: rtc: sun6i: Add H616, R329, and D1 support These new RTC variants all have a single alarm, like the R40 variant. For the new SoCs, start requiring a complete list of input clocks. The H616 has three required clocks. The R329 also has three required clocks (but one is different), plus an optional crystal oscillator input. The D1 RTC is identical to the one in the R329. And since these new SoCs will have a well-defined output clock order as well, they do not need the clock-output-names property. Signed-off-by: Samuel Holland Reviewed-by: Rob Herring Reviewed-by: Maxime Ripard Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20220203021736.13434-3-samuel@sholland.org --- include/dt-bindings/clock/sun6i-rtc.h | 10 ++++++++++ 1 file changed, 10 insertions(+) create mode 100644 include/dt-bindings/clock/sun6i-rtc.h (limited to 'include') diff --git a/include/dt-bindings/clock/sun6i-rtc.h b/include/dt-bindings/clock/sun6i-rtc.h new file mode 100644 index 000000000000..c845493e4d37 --- /dev/null +++ b/include/dt-bindings/clock/sun6i-rtc.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: (GPL-2.0+ or MIT) */ + +#ifndef _DT_BINDINGS_CLK_SUN6I_RTC_H_ +#define _DT_BINDINGS_CLK_SUN6I_RTC_H_ + +#define CLK_OSC32K 0 +#define CLK_OSC32K_FANOUT 1 +#define CLK_IOSC 2 + +#endif /* _DT_BINDINGS_CLK_SUN6I_RTC_H_ */ -- cgit v1.2.3 From b62a8486de3ab1d7c2353ec422b9cca3abfcfbcd Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Mon, 31 Jan 2022 16:54:52 +0000 Subject: elfcore: Replace CONFIG_{IA64, UML} checks with a new option As arm64 is about to introduce MTE-specific phdrs in the core dump, add a common CONFIG_ARCH_BINFMT_ELF_EXTRA_PHDRS option currently selectable by UML_X86 and IA64. Signed-off-by: Catalin Marinas Cc: Eric Biederman Link: https://lore.kernel.org/r/20220131165456.2160675-2-catalin.marinas@arm.com Signed-off-by: Will Deacon --- include/linux/elfcore.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index 746e081879a5..f8e206e82476 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -114,7 +114,7 @@ static inline int elf_core_copy_task_fpregs(struct task_struct *t, struct pt_reg #endif } -#if (defined(CONFIG_UML) && defined(CONFIG_X86_32)) || defined(CONFIG_IA64) +#ifdef CONFIG_ARCH_BINFMT_ELF_EXTRA_PHDRS /* * These functions parameterize elf_core_dump in fs/binfmt_elf.c to write out * extra segments containing the gate DSO contents. Dumping its @@ -149,6 +149,6 @@ static inline size_t elf_core_extra_data_size(void) { return 0; } -#endif +#endif /* CONFIG_ARCH_BINFMT_ELF_EXTRA_PHDRS */ #endif /* _LINUX_ELFCORE_H */ -- cgit v1.2.3 From 761b9b366cec0c81a1cd80930f00611d86521d1b Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Mon, 31 Jan 2022 16:54:53 +0000 Subject: elf: Introduce the ARM MTE ELF segment type Memory tags will be dumped in the core file as segments with their own type. Discussions with the binutils and the generic ABI community settled on using new definitions in the PT_*PROC space (and to be documented in the processor-specific ABIs). Introduce PT_ARM_MEMTAG_MTE as (PT_LOPROC + 0x1). Not included in this patch since there is no upstream support but the CHERI/BSD community will also reserve: #define PT_ARM_MEMTAG_CHERI (PT_LOPROC + 0x2) #define PT_RISCV_MEMTAG_CHERI (PT_LOPROC + 0x3) Signed-off-by: Catalin Marinas Acked-by: Luis Machado Link: https://lore.kernel.org/r/20220131165456.2160675-3-catalin.marinas@arm.com Signed-off-by: Will Deacon --- include/uapi/linux/elf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 61bf4774b8f2..fe8e5b74cb39 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -40,6 +40,9 @@ typedef __s64 Elf64_Sxword; #define PT_GNU_STACK (PT_LOOS + 0x474e551) +/* ARM MTE memory tag segment type */ +#define PT_ARM_MEMTAG_MTE (PT_LOPROC + 0x1) + /* * Extended Numbering * -- cgit v1.2.3 From 2509969a9862b522d2208e8663057fb227556687 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Fri, 4 Feb 2022 16:13:41 -0800 Subject: drm: Plumb debugfs_init through to panels We'd like panels to be able to add things to debugfs underneath the connector's directory. Let's plumb it through. A panel will be able to put things in a "panel" directory under the connector's directory. Note that debugfs is not ABI and so it's always possible that the location that the panel gets for its debugfs could change in the future. NOTE: this currently only works if you're using a modern architecture. Specifically the plumbing relies on _both_ drm_bridge_connector and drm_panel_bridge. If you're not using one or both of these things then things won't be plumbed through. As a side effect of this change, drm_bridges can also get callbacks to put stuff underneath the connector's debugfs directory. At the moment all bridges in the chain have their debugfs_init() called with the connector's root directory. Signed-off-by: Douglas Anderson Reviewed-by: Javier Martinez Canillas Reviewed-by: Laurent Pinchart Link: https://patchwork.freedesktop.org/patch/msgid/20220204161245.v2.2.Ib0bd5346135cbb0b63006b69b61d4c8af6484740@changeid --- include/drm/drm_bridge.h | 7 +++++++ include/drm/drm_connector.h | 7 +++++++ include/drm/drm_panel.h | 8 ++++++++ 3 files changed, 22 insertions(+) (limited to 'include') diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h index 061d87313fac..f27b4060faa2 100644 --- a/include/drm/drm_bridge.h +++ b/include/drm/drm_bridge.h @@ -649,6 +649,13 @@ struct drm_bridge_funcs { * the DRM_BRIDGE_OP_HPD flag in their &drm_bridge->ops. */ void (*hpd_disable)(struct drm_bridge *bridge); + + /** + * @debugfs_init: + * + * Allows bridges to create bridge-specific debugfs files. + */ + void (*debugfs_init)(struct drm_bridge *bridge, struct dentry *root); }; /** diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index 5e36eb3df66f..5166186146f4 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -1142,6 +1142,13 @@ struct drm_connector_funcs { * has been received from a source outside the display driver / device. */ void (*oob_hotplug_event)(struct drm_connector *connector); + + /** + * @debugfs_init: + * + * Allows connectors to create connector-specific debugfs files. + */ + void (*debugfs_init)(struct drm_connector *connector, struct dentry *root); }; /** diff --git a/include/drm/drm_panel.h b/include/drm/drm_panel.h index 4602f833eb51..1ba2d424a53f 100644 --- a/include/drm/drm_panel.h +++ b/include/drm/drm_panel.h @@ -29,6 +29,7 @@ #include struct backlight_device; +struct dentry; struct device_node; struct drm_connector; struct drm_device; @@ -125,6 +126,13 @@ struct drm_panel_funcs { */ int (*get_timings)(struct drm_panel *panel, unsigned int num_timings, struct display_timing *timings); + + /** + * @debugfs_init: + * + * Allows panels to create panels-specific debugfs files. + */ + void (*debugfs_init)(struct drm_panel *panel, struct dentry *root); }; /** -- cgit v1.2.3 From f41b6be1ebdae452819551ed35a46e6fd32bf467 Mon Sep 17 00:00:00 2001 From: Jens Wiklander Date: Fri, 4 Feb 2022 10:33:51 +0100 Subject: tee: remove unused tee_shm_pool_alloc_res_mem() None of the drivers in the TEE subsystem uses tee_shm_pool_alloc_res_mem() so remove the function. Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 30 ------------------------------ 1 file changed, 30 deletions(-) (limited to 'include') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 5e1533ee3785..6b0f0d01ebdf 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -278,36 +278,6 @@ static inline void tee_shm_pool_mgr_destroy(struct tee_shm_pool_mgr *poolm) poolm->ops->destroy_poolmgr(poolm); } -/** - * struct tee_shm_pool_mem_info - holds information needed to create a shared - * memory pool - * @vaddr: Virtual address of start of pool - * @paddr: Physical address of start of pool - * @size: Size in bytes of the pool - */ -struct tee_shm_pool_mem_info { - unsigned long vaddr; - phys_addr_t paddr; - size_t size; -}; - -/** - * tee_shm_pool_alloc_res_mem() - Create a shared memory pool from reserved - * memory range - * @priv_info: Information for driver private shared memory pool - * @dmabuf_info: Information for dma-buf shared memory pool - * - * Start and end of pools will must be page aligned. - * - * Allocation with the flag TEE_SHM_DMA_BUF set will use the range supplied - * in @dmabuf, others will use the range provided by @priv. - * - * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure. - */ -struct tee_shm_pool * -tee_shm_pool_alloc_res_mem(struct tee_shm_pool_mem_info *priv_info, - struct tee_shm_pool_mem_info *dmabuf_info); - /** * tee_shm_pool_free() - Free a shared memory pool * @pool: The shared memory pool to free -- cgit v1.2.3 From 71cc47d4cc1f7a333584e0f2f7c863c71a6d3ced Mon Sep 17 00:00:00 2001 From: Jens Wiklander Date: Fri, 4 Feb 2022 10:33:52 +0100 Subject: tee: add tee_shm_alloc_user_buf() Adds a new function tee_shm_alloc_user_buf() for user mode allocations, replacing passing the flags TEE_SHM_MAPPED | TEE_SHM_DMA_BUF to tee_shm_alloc(). Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 6b0f0d01ebdf..a4393c8c38f3 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2015-2016, Linaro Limited + * Copyright (c) 2015-2016 Linaro Limited */ #ifndef __TEE_DRV_H -- cgit v1.2.3 From d88e0493a054c9fe72ade41a42d42e958ee6503d Mon Sep 17 00:00:00 2001 From: Jens Wiklander Date: Fri, 4 Feb 2022 10:33:53 +0100 Subject: tee: simplify shm pool handling Replaces the shared memory pool based on two pools with a single pool. The alloc() function pointer in struct tee_shm_pool_ops gets another parameter, align. This makes it possible to make less than page aligned allocations from the optional reserved shared memory pool while still making user space allocations page aligned. With in practice unchanged behaviour using only a single pool for bookkeeping. The allocation algorithm in the static OP-TEE shared memory pool is changed from best-fit to first-fit since only the latter supports an alignment parameter. The best-fit algorithm was previously the default choice and not a conscious one. The optee and amdtee drivers are updated as needed to work with this changed pool handling. This also removes OPTEE_SHM_NUM_PRIV_PAGES which becomes obsolete with this change as the private pages can be mixed with the payload pages. The OP-TEE driver changes minimum alignment for argument struct from 8 bytes to 512 bytes. A typical OP-TEE private shm allocation is 224 bytes (argument struct with 6 parameters, needed for open session). So with an alignment of 512 well waste a bit more than 50%. Before this we had a single page reserved for this so worst case usage compared to that would be 3 pages instead of 1 page. However, this worst case only occurs if there is a high pressure from multiple threads on secure world. All in all this should scale up and down better than fixed boundaries. Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 60 +++++++++++++++++-------------------------------- 1 file changed, 20 insertions(+), 40 deletions(-) (limited to 'include') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index a4393c8c38f3..ed641dc314bd 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2015-2016 Linaro Limited + * Copyright (c) 2015-2022 Linaro Limited */ #ifndef __TEE_DRV_H @@ -221,62 +221,39 @@ struct tee_shm { }; /** - * struct tee_shm_pool_mgr - shared memory manager + * struct tee_shm_pool - shared memory pool * @ops: operations * @private_data: private data for the shared memory manager */ -struct tee_shm_pool_mgr { - const struct tee_shm_pool_mgr_ops *ops; +struct tee_shm_pool { + const struct tee_shm_pool_ops *ops; void *private_data; }; /** - * struct tee_shm_pool_mgr_ops - shared memory pool manager operations + * struct tee_shm_pool_ops - shared memory pool operations * @alloc: called when allocating shared memory * @free: called when freeing shared memory - * @destroy_poolmgr: called when destroying the pool manager + * @destroy_pool: called when destroying the pool */ -struct tee_shm_pool_mgr_ops { - int (*alloc)(struct tee_shm_pool_mgr *poolmgr, struct tee_shm *shm, - size_t size); - void (*free)(struct tee_shm_pool_mgr *poolmgr, struct tee_shm *shm); - void (*destroy_poolmgr)(struct tee_shm_pool_mgr *poolmgr); +struct tee_shm_pool_ops { + int (*alloc)(struct tee_shm_pool *pool, struct tee_shm *shm, + size_t size, size_t align); + void (*free)(struct tee_shm_pool *pool, struct tee_shm *shm); + void (*destroy_pool)(struct tee_shm_pool *pool); }; -/** - * tee_shm_pool_alloc() - Create a shared memory pool from shm managers - * @priv_mgr: manager for driver private shared memory allocations - * @dmabuf_mgr: manager for dma-buf shared memory allocations - * - * Allocation with the flag TEE_SHM_DMA_BUF set will use the range supplied - * in @dmabuf, others will use the range provided by @priv. - * - * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure. - */ -struct tee_shm_pool *tee_shm_pool_alloc(struct tee_shm_pool_mgr *priv_mgr, - struct tee_shm_pool_mgr *dmabuf_mgr); - /* - * tee_shm_pool_mgr_alloc_res_mem() - Create a shm manager for reserved - * memory + * tee_shm_pool_alloc_res_mem() - Create a shm manager for reserved memory * @vaddr: Virtual address of start of pool * @paddr: Physical address of start of pool * @size: Size in bytes of the pool * - * @returns pointer to a 'struct tee_shm_pool_mgr' or an ERR_PTR on failure. - */ -struct tee_shm_pool_mgr *tee_shm_pool_mgr_alloc_res_mem(unsigned long vaddr, - phys_addr_t paddr, - size_t size, - int min_alloc_order); - -/** - * tee_shm_pool_mgr_destroy() - Free a shared memory manager + * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure. */ -static inline void tee_shm_pool_mgr_destroy(struct tee_shm_pool_mgr *poolm) -{ - poolm->ops->destroy_poolmgr(poolm); -} +struct tee_shm_pool *tee_shm_pool_alloc_res_mem(unsigned long vaddr, + phys_addr_t paddr, size_t size, + int min_alloc_order); /** * tee_shm_pool_free() - Free a shared memory pool @@ -285,7 +262,10 @@ static inline void tee_shm_pool_mgr_destroy(struct tee_shm_pool_mgr *poolm) * The must be no remaining shared memory allocated from this pool when * this function is called. */ -void tee_shm_pool_free(struct tee_shm_pool *pool); +static inline void tee_shm_pool_free(struct tee_shm_pool *pool) +{ + pool->ops->destroy_pool(pool); +} /** * tee_get_drvdata() - Return driver_data pointer -- cgit v1.2.3 From 5d41f1b3e3282909b6bbceacb9aebe1d3c849a49 Mon Sep 17 00:00:00 2001 From: Jens Wiklander Date: Fri, 4 Feb 2022 10:33:54 +0100 Subject: tee: replace tee_shm_alloc() tee_shm_alloc() is replaced by three new functions, tee_shm_alloc_user_buf() - for user mode allocations, replacing passing the flags TEE_SHM_MAPPED | TEE_SHM_DMA_BUF tee_shm_alloc_kernel_buf() - for kernel mode allocations, slightly optimized compared to using the flags TEE_SHM_MAPPED | TEE_SHM_DMA_BUF. tee_shm_alloc_priv_buf() - primarily for TEE driver internal use. This also makes the interface easier to use as we can get rid of the somewhat hard to use flags parameter. The TEE subsystem and the TEE drivers are updated to use the new functions instead. Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index ed641dc314bd..7f038f8787c7 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -273,21 +273,7 @@ static inline void tee_shm_pool_free(struct tee_shm_pool *pool) */ void *tee_get_drvdata(struct tee_device *teedev); -/** - * tee_shm_alloc() - Allocate shared memory - * @ctx: Context that allocates the shared memory - * @size: Requested size of shared memory - * @flags: Flags setting properties for the requested shared memory. - * - * Memory allocated as global shared memory is automatically freed when the - * TEE file pointer is closed. The @flags field uses the bits defined by - * TEE_SHM_* above. TEE_SHM_MAPPED must currently always be set. If - * TEE_SHM_DMA_BUF global shared memory will be allocated and associated - * with a dma-buf handle, else driver private memory. - * - * @returns a pointer to 'struct tee_shm' - */ -struct tee_shm *tee_shm_alloc(struct tee_context *ctx, size_t size, u32 flags); +struct tee_shm *tee_shm_alloc_priv_buf(struct tee_context *ctx, size_t size); struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size); /** -- cgit v1.2.3 From 056d3fed3d1ff3f5d699be337f048f9eed2befaf Mon Sep 17 00:00:00 2001 From: Jens Wiklander Date: Fri, 4 Feb 2022 10:33:56 +0100 Subject: tee: add tee_shm_register_{user,kernel}_buf() Adds the two new functions tee_shm_register_user_buf() and tee_shm_register_kernel_buf() which should be used instead of the old tee_shm_register(). This avoids having the caller supplying the flags parameter which exposes a bit more than desired of the internals of the TEE subsystem. Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 7f038f8787c7..c9d2cc32a5ed 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -287,6 +287,8 @@ struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size); */ struct tee_shm *tee_shm_register(struct tee_context *ctx, unsigned long addr, size_t length, u32 flags); +struct tee_shm *tee_shm_register_kernel_buf(struct tee_context *ctx, + void *addr, size_t length); /** * tee_shm_is_registered() - Check if shared memory object in registered in TEE -- cgit v1.2.3 From 53e16519c2eccdb2e1b123405466a29aaea1132e Mon Sep 17 00:00:00 2001 From: Jens Wiklander Date: Fri, 4 Feb 2022 10:33:58 +0100 Subject: tee: replace tee_shm_register() tee_shm_register() is replaced by the previously introduced functions tee_shm_register_user_buf() and tee_shm_register_kernel_buf(). Since there are not external callers left we can remove tee_shm_register() and refactor the remains. Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index c9d2cc32a5ed..a3b663ef0694 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -276,17 +276,6 @@ void *tee_get_drvdata(struct tee_device *teedev); struct tee_shm *tee_shm_alloc_priv_buf(struct tee_context *ctx, size_t size); struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size); -/** - * tee_shm_register() - Register shared memory buffer - * @ctx: Context that registers the shared memory - * @addr: Address is userspace of the shared buffer - * @length: Length of the shared buffer - * @flags: Flags setting properties for the requested shared memory. - * - * @returns a pointer to 'struct tee_shm' - */ -struct tee_shm *tee_shm_register(struct tee_context *ctx, unsigned long addr, - size_t length, u32 flags); struct tee_shm *tee_shm_register_kernel_buf(struct tee_context *ctx, void *addr, size_t length); -- cgit v1.2.3 From a45ea4efa358577c623d7353a6ba9af3c17f6ca0 Mon Sep 17 00:00:00 2001 From: Jens Wiklander Date: Fri, 4 Feb 2022 10:33:59 +0100 Subject: tee: refactor TEE_SHM_* flags Removes the redundant TEE_SHM_DMA_BUF, TEE_SHM_EXT_DMA_BUF, TEE_SHM_MAPPED and TEE_SHM_KERNEL_MAPPED flags. TEE_SHM_REGISTER is renamed to TEE_SHM_DYNAMIC in order to better match its usage. Assigns new values to the remaining flags to void gaps. Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index a3b663ef0694..911cad324acc 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -20,14 +20,11 @@ * specific TEE driver. */ -#define TEE_SHM_MAPPED BIT(0) /* Memory mapped by the kernel */ -#define TEE_SHM_DMA_BUF BIT(1) /* Memory with dma-buf handle */ -#define TEE_SHM_EXT_DMA_BUF BIT(2) /* Memory with dma-buf handle */ -#define TEE_SHM_REGISTER BIT(3) /* Memory registered in secure world */ -#define TEE_SHM_USER_MAPPED BIT(4) /* Memory mapped in user space */ -#define TEE_SHM_POOL BIT(5) /* Memory allocated from pool */ -#define TEE_SHM_KERNEL_MAPPED BIT(6) /* Memory mapped in kernel space */ -#define TEE_SHM_PRIV BIT(7) /* Memory private to TEE driver */ +#define TEE_SHM_DYNAMIC BIT(0) /* Dynamic shared memory registered */ + /* in secure world */ +#define TEE_SHM_USER_MAPPED BIT(1) /* Memory mapped in user space */ +#define TEE_SHM_POOL BIT(2) /* Memory allocated from pool */ +#define TEE_SHM_PRIV BIT(3) /* Memory private to TEE driver */ struct device; struct tee_device; @@ -280,13 +277,13 @@ struct tee_shm *tee_shm_register_kernel_buf(struct tee_context *ctx, void *addr, size_t length); /** - * tee_shm_is_registered() - Check if shared memory object in registered in TEE + * tee_shm_is_dynamic() - Check if shared memory object is of the dynamic kind * @shm: Shared memory handle - * @returns true if object is registered in TEE + * @returns true if object is dynamic shared memory */ -static inline bool tee_shm_is_registered(struct tee_shm *shm) +static inline bool tee_shm_is_dynamic(struct tee_shm *shm) { - return shm && (shm->flags & TEE_SHM_REGISTER); + return shm && (shm->flags & TEE_SHM_DYNAMIC); } /** -- cgit v1.2.3 From 8d23a54f5beea59b560855fb571e5d73d783e0b4 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 15 Feb 2022 19:02:12 +0200 Subject: net: bridge: switchdev: differentiate new VLANs from changed ones br_switchdev_port_vlan_add() currently emits a SWITCHDEV_PORT_OBJ_ADD event with a SWITCHDEV_OBJ_ID_PORT_VLAN for 2 distinct cases: - a struct net_bridge_vlan got created - an existing struct net_bridge_vlan was modified This makes it impossible for switchdev drivers to properly balance PORT_OBJ_ADD with PORT_OBJ_DEL events, so if we want to allow that to happen, we must provide a way for drivers to distinguish between a VLAN with changed flags and a new one. Annotate struct switchdev_obj_port_vlan with a "bool changed" that distinguishes the 2 cases above. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/switchdev.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index d353793dfeb5..92cc763991e9 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -81,6 +81,13 @@ struct switchdev_obj_port_vlan { struct switchdev_obj obj; u16 flags; u16 vid; + /* If set, the notifier signifies a change of one of the following + * flags for a VLAN that already exists: + * - BRIDGE_VLAN_INFO_PVID + * - BRIDGE_VLAN_INFO_UNTAGGED + * Entries with BRIDGE_VLAN_INFO_BRENTRY unset are not notified at all. + */ + bool changed; }; #define SWITCHDEV_OBJ_PORT_VLAN(OBJ) \ -- cgit v1.2.3 From c4076cdd21f8d68a96f1e7124bd8915c7e31a474 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 15 Feb 2022 19:02:16 +0200 Subject: net: switchdev: introduce switchdev_handle_port_obj_{add,del} for foreign interfaces The switchdev_handle_port_obj_add() helper is good for replicating a port object on the lower interfaces of @dev, if that object was emitted on a bridge, or on a bridge port that is a LAG. However, drivers that use this helper limit themselves to a box from which they can no longer intercept port objects notified on neighbor ports ("foreign interfaces"). One such driver is DSA, where software bridging with foreign interfaces such as standalone NICs or Wi-Fi APs is an important use case. There, a VLAN installed on a neighbor bridge port roughly corresponds to a forwarding VLAN installed on the DSA switch's CPU port. To support this use case while also making use of the benefits of the switchdev_handle_* replication helper for port objects, introduce a new variant of these functions that crawls through the neighbor ports of @dev, in search of potentially compatible switchdev ports that are interested in the event. The strategy is identical to switchdev_handle_fdb_event_to_device(): if @dev wasn't a switchdev interface, then go one step upper, and recursively call this function on the bridge that this port belongs to. At the next recursion step, __switchdev_handle_port_obj_add() will iterate through the bridge's lower interfaces. Among those, some will be switchdev interfaces, and one will be the original @dev that we came from. To prevent infinite recursion, we must suppress reentry into the original @dev, and just call the @add_cb for the switchdev_interfaces. It looks like this: br0 / | \ / | \ / | \ swp0 swp1 eth0 1. __switchdev_handle_port_obj_add(eth0) -> check_cb(eth0) returns false -> eth0 has no lower interfaces -> eth0's bridge is br0 -> switchdev_lower_dev_find(br0, check_cb, foreign_dev_check_cb)) finds br0 2. __switchdev_handle_port_obj_add(br0) -> check_cb(br0) returns false -> netdev_for_each_lower_dev -> check_cb(swp0) returns true, so we don't skip this interface 3. __switchdev_handle_port_obj_add(swp0) -> check_cb(swp0) returns true, so we call add_cb(swp0) (back to netdev_for_each_lower_dev from 2) -> check_cb(swp1) returns true, so we don't skip this interface 4. __switchdev_handle_port_obj_add(swp1) -> check_cb(swp1) returns true, so we call add_cb(swp1) (back to netdev_for_each_lower_dev from 2) -> check_cb(eth0) returns false, so we skip this interface to avoid infinite recursion Note: eth0 could have been a LAG, and we don't want to suppress the recursion through its lowers if those exist, so when check_cb() returns false, we still call switchdev_lower_dev_find() to estimate whether there's anything worth a recursion beneath that LAG. Using check_cb() and foreign_dev_check_cb(), switchdev_lower_dev_find() not only figures out whether the lowers of the LAG are switchdev, but also whether they actively offload the LAG or not (whether the LAG is "foreign" to the switchdev interface or not). The port_obj_info->orig_dev is preserved across recursive calls, so switchdev drivers still know on which device was this notification originally emitted. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/switchdev.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 92cc763991e9..c32e1c8f79ec 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -324,11 +324,26 @@ int switchdev_handle_port_obj_add(struct net_device *dev, int (*add_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack)); +int switchdev_handle_port_obj_add_foreign(struct net_device *dev, + struct switchdev_notifier_port_obj_info *port_obj_info, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), + int (*add_cb)(struct net_device *dev, const void *ctx, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack)); int switchdev_handle_port_obj_del(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), int (*del_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj)); +int switchdev_handle_port_obj_del_foreign(struct net_device *dev, + struct switchdev_notifier_port_obj_info *port_obj_info, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), + int (*del_cb)(struct net_device *dev, const void *ctx, + const struct switchdev_obj *obj)); int switchdev_handle_port_attr_set(struct net_device *dev, struct switchdev_notifier_port_attr_info *port_attr_info, @@ -447,6 +462,18 @@ switchdev_handle_port_obj_add(struct net_device *dev, return 0; } +static inline int switchdev_handle_port_obj_add_foreign(struct net_device *dev, + struct switchdev_notifier_port_obj_info *port_obj_info, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), + int (*add_cb)(struct net_device *dev, const void *ctx, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack)) +{ + return 0; +} + static inline int switchdev_handle_port_obj_del(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, @@ -457,6 +484,18 @@ switchdev_handle_port_obj_del(struct net_device *dev, return 0; } +static inline int +switchdev_handle_port_obj_del_foreign(struct net_device *dev, + struct switchdev_notifier_port_obj_info *port_obj_info, + bool (*check_cb)(const struct net_device *dev), + bool (*foreign_dev_check_cb)(const struct net_device *dev, + const struct net_device *foreign_dev), + int (*del_cb)(struct net_device *dev, const void *ctx, + const struct switchdev_obj *obj)) +{ + return 0; +} + static inline int switchdev_handle_port_attr_set(struct net_device *dev, struct switchdev_notifier_port_attr_info *port_attr_info, -- cgit v1.2.3 From 134ef2388e7f3271d13223decdb5e45b0f84489f Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 15 Feb 2022 19:02:17 +0200 Subject: net: dsa: add explicit support for host bridge VLANs Currently, DSA programs VLANs on shared (DSA and CPU) ports each time it does so on user ports. This is good for basic functionality but has several limitations: - the VLAN group which must reach the CPU may be radically different from the VLAN group that must be autonomously forwarded by the switch. In other words, the admin may want to isolate noisy stations and avoid traffic from them going to the control processor of the switch, where it would just waste useless cycles. The bridge already supports independent control of VLAN groups on bridge ports and on the bridge itself, and when VLAN-aware, it will drop packets in software anyway if their VID isn't added as a 'self' entry towards the bridge device. - Replaying host FDB entries may depend, for some drivers like mv88e6xxx, on replaying the host VLANs as well. The 2 VLAN groups are approximately the same in most regular cases, but there are corner cases when timing matters, and DSA's approximation of replicating VLANs on shared ports simply does not work. - If a user makes the bridge (implicitly the CPU port) join a VLAN by accident, there is no way for the CPU port to isolate itself from that noisy VLAN except by rebooting the system. This is because for each VLAN added on a user port, DSA will add it on shared ports too, but for each VLAN deletion on a user port, it will remain installed on shared ports, since DSA has no good indication of whether the VLAN is still in use or not. Now that the bridge driver emits well-balanced SWITCHDEV_OBJ_ID_PORT_VLAN addition and removal events, DSA has a simple and straightforward task of separating the bridge port VLANs (these have an orig_dev which is a DSA slave interface, or a LAG interface) from the host VLANs (these have an orig_dev which is a bridge interface), and to keep a simple reference count of each VID on each shared port. Forwarding VLANs must be installed on the bridge ports and on all DSA ports interconnecting them. We don't have a good view of the exact topology, so we simply install forwarding VLANs on all DSA ports, which is what has been done until now. Host VLANs must be installed primarily on the dedicated CPU port of each bridge port. More subtly, they must also be installed on upstream-facing and downstream-facing DSA ports that are connecting the bridge ports and the CPU. This ensures that the mv88e6xxx's problem (VID of host FDB entry may be absent from VTU) is still addressed even if that switch is in a cross-chip setup, and it has no local CPU port. Therefore: - user ports contain only bridge port (forwarding) VLANs, and no refcounting is necessary - DSA ports contain both forwarding and host VLANs. Refcounting is necessary among these 2 types. - CPU ports contain only host VLANs. Refcounting is also necessary. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/dsa.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index fd1f62a6e0a8..85cb9aed4c51 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -312,6 +312,10 @@ struct dsa_port { struct mutex addr_lists_lock; struct list_head fdbs; struct list_head mdbs; + + /* List of VLANs that CPU and DSA ports are members of. */ + struct mutex vlans_lock; + struct list_head vlans; }; /* TODO: ideally DSA ports would have a single dp->link_dp member, @@ -332,6 +336,12 @@ struct dsa_mac_addr { struct list_head list; }; +struct dsa_vlan { + u16 vid; + refcount_t refcount; + struct list_head list; +}; + struct dsa_switch { struct device *dev; -- cgit v1.2.3 From a257cacc38718c83cee003487e03197f237f5c3f Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 15 Feb 2022 13:41:02 +0100 Subject: asm-generic: Define CONFIG_HAVE_FUNCTION_DESCRIPTORS Replace HAVE_DEREFERENCE_FUNCTION_DESCRIPTOR by a config option named CONFIG_HAVE_FUNCTION_DESCRIPTORS and use it instead of 'dereference_function_descriptor' macro to know whether an arch has function descriptors. To limit churn in one of the following patches, use an #ifdef/#else construct with empty first part instead of an #ifndef in asm-generic/sections.h On powerpc, make sure the config option matches the ABI used by the compiler with a BUILD_BUG_ON() and add missing _CALL_ELF=2 when calling 'sparse' so that sparse sees the same piece of code as GCC. And include a helper to check whether an arch has function descriptors or not : have_function_descriptors() Signed-off-by: Christophe Leroy Reviewed-by: Kees Cook Reviewed-by: Nicholas Piggin Acked-by: Helge Deller Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/4a0f11fb0ea74a3197bc44dd7ba25e53a24fd03d.1644928018.git.christophe.leroy@csgroup.eu --- include/asm-generic/sections.h | 8 +++++++- include/linux/kallsyms.h | 2 +- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index 690f741764e1..3ef83e1aebee 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -59,11 +59,17 @@ extern char __noinstr_text_start[], __noinstr_text_end[]; extern __visible const void __nosave_begin, __nosave_end; /* Function descriptor handling (if any). Override in asm/sections.h */ -#ifndef dereference_function_descriptor +#ifdef CONFIG_HAVE_FUNCTION_DESCRIPTORS +#else #define dereference_function_descriptor(p) ((void *)(p)) #define dereference_kernel_function_descriptor(p) ((void *)(p)) #endif +static inline bool have_function_descriptors(void) +{ + return IS_ENABLED(CONFIG_HAVE_FUNCTION_DESCRIPTORS); +} + /** * memory_contains - checks if an object is contained within a memory region * @begin: virtual address of the beginning of the memory region diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 4176c7eca7b5..ce1bd2fbf23e 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -48,7 +48,7 @@ static inline int is_ksym_addr(unsigned long addr) static inline void *dereference_symbol_descriptor(void *ptr) { -#ifdef HAVE_DEREFERENCE_FUNCTION_DESCRIPTOR +#ifdef CONFIG_HAVE_FUNCTION_DESCRIPTORS struct module *mod; ptr = dereference_kernel_function_descriptor(ptr); -- cgit v1.2.3 From 0dc690e4ef5b901e9d4b53520854fbd5c749e09d Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 15 Feb 2022 13:41:03 +0100 Subject: asm-generic: Define 'func_desc_t' to commonly describe function descriptors We have three architectures using function descriptors, each with its own type and name. Add a common typedef that can be used in generic code. Also add a stub typedef for architecture without function descriptors, to avoid a forest of #ifdefs. It replaces the similar 'func_desc_t' previously defined in arch/powerpc/kernel/module_64.c Signed-off-by: Christophe Leroy Reviewed-by: Kees Cook Acked-by: Arnd Bergmann Acked-by: Helge Deller Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/f1f91b142b3c1082bdc1586ce71c9bac1e75213c.1644928018.git.christophe.leroy@csgroup.eu --- include/asm-generic/sections.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index 3ef83e1aebee..bbf97502470c 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -63,6 +63,11 @@ extern __visible const void __nosave_begin, __nosave_end; #else #define dereference_function_descriptor(p) ((void *)(p)) #define dereference_kernel_function_descriptor(p) ((void *)(p)) + +/* An address is simply the address of the function. */ +typedef struct { + unsigned long addr; +} func_desc_t; #endif static inline bool have_function_descriptors(void) -- cgit v1.2.3 From e1478d8eaf27704db17a44dee4c53696ed01fc9c Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 15 Feb 2022 13:41:04 +0100 Subject: asm-generic: Refactor dereference_[kernel]_function_descriptor() dereference_function_descriptor() and dereference_kernel_function_descriptor() are identical on the three architectures implementing them. Make them common and put them out-of-line in kernel/extable.c which is one of the users and has similar type of functions. Signed-off-by: Christophe Leroy Reviewed-by: Kees Cook Reviewed-by: Arnd Bergmann Acked-by: Helge Deller Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/449db09b2eba57f4ab05f80102a67d8675bc8bcd.1644928018.git.christophe.leroy@csgroup.eu --- include/asm-generic/sections.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index bbf97502470c..d0f7bdd2fdf2 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -60,6 +60,8 @@ extern __visible const void __nosave_begin, __nosave_end; /* Function descriptor handling (if any). Override in asm/sections.h */ #ifdef CONFIG_HAVE_FUNCTION_DESCRIPTORS +void *dereference_function_descriptor(void *ptr); +void *dereference_kernel_function_descriptor(void *ptr); #else #define dereference_function_descriptor(p) ((void *)(p)) #define dereference_kernel_function_descriptor(p) ((void *)(p)) -- cgit v1.2.3 From bcf8b616deb8794179e3e9c6233a53f42664afb2 Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Mon, 14 Feb 2022 14:37:06 +0100 Subject: drm/format-helper: Add drm_fb_xrgb8888_to_mono_reversed() Add support to convert from XR24 to reversed monochrome for drivers that control monochromatic display panels, that only have 1 bit per pixel. The function does a line-by-line conversion doing an intermediate step first from XR24 to 8-bit grayscale and then to reversed monochrome. The drm_fb_gray8_to_mono_reversed_line() helper was based on code from drivers/gpu/drm/tiny/repaper.c driver. Signed-off-by: Javier Martinez Canillas Reviewed-by: Thomas Zimmermann Reviewed-by: Andy Shevchenko Reviewed-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20220214133710.3278506-3-javierm@redhat.com --- include/drm/drm_format_helper.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/drm/drm_format_helper.h b/include/drm/drm_format_helper.h index b30ed5de0a33..0b0937c0b2f6 100644 --- a/include/drm/drm_format_helper.h +++ b/include/drm/drm_format_helper.h @@ -43,4 +43,8 @@ int drm_fb_blit_toio(void __iomem *dst, unsigned int dst_pitch, uint32_t dst_for const void *vmap, const struct drm_framebuffer *fb, const struct drm_rect *rect); +void drm_fb_xrgb8888_to_mono_reversed(void *dst, unsigned int dst_pitch, const void *src, + const struct drm_framebuffer *fb, + const struct drm_rect *clip); + #endif /* __LINUX_DRM_FORMAT_HELPER_H */ -- cgit v1.2.3 From 08bc13d8efe30258850ecdc5d4f38c0bc07689c0 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 10 Feb 2022 20:12:43 +0100 Subject: ieee80211: use tab to indent struct ieee80211_neighbor_ap_info Somehow spaces were used here, use tab instead. Link: https://lore.kernel.org/r/20220210201242.da8fa2e5ae8d.Ia452db01876e52e815f6337fef437049df0d8bd9@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 60ee7b3f58e7..a2940a853783 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -4005,10 +4005,10 @@ static inline bool for_each_element_completed(const struct element *element, #define IEEE80211_RNR_TBTT_PARAMS_COLOC_AP 0x40 struct ieee80211_neighbor_ap_info { - u8 tbtt_info_hdr; - u8 tbtt_info_len; - u8 op_class; - u8 channel; + u8 tbtt_info_hdr; + u8 tbtt_info_len; + u8 op_class; + u8 channel; } __packed; enum ieee80211_range_params_max_total_ltf { -- cgit v1.2.3 From d61f4274daa41565b5f9ce589b4ba1239781c139 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 14 Feb 2022 17:29:21 +0100 Subject: ieee80211: add helper to check HE capability element size This element has a very dynamic structure, create a small helper function to validate its size. We're currently checking it in mac80211 in a conversion function, but that's actually slightly buggy. Link: https://lore.kernel.org/r/20220214172920.750bee9eaf37.Ie18359bd38143b7dc949078f10752413e6d36854@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index a2940a853783..dfc84680af82 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -9,7 +9,7 @@ * Copyright (c) 2006, Michael Wu * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright (c) 2016 - 2017 Intel Deutschland GmbH - * Copyright (c) 2018 - 2021 Intel Corporation + * Copyright (c) 2018 - 2022 Intel Corporation */ #ifndef LINUX_IEEE80211_H @@ -2338,6 +2338,29 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) return n; } +static inline bool ieee80211_he_capa_size_ok(const u8 *data, u8 len) +{ + const struct ieee80211_he_cap_elem *he_cap_ie_elem = (const void *)data; + u8 needed = sizeof(*he_cap_ie_elem); + + if (len < needed) + return false; + + needed += ieee80211_he_mcs_nss_size(he_cap_ie_elem); + if (len < needed) + return false; + + if (he_cap_ie_elem->phy_cap_info[6] & + IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) { + if (len < needed + 1) + return false; + needed += ieee80211_he_ppe_size(data[needed], + he_cap_ie_elem->phy_cap_info); + } + + return len >= needed; +} + /* HE Operation defines */ #define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK 0x00000007 #define IEEE80211_HE_OPERATION_TWT_REQUIRED 0x00000008 -- cgit v1.2.3 From cbc1ca0a9d0a54cb8aa7c54c16e71599551e3f74 Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Mon, 14 Feb 2022 17:29:51 +0100 Subject: ieee80211: Add EHT (802.11be) definitions Based on Draft P802.11be_D1.4. Signed-off-by: Ilan Peer Link: https://lore.kernel.org/r/20220214173004.928e23cacb2b.Id30a3ef2844b296efbd5486fe1da9ca36a95c5cf@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 299 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 299 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index dfc84680af82..7204bc28ca31 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -1925,6 +1926,111 @@ struct ieee80211_mu_edca_param_set { struct ieee80211_he_mu_edca_param_ac_rec ac_vo; } __packed; +#define IEEE80211_EHT_MCS_NSS_RX 0x0f +#define IEEE80211_EHT_MCS_NSS_TX 0xf0 + +/** + * struct ieee80211_eht_mcs_nss_supp_20mhz_only - EHT 20MHz only station max + * supported NSS for per MCS. + * + * For each field below, bits 0 - 3 indicate the maximal number of spatial + * streams for Rx, and bits 4 - 7 indicate the maximal number of spatial streams + * for Tx. + * + * @rx_tx_mcs7_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 0 - 7. + * @rx_tx_mcs9_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 8 - 9. + * @rx_tx_mcs11_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 10 - 11. + * @rx_tx_mcs13_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 12 - 13. + */ +struct ieee80211_eht_mcs_nss_supp_20mhz_only { + u8 rx_tx_mcs7_max_nss; + u8 rx_tx_mcs9_max_nss; + u8 rx_tx_mcs11_max_nss; + u8 rx_tx_mcs13_max_nss; +}; + +/** + * struct ieee80211_eht_mcs_nss_supp_bw - EHT max supported NSS per MCS (except + * 20MHz only stations). + * + * For each field below, bits 0 - 3 indicate the maximal number of spatial + * streams for Rx, and bits 4 - 7 indicate the maximal number of spatial streams + * for Tx. + * + * @rx_tx_mcs9_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 0 - 9. + * @rx_tx_mcs11_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 10 - 11. + * @rx_tx_mcs13_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 12 - 13. + */ +struct ieee80211_eht_mcs_nss_supp_bw { + u8 rx_tx_mcs9_max_nss; + u8 rx_tx_mcs11_max_nss; + u8 rx_tx_mcs13_max_nss; +}; + +/** + * struct ieee80211_eht_cap_elem_fixed - EHT capabilities fixed data + * + * This structure is the "EHT Capabilities element" fixed fields as + * described in P802.11be_D1.4 section 9.4.2.313. + * + * @mac_cap_info: MAC capabilities, see IEEE80211_EHT_MAC_CAP* + * @phy_cap_info: PHY capabilities, see IEEE80211_EHT_PHY_CAP* + */ +struct ieee80211_eht_cap_elem_fixed { + u8 mac_cap_info[2]; + u8 phy_cap_info[9]; +} __packed; + +/** + * struct ieee80211_eht_cap_elem - EHT capabilities element + * @fixed: fixed parts, see &ieee80211_eht_cap_elem_fixed + * @optional: optional parts + */ +struct ieee80211_eht_cap_elem { + struct ieee80211_eht_cap_elem_fixed fixed; + + /* + * Followed by: + * Supported EHT-MCS And NSS Set field: 4, 3, 6 or 9 octets. + * EHT PPE Thresholds field: variable length. + */ + u8 optional[]; +} __packed; + +/** + * struct ieee80211_eht_operation - eht operation element + * + * This structure is the "EHT Operation Element" fields as + * described in P802.11be_D1.4 section 9.4.2.311 + * + * FIXME: The spec is unclear how big the fields are, and doesn't + * indicate the "Disabled Subchannel Bitmap Present" in the + * structure (Figure 9-1002a) at all ... + */ +struct ieee80211_eht_operation { + u8 chan_width; + u8 ccfs; + u8 present_bm; + + u8 disable_subchannel_bitmap[]; +} __packed; + +#define IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT 0x1 + /* 802.11ac VHT Capabilities */ #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 0x00000000 #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 0x00000001 @@ -2129,6 +2235,8 @@ enum ieee80211_client_reg_power { #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G 0x04 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G 0x08 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G 0x10 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL 0x1e + #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_2G 0x20 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_5G 0x40 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK 0xfe @@ -2622,6 +2730,194 @@ ieee80211_he_spr_size(const u8 *he_spr_ie) #define S1G_OPER_CH_WIDTH_PRIMARY_1MHZ BIT(0) #define S1G_OPER_CH_WIDTH_OPER GENMASK(4, 1) +/* EHT MAC capabilities as defined in P802.11be_D1.4 section 9.4.2.313.2 */ +#define IEEE80211_EHT_MAC_CAP0_NSEP_PRIO_ACCESS 0x01 +#define IEEE80211_EHT_MAC_CAP0_OM_CONTROL 0x02 +#define IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 0x04 +#define IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2 0x08 +#define IEEE80211_EHT_MAC_CAP0_RESTRICTED_TWT 0x10 +#define IEEE80211_EHT_MAC_CAP0_SCS_TRAFFIC_DESC 0x20 +#define IEEE80211_EHT_MAC_CAP0_MAX_AMPDU_LEN_MASK 0xc0 +#define IEEE80211_EHT_MAC_CAP0_MAX_AMPDU_LEN_3895 0 +#define IEEE80211_EHT_MAC_CAP0_MAX_AMPDU_LEN_7991 1 +#define IEEE80211_EHT_MAC_CAP0_MAX_AMPDU_LEN_11454 2 + +/* EHT PHY capabilities as defined in P802.11be_D1.4 section 9.4.2.313.3 */ +#define IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ 0x02 +#define IEEE80211_EHT_PHY_CAP0_242_TONE_RU_GT20MHZ 0x04 +#define IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI 0x08 +#define IEEE80211_EHT_PHY_CAP0_PARTIAL_BW_UL_MU_MIMO 0x10 +#define IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER 0x20 +#define IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMEE 0x40 + +/* EHT beamformee number of spatial streams <= 80MHz is split */ +#define IEEE80211_EHT_PHY_CAP0_BEAMFORMEE_SS_80MHZ_MASK 0x80 +#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_80MHZ_MASK 0x03 + +#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK 0x1c +#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_320MHZ_MASK 0xe0 + +#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_80MHZ_MASK 0x07 +#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK 0x38 + +/* EHT number of sounding dimensions for 320MHz is split */ +#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK 0xc0 +#define IEEE80211_EHT_PHY_CAP3_SOUNDING_DIM_320MHZ_MASK 0x01 +#define IEEE80211_EHT_PHY_CAP3_NG_16_SU_FEEDBACK 0x02 +#define IEEE80211_EHT_PHY_CAP3_NG_16_MU_FEEDBACK 0x04 +#define IEEE80211_EHT_PHY_CAP3_CODEBOOK_4_2_SU_FDBK 0x08 +#define IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK 0x10 +#define IEEE80211_EHT_PHY_CAP3_TRIG_SU_BF_FDBK 0x20 +#define IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK 0x40 +#define IEEE80211_EHT_PHY_CAP3_TRIG_CQI_FDBK 0x80 + +#define IEEE80211_EHT_PHY_CAP4_PART_BW_DL_MU_MIMO 0x01 +#define IEEE80211_EHT_PHY_CAP4_PSR_SR_SUPP 0x02 +#define IEEE80211_EHT_PHY_CAP4_POWER_BOOST_FACT_SUPP 0x04 +#define IEEE80211_EHT_PHY_CAP4_EHT_MU_PPDU_4_EHT_LTF_08_GI 0x08 +#define IEEE80211_EHT_PHY_CAP4_MAX_NC_MASK 0xf0 + +#define IEEE80211_EHT_PHY_CAP5_NON_TRIG_CQI_FEEDBACK 0x01 +#define IEEE80211_EHT_PHY_CAP5_TX_LESS_242_TONE_RU_SUPP 0x02 +#define IEEE80211_EHT_PHY_CAP5_RX_LESS_242_TONE_RU_SUPP 0x04 +#define IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT 0x08 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK 0x30 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_0US 0 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_8US 1 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_16US 2 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_20US 3 + +/* Maximum number of supported EHT LTF is split */ +#define IEEE80211_EHT_PHY_CAP5_MAX_NUM_SUPP_EHT_LTF_MASK 0xc0 +#define IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK 0x07 + +#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK 0x78 +#define IEEE80211_EHT_PHY_CAP6_EHT_DUP_6GHZ_SUPP 0x80 + +#define IEEE80211_EHT_PHY_CAP7_20MHZ_STA_RX_NDP_WIDER_BW 0x01 +#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ 0x02 +#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ 0x04 +#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_320MHZ 0x08 +#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ 0x10 +#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ 0x20 +#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_320MHZ 0x40 +#define IEEE80211_EHT_PHY_CAP7_TB_SOUNDING_FDBK_RATE_LIMIT 0x80 + +#define IEEE80211_EHT_PHY_CAP8_RX_1024QAM_WIDER_BW_DL_OFDMA 0x01 +#define IEEE80211_EHT_PHY_CAP8_RX_4096QAM_WIDER_BW_DL_OFDMA 0x02 + +/* + * EHT operation channel width as defined in P802.11be_D1.4 section 9.4.2.311 + */ +#define IEEE80211_EHT_OPER_CHAN_WIDTH 0x7 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_20MHZ 0 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_40MHZ 1 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_80MHZ 2 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_160MHZ 3 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_320MHZ 4 + +/* Calculate 802.11be EHT capabilities IE Tx/Rx EHT MCS NSS Support Field size */ +static inline u8 +ieee80211_eht_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap, + const struct ieee80211_eht_cap_elem_fixed *eht_cap) +{ + u8 count = 0; + + /* on 2.4 GHz, if it supports 40 MHz, the result is 3 */ + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G) + return 3; + + /* on 2.4 GHz, these three bits are reserved, so should be 0 */ + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G) + count += 3; + + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) + count += 3; + + if (eht_cap->phy_cap_info[0] & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ) + count += 3; + + return count ? count : 4; +} + +/* 802.11be EHT PPE Thresholds */ +#define IEEE80211_EHT_PPE_THRES_NSS_POS 0 +#define IEEE80211_EHT_PPE_THRES_NSS_MASK 0xf +#define IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK 0x1f0 +#define IEEE80211_EHT_PPE_THRES_INFO_PPET_SIZE 3 +#define IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE 9 + +/* + * Calculate 802.11be EHT capabilities IE EHT field size + */ +static inline u8 +ieee80211_eht_ppe_size(u16 ppe_thres_hdr, const u8 *phy_cap_info) +{ + u32 n; + + if (!(phy_cap_info[5] & + IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT)) + return 0; + + n = hweight16(ppe_thres_hdr & + IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK); + n *= 1 + u16_get_bits(ppe_thres_hdr, IEEE80211_EHT_PPE_THRES_NSS_MASK); + + /* + * Each pair is 6 bits, and we need to add the 9 "header" bits to the + * total size. + */ + n = n * IEEE80211_EHT_PPE_THRES_INFO_PPET_SIZE * 2 + + IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE; + return DIV_ROUND_UP(n, 8); +} + +static inline bool +ieee80211_eht_capa_size_ok(const u8 *he_capa, const u8 *data, u8 len) +{ + const struct ieee80211_eht_cap_elem_fixed *elem = (const void *)data; + u8 needed = sizeof(struct ieee80211_eht_cap_elem_fixed); + + if (len < needed || !he_capa) + return false; + + needed += ieee80211_eht_mcs_nss_size((const void *)he_capa, + (const void *)data); + if (len < needed) + return false; + + if (elem->phy_cap_info[5] & + IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT) { + u16 ppe_thres_hdr; + + if (len < needed + sizeof(ppe_thres_hdr)) + return false; + + ppe_thres_hdr = get_unaligned_le16(data + needed); + needed += ieee80211_eht_ppe_size(ppe_thres_hdr, + elem->phy_cap_info); + } + + return len >= needed; +} + +static inline bool +ieee80211_eht_oper_size_ok(const u8 *data, u8 len) +{ + const struct ieee80211_eht_operation *elem = (const void *)data; + u8 needed = sizeof(*elem); + + if (len < needed) + return false; + + if (elem->present_bm & IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT) + needed += 2; + + return len >= needed; +} #define LISTEN_INT_USF GENMASK(15, 14) #define LISTEN_INT_UI GENMASK(13, 0) @@ -3077,6 +3373,9 @@ enum ieee80211_eid_ext { WLAN_EID_EXT_SHORT_SSID_LIST = 58, WLAN_EID_EXT_HE_6GHZ_CAPA = 59, WLAN_EID_EXT_UL_MU_POWER_CAPA = 60, + WLAN_EID_EXT_EHT_OPERATION = 106, + WLAN_EID_EXT_EHT_MULTI_LINK = 107, + WLAN_EID_EXT_EHT_CAPABILITY = 108, }; /* Action category code */ -- cgit v1.2.3 From 2a2c86f15e17c5013b9897b67d895e64a25ae3cb Mon Sep 17 00:00:00 2001 From: Mordechay Goodstein Date: Mon, 14 Feb 2022 17:29:52 +0100 Subject: ieee80211: add EHT 1K aggregation definitions We add the fields for parsing extended ADDBA request/respond, and new max 1K aggregation for limit ADDBA request/respond. Adjust drivers to use the proper macro, IEEE80211_MAX_AMPDU_BUF -> IEEE80211_MAX_AMPDU_BUF_HE. Signed-off-by: Mordechay Goodstein Link: https://lore.kernel.org/r/20220214173004.b8b447ce95b7.I0ee2554c94e89abc7a752b0f7cc7fd79c273efea@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 7204bc28ca31..a4143466cb32 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1024,6 +1024,8 @@ struct ieee80211_tpc_report_ie { #define IEEE80211_ADDBA_EXT_FRAG_LEVEL_MASK GENMASK(2, 1) #define IEEE80211_ADDBA_EXT_FRAG_LEVEL_SHIFT 1 #define IEEE80211_ADDBA_EXT_NO_FRAG BIT(0) +#define IEEE80211_ADDBA_EXT_BUF_SIZE_MASK GENMASK(7, 5) +#define IEEE80211_ADDBA_EXT_BUF_SIZE_SHIFT 10 struct ieee80211_addba_ext_ie { u8 data; @@ -1698,10 +1700,12 @@ struct ieee80211_ht_operation { * A-MPDU buffer sizes * According to HT size varies from 8 to 64 frames * HE adds the ability to have up to 256 frames. + * EHT adds the ability to have up to 1K frames. */ #define IEEE80211_MIN_AMPDU_BUF 0x8 #define IEEE80211_MAX_AMPDU_BUF_HT 0x40 -#define IEEE80211_MAX_AMPDU_BUF 0x100 +#define IEEE80211_MAX_AMPDU_BUF_HE 0x100 +#define IEEE80211_MAX_AMPDU_BUF_EHT 0x400 /* Spatial Multiplexing Power Save Modes (for capability) */ -- cgit v1.2.3 From 5cd5a8a3e2fb11b1c8a09f062c44c1e228ef987a Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Mon, 14 Feb 2022 17:29:53 +0100 Subject: cfg80211: Add data structures to capture EHT capabilities And advertise EHT capabilities to user space when supported. Signed-off-by: Ilan Peer Link: https://lore.kernel.org/r/20220214173004.6fb70658529f.I2413a37c8f7d2d6d638038a3d95360a3fce0114d@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 63 ++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/nl80211.h | 12 +++++++++ 2 files changed, 75 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f6db085ff3df..7bec15f605be 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -360,6 +360,48 @@ struct ieee80211_sta_he_cap { u8 ppe_thres[IEEE80211_HE_PPE_THRES_MAX_LEN]; }; +/** + * struct ieee80211_eht_mcs_nss_supp - EHT max supported NSS per MCS + * + * See P802.11be_D1.3 Table 9-401k - "Subfields of the Supported EHT-MCS + * and NSS Set field" + * + * @only_20mhz: MCS/NSS support for 20 MHz-only STA. + * @bw._80: MCS/NSS support for BW <= 80 MHz + * @bw._160: MCS/NSS support for BW = 160 MHz + * @bw._320: MCS/NSS support for BW = 320 MHz + */ +struct ieee80211_eht_mcs_nss_supp { + union { + struct ieee80211_eht_mcs_nss_supp_20mhz_only only_20mhz; + struct { + struct ieee80211_eht_mcs_nss_supp_bw _80; + struct ieee80211_eht_mcs_nss_supp_bw _160; + struct ieee80211_eht_mcs_nss_supp_bw _320; + } __packed bw; + } __packed; +} __packed; + +#define IEEE80211_EHT_PPE_THRES_MAX_LEN 32 + +/** + * struct ieee80211_sta_eht_cap - STA's EHT capabilities + * + * This structure describes most essential parameters needed + * to describe 802.11be EHT capabilities for a STA. + * + * @has_eht: true iff EHT data is valid. + * @eht_cap_elem: Fixed portion of the eht capabilities element. + * @eht_mcs_nss_supp: The supported NSS/MCS combinations. + * @eht_ppe_thres: Holds the PPE Thresholds data. + */ +struct ieee80211_sta_eht_cap { + bool has_eht; + struct ieee80211_eht_cap_elem_fixed eht_cap_elem; + struct ieee80211_eht_mcs_nss_supp eht_mcs_nss_supp; + u8 eht_ppe_thres[IEEE80211_EHT_PPE_THRES_MAX_LEN]; +}; + /** * struct ieee80211_sband_iftype_data - sband data per interface type * @@ -379,6 +421,7 @@ struct ieee80211_sband_iftype_data { u16 types_mask; struct ieee80211_sta_he_cap he_cap; struct ieee80211_he_6ghz_capa he_6ghz_capa; + struct ieee80211_sta_eht_cap eht_cap; struct { const u8 *data; unsigned int len; @@ -561,6 +604,26 @@ ieee80211_get_he_6ghz_capa(const struct ieee80211_supported_band *sband, return data->he_6ghz_capa.capa; } +/** + * ieee80211_get_eht_iftype_cap - return ETH capabilities for an sband's iftype + * @sband: the sband to search for the iftype on + * @iftype: enum nl80211_iftype + * + * Return: pointer to the struct ieee80211_sta_eht_cap, or NULL is none found + */ +static inline const struct ieee80211_sta_eht_cap * +ieee80211_get_eht_iftype_cap(const struct ieee80211_supported_band *sband, + enum nl80211_iftype iftype) +{ + const struct ieee80211_sband_iftype_data *data = + ieee80211_get_sband_iftype_data(sband, iftype); + + if (data && data->eht_cap.has_eht) + return &data->eht_cap; + + return NULL; +} + /** * wiphy_read_of_freq_limits - read frequency limits from device tree * diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 195a238a322e..d305a8b8c536 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3766,6 +3766,14 @@ enum nl80211_mpath_info { * given for all 6 GHz band channels * @NL80211_BAND_IFTYPE_ATTR_VENDOR_ELEMS: vendor element capabilities that are * advertised on this band/for this iftype (binary) + * @NL80211_BAND_IFTYPE_ATTR_EHT_CAP_MAC: EHT MAC capabilities as in EHT + * capabilities element + * @NL80211_BAND_IFTYPE_ATTR_EHT_CAP_PHY: EHT PHY capabilities as in EHT + * capabilities element + * @NL80211_BAND_IFTYPE_ATTR_EHT_CAP_MCS_SET: EHT supported NSS/MCS as in EHT + * capabilities element + * @NL80211_BAND_IFTYPE_ATTR_EHT_CAP_PPE: EHT PPE thresholds information as + * defined in EHT capabilities element * @__NL80211_BAND_IFTYPE_ATTR_AFTER_LAST: internal use * @NL80211_BAND_IFTYPE_ATTR_MAX: highest band attribute currently defined */ @@ -3779,6 +3787,10 @@ enum nl80211_band_iftype_attr { NL80211_BAND_IFTYPE_ATTR_HE_CAP_PPE, NL80211_BAND_IFTYPE_ATTR_HE_6GHZ_CAPA, NL80211_BAND_IFTYPE_ATTR_VENDOR_ELEMS, + NL80211_BAND_IFTYPE_ATTR_EHT_CAP_MAC, + NL80211_BAND_IFTYPE_ATTR_EHT_CAP_PHY, + NL80211_BAND_IFTYPE_ATTR_EHT_CAP_MCS_SET, + NL80211_BAND_IFTYPE_ATTR_EHT_CAP_PPE, /* keep last */ __NL80211_BAND_IFTYPE_ATTR_AFTER_LAST, -- cgit v1.2.3 From 3743bec6120ae0748cb3fda6ff80a690117ef1f3 Mon Sep 17 00:00:00 2001 From: Jia Ding Date: Mon, 14 Feb 2022 17:29:54 +0100 Subject: cfg80211: Add support for EHT 320 MHz channel width Add 320 MHz support in the channel def and center frequency validation with compatible check. Signed-off-by: Jia Ding Co-authored-by: Karthikeyan Periyasamy Signed-off-by: Karthikeyan Periyasamy Co-authored-by: Muna Sinada Signed-off-by: Muna Sinada Co-authored-by: Veerendranath Jakkam Signed-off-by: Veerendranath Jakkam Link: https://lore.kernel.org/r/1640163883-12696-5-git-send-email-quic_vjakkam@quicinc.com Link: https://lore.kernel.org/r/20220214163009.175289-1-johannes@sipsolutions.net Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 7 ++++++- include/uapi/linux/nl80211.h | 3 +++ 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7bec15f605be..a27f2d699dac 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -109,7 +109,11 @@ struct wiphy; * on this channel. * @IEEE80211_CHAN_16MHZ: 16 MHz bandwidth is permitted * on this channel. - * + * @IEEE80211_CHAN_NO_320MHZ: If the driver supports 320 MHz on the band, + * this flag indicates that a 320 MHz channel cannot use this + * channel as the control or any of the secondary channels. + * This may be due to the driver or due to regulatory bandwidth + * restrictions. */ enum ieee80211_channel_flags { IEEE80211_CHAN_DISABLED = 1<<0, @@ -131,6 +135,7 @@ enum ieee80211_channel_flags { IEEE80211_CHAN_4MHZ = 1<<16, IEEE80211_CHAN_8MHZ = 1<<17, IEEE80211_CHAN_16MHZ = 1<<18, + IEEE80211_CHAN_NO_320MHZ = 1<<19, }; #define IEEE80211_CHAN_NO_HT40 \ diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index d305a8b8c536..9e05973f3f56 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4684,6 +4684,8 @@ enum nl80211_key_mode { * @NL80211_CHAN_WIDTH_4: 4 MHz OFDM channel * @NL80211_CHAN_WIDTH_8: 8 MHz OFDM channel * @NL80211_CHAN_WIDTH_16: 16 MHz OFDM channel + * @NL80211_CHAN_WIDTH_320: 320 MHz channel, the %NL80211_ATTR_CENTER_FREQ1 + * attribute must be provided as well */ enum nl80211_chan_width { NL80211_CHAN_WIDTH_20_NOHT, @@ -4699,6 +4701,7 @@ enum nl80211_chan_width { NL80211_CHAN_WIDTH_4, NL80211_CHAN_WIDTH_8, NL80211_CHAN_WIDTH_16, + NL80211_CHAN_WIDTH_320, }; /** -- cgit v1.2.3 From cfb14110acf87b4db62e07ba08a80429f1749f40 Mon Sep 17 00:00:00 2001 From: Veerendranath Jakkam Date: Mon, 14 Feb 2022 17:29:55 +0100 Subject: nl80211: add EHT MCS support Add support for reporting and calculating EHT bitrates. Signed-off-by: Veerendranath Jakkam Link: https://lore.kernel.org/r/1640163883-12696-7-git-send-email-quic_vjakkam@quicinc.com Link: https://lore.kernel.org/r/20220214163009.175289-2-johannes@sipsolutions.net Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 11 ++++++++ include/uapi/linux/nl80211.h | 62 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 73 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index a27f2d699dac..f35ffd81d213 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1595,6 +1595,7 @@ int cfg80211_check_station_change(struct wiphy *wiphy, * @RATE_INFO_FLAGS_HE_MCS: HE MCS information * @RATE_INFO_FLAGS_EDMG: 60GHz MCS in EDMG mode * @RATE_INFO_FLAGS_EXTENDED_SC_DMG: 60GHz extended SC MCS + * @RATE_INFO_FLAGS_EHT_MCS: EHT MCS information */ enum rate_info_flags { RATE_INFO_FLAGS_MCS = BIT(0), @@ -1604,6 +1605,7 @@ enum rate_info_flags { RATE_INFO_FLAGS_HE_MCS = BIT(4), RATE_INFO_FLAGS_EDMG = BIT(5), RATE_INFO_FLAGS_EXTENDED_SC_DMG = BIT(6), + RATE_INFO_FLAGS_EHT_MCS = BIT(7), }; /** @@ -1618,6 +1620,8 @@ enum rate_info_flags { * @RATE_INFO_BW_80: 80 MHz bandwidth * @RATE_INFO_BW_160: 160 MHz bandwidth * @RATE_INFO_BW_HE_RU: bandwidth determined by HE RU allocation + * @RATE_INFO_BW_320: 320 MHz bandwidth + * @RATE_INFO_BW_EHT_RU: bandwidth determined by EHT RU allocation */ enum rate_info_bw { RATE_INFO_BW_20 = 0, @@ -1627,6 +1631,8 @@ enum rate_info_bw { RATE_INFO_BW_80, RATE_INFO_BW_160, RATE_INFO_BW_HE_RU, + RATE_INFO_BW_320, + RATE_INFO_BW_EHT_RU, }; /** @@ -1644,6 +1650,9 @@ enum rate_info_bw { * @he_ru_alloc: HE RU allocation (from &enum nl80211_he_ru_alloc, * only valid if bw is %RATE_INFO_BW_HE_RU) * @n_bonded_ch: In case of EDMG the number of bonded channels (1-4) + * @eht_gi: EHT guard interval (from &enum nl80211_eht_gi) + * @eht_ru_alloc: EHT RU allocation (from &enum nl80211_eht_ru_alloc, + * only valid if bw is %RATE_INFO_BW_EHT_RU) */ struct rate_info { u8 flags; @@ -1655,6 +1664,8 @@ struct rate_info { u8 he_dcm; u8 he_ru_alloc; u8 n_bonded_ch; + u8 eht_gi; + u8 eht_ru_alloc; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 9e05973f3f56..d0ba70ea5d04 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3392,6 +3392,56 @@ enum nl80211_he_ru_alloc { NL80211_RATE_INFO_HE_RU_ALLOC_2x996, }; +/** + * enum nl80211_eht_gi - EHT guard interval + * @NL80211_RATE_INFO_EHT_GI_0_8: 0.8 usec + * @NL80211_RATE_INFO_EHT_GI_1_6: 1.6 usec + * @NL80211_RATE_INFO_EHT_GI_3_2: 3.2 usec + */ +enum nl80211_eht_gi { + NL80211_RATE_INFO_EHT_GI_0_8, + NL80211_RATE_INFO_EHT_GI_1_6, + NL80211_RATE_INFO_EHT_GI_3_2, +}; + +/** + * enum nl80211_eht_ru_alloc - EHT RU allocation values + * @NL80211_RATE_INFO_EHT_RU_ALLOC_26: 26-tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_52: 52-tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_52P26: 52+26-tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_106: 106-tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_106P26: 106+26 tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_242: 242-tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_484: 484-tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_484P242: 484+242 tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_996: 996-tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_996P484: 996+484 tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_996P484P242: 996+484+242 tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_2x996: 2x996-tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_2x996P484: 2x996+484 tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_3x996: 3x996-tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_3x996P484: 3x996+484 tone RU allocation + * @NL80211_RATE_INFO_EHT_RU_ALLOC_4x996: 4x996-tone RU allocation + */ +enum nl80211_eht_ru_alloc { + NL80211_RATE_INFO_EHT_RU_ALLOC_26, + NL80211_RATE_INFO_EHT_RU_ALLOC_52, + NL80211_RATE_INFO_EHT_RU_ALLOC_52P26, + NL80211_RATE_INFO_EHT_RU_ALLOC_106, + NL80211_RATE_INFO_EHT_RU_ALLOC_106P26, + NL80211_RATE_INFO_EHT_RU_ALLOC_242, + NL80211_RATE_INFO_EHT_RU_ALLOC_484, + NL80211_RATE_INFO_EHT_RU_ALLOC_484P242, + NL80211_RATE_INFO_EHT_RU_ALLOC_996, + NL80211_RATE_INFO_EHT_RU_ALLOC_996P484, + NL80211_RATE_INFO_EHT_RU_ALLOC_996P484P242, + NL80211_RATE_INFO_EHT_RU_ALLOC_2x996, + NL80211_RATE_INFO_EHT_RU_ALLOC_2x996P484, + NL80211_RATE_INFO_EHT_RU_ALLOC_3x996, + NL80211_RATE_INFO_EHT_RU_ALLOC_3x996P484, + NL80211_RATE_INFO_EHT_RU_ALLOC_4x996, +}; + /** * enum nl80211_rate_info - bitrate information * @@ -3431,6 +3481,13 @@ enum nl80211_he_ru_alloc { * @NL80211_RATE_INFO_HE_DCM: HE DCM value (u8, 0/1) * @NL80211_RATE_INFO_RU_ALLOC: HE RU allocation, if not present then * non-OFDMA was used (u8, see &enum nl80211_he_ru_alloc) + * @NL80211_RATE_INFO_320_MHZ_WIDTH: 320 MHz bitrate + * @NL80211_RATE_INFO_EHT_MCS: EHT MCS index (u8, 0-15) + * @NL80211_RATE_INFO_EHT_NSS: EHT NSS value (u8, 1-8) + * @NL80211_RATE_INFO_EHT_GI: EHT guard interval identifier + * (u8, see &enum nl80211_eht_gi) + * @NL80211_RATE_INFO_EHT_RU_ALLOC: EHT RU allocation, if not present then + * non-OFDMA was used (u8, see &enum nl80211_eht_ru_alloc) * @__NL80211_RATE_INFO_AFTER_LAST: internal use */ enum nl80211_rate_info { @@ -3452,6 +3509,11 @@ enum nl80211_rate_info { NL80211_RATE_INFO_HE_GI, NL80211_RATE_INFO_HE_DCM, NL80211_RATE_INFO_HE_RU_ALLOC, + NL80211_RATE_INFO_320_MHZ_WIDTH, + NL80211_RATE_INFO_EHT_MCS, + NL80211_RATE_INFO_EHT_NSS, + NL80211_RATE_INFO_EHT_GI, + NL80211_RATE_INFO_EHT_RU_ALLOC, /* keep last */ __NL80211_RATE_INFO_AFTER_LAST, -- cgit v1.2.3 From c2b3d7699fb0ce66538b829af43970acc2f89060 Mon Sep 17 00:00:00 2001 From: Sriram R Date: Mon, 14 Feb 2022 17:29:56 +0100 Subject: nl80211: add support for 320MHz channel limitation Add support to advertise drivers or regulatory limitations on 320 MHz channels to userspace. Signed-off-by: Sriram R Co-authored-by: Karthikeyan Periyasamy Signed-off-by: Karthikeyan Periyasamy Co-authored-by: Veerendranath Jakkam Signed-off-by: Veerendranath Jakkam Link: https://lore.kernel.org/r/1640163883-12696-6-git-send-email-quic_vjakkam@quicinc.com Link: https://lore.kernel.org/r/20220214163009.175289-3-johannes@sipsolutions.net Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index d0ba70ea5d04..6a338dafcd07 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3997,6 +3997,8 @@ enum nl80211_wmm_rule { * on this channel in current regulatory domain. * @NL80211_FREQUENCY_ATTR_16MHZ: 16 MHz operation is allowed * on this channel in current regulatory domain. + * @NL80211_FREQUENCY_ATTR_NO_320MHZ: any 320 MHz channel using this channel + * as the primary or any of the secondary channels isn't possible * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number * currently defined * @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use @@ -4033,6 +4035,7 @@ enum nl80211_frequency_attr { NL80211_FREQUENCY_ATTR_4MHZ, NL80211_FREQUENCY_ATTR_8MHZ, NL80211_FREQUENCY_ATTR_16MHZ, + NL80211_FREQUENCY_ATTR_NO_320MHZ, /* keep last */ __NL80211_FREQUENCY_ATTR_AFTER_LAST, @@ -4231,6 +4234,7 @@ enum nl80211_sched_scan_match_attr { * @NL80211_RRF_NO_80MHZ: 80MHz operation not allowed * @NL80211_RRF_NO_160MHZ: 160MHz operation not allowed * @NL80211_RRF_NO_HE: HE operation not allowed + * @NL80211_RRF_NO_320MHZ: 320MHz operation not allowed */ enum nl80211_reg_rule_flags { NL80211_RRF_NO_OFDM = 1<<0, @@ -4249,6 +4253,7 @@ enum nl80211_reg_rule_flags { NL80211_RRF_NO_80MHZ = 1<<15, NL80211_RRF_NO_160MHZ = 1<<16, NL80211_RRF_NO_HE = 1<<17, + NL80211_RRF_NO_320MHZ = 1<<18, }; #define NL80211_RRF_PASSIVE_SCAN NL80211_RRF_NO_IR -- cgit v1.2.3 From 31846b657857e6a73d982604f36a34710d98902c Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Mon, 14 Feb 2022 17:29:57 +0100 Subject: cfg80211: add NO-EHT flag to regulatory This may be necessary in some cases, add a flag and propagate it, just like the NO-HE that already exists. Signed-off-by: Ilan Peer [split off from a combined 320/no-EHT patch] Link: https://lore.kernel.org/r/20220214173004.dbb85a7b86bb.Ifc1e2daac51c1cc5f895ccfb79faf5eaec3950ec@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 ++ include/uapi/linux/nl80211.h | 3 +++ 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f35ffd81d213..5cfc483dece1 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -114,6 +114,7 @@ struct wiphy; * channel as the control or any of the secondary channels. * This may be due to the driver or due to regulatory bandwidth * restrictions. + * @IEEE80211_CHAN_NO_EHT: EHT operation is not permitted on this channel. */ enum ieee80211_channel_flags { IEEE80211_CHAN_DISABLED = 1<<0, @@ -136,6 +137,7 @@ enum ieee80211_channel_flags { IEEE80211_CHAN_8MHZ = 1<<17, IEEE80211_CHAN_16MHZ = 1<<18, IEEE80211_CHAN_NO_320MHZ = 1<<19, + IEEE80211_CHAN_NO_EHT = 1<<20, }; #define IEEE80211_CHAN_NO_HT40 \ diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 6a338dafcd07..baf6433c0119 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3999,6 +3999,8 @@ enum nl80211_wmm_rule { * on this channel in current regulatory domain. * @NL80211_FREQUENCY_ATTR_NO_320MHZ: any 320 MHz channel using this channel * as the primary or any of the secondary channels isn't possible + * @NL80211_FREQUENCY_ATTR_NO_EHT: EHT operation is not allowed on this channel + * in current regulatory domain. * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number * currently defined * @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use @@ -4036,6 +4038,7 @@ enum nl80211_frequency_attr { NL80211_FREQUENCY_ATTR_8MHZ, NL80211_FREQUENCY_ATTR_16MHZ, NL80211_FREQUENCY_ATTR_NO_320MHZ, + NL80211_FREQUENCY_ATTR_NO_EHT, /* keep last */ __NL80211_FREQUENCY_ATTR_AFTER_LAST, -- cgit v1.2.3 From ea05fd3581d32a0f1098657005c7a9b763798fe8 Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Mon, 14 Feb 2022 17:29:58 +0100 Subject: cfg80211: Support configuration of station EHT capabilities Add attributes and some code bits to support userspace passing in EHT capabilities of stations. Signed-off-by: Ilan Peer Link: https://lore.kernel.org/r/20220214173004.ecf0b3ff9627.Icb4a5f2ec7b41d9008ac4cfc16c59baeb84793d3@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 4 ++++ include/uapi/linux/nl80211.h | 10 +++++++++- 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5cfc483dece1..68713388b617 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1487,6 +1487,8 @@ struct sta_txpwr { * @airtime_weight: airtime scheduler weight for this station * @txpwr: transmit power for an associated station * @he_6ghz_capa: HE 6 GHz Band capabilities of station + * @eht_capa: EHT capabilities of station + * @eht_capa_len: the length of the EHT capabilities */ struct station_parameters { const u8 *supported_rates; @@ -1520,6 +1522,8 @@ struct station_parameters { u16 airtime_weight; struct sta_txpwr txpwr; const struct ieee80211_he_6ghz_capa *he_6ghz_capa; + const struct ieee80211_eht_cap_elem *eht_capa; + u8 eht_capa_len; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index baf6433c0119..98ed52663d6b 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -11,7 +11,7 @@ * Copyright 2008 Jouni Malinen * Copyright 2008 Colin McCabe * Copyright 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2021 Intel Corporation + * Copyright (C) 2018-2022 Intel Corporation * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -2659,6 +2659,10 @@ enum nl80211_commands { * enumerated in &enum nl80211_ap_settings_flags. This attribute shall be * used with %NL80211_CMD_START_AP request. * + * @NL80211_ATTR_EHT_CAPABILITY: EHT Capability information element (from + * association request when used with NL80211_CMD_NEW_STATION). Can be set + * only if %NL80211_STA_FLAG_WME is set. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3169,6 +3173,8 @@ enum nl80211_attrs { NL80211_ATTR_AP_SETTINGS_FLAGS, + NL80211_ATTR_EHT_CAPABILITY, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -3224,6 +3230,8 @@ enum nl80211_attrs { #define NL80211_HE_MAX_CAPABILITY_LEN 54 #define NL80211_MAX_NR_CIPHER_SUITES 5 #define NL80211_MAX_NR_AKM_SUITES 2 +#define NL80211_EHT_MIN_CAPABILITY_LEN 13 +#define NL80211_EHT_MAX_CAPABILITY_LEN 51 #define NL80211_MIN_REMAIN_ON_CHANNEL_TIME 10 -- cgit v1.2.3 From 5dca295dd76756c7918ad7113fc4a3cf8262ed43 Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Mon, 14 Feb 2022 17:30:00 +0100 Subject: mac80211: Add initial support for EHT and 320 MHz channels Add initial support for EHT and 320 MHz bandwidth in mac80211. As a new IEEE80211_STA_RX_BW_320 is added to enum ieee80211_sta_rx_bandwidth, update the drivers to avoid compilation warnings. Signed-off-by: Ilan Peer Link: https://lore.kernel.org/r/20220214173004.0f144cc0bba6.Iad18111264da87eed5fd7b017f0cc6e58c604e07@changeid Signed-off-by: Johannes Berg --- include/net/mac80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index bd6912d0292b..586d3c26c8ac 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2005,6 +2005,7 @@ enum ieee80211_sta_state { * @IEEE80211_STA_RX_BW_80: station can receive up to 80 MHz * @IEEE80211_STA_RX_BW_160: station can receive up to 160 MHz * (including 80+80 MHz) + * @IEEE80211_STA_RX_BW_320: station can receive up to 320 MHz * * Implementation note: 20 must be zero to be initialized * correctly, the values must be sorted. @@ -2014,6 +2015,7 @@ enum ieee80211_sta_rx_bandwidth { IEEE80211_STA_RX_BW_40, IEEE80211_STA_RX_BW_80, IEEE80211_STA_RX_BW_160, + IEEE80211_STA_RX_BW_320, }; /** -- cgit v1.2.3 From a1de64078bf7a3fed856fef5334132ba1963b683 Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Mon, 14 Feb 2022 17:30:02 +0100 Subject: mac80211: Handle station association response with EHT When the association is an EHT association, parse the EHT element from the association response and update the station's EHT capabilities accordingly. Signed-off-by: Ilan Peer Link: https://lore.kernel.org/r/20220214173004.f33574718755.I21182234c5303d9423eabd5eb997e7cf75f8e0c8@changeid Signed-off-by: Johannes Berg --- include/net/mac80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 586d3c26c8ac..f118b8fe667a 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -636,6 +636,7 @@ struct ieee80211_fils_discovery { * @tx_pwr_env: transmit power envelope array of BSS. * @tx_pwr_env_num: number of @tx_pwr_env. * @pwr_reduction: power constraint of BSS. + * @eht_support: does this BSS support EHT */ struct ieee80211_bss_conf { const u8 *bssid; @@ -710,6 +711,7 @@ struct ieee80211_bss_conf { struct ieee80211_tx_pwr_env tx_pwr_env[IEEE80211_TPE_MAX_IE_COUNT]; u8 tx_pwr_env_num; u8 pwr_reduction; + bool eht_support; }; /** @@ -2071,6 +2073,7 @@ struct ieee80211_sta_txpwr { * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities * @he_cap: HE capabilities of this STA * @he_6ghz_capa: on 6 GHz, holds the HE 6 GHz band capabilities + * @eht_cap: EHT capabilities of this STA * @max_rx_aggregation_subframes: maximal amount of frames in a single AMPDU * that this station is allowed to transmit to us. * Can be modified by driver. @@ -2111,6 +2114,7 @@ struct ieee80211_sta { struct ieee80211_sta_vht_cap vht_cap; struct ieee80211_sta_he_cap he_cap; struct ieee80211_he_6ghz_capa he_6ghz_capa; + struct ieee80211_sta_eht_cap eht_cap; u16 max_rx_aggregation_subframes; bool wme; u8 uapsd_queues; -- cgit v1.2.3 From e6df4ead85d9da1b07dd40bd4c6d2182f3e210c4 Mon Sep 17 00:00:00 2001 From: Zhaoyang Huang Date: Tue, 25 Jan 2022 14:56:58 +0800 Subject: psi: fix possible trigger missing in the window When a new threshold breaching stall happens after a psi event was generated and within the window duration, the new event is not generated because the events are rate-limited to one per window. If after that no new stall is recorded then the event will not be generated even after rate-limiting duration has passed. This is happening because with no new stall, window_update will not be called even though threshold was previously breached. To fix this, record threshold breaching occurrence and generate the event once window duration is passed. Suggested-by: Suren Baghdasaryan Signed-off-by: Zhaoyang Huang Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Acked-by: Suren Baghdasaryan Link: https://lore.kernel.org/r/1643093818-19835-1-git-send-email-huangzhaoyang@gmail.com --- include/linux/psi_types.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 516c0fe836fd..dc3ec5e4b9ee 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -144,6 +144,9 @@ struct psi_trigger { /* Refcounting to prevent premature destruction */ struct kref refcount; + + /* Deferred event(s) from previous ratelimit window */ + bool pending_event; }; struct psi_group { -- cgit v1.2.3 From 04d4e665a60902cf36e7ad39af1179cb5df542ad Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 7 Feb 2022 16:59:06 +0100 Subject: sched/isolation: Use single feature type while referring to housekeeping cpumask Refer to housekeeping APIs using single feature types instead of flags. This prevents from passing multiple isolation features at once to housekeeping interfaces, which soon won't be possible anymore as each isolation features will have their own cpumask. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Juri Lelli Reviewed-by: Phil Auld Link: https://lore.kernel.org/r/20220207155910.527133-5-frederic@kernel.org --- include/linux/sched/isolation.h | 43 +++++++++++++++++++++-------------------- 1 file changed, 22 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index cc9f393e2a70..8c15abd67aed 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -5,54 +5,55 @@ #include #include -enum hk_flags { - HK_FLAG_TIMER = 1, - HK_FLAG_RCU = (1 << 1), - HK_FLAG_MISC = (1 << 2), - HK_FLAG_SCHED = (1 << 3), - HK_FLAG_TICK = (1 << 4), - HK_FLAG_DOMAIN = (1 << 5), - HK_FLAG_WQ = (1 << 6), - HK_FLAG_MANAGED_IRQ = (1 << 7), - HK_FLAG_KTHREAD = (1 << 8), +enum hk_type { + HK_TYPE_TIMER, + HK_TYPE_RCU, + HK_TYPE_MISC, + HK_TYPE_SCHED, + HK_TYPE_TICK, + HK_TYPE_DOMAIN, + HK_TYPE_WQ, + HK_TYPE_MANAGED_IRQ, + HK_TYPE_KTHREAD, + HK_TYPE_MAX }; #ifdef CONFIG_CPU_ISOLATION DECLARE_STATIC_KEY_FALSE(housekeeping_overridden); -extern int housekeeping_any_cpu(enum hk_flags flags); -extern const struct cpumask *housekeeping_cpumask(enum hk_flags flags); -extern bool housekeeping_enabled(enum hk_flags flags); -extern void housekeeping_affine(struct task_struct *t, enum hk_flags flags); -extern bool housekeeping_test_cpu(int cpu, enum hk_flags flags); +extern int housekeeping_any_cpu(enum hk_type type); +extern const struct cpumask *housekeeping_cpumask(enum hk_type type); +extern bool housekeeping_enabled(enum hk_type type); +extern void housekeeping_affine(struct task_struct *t, enum hk_type type); +extern bool housekeeping_test_cpu(int cpu, enum hk_type type); extern void __init housekeeping_init(void); #else -static inline int housekeeping_any_cpu(enum hk_flags flags) +static inline int housekeeping_any_cpu(enum hk_type type) { return smp_processor_id(); } -static inline const struct cpumask *housekeeping_cpumask(enum hk_flags flags) +static inline const struct cpumask *housekeeping_cpumask(enum hk_type type) { return cpu_possible_mask; } -static inline bool housekeeping_enabled(enum hk_flags flags) +static inline bool housekeeping_enabled(enum hk_type type) { return false; } static inline void housekeeping_affine(struct task_struct *t, - enum hk_flags flags) { } + enum hk_type type) { } static inline void housekeeping_init(void) { } #endif /* CONFIG_CPU_ISOLATION */ -static inline bool housekeeping_cpu(int cpu, enum hk_flags flags) +static inline bool housekeeping_cpu(int cpu, enum hk_type type) { #ifdef CONFIG_CPU_ISOLATION if (static_branch_unlikely(&housekeeping_overridden)) - return housekeeping_test_cpu(cpu, flags); + return housekeeping_test_cpu(cpu, type); #endif return true; } -- cgit v1.2.3 From fe65deb56e552a8c9bf7f27860dbdeac12a36116 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 14 Feb 2022 01:57:16 +0900 Subject: jump_label: Avoid unneeded casts in STATIC_KEY_INIT_{TRUE,FALSE} Commit 3821fd35b58d ("jump_label: Reduce the size of struct static_key") introduced the union to struct static_key. It is more natual to set JUMP_TYPE_* to the .type field without casting. Signed-off-by: Masahiro Yamada Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20220213165717.2354046-1-masahiroy@kernel.org --- include/linux/jump_label.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 48b9b2a82767..6924e6837e6d 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -251,10 +251,10 @@ extern void static_key_disable_cpuslocked(struct static_key *key); */ #define STATIC_KEY_INIT_TRUE \ { .enabled = { 1 }, \ - { .entries = (void *)JUMP_TYPE_TRUE } } + { .type = JUMP_TYPE_TRUE } } #define STATIC_KEY_INIT_FALSE \ { .enabled = { 0 }, \ - { .entries = (void *)JUMP_TYPE_FALSE } } + { .type = JUMP_TYPE_FALSE } } #else /* !CONFIG_JUMP_LABEL */ -- cgit v1.2.3 From cd27ccfc727e99352321c0c75012ab9c5a90321e Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 14 Feb 2022 01:57:17 +0900 Subject: jump_label: Refactor #ifdef of struct static_key Move #ifdef CONFIG_JUMP_LABEL inside the struct static_key. Signed-off-by: Masahiro Yamada Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20220213165717.2354046-2-masahiroy@kernel.org --- include/linux/jump_label.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 6924e6837e6d..107751cc047b 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -82,10 +82,9 @@ extern bool static_key_initialized; "%s(): static key '%pS' used before call to jump_label_init()", \ __func__, (key)) -#ifdef CONFIG_JUMP_LABEL - struct static_key { atomic_t enabled; +#ifdef CONFIG_JUMP_LABEL /* * Note: * To make anonymous unions work with old compilers, the static @@ -104,13 +103,9 @@ struct static_key { struct jump_entry *entries; struct static_key_mod *next; }; +#endif /* CONFIG_JUMP_LABEL */ }; -#else -struct static_key { - atomic_t enabled; -}; -#endif /* CONFIG_JUMP_LABEL */ #endif /* __ASSEMBLY__ */ #ifdef CONFIG_JUMP_LABEL -- cgit v1.2.3 From 8c30e2d81bfddc5ab9f6b04db1c0f7d6ca7bdf46 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 11 Feb 2022 10:46:40 +0100 Subject: fbdev: Don't sort deferred-I/O pages by default Fbdev's deferred I/O sorts all dirty pages by default, which incurs a significant overhead. Make the sorting step optional and update the few drivers that require it. Use a FIFO list by default. Most fbdev drivers with deferred I/O build a bounding rectangle around the dirty pages or simply flush the whole screen. The only two affected DRM drivers, generic fbdev and vmwgfx, both use a bounding rectangle. In those cases, the exact order of the pages doesn't matter. The other drivers look at the page index or handle pages one-by-one. The patch sets the sort_pagelist flag for those, even though some of them would probably work correctly without sorting. Driver maintainers should update their driver accordingly. Sorting pages by memory offset for deferred I/O performs an implicit bubble-sort step on the list of dirty pages. The algorithm goes through the list of dirty pages and inserts each new page according to its index field. Even worse, list traversal always starts at the first entry. As video memory is most likely updated scanline by scanline, the algorithm traverses through the complete list for each updated page. For example, with 1024x768x32bpp each page covers exactly one scanline. Writing a single screen update from top to bottom requires updating 768 pages. With an average list length of 384 entries, a screen update creates (768 * 384 =) 294912 compare operation. Fix this by making the sorting step opt-in and update the few drivers that require it. All other drivers work with unsorted page lists. Pages are appended to the list. Therefore, in the common case of writing the framebuffer top to bottom, pages are still sorted by offset, which may have a positive effect on performance. Playing a video [1] in mplayer's benchmark mode shows the difference (i7-4790, FullHD, simpledrm, kernel with debugging). mplayer -benchmark -nosound -vo fbdev ./big_buck_bunny_720p_stereo.ogg With sorted page lists: BENCHMARKs: VC: 32.960s VO: 73.068s A: 0.000s Sys: 2.413s = 108.441s BENCHMARK%: VC: 30.3947% VO: 67.3802% A: 0.0000% Sys: 2.2251% = 100.0000% With unsorted page lists: BENCHMARKs: VC: 31.005s VO: 42.889s A: 0.000s Sys: 2.256s = 76.150s BENCHMARK%: VC: 40.7156% VO: 56.3219% A: 0.0000% Sys: 2.9625% = 100.0000% VC shows the overhead of video decoding, VO shows the overhead of the video output. Using unsorted page lists reduces the benchmark's run time by ~32s/~25%. v2: * Make sorted pagelists the special case (Sam) * Comment on drivers' use of pagelist (Sam) * Warn about the overhead in comment Signed-off-by: Thomas Zimmermann Acked-by: Sam Ravnborg Acked-by: Andy Shevchenko Link: https://download.blender.org/peach/bigbuckbunny_movies/big_buck_bunny_720p_stereo.ogg # [1] Link: https://patchwork.freedesktop.org/patch/msgid/20220211094640.21632-3-tzimmermann@suse.de --- include/linux/fb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fb.h b/include/linux/fb.h index 9a14f3f8a329..39baa9a70779 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -204,6 +204,7 @@ struct fb_pixmap { struct fb_deferred_io { /* delay between mkwrite and deferred handler */ unsigned long delay; + bool sort_pagelist; /* sort pagelist by offset */ struct mutex lock; /* mutex that protects the page list */ struct list_head pagelist; /* list of touched pages */ /* callback */ -- cgit v1.2.3 From e1be43d9b5d0d1310dbd90185a8e5c7145dde40f Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Sat, 18 Sep 2021 15:17:53 -0700 Subject: overflow: Implement size_t saturating arithmetic helpers In order to perform more open-coded replacements of common allocation size arithmetic, the kernel needs saturating (SIZE_MAX) helpers for multiplication, addition, and subtraction. For example, it is common in allocators, especially on realloc, to add to an existing size: p = krealloc(map->patch, sizeof(struct reg_sequence) * (map->patch_regs + num_regs), GFP_KERNEL); There is no existing saturating replacement for this calculation, and just leaving the addition open coded inside array_size() could potentially overflow as well. For example, an overflow in an expression for a size_t argument might wrap to zero: array_size(anything, something_at_size_max + 1) == 0 Introduce size_mul(), size_add(), and size_sub() helpers that implicitly promote arguments to size_t and saturated calculations for use in allocations. With these helpers it is also possible to redefine array_size(), array3_size(), flex_array_size(), and struct_size() in terms of the new helpers. As with the check_*_overflow() helpers, the new helpers use __must_check, though what is really desired is a way to make sure that assignment is only to a size_t lvalue. Without this, it's still possible to introduce overflow/underflow via type conversion (i.e. from size_t to int). Enforcing this will currently need to be left to static analysis or future use of -Wconversion. Additionally update the overflow unit tests to force runtime evaluation for the pathological cases. Cc: Rasmus Villemoes Cc: Gustavo A. R. Silva Cc: Nathan Chancellor Cc: Jason Gunthorpe Cc: Nick Desaulniers Cc: Leon Romanovsky Cc: Keith Busch Cc: Len Baker Signed-off-by: Kees Cook --- include/linux/overflow.h | 110 +++++++++++++++++++++++++++++------------------ 1 file changed, 69 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/include/linux/overflow.h b/include/linux/overflow.h index 4669632bd72b..59d7228104d0 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -118,81 +118,94 @@ static inline bool __must_check __must_check_overflow(bool overflow) })) /** - * array_size() - Calculate size of 2-dimensional array. - * - * @a: dimension one - * @b: dimension two + * size_mul() - Calculate size_t multiplication with saturation at SIZE_MAX * - * Calculates size of 2-dimensional array: @a * @b. + * @factor1: first factor + * @factor2: second factor * - * Returns: number of bytes needed to represent the array or SIZE_MAX on - * overflow. + * Returns: calculate @factor1 * @factor2, both promoted to size_t, + * with any overflow causing the return value to be SIZE_MAX. The + * lvalue must be size_t to avoid implicit type conversion. */ -static inline __must_check size_t array_size(size_t a, size_t b) +static inline size_t __must_check size_mul(size_t factor1, size_t factor2) { size_t bytes; - if (check_mul_overflow(a, b, &bytes)) + if (check_mul_overflow(factor1, factor2, &bytes)) return SIZE_MAX; return bytes; } /** - * array3_size() - Calculate size of 3-dimensional array. + * size_add() - Calculate size_t addition with saturation at SIZE_MAX * - * @a: dimension one - * @b: dimension two - * @c: dimension three - * - * Calculates size of 3-dimensional array: @a * @b * @c. + * @addend1: first addend + * @addend2: second addend * - * Returns: number of bytes needed to represent the array or SIZE_MAX on - * overflow. + * Returns: calculate @addend1 + @addend2, both promoted to size_t, + * with any overflow causing the return value to be SIZE_MAX. The + * lvalue must be size_t to avoid implicit type conversion. */ -static inline __must_check size_t array3_size(size_t a, size_t b, size_t c) +static inline size_t __must_check size_add(size_t addend1, size_t addend2) { size_t bytes; - if (check_mul_overflow(a, b, &bytes)) - return SIZE_MAX; - if (check_mul_overflow(bytes, c, &bytes)) + if (check_add_overflow(addend1, addend2, &bytes)) return SIZE_MAX; return bytes; } -/* - * Compute a*b+c, returning SIZE_MAX on overflow. Internal helper for - * struct_size() below. +/** + * size_sub() - Calculate size_t subtraction with saturation at SIZE_MAX + * + * @minuend: value to subtract from + * @subtrahend: value to subtract from @minuend + * + * Returns: calculate @minuend - @subtrahend, both promoted to size_t, + * with any overflow causing the return value to be SIZE_MAX. For + * composition with the size_add() and size_mul() helpers, neither + * argument may be SIZE_MAX (or the result with be forced to SIZE_MAX). + * The lvalue must be size_t to avoid implicit type conversion. */ -static inline __must_check size_t __ab_c_size(size_t a, size_t b, size_t c) +static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) { size_t bytes; - if (check_mul_overflow(a, b, &bytes)) - return SIZE_MAX; - if (check_add_overflow(bytes, c, &bytes)) + if (minuend == SIZE_MAX || subtrahend == SIZE_MAX || + check_sub_overflow(minuend, subtrahend, &bytes)) return SIZE_MAX; return bytes; } /** - * struct_size() - Calculate size of structure with trailing array. - * @p: Pointer to the structure. - * @member: Name of the array member. - * @count: Number of elements in the array. + * array_size() - Calculate size of 2-dimensional array. * - * Calculates size of memory needed for structure @p followed by an - * array of @count number of @member elements. + * @a: dimension one + * @b: dimension two * - * Return: number of bytes needed or SIZE_MAX on overflow. + * Calculates size of 2-dimensional array: @a * @b. + * + * Returns: number of bytes needed to represent the array or SIZE_MAX on + * overflow. */ -#define struct_size(p, member, count) \ - __ab_c_size(count, \ - sizeof(*(p)->member) + __must_be_array((p)->member),\ - sizeof(*(p))) +#define array_size(a, b) size_mul(a, b) + +/** + * array3_size() - Calculate size of 3-dimensional array. + * + * @a: dimension one + * @b: dimension two + * @c: dimension three + * + * Calculates size of 3-dimensional array: @a * @b * @c. + * + * Returns: number of bytes needed to represent the array or SIZE_MAX on + * overflow. + */ +#define array3_size(a, b, c) size_mul(size_mul(a, b), c) /** * flex_array_size() - Calculate size of a flexible array member @@ -208,7 +221,22 @@ static inline __must_check size_t __ab_c_size(size_t a, size_t b, size_t c) * Return: number of bytes needed or SIZE_MAX on overflow. */ #define flex_array_size(p, member, count) \ - array_size(count, \ - sizeof(*(p)->member) + __must_be_array((p)->member)) + size_mul(count, \ + sizeof(*(p)->member) + __must_be_array((p)->member)) + +/** + * struct_size() - Calculate size of structure with trailing flexible array. + * + * @p: Pointer to the structure. + * @member: Name of the array member. + * @count: Number of elements in the array. + * + * Calculates size of memory needed for structure @p followed by an + * array of @count number of @member elements. + * + * Return: number of bytes needed or SIZE_MAX on overflow. + */ +#define struct_size(p, member, count) \ + size_add(sizeof(*(p)), flex_array_size(p, member, count)) #endif /* __LINUX_OVERFLOW_H */ -- cgit v1.2.3 From 79aa0367385ceaf5351ea77ea1fb66136739ea9d Mon Sep 17 00:00:00 2001 From: Felix Kuehling Date: Tue, 15 Feb 2022 18:54:38 -0500 Subject: drm/amdkfd: Replace zero-length array with flexible-array member MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reference: https://www.kernel.org/doc/html/latest/process/deprecated.html#zero-length-and-one-element-arrays CC: Changcheng Deng Signed-off-by: Felix Kuehling Reviewed-by: Philip Yang Reviewed-by: Christian König Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 6e4268f5e482..baec5a41de3e 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -673,7 +673,7 @@ struct kfd_ioctl_svm_args { __u32 op; __u32 nattr; /* Variable length array of attributes */ - struct kfd_ioctl_svm_attribute attrs[0]; + struct kfd_ioctl_svm_attribute attrs[]; }; /** -- cgit v1.2.3 From a65dbf7cded724a5ed4a5e1a718616b048ca0c34 Mon Sep 17 00:00:00 2001 From: Prike Liang Date: Thu, 23 Dec 2021 09:35:37 +0800 Subject: drm/amdgpu/gfx10: Add GC 10.3.7 Support Needed to properly initialize GC 10.3.7. Signed-off-by: Prike Liang Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 76b580d10a52..55fa660e35f4 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -1151,6 +1151,7 @@ struct drm_amdgpu_info_video_caps { #define AMDGPU_FAMILY_NV 143 /* Navi10 */ #define AMDGPU_FAMILY_VGH 144 /* Van Gogh */ #define AMDGPU_FAMILY_YC 146 /* Yellow Carp */ +#define AMDGPU_FAMILY_GC_10_3_7 151 /* GC 10.3.7 */ #if defined(__cplusplus) } -- cgit v1.2.3 From 230f6fa2c1db6a3f3e668cfe95995ac8e6eee212 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 9 Feb 2022 16:40:41 -0800 Subject: overflow: Provide constant expression struct_size There have been cases where struct_size() (or flex_array_size()) needs to be calculated for an initializer, which requires it be a constant expression. This is possible when the "count" argument is a constant expression, so provide this ability for the helpers. Cc: Gustavo A. R. Silva Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Rasmus Villemoes Signed-off-by: Kees Cook Reviewed-by: Gustavo A. R. Silva Tested-by: Gustavo A. R. Silva Link: https://lore.kernel.org/lkml/20220210010407.GA701603@embeddedor --- include/linux/overflow.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/overflow.h b/include/linux/overflow.h index 59d7228104d0..f1221d11f8e5 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -4,6 +4,7 @@ #include #include +#include /* * We need to compute the minimum and maximum values representable in a given @@ -221,8 +222,9 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) * Return: number of bytes needed or SIZE_MAX on overflow. */ #define flex_array_size(p, member, count) \ - size_mul(count, \ - sizeof(*(p)->member) + __must_be_array((p)->member)) + __builtin_choose_expr(__is_constexpr(count), \ + (count) * sizeof(*(p)->member) + __must_be_array((p)->member), \ + size_mul(count, sizeof(*(p)->member) + __must_be_array((p)->member))) /** * struct_size() - Calculate size of structure with trailing flexible array. @@ -237,6 +239,8 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) * Return: number of bytes needed or SIZE_MAX on overflow. */ #define struct_size(p, member, count) \ - size_add(sizeof(*(p)), flex_array_size(p, member, count)) + __builtin_choose_expr(__is_constexpr(count), \ + sizeof(*(p)) + flex_array_size(p, member, count), \ + size_add(sizeof(*(p)), flex_array_size(p, member, count))) #endif /* __LINUX_OVERFLOW_H */ -- cgit v1.2.3 From 28db4711bf48303814dcfd8d41a41106e90bc374 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 15 Feb 2022 11:05:38 +0100 Subject: blk-mq: remove the request_queue argument to blk_insert_cloned_request The request must be submitted to the queue it was allocated for, so remove the extra request_queue argument. Signed-off-by: Christoph Hellwig Reviewed-by: Mike Snitzer Link: https://lore.kernel.org/r/20220215100540.3892965-4-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index d319ffa59354..3a41d50b85d3 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -952,8 +952,7 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio *, void *), void *data); void blk_rq_unprep_clone(struct request *rq); -blk_status_t blk_insert_cloned_request(struct request_queue *q, - struct request *rq); +blk_status_t blk_insert_cloned_request(struct request *rq); struct rq_map_data { struct page **pages; -- cgit v1.2.3 From 76792055c4c8b2472ca1ae48e0ddaf8497529f08 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 15 Feb 2022 10:45:10 +0100 Subject: block: add a ->free_disk method Add a method to notify the driver that the gendisk is about to be freed. This allows drivers to tie the lifetime of their private data to that of the gendisk and thus deal with device removal races without expensive synchronization and boilerplate code. A new flag is added so that ->free_disk is only called after a successful call to add_disk, which significantly simplifies the error handling path during probing. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220215094514.3828912-2-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 3bfc75a2a450..f757f9c2871f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -146,6 +146,7 @@ struct gendisk { #define GD_READ_ONLY 1 #define GD_DEAD 2 #define GD_NATIVE_CAPACITY 3 +#define GD_ADDED 4 struct mutex open_mutex; /* open/close mutex */ unsigned open_partitions; /* number of open partitions */ @@ -1464,6 +1465,7 @@ struct block_device_operations { void (*unlock_native_capacity) (struct gendisk *); int (*getgeo)(struct block_device *, struct hd_geometry *); int (*set_read_only)(struct block_device *bdev, bool ro); + void (*free_disk)(struct gendisk *disk); /* this callback is with swap_lock and sometimes page table lock held */ void (*swap_slot_free_notify) (struct block_device *, unsigned long); int (*report_zones)(struct gendisk *, sector_t sector, -- cgit v1.2.3 From f8e9ce4a6e85067d7d7cfa89167f5ce5f0ec2a8a Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Tue, 15 Feb 2022 18:11:24 -0800 Subject: mptcp: mptcp_parse_option is no longer exported Options parsing in now done from mptcp_incoming_options(). mptcp_parse_option() has been removed from mptcp.h when CONFIG_MPTCP is defined but not when it is not. Fixes: cfde141ea3fa ("mptcp: move option parsing into mptcp_incoming_options()") Acked-by: Paolo Abeni Signed-off-by: Matthieu Baerts Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- include/net/mptcp.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/net/mptcp.h b/include/net/mptcp.h index a925349b4b89..0a3b0fb04a3b 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -217,12 +217,6 @@ static inline bool rsk_drop_req(const struct request_sock *req) return false; } -static inline void mptcp_parse_option(const struct sk_buff *skb, - const unsigned char *ptr, int opsize, - struct tcp_options_received *opt_rx) -{ -} - static inline bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, unsigned int *size, struct mptcp_out_options *opts) -- cgit v1.2.3 From 72113d0a7d90d950c7c9a87ab905bffb6bc5752d Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 10 Feb 2022 11:11:24 +0900 Subject: signal.h: add linux/signal.h and asm/signal.h to UAPI compile-test coverage MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit linux/signal.h and asm/signal.h are currently excluded from the UAPI compile-test because of the errors like follows: HDRTEST usr/include/asm/signal.h In file included from : ./usr/include/asm/signal.h:103:9: error: unknown type name ‘size_t’ 103 | size_t ss_size; | ^~~~~~ The errors can be fixed by replacing size_t with __kernel_size_t. Then, remove the no-header-test entries from user/include/Makefile. Signed-off-by: Masahiro Yamada Reviewed-by: Arnd Bergmann Reviewed-by: Geert Uytterhoeven Acked-by: Geert Uytterhoeven Signed-off-by: Arnd Bergmann --- include/uapi/asm-generic/signal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/asm-generic/signal.h b/include/uapi/asm-generic/signal.h index f634822906e4..0eb69dc8e572 100644 --- a/include/uapi/asm-generic/signal.h +++ b/include/uapi/asm-generic/signal.h @@ -85,7 +85,7 @@ struct sigaction { typedef struct sigaltstack { void __user *ss_sp; int ss_flags; - size_t ss_size; + __kernel_size_t ss_size; } stack_t; #endif /* __ASSEMBLY__ */ -- cgit v1.2.3 From 4a3233c1a69885aa7e71c48ff39ae11c212ac90a Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 10 Feb 2022 11:11:25 +0900 Subject: shmbuf.h: add asm/shmbuf.h to UAPI compile-test coverage MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit asm/shmbuf.h is currently excluded from the UAPI compile-test because of the errors like follows: HDRTEST usr/include/asm/shmbuf.h In file included from ./usr/include/asm/shmbuf.h:6, from : ./usr/include/asm-generic/shmbuf.h:26:33: error: field ‘shm_perm’ has incomplete type 26 | struct ipc64_perm shm_perm; /* operation perms */ | ^~~~~~~~ ./usr/include/asm-generic/shmbuf.h:27:9: error: unknown type name ‘size_t’ 27 | size_t shm_segsz; /* size of segment (bytes) */ | ^~~~~~ ./usr/include/asm-generic/shmbuf.h:40:9: error: unknown type name ‘__kernel_pid_t’ 40 | __kernel_pid_t shm_cpid; /* pid of creator */ | ^~~~~~~~~~~~~~ ./usr/include/asm-generic/shmbuf.h:41:9: error: unknown type name ‘__kernel_pid_t’ 41 | __kernel_pid_t shm_lpid; /* pid of last operator */ | ^~~~~~~~~~~~~~ The errors can be fixed by replacing size_t with __kernel_size_t and by including proper headers. Then, remove the no-header-test entry from user/include/Makefile. Signed-off-by: Masahiro Yamada Reviewed-by: Arnd Bergmann Signed-off-by: Arnd Bergmann --- include/uapi/asm-generic/shmbuf.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/asm-generic/shmbuf.h b/include/uapi/asm-generic/shmbuf.h index 2bab955e0fed..2979b6dd2c56 100644 --- a/include/uapi/asm-generic/shmbuf.h +++ b/include/uapi/asm-generic/shmbuf.h @@ -3,6 +3,8 @@ #define __ASM_GENERIC_SHMBUF_H #include +#include +#include /* * The shmid64_ds structure for x86 architecture. @@ -24,7 +26,7 @@ struct shmid64_ds { struct ipc64_perm shm_perm; /* operation perms */ - size_t shm_segsz; /* size of segment (bytes) */ + __kernel_size_t shm_segsz; /* size of segment (bytes) */ #if __BITS_PER_LONG == 64 long shm_atime; /* last attach time */ long shm_dtime; /* last detach time */ -- cgit v1.2.3 From 169adc2b6b3c5e86391921117b4ab3aaeb3c6ee1 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 10 Feb 2022 11:11:26 +0900 Subject: android/binder.h: add linux/android/binder(fs).h to UAPI compile-test coverage MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit linux/android/binder.h and linux/android/binderfs.h are currently excluded from the UAPI compile-test because of the errors like follows: HDRTEST usr/include/linux/android/binder.h In file included from : ./usr/include/linux/android/binder.h:291:9: error: unknown type name ‘pid_t’ 291 | pid_t sender_pid; | ^~~~~ ./usr/include/linux/android/binder.h:292:9: error: unknown type name ‘uid_t’ 292 | uid_t sender_euid; | ^~~~~ The errors can be fixed by replacing {pid,uid}_t with __kernel_{pid,uid}_t. Then, remove the no-header-test entries from user/include/Makefile. Signed-off-by: Masahiro Yamada Reviewed-by: Arnd Bergmann Signed-off-by: Arnd Bergmann --- include/uapi/linux/android/binder.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index 3246f2c74696..11157fae8a8e 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -288,8 +288,8 @@ struct binder_transaction_data { /* General information about the transaction. */ __u32 flags; - pid_t sender_pid; - uid_t sender_euid; + __kernel_pid_t sender_pid; + __kernel_uid_t sender_euid; binder_size_t data_size; /* number of bytes of data */ binder_size_t offsets_size; /* number of bytes of offsets */ -- cgit v1.2.3 From cbf2820341297b9aed0f846aba35556e94569210 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 10 Feb 2022 11:11:27 +0900 Subject: fsmap.h: add linux/fsmap.h to UAPI compile-test coverage MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit linux/fsmap.h is currently excluded from the UAPI compile-test because of the error like follows: HDRTEST usr/include/linux/fsmap.h In file included from : ./usr/include/linux/fsmap.h:72:19: error: unknown type name ‘size_t’ 72 | static __inline__ size_t | ^~~~~~ The error can be fixed by replacing size_t with __kernel_size_t. Then, remove the no-header-test entry from user/include/Makefile. Signed-off-by: Masahiro Yamada Reviewed-by: Arnd Bergmann Signed-off-by: Arnd Bergmann --- include/uapi/linux/fsmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/fsmap.h b/include/uapi/linux/fsmap.h index 91fd519a3f7d..c690d17f1d07 100644 --- a/include/uapi/linux/fsmap.h +++ b/include/uapi/linux/fsmap.h @@ -69,7 +69,7 @@ struct fsmap_head { }; /* Size of an fsmap_head with room for nr records. */ -static inline size_t +static inline __kernel_size_t fsmap_sizeof( unsigned int nr) { -- cgit v1.2.3 From 8b4bca21c2c0cb3b5adb80985830a81d4e5d7081 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 10 Feb 2022 11:11:28 +0900 Subject: kexec.h: add linux/kexec.h to UAPI compile-test coverage MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit linux/kexec.h is currently excluded from the UAPI compile-test because of the errors like follows: HDRTEST usr/include/linux/kexec.h In file included from : ./usr/include/linux/kexec.h:56:9: error: unknown type name ‘size_t’ 56 | size_t bufsz; | ^~~~~~ ./usr/include/linux/kexec.h:58:9: error: unknown type name ‘size_t’ 58 | size_t memsz; | ^~~~~~ The errors can be fixed by replacing size_t with __kernel_size_t. Then, remove the no-header-test entry from user/include/Makefile. Signed-off-by: Masahiro Yamada Reviewed-by: Arnd Bergmann Signed-off-by: Arnd Bergmann --- include/uapi/linux/kexec.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h index 778dc191c265..fb7e2ef60825 100644 --- a/include/uapi/linux/kexec.h +++ b/include/uapi/linux/kexec.h @@ -54,9 +54,9 @@ */ struct kexec_segment { const void *buf; - size_t bufsz; + __kernel_size_t bufsz; const void *mem; - size_t memsz; + __kernel_size_t memsz; }; #endif /* __KERNEL__ */ -- cgit v1.2.3 From 2a5c0fdc70cd653741e910e92ffeb2fa7376db07 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 10 Feb 2022 11:11:29 +0900 Subject: reiserfs_xattr.h: add linux/reiserfs_xattr.h to UAPI compile-test coverage MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit linux/reiserfs_xattr.h is currently excluded from the UAPI compile-test because of the error like follows: HDRTEST usr/include/linux/reiserfs_xattr.h In file included from : ./usr/include/linux/reiserfs_xattr.h:22:9: error: unknown type name ‘size_t’ 22 | size_t length; | ^~~~~~ The error can be fixed by replacing size_t with __kernel_size_t. Then, remove the no-header-test entry from user/include/Makefile. Signed-off-by: Masahiro Yamada Reviewed-by: Arnd Bergmann Signed-off-by: Arnd Bergmann --- include/uapi/linux/reiserfs_xattr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/reiserfs_xattr.h b/include/uapi/linux/reiserfs_xattr.h index 28f10842f047..503ad018ce5b 100644 --- a/include/uapi/linux/reiserfs_xattr.h +++ b/include/uapi/linux/reiserfs_xattr.h @@ -19,7 +19,7 @@ struct reiserfs_xattr_header { struct reiserfs_security_handle { const char *name; void *value; - size_t length; + __kernel_size_t length; }; #endif /* _LINUX_REISERFS_XATTR_H */ -- cgit v1.2.3 From 6a7bdd89f50d399dd02847e6f398d408b086df50 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Mon, 3 Jan 2022 17:24:11 +0100 Subject: media: v4l2-mediabus: Use structures to describe bus configuration The media bus configuration is specified through a set of flags, some of which being mutually exclusive. This doesn't scale to express more complex configurations. Improve the API by replacing the single flags field in v4l2_mbus_config by a union of v4l2_mbus_config_* structures. The flags themselves are still used in those structures, so they are kept here. Drivers are however updated to use structure fields instead of flags when already possible. Signed-off-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-mediabus.h | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-mediabus.h b/include/media/v4l2-mediabus.h index 9c4970fbd8ea..269aaf57ba32 100644 --- a/include/media/v4l2-mediabus.h +++ b/include/media/v4l2-mediabus.h @@ -166,12 +166,26 @@ enum v4l2_mbus_type { /** * struct v4l2_mbus_config - media bus configuration - * @type: in: interface type - * @flags: in / out: configuration flags, depending on @type + * @type: interface type + * @bus: bus configuration data structure + * @bus.parallel: embedded &struct v4l2_mbus_config_parallel. + * Used if the bus is parallel or BT.656. + * @bus.mipi_csi1: embedded &struct v4l2_mbus_config_mipi_csi1. + * Used if the bus is MIPI Alliance's Camera Serial + * Interface version 1 (MIPI CSI1) or Standard + * Mobile Imaging Architecture's Compact Camera Port 2 + * (SMIA CCP2). + * @bus.mipi_csi2: embedded &struct v4l2_mbus_config_mipi_csi2. + * Used if the bus is MIPI Alliance's Camera Serial + * Interface version 2 (MIPI CSI2). */ struct v4l2_mbus_config { enum v4l2_mbus_type type; - unsigned int flags; + union { + struct v4l2_mbus_config_parallel parallel; + struct v4l2_mbus_config_mipi_csi1 mipi_csi1; + struct v4l2_mbus_config_mipi_csi2 mipi_csi2; + } bus; }; /** -- cgit v1.2.3 From 20c238dfb26c23dc493e5fcfeea682af8b33375a Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Mon, 3 Jan 2022 17:24:12 +0100 Subject: media: v4l2-mediabus: Drop legacy V4L2_MBUS_CSI2_*_LANE flags The V4L2_MBUS_CSI2_*_LANE flags are a legacy API and are unused. Drop them. Signed-off-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-mediabus.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-mediabus.h b/include/media/v4l2-mediabus.h index 269aaf57ba32..44195ceeccca 100644 --- a/include/media/v4l2-mediabus.h +++ b/include/media/v4l2-mediabus.h @@ -21,8 +21,6 @@ * clear both the V4L2_MBUS_HSYNC_ACTIVE_HIGH and the * V4L2_MBUS_HSYNC_ACTIVE_LOW flag at the same time. Instead either flag * V4L2_MBUS_HSYNC_ACTIVE_HIGH or flag V4L2_MBUS_HSYNC_ACTIVE_LOW shall be set. - * The same is true for the V4L2_MBUS_CSI2_1/2/3/4_LANE flags group: only one - * of these four bits shall be set. * * TODO: replace the existing V4L2_MBUS_* flags with structures of fields * to avoid conflicting settings. @@ -69,11 +67,6 @@ #define V4L2_MBUS_DATA_ENABLE_LOW BIT(15) /* Serial flags */ -/* CSI-2 D-PHY number of data lanes. */ -#define V4L2_MBUS_CSI2_1_LANE BIT(0) -#define V4L2_MBUS_CSI2_2_LANE BIT(1) -#define V4L2_MBUS_CSI2_3_LANE BIT(2) -#define V4L2_MBUS_CSI2_4_LANE BIT(3) /* CSI-2 Virtual Channel identifiers. */ #define V4L2_MBUS_CSI2_CHANNEL_0 BIT(4) #define V4L2_MBUS_CSI2_CHANNEL_1 BIT(5) @@ -83,10 +76,6 @@ #define V4L2_MBUS_CSI2_CONTINUOUS_CLOCK BIT(8) #define V4L2_MBUS_CSI2_NONCONTINUOUS_CLOCK BIT(9) -#define V4L2_MBUS_CSI2_LANES (V4L2_MBUS_CSI2_1_LANE | \ - V4L2_MBUS_CSI2_2_LANE | \ - V4L2_MBUS_CSI2_3_LANE | \ - V4L2_MBUS_CSI2_4_LANE) #define V4L2_MBUS_CSI2_CHANNELS (V4L2_MBUS_CSI2_CHANNEL_0 | \ V4L2_MBUS_CSI2_CHANNEL_1 | \ V4L2_MBUS_CSI2_CHANNEL_2 | \ -- cgit v1.2.3 From 5a6ac3f4b46fd86d13e1d8ab4a55e4d89f3ab400 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Mon, 3 Jan 2022 17:24:13 +0100 Subject: media: v4l2-mediabus: Drop legacy V4L2_MBUS_CSI2_CHANNEL_* flags The V4L2_MBUS_CSI2_CHANNEL_* flags are a legacy API. Only V4L2_MBUS_CSI2_CHANNEL_0 is used, set in a single driver, and never read. Drop those flags. Virtual channel information should be conveyed through frame descriptors instead. Signed-off-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-mediabus.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-mediabus.h b/include/media/v4l2-mediabus.h index 44195ceeccca..c6626a22b394 100644 --- a/include/media/v4l2-mediabus.h +++ b/include/media/v4l2-mediabus.h @@ -67,20 +67,10 @@ #define V4L2_MBUS_DATA_ENABLE_LOW BIT(15) /* Serial flags */ -/* CSI-2 Virtual Channel identifiers. */ -#define V4L2_MBUS_CSI2_CHANNEL_0 BIT(4) -#define V4L2_MBUS_CSI2_CHANNEL_1 BIT(5) -#define V4L2_MBUS_CSI2_CHANNEL_2 BIT(6) -#define V4L2_MBUS_CSI2_CHANNEL_3 BIT(7) /* Clock non-continuous mode support. */ #define V4L2_MBUS_CSI2_CONTINUOUS_CLOCK BIT(8) #define V4L2_MBUS_CSI2_NONCONTINUOUS_CLOCK BIT(9) -#define V4L2_MBUS_CSI2_CHANNELS (V4L2_MBUS_CSI2_CHANNEL_0 | \ - V4L2_MBUS_CSI2_CHANNEL_1 | \ - V4L2_MBUS_CSI2_CHANNEL_2 | \ - V4L2_MBUS_CSI2_CHANNEL_3) - #define V4L2_MBUS_CSI2_MAX_DATA_LANES 8 /** -- cgit v1.2.3 From b9f7caa7753ad185e0dc7afb3ae4bd423d11f5c0 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Wed, 5 Jan 2022 21:15:58 +0100 Subject: media: v4l2-mediabus: Drop V4L2_MBUS_CSI2_CONTINUOUS_CLOCK flag MIPI CSI-2 continuous and non-continuous clock modes are mutually exclusive. Drop the V4L2_MBUS_CSI2_CONTINUOUS_CLOCK flag and use V4L2_MBUS_CSI2_NONCONTINUOUS_CLOCK only. Signed-off-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-mediabus.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-mediabus.h b/include/media/v4l2-mediabus.h index c6626a22b394..e0db3bcff9ed 100644 --- a/include/media/v4l2-mediabus.h +++ b/include/media/v4l2-mediabus.h @@ -68,8 +68,7 @@ /* Serial flags */ /* Clock non-continuous mode support. */ -#define V4L2_MBUS_CSI2_CONTINUOUS_CLOCK BIT(8) -#define V4L2_MBUS_CSI2_NONCONTINUOUS_CLOCK BIT(9) +#define V4L2_MBUS_CSI2_NONCONTINUOUS_CLOCK BIT(0) #define V4L2_MBUS_CSI2_MAX_DATA_LANES 8 -- cgit v1.2.3 From d4568fc8525897e683983806f813be1ae9eedaed Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 24 Jan 2022 18:29:52 +0100 Subject: media: omap3isp: Use struct_group() for memcpy() region In preparation for FORTIFY_SOURCE performing compile-time and run-time field bounds checking for memcpy(), memmove(), and memset(), avoid intentionally writing across neighboring fields. Wrap the target region in struct_group(). This additionally fixes a theoretical misalignment of the copy (since the size of "buf" changes between 64-bit and 32-bit, but this is likely never built for 64-bit). FWIW, I think this code is totally broken on 64-bit (which appears to not be a "real" build configuration): it would either always fail (with an uninitialized data->buf_size) or would cause corruption in userspace due to the copy_to_user() in the call path against an uninitialized data->buf value: omap3isp_stat_request_statistics_time32(...) struct omap3isp_stat_data data64; ... omap3isp_stat_request_statistics(stat, &data64); int omap3isp_stat_request_statistics(struct ispstat *stat, struct omap3isp_stat_data *data) ... buf = isp_stat_buf_get(stat, data); static struct ispstat_buffer *isp_stat_buf_get(struct ispstat *stat, struct omap3isp_stat_data *data) ... if (buf->buf_size > data->buf_size) { ... return ERR_PTR(-EINVAL); } ... rval = copy_to_user(data->buf, buf->virt_addr, buf->buf_size); Regardless, additionally initialize data64 to be zero-filled to avoid undefined behavior. Link: https://lore.kernel.org/lkml/20211215220505.GB21862@embeddedor Cc: Arnd Bergmann Fixes: 378e3f81cb56 ("media: omap3isp: support 64-bit version of omap3isp_stat_data") Cc: stable@vger.kernel.org Reviewed-by: Gustavo A. R. Silva Signed-off-by: Kees Cook Reviewed-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/omap3isp.h | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/omap3isp.h b/include/uapi/linux/omap3isp.h index 87b55755f4ff..d9db7ad43890 100644 --- a/include/uapi/linux/omap3isp.h +++ b/include/uapi/linux/omap3isp.h @@ -162,6 +162,7 @@ struct omap3isp_h3a_aewb_config { * struct omap3isp_stat_data - Statistic data sent to or received from user * @ts: Timestamp of returned framestats. * @buf: Pointer to pass to user. + * @buf_size: Size of buffer. * @frame_number: Frame number of requested stats. * @cur_frame: Current frame number being processed. * @config_counter: Number of the configuration associated with the data. @@ -176,10 +177,12 @@ struct omap3isp_stat_data { struct timeval ts; #endif void __user *buf; - __u32 buf_size; - __u16 frame_number; - __u16 cur_frame; - __u16 config_counter; + __struct_group(/* no tag */, frame, /* no attrs */, + __u32 buf_size; + __u16 frame_number; + __u16 cur_frame; + __u16 config_counter; + ); }; #ifdef __KERNEL__ @@ -189,10 +192,12 @@ struct omap3isp_stat_data_time32 { __s32 tv_usec; } ts; __u32 buf; - __u32 buf_size; - __u16 frame_number; - __u16 cur_frame; - __u16 config_counter; + __struct_group(/* no tag */, frame, /* no attrs */, + __u32 buf_size; + __u16 frame_number; + __u16 cur_frame; + __u16 config_counter; + ); }; #endif -- cgit v1.2.3 From 5cadbd897221431ea7f2c50510ed63042de9285f Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Sun, 23 Jan 2022 16:36:19 +0100 Subject: media: Define MIPI CSI-2 data types in a shared header file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are many CSI-2-related drivers in the media subsystem that come with their own macros to handle the CSI-2 data types (or just hardcode the numerical values). Provide a shared header with definitions for those data types that driver can use. Signed-off-by: Laurent Pinchart Reviewed-by: Niklas Söderlund Reviewed-by: Kieran Bingham Signed-off-by: Mauro Carvalho Chehab --- include/media/mipi-csi2.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) create mode 100644 include/media/mipi-csi2.h (limited to 'include') diff --git a/include/media/mipi-csi2.h b/include/media/mipi-csi2.h new file mode 100644 index 000000000000..392794e5badd --- /dev/null +++ b/include/media/mipi-csi2.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * MIPI CSI-2 Data Types + * + * Copyright (C) 2022 Laurent Pinchart + */ + +#ifndef _MEDIA_MIPI_CSI2_H +#define _MEDIA_MIPI_CSI2_H + +/* Short packet data types */ +#define MIPI_CSI2_DT_FS 0x00 +#define MIPI_CSI2_DT_FE 0x01 +#define MIPI_CSI2_DT_LS 0x02 +#define MIPI_CSI2_DT_LE 0x03 +#define MIPI_CSI2_DT_GENERIC_SHORT(n) (0x08 + (n)) /* 0..7 */ + +/* Long packet data types */ +#define MIPI_CSI2_DT_NULL 0x10 +#define MIPI_CSI2_DT_BLANKING 0x11 +#define MIPI_CSI2_DT_EMBEDDED_8B 0x12 +#define MIPI_CSI2_DT_YUV420_8B 0x18 +#define MIPI_CSI2_DT_YUV420_10B 0x19 +#define MIPI_CSI2_DT_YUV420_8B_LEGACY 0x1a +#define MIPI_CSI2_DT_YUV420_8B_CS 0x1c +#define MIPI_CSI2_DT_YUV420_10B_CS 0x1d +#define MIPI_CSI2_DT_YUV422_8B 0x1e +#define MIPI_CSI2_DT_YUV422_10B 0x1f +#define MIPI_CSI2_DT_RGB444 0x20 +#define MIPI_CSI2_DT_RGB555 0x21 +#define MIPI_CSI2_DT_RGB565 0x22 +#define MIPI_CSI2_DT_RGB666 0x23 +#define MIPI_CSI2_DT_RGB888 0x24 +#define MIPI_CSI2_DT_RAW24 0x27 +#define MIPI_CSI2_DT_RAW6 0x28 +#define MIPI_CSI2_DT_RAW7 0x29 +#define MIPI_CSI2_DT_RAW8 0x2a +#define MIPI_CSI2_DT_RAW10 0x2b +#define MIPI_CSI2_DT_RAW12 0x2c +#define MIPI_CSI2_DT_RAW14 0x2d +#define MIPI_CSI2_DT_RAW16 0x2e +#define MIPI_CSI2_DT_RAW20 0x2f +#define MIPI_CSI2_DT_USER_DEFINED(n) (0x30 + (n)) /* 0..7 */ + +#endif /* _MEDIA_MIPI_CSI2_H */ -- cgit v1.2.3 From 5224f79096170bf7b92cc8fe42a12f44b91e5f62 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 14 Feb 2022 19:11:44 -0600 Subject: treewide: Replace zero-length arrays with flexible-array members MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. This code was transformed with the help of Coccinelle: (next-20220214$ spatch --jobs $(getconf _NPROCESSORS_ONLN) --sp-file script.cocci --include-headers --dir . > output.patch) @@ identifier S, member, array; type T1, T2; @@ struct S { ... T1 member; T2 array[ - 0 ]; }; UAPI and wireless changes were intentionally excluded from this patch and will be sent out separately. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://www.kernel.org/doc/html/v5.16/process/deprecated.html#zero-length-and-one-element-arrays Link: https://github.com/KSPP/linux/issues/78 Reviewed-by: Kees Cook Signed-off-by: Gustavo A. R. Silva --- include/asm-generic/tlb.h | 4 ++-- include/linux/greybus/greybus_manifest.h | 4 ++-- include/linux/greybus/hd.h | 2 +- include/linux/greybus/module.h | 2 +- include/linux/i3c/ccc.h | 6 +++--- include/linux/platform_data/brcmfmac.h | 2 +- include/linux/platform_data/cros_ec_commands.h | 2 +- include/net/bluetooth/mgmt.h | 2 +- include/net/ioam6.h | 2 +- include/sound/sof/channel_map.h | 4 ++-- 10 files changed, 15 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 2c68a545ffa7..fd7feb5c7894 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -180,7 +180,7 @@ struct mmu_table_batch { struct rcu_head rcu; #endif unsigned int nr; - void *tables[0]; + void *tables[]; }; #define MAX_TABLE_BATCH \ @@ -227,7 +227,7 @@ struct mmu_gather_batch { struct mmu_gather_batch *next; unsigned int nr; unsigned int max; - struct page *pages[0]; + struct page *pages[]; }; #define MAX_GATHER_BATCH \ diff --git a/include/linux/greybus/greybus_manifest.h b/include/linux/greybus/greybus_manifest.h index 6e62fe478712..bef9eb2093e9 100644 --- a/include/linux/greybus/greybus_manifest.h +++ b/include/linux/greybus/greybus_manifest.h @@ -100,7 +100,7 @@ enum { struct greybus_descriptor_string { __u8 length; __u8 id; - __u8 string[0]; + __u8 string[]; } __packed; /* @@ -175,7 +175,7 @@ struct greybus_manifest_header { struct greybus_manifest { struct greybus_manifest_header header; - struct greybus_descriptor descriptors[0]; + struct greybus_descriptor descriptors[]; } __packed; #endif /* __GREYBUS_MANIFEST_H */ diff --git a/include/linux/greybus/hd.h b/include/linux/greybus/hd.h index d3faf0c1a569..718e2857054e 100644 --- a/include/linux/greybus/hd.h +++ b/include/linux/greybus/hd.h @@ -58,7 +58,7 @@ struct gb_host_device { struct gb_svc *svc; /* Private data for the host driver */ - unsigned long hd_priv[0] __aligned(sizeof(s64)); + unsigned long hd_priv[] __aligned(sizeof(s64)); }; #define to_gb_host_device(d) container_of(d, struct gb_host_device, dev) diff --git a/include/linux/greybus/module.h b/include/linux/greybus/module.h index 47b839af145d..3efe2133acfd 100644 --- a/include/linux/greybus/module.h +++ b/include/linux/greybus/module.h @@ -23,7 +23,7 @@ struct gb_module { bool disconnected; - struct gb_interface *interfaces[0]; + struct gb_interface *interfaces[]; }; #define to_gb_module(d) container_of(d, struct gb_module, dev) diff --git a/include/linux/i3c/ccc.h b/include/linux/i3c/ccc.h index 73b0982cc519..ad59a4ae60d1 100644 --- a/include/linux/i3c/ccc.h +++ b/include/linux/i3c/ccc.h @@ -132,7 +132,7 @@ struct i3c_ccc_dev_desc { struct i3c_ccc_defslvs { u8 count; struct i3c_ccc_dev_desc master; - struct i3c_ccc_dev_desc slaves[0]; + struct i3c_ccc_dev_desc slaves[]; } __packed; /** @@ -240,7 +240,7 @@ struct i3c_ccc_bridged_slave_desc { */ struct i3c_ccc_setbrgtgt { u8 count; - struct i3c_ccc_bridged_slave_desc bslaves[0]; + struct i3c_ccc_bridged_slave_desc bslaves[]; } __packed; /** @@ -318,7 +318,7 @@ enum i3c_ccc_setxtime_subcmd { */ struct i3c_ccc_setxtime { u8 subcmd; - u8 data[0]; + u8 data[]; } __packed; #define I3C_CCC_GETXTIME_SYNC_MODE BIT(0) diff --git a/include/linux/platform_data/brcmfmac.h b/include/linux/platform_data/brcmfmac.h index 2b5676ff35be..f922a192fe58 100644 --- a/include/linux/platform_data/brcmfmac.h +++ b/include/linux/platform_data/brcmfmac.h @@ -178,7 +178,7 @@ struct brcmfmac_platform_data { void (*power_off)(void); char *fw_alternative_path; int device_count; - struct brcmfmac_pd_device devices[0]; + struct brcmfmac_pd_device devices[]; }; diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 271bd87bff0a..728735aed980 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -5644,7 +5644,7 @@ struct ec_response_typec_discovery { uint8_t svid_count; /* Number of SVIDs partner sent */ uint16_t reserved; uint32_t discovery_vdo[6]; /* Max VDOs allowed after VDM header is 6 */ - struct svid_mode_info svids[0]; + struct svid_mode_info svids[]; } __ec_align1; /* USB Type-C commands for AP-controlled device policy. */ diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 107b25deae68..9607ec289fd0 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -696,7 +696,7 @@ struct mgmt_cp_set_blocked_keys { #define MGMT_READ_CONTROLLER_CAP_SIZE 0 struct mgmt_rp_read_controller_cap { __le16 cap_len; - __u8 cap[0]; + __u8 cap[]; } __packed; #define MGMT_OP_READ_EXP_FEATURES_INFO 0x0049 diff --git a/include/net/ioam6.h b/include/net/ioam6.h index 3f45ba37a2c6..781d2d8b2f29 100644 --- a/include/net/ioam6.h +++ b/include/net/ioam6.h @@ -35,7 +35,7 @@ struct ioam6_schema { int len; __be32 hdr; - u8 data[0]; + u8 data[]; }; struct ioam6_pernet_data { diff --git a/include/sound/sof/channel_map.h b/include/sound/sof/channel_map.h index fd3a30fcf756..d363f0ca6979 100644 --- a/include/sound/sof/channel_map.h +++ b/include/sound/sof/channel_map.h @@ -39,7 +39,7 @@ struct sof_ipc_channel_map { uint32_t ext_id; uint32_t ch_mask; uint32_t reserved; - int32_t ch_coeffs[0]; + int32_t ch_coeffs[]; } __packed; /** @@ -55,7 +55,7 @@ struct sof_ipc_stream_map { struct sof_ipc_cmd_hdr hdr; uint32_t num_ch_map; uint32_t reserved[3]; - struct sof_ipc_channel_map ch_map[0]; + struct sof_ipc_channel_map ch_map[]; } __packed; #endif /* __IPC_CHANNEL_MAP_H__ */ -- cgit v1.2.3 From c518afec288351347dbe05ea3d49d18fb9a9fff1 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 16 Feb 2022 16:30:05 +0200 Subject: net: mscc: ocelot: consolidate cookie allocation for private VCAP rules Every use case that needed VCAP filters (in order: DSA tag_8021q, MRP, PTP traps) has hardcoded filter identifiers that worked well enough for that use case alone. But when two or more of those use cases would be used together, some of those identifiers would overlap, leading to breakage. Add definitions for each cookie and centralize them in ocelot_vcap.h, such that the overlaps are more obvious. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot_vcap.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index 709cbc198fd2..562bcd972132 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -8,6 +8,22 @@ #include +/* Cookie definitions for private VCAP filters installed by the driver. + * Must be unique per VCAP block. + */ +#define OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN(ocelot, port) (port) +#define OCELOT_VCAP_IS1_TAG_8021Q_TXVLAN(ocelot, port) (port) +#define OCELOT_VCAP_IS1_TAG_8021Q_PTP_MMIO(ocelot) ((ocelot)->num_phys_ports) +#define OCELOT_VCAP_IS2_TAG_8021Q_TXVLAN(ocelot, port) (port) +#define OCELOT_VCAP_IS2_TAG_8021Q_PTP_MMIO(ocelot) ((ocelot)->num_phys_ports) +#define OCELOT_VCAP_IS2_L2_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports + 1) +#define OCELOT_VCAP_IS2_IPV4_GEN_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports + 2) +#define OCELOT_VCAP_IS2_IPV4_EV_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports + 3) +#define OCELOT_VCAP_IS2_IPV6_GEN_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports + 4) +#define OCELOT_VCAP_IS2_IPV6_EV_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports + 5) +#define OCELOT_VCAP_IS2_MRP_REDIRECT(ocelot, port) (port) +#define OCELOT_VCAP_IS2_MRP_TRAP(ocelot, port) ((ocelot)->num_phys_ports + (port)) + /* ================================================================= * VCAP Common * ================================================================= -- cgit v1.2.3 From 36fac35b29072e345d5fc485cf7841be265181b1 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 16 Feb 2022 16:30:06 +0200 Subject: net: mscc: ocelot: delete OCELOT_MRP_CPUQ MRP frames are configured to be trapped to the CPU queue 7, and this number is reflected in the extraction header. However, the information isn't used anywhere, so just leave MRP frames to go to CPU queue 0 unless needed otherwise. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index cacb103e4bad..2d7456c0e77d 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -105,8 +105,6 @@ #define REG_RESERVED_ADDR 0xffffffff #define REG_RESERVED(reg) REG(reg, REG_RESERVED_ADDR) -#define OCELOT_MRP_CPUQ 7 - enum ocelot_target { ANA = 1, QS, -- cgit v1.2.3 From b9bace6e534d431871a9d69cbd06d3a798f5086d Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 16 Feb 2022 16:30:07 +0200 Subject: net: mscc: ocelot: use a single VCAP filter for all MRP traps The MRP assist code installs a VCAP IS2 trapping rule for each port, but since the key and the action is the same, just the ingress port mask differs, there isn't any need to do this. We can save some space in the TCAM by using a single filter and adjusting the ingress port mask. Reuse the ocelot_trap_add() and ocelot_trap_del() functions for this purpose. Now that the cookies are no longer per port, we need to change the allocation scheme such that MRP traps use a fixed number. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot_vcap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index 562bcd972132..14ada097db0b 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -21,8 +21,8 @@ #define OCELOT_VCAP_IS2_IPV4_EV_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports + 3) #define OCELOT_VCAP_IS2_IPV6_GEN_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports + 4) #define OCELOT_VCAP_IS2_IPV6_EV_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports + 5) +#define OCELOT_VCAP_IS2_MRP_TRAP(ocelot) ((ocelot)->num_phys_ports + 6) #define OCELOT_VCAP_IS2_MRP_REDIRECT(ocelot, port) (port) -#define OCELOT_VCAP_IS2_MRP_TRAP(ocelot, port) ((ocelot)->num_phys_ports + (port)) /* ================================================================= * VCAP Common -- cgit v1.2.3 From 85ea0daabe5abc6add440f86565b7b9f6aff5535 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 16 Feb 2022 16:30:08 +0200 Subject: net: mscc: ocelot: avoid overlap in VCAP IS2 between PTP and MRP traps OCELOT_VCAP_IS2_TAG_8021Q_TXVLAN overlaps with OCELOT_VCAP_IS2_MRP_REDIRECT. To avoid this, make OCELOT_VCAP_IS2_MRP_REDIRECT take the cookie region from N to 2 * N - 1 (where N is ocelot->num_phys_ports). To avoid any risk that the singleton (not per port) VCAP IS2 filters overlap with per-port VCAP IS2 filters, we must ensure that the number of singleton filters is smaller than the number of physical ports. This is true right now, but may change in the future as switches with less ports get supported, or more singleton filters get added. So to be future-proof, let's move the singleton filters at the end of the range, where they won't overlap with anything to their right. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot_vcap.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index 14ada097db0b..ae0eec7f5dd2 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -15,14 +15,14 @@ #define OCELOT_VCAP_IS1_TAG_8021Q_TXVLAN(ocelot, port) (port) #define OCELOT_VCAP_IS1_TAG_8021Q_PTP_MMIO(ocelot) ((ocelot)->num_phys_ports) #define OCELOT_VCAP_IS2_TAG_8021Q_TXVLAN(ocelot, port) (port) -#define OCELOT_VCAP_IS2_TAG_8021Q_PTP_MMIO(ocelot) ((ocelot)->num_phys_ports) -#define OCELOT_VCAP_IS2_L2_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports + 1) -#define OCELOT_VCAP_IS2_IPV4_GEN_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports + 2) -#define OCELOT_VCAP_IS2_IPV4_EV_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports + 3) -#define OCELOT_VCAP_IS2_IPV6_GEN_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports + 4) -#define OCELOT_VCAP_IS2_IPV6_EV_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports + 5) -#define OCELOT_VCAP_IS2_MRP_TRAP(ocelot) ((ocelot)->num_phys_ports + 6) -#define OCELOT_VCAP_IS2_MRP_REDIRECT(ocelot, port) (port) +#define OCELOT_VCAP_IS2_MRP_REDIRECT(ocelot, port) ((ocelot)->num_phys_ports + (port)) +#define OCELOT_VCAP_IS2_TAG_8021Q_PTP_MMIO(ocelot) ((ocelot)->num_phys_ports * 2) +#define OCELOT_VCAP_IS2_L2_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2 + 1) +#define OCELOT_VCAP_IS2_IPV4_GEN_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2 + 2) +#define OCELOT_VCAP_IS2_IPV4_EV_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2 + 3) +#define OCELOT_VCAP_IS2_IPV6_GEN_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2 + 4) +#define OCELOT_VCAP_IS2_IPV6_EV_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2 + 5) +#define OCELOT_VCAP_IS2_MRP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2 + 6) /* ================================================================= * VCAP Common -- cgit v1.2.3 From e42bd4ed09aaf57949f199ae02d20a7108ccf73b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 16 Feb 2022 16:30:10 +0200 Subject: net: mscc: ocelot: keep traps in a list When using the ocelot-8021q tagging protocol, the CPU port isn't configured as an NPI port, but is a regular port. So a "trap to CPU" operation is actually a "redirect" operation. So DSA needs to set up the trapping action one way or another, depending on the tagging protocol in use. To ease DSA's work of modifying the action, keep all currently installed traps in a list, so that DSA can live-patch them when the tagging protocol changes. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 1 + include/soc/mscc/ocelot_vcap.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 2d7456c0e77d..78f56502bc09 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -689,6 +689,7 @@ struct ocelot { u8 base_mac[ETH_ALEN]; struct list_head vlans; + struct list_head traps; /* Switches like VSC9959 have flooding per traffic class */ int num_flooding_pgids; diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index ae0eec7f5dd2..69b3d880302d 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -682,6 +682,7 @@ struct ocelot_vcap_id { struct ocelot_vcap_filter { struct list_head list; + struct list_head trap_list; enum ocelot_vcap_filter_type type; int block_id; -- cgit v1.2.3 From 9d75b8818537fe64e6eae033765b9dc1b3107c15 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 16 Feb 2022 16:30:11 +0200 Subject: net: mscc: ocelot: annotate which traps need PTP timestamping The ocelot switch library does not need this information, but the felix DSA driver does. As a reminder, the VSC9959 switch in LS1028A doesn't have an IRQ line for packet extraction, so to be notified that a PTP packet needs to be dequeued, it receives that packet also over Ethernet, by setting up a packet trap. The Felix driver needs to install special kinds of traps for packets in need of RX timestamps, such that the packets are replicated both over Ethernet and over the CPU port module. But the Ocelot switch library sets up more than one trap for PTP event messages; it also traps PTP general messages, MRP control messages etc. Those packets don't need PTP timestamps, so there's no reason for the Felix driver to send them to the CPU port module. By knowing which traps need PTP timestamps, the Felix driver can adjust the traps installed using ocelot_trap_add() such that only those will actually get delivered to the CPU port module. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot_vcap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index 69b3d880302d..50af64e2ca3c 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -695,6 +695,7 @@ struct ocelot_vcap_filter { struct ocelot_vcap_action action; struct ocelot_vcap_stats stats; /* For VCAP IS1 and IS2 */ + bool take_ts; unsigned long ingress_port_mask; /* For VCAP ES0 */ struct ocelot_vcap_port ingress_port; -- cgit v1.2.3 From 9934800436552d2a4af4aaca62d779b33d1f6a63 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 16 Feb 2022 16:30:13 +0200 Subject: net: dsa: felix: update destinations of existing traps with ocelot-8021q Historically, the felix DSA driver has installed special traps such that PTP over L2 works with the ocelot-8021q tagging protocol; commit 0a6f17c6ae21 ("net: dsa: tag_ocelot_8021q: add support for PTP timestamping") has the details. Then the ocelot switch library also gained more comprehensive support for PTP traps through commit 96ca08c05838 ("net: mscc: ocelot: set up traps for PTP packets"). Right now, PTP over L2 works using ocelot-8021q via the traps it has set for itself, but nothing else does. Consolidating the two code blocks would make ocelot-8021q gain support for PTP over L4 and tc-flower traps, and at the same time avoid some code and TCAM duplication. The traps are similar in intent, but different in execution, so some explanation is required. The traps set up by felix_setup_mmio_filtering() are VCAP IS1 filters, which have a PAG that chains them to a VCAP IS2 filter, and the IS2 is where the 'trap' action resides. The traps set up by ocelot_trap_add(), on the other hand, have a single filter, in VCAP IS2. The reason for chaining VCAP IS1 and IS2 in Felix was to ensure that the hardcoded traps take precedence and cannot be overridden by the Ocelot switch library. So in principle, the PTP traps needed for ocelot-8021q in the Felix driver can rely on ocelot_trap_add(), but the filters need to be patched to account for a quirk that LS1028A has: the quirk_no_xtr_irq described in commit 0a6f17c6ae21 ("net: dsa: tag_ocelot_8021q: add support for PTP timestamping"). Live-patching is done by iterating through the trap list every time we know it has been updated, and transforming a trap into a redirect + CPU copy if ocelot-8021q is in use. Making the DSA ocelot-8021q tagger work with the Ocelot traps means we can eliminate the dedicated OCELOT_VCAP_IS1_TAG_8021Q_PTP_MMIO and OCELOT_VCAP_IS2_TAG_8021Q_PTP_MMIO cookies. To minimize the patch delta, OCELOT_VCAP_IS2_MRP_TRAP takes the place of OCELOT_VCAP_IS2_TAG_8021Q_PTP_MMIO (the alternative would have been to left-shift all cookie numbers by 1). Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot_vcap.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index 50af64e2ca3c..deb2ad9eb0a5 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -13,16 +13,14 @@ */ #define OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN(ocelot, port) (port) #define OCELOT_VCAP_IS1_TAG_8021Q_TXVLAN(ocelot, port) (port) -#define OCELOT_VCAP_IS1_TAG_8021Q_PTP_MMIO(ocelot) ((ocelot)->num_phys_ports) #define OCELOT_VCAP_IS2_TAG_8021Q_TXVLAN(ocelot, port) (port) #define OCELOT_VCAP_IS2_MRP_REDIRECT(ocelot, port) ((ocelot)->num_phys_ports + (port)) -#define OCELOT_VCAP_IS2_TAG_8021Q_PTP_MMIO(ocelot) ((ocelot)->num_phys_ports * 2) +#define OCELOT_VCAP_IS2_MRP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2) #define OCELOT_VCAP_IS2_L2_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2 + 1) #define OCELOT_VCAP_IS2_IPV4_GEN_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2 + 2) #define OCELOT_VCAP_IS2_IPV4_EV_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2 + 3) #define OCELOT_VCAP_IS2_IPV6_GEN_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2 + 4) #define OCELOT_VCAP_IS2_IPV6_EV_PTP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2 + 5) -#define OCELOT_VCAP_IS2_MRP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2 + 6) /* ================================================================= * VCAP Common -- cgit v1.2.3 From 40efe139ff605d80cc829ddf8c50c71d20399bf8 Mon Sep 17 00:00:00 2001 From: Sameer Pujar Date: Thu, 27 Jan 2022 12:57:32 +0530 Subject: dt-bindings: Add Tegra234 APE support Add clocks, power-domain and memory bindings to support APE subsystem on Tegra234. Signed-off-by: Sameer Pujar Signed-off-by: Thierry Reding --- include/dt-bindings/clock/tegra234-clock.h | 74 +++++++++++++++++++++++++- include/dt-bindings/memory/tegra234-mc.h | 7 +++ include/dt-bindings/power/tegra234-powergate.h | 9 ++++ 3 files changed, 89 insertions(+), 1 deletion(-) create mode 100644 include/dt-bindings/power/tegra234-powergate.h (limited to 'include') diff --git a/include/dt-bindings/clock/tegra234-clock.h b/include/dt-bindings/clock/tegra234-clock.h index 2529e7ec0bf4..5c201a8278ff 100644 --- a/include/dt-bindings/clock/tegra234-clock.h +++ b/include/dt-bindings/clock/tegra234-clock.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (c) 2018-2019, NVIDIA CORPORATION. All rights reserved. */ +/* Copyright (c) 2018-2022, NVIDIA CORPORATION. All rights reserved. */ #ifndef DT_BINDINGS_CLOCK_TEGRA234_CLOCK_H #define DT_BINDINGS_CLOCK_TEGRA234_CLOCK_H @@ -9,6 +9,26 @@ * @defgroup bpmp_clock_ids Clock ID's * @{ */ +/** output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_AHUB */ +#define TEGRA234_CLK_AHUB 4U +/** @brief output of gate CLK_ENB_APB2APE */ +#define TEGRA234_CLK_APB2APE 5U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_APE */ +#define TEGRA234_CLK_APE 6U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_AUD_MCLK */ +#define TEGRA234_CLK_AUD_MCLK 7U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_DMIC1 */ +#define TEGRA234_CLK_DMIC1 15U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_DMIC2 */ +#define TEGRA234_CLK_DMIC2 16U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_DMIC3 */ +#define TEGRA234_CLK_DMIC3 17U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_DMIC4 */ +#define TEGRA234_CLK_DMIC4 18U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_DSPK1 */ +#define TEGRA234_CLK_DSPK1 29U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_DSPK2 */ +#define TEGRA234_CLK_DSPK2 30U /** * @brief controls the EMC clock frequency. * @details Doing a clk_set_rate on this clock will select the @@ -36,8 +56,36 @@ #define TEGRA234_CLK_I2C8 54U /** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_I2C9 */ #define TEGRA234_CLK_I2C9 55U +/** output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_I2S1 */ +#define TEGRA234_CLK_I2S1 56U +/** @brief clock recovered from I2S1 input */ +#define TEGRA234_CLK_I2S1_SYNC_INPUT 57U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_I2S2 */ +#define TEGRA234_CLK_I2S2 58U +/** @brief clock recovered from I2S2 input */ +#define TEGRA234_CLK_I2S2_SYNC_INPUT 59U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_I2S3 */ +#define TEGRA234_CLK_I2S3 60U +/** @brief clock recovered from I2S3 input */ +#define TEGRA234_CLK_I2S3_SYNC_INPUT 61U +/** output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_I2S4 */ +#define TEGRA234_CLK_I2S4 62U +/** @brief clock recovered from I2S4 input */ +#define TEGRA234_CLK_I2S4_SYNC_INPUT 63U +/** output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_I2S5 */ +#define TEGRA234_CLK_I2S5 64U +/** @brief clock recovered from I2S5 input */ +#define TEGRA234_CLK_I2S5_SYNC_INPUT 65U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_I2S6 */ +#define TEGRA234_CLK_I2S6 66U +/** @brief clock recovered from I2S6 input */ +#define TEGRA234_CLK_I2S6_SYNC_INPUT 67U +/** PLL controlled by CLK_RST_CONTROLLER_PLLA_BASE for use by audio clocks */ +#define TEGRA234_CLK_PLLA 93U /** @brief PLLP clk output */ #define TEGRA234_CLK_PLLP_OUT0 102U +/** @brief output of the divider CLK_RST_CONTROLLER_PLLA_OUT */ +#define TEGRA234_CLK_PLLA_OUT0 104U /** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_PWM1 */ #define TEGRA234_CLK_PWM1 105U /** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_PWM2 */ @@ -56,6 +104,30 @@ #define TEGRA234_CLK_PWM8 112U /** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_SDMMC4 */ #define TEGRA234_CLK_SDMMC4 123U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_AUDIO_SYNC_CLK_DMIC1 */ +#define TEGRA234_CLK_SYNC_DMIC1 139U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_AUDIO_SYNC_CLK_DMIC2 */ +#define TEGRA234_CLK_SYNC_DMIC2 140U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_AUDIO_SYNC_CLK_DMIC3 */ +#define TEGRA234_CLK_SYNC_DMIC3 141U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_AUDIO_SYNC_CLK_DMIC4 */ +#define TEGRA234_CLK_SYNC_DMIC4 142U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_AUDIO_SYNC_CLK_DSPK1 */ +#define TEGRA234_CLK_SYNC_DSPK1 143U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_AUDIO_SYNC_CLK_DSPK2 */ +#define TEGRA234_CLK_SYNC_DSPK2 144U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_AUDIO_SYNC_CLK_I2S1 */ +#define TEGRA234_CLK_SYNC_I2S1 145U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_AUDIO_SYNC_CLK_I2S2 */ +#define TEGRA234_CLK_SYNC_I2S2 146U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_AUDIO_SYNC_CLK_I2S3 */ +#define TEGRA234_CLK_SYNC_I2S3 147U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_AUDIO_SYNC_CLK_I2S4 */ +#define TEGRA234_CLK_SYNC_I2S4 148U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_AUDIO_SYNC_CLK_I2S5 */ +#define TEGRA234_CLK_SYNC_I2S5 149U +/** @brief output of mux controlled by CLK_RST_CONTROLLER_AUDIO_SYNC_CLK_I2S6 */ +#define TEGRA234_CLK_SYNC_I2S6 150U /** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_UARTA */ #define TEGRA234_CLK_UARTA 155U /** @brief CLK_RST_CONTROLLER_CLK_SOURCE_SDMMC_LEGACY_TM switch divider output */ diff --git a/include/dt-bindings/memory/tegra234-mc.h b/include/dt-bindings/memory/tegra234-mc.h index 2662f70c15c6..42661dda1c53 100644 --- a/include/dt-bindings/memory/tegra234-mc.h +++ b/include/dt-bindings/memory/tegra234-mc.h @@ -1,4 +1,5 @@ /* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ +/* Copyright (c) 2018-2022, NVIDIA CORPORATION. All rights reserved. */ #ifndef DT_BINDINGS_MEMORY_TEGRA234_MC_H #define DT_BINDINGS_MEMORY_TEGRA234_MC_H @@ -7,6 +8,8 @@ #define TEGRA234_SID_INVALID 0x00 #define TEGRA234_SID_PASSTHROUGH 0x7f +/* NISO0 stream IDs */ +#define TEGRA234_SID_APE 0x02 /* NISO1 stream IDs */ #define TEGRA234_SID_SDMMC4 0x02 @@ -28,5 +31,9 @@ #define TEGRA234_MEMORY_CLIENT_BPMPDMAR 0x95 /* BPMPDMA write client */ #define TEGRA234_MEMORY_CLIENT_BPMPDMAW 0x96 +/* APEDMA read client */ +#define TEGRA234_MEMORY_CLIENT_APEDMAR 0x9f +/* APEDMA write client */ +#define TEGRA234_MEMORY_CLIENT_APEDMAW 0xa0 #endif diff --git a/include/dt-bindings/power/tegra234-powergate.h b/include/dt-bindings/power/tegra234-powergate.h new file mode 100644 index 000000000000..8e28fcbdc038 --- /dev/null +++ b/include/dt-bindings/power/tegra234-powergate.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018-2022, NVIDIA CORPORATION. All rights reserved. */ + +#ifndef __ABI_MACH_T234_POWERGATE_T234_H_ +#define __ABI_MACH_T234_POWERGATE_T234_H_ + +#define TEGRA234_POWER_DOMAIN_AUD 2U + +#endif -- cgit v1.2.3 From 2e7dfb0e9cacad0f1adbc4b97f0b96ba35027f24 Mon Sep 17 00:00:00 2001 From: Samuel Holland Date: Sun, 13 Feb 2022 23:01:16 -0600 Subject: usb: typec: Factor out non-PD fwnode properties Basic programmable non-PD Type-C port controllers do not need the full TCPM library, but they share the same devicetree binding and the same typec_capability structure. Factor out a helper for parsing those properties which map to fields in struct typec_capability, so the code can be shared between TCPM and basic non-TCPM drivers. Reviewed-by: Heikki Krogerus Signed-off-by: Samuel Holland Link: https://lore.kernel.org/r/20220214050118.61015-4-samuel@sholland.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index 7ba45a97eeae..fdf737d48b3b 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -295,6 +295,9 @@ int typec_set_mode(struct typec_port *port, int mode); void *typec_get_drvdata(struct typec_port *port); +int typec_get_fw_cap(struct typec_capability *cap, + struct fwnode_handle *fwnode); + int typec_find_pwr_opmode(const char *name); int typec_find_orientation(const char *name); int typec_find_port_power_role(const char *name); -- cgit v1.2.3 From ebcbc6ea7d8a604ad8504dae70a6ac1b1e64a0b7 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 14 Feb 2022 18:20:24 -0800 Subject: mm/munlock: delete page_mlock() and all its works We have recommended some applications to mlock their userspace, but that turns out to be counter-productive: when many processes mlock the same file, contention on rmap's i_mmap_rwsem can become intolerable at exit: it is needed for write, to remove any vma mapping that file from rmap's tree; but hogged for read by those with mlocks calling page_mlock() (formerly known as try_to_munlock()) on *each* page mapped from the file (the purpose being to find out whether another process has the page mlocked, so therefore it should not be unmlocked yet). Several optimizations have been made in the past: one is to skip page_mlock() when mapcount tells that nothing else has this page mapped; but that doesn't help at all when others do have it mapped. This time around, I initially intended to add a preliminary search of the rmap tree for overlapping VM_LOCKED ranges; but that gets messy with locking order, when in doubt whether a page is actually present; and risks adding even more contention on the i_mmap_rwsem. A solution would be much easier, if only there were space in struct page for an mlock_count... but actually, most of the time, there is space for it - an mlocked page spends most of its life on an unevictable LRU, but since 3.18 removed the scan_unevictable_pages sysctl, that "LRU" has been redundant. Let's try to reuse its page->lru. But leave that until a later patch: in this patch, clear the ground by removing page_mlock(), and all the infrastructure that has gathered around it - which mostly hinders understanding, and will make reviewing new additions harder. Don't mind those old comments about THPs, they date from before 4.5's refcounting rework: splitting is not a risk here. Just keep a minimal version of munlock_vma_page(), as reminder of what it should attend to (in particular, the odd way PGSTRANDED is counted out of PGMUNLOCKED), and likewise a stub for munlock_vma_pages_range(). Move unchanged __mlock_posix_error_return() out of the way, down to above its caller: this series then makes no further change after mlock_fixup(). After this and each following commit, the kernel builds, boots and runs; but with deficiencies which may show up in testing of mlock and munlock. The system calls succeed or fail as before, and mlock remains effective in preventing page reclaim; but meminfo's Unevictable and Mlocked amounts may be shown too low after mlock, grow, then stay too high after munlock: with previously mlocked pages remaining unevictable for too long, until finally unmapped and freed and counts corrected. Normal service will be resumed in "mm/munlock: mlock_pte_range() when mlocking or munlocking". Signed-off-by: Hugh Dickins Acked-by: Vlastimil Babka Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/rmap.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index e704b1a4c06c..dc48aa8c2c94 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -237,12 +237,6 @@ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *); */ int folio_mkclean(struct folio *); -/* - * called in munlock()/munmap() path to check for other vmas holding - * the page mlocked. - */ -void page_mlock(struct page *page); - void remove_migration_ptes(struct page *old, struct page *new, bool locked); /* -- cgit v1.2.3 From b67bf49ce7aae72f63739abee6ac25f64bf20081 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 14 Feb 2022 18:21:52 -0800 Subject: mm/munlock: delete FOLL_MLOCK and FOLL_POPULATE If counting page mlocks, we must not double-count: follow_page_pte() can tell if a page has already been Mlocked or not, but cannot tell if a pte has already been counted or not: that will have to be done when the pte is mapped in (which lru_cache_add_inactive_or_unevictable() already tracks for new anon pages, but there's no such tracking yet for others). Delete all the FOLL_MLOCK code - faulting in the missing pages will do all that is necessary, without special mlock_vma_page() calls from here. But then FOLL_POPULATE turns out to serve no purpose - it was there so that its absence would tell faultin_page() not to faultin page when setting up VM_LOCKONFAULT areas; but if there's no special work needed here for mlock, then there's no work at all here for VM_LOCKONFAULT. Have I got that right? I've not looked into the history, but see that FOLL_POPULATE goes back before VM_LOCKONFAULT: did it serve a different purpose before? Ah, yes, it was used to skip the old stack guard page. And is it intentional that COW is not broken on existing pages when setting up a VM_LOCKONFAULT area? I can see that being argued either way, and have no reason to disagree with current behaviour. Signed-off-by: Hugh Dickins Acked-by: Vlastimil Babka Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/mm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 213cc569b192..74ee50c2033b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2925,13 +2925,11 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #define FOLL_FORCE 0x10 /* get_user_pages read/write w/o permission */ #define FOLL_NOWAIT 0x20 /* if a disk transfer is needed, start the IO * and return without waiting upon it */ -#define FOLL_POPULATE 0x40 /* fault in pages (with FOLL_MLOCK) */ #define FOLL_NOFAULT 0x80 /* do not fault in pages */ #define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ #define FOLL_NUMA 0x200 /* force NUMA hinting page fault */ #define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */ #define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */ -#define FOLL_MLOCK 0x1000 /* lock present pages */ #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ #define FOLL_COW 0x4000 /* internal GUP flag */ #define FOLL_ANON 0x8000 /* don't do file mappings */ -- cgit v1.2.3 From cea86fe246b694a191804b47378eb9d77aefabec Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 14 Feb 2022 18:26:39 -0800 Subject: mm/munlock: rmap call mlock_vma_page() munlock_vma_page() Add vma argument to mlock_vma_page() and munlock_vma_page(), make them inline functions which check (vma->vm_flags & VM_LOCKED) before calling mlock_page() and munlock_page() in mm/mlock.c. Add bool compound to mlock_vma_page() and munlock_vma_page(): this is because we have understandable difficulty in accounting pte maps of THPs, and if passed a PageHead page, mlock_page() and munlock_page() cannot tell whether it's a pmd map to be counted or a pte map to be ignored. Add vma arg to page_add_file_rmap() and page_remove_rmap(), like the others, and use that to call mlock_vma_page() at the end of the page adds, and munlock_vma_page() at the end of page_remove_rmap() (end or beginning? unimportant, but end was easier for assertions in testing). No page lock is required (although almost all adds happen to hold it): delete the "Serialize with page migration" BUG_ON(!PageLocked(page))s. Certainly page lock did serialize with page migration, but I'm having difficulty explaining why that was ever important. Mlock accounting on THPs has been hard to define, differed between anon and file, involved PageDoubleMap in some places and not others, required clear_page_mlock() at some points. Keep it simple now: just count the pmds and ignore the ptes, there is no reason for ptes to undo pmd mlocks. page_add_new_anon_rmap() callers unchanged: they have long been calling lru_cache_add_inactive_or_unevictable(), which does its own VM_LOCKED handling (it also checks for not VM_SPECIAL: I think that's overcautious, and inconsistent with other checks, that mmap_region() already prevents VM_LOCKED on VM_SPECIAL; but haven't quite convinced myself to change it). Signed-off-by: Hugh Dickins Acked-by: Vlastimil Babka Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/rmap.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index dc48aa8c2c94..ac29b076082b 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -167,18 +167,19 @@ struct anon_vma *page_get_anon_vma(struct page *page); */ void page_move_anon_rmap(struct page *, struct vm_area_struct *); void page_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long, bool); + unsigned long address, bool compound); void do_page_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long, int); + unsigned long address, int flags); void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long, bool); -void page_add_file_rmap(struct page *, bool); -void page_remove_rmap(struct page *, bool); - + unsigned long address, bool compound); +void page_add_file_rmap(struct page *, struct vm_area_struct *, + bool compound); +void page_remove_rmap(struct page *, struct vm_area_struct *, + bool compound); void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long); + unsigned long address); void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long); + unsigned long address); static inline void page_dup_rmap(struct page *page, bool compound) { -- cgit v1.2.3 From 07ca760673088f262da57ff42c15558688565aa2 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 14 Feb 2022 18:29:54 -0800 Subject: mm/munlock: maintain page->mlock_count while unevictable Previous patches have been preparatory: now implement page->mlock_count. The ordering of the "Unevictable LRU" is of no significance, and there is no point holding unevictable pages on a list: place page->mlock_count to overlay page->lru.prev (since page->lru.next is overlaid by compound_head, which needs to be even so as not to satisfy PageTail - though 2 could be added instead of 1 for each mlock, if that's ever an improvement). But it's only safe to rely on or modify page->mlock_count while lruvec lock is held and page is on unevictable "LRU" - we can save lots of edits by continuing to pretend that there's an imaginary LRU here (there is an unevictable count which still needs to be maintained, but not a list). The mlock_count technique suffers from an unreliability much like with page_mlock(): while someone else has the page off LRU, not much can be done. As before, err on the safe side (behave as if mlock_count 0), and let try_to_unlock_one() move the page to unevictable if reclaim finds out later on - a few misplaced pages don't matter, what we want to avoid is imbalancing reclaim by flooding evictable lists with unevictable pages. I am not a fan of "if (!isolate_lru_page(page)) putback_lru_page(page);": if we have taken lruvec lock to get the page off its present list, then we save everyone trouble (and however many extra atomic ops) by putting it on its destination list immediately. Signed-off-by: Hugh Dickins Acked-by: Vlastimil Babka Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/mm_inline.h | 11 ++++++++--- include/linux/mm_types.h | 19 +++++++++++++++++-- 2 files changed, 25 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index b725839dfe71..884d6f6af05b 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -99,7 +99,8 @@ void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio) update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); - list_add(&folio->lru, &lruvec->lists[lru]); + if (lru != LRU_UNEVICTABLE) + list_add(&folio->lru, &lruvec->lists[lru]); } static __always_inline void add_page_to_lru_list(struct page *page, @@ -115,6 +116,7 @@ void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio) update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); + /* This is not expected to be used on LRU_UNEVICTABLE */ list_add_tail(&folio->lru, &lruvec->lists[lru]); } @@ -127,8 +129,11 @@ static __always_inline void add_page_to_lru_list_tail(struct page *page, static __always_inline void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio) { - list_del(&folio->lru); - update_lru_size(lruvec, folio_lru_list(folio), folio_zonenum(folio), + enum lru_list lru = folio_lru_list(folio); + + if (lru != LRU_UNEVICTABLE) + list_del(&folio->lru); + update_lru_size(lruvec, lru, folio_zonenum(folio), -folio_nr_pages(folio)); } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5140e5feb486..475bdb282769 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -85,7 +85,16 @@ struct page { * lruvec->lru_lock. Sometimes used as a generic list * by the page owner. */ - struct list_head lru; + union { + struct list_head lru; + /* Or, for the Unevictable "LRU list" slot */ + struct { + /* Always even, to negate PageTail */ + void *__filler; + /* Count page's or folio's mlocks */ + unsigned int mlock_count; + }; + }; /* See page-flags.h for PAGE_MAPPING_FLAGS */ struct address_space *mapping; pgoff_t index; /* Our offset within mapping. */ @@ -241,7 +250,13 @@ struct folio { struct { /* public: */ unsigned long flags; - struct list_head lru; + union { + struct list_head lru; + struct { + void *__filler; + unsigned int mlock_count; + }; + }; struct address_space *mapping; pgoff_t index; void *private; -- cgit v1.2.3 From 4fe6a63077a6d3c143d68f6b96e4051f1d0740ac Mon Sep 17 00:00:00 2001 From: Stephen Kitt Date: Thu, 17 Feb 2022 14:27:55 +0100 Subject: ASoC: SOF: Replace zero-length array with flexible-array member There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use "flexible array members"[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. This helps with the ongoing efforts to globally enable -Warray-bounds and get us closer to being able to tighten the FORTIFY_SOURCE routines on memcpy(). [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://www.kernel.org/doc/html/latest/process/deprecated.html#zero-length-and-one-element-arrays Link: https://github.com/KSPP/linux/issues/78 Link: https://github.com/KSPP/linux/issues/180 Suggested-by: Gustavo A. R. Silva Signed-off-by: Stephen Kitt Acked-by: Pierre-Louis Bossart Reviewed-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20220217132755.1786130-1-steve@sk2.org Signed-off-by: Mark Brown --- include/sound/sof/topology.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/sof/topology.h b/include/sound/sof/topology.h index d12736e14b69..adee6afd1490 100644 --- a/include/sound/sof/topology.h +++ b/include/sound/sof/topology.h @@ -237,7 +237,7 @@ struct sof_ipc_comp_process { /* reserved for future use */ uint32_t reserved[7]; - uint8_t data[0]; + uint8_t data[]; } __packed; /* frees components, buffers and pipelines -- cgit v1.2.3 From 874bfdfa4735cbb1b0d6e0c6157c712a312371a1 Mon Sep 17 00:00:00 2001 From: Yifan Zhang Date: Thu, 10 Feb 2022 14:42:09 -0500 Subject: drm/amdgpu: add gc 10.3.6 support this patch adds gc 10.3.6 support. Signed-off-by: Yifan Zhang Reviewed-by: Alex Deucher Reviewed-by: Huang Rui Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 55fa660e35f4..1d65c1fbc4ec 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -1151,6 +1151,7 @@ struct drm_amdgpu_info_video_caps { #define AMDGPU_FAMILY_NV 143 /* Navi10 */ #define AMDGPU_FAMILY_VGH 144 /* Van Gogh */ #define AMDGPU_FAMILY_YC 146 /* Yellow Carp */ +#define AMDGPU_FAMILY_GC_10_3_6 149 /* GC 10.3.6 */ #define AMDGPU_FAMILY_GC_10_3_7 151 /* GC 10.3.7 */ #if defined(__cplusplus) -- cgit v1.2.3 From 904b10fb189cc15376e9bfce1ef0282e68b0b004 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Mon, 14 Feb 2022 12:41:08 +0100 Subject: PCI: Add defines for normal and subtractive PCI bridges MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add these PCI class codes to pci_ids.h: PCI_CLASS_BRIDGE_PCI_NORMAL PCI_CLASS_BRIDGE_PCI_SUBTRACTIVE Use these defines in all kernel code for describing PCI class codes for normal and subtractive PCI bridges. [bhelgaas: similar change in pci-mvebu.c] Link: https://lore.kernel.org/r/20220214114109.26809-1-pali@kernel.org Signed-off-by: Pali Rohár Signed-off-by: Bjorn Helgaas --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index aad54c666407..130949c3b486 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -60,6 +60,8 @@ #define PCI_CLASS_BRIDGE_EISA 0x0602 #define PCI_CLASS_BRIDGE_MC 0x0603 #define PCI_CLASS_BRIDGE_PCI 0x0604 +#define PCI_CLASS_BRIDGE_PCI_NORMAL 0x060400 +#define PCI_CLASS_BRIDGE_PCI_SUBTRACTIVE 0x060401 #define PCI_CLASS_BRIDGE_PCMCIA 0x0605 #define PCI_CLASS_BRIDGE_NUBUS 0x0606 #define PCI_CLASS_BRIDGE_CARDBUS 0x0607 -- cgit v1.2.3 From d2b1d186ce2eac6b15d31db3e2750ee8e02bbe81 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 16 Feb 2022 21:37:26 +0200 Subject: net: dsa: delete unused exported symbols for ethtool PHY stats Introduced in commit cf963573039a ("net: dsa: Allow providing PHY statistics from CPU port"), it appears these were never used. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/20220216193726.2926320-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 1456313a1faa..c8626dec970c 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -1257,9 +1257,6 @@ static inline bool dsa_slave_dev_check(const struct net_device *dev) #endif netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev); -int dsa_port_get_phy_strings(struct dsa_port *dp, uint8_t *data); -int dsa_port_get_ethtool_phy_stats(struct dsa_port *dp, uint64_t *data); -int dsa_port_get_phy_sset_count(struct dsa_port *dp); void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up); struct dsa_tag_driver { -- cgit v1.2.3 From 091296d30917f6e63a9402974f546412dfb2a8e6 Mon Sep 17 00:00:00 2001 From: Miri Korenblit Date: Sat, 5 Feb 2022 11:21:36 +0200 Subject: iwlwifi: mvm: refactor setting PPE thresholds in STA_HE_CTXT_CMD We are setting the PPE Thresholds in STA_HE_CTXT_CMD according to HE PHY Capabilities IE. As EHT is introduced, we will have to set this thresholds according to EHT PHY Capabilities IE if we're in an EHT connection. Some parts of the code can be used for both HE and EHT. Put this parts in functions which will be used in the patch which adds support for EHT PPE. Signed-off-by: Miri Korenblit Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20220205112029.48a508dfffef.If392e44d88f96ebed7fadf827e327194d4bd97b1@changeid Signed-off-by: Luca Coelho --- include/linux/ieee80211.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index a4143466cb32..75d40acb60c1 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2421,6 +2421,7 @@ ieee80211_he_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap) #define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK 0x78 #define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_POS (3) #define IEEE80211_PPE_THRES_INFO_PPET_SIZE (3) +#define IEEE80211_HE_PPE_THRES_INFO_HEADER_SIZE (7) /* * Calculate 802.11ax HE capabilities IE PPE field size -- cgit v1.2.3 From 8467fadc115cb08bb1cbc7885cb7b7ef1871cae4 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Thu, 17 Feb 2022 10:07:55 +0200 Subject: net: gro: Fix a 'directive in macro's argument list' sparse warning Following the cited commit, sparse started complaining about: ../include/net/gro.h:58:1: warning: directive in macro's argument list ../include/net/gro.h:59:1: warning: directive in macro's argument list Fix that by moving the defines out of the struct_group() macro. Fixes: de5a1f3ce4c8 ("net: gro: minor optimization for dev_gro_receive()") Reviewed-by: Maxim Mikityanskiy Signed-off-by: Gal Pressman Acked-by: Alexander Lobakin Acked-by: Paolo Abeni Signed-off-by: David S. Miller --- include/net/gro.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/gro.h b/include/net/gro.h index a765fedda5c4..867656b0739c 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -35,6 +35,9 @@ struct napi_gro_cb { /* jiffies when first packet was created/queued */ unsigned long age; +/* Used in napi_gro_cb::free */ +#define NAPI_GRO_FREE 1 +#define NAPI_GRO_FREE_STOLEN_HEAD 2 /* portion of the cb set to zero at every gro iteration */ struct_group(zeroed, @@ -55,8 +58,6 @@ struct napi_gro_cb { /* Free the skb? */ u8 free:2; -#define NAPI_GRO_FREE 1 -#define NAPI_GRO_FREE_STOLEN_HEAD 2 /* Used in foo-over-udp, set in udp[46]_gro_receive */ u8 is_ipv6:1; -- cgit v1.2.3 From bde018222c6b084ac32933a9f933581dd83da18e Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Thu, 17 Feb 2022 18:30:35 +0000 Subject: net: dsa: add support for phylink mac_select_pcs() Add DSA support for the phylink mac_select_pcs() method so DSA drivers can return provide phylink with the appropriate PCS for the PHY interface mode. Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- include/net/dsa.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index c8626dec970c..bc6eef6af810 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -788,6 +788,9 @@ struct dsa_switch_ops { void (*phylink_validate)(struct dsa_switch *ds, int port, unsigned long *supported, struct phylink_link_state *state); + struct phylink_pcs *(*phylink_mac_select_pcs)(struct dsa_switch *ds, + int port, + phy_interface_t iface); int (*phylink_mac_link_state)(struct dsa_switch *ds, int port, struct phylink_link_state *state); void (*phylink_mac_config)(struct dsa_switch *ds, int port, -- cgit v1.2.3 From 6de74d1069b821e96460d0fc2edfc35785db04fb Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Wed, 9 Feb 2022 08:11:10 -0800 Subject: hv_utils: Add comment about max VMbus packet size in VSS driver The VSS driver allocates a VMbus receive buffer significantly larger than sizeof(hv_vss_msg), with no explanation. To help prevent future mistakes, add a #define and comment about why this is done. No functional change. Signed-off-by: Michael Kelley Link: https://lore.kernel.org/r/1644423070-75125-1-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- include/uapi/linux/hyperv.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/hyperv.h b/include/uapi/linux/hyperv.h index daf82a230c0e..aaa502a7bff4 100644 --- a/include/uapi/linux/hyperv.h +++ b/include/uapi/linux/hyperv.h @@ -90,6 +90,17 @@ struct hv_vss_check_dm_info { __u32 flags; } __attribute__((packed)); +/* + * struct hv_vss_msg encodes the fields that the Linux VSS + * driver accesses. However, FREEZE messages from Hyper-V contain + * additional LUN information that Linux doesn't use and are not + * represented in struct hv_vss_msg. A received FREEZE message may + * be as large as 6,260 bytes, so the driver must allocate at least + * that much space, not sizeof(struct hv_vss_msg). Other messages + * such as AUTO_RECOVER may be as large as 12,500 bytes. However, + * because the Linux VSS driver responds that it doesn't support + * auto-recovery, it should not receive such messages. + */ struct hv_vss_msg { union { struct hv_vss_hdr vss_hdr; -- cgit v1.2.3 From ec87cf3782f7b05ae15e061d36c763c35488f292 Mon Sep 17 00:00:00 2001 From: Sergey Shtylyov Date: Wed, 2 Feb 2022 23:58:21 +0300 Subject: ata: libata: make ata_host_suspend() *void* MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ata_host_suspend() always returns 0, so the result checks in many drivers look pointless. Let's make this function return *void* instead of *int*. Found by Linux Verification Center (linuxtesting.org) with the SVACE static analysis tool. Signed-off-by: Sergey Shtylyov Acked-by: Uwe Kleine-König Reviewed-by: Hannes Reinecke Signed-off-by: Damien Le Moal --- include/linux/libata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/libata.h b/include/linux/libata.h index 605756f645be..a49e75c4206d 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1080,7 +1080,7 @@ extern int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *dev, extern bool ata_link_online(struct ata_link *link); extern bool ata_link_offline(struct ata_link *link); #ifdef CONFIG_PM -extern int ata_host_suspend(struct ata_host *host, pm_message_t mesg); +extern void ata_host_suspend(struct ata_host *host, pm_message_t mesg); extern void ata_host_resume(struct ata_host *host); extern void ata_sas_port_suspend(struct ata_port *ap); extern void ata_sas_port_resume(struct ata_port *ap); -- cgit v1.2.3 From 47f0bd5032106469827cf56c8b45bb9101112105 Mon Sep 17 00:00:00 2001 From: Jacques de Laval Date: Thu, 17 Feb 2022 16:02:02 +0100 Subject: net: Add new protocol attribute to IP addresses This patch adds a new protocol attribute to IPv4 and IPv6 addresses. Inspiration was taken from the protocol attribute of routes. User space applications like iproute2 can set/get the protocol with the Netlink API. The attribute is stored as an 8-bit unsigned integer. The protocol attribute is set by kernel for these categories: - IPv4 and IPv6 loopback addresses - IPv6 addresses generated from router announcements - IPv6 link local addresses User space may pass custom protocols, not defined by the kernel. Grouping addresses on their origin is useful in scenarios where you want to distinguish between addresses based on who added them, e.g. kernel vs. user space. Tagging addresses with a string label is an existing feature that could be used as a solution. Unfortunately the max length of a label is 15 characters, and for compatibility reasons the label must be prefixed with the name of the device followed by a colon. Since device names also have a max length of 15 characters, only -1 characters is guaranteed to be available for any origin tag, which is not that much. A reference implementation of user space setting and getting protocols is available for iproute2: https://github.com/westermo/iproute2/commit/9a6ea18bd79f47f293e5edc7780f315ea42ff540 Signed-off-by: Jacques de Laval Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20220217150202.80802-1-Jacques.De.Laval@westermo.com Signed-off-by: Jakub Kicinski --- include/linux/inetdevice.h | 1 + include/net/addrconf.h | 2 ++ include/net/if_inet6.h | 2 ++ include/uapi/linux/if_addr.h | 9 ++++++++- 4 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 674aeead6260..ead323243e7b 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -150,6 +150,7 @@ struct in_ifaddr { __be32 ifa_broadcast; unsigned char ifa_scope; unsigned char ifa_prefixlen; + unsigned char ifa_proto; __u32 ifa_flags; char ifa_label[IFNAMSIZ]; diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 59940e230b78..f7506f08e505 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -64,6 +64,8 @@ struct ifa6_config { const struct in6_addr *pfx; unsigned int plen; + u8 ifa_proto; + const struct in6_addr *peer_pfx; u32 rt_priority; diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index f026cf08a8e8..4cfdef6ca4f6 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -71,6 +71,8 @@ struct inet6_ifaddr { bool tokenized; + u8 ifa_proto; + struct rcu_head rcu; struct in6_addr peer_addr; }; diff --git a/include/uapi/linux/if_addr.h b/include/uapi/linux/if_addr.h index dfcf3ce0097f..1c392dd95a5e 100644 --- a/include/uapi/linux/if_addr.h +++ b/include/uapi/linux/if_addr.h @@ -33,8 +33,9 @@ enum { IFA_CACHEINFO, IFA_MULTICAST, IFA_FLAGS, - IFA_RT_PRIORITY, /* u32, priority/metric for prefix route */ + IFA_RT_PRIORITY, /* u32, priority/metric for prefix route */ IFA_TARGET_NETNSID, + IFA_PROTO, /* u8, address protocol */ __IFA_MAX, }; @@ -69,4 +70,10 @@ struct ifa_cacheinfo { #define IFA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifaddrmsg)) #endif +/* ifa_proto */ +#define IFAPROT_UNSPEC 0 +#define IFAPROT_KERNEL_LO 1 /* loopback */ +#define IFAPROT_KERNEL_RA 2 /* set by kernel from router announcement */ +#define IFAPROT_KERNEL_LL 3 /* link-local set by kernel */ + #endif -- cgit v1.2.3 From cb196b725936f6b776ad1d073f66fbe92aa798fa Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Fri, 18 Feb 2022 12:25:53 +0800 Subject: mctp: replace mctp_address_ok with more fine-grained helpers Currently, we have mctp_address_ok(), which checks if an EID is in the "valid" range of 8-254 inclusive. However, 0 and 255 may also be valid addresses, depending on context. 0 is the NULL EID, which may be set when physical addressing is used. 255 is valid as a destination address for broadcasts. This change renames mctp_address_ok to mctp_address_unicast, and adds similar helpers for broadcast and null EIDs, which will be used in an upcoming commit. Signed-off-by: Jeremy Kerr Signed-off-by: Jakub Kicinski --- include/net/mctp.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mctp.h b/include/net/mctp.h index e80a4baf8379..d37268fe6825 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -40,11 +40,21 @@ struct mctp_hdr { #define MCTP_INITIAL_DEFAULT_NET 1 -static inline bool mctp_address_ok(mctp_eid_t eid) +static inline bool mctp_address_unicast(mctp_eid_t eid) { return eid >= 8 && eid < 255; } +static inline bool mctp_address_broadcast(mctp_eid_t eid) +{ + return eid == 255; +} + +static inline bool mctp_address_null(mctp_eid_t eid) +{ + return eid == 0; +} + static inline bool mctp_address_matches(mctp_eid_t match, mctp_eid_t eid) { return match == eid || match == MCTP_ADDR_ANY; -- cgit v1.2.3 From 8a69fe0be143b0a1af829f85f0e9a1ae7d6a04db Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 14 Feb 2022 16:52:11 +0000 Subject: sched/preempt: Refactor sched_dynamic_update() Currently sched_dynamic_update needs to open-code the enabled/disabled function names for each preemption model it supports, when in practice this is a boolean enabled/disabled state for each function. Make this clearer and avoid repetition by defining the enabled/disabled states at the function definition, and using helper macros to perform the static_call_update(). Where x86 currently overrides the enabled function, it is made to provide both the enabled and disabled states for consistency, with defaults provided by the core code otherwise. In subsequent patches this will allow us to support PREEMPT_DYNAMIC without static calls. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Acked-by: Ard Biesheuvel Acked-by: Frederic Weisbecker Link: https://lore.kernel.org/r/20220214165216.2231574-3-mark.rutland@arm.com --- include/linux/entry-common.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index 2e2b8d6140ed..a01ac1a0a292 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -456,6 +456,8 @@ irqentry_state_t noinstr irqentry_enter(struct pt_regs *regs); */ void irqentry_exit_cond_resched(void); #ifdef CONFIG_PREEMPT_DYNAMIC +#define irqentry_exit_cond_resched_dynamic_enabled irqentry_exit_cond_resched +#define irqentry_exit_cond_resched_dynamic_disabled NULL DECLARE_STATIC_CALL(irqentry_exit_cond_resched, irqentry_exit_cond_resched); #endif -- cgit v1.2.3 From 4624a14f4daa8ab4578d274555fd8847254ce339 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 14 Feb 2022 16:52:12 +0000 Subject: sched/preempt: Simplify irqentry_exit_cond_resched() callers Currently callers of irqentry_exit_cond_resched() need to be aware of whether the function should be indirected via a static call, leading to ugly ifdeffery in callers. Save them the hassle with a static inline wrapper that does the right thing. The raw_irqentry_exit_cond_resched() will also be useful in subsequent patches which will add conditional wrappers for preemption functions. Note: in arch/x86/entry/common.c, xen_pv_evtchn_do_upcall() always calls irqentry_exit_cond_resched() directly, even when PREEMPT_DYNAMIC is in use. I believe this is a latent bug (which this patch corrects), but I'm not entirely certain this wasn't deliberate. Signed-off-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Acked-by: Ard Biesheuvel Acked-by: Frederic Weisbecker Link: https://lore.kernel.org/r/20220214165216.2231574-4-mark.rutland@arm.com --- include/linux/entry-common.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index a01ac1a0a292..dfd84c59b144 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -454,11 +454,14 @@ irqentry_state_t noinstr irqentry_enter(struct pt_regs *regs); * * Conditional reschedule with additional sanity checks. */ -void irqentry_exit_cond_resched(void); +void raw_irqentry_exit_cond_resched(void); #ifdef CONFIG_PREEMPT_DYNAMIC -#define irqentry_exit_cond_resched_dynamic_enabled irqentry_exit_cond_resched +#define irqentry_exit_cond_resched_dynamic_enabled raw_irqentry_exit_cond_resched #define irqentry_exit_cond_resched_dynamic_disabled NULL -DECLARE_STATIC_CALL(irqentry_exit_cond_resched, irqentry_exit_cond_resched); +DECLARE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched); +#define irqentry_exit_cond_resched() static_call(irqentry_exit_cond_resched)() +#else +#define irqentry_exit_cond_resched() raw_irqentry_exit_cond_resched() #endif /** -- cgit v1.2.3 From 99cf983cc8bca4adb461b519664c939a565cfd4d Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 14 Feb 2022 16:52:14 +0000 Subject: sched/preempt: Add PREEMPT_DYNAMIC using static keys Where an architecture selects HAVE_STATIC_CALL but not HAVE_STATIC_CALL_INLINE, each static call has an out-of-line trampoline which will either branch to a callee or return to the caller. On such architectures, a number of constraints can conspire to make those trampolines more complicated and potentially less useful than we'd like. For example: * Hardware and software control flow integrity schemes can require the addition of "landing pad" instructions (e.g. `BTI` for arm64), which will also be present at the "real" callee. * Limited branch ranges can require that trampolines generate or load an address into a register and perform an indirect branch (or at least have a slow path that does so). This loses some of the benefits of having a direct branch. * Interaction with SW CFI schemes can be complicated and fragile, e.g. requiring that we can recognise idiomatic codegen and remove indirections understand, at least until clang proves more helpful mechanisms for dealing with this. For PREEMPT_DYNAMIC, we don't need the full power of static calls, as we really only need to enable/disable specific preemption functions. We can achieve the same effect without a number of the pain points above by using static keys to fold early returns into the preemption functions themselves rather than in an out-of-line trampoline, effectively inlining the trampoline into the start of the function. For arm64, this results in good code generation. For example, the dynamic_cond_resched() wrapper looks as follows when enabled. When disabled, the first `B` is replaced with a `NOP`, resulting in an early return. | : | bti c | b // or `nop` | mov w0, #0x0 | ret | mrs x0, sp_el0 | ldr x0, [x0, #8] | cbnz x0, | paciasp | stp x29, x30, [sp, #-16]! | mov x29, sp | bl | mov w0, #0x1 | ldp x29, x30, [sp], #16 | autiasp | ret ... compared to the regular form of the function: | <__cond_resched>: | bti c | mrs x0, sp_el0 | ldr x1, [x0, #8] | cbz x1, <__cond_resched+0x18> | mov w0, #0x0 | ret | paciasp | stp x29, x30, [sp, #-16]! | mov x29, sp | bl | mov w0, #0x1 | ldp x29, x30, [sp], #16 | autiasp | ret Any architecture which implements static keys should be able to use this to implement PREEMPT_DYNAMIC with similar cost to non-inlined static calls. Since this is likely to have greater overhead than (inlined) static calls, PREEMPT_DYNAMIC is only defaulted to enabled when HAVE_PREEMPT_DYNAMIC_CALL is selected. Signed-off-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Acked-by: Ard Biesheuvel Acked-by: Frederic Weisbecker Link: https://lore.kernel.org/r/20220214165216.2231574-6-mark.rutland@arm.com --- include/linux/entry-common.h | 10 ++++++++-- include/linux/kernel.h | 7 ++++++- include/linux/sched.h | 10 +++++++++- 3 files changed, 23 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index dfd84c59b144..141952f4fee8 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -456,13 +456,19 @@ irqentry_state_t noinstr irqentry_enter(struct pt_regs *regs); */ void raw_irqentry_exit_cond_resched(void); #ifdef CONFIG_PREEMPT_DYNAMIC +#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) #define irqentry_exit_cond_resched_dynamic_enabled raw_irqentry_exit_cond_resched #define irqentry_exit_cond_resched_dynamic_disabled NULL DECLARE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched); #define irqentry_exit_cond_resched() static_call(irqentry_exit_cond_resched)() -#else -#define irqentry_exit_cond_resched() raw_irqentry_exit_cond_resched() +#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) +DECLARE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched); +void dynamic_irqentry_exit_cond_resched(void); +#define irqentry_exit_cond_resched() dynamic_irqentry_exit_cond_resched() #endif +#else /* CONFIG_PREEMPT_DYNAMIC */ +#define irqentry_exit_cond_resched() raw_irqentry_exit_cond_resched() +#endif /* CONFIG_PREEMPT_DYNAMIC */ /** * irqentry_exit - Handle return from exception that used irqentry_enter() diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 33f47a996513..a890428bcc1a 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -99,7 +99,7 @@ struct user; extern int __cond_resched(void); # define might_resched() __cond_resched() -#elif defined(CONFIG_PREEMPT_DYNAMIC) +#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) extern int __cond_resched(void); @@ -110,6 +110,11 @@ static __always_inline void might_resched(void) static_call_mod(might_resched)(); } +#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) + +extern int dynamic_might_resched(void); +# define might_resched() dynamic_might_resched() + #else # define might_resched() do { } while (0) diff --git a/include/linux/sched.h b/include/linux/sched.h index 508b91d57470..de03ddeb064b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2020,7 +2020,7 @@ static inline int test_tsk_need_resched(struct task_struct *tsk) #if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) extern int __cond_resched(void); -#ifdef CONFIG_PREEMPT_DYNAMIC +#if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) DECLARE_STATIC_CALL(cond_resched, __cond_resched); @@ -2029,6 +2029,14 @@ static __always_inline int _cond_resched(void) return static_call_mod(cond_resched)(); } +#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) +extern int dynamic_cond_resched(void); + +static __always_inline int _cond_resched(void) +{ + return dynamic_cond_resched(); +} + #else static inline int _cond_resched(void) -- cgit v1.2.3 From 4b340a5a726dafba15b366c4009aa0a8f77631ac Mon Sep 17 00:00:00 2001 From: Mobashshera Rasool Date: Thu, 17 Feb 2022 07:46:40 +0000 Subject: net: ip6mr: add support for passing full packet on wrong mif This patch adds support for MRT6MSG_WRMIFWHOLE which is used to pass full packet and real vif id when the incoming interface is wrong. While the RP and FHR are setting up state we need to be sending the registers encapsulated with all the data inside otherwise we lose it. The RP then decapsulates it and forwards it to the interested parties. Currently with WRONGMIF we can only be sending empty register packets and will lose that data. This behaviour can be enabled by using MRT_PIM with val == MRT6MSG_WRMIFWHOLE. This doesn't prevent MRT6MSG_WRONGMIF from happening, it happens in addition to it, also it is controlled by the same throttling parameters as WRONGMIF (i.e. 1 packet per 3 seconds currently). Both messages are generated to keep backwards compatibily and avoid breaking someone who was enabling MRT_PIM with val == 4, since any positive val is accepted and treated the same. Signed-off-by: Mobashshera Rasool Signed-off-by: David S. Miller --- include/uapi/linux/mroute6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/mroute6.h b/include/uapi/linux/mroute6.h index a1fd6173e2db..1d90c21a6251 100644 --- a/include/uapi/linux/mroute6.h +++ b/include/uapi/linux/mroute6.h @@ -134,6 +134,7 @@ struct mrt6msg { #define MRT6MSG_NOCACHE 1 #define MRT6MSG_WRONGMIF 2 #define MRT6MSG_WHOLEPKT 3 /* used for use level encap */ +#define MRT6MSG_WRMIFWHOLE 4 /* For PIM Register and assert processing */ __u8 im6_mbz; /* must be zero */ __u8 im6_msgtype; /* what type of message */ __u16 im6_mif; /* mif rec'd on */ -- cgit v1.2.3 From ccfbf44d4c7fb7c64cf79b3f2a5ae522e5165878 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Sat, 19 Feb 2022 11:47:17 +0000 Subject: net: dsa: remove pcs_poll With drivers converted over to using phylink PCS, there is no need for the struct dsa_switch member "pcs_poll" to exist anymore - there is a flag in the struct phylink_pcs which indicates whether this PCS needs to be polled which supersedes this. Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- include/net/dsa.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index bc6eef6af810..f13de2d8aef3 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -391,11 +391,6 @@ struct dsa_switch { */ u32 vlan_filtering:1; - /* MAC PCS does not provide link state change interrupt, and requires - * polling. Flag passed on to PHYLINK. - */ - u32 pcs_poll:1; - /* For switches that only have the MRU configurable. To ensure the * configured MTU is not exceeded, normalization of MRU on all bridged * interfaces is needed. -- cgit v1.2.3 From 64b4a0f8b51b20e0c9dbff7748365994364d5f01 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Sat, 19 Feb 2022 11:47:22 +0000 Subject: net: phylink: remove phylink_config's pcs_poll phylink_config's pcs_poll is no longer used, let's get rid of it. Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- include/linux/phylink.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index cca149f78d35..9ef9b7047f19 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -86,7 +86,6 @@ enum phylink_op_type { * @type: operation type of PHYLINK instance * @legacy_pre_march2020: driver has not been updated for March 2020 updates * (See commit 7cceb599d15d ("net: phylink: avoid mac_config calls") - * @pcs_poll: MAC PCS cannot provide link change interrupt * @poll_fixed_state: if true, starts link_poll, * if MAC link is at %MLO_AN_FIXED mode. * @ovr_an_inband: if true, override PCS to MLO_AN_INBAND @@ -100,7 +99,6 @@ struct phylink_config { struct device *dev; enum phylink_op_type type; bool legacy_pre_march2020; - bool pcs_poll; bool poll_fixed_state; bool ovr_an_inband; void (*get_fixed_state)(struct phylink_config *config, -- cgit v1.2.3 From 1d6049a3b14feb39c8d6c8f538a711dcc54f88e0 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 17 Feb 2022 23:42:30 +0800 Subject: scsi: libsas: Use enum for response frame DATAPRES field As defined in table 126 of the SAS spec 1.1, use an enum for the DATAPRES field, which makes reading the code easier. Also change sas_ssp_task_response() to use a switch statement, which is more suitable (than if-else), as suggested by Christoph. Link: https://lore.kernel.org/r/1645112566-115804-3-git-send-email-john.garry@huawei.com Suggested-by: Xiang Chen Tested-by: Yihang Li Tested-by: Damien Le Moal Reviewed-by: Jack Wang Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/sas.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/scsi/sas.h b/include/scsi/sas.h index 64154c1fed02..332a463d08ef 100644 --- a/include/scsi/sas.h +++ b/include/scsi/sas.h @@ -191,6 +191,13 @@ enum sas_gpio_reg_type { SAS_GPIO_REG_TX_GP = 4, }; +/* Response frame DATAPRES field */ +enum { + SAS_DATAPRES_NO_DATA = 0, + SAS_DATAPRES_RESPONSE_DATA = 1, + SAS_DATAPRES_SENSE_DATA = 2, +}; + struct dev_to_host_fis { u8 fis_type; /* 0x34 */ u8 flags; -- cgit v1.2.3 From 25882c82f850e3e972a973e0af310b3e58de38fd Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 17 Feb 2022 23:42:31 +0800 Subject: scsi: libsas: Delete lldd_clear_aca callback This callback is never called, so remove support. Link: https://lore.kernel.org/r/1645112566-115804-4-git-send-email-john.garry@huawei.com Tested-by: Yihang Li Tested-by: Damien Le Moal Reviewed-by: Jack Wang Reviewed-by: Christoph Hellwig Reviewed-by: Xiang Chen Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index fad328d3a551..8026c1bb57ba 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -636,7 +636,6 @@ struct sas_domain_function_template { /* Task Management Functions. Must be called from process context. */ int (*lldd_abort_task)(struct sas_task *); int (*lldd_abort_task_set)(struct domain_device *, u8 *lun); - int (*lldd_clear_aca)(struct domain_device *, u8 *lun); int (*lldd_clear_task_set)(struct domain_device *, u8 *lun); int (*lldd_I_T_nexus_reset)(struct domain_device *); int (*lldd_ata_check_ready)(struct domain_device *); -- cgit v1.2.3 From 2dd6801a671c0a82e756355d20669ad5bbe89073 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 17 Feb 2022 23:42:32 +0800 Subject: scsi: libsas: Delete SAS_SG_ERR No LLDD sets exec status as SAS_SG_ERR, so remove support. Link: https://lore.kernel.org/r/1645112566-115804-5-git-send-email-john.garry@huawei.com Tested-by: Damien Le Moal Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 8026c1bb57ba..cd2b2b67bf93 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -492,7 +492,6 @@ enum exec_status { SAS_INTERRUPTED, SAS_QUEUE_FULL, SAS_DEVICE_UNKNOWN, - SAS_SG_ERR, SAS_OPEN_REJECT, SAS_OPEN_TO, SAS_PROTO_RESPONSE, -- cgit v1.2.3 From bbfe82cdbaf84e6622ceb6f3447c8c4bb7dde7ab Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 17 Feb 2022 23:42:35 +0800 Subject: scsi: libsas: Add struct sas_tmf_task Some of the LLDDs which use libsas have their own definition of a struct to hold TMF info, so add a common struct for libsas. Also add an interim force phy id field for hisi_sas driver, which will be removed once the STP "TMF" code is factored out. Even though some LLDDs (pm8001) use a u32 for the tag, u16 will be adequate, as that named driver only uses tags in range [0, 1024). Link: https://lore.kernel.org/r/1645112566-115804-8-git-send-email-john.garry@huawei.com Tested-by: Yihang Li Tested-by: Damien Le Moal Reviewed-by: Christoph Hellwig Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index cd2b2b67bf93..7a55853fad7b 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -576,6 +576,15 @@ struct sas_ssp_task { struct scsi_cmnd *cmd; }; +struct sas_tmf_task { + u8 tmf; + u16 tag_of_task_to_be_managed; + + /* Temp */ + int force_phy; + int phy_id; +}; + struct sas_task { struct domain_device *dev; -- cgit v1.2.3 From 96e54376a8b27066d32ca36800318c43e6b6d2c5 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 17 Feb 2022 23:42:36 +0800 Subject: scsi: libsas: Add sas_task.tmf Add a pointer to a sas_tmf_task to the sas_task struct, as this will be used when the common LLDD TMF code is factored out. Also set it for the LLDDs to store per-sas_task TMF info. Link: https://lore.kernel.org/r/1645112566-115804-9-git-send-email-john.garry@huawei.com Tested-by: Yihang Li Tested-by: Damien Le Moal Reviewed-by: Christoph Hellwig Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 7a55853fad7b..9c181ebccfee 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -610,6 +610,7 @@ struct sas_task { void *lldd_task; /* for use by LLDDs */ void *uldd_task; struct sas_task_slow *slow_task; + struct sas_tmf_task *tmf; }; struct sas_task_slow { -- cgit v1.2.3 From 2037a340314f4be8977563006476bd15c859eda2 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 17 Feb 2022 23:42:39 +0800 Subject: scsi: libsas: Add TMF handler exec complete callback The pm8001 TMF handler has some special processing when the TMF completes, so add a callback and fill it in for the pm8001 driver. Link: https://lore.kernel.org/r/1645112566-115804-12-git-send-email-john.garry@huawei.com Tested-by: Yihang Li Tested-by: Damien Le Moal Reviewed-by: Christoph Hellwig Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 9c181ebccfee..dd6551e809a0 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -652,6 +652,9 @@ struct sas_domain_function_template { int (*lldd_lu_reset)(struct domain_device *, u8 *lun); int (*lldd_query_task)(struct sas_task *); + /* Special TMF callbacks */ + void (*lldd_tmf_exec_complete)(struct domain_device *dev); + /* Port and Adapter management */ int (*lldd_clear_nexus_port)(struct asd_sas_port *); int (*lldd_clear_nexus_ha)(struct sas_ha_struct *); -- cgit v1.2.3 From 693e66a0a6ac56322687f614ba6e8bfbc43a1530 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 17 Feb 2022 23:42:40 +0800 Subject: scsi: libsas: Add TMF handler aborted callback The hisi_sas and pm8001 TMF handlers have some special processing for when the TMF is aborted, so add a callback and fill it in for those drivers. Link: https://lore.kernel.org/r/1645112566-115804-13-git-send-email-john.garry@huawei.com Tested-by: Yihang Li Tested-by: Damien Le Moal Reviewed-by: Christoph Hellwig Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index dd6551e809a0..c44de478e314 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -654,6 +654,7 @@ struct sas_domain_function_template { /* Special TMF callbacks */ void (*lldd_tmf_exec_complete)(struct domain_device *dev); + void (*lldd_tmf_aborted)(struct sas_task *task); /* Port and Adapter management */ int (*lldd_clear_nexus_port)(struct asd_sas_port *); -- cgit v1.2.3 From 69b80a0ed0b5d0c54ee1618eb5a015699e8c47c5 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 17 Feb 2022 23:42:41 +0800 Subject: scsi: libsas: Add sas_abort_task_set() Add a generic implementation of abort task set TMF handler, and use in LLDDs. Link: https://lore.kernel.org/r/1645112566-115804-14-git-send-email-john.garry@huawei.com Tested-by: Yihang Li Tested-by: Damien Le Moal Reviewed-by: Christoph Hellwig Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index c44de478e314..53fdc18bdd09 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -722,6 +722,8 @@ struct sas_phy *sas_get_local_phy(struct domain_device *dev); int sas_request_addr(struct Scsi_Host *shost, u8 *addr); +int sas_abort_task_set(struct domain_device *dev, u8 *lun); + int sas_notify_port_event(struct asd_sas_phy *phy, enum port_event event, gfp_t gfp_flags); int sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event, -- cgit v1.2.3 From e8585452953a040a6d1d901e5b2e8c327f09e219 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 17 Feb 2022 23:42:42 +0800 Subject: scsi: libsas: Add sas_clear_task_set() Add a generic implementation of clear task set TMF handler, and use in LLDDs. Link: https://lore.kernel.org/r/1645112566-115804-15-git-send-email-john.garry@huawei.com Tested-by: Yihang Li Tested-by: Damien Le Moal Reviewed-by: Christoph Hellwig Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 53fdc18bdd09..f71a47740ff8 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -723,6 +723,7 @@ struct sas_phy *sas_get_local_phy(struct domain_device *dev); int sas_request_addr(struct Scsi_Host *shost, u8 *addr); int sas_abort_task_set(struct domain_device *dev, u8 *lun); +int sas_clear_task_set(struct domain_device *dev, u8 *lun); int sas_notify_port_event(struct asd_sas_phy *phy, enum port_event event, gfp_t gfp_flags); -- cgit v1.2.3 From 29d7769055a21968c0bbfe866affe1640d90bd1d Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 17 Feb 2022 23:42:43 +0800 Subject: scsi: libsas: Add sas_lu_reset() Add a generic implementation of LU reset TMF handler, and use in LLDDs. Link: https://lore.kernel.org/r/1645112566-115804-16-git-send-email-john.garry@huawei.com Tested-by: Yihang Li Tested-by: Damien Le Moal Reviewed-by: Christoph Hellwig Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index f71a47740ff8..7b1e2e7f5a6c 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -724,6 +724,7 @@ int sas_request_addr(struct Scsi_Host *shost, u8 *addr); int sas_abort_task_set(struct domain_device *dev, u8 *lun); int sas_clear_task_set(struct domain_device *dev, u8 *lun); +int sas_lu_reset(struct domain_device *dev, u8 *lun); int sas_notify_port_event(struct asd_sas_phy *phy, enum port_event event, gfp_t gfp_flags); -- cgit v1.2.3 From 72f8810e1fdcd52deedfd294497fa8337703a632 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 17 Feb 2022 23:42:44 +0800 Subject: scsi: libsas: Add sas_query_task() Add a generic implementation of query task TMF handler, and use in LLDDs. Link: https://lore.kernel.org/r/1645112566-115804-17-git-send-email-john.garry@huawei.com Tested-by: Yihang Li Tested-by: Damien Le Moal Reviewed-by: Christoph Hellwig Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 7b1e2e7f5a6c..bf8613fb1c4e 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -725,6 +725,7 @@ int sas_request_addr(struct Scsi_Host *shost, u8 *addr); int sas_abort_task_set(struct domain_device *dev, u8 *lun); int sas_clear_task_set(struct domain_device *dev, u8 *lun); int sas_lu_reset(struct domain_device *dev, u8 *lun); +int sas_query_task(struct sas_task *task, u16 tag); int sas_notify_port_event(struct asd_sas_phy *phy, enum port_event event, gfp_t gfp_flags); -- cgit v1.2.3 From 4fea759edfa795b170a72bfd3be7b7601012ce4b Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 17 Feb 2022 23:42:45 +0800 Subject: scsi: libsas: Add sas_abort_task() Add a generic implementation of abort task TMF handler, and use in LLDDs. With that, some LLDDs custom TMF functions can now be deleted. Link: https://lore.kernel.org/r/1645112566-115804-18-git-send-email-john.garry@huawei.com Tested-by: Yihang Li Tested-by: Damien Le Moal Reviewed-by: Christoph Hellwig Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index bf8613fb1c4e..4ea964d33600 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -726,6 +726,7 @@ int sas_abort_task_set(struct domain_device *dev, u8 *lun); int sas_clear_task_set(struct domain_device *dev, u8 *lun); int sas_lu_reset(struct domain_device *dev, u8 *lun); int sas_query_task(struct sas_task *task, u16 tag); +int sas_abort_task(struct sas_task *task, u16 tag); int sas_notify_port_event(struct asd_sas_phy *phy, enum port_event event, gfp_t gfp_flags); -- cgit v1.2.3 From efcef265fd83d9a68a68926abecb3e1dd3e260a8 Mon Sep 17 00:00:00 2001 From: Sergey Shtylyov Date: Tue, 15 Feb 2022 21:49:26 +0300 Subject: ata: add/use ata_taskfile::{error|status} fields Add the explicit error and status register fields to 'struct ata_taskfile' using the anonymous *union*s ('struct ide_taskfile' had that for ages!) and update the libata taskfile code accordingly. There should be no object code changes resulting from that... Signed-off-by: Sergey Shtylyov Signed-off-by: Damien Le Moal --- include/linux/libata.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/libata.h b/include/linux/libata.h index a49e75c4206d..0619ae462ecd 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -518,7 +518,10 @@ struct ata_taskfile { u8 hob_lbam; u8 hob_lbah; - u8 feature; + union { + u8 error; + u8 feature; + }; u8 nsect; u8 lbal; u8 lbam; @@ -526,7 +529,10 @@ struct ata_taskfile { u8 device; - u8 command; /* IO operation */ + union { + u8 status; + u8 command; + }; u32 auxiliary; /* auxiliary field */ /* from SATA 3.1 and */ -- cgit v1.2.3 From cccd73d607fee52f35b4b030408fa5f6c21ef503 Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Wed, 16 Feb 2022 09:41:32 -0800 Subject: iosys-map: Add offset to iosys_map_memcpy_to() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In certain situations it's useful to be able to write to an offset of the mapping. Add a dst_offset to iosys_map_memcpy_to(). Cc: Sumit Semwal Cc: Christian König Cc: Thomas Zimmermann Cc: dri-devel@lists.freedesktop.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Lucas De Marchi Reviewed-by: Christian König Reviewed-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20220216174147.3073235-2-lucas.demarchi@intel.com --- include/linux/iosys-map.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/iosys-map.h b/include/linux/iosys-map.h index f4186f91caa6..edd730b1e899 100644 --- a/include/linux/iosys-map.h +++ b/include/linux/iosys-map.h @@ -220,22 +220,23 @@ static inline void iosys_map_clear(struct iosys_map *map) } /** - * iosys_map_memcpy_to - Memcpy into iosys mapping + * iosys_map_memcpy_to - Memcpy into offset of iosys_map * @dst: The iosys_map structure + * @dst_offset: The offset from which to copy * @src: The source buffer * @len: The number of byte in src * - * Copies data into a iosys mapping. The source buffer is in system - * memory. Depending on the buffer's location, the helper picks the correct - * method of accessing the memory. + * Copies data into a iosys_map with an offset. The source buffer is in + * system memory. Depending on the buffer's location, the helper picks the + * correct method of accessing the memory. */ -static inline void iosys_map_memcpy_to(struct iosys_map *dst, const void *src, - size_t len) +static inline void iosys_map_memcpy_to(struct iosys_map *dst, size_t dst_offset, + const void *src, size_t len) { if (dst->is_iomem) - memcpy_toio(dst->vaddr_iomem, src, len); + memcpy_toio(dst->vaddr_iomem + dst_offset, src, len); else - memcpy(dst->vaddr, src, len); + memcpy(dst->vaddr + dst_offset, src, len); } /** -- cgit v1.2.3 From e62f25e8b3cdd29224c27938addba817aedd4b54 Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Wed, 16 Feb 2022 09:41:33 -0800 Subject: iosys-map: Add a few more helpers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit First the simplest ones: - iosys_map_memset(): when abstracting system and I/O memory, just like the memcpy() use case, memset() also has dedicated functions to be called for using IO memory. - iosys_map_memcpy_from(): we may need to copy data from I/O memory, not only to. In certain situations it's useful to be able to read or write to an offset that is calculated by having the memory layout given by a struct declaration. Usually we are going to read/write a u8, u16, u32 or u64. As a pre-requisite for the implementation, add iosys_map_memcpy_from() to be the equivalent of iosys_map_memcpy_to(), but in the other direction. Then add 2 pairs of macros: - iosys_map_rd() / iosys_map_wr() - iosys_map_rd_field() / iosys_map_wr_field() The first pair takes the C-type and offset to read/write. The second pair uses a struct describing the layout of the mapping in order to calculate the offset and size being read/written. We could use readb, readw, readl, readq and the write* counterparts, however due to alignment issues this may not work on all architectures. If alignment needs to be checked to call the right function, it's not possible to decide at compile-time which function to call: so just leave the decision to the memcpy function that will do exactly that. Finally, in order to use the above macros with a map derived from another, add another initializer: IOSYS_MAP_INIT_OFFSET(). v2: - Rework IOSYS_MAP_INIT_OFFSET() so it doesn't rely on aliasing rules within the union - Add offset to both iosys_map_rd_field() and iosys_map_wr_field() to allow the struct itself to be at an offset from the mapping - Add documentation to iosys_map_rd_field() with example and expected memory layout v3: - Drop kernel.h include as it's not needed anymore Cc: Sumit Semwal Cc: Christian König Cc: Thomas Zimmermann Cc: Mauro Carvalho Chehab Cc: dri-devel@lists.freedesktop.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Lucas De Marchi Reviewed-by: Mauro Carvalho Chehab Reviewed-by: Matt Atwood Reviewed-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20220216174147.3073235-3-lucas.demarchi@intel.com --- include/linux/iosys-map.h | 201 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 201 insertions(+) (limited to 'include') diff --git a/include/linux/iosys-map.h b/include/linux/iosys-map.h index edd730b1e899..e69a002d5aa4 100644 --- a/include/linux/iosys-map.h +++ b/include/linux/iosys-map.h @@ -120,6 +120,45 @@ struct iosys_map { .is_iomem = false, \ } +/** + * IOSYS_MAP_INIT_OFFSET - Initializes struct iosys_map from another iosys_map + * @map_: The dma-buf mapping structure to copy from + * @offset_: Offset to add to the other mapping + * + * Initializes a new iosys_map struct based on another passed as argument. It + * does a shallow copy of the struct so it's possible to update the back storage + * without changing where the original map points to. It is the equivalent of + * doing: + * + * .. code-block:: c + * + * iosys_map map = other_map; + * iosys_map_incr(&map, &offset); + * + * Example usage: + * + * .. code-block:: c + * + * void foo(struct device *dev, struct iosys_map *base_map) + * { + * ... + * struct iosys_map map = IOSYS_MAP_INIT_OFFSET(base_map, FIELD_OFFSET); + * ... + * } + * + * The advantage of using the initializer over just increasing the offset with + * iosys_map_incr() like above is that the new map will always point to the + * right place of the buffer during its scope. It reduces the risk of updating + * the wrong part of the buffer and having no compiler warning about that. If + * the assignment to IOSYS_MAP_INIT_OFFSET() is forgotten, the compiler can warn + * about the use of uninitialized variable. + */ +#define IOSYS_MAP_INIT_OFFSET(map_, offset_) ({ \ + struct iosys_map copy = *map_; \ + iosys_map_incr(©, offset_); \ + copy; \ +}) + /** * iosys_map_set_vaddr - Sets a iosys mapping structure to an address in system memory * @map: The iosys_map structure @@ -239,6 +278,26 @@ static inline void iosys_map_memcpy_to(struct iosys_map *dst, size_t dst_offset, memcpy(dst->vaddr + dst_offset, src, len); } +/** + * iosys_map_memcpy_from - Memcpy from iosys_map into system memory + * @dst: Destination in system memory + * @src: The iosys_map structure + * @src_offset: The offset from which to copy + * @len: The number of byte in src + * + * Copies data from a iosys_map with an offset. The dest buffer is in + * system memory. Depending on the mapping location, the helper picks the + * correct method of accessing the memory. + */ +static inline void iosys_map_memcpy_from(void *dst, const struct iosys_map *src, + size_t src_offset, size_t len) +{ + if (src->is_iomem) + memcpy_fromio(dst, src->vaddr_iomem + src_offset, len); + else + memcpy(dst, src->vaddr + src_offset, len); +} + /** * iosys_map_incr - Increments the address stored in a iosys mapping * @map: The iosys_map structure @@ -255,4 +314,146 @@ static inline void iosys_map_incr(struct iosys_map *map, size_t incr) map->vaddr += incr; } +/** + * iosys_map_memset - Memset iosys_map + * @dst: The iosys_map structure + * @offset: Offset from dst where to start setting value + * @value: The value to set + * @len: The number of bytes to set in dst + * + * Set value in iosys_map. Depending on the buffer's location, the helper + * picks the correct method of accessing the memory. + */ +static inline void iosys_map_memset(struct iosys_map *dst, size_t offset, + int value, size_t len) +{ + if (dst->is_iomem) + memset_io(dst->vaddr_iomem + offset, value, len); + else + memset(dst->vaddr + offset, value, len); +} + +/** + * iosys_map_rd - Read a C-type value from the iosys_map + * + * @map__: The iosys_map structure + * @offset__: The offset from which to read + * @type__: Type of the value being read + * + * Read a C type value from iosys_map, handling possible un-aligned accesses to + * the mapping. + * + * Returns: + * The value read from the mapping. + */ +#define iosys_map_rd(map__, offset__, type__) ({ \ + type__ val; \ + iosys_map_memcpy_from(&val, map__, offset__, sizeof(val)); \ + val; \ +}) + +/** + * iosys_map_wr - Write a C-type value to the iosys_map + * + * @map__: The iosys_map structure + * @offset__: The offset from the mapping to write to + * @type__: Type of the value being written + * @val__: Value to write + * + * Write a C-type value to the iosys_map, handling possible un-aligned accesses + * to the mapping. + */ +#define iosys_map_wr(map__, offset__, type__, val__) ({ \ + type__ val = (val__); \ + iosys_map_memcpy_to(map__, offset__, &val, sizeof(val)); \ +}) + +/** + * iosys_map_rd_field - Read a member from a struct in the iosys_map + * + * @map__: The iosys_map structure + * @struct_offset__: Offset from the beggining of the map, where the struct + * is located + * @struct_type__: The struct describing the layout of the mapping + * @field__: Member of the struct to read + * + * Read a value from iosys_map considering its layout is described by a C struct + * starting at @struct_offset__. The field offset and size is calculated and its + * value read handling possible un-aligned memory accesses. For example: suppose + * there is a @struct foo defined as below and the value ``foo.field2.inner2`` + * needs to be read from the iosys_map: + * + * .. code-block:: c + * + * struct foo { + * int field1; + * struct { + * int inner1; + * int inner2; + * } field2; + * int field3; + * } __packed; + * + * This is the expected memory layout of a buffer using iosys_map_rd_field(): + * + * +------------------------------+--------------------------+ + * | Address | Content | + * +==============================+==========================+ + * | buffer + 0000 | start of mmapped buffer | + * | | pointed by iosys_map | + * +------------------------------+--------------------------+ + * | ... | ... | + * +------------------------------+--------------------------+ + * | buffer + ``struct_offset__`` | start of ``struct foo`` | + * +------------------------------+--------------------------+ + * | ... | ... | + * +------------------------------+--------------------------+ + * | buffer + wwww | ``foo.field2.inner2`` | + * +------------------------------+--------------------------+ + * | ... | ... | + * +------------------------------+--------------------------+ + * | buffer + yyyy | end of ``struct foo`` | + * +------------------------------+--------------------------+ + * | ... | ... | + * +------------------------------+--------------------------+ + * | buffer + zzzz | end of mmaped buffer | + * +------------------------------+--------------------------+ + * + * Values automatically calculated by this macro or not needed are denoted by + * wwww, yyyy and zzzz. This is the code to read that value: + * + * .. code-block:: c + * + * x = iosys_map_rd_field(&map, offset, struct foo, field2.inner2); + * + * Returns: + * The value read from the mapping. + */ +#define iosys_map_rd_field(map__, struct_offset__, struct_type__, field__) ({ \ + struct_type__ *s; \ + iosys_map_rd(map__, struct_offset__ + offsetof(struct_type__, field__), \ + typeof(s->field__)); \ +}) + +/** + * iosys_map_wr_field - Write to a member of a struct in the iosys_map + * + * @map__: The iosys_map structure + * @struct_offset__: Offset from the beggining of the map, where the struct + * is located + * @struct_type__: The struct describing the layout of the mapping + * @field__: Member of the struct to read + * @val__: Value to write + * + * Write a value to the iosys_map considering its layout is described by a C struct + * starting at @struct_offset__. The field offset and size is calculated and the + * @val__ is written handling possible un-aligned memory accesses. Refer to + * iosys_map_rd_field() for expected usage and memory layout. + */ +#define iosys_map_wr_field(map__, struct_offset__, struct_type__, field__, val__) ({ \ + struct_type__ *s; \ + iosys_map_wr(map__, struct_offset__ + offsetof(struct_type__, field__), \ + typeof(s->field__), val__); \ +}) + #endif /* __IOSYS_MAP_H__ */ -- cgit v1.2.3 From caa574ffc4aaf4f29b890223878c63e2e7772f62 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Sat, 19 Feb 2022 00:17:49 +0530 Subject: drm/i915/uapi: document behaviour for DG2 64K support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On discrete platforms like DG2, we need to support a minimum page size of 64K when dealing with device local-memory. This is quite tricky for various reasons, so try to document the new implicit uapi for this. v4: Kdoc modification. v3: fix typos and less emphasis v2: Fixed suggestions on formatting [Daniel] Signed-off-by: Matthew Auld Signed-off-by: Ramalingam C Signed-off-by: Robert Beckett Acked-by: Jordan Justen Reviewed-by: Ramalingam C Reviewed-by: Thomas Hellström cc: Simon Ser cc: Pekka Paalanen Cc: Jordan Justen Cc: Kenneth Graunke Cc: mesa-dev@lists.freedesktop.org Cc: Tony Ye Cc: Slawomir Milczarek Signed-off-by: Lucas De Marchi Link: https://patchwork.freedesktop.org/patch/msgid/20220218184752.7524-13-ramalingam.c@intel.com --- include/uapi/drm/i915_drm.h | 45 ++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 40 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 914ebd9290e5..05c3642aaece 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -1118,10 +1118,16 @@ struct drm_i915_gem_exec_object2 { /** * When the EXEC_OBJECT_PINNED flag is specified this is populated by * the user with the GTT offset at which this object will be pinned. + * * When the I915_EXEC_NO_RELOC flag is specified this must contain the * presumed_offset of the object. + * * During execbuffer2 the kernel populates it with the value of the * current GTT offset of the object, for future presumed_offset writes. + * + * See struct drm_i915_gem_create_ext for the rules when dealing with + * alignment restrictions with I915_MEMORY_CLASS_DEVICE, on devices with + * minimum page sizes, like DG2. */ __u64 offset; @@ -3144,11 +3150,40 @@ struct drm_i915_gem_create_ext { * * The (page-aligned) allocated size for the object will be returned. * - * Note that for some devices we have might have further minimum - * page-size restrictions(larger than 4K), like for device local-memory. - * However in general the final size here should always reflect any - * rounding up, if for example using the I915_GEM_CREATE_EXT_MEMORY_REGIONS - * extension to place the object in device local-memory. + * + * DG2 64K min page size implications: + * + * On discrete platforms, starting from DG2, we have to contend with GTT + * page size restrictions when dealing with I915_MEMORY_CLASS_DEVICE + * objects. Specifically the hardware only supports 64K or larger GTT + * page sizes for such memory. The kernel will already ensure that all + * I915_MEMORY_CLASS_DEVICE memory is allocated using 64K or larger page + * sizes underneath. + * + * Note that the returned size here will always reflect any required + * rounding up done by the kernel, i.e 4K will now become 64K on devices + * such as DG2. + * + * Special DG2 GTT address alignment requirement: + * + * The GTT alignment will also need to be at least 2M for such objects. + * + * Note that due to how the hardware implements 64K GTT page support, we + * have some further complications: + * + * 1) The entire PDE (which covers a 2MB virtual address range), must + * contain only 64K PTEs, i.e mixing 4K and 64K PTEs in the same + * PDE is forbidden by the hardware. + * + * 2) We still need to support 4K PTEs for I915_MEMORY_CLASS_SYSTEM + * objects. + * + * To keep things simple for userland, we mandate that any GTT mappings + * must be aligned to and rounded up to 2MB. The kernel will internally + * pad them out to the next 2MB boundary. As this only wastes virtual + * address space and avoids userland having to copy any needlessly + * complicated PDE sharing scheme (coloring) and only affects DG2, this + * is deemed to be a good compromise. */ __u64 size; /** -- cgit v1.2.3 From 643b622b51f1f0015e0a80f90b4ef9032e6ddb1b Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sun, 20 Feb 2022 15:06:32 +0800 Subject: net: tcp: add skb drop reasons to tcp_v{4,6}_inbound_md5_hash() Pass the address of drop reason to tcp_v4_inbound_md5_hash() and tcp_v6_inbound_md5_hash() to store the reasons for skb drops when this function fails. Therefore, the drop reason can be passed to kfree_skb_reason() when the skb needs to be freed. Following drop reasons are added: SKB_DROP_REASON_TCP_MD5NOTFOUND SKB_DROP_REASON_TCP_MD5UNEXPECTED SKB_DROP_REASON_TCP_MD5FAILURE SKB_DROP_REASON_TCP_MD5* above correspond to LINUX_MIB_TCPMD5* Reviewed-by: Mengen Sun Reviewed-by: Hao Peng Signed-off-by: Menglong Dong Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 12 ++++++++++++ include/trace/events/skb.h | 4 ++++ 2 files changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a5adbf6b51e8..46678eb587ff 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -346,6 +346,18 @@ enum skb_drop_reason { * udp packet drop out of * udp_memory_allocated. */ + SKB_DROP_REASON_TCP_MD5NOTFOUND, /* no MD5 hash and one + * expected, corresponding + * to LINUX_MIB_TCPMD5NOTFOUND + */ + SKB_DROP_REASON_TCP_MD5UNEXPECTED, /* MD5 hash and we're not + * expecting one, corresponding + * to LINUX_MIB_TCPMD5UNEXPECTED + */ + SKB_DROP_REASON_TCP_MD5FAILURE, /* MD5 hash and its wrong, + * corresponding to + * LINUX_MIB_TCPMD5FAILURE + */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index cfcfd26399f7..46c06b0be850 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -27,6 +27,10 @@ EM(SKB_DROP_REASON_IP_NOPROTO, IP_NOPROTO) \ EM(SKB_DROP_REASON_SOCKET_RCVBUFF, SOCKET_RCVBUFF) \ EM(SKB_DROP_REASON_PROTO_MEM, PROTO_MEM) \ + EM(SKB_DROP_REASON_TCP_MD5NOTFOUND, TCP_MD5NOTFOUND) \ + EM(SKB_DROP_REASON_TCP_MD5UNEXPECTED, \ + TCP_MD5UNEXPECTED) \ + EM(SKB_DROP_REASON_TCP_MD5FAILURE, TCP_MD5FAILURE) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From 7a26dc9e7b43f5a24c4b843713e728582adf1c38 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sun, 20 Feb 2022 15:06:33 +0800 Subject: net: tcp: add skb drop reasons to tcp_add_backlog() Pass the address of drop_reason to tcp_add_backlog() to store the reasons for skb drops when fails. Following drop reasons are introduced: SKB_DROP_REASON_SOCKET_BACKLOG Reviewed-by: Mengen Sun Reviewed-by: Hao Peng Signed-off-by: Menglong Dong Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++++ include/net/tcp.h | 3 ++- include/trace/events/skb.h | 1 + 3 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 46678eb587ff..f7f33c79945b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -358,6 +358,10 @@ enum skb_drop_reason { * corresponding to * LINUX_MIB_TCPMD5FAILURE */ + SKB_DROP_REASON_SOCKET_BACKLOG, /* failed to add skb to socket + * backlog (see + * LINUX_MIB_TCPBACKLOGDROP) + */ SKB_DROP_REASON_MAX, }; diff --git a/include/net/tcp.h b/include/net/tcp.h index eff2487d972d..04f4650e0ff0 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1367,7 +1367,8 @@ static inline bool tcp_checksum_complete(struct sk_buff *skb) __skb_checksum_complete(skb); } -bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb); +bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, + enum skb_drop_reason *reason); #ifdef CONFIG_INET void __sk_defer_free_flush(struct sock *sk); diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 46c06b0be850..bfccd77e9071 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -31,6 +31,7 @@ EM(SKB_DROP_REASON_TCP_MD5UNEXPECTED, \ TCP_MD5UNEXPECTED) \ EM(SKB_DROP_REASON_TCP_MD5FAILURE, TCP_MD5FAILURE) \ + EM(SKB_DROP_REASON_SOCKET_BACKLOG, SOCKET_BACKLOG) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From 2a968ef60e1fac4e694d9f60ce19a3b66b40e8c3 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sun, 20 Feb 2022 15:06:35 +0800 Subject: net: tcp: use tcp_drop_reason() for tcp_rcv_established() Replace tcp_drop() used in tcp_rcv_established() with tcp_drop_reason(). Following drop reasons are added: SKB_DROP_REASON_TCP_FLAGS Reviewed-by: Mengen Sun Reviewed-by: Hao Peng Signed-off-by: Menglong Dong Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + include/trace/events/skb.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f7f33c79945b..671db9f49efe 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -362,6 +362,7 @@ enum skb_drop_reason { * backlog (see * LINUX_MIB_TCPBACKLOGDROP) */ + SKB_DROP_REASON_TCP_FLAGS, /* TCP flags invalid */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index bfccd77e9071..d332e7313a61 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -32,6 +32,7 @@ TCP_MD5UNEXPECTED) \ EM(SKB_DROP_REASON_TCP_MD5FAILURE, TCP_MD5FAILURE) \ EM(SKB_DROP_REASON_SOCKET_BACKLOG, SOCKET_BACKLOG) \ + EM(SKB_DROP_REASON_TCP_FLAGS, TCP_FLAGS) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From a7ec381049c0d1f03e342063d75f5c3b314d0ec2 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sun, 20 Feb 2022 15:06:36 +0800 Subject: net: tcp: use tcp_drop_reason() for tcp_data_queue() Replace tcp_drop() used in tcp_data_queue() with tcp_drop_reason(). Following drop reasons are introduced: SKB_DROP_REASON_TCP_ZEROWINDOW SKB_DROP_REASON_TCP_OLD_DATA SKB_DROP_REASON_TCP_OVERWINDOW SKB_DROP_REASON_TCP_OLD_DATA is used for the case that end_seq of skb less than the left edges of receive window. (Maybe there is a better name?) Reviewed-by: Mengen Sun Reviewed-by: Hao Peng Signed-off-by: Menglong Dong Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 13 +++++++++++++ include/trace/events/skb.h | 3 +++ 2 files changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 671db9f49efe..554ef2c848ee 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -363,6 +363,19 @@ enum skb_drop_reason { * LINUX_MIB_TCPBACKLOGDROP) */ SKB_DROP_REASON_TCP_FLAGS, /* TCP flags invalid */ + SKB_DROP_REASON_TCP_ZEROWINDOW, /* TCP receive window size is zero, + * see LINUX_MIB_TCPZEROWINDOWDROP + */ + SKB_DROP_REASON_TCP_OLD_DATA, /* the TCP data reveived is already + * received before (spurious retrans + * may happened), see + * LINUX_MIB_DELAYEDACKLOST + */ + SKB_DROP_REASON_TCP_OVERWINDOW, /* the TCP data is out of window, + * the seq of the first byte exceed + * the right edges of receive + * window + */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index d332e7313a61..cc1c8f7eaf72 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -33,6 +33,9 @@ EM(SKB_DROP_REASON_TCP_MD5FAILURE, TCP_MD5FAILURE) \ EM(SKB_DROP_REASON_SOCKET_BACKLOG, SOCKET_BACKLOG) \ EM(SKB_DROP_REASON_TCP_FLAGS, TCP_FLAGS) \ + EM(SKB_DROP_REASON_TCP_ZEROWINDOW, TCP_ZEROWINDOW) \ + EM(SKB_DROP_REASON_TCP_OLD_DATA, TCP_OLD_DATA) \ + EM(SKB_DROP_REASON_TCP_OVERWINDOW, TCP_OVERWINDOW) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From d25e481be0c519d1a458b14191dc8c2a8bb3e24a Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sun, 20 Feb 2022 15:06:37 +0800 Subject: net: tcp: use tcp_drop_reason() for tcp_data_queue_ofo() Replace tcp_drop() used in tcp_data_queue_ofo with tcp_drop_reason(). Following drop reasons are introduced: SKB_DROP_REASON_TCP_OFOMERGE Reviewed-by: Mengen Sun Reviewed-by: Hao Peng Signed-off-by: Menglong Dong Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++++ include/trace/events/skb.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 554ef2c848ee..a3e90efe6586 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -376,6 +376,10 @@ enum skb_drop_reason { * the right edges of receive * window */ + SKB_DROP_REASON_TCP_OFOMERGE, /* the data of skb is already in + * the ofo queue, corresponding to + * LINUX_MIB_TCPOFOMERGE + */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index cc1c8f7eaf72..2ab7193313aa 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -36,6 +36,7 @@ EM(SKB_DROP_REASON_TCP_ZEROWINDOW, TCP_ZEROWINDOW) \ EM(SKB_DROP_REASON_TCP_OLD_DATA, TCP_OLD_DATA) \ EM(SKB_DROP_REASON_TCP_OVERWINDOW, TCP_OVERWINDOW) \ + EM(SKB_DROP_REASON_TCP_OFOMERGE, TCP_OFOMERGE) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From a1dc6308865df719efb2a2f8a5f0f5979602d267 Mon Sep 17 00:00:00 2001 From: Amitay Isaacs Date: Fri, 21 Jan 2022 16:08:16 +1030 Subject: fsi: sbefifo: Implement FSI_SBEFIFO_READ_TIMEOUT_SECONDS ioctl FSI_SBEFIFO_READ_TIMEOUT_SECONDS ioctl sets the read timeout (in seconds) for the response received by sbefifo device from sbe. The timeout affects only the read operation on current sbefifo device fd. Certain SBE operations can take long time to complete and the default timeout of 10 seconds might not be sufficient to start receiving response from SBE. In such cases, allow the timeout to be set to the maximum of 120 seconds. The kernel does not contain the definition of the various SBE operations, so we must expose an interface to userspace to set the timeout for the given operation. Signed-off-by: Amitay Isaacs Signed-off-by: Joel Stanley Reviewed-by: Eddie James Link: https://lore.kernel.org/r/20220121053816.82253-3-joel@jms.id.au Signed-off-by: Joel Stanley --- include/uapi/linux/fsi.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/fsi.h b/include/uapi/linux/fsi.h index da577ecd90e7..b2f1977378c7 100644 --- a/include/uapi/linux/fsi.h +++ b/include/uapi/linux/fsi.h @@ -55,4 +55,18 @@ struct scom_access { #define FSI_SCOM_WRITE _IOWR('s', 0x02, struct scom_access) #define FSI_SCOM_RESET _IOW('s', 0x03, __u32) +/* + * /dev/sbefifo* ioctl interface + */ + +/** + * FSI_SBEFIFO_READ_TIMEOUT sets the read timeout for response from SBE. + * + * The read timeout is specified in seconds. The minimum value of read + * timeout is 10 seconds (default) and the maximum value of read timeout is + * 120 seconds. A read timeout of 0 will reset the value to the default of + * (10 seconds). + */ +#define FSI_SBEFIFO_READ_TIMEOUT_SECONDS _IOW('s', 0x00, __u32) + #endif /* _UAPI_LINUX_FSI_H */ -- cgit v1.2.3 From f2af60bb7ce2fa5397f401cbf65725d9c87329a4 Mon Sep 17 00:00:00 2001 From: Eddie James Date: Mon, 7 Feb 2022 10:16:40 -0600 Subject: fsi: Add trace events in initialization path Add definitions for trace events to show the scanning flow. Signed-off-by: Eddie James Reviewed-by: Steven Rostedt (Google) Link: https://lore.kernel.org/r/20220207161640.35605-1-eajames@linux.ibm.com Signed-off-by: Joel Stanley --- include/trace/events/fsi.h | 86 ++++++++++++++++++++++++++++++++ include/trace/events/fsi_master_aspeed.h | 12 +++++ 2 files changed, 98 insertions(+) (limited to 'include') diff --git a/include/trace/events/fsi.h b/include/trace/events/fsi.h index 9832cb8e0eb0..c9a72e8432b8 100644 --- a/include/trace/events/fsi.h +++ b/include/trace/events/fsi.h @@ -122,6 +122,92 @@ TRACE_EVENT(fsi_master_break, ) ); +TRACE_EVENT(fsi_slave_init, + TP_PROTO(const struct fsi_slave *slave), + TP_ARGS(slave), + TP_STRUCT__entry( + __field(int, master_idx) + __field(int, master_n_links) + __field(int, idx) + __field(int, link) + __field(int, chip_id) + __field(__u32, cfam_id) + __field(__u32, size) + ), + TP_fast_assign( + __entry->master_idx = slave->master->idx; + __entry->master_n_links = slave->master->n_links; + __entry->idx = slave->cdev_idx; + __entry->link = slave->link; + __entry->chip_id = slave->chip_id; + __entry->cfam_id = slave->cfam_id; + __entry->size = slave->size; + ), + TP_printk("fsi%d: idx:%d link:%d/%d cid:%d cfam:%08x %08x", + __entry->master_idx, + __entry->idx, + __entry->link, + __entry->master_n_links, + __entry->chip_id, + __entry->cfam_id, + __entry->size + ) +); + +TRACE_EVENT(fsi_slave_invalid_cfam, + TP_PROTO(const struct fsi_master *master, int link, uint32_t cfam_id), + TP_ARGS(master, link, cfam_id), + TP_STRUCT__entry( + __field(int, master_idx) + __field(int, master_n_links) + __field(int, link) + __field(__u32, cfam_id) + ), + TP_fast_assign( + __entry->master_idx = master->idx; + __entry->master_n_links = master->n_links; + __entry->link = link; + __entry->cfam_id = cfam_id; + ), + TP_printk("fsi%d: cfam:%08x link:%d/%d", + __entry->master_idx, + __entry->cfam_id, + __entry->link, + __entry->master_n_links + ) +); + +TRACE_EVENT(fsi_dev_init, + TP_PROTO(const struct fsi_device *dev), + TP_ARGS(dev), + TP_STRUCT__entry( + __field(int, master_idx) + __field(int, link) + __field(int, type) + __field(int, unit) + __field(int, version) + __field(__u32, addr) + __field(__u32, size) + ), + TP_fast_assign( + __entry->master_idx = dev->slave->master->idx; + __entry->link = dev->slave->link; + __entry->type = dev->engine_type; + __entry->unit = dev->unit; + __entry->version = dev->version; + __entry->addr = dev->addr; + __entry->size = dev->size; + ), + TP_printk("fsi%d: slv%d: t:%02x u:%02x v:%02x %08x@%08x", + __entry->master_idx, + __entry->link, + __entry->type, + __entry->unit, + __entry->version, + __entry->size, + __entry->addr + ) +); #endif /* _TRACE_FSI_H */ diff --git a/include/trace/events/fsi_master_aspeed.h b/include/trace/events/fsi_master_aspeed.h index a355ceacc33f..0fff873775f1 100644 --- a/include/trace/events/fsi_master_aspeed.h +++ b/include/trace/events/fsi_master_aspeed.h @@ -72,6 +72,18 @@ TRACE_EVENT(fsi_master_aspeed_opb_error, ) ); +TRACE_EVENT(fsi_master_aspeed_cfam_reset, + TP_PROTO(bool start), + TP_ARGS(start), + TP_STRUCT__entry( + __field(bool, start) + ), + TP_fast_assign( + __entry->start = start; + ), + TP_printk("%s", __entry->start ? "start" : "end") +); + #endif #include -- cgit v1.2.3 From fefee95488412796b293d28c948be6fce63d149b Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Mon, 14 Feb 2022 11:14:01 +0100 Subject: ALSA: hda: Add snd_hdac_ext_bus_link_at() helper This patch exposes a new helper to directly retrieve the link from the codec address, and makes use of this helper when retrieving the link from the codec name. Signed-off-by: Cezary Rojewski Link: https://lore.kernel.org/r/20220214101404.4074026-2-cezary.rojewski@intel.com Signed-off-by: Takashi Iwai --- include/sound/hdaudio_ext.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/sound/hdaudio_ext.h b/include/sound/hdaudio_ext.h index 77123c3e4095..b0c8e4936168 100644 --- a/include/sound/hdaudio_ext.h +++ b/include/sound/hdaudio_ext.h @@ -28,6 +28,7 @@ void snd_hdac_ext_stream_spbcap_enable(struct hdac_bus *chip, bool enable, int index); int snd_hdac_ext_bus_get_ml_capabilities(struct hdac_bus *bus); +struct hdac_ext_link *snd_hdac_ext_bus_link_at(struct hdac_bus *bus, int addr); struct hdac_ext_link *snd_hdac_ext_bus_get_link(struct hdac_bus *bus, const char *codec_name); -- cgit v1.2.3 From 595511a3ab80d9ec6649bbf22a99bee169026fd1 Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Mon, 14 Feb 2022 11:14:02 +0100 Subject: ALSA: hda: Update and expose snd_hda_codec_device_init() With few changes, snd_hda_codec_device_init() can be re-used by ASoC drivers. While at it, provide kernel doc for the exposed function. Signed-off-by: Cezary Rojewski Link: https://lore.kernel.org/r/20220214101404.4074026-3-cezary.rojewski@intel.com Signed-off-by: Takashi Iwai --- include/sound/hda_codec.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/sound/hda_codec.h b/include/sound/hda_codec.h index 82d9daa17851..5e3cbcca42f0 100644 --- a/include/sound/hda_codec.h +++ b/include/sound/hda_codec.h @@ -306,6 +306,9 @@ struct hda_codec { /* * constructors */ +__printf(3, 4) struct hda_codec * +snd_hda_codec_device_init(struct hda_bus *bus, unsigned int codec_addr, + const char *fmt, ...); int snd_hda_codec_new(struct hda_bus *bus, struct snd_card *card, unsigned int codec_addr, struct hda_codec **codecp); int snd_hda_codec_device_new(struct hda_bus *bus, struct snd_card *card, -- cgit v1.2.3 From 17e0c4cbb748fca764ee184c50b60b3a7b0e0dc7 Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Mon, 14 Feb 2022 11:14:03 +0100 Subject: ALSA: hda: Update and expose codec register procedures With few changes, snd_hda_codec_register() and its unregister-counterpart can be re-used by ASoC drivers. While at it, provide kernel doc for the exposed functions. Due to ALSA-device vs ASoC-component organization differences, new 'snddev_managed' argument is specified allowing for better control over codec registration process. Signed-off-by: Cezary Rojewski Link: https://lore.kernel.org/r/20220214101404.4074026-4-cezary.rojewski@intel.com Signed-off-by: Takashi Iwai --- include/sound/hda_codec.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/hda_codec.h b/include/sound/hda_codec.h index 5e3cbcca42f0..f74abc13414f 100644 --- a/include/sound/hda_codec.h +++ b/include/sound/hda_codec.h @@ -312,9 +312,12 @@ snd_hda_codec_device_init(struct hda_bus *bus, unsigned int codec_addr, int snd_hda_codec_new(struct hda_bus *bus, struct snd_card *card, unsigned int codec_addr, struct hda_codec **codecp); int snd_hda_codec_device_new(struct hda_bus *bus, struct snd_card *card, - unsigned int codec_addr, struct hda_codec *codec); + unsigned int codec_addr, struct hda_codec *codec, + bool snddev_managed); int snd_hda_codec_configure(struct hda_codec *codec); int snd_hda_codec_update_widgets(struct hda_codec *codec); +void snd_hda_codec_register(struct hda_codec *codec); +void snd_hda_codec_unregister(struct hda_codec *codec); /* * low level functions -- cgit v1.2.3 From bb682f7a91af08f1fdb669d3911978d7166a65d1 Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Mon, 14 Feb 2022 11:14:04 +0100 Subject: ALSA: hda: Expose codec cleanup and power-save functions With few changes, snd_hda_codec_set_power_save() and snd_hda_codec_cleanup_for_unbind() can be re-used by ASoC drivers. While at it, provide kernel doc for the exposed functions. Signed-off-by: Cezary Rojewski Link: https://lore.kernel.org/r/20220214101404.4074026-5-cezary.rojewski@intel.com Signed-off-by: Takashi Iwai --- include/sound/hda_codec.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/sound/hda_codec.h b/include/sound/hda_codec.h index f74abc13414f..77426ff58338 100644 --- a/include/sound/hda_codec.h +++ b/include/sound/hda_codec.h @@ -318,6 +318,7 @@ int snd_hda_codec_configure(struct hda_codec *codec); int snd_hda_codec_update_widgets(struct hda_codec *codec); void snd_hda_codec_register(struct hda_codec *codec); void snd_hda_codec_unregister(struct hda_codec *codec); +void snd_hda_codec_cleanup_for_unbind(struct hda_codec *codec); /* * low level functions @@ -496,9 +497,11 @@ int hda_call_check_power_status(struct hda_codec *codec, hda_nid_t nid) #define snd_hda_power_down(codec) snd_hdac_power_down(&(codec)->core) #define snd_hda_power_down_pm(codec) snd_hdac_power_down_pm(&(codec)->core) #ifdef CONFIG_PM +void snd_hda_codec_set_power_save(struct hda_codec *codec, int delay); void snd_hda_set_power_save(struct hda_bus *bus, int delay); void snd_hda_update_power_acct(struct hda_codec *codec); #else +static inline void snd_hda_codec_set_power_save(struct hda_codec *codec, int delay) {} static inline void snd_hda_set_power_save(struct hda_bus *bus, int delay) {} #endif -- cgit v1.2.3 From 509853f9e1e7b1490dc79f735a5dbafc9298f40d Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 11 Feb 2022 19:14:54 +0100 Subject: genirq: Provide generic_handle_irq_safe() Provide generic_handle_irq_safe() which can used from any context. Suggested-by: Thomas Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Reviewed-by: Hans de Goede Reviewed-by: Oleksandr Natalenko Reviewed-by: Wolfram Sang Link: https://lore.kernel.org/r/20220211181500.1856198-2-bigeasy@linutronix.de --- include/linux/irqdesc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 93d270ca0c56..a77584593f7d 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -160,6 +160,7 @@ static inline void generic_handle_irq_desc(struct irq_desc *desc) int handle_irq_desc(struct irq_desc *desc); int generic_handle_irq(unsigned int irq); +int generic_handle_irq_safe(unsigned int irq); #ifdef CONFIG_IRQ_DOMAIN /* -- cgit v1.2.3 From 05976c5f3bff8f8b5230da4b39f7cd6dfba9943e Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Thu, 17 Feb 2022 13:12:31 +0000 Subject: firmware: arm_scmi: Support optional system wide atomic-threshold-us An SCMI agent can be configured system-wide with a well-defined atomic threshold: only SCMI synchronous command whose latency has been advertised by the SCMI platform to be lower or equal to this configured threshold will be considered for atomic operations, when requested and if supported by the underlying transport at all. Link: https://lore.kernel.org/r/20220217131234.50328-6-cristian.marussi@arm.com Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 9f895cb81818..fdf6bd83cc59 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -619,6 +619,8 @@ struct scmi_notify_ops { * be interested to know if they can assume SCMI * command transactions associated to this handle will * never sleep and act accordingly. + * An optional atomic threshold value could be returned + * where configured. * @notify_ops: pointer to set of notifications related operations */ struct scmi_handle { @@ -629,7 +631,8 @@ struct scmi_handle { (*devm_protocol_get)(struct scmi_device *sdev, u8 proto, struct scmi_protocol_handle **ph); void (*devm_protocol_put)(struct scmi_device *sdev, u8 proto); - bool (*is_transport_atomic)(const struct scmi_handle *handle); + bool (*is_transport_atomic)(const struct scmi_handle *handle, + unsigned int *atomic_threshold); const struct scmi_notify_ops *notify_ops; }; -- cgit v1.2.3 From b7bd36f2e9430a58aefdc326f8e6653e9b000243 Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Thu, 17 Feb 2022 13:12:32 +0000 Subject: firmware: arm_scmi: Add atomic support to clock protocol Introduce new _atomic variant for SCMI clock protocol operations related to enable disable operations: when an atomic operation is required the xfer poll_completion flag is set for that transaction. Link: https://lore.kernel.org/r/20220217131234.50328-7-cristian.marussi@arm.com Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index fdf6bd83cc59..306e576835f8 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -82,6 +82,9 @@ struct scmi_clk_proto_ops { u64 rate); int (*enable)(const struct scmi_protocol_handle *ph, u32 clk_id); int (*disable)(const struct scmi_protocol_handle *ph, u32 clk_id); + int (*enable_atomic)(const struct scmi_protocol_handle *ph, u32 clk_id); + int (*disable_atomic)(const struct scmi_protocol_handle *ph, + u32 clk_id); }; /** -- cgit v1.2.3 From 18f295b758b227857133f680a397a42e83c62f3f Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Thu, 17 Feb 2022 13:12:33 +0000 Subject: firmware: arm_scmi: Add support for clock_enable_latency An SCMI platform can optionally advertise an enable latency typically associated with a specific clock resource: add support for parsing such optional message field and export such information in the usual publicly accessible clock descriptor. Link: https://lore.kernel.org/r/20220217131234.50328-8-cristian.marussi@arm.com Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 306e576835f8..b87551f41f9f 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -42,6 +42,7 @@ struct scmi_revision_info { struct scmi_clock_info { char name[SCMI_MAX_STR_SIZE]; + unsigned int enable_latency; bool rate_discrete; union { struct { -- cgit v1.2.3 From 0c51e12e218f20b7d976158fdc18019627326f7a Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sat, 19 Feb 2022 17:45:19 +0200 Subject: ipv4: Invalidate neighbour for broadcast address upon address addition In case user space sends a packet destined to a broadcast address when a matching broadcast route is not configured, the kernel will create a unicast neighbour entry that will never be resolved [1]. When the broadcast route is configured, the unicast neighbour entry will not be invalidated and continue to linger, resulting in packets being dropped. Solve this by invalidating unresolved neighbour entries for broadcast addresses after routes for these addresses are internally configured by the kernel. This allows the kernel to create a broadcast neighbour entry following the next route lookup. Another possible solution that is more generic but also more complex is to have the ARP code register a listener to the FIB notification chain and invalidate matching neighbour entries upon the addition of broadcast routes. It is also possible to wave off the issue as a user space problem, but it seems a bit excessive to expect user space to be that intimately familiar with the inner workings of the FIB/neighbour kernel code. [1] https://lore.kernel.org/netdev/55a04a8f-56f3-f73c-2aea-2195923f09d1@huawei.com/ Reported-by: Wang Hai Signed-off-by: Ido Schimmel Tested-by: Wang Hai Signed-off-by: David S. Miller --- include/net/arp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/arp.h b/include/net/arp.h index 031374ac2f22..d7ef4ec71dfe 100644 --- a/include/net/arp.h +++ b/include/net/arp.h @@ -65,6 +65,7 @@ void arp_send(int type, int ptype, __be32 dest_ip, const unsigned char *src_hw, const unsigned char *th); int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir); void arp_ifdown(struct net_device *dev); +int arp_invalidate(struct net_device *dev, __be32 ip, bool force); struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, -- cgit v1.2.3 From 696c65444120cfe98ae704e86a59df8666fabf1d Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Mon, 21 Feb 2022 13:54:53 +0800 Subject: ipv6: separate ndisc_ns_create() from ndisc_send_ns() This patch separate NS message allocation steps from ndisc_send_ns(), so it could be used in other places, like bonding, to allocate and send IPv6 NS message. Also export ndisc_send_skb() and ndisc_ns_create() for later bonding usage. Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- include/net/ndisc.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 53cb8de0e589..aac3a42de432 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -447,10 +447,15 @@ void ndisc_cleanup(void); int ndisc_rcv(struct sk_buff *skb); +struct sk_buff *ndisc_ns_create(struct net_device *dev, const struct in6_addr *solicit, + const struct in6_addr *saddr, u64 nonce); void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, const struct in6_addr *daddr, const struct in6_addr *saddr, u64 nonce); +void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr, + const struct in6_addr *saddr); + void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr); void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr, -- cgit v1.2.3 From 841e95641e4cb695586b036f330d6d272fcd7173 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Mon, 21 Feb 2022 13:54:55 +0800 Subject: bonding: add extra field for bond_opt_value Adding an extra storage field for bond_opt_value so we can set large bytes of data for bonding options in future, e.g. IPv6 address. Define a new call bond_opt_initextra(). Also change the checking order of __bond_opt_init() and check values first. Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- include/net/bond_options.h | 27 ++++++++++++++++++--------- 1 file changed, 18 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/bond_options.h b/include/net/bond_options.h index dd75c071f67e..286b29c6c451 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -71,14 +71,18 @@ enum { /* This structure is used for storing option values and for passing option * values when changing an option. The logic when used as an arg is as follows: - * - if string != NULL -> parse it, if the opt is RAW type then return it, else - * return the parse result - * - if string == NULL -> parse value + * - if value != ULLONG_MAX -> parse value + * - if string != NULL -> parse string + * - if the opt is RAW data and length less than maxlen, + * copy the data to extra storage */ + +#define BOND_OPT_EXTRA_MAXLEN 16 struct bond_opt_value { char *string; u64 value; u32 flags; + char extra[BOND_OPT_EXTRA_MAXLEN]; }; struct bonding; @@ -118,17 +122,22 @@ const struct bond_opt_value *bond_opt_get_val(unsigned int option, u64 val); * When value is ULLONG_MAX then string will be used. */ static inline void __bond_opt_init(struct bond_opt_value *optval, - char *string, u64 value) + char *string, u64 value, + void *extra, size_t extra_len) { memset(optval, 0, sizeof(*optval)); optval->value = ULLONG_MAX; - if (value == ULLONG_MAX) - optval->string = string; - else + if (value != ULLONG_MAX) optval->value = value; + else if (string) + optval->string = string; + else if (extra_len <= BOND_OPT_EXTRA_MAXLEN) + memcpy(optval->extra, extra, extra_len); } -#define bond_opt_initval(optval, value) __bond_opt_init(optval, NULL, value) -#define bond_opt_initstr(optval, str) __bond_opt_init(optval, str, ULLONG_MAX) +#define bond_opt_initval(optval, value) __bond_opt_init(optval, NULL, value, NULL, 0) +#define bond_opt_initstr(optval, str) __bond_opt_init(optval, str, ULLONG_MAX, NULL, 0) +#define bond_opt_initextra(optval, extra, extra_len) \ + __bond_opt_init(optval, NULL, ULLONG_MAX, extra, extra_len) void bond_option_arp_ip_targets_clear(struct bonding *bond); -- cgit v1.2.3 From 4e24be018eb9dbcefa4b01c07e298b147dc1a4d7 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Mon, 21 Feb 2022 13:54:56 +0800 Subject: bonding: add new parameter ns_targets Add a new bonding parameter ns_targets to store IPv6 address. Add required bond_ns_send/rcv functions first before adding IPv6 address option setting. Add two functions bond_send/rcv_validate so we can send/recv ARP and NS at the same time. Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- include/net/bonding.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bonding.h b/include/net/bonding.h index 7dead855a72d..f3b986f6b6e4 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -29,8 +29,11 @@ #include #include #include +#include +#include #define BOND_MAX_ARP_TARGETS 16 +#define BOND_MAX_NS_TARGETS BOND_MAX_ARP_TARGETS #define BOND_DEFAULT_MIIMON 100 @@ -146,6 +149,7 @@ struct bond_params { struct reciprocal_value reciprocal_packets_per_slave; u16 ad_actor_sys_prio; u16 ad_user_port_key; + struct in6_addr ns_targets[BOND_MAX_NS_TARGETS]; /* 2 bytes of padding : see ether_addr_equal_64bits() */ u8 ad_actor_system[ETH_ALEN + 2]; @@ -628,7 +632,7 @@ struct bond_net { struct class_attribute class_attr_bonding_masters; }; -int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave); +int bond_rcv_validate(const struct sk_buff *skb, struct bonding *bond, struct slave *slave); netdev_tx_t bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev); int bond_create(struct net *net, const char *name); int bond_create_sysfs(struct bond_net *net); @@ -735,6 +739,19 @@ static inline int bond_get_targets_ip(__be32 *targets, __be32 ip) return -1; } +static inline int bond_get_targets_ip6(struct in6_addr *targets, struct in6_addr *ip) +{ + int i; + + for (i = 0; i < BOND_MAX_NS_TARGETS; i++) + if (ipv6_addr_equal(&targets[i], ip)) + return i; + else if (ipv6_addr_any(&targets[i])) + break; + + return -1; +} + /* exported from bond_main.c */ extern unsigned int bond_net_id; -- cgit v1.2.3 From 129e3c1bab24d27d0fa6e505a472345a92d7a2b0 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Mon, 21 Feb 2022 13:54:57 +0800 Subject: bonding: add new option ns_ip6_target This patch add a new bonding option ns_ip6_target, which correspond to the arp_ip_target. With this we set IPv6 targets and send IPv6 NS request to determine the health of the link. For other related options like the validation, we still use arp_validate, and will change to ns_validate later. Note: the sysfs configuration support was removed based on https://lore.kernel.org/netdev/8863.1645071997@famine Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- include/net/bond_options.h | 4 ++++ include/net/bonding.h | 7 +++++++ include/uapi/linux/if_link.h | 1 + 3 files changed, 12 insertions(+) (limited to 'include') diff --git a/include/net/bond_options.h b/include/net/bond_options.h index 286b29c6c451..61b49063791c 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -66,6 +66,7 @@ enum { BOND_OPT_PEER_NOTIF_DELAY, BOND_OPT_LACP_ACTIVE, BOND_OPT_MISSED_MAX, + BOND_OPT_NS_TARGETS, BOND_OPT_LAST }; @@ -140,5 +141,8 @@ static inline void __bond_opt_init(struct bond_opt_value *optval, __bond_opt_init(optval, NULL, ULLONG_MAX, extra, extra_len) void bond_option_arp_ip_targets_clear(struct bonding *bond); +#if IS_ENABLED(CONFIG_IPV6) +void bond_option_ns_ip6_targets_clear(struct bonding *bond); +#endif #endif /* _NET_BOND_OPTIONS_H */ diff --git a/include/net/bonding.h b/include/net/bonding.h index f3b986f6b6e4..d0dfe727e0b1 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -503,6 +503,13 @@ static inline int bond_is_ip_target_ok(__be32 addr) return !ipv4_is_lbcast(addr) && !ipv4_is_zeronet(addr); } +static inline int bond_is_ip6_target_ok(struct in6_addr *addr) +{ + return !ipv6_addr_any(addr) && + !ipv6_addr_loopback(addr) && + !ipv6_addr_is_multicast(addr); +} + /* Get the oldest arp which we've received on this slave for bond's * arp_targets. */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 6218f93f5c1a..e1ba2d51b717 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -860,6 +860,7 @@ enum { IFLA_BOND_PEER_NOTIF_DELAY, IFLA_BOND_AD_LACP_ACTIVE, IFLA_BOND_MISSED_MAX, + IFLA_BOND_NS_IP6_TARGET, __IFLA_BOND_MAX, }; -- cgit v1.2.3 From 9c07f57869e90140080cfc282cc628d123e27704 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 2 Feb 2022 13:30:03 +0100 Subject: random: simplify entropy debiting Our pool is 256 bits, and we only ever use all of it or don't use it at all, which is decided by whether or not it has at least 128 bits in it. So we can drastically simplify the accounting and cmpxchg loop to do exactly this. While we're at it, we move the minimum bit size into a constant so it can be shared between the two places where it matters. The reason we want any of this is for the case in which an attacker has compromised the current state, and then bruteforces small amounts of entropy added to it. By demanding a particular minimum amount of entropy be present before reseeding, we make that bruteforcing difficult. Note that this rationale no longer includes anything about /dev/random blocking at the right moment, since /dev/random no longer blocks (except for at ~boot), but rather uses the crng. In a former life, /dev/random was different and therefore required a more nuanced account(), but this is no longer. Behaviorally, nothing changes here. This is just a simplification of the code. Cc: Theodore Ts'o Cc: Greg Kroah-Hartman Reviewed-by: Eric Biggers Reviewed-by: Dominik Brodowski Signed-off-by: Jason A. Donenfeld --- include/trace/events/random.h | 30 ++++++------------------------ 1 file changed, 6 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/trace/events/random.h b/include/trace/events/random.h index a2d9aa16a5d7..ad149aeaf42c 100644 --- a/include/trace/events/random.h +++ b/include/trace/events/random.h @@ -79,22 +79,6 @@ TRACE_EVENT(credit_entropy_bits, __entry->bits, __entry->entropy_count, (void *)__entry->IP) ); -TRACE_EVENT(debit_entropy, - TP_PROTO(int debit_bits), - - TP_ARGS( debit_bits), - - TP_STRUCT__entry( - __field( int, debit_bits ) - ), - - TP_fast_assign( - __entry->debit_bits = debit_bits; - ), - - TP_printk("input pool: debit_bits %d", __entry->debit_bits) -); - TRACE_EVENT(add_input_randomness, TP_PROTO(int input_bits), @@ -161,31 +145,29 @@ DEFINE_EVENT(random__get_random_bytes, get_random_bytes_arch, ); DECLARE_EVENT_CLASS(random__extract_entropy, - TP_PROTO(int nbytes, int entropy_count, unsigned long IP), + TP_PROTO(int nbytes, int entropy_count), - TP_ARGS(nbytes, entropy_count, IP), + TP_ARGS(nbytes, entropy_count), TP_STRUCT__entry( __field( int, nbytes ) __field( int, entropy_count ) - __field(unsigned long, IP ) ), TP_fast_assign( __entry->nbytes = nbytes; __entry->entropy_count = entropy_count; - __entry->IP = IP; ), - TP_printk("input pool: nbytes %d entropy_count %d caller %pS", - __entry->nbytes, __entry->entropy_count, (void *)__entry->IP) + TP_printk("input pool: nbytes %d entropy_count %d", + __entry->nbytes, __entry->entropy_count) ); DEFINE_EVENT(random__extract_entropy, extract_entropy, - TP_PROTO(int nbytes, int entropy_count, unsigned long IP), + TP_PROTO(int nbytes, int entropy_count), - TP_ARGS(nbytes, entropy_count, IP) + TP_ARGS(nbytes, entropy_count) ); TRACE_EVENT(urandom_read, -- cgit v1.2.3 From 512865d83fd9685a4d5aab26f898737b57d3187e Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 21 Feb 2022 15:35:22 +0000 Subject: KVM: arm64: Bump guest PSCI version to 1.1 Expose PSCI version v1.1 to the guest by default. The only difference for now is that an updated version number is reported by PSCI_VERSION. Cc: Marc Zyngier Cc: James Morse Cc: Alexandru Elisei Cc: Suzuki K Poulose Signed-off-by: Will Deacon Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220221153524.15397-2-will@kernel.org --- include/kvm/arm_psci.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h index 5b58bd2fe088..4a1003323a0c 100644 --- a/include/kvm/arm_psci.h +++ b/include/kvm/arm_psci.h @@ -13,8 +13,9 @@ #define KVM_ARM_PSCI_0_1 PSCI_VERSION(0, 1) #define KVM_ARM_PSCI_0_2 PSCI_VERSION(0, 2) #define KVM_ARM_PSCI_1_0 PSCI_VERSION(1, 0) +#define KVM_ARM_PSCI_1_1 PSCI_VERSION(1, 1) -#define KVM_ARM_PSCI_LATEST KVM_ARM_PSCI_1_0 +#define KVM_ARM_PSCI_LATEST KVM_ARM_PSCI_1_1 /* * We need the KVM pointer independently from the vcpu as we can call -- cgit v1.2.3 From d43583b890e7cb0078d13d056753a56602b92406 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 21 Feb 2022 15:35:23 +0000 Subject: KVM: arm64: Expose PSCI SYSTEM_RESET2 call to the guest PSCI v1.1 introduces the optional SYSTEM_RESET2 call, which allows the caller to provide a vendor-specific "reset type" and "cookie" to request a particular form of reset or shutdown. Expose this call to the guest and handle it in the same way as PSCI SYSTEM_RESET, along with some basic range checking on the type argument. Cc: Marc Zyngier Cc: James Morse Cc: Alexandru Elisei Cc: Suzuki K Poulose Signed-off-by: Will Deacon Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220221153524.15397-3-will@kernel.org --- include/uapi/linux/psci.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/psci.h b/include/uapi/linux/psci.h index 2fcad1dd0b0e..2bf93c0d6354 100644 --- a/include/uapi/linux/psci.h +++ b/include/uapi/linux/psci.h @@ -82,6 +82,10 @@ #define PSCI_0_2_TOS_UP_NO_MIGRATE 1 #define PSCI_0_2_TOS_MP 2 +/* PSCI v1.1 reset type encoding for SYSTEM_RESET2 */ +#define PSCI_1_1_RESET_TYPE_SYSTEM_WARM_RESET 0 +#define PSCI_1_1_RESET_TYPE_VENDOR_START 0x80000000U + /* PSCI version decoding (independent of PSCI version) */ #define PSCI_VERSION_MAJOR_SHIFT 16 #define PSCI_VERSION_MINOR_MASK \ -- cgit v1.2.3 From 190fae468592bc2f0efc8b928920f8f712b5831e Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Sun, 20 Feb 2022 15:15:15 +0000 Subject: nvmem: core: Remove unused devm_nvmem_unregister() There are no users and seems no will come of the devm_nvmem_unregister(). Remove the function and remove the unused devm_nvmem_match() along with it. Signed-off-by: Andy Shevchenko Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20220220151527.17216-2-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-provider.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 98efb7b5660d..99c01c43d7a8 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -133,8 +133,6 @@ void nvmem_unregister(struct nvmem_device *nvmem); struct nvmem_device *devm_nvmem_register(struct device *dev, const struct nvmem_config *cfg); -int devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem); - void nvmem_add_cell_table(struct nvmem_cell_table *table); void nvmem_del_cell_table(struct nvmem_cell_table *table); @@ -153,12 +151,6 @@ devm_nvmem_register(struct device *dev, const struct nvmem_config *c) return nvmem_register(c); } -static inline int -devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem) -{ - return -EOPNOTSUPP; -} - static inline void nvmem_add_cell_table(struct nvmem_cell_table *table) {} static inline void nvmem_del_cell_table(struct nvmem_cell_table *table) {} -- cgit v1.2.3 From a603ca60cebff8589882427a67f870ed946b3fc8 Mon Sep 17 00:00:00 2001 From: Zev Weiss Date: Thu, 10 Feb 2022 16:42:03 -0800 Subject: serial: 8250_aspeed_vuart: add PORT_ASPEED_VUART port type Commit 54da3e381c2b ("serial: 8250_aspeed_vuart: use UPF_IOREMAP to set up register mapping") fixed a bug that had, as a side-effect, prevented the 8250_aspeed_vuart driver from enabling the VUART's FIFOs. However, fixing that (and hence enabling the FIFOs) has in turn revealed what appears to be a hardware bug in the ASPEED VUART in which the host-side THRE bit doesn't get if the BMC-side receive FIFO trigger level is set to anything but one byte. This causes problems for polled-mode writes from the host -- for example, Linux kernel console writes proceed at a glacial pace (less than 100 bytes per second) because the write path waits for a 10ms timeout to expire after every character instead of being able to continue on to the next character upon seeing THRE asserted. (GRUB behaves similarly.) As a workaround, introduce a new port type for the ASPEED VUART that's identical to PORT_16550A as it had previously been using, but with UART_FCR_R_TRIG_00 instead to set the receive FIFO trigger level to one byte, which (experimentally) seems to avoid the problematic THRE behavior. Fixes: 54da3e381c2b ("serial: 8250_aspeed_vuart: use UPF_IOREMAP to set up register mapping") Tested-by: Konstantin Aladyshev Reviewed-by: Andy Shevchenko Signed-off-by: Zev Weiss Link: https://lore.kernel.org/r/20220211004203.14915-1-zev@bewilderbeest.net Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/serial_core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index c4042dcfdc0c..8885e69178bd 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -68,6 +68,9 @@ /* NVIDIA Tegra Combined UART */ #define PORT_TEGRA_TCU 41 +/* ASPEED AST2x00 virtual UART */ +#define PORT_ASPEED_VUART 42 + /* Intel EG20 */ #define PORT_PCH_8LINE 44 #define PORT_PCH_2LINE 45 -- cgit v1.2.3 From a1a5cfe70cd29a59a9a85290dfe95ed1c8df1193 Mon Sep 17 00:00:00 2001 From: Cosmin Tanislav Date: Mon, 14 Feb 2022 09:38:06 +0200 Subject: iio: introduce mag_referenced Some accelerometers that support activity and inactivity events also support a referenced mode, in which the gravitational acceleration is taken as a point of reference before comparing the acceleration to the specified activity and inactivity magnitude. For example, in the case of the ADXL367, for activity detection, the formula is: abs(acceleration - reference) > magnitude Add a new event type that makes this behavior clear. Signed-off-by: Cosmin Tanislav Link: https://lore.kernel.org/r/20220214073810.781016-2-cosmin.tanislav@analog.com Signed-off-by: Jonathan Cameron --- include/uapi/linux/iio/types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h index 48c13147c0a8..472cead10d8d 100644 --- a/include/uapi/linux/iio/types.h +++ b/include/uapi/linux/iio/types.h @@ -104,6 +104,7 @@ enum iio_event_type { IIO_EV_TYPE_THRESH_ADAPTIVE, IIO_EV_TYPE_MAG_ADAPTIVE, IIO_EV_TYPE_CHANGE, + IIO_EV_TYPE_MAG_REFERENCED, }; enum iio_event_direction { -- cgit v1.2.3 From 04ec96b768c9dd43946b047c3da60dcc66431370 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 9 Feb 2022 14:43:25 +0100 Subject: random: make more consistent use of integer types We've been using a flurry of int, unsigned int, size_t, and ssize_t. Let's unify all of this into size_t where it makes sense, as it does in most places, and leave ssize_t for return values with possible errors. In addition, keeping with the convention of other functions in this file, functions that are dealing with raw bytes now take void * consistently instead of a mix of that and u8 *, because much of the time we're actually passing some other structure that is then interpreted as bytes by the function. We also take the opportunity to fix the outdated and incorrect comment in get_random_bytes_arch(). Cc: Theodore Ts'o Reviewed-by: Dominik Brodowski Reviewed-by: Jann Horn Reviewed-by: Eric Biggers Signed-off-by: Jason A. Donenfeld --- include/linux/hw_random.h | 2 +- include/linux/random.h | 10 +++--- include/trace/events/random.h | 79 +++++++++++++++++++++---------------------- 3 files changed, 44 insertions(+), 47 deletions(-) (limited to 'include') diff --git a/include/linux/hw_random.h b/include/linux/hw_random.h index 8e6dd908da21..1a9fc38f8938 100644 --- a/include/linux/hw_random.h +++ b/include/linux/hw_random.h @@ -61,6 +61,6 @@ extern int devm_hwrng_register(struct device *dev, struct hwrng *rng); extern void hwrng_unregister(struct hwrng *rng); extern void devm_hwrng_unregister(struct device *dve, struct hwrng *rng); /** Feed random bits into the pool. */ -extern void add_hwgenerator_randomness(const char *buffer, size_t count, size_t entropy); +extern void add_hwgenerator_randomness(const void *buffer, size_t count, size_t entropy); #endif /* LINUX_HWRANDOM_H_ */ diff --git a/include/linux/random.h b/include/linux/random.h index c45b2693e51f..e92efb39779c 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -20,8 +20,8 @@ struct random_ready_callback { struct module *owner; }; -extern void add_device_randomness(const void *, unsigned int); -extern void add_bootloader_randomness(const void *, unsigned int); +extern void add_device_randomness(const void *, size_t); +extern void add_bootloader_randomness(const void *, size_t); #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) static inline void add_latent_entropy(void) @@ -37,13 +37,13 @@ extern void add_input_randomness(unsigned int type, unsigned int code, unsigned int value) __latent_entropy; extern void add_interrupt_randomness(int irq) __latent_entropy; -extern void get_random_bytes(void *buf, int nbytes); +extern void get_random_bytes(void *buf, size_t nbytes); extern int wait_for_random_bytes(void); extern int __init rand_initialize(void); extern bool rng_is_initialized(void); extern int add_random_ready_callback(struct random_ready_callback *rdy); extern void del_random_ready_callback(struct random_ready_callback *rdy); -extern int __must_check get_random_bytes_arch(void *buf, int nbytes); +extern size_t __must_check get_random_bytes_arch(void *buf, size_t nbytes); #ifndef MODULE extern const struct file_operations random_fops, urandom_fops; @@ -87,7 +87,7 @@ static inline unsigned long get_random_canary(void) /* Calls wait_for_random_bytes() and then calls get_random_bytes(buf, nbytes). * Returns the result of the call to wait_for_random_bytes. */ -static inline int get_random_bytes_wait(void *buf, int nbytes) +static inline int get_random_bytes_wait(void *buf, size_t nbytes) { int ret = wait_for_random_bytes(); get_random_bytes(buf, nbytes); diff --git a/include/trace/events/random.h b/include/trace/events/random.h index ad149aeaf42c..0609a2810a12 100644 --- a/include/trace/events/random.h +++ b/include/trace/events/random.h @@ -9,13 +9,13 @@ #include TRACE_EVENT(add_device_randomness, - TP_PROTO(int bytes, unsigned long IP), + TP_PROTO(size_t bytes, unsigned long IP), TP_ARGS(bytes, IP), TP_STRUCT__entry( - __field( int, bytes ) - __field(unsigned long, IP ) + __field(size_t, bytes ) + __field(unsigned long, IP ) ), TP_fast_assign( @@ -23,18 +23,18 @@ TRACE_EVENT(add_device_randomness, __entry->IP = IP; ), - TP_printk("bytes %d caller %pS", + TP_printk("bytes %zu caller %pS", __entry->bytes, (void *)__entry->IP) ); DECLARE_EVENT_CLASS(random__mix_pool_bytes, - TP_PROTO(int bytes, unsigned long IP), + TP_PROTO(size_t bytes, unsigned long IP), TP_ARGS(bytes, IP), TP_STRUCT__entry( - __field( int, bytes ) - __field(unsigned long, IP ) + __field(size_t, bytes ) + __field(unsigned long, IP ) ), TP_fast_assign( @@ -42,12 +42,12 @@ DECLARE_EVENT_CLASS(random__mix_pool_bytes, __entry->IP = IP; ), - TP_printk("input pool: bytes %d caller %pS", + TP_printk("input pool: bytes %zu caller %pS", __entry->bytes, (void *)__entry->IP) ); DEFINE_EVENT(random__mix_pool_bytes, mix_pool_bytes, - TP_PROTO(int bytes, unsigned long IP), + TP_PROTO(size_t bytes, unsigned long IP), TP_ARGS(bytes, IP) ); @@ -59,13 +59,13 @@ DEFINE_EVENT(random__mix_pool_bytes, mix_pool_bytes_nolock, ); TRACE_EVENT(credit_entropy_bits, - TP_PROTO(int bits, int entropy_count, unsigned long IP), + TP_PROTO(size_t bits, size_t entropy_count, unsigned long IP), TP_ARGS(bits, entropy_count, IP), TP_STRUCT__entry( - __field( int, bits ) - __field( int, entropy_count ) + __field(size_t, bits ) + __field(size_t, entropy_count ) __field(unsigned long, IP ) ), @@ -75,34 +75,34 @@ TRACE_EVENT(credit_entropy_bits, __entry->IP = IP; ), - TP_printk("input pool: bits %d entropy_count %d caller %pS", + TP_printk("input pool: bits %zu entropy_count %zu caller %pS", __entry->bits, __entry->entropy_count, (void *)__entry->IP) ); TRACE_EVENT(add_input_randomness, - TP_PROTO(int input_bits), + TP_PROTO(size_t input_bits), TP_ARGS(input_bits), TP_STRUCT__entry( - __field( int, input_bits ) + __field(size_t, input_bits ) ), TP_fast_assign( __entry->input_bits = input_bits; ), - TP_printk("input_pool_bits %d", __entry->input_bits) + TP_printk("input_pool_bits %zu", __entry->input_bits) ); TRACE_EVENT(add_disk_randomness, - TP_PROTO(dev_t dev, int input_bits), + TP_PROTO(dev_t dev, size_t input_bits), TP_ARGS(dev, input_bits), TP_STRUCT__entry( - __field( dev_t, dev ) - __field( int, input_bits ) + __field(dev_t, dev ) + __field(size_t, input_bits ) ), TP_fast_assign( @@ -110,17 +110,17 @@ TRACE_EVENT(add_disk_randomness, __entry->input_bits = input_bits; ), - TP_printk("dev %d,%d input_pool_bits %d", MAJOR(__entry->dev), + TP_printk("dev %d,%d input_pool_bits %zu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->input_bits) ); DECLARE_EVENT_CLASS(random__get_random_bytes, - TP_PROTO(int nbytes, unsigned long IP), + TP_PROTO(size_t nbytes, unsigned long IP), TP_ARGS(nbytes, IP), TP_STRUCT__entry( - __field( int, nbytes ) + __field(size_t, nbytes ) __field(unsigned long, IP ) ), @@ -129,29 +129,29 @@ DECLARE_EVENT_CLASS(random__get_random_bytes, __entry->IP = IP; ), - TP_printk("nbytes %d caller %pS", __entry->nbytes, (void *)__entry->IP) + TP_printk("nbytes %zu caller %pS", __entry->nbytes, (void *)__entry->IP) ); DEFINE_EVENT(random__get_random_bytes, get_random_bytes, - TP_PROTO(int nbytes, unsigned long IP), + TP_PROTO(size_t nbytes, unsigned long IP), TP_ARGS(nbytes, IP) ); DEFINE_EVENT(random__get_random_bytes, get_random_bytes_arch, - TP_PROTO(int nbytes, unsigned long IP), + TP_PROTO(size_t nbytes, unsigned long IP), TP_ARGS(nbytes, IP) ); DECLARE_EVENT_CLASS(random__extract_entropy, - TP_PROTO(int nbytes, int entropy_count), + TP_PROTO(size_t nbytes, size_t entropy_count), TP_ARGS(nbytes, entropy_count), TP_STRUCT__entry( - __field( int, nbytes ) - __field( int, entropy_count ) + __field( size_t, nbytes ) + __field( size_t, entropy_count ) ), TP_fast_assign( @@ -159,37 +159,34 @@ DECLARE_EVENT_CLASS(random__extract_entropy, __entry->entropy_count = entropy_count; ), - TP_printk("input pool: nbytes %d entropy_count %d", + TP_printk("input pool: nbytes %zu entropy_count %zu", __entry->nbytes, __entry->entropy_count) ); DEFINE_EVENT(random__extract_entropy, extract_entropy, - TP_PROTO(int nbytes, int entropy_count), + TP_PROTO(size_t nbytes, size_t entropy_count), TP_ARGS(nbytes, entropy_count) ); TRACE_EVENT(urandom_read, - TP_PROTO(int got_bits, int pool_left, int input_left), + TP_PROTO(size_t nbytes, size_t entropy_count), - TP_ARGS(got_bits, pool_left, input_left), + TP_ARGS(nbytes, entropy_count), TP_STRUCT__entry( - __field( int, got_bits ) - __field( int, pool_left ) - __field( int, input_left ) + __field( size_t, nbytes ) + __field( size_t, entropy_count ) ), TP_fast_assign( - __entry->got_bits = got_bits; - __entry->pool_left = pool_left; - __entry->input_left = input_left; + __entry->nbytes = nbytes; + __entry->entropy_count = entropy_count; ), - TP_printk("got_bits %d nonblocking_pool_entropy_left %d " - "input_entropy_left %d", __entry->got_bits, - __entry->pool_left, __entry->input_left) + TP_printk("reading: nbytes %zu entropy_count %zu", + __entry->nbytes, __entry->entropy_count) ); TRACE_EVENT(prandom_u32, -- cgit v1.2.3 From 14c174633f349cb41ea90c2c0aaddac157012f74 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Thu, 10 Feb 2022 16:40:44 +0100 Subject: random: remove unused tracepoints These explicit tracepoints aren't really used and show sign of aging. It's work to keep these up to date, and before I attempted to keep them up to date, they weren't up to date, which indicates that they're not really used. These days there are better ways of introspecting anyway. Cc: Theodore Ts'o Reviewed-by: Dominik Brodowski Reviewed-by: Eric Biggers Signed-off-by: Jason A. Donenfeld --- include/trace/events/random.h | 212 ------------------------------------------ 1 file changed, 212 deletions(-) delete mode 100644 include/trace/events/random.h (limited to 'include') diff --git a/include/trace/events/random.h b/include/trace/events/random.h deleted file mode 100644 index 0609a2810a12..000000000000 --- a/include/trace/events/random.h +++ /dev/null @@ -1,212 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#undef TRACE_SYSTEM -#define TRACE_SYSTEM random - -#if !defined(_TRACE_RANDOM_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_RANDOM_H - -#include -#include - -TRACE_EVENT(add_device_randomness, - TP_PROTO(size_t bytes, unsigned long IP), - - TP_ARGS(bytes, IP), - - TP_STRUCT__entry( - __field(size_t, bytes ) - __field(unsigned long, IP ) - ), - - TP_fast_assign( - __entry->bytes = bytes; - __entry->IP = IP; - ), - - TP_printk("bytes %zu caller %pS", - __entry->bytes, (void *)__entry->IP) -); - -DECLARE_EVENT_CLASS(random__mix_pool_bytes, - TP_PROTO(size_t bytes, unsigned long IP), - - TP_ARGS(bytes, IP), - - TP_STRUCT__entry( - __field(size_t, bytes ) - __field(unsigned long, IP ) - ), - - TP_fast_assign( - __entry->bytes = bytes; - __entry->IP = IP; - ), - - TP_printk("input pool: bytes %zu caller %pS", - __entry->bytes, (void *)__entry->IP) -); - -DEFINE_EVENT(random__mix_pool_bytes, mix_pool_bytes, - TP_PROTO(size_t bytes, unsigned long IP), - - TP_ARGS(bytes, IP) -); - -DEFINE_EVENT(random__mix_pool_bytes, mix_pool_bytes_nolock, - TP_PROTO(int bytes, unsigned long IP), - - TP_ARGS(bytes, IP) -); - -TRACE_EVENT(credit_entropy_bits, - TP_PROTO(size_t bits, size_t entropy_count, unsigned long IP), - - TP_ARGS(bits, entropy_count, IP), - - TP_STRUCT__entry( - __field(size_t, bits ) - __field(size_t, entropy_count ) - __field(unsigned long, IP ) - ), - - TP_fast_assign( - __entry->bits = bits; - __entry->entropy_count = entropy_count; - __entry->IP = IP; - ), - - TP_printk("input pool: bits %zu entropy_count %zu caller %pS", - __entry->bits, __entry->entropy_count, (void *)__entry->IP) -); - -TRACE_EVENT(add_input_randomness, - TP_PROTO(size_t input_bits), - - TP_ARGS(input_bits), - - TP_STRUCT__entry( - __field(size_t, input_bits ) - ), - - TP_fast_assign( - __entry->input_bits = input_bits; - ), - - TP_printk("input_pool_bits %zu", __entry->input_bits) -); - -TRACE_EVENT(add_disk_randomness, - TP_PROTO(dev_t dev, size_t input_bits), - - TP_ARGS(dev, input_bits), - - TP_STRUCT__entry( - __field(dev_t, dev ) - __field(size_t, input_bits ) - ), - - TP_fast_assign( - __entry->dev = dev; - __entry->input_bits = input_bits; - ), - - TP_printk("dev %d,%d input_pool_bits %zu", MAJOR(__entry->dev), - MINOR(__entry->dev), __entry->input_bits) -); - -DECLARE_EVENT_CLASS(random__get_random_bytes, - TP_PROTO(size_t nbytes, unsigned long IP), - - TP_ARGS(nbytes, IP), - - TP_STRUCT__entry( - __field(size_t, nbytes ) - __field(unsigned long, IP ) - ), - - TP_fast_assign( - __entry->nbytes = nbytes; - __entry->IP = IP; - ), - - TP_printk("nbytes %zu caller %pS", __entry->nbytes, (void *)__entry->IP) -); - -DEFINE_EVENT(random__get_random_bytes, get_random_bytes, - TP_PROTO(size_t nbytes, unsigned long IP), - - TP_ARGS(nbytes, IP) -); - -DEFINE_EVENT(random__get_random_bytes, get_random_bytes_arch, - TP_PROTO(size_t nbytes, unsigned long IP), - - TP_ARGS(nbytes, IP) -); - -DECLARE_EVENT_CLASS(random__extract_entropy, - TP_PROTO(size_t nbytes, size_t entropy_count), - - TP_ARGS(nbytes, entropy_count), - - TP_STRUCT__entry( - __field( size_t, nbytes ) - __field( size_t, entropy_count ) - ), - - TP_fast_assign( - __entry->nbytes = nbytes; - __entry->entropy_count = entropy_count; - ), - - TP_printk("input pool: nbytes %zu entropy_count %zu", - __entry->nbytes, __entry->entropy_count) -); - - -DEFINE_EVENT(random__extract_entropy, extract_entropy, - TP_PROTO(size_t nbytes, size_t entropy_count), - - TP_ARGS(nbytes, entropy_count) -); - -TRACE_EVENT(urandom_read, - TP_PROTO(size_t nbytes, size_t entropy_count), - - TP_ARGS(nbytes, entropy_count), - - TP_STRUCT__entry( - __field( size_t, nbytes ) - __field( size_t, entropy_count ) - ), - - TP_fast_assign( - __entry->nbytes = nbytes; - __entry->entropy_count = entropy_count; - ), - - TP_printk("reading: nbytes %zu entropy_count %zu", - __entry->nbytes, __entry->entropy_count) -); - -TRACE_EVENT(prandom_u32, - - TP_PROTO(unsigned int ret), - - TP_ARGS(ret), - - TP_STRUCT__entry( - __field( unsigned int, ret) - ), - - TP_fast_assign( - __entry->ret = ret; - ), - - TP_printk("ret=%u" , __entry->ret) -); - -#endif /* _TRACE_RANDOM_H */ - -/* This part must be outside protection */ -#include -- cgit v1.2.3 From 6071a6c0fba2d747742cadcbb3ba26ed756ed73b Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Fri, 11 Feb 2022 12:28:33 +0100 Subject: random: remove useless header comment This really adds nothing at all useful. Cc: Theodore Ts'o Reviewed-by: Dominik Brodowski Reviewed-by: Eric Biggers Signed-off-by: Jason A. Donenfeld --- include/linux/random.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index e92efb39779c..37e1e8c43d7e 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -1,9 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* - * include/linux/random.h - * - * Include file for the random number generator. - */ + #ifndef _LINUX_RANDOM_H #define _LINUX_RANDOM_H -- cgit v1.2.3 From b777c38239fec5a528e59f55b379e31b1a187524 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Sun, 13 Feb 2022 16:17:01 +0100 Subject: random: pull add_hwgenerator_randomness() declaration into random.h add_hwgenerator_randomness() is a function implemented and documented inside of random.c. It is the way that hardware RNGs push data into it. Therefore, it should be declared in random.h. Otherwise sparse complains with: random.c:1137:6: warning: symbol 'add_hwgenerator_randomness' was not declared. Should it be static? The alternative would be to include hw_random.h into random.c, but that wouldn't really be good for anything except slowing down compile time. Cc: Matt Mackall Cc: Theodore Ts'o Acked-by: Herbert Xu Reviewed-by: Eric Biggers Reviewed-by: Dominik Brodowski Signed-off-by: Jason A. Donenfeld --- include/linux/hw_random.h | 2 -- include/linux/random.h | 2 ++ 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/hw_random.h b/include/linux/hw_random.h index 1a9fc38f8938..aa1d4da03538 100644 --- a/include/linux/hw_random.h +++ b/include/linux/hw_random.h @@ -60,7 +60,5 @@ extern int devm_hwrng_register(struct device *dev, struct hwrng *rng); /** Unregister a Hardware Random Number Generator driver. */ extern void hwrng_unregister(struct hwrng *rng); extern void devm_hwrng_unregister(struct device *dve, struct hwrng *rng); -/** Feed random bits into the pool. */ -extern void add_hwgenerator_randomness(const void *buffer, size_t count, size_t entropy); #endif /* LINUX_HWRANDOM_H_ */ diff --git a/include/linux/random.h b/include/linux/random.h index 37e1e8c43d7e..d7354de9351e 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -32,6 +32,8 @@ static inline void add_latent_entropy(void) {} extern void add_input_randomness(unsigned int type, unsigned int code, unsigned int value) __latent_entropy; extern void add_interrupt_randomness(int irq) __latent_entropy; +extern void add_hwgenerator_randomness(const void *buffer, size_t count, + size_t entropy); extern void get_random_bytes(void *buf, size_t nbytes); extern int wait_for_random_bytes(void); -- cgit v1.2.3 From 3191dd5a1179ef0fad5a050a1702ae98b6251e8f Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Sun, 13 Feb 2022 22:48:04 +0100 Subject: random: clear fast pool, crng, and batches in cpuhp bring up For the irq randomness fast pool, rather than having to use expensive atomics, which were visibly the most expensive thing in the entire irq handler, simply take care of the extreme edge case of resetting count to zero in the cpuhp online handler, just after workqueues have been reenabled. This simplifies the code a bit and lets us use vanilla variables rather than atomics, and performance should be improved. As well, very early on when the CPU comes up, while interrupts are still disabled, we clear out the per-cpu crng and its batches, so that it always starts with fresh randomness. Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Theodore Ts'o Cc: Sultan Alsawaf Cc: Dominik Brodowski Acked-by: Sebastian Andrzej Siewior Signed-off-by: Jason A. Donenfeld --- include/linux/cpuhotplug.h | 2 ++ include/linux/random.h | 5 +++++ 2 files changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 411a428ace4d..481e565cc5c4 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -100,6 +100,7 @@ enum cpuhp_state { CPUHP_AP_ARM_CACHE_B15_RAC_DEAD, CPUHP_PADATA_DEAD, CPUHP_AP_DTPM_CPU_DEAD, + CPUHP_RANDOM_PREPARE, CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, @@ -240,6 +241,7 @@ enum cpuhp_state { CPUHP_AP_PERF_CSKY_ONLINE, CPUHP_AP_WATCHDOG_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, + CPUHP_AP_RANDOM_ONLINE, CPUHP_AP_RCUTREE_ONLINE, CPUHP_AP_BASE_CACHEINFO_ONLINE, CPUHP_AP_ONLINE_DYN, diff --git a/include/linux/random.h b/include/linux/random.h index d7354de9351e..6148b8d1ccf3 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -156,4 +156,9 @@ static inline bool __init arch_get_random_long_early(unsigned long *v) } #endif +#ifdef CONFIG_SMP +extern int random_prepare_cpu(unsigned int cpu); +extern int random_online_cpu(unsigned int cpu); +#endif + #endif /* _LINUX_RANDOM_H */ -- cgit v1.2.3 From 0fbb4d93b38bce1f8235aacfa37e90ad8f011473 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 17 Feb 2022 23:40:32 -0500 Subject: dm: add dm_submit_bio_remap interface Where possible, switch from early bio-based IO accounting (at the time DM clones each incoming bio) to late IO accounting just before each remapped bio is issued to underlying device via submit_bio_noacct(). Allows more precise bio-based IO accounting for DM targets that use their own workqueues to perform additional processing of each bio in conjunction with their DM_MAPIO_SUBMITTED return from their map function. When a target is updated to use dm_submit_bio_remap() they must also set ti->accounts_remapped_io to true. Use xchg() in start_io_acct(), as suggested by Mikulas, to ensure each IO is only started once. The xchg race only happens if __send_duplicate_bios() sends multiple bios -- that case is reflected via tio->is_duplicate_bio. Given the niche nature of this race, it is best to avoid any xchg performance penalty for normal IO. For IO that was never submitted with dm_bio_submit_remap(), but the target completes the clone with bio_endio, accounting is started then ended and pending_io counter decremented. Reviewed-by: Mikulas Patocka Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 7 +++++++ include/uapi/linux/dm-ioctl.h | 4 ++-- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index b26fecf6c8e8..7752d14d13f8 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -362,6 +362,12 @@ struct dm_target { * zone append operations using regular writes. */ bool emulate_zone_append:1; + + /* + * Set if the target will submit IO using dm_submit_bio_remap() + * after returning DM_MAPIO_SUBMITTED from its map function. + */ + bool accounts_remapped_io:1; }; void *dm_per_bio_data(struct bio *bio, size_t data_size); @@ -465,6 +471,7 @@ int dm_suspended(struct dm_target *ti); int dm_post_suspending(struct dm_target *ti); int dm_noflush_suspending(struct dm_target *ti); void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors); +void dm_submit_bio_remap(struct bio *clone, struct bio *tgt_clone, bool from_wq); union map_info *dm_get_rq_mapinfo(struct request *rq); #ifdef CONFIG_BLK_DEV_ZONED diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h index c12ce30b52df..2e9550fef90f 100644 --- a/include/uapi/linux/dm-ioctl.h +++ b/include/uapi/linux/dm-ioctl.h @@ -286,9 +286,9 @@ enum { #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 45 +#define DM_VERSION_MINOR 46 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2021-03-22)" +#define DM_VERSION_EXTRA "-ioctl (2022-02-22)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ -- cgit v1.2.3 From afea229fe10282da14595870b44f82792451dfb2 Mon Sep 17 00:00:00 2001 From: Arunpravin Date: Mon, 21 Feb 2022 22:15:48 +0530 Subject: drm: improve drm_buddy_alloc function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - Make drm_buddy_alloc a single function to handle range allocation and non-range allocation demands - Implemented a new function alloc_range() which allocates the requested power-of-two block comply with range limitations - Moved order computation and memory alignment logic from i915 driver to drm buddy v2: merged below changes to keep the build unbroken - drm_buddy_alloc_range() becomes obsolete and may be removed - enable ttm range allocation (fpfn / lpfn) support in i915 driver - apply enhanced drm_buddy_alloc() function to i915 driver v3(Matthew Auld): - Fix alignment issues and remove unnecessary list_empty check - add more validation checks for input arguments - make alloc_range() block allocations as bottom-up - optimize order computation logic - replace uint64_t with u64, which is preferred in the kernel v4(Matthew Auld): - keep drm_buddy_alloc_range() function implementation for generic actual range allocations - keep alloc_range() implementation for end bias allocations v5(Matthew Auld): - modify drm_buddy_alloc() passing argument place->lpfn to lpfn as place->lpfn will currently always be zero for i915 v6(Matthew Auld): - fixup potential uaf - If we are unlucky and can't allocate enough memory when splitting blocks, where we temporarily end up with the given block and its buddy on the respective free list, then we need to ensure we delete both blocks, and no just the buddy, before potentially freeing them - fix warnings reported by kernel test robot v7(Matthew Auld): - revert fixup potential uaf - keep __alloc_range() add node to the list logic same as drm_buddy_alloc_blocks() by having a temporary list variable - at drm_buddy_alloc_blocks() keep i915 range_overflows macro and add a new check for end variable v8: - fix warnings reported by kernel test robot v9(Matthew Auld): - remove DRM_BUDDY_RANGE_ALLOCATION flag - remove unnecessary function description v10: - keep DRM_BUDDY_RANGE_ALLOCATION flag as removing the flag and replacing with (end < size) logic fails amdgpu driver load Signed-off-by: Arunpravin Reviewed-by: Matthew Auld Signed-off-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20220221164552.2434-1-Arunpravin.PaneerSelvam@amd.com --- include/drm/drm_buddy.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/drm/drm_buddy.h b/include/drm/drm_buddy.h index f524db152413..54f25a372f27 100644 --- a/include/drm/drm_buddy.h +++ b/include/drm/drm_buddy.h @@ -22,6 +22,8 @@ start__ >= max__ || size__ > max__ - start__; \ }) +#define DRM_BUDDY_RANGE_ALLOCATION (1 << 0) + struct drm_buddy_block { #define DRM_BUDDY_HEADER_OFFSET GENMASK_ULL(63, 12) #define DRM_BUDDY_HEADER_STATE GENMASK_ULL(11, 10) @@ -131,12 +133,11 @@ int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size); void drm_buddy_fini(struct drm_buddy *mm); -struct drm_buddy_block * -drm_buddy_alloc_blocks(struct drm_buddy *mm, unsigned int order); - -int drm_buddy_alloc_range(struct drm_buddy *mm, - struct list_head *blocks, - u64 start, u64 size); +int drm_buddy_alloc_blocks(struct drm_buddy *mm, + u64 start, u64 end, u64 size, + u64 min_page_size, + struct list_head *blocks, + unsigned long flags); void drm_buddy_free_block(struct drm_buddy *mm, struct drm_buddy_block *block); -- cgit v1.2.3 From 476e4063022787b5720758239ee4c22fa2495e82 Mon Sep 17 00:00:00 2001 From: Arunpravin Date: Mon, 21 Feb 2022 22:15:49 +0530 Subject: drm: implement top-down allocation method MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Implemented a function which walk through the order list, compares the offset and returns the maximum offset block, this method is unpredictable in obtaining the high range address blocks which depends on allocation and deallocation. for instance, if driver requests address at a low specific range, allocator traverses from the root block and splits the larger blocks until it reaches the specific block and in the process of splitting, lower orders in the freelist are occupied with low range address blocks and for the subsequent TOPDOWN memory request we may return the low range blocks.To overcome this issue, we may go with the below approach. The other approach, sorting each order list entries in ascending order and compares the last entry of each order list in the freelist and return the max block. This creates sorting overhead on every drm_buddy_free() request and split up of larger blocks for a single page request. v2: - Fix alignment issues(Matthew Auld) - Remove unnecessary list_empty check(Matthew Auld) - merged the below patch to see the feature in action - add top-down alloc support to i915 driver Signed-off-by: Arunpravin Reviewed-by: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20220221164552.2434-2-Arunpravin.PaneerSelvam@amd.com Signed-off-by: Christian König --- include/drm/drm_buddy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/drm/drm_buddy.h b/include/drm/drm_buddy.h index 54f25a372f27..f0378fb48d06 100644 --- a/include/drm/drm_buddy.h +++ b/include/drm/drm_buddy.h @@ -23,6 +23,7 @@ }) #define DRM_BUDDY_RANGE_ALLOCATION (1 << 0) +#define DRM_BUDDY_TOPDOWN_ALLOCATION (1 << 1) struct drm_buddy_block { #define DRM_BUDDY_HEADER_OFFSET GENMASK_ULL(63, 12) -- cgit v1.2.3 From 95ee2a8b4b3cd1fb25f7e14e2202da4045030173 Mon Sep 17 00:00:00 2001 From: Arunpravin Date: Mon, 21 Feb 2022 22:15:50 +0530 Subject: drm: implement a method to free unused pages MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On contiguous allocation, we round up the size to the *next* power of 2, implement a function to free the unused pages after the newly allocate block. v2(Matthew Auld): - replace function name 'drm_buddy_free_unused_pages' with drm_buddy_block_trim - replace input argument name 'actual_size' with 'new_size' - add more validation checks for input arguments - add overlaps check to avoid needless searching and splitting - merged the below patch to see the feature in action - add free unused pages support to i915 driver - lock drm_buddy_block_trim() function as it calls mark_free/mark_split are all globally visible v3(Matthew Auld): - remove trim method error handling as we address the failure case at drm_buddy_block_trim() function v4: - in case of trim, at __alloc_range() split_block failure path marks the block as free and removes it from the original list, potentially also freeing it, to overcome this problem, we turn the drm_buddy_block_trim() input node into a temporary node to prevent recursively freeing itself, but still retain the un-splitting/freeing of the other nodes(Matthew Auld) - modify the drm_buddy_block_trim() function return type v5(Matthew Auld): - revert drm_buddy_block_trim() function return type changes in v4 - modify drm_buddy_block_trim() passing argument n_pages to original_size as n_pages has already been rounded up to the next power-of-two and passing n_pages results noop v6: - fix warnings reported by kernel test robot v7: - modify drm_buddy_block_trim() function doc description - at drm_buddy_block_trim() handle non-allocated block as a serious programmer error - fix a typo Signed-off-by: Arunpravin Reviewed-by: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20220221164552.2434-3-Arunpravin.PaneerSelvam@amd.com Signed-off-by: Christian König --- include/drm/drm_buddy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/drm/drm_buddy.h b/include/drm/drm_buddy.h index f0378fb48d06..bd21f9dfd15e 100644 --- a/include/drm/drm_buddy.h +++ b/include/drm/drm_buddy.h @@ -140,6 +140,10 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm, struct list_head *blocks, unsigned long flags); +int drm_buddy_block_trim(struct drm_buddy *mm, + u64 new_size, + struct list_head *blocks); + void drm_buddy_free_block(struct drm_buddy *mm, struct drm_buddy_block *block); void drm_buddy_free_list(struct drm_buddy *mm, struct list_head *objects); -- cgit v1.2.3 From a8b9d116cda047f38ba29ce26df49c57479ffaa2 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Wed, 26 Jan 2022 05:18:26 -0800 Subject: dm: cleanup double word in comment Remove the second 'a'. Signed-off-by: Tom Rix Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 7752d14d13f8..70cd9449275a 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -358,7 +358,7 @@ struct dm_target { bool limit_swap_bios:1; /* - * Set if this target implements a a zoned device and needs emulation of + * Set if this target implements a zoned device and needs emulation of * zone append operations using regular writes. */ bool emulate_zone_append:1; -- cgit v1.2.3 From e0891269a8c25715bd9510dc355326b00ab42db2 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 16 Feb 2022 16:22:26 +0000 Subject: linkage: add SYM_FUNC_ALIAS{,_LOCAL,_WEAK}() Currently aliasing an asm function requires adding START and END annotations for each name, as per Documentation/asm-annotations.rst: SYM_FUNC_START_ALIAS(__memset) SYM_FUNC_START(memset) ... asm insns ... SYM_FUNC_END(memset) SYM_FUNC_END_ALIAS(__memset) This is more painful than necessary to maintain, especially where a function has many aliases, some of which we may wish to define conditionally. For example, arm64's memcpy/memmove implementation (which uses some arch-specific SYM_*() helpers) has: SYM_FUNC_START_ALIAS(__memmove) SYM_FUNC_START_ALIAS_WEAK_PI(memmove) SYM_FUNC_START_ALIAS(__memcpy) SYM_FUNC_START_WEAK_PI(memcpy) ... asm insns ... SYM_FUNC_END_PI(memcpy) EXPORT_SYMBOL(memcpy) SYM_FUNC_END_ALIAS(__memcpy) EXPORT_SYMBOL(__memcpy) SYM_FUNC_END_ALIAS_PI(memmove) EXPORT_SYMBOL(memmove) SYM_FUNC_END_ALIAS(__memmove) EXPORT_SYMBOL(__memmove) SYM_FUNC_START(name) It would be much nicer if we could define the aliases *after* the standard function definition. This would avoid the need to specify each symbol name twice, and would make it easier to spot the canonical function definition. This patch adds new macros to allow us to do so, which allows the above example to be rewritten more succinctly as: SYM_FUNC_START(__pi_memcpy) ... asm insns ... SYM_FUNC_END(__pi_memcpy) SYM_FUNC_ALIAS(__memcpy, __pi_memcpy) EXPORT_SYMBOL(__memcpy) SYM_FUNC_ALIAS_WEAK(memcpy, __memcpy) EXPORT_SYMBOL(memcpy) SYM_FUNC_ALIAS(__pi_memmove, __pi_memcpy) SYM_FUNC_ALIAS(__memmove, __pi_memmove) EXPORT_SYMBOL(__memmove) SYM_FUNC_ALIAS_WEAK(memmove, __memmove) EXPORT_SYMBOL(memmove) The reduction in duplication will also make it possible to replace some uses of WEAK with more accurate Kconfig guards, e.g. #ifndef CONFIG_KASAN SYM_FUNC_ALIAS(memmove, __memmove) EXPORT_SYMBOL(memmove) #endif ... which should make it easier to ensure that symbols are neither used nor overidden unexpectedly. The existing SYM_FUNC_START_ALIAS() and SYM_FUNC_START_LOCAL_ALIAS() are marked as deprecated, and will be removed once existing users are moved over to the new scheme. The tools/perf/ copy of linkage.h is updated to match. A subsequent patch will depend upon this when updating the x86 asm annotations. Signed-off-by: Mark Rutland Acked-by: Ard Biesheuvel Acked-by: Josh Poimboeuf Acked-by: Mark Brown Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: Jiri Slaby Cc: Peter Zijlstra Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220216162229.1076788-2-mark.rutland@arm.com Signed-off-by: Will Deacon --- include/linux/linkage.h | 37 ++++++++++++++++++++++++++++++++++++- 1 file changed, 36 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/linkage.h b/include/linux/linkage.h index dbf8506decca..e574a84d8b11 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -165,7 +165,18 @@ #ifndef SYM_END #define SYM_END(name, sym_type) \ .type name sym_type ASM_NL \ - .size name, .-name + .set .L__sym_size_##name, .-name ASM_NL \ + .size name, .L__sym_size_##name +#endif + +/* SYM_ALIAS -- use only if you have to */ +#ifndef SYM_ALIAS +#define SYM_ALIAS(alias, name, sym_type, linkage) \ + linkage(alias) ASM_NL \ + .set alias, name ASM_NL \ + .type alias sym_type ASM_NL \ + .set .L__sym_size_##alias, .L__sym_size_##name ASM_NL \ + .size alias, .L__sym_size_##alias #endif /* === code annotations === */ @@ -275,6 +286,30 @@ SYM_END(name, SYM_T_FUNC) #endif +/* + * SYM_FUNC_ALIAS -- define a global alias for an existing function + */ +#ifndef SYM_FUNC_ALIAS +#define SYM_FUNC_ALIAS(alias, name) \ + SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_GLOBAL) +#endif + +/* + * SYM_FUNC_ALIAS_LOCAL -- define a local alias for an existing function + */ +#ifndef SYM_FUNC_ALIAS_LOCAL +#define SYM_FUNC_ALIAS_LOCAL(alias, name) \ + SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_LOCAL) +#endif + +/* + * SYM_FUNC_ALIAS_WEAK -- define a weak global alias for an existing function + */ +#ifndef SYM_FUNC_ALIAS_WEAK +#define SYM_FUNC_ALIAS_WEAK(alias, name) \ + SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_WEAK) +#endif + /* SYM_CODE_START -- use for non-C (special) functions */ #ifndef SYM_CODE_START #define SYM_CODE_START(name) \ -- cgit v1.2.3 From be9aea74400433e03c2a8b0260fc9ffe2495f698 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 16 Feb 2022 16:22:29 +0000 Subject: linkage: remove SYM_FUNC_{START,END}_ALIAS() Now that all aliases are defined using SYM_FUNC_ALIAS(), remove the old SYM_FUNC_{START,END}_ALIAS() macros. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Acked-by: Ard Biesheuvel Acked-by: Josh Poimboeuf Acked-by: Mark Brown Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: Jiri Slaby Cc: Peter Zijlstra Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220216162229.1076788-5-mark.rutland@arm.com Signed-off-by: Will Deacon --- include/linux/linkage.h | 30 ------------------------------ 1 file changed, 30 deletions(-) (limited to 'include') diff --git a/include/linux/linkage.h b/include/linux/linkage.h index e574a84d8b11..acb1ad2356f1 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -211,30 +211,8 @@ SYM_ENTRY(name, linkage, SYM_A_NONE) #endif -/* - * SYM_FUNC_START_LOCAL_ALIAS -- use where there are two local names for one - * function - */ -#ifndef SYM_FUNC_START_LOCAL_ALIAS -#define SYM_FUNC_START_LOCAL_ALIAS(name) \ - SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN) -#endif - -/* - * SYM_FUNC_START_ALIAS -- use where there are two global names for one - * function - */ -#ifndef SYM_FUNC_START_ALIAS -#define SYM_FUNC_START_ALIAS(name) \ - SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) -#endif - /* SYM_FUNC_START -- use for global functions */ #ifndef SYM_FUNC_START -/* - * The same as SYM_FUNC_START_ALIAS, but we will need to distinguish these two - * later. - */ #define SYM_FUNC_START(name) \ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #endif @@ -247,7 +225,6 @@ /* SYM_FUNC_START_LOCAL -- use for local functions */ #ifndef SYM_FUNC_START_LOCAL -/* the same as SYM_FUNC_START_LOCAL_ALIAS, see comment near SYM_FUNC_START */ #define SYM_FUNC_START_LOCAL(name) \ SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN) #endif @@ -270,18 +247,11 @@ SYM_START(name, SYM_L_WEAK, SYM_A_NONE) #endif -/* SYM_FUNC_END_ALIAS -- the end of LOCAL_ALIASed or ALIASed function */ -#ifndef SYM_FUNC_END_ALIAS -#define SYM_FUNC_END_ALIAS(name) \ - SYM_END(name, SYM_T_FUNC) -#endif - /* * SYM_FUNC_END -- the end of SYM_FUNC_START_LOCAL, SYM_FUNC_START, * SYM_FUNC_START_WEAK, ... */ #ifndef SYM_FUNC_END -/* the same as SYM_FUNC_END_ALIAS, see comment near SYM_FUNC_START */ #define SYM_FUNC_END(name) \ SYM_END(name, SYM_T_FUNC) #endif -- cgit v1.2.3 From 6e031ec0e5a2dda53e12e0d2a7e9b15b47a3c502 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 24 Jan 2022 16:11:37 -0700 Subject: vfio/pci: Stub vfio_pci_vga_rw when !CONFIG_VFIO_PCI_VGA Resolve build errors reported against UML build for undefined ioport_map() and ioport_unmap() functions. Without this config option a device cannot have vfio_pci_core_device.has_vga set, so the existing function would always return -EINVAL anyway. Reported-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20220123125737.2658758-1-geert@linux-m68k.org Link: https://lore.kernel.org/r/164306582968.3758255.15192949639574660648.stgit@omen Signed-off-by: Alex Williamson --- include/linux/vfio_pci_core.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index ef9a44b6cf5d..ae6f4838ab75 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -159,8 +159,17 @@ extern ssize_t vfio_pci_config_rw(struct vfio_pci_core_device *vdev, extern ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf, size_t count, loff_t *ppos, bool iswrite); +#ifdef CONFIG_VFIO_PCI_VGA extern ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf, size_t count, loff_t *ppos, bool iswrite); +#else +static inline ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, + char __user *buf, size_t count, + loff_t *ppos, bool iswrite) +{ + return -EINVAL; +} +#endif extern long vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset, uint64_t data, int count, int fd); -- cgit v1.2.3 From 1a03d3f13ffe5dd24142d6db629e72c11b704d99 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 17 Feb 2022 11:24:04 +0100 Subject: fork: Move task stack accounting to do_exit() There is no need to perform the stack accounting of the outgoing task in its final schedule() invocation which happens with preemption disabled. The task is leaving, the resources will be freed and the accounting can happen in do_exit() before the actual schedule invocation which frees the stack memory. Move the accounting of the stack memory from release_task_stack() to exit_task_stack_account() which then can be invoked from do_exit(). Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Acked-by: Andy Lutomirski Link: https://lore.kernel.org/r/20220217102406.3697941-7-bigeasy@linutronix.de --- include/linux/sched/task_stack.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index d10150587d81..892562ebbd3a 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -79,6 +79,8 @@ static inline void *try_get_task_stack(struct task_struct *tsk) static inline void put_task_stack(struct task_struct *tsk) {} #endif +void exit_task_stack_account(struct task_struct *tsk); + #define task_stack_end_corrupted(task) \ (*(end_of_stack(task)) != STACK_END_MAGIC) -- cgit v1.2.3 From f9b5e46f4097eb298f68e5b02f70697a90a44739 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Fri, 18 Feb 2022 17:29:44 -0800 Subject: kasan: split kasan_*enabled() functions into a separate header In an upcoming commit we are going to need to call kasan_hw_tags_enabled() from arch/arm64/include/asm/mte.h. This would create a circular dependency between headers if KASAN_GENERIC or KASAN_SW_TAGS is enabled: linux/kasan.h -> linux/pgtable.h -> asm/pgtable.h -> asm/mte.h -> linux/kasan.h. Break the cycle by introducing a new header linux/kasan-enabled.h with the kasan_*enabled() functions that can be included from asm/mte.h. Link: https://linux-review.googlesource.com/id/I5b0d96c6ed0026fc790899e14d42b2fac6ab568e Signed-off-by: Peter Collingbourne Reviewed-by: Andrey Konovalov Link: https://lore.kernel.org/r/20220219012945.894950-1-pcc@google.com Signed-off-by: Will Deacon --- include/linux/kasan-enabled.h | 33 +++++++++++++++++++++++++++++++++ include/linux/kasan.h | 23 +---------------------- 2 files changed, 34 insertions(+), 22 deletions(-) create mode 100644 include/linux/kasan-enabled.h (limited to 'include') diff --git a/include/linux/kasan-enabled.h b/include/linux/kasan-enabled.h new file mode 100644 index 000000000000..4b6615375022 --- /dev/null +++ b/include/linux/kasan-enabled.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_KASAN_ENABLED_H +#define _LINUX_KASAN_ENABLED_H + +#ifdef CONFIG_KASAN_HW_TAGS + +DECLARE_STATIC_KEY_FALSE(kasan_flag_enabled); + +static __always_inline bool kasan_enabled(void) +{ + return static_branch_likely(&kasan_flag_enabled); +} + +static inline bool kasan_hw_tags_enabled(void) +{ + return kasan_enabled(); +} + +#else /* CONFIG_KASAN_HW_TAGS */ + +static inline bool kasan_enabled(void) +{ + return IS_ENABLED(CONFIG_KASAN); +} + +static inline bool kasan_hw_tags_enabled(void) +{ + return false; +} + +#endif /* CONFIG_KASAN_HW_TAGS */ + +#endif /* LINUX_KASAN_ENABLED_H */ diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 4a45562d8893..b6a93261c92a 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -3,6 +3,7 @@ #define _LINUX_KASAN_H #include +#include #include #include #include @@ -83,33 +84,11 @@ static inline void kasan_disable_current(void) {} #ifdef CONFIG_KASAN_HW_TAGS -DECLARE_STATIC_KEY_FALSE(kasan_flag_enabled); - -static __always_inline bool kasan_enabled(void) -{ - return static_branch_likely(&kasan_flag_enabled); -} - -static inline bool kasan_hw_tags_enabled(void) -{ - return kasan_enabled(); -} - void kasan_alloc_pages(struct page *page, unsigned int order, gfp_t flags); void kasan_free_pages(struct page *page, unsigned int order); #else /* CONFIG_KASAN_HW_TAGS */ -static inline bool kasan_enabled(void) -{ - return IS_ENABLED(CONFIG_KASAN); -} - -static inline bool kasan_hw_tags_enabled(void) -{ - return false; -} - static __always_inline void kasan_alloc_pages(struct page *page, unsigned int order, gfp_t flags) { -- cgit v1.2.3 From 3f2e252ef727318f81588704461735617ad55b88 Mon Sep 17 00:00:00 2001 From: John Garry Date: Tue, 22 Feb 2022 20:50:59 +0800 Subject: scsi: libsas: Add sas_execute_ata_cmd() Add a function to execute an ATA command using the TMF code, and use in the hisi_sas driver. That driver needs to be able to issue the command on a specific phy, so add an interface for that. With that, hisi_sas_exec_internal_tmf_task() may be deleted. Link: https://lore.kernel.org/r/1645534259-27068-19-git-send-email-john.garry@huawei.com Tested-by: Yihang Li Tested-by: Damien Le Moal Reviewed-by: Christoph Hellwig Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 7 +++---- include/scsi/sas_ata.h | 8 ++++++++ 2 files changed, 11 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 4ea964d33600..dc529cc92d65 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -552,6 +552,9 @@ struct sas_ata_task { u8 stp_affil_pol:1; u8 device_control_reg_update:1; + + bool force_phy; + int force_phy_id; }; struct sas_smp_task { @@ -579,10 +582,6 @@ struct sas_ssp_task { struct sas_tmf_task { u8 tmf; u16 tag_of_task_to_be_managed; - - /* Temp */ - int force_phy; - int phy_id; }; struct sas_task { diff --git a/include/scsi/sas_ata.h b/include/scsi/sas_ata.h index 21e7c10c6295..d47dea70855d 100644 --- a/include/scsi/sas_ata.h +++ b/include/scsi/sas_ata.h @@ -32,6 +32,8 @@ void sas_probe_sata(struct asd_sas_port *port); void sas_suspend_sata(struct asd_sas_port *port); void sas_resume_sata(struct asd_sas_port *port); void sas_ata_end_eh(struct ata_port *ap); +int sas_execute_ata_cmd(struct domain_device *device, u8 *fis, + int force_phy_id); #else @@ -83,6 +85,12 @@ static inline int sas_get_ata_info(struct domain_device *dev, struct ex_phy *phy static inline void sas_ata_end_eh(struct ata_port *ap) { } + +static inline int sas_execute_ata_cmd(struct domain_device *device, u8 *fis, + int force_phy_id) +{ + return 0; +} #endif #endif /* _SAS_ATA_H_ */ -- cgit v1.2.3 From db22de3eb0352d2f8e7cda08f3fa65690e3fd64d Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 18 Feb 2022 11:50:53 -0800 Subject: scsi: iscsi: Stop using the SCSI pointer Instead of storing the iSCSI task pointer and the session age in the SCSI pointer, use command-private variables. This patch prepares for removal of the SCSI pointer from struct scsi_cmnd. The list of iSCSI drivers has been obtained as follows: $ git grep -lw iscsi_host_alloc drivers/infiniband/ulp/iser/iscsi_iser.c drivers/scsi/be2iscsi/be_main.c drivers/scsi/bnx2i/bnx2i_iscsi.c drivers/scsi/cxgbi/libcxgbi.c drivers/scsi/iscsi_tcp.c drivers/scsi/libiscsi.c drivers/scsi/qedi/qedi_main.c drivers/scsi/qla4xxx/ql4_os.c include/scsi/libiscsi.h Note: it is not clear to me how the qla4xxx driver can work without this patch since it uses the scsi_cmnd::SCp.ptr member for two different purposes: - The qla4xxx driver uses this member to store a struct srb pointer. - libiscsi uses this member to store a struct iscsi_task pointer. Reviewed-by: Lee Duncan Reviewed-by: Hannes Reinecke Reviewed-by: Himanshu Madhani Cc: Chris Leech Cc: Sagi Grimberg Cc: Nilesh Javali Cc: Manish Rangankar Cc: Karen Xie Cc: Ketan Mukadam Signed-off-by: Bart Van Assche iscsi Link: https://lore.kernel.org/r/20220218195117.25689-26-bvanassche@acm.org Signed-off-by: Martin K. Petersen --- include/scsi/libiscsi.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index 4ee233e5a6ff..cb805ed9cbf1 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -19,6 +19,7 @@ #include #include #include +#include #include struct scsi_transport_template; @@ -152,6 +153,17 @@ static inline bool iscsi_task_is_completed(struct iscsi_task *task) task->state == ISCSI_TASK_ABRT_SESS_RECOV; } +/* Private data associated with struct scsi_cmnd. */ +struct iscsi_cmd { + struct iscsi_task *task; + int age; +}; + +static inline struct iscsi_cmd *iscsi_cmd(struct scsi_cmnd *cmd) +{ + return scsi_cmd_priv(cmd); +} + /* Connection's states */ enum { ISCSI_CONN_INITIAL_STAGE, -- cgit v1.2.3 From 5d21aa3636fa8c7d3a2a69be93287da164054a3a Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 18 Feb 2022 11:50:55 -0800 Subject: scsi: libfc: Stop using the SCSI pointer Move the fc_fcp_pkt pointer, the residual length and the SCSI status into the new data structure libfc_cmd_priv. This patch prepares for removal of the SCSI pointer from struct scsi_cmnd. The user of the libfc data path functions have been identified as follows: $ git grep -lw fc_queuecommand | grep -v scsi/libfc/ drivers/scsi/fcoe/fcoe.c Link: https://lore.kernel.org/r/20220218195117.25689-28-bvanassche@acm.org Cc: Saurav Kashyap Cc: Javed Hasan Reviewed-by: Himanshu Madhani Reviewed-by: Hannes Reinecke Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- include/scsi/libfc.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/scsi/libfc.h b/include/scsi/libfc.h index eeb8d689ff6b..6e29e1719db1 100644 --- a/include/scsi/libfc.h +++ b/include/scsi/libfc.h @@ -351,6 +351,15 @@ struct fc_fcp_pkt { struct completion tm_done; } ____cacheline_aligned_in_smp; +/* + * @fsp should be tested and set under the scsi_pkt_queue lock + */ +struct libfc_cmd_priv { + struct fc_fcp_pkt *fsp; + u32 resid_len; + u8 status; +}; + /* * Structure and function definitions for managing Fibre Channel Exchanges * and Sequences -- cgit v1.2.3 From 8264aee803a2168124d1eb867a893047dc2977a0 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 18 Feb 2022 11:51:17 -0800 Subject: scsi: core: Remove struct scsi_pointer from struct scsi_cmnd Remove struct scsi_pointer from struct scsi_cmnd since the previous patches removed all users of that member of struct scsi_cmnd. Additionally, reorder the members of struct scsi_cmnd such that the statement that the field below can be modified by the SCSI LLD is again correct. Link: https://lore.kernel.org/r/20220218195117.25689-50-bvanassche@acm.org Cc: Ming Lei Cc: Hannes Reinecke Cc: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Himanshu Madhani Reviewed-by: Hannes Reinecke Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- include/scsi/scsi_cmnd.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index ff1c4b51f7ae..7a19c8bbaed9 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -123,11 +123,15 @@ struct scsi_cmnd { * command (auto-sense). Length must be * SCSI_SENSE_BUFFERSIZE bytes. */ + int flags; /* Command flags */ + unsigned long state; /* Command completion state */ + + unsigned int extra_len; /* length of alignment and padding */ + /* - * The following fields can be written to by the host specific code. - * Everything else should be left alone. + * The fields below can be modified by the LLD but the fields above + * must not be modified. */ - struct scsi_pointer SCp; /* Scratchpad used by some host adapters */ unsigned char *host_scribble; /* The host adapter is allowed to * call scsi_malloc and get some memory @@ -138,10 +142,6 @@ struct scsi_cmnd { * to be at an address < 16Mb). */ int result; /* Status code from lower level driver */ - int flags; /* Command flags */ - unsigned long state; /* Command completion state */ - - unsigned int extra_len; /* length of alignment and padding */ }; /* Variant of blk_mq_rq_from_pdu() that verifies the type of its argument. */ -- cgit v1.2.3 From a773187e37fa5c3bcd92ffda9085707df34f903a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 9 Feb 2022 09:28:27 +0100 Subject: scsi: dm: Remove WRITE_SAME support There are no more end-users of REQ_OP_WRITE_SAME left, so we can start deleting it. Link: https://lore.kernel.org/r/20220209082828.2629273-7-hch@lst.de Reviewed-by: Mike Snitzer Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- include/linux/device-mapper.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index b26fecf6c8e8..721db99f4f63 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -316,12 +316,6 @@ struct dm_target { */ unsigned num_secure_erase_bios; - /* - * The number of WRITE SAME bios that will be submitted to the target. - * The bio number can be accessed with dm_bio_get_target_bio_nr. - */ - unsigned num_write_same_bios; - /* * The number of WRITE ZEROES bios that will be submitted to the target. * The bio number can be accessed with dm_bio_get_target_bio_nr. -- cgit v1.2.3 From 73bd66d9c834220579c881a3eb020fd8917075d8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 9 Feb 2022 09:28:28 +0100 Subject: scsi: block: Remove REQ_OP_WRITE_SAME support No more users of REQ_OP_WRITE_SAME or drivers implementing it are left, so remove the infrastructure. [mkp: fold in and tweak sysfs reporting fix] Link: https://lore.kernel.org/r/20220209082828.2629273-8-hch@lst.de Reviewed-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- include/linux/bio.h | 3 --- include/linux/blk_types.h | 2 -- include/linux/blkdev.h | 19 ------------------- 3 files changed, 24 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 117d7f248ac9..eb402afa370a 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -65,7 +65,6 @@ static inline bool bio_no_advance_iter(const struct bio *bio) { return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE || - bio_op(bio) == REQ_OP_WRITE_SAME || bio_op(bio) == REQ_OP_WRITE_ZEROES; } @@ -186,8 +185,6 @@ static inline unsigned bio_segments(struct bio *bio) case REQ_OP_SECURE_ERASE: case REQ_OP_WRITE_ZEROES: return 0; - case REQ_OP_WRITE_SAME: - return 1; default: break; } diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index fe065c394fff..077adf4b6e73 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -354,8 +354,6 @@ enum req_opf { REQ_OP_DISCARD = 3, /* securely erase sectors */ REQ_OP_SECURE_ERASE = 5, - /* write the same sector many times */ - REQ_OP_WRITE_SAME = 7, /* write the zero filled sector many times */ REQ_OP_WRITE_ZEROES = 9, /* Open a zone */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9c95df26fc26..b10470d5e986 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -97,7 +97,6 @@ struct queue_limits { unsigned int io_opt; unsigned int max_discard_sectors; unsigned int max_hw_discard_sectors; - unsigned int max_write_same_sectors; unsigned int max_write_zeroes_sectors; unsigned int max_zone_append_sectors; unsigned int discard_granularity; @@ -651,9 +650,6 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, return min(q->limits.max_discard_sectors, UINT_MAX >> SECTOR_SHIFT); - if (unlikely(op == REQ_OP_WRITE_SAME)) - return q->limits.max_write_same_sectors; - if (unlikely(op == REQ_OP_WRITE_ZEROES)) return q->limits.max_write_zeroes_sectors; @@ -696,8 +692,6 @@ extern void blk_queue_max_discard_segments(struct request_queue *, extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); -extern void blk_queue_max_write_same_sectors(struct request_queue *q, - unsigned int max_write_same_sectors); extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q, unsigned int max_write_same_sectors); extern void blk_queue_logical_block_size(struct request_queue *, unsigned int); @@ -842,9 +836,6 @@ static inline long nr_blockdev_pages(void) extern void blk_io_schedule(void); -extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, struct page *page); - #define BLKDEV_DISCARD_SECURE (1 << 0) /* issue a secure erase */ extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, @@ -1071,16 +1062,6 @@ static inline int bdev_discard_alignment(struct block_device *bdev) return q->limits.discard_alignment; } -static inline unsigned int bdev_write_same(struct block_device *bdev) -{ - struct request_queue *q = bdev_get_queue(bdev); - - if (q) - return q->limits.max_write_same_sectors; - - return 0; -} - static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); -- cgit v1.2.3 From 763087dab97547230a6807c865a6a5ae53a59247 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 21 Feb 2022 19:21:12 -0800 Subject: net: add skb_set_end_offset() helper We have multiple places where this helper is convenient, and plan using it in the following patch. Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a3e90efe6586..115be7f73487 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1536,6 +1536,11 @@ static inline unsigned int skb_end_offset(const struct sk_buff *skb) { return skb->end; } + +static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) +{ + skb->end = offset; +} #else static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { @@ -1546,6 +1551,11 @@ static inline unsigned int skb_end_offset(const struct sk_buff *skb) { return skb->end - skb->head; } + +static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) +{ + skb->end = skb->head + offset; +} #endif /* Internal */ -- cgit v1.2.3 From 2b88cba55883eaafbc9b7cbff0b2c7cdba71ed01 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 21 Feb 2022 19:21:13 -0800 Subject: net: preserve skb_end_offset() in skb_unclone_keeptruesize() syzbot found another way to trigger the infamous WARN_ON_ONCE(delta < len) in skb_try_coalesce() [1] I was able to root cause the issue to kfence. When kfence is in action, the following assertion is no longer true: int size = xxxx; void *ptr1 = kmalloc(size, gfp); void *ptr2 = kmalloc(size, gfp); if (ptr1 && ptr2) ASSERT(ksize(ptr1) == ksize(ptr2)); We attempted to fix these issues in the blamed commits, but forgot that TCP was possibly shifting data after skb_unclone_keeptruesize() has been used, notably from tcp_retrans_try_collapse(). So we not only need to keep same skb->truesize value, we also need to make sure TCP wont fill new tailroom that pskb_expand_head() was able to get from a addr = kmalloc(...) followed by ksize(addr) Split skb_unclone_keeptruesize() into two parts: 1) Inline skb_unclone_keeptruesize() for the common case, when skb is not cloned. 2) Out of line __skb_unclone_keeptruesize() for the 'slow path'. WARNING: CPU: 1 PID: 6490 at net/core/skbuff.c:5295 skb_try_coalesce+0x1235/0x1560 net/core/skbuff.c:5295 Modules linked in: CPU: 1 PID: 6490 Comm: syz-executor161 Not tainted 5.17.0-rc4-syzkaller-00229-g4f12b742eb2b #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:skb_try_coalesce+0x1235/0x1560 net/core/skbuff.c:5295 Code: bf 01 00 00 00 0f b7 c0 89 c6 89 44 24 20 e8 62 24 4e fa 8b 44 24 20 83 e8 01 0f 85 e5 f0 ff ff e9 87 f4 ff ff e8 cb 20 4e fa <0f> 0b e9 06 f9 ff ff e8 af b2 95 fa e9 69 f0 ff ff e8 95 b2 95 fa RSP: 0018:ffffc900063af268 EFLAGS: 00010293 RAX: 0000000000000000 RBX: 00000000ffffffd5 RCX: 0000000000000000 RDX: ffff88806fc05700 RSI: ffffffff872abd55 RDI: 0000000000000003 RBP: ffff88806e675500 R08: 00000000ffffffd5 R09: 0000000000000000 R10: ffffffff872ab659 R11: 0000000000000000 R12: ffff88806dd554e8 R13: ffff88806dd9bac0 R14: ffff88806dd9a2c0 R15: 0000000000000155 FS: 00007f18014f9700(0000) GS:ffff8880b9c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020002000 CR3: 000000006be7a000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: tcp_try_coalesce net/ipv4/tcp_input.c:4651 [inline] tcp_try_coalesce+0x393/0x920 net/ipv4/tcp_input.c:4630 tcp_queue_rcv+0x8a/0x6e0 net/ipv4/tcp_input.c:4914 tcp_data_queue+0x11fd/0x4bb0 net/ipv4/tcp_input.c:5025 tcp_rcv_established+0x81e/0x1ff0 net/ipv4/tcp_input.c:5947 tcp_v4_do_rcv+0x65e/0x980 net/ipv4/tcp_ipv4.c:1719 sk_backlog_rcv include/net/sock.h:1037 [inline] __release_sock+0x134/0x3b0 net/core/sock.c:2779 release_sock+0x54/0x1b0 net/core/sock.c:3311 sk_wait_data+0x177/0x450 net/core/sock.c:2821 tcp_recvmsg_locked+0xe28/0x1fd0 net/ipv4/tcp.c:2457 tcp_recvmsg+0x137/0x610 net/ipv4/tcp.c:2572 inet_recvmsg+0x11b/0x5e0 net/ipv4/af_inet.c:850 sock_recvmsg_nosec net/socket.c:948 [inline] sock_recvmsg net/socket.c:966 [inline] sock_recvmsg net/socket.c:962 [inline] ____sys_recvmsg+0x2c4/0x600 net/socket.c:2632 ___sys_recvmsg+0x127/0x200 net/socket.c:2674 __sys_recvmsg+0xe2/0x1a0 net/socket.c:2704 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae Fixes: c4777efa751d ("net: add and use skb_unclone_keeptruesize() helper") Fixes: 097b9146c0e2 ("net: fix up truesize of cloned skb in skb_prepare_for_shift()") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Marco Elver Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 115be7f73487..31be38078918 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1795,19 +1795,19 @@ static inline int skb_unclone(struct sk_buff *skb, gfp_t pri) return 0; } -/* This variant of skb_unclone() makes sure skb->truesize is not changed */ +/* This variant of skb_unclone() makes sure skb->truesize + * and skb_end_offset() are not changed, whenever a new skb->head is needed. + * + * Indeed there is no guarantee that ksize(kmalloc(X)) == ksize(kmalloc(X)) + * when various debugging features are in place. + */ +int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri); static inline int skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); - if (skb_cloned(skb)) { - unsigned int save = skb->truesize; - int res; - - res = pskb_expand_head(skb, 0, 0, pri); - skb->truesize = save; - return res; - } + if (skb_cloned(skb)) + return __skb_unclone_keeptruesize(skb, pri); return 0; } -- cgit v1.2.3 From d0b9d6dcaa5ac480c272683919f387cc6d82b638 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 23 Sep 2021 20:42:44 +0200 Subject: sched/headers: Fix header to build standalone: Uses various kernel types that don't build standalone. Signed-off-by: Ingo Molnar Reviewed-by: Peter Zijlstra --- include/linux/sched_clock.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h index 835ee87ed792..cb41c5edb4d4 100644 --- a/include/linux/sched_clock.h +++ b/include/linux/sched_clock.h @@ -5,6 +5,8 @@ #ifndef LINUX_SCHED_CLOCK #define LINUX_SCHED_CLOCK +#include + #ifdef CONFIG_GENERIC_SCHED_CLOCK /** * struct clock_read_data - data required to read from sched_clock() -- cgit v1.2.3 From 8ab62eda177bc350f34fea4fcea23603b8184bfd Mon Sep 17 00:00:00 2001 From: Jiawei Gu Date: Tue, 22 Feb 2022 17:42:52 +0800 Subject: drm/sched: Add device pointer to drm_gpu_scheduler MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add device pointer so scheduler's printing can use DRM_DEV_ERROR() instead, which makes life easier under multiple GPU scenario. v2: amend all calls of drm_sched_init() v3: fill dev pointer for all drm_sched_init() calls Signed-off-by: Jiawei Gu Reviewed-by: Andrey Grodzovsky Reviewed-by: Christian König Signed-off-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20220221095705.5290-1-Jiawei.Gu@amd.com --- include/drm/gpu_scheduler.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index bbc22fad8d80..944f83ef9f2e 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -457,13 +457,14 @@ struct drm_gpu_scheduler { atomic_t _score; bool ready; bool free_guilty; + struct device *dev; }; int drm_sched_init(struct drm_gpu_scheduler *sched, const struct drm_sched_backend_ops *ops, uint32_t hw_submission, unsigned hang_limit, long timeout, struct workqueue_struct *timeout_wq, - atomic_t *score, const char *name); + atomic_t *score, const char *name, struct device *dev); void drm_sched_fini(struct drm_gpu_scheduler *sched); int drm_sched_job_init(struct drm_sched_job *job, -- cgit v1.2.3 From 92937f170d3f49f41d7acb86243ee691a98eb2be Mon Sep 17 00:00:00 2001 From: Arunpravin Date: Tue, 22 Feb 2022 23:18:41 +0530 Subject: drm/selftests: add drm buddy alloc range testcase MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - add a test to check the range allocation - export get_buddy() function in drm_buddy.c - export drm_prandom_u32_max_state() in lib/drm_random.c - include helper functions - include prime number header file v2: - add drm_get_buddy() function description (Matthew Auld) - removed unnecessary test succeeded print Signed-off-by: Arunpravin Reviewed-by: Matthew Auld Acked-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20220222174845.2175-3-Arunpravin.PaneerSelvam@amd.com Signed-off-by: Christian König --- include/drm/drm_buddy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/drm/drm_buddy.h b/include/drm/drm_buddy.h index bd21f9dfd15e..572077ff8ae7 100644 --- a/include/drm/drm_buddy.h +++ b/include/drm/drm_buddy.h @@ -134,6 +134,9 @@ int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size); void drm_buddy_fini(struct drm_buddy *mm); +struct drm_buddy_block * +drm_get_buddy(struct drm_buddy_block *block); + int drm_buddy_alloc_blocks(struct drm_buddy *mm, u64 start, u64 end, u64 size, u64 min_page_size, -- cgit v1.2.3 From 669f45f19cf7feea7066dce86a0ce89dfc8a2065 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 22 Feb 2022 13:23:59 +0100 Subject: sched/headers: Add initial new headers as identity mappings This allows code sharing between fast-headers tree and the vanilla scheduler tree. Signed-off-by: Ingo Molnar Reviewed-by: Peter Zijlstra --- include/linux/cgroup_api.h | 1 + include/linux/cpumask_api.h | 1 + include/linux/fs_api.h | 1 + include/linux/gfp_api.h | 1 + include/linux/hashtable_api.h | 1 + include/linux/hrtimer_api.h | 1 + include/linux/kobject_api.h | 1 + include/linux/kref_api.h | 1 + include/linux/ktime_api.h | 1 + include/linux/llist_api.h | 1 + include/linux/lockdep_api.h | 1 + include/linux/mm_api.h | 1 + include/linux/mutex_api.h | 1 + include/linux/perf_event_api.h | 1 + include/linux/pgtable_api.h | 1 + include/linux/ptrace_api.h | 1 + include/linux/rcuwait_api.h | 1 + include/linux/refcount_api.h | 1 + include/linux/sched/affinity.h | 1 + include/linux/sched/cond_resched.h | 1 + include/linux/sched/posix-timers.h | 1 + include/linux/sched/rseq_api.h | 1 + include/linux/sched/task_flags.h | 1 + include/linux/sched/thread_info_api.h | 1 + include/linux/seqlock_api.h | 1 + include/linux/softirq.h | 1 + include/linux/spinlock_api.h | 1 + include/linux/swait_api.h | 1 + include/linux/syscalls_api.h | 1 + include/linux/u64_stats_sync_api.h | 1 + include/linux/wait_api.h | 1 + include/linux/workqueue_api.h | 1 + 32 files changed, 32 insertions(+) create mode 100644 include/linux/cgroup_api.h create mode 100644 include/linux/cpumask_api.h create mode 100644 include/linux/fs_api.h create mode 100644 include/linux/gfp_api.h create mode 100644 include/linux/hashtable_api.h create mode 100644 include/linux/hrtimer_api.h create mode 100644 include/linux/kobject_api.h create mode 100644 include/linux/kref_api.h create mode 100644 include/linux/ktime_api.h create mode 100644 include/linux/llist_api.h create mode 100644 include/linux/lockdep_api.h create mode 100644 include/linux/mm_api.h create mode 100644 include/linux/mutex_api.h create mode 100644 include/linux/perf_event_api.h create mode 100644 include/linux/pgtable_api.h create mode 100644 include/linux/ptrace_api.h create mode 100644 include/linux/rcuwait_api.h create mode 100644 include/linux/refcount_api.h create mode 100644 include/linux/sched/affinity.h create mode 100644 include/linux/sched/cond_resched.h create mode 100644 include/linux/sched/posix-timers.h create mode 100644 include/linux/sched/rseq_api.h create mode 100644 include/linux/sched/task_flags.h create mode 100644 include/linux/sched/thread_info_api.h create mode 100644 include/linux/seqlock_api.h create mode 100644 include/linux/softirq.h create mode 100644 include/linux/spinlock_api.h create mode 100644 include/linux/swait_api.h create mode 100644 include/linux/syscalls_api.h create mode 100644 include/linux/u64_stats_sync_api.h create mode 100644 include/linux/wait_api.h create mode 100644 include/linux/workqueue_api.h (limited to 'include') diff --git a/include/linux/cgroup_api.h b/include/linux/cgroup_api.h new file mode 100644 index 000000000000..d0cfe8025111 --- /dev/null +++ b/include/linux/cgroup_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/cpumask_api.h b/include/linux/cpumask_api.h new file mode 100644 index 000000000000..83bd3ebe82b0 --- /dev/null +++ b/include/linux/cpumask_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/fs_api.h b/include/linux/fs_api.h new file mode 100644 index 000000000000..83be38d6d413 --- /dev/null +++ b/include/linux/fs_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/gfp_api.h b/include/linux/gfp_api.h new file mode 100644 index 000000000000..5a05a2764a86 --- /dev/null +++ b/include/linux/gfp_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/hashtable_api.h b/include/linux/hashtable_api.h new file mode 100644 index 000000000000..c268ac2c5c0e --- /dev/null +++ b/include/linux/hashtable_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/hrtimer_api.h b/include/linux/hrtimer_api.h new file mode 100644 index 000000000000..8d9700894468 --- /dev/null +++ b/include/linux/hrtimer_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/kobject_api.h b/include/linux/kobject_api.h new file mode 100644 index 000000000000..6e36a054c2d6 --- /dev/null +++ b/include/linux/kobject_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/kref_api.h b/include/linux/kref_api.h new file mode 100644 index 000000000000..d67e554721d2 --- /dev/null +++ b/include/linux/kref_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/ktime_api.h b/include/linux/ktime_api.h new file mode 100644 index 000000000000..f697d493960f --- /dev/null +++ b/include/linux/ktime_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/llist_api.h b/include/linux/llist_api.h new file mode 100644 index 000000000000..625bec0393a1 --- /dev/null +++ b/include/linux/llist_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/lockdep_api.h b/include/linux/lockdep_api.h new file mode 100644 index 000000000000..907e66979ab2 --- /dev/null +++ b/include/linux/lockdep_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/mm_api.h b/include/linux/mm_api.h new file mode 100644 index 000000000000..a5ace2b198b8 --- /dev/null +++ b/include/linux/mm_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/mutex_api.h b/include/linux/mutex_api.h new file mode 100644 index 000000000000..85ab9491e13e --- /dev/null +++ b/include/linux/mutex_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/perf_event_api.h b/include/linux/perf_event_api.h new file mode 100644 index 000000000000..c2fd6048b790 --- /dev/null +++ b/include/linux/perf_event_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/pgtable_api.h b/include/linux/pgtable_api.h new file mode 100644 index 000000000000..ff367a4ba8c4 --- /dev/null +++ b/include/linux/pgtable_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/ptrace_api.h b/include/linux/ptrace_api.h new file mode 100644 index 000000000000..26e7d275ad8d --- /dev/null +++ b/include/linux/ptrace_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/rcuwait_api.h b/include/linux/rcuwait_api.h new file mode 100644 index 000000000000..f962e28544dd --- /dev/null +++ b/include/linux/rcuwait_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/refcount_api.h b/include/linux/refcount_api.h new file mode 100644 index 000000000000..5f032589f568 --- /dev/null +++ b/include/linux/refcount_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/sched/affinity.h b/include/linux/sched/affinity.h new file mode 100644 index 000000000000..227f5be81bcd --- /dev/null +++ b/include/linux/sched/affinity.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/sched/cond_resched.h b/include/linux/sched/cond_resched.h new file mode 100644 index 000000000000..227f5be81bcd --- /dev/null +++ b/include/linux/sched/cond_resched.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/sched/posix-timers.h b/include/linux/sched/posix-timers.h new file mode 100644 index 000000000000..523a381d6c88 --- /dev/null +++ b/include/linux/sched/posix-timers.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/sched/rseq_api.h b/include/linux/sched/rseq_api.h new file mode 100644 index 000000000000..cf2af72693e1 --- /dev/null +++ b/include/linux/sched/rseq_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/sched/task_flags.h b/include/linux/sched/task_flags.h new file mode 100644 index 000000000000..227f5be81bcd --- /dev/null +++ b/include/linux/sched/task_flags.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/sched/thread_info_api.h b/include/linux/sched/thread_info_api.h new file mode 100644 index 000000000000..2c60fbc16c08 --- /dev/null +++ b/include/linux/sched/thread_info_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/seqlock_api.h b/include/linux/seqlock_api.h new file mode 100644 index 000000000000..be91e7d3b826 --- /dev/null +++ b/include/linux/seqlock_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/softirq.h b/include/linux/softirq.h new file mode 100644 index 000000000000..c73d7dcb4cb5 --- /dev/null +++ b/include/linux/softirq.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/spinlock_api.h b/include/linux/spinlock_api.h new file mode 100644 index 000000000000..6338b27f98df --- /dev/null +++ b/include/linux/spinlock_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/swait_api.h b/include/linux/swait_api.h new file mode 100644 index 000000000000..1eeaaaaa5ea7 --- /dev/null +++ b/include/linux/swait_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/syscalls_api.h b/include/linux/syscalls_api.h new file mode 100644 index 000000000000..23e012b04db4 --- /dev/null +++ b/include/linux/syscalls_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/u64_stats_sync_api.h b/include/linux/u64_stats_sync_api.h new file mode 100644 index 000000000000..c72ca63da44b --- /dev/null +++ b/include/linux/u64_stats_sync_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/wait_api.h b/include/linux/wait_api.h new file mode 100644 index 000000000000..4e930548935a --- /dev/null +++ b/include/linux/wait_api.h @@ -0,0 +1 @@ +#include diff --git a/include/linux/workqueue_api.h b/include/linux/workqueue_api.h new file mode 100644 index 000000000000..77debb5d2760 --- /dev/null +++ b/include/linux/workqueue_api.h @@ -0,0 +1 @@ +#include -- cgit v1.2.3 From fbed5664b73830dcb1a19af4f7f1f1b424f54609 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 22 Feb 2022 13:28:20 +0100 Subject: sched/headers: Make the header build standalone This header depends on various scheduler definitions. Signed-off-by: Ingo Molnar Reviewed-by: Peter Zijlstra --- include/linux/sched/deadline.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index 1aff00b65f3c..7c83d4d5a971 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -6,6 +6,8 @@ * NORMAL/BATCH tasks. */ +#include + #define MAX_DL_PRIO 0 static inline int dl_prio(int prio) -- cgit v1.2.3 From b26ef81c46ed15d11ddddba9ba1cd52c749385ad Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 22 Feb 2022 14:04:50 -0800 Subject: drop_monitor: remove quadratic behavior drop_monitor is using an unique list on which all netdevices in the host have an element, regardless of their netns. This scales poorly, not only at device unregister time (what I caught during my netns dismantle stress tests), but also at packet processing time whenever trace_napi_poll_hit() is called. If the intent was to avoid adding one pointer in 'struct net_device' then surely we prefer O(1) behavior. Signed-off-by: Eric Dumazet Cc: Neil Horman Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 93fc680b658f..c79ee2296296 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2236,7 +2236,9 @@ struct net_device { #if IS_ENABLED(CONFIG_MRP) struct mrp_port __rcu *mrp_port; #endif - +#if IS_ENABLED(CONFIG_NET_DROP_MONITOR) + struct dm_hw_stat_delta __rcu *dm_private; +#endif struct device dev; const struct attribute_group *sysfs_groups[4]; const struct attribute_group *sysfs_rx_queue_group; -- cgit v1.2.3 From a21d9a670d81103db7f788de1a4a4a6e4b891a0b Mon Sep 17 00:00:00 2001 From: Hans Schultz Date: Wed, 23 Feb 2022 11:16:46 +0100 Subject: net: bridge: Add support for bridge port in locked mode In a 802.1X scenario, clients connected to a bridge port shall not be allowed to have traffic forwarded until fully authenticated. A static fdb entry of the clients MAC address for the bridge port unlocks the client and allows bidirectional communication. This scenario is facilitated with setting the bridge port in locked mode, which is also supported by various switchcore chipsets. Signed-off-by: Hans Schultz Acked-by: Nikolay Aleksandrov Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 1 + include/uapi/linux/if_link.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 509e18c7e740..3aae023a9353 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -58,6 +58,7 @@ struct br_ip_list { #define BR_MRP_LOST_CONT BIT(18) #define BR_MRP_LOST_IN_CONT BIT(19) #define BR_TX_FWD_OFFLOAD BIT(20) +#define BR_PORT_LOCKED BIT(21) #define BR_DEFAULT_AGEING_TIME (300 * HZ) diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index e1ba2d51b717..be09d2ad4b5d 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -537,6 +537,7 @@ enum { IFLA_BRPORT_MRP_IN_OPEN, IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, + IFLA_BRPORT_LOCKED, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) -- cgit v1.2.3 From f2eb478f2f322217aa642e11c1cc011f99c797e6 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 22 Feb 2022 08:07:13 +0100 Subject: kernfs: move struct kernfs_root out of the public view. There is no need to have struct kernfs_root be part of kernfs.h for the whole kernel to see and poke around it. Move it internal to kernfs code and provide a helper function, kernfs_root_to_node(), to handle the one field that kernfs users were directly accessing from the structure. Cc: Imran Khan Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20220222070713.3517679-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/kernfs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 861c4f0f8a29..62aff082dc3f 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -185,6 +185,7 @@ struct kernfs_syscall_ops { struct kernfs_root *root); }; +#if 0 struct kernfs_root { /* published fields */ struct kernfs_node *kn; @@ -202,6 +203,9 @@ struct kernfs_root { wait_queue_head_t deactivate_waitq; struct rw_semaphore kernfs_rwsem; }; +#endif + +struct kernfs_node *kernfs_root_to_node(struct kernfs_root *root); struct kernfs_open_file { /* published fields */ -- cgit v1.2.3 From c404c64d64bc31bebe8a2015103671f7cd282731 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Sun, 30 Jan 2022 22:02:06 +0100 Subject: powercap/dtpm: Destroy hierarchy function The hierarchy creation function exits but without a destroy hierarchy function. Due to that, the modules creating the hierarchy can not be unloaded properly because they don't have an exit callback. Provide the dtpm_destroy_hierarchy() function to remove the previously created hierarchy. The function relies on all the release mechanisms implemented by the underlying powercap framework. Signed-off-by: Daniel Lezcano Reviewed-by: Ulf Hansson Link: https://lore.kernel.org/r/20220130210210.549877-4-daniel.lezcano@linaro.org --- include/linux/dtpm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/dtpm.h b/include/linux/dtpm.h index f7a25c70dd4c..a4a13514b730 100644 --- a/include/linux/dtpm.h +++ b/include/linux/dtpm.h @@ -37,6 +37,7 @@ struct device_node; struct dtpm_subsys_ops { const char *name; int (*init)(void); + void (*exit)(void); int (*setup)(struct dtpm *, struct device_node *); }; @@ -67,4 +68,6 @@ void dtpm_unregister(struct dtpm *dtpm); int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent); int dtpm_create_hierarchy(struct of_device_id *dtpm_match_table); + +void dtpm_destroy_hierarchy(void); #endif -- cgit v1.2.3 From 43c075959de3c45608636d9d80ff9e61d166fb21 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 26 Jan 2022 10:57:07 -0800 Subject: mlx5: remove unused static inlines mlx5 has some unused static inline helpers in include/ while at it also clean static inlines in the driver itself. Signed-off-by: Jakub Kicinski Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 78655d8d13a7..1b398c9e17b9 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -863,20 +863,10 @@ struct mlx5_hca_vport_context { bool grh_required; }; -static inline void *mlx5_buf_offset(struct mlx5_frag_buf *buf, int offset) -{ - return buf->frags->buf + offset; -} - #define STRUCT_FIELD(header, field) \ .struct_offset_bytes = offsetof(struct ib_unpacked_ ## header, field), \ .struct_size_bytes = sizeof((struct ib_unpacked_ ## header *)0)->field -static inline struct mlx5_core_dev *pci2mlx5_core_dev(struct pci_dev *pdev) -{ - return pci_get_drvdata(pdev); -} - extern struct dentry *mlx5_debugfs_root; static inline u16 fw_rev_maj(struct mlx5_core_dev *dev) -- cgit v1.2.3 From c2c922dae77f36e24d246c6e310cee0c61afc6fb Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Mon, 29 Nov 2021 16:24:28 +0200 Subject: net/mlx5: Add ability to insert to specific flow group If the flow table isn't an autogroup the upper driver has to create the flow groups explicitly. This information can't later be used when creating rules to insert into a specific flow group. Allow such use case. Signed-off-by: Mark Bloch Reviewed-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index b1aad14689e3..e3bfed68b08a 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -224,6 +224,7 @@ struct mlx5_flow_act { u32 flags; struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH]; struct ib_counters *counters; + struct mlx5_flow_group *fg; }; #define MLX5_DECLARE_FLOW_ACT(name) \ -- cgit v1.2.3 From 605bef0015b163867127202b821dce79804d603d Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Sun, 5 Apr 2020 17:50:25 -0700 Subject: net/mlx5: cmdif, cmd_check refactoring Do not mangle the command outbox in the internal low level cmd_exec and cmd_invoke functions. Instead return a proper unique error code and move the driver error checking to be at a higher level in mlx5_cmd_exec(). Signed-off-by: Saeed Mahameed Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 1b398c9e17b9..8a8408708e6c 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -981,7 +981,6 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); -void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome); bool mlx5_cmd_is_down(struct mlx5_core_dev *dev); int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type); -- cgit v1.2.3 From f23519e542e51c19ab3081deb089bb3f8fec7bb9 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Sat, 17 Aug 2019 03:05:10 -0700 Subject: net/mlx5: cmdif, Add new api for command execution Add mlx5_cmd_do. Unlike mlx5_cmd_exec, this function will not modify or translate outbox.status. The function will return: return = 0: Command was executed, outbox.status == MLX5_CMD_STAT_OK. return = -EREMOTEIO: Executed, outbox.status != MLX5_CMD_STAT_OK. return < 0: Command execution couldn't be performed by FW or driver. And document other mlx5_cmd_exec functions. Signed-off-by: Saeed Mahameed Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 8a8408708e6c..1b9bec8fa870 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -964,6 +964,8 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, void *out, int out_size, mlx5_async_cbk_t callback, struct mlx5_async_work *work); +int mlx5_cmd_do(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); +int mlx5_cmd_check(struct mlx5_core_dev *dev, int err, void *in, void *out); int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); -- cgit v1.2.3 From 31803e59233efc838b9dcb26edea28a4b2389e97 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Mon, 30 Mar 2020 21:12:58 -0700 Subject: net/mlx5: Use mlx5_cmd_do() in core create_{cq,dct} mlx5_core_create_{cq/dct} functions are non-trivial mlx5 commands functions. They check command execution status themselves and hide valuable FW failure information. For mlx5_core/eth kernel user this is what we actually want, but for a devx/rdma user the hidden information is essential and should be propagated up to the caller, thus we convert these commands to use mlx5_cmd_do to return the FW/driver and command outbox status as is, and let the caller decide what to do with it. For kernel callers of mlx5_core_create_{cq/dct} or those who only care about the binary status (FAIL/SUCCESS) they must check status themselves via mlx5_cmd_check() to restore the current behavior. err = mlx5_create_cq(in, out) err = mlx5_cmd_check(err, in, out) if (err) // handle err For DEVX users and those who care about full visibility, They will just propagate the error to user space, and app can check if err == -EREMOTEIO, then outbox.{status,syndrome} are valid. API Note: mlx5_cmd_check() must be used by kernel users since it allows the driver to intercept the command execution status and return a driver simulated status in case of driver induced error handling or reset/recovery flows. Signed-off-by: Saeed Mahameed Signed-off-by: Saeed Mahameed --- include/linux/mlx5/cq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 7bfb67363434..cb15308b5cb0 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -183,6 +183,8 @@ static inline void mlx5_cq_put(struct mlx5_core_cq *cq) complete(&cq->free); } +int mlx5_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, + u32 *in, int inlen, u32 *out, int outlen); int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, u32 *in, int inlen, u32 *out, int outlen); int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq); -- cgit v1.2.3 From 0a41527608e7f3da61e76564f5a8749a1fddc7f1 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Tue, 31 Mar 2020 22:03:00 -0700 Subject: net/mlx5: cmdif, Refactor error handling and reporting of async commands Same as the new mlx5_cmd_do API, report all information to callers and let them handle the error values and outbox parsing. The user callback status "work->user_callback(status)" is now similar to the error rc code returned from the blocking mlx5_cmd_do() version, and now is defined as follows: -EREMOTEIO : Command executed by FW, outbox.status != MLX5_CMD_STAT_OK. Caller must check FW outbox status. 0 : Command execution successful, outbox.status == MLX5_CMD_STAT_OK. < 0 : Command couldn't execute, FW or driver induced error. Signed-off-by: Saeed Mahameed Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 1b9bec8fa870..432151d7d0bf 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -955,6 +955,7 @@ typedef void (*mlx5_async_cbk_t)(int status, struct mlx5_async_work *context); struct mlx5_async_work { struct mlx5_async_ctx *ctx; mlx5_async_cbk_t user_callback; + void *out; /* pointer to the cmd output buffer */ }; void mlx5_cmd_init_async_ctx(struct mlx5_core_dev *dev, @@ -963,7 +964,7 @@ void mlx5_cmd_cleanup_async_ctx(struct mlx5_async_ctx *ctx); int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, void *out, int out_size, mlx5_async_cbk_t callback, struct mlx5_async_work *work); - +void mlx5_cmd_out_err(struct mlx5_core_dev *dev, u16 opcode, u16 op_mod, void *out); int mlx5_cmd_do(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); int mlx5_cmd_check(struct mlx5_core_dev *dev, int err, void *in, void *out); int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, -- cgit v1.2.3 From 72fb3b60a3114a1154a8ae5629ea3b43a88a7a4d Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Sat, 14 Aug 2021 17:57:51 +0300 Subject: net/mlx5: Add reset_state field to MFRL register Add new field reset_state to MFRL register. This field expose current state of sync reset for fw update. This field enables sharing with the user more details on why fw activate failed in case it failed the sync reset stage. Signed-off-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 598ac3bcc901..8ca2d65ff789 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -9694,7 +9694,8 @@ struct mlx5_ifc_pcam_reg_bits { }; struct mlx5_ifc_mcam_enhanced_features_bits { - u8 reserved_at_0[0x6b]; + u8 reserved_at_0[0x6a]; + u8 reset_state[0x1]; u8 ptpcyc2realtime_modify[0x1]; u8 reserved_at_6c[0x2]; u8 pci_status_and_power[0x1]; @@ -10375,6 +10376,14 @@ struct mlx5_ifc_mcda_reg_bits { u8 data[][0x20]; }; +enum { + MLX5_MFRL_REG_RESET_STATE_IDLE = 0, + MLX5_MFRL_REG_RESET_STATE_IN_NEGOTIATION = 1, + MLX5_MFRL_REG_RESET_STATE_RESET_IN_PROGRESS = 2, + MLX5_MFRL_REG_RESET_STATE_TIMEOUT = 3, + MLX5_MFRL_REG_RESET_STATE_NACK = 4, +}; + enum { MLX5_MFRL_REG_RESET_TYPE_FULL_CHIP = BIT(0), MLX5_MFRL_REG_RESET_TYPE_NET_PORT_ALIVE = BIT(1), @@ -10393,7 +10402,8 @@ struct mlx5_ifc_mfrl_reg_bits { u8 pci_sync_for_fw_update_start[0x1]; u8 pci_sync_for_fw_update_resp[0x2]; u8 rst_type_sel[0x3]; - u8 reserved_at_28[0x8]; + u8 reserved_at_28[0x4]; + u8 reset_state[0x4]; u8 reset_type[0x8]; u8 reset_level[0x8]; }; -- cgit v1.2.3 From 45fee8edb4b333af79efad7a99de51718ebda94b Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Mon, 6 Sep 2021 11:02:44 +0300 Subject: net/mlx5: Add clarification on sync reset failure In case devlink reload action fw_activate failed in sync reset stage, use the new MFRL field reset_state to find why it failed and share this clarification with the user. Signed-off-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 432151d7d0bf..d3b1a6a1f8d2 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1031,6 +1031,9 @@ int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn) void mlx5_qp_debugfs_init(struct mlx5_core_dev *dev); void mlx5_qp_debugfs_cleanup(struct mlx5_core_dev *dev); +int mlx5_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in, + void *data_out, int size_out, u16 reg_id, int arg, + int write, bool verbose); int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in, void *data_out, int size_out, u16 reg_num, int arg, int write); -- cgit v1.2.3 From 1241e329ce2e1f5b1039fd356b75867b29721ad2 Mon Sep 17 00:00:00 2001 From: Subbaraya Sundeep Date: Wed, 23 Feb 2022 00:09:12 +0530 Subject: ethtool: add support to set/get completion queue event size Add support to set completion queue event size via ethtool -G parameter and get it via ethtool -g parameter. ~ # ./ethtool -G eth0 cqe-size 512 ~ # ./ethtool -g eth0 Ring parameters for eth0: Pre-set maximums: RX: 1048576 RX Mini: n/a RX Jumbo: n/a TX: 1048576 Current hardware settings: RX: 256 RX Mini: n/a RX Jumbo: n/a TX: 4096 RX Buf Len: 2048 CQE Size: 128 Signed-off-by: Subbaraya Sundeep Signed-off-by: Sunil Goutham Signed-off-by: Jakub Kicinski --- include/linux/ethtool.h | 4 ++++ include/uapi/linux/ethtool_netlink.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index e0853f48b75e..4af58459a1e7 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -71,18 +71,22 @@ enum { * struct kernel_ethtool_ringparam - RX/TX ring configuration * @rx_buf_len: Current length of buffers on the rx ring. * @tcp_data_split: Scatter packet headers and data to separate buffers + * @cqe_size: Size of TX/RX completion queue event */ struct kernel_ethtool_ringparam { u32 rx_buf_len; u8 tcp_data_split; + u32 cqe_size; }; /** * enum ethtool_supported_ring_param - indicator caps for setting ring params * @ETHTOOL_RING_USE_RX_BUF_LEN: capture for setting rx_buf_len + * @ETHTOOL_RING_USE_CQE_SIZE: capture for setting cqe_size */ enum ethtool_supported_ring_param { ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0), + ETHTOOL_RING_USE_CQE_SIZE = BIT(1), }; #define __ETH_RSS_HASH_BIT(bit) ((u32)1 << (bit)) diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 417d4280d7b5..979850221b8d 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -337,6 +337,7 @@ enum { ETHTOOL_A_RINGS_TX, /* u32 */ ETHTOOL_A_RINGS_RX_BUF_LEN, /* u32 */ ETHTOOL_A_RINGS_TCP_DATA_SPLIT, /* u8 */ + ETHTOOL_A_RINGS_CQE_SIZE, /* u32 */ /* add new constants above here */ __ETHTOOL_A_RINGS_CNT, -- cgit v1.2.3 From 5597f082fcaf17e2d9adee7a1f6fa02f5872f9d5 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Thu, 13 Jan 2022 15:34:07 +0100 Subject: can: bittiming: mark function arguments and local variables as const This patch marks the arguments of some functions as well as some local variables as constant. Link: https://lore.kernel.org/all/20220124215642.3474154-7-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/bittiming.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/can/bittiming.h b/include/linux/can/bittiming.h index a81652d1c6f3..7ae21c0f7f23 100644 --- a/include/linux/can/bittiming.h +++ b/include/linux/can/bittiming.h @@ -113,7 +113,7 @@ struct can_tdc_const { }; #ifdef CONFIG_CAN_CALC_BITTIMING -int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt, +int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, const struct can_bittiming_const *btc); void can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, @@ -121,7 +121,7 @@ void can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, u32 *ctrlmode, u32 ctrlmode_supported); #else /* !CONFIG_CAN_CALC_BITTIMING */ static inline int -can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt, +can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, const struct can_bittiming_const *btc) { netdev_err(dev, "bit-timing calculation not available\n"); @@ -136,7 +136,7 @@ can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, } #endif /* CONFIG_CAN_CALC_BITTIMING */ -int can_get_bittiming(struct net_device *dev, struct can_bittiming *bt, +int can_get_bittiming(const struct net_device *dev, struct can_bittiming *bt, const struct can_bittiming_const *btc, const u32 *bitrate_const, const unsigned int bitrate_const_cnt); -- cgit v1.2.3 From 05f2281b4192320a20d746df6146b3dd82f96e39 Mon Sep 17 00:00:00 2001 From: Ricardo Rivera-Matos Date: Mon, 14 Feb 2022 18:07:56 -0600 Subject: power: supply: Introduces bypass charging property Adds a POWER_SUPPLY_CHARGE_TYPE_BYPASS option to the POWER_SUPPLY_PROP_CHARGE_TYPE property to facilitate bypass charging operation. In bypass charging operation, the charger bypasses the charging path around the integrated converter allowing for a "smart" wall adaptor to perform the power conversion externally. This operational mode is critical for the USB PPS standard of power adaptors and is becoming a common feature in modern charging ICs such as: - BQ25980 - BQ25975 - BQ25960 - LN8000 - LN8410 Signed-off-by: Ricardo Rivera-Matos Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 006111917d1a..c135196aa9d1 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -49,6 +49,7 @@ enum { POWER_SUPPLY_CHARGE_TYPE_ADAPTIVE, /* dynamically adjusted speed */ POWER_SUPPLY_CHARGE_TYPE_CUSTOM, /* use CHARGE_CONTROL_* props */ POWER_SUPPLY_CHARGE_TYPE_LONGLIFE, /* slow speed, longer life */ + POWER_SUPPLY_CHARGE_TYPE_BYPASS, /* bypassing the charger */ }; enum { -- cgit v1.2.3 From a3a59919ab662682a2cb77b25b0f7b9e6c78737e Mon Sep 17 00:00:00 2001 From: Jean-Jacques Hiblot Date: Mon, 21 Feb 2022 10:50:27 +0100 Subject: dt-bindings: clock: r9a06g032: Add the definition of the watchdog clock This clock is actually the REF_SYNC_D8 clock. Signed-off-by: Jean-Jacques Hiblot Acked-by: Rob Herring Link: https://lore.kernel.org/r/20220221095032.95054-2-jjhiblot@traphandler.com Signed-off-by: Geert Uytterhoeven --- include/dt-bindings/clock/r9a06g032-sysctrl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/clock/r9a06g032-sysctrl.h b/include/dt-bindings/clock/r9a06g032-sysctrl.h index 90c0f3dc1ba1..d9d7b8b4f426 100644 --- a/include/dt-bindings/clock/r9a06g032-sysctrl.h +++ b/include/dt-bindings/clock/r9a06g032-sysctrl.h @@ -74,6 +74,7 @@ #define R9A06G032_CLK_DDRPHY_PCLK 81 /* AKA CLK_REF_SYNC_D4 */ #define R9A06G032_CLK_FW 81 /* AKA CLK_REF_SYNC_D4 */ #define R9A06G032_CLK_CRYPTO 81 /* AKA CLK_REF_SYNC_D4 */ +#define R9A06G032_CLK_WATCHDOG 82 /* AKA CLK_REF_SYNC_D8 */ #define R9A06G032_CLK_A7MP 84 /* AKA DIV_CA7 */ #define R9A06G032_HCLK_CAN0 85 #define R9A06G032_HCLK_CAN1 86 -- cgit v1.2.3 From 4f0b903ded728c505850daf2914bfc08841f0ae6 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 23 Feb 2022 17:14:37 +0200 Subject: fsnotify: fix merge with parent's ignored mask fsnotify_parent() does not consider the parent's mark at all unless the parent inode shows interest in events on children and in the specific event. So unless parent added an event to both its mark mask and ignored mask, the event will not be ignored. Fix this by declaring the interest of an object in an event when the event is in either a mark mask or ignored mask. Link: https://lore.kernel.org/r/20220223151438.790268-2-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 790c31844db5..5f9c960049b0 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -601,6 +601,21 @@ extern void fsnotify_remove_queued_event(struct fsnotify_group *group, /* functions used to manipulate the marks attached to inodes */ +/* Get mask for calculating object interest taking ignored mask into account */ +static inline __u32 fsnotify_calc_mask(struct fsnotify_mark *mark) +{ + __u32 mask = mark->mask; + + if (!mark->ignored_mask) + return mask; + + /* + * If mark is interested in ignoring events on children, the object must + * show interest in those events for fsnotify_parent() to notice it. + */ + return mask | (mark->ignored_mask & ALL_FSNOTIFY_EVENTS); +} + /* Get mask of events for a list of marks */ extern __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn); /* Calculate mask of events for a list of marks */ -- cgit v1.2.3 From 04e317ba72d07901b03399b3d1525e83424df5b3 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 23 Feb 2022 17:14:38 +0200 Subject: fsnotify: optimize FS_MODIFY events with no ignored masks fsnotify() treats FS_MODIFY events specially - it does not skip them even if the FS_MODIFY event does not apear in the object's fsnotify mask. This is because send_to_group() checks if FS_MODIFY needs to clear ignored mask of marks. The common case is that an object does not have any mark with ignored mask and in particular, that it does not have a mark with ignored mask and without the FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY flag. Set FS_MODIFY in object's fsnotify mask during fsnotify_recalc_mask() if object has a mark with an ignored mask and without the FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY flag and remove the special treatment of FS_MODIFY in fsnotify(), so that FS_MODIFY events could be optimized in the common case. Call fsnotify_recalc_mask() from fanotify after adding or removing an ignored mask from a mark without FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY or when adding the FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY flag to a mark with ignored mask (the flag cannot be removed by fanotify uapi). Performance results for doing 10000000 write(2)s to tmpfs: vanilla patched without notification mark 25.486+-1.054 24.965+-0.244 with notification mark 30.111+-0.139 26.891+-1.355 So we can see the overhead of notification subsystem has been drastically reduced. Link: https://lore.kernel.org/r/20220223151438.790268-3-amir73il@gmail.com Suggested-by: Jan Kara Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 5f9c960049b0..0805b74cae44 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -609,6 +609,10 @@ static inline __u32 fsnotify_calc_mask(struct fsnotify_mark *mark) if (!mark->ignored_mask) return mask; + /* Interest in FS_MODIFY may be needed for clearing ignored mask */ + if (!(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) + mask |= FS_MODIFY; + /* * If mark is interested in ignoring events on children, the object must * show interest in those events for fsnotify_parent() to notice it. -- cgit v1.2.3 From 0cc62aed370d91ec3d5cf258e53028c736e88a09 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 21 Jan 2022 08:42:21 +0000 Subject: sizes.h: Add SZ_1T macro MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Today drivers/pci/controller/pci-xgene.c defines SZ_1T Move it into linux/sizes.h so that it can be re-used elsewhere. Link: https://lore.kernel.org/r/575cb7164cf124c75df7cb9242ea7374733942bf.1642752946.git.christophe.leroy@csgroup.eu Signed-off-by: Christophe Leroy Signed-off-by: Lorenzo Pieralisi Reviewed-by: Krzysztof Wilczyński Acked-by: Bjorn Helgaas Cc: Toan Le Cc: linux-pci@vger.kernel.org --- include/linux/sizes.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/sizes.h b/include/linux/sizes.h index 1ac79bcee2bb..84aa448d8bb3 100644 --- a/include/linux/sizes.h +++ b/include/linux/sizes.h @@ -47,6 +47,8 @@ #define SZ_8G _AC(0x200000000, ULL) #define SZ_16G _AC(0x400000000, ULL) #define SZ_32G _AC(0x800000000, ULL) + +#define SZ_1T _AC(0x10000000000, ULL) #define SZ_64T _AC(0x400000000000, ULL) #endif /* __LINUX_SIZES_H__ */ -- cgit v1.2.3 From c6e7deb0f092616bd8cb19e8c436b212c64daaab Mon Sep 17 00:00:00 2001 From: Stanislav Lisovskiy Date: Tue, 18 Jan 2022 13:55:43 +0200 Subject: drm/i915: Introduce new Tile 4 format This tiling layout uses 4KB tiles in a row-major layout. It has the same shape as Tile Y at two granularities: 4KB (128B x 32) and 64B (16B x 4). It only differs from Tile Y at the 256B granularity in between. At this granularity, Tile Y has a shape of 16B x 32 rows, but this tiling has a shape of 64B x 8 rows. Reviewed-by: Imre Deak Acked-by: Nanley Chery Signed-off-by: Stanislav Lisovskiy Link: https://patchwork.freedesktop.org/patch/msgid/20220118115544.15116-2-stanislav.lisovskiy@intel.com --- include/uapi/drm/drm_fourcc.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index fc0c1454d275..b73fe6797fc3 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -572,6 +572,17 @@ extern "C" { */ #define I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC fourcc_mod_code(INTEL, 8) +/* + * Intel Tile 4 layout + * + * This is a tiled layout using 4KB tiles in a row-major layout. It has the same + * shape as Tile Y at two granularities: 4KB (128B x 32) and 64B (16B x 4). It + * only differs from Tile Y at the 256B granularity in between. At this + * granularity, Tile Y has a shape of 16B x 32 rows, but this tiling has a shape + * of 64B x 8 rows. + */ +#define I915_FORMAT_MOD_4_TILED fourcc_mod_code(INTEL, 9) + /* * Tiled, NV12MT, grouped in 64 (pixels) x 32 (lines) -sized macroblocks * -- cgit v1.2.3 From 07d743902a1205d54d93c0637c22575811014431 Mon Sep 17 00:00:00 2001 From: Mohan Kumar Date: Wed, 16 Feb 2022 14:52:38 +0530 Subject: dt-bindings: Add HDA support for Tegra234 Add hda clocks, memory ,power and reset binding entries for Tegra234. Signed-off-by: Mohan Kumar Signed-off-by: Thierry Reding --- include/dt-bindings/clock/tegra234-clock.h | 4 ++++ include/dt-bindings/memory/tegra234-mc.h | 5 +++++ include/dt-bindings/power/tegra234-powergate.h | 1 + include/dt-bindings/reset/tegra234-reset.h | 2 ++ 4 files changed, 12 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/clock/tegra234-clock.h b/include/dt-bindings/clock/tegra234-clock.h index 5c201a8278ff..0c38769c4a76 100644 --- a/include/dt-bindings/clock/tegra234-clock.h +++ b/include/dt-bindings/clock/tegra234-clock.h @@ -136,4 +136,8 @@ #define TEGRA234_CLK_PLLC4 237U /** @brief 32K input clock provided by PMIC */ #define TEGRA234_CLK_CLK_32K 289U +/** @brief CLK_RST_CONTROLLER_AZA2XBITCLK_OUT_SWITCH_DIVIDER switch divider output (aza_2xbitclk) */ +#define TEGRA234_CLK_AZA_2XBIT 457U +/** @brief aza_2xbitclk / 2 (aza_bitclk) */ +#define TEGRA234_CLK_AZA_BIT 458U #endif diff --git a/include/dt-bindings/memory/tegra234-mc.h b/include/dt-bindings/memory/tegra234-mc.h index 42661dda1c53..672b953cadd3 100644 --- a/include/dt-bindings/memory/tegra234-mc.h +++ b/include/dt-bindings/memory/tegra234-mc.h @@ -10,6 +10,7 @@ /* NISO0 stream IDs */ #define TEGRA234_SID_APE 0x02 +#define TEGRA234_SID_HDA 0x03 /* NISO1 stream IDs */ #define TEGRA234_SID_SDMMC4 0x02 @@ -19,6 +20,10 @@ * memory client IDs */ +/* High-definition audio (HDA) read clients */ +#define TEGRA234_MEMORY_CLIENT_HDAR 0x15 +/* High-definition audio (HDA) write clients */ +#define TEGRA234_MEMORY_CLIENT_HDAW 0x35 /* sdmmcd memory read client */ #define TEGRA234_MEMORY_CLIENT_SDMMCRAB 0x63 /* sdmmcd memory write client */ diff --git a/include/dt-bindings/power/tegra234-powergate.h b/include/dt-bindings/power/tegra234-powergate.h index 8e28fcbdc038..a635a8b53810 100644 --- a/include/dt-bindings/power/tegra234-powergate.h +++ b/include/dt-bindings/power/tegra234-powergate.h @@ -5,5 +5,6 @@ #define __ABI_MACH_T234_POWERGATE_T234_H_ #define TEGRA234_POWER_DOMAIN_AUD 2U +#define TEGRA234_POWER_DOMAIN_DISP 3U #endif diff --git a/include/dt-bindings/reset/tegra234-reset.h b/include/dt-bindings/reset/tegra234-reset.h index ba390b86361d..178e73a687f0 100644 --- a/include/dt-bindings/reset/tegra234-reset.h +++ b/include/dt-bindings/reset/tegra234-reset.h @@ -10,6 +10,8 @@ * @brief Identifiers for Resets controllable by firmware * @{ */ +#define TEGRA234_RESET_HDA 20U +#define TEGRA234_RESET_HDACODEC 21U #define TEGRA234_RESET_I2C1 24U #define TEGRA234_RESET_I2C2 29U #define TEGRA234_RESET_I2C3 30U -- cgit v1.2.3 From d06a171e07bc6aa524b402c754611ef08a34b131 Mon Sep 17 00:00:00 2001 From: Vidya Sagar Date: Sat, 5 Feb 2022 21:51:35 +0530 Subject: dt-bindings: Add Tegra234 PCIe clocks and resets Add the clocks and resets used by the PCIe hardware found on Tegra234 SoCs. Signed-off-by: Vidya Sagar Acked-by: Rob Herring Signed-off-by: Thierry Reding --- include/dt-bindings/clock/tegra234-clock.h | 22 ++++++++++++++++++++++ include/dt-bindings/reset/tegra234-reset.h | 27 ++++++++++++++++++++++++++- 2 files changed, 48 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/clock/tegra234-clock.h b/include/dt-bindings/clock/tegra234-clock.h index 0c38769c4a76..8cae969e8cba 100644 --- a/include/dt-bindings/clock/tegra234-clock.h +++ b/include/dt-bindings/clock/tegra234-clock.h @@ -130,8 +130,30 @@ #define TEGRA234_CLK_SYNC_I2S6 150U /** @brief output of mux controlled by CLK_RST_CONTROLLER_CLK_SOURCE_UARTA */ #define TEGRA234_CLK_UARTA 155U +/** @brief output of gate CLK_ENB_PEX1_CORE_6 */ +#define TEGRA234_CLK_PEX1_C6_CORE 161U +/** @brief output of gate CLK_ENB_PEX2_CORE_7 */ +#define TEGRA234_CLK_PEX2_C7_CORE 171U +/** @brief output of gate CLK_ENB_PEX2_CORE_8 */ +#define TEGRA234_CLK_PEX2_C8_CORE 172U +/** @brief output of gate CLK_ENB_PEX2_CORE_9 */ +#define TEGRA234_CLK_PEX2_C9_CORE 173U +/** @brief output of gate CLK_ENB_PEX2_CORE_10 */ +#define TEGRA234_CLK_PEX2_C10_CORE 187U /** @brief CLK_RST_CONTROLLER_CLK_SOURCE_SDMMC_LEGACY_TM switch divider output */ #define TEGRA234_CLK_SDMMC_LEGACY_TM 219U +/** @brief output of gate CLK_ENB_PEX0_CORE_0 */ +#define TEGRA234_CLK_PEX0_C0_CORE 220U +/** @brief output of gate CLK_ENB_PEX0_CORE_1 */ +#define TEGRA234_CLK_PEX0_C1_CORE 221U +/** @brief output of gate CLK_ENB_PEX0_CORE_2 */ +#define TEGRA234_CLK_PEX0_C2_CORE 222U +/** @brief output of gate CLK_ENB_PEX0_CORE_3 */ +#define TEGRA234_CLK_PEX0_C3_CORE 223U +/** @brief output of gate CLK_ENB_PEX0_CORE_4 */ +#define TEGRA234_CLK_PEX0_C4_CORE 224U +/** @brief output of gate CLK_ENB_PEX1_CORE_5 */ +#define TEGRA234_CLK_PEX1_C5_CORE 225U /** @brief PLL controlled by CLK_RST_CONTROLLER_PLLC4_BASE */ #define TEGRA234_CLK_PLLC4 237U /** @brief 32K input clock provided by PMIC */ diff --git a/include/dt-bindings/reset/tegra234-reset.h b/include/dt-bindings/reset/tegra234-reset.h index 178e73a687f0..1362cd5e03f0 100644 --- a/include/dt-bindings/reset/tegra234-reset.h +++ b/include/dt-bindings/reset/tegra234-reset.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (c) 2018-2020, NVIDIA CORPORATION. All rights reserved. */ +/* Copyright (c) 2018-2022, NVIDIA CORPORATION. All rights reserved. */ #ifndef DT_BINDINGS_RESET_TEGRA234_RESET_H #define DT_BINDINGS_RESET_TEGRA234_RESET_H @@ -10,9 +10,18 @@ * @brief Identifiers for Resets controllable by firmware * @{ */ +#define TEGRA234_RESET_PEX1_CORE_6 11U +#define TEGRA234_RESET_PEX1_CORE_6_APB 12U +#define TEGRA234_RESET_PEX1_COMMON_APB 13U +#define TEGRA234_RESET_PEX2_CORE_7 14U +#define TEGRA234_RESET_PEX2_CORE_7_APB 15U #define TEGRA234_RESET_HDA 20U #define TEGRA234_RESET_HDACODEC 21U #define TEGRA234_RESET_I2C1 24U +#define TEGRA234_RESET_PEX2_CORE_8 25U +#define TEGRA234_RESET_PEX2_CORE_8_APB 26U +#define TEGRA234_RESET_PEX2_CORE_9 27U +#define TEGRA234_RESET_PEX2_CORE_9_APB 28U #define TEGRA234_RESET_I2C2 29U #define TEGRA234_RESET_I2C3 30U #define TEGRA234_RESET_I2C4 31U @@ -20,6 +29,9 @@ #define TEGRA234_RESET_I2C7 33U #define TEGRA234_RESET_I2C8 34U #define TEGRA234_RESET_I2C9 35U +#define TEGRA234_RESET_PEX2_CORE_10 56U +#define TEGRA234_RESET_PEX2_CORE_10_APB 57U +#define TEGRA234_RESET_PEX2_COMMON_APB 58U #define TEGRA234_RESET_PWM1 68U #define TEGRA234_RESET_PWM2 69U #define TEGRA234_RESET_PWM3 70U @@ -30,6 +42,19 @@ #define TEGRA234_RESET_PWM8 75U #define TEGRA234_RESET_SDMMC4 85U #define TEGRA234_RESET_UARTA 100U +#define TEGRA234_RESET_PEX0_CORE_0 116U +#define TEGRA234_RESET_PEX0_CORE_1 117U +#define TEGRA234_RESET_PEX0_CORE_2 118U +#define TEGRA234_RESET_PEX0_CORE_3 119U +#define TEGRA234_RESET_PEX0_CORE_4 120U +#define TEGRA234_RESET_PEX0_CORE_0_APB 121U +#define TEGRA234_RESET_PEX0_CORE_1_APB 122U +#define TEGRA234_RESET_PEX0_CORE_2_APB 123U +#define TEGRA234_RESET_PEX0_CORE_3_APB 124U +#define TEGRA234_RESET_PEX0_CORE_4_APB 125U +#define TEGRA234_RESET_PEX0_COMMON_APB 126U +#define TEGRA234_RESET_PEX1_CORE_5 129U +#define TEGRA234_RESET_PEX1_CORE_5_APB 130U /** @} */ -- cgit v1.2.3 From 6460278f6faf31cae753f0e94c6ba8483b272612 Mon Sep 17 00:00:00 2001 From: Vidya Sagar Date: Sat, 5 Feb 2022 21:51:36 +0530 Subject: dt-bindings: power: Add Tegra234 PCIe power domains Add power domain IDs for the four PCIe power partitions found on Tegra234. Signed-off-by: Vidya Sagar Acked-by: Rob Herring Signed-off-by: Thierry Reding --- include/dt-bindings/power/tegra234-powergate.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/power/tegra234-powergate.h b/include/dt-bindings/power/tegra234-powergate.h index a635a8b53810..f610eee9bce8 100644 --- a/include/dt-bindings/power/tegra234-powergate.h +++ b/include/dt-bindings/power/tegra234-powergate.h @@ -6,5 +6,17 @@ #define TEGRA234_POWER_DOMAIN_AUD 2U #define TEGRA234_POWER_DOMAIN_DISP 3U +#define TEGRA234_POWER_DOMAIN_PCIEX8A 5U +#define TEGRA234_POWER_DOMAIN_PCIEX4A 6U +#define TEGRA234_POWER_DOMAIN_PCIEX4BA 7U +#define TEGRA234_POWER_DOMAIN_PCIEX4BB 8U +#define TEGRA234_POWER_DOMAIN_PCIEX1A 9U +#define TEGRA234_POWER_DOMAIN_PCIEX4CA 13U +#define TEGRA234_POWER_DOMAIN_PCIEX4CB 14U +#define TEGRA234_POWER_DOMAIN_PCIEX4CC 15U +#define TEGRA234_POWER_DOMAIN_PCIEX8B 16U +#define TEGRA234_POWER_DOMAIN_MGBEA 17U +#define TEGRA234_POWER_DOMAIN_MGBEB 18U +#define TEGRA234_POWER_DOMAIN_MGBEC 19U #endif -- cgit v1.2.3 From a4ad66da3fccebdcbd53d55c035d5851b73f8bcb Mon Sep 17 00:00:00 2001 From: Vidya Sagar Date: Sat, 5 Feb 2022 21:51:37 +0530 Subject: dt-bindings: memory: Add Tegra234 PCIe memory Add the memory client and stream ID definitions for the PCIe hardware found on Tegra234 SoCs. Signed-off-by: Vidya Sagar Acked-by: Rob Herring Signed-off-by: Thierry Reding --- include/dt-bindings/memory/tegra234-mc.h | 63 ++++++++++++++++++++++++++++++++ 1 file changed, 63 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/memory/tegra234-mc.h b/include/dt-bindings/memory/tegra234-mc.h index 672b953cadd3..e3b0e9da295d 100644 --- a/include/dt-bindings/memory/tegra234-mc.h +++ b/include/dt-bindings/memory/tegra234-mc.h @@ -11,9 +11,20 @@ /* NISO0 stream IDs */ #define TEGRA234_SID_APE 0x02 #define TEGRA234_SID_HDA 0x03 +#define TEGRA234_SID_PCIE0 0x12 +#define TEGRA234_SID_PCIE4 0x13 +#define TEGRA234_SID_PCIE5 0x14 +#define TEGRA234_SID_PCIE6 0x15 +#define TEGRA234_SID_PCIE9 0x1f /* NISO1 stream IDs */ #define TEGRA234_SID_SDMMC4 0x02 +#define TEGRA234_SID_PCIE1 0x05 +#define TEGRA234_SID_PCIE2 0x06 +#define TEGRA234_SID_PCIE3 0x07 +#define TEGRA234_SID_PCIE7 0x08 +#define TEGRA234_SID_PCIE8 0x09 +#define TEGRA234_SID_PCIE10 0x0b #define TEGRA234_SID_BPMP 0x10 /* @@ -22,8 +33,34 @@ /* High-definition audio (HDA) read clients */ #define TEGRA234_MEMORY_CLIENT_HDAR 0x15 +/* PCIE6 read clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE6AR 0x28 +/* PCIE6 write clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE6AW 0x29 +/* PCIE7 read clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE7AR 0x2a +/* PCIE7 write clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE7AW 0x30 +/* PCIE8 read clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE8AR 0x32 /* High-definition audio (HDA) write clients */ #define TEGRA234_MEMORY_CLIENT_HDAW 0x35 +/* PCIE8 write clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE8AW 0x3b +/* PCIE9 read clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE9AR 0x3c +/* PCIE6r1 read clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE6AR1 0x3d +/* PCIE9 write clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE9AW 0x3e +/* PCIE10 read clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE10AR 0x3f +/* PCIE10 write clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE10AW 0x40 +/* PCIE10r1 read clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE10AR1 0x48 +/* PCIE7r1 read clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE7AR1 0x49 /* sdmmcd memory read client */ #define TEGRA234_MEMORY_CLIENT_SDMMCRAB 0x63 /* sdmmcd memory write client */ @@ -40,5 +77,31 @@ #define TEGRA234_MEMORY_CLIENT_APEDMAR 0x9f /* APEDMA write client */ #define TEGRA234_MEMORY_CLIENT_APEDMAW 0xa0 +/* PCIE0 read clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE0R 0xd8 +/* PCIE0 write clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE0W 0xd9 +/* PCIE1 read clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE1R 0xda +/* PCIE1 write clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE1W 0xdb +/* PCIE2 read clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE2AR 0xdc +/* PCIE2 write clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE2AW 0xdd +/* PCIE3 read clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE3R 0xde +/* PCIE3 write clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE3W 0xdf +/* PCIE4 read clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE4R 0xe0 +/* PCIE4 write clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE4W 0xe1 +/* PCIE5 read clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE5R 0xe2 +/* PCIE5 write clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE5W 0xe3 +/* PCIE5r1 read clients */ +#define TEGRA234_MEMORY_CLIENT_PCIE5R1 0xef #endif -- cgit v1.2.3 From d148363684a41162a835c1803c02cfd90b22b2c6 Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Sun, 20 Feb 2022 23:30:01 +0100 Subject: dt-bindings: power: rpmpd: Add MSM8226 to rpmpd binding Add compatible and constants for the power domains exposed by the MSM8226 RPM. Signed-off-by: Luca Weiss Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220220223004.507739-1-luca@z3ntu.xyz --- include/dt-bindings/power/qcom-rpmpd.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/power/qcom-rpmpd.h b/include/dt-bindings/power/qcom-rpmpd.h index edfc1ff2acb3..c002cc6ddf55 100644 --- a/include/dt-bindings/power/qcom-rpmpd.h +++ b/include/dt-bindings/power/qcom-rpmpd.h @@ -139,6 +139,11 @@ #define MDM9607_VDDMX_AO 4 #define MDM9607_VDDMX_VFL 5 +/* MSM8226 Power Domain Indexes */ +#define MSM8226_VDDCX 0 +#define MSM8226_VDDCX_AO 1 +#define MSM8226_VDDCX_VFC 2 + /* MSM8939 Power Domains */ #define MSM8939_VDDMDCX 0 #define MSM8939_VDDMDCX_AO 1 -- cgit v1.2.3 From 46a76724e4c93bb1cda8ee11276001a92d1f7987 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 23 Feb 2022 16:00:44 +0200 Subject: net: dsa: rename references to "lag" as "lag_dev" In preparation of converting struct net_device *dp->lag_dev into a struct dsa_lag *dp->lag, we need to rename, for consistency purposes, all occurrences of the "lag" variable in the DSA core to "lag_dev". Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index f13de2d8aef3..ef7f446cbdf4 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -182,12 +182,12 @@ static inline struct net_device *dsa_lag_dev(struct dsa_switch_tree *dst, } static inline int dsa_lag_id(struct dsa_switch_tree *dst, - struct net_device *lag) + struct net_device *lag_dev) { unsigned int id; dsa_lags_foreach_id(id, dst) { - if (dsa_lag_dev(dst, id) == lag) + if (dsa_lag_dev(dst, id) == lag_dev) return id; } @@ -966,10 +966,10 @@ struct dsa_switch_ops { int (*crosschip_lag_change)(struct dsa_switch *ds, int sw_index, int port); int (*crosschip_lag_join)(struct dsa_switch *ds, int sw_index, - int port, struct net_device *lag, + int port, struct net_device *lag_dev, struct netdev_lag_upper_info *info); int (*crosschip_lag_leave)(struct dsa_switch *ds, int sw_index, - int port, struct net_device *lag); + int port, struct net_device *lag_dev); /* * PTP functionality @@ -1041,10 +1041,10 @@ struct dsa_switch_ops { */ int (*port_lag_change)(struct dsa_switch *ds, int port); int (*port_lag_join)(struct dsa_switch *ds, int port, - struct net_device *lag, + struct net_device *lag_dev, struct netdev_lag_upper_info *info); int (*port_lag_leave)(struct dsa_switch *ds, int port, - struct net_device *lag); + struct net_device *lag_dev); /* * HSR integration -- cgit v1.2.3 From 3d4a0a2a46ab8ff8897dfd6324edee5e8184d2c5 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 23 Feb 2022 16:00:47 +0200 Subject: net: dsa: make LAG IDs one-based The DSA LAG API will be changed to become more similar with the bridge data structures, where struct dsa_bridge holds an unsigned int num, which is generated by DSA and is one-based. We have a similar thing going with the DSA LAG, except that isn't stored anywhere, it is calculated dynamically by dsa_lag_id() by iterating through dst->lags. The idea of encoding an invalid (or not requested) LAG ID as zero for the purpose of simplifying checks in drivers means that the LAG IDs passed by DSA to drivers need to be one-based too. So back-and-forth conversion is needed when indexing the dst->lags array, as well as in drivers which assume a zero-based index. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index ef7f446cbdf4..3ae93adda25d 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -163,9 +163,10 @@ struct dsa_switch_tree { unsigned int last_switch; }; +/* LAG IDs are one-based, the dst->lags array is zero-based */ #define dsa_lags_foreach_id(_id, _dst) \ - for ((_id) = 0; (_id) < (_dst)->lags_len; (_id)++) \ - if ((_dst)->lags[(_id)]) + for ((_id) = 1; (_id) <= (_dst)->lags_len; (_id)++) \ + if ((_dst)->lags[(_id) - 1]) #define dsa_lag_foreach_port(_dp, _dst, _lag) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ @@ -178,7 +179,8 @@ struct dsa_switch_tree { static inline struct net_device *dsa_lag_dev(struct dsa_switch_tree *dst, unsigned int id) { - return dst->lags[id]; + /* DSA LAG IDs are one-based, dst->lags is zero-based */ + return dst->lags[id - 1]; } static inline int dsa_lag_id(struct dsa_switch_tree *dst, -- cgit v1.2.3 From dedd6a009f4191989bee83c1faf66728648a223f Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 23 Feb 2022 16:00:49 +0200 Subject: net: dsa: create a dsa_lag structure The main purpose of this change is to create a data structure for a LAG as seen by DSA. This is similar to what we have for bridging - we pass a copy of this structure by value to ->port_lag_join and ->port_lag_leave. For now we keep the lag_dev, id and a reference count in it. Future patches will add a list of FDB entries for the LAG (these also need to be refcounted to work properly). The LAG structure is created using dsa_port_lag_create() and destroyed using dsa_port_lag_destroy(), just like we have for bridging. Because now, the dsa_lag itself is refcounted, we can simplify dsa_lag_map() and dsa_lag_unmap(). These functions need to keep a LAG in the dst->lags array only as long as at least one port uses it. The refcounting logic inside those functions can be removed now - they are called only when we should perform the operation. dsa_lag_dev() is renamed to dsa_lag_by_id() and now returns the dsa_lag structure instead of the lag_dev net_device. dsa_lag_foreach_port() now takes the dsa_lag structure as argument. dst->lags holds an array of dsa_lag structures. dsa_lag_map() now also saves the dsa_lag->id value, so that linear walking of dst->lags in drivers using dsa_lag_id() is no longer necessary. They can just look at lag.id. dsa_port_lag_id_get() is a helper, similar to dsa_port_bridge_num_get(), which can be used by drivers to get the LAG ID assigned by DSA to a given port. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 50 +++++++++++++++++++++++++++++++++++++------------- 1 file changed, 37 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 3ae93adda25d..81ed34998416 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -116,6 +116,12 @@ struct dsa_netdevice_ops { #define MODULE_ALIAS_DSA_TAG_DRIVER(__proto) \ MODULE_ALIAS(DSA_TAG_DRIVER_ALIAS __stringify(__proto##_VALUE)) +struct dsa_lag { + struct net_device *dev; + unsigned int id; + refcount_t refcount; +}; + struct dsa_switch_tree { struct list_head list; @@ -134,7 +140,7 @@ struct dsa_switch_tree { /* Maps offloaded LAG netdevs to a zero-based linear ID for * drivers that need it. */ - struct net_device **lags; + struct dsa_lag **lags; /* Tagging protocol operations */ const struct dsa_device_ops *tag_ops; @@ -170,14 +176,14 @@ struct dsa_switch_tree { #define dsa_lag_foreach_port(_dp, _dst, _lag) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ - if ((_dp)->lag_dev == (_lag)) + if (dsa_port_offloads_lag((_dp), (_lag))) #define dsa_hsr_foreach_port(_dp, _ds, _hsr) \ list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds) && (_dp)->hsr_dev == (_hsr)) -static inline struct net_device *dsa_lag_dev(struct dsa_switch_tree *dst, - unsigned int id) +static inline struct dsa_lag *dsa_lag_by_id(struct dsa_switch_tree *dst, + unsigned int id) { /* DSA LAG IDs are one-based, dst->lags is zero-based */ return dst->lags[id - 1]; @@ -189,8 +195,10 @@ static inline int dsa_lag_id(struct dsa_switch_tree *dst, unsigned int id; dsa_lags_foreach_id(id, dst) { - if (dsa_lag_dev(dst, id) == lag_dev) - return id; + struct dsa_lag *lag = dsa_lag_by_id(dst, id); + + if (lag->dev == lag_dev) + return lag->id; } return -ENODEV; @@ -293,7 +301,7 @@ struct dsa_port { struct devlink_port devlink_port; struct phylink *pl; struct phylink_config pl_config; - struct net_device *lag_dev; + struct dsa_lag *lag; struct net_device *hsr_dev; struct list_head list; @@ -643,14 +651,30 @@ static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp) return dp->vlan_filtering; } +static inline unsigned int dsa_port_lag_id_get(struct dsa_port *dp) +{ + return dp->lag ? dp->lag->id : 0; +} + +static inline struct net_device *dsa_port_lag_dev_get(struct dsa_port *dp) +{ + return dp->lag ? dp->lag->dev : NULL; +} + +static inline bool dsa_port_offloads_lag(struct dsa_port *dp, + const struct dsa_lag *lag) +{ + return dsa_port_lag_dev_get(dp) == lag->dev; +} + static inline struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp) { if (!dp->bridge) return NULL; - if (dp->lag_dev) - return dp->lag_dev; + if (dp->lag) + return dp->lag->dev; else if (dp->hsr_dev) return dp->hsr_dev; @@ -968,10 +992,10 @@ struct dsa_switch_ops { int (*crosschip_lag_change)(struct dsa_switch *ds, int sw_index, int port); int (*crosschip_lag_join)(struct dsa_switch *ds, int sw_index, - int port, struct net_device *lag_dev, + int port, struct dsa_lag lag, struct netdev_lag_upper_info *info); int (*crosschip_lag_leave)(struct dsa_switch *ds, int sw_index, - int port, struct net_device *lag_dev); + int port, struct dsa_lag lag); /* * PTP functionality @@ -1043,10 +1067,10 @@ struct dsa_switch_ops { */ int (*port_lag_change)(struct dsa_switch *ds, int port); int (*port_lag_join)(struct dsa_switch *ds, int port, - struct net_device *lag_dev, + struct dsa_lag lag, struct netdev_lag_upper_info *info); int (*port_lag_leave)(struct dsa_switch *ds, int port, - struct net_device *lag_dev); + struct dsa_lag lag); /* * HSR integration -- cgit v1.2.3 From ec638740fce990ad2b9af43ead8088d6d6eb2145 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 23 Feb 2022 16:00:50 +0200 Subject: net: switchdev: remove lag_mod_cb from switchdev_handle_fdb_event_to_device When the switchdev_handle_fdb_event_to_device() event replication helper was created, my original thought was that FDB events on LAG interfaces should most likely be special-cased, not just replicated towards all switchdev ports beneath that LAG. So this replication helper currently does not recurse through switchdev lower interfaces of LAG bridge ports, but rather calls the lag_mod_cb() if that was provided. No switchdev driver uses this helper for FDB events on LAG interfaces yet, so that was an assumption which was yet to be tested. It is certainly usable for that purpose, as my RFC series shows: https://patchwork.kernel.org/project/netdevbpf/cover/20220210125201.2859463-1-vladimir.oltean@nxp.com/ however this approach is slightly convoluted because: - the switchdev driver gets a "dev" that isn't its own net device, but rather the LAG net device. It must call switchdev_lower_dev_find(dev) in order to get a handle of any of its own net devices (the ones that pass check_cb). - in order for FDB entries on LAG ports to be correctly refcounted per the number of switchdev ports beneath that LAG, we haven't escaped the need to iterate through the LAG's lower interfaces. Except that is now the responsibility of the switchdev driver, because the replication helper just stopped half-way. So, even though yes, FDB events on LAG bridge ports must be special-cased, in the end it's simpler to let switchdev_handle_fdb_* just iterate through the LAG port's switchdev lowers, and let the switchdev driver figure out that those physical ports are under a LAG. The switchdev_handle_fdb_event_to_device() helper takes a "foreign_dev_check" callback so it can figure out whether @dev can autonomously forward to @foreign_dev. DSA fills this method properly: if the LAG is offloaded by another port in the same tree as @dev, then it isn't foreign. If it is a software LAG, it is foreign - forwarding happens in software. Whether an interface is foreign or not decides whether the replication helper will go through the LAG's switchdev lowers or not. Since the lan966x doesn't properly fill this out, FDB events on software LAG uppers will get called. By changing lan966x_foreign_dev_check(), we can suppress them. Whereas DSA will now start receiving FDB events for its offloaded LAG uppers, so we need to return -EOPNOTSUPP, since we currently don't do the right thing for them. Cc: Horatiu Vultur Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/net/switchdev.h | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index c32e1c8f79ec..3e424d40fae3 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -313,10 +313,7 @@ int switchdev_handle_fdb_event_to_device(struct net_device *dev, unsigned long e const struct net_device *foreign_dev), int (*mod_cb)(struct net_device *dev, struct net_device *orig_dev, unsigned long event, const void *ctx, - const struct switchdev_notifier_fdb_info *fdb_info), - int (*lag_mod_cb)(struct net_device *dev, struct net_device *orig_dev, - unsigned long event, const void *ctx, - const struct switchdev_notifier_fdb_info *fdb_info)); + const struct switchdev_notifier_fdb_info *fdb_info)); int switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, @@ -443,10 +440,7 @@ switchdev_handle_fdb_event_to_device(struct net_device *dev, unsigned long event const struct net_device *foreign_dev), int (*mod_cb)(struct net_device *dev, struct net_device *orig_dev, unsigned long event, const void *ctx, - const struct switchdev_notifier_fdb_info *fdb_info), - int (*lag_mod_cb)(struct net_device *dev, struct net_device *orig_dev, - unsigned long event, const void *ctx, - const struct switchdev_notifier_fdb_info *fdb_info)) + const struct switchdev_notifier_fdb_info *fdb_info)) { return 0; } -- cgit v1.2.3 From e212fa7c54184b7b1f88990bd328b23b567cbf41 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 23 Feb 2022 16:00:53 +0200 Subject: net: dsa: support FDB events on offloaded LAG interfaces This change introduces support for installing static FDB entries towards a bridge port that is a LAG of multiple DSA switch ports, as well as support for filtering towards the CPU local FDB entries emitted for LAG interfaces that are bridge ports. Conceptually, host addresses on LAG ports are identical to what we do for plain bridge ports. Whereas FDB entries _towards_ a LAG can't simply be replicated towards all member ports like we do for multicast, or VLAN. Instead we need new driver API. Hardware usually considers a LAG to be a "logical port", and sets the entire LAG as the forwarding destination. The physical egress port selection within the LAG is made by hashing policy, as usual. To represent the logical port corresponding to the LAG, we pass by value a copy of the dsa_lag structure to all switches in the tree that have at least one port in that LAG. To illustrate why a refcounted list of FDB entries is needed in struct dsa_lag, it is enough to say that: - a LAG may be a bridge port and may therefore receive FDB events even while it isn't yet offloaded by any DSA interface - DSA interfaces may be removed from a LAG while that is a bridge port; we don't want FDB entries lingering around, but we don't want to remove entries that are still in use, either For all the cases below to work, the idea is to always keep an FDB entry on a LAG with a reference count equal to the DSA member ports. So: - if a port joins a LAG, it requests the bridge to replay the FDB, and the FDB entries get created, or their refcount gets bumped by one - if a port leaves a LAG, the FDB replay deletes or decrements refcount by one - if an FDB is installed towards a LAG with ports already present, that entry is created (if it doesn't exist) and its refcount is bumped by the amount of ports already present in the LAG echo "Adding FDB entry to bond with existing ports" ip link del bond0 ip link add bond0 type bond mode 802.3ad ip link set swp1 down && ip link set swp1 master bond0 && ip link set swp1 up ip link set swp2 down && ip link set swp2 master bond0 && ip link set swp2 up ip link del br0 ip link add br0 type bridge ip link set bond0 master br0 bridge fdb add dev bond0 00:01:02:03:04:05 master static ip link del br0 ip link del bond0 echo "Adding FDB entry to empty bond" ip link del bond0 ip link add bond0 type bond mode 802.3ad ip link del br0 ip link add br0 type bridge ip link set bond0 master br0 bridge fdb add dev bond0 00:01:02:03:04:05 master static ip link set swp1 down && ip link set swp1 master bond0 && ip link set swp1 up ip link set swp2 down && ip link set swp2 master bond0 && ip link set swp2 up ip link del br0 ip link del bond0 echo "Adding FDB entry to empty bond, then removing ports one by one" ip link del bond0 ip link add bond0 type bond mode 802.3ad ip link del br0 ip link add br0 type bridge ip link set bond0 master br0 bridge fdb add dev bond0 00:01:02:03:04:05 master static ip link set swp1 down && ip link set swp1 master bond0 && ip link set swp1 up ip link set swp2 down && ip link set swp2 master bond0 && ip link set swp2 up ip link set swp1 nomaster ip link set swp2 nomaster ip link del br0 ip link del bond0 Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 81ed34998416..01faba89c987 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -119,6 +119,8 @@ struct dsa_netdevice_ops { struct dsa_lag { struct net_device *dev; unsigned int id; + struct mutex fdb_lock; + struct list_head fdbs; refcount_t refcount; }; @@ -944,6 +946,10 @@ struct dsa_switch_ops { const unsigned char *addr, u16 vid); int (*port_fdb_dump)(struct dsa_switch *ds, int port, dsa_fdb_dump_cb_t *cb, void *data); + int (*lag_fdb_add)(struct dsa_switch *ds, struct dsa_lag lag, + const unsigned char *addr, u16 vid); + int (*lag_fdb_del)(struct dsa_switch *ds, struct dsa_lag lag, + const unsigned char *addr, u16 vid); /* * Multicast database -- cgit v1.2.3 From 961d8b699070070fb3a9639af61641a52c8e49ef Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 23 Feb 2022 16:00:54 +0200 Subject: net: dsa: felix: support FDB entries on offloaded LAG interfaces This adds the logic in the Felix DSA driver and Ocelot switch library. For Ocelot switches, the DEST_IDX that is the output of the MAC table lookup is a logical port (equal to physical port, if no LAG is used, or a dynamically allocated number otherwise). The allocation we have in place for LAG IDs is different from DSA's, so we can't use that: - DSA allocates a continuous range of LAG IDs starting from 1 - Ocelot appears to require that physical ports and LAG IDs are in the same space of [0, num_phys_ports), and additionally, ports that aren't in a LAG must have physical port id == logical port id The implication is that an FDB entry towards a LAG might need to be deleted and reinstalled when the LAG ID changes. Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 78f56502bc09..dd4fc34d2992 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -635,6 +635,13 @@ enum macaccess_entry_type { #define OCELOT_QUIRK_PCS_PERFORMS_RATE_ADAPTATION BIT(0) #define OCELOT_QUIRK_QSGMII_PORTS_MUST_BE_UP BIT(1) +struct ocelot_lag_fdb { + unsigned char addr[ETH_ALEN]; + u16 vid; + struct net_device *bond; + struct list_head list; +}; + struct ocelot_port { struct ocelot *ocelot; @@ -690,6 +697,7 @@ struct ocelot { struct list_head vlans; struct list_head traps; + struct list_head lag_fdbs; /* Switches like VSC9959 have flooding per traffic class */ int num_flooding_pgids; @@ -866,6 +874,10 @@ int ocelot_fdb_add(struct ocelot *ocelot, int port, const unsigned char *addr, u16 vid); int ocelot_fdb_del(struct ocelot *ocelot, int port, const unsigned char *addr, u16 vid); +int ocelot_lag_fdb_add(struct ocelot *ocelot, struct net_device *bond, + const unsigned char *addr, u16 vid); +int ocelot_lag_fdb_del(struct ocelot *ocelot, struct net_device *bond, + const unsigned char *addr, u16 vid); int ocelot_vlan_prepare(struct ocelot *ocelot, int port, u16 vid, bool pvid, bool untagged, struct netlink_ext_ack *extack); int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid, -- cgit v1.2.3 From 7bbb765b73496699a165d505ecdce962f903b422 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Wed, 23 Feb 2022 17:57:40 +0000 Subject: net/tcp: Merge TCP-MD5 inbound callbacks The functions do essentially the same work to verify TCP-MD5 sign. Code can be merged into one family-independent function in order to reduce copy'n'paste and generated code. Later with TCP-AO option added, this will allow to create one function that's responsible for segment verification, that will have all the different checks for MD5/AO/non-signed packets, which in turn will help to see checks for all corner-cases in one function, rather than spread around different families and functions. Cc: Eric Dumazet Cc: Hideaki YOSHIFUJI Signed-off-by: Dmitry Safonov Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20220223175740.452397-1-dima@arista.com Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 04f4650e0ff0..479a27777ad6 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1674,6 +1674,11 @@ tcp_md5_do_lookup(const struct sock *sk, int l3index, return NULL; return __tcp_md5_do_lookup(sk, l3index, addr, family); } +bool tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, + enum skb_drop_reason *reason, + const void *saddr, const void *daddr, + int family, int dif, int sdif); + #define tcp_twsk_md5_key(twsk) ((twsk)->tw_md5_key) #else @@ -1683,6 +1688,14 @@ tcp_md5_do_lookup(const struct sock *sk, int l3index, { return NULL; } +static inline bool tcp_inbound_md5_hash(const struct sock *sk, + const struct sk_buff *skb, + enum skb_drop_reason *reason, + const void *saddr, const void *daddr, + int family, int dif, int sdif) +{ + return false; +} #define tcp_twsk_md5_key(twsk) NULL #endif -- cgit v1.2.3 From 34737e26980341519d00e84711fe619f9f47e79c Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 11 Feb 2022 08:50:00 +0100 Subject: uaccess: add generic __{get,put}_kernel_nofault Nine architectures are still missing __{get,put}_kernel_nofault: alpha, ia64, microblaze, nds32, nios2, openrisc, sh, sparc32, xtensa. Add a generic version that lets everything use the normal copy_{from,to}_kernel_nofault() code based on these, removing the last use of get_fs()/set_fs() from architecture-independent code. Reviewed-by: Christoph Hellwig Acked-by: Geert Uytterhoeven Signed-off-by: Arnd Bergmann --- include/asm-generic/uaccess.h | 2 -- include/linux/uaccess.h | 19 +++++++++++++++++++ 2 files changed, 19 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h index 10ffa8b5c117..0870fa11a7c5 100644 --- a/include/asm-generic/uaccess.h +++ b/include/asm-generic/uaccess.h @@ -77,8 +77,6 @@ do { \ goto err_label; \ } while (0) -#define HAVE_GET_KERNEL_NOFAULT 1 - static inline __must_check unsigned long raw_copy_from_user(void *to, const void __user * from, unsigned long n) { diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index ac0394087f7d..67e9bc94dc40 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -368,6 +368,25 @@ long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); long strnlen_user_nofault(const void __user *unsafe_addr, long count); +#ifndef __get_kernel_nofault +#define __get_kernel_nofault(dst, src, type, label) \ +do { \ + type __user *p = (type __force __user *)(src); \ + type data; \ + if (__get_user(data, p)) \ + goto label; \ + *(type *)dst = data; \ +} while (0) + +#define __put_kernel_nofault(dst, src, type, label) \ +do { \ + type __user *p = (type __force __user *)(dst); \ + type data = *(type *)src; \ + if (__put_user(data, p)) \ + goto label; \ +} while (0) +#endif + /** * get_kernel_nofault(): safely attempt to read from a location * @val: read into this variable -- cgit v1.2.3 From 12700c17fc286149324f92d6d380bc48e43f253d Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 15 Feb 2022 17:55:04 +0100 Subject: uaccess: generalize access_ok() There are many different ways that access_ok() is defined across architectures, but in the end, they all just compare against the user_addr_max() value or they accept anything. Provide one definition that works for most architectures, checking against TASK_SIZE_MAX for user processes or skipping the check inside of uaccess_kernel() sections. For architectures without CONFIG_SET_FS(), this should be the fastest check, as it comes down to a single comparison of a pointer against a compile-time constant, while the architecture specific versions tend to do something more complex for historic reasons or get something wrong. Type checking for __user annotations is handled inconsistently across architectures, but this is easily simplified as well by using an inline function that takes a 'const void __user *' argument. A handful of callers need an extra __user annotation for this. Some architectures had trick to use 33-bit or 65-bit arithmetic on the addresses to calculate the overflow, however this simpler version uses fewer registers, which means it can produce better object code in the end despite needing a second (statically predicted) branch. Reviewed-by: Christoph Hellwig Acked-by: Mark Rutland [arm64, asm-generic] Acked-by: Geert Uytterhoeven Acked-by: Stafford Horne Acked-by: Dinh Nguyen Signed-off-by: Arnd Bergmann --- include/asm-generic/access_ok.h | 60 +++++++++++++++++++++++++++++++++++++++++ include/asm-generic/uaccess.h | 21 +-------------- include/linux/uaccess.h | 7 ----- 3 files changed, 61 insertions(+), 27 deletions(-) create mode 100644 include/asm-generic/access_ok.h (limited to 'include') diff --git a/include/asm-generic/access_ok.h b/include/asm-generic/access_ok.h new file mode 100644 index 000000000000..d38cc5dad65b --- /dev/null +++ b/include/asm-generic/access_ok.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_GENERIC_ACCESS_OK_H__ +#define __ASM_GENERIC_ACCESS_OK_H__ + +/* + * Checking whether a pointer is valid for user space access. + * These definitions work on most architectures, but overrides can + * be used where necessary. + */ + +/* + * architectures with compat tasks have a variable TASK_SIZE and should + * override this to a constant. + */ +#ifndef TASK_SIZE_MAX +#define TASK_SIZE_MAX TASK_SIZE +#endif + +#ifndef uaccess_kernel +#ifdef CONFIG_SET_FS +#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) +#else +#define uaccess_kernel() (0) +#endif +#endif + +#ifndef user_addr_max +#define user_addr_max() (uaccess_kernel() ? ~0UL : TASK_SIZE_MAX) +#endif + +#ifndef __access_ok +/* + * 'size' is a compile-time constant for most callers, so optimize for + * this case to turn the check into a single comparison against a constant + * limit and catch all possible overflows. + * On architectures with separate user address space (m68k, s390, parisc, + * sparc64) or those without an MMU, this should always return true. + * + * This version was originally contributed by Jonas Bonn for the + * OpenRISC architecture, and was found to be the most efficient + * for constant 'size' and 'limit' values. + */ +static inline int __access_ok(const void __user *ptr, unsigned long size) +{ + unsigned long limit = user_addr_max(); + unsigned long addr = (unsigned long)ptr; + + if (IS_ENABLED(CONFIG_ALTERNATE_USER_ADDRESS_SPACE) || + !IS_ENABLED(CONFIG_MMU)) + return true; + + return (size <= limit) && (addr <= (limit - size)); +} +#endif + +#ifndef access_ok +#define access_ok(addr, size) likely(__access_ok(addr, size)) +#endif + +#endif diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h index 0870fa11a7c5..ebc685dc8d74 100644 --- a/include/asm-generic/uaccess.h +++ b/include/asm-generic/uaccess.h @@ -114,28 +114,9 @@ static inline void set_fs(mm_segment_t fs) } #endif -#ifndef uaccess_kernel -#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) -#endif - -#ifndef user_addr_max -#define user_addr_max() (uaccess_kernel() ? ~0UL : TASK_SIZE) -#endif - #endif /* CONFIG_SET_FS */ -#define access_ok(addr, size) __access_ok((unsigned long)(addr),(size)) - -/* - * The architecture should really override this if possible, at least - * doing a check on the get_fs() - */ -#ifndef __access_ok -static inline int __access_ok(unsigned long addr, unsigned long size) -{ - return 1; -} -#endif +#include /* * These are the main single-value transfer routines. They automatically diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 67e9bc94dc40..2c31667e62e0 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -33,13 +33,6 @@ typedef struct { /* empty dummy */ } mm_segment_t; -#ifndef TASK_SIZE_MAX -#define TASK_SIZE_MAX TASK_SIZE -#endif - -#define uaccess_kernel() (false) -#define user_addr_max() (TASK_SIZE_MAX) - static inline mm_segment_t force_uaccess_begin(void) { return (mm_segment_t) { }; -- cgit v1.2.3 From 967747bbc084b93b54e66f9047d342232314cd25 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 11 Feb 2022 21:42:45 +0100 Subject: uaccess: remove CONFIG_SET_FS There are no remaining callers of set_fs(), so CONFIG_SET_FS can be removed globally, along with the thread_info field and any references to it. This turns access_ok() into a cheaper check against TASK_SIZE_MAX. As CONFIG_SET_FS is now gone, drop all remaining references to set_fs()/get_fs(), mm_segment_t, user_addr_max() and uaccess_kernel(). Acked-by: Sam Ravnborg # for sparc32 changes Acked-by: "Eric W. Biederman" Tested-by: Sergey Matyukevich # for arc changes Acked-by: Stafford Horne # [openrisc, asm-generic] Acked-by: Dinh Nguyen Signed-off-by: Arnd Bergmann --- include/asm-generic/access_ok.h | 14 +------------- include/asm-generic/uaccess.h | 25 +------------------------ include/linux/syscalls.h | 4 ---- include/linux/uaccess.h | 33 --------------------------------- include/rdma/ib.h | 2 +- 5 files changed, 3 insertions(+), 75 deletions(-) (limited to 'include') diff --git a/include/asm-generic/access_ok.h b/include/asm-generic/access_ok.h index d38cc5dad65b..2866ae61b1cd 100644 --- a/include/asm-generic/access_ok.h +++ b/include/asm-generic/access_ok.h @@ -16,18 +16,6 @@ #define TASK_SIZE_MAX TASK_SIZE #endif -#ifndef uaccess_kernel -#ifdef CONFIG_SET_FS -#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) -#else -#define uaccess_kernel() (0) -#endif -#endif - -#ifndef user_addr_max -#define user_addr_max() (uaccess_kernel() ? ~0UL : TASK_SIZE_MAX) -#endif - #ifndef __access_ok /* * 'size' is a compile-time constant for most callers, so optimize for @@ -42,7 +30,7 @@ */ static inline int __access_ok(const void __user *ptr, unsigned long size) { - unsigned long limit = user_addr_max(); + unsigned long limit = TASK_SIZE_MAX; unsigned long addr = (unsigned long)ptr; if (IS_ENABLED(CONFIG_ALTERNATE_USER_ADDRESS_SPACE) || diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h index ebc685dc8d74..a5be9e61a2a2 100644 --- a/include/asm-generic/uaccess.h +++ b/include/asm-generic/uaccess.h @@ -8,6 +8,7 @@ * address space, e.g. all NOMMU machines. */ #include +#include #ifdef CONFIG_UACCESS_MEMCPY #include @@ -94,30 +95,6 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n) #define INLINE_COPY_TO_USER #endif /* CONFIG_UACCESS_MEMCPY */ -#ifdef CONFIG_SET_FS -#define MAKE_MM_SEG(s) ((mm_segment_t) { (s) }) - -#ifndef KERNEL_DS -#define KERNEL_DS MAKE_MM_SEG(~0UL) -#endif - -#ifndef USER_DS -#define USER_DS MAKE_MM_SEG(TASK_SIZE - 1) -#endif - -#ifndef get_fs -#define get_fs() (current_thread_info()->addr_limit) - -static inline void set_fs(mm_segment_t fs) -{ - current_thread_info()->addr_limit = fs; -} -#endif - -#endif /* CONFIG_SET_FS */ - -#include - /* * These are the main single-value transfer routines. They automatically * use the right size if we just have the right pointer type. diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 819c0cb00b6d..a34b0f9a9972 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -290,10 +290,6 @@ static inline void addr_limit_user_check(void) return; #endif - if (CHECK_DATA_CORRUPTION(uaccess_kernel(), - "Invalid address limit on user-mode return")) - force_sig(SIGKILL); - #ifdef TIF_FSCHECK clear_thread_flag(TIF_FSCHECK); #endif diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 2c31667e62e0..2421a41f3a8e 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -10,39 +10,6 @@ #include -#ifdef CONFIG_SET_FS -/* - * Force the uaccess routines to be wired up for actual userspace access, - * overriding any possible set_fs(KERNEL_DS) still lingering around. Undone - * using force_uaccess_end below. - */ -static inline mm_segment_t force_uaccess_begin(void) -{ - mm_segment_t fs = get_fs(); - - set_fs(USER_DS); - return fs; -} - -static inline void force_uaccess_end(mm_segment_t oldfs) -{ - set_fs(oldfs); -} -#else /* CONFIG_SET_FS */ -typedef struct { - /* empty dummy */ -} mm_segment_t; - -static inline mm_segment_t force_uaccess_begin(void) -{ - return (mm_segment_t) { }; -} - -static inline void force_uaccess_end(mm_segment_t oldfs) -{ -} -#endif /* CONFIG_SET_FS */ - /* * Architectures should provide two primitives (raw_copy_{to,from}_user()) * and get rid of their private instances of copy_{to,from}_user() and diff --git a/include/rdma/ib.h b/include/rdma/ib.h index 83139b9ce409..f7c185ff7a11 100644 --- a/include/rdma/ib.h +++ b/include/rdma/ib.h @@ -75,7 +75,7 @@ struct sockaddr_ib { */ static inline bool ib_safe_file_access(struct file *filp) { - return filp->f_cred == current_cred() && !uaccess_kernel(); + return filp->f_cred == current_cred(); } #endif /* _RDMA_IB_H */ -- cgit v1.2.3 From 440c7317e4bb243f9464fa508d675db944972dd6 Mon Sep 17 00:00:00 2001 From: Robert Marko Date: Mon, 31 Jan 2022 14:30:46 +0100 Subject: dt-bindings: reset: Add Delta TN48M Add header for the Delta TN48M CPLD provided resets. Acked-by: Philipp Zabel Signed-off-by: Robert Marko Link: https://lore.kernel.org/r/20220131133049.77780-4-robert.marko@sartura.hr Signed-off-by: Greg Kroah-Hartman --- include/dt-bindings/reset/delta,tn48m-reset.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100644 include/dt-bindings/reset/delta,tn48m-reset.h (limited to 'include') diff --git a/include/dt-bindings/reset/delta,tn48m-reset.h b/include/dt-bindings/reset/delta,tn48m-reset.h new file mode 100644 index 000000000000..d4e9ed12de3e --- /dev/null +++ b/include/dt-bindings/reset/delta,tn48m-reset.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Delta TN48M CPLD GPIO driver + * + * Copyright (C) 2021 Sartura Ltd. + * + * Author: Robert Marko + */ + +#ifndef _DT_BINDINGS_RESET_TN48M_H +#define _DT_BINDINGS_RESET_TN48M_H + +#define CPU_88F7040_RESET 0 +#define CPU_88F6820_RESET 1 +#define MAC_98DX3265_RESET 2 +#define PHY_88E1680_RESET 3 +#define PHY_88E1512_RESET 4 +#define POE_RESET 5 + +#endif /* _DT_BINDINGS_RESET_TN48M_H */ -- cgit v1.2.3 From d4da1f27396fb1dde079447a3612f4f512caed07 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 24 Feb 2022 19:56:09 -0800 Subject: drm/dp: Fix off-by-one in register cache size The pcon_dsc_dpcd array holds 13 registers (0x92 through 0x9E). Fix the math to calculate the max size. Found from a -Warray-bounds build: drivers/gpu/drm/drm_dp_helper.c: In function 'drm_dp_pcon_dsc_bpp_incr': drivers/gpu/drm/drm_dp_helper.c:3130:28: error: array subscript 12 is outside array bounds of 'const u8[12]' {aka 'const unsigned char[12]'} [-Werror=array-bounds] 3130 | buf = pcon_dsc_dpcd[DP_PCON_DSC_BPP_INCR - DP_PCON_DSC_ENCODER]; | ~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/gpu/drm/drm_dp_helper.c:3126:39: note: while referencing 'pcon_dsc_dpcd' 3126 | int drm_dp_pcon_dsc_bpp_incr(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]) | ~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Cc: Daniel Vetter Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Thomas Zimmermann Cc: David Airlie Cc: dri-devel@lists.freedesktop.org Fixes: e2e16da398d9 ("drm/dp_helper: Add support for Configuring DSC for HDMI2.1 Pcon") Cc: stable@vger.kernel.org Reviewed-by: Gustavo A. R. Silva Link: https://lore.kernel.org/lkml/20211214001849.GA62559@embeddedor/ Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220105173310.2420598-1-keescook@chromium.org Signed-off-by: Thierry Reding Link: https://patchwork.freedesktop.org/patch/msgid/20220225035610.2552144-2-keescook@chromium.org --- include/drm/dp/drm_dp_helper.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/dp/drm_dp_helper.h b/include/drm/dp/drm_dp_helper.h index 98d020835b49..8c277be9626d 100644 --- a/include/drm/dp/drm_dp_helper.h +++ b/include/drm/dp/drm_dp_helper.h @@ -456,7 +456,7 @@ struct drm_panel; #define DP_FEC_CAPABILITY_1 0x091 /* 2.0 */ /* DP-HDMI2.1 PCON DSC ENCODER SUPPORT */ -#define DP_PCON_DSC_ENCODER_CAP_SIZE 0xC /* 0x9E - 0x92 */ +#define DP_PCON_DSC_ENCODER_CAP_SIZE 0xD /* 0x92 through 0x9E */ #define DP_PCON_DSC_ENCODER 0x092 # define DP_PCON_DSC_ENCODER_SUPPORTED (1 << 0) # define DP_PCON_DSC_PPS_ENC_OVERRIDE (1 << 1) -- cgit v1.2.3 From a2151490cc6c57b368d7974ffd447a8b36ade639 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 24 Feb 2022 19:56:10 -0800 Subject: drm/dp: Fix OOB read when handling Post Cursor2 register The link_status array was not large enough to read the Adjust Request Post Cursor2 register, so remove the common helper function to avoid an OOB read, found with a -Warray-bounds build: drivers/gpu/drm/drm_dp_helper.c: In function 'drm_dp_get_adjust_request_post_cursor': drivers/gpu/drm/drm_dp_helper.c:59:27: error: array subscript 10 is outside array bounds of 'const u8[6]' {aka 'const unsigned char[6]'} [-Werror=array-bounds] 59 | return link_status[r - DP_LANE0_1_STATUS]; | ~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~ drivers/gpu/drm/drm_dp_helper.c:147:51: note: while referencing 'link_status' 147 | u8 drm_dp_get_adjust_request_post_cursor(const u8 link_status[DP_LINK_STATUS_SIZE], | ~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Replace the only user of the helper with an open-coded fetch and decode, similar to drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c. Cc: Daniel Vetter Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Thomas Zimmermann Cc: David Airlie Cc: dri-devel@lists.freedesktop.org Fixes: 79465e0ffeb9 ("drm/dp: Add helper to get post-cursor adjustments") Signed-off-by: Kees Cook Reviewed-by: Gustavo A. R. Silva Reviewed-by: Jani Nikula Link: https://lore.kernel.org/r/20220105173507.2420910-1-keescook@chromium.org Signed-off-by: Thierry Reding --- include/drm/dp/drm_dp_helper.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/drm/dp/drm_dp_helper.h b/include/drm/dp/drm_dp_helper.h index 8c277be9626d..dad1442c91df 100644 --- a/include/drm/dp/drm_dp_helper.h +++ b/include/drm/dp/drm_dp_helper.h @@ -1525,8 +1525,6 @@ u8 drm_dp_get_adjust_request_pre_emphasis(const u8 link_status[DP_LINK_STATUS_SI int lane); u8 drm_dp_get_adjust_tx_ffe_preset(const u8 link_status[DP_LINK_STATUS_SIZE], int lane); -u8 drm_dp_get_adjust_request_post_cursor(const u8 link_status[DP_LINK_STATUS_SIZE], - unsigned int lane); #define DP_BRANCH_OUI_HEADER_SIZE 0xc #define DP_RECEIVER_CAP_SIZE 0xf -- cgit v1.2.3 From 2c861b73a23b1237bdd054b6023bb27f6747c2b9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Sat, 19 Feb 2022 16:28:13 +0100 Subject: math64: New DIV_U64_ROUND_CLOSEST helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Provide DIV_U64_ROUND_CLOSEST helper which uses div_u64 to perform division rounded to the closest integer using unsigned 64bit dividend and unsigned 32bit divisor. Reviewed-by: Marek Behún Signed-off-by: Pali Rohár Signed-off-by: Marek Behún Link: https://lore.kernel.org/r/20220219152818.4319-2-kabel@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/math64.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/math64.h b/include/linux/math64.h index 2928f03d6d46..a14f40de1dca 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -300,6 +300,19 @@ u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div); #define DIV64_U64_ROUND_CLOSEST(dividend, divisor) \ ({ u64 _tmp = (divisor); div64_u64((dividend) + _tmp / 2, _tmp); }) +/* + * DIV_U64_ROUND_CLOSEST - unsigned 64bit divide with 32bit divisor rounded to nearest integer + * @dividend: unsigned 64bit dividend + * @divisor: unsigned 32bit divisor + * + * Divide unsigned 64bit dividend by unsigned 32bit divisor + * and round to closest integer. + * + * Return: dividend / divisor rounded to nearest integer + */ +#define DIV_U64_ROUND_CLOSEST(dividend, divisor) \ + ({ u32 _tmp = (divisor); div_u64((u64)(dividend) + _tmp / 2, _tmp); }) + /* * DIV_S64_ROUND_CLOSEST - signed 64bit divide with 32bit divisor rounded to nearest integer * @dividend: signed 64bit dividend -- cgit v1.2.3 From 28a3f0601727d521a1c6cce62ecbcb7402a9e4f5 Mon Sep 17 00:00:00 2001 From: Toms Atteka Date: Wed, 23 Feb 2022 16:54:09 -0800 Subject: net: openvswitch: IPv6: Add IPv6 extension header support This change adds a new OpenFlow field OFPXMT_OFB_IPV6_EXTHDR and packets can be filtered using ipv6_ext flag. Signed-off-by: Toms Atteka Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 150bcff49b1c..9d1710f20505 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -351,6 +351,7 @@ enum ovs_key_attr { OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4, /* struct ovs_key_ct_tuple_ipv4 */ OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6, /* struct ovs_key_ct_tuple_ipv6 */ OVS_KEY_ATTR_NSH, /* Nested set of ovs_nsh_key_* */ + OVS_KEY_ATTR_IPV6_EXTHDRS, /* struct ovs_key_ipv6_exthdr */ #ifdef __KERNEL__ OVS_KEY_ATTR_TUNNEL_INFO, /* struct ip_tunnel_info */ @@ -430,6 +431,11 @@ struct ovs_key_ipv6 { __u8 ipv6_frag; /* One of OVS_FRAG_TYPE_*. */ }; +/* separate structure to support backward compatibility with older user space */ +struct ovs_key_ipv6_exthdrs { + __u16 hdrs; +}; + struct ovs_key_tcp { __be16 tcp_src; __be16 tcp_dst; -- cgit v1.2.3 From 085a884434f3e3b08349a0ba0904f9f561739d57 Mon Sep 17 00:00:00 2001 From: Richard Gong Date: Wed, 23 Feb 2022 08:49:08 -0600 Subject: firmware: stratix10-svc: extend SVC driver to get the firmware version Extend Intel service layer driver to get the firmware version running at FPGA device. Therefore FPGA manager driver, one of Intel service layer driver's client, can decide whether to handle the newly added bitstream authentication function based on the retrieved firmware version. Link: https://lore.kernel.org/lkml/1617114785-22211-2-git-send-email-richard.gong@linux.intel.com Acked-by: Moritz Fischr Signed-off-by: Richard Gong Signed-off-by: Dinh Nguyen Link: https://lore.kernel.org/r/20220223144908.399522-2-dinguyen@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/intel/stratix10-smc.h | 21 +++++++++++++++++++-- include/linux/firmware/intel/stratix10-svc-client.h | 4 ++++ 2 files changed, 23 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/firmware/intel/stratix10-smc.h b/include/linux/firmware/intel/stratix10-smc.h index c3e5ab014caf..aad497a9ad8b 100644 --- a/include/linux/firmware/intel/stratix10-smc.h +++ b/include/linux/firmware/intel/stratix10-smc.h @@ -321,8 +321,6 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE) #define INTEL_SIP_SMC_ECC_DBE \ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_ECC_DBE) -#endif - /** * Request INTEL_SIP_SMC_RSU_NOTIFY * @@ -404,3 +402,22 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE) #define INTEL_SIP_SMC_FUNCID_RSU_MAX_RETRY 18 #define INTEL_SIP_SMC_RSU_MAX_RETRY \ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_RSU_MAX_RETRY) + +/** + * Request INTEL_SIP_SMC_FIRMWARE_VERSION + * + * Sync call used to query the version of running firmware + * + * Call register usage: + * a0 INTEL_SIP_SMC_FIRMWARE_VERSION + * a1-a7 not used + * + * Return status: + * a0 INTEL_SIP_SMC_STATUS_OK or INTEL_SIP_SMC_STATUS_ERROR + * a1 running firmware version + */ +#define INTEL_SIP_SMC_FUNCID_FIRMWARE_VERSION 31 +#define INTEL_SIP_SMC_FIRMWARE_VERSION \ + INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FIRMWARE_VERSION) + +#endif diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h index 19781b0f6429..18c1841fdb1f 100644 --- a/include/linux/firmware/intel/stratix10-svc-client.h +++ b/include/linux/firmware/intel/stratix10-svc-client.h @@ -104,6 +104,9 @@ struct stratix10_svc_chan; * * @COMMAND_RSU_DCMF_VERSION: query firmware for the DCMF version, return status * is SVC_STATUS_OK or SVC_STATUS_ERROR + * + * @COMMAND_FIRMWARE_VERSION: query running firmware version, return status + * is SVC_STATUS_OK or SVC_STATUS_ERROR */ enum stratix10_svc_command_code { COMMAND_NOOP = 0, @@ -117,6 +120,7 @@ enum stratix10_svc_command_code { COMMAND_RSU_RETRY, COMMAND_RSU_MAX_RETRY, COMMAND_RSU_DCMF_VERSION, + COMMAND_FIRMWARE_VERSION, }; /** -- cgit v1.2.3 From f1d0821bf37ba3cecee0fd1e9ae72a943a69d01d Mon Sep 17 00:00:00 2001 From: Ronak Jain Date: Wed, 9 Feb 2022 00:27:07 -0800 Subject: firmware: xilinx: Add support for runtime features Add support for runtime features by using an IOCTL call. The features can be enabled or disabled from the firmware as well as the features can be configured at runtime by querying IOCTL_SET_FEATURE_CONFIG id. Similarly, the user can get the configured values of features by querying IOCTL_GET_FEATURE_CONFIG id. Acked-by: Michal Simek Signed-off-by: Ronak Jain Link: https://lore.kernel.org/r/20220209082709.32378-2-ronak.jain@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 907cb01890cf..cf557fbeb8c7 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -143,6 +143,9 @@ enum pm_ioctl_id { IOCTL_OSPI_MUX_SELECT = 21, /* Register SGI to ATF */ IOCTL_REGISTER_SGI = 25, + /* Runtime feature configuration */ + IOCTL_SET_FEATURE_CONFIG = 26, + IOCTL_GET_FEATURE_CONFIG = 27, }; enum pm_query_id { @@ -376,6 +379,14 @@ enum ospi_mux_select_type { PM_OSPI_MUX_SEL_LINEAR = 1, }; +enum pm_feature_config_id { + PM_FEATURE_INVALID = 0, + PM_FEATURE_OVERTEMP_STATUS = 1, + PM_FEATURE_OVERTEMP_VALUE = 2, + PM_FEATURE_EXTWDT_STATUS = 3, + PM_FEATURE_EXTWDT_VALUE = 4, +}; + /** * struct zynqmp_pm_query_data - PM query data * @qid: query ID @@ -447,6 +458,8 @@ int zynqmp_pm_load_pdi(const u32 src, const u64 address); int zynqmp_pm_register_notifier(const u32 node, const u32 event, const u32 wake, const u32 enable); int zynqmp_pm_feature(const u32 api_id); +int zynqmp_pm_set_feature_config(enum pm_feature_config_id id, u32 value); +int zynqmp_pm_get_feature_config(enum pm_feature_config_id id, u32 *payload); #else static inline int zynqmp_pm_get_api_version(u32 *version) { @@ -689,6 +702,18 @@ static inline int zynqmp_pm_feature(const u32 api_id) { return -ENODEV; } + +static inline int zynqmp_pm_set_feature_config(enum pm_feature_config_id id, + u32 value) +{ + return -ENODEV; +} + +static inline int zynqmp_pm_get_feature_config(enum pm_feature_config_id id, + u32 *payload) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 2502960fba7e94e090112069694365295c32ccc5 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Mon, 14 Feb 2022 14:07:57 +0800 Subject: component: Add common helper for compare/release functions The component requires the compare/release functions, there are so many copies in current kernel. Just define four common helpers for them. Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Signed-off-by: Yong Wu Link: https://lore.kernel.org/r/20220214060819.7334-2-yong.wu@mediatek.com Signed-off-by: Greg Kroah-Hartman --- include/linux/component.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/component.h b/include/linux/component.h index 7012569c6546..df4aa75c9e7c 100644 --- a/include/linux/component.h +++ b/include/linux/component.h @@ -82,6 +82,12 @@ struct component_master_ops { void (*unbind)(struct device *master); }; +/* A set helper functions for component compare/release */ +int component_compare_of(struct device *dev, void *data); +void component_release_of(struct device *dev, void *data); +int component_compare_dev(struct device *dev, void *data); +int component_compare_dev_name(struct device *dev, void *data); + void component_master_del(struct device *, const struct component_master_ops *); -- cgit v1.2.3 From dc3005703f8cd893d325081c20b400e08377d9bb Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Thu, 13 Jan 2022 16:48:51 +0200 Subject: ARM: at91: ddr: remove CONFIG_SOC_SAMA7 dependency Remove CONFIG_SOC_SAMA7 dependency to avoid having #ifdef preprocessor directives in driver code (arch/arm/mach-at91/pm.c). This prepares the code for next commits. Signed-off-by: Claudiu Beznea Signed-off-by: Nicolas Ferre Link: https://lore.kernel.org/r/20220113144900.906370-2-claudiu.beznea@microchip.com --- include/soc/at91/sama7-ddr.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/soc/at91/sama7-ddr.h b/include/soc/at91/sama7-ddr.h index f6542584ca13..13b47e26cdbe 100644 --- a/include/soc/at91/sama7-ddr.h +++ b/include/soc/at91/sama7-ddr.h @@ -11,8 +11,6 @@ #ifndef __SAMA7_DDR_H__ #define __SAMA7_DDR_H__ -#ifdef CONFIG_SOC_SAMA7 - /* DDR3PHY */ #define DDR3PHY_PIR (0x04) /* DDR3PHY PHY Initialization Register */ #define DDR3PHY_PIR_DLLBYP (1 << 17) /* DLL Bypass */ @@ -75,6 +73,4 @@ #define UDDRC_PCTRL_3 (0x6A0) /* UDDRC Port 3 Control Register */ #define UDDRC_PCTRL_4 (0x750) /* UDDRC Port 4 Control Register */ -#endif /* CONFIG_SOC_SAMA7 */ - #endif /* __SAMA7_DDR_H__ */ -- cgit v1.2.3 From 55614e682a2c9fac12a0f121b43b93ff4915d0e6 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Thu, 13 Jan 2022 16:48:52 +0200 Subject: ARM: at91: ddr: align macro definitions Align all macro definitions. Signed-off-by: Claudiu Beznea Signed-off-by: Nicolas Ferre Link: https://lore.kernel.org/r/20220113144900.906370-3-claudiu.beznea@microchip.com --- include/soc/at91/sama7-ddr.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/soc/at91/sama7-ddr.h b/include/soc/at91/sama7-ddr.h index 13b47e26cdbe..817b360efbb8 100644 --- a/include/soc/at91/sama7-ddr.h +++ b/include/soc/at91/sama7-ddr.h @@ -13,11 +13,11 @@ /* DDR3PHY */ #define DDR3PHY_PIR (0x04) /* DDR3PHY PHY Initialization Register */ -#define DDR3PHY_PIR_DLLBYP (1 << 17) /* DLL Bypass */ +#define DDR3PHY_PIR_DLLBYP (1 << 17) /* DLL Bypass */ #define DDR3PHY_PIR_ITMSRST (1 << 4) /* Interface Timing Module Soft Reset */ -#define DDR3PHY_PIR_DLLLOCK (1 << 2) /* DLL Lock */ +#define DDR3PHY_PIR_DLLLOCK (1 << 2) /* DLL Lock */ #define DDR3PHY_PIR_DLLSRST (1 << 1) /* DLL Soft Rest */ -#define DDR3PHY_PIR_INIT (1 << 0) /* Initialization Trigger */ +#define DDR3PHY_PIR_INIT (1 << 0) /* Initialization Trigger */ #define DDR3PHY_PGCR (0x08) /* DDR3PHY PHY General Configuration Register */ #define DDR3PHY_PGCR_CKDV1 (1 << 13) /* CK# Disable Value */ @@ -65,7 +65,7 @@ #define UDDRC_SWSTAT_SW_DONE_ACK (1 << 0) /* Register programming done */ #define UDDRC_PSTAT (0x3FC) /* UDDRC Port Status Register */ -#define UDDRC_PSTAT_ALL_PORTS (0x1F001F) /* Read + writes outstanding transactions on all ports */ +#define UDDRC_PSTAT_ALL_PORTS (0x1F001F) /* Read + writes outstanding transactions on all ports */ #define UDDRC_PCTRL_0 (0x490) /* UDDRC Port 0 Control Register */ #define UDDRC_PCTRL_1 (0x540) /* UDDRC Port 1 Control Register */ -- cgit v1.2.3 From 9a0775c9cd3d89d1fe957a137131681a33f5736b Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Thu, 13 Jan 2022 16:48:53 +0200 Subject: ARM: at91: ddr: fix typo to align with datasheet naming Fix typo on UDDRC_PWRCTL.SELFREF_SW bitmask to align with datasheet naming. Signed-off-by: Claudiu Beznea Signed-off-by: Nicolas Ferre Link: https://lore.kernel.org/r/20220113144900.906370-4-claudiu.beznea@microchip.com --- include/soc/at91/sama7-ddr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/soc/at91/sama7-ddr.h b/include/soc/at91/sama7-ddr.h index 817b360efbb8..fee1b11bddca 100644 --- a/include/soc/at91/sama7-ddr.h +++ b/include/soc/at91/sama7-ddr.h @@ -53,7 +53,7 @@ #define UDDRC_STAT_OPMODE_MSK (0x7 << 0) /* Operating mode mask */ #define UDDRC_PWRCTL (0x30) /* UDDRC Low Power Control Register */ -#define UDDRC_PWRCTRL_SELFREF_SW (1 << 5) /* Software self-refresh */ +#define UDDRC_PWRCTL_SELFREF_SW (1 << 5) /* Software self-refresh */ #define UDDRC_DFIMISC (0x1B0) /* UDDRC DFI Miscellaneous Control Register */ #define UDDRC_DFIMISC_DFI_INIT_COMPLETE_EN (1 << 0) /* PHY initialization complete enable signal */ -- cgit v1.2.3 From 9584e7263e9ebcd94b184dc3efc847355a624220 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Thu, 13 Jan 2022 16:48:54 +0200 Subject: ARM: at91: PM: add cpu idle support for sama7g5 Add CPU idle support for SAMA7G5. Support will make use of PMC_CPU_RATIO register to divide the CPU clock by 16 before switching it to idle and use automatic self-refresh option of DDR controller. Signed-off-by: Claudiu Beznea Acked-by: Stephen Boyd Signed-off-by: Nicolas Ferre Link: https://lore.kernel.org/r/20220113144900.906370-5-claudiu.beznea@microchip.com --- include/linux/clk/at91_pmc.h | 4 ++++ include/soc/at91/sama7-ddr.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h index ccb3f034bfa9..3484309b59bf 100644 --- a/include/linux/clk/at91_pmc.h +++ b/include/linux/clk/at91_pmc.h @@ -78,6 +78,10 @@ #define AT91_PMC_MAINRDY (1 << 16) /* Main Clock Ready */ #define AT91_CKGR_PLLAR 0x28 /* PLL A Register */ + +#define AT91_PMC_RATIO 0x2c /* Processor clock ratio register [SAMA7G5 only] */ +#define AT91_PMC_RATIO_RATIO (0xf) /* CPU clock ratio. */ + #define AT91_CKGR_PLLBR 0x2c /* PLL B Register */ #define AT91_PMC_DIV (0xff << 0) /* Divider */ #define AT91_PMC_PLLCOUNT (0x3f << 8) /* PLL Counter */ diff --git a/include/soc/at91/sama7-ddr.h b/include/soc/at91/sama7-ddr.h index fee1b11bddca..9e17247474fa 100644 --- a/include/soc/at91/sama7-ddr.h +++ b/include/soc/at91/sama7-ddr.h @@ -53,6 +53,7 @@ #define UDDRC_STAT_OPMODE_MSK (0x7 << 0) /* Operating mode mask */ #define UDDRC_PWRCTL (0x30) /* UDDRC Low Power Control Register */ +#define UDDRC_PWRCTL_SELFREF_EN (1 << 0) /* Automatic self-refresh */ #define UDDRC_PWRCTL_SELFREF_SW (1 << 5) /* Software self-refresh */ #define UDDRC_DFIMISC (0x1B0) /* UDDRC DFI Miscellaneous Control Register */ -- cgit v1.2.3 From d0054a470c33902f5ae88835ed8a8ecc3cf8faa4 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Thu, 17 Feb 2022 10:13:50 +0000 Subject: soc: add microchip polarfire soc system controller This driver provides an interface for other drivers to access the functions of the system controller on the Microchip PolarFire SoC. Signed-off-by: Conor Dooley Signed-off-by: Nicolas Ferre Link: https://lore.kernel.org/r/20220217101349.2374873-2-conor.dooley@microchip.com --- include/soc/microchip/mpfs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/soc/microchip/mpfs.h b/include/soc/microchip/mpfs.h index 2b64c95f3be5..6466515262bd 100644 --- a/include/soc/microchip/mpfs.h +++ b/include/soc/microchip/mpfs.h @@ -34,9 +34,9 @@ struct mpfs_mss_response { #if IS_ENABLED(CONFIG_POLARFIRE_SOC_SYS_CTRL) -int mpfs_blocking_transaction(struct mpfs_sys_controller *mpfs_client, void *msg); +int mpfs_blocking_transaction(struct mpfs_sys_controller *mpfs_client, struct mpfs_mss_msg *msg); -struct mpfs_sys_controller *mpfs_sys_controller_get(struct device_node *mailbox_node); +struct mpfs_sys_controller *mpfs_sys_controller_get(struct device *dev); #endif /* if IS_ENABLED(CONFIG_POLARFIRE_SOC_SYS_CTRL) */ -- cgit v1.2.3 From fcfaff508b9fa9ad6d8a17d4855e3ec7382886ae Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Mon, 7 Feb 2022 05:09:51 -0800 Subject: soc/tegra: bpmp: cleanup double word in comment Remove the second 'or'. Signed-off-by: Tom Rix Signed-off-by: Thierry Reding --- include/soc/tegra/bpmp-abi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/soc/tegra/bpmp-abi.h b/include/soc/tegra/bpmp-abi.h index bff99f23860c..53171e324d1c 100644 --- a/include/soc/tegra/bpmp-abi.h +++ b/include/soc/tegra/bpmp-abi.h @@ -931,7 +931,7 @@ enum mrq_reset_commands { * @brief Request with MRQ_RESET * * Used by the sender of an #MRQ_RESET message to request BPMP to - * assert or or deassert a given reset line. + * assert or deassert a given reset line. */ struct mrq_reset_request { /** @brief Reset action to perform (@ref mrq_reset_commands) */ -- cgit v1.2.3 From ba7bb663f5547ef474c98df99a97bb4a13c5715f Mon Sep 17 00:00:00 2001 From: David Dunn Date: Wed, 23 Feb 2022 22:57:41 +0000 Subject: KVM: x86: Provide per VM capability for disabling PMU virtualization Add a new capability, KVM_CAP_PMU_CAPABILITY, that takes a bitmask of settings/features to allow userspace to configure PMU virtualization on a per-VM basis. For now, support a single flag, KVM_PMU_CAP_DISABLE, to allow disabling PMU virtualization for a VM even when KVM is configured with enable_pmu=true a module level. To keep KVM simple, disallow changing VM's PMU configuration after vCPUs have been created. Signed-off-by: David Dunn Message-Id: <20220223225743.2703915-2-daviddunn@google.com> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index a02bbf8fd0f6..d2f1efc3aa35 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1142,6 +1142,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_SYS_ATTRIBUTES 209 #define KVM_CAP_PPC_AIL_MODE_3 210 #define KVM_CAP_S390_MEM_OP_EXTENSION 211 +#define KVM_CAP_PMU_CAPABILITY 212 #ifdef KVM_CAP_IRQ_ROUTING @@ -1978,6 +1979,8 @@ struct kvm_dirty_gfn { #define KVM_BUS_LOCK_DETECTION_OFF (1 << 0) #define KVM_BUS_LOCK_DETECTION_EXIT (1 << 1) +#define KVM_PMU_CAP_DISABLE (1 << 0) + /** * struct kvm_stats_header - Header of per vm/vcpu binary statistics data. * @flags: Some extra information for header, always 0 for now. -- cgit v1.2.3 From 766121ba5de38a6f67980ec24a6af76c55def100 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 16 Feb 2022 17:32:24 +0000 Subject: arm64/mte: Add userspace interface for enabling asymmetric mode The architecture provides an asymmetric mode for MTE where tag mismatches are checked asynchronously for stores but synchronously for loads. Allow userspace processes to select this and make it available as a default mode via the existing per-CPU sysfs interface. Since there PR_MTE_TCF_ values are a bitmask (allowing the kernel to choose between the multiple modes) and there are no free bits adjacent to the existing PR_MTE_TCF_ bits the set of bits used to specify the mode becomes disjoint. Programs using the new interface should be aware of this and programs that do not use it will not see any change in behaviour. When userspace requests two possible modes but the system default for the CPU is the third mode (eg, default is synchronous but userspace requests either asynchronous or asymmetric) the preference order is: ASYMM > ASYNC > SYNC This situation is not currently possible since there are only two modes and it is mandatory to have a system default so there could be no ambiguity and there is no ABI change. The chosen order is basically arbitrary as we do not have a clear metric for what is better here. If userspace requests specifically asymmetric mode via the prctl() and the system does not support it then we will return an error, this mirrors how we handle the case where userspace enables MTE on a system that does not support MTE at all and the behaviour that will be seen if running on an older kernel that does not support userspace use of asymmetric mode. Attempts to set asymmetric mode as the default mode will result in an error if the system does not support it. Signed-off-by: Mark Brown Reviewed-by: Catalin Marinas Reviewed-by: Vincenzo Frascino Tested-by: Branislav Rankov Link: https://lore.kernel.org/r/20220216173224.2342152-5-broonie@kernel.org Signed-off-by: Will Deacon --- include/uapi/linux/prctl.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index e998764f0262..4ae2b21e4066 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -238,7 +238,9 @@ struct prctl_mm_map { # define PR_MTE_TCF_NONE 0UL # define PR_MTE_TCF_SYNC (1UL << 1) # define PR_MTE_TCF_ASYNC (1UL << 2) -# define PR_MTE_TCF_MASK (PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC) +# define PR_MTE_TCF_ASYMM (1UL << 19) +# define PR_MTE_TCF_MASK (PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC | \ + PR_MTE_TCF_ASYMM) /* MTE tag inclusion mask */ # define PR_MTE_TAG_SHIFT 3 # define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT) -- cgit v1.2.3 From 8b4195cd6dc3f1f0ab457d23d21e9f72fde0760a Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Wed, 23 Feb 2022 14:43:47 +0100 Subject: mtd: spi-nor: move all xilinx specifics into xilinx.c Mechanically move all the xilinx functions to its own module. Then register the new flash specific ready() function. Signed-off-by: Michael Walle Signed-off-by: Tudor Ambarus Reviewed-by: Pratyush Yadav Link: https://lore.kernel.org/r/20220223134358.1914798-22-michael@walle.cc --- include/linux/mtd/spi-nor.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index fc90fce26e33..b44b05a6f934 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -86,15 +86,6 @@ #define SPINOR_OP_BP 0x02 /* Byte program */ #define SPINOR_OP_AAI_WP 0xad /* Auto address increment word program */ -/* Used for S3AN flashes only */ -#define SPINOR_OP_XSE 0x50 /* Sector erase */ -#define SPINOR_OP_XPP 0x82 /* Page program */ -#define SPINOR_OP_XRDSR 0xd7 /* Read status register */ - -#define XSR_PAGESIZE BIT(0) /* Page size in Po2 or Linear */ -#define XSR_RDY BIT(7) /* Ready */ - - /* Used for Macronix and Winbond flashes. */ #define SPINOR_OP_EN4B 0xb7 /* Enter 4-byte mode */ #define SPINOR_OP_EX4B 0xe9 /* Exit 4-byte mode */ -- cgit v1.2.3 From c770abe52d81089a8b8ecd1fe42722e29bbab5f5 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Wed, 23 Feb 2022 14:43:50 +0100 Subject: mtd: spi-nor: move all micron-st specifics into micron-st.c The flag status register is only available on micron flashes. Move all the functions around that into the micron module. This is almost a mechanical move except for the spi_nor_fsr_ready() which now also checks the normal status register. Previously, this was done in spi_nor_ready(). Signed-off-by: Michael Walle Signed-off-by: Tudor Ambarus Tested-by: Pratyush Yadav # on mt35xu512aba, s28hs512t Reviewed-by: Pratyush Yadav Link: https://lore.kernel.org/r/20220223134358.1914798-25-michael@walle.cc --- include/linux/mtd/spi-nor.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index b44b05a6f934..4622251a79ff 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -47,8 +47,6 @@ #define SPINOR_OP_RDID 0x9f /* Read JEDEC ID */ #define SPINOR_OP_RDSFDP 0x5a /* Read SFDP */ #define SPINOR_OP_RDCR 0x35 /* Read configuration register */ -#define SPINOR_OP_RDFSR 0x70 /* Read flag status register */ -#define SPINOR_OP_CLFSR 0x50 /* Clear flag status register */ #define SPINOR_OP_RDEAR 0xc8 /* Read Extended Address Register */ #define SPINOR_OP_WREAR 0xc5 /* Write Extended Address Register */ #define SPINOR_OP_SRSTEN 0x66 /* Software Reset Enable */ @@ -126,12 +124,6 @@ /* Enhanced Volatile Configuration Register bits */ #define EVCR_QUAD_EN_MICRON BIT(7) /* Micron Quad I/O */ -/* Flag Status Register bits */ -#define FSR_READY BIT(7) /* Device status, 0 = Busy, 1 = Ready */ -#define FSR_E_ERR BIT(5) /* Erase operation status */ -#define FSR_P_ERR BIT(4) /* Program operation status */ -#define FSR_PT_ERR BIT(1) /* Protection error bit */ - /* Status Register 2 bits. */ #define SR2_QUAD_EN_BIT1 BIT(1) #define SR2_LB1 BIT(3) /* Security Register Lock Bit 1 */ -- cgit v1.2.3 From 837d5181beef068c16bb8424c2c1571a7d5d7966 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Wed, 23 Feb 2022 14:43:54 +0100 Subject: mtd: spi-nor: move all spansion specifics into spansion.c The clear status register flags is only available on spansion flashes. Move all the functions around that into the spanion module. Signed-off-by: Michael Walle Signed-off-by: Tudor Ambarus Tested-by: Pratyush Yadav # on mt35xu512aba, s28hs512t Reviewed-by: Pratyush Yadav Link: https://lore.kernel.org/r/20220223134358.1914798-29-michael@walle.cc --- include/linux/mtd/spi-nor.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 4622251a79ff..5e25a7b75ae2 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -90,7 +90,6 @@ /* Used for Spansion flashes only. */ #define SPINOR_OP_BRWR 0x17 /* Bank register write */ -#define SPINOR_OP_CLSR 0x30 /* Clear status register 1 */ /* Used for Micron flashes only. */ #define SPINOR_OP_RD_EVCR 0x65 /* Read EVCR register */ -- cgit v1.2.3 From adf47b75297ebc71c53b6dc2d3c55f42b8fb79fd Mon Sep 17 00:00:00 2001 From: Dave Stevenson Date: Mon, 21 Feb 2022 10:59:02 +0100 Subject: drm/object: Add drm_object_property_get_default_value() function Some functions to create properties (drm_plane_create_zpos_property or drm_plane_create_color_properties for example) will ask for a range of acceptable value and an initial one. This initial value is then stored in the values array for that property. Let's provide an helper to access this property. Acked-by: Daniel Vetter Reviewed-by: Laurent Pinchart Signed-off-by: Dave Stevenson Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20220221095918.18763-7-maxime@cerno.tech --- include/drm/drm_mode_object.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/drm/drm_mode_object.h b/include/drm/drm_mode_object.h index c34a3e8030e1..912f1e415685 100644 --- a/include/drm/drm_mode_object.h +++ b/include/drm/drm_mode_object.h @@ -98,6 +98,10 @@ struct drm_object_properties { * Hence atomic drivers should not use drm_object_property_set_value() * and drm_object_property_get_value() on mutable objects, i.e. those * without the DRM_MODE_PROP_IMMUTABLE flag set. + * + * For atomic drivers the default value of properties is stored in this + * array, so drm_object_property_get_default_value can be used to + * retrieve it. */ uint64_t values[DRM_OBJECT_MAX_PROPERTY]; }; @@ -126,6 +130,9 @@ int drm_object_property_set_value(struct drm_mode_object *obj, int drm_object_property_get_value(struct drm_mode_object *obj, struct drm_property *property, uint64_t *value); +int drm_object_property_get_default_value(struct drm_mode_object *obj, + struct drm_property *property, + uint64_t *val); void drm_object_attach_property(struct drm_mode_object *obj, struct drm_property *property, -- cgit v1.2.3 From 8786fde8421ce755a842051f9528674a1b1f0b9a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 22 Jan 2022 20:54:52 +0000 Subject: Convert NFS from readpages to readahead NFS is one of the last two users of the deprecated ->readpages aop. This conversion looks straightforward, but I have only compile-tested it. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 68f81d8d36de..333ea05e2531 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -601,8 +601,7 @@ nfs_have_writebacks(struct inode *inode) * linux/fs/nfs/read.c */ extern int nfs_readpage(struct file *, struct page *); -extern int nfs_readpages(struct file *, struct address_space *, - struct list_head *, unsigned); +void nfs_readahead(struct readahead_control *); /* * inline functions -- cgit v1.2.3 From 43245eca6e670ebf65908b549641c1460a9cc944 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Wed, 2 Feb 2022 17:55:02 -0500 Subject: NFSv4.1 support for NFS4_RESULT_PRESERVER_UNLINKED In 4.1+, the server is allowed to set a flag NFS4_RESULT_PRESERVE_UNLINKED in reply to the OPEN, that tells the client that it does not need to do a silly rename of an opened file when it's being removed. Signed-off-by: Olga Kornievskaia Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + include/uapi/linux/nfs4.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 333ea05e2531..0e79dbbc759a 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -277,6 +277,7 @@ struct nfs4_copy_state { #define NFS_INO_STALE (1) /* possible stale inode */ #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ #define NFS_INO_INVALIDATING (3) /* inode is being invalidated */ +#define NFS_INO_PRESERVE_UNLINKED (4) /* preserve file if removed while open */ #define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ #define NFS_INO_FORCE_READDIR (7) /* force readdirplus */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ diff --git a/include/uapi/linux/nfs4.h b/include/uapi/linux/nfs4.h index 800bb0ffa6e6..1d2043708bf1 100644 --- a/include/uapi/linux/nfs4.h +++ b/include/uapi/linux/nfs4.h @@ -45,6 +45,7 @@ #define NFS4_OPEN_RESULT_CONFIRM 0x0002 #define NFS4_OPEN_RESULT_LOCKTYPE_POSIX 0x0004 +#define NFS4_OPEN_RESULT_PRESERVE_UNLINKED 0x0008 #define NFS4_OPEN_RESULT_MAY_NOTIFY_LOCK 0x0020 #define NFS4_SHARE_ACCESS_MASK 0x000F -- cgit v1.2.3 From 88a6099fc3274a27814d26dd688fdc5cd7a480ee Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 9 Feb 2022 13:22:48 -0500 Subject: NFS: Replace last uses of NFS_INO_REVAL_PAGECACHE Now that we have more fine grained attribute revalidation, let's just get rid of NFS_INO_REVAL_PAGECACHE. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 0e79dbbc759a..ce3128e4bffa 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -356,11 +356,9 @@ static inline void nfs_mark_for_revalidate(struct inode *inode) struct nfs_inode *nfsi = NFS_I(inode); spin_lock(&inode->i_lock); - nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE - | NFS_INO_INVALID_ACCESS - | NFS_INO_INVALID_ACL - | NFS_INO_INVALID_CHANGE - | NFS_INO_INVALID_CTIME; + nfsi->cache_validity |= NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | + NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | + NFS_INO_INVALID_SIZE; if (S_ISDIR(inode->i_mode)) nfsi->cache_validity |= NFS_INO_INVALID_DATA; spin_unlock(&inode->i_lock); -- cgit v1.2.3 From 41e97b7f8a15d15da03ca15e6ff7b9b7ab7f588c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 9 Feb 2022 13:26:19 -0500 Subject: NFS: Remove unused flag NFS_INO_REVAL_PAGECACHE Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index ce3128e4bffa..72a732a5103c 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -247,7 +247,6 @@ struct nfs4_copy_state { #define NFS_INO_INVALID_ATIME BIT(2) /* cached atime is invalid */ #define NFS_INO_INVALID_ACCESS BIT(3) /* cached access cred invalid */ #define NFS_INO_INVALID_ACL BIT(4) /* cached acls are invalid */ -#define NFS_INO_REVAL_PAGECACHE BIT(5) /* must revalidate pagecache */ #define NFS_INO_REVAL_FORCED BIT(6) /* force revalidation ignoring a delegation */ #define NFS_INO_INVALID_LABEL BIT(7) /* cached label is invalid */ #define NFS_INO_INVALID_CHANGE BIT(8) /* cached change is invalid */ -- cgit v1.2.3 From 891b7023010cc0d62d814619b1893745d7613f7f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jonathan=20Neusch=C3=A4fer?= Date: Sat, 5 Feb 2022 11:36:09 +0100 Subject: clk: mux: Declare u32 *table parameter as const MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The elements of the table are never modified in clk-mux.c. To make this clear to clock drivers, declare the parameter as const u32 *table. Signed-off-by: Jonathan Neuschäfer Link: https://lore.kernel.org/r/20220205103613.1216218-4-j.neuschaefer@gmx.net Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 2faa6f7aa8a8..27be57528874 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -888,7 +888,7 @@ void clk_hw_unregister_divider(struct clk_hw *hw); struct clk_mux { struct clk_hw hw; void __iomem *reg; - u32 *table; + const u32 *table; u32 mask; u8 shift; u8 flags; @@ -913,18 +913,18 @@ struct clk_hw *__clk_hw_register_mux(struct device *dev, struct device_node *np, const struct clk_hw **parent_hws, const struct clk_parent_data *parent_data, unsigned long flags, void __iomem *reg, u8 shift, u32 mask, - u8 clk_mux_flags, u32 *table, spinlock_t *lock); + u8 clk_mux_flags, const u32 *table, spinlock_t *lock); struct clk_hw *__devm_clk_hw_register_mux(struct device *dev, struct device_node *np, const char *name, u8 num_parents, const char * const *parent_names, const struct clk_hw **parent_hws, const struct clk_parent_data *parent_data, unsigned long flags, void __iomem *reg, u8 shift, u32 mask, - u8 clk_mux_flags, u32 *table, spinlock_t *lock); + u8 clk_mux_flags, const u32 *table, spinlock_t *lock); struct clk *clk_register_mux_table(struct device *dev, const char *name, const char * const *parent_names, u8 num_parents, unsigned long flags, void __iomem *reg, u8 shift, u32 mask, - u8 clk_mux_flags, u32 *table, spinlock_t *lock); + u8 clk_mux_flags, const u32 *table, spinlock_t *lock); #define clk_register_mux(dev, name, parent_names, num_parents, flags, reg, \ shift, width, clk_mux_flags, lock) \ @@ -962,9 +962,9 @@ struct clk *clk_register_mux_table(struct device *dev, const char *name, (shift), BIT((width)) - 1, (clk_mux_flags), \ NULL, (lock)) -int clk_mux_val_to_index(struct clk_hw *hw, u32 *table, unsigned int flags, +int clk_mux_val_to_index(struct clk_hw *hw, const u32 *table, unsigned int flags, unsigned int val); -unsigned int clk_mux_index_to_val(u32 *table, unsigned int flags, u8 index); +unsigned int clk_mux_index_to_val(const u32 *table, unsigned int flags, u8 index); void clk_unregister_mux(struct clk *clk); void clk_hw_unregister_mux(struct clk_hw *hw); -- cgit v1.2.3 From f7f497cb702462e8505ff3d8d4e7722ad95626a1 Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Wed, 16 Feb 2022 12:30:35 +0530 Subject: jbd2: kill t_handle_lock transaction spinlock This patch kills t_handle_lock transaction spinlock completely from jbd2. To explain the reasoning, currently there were three sites at which this spinlock was used. 1. jbd2_journal_wait_updates() a. Based on careful code review it can be seen that, we don't need this lock here. This is since we wait for any currently ongoing updates based on a atomic variable t_updates. And we anyway don't take any t_handle_lock while in stop_this_handle(). i.e. write_lock(&journal->j_state_lock() jbd2_journal_wait_updates() stop_this_handle() while (atomic_read(txn->t_updates) { | DEFINE_WAIT(wait); | prepare_to_wait(); | if (atomic_read(txn->t_updates) if (atomic_dec_and_test(txn->t_updates)) write_unlock(&journal->j_state_lock); schedule(); wake_up() write_lock(&journal->j_state_lock); finish_wait(); } txn->t_state = T_COMMIT write_unlock(&journal->j_state_lock); b. Also note that between atomic_inc(&txn->t_updates) in start_this_handle() and jbd2_journal_wait_updates(), the synchronization happens via read_lock(journal->j_state_lock) in start_this_handle(); 2. jbd2_journal_extend() a. jbd2_journal_extend() is called with the handle of each process from task_struct. So no lock required in updating member fields of handle_t b. For member fields of h_transaction, all updates happens only via atomic APIs (which is also within read_lock()). So, no need of this transaction spinlock. 3. update_t_max_wait() Based on Jan suggestion, this can be carefully removed using atomic cmpxchg API. Note that there can be several processes which are waiting for a new transaction to be allocated and started. For doing this only one process will succeed in taking write_lock() and allocating a new txn. After that all of the process will be updating the t_max_wait (max transaction wait time). This can be done via below method w/o taking any locks using atomic cmpxchg. For more details refer [1] new = get_new_val(); old = READ_ONCE(ptr->max_val); while (old < new) old = cmpxchg(&ptr->max_val, old, new); [1]: https://lwn.net/Articles/849237/ Suggested-by: Jan Kara Signed-off-by: Ritesh Harjani Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/d89e599658b4a1f3893a48c6feded200073037fc.1644992076.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 9c3ada74ffb1..a787872e1e86 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -554,9 +554,6 @@ struct transaction_chp_stats_s { * ->j_list_lock * * j_state_lock - * ->t_handle_lock - * - * j_state_lock * ->j_list_lock (journal_unmap_buffer) * */ -- cgit v1.2.3 From 9e8d5470325f25bed7d33f9faaae6d5e4f313650 Mon Sep 17 00:00:00 2001 From: Hammer Hsieh Date: Tue, 22 Feb 2022 17:36:03 +0800 Subject: serial: sunplus-uart: Add Sunplus SoC UART Driver Add Sunplus SoC UART Driver. SP7021 UART block contains 5 UARTs. There are UART0~4 that supported in SP7021, the features list as below. Support Full-duplex communication. Support data packet length configurable. Support stop bit number configurable. Support force break condition. Support baud rate configurable. Support error detection and report. Support RXD Noise Rejection Vote configurable. UART0 pinout only support TX/RX two pins. UART1 to UART4 pinout support TX/RX/CTS/RTS four pins. Normally UART0 used for kernel console, also can be used for normal uart. Command line set "console=ttySUP0,115200", SUP means Sunplus Uart Port. UART driver probe will create path named "/dev/ttySUPx". https://sunplus.atlassian.net/wiki/spaces/doc/pages/1873412290/13.+Universal+Asynchronous+Receiver+Transmitter+UART Signed-off-by: Hammer Hsieh Link: https://lore.kernel.org/r/1645522563-17183-3-git-send-email-hammerh0314@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/serial_core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index 8885e69178bd..6faf502b7860 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -277,4 +277,7 @@ /* Freescale LINFlexD UART */ #define PORT_LINFLEXUART 122 +/* Sunplus UART */ +#define PORT_SUNPLUS 123 + #endif /* _UAPILINUX_SERIAL_CORE_H */ -- cgit v1.2.3 From c2faf737abfb10f88f2d2612d573e9edc3c42c37 Mon Sep 17 00:00:00 2001 From: Max Staudt Date: Fri, 11 Feb 2022 15:10:36 +0100 Subject: tty: Reserve ldisc 29 for development purposes It's handy to have an ldisc number free for out-of-tree testing. This way, a new ldisc can be developed on any running system, without having to recompile the kernel just to define a new number. This is the highest number (and also the last one) available under the old numbering scheme, so let's reserve it before it's too late. From now on, every new ldisc upstreamed will have to increment NR_LDISCS in lockstep with its addition to the table in tty.h. Signed-off-by: Max Staudt Link: https://lore.kernel.org/r/20220211141036.6403-1-max@enpas.org Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/tty.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/tty.h b/include/uapi/linux/tty.h index a58deb3061eb..9d0f06bfbac3 100644 --- a/include/uapi/linux/tty.h +++ b/include/uapi/linux/tty.h @@ -6,8 +6,6 @@ * 'tty.h' defines some structures used by tty_io.c and some defines. */ -#define NR_LDISCS 30 - /* line disciplines */ #define N_TTY 0 #define N_SLIP 1 @@ -39,5 +37,9 @@ #define N_SPEAKUP 26 /* Speakup communication with synths */ #define N_NULL 27 /* Null ldisc used for error handling */ #define N_MCTP 28 /* MCTP-over-serial */ +#define N_DEVELOPMENT 29 /* Manual out-of-tree testing */ + +/* Always the newest line discipline + 1 */ +#define NR_LDISCS 30 #endif /* _UAPI_LINUX_TTY_H */ -- cgit v1.2.3 From 5e187189ec324f78035d33a4bc123a9c4ca6f3e3 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sat, 26 Feb 2022 12:18:29 +0800 Subject: net: ip: add skb drop reasons for ip egress path Replace kfree_skb() which is used in the packet egress path of IP layer with kfree_skb_reason(). Functions that are involved include: __ip_queue_xmit() ip_finish_output() ip_mc_finish_output() ip6_output() ip6_finish_output() ip6_finish_output2() Following new drop reasons are introduced: SKB_DROP_REASON_IP_OUTNOROUTES SKB_DROP_REASON_BPF_CGROUP_EGRESS SKB_DROP_REASON_IPV6DISABLED SKB_DROP_REASON_NEIGH_CREATEFAIL Reviewed-by: Mengen Sun Reviewed-by: Hao Peng Signed-off-by: Menglong Dong Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 9 +++++++++ include/trace/events/skb.h | 5 +++++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 31be38078918..62b4bed1b7bc 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -380,6 +380,15 @@ enum skb_drop_reason { * the ofo queue, corresponding to * LINUX_MIB_TCPOFOMERGE */ + SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */ + SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by + * BPF_PROG_TYPE_CGROUP_SKB + * eBPF program + */ + SKB_DROP_REASON_IPV6DISABLED, /* IPv6 is disabled on the device */ + SKB_DROP_REASON_NEIGH_CREATEFAIL, /* failed to create neigh + * entry + */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 2ab7193313aa..97f8097651da 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -37,6 +37,11 @@ EM(SKB_DROP_REASON_TCP_OLD_DATA, TCP_OLD_DATA) \ EM(SKB_DROP_REASON_TCP_OVERWINDOW, TCP_OVERWINDOW) \ EM(SKB_DROP_REASON_TCP_OFOMERGE, TCP_OFOMERGE) \ + EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES) \ + EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS, \ + BPF_CGROUP_EGRESS) \ + EM(SKB_DROP_REASON_IPV6DISABLED, IPV6DISABLED) \ + EM(SKB_DROP_REASON_NEIGH_CREATEFAIL, NEIGH_CREATEFAIL) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From a5736edda10ca2ba075606baad1dda3f2426766d Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sat, 26 Feb 2022 12:18:30 +0800 Subject: net: neigh: use kfree_skb_reason() for __neigh_event_send() Replace kfree_skb() used in __neigh_event_send() with kfree_skb_reason(). Following drop reasons are added: SKB_DROP_REASON_NEIGH_FAILED SKB_DROP_REASON_NEIGH_QUEUEFULL SKB_DROP_REASON_NEIGH_DEAD The first two reasons above should be the hot path that skb drops in neighbour subsystem. Reviewed-by: Mengen Sun Reviewed-by: Hao Peng Signed-off-by: Menglong Dong Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 +++++ include/trace/events/skb.h | 3 +++ 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 62b4bed1b7bc..d67941f78b92 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -389,6 +389,11 @@ enum skb_drop_reason { SKB_DROP_REASON_NEIGH_CREATEFAIL, /* failed to create neigh * entry */ + SKB_DROP_REASON_NEIGH_FAILED, /* neigh entry in failed state */ + SKB_DROP_REASON_NEIGH_QUEUEFULL, /* arp_queue for neigh + * entry is full + */ + SKB_DROP_REASON_NEIGH_DEAD, /* neigh entry is dead */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 97f8097651da..1977f301260d 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -42,6 +42,9 @@ BPF_CGROUP_EGRESS) \ EM(SKB_DROP_REASON_IPV6DISABLED, IPV6DISABLED) \ EM(SKB_DROP_REASON_NEIGH_CREATEFAIL, NEIGH_CREATEFAIL) \ + EM(SKB_DROP_REASON_NEIGH_FAILED, NEIGH_FAILED) \ + EM(SKB_DROP_REASON_NEIGH_QUEUEFULL, NEIGH_QUEUEFULL) \ + EM(SKB_DROP_REASON_NEIGH_DEAD, NEIGH_DEAD) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From 21ca9fb62d4688da41825e0f05d8e7e26afc69d6 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 24 Feb 2022 16:20:10 +0200 Subject: PCI/IOV: Add pci_iov_vf_id() to get VF index The PCI core uses the VF index internally, often called the vf_id, during the setup of the VF, eg pci_iov_add_virtfn(). This index is needed for device drivers that implement live migration for their internal operations that configure/control their VFs. Specifically, mlx5_vfio_pci driver that is introduced in coming patches from this series needs it and not the bus/device/function which is exposed today. Add pci_iov_vf_id() which computes the vf_id by reversing the math that was used to create the bus/device/function. Link: https://lore.kernel.org/all/20220224142024.147653-2-yishaih@nvidia.com Signed-off-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/pci.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 8253a5413d7c..3d4ff7b35ad1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2166,7 +2166,7 @@ void __iomem *pci_ioremap_wc_bar(struct pci_dev *pdev, int bar); #ifdef CONFIG_PCI_IOV int pci_iov_virtfn_bus(struct pci_dev *dev, int id); int pci_iov_virtfn_devfn(struct pci_dev *dev, int id); - +int pci_iov_vf_id(struct pci_dev *dev); int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn); void pci_disable_sriov(struct pci_dev *dev); @@ -2194,6 +2194,12 @@ static inline int pci_iov_virtfn_devfn(struct pci_dev *dev, int id) { return -ENOSYS; } + +static inline int pci_iov_vf_id(struct pci_dev *dev) +{ + return -ENOSYS; +} + static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn) { return -ENODEV; } -- cgit v1.2.3 From a7e9f240c0da4fb73a353c603daf4beba04c6ecf Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 24 Feb 2022 16:20:13 +0200 Subject: PCI/IOV: Add pci_iov_get_pf_drvdata() to allow VF reaching the drvdata of a PF There are some cases where a SR-IOV VF driver will need to reach into and interact with the PF driver. This requires accessing the drvdata of the PF. Provide a function pci_iov_get_pf_drvdata() to return this PF drvdata in a safe way. Normally accessing a drvdata of a foreign struct device would be done using the device_lock() to protect against device driver probe()/remove() races. However, due to the design of pci_enable_sriov() this will result in a ABBA deadlock on the device_lock as the PF's device_lock is held during PF sriov_configure() while calling pci_enable_sriov() which in turn holds the VF's device_lock while calling VF probe(), and similarly for remove. This means the VF driver can never obtain the PF's device_lock. Instead use the implicit locking created by pci_enable/disable_sriov(). A VF driver can access its PF drvdata only while its own driver is attached, and the PF driver can control access to its own drvdata based on when it calls pci_enable/disable_sriov(). To use this API the PF driver will setup the PF drvdata in the probe() function. pci_enable_sriov() is only called from sriov_configure() which cannot happen until probe() completes, ensuring no VF races with drvdata setup. For removal, the PF driver must call pci_disable_sriov() in its remove function before destroying any of the drvdata. This ensures that all VF drivers are unbound before returning, fencing concurrent access to the drvdata. The introduction of a new function to do this access makes clear the special locking scheme and the documents the requirements on the PF/VF drivers using this. Link: https://lore.kernel.org/all/20220224142024.147653-5-yishaih@nvidia.com Signed-off-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/pci.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 3d4ff7b35ad1..60d423d8f0c4 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2167,6 +2167,7 @@ void __iomem *pci_ioremap_wc_bar(struct pci_dev *pdev, int bar); int pci_iov_virtfn_bus(struct pci_dev *dev, int id); int pci_iov_virtfn_devfn(struct pci_dev *dev, int id); int pci_iov_vf_id(struct pci_dev *dev); +void *pci_iov_get_pf_drvdata(struct pci_dev *dev, struct pci_driver *pf_driver); int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn); void pci_disable_sriov(struct pci_dev *dev); @@ -2200,6 +2201,12 @@ static inline int pci_iov_vf_id(struct pci_dev *dev) return -ENOSYS; } +static inline void *pci_iov_get_pf_drvdata(struct pci_dev *dev, + struct pci_driver *pf_driver) +{ + return ERR_PTR(-EINVAL); +} + static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn) { return -ENODEV; } -- cgit v1.2.3 From 1695b97b291e79295bf5c26cba5ecc4b443d8ac7 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 24 Feb 2022 16:20:14 +0200 Subject: net/mlx5: Expose APIs to get/put the mlx5 core device Expose an API to get the mlx5 core device from a given VF PCI device if mlx5_core is its driver. Upon the get API we stay with the intf_state_mutex locked to make sure that the device can't be gone/unloaded till the caller will complete its job over the device, this expects to be for a short period of time for any flow that the lock is taken. Upon the put API we unlock the intf_state_mutex. The use case for those APIs is the migration flow of a VF over VFIO PCI. In that case the VF doesn't ride on mlx5_core, because the device is driving *two* different PCI devices, the PF owned by mlx5_core and the VF owned by the vfio driver. The mlx5_core of the PF is accessed only during the narrow window of the VF's ioctl that requires its services. This allows the PF driver to be more independent of the VF driver, so long as it doesn't reset the FW. Link: https://lore.kernel.org/all/20220224142024.147653-6-yishaih@nvidia.com Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 78655d8d13a7..319322a8ff94 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1143,6 +1143,9 @@ int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, u64 length, u16 uid, phys_addr_t addr, u32 obj_id); +struct mlx5_core_dev *mlx5_vf_get_core_dev(struct pci_dev *pdev); +void mlx5_vf_put_core_dev(struct mlx5_core_dev *mdev); + #ifdef CONFIG_MLX5_CORE_IPOIB struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, struct ib_device *ibdev, -- cgit v1.2.3 From adfdaff3d14fe819a0420d81788f7ebbcd954940 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 24 Feb 2022 16:20:15 +0200 Subject: net/mlx5: Introduce migration bits and structures Introduce migration IFC related stuff to enable migration commands. Link: https://lore.kernel.org/all/20220224142024.147653-7-yishaih@nvidia.com Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 147 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 146 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 598ac3bcc901..b1c27409c997 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -127,6 +127,11 @@ enum { MLX5_CMD_OP_QUERY_SF_PARTITION = 0x111, MLX5_CMD_OP_ALLOC_SF = 0x113, MLX5_CMD_OP_DEALLOC_SF = 0x114, + MLX5_CMD_OP_SUSPEND_VHCA = 0x115, + MLX5_CMD_OP_RESUME_VHCA = 0x116, + MLX5_CMD_OP_QUERY_VHCA_MIGRATION_STATE = 0x117, + MLX5_CMD_OP_SAVE_VHCA_STATE = 0x118, + MLX5_CMD_OP_LOAD_VHCA_STATE = 0x119, MLX5_CMD_OP_CREATE_MKEY = 0x200, MLX5_CMD_OP_QUERY_MKEY = 0x201, MLX5_CMD_OP_DESTROY_MKEY = 0x202, @@ -1757,7 +1762,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_682[0x1]; u8 log_max_sf[0x5]; u8 apu[0x1]; - u8 reserved_at_689[0x7]; + u8 reserved_at_689[0x4]; + u8 migration[0x1]; + u8 reserved_at_68e[0x2]; u8 log_min_sf_size[0x8]; u8 max_num_sf_partitions[0x8]; @@ -11519,4 +11526,142 @@ enum { MLX5_MTT_PERM_RW = MLX5_MTT_PERM_READ | MLX5_MTT_PERM_WRITE, }; +enum { + MLX5_SUSPEND_VHCA_IN_OP_MOD_SUSPEND_INITIATOR = 0x0, + MLX5_SUSPEND_VHCA_IN_OP_MOD_SUSPEND_RESPONDER = 0x1, +}; + +struct mlx5_ifc_suspend_vhca_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_suspend_vhca_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +enum { + MLX5_RESUME_VHCA_IN_OP_MOD_RESUME_RESPONDER = 0x0, + MLX5_RESUME_VHCA_IN_OP_MOD_RESUME_INITIATOR = 0x1, +}; + +struct mlx5_ifc_resume_vhca_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_resume_vhca_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_query_vhca_migration_state_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_query_vhca_migration_state_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; + + u8 required_umem_size[0x20]; + + u8 reserved_at_a0[0x160]; +}; + +struct mlx5_ifc_save_vhca_state_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x20]; + + u8 va[0x40]; + + u8 mkey[0x20]; + + u8 size[0x20]; +}; + +struct mlx5_ifc_save_vhca_state_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 actual_image_size[0x20]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_load_vhca_state_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x20]; + + u8 va[0x40]; + + u8 mkey[0x20]; + + u8 size[0x20]; +}; + +struct mlx5_ifc_load_vhca_state_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + #endif /* MLX5_IFC_H */ -- cgit v1.2.3 From e8eb9e32999dc5995b19d5141f8ebb38f69696fc Mon Sep 17 00:00:00 2001 From: Dimitris Michailidis Date: Thu, 24 Feb 2022 18:58:55 -0800 Subject: PCI: Add Fungible Vendor ID to pci_ids.h Cc: Bjorn Helgaas Cc: linux-pci@vger.kernel.org Signed-off-by: Dimitris Michailidis Acked-by: Bjorn Helgaas Signed-off-by: David S. Miller --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index aad54c666407..c7e6f2043c7d 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2561,6 +2561,8 @@ #define PCI_VENDOR_ID_HYGON 0x1d94 +#define PCI_VENDOR_ID_FUNGIBLE 0x1dad + #define PCI_VENDOR_ID_HXT 0x1dbf #define PCI_VENDOR_ID_TEKRAM 0x1de1 -- cgit v1.2.3 From 91495f21fcec3a889d6a9c21e6df16c4c15f2184 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 25 Feb 2022 11:22:16 +0200 Subject: net: dsa: tag_8021q: replace the SVL bridging with VLAN-unaware IVL bridging For VLAN-unaware bridging, tag_8021q uses something perhaps a bit too tied with the sja1105 switch: each port uses the same pvid which is also used for standalone operation (a unique one from which the source port and device ID can be retrieved when packets from that port are forwarded to the CPU). Since each port has a unique pvid when performing autonomous forwarding, the switch must be configured for Shared VLAN Learning (SVL) such that the VLAN ID itself is ignored when performing FDB lookups. Without SVL, packets would always be flooded, since FDB lookup in the source port's VLAN would never find any entry. First of all, to make tag_8021q more palatable to switches which might not support Shared VLAN Learning, let's just use a common VLAN for all ports that are under the same bridge. Secondly, using Shared VLAN Learning means that FDB isolation can never be enforced. But if all ports under the same VLAN-unaware bridge share the same VLAN ID, it can. The disadvantage is that the CPU port can no longer perform precise source port identification for these packets. But at least we have a mechanism which has proven to be adequate for that situation: imprecise RX (dsa_find_designated_bridge_port_by_vid), which is what we use for termination on VLAN-aware bridges. The VLAN ID that VLAN-unaware bridges will use with tag_8021q is the same one as we were previously using for imprecise TX (bridge TX forwarding offload). It is already allocated, it is just a matter of using it. Note that because now all ports under the same bridge share the same VLAN, the complexity of performing a tag_8021q bridge join decreases dramatically. We no longer have to install the RX VLAN of a newly joining port into the port membership of the existing bridge ports. The newly joining port just becomes a member of the VLAN corresponding to that bridge, and the other ports are already members of it from when they joined the bridge themselves. So forwarding works properly. This means that we can unhook dsa_tag_8021q_bridge_{join,leave} from the cross-chip notifier level dsa_switch_bridge_{join,leave}. We can put these calls directly into the sja1105 driver. With this new mode of operation, a port controlled by tag_8021q can have two pvids whereas before it could only have one. The pvid for standalone operation is different from the pvid used for VLAN-unaware bridging. This is done, again, so that FDB isolation can be enforced. Let tag_8021q manage this by deleting the standalone pvid when a port joins a bridge, and restoring it when it leaves it. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 939a1beaddf7..f47f227baa27 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -32,17 +32,17 @@ int dsa_tag_8021q_register(struct dsa_switch *ds, __be16 proto); void dsa_tag_8021q_unregister(struct dsa_switch *ds); +int dsa_tag_8021q_bridge_join(struct dsa_switch *ds, int port, + struct dsa_bridge bridge); + +void dsa_tag_8021q_bridge_leave(struct dsa_switch *ds, int port, + struct dsa_bridge bridge); + struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci); void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id); -int dsa_tag_8021q_bridge_tx_fwd_offload(struct dsa_switch *ds, int port, - struct dsa_bridge bridge); - -void dsa_tag_8021q_bridge_tx_fwd_unoffload(struct dsa_switch *ds, int port, - struct dsa_bridge bridge); - u16 dsa_8021q_bridge_tx_fwd_offload_vid(unsigned int bridge_num); u16 dsa_tag_8021q_tx_vid(const struct dsa_port *dp); -- cgit v1.2.3 From d7f9787a763f35225287aedb9364c972ae128d18 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 25 Feb 2022 11:22:17 +0200 Subject: net: dsa: tag_8021q: add support for imprecise RX based on the VBID The sja1105 switch can't populate the PORT field of the tag_8021q header when sending a frame to the CPU with a non-zero VBID. Similar to dsa_find_designated_bridge_port_by_vid() which performs imprecise RX for VLAN-aware bridges, let's introduce a helper in tag_8021q for performing imprecise RX based on the VLAN that it has allocated for a VLAN-unaware bridge. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index f47f227baa27..92f5243b841e 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -41,7 +41,11 @@ void dsa_tag_8021q_bridge_leave(struct dsa_switch *ds, int port, struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci); -void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id); +void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, + int *vbid); + +struct net_device *dsa_tag_8021q_find_port_by_vbid(struct net_device *master, + int vbid); u16 dsa_8021q_bridge_tx_fwd_offload_vid(unsigned int bridge_num); -- cgit v1.2.3 From 04b67e18ce5b29785578397f6785f28f512d64aa Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 25 Feb 2022 11:22:20 +0200 Subject: net: dsa: tag_8021q: merge RX and TX VLANs In the old Shared VLAN Learning mode of operation that tag_8021q previously used for forwarding, we needed to have distinct concepts for an RX and a TX VLAN. An RX VLAN could be installed on all ports that were members of a given bridge, so that autonomous forwarding could still work, while a TX VLAN was dedicated for precise packet steering, so it just contained the CPU port and one egress port. Now that tag_8021q uses Independent VLAN Learning and imprecise RX/TX all over, those lines have been blurred and we no longer have the need to do precise TX towards a port that is in a bridge. As for standalone ports, it is fine to use the same VLAN ID for both RX and TX. This patch changes the tag_8021q format by shifting the VLAN range it reserves, and halving it. Previously, our DIR bits were encoding the VLAN direction (RX/TX) and were set to either 1 or 2. This meant that tag_8021q reserved 2K VLANs, or 50% of the available range. Change the DIR bits to a hardcoded value of 3 now, which makes tag_8021q reserve only 1K VLANs, and a different range now (the last 1K). This is done so that we leave the old format in place in case we need to return to it. In terms of code, the vid_is_dsa_8021q_rxvlan and vid_is_dsa_8021q_txvlan functions go away. Any vid_is_dsa_8021q is both a TX and an RX VLAN, and they are no longer distinct. For example, felix which did different things for different VLAN types, now needs to handle the RX and the TX logic for the same VLAN. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 92f5243b841e..b4e2862633f6 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -49,18 +49,12 @@ struct net_device *dsa_tag_8021q_find_port_by_vbid(struct net_device *master, u16 dsa_8021q_bridge_tx_fwd_offload_vid(unsigned int bridge_num); -u16 dsa_tag_8021q_tx_vid(const struct dsa_port *dp); - -u16 dsa_tag_8021q_rx_vid(const struct dsa_port *dp); +u16 dsa_tag_8021q_standalone_vid(const struct dsa_port *dp); int dsa_8021q_rx_switch_id(u16 vid); int dsa_8021q_rx_source_port(u16 vid); -bool vid_is_dsa_8021q_rxvlan(u16 vid); - -bool vid_is_dsa_8021q_txvlan(u16 vid); - bool vid_is_dsa_8021q(u16 vid); #endif /* _NET_DSA_8021Q_H */ -- cgit v1.2.3 From b6362bdf750b4ba266d4a10156174ec52460e73d Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 25 Feb 2022 11:22:21 +0200 Subject: net: dsa: tag_8021q: rename dsa_8021q_bridge_tx_fwd_offload_vid The dsa_8021q_bridge_tx_fwd_offload_vid is no longer used just for bridge TX forwarding offload, it is the private VLAN reserved for VLAN-unaware bridging in a way that is compatible with FDB isolation. So just rename it dsa_tag_8021q_bridge_vid. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/dsa/8021q.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index b4e2862633f6..3ed117e299ec 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -47,7 +47,7 @@ void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, struct net_device *dsa_tag_8021q_find_port_by_vbid(struct net_device *master, int vbid); -u16 dsa_8021q_bridge_tx_fwd_offload_vid(unsigned int bridge_num); +u16 dsa_tag_8021q_bridge_vid(unsigned int bridge_num); u16 dsa_tag_8021q_standalone_vid(const struct dsa_port *dp); -- cgit v1.2.3 From c26933639b5402c174c65c01d33f145622784012 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 25 Feb 2022 11:22:22 +0200 Subject: net: dsa: request drivers to perform FDB isolation For DSA, to encourage drivers to perform FDB isolation simply means to track which bridge does each FDB and MDB entry belong to. It then becomes the driver responsibility to use something that makes the FDB entry from one bridge not match the FDB lookup of ports from other bridges. The top-level functions where the bridge is determined are: - dsa_port_fdb_{add,del} - dsa_port_host_fdb_{add,del} - dsa_port_mdb_{add,del} - dsa_port_host_mdb_{add,del} aka the pre-crosschip-notifier functions. Changing the API to pass a reference to a bridge is not superfluous, and looking at the passed bridge argument is not the same as having the driver look at dsa_to_port(ds, port)->bridge from the ->port_fdb_add() method. DSA installs FDB and MDB entries on shared (CPU and DSA) ports as well, and those do not have any dp->bridge information to retrieve, because they are not in any bridge - they are merely the pipes that serve the user ports that are in one or multiple bridges. The struct dsa_bridge associated with each FDB/MDB entry is encapsulated in a larger "struct dsa_db" database. Although only databases associated to bridges are notified for now, this API will be the starting point for implementing IFF_UNICAST_FLT in DSA. There, the idea is to install FDB entries on the CPU port which belong to the corresponding user port's port database. These are supposed to match only when the port is standalone. It is better to introduce the API in its expected final form than to introduce it for bridges first, then to have to change drivers which may have made one or more assumptions. Drivers can use the provided bridge.num, but they can also use a different numbering scheme that is more convenient. DSA must perform refcounting on the CPU and DSA ports by also taking into account the bridge number. So if two bridges request the same local address, DSA must notify the driver twice, once for each bridge. In fact, if the driver supports FDB isolation, DSA must perform refcounting per bridge, but if the driver doesn't, DSA must refcount host addresses across all bridges, otherwise it would be telling the driver to delete an FDB entry for a bridge and the driver would delete it for all bridges. So introduce a bool fdb_isolation in drivers which would make all bridge databases passed to the cross-chip notifier have the same number (0). This makes dsa_mac_addr_find() -> dsa_db_equal() say that all bridge databases are the same database - which is essentially the legacy behavior. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/dsa.h | 42 ++++++++++++++++++++++++++++++++++++------ 1 file changed, 36 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 01faba89c987..87c5f18eb381 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -341,11 +341,28 @@ struct dsa_link { struct list_head list; }; +enum dsa_db_type { + DSA_DB_PORT, + DSA_DB_LAG, + DSA_DB_BRIDGE, +}; + +struct dsa_db { + enum dsa_db_type type; + + union { + const struct dsa_port *dp; + struct dsa_lag lag; + struct dsa_bridge bridge; + }; +}; + struct dsa_mac_addr { unsigned char addr[ETH_ALEN]; u16 vid; refcount_t refcount; struct list_head list; + struct dsa_db db; }; struct dsa_vlan { @@ -409,6 +426,13 @@ struct dsa_switch { */ u32 mtu_enforcement_ingress:1; + /* Drivers that isolate the FDBs of multiple bridges must set this + * to true to receive the bridge as an argument in .port_fdb_{add,del} + * and .port_mdb_{add,del}. Otherwise, the bridge.num will always be + * passed as zero. + */ + u32 fdb_isolation:1; + /* Listener for switch fabric events */ struct notifier_block nb; @@ -941,23 +965,29 @@ struct dsa_switch_ops { * Forwarding database */ int (*port_fdb_add)(struct dsa_switch *ds, int port, - const unsigned char *addr, u16 vid); + const unsigned char *addr, u16 vid, + struct dsa_db db); int (*port_fdb_del)(struct dsa_switch *ds, int port, - const unsigned char *addr, u16 vid); + const unsigned char *addr, u16 vid, + struct dsa_db db); int (*port_fdb_dump)(struct dsa_switch *ds, int port, dsa_fdb_dump_cb_t *cb, void *data); int (*lag_fdb_add)(struct dsa_switch *ds, struct dsa_lag lag, - const unsigned char *addr, u16 vid); + const unsigned char *addr, u16 vid, + struct dsa_db db); int (*lag_fdb_del)(struct dsa_switch *ds, struct dsa_lag lag, - const unsigned char *addr, u16 vid); + const unsigned char *addr, u16 vid, + struct dsa_db db); /* * Multicast database */ int (*port_mdb_add)(struct dsa_switch *ds, int port, - const struct switchdev_obj_port_mdb *mdb); + const struct switchdev_obj_port_mdb *mdb, + struct dsa_db db); int (*port_mdb_del)(struct dsa_switch *ds, int port, - const struct switchdev_obj_port_mdb *mdb); + const struct switchdev_obj_port_mdb *mdb, + struct dsa_db db); /* * RXNFC */ -- cgit v1.2.3 From 06b9cce42634a50f2840777a66553b02320db5ef Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 25 Feb 2022 11:22:23 +0200 Subject: net: dsa: pass extack to .port_bridge_join driver methods As FDB isolation cannot be enforced between VLAN-aware bridges in lack of hardware assistance like extra FID bits, it seems plausible that many DSA switches cannot do it. Therefore, they need to reject configurations with multiple VLAN-aware bridges from the two code paths that can transition towards that state: - joining a VLAN-aware bridge - toggling VLAN awareness on an existing bridge The .port_vlan_filtering method already propagates the netlink extack to the driver, let's propagate it from .port_bridge_join too, to make sure that the driver can use the same function for both. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/dsa.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 87c5f18eb381..cfedcfb86350 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -937,7 +937,8 @@ struct dsa_switch_ops { int (*set_ageing_time)(struct dsa_switch *ds, unsigned int msecs); int (*port_bridge_join)(struct dsa_switch *ds, int port, struct dsa_bridge bridge, - bool *tx_fwd_offload); + bool *tx_fwd_offload, + struct netlink_ext_ack *extack); void (*port_bridge_leave)(struct dsa_switch *ds, int port, struct dsa_bridge bridge); void (*port_stp_state_set)(struct dsa_switch *ds, int port, @@ -1021,7 +1022,8 @@ struct dsa_switch_ops { */ int (*crosschip_bridge_join)(struct dsa_switch *ds, int tree_index, int sw_index, int port, - struct dsa_bridge bridge); + struct dsa_bridge bridge, + struct netlink_ext_ack *extack); void (*crosschip_bridge_leave)(struct dsa_switch *ds, int tree_index, int sw_index, int port, struct dsa_bridge bridge); -- cgit v1.2.3 From 54c319846086e57071fd0e92d20f2cba0fbf0e79 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 25 Feb 2022 11:22:25 +0200 Subject: net: mscc: ocelot: enforce FDB isolation when VLAN-unaware Currently ocelot uses a pvid of 0 for standalone ports and ports under a VLAN-unaware bridge, and the pvid of the bridge for ports under a VLAN-aware bridge. Standalone ports do not perform learning, but packets received on them are still subject to FDB lookups. So if the MAC DA that a standalone port receives has been also learned on a VLAN-unaware bridge port, ocelot will attempt to forward to that port, even though it can't, so it will drop packets. So there is a desire to avoid that, and isolate the FDBs of different bridges from one another, and from standalone ports. The ocelot switch library has two distinct entry points: the felix DSA driver and the ocelot switchdev driver. We need to code up a minimal bridge_num allocation in the ocelot switchdev driver too, this is copied from DSA with the exception that ocelot does not care about DSA trees, cross-chip bridging etc. So it only looks at its own ports that are already in the same bridge. The ocelot switchdev driver uses the bridge_num it has allocated itself, while the felix driver uses the bridge_num allocated by DSA. They are both stored inside ocelot_port->bridge_num by the common function ocelot_port_bridge_join() which receives the bridge_num passed by value. Once we have a bridge_num, we can only use it to enforce isolation between VLAN-unaware bridges. As far as I can see, ocelot does not have anything like a FID that further makes VLAN 100 from a port be different to VLAN 100 from another port with regard to FDB lookup. So we simply deny multiple VLAN-aware bridges. For VLAN-unaware bridges, we crop the 4000-4095 VLAN region and we allocate a VLAN for each bridge_num. This will be used as the pvid of each port that is under that VLAN-unaware bridge, for as long as that bridge is VLAN-unaware. VID 0 remains only for standalone ports. It is okay if all standalone ports use the same VID 0, since they perform no address learning, the FDB will contain no entry in VLAN 0, so the packets will always be flooded to the only possible destination, the CPU port. The CPU port module doesn't need to be member of the VLANs to receive packets, but if we use the DSA tag_8021q protocol, those packets are part of the data plane as far as ocelot is concerned, so there it needs to. Just ensure that the DSA tag_8021q CPU port is a member of all reserved VLANs when it is created, and is removed when it is deleted. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 31 +++++++++++++++++++++---------- 1 file changed, 21 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index dd4fc34d2992..ee3c59639d70 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -668,6 +668,7 @@ struct ocelot_port { u16 mrp_ring_id; struct net_device *bridge; + int bridge_num; u8 stp_state; int speed; @@ -713,6 +714,8 @@ struct ocelot { enum ocelot_tag_prefix npi_inj_prefix; enum ocelot_tag_prefix npi_xtr_prefix; + unsigned long bridges; + struct list_head multicast; struct list_head pgids; @@ -846,6 +849,9 @@ void ocelot_deinit(struct ocelot *ocelot); void ocelot_init_port(struct ocelot *ocelot, int port); void ocelot_deinit_port(struct ocelot *ocelot, int port); +void ocelot_port_set_dsa_8021q_cpu(struct ocelot *ocelot, int port); +void ocelot_port_unset_dsa_8021q_cpu(struct ocelot *ocelot, int port); + /* DSA callbacks */ void ocelot_get_strings(struct ocelot *ocelot, int port, u32 sset, u8 *data); void ocelot_get_ethtool_stats(struct ocelot *ocelot, int port, u64 *data); @@ -863,21 +869,24 @@ int ocelot_port_pre_bridge_flags(struct ocelot *ocelot, int port, struct switchdev_brport_flags val); void ocelot_port_bridge_flags(struct ocelot *ocelot, int port, struct switchdev_brport_flags val); -void ocelot_port_bridge_join(struct ocelot *ocelot, int port, - struct net_device *bridge); +int ocelot_port_bridge_join(struct ocelot *ocelot, int port, + struct net_device *bridge, int bridge_num, + struct netlink_ext_ack *extack); void ocelot_port_bridge_leave(struct ocelot *ocelot, int port, struct net_device *bridge); int ocelot_mact_flush(struct ocelot *ocelot, int port); int ocelot_fdb_dump(struct ocelot *ocelot, int port, dsa_fdb_dump_cb_t *cb, void *data); -int ocelot_fdb_add(struct ocelot *ocelot, int port, - const unsigned char *addr, u16 vid); -int ocelot_fdb_del(struct ocelot *ocelot, int port, - const unsigned char *addr, u16 vid); +int ocelot_fdb_add(struct ocelot *ocelot, int port, const unsigned char *addr, + u16 vid, const struct net_device *bridge); +int ocelot_fdb_del(struct ocelot *ocelot, int port, const unsigned char *addr, + u16 vid, const struct net_device *bridge); int ocelot_lag_fdb_add(struct ocelot *ocelot, struct net_device *bond, - const unsigned char *addr, u16 vid); + const unsigned char *addr, u16 vid, + const struct net_device *bridge); int ocelot_lag_fdb_del(struct ocelot *ocelot, struct net_device *bond, - const unsigned char *addr, u16 vid); + const unsigned char *addr, u16 vid, + const struct net_device *bridge); int ocelot_vlan_prepare(struct ocelot *ocelot, int port, u16 vid, bool pvid, bool untagged, struct netlink_ext_ack *extack); int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid, @@ -901,9 +910,11 @@ int ocelot_cls_flower_destroy(struct ocelot *ocelot, int port, int ocelot_cls_flower_stats(struct ocelot *ocelot, int port, struct flow_cls_offload *f, bool ingress); int ocelot_port_mdb_add(struct ocelot *ocelot, int port, - const struct switchdev_obj_port_mdb *mdb); + const struct switchdev_obj_port_mdb *mdb, + const struct net_device *bridge); int ocelot_port_mdb_del(struct ocelot *ocelot, int port, - const struct switchdev_obj_port_mdb *mdb); + const struct switchdev_obj_port_mdb *mdb, + const struct net_device *bridge); int ocelot_port_lag_join(struct ocelot *ocelot, int port, struct net_device *bond, struct netdev_lag_upper_info *info); -- cgit v1.2.3 From bc437f7515f5e14aec9f2801412d9ea48116a97d Mon Sep 17 00:00:00 2001 From: Liam Beguin Date: Sat, 12 Feb 2022 21:57:30 -0500 Subject: iio: afe: rescale: expose scale processing function In preparation for the addition of kunit tests, expose the logic responsible for combining channel scales. Signed-off-by: Liam Beguin Reviewed-by: Peter Rosin Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20220213025739.2561834-2-liambeguin@gmail.com Signed-off-by: Jonathan Cameron --- include/linux/iio/afe/rescale.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) create mode 100644 include/linux/iio/afe/rescale.h (limited to 'include') diff --git a/include/linux/iio/afe/rescale.h b/include/linux/iio/afe/rescale.h new file mode 100644 index 000000000000..8a2eb34af327 --- /dev/null +++ b/include/linux/iio/afe/rescale.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2018 Axentia Technologies AB + */ + +#ifndef __IIO_RESCALE_H__ +#define __IIO_RESCALE_H__ + +#include +#include + +struct device; +struct rescale; + +struct rescale_cfg { + enum iio_chan_type type; + int (*props)(struct device *dev, struct rescale *rescale); +}; + +struct rescale { + const struct rescale_cfg *cfg; + struct iio_channel *source; + struct iio_chan_spec chan; + struct iio_chan_spec_ext_info *ext_info; + bool chan_processed; + s32 numerator; + s32 denominator; +}; + +int rescale_process_scale(struct rescale *rescale, int scale_type, + int *val, int *val2); +#endif /* __IIO_RESCALE_H__ */ -- cgit v1.2.3 From a29c3283653b80b916c5ca5292c5d36415e38e92 Mon Sep 17 00:00:00 2001 From: Liam Beguin Date: Sat, 12 Feb 2022 21:57:32 -0500 Subject: iio: afe: rescale: add offset support This is a preparatory change required for the addition of temperature sensing front ends. Signed-off-by: Liam Beguin Reviewed-by: Peter Rosin Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20220213025739.2561834-4-liambeguin@gmail.com Signed-off-by: Jonathan Cameron --- include/linux/iio/afe/rescale.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/iio/afe/rescale.h b/include/linux/iio/afe/rescale.h index 8a2eb34af327..6eecb435488f 100644 --- a/include/linux/iio/afe/rescale.h +++ b/include/linux/iio/afe/rescale.h @@ -25,8 +25,12 @@ struct rescale { bool chan_processed; s32 numerator; s32 denominator; + s32 offset; }; int rescale_process_scale(struct rescale *rescale, int scale_type, int *val, int *val2); +int rescale_process_offset(struct rescale *rescale, int scale_type, + int scale, int scale2, int schan_off, + int *val, int *val2); #endif /* __IIO_RESCALE_H__ */ -- cgit v1.2.3 From fad278388e01e3658a356118bed8ee2c2408d280 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 24 May 2021 21:15:15 -0700 Subject: media: omap3isp: Use struct_group() for memcpy() region In preparation for FORTIFY_SOURCE performing compile-time and run-time field bounds checking for memcpy(), memmove(), and memset(), avoid intentionally writing across neighboring fields. Wrap the target region in struct_group(). This additionally fixes a theoretical misalignment of the copy (since the size of "buf" changes between 64-bit and 32-bit, but this is likely never built for 64-bit). FWIW, I think this code is totally broken on 64-bit (which appears to not be a "real" build configuration): it would either always fail (with an uninitialized data->buf_size) or would cause corruption in userspace due to the copy_to_user() in the call path against an uninitialized data->buf value: omap3isp_stat_request_statistics_time32(...) struct omap3isp_stat_data data64; ... omap3isp_stat_request_statistics(stat, &data64); int omap3isp_stat_request_statistics(struct ispstat *stat, struct omap3isp_stat_data *data) ... buf = isp_stat_buf_get(stat, data); static struct ispstat_buffer *isp_stat_buf_get(struct ispstat *stat, struct omap3isp_stat_data *data) ... if (buf->buf_size > data->buf_size) { ... return ERR_PTR(-EINVAL); } ... rval = copy_to_user(data->buf, buf->virt_addr, buf->buf_size); Regardless, additionally initialize data64 to be zero-filled to avoid undefined behavior. Cc: Laurent Pinchart Cc: Mauro Carvalho Chehab Cc: Arnd Bergmann Cc: Sakari Ailus Cc: linux-media@vger.kernel.org Fixes: 378e3f81cb56 ("media: omap3isp: support 64-bit version of omap3isp_stat_data") Cc: stable@vger.kernel.org Reviewed-by: Gustavo A. R. Silva Link: https://lore.kernel.org/lkml/20211215220505.GB21862@embeddedor Signed-off-by: Kees Cook --- include/uapi/linux/omap3isp.h | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/omap3isp.h b/include/uapi/linux/omap3isp.h index 87b55755f4ff..d9db7ad43890 100644 --- a/include/uapi/linux/omap3isp.h +++ b/include/uapi/linux/omap3isp.h @@ -162,6 +162,7 @@ struct omap3isp_h3a_aewb_config { * struct omap3isp_stat_data - Statistic data sent to or received from user * @ts: Timestamp of returned framestats. * @buf: Pointer to pass to user. + * @buf_size: Size of buffer. * @frame_number: Frame number of requested stats. * @cur_frame: Current frame number being processed. * @config_counter: Number of the configuration associated with the data. @@ -176,10 +177,12 @@ struct omap3isp_stat_data { struct timeval ts; #endif void __user *buf; - __u32 buf_size; - __u16 frame_number; - __u16 cur_frame; - __u16 config_counter; + __struct_group(/* no tag */, frame, /* no attrs */, + __u32 buf_size; + __u16 frame_number; + __u16 cur_frame; + __u16 config_counter; + ); }; #ifdef __KERNEL__ @@ -189,10 +192,12 @@ struct omap3isp_stat_data_time32 { __s32 tv_usec; } ts; __u32 buf; - __u32 buf_size; - __u16 frame_number; - __u16 cur_frame; - __u16 config_counter; + __struct_group(/* no tag */, frame, /* no attrs */, + __u32 buf_size; + __u16 frame_number; + __u16 cur_frame; + __u16 config_counter; + ); }; #endif -- cgit v1.2.3 From e75d16e58467c5703821e12536c7dc438f3c425d Mon Sep 17 00:00:00 2001 From: Armin Wolf Date: Thu, 24 Feb 2022 07:12:09 +0100 Subject: hwmon: (core) Add support for pwm auto channels attribute pwm[1-*]_auto_channels_temp is documented as an official hwmon sysfs attribute, yet there is no support for it in the new with_info-API. Fix that. Signed-off-by: Armin Wolf Link: https://lore.kernel.org/r/20220224061210.16452-2-W_Armin@gmx.de Signed-off-by: Guenter Roeck --- include/linux/hwmon.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index fad1f1df26df..eba380b76d15 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -332,12 +332,14 @@ enum hwmon_pwm_attributes { hwmon_pwm_enable, hwmon_pwm_mode, hwmon_pwm_freq, + hwmon_pwm_auto_channels_temp, }; #define HWMON_PWM_INPUT BIT(hwmon_pwm_input) #define HWMON_PWM_ENABLE BIT(hwmon_pwm_enable) #define HWMON_PWM_MODE BIT(hwmon_pwm_mode) #define HWMON_PWM_FREQ BIT(hwmon_pwm_freq) +#define HWMON_PWM_AUTO_CHANNELS_TEMP BIT(hwmon_pwm_auto_channels_temp) enum hwmon_intrusion_attributes { hwmon_intrusion_alarm, -- cgit v1.2.3 From c5b483d5c1a26b6006180f5dc7b2f8674f19afa3 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 14 Feb 2022 16:39:03 -0600 Subject: scsi: libfc: Replace one-element arrays with flexible-array members Use flexible-array members in struct fc_fdmi_attr_entry and fs_fdmi_attrs instead of one-element arrays, and refactor the code accordingly. Also, this helps with the ongoing efforts to globally enable -Warray-bounds and get us closer to being able to tighten the FORTIFY_SOURCE routines on memcpy(). https://github.com/KSPP/linux/issues/79 https://github.com/ClangBuiltLinux/linux/issues/1590 Link: https://lore.kernel.org/r/20220214223903.GA859464@embeddedor Signed-off-by: Gustavo A. R. Silva Signed-off-by: Martin K. Petersen --- include/scsi/fc/fc_ms.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/scsi/fc/fc_ms.h b/include/scsi/fc/fc_ms.h index 00191695233a..56a5d2b5a624 100644 --- a/include/scsi/fc/fc_ms.h +++ b/include/scsi/fc/fc_ms.h @@ -158,7 +158,7 @@ struct fc_fdmi_port_name { struct fc_fdmi_attr_entry { __be16 type; __be16 len; - __u8 value[1]; + __u8 value[]; } __attribute__((__packed__)); /* @@ -166,7 +166,7 @@ struct fc_fdmi_attr_entry { */ struct fs_fdmi_attrs { __be32 numattrs; - struct fc_fdmi_attr_entry attr[1]; + struct fc_fdmi_attr_entry attr[]; } __attribute__((__packed__)); /* -- cgit v1.2.3 From f1834fd1635be4b530a7e070c04a6158b8f78c0e Mon Sep 17 00:00:00 2001 From: John Garry Date: Fri, 25 Feb 2022 18:57:35 +0800 Subject: scsi: libsas: Make sas_notify_{phy,port}_event() return void Nobody checks the return codes, so make them return void. Indeed, if the LLDD cannot send an event, nothing much can be done in the LLDD about it. Also remove prototype for sas_notify_phy_event() in sas_internal.h, which should not be there. Link: https://lore.kernel.org/r/1645786656-221630-2-git-send-email-john.garry@huawei.com Reviewed-by: Xiang Chen Reviewed-by: Damien Le Moal Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index dc529cc92d65..df2c8fc43429 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -727,9 +727,9 @@ int sas_lu_reset(struct domain_device *dev, u8 *lun); int sas_query_task(struct sas_task *task, u16 tag); int sas_abort_task(struct sas_task *task, u16 tag); -int sas_notify_port_event(struct asd_sas_phy *phy, enum port_event event, - gfp_t gfp_flags); -int sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event, - gfp_t gfp_flags); +void sas_notify_port_event(struct asd_sas_phy *phy, enum port_event event, + gfp_t gfp_flags); +void sas_notify_phy_event(struct asd_sas_phy *phy, enum phy_event event, + gfp_t gfp_flags); #endif /* _SASLIB_H_ */ -- cgit v1.2.3 From 95ae342dc939a220b7afbd3a65f7106258f67cad Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Noralf=20Tr=C3=B8nnes?= Date: Sun, 27 Feb 2022 13:47:11 +0100 Subject: drm/modes: Add of_get_drm_panel_display_mode() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a function to get a drm_display_mode from a panel-timing device tree subnode. Suggested-by: Sam Ravnborg Reviewed-by: Sam Ravnborg Signed-off-by: Noralf Trønnes Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20220227124713.39766-4-noralf@tronnes.org --- include/drm/drm_modes.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/drm/drm_modes.h b/include/drm/drm_modes.h index 29ba4adf0c53..2fa6b2c33b3f 100644 --- a/include/drm/drm_modes.h +++ b/include/drm/drm_modes.h @@ -466,6 +466,8 @@ void drm_bus_flags_from_videomode(const struct videomode *vm, u32 *bus_flags); int of_get_drm_display_mode(struct device_node *np, struct drm_display_mode *dmode, u32 *bus_flags, int index); +int of_get_drm_panel_display_mode(struct device_node *np, + struct drm_display_mode *dmode, u32 *bus_flags); #else static inline int of_get_drm_display_mode(struct device_node *np, struct drm_display_mode *dmode, @@ -473,6 +475,12 @@ static inline int of_get_drm_display_mode(struct device_node *np, { return -EINVAL; } + +static inline int of_get_drm_panel_display_mode(struct device_node *np, + struct drm_display_mode *dmode, u32 *bus_flags) +{ + return -EINVAL; +} #endif void drm_mode_set_name(struct drm_display_mode *mode); -- cgit v1.2.3 From 1e7e8e18db0fdd4da4e91597cf4d59265b8f351f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Noralf=20Tr=C3=B8nnes?= Date: Sun, 27 Feb 2022 13:47:12 +0100 Subject: drm/mipi-dbi: Add driver_private member to struct mipi_dbi_dev MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit devm_drm_dev_alloc() can't allocate structures that embed a structure which then again embeds drm_device. Workaround this by adding a driver_private pointer to struct mipi_dbi_dev which the driver can use for its additional state. v3: - Add documentation Acked-by: Maxime Ripard Acked-by: Sam Ravnborg Signed-off-by: Noralf Trønnes Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20220227124713.39766-5-noralf@tronnes.org --- include/drm/drm_mipi_dbi.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/drm/drm_mipi_dbi.h b/include/drm/drm_mipi_dbi.h index 6fe13cce2670..dad2f187b64b 100644 --- a/include/drm/drm_mipi_dbi.h +++ b/include/drm/drm_mipi_dbi.h @@ -130,6 +130,14 @@ struct mipi_dbi_dev { * @dbi: MIPI DBI interface */ struct mipi_dbi dbi; + + /** + * @driver_private: Driver private data. + * Necessary for drivers with private data since devm_drm_dev_alloc() + * can't allocate structures that embed a structure which then again + * embeds drm_device. + */ + void *driver_private; }; static inline struct mipi_dbi_dev *drm_to_mipi_dbi_dev(struct drm_device *drm) -- cgit v1.2.3 From d72ce7d324786257410bec6b36e3756647dd76fd Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 26 Feb 2022 00:27:55 +0100 Subject: power: supply: ab8500: Standardize maintenance charging Maintenance charging is the phase of keeping up the charge after the battery has charged fully using CC/CV charging. This can be done in many successive phases and is usually done with a slightly lower constant voltage than CV, and a slightly lower allowed current. Add an array of maintenance charging points each with a current, voltage and safety timer, and add helper functions to use these. Migrate the AB8500 code over. This is used in several Samsung products using the AB8500 and these batteries and their complete parameters will be added later as full examples, but the default battery in the AB8500 code serves as a reasonable example so far. Reviewed-by: Matti Vaittinen Signed-off-by: Linus Walleij Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 64 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 64 insertions(+) (limited to 'include') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index c135196aa9d1..8ced6550caa7 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -349,6 +349,52 @@ struct power_supply_resistance_temp_table { int resistance; /* internal resistance percent */ }; +/** + * struct power_supply_maintenance_charge_table - setting for maintenace charging + * @charge_current_max_ua: maintenance charging current that is used to keep + * the charge of the battery full as current is consumed after full charging. + * The corresponding charge_voltage_max_uv is used as a safeguard: when we + * reach this voltage the maintenance charging current is turned off. It is + * turned back on if we fall below this voltage. + * @charge_voltage_max_uv: maintenance charging voltage that is usually a bit + * lower than the constant_charge_voltage_max_uv. We can apply this settings + * charge_current_max_ua until we get back up to this voltage. + * @safety_timer_minutes: maintenance charging safety timer, with an expiry + * time in minutes. We will only use maintenance charging in this setting + * for a certain amount of time, then we will first move to the next + * maintenance charge current and voltage pair in respective array and wait + * for the next safety timer timeout, or, if we reached the last maintencance + * charging setting, disable charging until we reach + * charge_restart_voltage_uv and restart ordinary CC/CV charging from there. + * These timers should be chosen to align with the typical discharge curve + * for the battery. + * + * When the main CC/CV charging is complete the battery can optionally be + * maintenance charged at the voltages from this table: a table of settings is + * traversed using a slightly lower current and voltage than what is used for + * CC/CV charging. The maintenance charging will for safety reasons not go on + * indefinately: we lower the current and voltage with successive maintenance + * settings, then disable charging completely after we reach the last one, + * and after that we do not restart charging until we reach + * charge_restart_voltage_uv (see struct power_supply_battery_info) and restart + * ordinary CC/CV charging from there. + * + * As an example, a Samsung EB425161LA Lithium-Ion battery is CC/CV charged + * at 900mA to 4340mV, then maintenance charged at 600mA and 4150mV for + * 60 hours, then maintenance charged at 600mA and 4100mV for 200 hours. + * After this the charge cycle is restarted waiting for + * charge_restart_voltage_uv. + * + * For most mobile electronics this type of maintenance charging is enough for + * the user to disconnect the device and make use of it before both maintenance + * charging cycles are complete. + */ +struct power_supply_maintenance_charge_table { + int charge_current_max_ua; + int charge_voltage_max_uv; + int charge_safety_timer_minutes; +}; + #define POWER_SUPPLY_OCV_TEMP_MAX 20 /** @@ -394,6 +440,10 @@ struct power_supply_resistance_temp_table { * @constant_charge_voltage_max_uv: voltage in microvolts signifying the end of * the CC (constant current) charging phase and the beginning of the CV * (constant voltage) charging phase. + * @maintenance_charge: an array of maintenance charging settings to be used + * after the main CC/CV charging phase is complete. + * @maintenance_charge_size: the number of maintenance charging settings in + * maintenance_charge. * @factory_internal_resistance_uohm: the internal resistance of the battery * at fabrication time, expressed in microohms. This resistance will vary * depending on the lifetime and charge of the battery, so this is just a @@ -543,6 +593,8 @@ struct power_supply_battery_info { int overvoltage_limit_uv; int constant_charge_current_max_ua; int constant_charge_voltage_max_uv; + struct power_supply_maintenance_charge_table *maintenance_charge; + int maintenance_charge_size; int factory_internal_resistance_uohm; int ocv_temp[POWER_SUPPLY_OCV_TEMP_MAX]; int temp_ambient_alert_min; @@ -596,6 +648,8 @@ extern int power_supply_batinfo_ocv2cap(struct power_supply_battery_info *info, extern int power_supply_temp2resist_simple(struct power_supply_resistance_temp_table *table, int table_len, int temp); +extern struct power_supply_maintenance_charge_table * +power_supply_get_maintenance_charging_setting(struct power_supply_battery_info *info, int index); extern void power_supply_changed(struct power_supply *psy); extern int power_supply_am_i_supplied(struct power_supply *psy); int power_supply_get_property_from_supplier(struct power_supply *psy, @@ -603,6 +657,16 @@ int power_supply_get_property_from_supplier(struct power_supply *psy, union power_supply_propval *val); extern int power_supply_set_battery_charged(struct power_supply *psy); +static inline bool +power_supply_supports_maintenance_charging(struct power_supply_battery_info *info) +{ + struct power_supply_maintenance_charge_table *mt; + + mt = power_supply_get_maintenance_charging_setting(info, 0); + + return (mt != NULL); +} + #ifdef CONFIG_POWER_SUPPLY extern int power_supply_is_system_supplied(void); #else -- cgit v1.2.3 From 0e8b903b522b5a3cb473035cea085d396dd7150a Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 26 Feb 2022 00:27:56 +0100 Subject: power: supply: ab8500: Standardize alert mode charging The AB8500 code is using a special current and voltage setting when the battery is in "alert mode", i.e. when it is starting to go outside normal operating conditions so it is too cold or too hot. This makes sense as a way for the charging algorithm to deal with hostile environments. Add the needed members to the struct power_supply_battery_info, and switch the AB8500 charging code over to using this. Reviewed-by: Matti Vaittineen Signed-off-by: Linus Walleij Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 8ced6550caa7..f8601598d3d3 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -444,6 +444,19 @@ struct power_supply_maintenance_charge_table { * after the main CC/CV charging phase is complete. * @maintenance_charge_size: the number of maintenance charging settings in * maintenance_charge. + * @alert_low_temp_charge_current_ua: The charging current to use if the battery + * enters low alert temperature, i.e. if the internal temperature is between + * temp_alert_min and temp_min. No matter the charging phase, this + * and alert_high_temp_charge_voltage_uv will be applied. + * @alert_low_temp_charge_voltage_uv: Same as alert_low_temp_charge_current_ua, + * but for the charging voltage. + * @alert_high_temp_charge_current_ua: The charging current to use if the + * battery enters high alert temperature, i.e. if the internal temperature is + * between temp_alert_max and temp_max. No matter the charging phase, this + * and alert_high_temp_charge_voltage_uv will be applied, usually lowering + * the charging current as an evasive manouver. + * @alert_high_temp_charge_voltage_uv: Same as + * alert_high_temp_charge_current_ua, but for the charging voltage. * @factory_internal_resistance_uohm: the internal resistance of the battery * at fabrication time, expressed in microohms. This resistance will vary * depending on the lifetime and charge of the battery, so this is just a @@ -595,6 +608,10 @@ struct power_supply_battery_info { int constant_charge_voltage_max_uv; struct power_supply_maintenance_charge_table *maintenance_charge; int maintenance_charge_size; + int alert_low_temp_charge_current_ua; + int alert_low_temp_charge_voltage_uv; + int alert_high_temp_charge_current_ua; + int alert_high_temp_charge_voltage_uv; int factory_internal_resistance_uohm; int ocv_temp[POWER_SUPPLY_OCV_TEMP_MAX]; int temp_ambient_alert_min; -- cgit v1.2.3 From 1f918e0fe43ec41d906e2cf96b80b15451fed7ba Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 26 Feb 2022 00:27:57 +0100 Subject: power: supply: ab8500: Standardize BTI resistance The Battery Type Indicator (BTI) resistor is a resistor mounted between a special terminal on the battery and ground. By sending a fixed current (such as 7mA) through this resistor and measuring the voltage over it, the resistance can be determined, and this verifies the battery type. Typical side view of the battery: o o o GND BTI +3.8V Typical example of the electrical layout: +3.8 V BTI | | | + | _______ [ ] 7kOhm ___ | | | | | GND GND By verifying this resistance before attempting to charge the battery we add an additional level of security. In some systems this is used for plug-and-play of batteries with different capacity. In other cases, this is merely used to verify that the right type of battery is connected, if several batteries have the same physical shape and can be plugged into the same slot. Sometimes this is just a surplus security mechanism. Nokia and Samsung among many other vendors are known to use these BTI resistors. Add the BTI properties to struct power_supply_battery_info and switch the AB8500 charger code over to using it. Signed-off-by: Linus Walleij Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index f8601598d3d3..7fdc03cf2285 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -498,6 +498,14 @@ struct power_supply_maintenance_charge_table { * by temperature: highest temperature with lowest resistance first, lowest * temperature with highest resistance last. * @resist_table_size: the number of items in the resist_table. + * @bti_resistance_ohm: The Battery Type Indicator (BIT) nominal resistance + * in ohms for this battery, if an identification resistor is mounted + * between a third battery terminal and ground. This scheme is used by a lot + * of mobile device batteries. + * @bti_resistance_tolerance: The tolerance in percent of the BTI resistance, + * for example 10 for +/- 10%, if the bti_resistance is set to 7000 and the + * tolerance is 10% we will detect a proper battery if the BTI resistance + * is between 6300 and 7700 Ohm. * * This is the recommended struct to manage static battery parameters, * populated by power_supply_get_battery_info(). Most platform drivers should @@ -624,6 +632,8 @@ struct power_supply_battery_info { int ocv_table_size[POWER_SUPPLY_OCV_TEMP_MAX]; struct power_supply_resistance_temp_table *resist_table; int resist_table_size; + int bti_resistance_ohm; + int bti_resistance_tolerance; }; extern struct atomic_notifier_head power_supply_notifier; @@ -667,6 +677,8 @@ power_supply_temp2resist_simple(struct power_supply_resistance_temp_table *table int table_len, int temp); extern struct power_supply_maintenance_charge_table * power_supply_get_maintenance_charging_setting(struct power_supply_battery_info *info, int index); +extern bool power_supply_battery_bti_in_range(struct power_supply_battery_info *info, + int resistance); extern void power_supply_changed(struct power_supply *psy); extern int power_supply_am_i_supplied(struct power_supply *psy); int power_supply_get_property_from_supplier(struct power_supply *psy, @@ -684,6 +696,7 @@ power_supply_supports_maintenance_charging(struct power_supply_battery_info *inf return (mt != NULL); } + #ifdef CONFIG_POWER_SUPPLY extern int power_supply_is_system_supplied(void); #else -- cgit v1.2.3 From e9e7d165b4b0413c5b7db74515e4981a226b78a0 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 26 Feb 2022 00:27:58 +0100 Subject: power: supply: Support VBAT-to-Ri lookup tables In Samsung devices, the method used to compensate for temperature, age, load etc is by way of VBAT to Ri tables, which correlates the battery voltage under load (VBAT) to an internal resistance (Ri). Using this Ri and a measurement of the current out of the battery (IBAT) the open circuit voltage (OCV) can be calculated as: OCV = VBAT - (Ri * IBAT) The details are described in comments to struct power_supply_battery_info in the commit. Since not all batteries supply this VBAT-to-Ri data, the fallback method to use the temperature-to-Ri lookup table can also be used as a fallback. Add two helper functions to check if we have the tables needed for using power_supply_vbat2ri() or power_supply_temp2resist_simple() respectively, so capacity estimation code can choose which one to employ. Signed-off-by: Linus Walleij Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 113 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 111 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 7fdc03cf2285..cb380c1d9459 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -349,6 +349,11 @@ struct power_supply_resistance_temp_table { int resistance; /* internal resistance percent */ }; +struct power_supply_vbat_ri_table { + int vbat_uv; /* Battery voltage in microvolt */ + int ri_uohm; /* Internal resistance in microohm */ +}; + /** * struct power_supply_maintenance_charge_table - setting for maintenace charging * @charge_current_max_ua: maintenance charging current that is used to keep @@ -460,7 +465,14 @@ struct power_supply_maintenance_charge_table { * @factory_internal_resistance_uohm: the internal resistance of the battery * at fabrication time, expressed in microohms. This resistance will vary * depending on the lifetime and charge of the battery, so this is just a - * nominal ballpark figure. + * nominal ballpark figure. This internal resistance is given for the state + * when the battery is discharging. + * @factory_internal_resistance_charging_uohm: the internal resistance of the + * battery at fabrication time while charging, expressed in microohms. + * The charging process will affect the internal resistance of the battery + * so this value provides a better resistance under these circumstances. + * This resistance will vary depending on the lifetime and charge of the + * battery, so this is just a nominal ballpark figure. * @ocv_temp: array indicating the open circuit voltage (OCV) capacity * temperature indices. This is an array of temperatures in degrees Celsius * indicating which capacity table to use for a certain temperature, since @@ -498,6 +510,21 @@ struct power_supply_maintenance_charge_table { * by temperature: highest temperature with lowest resistance first, lowest * temperature with highest resistance last. * @resist_table_size: the number of items in the resist_table. + * @vbat2ri_discharging: this is a table that correlates Battery voltage (VBAT) + * to internal resistance (Ri). The resistance is given in microohm for the + * corresponding voltage in microvolts. The internal resistance is used to + * determine the open circuit voltage so that we can determine the capacity + * of the battery. These voltages to resistance tables apply when the battery + * is discharging. The table must be ordered descending by voltage: highest + * voltage first. + * @vbat2ri_discharging_size: the number of items in the vbat2ri_discharging + * table. + * @vbat2ri_charging: same function as vbat2ri_discharging but for the state + * when the battery is charging. Being under charge changes the battery's + * internal resistance characteristics so a separate table is needed.* + * The table must be ordered descending by voltage: highest voltage first. + * @vbat2ri_charging_size: the number of items in the vbat2ri_charging + * table. * @bti_resistance_ohm: The Battery Type Indicator (BIT) nominal resistance * in ohms for this battery, if an identification resistor is mounted * between a third battery terminal and ground. This scheme is used by a lot @@ -512,7 +539,9 @@ struct power_supply_maintenance_charge_table { * use these for consistency. * * Its field names must correspond to elements in enum power_supply_property. - * The default field value is -EINVAL. + * The default field value is -EINVAL or NULL for pointers. + * + * CC/CV CHARGING: * * The charging parameters here assume a CC/CV charging scheme. This method * is most common with Lithium Ion batteries (other methods are possible) and @@ -597,6 +626,66 @@ struct power_supply_maintenance_charge_table { * Overcharging Lithium Ion cells can be DANGEROUS and lead to fire or * explosions. * + * DETERMINING BATTERY CAPACITY: + * + * Several members of the struct deal with trying to determine the remaining + * capacity in the battery, usually as a percentage of charge. In practice + * many chargers uses a so-called fuel gauge or coloumb counter that measure + * how much charge goes into the battery and how much goes out (+/- leak + * consumption). This does not help if we do not know how much capacity the + * battery has to begin with, such as when it is first used or was taken out + * and charged in a separate charger. Therefore many capacity algorithms use + * the open circuit voltage with a look-up table to determine the rough + * capacity of the battery. The open circuit voltage can be conceptualized + * with an ideal voltage source (V) in series with an internal resistance (Ri) + * like this: + * + * +-------> IBAT >----------------+ + * | ^ | + * [ ] Ri | | + * | | VBAT | + * o <---------- | | + * +| ^ | [ ] Rload + * .---. | | | + * | V | | OCV | | + * '---' | | | + * | | | | + * GND +-------------------------------+ + * + * If we disconnect the load (here simplified as a fixed resistance Rload) + * and measure VBAT with a infinite impedance voltage meter we will get + * VBAT = OCV and this assumption is sometimes made even under load, assuming + * Rload is insignificant. However this will be of dubious quality because the + * load is rarely that small and Ri is strongly nonlinear depending on + * temperature and how much capacity is left in the battery due to the + * chemistry involved. + * + * In many practical applications we cannot just disconnect the battery from + * the load, so instead we often try to measure the instantaneous IBAT (the + * current out from the battery), estimate the Ri and thus calculate the + * voltage drop over Ri and compensate like this: + * + * OCV = VBAT - (IBAT * Ri) + * + * The tables vbat2ri_discharging and vbat2ri_charging are used to determine + * (by interpolation) the Ri from the VBAT under load. These curves are highly + * nonlinear and may need many datapoints but can be found in datasheets for + * some batteries. This gives the compensated open circuit voltage (OCV) for + * the battery even under load. Using this method will also compensate for + * temperature changes in the environment: this will also make the internal + * resistance change, and it will affect the VBAT under load, so correlating + * VBAT to Ri takes both remaining capacity and temperature into consideration. + * + * Alternatively a manufacturer can specify how the capacity of the battery + * is dependent on the battery temperature which is the main factor affecting + * Ri. As we know all checmical reactions are faster when it is warm and slower + * when it is cold. You can put in 1500mAh and only get 800mAh out before the + * voltage drops too low for example. This effect is also highly nonlinear and + * the purpose of the table resist_table: this will take a temperature and + * tell us how big percentage of Ri the specified temperature correlates to. + * Usually we have 100% of the factory_internal_resistance_uohm at 25 degrees + * Celsius. + * * The power supply class itself doesn't use this struct as of now. */ @@ -621,6 +710,7 @@ struct power_supply_battery_info { int alert_high_temp_charge_current_ua; int alert_high_temp_charge_voltage_uv; int factory_internal_resistance_uohm; + int factory_internal_resistance_charging_uohm; int ocv_temp[POWER_SUPPLY_OCV_TEMP_MAX]; int temp_ambient_alert_min; int temp_ambient_alert_max; @@ -632,6 +722,10 @@ struct power_supply_battery_info { int ocv_table_size[POWER_SUPPLY_OCV_TEMP_MAX]; struct power_supply_resistance_temp_table *resist_table; int resist_table_size; + struct power_supply_vbat_ri_table *vbat2ri_discharging; + int vbat2ri_discharging_size; + struct power_supply_vbat_ri_table *vbat2ri_charging; + int vbat2ri_charging_size; int bti_resistance_ohm; int bti_resistance_tolerance; }; @@ -675,6 +769,8 @@ extern int power_supply_batinfo_ocv2cap(struct power_supply_battery_info *info, extern int power_supply_temp2resist_simple(struct power_supply_resistance_temp_table *table, int table_len, int temp); +extern int power_supply_vbat2ri(struct power_supply_battery_info *info, + int vbat_uv, bool charging); extern struct power_supply_maintenance_charge_table * power_supply_get_maintenance_charging_setting(struct power_supply_battery_info *info, int index); extern bool power_supply_battery_bti_in_range(struct power_supply_battery_info *info, @@ -696,6 +792,19 @@ power_supply_supports_maintenance_charging(struct power_supply_battery_info *inf return (mt != NULL); } +static inline bool +power_supply_supports_vbat2ri(struct power_supply_battery_info *info) +{ + return ((info->vbat2ri_discharging != NULL) && + info->vbat2ri_discharging_size > 0); +} + +static inline bool +power_supply_supports_temp2ri(struct power_supply_battery_info *info) +{ + return ((info->resist_table != NULL) && + info->resist_table_size > 0); +} #ifdef CONFIG_POWER_SUPPLY extern int power_supply_is_system_supplied(void); -- cgit v1.2.3 From 73c022e129630fb16e5eb64d98ce5f14d9b74efd Mon Sep 17 00:00:00 2001 From: Chun-Jie Chen Date: Sun, 30 Jan 2022 09:21:00 +0800 Subject: dt-bindings: power: Add MT8195 power domains Add power domains dt-bindings for MT8195. Signed-off-by: Chun-Jie Chen Acked-by: Rob Herring Reviewed-by: Enric Balletbo i Serra Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20220130012104.5292-2-chun-jie.chen@mediatek.com Signed-off-by: Matthias Brugger --- include/dt-bindings/power/mt8195-power.h | 46 ++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) create mode 100644 include/dt-bindings/power/mt8195-power.h (limited to 'include') diff --git a/include/dt-bindings/power/mt8195-power.h b/include/dt-bindings/power/mt8195-power.h new file mode 100644 index 000000000000..b20ca4b3e3a8 --- /dev/null +++ b/include/dt-bindings/power/mt8195-power.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ +/* + * Copyright (c) 2021 MediaTek Inc. + * Author: Chun-Jie Chen + */ + +#ifndef _DT_BINDINGS_POWER_MT8195_POWER_H +#define _DT_BINDINGS_POWER_MT8195_POWER_H + +#define MT8195_POWER_DOMAIN_PCIE_MAC_P0 0 +#define MT8195_POWER_DOMAIN_PCIE_MAC_P1 1 +#define MT8195_POWER_DOMAIN_PCIE_PHY 2 +#define MT8195_POWER_DOMAIN_SSUSB_PCIE_PHY 3 +#define MT8195_POWER_DOMAIN_CSI_RX_TOP 4 +#define MT8195_POWER_DOMAIN_ETHER 5 +#define MT8195_POWER_DOMAIN_ADSP 6 +#define MT8195_POWER_DOMAIN_AUDIO 7 +#define MT8195_POWER_DOMAIN_MFG0 8 +#define MT8195_POWER_DOMAIN_MFG1 9 +#define MT8195_POWER_DOMAIN_MFG2 10 +#define MT8195_POWER_DOMAIN_MFG3 11 +#define MT8195_POWER_DOMAIN_MFG4 12 +#define MT8195_POWER_DOMAIN_MFG5 13 +#define MT8195_POWER_DOMAIN_MFG6 14 +#define MT8195_POWER_DOMAIN_VPPSYS0 15 +#define MT8195_POWER_DOMAIN_VDOSYS0 16 +#define MT8195_POWER_DOMAIN_VPPSYS1 17 +#define MT8195_POWER_DOMAIN_VDOSYS1 18 +#define MT8195_POWER_DOMAIN_DP_TX 19 +#define MT8195_POWER_DOMAIN_EPD_TX 20 +#define MT8195_POWER_DOMAIN_HDMI_TX 21 +#define MT8195_POWER_DOMAIN_WPESYS 22 +#define MT8195_POWER_DOMAIN_VDEC0 23 +#define MT8195_POWER_DOMAIN_VDEC1 24 +#define MT8195_POWER_DOMAIN_VDEC2 25 +#define MT8195_POWER_DOMAIN_VENC 26 +#define MT8195_POWER_DOMAIN_VENC_CORE1 27 +#define MT8195_POWER_DOMAIN_IMG 28 +#define MT8195_POWER_DOMAIN_DIP 29 +#define MT8195_POWER_DOMAIN_IPE 30 +#define MT8195_POWER_DOMAIN_CAM 31 +#define MT8195_POWER_DOMAIN_CAM_RAWA 32 +#define MT8195_POWER_DOMAIN_CAM_RAWB 33 +#define MT8195_POWER_DOMAIN_CAM_MRAW 34 + +#endif /* _DT_BINDINGS_POWER_MT8195_POWER_H */ -- cgit v1.2.3 From 342479c86d3e8f9e946a07ff0cafbd36511ae30a Mon Sep 17 00:00:00 2001 From: Chun-Jie Chen Date: Sun, 30 Jan 2022 09:21:04 +0800 Subject: soc: mediatek: pm-domains: Add support for mt8195 Add domain control data including bus protection data size change due to more protection steps in mt8195. Signed-off-by: Chun-Jie Chen Reviewed-by: Chen-Yu Tsai Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20220130012104.5292-6-chun-jie.chen@mediatek.com Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/infracfg.h | 82 +++++++++++++++++++++++++++++++++++ 1 file changed, 82 insertions(+) (limited to 'include') diff --git a/include/linux/soc/mediatek/infracfg.h b/include/linux/soc/mediatek/infracfg.h index 4615a228da51..d858e0bab7a2 100644 --- a/include/linux/soc/mediatek/infracfg.h +++ b/include/linux/soc/mediatek/infracfg.h @@ -2,6 +2,88 @@ #ifndef __SOC_MEDIATEK_INFRACFG_H #define __SOC_MEDIATEK_INFRACFG_H +#define MT8195_TOP_AXI_PROT_EN_STA1 0x228 +#define MT8195_TOP_AXI_PROT_EN_1_STA1 0x258 +#define MT8195_TOP_AXI_PROT_EN_SET 0x2a0 +#define MT8195_TOP_AXI_PROT_EN_CLR 0x2a4 +#define MT8195_TOP_AXI_PROT_EN_1_SET 0x2a8 +#define MT8195_TOP_AXI_PROT_EN_1_CLR 0x2ac +#define MT8195_TOP_AXI_PROT_EN_MM_SET 0x2d4 +#define MT8195_TOP_AXI_PROT_EN_MM_CLR 0x2d8 +#define MT8195_TOP_AXI_PROT_EN_MM_STA1 0x2ec +#define MT8195_TOP_AXI_PROT_EN_2_SET 0x714 +#define MT8195_TOP_AXI_PROT_EN_2_CLR 0x718 +#define MT8195_TOP_AXI_PROT_EN_2_STA1 0x724 +#define MT8195_TOP_AXI_PROT_EN_VDNR_SET 0xb84 +#define MT8195_TOP_AXI_PROT_EN_VDNR_CLR 0xb88 +#define MT8195_TOP_AXI_PROT_EN_VDNR_STA1 0xb90 +#define MT8195_TOP_AXI_PROT_EN_VDNR_1_SET 0xba4 +#define MT8195_TOP_AXI_PROT_EN_VDNR_1_CLR 0xba8 +#define MT8195_TOP_AXI_PROT_EN_VDNR_1_STA1 0xbb0 +#define MT8195_TOP_AXI_PROT_EN_VDNR_2_SET 0xbb8 +#define MT8195_TOP_AXI_PROT_EN_VDNR_2_CLR 0xbbc +#define MT8195_TOP_AXI_PROT_EN_VDNR_2_STA1 0xbc4 +#define MT8195_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_SET 0xbcc +#define MT8195_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_CLR 0xbd0 +#define MT8195_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_STA1 0xbd8 +#define MT8195_TOP_AXI_PROT_EN_MM_2_SET 0xdcc +#define MT8195_TOP_AXI_PROT_EN_MM_2_CLR 0xdd0 +#define MT8195_TOP_AXI_PROT_EN_MM_2_STA1 0xdd8 + +#define MT8195_TOP_AXI_PROT_EN_VDOSYS0 BIT(6) +#define MT8195_TOP_AXI_PROT_EN_VPPSYS0 BIT(10) +#define MT8195_TOP_AXI_PROT_EN_MFG1 BIT(11) +#define MT8195_TOP_AXI_PROT_EN_MFG1_2ND GENMASK(22, 21) +#define MT8195_TOP_AXI_PROT_EN_VPPSYS0_2ND BIT(23) +#define MT8195_TOP_AXI_PROT_EN_1_MFG1 GENMASK(20, 19) +#define MT8195_TOP_AXI_PROT_EN_1_CAM BIT(22) +#define MT8195_TOP_AXI_PROT_EN_2_CAM BIT(0) +#define MT8195_TOP_AXI_PROT_EN_2_MFG1_2ND GENMASK(6, 5) +#define MT8195_TOP_AXI_PROT_EN_2_MFG1 BIT(7) +#define MT8195_TOP_AXI_PROT_EN_2_AUDIO (BIT(9) | BIT(11)) +#define MT8195_TOP_AXI_PROT_EN_2_ADSP (BIT(12) | GENMASK(16, 14)) +#define MT8195_TOP_AXI_PROT_EN_MM_CAM (BIT(0) | BIT(2) | BIT(4)) +#define MT8195_TOP_AXI_PROT_EN_MM_IPE BIT(1) +#define MT8195_TOP_AXI_PROT_EN_MM_IMG BIT(3) +#define MT8195_TOP_AXI_PROT_EN_MM_VDOSYS0 GENMASK(21, 17) +#define MT8195_TOP_AXI_PROT_EN_MM_VPPSYS1 GENMASK(8, 5) +#define MT8195_TOP_AXI_PROT_EN_MM_VENC (BIT(9) | BIT(11)) +#define MT8195_TOP_AXI_PROT_EN_MM_VENC_CORE1 (BIT(10) | BIT(12)) +#define MT8195_TOP_AXI_PROT_EN_MM_VDEC0 BIT(13) +#define MT8195_TOP_AXI_PROT_EN_MM_VDEC1 BIT(14) +#define MT8195_TOP_AXI_PROT_EN_MM_VDOSYS1_2ND BIT(22) +#define MT8195_TOP_AXI_PROT_EN_MM_VPPSYS1_2ND BIT(23) +#define MT8195_TOP_AXI_PROT_EN_MM_CAM_2ND BIT(24) +#define MT8195_TOP_AXI_PROT_EN_MM_IMG_2ND BIT(25) +#define MT8195_TOP_AXI_PROT_EN_MM_VENC_2ND BIT(26) +#define MT8195_TOP_AXI_PROT_EN_MM_WPESYS BIT(27) +#define MT8195_TOP_AXI_PROT_EN_MM_VDEC0_2ND BIT(28) +#define MT8195_TOP_AXI_PROT_EN_MM_VDEC1_2ND BIT(29) +#define MT8195_TOP_AXI_PROT_EN_MM_VDOSYS1 GENMASK(31, 30) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VPPSYS0_2ND (GENMASK(1, 0) | BIT(4) | BIT(11)) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VENC BIT(2) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VENC_CORE1 (BIT(3) | BIT(15)) +#define MT8195_TOP_AXI_PROT_EN_MM_2_CAM (BIT(5) | BIT(17)) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VPPSYS1 (GENMASK(7, 6) | BIT(18)) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VPPSYS0 GENMASK(9, 8) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VDOSYS1 BIT(10) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VDEC2_2ND BIT(12) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VDEC0_2ND BIT(13) +#define MT8195_TOP_AXI_PROT_EN_MM_2_WPESYS_2ND BIT(14) +#define MT8195_TOP_AXI_PROT_EN_MM_2_IPE BIT(16) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VDEC2 BIT(21) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VDEC0 BIT(22) +#define MT8195_TOP_AXI_PROT_EN_MM_2_WPESYS GENMASK(24, 23) +#define MT8195_TOP_AXI_PROT_EN_VDNR_1_EPD_TX BIT(1) +#define MT8195_TOP_AXI_PROT_EN_VDNR_1_DP_TX BIT(2) +#define MT8195_TOP_AXI_PROT_EN_VDNR_PCIE_MAC_P0 (BIT(11) | BIT(28)) +#define MT8195_TOP_AXI_PROT_EN_VDNR_PCIE_MAC_P1 (BIT(12) | BIT(29)) +#define MT8195_TOP_AXI_PROT_EN_VDNR_1_PCIE_MAC_P0 BIT(13) +#define MT8195_TOP_AXI_PROT_EN_VDNR_1_PCIE_MAC_P1 BIT(14) +#define MT8195_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_MFG1 (BIT(17) | BIT(19)) +#define MT8195_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_VPPSYS0 BIT(20) +#define MT8195_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_VDOSYS0 BIT(21) + #define MT8192_TOP_AXI_PROT_EN_STA1 0x228 #define MT8192_TOP_AXI_PROT_EN_1_STA1 0x258 #define MT8192_TOP_AXI_PROT_EN_SET 0x2a0 -- cgit v1.2.3 From c8a006896fce9410cb7c479b6b52de553b69bfd9 Mon Sep 17 00:00:00 2001 From: Chun-Jie Chen Date: Tue, 15 Feb 2022 18:49:16 +0800 Subject: dt-bindings: power: Add MT8186 power domains Add power domains dt-bindings for MT8186. Signed-off-by: Chun-Jie Chen Acked-by: Rob Herring Link: https://lore.kernel.org/r/20220215104917.5726-2-chun-jie.chen@mediatek.com Signed-off-by: Matthias Brugger --- include/dt-bindings/power/mt8186-power.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) create mode 100644 include/dt-bindings/power/mt8186-power.h (limited to 'include') diff --git a/include/dt-bindings/power/mt8186-power.h b/include/dt-bindings/power/mt8186-power.h new file mode 100644 index 000000000000..429f7197f6b6 --- /dev/null +++ b/include/dt-bindings/power/mt8186-power.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Chun-Jie Chen + */ + +#ifndef _DT_BINDINGS_POWER_MT8186_POWER_H +#define _DT_BINDINGS_POWER_MT8186_POWER_H + +#define MT8186_POWER_DOMAIN_MFG0 0 +#define MT8186_POWER_DOMAIN_MFG1 1 +#define MT8186_POWER_DOMAIN_MFG2 2 +#define MT8186_POWER_DOMAIN_MFG3 3 +#define MT8186_POWER_DOMAIN_SSUSB 4 +#define MT8186_POWER_DOMAIN_SSUSB_P1 5 +#define MT8186_POWER_DOMAIN_DIS 6 +#define MT8186_POWER_DOMAIN_IMG 7 +#define MT8186_POWER_DOMAIN_IMG2 8 +#define MT8186_POWER_DOMAIN_IPE 9 +#define MT8186_POWER_DOMAIN_CAM 10 +#define MT8186_POWER_DOMAIN_CAM_RAWA 11 +#define MT8186_POWER_DOMAIN_CAM_RAWB 12 +#define MT8186_POWER_DOMAIN_VENC 13 +#define MT8186_POWER_DOMAIN_VDEC 14 +#define MT8186_POWER_DOMAIN_WPE 15 +#define MT8186_POWER_DOMAIN_CONN_ON 16 +#define MT8186_POWER_DOMAIN_CSIRX_TOP 17 +#define MT8186_POWER_DOMAIN_ADSP_AO 18 +#define MT8186_POWER_DOMAIN_ADSP_INFRA 19 +#define MT8186_POWER_DOMAIN_ADSP_TOP 20 + +#endif /* _DT_BINDINGS_POWER_MT8186_POWER_H */ -- cgit v1.2.3 From 88590cbc17033c86c8591d9f22401325961a8a59 Mon Sep 17 00:00:00 2001 From: Chun-Jie Chen Date: Tue, 15 Feb 2022 18:49:17 +0800 Subject: soc: mediatek: pm-domains: Add support for mt8186 Add power domain control data in mt8186. Signed-off-by: Chun-Jie Chen Link: https://lore.kernel.org/r/20220215104917.5726-3-chun-jie.chen@mediatek.com Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/infracfg.h | 48 +++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) (limited to 'include') diff --git a/include/linux/soc/mediatek/infracfg.h b/include/linux/soc/mediatek/infracfg.h index d858e0bab7a2..8a1c2040a28e 100644 --- a/include/linux/soc/mediatek/infracfg.h +++ b/include/linux/soc/mediatek/infracfg.h @@ -140,6 +140,54 @@ #define MT8192_TOP_AXI_PROT_EN_MM_2_MDP_2ND BIT(13) #define MT8192_TOP_AXI_PROT_EN_VDNR_CAM BIT(21) +#define MT8186_TOP_AXI_PROT_EN_SET (0x2A0) +#define MT8186_TOP_AXI_PROT_EN_CLR (0x2A4) +#define MT8186_TOP_AXI_PROT_EN_STA (0x228) +#define MT8186_TOP_AXI_PROT_EN_1_SET (0x2A8) +#define MT8186_TOP_AXI_PROT_EN_1_CLR (0x2AC) +#define MT8186_TOP_AXI_PROT_EN_1_STA (0x258) +#define MT8186_TOP_AXI_PROT_EN_2_SET (0x2B0) +#define MT8186_TOP_AXI_PROT_EN_2_CLR (0x2B4) +#define MT8186_TOP_AXI_PROT_EN_2_STA (0x26C) +#define MT8186_TOP_AXI_PROT_EN_3_SET (0x2B8) +#define MT8186_TOP_AXI_PROT_EN_3_CLR (0x2BC) +#define MT8186_TOP_AXI_PROT_EN_3_STA (0x2C8) + +/* MFG1 */ +#define MT8186_TOP_AXI_PROT_EN_1_MFG1_STEP1 (GENMASK(28, 27)) +#define MT8186_TOP_AXI_PROT_EN_MFG1_STEP2 (GENMASK(22, 21)) +#define MT8186_TOP_AXI_PROT_EN_MFG1_STEP3 (BIT(25)) +#define MT8186_TOP_AXI_PROT_EN_1_MFG1_STEP4 (BIT(29)) +/* DIS */ +#define MT8186_TOP_AXI_PROT_EN_1_DIS_STEP1 (GENMASK(12, 11)) +#define MT8186_TOP_AXI_PROT_EN_DIS_STEP2 (GENMASK(2, 1) | GENMASK(11, 10)) +/* IMG */ +#define MT8186_TOP_AXI_PROT_EN_1_IMG_STEP1 (BIT(23)) +#define MT8186_TOP_AXI_PROT_EN_1_IMG_STEP2 (BIT(15)) +/* IPE */ +#define MT8186_TOP_AXI_PROT_EN_1_IPE_STEP1 (BIT(24)) +#define MT8186_TOP_AXI_PROT_EN_1_IPE_STEP2 (BIT(16)) +/* CAM */ +#define MT8186_TOP_AXI_PROT_EN_1_CAM_STEP1 (GENMASK(22, 21)) +#define MT8186_TOP_AXI_PROT_EN_1_CAM_STEP2 (GENMASK(14, 13)) +/* VENC */ +#define MT8186_TOP_AXI_PROT_EN_1_VENC_STEP1 (BIT(31)) +#define MT8186_TOP_AXI_PROT_EN_1_VENC_STEP2 (BIT(19)) +/* VDEC */ +#define MT8186_TOP_AXI_PROT_EN_1_VDEC_STEP1 (BIT(30)) +#define MT8186_TOP_AXI_PROT_EN_1_VDEC_STEP2 (BIT(17)) +/* WPE */ +#define MT8186_TOP_AXI_PROT_EN_2_WPE_STEP1 (BIT(17)) +#define MT8186_TOP_AXI_PROT_EN_2_WPE_STEP2 (BIT(16)) +/* CONN_ON */ +#define MT8186_TOP_AXI_PROT_EN_1_CONN_ON_STEP1 (BIT(18)) +#define MT8186_TOP_AXI_PROT_EN_CONN_ON_STEP2 (BIT(14)) +#define MT8186_TOP_AXI_PROT_EN_CONN_ON_STEP3 (BIT(13)) +#define MT8186_TOP_AXI_PROT_EN_CONN_ON_STEP4 (BIT(16)) +/* ADSP_TOP */ +#define MT8186_TOP_AXI_PROT_EN_3_ADSP_TOP_STEP1 (GENMASK(12, 11)) +#define MT8186_TOP_AXI_PROT_EN_3_ADSP_TOP_STEP2 (GENMASK(1, 0)) + #define MT8183_TOP_AXI_PROT_EN_STA1 0x228 #define MT8183_TOP_AXI_PROT_EN_STA1_1 0x258 #define MT8183_TOP_AXI_PROT_EN_SET 0x2a0 -- cgit v1.2.3 From b8cd5831c61cadee4493248babef8386f836f31c Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Thu, 24 Feb 2022 10:29:07 +0000 Subject: net: flow_offload: add tc police action parameters The current police offload action entry is missing exceed/notexceed actions and parameters that can be configured by tc police action. Add the missing parameters as a pre-step for offloading police actions to hardware. Signed-off-by: Jianbo Liu Signed-off-by: Roi Dayan Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/flow_offload.h | 9 +++++++++ include/net/tc_act/tc_police.h | 30 ++++++++++++++++++++++++++++++ 2 files changed, 39 insertions(+) (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 5b8c54eb7a6b..74f44d44abe3 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -148,6 +148,8 @@ enum flow_action_id { FLOW_ACTION_MPLS_MANGLE, FLOW_ACTION_GATE, FLOW_ACTION_PPPOE_PUSH, + FLOW_ACTION_JUMP, + FLOW_ACTION_PIPE, NUM_FLOW_ACTIONS, }; @@ -235,9 +237,16 @@ struct flow_action_entry { struct { /* FLOW_ACTION_POLICE */ u32 burst; u64 rate_bytes_ps; + u64 peakrate_bytes_ps; + u32 avrate; + u16 overhead; u64 burst_pkt; u64 rate_pkt_ps; u32 mtu; + struct { + enum flow_action_id act_id; + u32 extval; + } exceed, notexceed; } police; struct { /* FLOW_ACTION_CT */ int action; diff --git a/include/net/tc_act/tc_police.h b/include/net/tc_act/tc_police.h index 72649512dcdd..283bde711a42 100644 --- a/include/net/tc_act/tc_police.h +++ b/include/net/tc_act/tc_police.h @@ -159,4 +159,34 @@ static inline u32 tcf_police_tcfp_mtu(const struct tc_action *act) return params->tcfp_mtu; } +static inline u64 tcf_police_peakrate_bytes_ps(const struct tc_action *act) +{ + struct tcf_police *police = to_police(act); + struct tcf_police_params *params; + + params = rcu_dereference_protected(police->params, + lockdep_is_held(&police->tcf_lock)); + return params->peak.rate_bytes_ps; +} + +static inline u32 tcf_police_tcfp_ewma_rate(const struct tc_action *act) +{ + struct tcf_police *police = to_police(act); + struct tcf_police_params *params; + + params = rcu_dereference_protected(police->params, + lockdep_is_held(&police->tcf_lock)); + return params->tcfp_ewma_rate; +} + +static inline u16 tcf_police_rate_overhead(const struct tc_action *act) +{ + struct tcf_police *police = to_police(act); + struct tcf_police_params *params; + + params = rcu_dereference_protected(police->params, + lockdep_is_held(&police->tcf_lock)); + return params->rate.overhead; +} + #endif /* __NET_TC_POLICE_H */ -- cgit v1.2.3 From d97b4b105ce71f9f907f1511986cc1d224126772 Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Thu, 24 Feb 2022 10:29:08 +0000 Subject: flow_offload: reject offload for all drivers with invalid police parameters As more police parameters are passed to flow_offload, driver can check them to make sure hardware handles packets in the way indicated by tc. The conform-exceed control should be drop/pipe or drop/ok. Besides, for drop/ok, the police should be the last action. As hardware can't configure peakrate/avrate/overhead, offload should not be supported if any of them is configured. Signed-off-by: Jianbo Liu Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/flow_offload.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 74f44d44abe3..92267d23083e 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -311,6 +311,12 @@ static inline bool flow_offload_has_one_action(const struct flow_action *action) return action->num_entries == 1; } +static inline bool flow_action_is_last_entry(const struct flow_action *action, + const struct flow_action_entry *entry) +{ + return entry == &action->entries[action->num_entries - 1]; +} + #define flow_action_for_each(__i, __act, __actions) \ for (__i = 0, __act = &(__actions)->entries[0]; \ __i < (__actions)->num_entries; \ -- cgit v1.2.3 From e096242e1ee2e800df5e8d9a5508135902e8e1b5 Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Fri, 25 Feb 2022 17:32:37 +0530 Subject: dt-bindings: pinctrl: k3: Introduce pinmux definitions for AM62 Add pinctrl macros for AM62x SoCs. These macro definitions are similar to that of previous platforms, but adding new definitions to avoid any naming confusions in the SoC dts files. checkpatch insists the following error exists: ERROR: Macros with complex values should be enclosed in parentheses However, we do not need parentheses enclosing the values for this macro as we do intend it to generate two separate values as has been done for other similar platforms. Signed-off-by: Suman Anna Signed-off-by: Vignesh Raghavendra Acked-by: Rob Herring Reviewed-by: Bryan Brattlof Signed-off-by: Nishanth Menon Link: https://lore.kernel.org/r/20220225120239.1303821-4-vigneshr@ti.com --- include/dt-bindings/pinctrl/k3.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/pinctrl/k3.h b/include/dt-bindings/pinctrl/k3.h index 63e038e36ca3..a5204ab91d3e 100644 --- a/include/dt-bindings/pinctrl/k3.h +++ b/include/dt-bindings/pinctrl/k3.h @@ -41,4 +41,7 @@ #define J721S2_IOPAD(pa, val, muxmode) (((pa) & 0x1fff)) ((val) | (muxmode)) #define J721S2_WKUP_IOPAD(pa, val, muxmode) (((pa) & 0x1fff)) ((val) | (muxmode)) +#define AM62X_IOPAD(pa, val, muxmode) (((pa) & 0x1fff)) ((val) | (muxmode)) +#define AM62X_MCU_IOPAD(pa, val, muxmode) (((pa) & 0x1fff)) ((val) | (muxmode)) + #endif -- cgit v1.2.3 From e65b831a1e191caff3fc0d06bc7019cdaf8f868e Mon Sep 17 00:00:00 2001 From: Qinghua Jin Date: Fri, 7 Jan 2022 10:22:58 +0800 Subject: nvme-fc: fix a typo subsytem -> subsystem Signed-off-by: Qinghua Jin Signed-off-by: Christoph Hellwig --- include/linux/nvme-fc-driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index cb909edb76c4..5358a5facdee 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -721,7 +721,7 @@ enum { * * Fields with static values for the port. Initialized by the * port_info struct supplied to the registration call. - * @port_num: NVME-FC transport subsytem port number + * @port_num: NVME-FC transport subsystem port number * @node_name: FC WWNN for the port * @port_name: FC WWPN for the port * @private: pointer to memory allocated alongside the local port -- cgit v1.2.3 From bd83fe6f2cd2133beaac7c423fd36c3515048fc8 Mon Sep 17 00:00:00 2001 From: Alan Adamson Date: Thu, 3 Feb 2022 00:11:53 -0800 Subject: nvme: add verbose error logging Improves logging of NVMe errors. If NVME_VERBOSE_ERRORS is configured, a verbose description of the error is logged, otherwise only status codes/bits is logged. Signed-off-by: Chaitanya Kulkarni [kch]: fix several nits, cosmetics, and trim down code. Signed-off-by: Martin K. Petersen Signed-off-by: Alan Adamson Reviewed-by: Himanshu Madhani Reviewed-by: Keith Busch Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 855dd9b3e84b..1f946e5bf7c1 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -1636,6 +1636,7 @@ enum { NVME_SC_HOST_ABORTED_CMD = 0x371, NVME_SC_CRD = 0x1800, + NVME_SC_MORE = 0x2000, NVME_SC_DNR = 0x4000, }; -- cgit v1.2.3 From 89377bc1975c2993bde4a498a3a4e5817ac0ae2c Mon Sep 17 00:00:00 2001 From: Kanchan Joshi Date: Thu, 10 Feb 2022 11:07:55 +0530 Subject: nvme: add vectored-io support for user-passthrough Add a new NVME_IOCTL_IO64_CMD_VEC ioctl that works like the existing NVME_IOCTL_IO64_CMD ioctl except that it takes and array of iovecs and thus supports vectored I/O. - cmd.addr is base address of user iovec array - cmd.vec_cnt is count of iovec array elements This patch does not include vectored-variant for admin-commands as most of them are light on buffers and likely to have low invocation frequency. Signed-off-by: Kanchan Joshi Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- include/uapi/linux/nvme_ioctl.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h index d99b5a772698..b2e43185e3b5 100644 --- a/include/uapi/linux/nvme_ioctl.h +++ b/include/uapi/linux/nvme_ioctl.h @@ -55,7 +55,10 @@ struct nvme_passthru_cmd64 { __u64 metadata; __u64 addr; __u32 metadata_len; - __u32 data_len; + union { + __u32 data_len; /* for non-vectored io */ + __u32 vec_cnt; /* for vectored io */ + }; __u32 cdw10; __u32 cdw11; __u32 cdw12; @@ -78,5 +81,6 @@ struct nvme_passthru_cmd64 { #define NVME_IOCTL_RESCAN _IO('N', 0x46) #define NVME_IOCTL_ADMIN64_CMD _IOWR('N', 0x47, struct nvme_passthru_cmd64) #define NVME_IOCTL_IO64_CMD _IOWR('N', 0x48, struct nvme_passthru_cmd64) +#define NVME_IOCTL_IO64_CMD_VEC _IOWR('N', 0x49, struct nvme_passthru_cmd64) #endif /* _UAPI_LINUX_NVME_IOCTL_H */ -- cgit v1.2.3 From 86c2457a8e8112f16af8fd10a3e1dd7a302c3c3e Mon Sep 17 00:00:00 2001 From: Martin Belanger Date: Tue, 8 Feb 2022 14:33:46 -0500 Subject: nvme: expose cntrltype and dctype through sysfs TP8010 introduces the Discovery Controller Type attribute (dctype). The dctype is returned in the response to the Identify command. This patch exposes the dctype through the sysfs. Since the dctype depends on the Controller Type (cntrltype), another attribute of the Identify response, the patch also exposes the cntrltype as well. The dctype will only be displayed for discovery controllers. A note about the naming of this attribute: Although TP8010 calls this attribute the Discovery Controller Type, note that the dctype is now part of the response to the Identify command for all controller types. I/O, Discovery, and Admin controllers all share the same Identify response PDU structure. Non-discovery controllers as well as pre-TP8010 discovery controllers will continue to set this field to 0 (which has always been the default for reserved bytes). Per TP8010, the value 0 now means "Discovery controller type is not reported" instead of "Reserved". One could argue that this definition is correct even for non-discovery controllers, and by extension, exposing it in the sysfs for non-discovery controllers is appropriate. Signed-off-by: Martin Belanger Reviewed-by: Chaitanya Kulkarni Reviewed-by: John Meneghini Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 1f946e5bf7c1..9dbc3ef4daf7 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -43,6 +43,12 @@ enum nvme_ctrl_type { NVME_CTRL_ADMIN = 3, /* Administrative controller */ }; +enum nvme_dctype { + NVME_DCTYPE_NOT_REPORTED = 0, + NVME_DCTYPE_DDC = 1, /* Direct Discovery Controller */ + NVME_DCTYPE_CDC = 2, /* Central Discovery Controller */ +}; + /* Address Family codes for Discovery Log Page entry ADRFAM field */ enum { NVMF_ADDR_FAMILY_PCI = 0, /* PCIe */ @@ -320,7 +326,9 @@ struct nvme_id_ctrl { __le16 icdoff; __u8 ctrattr; __u8 msdbd; - __u8 rsvd1804[244]; + __u8 rsvd1804[2]; + __u8 dctype; + __u8 rsvd1807[241]; struct nvme_id_power_state psd[32]; __u8 vs[1024]; }; -- cgit v1.2.3 From a5081bad2eac5108593ac36b6551201f0df9e897 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Sat, 26 Feb 2022 14:56:22 +0000 Subject: net: phylink: remove phylink_set_pcs() As all users of phylink_set_pcs() have now been updated to use the mac_select_pcs() method, it can be removed from the phylink kernel API and its functionality moved into phylink_major_config(). Removing phylink_set_pcs() gives us a single approach for attaching a PCS within phylink. Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- include/linux/phylink.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 9ef9b7047f19..223781622b33 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -532,7 +532,6 @@ void phylink_generic_validate(struct phylink_config *config, struct phylink *phylink_create(struct phylink_config *, struct fwnode_handle *, phy_interface_t iface, const struct phylink_mac_ops *mac_ops); -void phylink_set_pcs(struct phylink *, struct phylink_pcs *pcs); void phylink_destroy(struct phylink *); int phylink_connect_phy(struct phylink *, struct phy_device *); -- cgit v1.2.3 From aa3766def7506e5d9bd6c8387dcfe3629eb2a1f2 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Tue, 18 Jan 2022 14:58:30 +0200 Subject: habanalabs: expose number of user interrupts Currently we only expose to the user the ID of the first available user interrupt. To make user interrupts allocation truly dynamic, we need to also expose the number of user interrupts. Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 371dfc4243b3..12976f7a8d84 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -404,6 +404,8 @@ enum hl_server_type { * @cpucp_version: The CPUCP f/w version. * @card_name: The card name as passed by the f/w. * @dram_page_size: The DRAM physical page size. + * @number_of_user_interrupts: The number of interrupts that are available to the userspace + * application to use. Relevant for Gaudi2 and later. */ struct hl_info_hw_ip_info { __u64 sram_base_address; @@ -428,6 +430,9 @@ struct hl_info_hw_ip_info { __u8 card_name[HL_INFO_CARD_NAME_MAX_LEN]; __u64 reserved2; __u64 dram_page_size; + __u32 reserved3; + __u16 number_of_user_interrupts; + __u16 pad2; }; struct hl_info_dram_usage { -- cgit v1.2.3 From 9158bf69e74f98fea6847cca93bbf33a589bebcd Mon Sep 17 00:00:00 2001 From: farah kassabri Date: Thu, 23 Dec 2021 13:24:34 +0200 Subject: habanalabs: Timestamps buffers registration Timestamp registration API allows the user to register a timestamp record event which will make the driver set timestamp when CQ counter reaches the target value and write it to a specific location specified by the user. This is a non blocking API, unlike the wait_for_interrupt which is a blocking one. Signed-off-by: farah kassabri Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 37 +++++++++++++++++++++++++++++++++++-- 1 file changed, 35 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 12976f7a8d84..e21db03196ae 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note * - * Copyright 2016-2020 HabanaLabs, Ltd. + * Copyright 2016-2021 HabanaLabs, Ltd. * All Rights Reserved. * */ @@ -30,6 +30,9 @@ */ #define GAUDI_FIRST_AVAILABLE_W_S_MONITOR 72 +/* Max number of elements in timestamps registration buffers */ +#define TS_MAX_ELEMENTS_NUM (1 << 20) /* 1MB */ + /* * Goya queue Numbering * @@ -695,10 +698,12 @@ struct hl_cb_in { __u64 cb_handle; /* HL_CB_OP_* */ __u32 op; + /* Size of CB. Maximum size is HL_MAX_CB_SIZE. The minimum size that * will be allocated, regardless of this parameter's value, is PAGE_SIZE */ __u32 cb_size; + /* Context ID - Currently not in use */ __u32 ctx_id; /* HL_CB_FLAGS_* */ @@ -964,6 +969,7 @@ union hl_cs_args { #define HL_WAIT_CS_FLAGS_INTERRUPT_MASK 0xFFF00000 #define HL_WAIT_CS_FLAGS_MULTI_CS 0x4 #define HL_WAIT_CS_FLAGS_INTERRUPT_KERNEL_CQ 0x10 +#define HL_WAIT_CS_FLAGS_REGISTER_INTERRUPT 0x20 #define HL_WAIT_MULTI_CS_LIST_MAX_LEN 32 @@ -1036,6 +1042,20 @@ struct hl_wait_cs_in { * relevant only when HL_WAIT_CS_FLAGS_INTERRUPT_KERNEL_CQ is set */ __u64 cq_counters_offset; + + /* + * Timestamp_handle timestamps buffer handle. + * relevant only when HL_WAIT_CS_FLAGS_REGISTER_INTERRUPT is set + */ + __u64 timestamp_handle; + + /* + * Timestamp_offset is offset inside the timestamp buffer pointed by timestamp_handle above. + * upon interrupt, if the cq reached the target value then driver will write + * timestamp to this offset. + * relevant only when HL_WAIT_CS_FLAGS_REGISTER_INTERRUPT is set + */ + __u64 timestamp_offset; }; #define HL_WAIT_CS_STATUS_COMPLETED 0 @@ -1082,6 +1102,14 @@ union hl_wait_cs_args { */ #define HL_MEM_OP_EXPORT_DMABUF_FD 5 +/* Opcode to create timestamps pool for user interrupts registration support + * The memory will be allocated by the kernel driver, A timestamp buffer which the user + * will get handle to it for mmap, and another internal buffer used by the + * driver for registration management + * The memory will be freed when the user closes the file descriptor(ctx close) + */ +#define HL_MEM_OP_TS_ALLOC 6 + /* Memory flags */ #define HL_MEM_CONTIGUOUS 0x1 #define HL_MEM_SHARED 0x2 @@ -1173,9 +1201,14 @@ struct hl_mem_in { * DMA-BUF file/FD flags. */ __u32 flags; + /* Context ID - Currently not in use */ __u32 ctx_id; - __u32 pad; + + /* number of timestamp elements + * used only when HL_MEM_OP_TS_ALLOC opcode + */ + __u32 num_of_elements; }; struct hl_mem_out { -- cgit v1.2.3 From 9349a321d327d08a4e91f9b6aca9c1f3a3a25306 Mon Sep 17 00:00:00 2001 From: Ohad Sharabi Date: Mon, 14 Feb 2022 15:20:08 +0200 Subject: habanalabs: use kernel-doc for memory ioctl documentation Re-format the comments for the memory ioctl structure to be in kernel-doc style. Signed-off-by: Ohad Sharabi Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 111 +++++++++++++++++++++-------------------- 1 file changed, 57 insertions(+), 54 deletions(-) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index e21db03196ae..a2a953a91b5e 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -1116,98 +1116,101 @@ union hl_wait_cs_args { #define HL_MEM_USERPTR 0x4 #define HL_MEM_FORCE_HINT 0x8 +/** + * structure hl_mem_in - structure that handle input args for memory IOCTL + * @union arg: union of structures to be used based on the input operation + * @op: specify the requested memory operation (one of the HL_MEM_OP_* definitions). + * @flags: flags for the memory operation (one of the HL_MEM_* definitions). + * For the HL_MEM_OP_EXPORT_DMABUF_FD opcode, this field holds the DMA-BUF file/FD flags. + * @ctx_id: context ID - currently not in use. + * @num_of_elements: number of timestamp elements used only with HL_MEM_OP_TS_ALLOC opcode. + */ struct hl_mem_in { union { - /* HL_MEM_OP_ALLOC- allocate device memory */ + /** + * structure for device memory allocation (used with the HL_MEM_OP_ALLOC op) + * @mem_size: memory size to allocate + */ struct { - /* Size to alloc */ __u64 mem_size; } alloc; - /* HL_MEM_OP_FREE - free device memory */ + /** + * structure for free-ing device memory (used with the HL_MEM_OP_FREE op) + * @handle: handle returned from HL_MEM_OP_ALLOC + */ struct { - /* Handle returned from HL_MEM_OP_ALLOC */ __u64 handle; } free; - /* HL_MEM_OP_MAP - map device memory */ + /** + * structure for mapping device memory (used with the HL_MEM_OP_MAP op) + * @hint_addr: requested virtual address of mapped memory. + * the driver will try to map the requested region to this hint + * address, as long as the address is valid and not already mapped. + * the user should check the returned address of the IOCTL to make + * sure he got the hint address. + * passing 0 here means that the driver will choose the address itself. + * @handle: handle returned from HL_MEM_OP_ALLOC. + */ struct { - /* - * Requested virtual address of mapped memory. - * The driver will try to map the requested region to - * this hint address, as long as the address is valid - * and not already mapped. The user should check the - * returned address of the IOCTL to make sure he got - * the hint address. Passing 0 here means that the - * driver will choose the address itself. - */ __u64 hint_addr; - /* Handle returned from HL_MEM_OP_ALLOC */ __u64 handle; } map_device; - /* HL_MEM_OP_MAP - map host memory */ + /** + * structure for mapping host memory (used with the HL_MEM_OP_MAP op) + * @host_virt_addr: address of allocated host memory. + * @hint_addr: requested virtual address of mapped memory. + * the driver will try to map the requested region to this hint + * address, as long as the address is valid and not already mapped. + * the user should check the returned address of the IOCTL to make + * sure he got the hint address. + * passing 0 here means that the driver will choose the address itself. + * @size: size of allocated host memory. + */ struct { - /* Address of allocated host memory */ __u64 host_virt_addr; - /* - * Requested virtual address of mapped memory. - * The driver will try to map the requested region to - * this hint address, as long as the address is valid - * and not already mapped. The user should check the - * returned address of the IOCTL to make sure he got - * the hint address. Passing 0 here means that the - * driver will choose the address itself. - */ __u64 hint_addr; - /* Size of allocated host memory */ __u64 mem_size; } map_host; - /* HL_MEM_OP_MAP_BLOCK - map a hw block */ + /** + * structure for mapping hw block (used with the HL_MEM_OP_MAP_BLOCK op) + * @block_addr:HW block address to map, a handle and size will be returned + * to the user and will be used to mmap the relevant block. + * only addresses from configuration space are allowed. + */ struct { - /* - * HW block address to map, a handle and size will be - * returned to the user and will be used to mmap the - * relevant block. Only addresses from configuration - * space are allowed. - */ __u64 block_addr; } map_block; - /* HL_MEM_OP_UNMAP - unmap host memory */ + /** + * structure for unmapping host memory (used with the HL_MEM_OP_UNMAP op) + * @device_virt_addr: virtual address returned from HL_MEM_OP_MAP + */ struct { - /* Virtual address returned from HL_MEM_OP_MAP */ __u64 device_virt_addr; } unmap; - /* HL_MEM_OP_EXPORT_DMABUF_FD */ + /** + * structure for exporting DMABUF object (used with + * the HL_MEM_OP_EXPORT_DMABUF_FD op) + * @handle: handle returned from HL_MEM_OP_ALLOC. + * in Gaudi, where we don't have MMU for the device memory, the + * driver expects a physical address (instead of a handle) in the + * device memory space. + * @mem_size: size of memory allocation. Relevant only for GAUDI + */ struct { - /* Handle returned from HL_MEM_OP_ALLOC. In Gaudi, - * where we don't have MMU for the device memory, the - * driver expects a physical address (instead of - * a handle) in the device memory space. - */ __u64 handle; - /* Size of memory allocation. Relevant only for GAUDI */ __u64 mem_size; } export_dmabuf_fd; }; - /* HL_MEM_OP_* */ __u32 op; - /* HL_MEM_* flags. - * For the HL_MEM_OP_EXPORT_DMABUF_FD opcode, this field holds the - * DMA-BUF file/FD flags. - */ __u32 flags; - - /* Context ID - Currently not in use */ __u32 ctx_id; - - /* number of timestamp elements - * used only when HL_MEM_OP_TS_ALLOC opcode - */ __u32 num_of_elements; }; -- cgit v1.2.3 From f23f280277d5a701de99c6652623b6bf8801c534 Mon Sep 17 00:00:00 2001 From: Ohad Sharabi Date: Mon, 14 Feb 2022 15:22:00 +0200 Subject: habanalabs: allow user to set allocation page size In future ASICs the MMU will be able to work with multiple page sizes, thus a new flag is added to allow the user to set the requested page size. This flag is added since the whole DRAM is allocated for the user and the user also should be familiar with the memory usage use case. As such, the user may choose to "over allocate" memory in favor of performance (for instance- large page allocations covers more memory in less TLB entries). For example: say available page sizes are of 1MB and 32MB. If user wants to allocate 40MB the user can either set page size to 1MB and allocate the exact amount of memory (but will result in 40 TLB entries) or the user can use 32MB pages, "waste" 8MB of physical memory but occupy only 2 TLB entries. Note that this feature will be available only to ASIC that supports multiple DRAM page sizes. Signed-off-by: Ohad Sharabi Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index a2a953a91b5e..1d6b4f0c4159 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note * - * Copyright 2016-2021 HabanaLabs, Ltd. + * Copyright 2016-2022 HabanaLabs, Ltd. * All Rights Reserved. * */ @@ -1130,9 +1130,12 @@ struct hl_mem_in { /** * structure for device memory allocation (used with the HL_MEM_OP_ALLOC op) * @mem_size: memory size to allocate + * @page_size: page size to use on allocation. when the value is 0 the default page + * size will be taken. */ struct { __u64 mem_size; + __u64 page_size; } alloc; /** -- cgit v1.2.3 From 989192ac6ad54acccd5dd1c058055dacd6b94b30 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 16 Feb 2022 10:52:41 +0800 Subject: iommu/vt-d: Remove guest pasid related callbacks The guest pasid related callbacks are not called in the tree. Remove them to avoid dead code. Signed-off-by: Lu Baolu Reviewed-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20220216025249.3459465-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 10 ---------- include/linux/intel-svm.h | 12 ------------ 2 files changed, 22 deletions(-) (limited to 'include') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 69230fd695ea..beaacb589abd 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -525,12 +525,6 @@ struct context_entry { */ #define DOMAIN_FLAG_USE_FIRST_LEVEL BIT(1) -/* - * Domain represents a virtual machine which demands iommu nested - * translation mode support. - */ -#define DOMAIN_FLAG_NESTING_MODE BIT(2) - struct dmar_domain { int nid; /* node id */ @@ -765,9 +759,6 @@ struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn); extern void intel_svm_check(struct intel_iommu *iommu); extern int intel_svm_enable_prq(struct intel_iommu *iommu); extern int intel_svm_finish_prq(struct intel_iommu *iommu); -int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev, - struct iommu_gpasid_bind_data *data); -int intel_svm_unbind_gpasid(struct device *dev, u32 pasid); struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm, void *drvdata); void intel_svm_unbind(struct iommu_sva *handle); @@ -795,7 +786,6 @@ struct intel_svm { unsigned int flags; u32 pasid; - int gpasid; /* In case that guest PASID is different from host PASID */ struct list_head devs; }; #else diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index 1b73bab7eeff..b3b125b332aa 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -25,17 +25,5 @@ * do such IOTLB flushes automatically. */ #define SVM_FLAG_SUPERVISOR_MODE BIT(0) -/* - * The SVM_FLAG_GUEST_MODE flag is used when a PASID bind is for guest - * processes. Compared to the host bind, the primary differences are: - * 1. mm life cycle management - * 2. fault reporting - */ -#define SVM_FLAG_GUEST_MODE BIT(1) -/* - * The SVM_FLAG_GUEST_PASID flag is used when a guest has its own PASID space, - * which requires guest and host PASID translation at both directions. - */ -#define SVM_FLAG_GUEST_PASID BIT(2) #endif /* __INTEL_SVM_H__ */ -- cgit v1.2.3 From 0c9f178778919bb500443f340647b44227778fb2 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 16 Feb 2022 10:52:42 +0800 Subject: iommu: Remove guest pasid related interfaces and definitions The guest pasid related uapi interfaces and definitions are not referenced anywhere in the tree. We've also reached a consensus to replace them with a new iommufd design. Remove them to avoid dead code. Signed-off-by: Lu Baolu Reviewed-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20220216025249.3459465-3-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 44 ----------- include/uapi/linux/iommu.h | 181 --------------------------------------------- 2 files changed, 225 deletions(-) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index de0c57a567c8..cde1d0aad60f 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -229,9 +229,6 @@ struct iommu_iotlb_gather { * @sva_unbind: Unbind process address space from device * @sva_get_pasid: Get PASID associated to a SVA handle * @page_response: handle page request response - * @cache_invalidate: invalidate translation caches - * @sva_bind_gpasid: bind guest pasid and mm - * @sva_unbind_gpasid: unbind guest pasid and mm * @def_domain_type: device default domain type, return value: * - IOMMU_DOMAIN_IDENTITY: must use an identity domain * - IOMMU_DOMAIN_DMA: must use a dma domain @@ -301,12 +298,6 @@ struct iommu_ops { int (*page_response)(struct device *dev, struct iommu_fault_event *evt, struct iommu_page_response *msg); - int (*cache_invalidate)(struct iommu_domain *domain, struct device *dev, - struct iommu_cache_invalidate_info *inv_info); - int (*sva_bind_gpasid)(struct iommu_domain *domain, - struct device *dev, struct iommu_gpasid_bind_data *data); - - int (*sva_unbind_gpasid)(struct device *dev, u32 pasid); int (*def_domain_type)(struct device *dev); @@ -421,14 +412,6 @@ extern int iommu_attach_device(struct iommu_domain *domain, struct device *dev); extern void iommu_detach_device(struct iommu_domain *domain, struct device *dev); -extern int iommu_uapi_cache_invalidate(struct iommu_domain *domain, - struct device *dev, - void __user *uinfo); - -extern int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, - struct device *dev, void __user *udata); -extern int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, void __user *udata); extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev, ioasid_t pasid); extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); @@ -1051,33 +1034,6 @@ static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle) return IOMMU_PASID_INVALID; } -static inline int -iommu_uapi_cache_invalidate(struct iommu_domain *domain, - struct device *dev, - struct iommu_cache_invalidate_info *inv_info) -{ - return -ENODEV; -} - -static inline int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, - struct device *dev, void __user *udata) -{ - return -ENODEV; -} - -static inline int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, void __user *udata) -{ - return -ENODEV; -} - -static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, - ioasid_t pasid) -{ - return -ENODEV; -} - static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev) { return NULL; diff --git a/include/uapi/linux/iommu.h b/include/uapi/linux/iommu.h index 59178fc229ca..65d8b0234f69 100644 --- a/include/uapi/linux/iommu.h +++ b/include/uapi/linux/iommu.h @@ -158,185 +158,4 @@ struct iommu_page_response { __u32 code; }; -/* defines the granularity of the invalidation */ -enum iommu_inv_granularity { - IOMMU_INV_GRANU_DOMAIN, /* domain-selective invalidation */ - IOMMU_INV_GRANU_PASID, /* PASID-selective invalidation */ - IOMMU_INV_GRANU_ADDR, /* page-selective invalidation */ - IOMMU_INV_GRANU_NR, /* number of invalidation granularities */ -}; - -/** - * struct iommu_inv_addr_info - Address Selective Invalidation Structure - * - * @flags: indicates the granularity of the address-selective invalidation - * - If the PASID bit is set, the @pasid field is populated and the invalidation - * relates to cache entries tagged with this PASID and matching the address - * range. - * - If ARCHID bit is set, @archid is populated and the invalidation relates - * to cache entries tagged with this architecture specific ID and matching - * the address range. - * - Both PASID and ARCHID can be set as they may tag different caches. - * - If neither PASID or ARCHID is set, global addr invalidation applies. - * - The LEAF flag indicates whether only the leaf PTE caching needs to be - * invalidated and other paging structure caches can be preserved. - * @pasid: process address space ID - * @archid: architecture-specific ID - * @addr: first stage/level input address - * @granule_size: page/block size of the mapping in bytes - * @nb_granules: number of contiguous granules to be invalidated - */ -struct iommu_inv_addr_info { -#define IOMMU_INV_ADDR_FLAGS_PASID (1 << 0) -#define IOMMU_INV_ADDR_FLAGS_ARCHID (1 << 1) -#define IOMMU_INV_ADDR_FLAGS_LEAF (1 << 2) - __u32 flags; - __u32 archid; - __u64 pasid; - __u64 addr; - __u64 granule_size; - __u64 nb_granules; -}; - -/** - * struct iommu_inv_pasid_info - PASID Selective Invalidation Structure - * - * @flags: indicates the granularity of the PASID-selective invalidation - * - If the PASID bit is set, the @pasid field is populated and the invalidation - * relates to cache entries tagged with this PASID and matching the address - * range. - * - If the ARCHID bit is set, the @archid is populated and the invalidation - * relates to cache entries tagged with this architecture specific ID and - * matching the address range. - * - Both PASID and ARCHID can be set as they may tag different caches. - * - At least one of PASID or ARCHID must be set. - * @pasid: process address space ID - * @archid: architecture-specific ID - */ -struct iommu_inv_pasid_info { -#define IOMMU_INV_PASID_FLAGS_PASID (1 << 0) -#define IOMMU_INV_PASID_FLAGS_ARCHID (1 << 1) - __u32 flags; - __u32 archid; - __u64 pasid; -}; - -/** - * struct iommu_cache_invalidate_info - First level/stage invalidation - * information - * @argsz: User filled size of this data - * @version: API version of this structure - * @cache: bitfield that allows to select which caches to invalidate - * @granularity: defines the lowest granularity used for the invalidation: - * domain > PASID > addr - * @padding: reserved for future use (should be zero) - * @pasid_info: invalidation data when @granularity is %IOMMU_INV_GRANU_PASID - * @addr_info: invalidation data when @granularity is %IOMMU_INV_GRANU_ADDR - * - * Not all the combinations of cache/granularity are valid: - * - * +--------------+---------------+---------------+---------------+ - * | type / | DEV_IOTLB | IOTLB | PASID | - * | granularity | | | cache | - * +==============+===============+===============+===============+ - * | DOMAIN | N/A | Y | Y | - * +--------------+---------------+---------------+---------------+ - * | PASID | Y | Y | Y | - * +--------------+---------------+---------------+---------------+ - * | ADDR | Y | Y | N/A | - * +--------------+---------------+---------------+---------------+ - * - * Invalidations by %IOMMU_INV_GRANU_DOMAIN don't take any argument other than - * @version and @cache. - * - * If multiple cache types are invalidated simultaneously, they all - * must support the used granularity. - */ -struct iommu_cache_invalidate_info { - __u32 argsz; -#define IOMMU_CACHE_INVALIDATE_INFO_VERSION_1 1 - __u32 version; -/* IOMMU paging structure cache */ -#define IOMMU_CACHE_INV_TYPE_IOTLB (1 << 0) /* IOMMU IOTLB */ -#define IOMMU_CACHE_INV_TYPE_DEV_IOTLB (1 << 1) /* Device IOTLB */ -#define IOMMU_CACHE_INV_TYPE_PASID (1 << 2) /* PASID cache */ -#define IOMMU_CACHE_INV_TYPE_NR (3) - __u8 cache; - __u8 granularity; - __u8 padding[6]; - union { - struct iommu_inv_pasid_info pasid_info; - struct iommu_inv_addr_info addr_info; - } granu; -}; - -/** - * struct iommu_gpasid_bind_data_vtd - Intel VT-d specific data on device and guest - * SVA binding. - * - * @flags: VT-d PASID table entry attributes - * @pat: Page attribute table data to compute effective memory type - * @emt: Extended memory type - * - * Only guest vIOMMU selectable and effective options are passed down to - * the host IOMMU. - */ -struct iommu_gpasid_bind_data_vtd { -#define IOMMU_SVA_VTD_GPASID_SRE (1 << 0) /* supervisor request */ -#define IOMMU_SVA_VTD_GPASID_EAFE (1 << 1) /* extended access enable */ -#define IOMMU_SVA_VTD_GPASID_PCD (1 << 2) /* page-level cache disable */ -#define IOMMU_SVA_VTD_GPASID_PWT (1 << 3) /* page-level write through */ -#define IOMMU_SVA_VTD_GPASID_EMTE (1 << 4) /* extended mem type enable */ -#define IOMMU_SVA_VTD_GPASID_CD (1 << 5) /* PASID-level cache disable */ -#define IOMMU_SVA_VTD_GPASID_WPE (1 << 6) /* Write protect enable */ -#define IOMMU_SVA_VTD_GPASID_LAST (1 << 7) - __u64 flags; - __u32 pat; - __u32 emt; -}; - -#define IOMMU_SVA_VTD_GPASID_MTS_MASK (IOMMU_SVA_VTD_GPASID_CD | \ - IOMMU_SVA_VTD_GPASID_EMTE | \ - IOMMU_SVA_VTD_GPASID_PCD | \ - IOMMU_SVA_VTD_GPASID_PWT) - -/** - * struct iommu_gpasid_bind_data - Information about device and guest PASID binding - * @argsz: User filled size of this data - * @version: Version of this data structure - * @format: PASID table entry format - * @flags: Additional information on guest bind request - * @gpgd: Guest page directory base of the guest mm to bind - * @hpasid: Process address space ID used for the guest mm in host IOMMU - * @gpasid: Process address space ID used for the guest mm in guest IOMMU - * @addr_width: Guest virtual address width - * @padding: Reserved for future use (should be zero) - * @vtd: Intel VT-d specific data - * - * Guest to host PASID mapping can be an identity or non-identity, where guest - * has its own PASID space. For non-identify mapping, guest to host PASID lookup - * is needed when VM programs guest PASID into an assigned device. VMM may - * trap such PASID programming then request host IOMMU driver to convert guest - * PASID to host PASID based on this bind data. - */ -struct iommu_gpasid_bind_data { - __u32 argsz; -#define IOMMU_GPASID_BIND_VERSION_1 1 - __u32 version; -#define IOMMU_PASID_FORMAT_INTEL_VTD 1 -#define IOMMU_PASID_FORMAT_LAST 2 - __u32 format; - __u32 addr_width; -#define IOMMU_SVA_GPASID_VAL (1 << 0) /* guest PASID valid */ - __u64 flags; - __u64 gpgd; - __u64 hpasid; - __u64 gpasid; - __u8 padding[8]; - /* Vendor specific data */ - union { - struct iommu_gpasid_bind_data_vtd vtd; - } vendor; -}; - #endif /* _UAPI_IOMMU_H */ -- cgit v1.2.3 From 241469685d8d54075f12a6f3eb0628f85e13ff37 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 16 Feb 2022 10:52:43 +0800 Subject: iommu/vt-d: Remove aux-domain related callbacks The aux-domain related callbacks are not called in the tree. Remove them to avoid dead code. Signed-off-by: Lu Baolu Reviewed-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20220216025249.3459465-4-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index beaacb589abd..5cfda90b2cca 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -542,7 +542,6 @@ struct dmar_domain { u8 iommu_snooping: 1; /* indicate snooping control feature */ struct list_head devices; /* all devices' list */ - struct list_head subdevices; /* all subdevices' list */ struct iova_domain iovad; /* iova's that belong to this domain */ struct dma_pte *pgd; /* virtual address */ @@ -557,11 +556,6 @@ struct dmar_domain { 2 == 1GiB, 3 == 512GiB, 4 == 1TiB */ u64 max_addr; /* maximum mapped address */ - u32 default_pasid; /* - * The default pasid used for non-SVM - * traffic on mediated devices. - */ - struct iommu_domain domain; /* generic domain data structure for iommu core */ }; @@ -614,21 +608,11 @@ struct intel_iommu { void *perf_statistic; }; -/* Per subdevice private data */ -struct subdev_domain_info { - struct list_head link_phys; /* link to phys device siblings */ - struct list_head link_domain; /* link to domain siblings */ - struct device *pdev; /* physical device derived from */ - struct dmar_domain *domain; /* aux-domain */ - int users; /* user count */ -}; - /* PCI domain-device relationship */ struct device_domain_info { struct list_head link; /* link to domain siblings */ struct list_head global; /* link to global list */ struct list_head table; /* link to pasid table */ - struct list_head subdevices; /* subdevices sibling */ u32 segment; /* PCI segment number */ u8 bus; /* PCI bus number */ u8 devfn; /* PCI devfn number */ @@ -639,7 +623,6 @@ struct device_domain_info { u8 pri_enabled:1; u8 ats_supported:1; u8 ats_enabled:1; - u8 auxd_enabled:1; /* Multiple domains per device */ u8 ats_qdep; struct device *dev; /* it's NULL for PCIe-to-PCI bridge */ struct intel_iommu *iommu; /* IOMMU used by this device */ -- cgit v1.2.3 From 8652d875939b6a1fe6d5c93cf4fb91df61cda5a7 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 16 Feb 2022 10:52:44 +0800 Subject: iommu: Remove aux-domain related interfaces and iommu_ops The aux-domain related interfaces and iommu_ops are not referenced anywhere in the tree. We've also reached a consensus to redesign it based the new iommufd framework. Remove them to avoid dead code. Signed-off-by: Lu Baolu Reviewed-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20220216025249.3459465-5-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 29 ----------------------------- 1 file changed, 29 deletions(-) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index cde1d0aad60f..9983a01373b2 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -144,7 +144,6 @@ struct iommu_resv_region { /** * enum iommu_dev_features - Per device IOMMU features - * @IOMMU_DEV_FEAT_AUX: Auxiliary domain feature * @IOMMU_DEV_FEAT_SVA: Shared Virtual Addresses * @IOMMU_DEV_FEAT_IOPF: I/O Page Faults such as PRI or Stall. Generally * enabling %IOMMU_DEV_FEAT_SVA requires @@ -157,7 +156,6 @@ struct iommu_resv_region { * iommu_dev_has_feature(), and enable it using iommu_dev_enable_feature(). */ enum iommu_dev_features { - IOMMU_DEV_FEAT_AUX, IOMMU_DEV_FEAT_SVA, IOMMU_DEV_FEAT_IOPF, }; @@ -223,8 +221,6 @@ struct iommu_iotlb_gather { * @dev_has/enable/disable_feat: per device entries to check/enable/disable * iommu specific features. * @dev_feat_enabled: check enabled feature - * @aux_attach/detach_dev: aux-domain specific attach/detach entries. - * @aux_get_pasid: get the pasid given an aux-domain * @sva_bind: Bind process address space to device * @sva_unbind: Unbind process address space from device * @sva_get_pasid: Get PASID associated to a SVA handle @@ -285,11 +281,6 @@ struct iommu_ops { int (*dev_enable_feat)(struct device *dev, enum iommu_dev_features f); int (*dev_disable_feat)(struct device *dev, enum iommu_dev_features f); - /* Aux-domain specific attach/detach entries */ - int (*aux_attach_dev)(struct iommu_domain *domain, struct device *dev); - void (*aux_detach_dev)(struct iommu_domain *domain, struct device *dev); - int (*aux_get_pasid)(struct iommu_domain *domain, struct device *dev); - struct iommu_sva *(*sva_bind)(struct device *dev, struct mm_struct *mm, void *drvdata); void (*sva_unbind)(struct iommu_sva *handle); @@ -655,9 +646,6 @@ void iommu_release_device(struct device *dev); int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f); int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features f); bool iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features f); -int iommu_aux_attach_device(struct iommu_domain *domain, struct device *dev); -void iommu_aux_detach_device(struct iommu_domain *domain, struct device *dev); -int iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev); struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, @@ -1002,23 +990,6 @@ iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat) return -ENODEV; } -static inline int -iommu_aux_attach_device(struct iommu_domain *domain, struct device *dev) -{ - return -ENODEV; -} - -static inline void -iommu_aux_detach_device(struct iommu_domain *domain, struct device *dev) -{ -} - -static inline int -iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev) -{ - return -ENODEV; -} - static inline struct iommu_sva * iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata) { -- cgit v1.2.3 From 71fe30698dc3be6fd277c49c0c7b220c7ae92ffd Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 16 Feb 2022 10:52:45 +0800 Subject: iommu: Remove apply_resv_region The apply_resv_region callback in iommu_ops was introduced to reserve an IOVA range in the given DMA domain when the IOMMU driver manages the IOVA by itself. As all drivers converted to use dma-iommu in the core, there's no driver using this anymore. Remove it to avoid dead code. Suggested-by: Robin Murphy Signed-off-by: Lu Baolu Reviewed-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20220216025249.3459465-6-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 9983a01373b2..9ffa2e88f3d0 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -214,7 +214,6 @@ struct iommu_iotlb_gather { * @set_pgtable_quirks: Set io page table quirks (IO_PGTABLE_QUIRK_*) * @get_resv_regions: Request list of reserved regions for a device * @put_resv_regions: Free list of reserved regions for a device - * @apply_resv_region: Temporary helper call-back for iova reserved ranges * @of_xlate: add OF master IDs to iommu grouping * @is_attach_deferred: Check if domain attach should be deferred from iommu * driver init to device driver init (default no) @@ -268,9 +267,6 @@ struct iommu_ops { /* Request/Free a list of reserved regions for a device */ void (*get_resv_regions)(struct device *dev, struct list_head *list); void (*put_resv_regions)(struct device *dev, struct list_head *list); - void (*apply_resv_region)(struct device *dev, - struct iommu_domain *domain, - struct iommu_resv_region *region); int (*of_xlate)(struct device *dev, struct of_phandle_args *args); bool (*is_attach_deferred)(struct iommu_domain *domain, struct device *dev); -- cgit v1.2.3 From 3f6634d997dba8140b3a7cba01776b9638d70dff Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 16 Feb 2022 10:52:47 +0800 Subject: iommu: Use right way to retrieve iommu_ops The common iommu_ops is hooked to both device and domain. When a helper has both device and domain pointer, the way to get the iommu_ops looks messy in iommu core. This sorts out the way to get iommu_ops. The device related helpers go through device pointer, while the domain related ones go through domain pointer. Signed-off-by: Lu Baolu Reviewed-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20220216025249.3459465-8-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 9ffa2e88f3d0..90f1b5e3809d 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -381,6 +381,17 @@ static inline void iommu_iotlb_gather_init(struct iommu_iotlb_gather *gather) }; } +static inline const struct iommu_ops *dev_iommu_ops(struct device *dev) +{ + /* + * Assume that valid ops must be installed if iommu_probe_device() + * has succeeded. The device ops are essentially for internal use + * within the IOMMU subsystem itself, so we should be able to trust + * ourselves not to misuse the helper. + */ + return dev->iommu->iommu_dev->ops; +} + #define IOMMU_GROUP_NOTIFY_ADD_DEVICE 1 /* Device added */ #define IOMMU_GROUP_NOTIFY_DEL_DEVICE 2 /* Pre Device removed */ #define IOMMU_GROUP_NOTIFY_BIND_DRIVER 3 /* Pre Driver bind */ -- cgit v1.2.3 From 41bb23e70b50b89b6137cbecd37009d782454860 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 16 Feb 2022 10:52:48 +0800 Subject: iommu: Remove unused argument in is_attach_deferred The is_attach_deferred iommu_ops callback is a device op. The domain argument is unnecessary and never used. Remove it to make code clean. Suggested-by: Robin Murphy Signed-off-by: Lu Baolu Reviewed-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20220216025249.3459465-9-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 90f1b5e3809d..1ded6076a75c 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -269,7 +269,7 @@ struct iommu_ops { void (*put_resv_regions)(struct device *dev, struct list_head *list); int (*of_xlate)(struct device *dev, struct of_phandle_args *args); - bool (*is_attach_deferred)(struct iommu_domain *domain, struct device *dev); + bool (*is_attach_deferred)(struct device *dev); /* Per device IOMMU features */ bool (*dev_has_feat)(struct device *dev, enum iommu_dev_features f); -- cgit v1.2.3 From 9a630a4b41a2639b65d024a5d2d88ed3ecca130a Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 16 Feb 2022 10:52:49 +0800 Subject: iommu: Split struct iommu_ops Move the domain specific operations out of struct iommu_ops into a new structure that only has domain specific operations. This solves the problem of needing to know if the method vector for a given operation needs to be retrieved from the device or the domain. Logically the domain ops are the ones that make sense for external subsystems and endpoint drivers to use, while device ops, with the sole exception of domain_alloc, are IOMMU API internals. Signed-off-by: Lu Baolu Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20220216025249.3459465-10-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 91 ++++++++++++++++++++++++++++++--------------------- 1 file changed, 53 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 1ded6076a75c..9208eca4b0d1 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -37,6 +37,7 @@ struct iommu_group; struct bus_type; struct device; struct iommu_domain; +struct iommu_domain_ops; struct notifier_block; struct iommu_sva; struct iommu_fault_event; @@ -88,7 +89,7 @@ struct iommu_domain_geometry { struct iommu_domain { unsigned type; - const struct iommu_ops *ops; + const struct iommu_domain_ops *ops; unsigned long pgsize_bitmap; /* Bitmap of page sizes in use */ iommu_fault_handler_t handler; void *handler_token; @@ -192,26 +193,11 @@ struct iommu_iotlb_gather { * struct iommu_ops - iommu ops and capabilities * @capable: check capability * @domain_alloc: allocate iommu domain - * @domain_free: free iommu domain - * @attach_dev: attach device to an iommu domain - * @detach_dev: detach device from an iommu domain - * @map: map a physically contiguous memory region to an iommu domain - * @map_pages: map a physically contiguous set of pages of the same size to - * an iommu domain. - * @unmap: unmap a physically contiguous memory region from an iommu domain - * @unmap_pages: unmap a number of pages of the same size from an iommu domain - * @flush_iotlb_all: Synchronously flush all hardware TLBs for this domain - * @iotlb_sync_map: Sync mappings created recently using @map to the hardware - * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush - * queue - * @iova_to_phys: translate iova to physical address * @probe_device: Add device to iommu driver handling * @release_device: Remove device from iommu driver handling * @probe_finalize: Do final setup work after the device is added to an IOMMU * group and attached to the groups domain * @device_group: find iommu group for a particular device - * @enable_nesting: Enable nesting - * @set_pgtable_quirks: Set io page table quirks (IO_PGTABLE_QUIRK_*) * @get_resv_regions: Request list of reserved regions for a device * @put_resv_regions: Free list of reserved regions for a device * @of_xlate: add OF master IDs to iommu grouping @@ -228,6 +214,7 @@ struct iommu_iotlb_gather { * - IOMMU_DOMAIN_IDENTITY: must use an identity domain * - IOMMU_DOMAIN_DMA: must use a dma domain * - 0: use the default setting + * @default_domain_ops: the default ops for domains * @pgsize_bitmap: bitmap of all possible supported page sizes * @owner: Driver module providing these ops */ @@ -236,33 +223,11 @@ struct iommu_ops { /* Domain allocation and freeing by the iommu driver */ struct iommu_domain *(*domain_alloc)(unsigned iommu_domain_type); - void (*domain_free)(struct iommu_domain *); - int (*attach_dev)(struct iommu_domain *domain, struct device *dev); - void (*detach_dev)(struct iommu_domain *domain, struct device *dev); - int (*map)(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot, gfp_t gfp); - int (*map_pages)(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t pgsize, size_t pgcount, - int prot, gfp_t gfp, size_t *mapped); - size_t (*unmap)(struct iommu_domain *domain, unsigned long iova, - size_t size, struct iommu_iotlb_gather *iotlb_gather); - size_t (*unmap_pages)(struct iommu_domain *domain, unsigned long iova, - size_t pgsize, size_t pgcount, - struct iommu_iotlb_gather *iotlb_gather); - void (*flush_iotlb_all)(struct iommu_domain *domain); - void (*iotlb_sync_map)(struct iommu_domain *domain, unsigned long iova, - size_t size); - void (*iotlb_sync)(struct iommu_domain *domain, - struct iommu_iotlb_gather *iotlb_gather); - phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova); struct iommu_device *(*probe_device)(struct device *dev); void (*release_device)(struct device *dev); void (*probe_finalize)(struct device *dev); struct iommu_group *(*device_group)(struct device *dev); - int (*enable_nesting)(struct iommu_domain *domain); - int (*set_pgtable_quirks)(struct iommu_domain *domain, - unsigned long quirks); /* Request/Free a list of reserved regions for a device */ void (*get_resv_regions)(struct device *dev, struct list_head *list); @@ -288,10 +253,60 @@ struct iommu_ops { int (*def_domain_type)(struct device *dev); + const struct iommu_domain_ops *default_domain_ops; unsigned long pgsize_bitmap; struct module *owner; }; +/** + * struct iommu_domain_ops - domain specific operations + * @attach_dev: attach an iommu domain to a device + * @detach_dev: detach an iommu domain from a device + * @map: map a physically contiguous memory region to an iommu domain + * @map_pages: map a physically contiguous set of pages of the same size to + * an iommu domain. + * @unmap: unmap a physically contiguous memory region from an iommu domain + * @unmap_pages: unmap a number of pages of the same size from an iommu domain + * @flush_iotlb_all: Synchronously flush all hardware TLBs for this domain + * @iotlb_sync_map: Sync mappings created recently using @map to the hardware + * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush + * queue + * @iova_to_phys: translate iova to physical address + * @enable_nesting: Enable nesting + * @set_pgtable_quirks: Set io page table quirks (IO_PGTABLE_QUIRK_*) + * @free: Release the domain after use. + */ +struct iommu_domain_ops { + int (*attach_dev)(struct iommu_domain *domain, struct device *dev); + void (*detach_dev)(struct iommu_domain *domain, struct device *dev); + + int (*map)(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot, gfp_t gfp); + int (*map_pages)(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t pgsize, size_t pgcount, + int prot, gfp_t gfp, size_t *mapped); + size_t (*unmap)(struct iommu_domain *domain, unsigned long iova, + size_t size, struct iommu_iotlb_gather *iotlb_gather); + size_t (*unmap_pages)(struct iommu_domain *domain, unsigned long iova, + size_t pgsize, size_t pgcount, + struct iommu_iotlb_gather *iotlb_gather); + + void (*flush_iotlb_all)(struct iommu_domain *domain); + void (*iotlb_sync_map)(struct iommu_domain *domain, unsigned long iova, + size_t size); + void (*iotlb_sync)(struct iommu_domain *domain, + struct iommu_iotlb_gather *iotlb_gather); + + phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, + dma_addr_t iova); + + int (*enable_nesting)(struct iommu_domain *domain); + int (*set_pgtable_quirks)(struct iommu_domain *domain, + unsigned long quirks); + + void (*free)(struct iommu_domain *domain); +}; + /** * struct iommu_device - IOMMU core representation of one IOMMU hardware * instance -- cgit v1.2.3 From 6bb477df04366e0f69dd2f49e1ae1099069326bc Mon Sep 17 00:00:00 2001 From: Yun Zhou Date: Thu, 17 Feb 2022 22:12:34 +0800 Subject: spi: use specific last_cs instead of last_cs_enable Commit d40f0b6f2e21 instroduced last_cs_enable to avoid setting chipselect if it's not necessary, but it also introduces a bug. The chipselect may not be set correctly on multi-device SPI busses. The reason is that we can't judge the chipselect by bool last_cs_enable, since chipselect may be modified after other devices were accessed. So we should record the specific state of chipselect in case of confusion. Signed-off-by: Yun Zhou Link: https://lore.kernel.org/r/20220217141234.72737-1-yun.zhou@windriver.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 579d71cdf6fa..7d005fa4631c 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -370,7 +370,8 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @cur_msg_prepared: spi_prepare_message was called for the currently * in-flight message * @cur_msg_mapped: message has been mapped for DMA - * @last_cs_enable: was enable true on the last call to set_cs. + * @last_cs: the last chip_select that is recorded by set_cs, -1 on non chip + * selected * @last_cs_mode_high: was (mode & SPI_CS_HIGH) true on the last call to set_cs. * @xfer_completion: used by core transfer_one_message() * @busy: message pump is busy @@ -603,7 +604,7 @@ struct spi_controller { bool auto_runtime_pm; bool cur_msg_prepared; bool cur_msg_mapped; - bool last_cs_enable; + char last_cs; bool last_cs_mode_high; bool fallback; struct completion xfer_completion; -- cgit v1.2.3 From 20f01f163203666010ee1560852590a0c0572726 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 24 Jan 2022 13:59:38 -0800 Subject: blk-crypto: show crypto capabilities in sysfs Add sysfs files that expose the inline encryption capabilities of request queues: /sys/block/$disk/queue/crypto/max_dun_bits /sys/block/$disk/queue/crypto/modes/$mode /sys/block/$disk/queue/crypto/num_keyslots Userspace can use these new files to decide what encryption settings to use, or whether to use inline encryption at all. This also brings the crypto capabilities in line with the other queue properties, which are already discoverable via the queue directory in sysfs. Design notes: - Place the new files in a new subdirectory "crypto" to group them together and to avoid complicating the main "queue" directory. This also makes it possible to replace "crypto" with a symlink later if we ever make the blk_crypto_profiles into real kobjects (see below). - It was necessary to define a new kobject that corresponds to the crypto subdirectory. For now, this kobject just contains a pointer to the blk_crypto_profile. Note that multiple queues (and hence multiple such kobjects) may refer to the same blk_crypto_profile. An alternative design would more closely match the current kernel data structures: the blk_crypto_profile could be a kobject itself, located directly under the host controller device's kobject, while /sys/block/$disk/queue/crypto would be a symlink to it. I decided not to do that for now because it would require a lot more changes, such as no longer embedding blk_crypto_profile in other structures, and also because I'm not sure we can rule out moving the crypto capabilities into 'struct queue_limits' in the future. (Even if multiple queues share the same crypto engine, maybe the supported data unit sizes could differ due to other queue properties.) It would also still be possible to switch to that design later without breaking userspace, by replacing the directory with a symlink. - Use "max_dun_bits" instead of "max_dun_bytes". Currently, the kernel internally stores this value in bytes, but that's an implementation detail. It probably makes more sense to talk about this value in bits, and choosing bits is more future-proof. - "modes" is a sub-subdirectory, since there may be multiple supported crypto modes, sysfs is supposed to have one value per file, and it makes sense to group all the mode files together. - Each mode had to be named. The crypto API names like "xts(aes)" are not appropriate because they don't specify the key size. Therefore, I assigned new names. The exact names chosen are arbitrary, but they happen to match the names used in log messages in fs/crypto/. - The "num_keyslots" file is a bit different from the others in that it is only useful to know for performance reasons. However, it's included as it can still be useful. For example, a user might not want to use inline encryption if there aren't very many keyslots. Reviewed-by: Hannes Reinecke Signed-off-by: Eric Biggers Link: https://lore.kernel.org/r/20220124215938.2769-4-ebiggers@kernel.org Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f757f9c2871f..e19947d84f12 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -413,6 +413,7 @@ struct request_queue { #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct blk_crypto_profile *crypto_profile; + struct kobject *crypto_kobject; #endif unsigned int rq_timeout; -- cgit v1.2.3 From 25d490eb46486e88c16e64d9eb7cfd33a642d596 Mon Sep 17 00:00:00 2001 From: Wang Kefeng Date: Sat, 18 Dec 2021 09:30:40 +0100 Subject: ARM: 9172/1: amba: Cleanup amba pclk operation There is no user about amba_pclk_[un]prepare() besides pl330.c, directly use clk_[un]prepare(). After this, all the function about amba pclk operation, enable, disable, [un]prepare could be killed. Acked-by: Vinod Koul Signed-off-by: Kefeng Wang Signed-off-by: Russell King (Oracle) --- include/linux/amba/bus.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include') diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 6c7f47846971..09174970b855 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -121,26 +121,6 @@ struct amba_device *amba_find_device(const char *, struct device *, unsigned int int amba_request_regions(struct amba_device *, const char *); void amba_release_regions(struct amba_device *); -static inline int amba_pclk_enable(struct amba_device *dev) -{ - return clk_enable(dev->pclk); -} - -static inline void amba_pclk_disable(struct amba_device *dev) -{ - clk_disable(dev->pclk); -} - -static inline int amba_pclk_prepare(struct amba_device *dev) -{ - return clk_prepare(dev->pclk); -} - -static inline void amba_pclk_unprepare(struct amba_device *dev) -{ - clk_unprepare(dev->pclk); -} - /* Some drivers don't use the struct amba_device */ #define AMBA_CONFIG_BITS(a) (((a) >> 24) & 0xff) #define AMBA_REV_BITS(a) (((a) >> 20) & 0x0f) -- cgit v1.2.3 From dacf3ca134d0dc105caee77651a349a86bd77456 Mon Sep 17 00:00:00 2001 From: Wang Kefeng Date: Sat, 18 Dec 2021 09:30:41 +0100 Subject: ARM: 9173/1: amba: kill amba_find_match() There is no one use amba_find_match(), kill it. Signed-off-by: Kefeng Wang Signed-off-by: Russell King (Oracle) --- include/linux/amba/bus.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 09174970b855..6562f543c3e0 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -117,7 +117,6 @@ void amba_device_put(struct amba_device *); int amba_device_add(struct amba_device *, struct resource *); int amba_device_register(struct amba_device *, struct resource *); void amba_device_unregister(struct amba_device *); -struct amba_device *amba_find_device(const char *, struct device *, unsigned int, unsigned int); int amba_request_regions(struct amba_device *, const char *); void amba_release_regions(struct amba_device *); -- cgit v1.2.3 From 1a93b82c59ab45f2d9f14c47f09d2e341ff02381 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 18 Feb 2022 07:07:08 -0500 Subject: NFS: constify nfs_server_capable() and nfs_have_writebacks() Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 72a732a5103c..6e10725887d1 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -363,7 +363,7 @@ static inline void nfs_mark_for_revalidate(struct inode *inode) spin_unlock(&inode->i_lock); } -static inline int nfs_server_capable(struct inode *inode, int cap) +static inline int nfs_server_capable(const struct inode *inode, int cap) { return NFS_SERVER(inode)->caps & cap; } @@ -587,12 +587,11 @@ extern struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail); extern void nfs_commit_free(struct nfs_commit_data *data); bool nfs_commit_end(struct nfs_mds_commit_info *cinfo); -static inline int -nfs_have_writebacks(struct inode *inode) +static inline bool nfs_have_writebacks(const struct inode *inode) { if (S_ISREG(inode->i_mode)) return atomic_long_read(&NFS_I(inode)->nrequests) != 0; - return 0; + return false; } /* -- cgit v1.2.3 From d07c9ad622474616e94572e59e725c2c4a494fb4 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 11 Jan 2022 12:43:55 -0500 Subject: tracing: Introduce helpers to safely handle dynamic-sized sockaddrs Enable a struct sockaddr to be stored in a trace record as a dynamically-sized field. The common cases are AF_INET and AF_INET6 which are different sizes, and are vastly smaller than a struct sockaddr_storage. These are safer because, when used properly, the size of the sockaddr destination field in each trace record is now guaranteed to be the same as the source address that is being copied into it. Link: https://lore.kernel.org/all/164182978641.8391.8277203495236105391.stgit@bazille.1015granger.net/ Signed-off-by: Chuck Lever --- include/trace/bpf_probe.h | 6 +++++ include/trace/perf.h | 6 +++++ include/trace/trace_events.h | 55 ++++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 65 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h index 7660a7846586..6a13220d2d27 100644 --- a/include/trace/bpf_probe.h +++ b/include/trace/bpf_probe.h @@ -21,6 +21,9 @@ #undef __get_bitmask #define __get_bitmask(field) (char *)__get_dynamic_array(field) +#undef __get_sockaddr +#define __get_sockaddr(field) ((struct sockaddr *)__get_dynamic_array(field)) + #undef __get_rel_dynamic_array #define __get_rel_dynamic_array(field) \ ((void *)(&__entry->__rel_loc_##field) + \ @@ -37,6 +40,9 @@ #undef __get_rel_bitmask #define __get_rel_bitmask(field) (char *)__get_rel_dynamic_array(field) +#undef __get_rel_sockaddr +#define __get_rel_sockaddr(field) ((struct sockaddr *)__get_rel_dynamic_array(field)) + #undef __perf_count #define __perf_count(c) (c) diff --git a/include/trace/perf.h b/include/trace/perf.h index 5d48c46a3008..5800d13146c3 100644 --- a/include/trace/perf.h +++ b/include/trace/perf.h @@ -21,6 +21,9 @@ #undef __get_bitmask #define __get_bitmask(field) (char *)__get_dynamic_array(field) +#undef __get_sockaddr +#define __get_sockaddr(field) ((struct sockaddr *)__get_dynamic_array(field)) + #undef __get_rel_dynamic_array #define __get_rel_dynamic_array(field) \ ((void *)__entry + \ @@ -38,6 +41,9 @@ #undef __get_rel_bitmask #define __get_rel_bitmask(field) (char *)__get_rel_dynamic_array(field) +#undef __get_rel_sockaddr +#define __get_rel_sockaddr(field) ((struct sockaddr *)__get_rel_dynamic_array(field)) + #undef __perf_count #define __perf_count(c) (__count = (c)) diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h index 3d29919045af..7c86cc541c7a 100644 --- a/include/trace/trace_events.h +++ b/include/trace/trace_events.h @@ -108,6 +108,9 @@ TRACE_MAKE_SYSTEM_STR(); #undef __bitmask #define __bitmask(item, nr_bits) __dynamic_array(char, item, -1) +#undef __sockaddr +#define __sockaddr(field, len) __dynamic_array(u8, field, len) + #undef __rel_dynamic_array #define __rel_dynamic_array(type, item, len) u32 __rel_loc_##item; @@ -120,6 +123,9 @@ TRACE_MAKE_SYSTEM_STR(); #undef __rel_bitmask #define __rel_bitmask(item, nr_bits) __rel_dynamic_array(char, item, -1) +#undef __rel_sockaddr +#define __rel_sockaddr(field, len) __rel_dynamic_array(u8, field, len) + #undef TP_STRUCT__entry #define TP_STRUCT__entry(args...) args @@ -212,11 +218,14 @@ TRACE_MAKE_SYSTEM_STR(); #undef __string #define __string(item, src) __dynamic_array(char, item, -1) +#undef __string_len +#define __string_len(item, src, len) __dynamic_array(char, item, -1) + #undef __bitmask #define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1) -#undef __string_len -#define __string_len(item, src, len) __dynamic_array(char, item, -1) +#undef __sockaddr +#define __sockaddr(field, len) __dynamic_array(u8, field, len) #undef __rel_dynamic_array #define __rel_dynamic_array(type, item, len) u32 item; @@ -230,6 +239,9 @@ TRACE_MAKE_SYSTEM_STR(); #undef __rel_bitmask #define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1) +#undef __rel_sockaddr +#define __rel_sockaddr(field, len) __rel_dynamic_array(u8, field, len) + #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ struct trace_event_data_offsets_##call { \ @@ -349,6 +361,12 @@ TRACE_MAKE_SYSTEM_STR(); trace_print_bitmask_seq(p, __bitmask, __bitmask_size); \ }) +#undef __get_sockaddr +#define __get_sockaddr(field) ((struct sockaddr *)__get_dynamic_array(field)) + +#undef __get_rel_sockaddr +#define __get_rel_sockaddr(field) ((struct sockaddr *)__get_rel_dynamic_array(field)) + #undef __print_flags #define __print_flags(flag, delim, flag_array...) \ ({ \ @@ -518,6 +536,9 @@ static struct trace_event_functions trace_event_type_funcs_##call = { \ #undef __bitmask #define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1) +#undef __sockaddr +#define __sockaddr(field, len) __dynamic_array(u8, field, len) + #undef __rel_dynamic_array #define __rel_dynamic_array(_type, _item, _len) { \ .type = "__rel_loc " #_type "[]", .name = #_item, \ @@ -533,6 +554,9 @@ static struct trace_event_functions trace_event_type_funcs_##call = { \ #undef __rel_bitmask #define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1) +#undef __rel_sockaddr +#define __rel_sockaddr(field, len) __rel_dynamic_array(u8, field, len) + #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, func, print) \ static struct trace_event_fields trace_event_fields_##call[] = { \ @@ -624,6 +648,12 @@ static struct trace_event_fields trace_event_fields_##call[] = { \ #define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, \ __bitmask_size_in_longs(nr_bits)) +#undef __sockaddr +#define __sockaddr(field, len) __dynamic_array(u8, field, len) + +#undef __rel_sockaddr +#define __rel_sockaddr(field, len) __rel_dynamic_array(u8, field, len) + #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ static inline notrace int trace_event_get_offsets_##call( \ @@ -788,6 +818,15 @@ static inline notrace int trace_event_get_offsets_##call( \ #define __assign_bitmask(dst, src, nr_bits) \ memcpy(__get_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits)) +#undef __sockaddr +#define __sockaddr(field, len) __dynamic_array(u8, field, len) + +#undef __get_sockaddr +#define __get_sockaddr(field) ((struct sockaddr *)__get_dynamic_array(field)) + +#define __assign_sockaddr(dest, src, len) \ + memcpy(__get_dynamic_array(dest), src, len) + #undef __rel_dynamic_array #define __rel_dynamic_array(type, item, len) \ __entry->__rel_loc_##item = __data_offsets.item; @@ -819,6 +858,16 @@ static inline notrace int trace_event_get_offsets_##call( \ #define __assign_rel_bitmask(dst, src, nr_bits) \ memcpy(__get_rel_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits)) +#undef __rel_sockaddr +#define __rel_sockaddr(field, len) __rel_dynamic_array(u8, field, len) + +#undef __get_rel_sockaddr +#define __get_rel_sockaddr(field) ((struct sockaddr *)__get_rel_dynamic_array(field)) + +#define __assign_rel_sockaddr(dest, src, len) \ + memcpy(__get_rel_dynamic_array(dest), src, len) + + #undef TP_fast_assign #define TP_fast_assign(args...) args @@ -883,10 +932,12 @@ static inline void ftrace_test_probe_##call(void) \ #undef __get_dynamic_array_len #undef __get_str #undef __get_bitmask +#undef __get_sockaddr #undef __get_rel_dynamic_array #undef __get_rel_dynamic_array_len #undef __get_rel_str #undef __get_rel_bitmask +#undef __get_rel_sockaddr #undef __print_array #undef __print_hex_dump -- cgit v1.2.3 From 26ce14e77a827fd73a650cffea4db7ddcc62ebc4 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 24 Jan 2022 11:31:45 -0500 Subject: SUNRPC: Improve sockaddr handling in the svc_xprt_create_error trace point Clean up: Use the new __sockaddr field to record the socket address. Signed-off-by: Chuck Lever --- include/trace/events/sunrpc.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 29982d60b68a..39ed91dca5ab 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -1774,18 +1774,18 @@ TRACE_EVENT(svc_xprt_create_err, __field(long, error) __string(program, program) __string(protocol, protocol) - __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + __sockaddr(addr, salen) ), TP_fast_assign( __entry->error = PTR_ERR(xprt); __assign_str(program, program); __assign_str(protocol, protocol); - memcpy(__entry->addr, sap, min(salen, sizeof(__entry->addr))); + __assign_sockaddr(addr, sap, salen); ), TP_printk("addr=%pISpc program=%s protocol=%s error=%ld", - __entry->addr, __get_str(program), __get_str(protocol), + __get_sockaddr(addr), __get_str(program), __get_str(protocol), __entry->error) ); -- cgit v1.2.3 From aca3ed791553f1f9f994273a12b30c35b40f2769 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 19 Oct 2021 17:07:44 -0400 Subject: SUNRPC: Same as SVC_RQST_ENDPOINT, but without the xid Signed-off-by: Chuck Lever --- include/trace/events/sunrpc.h | 112 ++++++++++++++++++++++++++---------------- 1 file changed, 71 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 39ed91dca5ab..84f585319695 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -1789,50 +1789,99 @@ TRACE_EVENT(svc_xprt_create_err, __entry->error) ); +#define SVC_XPRT_ENDPOINT_FIELDS(x) \ + __sockaddr(server, (x)->xpt_locallen) \ + __sockaddr(client, (x)->xpt_remotelen) \ + __field(unsigned long, flags) \ + __field(unsigned int, netns_ino) + +#define SVC_XPRT_ENDPOINT_ASSIGNMENTS(x) \ + do { \ + __assign_sockaddr(server, &(x)->xpt_local, \ + (x)->xpt_locallen); \ + __assign_sockaddr(client, &(x)->xpt_remote, \ + (x)->xpt_remotelen); \ + __entry->flags = (x)->xpt_flags; \ + __entry->netns_ino = (x)->xpt_net->ns.inum; \ + } while (0) + +#define SVC_XPRT_ENDPOINT_FORMAT \ + "server=%pISpc client=%pISpc flags=%s" + +#define SVC_XPRT_ENDPOINT_VARARGS \ + __get_sockaddr(server), __get_sockaddr(client), \ + show_svc_xprt_flags(__entry->flags) + TRACE_EVENT(svc_xprt_enqueue, - TP_PROTO(struct svc_xprt *xprt, struct svc_rqst *rqst), + TP_PROTO( + const struct svc_xprt *xprt, + const struct svc_rqst *rqst + ), TP_ARGS(xprt, rqst), TP_STRUCT__entry( + SVC_XPRT_ENDPOINT_FIELDS(xprt) + __field(int, pid) - __field(unsigned long, flags) - __string(addr, xprt->xpt_remotebuf) ), TP_fast_assign( + SVC_XPRT_ENDPOINT_ASSIGNMENTS(xprt); + __entry->pid = rqst? rqst->rq_task->pid : 0; - __entry->flags = xprt->xpt_flags; - __assign_str(addr, xprt->xpt_remotebuf); ), - TP_printk("addr=%s pid=%d flags=%s", __get_str(addr), - __entry->pid, show_svc_xprt_flags(__entry->flags)) + TP_printk(SVC_XPRT_ENDPOINT_FORMAT " pid=%d", + SVC_XPRT_ENDPOINT_VARARGS, __entry->pid) +); + +TRACE_EVENT(svc_xprt_dequeue, + TP_PROTO( + const struct svc_rqst *rqst + ), + + TP_ARGS(rqst), + + TP_STRUCT__entry( + SVC_XPRT_ENDPOINT_FIELDS(rqst->rq_xprt) + + __field(unsigned long, wakeup) + ), + + TP_fast_assign( + SVC_XPRT_ENDPOINT_ASSIGNMENTS(rqst->rq_xprt); + + __entry->wakeup = ktime_to_us(ktime_sub(ktime_get(), + rqst->rq_qtime)); + ), + + TP_printk(SVC_XPRT_ENDPOINT_FORMAT " wakeup-us=%lu", + SVC_XPRT_ENDPOINT_VARARGS, __entry->wakeup) ); DECLARE_EVENT_CLASS(svc_xprt_event, - TP_PROTO(struct svc_xprt *xprt), + TP_PROTO( + const struct svc_xprt *xprt + ), TP_ARGS(xprt), TP_STRUCT__entry( - __field(unsigned long, flags) - __string(addr, xprt->xpt_remotebuf) + SVC_XPRT_ENDPOINT_FIELDS(xprt) ), TP_fast_assign( - __entry->flags = xprt->xpt_flags; - __assign_str(addr, xprt->xpt_remotebuf); + SVC_XPRT_ENDPOINT_ASSIGNMENTS(xprt); ), - TP_printk("addr=%s flags=%s", __get_str(addr), - show_svc_xprt_flags(__entry->flags)) + TP_printk(SVC_XPRT_ENDPOINT_FORMAT, SVC_XPRT_ENDPOINT_VARARGS) ); #define DEFINE_SVC_XPRT_EVENT(name) \ DEFINE_EVENT(svc_xprt_event, svc_xprt_##name, \ TP_PROTO( \ - struct svc_xprt *xprt \ + const struct svc_xprt *xprt \ ), \ TP_ARGS(xprt)) @@ -1850,44 +1899,25 @@ TRACE_EVENT(svc_xprt_accept, TP_ARGS(xprt, service), TP_STRUCT__entry( - __string(addr, xprt->xpt_remotebuf) + SVC_XPRT_ENDPOINT_FIELDS(xprt) + __string(protocol, xprt->xpt_class->xcl_name) __string(service, service) ), TP_fast_assign( - __assign_str(addr, xprt->xpt_remotebuf); + SVC_XPRT_ENDPOINT_ASSIGNMENTS(xprt); + __assign_str(protocol, xprt->xpt_class->xcl_name); __assign_str(service, service); ), - TP_printk("addr=%s protocol=%s service=%s", - __get_str(addr), __get_str(protocol), __get_str(service) + TP_printk(SVC_XPRT_ENDPOINT_FORMAT " protocol=%s service=%s", + SVC_XPRT_ENDPOINT_VARARGS, + __get_str(protocol), __get_str(service) ) ); -TRACE_EVENT(svc_xprt_dequeue, - TP_PROTO(struct svc_rqst *rqst), - - TP_ARGS(rqst), - - TP_STRUCT__entry( - __field(unsigned long, flags) - __field(unsigned long, wakeup) - __string(addr, rqst->rq_xprt->xpt_remotebuf) - ), - - TP_fast_assign( - __entry->flags = rqst->rq_xprt->xpt_flags; - __entry->wakeup = ktime_to_us(ktime_sub(ktime_get(), - rqst->rq_qtime)); - __assign_str(addr, rqst->rq_xprt->xpt_remotebuf); - ), - - TP_printk("addr=%s flags=%s wakeup-us=%lu", __get_str(addr), - show_svc_xprt_flags(__entry->flags), __entry->wakeup) -); - TRACE_EVENT(svc_wake_up, TP_PROTO(int pid), -- cgit v1.2.3 From 70a60cbfb613d8f6ffd1d9ade187d0a868066500 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 19 Oct 2021 13:47:24 -0400 Subject: SUNRPC: Record endpoint information in trace log To make server-side trace events more useful in container-ized environments, capture not just the remote's IP address, but the local IP address and network namespace as well. Signed-off-by: Chuck Lever --- include/trace/events/sunrpc.h | 126 ++++++++++++++++++++++++++---------------- 1 file changed, 78 insertions(+), 48 deletions(-) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 84f585319695..ab8ae1f6ba84 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -1625,26 +1625,53 @@ TRACE_DEFINE_ENUM(SVC_COMPLETE); { SVC_PENDING, "SVC_PENDING" }, \ { SVC_COMPLETE, "SVC_COMPLETE" }) +#define SVC_RQST_ENDPOINT_FIELDS(r) \ + __sockaddr(server, (r)->rq_xprt->xpt_locallen) \ + __sockaddr(client, (r)->rq_xprt->xpt_remotelen) \ + __field(unsigned int, netns_ino) \ + __field(u32, xid) + +#define SVC_RQST_ENDPOINT_ASSIGNMENTS(r) \ + do { \ + struct svc_xprt *xprt = (r)->rq_xprt; \ + __assign_sockaddr(server, &xprt->xpt_local, \ + xprt->xpt_locallen); \ + __assign_sockaddr(client, &xprt->xpt_remote, \ + xprt->xpt_remotelen); \ + __entry->netns_ino = xprt->xpt_net->ns.inum; \ + __entry->xid = be32_to_cpu((r)->rq_xid); \ + } while (0) + +#define SVC_RQST_ENDPOINT_FORMAT \ + "xid=0x%08x server=%pISpc client=%pISpc" + +#define SVC_RQST_ENDPOINT_VARARGS \ + __entry->xid, __get_sockaddr(server), __get_sockaddr(client) + TRACE_EVENT(svc_authenticate, TP_PROTO(const struct svc_rqst *rqst, int auth_res), TP_ARGS(rqst, auth_res), TP_STRUCT__entry( - __field(u32, xid) + SVC_RQST_ENDPOINT_FIELDS(rqst) + __field(unsigned long, svc_status) __field(unsigned long, auth_stat) ), TP_fast_assign( - __entry->xid = be32_to_cpu(rqst->rq_xid); + SVC_RQST_ENDPOINT_ASSIGNMENTS(rqst); + __entry->svc_status = auth_res; __entry->auth_stat = be32_to_cpu(rqst->rq_auth_stat); ), - TP_printk("xid=0x%08x auth_res=%s auth_stat=%s", - __entry->xid, svc_show_status(__entry->svc_status), - rpc_show_auth_stat(__entry->auth_stat)) + TP_printk(SVC_RQST_ENDPOINT_FORMAT + " auth_res=%s auth_stat=%s", + SVC_RQST_ENDPOINT_VARARGS, + svc_show_status(__entry->svc_status), + rpc_show_auth_stat(__entry->auth_stat)) ); TRACE_EVENT(svc_process, @@ -1680,7 +1707,6 @@ TRACE_EVENT(svc_process, ); DECLARE_EVENT_CLASS(svc_rqst_event, - TP_PROTO( const struct svc_rqst *rqst ), @@ -1688,20 +1714,20 @@ DECLARE_EVENT_CLASS(svc_rqst_event, TP_ARGS(rqst), TP_STRUCT__entry( - __field(u32, xid) + SVC_RQST_ENDPOINT_FIELDS(rqst) + __field(unsigned long, flags) - __string(addr, rqst->rq_xprt->xpt_remotebuf) ), TP_fast_assign( - __entry->xid = be32_to_cpu(rqst->rq_xid); + SVC_RQST_ENDPOINT_ASSIGNMENTS(rqst); + __entry->flags = rqst->rq_flags; - __assign_str(addr, rqst->rq_xprt->xpt_remotebuf); ), - TP_printk("addr=%s xid=0x%08x flags=%s", - __get_str(addr), __entry->xid, - show_rqstp_flags(__entry->flags)) + TP_printk(SVC_RQST_ENDPOINT_FORMAT " flags=%s", + SVC_RQST_ENDPOINT_VARARGS, + show_rqstp_flags(__entry->flags)) ); #define DEFINE_SVC_RQST_EVENT(name) \ DEFINE_EVENT(svc_rqst_event, svc_##name, \ @@ -1714,34 +1740,63 @@ DEFINE_SVC_RQST_EVENT(defer); DEFINE_SVC_RQST_EVENT(drop); DECLARE_EVENT_CLASS(svc_rqst_status, - - TP_PROTO(struct svc_rqst *rqst, int status), + TP_PROTO( + const struct svc_rqst *rqst, + int status + ), TP_ARGS(rqst, status), TP_STRUCT__entry( - __field(u32, xid) + SVC_RQST_ENDPOINT_FIELDS(rqst) + __field(int, status) __field(unsigned long, flags) - __string(addr, rqst->rq_xprt->xpt_remotebuf) ), TP_fast_assign( - __entry->xid = be32_to_cpu(rqst->rq_xid); + SVC_RQST_ENDPOINT_ASSIGNMENTS(rqst); + __entry->status = status; __entry->flags = rqst->rq_flags; - __assign_str(addr, rqst->rq_xprt->xpt_remotebuf); ), - TP_printk("addr=%s xid=0x%08x status=%d flags=%s", - __get_str(addr), __entry->xid, - __entry->status, show_rqstp_flags(__entry->flags)) + TP_printk(SVC_RQST_ENDPOINT_FORMAT " status=%d flags=%s", + SVC_RQST_ENDPOINT_VARARGS, + __entry->status, show_rqstp_flags(__entry->flags)) ); DEFINE_EVENT(svc_rqst_status, svc_send, - TP_PROTO(struct svc_rqst *rqst, int status), + TP_PROTO(const struct svc_rqst *rqst, int status), TP_ARGS(rqst, status)); +TRACE_EVENT(svc_stats_latency, + TP_PROTO( + const struct svc_rqst *rqst + ), + + TP_ARGS(rqst), + + TP_STRUCT__entry( + SVC_RQST_ENDPOINT_FIELDS(rqst) + + __field(unsigned long, execute) + __string(procedure, svc_proc_name(rqst)) + ), + + TP_fast_assign( + SVC_RQST_ENDPOINT_ASSIGNMENTS(rqst); + + __entry->execute = ktime_to_us(ktime_sub(ktime_get(), + rqst->rq_stime)); + __assign_str(procedure, svc_proc_name(rqst)); + ), + + TP_printk(SVC_RQST_ENDPOINT_FORMAT " proc=%s execute-us=%lu", + SVC_RQST_ENDPOINT_VARARGS, + __get_str(procedure), __entry->execute) +); + #define show_svc_xprt_flags(flags) \ __print_flags(flags, "|", \ { (1UL << XPT_BUSY), "XPT_BUSY"}, \ @@ -1952,31 +2007,6 @@ TRACE_EVENT(svc_alloc_arg_err, TP_printk("pages=%u", __entry->pages) ); -TRACE_EVENT(svc_stats_latency, - TP_PROTO(const struct svc_rqst *rqst), - - TP_ARGS(rqst), - - TP_STRUCT__entry( - __field(u32, xid) - __field(unsigned long, execute) - __string(procedure, svc_proc_name(rqst)) - __string(addr, rqst->rq_xprt->xpt_remotebuf) - ), - - TP_fast_assign( - __entry->xid = be32_to_cpu(rqst->rq_xid); - __entry->execute = ktime_to_us(ktime_sub(ktime_get(), - rqst->rq_stime)); - __assign_str(procedure, svc_proc_name(rqst)); - __assign_str(addr, rqst->rq_xprt->xpt_remotebuf); - ), - - TP_printk("addr=%s xid=0x%08x proc=%s execute-us=%lu", - __get_str(addr), __entry->xid, __get_str(procedure), - __entry->execute) -); - DECLARE_EVENT_CLASS(svc_deferred_event, TP_PROTO( const struct svc_deferred_req *dr -- cgit v1.2.3 From a9ff2e99e9fa501ec965da03c18a5422b37a2f44 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 25 Jan 2022 10:17:59 -0500 Subject: SUNRPC: Remove the .svo_enqueue_xprt method We have never been able to track down and address the underlying cause of the performance issues with workqueue-based service support. svo_enqueue_xprt is called multiple times per RPC, so it adds instruction path length, but always ends up at the same function: svc_xprt_do_enqueue(). We do not anticipate needing this flexibility for dynamic nfsd thread management support. As a micro-optimization, remove .svo_enqueue_xprt because Spectre/Meltdown makes virtual function calls more costly. This change essentially reverts commit b9e13cdfac70 ("nfsd/sunrpc: turn enqueueing a svc_xprt into a svc_serv operation"). Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 3 --- include/linux/sunrpc/svc_xprt.h | 1 - 2 files changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index f35c22b3355f..6ef9c1cafd0b 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -61,9 +61,6 @@ struct svc_serv_ops { /* function for service threads to run */ int (*svo_function)(void *); - /* queue up a transport for servicing */ - void (*svo_enqueue_xprt)(struct svc_xprt *); - /* optional module to count when adding threads. * Thread function must call module_put_and_kthread_exit() to exit. */ diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 571f605bc91e..a3ba027fb4ba 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -131,7 +131,6 @@ int svc_create_xprt(struct svc_serv *, const char *, struct net *, const int, const unsigned short, int, const struct cred *); void svc_xprt_received(struct svc_xprt *xprt); -void svc_xprt_do_enqueue(struct svc_xprt *xprt); void svc_xprt_enqueue(struct svc_xprt *xprt); void svc_xprt_put(struct svc_xprt *xprt); void svc_xprt_copy_addrs(struct svc_rqst *rqstp, struct svc_xprt *xprt); -- cgit v1.2.3 From 87cdd8641c8a1ec6afd2468265e20840a57fd888 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 25 Jan 2022 13:49:29 -0500 Subject: SUNRPC: Remove svo_shutdown method Clean up. Neil observed that "any code that calls svc_shutdown_net() knows what the shutdown function should be, and so can call it directly." Signed-off-by: Chuck Lever Reviewed-by: NeilBrown --- include/linux/sunrpc/svc.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 6ef9c1cafd0b..63794d772eb3 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -55,9 +55,6 @@ struct svc_pool { struct svc_serv; struct svc_serv_ops { - /* Callback to use when last thread exits. */ - void (*svo_shutdown)(struct svc_serv *, struct net *); - /* function for service threads to run */ int (*svo_function)(void *); -- cgit v1.2.3 From 352ad31448fecc78a2e9b78da64eea5d63b8d0ce Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 26 Jan 2022 11:42:08 -0500 Subject: SUNRPC: Rename svc_create_xprt() Clean up: Use the "svc_xprt_" function naming convention as is used for other external APIs. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_xprt.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index a3ba027fb4ba..a7f6f17c3dc5 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -127,9 +127,10 @@ int svc_reg_xprt_class(struct svc_xprt_class *); void svc_unreg_xprt_class(struct svc_xprt_class *); void svc_xprt_init(struct net *, struct svc_xprt_class *, struct svc_xprt *, struct svc_serv *); -int svc_create_xprt(struct svc_serv *, const char *, struct net *, - const int, const unsigned short, int, - const struct cred *); +int svc_xprt_create(struct svc_serv *serv, const char *xprt_name, + struct net *net, const int family, + const unsigned short port, int flags, + const struct cred *cred); void svc_xprt_received(struct svc_xprt *xprt); void svc_xprt_enqueue(struct svc_xprt *xprt); void svc_xprt_put(struct svc_xprt *xprt); -- cgit v1.2.3 From 4355d767a21b9445958fc11bce9a9701f76529d3 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 31 Jan 2022 13:34:29 -0500 Subject: SUNRPC: Rename svc_close_xprt() Clean up: Use the "svc_xprt_" function naming convention as is used for other external APIs. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_xprt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index a7f6f17c3dc5..bf7d029fb48c 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -135,7 +135,7 @@ void svc_xprt_received(struct svc_xprt *xprt); void svc_xprt_enqueue(struct svc_xprt *xprt); void svc_xprt_put(struct svc_xprt *xprt); void svc_xprt_copy_addrs(struct svc_rqst *rqstp, struct svc_xprt *xprt); -void svc_close_xprt(struct svc_xprt *xprt); +void svc_xprt_close(struct svc_xprt *xprt); int svc_port_is_privileged(struct sockaddr *sin); int svc_print_xprts(char *buf, int maxlen); struct svc_xprt *svc_find_xprt(struct svc_serv *serv, const char *xcl_name, -- cgit v1.2.3 From c7d7ec8f043e53ad16e30f5ebb8b9df415ec0f2b Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 26 Jan 2022 11:30:55 -0500 Subject: SUNRPC: Remove svc_shutdown_net() Clean up: svc_shutdown_net() now does nothing but call svc_close_net(). Replace all external call sites. svc_close_net() is renamed to be the inverse of svc_xprt_create(). Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 1 - include/linux/sunrpc/svc_xprt.h | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 63794d772eb3..5603158b2aa7 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -508,7 +508,6 @@ struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, const struct svc_serv_ops *); int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); int svc_pool_stats_open(struct svc_serv *serv, struct file *file); -void svc_shutdown_net(struct svc_serv *, struct net *); int svc_process(struct svc_rqst *); int bc_svc_process(struct svc_serv *, struct rpc_rqst *, struct svc_rqst *); diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index bf7d029fb48c..42e113742429 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -131,6 +131,7 @@ int svc_xprt_create(struct svc_serv *serv, const char *xprt_name, struct net *net, const int family, const unsigned short port, int flags, const struct cred *cred); +void svc_xprt_destroy_all(struct svc_serv *serv, struct net *net); void svc_xprt_received(struct svc_xprt *xprt); void svc_xprt_enqueue(struct svc_xprt *xprt); void svc_xprt_put(struct svc_xprt *xprt); -- cgit v1.2.3 From f49169c97fceb21ad6a0aaf671c50b0f520f15a5 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 16 Feb 2022 12:31:09 -0500 Subject: NFSD: Remove svc_serv_ops::svo_module struct svc_serv_ops is about to be removed. Neil Brown says: > I suspect svo_module can go as well - I don't think the thread is > ever the thing that primarily keeps a module active. A random sample of kthread_create() callers shows sunrpc is the only one that manages module reference count in this way. Suggested-by: Neil Brown Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 5603158b2aa7..dfc9283f412f 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -57,11 +57,6 @@ struct svc_serv; struct svc_serv_ops { /* function for service threads to run */ int (*svo_function)(void *); - - /* optional module to count when adding threads. - * Thread function must call module_put_and_kthread_exit() to exit. - */ - struct module *svo_module; }; /* -- cgit v1.2.3 From 37902c6313090235c847af89c5515591261ee338 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 16 Feb 2022 12:16:27 -0500 Subject: NFSD: Move svc_serv_ops::svo_function into struct svc_serv Hoist svo_function back into svc_serv and remove struct svc_serv_ops, since the struct is now devoid of fields. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index dfc9283f412f..a5dda4987e8b 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -52,13 +52,6 @@ struct svc_pool { unsigned long sp_flags; } ____cacheline_aligned_in_smp; -struct svc_serv; - -struct svc_serv_ops { - /* function for service threads to run */ - int (*svo_function)(void *); -}; - /* * RPC service. * @@ -91,7 +84,8 @@ struct svc_serv { unsigned int sv_nrpools; /* number of thread pools */ struct svc_pool * sv_pools; /* array of thread pools */ - const struct svc_serv_ops *sv_ops; /* server operations */ + int (*sv_threadfn)(void *data); + #if defined(CONFIG_SUNRPC_BACKCHANNEL) struct list_head sv_cb_list; /* queue for callback requests * that arrive over the same @@ -492,7 +486,7 @@ int svc_rpcb_setup(struct svc_serv *serv, struct net *net); void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net); int svc_bind(struct svc_serv *serv, struct net *net); struct svc_serv *svc_create(struct svc_program *, unsigned int, - const struct svc_serv_ops *); + int (*threadfn)(void *data)); struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node); void svc_rqst_replace_page(struct svc_rqst *rqstp, @@ -500,7 +494,7 @@ void svc_rqst_replace_page(struct svc_rqst *rqstp, void svc_rqst_free(struct svc_rqst *); void svc_exit_thread(struct svc_rqst *); struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, - const struct svc_serv_ops *); + int (*threadfn)(void *data)); int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); int svc_pool_stats_open(struct svc_serv *serv, struct file *file); int svc_process(struct svc_rqst *); -- cgit v1.2.3 From 74aaf96feaca80285912cc6f19575b3e97177918 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 22 Feb 2022 13:10:52 -0500 Subject: SUNRPC: Teach server to recognize RPC_AUTH_TLS Initial support for the RPC_AUTH_TLS authentication flavor enables NFSD to eventually accept an RPC_AUTH_TLS probe from clients. This patch simply prevents NFSD from rejecting these probes completely. In the meantime, graft this support in now so that RPC_AUTH_TLS support keeps up with generic code and API changes in the RPC server. Down the road, server-side transport implementations will populate xpo_start_tls when they can support RPC-with-TLS. For example, TCP will eventually populate it, but RDMA won't. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 42e113742429..20068ccfd0cc 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -28,6 +28,7 @@ struct svc_xprt_ops { void (*xpo_free)(struct svc_xprt *); void (*xpo_secure_port)(struct svc_rqst *rqstp); void (*xpo_kill_temp_xprt)(struct svc_xprt *); + void (*xpo_start_tls)(struct svc_xprt *); }; struct svc_xprt_class { -- cgit v1.2.3 From 797bd4d41c8b41afc10fad39146ac9558cb39e94 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 24 Feb 2022 10:55:54 +0100 Subject: tty: serial: define UART_LCR_WLEN() macro Define a generic UART_LCR_WLEN() macro with a size argument. It can be used to encode byte size into an LCR value. Therefore we can use it to simplify the drivers using tty_get_char_size() in the next patches. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20220224095558.30929-1-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/serial.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/serial.h b/include/linux/serial.h index 0916107c77f9..0b8b7d7c8f33 100644 --- a/include/linux/serial.h +++ b/include/linux/serial.h @@ -12,6 +12,8 @@ #include #include +/* Helper for dealing with UART_LCR_WLEN* defines */ +#define UART_LCR_WLEN(x) ((x) - 5) /* * Counters of the input lines (CTS, DSR, RI, CD) interrupts -- cgit v1.2.3 From dcfd5192563909219f6304b4e3e10db071158eef Mon Sep 17 00:00:00 2001 From: Alyssa Rosenzweig Date: Tue, 15 Feb 2022 13:46:51 -0500 Subject: soc: mediatek: mtk-infracfg: Disable ACP on MT8192 MT8192 contains an experimental Accelerator Coherency Port implementation, which does not work correctly but was unintentionally enabled by default. For correct operation of the GPU, we must set a chicken bit disabling ACP on MT8192. Adapted from the following downstream change to the out-of-tree, legacy Mali GPU driver: https://chromium-review.googlesource.com/c/chromiumos/third_party/kernel/+/2781271/5 Note this change is required for both Panfrost and the legacy kernel driver. Co-developed-by: Robin Murphy Signed-off-by: Robin Murphy Signed-off-by: Alyssa Rosenzweig Cc: Nick Fan Cc: Nicolas Boichat Cc: Chen-Yu Tsai Cc: Stephen Boyd Cc: AngeloGioacchino Del Regno Tested-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20220215184651.12168-1-alyssa.rosenzweig@collabora.com Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/infracfg.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/soc/mediatek/infracfg.h b/include/linux/soc/mediatek/infracfg.h index 8a1c2040a28e..50804ac748bd 100644 --- a/include/linux/soc/mediatek/infracfg.h +++ b/include/linux/soc/mediatek/infracfg.h @@ -277,6 +277,9 @@ #define INFRA_TOPAXI_PROTECTEN_SET 0x0260 #define INFRA_TOPAXI_PROTECTEN_CLR 0x0264 +#define MT8192_INFRA_CTRL 0x290 +#define MT8192_INFRA_CTRL_DISABLE_MFG2ACP BIT(9) + #define REG_INFRA_MISC 0xf00 #define F_DDR_4GB_SUPPORT_EN BIT(13) -- cgit v1.2.3 From 7b8135f4df98b155b23754b6065c157861e268f1 Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Tue, 1 Mar 2022 05:04:34 +0000 Subject: rtnetlink: add new rtm tunnel api for tunnel id filtering This patch adds new rtm tunnel msg and api for tunnel id filtering in dst_metadata devices. First dst_metadata device to use the api is vxlan driver with AF_BRIDGE family. This and later changes add ability in vxlan driver to do tunnel id filtering (or vni filtering) on dst_metadata devices. This is similar to vlan api in the vlan filtering bridge. this patch includes selinux nlmsg_route_perms support for RTM_*TUNNEL api from Benjamin Poirier. Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 26 ++++++++++++++++++++++++++ include/uapi/linux/rtnetlink.h | 9 +++++++++ 2 files changed, 35 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index be09d2ad4b5d..3dfc9ff2ec9b 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -713,7 +713,32 @@ enum ipvlan_mode { #define IPVLAN_F_PRIVATE 0x01 #define IPVLAN_F_VEPA 0x02 +/* Tunnel RTM header */ +struct tunnel_msg { + __u8 family; + __u8 reserved1; + __u16 reserved2; + __u32 ifindex; +}; + /* VXLAN section */ +enum { + VXLAN_VNIFILTER_ENTRY_UNSPEC, + VXLAN_VNIFILTER_ENTRY_START, + VXLAN_VNIFILTER_ENTRY_END, + VXLAN_VNIFILTER_ENTRY_GROUP, + VXLAN_VNIFILTER_ENTRY_GROUP6, + __VXLAN_VNIFILTER_ENTRY_MAX +}; +#define VXLAN_VNIFILTER_ENTRY_MAX (__VXLAN_VNIFILTER_ENTRY_MAX - 1) + +enum { + VXLAN_VNIFILTER_UNSPEC, + VXLAN_VNIFILTER_ENTRY, + __VXLAN_VNIFILTER_MAX +}; +#define VXLAN_VNIFILTER_MAX (__VXLAN_VNIFILTER_MAX - 1) + enum { IFLA_VXLAN_UNSPEC, IFLA_VXLAN_ID, @@ -745,6 +770,7 @@ enum { IFLA_VXLAN_GPE, IFLA_VXLAN_TTL_INHERIT, IFLA_VXLAN_DF, + IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */ __IFLA_VXLAN_MAX }; #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 93d934cc4613..0970cb4b1b88 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -185,6 +185,13 @@ enum { RTM_GETNEXTHOPBUCKET, #define RTM_GETNEXTHOPBUCKET RTM_GETNEXTHOPBUCKET + RTM_NEWTUNNEL = 120, +#define RTM_NEWTUNNEL RTM_NEWTUNNEL + RTM_DELTUNNEL, +#define RTM_DELTUNNEL RTM_DELTUNNEL + RTM_GETTUNNEL, +#define RTM_GETTUNNEL RTM_GETTUNNEL + __RTM_MAX, #define RTM_MAX (((__RTM_MAX + 3) & ~3) - 1) }; @@ -756,6 +763,8 @@ enum rtnetlink_groups { #define RTNLGRP_BRVLAN RTNLGRP_BRVLAN RTNLGRP_MCTP_IFADDR, #define RTNLGRP_MCTP_IFADDR RTNLGRP_MCTP_IFADDR + RTNLGRP_TUNNEL, +#define RTNLGRP_TUNNEL RTNLGRP_TUNNEL __RTNLGRP_MAX }; #define RTNLGRP_MAX (__RTNLGRP_MAX - 1) -- cgit v1.2.3 From f9c4bb0b245cee35ef66f75bf409c9573d934cf9 Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Tue, 1 Mar 2022 05:04:36 +0000 Subject: vxlan: vni filtering support on collect metadata device MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds vnifiltering support to collect metadata device. Motivation: You can only use a single vxlan collect metadata device for a given vxlan udp port in the system today. The vxlan collect metadata device terminates all received vxlan packets. As shown in the below diagram, there are use-cases where you need to support multiple such vxlan devices in independent bridge domains. Each vxlan device must terminate the vni's it is configured for. Example usecase: In a service provider network a service provider typically supports multiple bridge domains with overlapping vlans. One bridge domain per customer. Vlans in each bridge domain are mapped to globally unique vxlan ranges assigned to each customer. vnifiltering support in collect metadata devices terminates only configured vnis. This is similar to vlan filtering in bridge driver. The vni filtering capability is provided by a new flag on collect metadata device. In the below pic: - customer1 is mapped to br1 bridge domain - customer2 is mapped to br2 bridge domain - customer1 vlan 10-11 is mapped to vni 1001-1002 - customer2 vlan 10-11 is mapped to vni 2001-2002 - br1 and br2 are vlan filtering bridges - vxlan1 and vxlan2 are collect metadata devices with vnifiltering enabled ┌──────────────────────────────────────────────────────────────────┐ │ switch │ │ │ │ ┌───────────┐ ┌───────────┐ │ │ │ │ │ │ │ │ │ br1 │ │ br2 │ │ │ └┬─────────┬┘ └──┬───────┬┘ │ │ vlans│ │ vlans │ │ │ │ 10,11│ │ 10,11│ │ │ │ │ vlanvnimap: │ vlanvnimap: │ │ │ 10-1001,11-1002 │ 10-2001,11-2002 │ │ │ │ │ │ │ │ ┌──────┴┐ ┌──┴─────────┐ ┌───┴────┐ │ │ │ │ swp1 │ │vxlan1 │ │ swp2 │ ┌┴─────────────┐ │ │ │ │ │ vnifilter:│ │ │ │vxlan2 │ │ │ └───┬───┘ │ 1001,1002│ └───┬────┘ │ vnifilter: │ │ │ │ └────────────┘ │ │ 2001,2002 │ │ │ │ │ └──────────────┘ │ │ │ │ │ └───────┼──────────────────────────────────┼───────────────────────┘ │ │ │ │ ┌─────┴───────┐ │ │ customer1 │ ┌─────┴──────┐ │ host/VM │ │customer2 │ └─────────────┘ │ host/VM │ └────────────┘ With this implementation, vxlan dst metadata device can be associated with range of vnis. struct vxlan_vni_node is introduced to represent a configured vni. We start with vni and its associated remote_ip in this structure. This structure can be extended to bring in other per vni attributes if there are usecases for it. A vni inherits an attribute from the base vxlan device if there is no per vni attributes defined. struct vxlan_dev gets a new rhashtable for vnis called vxlan_vni_group. vxlan_vnifilter.c implements the necessary netlink api, notifications and helper functions to process and manage lifecycle of vxlan_vni_node. This patch also adds new helper functions in vxlan_multicast.c to handle per vni remote_ip multicast groups which are part of vxlan_vni_group. Fix build problems: Reported-by: kernel test robot Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/net/vxlan.h | 28 ++++++++++++++++++++++++++-- 1 file changed, 26 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 5a934bebe630..8eb961bb9589 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -232,6 +232,25 @@ struct vxlan_dev_node { struct vxlan_dev *vxlan; }; +struct vxlan_vni_node { + struct rhash_head vnode; + struct vxlan_dev_node hlist4; /* vni hash table for IPv4 socket */ +#if IS_ENABLED(CONFIG_IPV6) + struct vxlan_dev_node hlist6; /* vni hash table for IPv6 socket */ +#endif + struct list_head vlist; + __be32 vni; + union vxlan_addr remote_ip; /* default remote ip for this vni */ + + struct rcu_head rcu; +}; + +struct vxlan_vni_group { + struct rhashtable vni_hash; + struct list_head vni_list; + u32 num_vnis; +}; + /* Pseudo network device */ struct vxlan_dev { struct vxlan_dev_node hlist4; /* vni hash table for IPv4 socket */ @@ -254,6 +273,8 @@ struct vxlan_dev { struct vxlan_config cfg; + struct vxlan_vni_group __rcu *vnigrp; + struct hlist_head fdb_head[FDB_HASH_SIZE]; }; @@ -274,6 +295,7 @@ struct vxlan_dev { #define VXLAN_F_GPE 0x4000 #define VXLAN_F_IPV6_LINKLOCAL 0x8000 #define VXLAN_F_TTL_INHERIT 0x10000 +#define VXLAN_F_VNIFILTER 0x20000 /* Flags that are used in the receive path. These flags must match in * order for a socket to be shareable @@ -283,7 +305,8 @@ struct vxlan_dev { VXLAN_F_UDP_ZERO_CSUM6_RX | \ VXLAN_F_REMCSUM_RX | \ VXLAN_F_REMCSUM_NOPARTIAL | \ - VXLAN_F_COLLECT_METADATA) + VXLAN_F_COLLECT_METADATA | \ + VXLAN_F_VNIFILTER) /* Flags that can be set together with VXLAN_F_GPE. */ #define VXLAN_F_ALLOWED_GPE (VXLAN_F_GPE | \ @@ -292,7 +315,8 @@ struct vxlan_dev { VXLAN_F_UDP_ZERO_CSUM_TX | \ VXLAN_F_UDP_ZERO_CSUM6_TX | \ VXLAN_F_UDP_ZERO_CSUM6_RX | \ - VXLAN_F_COLLECT_METADATA) + VXLAN_F_COLLECT_METADATA | \ + VXLAN_F_VNIFILTER) struct net_device *vxlan_dev_create(struct net *net, const char *name, u8 name_assign_type, struct vxlan_config *conf); -- cgit v1.2.3 From 4095e0e1328a3cd9e3b30174d6cb0edb3824256d Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 1 Mar 2022 05:04:38 +0000 Subject: drivers: vxlan: vnifilter: per vni stats Add per-vni statistics for vni filter mode. Counting Rx/Tx bytes/packets/drops/errors at the appropriate places. This patch changes vxlan_vs_find_vni to also return the vxlan_vni_node in cases where the vni belongs to a vni filtering vxlan device Signed-off-by: Nikolay Aleksandrov Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/net/vxlan.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include') diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 8eb961bb9589..bca5b01af247 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -227,6 +227,31 @@ struct vxlan_config { enum ifla_vxlan_df df; }; +enum { + VXLAN_VNI_STATS_RX, + VXLAN_VNI_STATS_RX_DROPS, + VXLAN_VNI_STATS_RX_ERRORS, + VXLAN_VNI_STATS_TX, + VXLAN_VNI_STATS_TX_DROPS, + VXLAN_VNI_STATS_TX_ERRORS, +}; + +struct vxlan_vni_stats { + u64 rx_packets; + u64 rx_bytes; + u64 rx_drops; + u64 rx_errors; + u64 tx_packets; + u64 tx_bytes; + u64 tx_drops; + u64 tx_errors; +}; + +struct vxlan_vni_stats_pcpu { + struct vxlan_vni_stats stats; + struct u64_stats_sync syncp; +}; + struct vxlan_dev_node { struct hlist_node hlist; struct vxlan_dev *vxlan; @@ -241,6 +266,7 @@ struct vxlan_vni_node { struct list_head vlist; __be32 vni; union vxlan_addr remote_ip; /* default remote ip for this vni */ + struct vxlan_vni_stats_pcpu __percpu *stats; struct rcu_head rcu; }; -- cgit v1.2.3 From 445b2f36bb4efb81f064e931f28b9ec19f114355 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 1 Mar 2022 05:04:39 +0000 Subject: drivers: vxlan: vnifilter: add support for stats dumping Add support for VXLAN vni filter entries' stats dumping Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 3dfc9ff2ec9b..e315e53125f4 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -716,18 +716,41 @@ enum ipvlan_mode { /* Tunnel RTM header */ struct tunnel_msg { __u8 family; - __u8 reserved1; + __u8 flags; __u16 reserved2; __u32 ifindex; }; /* VXLAN section */ + +/* include statistics in the dump */ +#define TUNNEL_MSG_FLAG_STATS 0x01 + +#define TUNNEL_MSG_VALID_USER_FLAGS TUNNEL_MSG_FLAG_STATS + +/* Embedded inside VXLAN_VNIFILTER_ENTRY_STATS */ +enum { + VNIFILTER_ENTRY_STATS_UNSPEC, + VNIFILTER_ENTRY_STATS_RX_BYTES, + VNIFILTER_ENTRY_STATS_RX_PKTS, + VNIFILTER_ENTRY_STATS_RX_DROPS, + VNIFILTER_ENTRY_STATS_RX_ERRORS, + VNIFILTER_ENTRY_STATS_TX_BYTES, + VNIFILTER_ENTRY_STATS_TX_PKTS, + VNIFILTER_ENTRY_STATS_TX_DROPS, + VNIFILTER_ENTRY_STATS_TX_ERRORS, + VNIFILTER_ENTRY_STATS_PAD, + __VNIFILTER_ENTRY_STATS_MAX +}; +#define VNIFILTER_ENTRY_STATS_MAX (__VNIFILTER_ENTRY_STATS_MAX - 1) + enum { VXLAN_VNIFILTER_ENTRY_UNSPEC, VXLAN_VNIFILTER_ENTRY_START, VXLAN_VNIFILTER_ENTRY_END, VXLAN_VNIFILTER_ENTRY_GROUP, VXLAN_VNIFILTER_ENTRY_GROUP6, + VXLAN_VNIFILTER_ENTRY_STATS, __VXLAN_VNIFILTER_ENTRY_MAX }; #define VXLAN_VNIFILTER_ENTRY_MAX (__VXLAN_VNIFILTER_ENTRY_MAX - 1) -- cgit v1.2.3 From 2f6f66ccd21e854cd3743bc8def68f8b4e7d91fc Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 25 Feb 2022 18:22:44 +0000 Subject: KVM: Drop kvm_reload_remote_mmus(), open code request in x86 users Remove the generic kvm_reload_remote_mmus() and open code its functionality into the two x86 callers. x86 is (obviously) the only architecture that uses the hook, and is also the only architecture that uses KVM_REQ_MMU_RELOAD in a way that's consistent with the name. That will change in a future patch, as x86's usage when zapping a single shadow page x86 doesn't actually _need_ to reload all vCPUs' MMUs, only MMUs whose root is being zapped actually need to be reloaded. s390 also uses KVM_REQ_MMU_RELOAD, but for a slightly different purpose. Drop the generic code in anticipation of implementing s390 and x86 arch specific requests, which will allow dropping KVM_REQ_MMU_RELOAD entirely. Opportunistically reword the x86 TDP MMU comment to avoid making references to functions (and requests!) when possible, and to remove the rather ambiguous "this". No functional change intended. Cc: Ben Gardon Signed-off-by: Sean Christopherson Reviewed-by: Ben Gardon Message-Id: <20220225182248.3812651-4-seanjc@google.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f11039944c08..0aeb47cffd43 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1325,7 +1325,6 @@ int kvm_vcpu_yield_to(struct kvm_vcpu *target); void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool usermode_vcpu_not_eligible); void kvm_flush_remote_tlbs(struct kvm *kvm); -void kvm_reload_remote_mmus(struct kvm *kvm); #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min); -- cgit v1.2.3 From e65a3b46b5b1fab92c3273bcf71e028a4d307400 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 25 Feb 2022 18:22:47 +0000 Subject: KVM: Drop KVM_REQ_MMU_RELOAD and update vcpu-requests.rst documentation Remove the now unused KVM_REQ_MMU_RELOAD, shift KVM_REQ_VM_DEAD into the unoccupied space, and update vcpu-requests.rst, which was missing an entry for KVM_REQ_VM_DEAD. Switching KVM_REQ_VM_DEAD to entry '1' also fixes the stale comment about bits 4-7 being reserved. Reviewed-by: Claudio Imbrenda Signed-off-by: Sean Christopherson Reviewed-by: Ben Gardon Message-Id: <20220225182248.3812651-7-seanjc@google.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 0aeb47cffd43..9536ffa0473b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -153,10 +153,9 @@ static inline bool is_error_page(struct page *page) * Bits 4-7 are reserved for more arch-independent bits. */ #define KVM_REQ_TLB_FLUSH (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) -#define KVM_REQ_MMU_RELOAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_VM_DEAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_UNBLOCK 2 #define KVM_REQ_UNHALT 3 -#define KVM_REQ_VM_DEAD (4 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_GPC_INVALIDATE (5 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQUEST_ARCH_BASE 8 -- cgit v1.2.3 From 462791bbfa350189e309a5a94541f6b63cd874e8 Mon Sep 17 00:00:00 2001 From: Dust Li Date: Tue, 1 Mar 2022 17:43:56 +0800 Subject: net/smc: add sysctl interface for SMC This patch add sysctl interface to support container environment for SMC as we talk in the mail list. Link: https://lore.kernel.org/netdev/20220224020253.GF5443@linux.alibaba.com Co-developed-by: Tony Lu Signed-off-by: Tony Lu Signed-off-by: Dust Li Signed-off-by: David S. Miller --- include/net/netns/smc.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/netns/smc.h b/include/net/netns/smc.h index 47b166684fd8..1682eae50579 100644 --- a/include/net/netns/smc.h +++ b/include/net/netns/smc.h @@ -14,5 +14,8 @@ struct netns_smc { struct smc_stats_rsn *fback_rsn; bool limit_smc_hs; /* constraint on handshake */ +#ifdef CONFIG_SYSCTL + struct ctl_table_header *smc_hdr; +#endif }; #endif -- cgit v1.2.3 From 12bbb0d163a90d81a2677cf7808d364697290207 Mon Sep 17 00:00:00 2001 From: Dust Li Date: Tue, 1 Mar 2022 17:43:58 +0800 Subject: net/smc: add sysctl for autocorking This add a new sysctl: net.smc.autocorking_size We can dynamically change the behaviour of autocorking by change the value of autocorking_size. Setting to 0 disables autocorking in SMC Signed-off-by: Dust Li Signed-off-by: David S. Miller --- include/net/netns/smc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netns/smc.h b/include/net/netns/smc.h index 1682eae50579..e5389eeaf8bd 100644 --- a/include/net/netns/smc.h +++ b/include/net/netns/smc.h @@ -17,5 +17,6 @@ struct netns_smc { #ifdef CONFIG_SYSCTL struct ctl_table_header *smc_hdr; #endif + unsigned int sysctl_autocorking_size; }; #endif -- cgit v1.2.3 From e45f1c1d70cae0d7a28ad60f9c6391e210354f0b Mon Sep 17 00:00:00 2001 From: Georgi Djakov Date: Tue, 1 Mar 2022 11:07:35 +0200 Subject: interconnect: Add stubs for the bulk API Add stub functions for the bulk API to allow compile testing. Reviewed-by: Alex Elder Link: https://lore.kernel.org/r/20220301090735.26599-1-djakov@kernel.org Signed-off-by: Georgi Djakov --- include/linux/interconnect.h | 36 +++++++++++++++++++++++++++++------- 1 file changed, 29 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/interconnect.h b/include/linux/interconnect.h index f2dd2fc8d3cd..f685777b875e 100644 --- a/include/linux/interconnect.h +++ b/include/linux/interconnect.h @@ -38,13 +38,6 @@ struct icc_bulk_data { u32 peak_bw; }; -int __must_check of_icc_bulk_get(struct device *dev, int num_paths, - struct icc_bulk_data *paths); -void icc_bulk_put(int num_paths, struct icc_bulk_data *paths); -int icc_bulk_set_bw(int num_paths, const struct icc_bulk_data *paths); -int icc_bulk_enable(int num_paths, const struct icc_bulk_data *paths); -void icc_bulk_disable(int num_paths, const struct icc_bulk_data *paths); - #if IS_ENABLED(CONFIG_INTERCONNECT) struct icc_path *icc_get(struct device *dev, const int src_id, @@ -58,6 +51,12 @@ int icc_disable(struct icc_path *path); int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw); void icc_set_tag(struct icc_path *path, u32 tag); const char *icc_get_name(struct icc_path *path); +int __must_check of_icc_bulk_get(struct device *dev, int num_paths, + struct icc_bulk_data *paths); +void icc_bulk_put(int num_paths, struct icc_bulk_data *paths); +int icc_bulk_set_bw(int num_paths, const struct icc_bulk_data *paths); +int icc_bulk_enable(int num_paths, const struct icc_bulk_data *paths); +void icc_bulk_disable(int num_paths, const struct icc_bulk_data *paths); #else @@ -112,6 +111,29 @@ static inline const char *icc_get_name(struct icc_path *path) return NULL; } +static inline int of_icc_bulk_get(struct device *dev, int num_paths, struct icc_bulk_data *paths) +{ + return 0; +} + +static inline void icc_bulk_put(int num_paths, struct icc_bulk_data *paths) +{ +} + +static inline int icc_bulk_set_bw(int num_paths, const struct icc_bulk_data *paths) +{ + return 0; +} + +static inline int icc_bulk_enable(int num_paths, const struct icc_bulk_data *paths) +{ + return 0; +} + +static inline void icc_bulk_disable(int num_paths, const struct icc_bulk_data *paths) +{ +} + #endif /* CONFIG_INTERCONNECT */ #endif /* __LINUX_INTERCONNECT_H */ -- cgit v1.2.3 From 1c1813a743fe84d0dcf53743baa4edc1f74c44c8 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Thu, 3 Feb 2022 15:32:15 +0100 Subject: HID: core: statically allocate read buffers This is a preparation patch for rethinking the generic processing of HID reports. We can actually pre-allocate all of our memory instead of dynamically allocating/freeing it whenever we parse a report. Signed-off-by: Benjamin Tissoires Reviewed-by: Ping Cheng Acked-by: Peter Hutterer Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/hid.h b/include/linux/hid.h index 7487b0586fe6..3fbfe0986659 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -476,6 +476,7 @@ struct hid_field { unsigned report_count; /* number of this field in the report */ unsigned report_type; /* (input,output,feature) */ __s32 *value; /* last known value(s) */ + __s32 *new_value; /* newly read value(s) */ __s32 logical_minimum; __s32 logical_maximum; __s32 physical_minimum; -- cgit v1.2.3 From b79c1abae5e19726c5060749e4e7c9e426b045c8 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Thu, 3 Feb 2022 15:32:17 +0100 Subject: HID: core: split data fetching from processing in hid_input_field() This is a preparatory patch for being able to process the usages out of order. We split the retrieval of the data in a separate function and also split out the processing of the usages depending if the field is an array or a variable. No functional changes from this patch. Signed-off-by: Benjamin Tissoires Reviewed-by: Ping Cheng Acked-by: Peter Hutterer Signed-off-by: Jiri Kosina --- include/linux/hid.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/hid.h b/include/linux/hid.h index 3fbfe0986659..cf79eb3da465 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -342,7 +342,7 @@ struct hid_item { * HID device quirks. */ -/* +/* * Increase this if you need to configure more HID quirks at module load time */ #define MAX_USBHID_BOOT_QUIRKS 4 @@ -483,6 +483,7 @@ struct hid_field { __s32 physical_maximum; __s32 unit_exponent; unsigned unit; + bool ignored; /* this field is ignored in this event */ struct hid_report *report; /* associated report */ unsigned index; /* index into report->field[] */ /* hidinput data */ -- cgit v1.2.3 From 22f4b026c3ddd4b26c5baa202bd3ee38feaa2e9a Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Thu, 3 Feb 2022 15:32:21 +0100 Subject: HID: compute an ordered list of input fields to process This will be used in a later commit: we build a list of input fields (and usage_index) that is ordered based on a usage priority. Changing the usage priority allows to re-order the processed list, meaning that we can enforce some usages to be process before others. For instance, before processing InRange in the HID tablets, we need to know if we are using the eraser (side or button). Enforcing a higher (lower number) priority for Invert allows to force the input stack to process that field before. Signed-off-by: Benjamin Tissoires Reviewed-by: Ping Cheng Acked-by: Peter Hutterer Signed-off-by: Jiri Kosina --- include/linux/hid.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/hid.h b/include/linux/hid.h index cf79eb3da465..f25020c0d6b8 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -477,6 +477,7 @@ struct hid_field { unsigned report_type; /* (input,output,feature) */ __s32 *value; /* last known value(s) */ __s32 *new_value; /* newly read value(s) */ + __s32 *usages_priorities; /* priority of each usage when reading the report */ __s32 logical_minimum; __s32 logical_maximum; __s32 physical_minimum; @@ -493,13 +494,22 @@ struct hid_field { #define HID_MAX_FIELDS 256 +struct hid_field_entry { + struct list_head list; + struct hid_field *field; + unsigned int index; + __s32 priority; +}; + struct hid_report { struct list_head list; struct list_head hidinput_list; + struct list_head field_entry_list; /* ordered list of input fields */ unsigned int id; /* id of this report */ unsigned int type; /* report type */ unsigned int application; /* application usage for this report */ struct hid_field *field[HID_MAX_FIELDS]; /* fields of the report */ + struct hid_field_entry *field_entries; /* allocated memory of input field_entry */ unsigned maxfield; /* maximum valid field index */ unsigned size; /* size of the report (bits) */ struct hid_device *device; /* associated device */ -- cgit v1.2.3 From 048cddfd440583a07530774fe20c7d26d7378155 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Thu, 3 Feb 2022 15:32:23 +0100 Subject: HID: input: enforce Invert usage to be processed before InRange When a device exposes both Invert and InRange, Invert must be processed before InRange. If we keep the order of the device and we process them out of order, InRange will first set BTN_TOOL_PEN, and then Invert will set BTN_TOOL_RUBBER. Userspace knows how to deal with that situation, but fixing it in the kernel is now easier. Signed-off-by: Benjamin Tissoires Reviewed-by: Ping Cheng Acked-by: Peter Hutterer Signed-off-by: Jiri Kosina --- include/linux/hid.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/hid.h b/include/linux/hid.h index f25020c0d6b8..eaad0655b05c 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -477,7 +477,9 @@ struct hid_field { unsigned report_type; /* (input,output,feature) */ __s32 *value; /* last known value(s) */ __s32 *new_value; /* newly read value(s) */ - __s32 *usages_priorities; /* priority of each usage when reading the report */ + __s32 *usages_priorities; /* priority of each usage when reading the report + * bits 8-16 are reserved for hid-input usage + */ __s32 logical_minimum; __s32 logical_maximum; __s32 physical_minimum; -- cgit v1.2.3 From 87562fcd134214a68e58d0714b820f2f2da75b1f Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Thu, 3 Feb 2022 15:32:24 +0100 Subject: HID: input: remove the need for HID_QUIRK_INVERT HID_QUIRK_INVERT is kind of complex to deal with and was bogus. Furthermore, it didn't make sense to use a global per struct hid_device quirk for something dynamic as the current state. Store the current tool information in the report itself, and re-order the processing of the fields to enforce having all the tablet "state" fields before getting to In Range and other input fields. This way, we now have all the information whether a tool is present or not while processing In Range. This new behavior enforces that only one tool gets forwarded to userspace at the same time, and that if either eraser or invert is set, we enforce BTN_TOOL_RUBBER. Note that the release of the previous tool now happens in its own EV_SYN report so userspace doesn't get confused by having 2 tools. These changes are tested in the following hid-tools regression tests: https://gitlab.freedesktop.org/libevdev/hid-tools/-/merge_requests/127 Signed-off-by: Benjamin Tissoires Reviewed-by: Ping Cheng Acked-by: Peter Hutterer Signed-off-by: Jiri Kosina --- include/linux/hid.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/hid.h b/include/linux/hid.h index eaad0655b05c..feb8df61168f 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -347,7 +347,7 @@ struct hid_item { */ #define MAX_USBHID_BOOT_QUIRKS 4 -#define HID_QUIRK_INVERT BIT(0) +/* BIT(0) reserved for backward compatibility, was HID_QUIRK_INVERT */ #define HID_QUIRK_NOTOUCH BIT(1) #define HID_QUIRK_IGNORE BIT(2) #define HID_QUIRK_NOGET BIT(3) @@ -515,6 +515,10 @@ struct hid_report { unsigned maxfield; /* maximum valid field index */ unsigned size; /* size of the report (bits) */ struct hid_device *device; /* associated device */ + + /* tool related state */ + bool tool_active; /* whether the current tool is active */ + unsigned int tool; /* BTN_TOOL_* */ }; #define HID_MAX_IDS 256 -- cgit v1.2.3 From 5c20000a4756f57c824e3045c978ef19136a676d Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Thu, 3 Feb 2022 15:32:25 +0100 Subject: HID: input: accommodate priorities for slotted devices Multitouch devices in hybrid mode are reporting multiple times the same collection. We should accommodate for this in our handling of priorities by defining the slots they belong to. Signed-off-by: Benjamin Tissoires Reviewed-by: Ping Cheng Acked-by: Peter Hutterer Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/hid.h b/include/linux/hid.h index feb8df61168f..4363a63b9775 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -492,6 +492,7 @@ struct hid_field { /* hidinput data */ struct hid_input *hidinput; /* associated input structure */ __u16 dpad; /* dpad input code */ + unsigned int slot_idx; /* slot index in a report */ }; #define HID_MAX_FIELDS 256 -- cgit v1.2.3 From dc6e0818bc9a0336d9accf3ea35d146d72aa7a18 Mon Sep 17 00:00:00 2001 From: Chengming Zhou Date: Sun, 20 Feb 2022 13:14:25 +0800 Subject: sched/cpuacct: Optimize away RCU read lock Since cpuacct_charge() is called from the scheduler update_curr(), we must already have rq lock held, then the RCU read lock can be optimized away. And do the same thing in it's wrapper cgroup_account_cputime(), but we can't use lockdep_assert_rq_held() there, which defined in kernel/sched/sched.h. Suggested-by: Peter Zijlstra (Intel) Signed-off-by: Chengming Zhou Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220220051426.5274-2-zhouchengming@bytedance.com --- include/linux/cgroup.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 75c151413fda..9a109c6ac0e0 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -791,11 +791,9 @@ static inline void cgroup_account_cputime(struct task_struct *task, cpuacct_charge(task, delta_exec); - rcu_read_lock(); cgrp = task_dfl_cgroup(task); if (cgroup_parent(cgrp)) __cgroup_account_cputime(cgrp, delta_exec); - rcu_read_unlock(); } static inline void cgroup_account_cputime_field(struct task_struct *task, -- cgit v1.2.3 From 3eba0505d03a9c1eb30d40c2330c0880b22d1b3a Mon Sep 17 00:00:00 2001 From: Chengming Zhou Date: Sun, 20 Feb 2022 13:14:26 +0800 Subject: sched/cpuacct: Remove redundant RCU read lock The cpuacct_account_field() and it's cgroup v2 wrapper cgroup_account_cputime_field() is only called from cputime in task_group_account_field(), which is already in RCU read-side critical section. So remove these redundant RCU read lock. Suggested-by: Tejun Heo Signed-off-by: Chengming Zhou Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220220051426.5274-3-zhouchengming@bytedance.com --- include/linux/cgroup.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 9a109c6ac0e0..1e356c222756 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -804,11 +804,9 @@ static inline void cgroup_account_cputime_field(struct task_struct *task, cpuacct_account_field(task, index, delta_exec); - rcu_read_lock(); cgrp = task_dfl_cgroup(task); if (cgroup_parent(cgrp)) __cgroup_account_cputime_field(cgrp, index, delta_exec); - rcu_read_unlock(); } #else /* CONFIG_CGROUPS */ -- cgit v1.2.3 From fa2c3254d7cfff5f7a916ab928a562d1165f17bb Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Thu, 20 Jan 2022 16:25:19 +0000 Subject: sched/tracing: Don't re-read p->state when emitting sched_switch event As of commit c6e7bd7afaeb ("sched/core: Optimize ttwu() spinning on p->on_cpu") the following sequence becomes possible: p->__state = TASK_INTERRUPTIBLE; __schedule() deactivate_task(p); ttwu() READ !p->on_rq p->__state=TASK_WAKING trace_sched_switch() __trace_sched_switch_state() task_state_index() return 0; TASK_WAKING isn't in TASK_REPORT, so the task appears as TASK_RUNNING in the trace event. Prevent this by pushing the value read from __schedule() down the trace event. Reported-by: Abhijeet Dharmapurikar Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Steven Rostedt (Google) Link: https://lore.kernel.org/r/20220120162520.570782-2-valentin.schneider@arm.com --- include/linux/sched.h | 11 ++++++++--- include/trace/events/sched.h | 11 +++++++---- 2 files changed, 15 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index f00132e7ef6e..457c8a058b77 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1620,10 +1620,10 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) #define TASK_REPORT_IDLE (TASK_REPORT + 1) #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) -static inline unsigned int task_state_index(struct task_struct *tsk) +static inline unsigned int __task_state_index(unsigned int tsk_state, + unsigned int tsk_exit_state) { - unsigned int tsk_state = READ_ONCE(tsk->__state); - unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT; + unsigned int state = (tsk_state | tsk_exit_state) & TASK_REPORT; BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX); @@ -1633,6 +1633,11 @@ static inline unsigned int task_state_index(struct task_struct *tsk) return fls(state); } +static inline unsigned int task_state_index(struct task_struct *tsk) +{ + return __task_state_index(READ_ONCE(tsk->__state), tsk->exit_state); +} + static inline char task_index_to_char(unsigned int state) { static const char state_char[] = "RSDTtXZPI"; diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 94640482cfe7..65e786756321 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -187,7 +187,9 @@ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new, TP_ARGS(p)); #ifdef CREATE_TRACE_POINTS -static inline long __trace_sched_switch_state(bool preempt, struct task_struct *p) +static inline long __trace_sched_switch_state(bool preempt, + unsigned int prev_state, + struct task_struct *p) { unsigned int state; @@ -208,7 +210,7 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct * * it for left shift operation to get the correct task->state * mapping. */ - state = task_state_index(p); + state = __task_state_index(prev_state, p->exit_state); return state ? (1 << (state - 1)) : state; } @@ -220,10 +222,11 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct * TRACE_EVENT(sched_switch, TP_PROTO(bool preempt, + unsigned int prev_state, struct task_struct *prev, struct task_struct *next), - TP_ARGS(preempt, prev, next), + TP_ARGS(preempt, prev_state, prev, next), TP_STRUCT__entry( __array( char, prev_comm, TASK_COMM_LEN ) @@ -239,7 +242,7 @@ TRACE_EVENT(sched_switch, memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN); __entry->prev_pid = prev->pid; __entry->prev_prio = prev->prio; - __entry->prev_state = __trace_sched_switch_state(preempt, prev); + __entry->prev_state = __trace_sched_switch_state(preempt, prev_state, prev); memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN); __entry->next_pid = next->pid; __entry->next_prio = next->prio; -- cgit v1.2.3 From 25795ef6299f07ce3838f3253a9cb34f64efcfae Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Thu, 20 Jan 2022 16:25:20 +0000 Subject: sched/tracing: Report TASK_RTLOCK_WAIT tasks as TASK_UNINTERRUPTIBLE MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit TASK_RTLOCK_WAIT currently isn't part of TASK_REPORT, thus a task blocking on an rtlock will appear as having a task state == 0, IOW TASK_RUNNING. The actual state is saved in p->saved_state, but reading it after reading p->__state has a few issues: o that could still be TASK_RUNNING in the case of e.g. rt_spin_lock o ttwu_state_match() might have changed that to TASK_RUNNING As pointed out by Eric, adding TASK_RTLOCK_WAIT to TASK_REPORT implies exposing a new state to userspace tools which way not know what to do with them. The only information that needs to be conveyed here is that a task is waiting on an rt_mutex, which matches TASK_UNINTERRUPTIBLE - there's no need for a new state. Reported-by: Uwe Kleine-König Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Steven Rostedt (Google) Link: https://lore.kernel.org/r/20220120162520.570782-3-valentin.schneider@arm.com --- include/linux/sched.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 457c8a058b77..78b606c9ab38 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1630,6 +1630,14 @@ static inline unsigned int __task_state_index(unsigned int tsk_state, if (tsk_state == TASK_IDLE) state = TASK_REPORT_IDLE; + /* + * We're lying here, but rather than expose a completely new task state + * to userspace, we can make this appear as if the task has gone through + * a regular rt_mutex_lock() call. + */ + if (tsk_state == TASK_RTLOCK_WAIT) + state = TASK_UNINTERRUPTIBLE; + return fls(state); } -- cgit v1.2.3 From cedd3614e5d9c80908099c19f8716714ce0610b1 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 24 Feb 2022 11:06:54 +0530 Subject: perf: Add irq and exception return branch types This expands generic branch type classification by adding two more entries there in i.e irq and exception return. Also updates the x86 implementation to process X86_BR_IRET and X86_BR_IRQ records as appropriate. This changes branch types reported to user space on x86 platform but it should not be a problem. The possible scenarios and impacts are enumerated here. Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/1645681014-3346-1-git-send-email-anshuman.khandual@arm.com --- include/uapi/linux/perf_event.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 1b65042ab1db..7dc71768749d 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -251,6 +251,8 @@ enum { PERF_BR_SYSRET = 8, /* syscall return */ PERF_BR_COND_CALL = 9, /* conditional function call */ PERF_BR_COND_RET = 10, /* conditional function return */ + PERF_BR_ERET = 11, /* exception return */ + PERF_BR_IRQ = 12, /* irq */ PERF_BR_MAX, }; -- cgit v1.2.3 From 6ddf5f165f13ab623d04aee2a473d35818255199 Mon Sep 17 00:00:00 2001 From: Milind Changire Date: Mon, 14 Feb 2022 05:01:01 +0000 Subject: ceph: add getvxattr op Problem: Some directory vxattrs (e.g. ceph.dir.pin.random) are governed by information that isn't necessarily shared with the client. Add support for the new GETVXATTR operation, which allows the client to query the MDS directly for vxattrs. When the client is queried for a vxattr that doesn't have a special handler, have it issue a GETVXATTR to the MDS directly. Solution: Adds new getvxattr op to fetch ceph.dir.pin*, ceph.dir.layout* and ceph.file.layout* vxattrs. If the entire layout for a dir or a file is being set, then it is expected that the layout be set in standard JSON format. Individual field value retrieval is not wrapped in JSON. The JSON format also applies while setting the vxattr if the entire layout is being set in one go. As a temporary measure, setting a vxattr can also be done in the old format. The old format will be deprecated in the future. URL: https://tracker.ceph.com/issues/51062 Signed-off-by: Milind Changire Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- include/linux/ceph/ceph_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 7ad6c3d0db7d..66db21ac5f0c 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -328,6 +328,7 @@ enum { CEPH_MDS_OP_LOOKUPPARENT = 0x00103, CEPH_MDS_OP_LOOKUPINO = 0x00104, CEPH_MDS_OP_LOOKUPNAME = 0x00105, + CEPH_MDS_OP_GETVXATTR = 0x00106, CEPH_MDS_OP_SETXATTR = 0x01105, CEPH_MDS_OP_RMXATTR = 0x01106, -- cgit v1.2.3 From ab58a5a1c0487b67f7409f39d3c8593d416d4e7f Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Tue, 15 Feb 2022 20:23:14 +0800 Subject: ceph: move to a dedicated slabcache for ceph_cap_snap There could be huge number of capsnaps around at any given time. On x86_64 the structure is 248 bytes, which will be rounded up to 256 bytes by kzalloc. Move this to a dedicated slabcache to save 8 bytes for each. [ jlayton: use kmem_cache_zalloc ] Signed-off-by: Xiubo Li Signed-off-by: Jeff Layton Signed-off-by: Ilya Dryomov --- include/linux/ceph/libceph.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index edf62eaa6285..00af2c98da75 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -284,6 +284,7 @@ DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld) extern struct kmem_cache *ceph_inode_cachep; extern struct kmem_cache *ceph_cap_cachep; +extern struct kmem_cache *ceph_cap_snap_cachep; extern struct kmem_cache *ceph_cap_flush_cachep; extern struct kmem_cache *ceph_dentry_cachep; extern struct kmem_cache *ceph_file_cachep; -- cgit v1.2.3 From 1753629ea0f34900467185b7d8b0db11a64f4728 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Wed, 23 Feb 2022 09:04:55 +0800 Subject: ceph: remove incorrect and unused CEPH_INO_DOTDOT macro Ceph have removed this macro and the 0x3 will be use for global dummy snaprealm. Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- include/linux/ceph/ceph_fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 66db21ac5f0c..f14f9bc290e6 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -29,7 +29,6 @@ #define CEPH_INO_ROOT 1 #define CEPH_INO_CEPH 2 /* hidden .ceph dir */ -#define CEPH_INO_DOTDOT 3 /* used by ceph fuse for parent (..) */ /* arbitrary limit on max # of monitors (cluster of 3 is typical) */ #define CEPH_MAX_MON 31 -- cgit v1.2.3 From 5ed91587e201c77b35a5555c8c082655bb5834fe Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Wed, 23 Feb 2022 09:04:56 +0800 Subject: ceph: do not release the global snaprealm until unmounting The global snaprealm would be created and then destroyed immediately every time when updating it. URL: https://tracker.ceph.com/issues/54362 Signed-off-by: Xiubo Li Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- include/linux/ceph/ceph_fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index f14f9bc290e6..86bf82dbd8b8 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -28,7 +28,8 @@ #define CEPH_INO_ROOT 1 -#define CEPH_INO_CEPH 2 /* hidden .ceph dir */ +#define CEPH_INO_CEPH 2 /* hidden .ceph dir */ +#define CEPH_INO_GLOBAL_SNAPREALM 3 /* global dummy snaprealm */ /* arbitrary limit on max # of monitors (cluster of 3 is typical) */ #define CEPH_MAX_MON 31 -- cgit v1.2.3 From 2cbfae0f50f7a0f8fc9d552bd856f6cd7b7608b6 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 24 Feb 2022 01:56:20 +0200 Subject: ACPI: platform: Constify properties parameter in acpi_create_platform_device() Properties are not and should not be changed in the callee, hence constify properties parameter in acpi_create_platform_device(). Signed-off-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 6274758648e3..9ac545379447 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -691,7 +691,7 @@ int acpi_device_uevent_modalias(struct device *, struct kobj_uevent_env *); int acpi_device_modalias(struct device *, char *, int); struct platform_device *acpi_create_platform_device(struct acpi_device *, - struct property_entry *); + const struct property_entry *); #define ACPI_PTR(_ptr) (_ptr) static inline void acpi_device_set_enumerated(struct acpi_device *adev) @@ -930,7 +930,7 @@ static inline int acpi_device_modalias(struct device *dev, static inline struct platform_device * acpi_create_platform_device(struct acpi_device *adev, - struct property_entry *properties) + const struct property_entry *properties) { return NULL; } -- cgit v1.2.3 From d65bc29be0ae4ca2368df25dc6f6247aefb57f07 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sun, 13 Feb 2022 22:25:20 +0300 Subject: binfmt: move more stuff undef CONFIG_COREDUMP struct linux_binfmt::core_dump and struct min_coredump::min_coredump are used under CONFIG_COREDUMP only. Shrink those embedded configs a bit. Signed-off-by: Alexey Dobriyan Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/YglbIFyN+OtwVyjW@localhost.localdomain --- include/linux/binfmts.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 049cf9421d83..5d651c219c99 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -98,8 +98,10 @@ struct linux_binfmt { struct module *module; int (*load_binary)(struct linux_binprm *); int (*load_shlib)(struct file *); +#ifdef CONFIG_COREDUMP int (*core_dump)(struct coredump_params *cprm); unsigned long min_coredump; /* minimal dump size */ +#endif } __randomize_layout; extern void __register_binfmt(struct linux_binfmt *fmt, int insert); -- cgit v1.2.3 From 4f0bfdfd8323e5b461fc1042143a1097dba9fced Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 23 Feb 2022 19:34:31 -0800 Subject: ELF: Properly redefine PT_GNU_* in terms of PT_LOOS The PT_GNU_* program header types are actually offsets from PT_LOOS, so redefine them as such, reorder them, and add the missing PT_GNU_RELRO. Cc: Eric Biederman Cc: Peter Collingbourne Cc: Catalin Marinas Cc: Dave Martin Signed-off-by: Kees Cook --- include/uapi/linux/elf.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 61bf4774b8f2..6438d55529bf 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -35,10 +35,11 @@ typedef __s64 Elf64_Sxword; #define PT_HIOS 0x6fffffff /* OS-specific */ #define PT_LOPROC 0x70000000 #define PT_HIPROC 0x7fffffff -#define PT_GNU_EH_FRAME 0x6474e550 -#define PT_GNU_PROPERTY 0x6474e553 - +#define PT_GNU_EH_FRAME (PT_LOOS + 0x474e550) #define PT_GNU_STACK (PT_LOOS + 0x474e551) +#define PT_GNU_RELRO (PT_LOOS + 0x474e552) +#define PT_GNU_PROPERTY (PT_LOOS + 0x474e553) + /* * Extended Numbering -- cgit v1.2.3 From dd0ca255f3d27a1bb43d8e9529fb3645f9a341a3 Mon Sep 17 00:00:00 2001 From: Daniel Braunwarth Date: Mon, 28 Feb 2022 14:30:28 +0100 Subject: if_ether.h: add PROFINET Ethertype Add the Ethertype for PROFINET protocol. Signed-off-by: Daniel Braunwarth Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_ether.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index c0c2f3ed5729..4f4ed35a16db 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -86,6 +86,7 @@ * over Ethernet */ #define ETH_P_PAE 0x888E /* Port Access Entity (IEEE 802.1X) */ +#define ETH_P_PROFINET 0x8892 /* PROFINET */ #define ETH_P_REALTEK 0x8899 /* Multiple proprietary protocols */ #define ETH_P_AOE 0x88A2 /* ATA over Ethernet */ #define ETH_P_8021AD 0x88A8 /* 802.1ad Service VLAN */ -- cgit v1.2.3 From cd73cda742fbe1f33ed7306c7a01aa64f4e6ebd5 Mon Sep 17 00:00:00 2001 From: Daniel Braunwarth Date: Mon, 28 Feb 2022 14:30:29 +0100 Subject: if_ether.h: add EtherCAT Ethertype Add the Ethertype for EtherCAT protocol. Signed-off-by: Daniel Braunwarth Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_ether.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 4f4ed35a16db..1d0bccc3fa54 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -89,6 +89,7 @@ #define ETH_P_PROFINET 0x8892 /* PROFINET */ #define ETH_P_REALTEK 0x8899 /* Multiple proprietary protocols */ #define ETH_P_AOE 0x88A2 /* ATA over Ethernet */ +#define ETH_P_ETHERCAT 0x88A4 /* EtherCAT */ #define ETH_P_8021AD 0x88A8 /* 802.1ad Service VLAN */ #define ETH_P_802_EX1 0x88B5 /* 802.1 Local Experimental 1. */ #define ETH_P_PREAUTH 0x88C7 /* 802.11 Preauthentication */ -- cgit v1.2.3 From ce70fd9a551af7424a7dace2a1ba05a7de8eae27 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Feb 2022 18:55:47 +0100 Subject: scsi: core: Remove the cmd field from struct scsi_request Now that each scsi_request is backed by a scsi_cmnd, there is no need to indirect the CDB storage. Change all submitters of SCSI passthrough requests to store the CDB information directly in the scsi_cmnd, and while doing so allocate the full 32 bytes that cover all Linux supported SCSI hosts instead of requiring dynamic allocation for > 16 byte CDBs. On 64-bit systems this does not change the size of the scsi_cmnd at all, while on 32-bit systems it slightly increases it for now, but that increase will be made up by the removal of the remaining scsi_request fields. Link: https://lore.kernel.org/r/20220224175552.988286-4-hch@lst.de Reviewed-by: Bart Van Assche Reviewed-by: John Garry Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- include/scsi/scsi_cmnd.h | 7 +------ include/scsi/scsi_eh.h | 4 +--- include/scsi/scsi_request.h | 11 ----------- 3 files changed, 2 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index 7a19c8bbaed9..3e432e25645a 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -28,9 +28,6 @@ struct scsi_driver; * supports without specifying a cmd_len by ULD's */ #define MAX_COMMAND_SIZE 16 -#if (MAX_COMMAND_SIZE > BLK_MAX_CDB) -# error MAX_COMMAND_SIZE can not be bigger than BLK_MAX_CDB -#endif struct scsi_data_buffer { struct sg_table table; @@ -100,9 +97,7 @@ struct scsi_cmnd { unsigned short cmd_len; enum dma_data_direction sc_data_direction; - /* These elements define the operation we are about to perform */ - unsigned char *cmnd; - + unsigned char cmnd[32]; /* SCSI CDB */ /* These elements define the operation we ultimately want to perform */ struct scsi_data_buffer sdb; diff --git a/include/scsi/scsi_eh.h b/include/scsi/scsi_eh.h index 468094254b3c..1ae08e81339f 100644 --- a/include/scsi/scsi_eh.h +++ b/include/scsi/scsi_eh.h @@ -38,10 +38,8 @@ struct scsi_eh_save { unsigned underflow; unsigned char cmd_len; unsigned char prot_op; - unsigned char *cmnd; + unsigned char cmnd[32]; struct scsi_data_buffer sdb; - /* new command support */ - unsigned char eh_cmnd[BLK_MAX_CDB]; struct scatterlist sense_sgl; }; diff --git a/include/scsi/scsi_request.h b/include/scsi/scsi_request.h index 9129b23e12bc..aeee0611bcbe 100644 --- a/include/scsi/scsi_request.h +++ b/include/scsi/scsi_request.h @@ -4,12 +4,7 @@ #include -#define BLK_MAX_CDB 16 - struct scsi_request { - unsigned char __cmd[BLK_MAX_CDB]; - unsigned char *cmd; - unsigned short cmd_len; int result; unsigned int sense_len; unsigned int resid_len; /* residual count */ @@ -22,10 +17,4 @@ static inline struct scsi_request *scsi_req(struct request *rq) return blk_mq_rq_to_pdu(rq); } -static inline void scsi_req_free_cmd(struct scsi_request *req) -{ - if (req->cmd != req->__cmd) - kfree(req->cmd); -} - #endif /* _SCSI_SCSI_REQUEST_H */ -- cgit v1.2.3 From 5b794f98074a8b7e8eb77dd43746062940b51160 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Feb 2022 18:55:48 +0100 Subject: scsi: core: Remove the sense and sense_len fields from struct scsi_request Just use the sense_buffer field in struct scsi_cmnd for the sense data and move the sense_len field over to struct scsi_cmnd. Link: https://lore.kernel.org/r/20220224175552.988286-5-hch@lst.de Reviewed-by: Bart Van Assche Reviewed-by: John Garry Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- include/scsi/scsi_cmnd.h | 1 + include/scsi/scsi_request.h | 2 -- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index 3e432e25645a..47add5b32f46 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -112,6 +112,7 @@ struct scsi_cmnd { reconnects. Probably == sector size */ + unsigned sense_len; unsigned char *sense_buffer; /* obtained by REQUEST SENSE when * CHECK CONDITION is received on original diff --git a/include/scsi/scsi_request.h b/include/scsi/scsi_request.h index aeee0611bcbe..bed1cc49132a 100644 --- a/include/scsi/scsi_request.h +++ b/include/scsi/scsi_request.h @@ -6,10 +6,8 @@ struct scsi_request { int result; - unsigned int sense_len; unsigned int resid_len; /* residual count */ int retries; - void *sense; }; static inline struct scsi_request *scsi_req(struct request *rq) -- cgit v1.2.3 From a9a4ea1166d640d1b397f24afc1cd7e96c46cd03 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Feb 2022 18:55:49 +0100 Subject: scsi: core: Move the resid_len field from struct scsi_request to struct scsi_cmnd Prepare for removing the scsi_request structure by moving the resid_len field to struct scsi_cmnd. Link: https://lore.kernel.org/r/20220224175552.988286-6-hch@lst.de Reviewed-by: Bart Van Assche Reviewed-by: John Garry Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- include/scsi/scsi_cmnd.h | 6 +++--- include/scsi/scsi_request.h | 1 - 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index 47add5b32f46..5ff0a6e8460c 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -111,7 +111,7 @@ struct scsi_cmnd { (ie, between disconnect / reconnects. Probably == sector size */ - + unsigned resid_len; /* residual count */ unsigned sense_len; unsigned char *sense_buffer; /* obtained by REQUEST SENSE when @@ -200,12 +200,12 @@ static inline unsigned scsi_bufflen(struct scsi_cmnd *cmd) static inline void scsi_set_resid(struct scsi_cmnd *cmd, unsigned int resid) { - cmd->req.resid_len = resid; + cmd->resid_len = resid; } static inline unsigned int scsi_get_resid(struct scsi_cmnd *cmd) { - return cmd->req.resid_len; + return cmd->resid_len; } #define scsi_for_each_sg(cmd, sg, nseg, __i) \ diff --git a/include/scsi/scsi_request.h b/include/scsi/scsi_request.h index bed1cc49132a..74be75336a54 100644 --- a/include/scsi/scsi_request.h +++ b/include/scsi/scsi_request.h @@ -6,7 +6,6 @@ struct scsi_request { int result; - unsigned int resid_len; /* residual count */ int retries; }; -- cgit v1.2.3 From dbb4c84d87af7416bb7e35f8e6dd8d87d5f221d4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Feb 2022 18:55:50 +0100 Subject: scsi: core: Move the result field from struct scsi_request to struct scsi_cmnd Prepare for removing the scsi_request structure by moving the result field to struct scsi_cmnd. Link: https://lore.kernel.org/r/20220224175552.988286-7-hch@lst.de Reviewed-by: Bart Van Assche Reviewed-by: John Garry Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- include/scsi/scsi_request.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/scsi/scsi_request.h b/include/scsi/scsi_request.h index 74be75336a54..929c7bd5c72f 100644 --- a/include/scsi/scsi_request.h +++ b/include/scsi/scsi_request.h @@ -5,7 +5,6 @@ #include struct scsi_request { - int result; int retries; }; -- cgit v1.2.3 From 6aded12b10e0c9536ee2c8ee33a1f7ed52f9cb34 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Feb 2022 18:55:51 +0100 Subject: scsi: core: Remove struct scsi_request Let submitters initialize the scmd->allowed field directly instead of indirecting through struct scsi_request and remove the now superfluous structure. Link: https://lore.kernel.org/r/20220224175552.988286-8-hch@lst.de Reviewed-by: Bart Van Assche Reviewed-by: John Garry Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- include/scsi/scsi_cmnd.h | 1 - include/scsi/scsi_request.h | 9 --------- 2 files changed, 10 deletions(-) (limited to 'include') diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index 5ff0a6e8460c..4b33ca6a7c7d 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -68,7 +68,6 @@ enum scsi_cmnd_submitter { } __packed; struct scsi_cmnd { - struct scsi_request req; struct scsi_device *device; struct list_head eh_entry; /* entry for the host eh_abort_list/eh_cmd_q */ struct delayed_work abort_work; diff --git a/include/scsi/scsi_request.h b/include/scsi/scsi_request.h index 929c7bd5c72f..6d424d3e8d02 100644 --- a/include/scsi/scsi_request.h +++ b/include/scsi/scsi_request.h @@ -4,13 +4,4 @@ #include -struct scsi_request { - int retries; -}; - -static inline struct scsi_request *scsi_req(struct request *rq) -{ - return blk_mq_rq_to_pdu(rq); -} - #endif /* _SCSI_SCSI_REQUEST_H */ -- cgit v1.2.3 From 26440303310591e29121964ede0048583cb3126d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 24 Feb 2022 18:55:52 +0100 Subject: scsi: core: Remove This header is empty now except for an include of , so remove it. Link: https://lore.kernel.org/r/20220224175552.988286-9-hch@lst.de Reviewed-by: Bart Van Assche Reviewed-by: John Garry Signed-off-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- include/linux/bsg-lib.h | 1 - include/scsi/scsi_cmnd.h | 1 - include/scsi/scsi_request.h | 7 ------- 3 files changed, 9 deletions(-) delete mode 100644 include/scsi/scsi_request.h (limited to 'include') diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index 6b211323a489..9e97ced2896d 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -10,7 +10,6 @@ #define _BLK_BSG_ #include -#include struct bsg_job; struct request; diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index 4b33ca6a7c7d..76c5eaeeb3b5 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -10,7 +10,6 @@ #include #include #include -#include struct Scsi_Host; struct scsi_driver; diff --git a/include/scsi/scsi_request.h b/include/scsi/scsi_request.h deleted file mode 100644 index 6d424d3e8d02..000000000000 --- a/include/scsi/scsi_request.h +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _SCSI_SCSI_REQUEST_H -#define _SCSI_SCSI_REQUEST_H - -#include - -#endif /* _SCSI_SCSI_REQUEST_H */ -- cgit v1.2.3 From d8ec5d67b8bb6593223f24c04e1d530d86748250 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sat, 26 Feb 2022 17:04:32 -0600 Subject: scsi: iscsi: Remove iscsi_scan_finished() qla4xxx does not use iscsi_scan_finished() anymore so remove it. Link: https://lore.kernel.org/r/20220226230435.38733-4-michael.christie@oracle.com Reviewed-by: Lee Duncan Reviewed-by: Chris Leech Signed-off-by: Mike Christie Signed-off-by: Martin K. Petersen --- include/scsi/scsi_transport_iscsi.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h index c5d7810fd792..90b55db46d7c 100644 --- a/include/scsi/scsi_transport_iscsi.h +++ b/include/scsi/scsi_transport_iscsi.h @@ -278,7 +278,6 @@ struct iscsi_cls_session { iscsi_dev_to_session(_stgt->dev.parent) struct iscsi_cls_host { - atomic_t nr_scans; struct mutex mutex; struct request_queue *bsg_q; uint32_t port_speed; @@ -448,7 +447,6 @@ extern void iscsi_get_conn(struct iscsi_cls_conn *conn); extern int iscsi_destroy_conn(struct iscsi_cls_conn *conn); extern void iscsi_unblock_session(struct iscsi_cls_session *session); extern void iscsi_block_session(struct iscsi_cls_session *session); -extern int iscsi_scan_finished(struct Scsi_Host *shost, unsigned long time); extern struct iscsi_endpoint *iscsi_create_endpoint(int dd_size); extern void iscsi_destroy_endpoint(struct iscsi_endpoint *ep); extern struct iscsi_endpoint *iscsi_lookup_endpoint(u64 handle); -- cgit v1.2.3 From 5842ea3668310466dcf645a23b6cd5012ce2eadf Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sat, 26 Feb 2022 17:04:33 -0600 Subject: scsi: iscsi: ql4xxx: Use per-session workqueue for unbinding We currently allocate a workqueue per host and only use it for removing the target. For the session per host case we could be using this workqueue to be able to do recoveries (block, unblock, timeout handling) in parallel. To also allow offload drivers to do their session recoveries in parallel, this drops the per host workqueue and replaces it with a per session one. Link: https://lore.kernel.org/r/20220226230435.38733-5-michael.christie@oracle.com Reviewed-by: Lee Duncan Reviewed-by: Chris Leech Signed-off-by: Mike Christie Signed-off-by: Martin K. Petersen --- include/scsi/scsi_transport_iscsi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h index 90b55db46d7c..7a0d24d3b916 100644 --- a/include/scsi/scsi_transport_iscsi.h +++ b/include/scsi/scsi_transport_iscsi.h @@ -251,6 +251,8 @@ struct iscsi_cls_session { bool recovery_tmo_sysfs_override; struct delayed_work recovery_work; + struct workqueue_struct *workq; + unsigned int target_id; bool ida_used; -- cgit v1.2.3 From 69af1c9577aae2149f79be6f485609250fdfb0ad Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sat, 26 Feb 2022 17:04:35 -0600 Subject: scsi: iscsi: Drop temp workq_name When the workqueue code was created it didn't allow variable args so we have been using a temp buffer. Drop that. Link: https://lore.kernel.org/r/20220226230435.38733-7-michael.christie@oracle.com Reviewed-by: Chris Leech Reviewed-by: Lee Duncan Signed-off-by: Mike Christie Signed-off-by: Martin K. Petersen --- include/scsi/libiscsi.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index cb805ed9cbf1..e76c94697c1b 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -383,7 +383,6 @@ struct iscsi_host { int state; struct workqueue_struct *workq; - char workq_name[20]; }; /* -- cgit v1.2.3 From af4edb1d50c6d1044cb34bc43621411b7ba2cffe Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 28 Feb 2022 13:36:51 +0200 Subject: scsi: core: sd: Add silence_suspend flag to suppress some PM messages Kernel messages produced during runtime PM can cause a never-ending cycle because user space utilities (e.g. journald or rsyslog) write the messages back to storage, causing runtime resume, more messages, and so on. Messages that tell of things that are expected to happen are arguably unnecessary, so add a flag to suppress them. This flag is used by the UFS driver. Link: https://lore.kernel.org/r/20220228113652.970857-2-adrian.hunter@intel.com Cc: stable@vger.kernel.org Signed-off-by: Adrian Hunter Signed-off-by: Martin K. Petersen --- include/scsi/scsi_device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 647c53b26105..57e3e239a1fc 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -206,6 +206,7 @@ struct scsi_device { unsigned rpm_autosuspend:1; /* Enable runtime autosuspend at device * creation time */ unsigned ignore_media_change:1; /* Ignore MEDIA CHANGE on resume */ + unsigned silence_suspend:1; /* Do not print runtime PM related messages */ unsigned int queue_stopped; /* request queue is quiesced */ bool offline_already; /* Device offline message logged */ -- cgit v1.2.3 From a6264056b39ee0c478e1d73bfc40f61a8cf3673f Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 1 Mar 2022 13:48:56 -0600 Subject: ASoC: soc-acpi: remove sof_fw_filename MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We've been using a default firmware name for each PCI/ACPI/OF platform for a while. The machine-specific sof_fw_filename is in practice not different from the default, and newer devices don't set this field, so let's remove the redundant definitions. When OEMs modify the base firmware, they can keep the same firmware name but store the file in a separate directory. Reviewed-by: Bard Liao Reviewed-by: Rander Wang Reviewed-by: Péter Ujfalusi Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20220301194903.60859-2-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/sound/soc-acpi.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h index ac0893df9c76..fdb536d699ff 100644 --- a/include/sound/soc-acpi.h +++ b/include/sound/soc-acpi.h @@ -142,7 +142,6 @@ struct snd_soc_acpi_link_adr { * audio codecs whose presence if checked with ACPI * @pdata: intended for platform data or machine specific-ops. This structure * is not constant since this field may be updated at run-time - * @sof_fw_filename: Sound Open Firmware file name, if enabled * @sof_tplg_filename: Sound Open Firmware topology file name, if enabled */ /* Descriptor for SST ASoC machine driver */ @@ -158,7 +157,6 @@ struct snd_soc_acpi_mach { const void *quirk_data; void *pdata; struct snd_soc_acpi_mach_params mach_params; - const char *sof_fw_filename; const char *sof_tplg_filename; }; -- cgit v1.2.3 From 728dd0ab37421396927749fc8cec9c2009c526c8 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 22 Feb 2022 08:59:33 -0500 Subject: NFS: Don't re-read the entire page cache to find the next cookie If the page cache entry that was last read gets invalidated for some reason, then make sure we can re-create it on the next call to readdir. This, combined with the cache page validation, allows us to reuse the cached value of page-index on successive calls to nfs_readdir. Credit is due to Benjamin Coddington for showing that the concept works, and that it allows for improved cache sharing between processes even in the case where pages are lost due to LRU or active invalidation. Suggested-by: Benjamin Coddington Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 6e10725887d1..1c533f2c1f36 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -105,6 +105,7 @@ struct nfs_open_dir_context { __be32 verf[NFS_DIR_VERIFIER_SIZE]; __u64 dir_cookie; __u64 dup_cookie; + __u64 last_cookie; pgoff_t page_index; signed char duped; bool eof; -- cgit v1.2.3 From 580f236737d13ee25d5b0b1d124f50014fe6833b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 7 Feb 2022 13:37:00 -0500 Subject: NFS: Adjust the amount of readahead performed by NFS readdir The current NFS readdir code will always try to maximise the amount of readahead it performs on the assumption that we can cache anything that isn't immediately read by the process. There are several cases where this assumption breaks down, including when the 'ls -l' heuristic kicks in to try to force use of readdirplus as a batch replacement for lookup/getattr. This patch therefore tries to tone down the amount of readahead we perform, and adjust it to try to match the amount of data being requested by user space. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 1c533f2c1f36..691a27936849 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -107,6 +107,7 @@ struct nfs_open_dir_context { __u64 dup_cookie; __u64 last_cookie; pgoff_t page_index; + unsigned int dtsize; signed char duped; bool eof; }; -- cgit v1.2.3 From 230bc98f7a2a49eb472d184bdec91fd3096384b3 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 17 Feb 2022 11:08:24 -0500 Subject: NFS: Improve heuristic for readdirplus The heuristic for readdirplus is designed to try to detect 'ls -l' and similar patterns. It does so by looking for cache hit/miss patterns in both the attribute cache and in the dcache of the files in a given directory, and then sets a flag for the readdirplus code to interpret. The problem with this approach is that a single attribute or dcache miss can cause the NFS code to force a refresh of the attributes for the entire set of files contained in the directory. To be able to make a more nuanced decision, let's sample the number of hits and misses in the set of open directory descriptors. That allows us to set thresholds at which we start preferring READDIRPLUS over regular READDIR, or at which we start to force a re-read of the remaining readdir cache using READDIRPLUS. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 691a27936849..20a4cf0acad2 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -101,6 +101,8 @@ struct nfs_open_context { struct nfs_open_dir_context { struct list_head list; + atomic_t cache_hits; + atomic_t cache_misses; unsigned long attr_gencount; __be32 verf[NFS_DIR_VERIFIER_SIZE]; __u64 dir_cookie; @@ -110,6 +112,7 @@ struct nfs_open_dir_context { unsigned int dtsize; signed char duped; bool eof; + struct rcu_head rcu_head; }; /* @@ -274,13 +277,11 @@ struct nfs4_copy_state { /* * Bit offsets in flags field */ -#define NFS_INO_ADVISE_RDPLUS (0) /* advise readdirplus */ #define NFS_INO_STALE (1) /* possible stale inode */ #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ #define NFS_INO_INVALIDATING (3) /* inode is being invalidated */ #define NFS_INO_PRESERVE_UNLINKED (4) /* preserve file if removed while open */ #define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ -#define NFS_INO_FORCE_READDIR (7) /* force readdirplus */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ #define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */ -- cgit v1.2.3 From f648022faa68ef76058aa121d1aa3a967d59cae8 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 23 Feb 2022 11:31:51 -0500 Subject: NFS: Convert readdir page cache to use a cookie based index Instead of using a linear index to address the pages, use the cookie of the first entry, since that is what we use to match the page anyway. This allows us to avoid re-reading the entire cache on a seekdir() type of operation. The latter is very common when re-exporting NFS, and is a major performance drain. The change does affect our duplicate cookie detection, since we can no longer rely on the page index as a linear offset for detecting whether we looped backwards. However since we no longer do a linear search through all the pages on each call to nfs_readdir(), this is less of a concern than it was previously. The other downside is that invalidate_mapping_pages() no longer can use the page index to avoid clearing pages that have been read. A subsequent patch will restore the functionality this provides to the 'ls -l' heuristic. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 20a4cf0acad2..42aad886d3c0 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -106,11 +106,9 @@ struct nfs_open_dir_context { unsigned long attr_gencount; __be32 verf[NFS_DIR_VERIFIER_SIZE]; __u64 dir_cookie; - __u64 dup_cookie; __u64 last_cookie; pgoff_t page_index; unsigned int dtsize; - signed char duped; bool eof; struct rcu_head rcu_head; }; -- cgit v1.2.3 From b0365ccb0712efacf99936e94e92eb7ae63de4d5 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 23 Feb 2022 13:29:59 -0500 Subject: NFS: Fix up forced readdirplus Avoid clearing the entire readdir page cache if we're just doing forced readdirplus for the 'ls -l' heuristic. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 42aad886d3c0..3893386ceaed 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -109,6 +109,7 @@ struct nfs_open_dir_context { __u64 last_cookie; pgoff_t page_index; unsigned int dtsize; + bool force_clear; bool eof; struct rcu_head rcu_head; }; -- cgit v1.2.3 From 0adf85b445c7fbc5d2df1f8c1bc54d62c4340237 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 27 Feb 2022 12:46:24 -0500 Subject: NFS: Optimise away the previous cookie field Replace the 'previous cookie' field in struct nfs_entry with the array->last_cookie. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 728cb0c1f0b6..82f7c2730b9a 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -745,8 +745,7 @@ struct nfs_auth_info { */ struct nfs_entry { __u64 ino; - __u64 cookie, - prev_cookie; + __u64 cookie; const char * name; unsigned int len; int eof; -- cgit v1.2.3 From 3c36fe9302d153283a0cea9e4e25a9e2143ac232 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 22 Feb 2022 20:51:42 +0100 Subject: ACPI: bus: Introduce acpi_bus_for_each_dev() In order to avoid exposing acpi_bus_type to modules, introduce an acpi_bus_for_each_dev() helper for iterating over all ACPI device objects and make typec_link_ports() use it instead of the raw bus_for_each_dev() along with acpi_bus_type. Having done that, drop the acpi_bus_type export. No intentional functional impact. Signed-off-by: Rafael J. Wysocki Reviewed-by: Greg Kroah-Hartman Reviewed-by: Heikki Krogerus --- include/acpi/acpi_bus.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index ca88c4706f2b..3f7f01f03869 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -480,6 +480,8 @@ void acpi_initialize_hp_context(struct acpi_device *adev, /* acpi_device.dev.bus == &acpi_bus_type */ extern struct bus_type acpi_bus_type; +int acpi_bus_for_each_dev(int (*fn)(struct device *, void *), void *data); + /* * Events * ------ -- cgit v1.2.3 From 1038fd78a1b8269b642ce09600242682186a78e2 Mon Sep 17 00:00:00 2001 From: Nicolai Stange Date: Mon, 21 Feb 2022 13:10:47 +0100 Subject: crypto: kpp - provide support for KPP template instances The upcoming support for the RFC 7919 ffdhe group parameters will be made available in the form of templates like "ffdhe2048(dh)", "ffdhe3072(dh)" and so on. Template instantiations thereof would wrap the inner "dh" kpp_alg and also provide kpp_alg services to the outside again. Furthermore, it might be perhaps be desirable to provide KDF templates in the future, which would similarly wrap an inner kpp_alg and present themselves to the outside as another kpp_alg, transforming the shared secret on its way out. Introduce the bits needed for supporting KPP template instances. Everything related to inner kpp_alg spawns potentially being held by such template instances will be deferred to a subsequent patch in order to facilitate review. Define struct struct kpp_instance in close analogy to the already existing skcipher_instance, shash_instance and alike, but wrapping a struct kpp_alg. Implement the new kpp_register_instance() template instance registration primitive. Provide some helper functions for - going back and forth between a generic struct crypto_instance and the new struct kpp_instance, - obtaining the instantiating kpp_instance from a crypto_kpp transform and - for accessing a given kpp_instance's implementation specific context data. Annotate everything with proper kernel-doc comments, even though include/crypto/internal/kpp.h is not considered for the generated docs. Signed-off-by: Nicolai Stange Reviewed-by: Hannes Reinecke Signed-off-by: Herbert Xu --- include/crypto/internal/kpp.h | 83 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 83 insertions(+) (limited to 'include') diff --git a/include/crypto/internal/kpp.h b/include/crypto/internal/kpp.h index 659b642efada..c4d5a970fe9d 100644 --- a/include/crypto/internal/kpp.h +++ b/include/crypto/internal/kpp.h @@ -10,6 +10,24 @@ #include #include +/** + * struct kpp_instance - KPP template instance + * @free: Callback getting invoked upon instance destruction. Must be set. + * @s: Internal. Generic crypto core instance state properly layout + * to alias with @alg as needed. + * @alg: The &struct kpp_alg implementation provided by the instance. + */ +struct kpp_instance { + void (*free)(struct kpp_instance *inst); + union { + struct { + char head[offsetof(struct kpp_alg, base)]; + struct crypto_instance base; + } s; + struct kpp_alg alg; + }; +}; + /* * Transform internal helpers. */ @@ -33,6 +51,62 @@ static inline const char *kpp_alg_name(struct crypto_kpp *tfm) return crypto_kpp_tfm(tfm)->__crt_alg->cra_name; } +/* + * Template instance internal helpers. + */ +/** + * kpp_crypto_instance() - Cast a &struct kpp_instance to the corresponding + * generic &struct crypto_instance. + * @inst: Pointer to the &struct kpp_instance to be cast. + * Return: A pointer to the &struct crypto_instance embedded in @inst. + */ +static inline struct crypto_instance *kpp_crypto_instance( + struct kpp_instance *inst) +{ + return &inst->s.base; +} + +/** + * kpp_instance() - Cast a generic &struct crypto_instance to the corresponding + * &struct kpp_instance. + * @inst: Pointer to the &struct crypto_instance to be cast. + * Return: A pointer to the &struct kpp_instance @inst is embedded in. + */ +static inline struct kpp_instance *kpp_instance(struct crypto_instance *inst) +{ + return container_of(inst, struct kpp_instance, s.base); +} + +/** + * kpp_alg_instance() - Get the &struct kpp_instance a given KPP transform has + * been instantiated from. + * @kpp: The KPP transform instantiated from some &struct kpp_instance. + * Return: The &struct kpp_instance associated with @kpp. + */ +static inline struct kpp_instance *kpp_alg_instance(struct crypto_kpp *kpp) +{ + return kpp_instance(crypto_tfm_alg_instance(&kpp->base)); +} + +/** + * kpp_instance_ctx() - Get a pointer to a &struct kpp_instance's implementation + * specific context data. + * @inst: The &struct kpp_instance whose context data to access. + * + * A KPP template implementation may allocate extra memory beyond the + * end of a &struct kpp_instance instantiated from &crypto_template.create(). + * This function provides a means to obtain a pointer to this area. + * + * Return: A pointer to the implementation specific context data. + */ +static inline void *kpp_instance_ctx(struct kpp_instance *inst) +{ + return crypto_instance_ctx(kpp_crypto_instance(inst)); +} + +/* + * KPP algorithm (un)registration functions. + */ /** * crypto_register_kpp() -- Register key-agreement protocol primitives algorithm * @@ -56,4 +130,13 @@ int crypto_register_kpp(struct kpp_alg *alg); */ void crypto_unregister_kpp(struct kpp_alg *alg); +/** + * kpp_register_instance() - Register a KPP template instance. + * @tmpl: The instantiating template. + * @inst: The KPP template instance to be registered. + * Return: %0 on success, negative error code otherwise. + */ +int kpp_register_instance(struct crypto_template *tmpl, + struct kpp_instance *inst); + #endif -- cgit v1.2.3 From 46ed5269bf7dac752f78fc5f8dc5efb52b483fe7 Mon Sep 17 00:00:00 2001 From: Nicolai Stange Date: Mon, 21 Feb 2022 13:10:48 +0100 Subject: crypto: kpp - provide support for KPP spawns The upcoming support for the RFC 7919 ffdhe group parameters will be made available in the form of templates like "ffdhe2048(dh)", "ffdhe3072(dh)" and so on. Template instantiations thereof would wrap the inner "dh" kpp_alg and also provide kpp_alg services to the outside again. The primitves needed for providing kpp_alg services from template instances have been introduced with the previous patch. Continue this work now and implement everything needed for enabling template instances to make use of inner KPP algorithms like "dh". More specifically, define a struct crypto_kpp_spawn in close analogy to crypto_skcipher_spawn, crypto_shash_spawn and alike. Implement a crypto_grab_kpp() and crypto_drop_kpp() pair for binding such a spawn to some inner kpp_alg and for releasing it respectively. Template implementations can instantiate transforms from the underlying kpp_alg by means of the new crypto_spawn_kpp(). Finally, provide the crypto_spawn_kpp_alg() helper for accessing a spawn's underlying kpp_alg during template instantiation. Annotate everything with proper kernel-doc comments, even though include/crypto/internal/kpp.h is not considered for the generated docs. Signed-off-by: Nicolai Stange Reviewed-by: Hannes Reinecke Signed-off-by: Herbert Xu --- include/crypto/internal/kpp.h | 75 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 75 insertions(+) (limited to 'include') diff --git a/include/crypto/internal/kpp.h b/include/crypto/internal/kpp.h index c4d5a970fe9d..9cb0662ebe87 100644 --- a/include/crypto/internal/kpp.h +++ b/include/crypto/internal/kpp.h @@ -28,6 +28,20 @@ struct kpp_instance { }; }; +/** + * struct crypto_kpp_spawn - KPP algorithm spawn + * @base: Internal. Generic crypto core spawn state. + * + * Template instances can get a hold on some inner KPP algorithm by + * binding a &struct crypto_kpp_spawn via + * crypto_grab_kpp(). Transforms may subsequently get instantiated + * from the referenced inner &struct kpp_alg by means of + * crypto_spawn_kpp(). + */ +struct crypto_kpp_spawn { + struct crypto_spawn base; +}; + /* * Transform internal helpers. */ @@ -139,4 +153,65 @@ void crypto_unregister_kpp(struct kpp_alg *alg); int kpp_register_instance(struct crypto_template *tmpl, struct kpp_instance *inst); +/* + * KPP spawn related functions. + */ +/** + * crypto_grab_kpp() - Look up a KPP algorithm and bind a spawn to it. + * @spawn: The KPP spawn to bind. + * @inst: The template instance owning @spawn. + * @name: The KPP algorithm name to look up. + * @type: The type bitset to pass on to the lookup. + * @mask: The mask bismask to pass on to the lookup. + * Return: %0 on success, a negative error code otherwise. + */ +int crypto_grab_kpp(struct crypto_kpp_spawn *spawn, + struct crypto_instance *inst, + const char *name, u32 type, u32 mask); + +/** + * crypto_drop_kpp() - Release a spawn previously bound via crypto_grab_kpp(). + * @spawn: The spawn to release. + */ +static inline void crypto_drop_kpp(struct crypto_kpp_spawn *spawn) +{ + crypto_drop_spawn(&spawn->base); +} + +/** + * crypto_spawn_kpp_alg() - Get the algorithm a KPP spawn has been bound to. + * @spawn: The spawn to get the referenced &struct kpp_alg for. + * + * This function as well as the returned result are safe to use only + * after @spawn has been successfully bound via crypto_grab_kpp() and + * up to until the template instance owning @spawn has either been + * registered successfully or the spawn has been released again via + * crypto_drop_spawn(). + * + * Return: A pointer to the &struct kpp_alg referenced from the spawn. + */ +static inline struct kpp_alg *crypto_spawn_kpp_alg( + struct crypto_kpp_spawn *spawn) +{ + return container_of(spawn->base.alg, struct kpp_alg, base); +} + +/** + * crypto_spawn_kpp() - Create a transform from a KPP spawn. + * @spawn: The spawn previously bound to some &struct kpp_alg via + * crypto_grab_kpp(). + * + * Once a &struct crypto_kpp_spawn has been successfully bound to a + * &struct kpp_alg via crypto_grab_kpp(), transforms for the latter + * may get instantiated from the former by means of this function. + * + * Return: A pointer to the freshly created KPP transform on success + * or an ``ERR_PTR()`` otherwise. + */ +static inline struct crypto_kpp *crypto_spawn_kpp( + struct crypto_kpp_spawn *spawn) +{ + return crypto_spawn_tfm2(&spawn->base); +} + #endif -- cgit v1.2.3 From 48c6d8b878c1d811015cfba1a302d8474a9aace6 Mon Sep 17 00:00:00 2001 From: Nicolai Stange Date: Mon, 21 Feb 2022 13:10:49 +0100 Subject: crypto: dh - remove struct dh's ->q member The only current user of the DH KPP algorithm, the keyctl(KEYCTL_DH_COMPUTE) syscall, doesn't set the domain parameter ->q in struct dh. Remove it and any associated (de)serialization code in crypto_dh_encode_key() and crypto_dh_decode_key. Adjust the encoded ->secret values in testmgr's DH test vectors accordingly. Note that the dh-generic implementation would have initialized its struct dh_ctx's ->q from the decoded struct dh's ->q, if present. If this struct dh_ctx's ->q would ever have been non-NULL, it would have enabled a full key validation as specified in NIST SP800-56A in dh_is_pubkey_valid(). However, as outlined above, ->q is always NULL in practice and the full key validation code is effectively dead. A later patch will make dh_is_pubkey_valid() to calculate Q from P on the fly, if possible, so don't remove struct dh_ctx's ->q now, but leave it there until that has happened. Signed-off-by: Nicolai Stange Reviewed-by: Hannes Reinecke Signed-off-by: Herbert Xu --- include/crypto/dh.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/crypto/dh.h b/include/crypto/dh.h index d71e9858ab86..2585f0e6bb69 100644 --- a/include/crypto/dh.h +++ b/include/crypto/dh.h @@ -24,21 +24,17 @@ * * @key: Private DH key * @p: Diffie-Hellman parameter P - * @q: Diffie-Hellman parameter Q * @g: Diffie-Hellman generator G * @key_size: Size of the private DH key * @p_size: Size of DH parameter P - * @q_size: Size of DH parameter Q * @g_size: Size of DH generator G */ struct dh { void *key; void *p; - void *q; void *g; unsigned int key_size; unsigned int p_size; - unsigned int q_size; unsigned int g_size; }; -- cgit v1.2.3 From 215bebc8c6ac438c382a6a56bd2764a2d4e1da72 Mon Sep 17 00:00:00 2001 From: Nicolai Stange Date: Mon, 21 Feb 2022 13:10:50 +0100 Subject: crypto: dh - constify struct dh's pointer members struct dh contains several pointer members corresponding to DH parameters: ->key, ->p and ->g. A subsequent commit will introduce "dh" wrapping templates of the form "ffdhe2048(dh)", "ffdhe3072(dh)" and so on in order to provide built-in support for the well-known safe-prime ffdhe group parameters specified in RFC 7919. These templates will need to set the group parameter related members of the (serialized) struct dh instance passed to the inner "dh" kpp_alg instance, i.e. ->p and ->g, to some constant, static storage arrays. Turn the struct dh pointer members' types into "pointer to const" in preparation for this. Signed-off-by: Nicolai Stange Reviewed-by: Hannes Reinecke Signed-off-by: Herbert Xu --- include/crypto/dh.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/crypto/dh.h b/include/crypto/dh.h index 2585f0e6bb69..67f3f6bca527 100644 --- a/include/crypto/dh.h +++ b/include/crypto/dh.h @@ -30,9 +30,9 @@ * @g_size: Size of DH generator G */ struct dh { - void *key; - void *p; - void *g; + const void *key; + const void *p; + const void *g; unsigned int key_size; unsigned int p_size; unsigned int g_size; -- cgit v1.2.3 From fae198935c442e09afa3ecca197e144f732068d7 Mon Sep 17 00:00:00 2001 From: Nicolai Stange Date: Mon, 21 Feb 2022 13:10:51 +0100 Subject: crypto: dh - split out deserialization code from crypto_dh_decode() A subsequent commit will introduce "dh" wrapping templates of the form "ffdhe2048(dh)", "ffdhe3072(dh)" and so on in order to provide built-in support for the well-known safe-prime ffdhe group parameters specified in RFC 7919. Those templates' ->set_secret() will wrap the inner "dh" implementation's ->set_secret() and set the ->p and ->g group parameters as appropriate on the way inwards. More specifically, - A ffdheXYZ(dh) user would call crypto_dh_encode() on a struct dh instance having ->p == ->g == NULL as well as ->p_size == ->g_size == 0 and pass the resulting buffer to the outer ->set_secret(). - This outer ->set_secret() would then decode the struct dh via crypto_dh_decode_key(), set ->p, ->g, ->p_size as well as ->g_size as appropriate for the group in question and encode the struct dh again before passing it further down to the inner "dh"'s ->set_secret(). The problem is that crypto_dh_decode_key() implements some basic checks which would reject parameter sets with ->p_size == 0 and thus, the ffdheXYZ templates' ->set_secret() cannot use it as-is for decoding the passed buffer. As the inner "dh"'s ->set_secret() will eventually conduct said checks on the final parameter set anyway, the outer ->set_secret() really only needs the decoding functionality. Split out the pure struct dh decoding part from crypto_dh_decode_key() into the new __crypto_dh_decode_key(). __crypto_dh_decode_key() gets defined in crypto/dh_helper.c, but will have to get called from crypto/dh.c and thus, its declaration must be somehow made available to the latter. Strictly speaking, __crypto_dh_decode_key() is internal to the dh_generic module, yet it would be a bit over the top to introduce a new header like e.g. include/crypto/internal/dh.h containing just a single prototype. Add the __crypto_dh_decode_key() declaration to include/crypto/dh.h instead. Provide a proper kernel-doc annotation, even though __crypto_dh_decode_key() is purposedly not on the function list specified in Documentation/crypto/api-kpp.rst. Signed-off-by: Nicolai Stange Reviewed-by: Hannes Reinecke Signed-off-by: Herbert Xu --- include/crypto/dh.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/crypto/dh.h b/include/crypto/dh.h index 67f3f6bca527..7b863e911cb4 100644 --- a/include/crypto/dh.h +++ b/include/crypto/dh.h @@ -79,4 +79,20 @@ int crypto_dh_encode_key(char *buf, unsigned int len, const struct dh *params); */ int crypto_dh_decode_key(const char *buf, unsigned int len, struct dh *params); +/** + * __crypto_dh_decode_key() - decode a private key without parameter checks + * @buf: Buffer holding a packet key that should be decoded + * @len: Length of the packet private key buffer + * @params: Buffer allocated by the caller that is filled with the + * unpacked DH private key. + * + * Internal function providing the same services as the exported + * crypto_dh_decode_key(), but without any of those basic parameter + * checks conducted by the latter. + * + * Return: -EINVAL if buffer has insufficient size, 0 on success + */ +int __crypto_dh_decode_key(const char *buf, unsigned int len, + struct dh *params); + #endif -- cgit v1.2.3 From d6097b8d5d55f26cd2244e7e7f00a5a077772a91 Mon Sep 17 00:00:00 2001 From: Nicolai Stange Date: Mon, 21 Feb 2022 13:10:58 +0100 Subject: crypto: api - allow algs only in specific constructions in FIPS mode Currently we do not distinguish between algorithms that fail on the self-test vs. those which are disabled in FIPS mode (not allowed). Both are marked as having failed the self-test. Recently the need arose to allow the usage of certain algorithms only as arguments to specific template instantiations in FIPS mode. For example, standalone "dh" must be blocked, but e.g. "ffdhe2048(dh)" is allowed. Other potential use cases include "cbcmac(aes)", which must only be used with ccm(), or "ghash", which must be used only for gcm(). This patch allows this scenario by adding a new flag FIPS_INTERNAL to indicate those algorithms that are not FIPS-allowed. They can then be used as template arguments only, i.e. when looked up via crypto_grab_spawn() to be more specific. The FIPS_INTERNAL bit gets propagated upwards recursively into the surrounding template instances, until the construction eventually matches an explicit testmgr entry with ->fips_allowed being set, if any. The behaviour to skip !->fips_allowed self-test executions in FIPS mode will be retained. Note that this effectively means that FIPS_INTERNAL algorithms are handled very similarly to the INTERNAL ones in this regard. It is expected that the FIPS_INTERNAL algorithms will receive sufficient testing when the larger constructions they're a part of, if any, get exercised by testmgr. Note that as a side-effect of this patch algorithms which are not FIPS-allowed will now return ENOENT instead of ELIBBAD. Hopefully this is not an issue as some people were relying on this already. Link: https://lore.kernel.org/r/YeEVSaMEVJb3cQkq@gondor.apana.org.au Originally-by: Herbert Xu Signed-off-by: Nicolai Stange Reviewed-by: Hannes Reinecke Signed-off-by: Herbert Xu --- include/linux/crypto.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 855869e1fd32..2324ab6f1846 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -132,6 +132,15 @@ */ #define CRYPTO_ALG_ALLOCATES_MEMORY 0x00010000 +/* + * Mark an algorithm as a service implementation only usable by a + * template and never by a normal user of the kernel crypto API. + * This is intended to be used by algorithms that are themselves + * not FIPS-approved but may instead be used to implement parts of + * a FIPS-approved algorithm (e.g., dh vs. ffdhe2048(dh)). + */ +#define CRYPTO_ALG_FIPS_INTERNAL 0x00020000 + /* * Transform masks and values (for crt_flags). */ -- cgit v1.2.3 From 7976c1492571a5fb234c416559a0d9790855c635 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 23 Feb 2022 08:07:01 +0100 Subject: crypto: crypto_xor - use helpers for unaligned accesses Dereferencing a misaligned pointer is undefined behavior in C, and may result in codegen on architectures such as ARM that trigger alignments traps and expensive fixups in software. Instead, use the get_aligned()/put_aligned() accessors, which are cheap or even completely free when CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS=y. In the converse case, the prior alignment checks ensure that the casts are safe, and so no unaligned accessors are necessary. Signed-off-by: Ard Biesheuvel Signed-off-by: Herbert Xu --- include/crypto/algapi.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h index f76ec723ceae..f50c5d1725da 100644 --- a/include/crypto/algapi.h +++ b/include/crypto/algapi.h @@ -13,6 +13,8 @@ #include #include +#include + /* * Maximum values for blocksize and alignmask, used to allocate * static buffers that are big enough for any combination of @@ -154,9 +156,11 @@ static inline void crypto_xor(u8 *dst, const u8 *src, unsigned int size) (size % sizeof(unsigned long)) == 0) { unsigned long *d = (unsigned long *)dst; unsigned long *s = (unsigned long *)src; + unsigned long l; while (size > 0) { - *d++ ^= *s++; + l = get_unaligned(d) ^ get_unaligned(s++); + put_unaligned(l, d++); size -= sizeof(unsigned long); } } else { @@ -173,9 +177,11 @@ static inline void crypto_xor_cpy(u8 *dst, const u8 *src1, const u8 *src2, unsigned long *d = (unsigned long *)dst; unsigned long *s1 = (unsigned long *)src1; unsigned long *s2 = (unsigned long *)src2; + unsigned long l; while (size > 0) { - *d++ = *s1++ ^ *s2++; + l = get_unaligned(s1++) ^ get_unaligned(s2++); + put_unaligned(l, d++); size -= sizeof(unsigned long); } } else { -- cgit v1.2.3 From 80f940ef527efdd8e36c69f7b5ee8e07ac8891d9 Mon Sep 17 00:00:00 2001 From: Harsha Date: Wed, 23 Feb 2022 16:05:02 +0530 Subject: firmware: xilinx: Add ZynqMP SHA API for SHA3 functionality This patch adds zynqmp_pm_sha_hash API in the ZynqMP firmware to compute SHA3 hash of given data. Signed-off-by: Harsha Signed-off-by: Kalyani Akula Acked-by: Michal Simek Signed-off-by: Herbert Xu --- include/linux/firmware/xlnx-zynqmp.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 907cb01890cf..f6783f58c64a 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -93,6 +93,7 @@ enum pm_api_id { PM_FPGA_LOAD = 22, PM_FPGA_GET_STATUS = 23, PM_GET_CHIPID = 24, + PM_SECURE_SHA = 26, PM_PINCTRL_REQUEST = 28, PM_PINCTRL_RELEASE = 29, PM_PINCTRL_GET_FUNCTION = 30, @@ -427,6 +428,7 @@ int zynqmp_pm_set_requirement(const u32 node, const u32 capabilities, const u32 qos, const enum zynqmp_pm_request_ack ack); int zynqmp_pm_aes_engine(const u64 address, u32 *out); +int zynqmp_pm_sha_hash(const u64 address, const u32 size, const u32 flags); int zynqmp_pm_fpga_load(const u64 address, const u32 size, const u32 flags); int zynqmp_pm_fpga_get_status(u32 *value); int zynqmp_pm_write_ggs(u32 index, u32 value); @@ -601,6 +603,12 @@ static inline int zynqmp_pm_aes_engine(const u64 address, u32 *out) return -ENODEV; } +static inline int zynqmp_pm_sha_hash(const u64 address, const u32 size, + const u32 flags) +{ + return -ENODEV; +} + static inline int zynqmp_pm_fpga_load(const u64 address, const u32 size, const u32 flags) { -- cgit v1.2.3 From d58b8a99cbb84c1eb3b3613d23c1a328695a9455 Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Fri, 25 Feb 2022 12:33:51 -0500 Subject: drm/amdkfd: Add SMI add event helper To remove duplicate code, unify event message format and simplify new event add in the following patches. Use KFD_SMI_EVENT_MSG_SIZE to define msg size, the same size will be used in user space to alloc the msg receive buffer. Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index baec5a41de3e..b40687bf1014 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -463,6 +463,7 @@ enum kfd_smi_event { }; #define KFD_SMI_EVENT_MASK_FROM_INDEX(i) (1ULL << ((i) - 1)) +#define KFD_SMI_EVENT_MSG_SIZE 96 struct kfd_ioctl_smi_events_args { __u32 gpuid; /* to KFD */ -- cgit v1.2.3 From 4f9a7a1dc2a294c5c5c4b0246e2281e6ec88fb91 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Wed, 2 Mar 2022 11:29:14 +0000 Subject: OPP: Add "opp-microwatt" supporting code Add new property to the OPP: power value. The OPP entry in the DT can have "opp-microwatt". Add the needed code to handle this new property in the existing infrastructure. Signed-off-by: Lukasz Luba Signed-off-by: Viresh Kumar --- include/linux/pm_opp.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 879c138c7b8e..0d85a63a1f78 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -32,14 +32,17 @@ enum dev_pm_opp_event { * @u_volt_min: Minimum voltage in microvolts corresponding to this OPP * @u_volt_max: Maximum voltage in microvolts corresponding to this OPP * @u_amp: Maximum current drawn by the device in microamperes + * @u_watt: Power used by the device in microwatts * - * This structure stores the voltage/current values for a single power supply. + * This structure stores the voltage/current/power values for a single power + * supply. */ struct dev_pm_opp_supply { unsigned long u_volt; unsigned long u_volt_min; unsigned long u_volt_max; unsigned long u_amp; + unsigned long u_watt; }; /** @@ -94,6 +97,8 @@ void dev_pm_opp_put_opp_table(struct opp_table *opp_table); unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp); +unsigned long dev_pm_opp_get_power(struct dev_pm_opp *opp); + unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp); unsigned int dev_pm_opp_get_level(struct dev_pm_opp *opp); @@ -186,6 +191,11 @@ static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp) return 0; } +static inline unsigned long dev_pm_opp_get_power(struct dev_pm_opp *opp) +{ + return 0; +} + static inline unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp) { return 0; -- cgit v1.2.3 From caeea9e6671984c3865918459d756b961a24bb49 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Wed, 2 Mar 2022 11:29:15 +0000 Subject: PM: EM: add macro to set .active_power() callback conditionally The Energy Model is able to use new power values coming from DT. Add a new macro which is helpful in setting the .active_power() callback conditionally in setup time. The dual-macro implementation handles both kernel configurations: w/ EM and w/o EM built-in. Reported-by: kernel test robot Signed-off-by: Lukasz Luba Signed-off-by: Viresh Kumar --- include/linux/energy_model.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 6377adc3b78d..9f3c400bc52d 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -116,6 +116,7 @@ struct em_data_callback { struct device *dev); }; #define EM_DATA_CB(_active_power_cb) { .active_power = &_active_power_cb } +#define EM_SET_ACTIVE_POWER_CB(em_cb, cb) ((em_cb).active_power = cb) struct em_perf_domain *em_cpu_get(int cpu); struct em_perf_domain *em_pd_get(struct device *dev); @@ -264,6 +265,7 @@ static inline int em_pd_nr_perf_states(struct em_perf_domain *pd) #else struct em_data_callback {}; #define EM_DATA_CB(_active_power_cb) { } +#define EM_SET_ACTIVE_POWER_CB(em_cb, cb) do { } while (0) static inline int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, -- cgit v1.2.3 From bf08824a0f4776fc0626b82b6924fa1a5643eacb Mon Sep 17 00:00:00 2001 From: Kurt Kanzenbach Date: Mon, 28 Feb 2022 20:58:56 +0100 Subject: flow_dissector: Add support for HSR Network drivers such as igb or igc call eth_get_headlen() to determine the header length for their to be constructed skbs in receive path. When running HSR on top of these drivers, it results in triggering BUG_ON() in skb_pull(). The reason is the skb headlen is not sufficient for HSR to work correctly. skb_pull() notices that. For instance, eth_get_headlen() returns 14 bytes for TCP traffic over HSR which is not correct. The problem is, the flow dissection code does not take HSR into account. Therefore, add support for it. Reported-by: Anthony Harivel Signed-off-by: Kurt Kanzenbach Link: https://lore.kernel.org/r/20220228195856.88187-1-kurt@linutronix.de Signed-off-by: Jakub Kicinski --- include/linux/if_hsr.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/if_hsr.h b/include/linux/if_hsr.h index 38bbc537d4e4..408539d5ea5f 100644 --- a/include/linux/if_hsr.h +++ b/include/linux/if_hsr.h @@ -9,6 +9,22 @@ enum hsr_version { PRP_V1, }; +/* HSR Tag. + * As defined in IEC-62439-3:2010, the HSR tag is really { ethertype = 0x88FB, + * path, LSDU_size, sequence Nr }. But we let eth_header() create { h_dest, + * h_source, h_proto = 0x88FB }, and add { path, LSDU_size, sequence Nr, + * encapsulated protocol } instead. + * + * Field names as defined in the IEC:2010 standard for HSR. + */ +struct hsr_tag { + __be16 path_and_LSDU_size; + __be16 sequence_nr; + __be16 encap_proto; +} __packed; + +#define HSR_HLEN 6 + #if IS_ENABLED(CONFIG_HSR) extern bool is_hsr_master(struct net_device *dev); extern int hsr_get_version(struct net_device *dev, enum hsr_version *ver); -- cgit v1.2.3 From 42f0c1934c7cb3e94c2fe8f5771245fa5631d0e7 Mon Sep 17 00:00:00 2001 From: Tao Chen Date: Tue, 1 Mar 2022 06:35:42 -0800 Subject: tcp: Remove the unused api Last tcp_write_queue_head() use was removed in commit 114f39feab36 ("tcp: restore autocorking"), so remove it. Signed-off-by: Tao Chen Link: https://lore.kernel.org/r/SYZP282MB33317DEE1253B37C0F57231E86029@SYZP282MB3331.AUSP282.PROD.OUTLOOK.COM Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 479a27777ad6..d486d7b6112d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1831,11 +1831,6 @@ static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk) return skb_rb_last(&sk->tcp_rtx_queue); } -static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk) -{ - return skb_peek(&sk->sk_write_queue); -} - static inline struct sk_buff *tcp_write_queue_tail(const struct sock *sk) { return skb_peek_tail(&sk->sk_write_queue); -- cgit v1.2.3 From 8610037e8106b48c79cfe0afb92b2b2466e51c3d Mon Sep 17 00:00:00 2001 From: Joe Damato Date: Tue, 1 Mar 2022 23:55:47 -0800 Subject: page_pool: Add allocation stats Add per-pool statistics counters for the allocation path of a page pool. These stats are incremented in softirq context, so no locking or per-cpu variables are needed. This code is disabled by default and a kernel config option is provided for users who wish to enable them. The statistics added are: - fast: successful fast path allocations - slow: slow path order-0 allocations - slow_high_order: slow path high order allocations - empty: ptr ring is empty, so a slow path allocation was forced. - refill: an allocation which triggered a refill of the cache - waive: pages obtained from the ptr ring that cannot be added to the cache due to a NUMA mismatch. Signed-off-by: Joe Damato Acked-by: Jesper Dangaard Brouer Reviewed-by: Ilias Apalodimas Signed-off-by: David S. Miller --- include/net/page_pool.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 97c3c19872ff..1f27e8a48830 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -84,6 +84,19 @@ struct page_pool_params { void *init_arg; }; +#ifdef CONFIG_PAGE_POOL_STATS +struct page_pool_alloc_stats { + u64 fast; /* fast path allocations */ + u64 slow; /* slow-path order 0 allocations */ + u64 slow_high_order; /* slow-path high order allocations */ + u64 empty; /* failed refills due to empty ptr ring, forcing + * slow path allocation + */ + u64 refill; /* allocations via successful refill */ + u64 waive; /* failed refills due to numa zone mismatch */ +}; +#endif + struct page_pool { struct page_pool_params p; @@ -96,6 +109,11 @@ struct page_pool { unsigned int frag_offset; struct page *frag_page; long frag_users; + +#ifdef CONFIG_PAGE_POOL_STATS + /* these stats are incremented while in softirq context */ + struct page_pool_alloc_stats alloc_stats; +#endif u32 xdp_mem_id; /* -- cgit v1.2.3 From ad6fa1e1ab1b8164f1ba296b1b4dc556a483bcad Mon Sep 17 00:00:00 2001 From: Joe Damato Date: Tue, 1 Mar 2022 23:55:48 -0800 Subject: page_pool: Add recycle stats Add per-cpu stats tracking page pool recycling events: - cached: recycling placed page in the page pool cache - cache_full: page pool cache was full - ring: page placed into the ptr ring - ring_full: page released from page pool because the ptr ring was full - released_refcnt: page released (and not recycled) because refcnt > 1 Signed-off-by: Joe Damato Acked-by: Jesper Dangaard Brouer Reviewed-by: Ilias Apalodimas Signed-off-by: David S. Miller --- include/net/page_pool.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 1f27e8a48830..298af95bbf96 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -95,6 +95,18 @@ struct page_pool_alloc_stats { u64 refill; /* allocations via successful refill */ u64 waive; /* failed refills due to numa zone mismatch */ }; + +struct page_pool_recycle_stats { + u64 cached; /* recycling placed page in the cache. */ + u64 cache_full; /* cache was full */ + u64 ring; /* recycling placed page back into ptr ring */ + u64 ring_full; /* page was released from page-pool because + * PTR ring was full. + */ + u64 released_refcnt; /* page released because of elevated + * refcnt + */ +}; #endif struct page_pool { @@ -144,6 +156,10 @@ struct page_pool { */ struct ptr_ring ring; +#ifdef CONFIG_PAGE_POOL_STATS + /* recycle stats are per-cpu to avoid locking */ + struct page_pool_recycle_stats __percpu *recycle_stats; +#endif atomic_t pages_state_release_cnt; /* A page_pool is strictly tied to a single RX-queue being -- cgit v1.2.3 From 6b95e3388b1ea0ca63500c5a6e39162dbf828433 Mon Sep 17 00:00:00 2001 From: Joe Damato Date: Tue, 1 Mar 2022 23:55:49 -0800 Subject: page_pool: Add function to batch and return stats Adds a function page_pool_get_stats which can be used by drivers to obtain stats for a specified page_pool. Signed-off-by: Joe Damato Acked-by: Jesper Dangaard Brouer Reviewed-by: Ilias Apalodimas Signed-off-by: David S. Miller --- include/net/page_pool.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 298af95bbf96..ea5fb70e5101 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -107,6 +107,23 @@ struct page_pool_recycle_stats { * refcnt */ }; + +/* This struct wraps the above stats structs so users of the + * page_pool_get_stats API can pass a single argument when requesting the + * stats for the page pool. + */ +struct page_pool_stats { + struct page_pool_alloc_stats alloc_stats; + struct page_pool_recycle_stats recycle_stats; +}; + +/* + * Drivers that wish to harvest page pool stats and report them to users + * (perhaps via ethtool, debugfs, or another mechanism) can allocate a + * struct page_pool_stats call page_pool_get_stats to get stats for the specified pool. + */ +bool page_pool_get_stats(struct page_pool *pool, + struct page_pool_stats *stats); #endif struct page_pool { -- cgit v1.2.3 From 46efc97b73060823fdc18103a5e317a8327d44e1 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 2 Mar 2022 18:31:17 +0200 Subject: net: rtnetlink: RTM_GETSTATS: Allow filtering inside nests The filter_mask field of RTM_GETSTATS header determines which top-level attributes should be included in the netlink response. This saves processing time by only including the bits that the user cares about instead of always dumping everything. This is doubly important for HW-backed statistics that would typically require a trip to the device to fetch the stats. So far there was only one HW-backed stat suite per attribute. However, IFLA_STATS_LINK_OFFLOAD_XSTATS is a nest, and will gain a new stat suite in the following patches. It would therefore be advantageous to be able to filter within that nest, and select just one or the other HW-backed statistics suite. Extend rtnetlink so that RTM_GETSTATS permits attributes in the payload. The scheme is as follows: - RTM_GETSTATS - struct if_stats_msg - attr nest IFLA_STATS_GET_FILTERS - attr IFLA_STATS_LINK_OFFLOAD_XSTATS - u32 filter_mask This scheme reuses the existing enumerators by nesting them in a dedicated context attribute. This is covered by policies as usual, therefore a gradual opt-in is possible. Currently only IFLA_STATS_LINK_OFFLOAD_XSTATS nest has filtering enabled, because for the SW counters the issue does not seem to be that important. rtnl_offload_xstats_get_size() and _fill() are extended to observe the requested filters. Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index e315e53125f4..4d62ea6e1288 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1207,6 +1207,16 @@ enum { #define IFLA_STATS_FILTER_BIT(ATTR) (1 << (ATTR - 1)) +enum { + IFLA_STATS_GETSET_UNSPEC, + IFLA_STATS_GET_FILTERS, /* Nest of IFLA_STATS_LINK_xxx, each a u32 with + * a filter mask for the corresponding group. + */ + __IFLA_STATS_GETSET_MAX, +}; + +#define IFLA_STATS_GETSET_MAX (__IFLA_STATS_GETSET_MAX - 1) + /* These are embedded into IFLA_STATS_LINK_XSTATS: * [IFLA_STATS_LINK_XSTATS] * -> [LINK_XSTATS_TYPE_xxx] -- cgit v1.2.3 From 9309f97aef6d8250bb484dabeac925c3a7c57716 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 2 Mar 2022 18:31:20 +0200 Subject: net: dev: Add hardware stats support Offloading switch device drivers may be able to collect statistics of the traffic taking place in the HW datapath that pertains to a certain soft netdevice, such as VLAN. Add the necessary infrastructure to allow exposing these statistics to the offloaded netdevice in question. The API was shaped by the following considerations: - Collection of HW statistics is not free: there may be a finite number of counters, and the act of counting may have a performance impact. It is therefore necessary to allow toggling whether HW counting should be done for any particular SW netdevice. - As the drivers are loaded and removed, a particular device may get offloaded and unoffloaded again. At the same time, the statistics values need to stay monotonic (modulo the eventual 64-bit wraparound), increasing only to reflect traffic measured in the device. To that end, the netdevice keeps around a lazily-allocated copy of struct rtnl_link_stats64. Device drivers then contribute to the values kept therein at various points. Even as the driver goes away, the struct stays around to maintain the statistics values. - Different HW devices may be able to count different things. The motivation behind this patch in particular is exposure of HW counters on Nvidia Spectrum switches, where the only practical approach to counting traffic on offloaded soft netdevices currently is to use router interface counters, and count L3 traffic. Correspondingly that is the statistics suite added in this patch. Other devices may be able to measure different kinds of traffic, and for that reason, the APIs are built to allow uniform access to different statistics suites. - Because soft netdevices and offloading drivers are only loosely bound, a netdevice uses a notifier chain to communicate with the drivers. Several new notifiers, NETDEV_OFFLOAD_XSTATS_*, have been added to carry messages to the offloading drivers. - Devices can have various conditions for when a particular counter is available. As the device is configured and reconfigured, the device offload may become or cease being suitable for counter binding. A netdevice can use a notifier type NETDEV_OFFLOAD_XSTATS_REPORT_USED to ping offloading drivers and determine whether anyone currently implements a given statistics suite. This information can then be propagated to user space. When the driver decides to unoffload a netdevice, it can use a newly-added function, netdev_offload_xstats_report_delta(), to record outstanding collected statistics, before destroying the HW counter. This patch adds a helper, call_netdevice_notifiers_info_robust(), for dispatching a notifier with the possibility of unwind when one of the consumers bails. Given the wish to eventually get rid of the global notifier block altogether, this helper only invokes the per-netns notifier block. Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/netdevice.h | 42 ++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/if_link.h | 15 +++++++++++++++ 2 files changed, 57 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c79ee2296296..19a27ac361ef 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1950,6 +1950,7 @@ enum netdev_ml_priv_type { * @watchdog_dev_tracker: refcount tracker used by watchdog. * @dev_registered_tracker: tracker for reference held while * registered + * @offload_xstats_l3: L3 HW stats for this netdevice. * * FIXME: cleanup struct net_device such that network protocol info * moves out. @@ -2287,6 +2288,7 @@ struct net_device { netdevice_tracker linkwatch_dev_tracker; netdevice_tracker watchdog_dev_tracker; netdevice_tracker dev_registered_tracker; + struct rtnl_hw_stats64 *offload_xstats_l3; }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -2727,6 +2729,10 @@ enum netdev_cmd { NETDEV_CVLAN_FILTER_DROP_INFO, NETDEV_SVLAN_FILTER_PUSH_INFO, NETDEV_SVLAN_FILTER_DROP_INFO, + NETDEV_OFFLOAD_XSTATS_ENABLE, + NETDEV_OFFLOAD_XSTATS_DISABLE, + NETDEV_OFFLOAD_XSTATS_REPORT_USED, + NETDEV_OFFLOAD_XSTATS_REPORT_DELTA, }; const char *netdev_cmd_to_name(enum netdev_cmd cmd); @@ -2777,6 +2783,42 @@ struct netdev_notifier_pre_changeaddr_info { const unsigned char *dev_addr; }; +enum netdev_offload_xstats_type { + NETDEV_OFFLOAD_XSTATS_TYPE_L3 = 1, +}; + +struct netdev_notifier_offload_xstats_info { + struct netdev_notifier_info info; /* must be first */ + enum netdev_offload_xstats_type type; + + union { + /* NETDEV_OFFLOAD_XSTATS_REPORT_DELTA */ + struct netdev_notifier_offload_xstats_rd *report_delta; + /* NETDEV_OFFLOAD_XSTATS_REPORT_USED */ + struct netdev_notifier_offload_xstats_ru *report_used; + }; +}; + +int netdev_offload_xstats_enable(struct net_device *dev, + enum netdev_offload_xstats_type type, + struct netlink_ext_ack *extack); +int netdev_offload_xstats_disable(struct net_device *dev, + enum netdev_offload_xstats_type type); +bool netdev_offload_xstats_enabled(const struct net_device *dev, + enum netdev_offload_xstats_type type); +int netdev_offload_xstats_get(struct net_device *dev, + enum netdev_offload_xstats_type type, + struct rtnl_hw_stats64 *stats, bool *used, + struct netlink_ext_ack *extack); +void +netdev_offload_xstats_report_delta(struct netdev_notifier_offload_xstats_rd *rd, + const struct rtnl_hw_stats64 *stats); +void +netdev_offload_xstats_report_used(struct netdev_notifier_offload_xstats_ru *ru); +void netdev_offload_xstats_push_delta(struct net_device *dev, + enum netdev_offload_xstats_type type, + const struct rtnl_hw_stats64 *stats); + static inline void netdev_notifier_info_init(struct netdev_notifier_info *info, struct net_device *dev) { diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 4d62ea6e1288..ef6a62a2e15d 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -245,6 +245,21 @@ struct rtnl_link_stats64 { __u64 rx_nohandler; }; +/* Subset of link stats useful for in-HW collection. Meaning of the fields is as + * for struct rtnl_link_stats64. + */ +struct rtnl_hw_stats64 { + __u64 rx_packets; + __u64 tx_packets; + __u64 rx_bytes; + __u64 tx_bytes; + __u64 rx_errors; + __u64 tx_errors; + __u64 rx_dropped; + __u64 tx_dropped; + __u64 multicast; +}; + /* The struct should be in sync with struct ifmap */ struct rtnl_link_ifmap { __u64 mem_start; -- cgit v1.2.3 From 0e7788fd76222dba3229eada9162efab185923fc Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 2 Mar 2022 18:31:21 +0200 Subject: net: rtnetlink: Add UAPI for obtaining L3 offload xstats Add a new IFLA_STATS_LINK_OFFLOAD_XSTATS child attribute, IFLA_OFFLOAD_XSTATS_L3_STATS, to carry statistics for traffic that takes place in a HW router. The offloaded HW stats are designed to allow per-netdevice enablement and disablement. Additionally, as a netdevice is configured, it may become or cease being suitable for binding of a HW counter. Both of these aspects need to be communicated to the userspace. To that end, add another child attribute, IFLA_OFFLOAD_XSTATS_HW_S_INFO: - attr nest IFLA_OFFLOAD_XSTATS_HW_S_INFO - attr nest IFLA_OFFLOAD_XSTATS_L3_STATS - attr IFLA_OFFLOAD_XSTATS_HW_S_INFO_REQUEST - {0,1} as u8 - attr IFLA_OFFLOAD_XSTATS_HW_S_INFO_USED - {0,1} as u8 Thus this one attribute is a nest that can be used to carry information about various types of HW statistics, and indexing is very simply done by wrapping the information for a given statistics suite into the attribute that carries the suite is the RTM_GETSTATS query. At the same time, because _HW_S_INFO is nested directly below IFLA_STATS_LINK_OFFLOAD_XSTATS, it is possible through filtering to request only the metadata about individual statistics suites, without having to hit the HW to get the actual counters. Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index ef6a62a2e15d..b1031f481d2f 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1249,10 +1249,21 @@ enum { enum { IFLA_OFFLOAD_XSTATS_UNSPEC, IFLA_OFFLOAD_XSTATS_CPU_HIT, /* struct rtnl_link_stats64 */ + IFLA_OFFLOAD_XSTATS_HW_S_INFO, /* HW stats info. A nest */ + IFLA_OFFLOAD_XSTATS_L3_STATS, /* struct rtnl_hw_stats64 */ __IFLA_OFFLOAD_XSTATS_MAX }; #define IFLA_OFFLOAD_XSTATS_MAX (__IFLA_OFFLOAD_XSTATS_MAX - 1) +enum { + IFLA_OFFLOAD_XSTATS_HW_S_INFO_UNSPEC, + IFLA_OFFLOAD_XSTATS_HW_S_INFO_REQUEST, /* u8 */ + IFLA_OFFLOAD_XSTATS_HW_S_INFO_USED, /* u8 */ + __IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX, +}; +#define IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX \ + (__IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX - 1) + /* XDP section */ #define XDP_FLAGS_UPDATE_IF_NOEXIST (1U << 0) -- cgit v1.2.3 From 03ba35667091337d8e632cf4b814f1c1b914609b Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 2 Mar 2022 18:31:22 +0200 Subject: net: rtnetlink: Add RTM_SETSTATS The offloaded HW stats are designed to allow per-netdevice enablement and disablement. These stats are only accessible through RTM_GETSTATS, and therefore should be toggled by a RTM_SETSTATS message. Add it, and the necessary skeleton handler. Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/uapi/linux/rtnetlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 0970cb4b1b88..14462dc159fd 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -146,6 +146,8 @@ enum { #define RTM_NEWSTATS RTM_NEWSTATS RTM_GETSTATS = 94, #define RTM_GETSTATS RTM_GETSTATS + RTM_SETSTATS, +#define RTM_SETSTATS RTM_SETSTATS RTM_NEWCACHEREPORT = 96, #define RTM_NEWCACHEREPORT RTM_NEWCACHEREPORT -- cgit v1.2.3 From 5fd0b838efac16046509f7fb100455d0463b9687 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 2 Mar 2022 18:31:23 +0200 Subject: net: rtnetlink: Add UAPI toggle for IFLA_OFFLOAD_XSTATS_L3_STATS The offloaded HW stats are designed to allow per-netdevice enablement and disablement. Add an attribute, IFLA_STATS_SET_OFFLOAD_XSTATS_L3_STATS, which should be carried by the RTM_SETSTATS message, and expresses a desire to toggle L3 offload xstats on or off. As part of the above, add an exported function rtnl_offload_xstats_notify() that drivers can use when they have installed or deinstalled the counters backing the HW stats. At this point, it is possible to enable, disable and query L3 offload xstats on netdevices. (However there is no driver actually implementing these.) Signed-off-by: Petr Machata Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 3 +++ include/uapi/linux/if_link.h | 1 + include/uapi/linux/rtnetlink.h | 2 ++ 3 files changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index bb9cb84114c1..7f970b16da3a 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -134,4 +134,7 @@ extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, int (*vlan_fill)(struct sk_buff *skb, struct net_device *dev, u32 filter_mask)); + +extern void rtnl_offload_xstats_notify(struct net_device *dev); + #endif /* __LINUX_RTNETLINK_H */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index b1031f481d2f..ddca20357e7e 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1227,6 +1227,7 @@ enum { IFLA_STATS_GET_FILTERS, /* Nest of IFLA_STATS_LINK_xxx, each a u32 with * a filter mask for the corresponding group. */ + IFLA_STATS_SET_OFFLOAD_XSTATS_L3_STATS, /* 0 or 1 as u8 */ __IFLA_STATS_GETSET_MAX, }; diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 14462dc159fd..51530aade46e 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -767,6 +767,8 @@ enum rtnetlink_groups { #define RTNLGRP_MCTP_IFADDR RTNLGRP_MCTP_IFADDR RTNLGRP_TUNNEL, #define RTNLGRP_TUNNEL RTNLGRP_TUNNEL + RTNLGRP_STATS, +#define RTNLGRP_STATS RTNLGRP_STATS __RTNLGRP_MAX }; #define RTNLGRP_MAX (__RTNLGRP_MAX - 1) -- cgit v1.2.3 From 445ad495f0ff71553693e6a2a9d7a3bc6917ca36 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 24 Feb 2022 16:20:17 +0200 Subject: vfio: Have the core code decode the VFIO_DEVICE_FEATURE ioctl Invoke a new device op 'device_feature' to handle just the data array portion of the command. This lifts the ioctl validation to the core code and makes it simpler for either the core code, or layered drivers, to implement their own feature values. Provide vfio_check_feature() to consolidate checking the flags/etc against what the driver supports. Link: https://lore.kernel.org/all/20220224142024.147653-9-yishaih@nvidia.com Signed-off-by: Jason Gunthorpe Tested-by: Shameer Kolothum Reviewed-by: Alex Williamson Reviewed-by: Cornelia Huck Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/vfio.h | 32 ++++++++++++++++++++++++++++++++ include/linux/vfio_pci_core.h | 2 ++ 2 files changed, 34 insertions(+) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 76191d7abed1..550c28f2ef60 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -55,6 +55,7 @@ struct vfio_device { * @match: Optional device name match callback (return: 0 for no-match, >0 for * match, -errno for abort (ex. match with insufficient or incorrect * additional args) + * @device_feature: Optional, fill in the VFIO_DEVICE_FEATURE ioctl */ struct vfio_device_ops { char *name; @@ -69,8 +70,39 @@ struct vfio_device_ops { int (*mmap)(struct vfio_device *vdev, struct vm_area_struct *vma); void (*request)(struct vfio_device *vdev, unsigned int count); int (*match)(struct vfio_device *vdev, char *buf); + int (*device_feature)(struct vfio_device *device, u32 flags, + void __user *arg, size_t argsz); }; +/** + * vfio_check_feature - Validate user input for the VFIO_DEVICE_FEATURE ioctl + * @flags: Arg from the device_feature op + * @argsz: Arg from the device_feature op + * @supported_ops: Combination of VFIO_DEVICE_FEATURE_GET and SET the driver + * supports + * @minsz: Minimum data size the driver accepts + * + * For use in a driver's device_feature op. Checks that the inputs to the + * VFIO_DEVICE_FEATURE ioctl are correct for the driver's feature. Returns 1 if + * the driver should execute the get or set, otherwise the relevant + * value should be returned. + */ +static inline int vfio_check_feature(u32 flags, size_t argsz, u32 supported_ops, + size_t minsz) +{ + if ((flags & (VFIO_DEVICE_FEATURE_GET | VFIO_DEVICE_FEATURE_SET)) & + ~supported_ops) + return -EINVAL; + if (flags & VFIO_DEVICE_FEATURE_PROBE) + return 0; + /* Without PROBE one of GET or SET must be requested */ + if (!(flags & (VFIO_DEVICE_FEATURE_GET | VFIO_DEVICE_FEATURE_SET))) + return -EINVAL; + if (argsz < minsz) + return -EINVAL; + return 1; +} + void vfio_init_group_dev(struct vfio_device *device, struct device *dev, const struct vfio_device_ops *ops); void vfio_uninit_group_dev(struct vfio_device *device); diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index ef9a44b6cf5d..beba0b2ed87d 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -220,6 +220,8 @@ int vfio_pci_core_sriov_configure(struct pci_dev *pdev, int nr_virtfn); extern const struct pci_error_handlers vfio_pci_core_err_handlers; long vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd, unsigned long arg); +int vfio_pci_core_ioctl_feature(struct vfio_device *device, u32 flags, + void __user *arg, size_t argsz); ssize_t vfio_pci_core_read(struct vfio_device *core_vdev, char __user *buf, size_t count, loff_t *ppos); ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *buf, -- cgit v1.2.3 From 115dcec65f61d53e25e1bed5e380468b30f98b14 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 24 Feb 2022 16:20:18 +0200 Subject: vfio: Define device migration protocol v2 Replace the existing region based migration protocol with an ioctl based protocol. The two protocols have the same general semantic behaviors, but the way the data is transported is changed. This is the STOP_COPY portion of the new protocol, it defines the 5 states for basic stop and copy migration and the protocol to move the migration data in/out of the kernel. Compared to the clarification of the v1 protocol Alex proposed: https://lore.kernel.org/r/163909282574.728533.7460416142511440919.stgit@omen This has a few deliberate functional differences: - ERROR arcs allow the device function to remain unchanged. - The protocol is not required to return to the original state on transition failure. Instead userspace can execute an unwind back to the original state, reset, or do something else without needing kernel support. This simplifies the kernel design and should userspace choose a policy like always reset, avoids doing useless work in the kernel on error handling paths. - PRE_COPY is made optional, userspace must discover it before using it. This reflects the fact that the majority of drivers we are aware of right now will not implement PRE_COPY. - segmentation is not part of the data stream protocol, the receiver does not have to reproduce the framing boundaries. The hybrid FSM for the device_state is described as a Mealy machine by documenting each of the arcs the driver is required to implement. Defining the remaining set of old/new device_state transitions as 'combination transitions' which are naturally defined as taking multiple FSM arcs along the shortest path within the FSM's digraph allows a complete matrix of transitions. A new VFIO_DEVICE_FEATURE of VFIO_DEVICE_FEATURE_MIG_DEVICE_STATE is defined to replace writing to the device_state field in the region. This allows returning a brand new FD whenever the requested transition opens a data transfer session. The VFIO core code implements the new feature and provides a helper function to the driver. Using the helper the driver only has to implement 6 of the FSM arcs and the other combination transitions are elaborated consistently from those arcs. A new VFIO_DEVICE_FEATURE of VFIO_DEVICE_FEATURE_MIGRATION is defined to report the capability for migration and indicate which set of states and arcs are supported by the device. The FSM provides a lot of flexibility to make backwards compatible extensions but the VFIO_DEVICE_FEATURE also allows for future breaking extensions for scenarios that cannot support even the basic STOP_COPY requirements. The VFIO_DEVICE_FEATURE_MIG_DEVICE_STATE with the GET option (i.e. VFIO_DEVICE_FEATURE_GET) can be used to read the current migration state of the VFIO device. Data transfer sessions are now carried over a file descriptor, instead of the region. The FD functions for the lifetime of the data transfer session. read() and write() transfer the data with normal Linux stream FD semantics. This design allows future expansion to support poll(), io_uring, and other performance optimizations. The complicated mmap mode for data transfer is discarded as current qemu doesn't take meaningful advantage of it, and the new qemu implementation avoids substantially all the performance penalty of using a read() on the region. Link: https://lore.kernel.org/all/20220224142024.147653-10-yishaih@nvidia.com Signed-off-by: Jason Gunthorpe Tested-by: Shameer Kolothum Reviewed-by: Kevin Tian Reviewed-by: Alex Williamson Reviewed-by: Cornelia Huck Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/vfio.h | 20 ++++++ include/uapi/linux/vfio.h | 174 ++++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 181 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 550c28f2ef60..c44e80bbbd3b 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -56,6 +56,16 @@ struct vfio_device { * match, -errno for abort (ex. match with insufficient or incorrect * additional args) * @device_feature: Optional, fill in the VFIO_DEVICE_FEATURE ioctl + * @migration_set_state: Optional callback to change the migration state for + * devices that support migration. It's mandatory for + * VFIO_DEVICE_FEATURE_MIGRATION migration support. + * The returned FD is used for data transfer according to the FSM + * definition. The driver is responsible to ensure that FD reaches end + * of stream or error whenever the migration FSM leaves a data transfer + * state or before close_device() returns. + * @migration_get_state: Optional callback to get the migration state for + * devices that support migration. It's mandatory for + * VFIO_DEVICE_FEATURE_MIGRATION migration support. */ struct vfio_device_ops { char *name; @@ -72,6 +82,11 @@ struct vfio_device_ops { int (*match)(struct vfio_device *vdev, char *buf); int (*device_feature)(struct vfio_device *device, u32 flags, void __user *arg, size_t argsz); + struct file *(*migration_set_state)( + struct vfio_device *device, + enum vfio_device_mig_state new_state); + int (*migration_get_state)(struct vfio_device *device, + enum vfio_device_mig_state *curr_state); }; /** @@ -114,6 +129,11 @@ extern void vfio_device_put(struct vfio_device *device); int vfio_assign_device_set(struct vfio_device *device, void *set_id); +int vfio_mig_get_next_state(struct vfio_device *device, + enum vfio_device_mig_state cur_fsm, + enum vfio_device_mig_state new_fsm, + enum vfio_device_mig_state *next_fsm); + /* * External user API */ diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index ef33ea002b0b..22ed358c04c5 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -605,25 +605,25 @@ struct vfio_region_gfx_edid { struct vfio_device_migration_info { __u32 device_state; /* VFIO device state */ -#define VFIO_DEVICE_STATE_STOP (0) -#define VFIO_DEVICE_STATE_RUNNING (1 << 0) -#define VFIO_DEVICE_STATE_SAVING (1 << 1) -#define VFIO_DEVICE_STATE_RESUMING (1 << 2) -#define VFIO_DEVICE_STATE_MASK (VFIO_DEVICE_STATE_RUNNING | \ - VFIO_DEVICE_STATE_SAVING | \ - VFIO_DEVICE_STATE_RESUMING) +#define VFIO_DEVICE_STATE_V1_STOP (0) +#define VFIO_DEVICE_STATE_V1_RUNNING (1 << 0) +#define VFIO_DEVICE_STATE_V1_SAVING (1 << 1) +#define VFIO_DEVICE_STATE_V1_RESUMING (1 << 2) +#define VFIO_DEVICE_STATE_MASK (VFIO_DEVICE_STATE_V1_RUNNING | \ + VFIO_DEVICE_STATE_V1_SAVING | \ + VFIO_DEVICE_STATE_V1_RESUMING) #define VFIO_DEVICE_STATE_VALID(state) \ - (state & VFIO_DEVICE_STATE_RESUMING ? \ - (state & VFIO_DEVICE_STATE_MASK) == VFIO_DEVICE_STATE_RESUMING : 1) + (state & VFIO_DEVICE_STATE_V1_RESUMING ? \ + (state & VFIO_DEVICE_STATE_MASK) == VFIO_DEVICE_STATE_V1_RESUMING : 1) #define VFIO_DEVICE_STATE_IS_ERROR(state) \ - ((state & VFIO_DEVICE_STATE_MASK) == (VFIO_DEVICE_STATE_SAVING | \ - VFIO_DEVICE_STATE_RESUMING)) + ((state & VFIO_DEVICE_STATE_MASK) == (VFIO_DEVICE_STATE_V1_SAVING | \ + VFIO_DEVICE_STATE_V1_RESUMING)) #define VFIO_DEVICE_STATE_SET_ERROR(state) \ - ((state & ~VFIO_DEVICE_STATE_MASK) | VFIO_DEVICE_SATE_SAVING | \ - VFIO_DEVICE_STATE_RESUMING) + ((state & ~VFIO_DEVICE_STATE_MASK) | VFIO_DEVICE_STATE_V1_SAVING | \ + VFIO_DEVICE_STATE_V1_RESUMING) __u32 reserved; __u64 pending_bytes; @@ -1002,6 +1002,154 @@ struct vfio_device_feature { */ #define VFIO_DEVICE_FEATURE_PCI_VF_TOKEN (0) +/* + * Indicates the device can support the migration API through + * VFIO_DEVICE_FEATURE_MIG_DEVICE_STATE. If this GET succeeds, the RUNNING and + * ERROR states are always supported. Support for additional states is + * indicated via the flags field; at least VFIO_MIGRATION_STOP_COPY must be + * set. + * + * VFIO_MIGRATION_STOP_COPY means that STOP, STOP_COPY and + * RESUMING are supported. + */ +struct vfio_device_feature_migration { + __aligned_u64 flags; +#define VFIO_MIGRATION_STOP_COPY (1 << 0) +}; +#define VFIO_DEVICE_FEATURE_MIGRATION 1 + +/* + * Upon VFIO_DEVICE_FEATURE_SET, execute a migration state change on the VFIO + * device. The new state is supplied in device_state, see enum + * vfio_device_mig_state for details + * + * The kernel migration driver must fully transition the device to the new state + * value before the operation returns to the user. + * + * The kernel migration driver must not generate asynchronous device state + * transitions outside of manipulation by the user or the VFIO_DEVICE_RESET + * ioctl as described above. + * + * If this function fails then current device_state may be the original + * operating state or some other state along the combination transition path. + * The user can then decide if it should execute a VFIO_DEVICE_RESET, attempt + * to return to the original state, or attempt to return to some other state + * such as RUNNING or STOP. + * + * If the new_state starts a new data transfer session then the FD associated + * with that session is returned in data_fd. The user is responsible to close + * this FD when it is finished. The user must consider the migration data stream + * carried over the FD to be opaque and must preserve the byte order of the + * stream. The user is not required to preserve buffer segmentation when writing + * the data stream during the RESUMING operation. + * + * Upon VFIO_DEVICE_FEATURE_GET, get the current migration state of the VFIO + * device, data_fd will be -1. + */ +struct vfio_device_feature_mig_state { + __u32 device_state; /* From enum vfio_device_mig_state */ + __s32 data_fd; +}; +#define VFIO_DEVICE_FEATURE_MIG_DEVICE_STATE 2 + +/* + * The device migration Finite State Machine is described by the enum + * vfio_device_mig_state. Some of the FSM arcs will create a migration data + * transfer session by returning a FD, in this case the migration data will + * flow over the FD using read() and write() as discussed below. + * + * There are 5 states to support VFIO_MIGRATION_STOP_COPY: + * RUNNING - The device is running normally + * STOP - The device does not change the internal or external state + * STOP_COPY - The device internal state can be read out + * RESUMING - The device is stopped and is loading a new internal state + * ERROR - The device has failed and must be reset + * + * The FSM takes actions on the arcs between FSM states. The driver implements + * the following behavior for the FSM arcs: + * + * RUNNING -> STOP + * STOP_COPY -> STOP + * While in STOP the device must stop the operation of the device. The device + * must not generate interrupts, DMA, or any other change to external state. + * It must not change its internal state. When stopped the device and kernel + * migration driver must accept and respond to interaction to support external + * subsystems in the STOP state, for example PCI MSI-X and PCI config space. + * Failure by the user to restrict device access while in STOP must not result + * in error conditions outside the user context (ex. host system faults). + * + * The STOP_COPY arc will terminate a data transfer session. + * + * RESUMING -> STOP + * Leaving RESUMING terminates a data transfer session and indicates the + * device should complete processing of the data delivered by write(). The + * kernel migration driver should complete the incorporation of data written + * to the data transfer FD into the device internal state and perform + * final validity and consistency checking of the new device state. If the + * user provided data is found to be incomplete, inconsistent, or otherwise + * invalid, the migration driver must fail the SET_STATE ioctl and + * optionally go to the ERROR state as described below. + * + * While in STOP the device has the same behavior as other STOP states + * described above. + * + * To abort a RESUMING session the device must be reset. + * + * STOP -> RUNNING + * While in RUNNING the device is fully operational, the device may generate + * interrupts, DMA, respond to MMIO, all vfio device regions are functional, + * and the device may advance its internal state. + * + * STOP -> STOP_COPY + * This arc begin the process of saving the device state and will return a + * new data_fd. + * + * While in the STOP_COPY state the device has the same behavior as STOP + * with the addition that the data transfers session continues to stream the + * migration state. End of stream on the FD indicates the entire device + * state has been transferred. + * + * The user should take steps to restrict access to vfio device regions while + * the device is in STOP_COPY or risk corruption of the device migration data + * stream. + * + * STOP -> RESUMING + * Entering the RESUMING state starts a process of restoring the device state + * and will return a new data_fd. The data stream fed into the data_fd should + * be taken from the data transfer output of a single FD during saving from + * a compatible device. The migration driver may alter/reset the internal + * device state for this arc if required to prepare the device to receive the + * migration data. + * + * any -> ERROR + * ERROR cannot be specified as a device state, however any transition request + * can be failed with an errno return and may then move the device_state into + * ERROR. In this case the device was unable to execute the requested arc and + * was also unable to restore the device to any valid device_state. + * To recover from ERROR VFIO_DEVICE_RESET must be used to return the + * device_state back to RUNNING. + * + * The remaining possible transitions are interpreted as combinations of the + * above FSM arcs. As there are multiple paths through the FSM arcs the path + * should be selected based on the following rules: + * - Select the shortest path. + * Refer to vfio_mig_get_next_state() for the result of the algorithm. + * + * The automatic transit through the FSM arcs that make up the combination + * transition is invisible to the user. When working with combination arcs the + * user may see any step along the path in the device_state if SET_STATE + * fails. When handling these types of errors users should anticipate future + * revisions of this protocol using new states and those states becoming + * visible in this case. + */ +enum vfio_device_mig_state { + VFIO_DEVICE_STATE_ERROR = 0, + VFIO_DEVICE_STATE_STOP = 1, + VFIO_DEVICE_STATE_RUNNING = 2, + VFIO_DEVICE_STATE_STOP_COPY = 3, + VFIO_DEVICE_STATE_RESUMING = 4, +}; + /* -------- API for Type1 VFIO IOMMU -------- */ /** -- cgit v1.2.3 From 8cb3d83b959be0631cd719b995c40c3cda21cd47 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 24 Feb 2022 16:20:19 +0200 Subject: vfio: Extend the device migration protocol with RUNNING_P2P The RUNNING_P2P state is designed to support multiple devices in the same VM that are doing P2P transactions between themselves. When in RUNNING_P2P the device must be able to accept incoming P2P transactions but should not generate outgoing P2P transactions. As an optional extension to the mandatory states it is defined as in between STOP and RUNNING: STOP -> RUNNING_P2P -> RUNNING -> RUNNING_P2P -> STOP For drivers that are unable to support RUNNING_P2P the core code silently merges RUNNING_P2P and RUNNING together. Unless driver support is present, the new state cannot be used in SET_STATE. Drivers that support this will be required to implement 4 FSM arcs beyond the basic FSM. 2 of the basic FSM arcs become combination transitions. Compared to the v1 clarification, NDMA is redefined into FSM states and is described in terms of the desired P2P quiescent behavior, noting that halting all DMA is an acceptable implementation. Link: https://lore.kernel.org/all/20220224142024.147653-11-yishaih@nvidia.com Signed-off-by: Jason Gunthorpe Tested-by: Shameer Kolothum Reviewed-by: Kevin Tian Reviewed-by: Alex Williamson Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/vfio.h | 1 + include/uapi/linux/vfio.h | 36 ++++++++++++++++++++++++++++++++++-- 2 files changed, 35 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index c44e80bbbd3b..66dda06ec42d 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -33,6 +33,7 @@ struct vfio_device { struct vfio_group *group; struct vfio_device_set *dev_set; struct list_head dev_set_list; + unsigned int migration_flags; /* Members below here are private, not for driver use */ refcount_t refcount; diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 22ed358c04c5..26a66f68371d 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -1011,10 +1011,16 @@ struct vfio_device_feature { * * VFIO_MIGRATION_STOP_COPY means that STOP, STOP_COPY and * RESUMING are supported. + * + * VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P means that RUNNING_P2P + * is supported in addition to the STOP_COPY states. + * + * Other combinations of flags have behavior to be defined in the future. */ struct vfio_device_feature_migration { __aligned_u64 flags; #define VFIO_MIGRATION_STOP_COPY (1 << 0) +#define VFIO_MIGRATION_P2P (1 << 1) }; #define VFIO_DEVICE_FEATURE_MIGRATION 1 @@ -1065,10 +1071,13 @@ struct vfio_device_feature_mig_state { * RESUMING - The device is stopped and is loading a new internal state * ERROR - The device has failed and must be reset * + * And 1 optional state to support VFIO_MIGRATION_P2P: + * RUNNING_P2P - RUNNING, except the device cannot do peer to peer DMA + * * The FSM takes actions on the arcs between FSM states. The driver implements * the following behavior for the FSM arcs: * - * RUNNING -> STOP + * RUNNING_P2P -> STOP * STOP_COPY -> STOP * While in STOP the device must stop the operation of the device. The device * must not generate interrupts, DMA, or any other change to external state. @@ -1095,11 +1104,16 @@ struct vfio_device_feature_mig_state { * * To abort a RESUMING session the device must be reset. * - * STOP -> RUNNING + * RUNNING_P2P -> RUNNING * While in RUNNING the device is fully operational, the device may generate * interrupts, DMA, respond to MMIO, all vfio device regions are functional, * and the device may advance its internal state. * + * RUNNING -> RUNNING_P2P + * STOP -> RUNNING_P2P + * While in RUNNING_P2P the device is partially running in the P2P quiescent + * state defined below. + * * STOP -> STOP_COPY * This arc begin the process of saving the device state and will return a * new data_fd. @@ -1129,6 +1143,18 @@ struct vfio_device_feature_mig_state { * To recover from ERROR VFIO_DEVICE_RESET must be used to return the * device_state back to RUNNING. * + * The optional peer to peer (P2P) quiescent state is intended to be a quiescent + * state for the device for the purposes of managing multiple devices within a + * user context where peer-to-peer DMA between devices may be active. The + * RUNNING_P2P states must prevent the device from initiating + * any new P2P DMA transactions. If the device can identify P2P transactions + * then it can stop only P2P DMA, otherwise it must stop all DMA. The migration + * driver must complete any such outstanding operations prior to completing the + * FSM arc into a P2P state. For the purpose of specification the states + * behave as though the device was fully running if not supported. Like while in + * STOP or STOP_COPY the user must not touch the device, otherwise the state + * can be exited. + * * The remaining possible transitions are interpreted as combinations of the * above FSM arcs. As there are multiple paths through the FSM arcs the path * should be selected based on the following rules: @@ -1141,6 +1167,11 @@ struct vfio_device_feature_mig_state { * fails. When handling these types of errors users should anticipate future * revisions of this protocol using new states and those states becoming * visible in this case. + * + * The optional states cannot be used with SET_STATE if the device does not + * support them. The user can discover if these states are supported by using + * VFIO_DEVICE_FEATURE_MIGRATION. By using combination transitions the user can + * avoid knowing about these optional states if the kernel driver supports them. */ enum vfio_device_mig_state { VFIO_DEVICE_STATE_ERROR = 0, @@ -1148,6 +1179,7 @@ enum vfio_device_mig_state { VFIO_DEVICE_STATE_RUNNING = 2, VFIO_DEVICE_STATE_STOP_COPY = 3, VFIO_DEVICE_STATE_RESUMING = 4, + VFIO_DEVICE_STATE_RUNNING_P2P = 5, }; /* -------- API for Type1 VFIO IOMMU -------- */ -- cgit v1.2.3 From 0f3f9cd7f752f6e685e378620babc5e34af6fb9f Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Thu, 24 Feb 2022 16:20:20 +0200 Subject: vfio: Remove migration protocol v1 documentation v1 was never implemented and is replaced by v2. The old uAPI documentation is removed from the header file. The old uAPI definitions are still kept in the header file to ease transition for userspace copying these headers. They will be fully removed down the road. Link: https://lore.kernel.org/all/20220224142024.147653-12-yishaih@nvidia.com Signed-off-by: Jason Gunthorpe Tested-by: Shameer Kolothum Reviewed-by: Alex Williamson Reviewed-by: Cornelia Huck Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/uapi/linux/vfio.h | 200 +--------------------------------------------- 1 file changed, 2 insertions(+), 198 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 26a66f68371d..fea86061b44e 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -323,7 +323,7 @@ struct vfio_region_info_cap_type { #define VFIO_REGION_TYPE_PCI_VENDOR_MASK (0xffff) #define VFIO_REGION_TYPE_GFX (1) #define VFIO_REGION_TYPE_CCW (2) -#define VFIO_REGION_TYPE_MIGRATION (3) +#define VFIO_REGION_TYPE_MIGRATION_DEPRECATED (3) /* sub-types for VFIO_REGION_TYPE_PCI_* */ @@ -405,203 +405,7 @@ struct vfio_region_gfx_edid { #define VFIO_REGION_SUBTYPE_CCW_CRW (3) /* sub-types for VFIO_REGION_TYPE_MIGRATION */ -#define VFIO_REGION_SUBTYPE_MIGRATION (1) - -/* - * The structure vfio_device_migration_info is placed at the 0th offset of - * the VFIO_REGION_SUBTYPE_MIGRATION region to get and set VFIO device related - * migration information. Field accesses from this structure are only supported - * at their native width and alignment. Otherwise, the result is undefined and - * vendor drivers should return an error. - * - * device_state: (read/write) - * - The user application writes to this field to inform the vendor driver - * about the device state to be transitioned to. - * - The vendor driver should take the necessary actions to change the - * device state. After successful transition to a given state, the - * vendor driver should return success on write(device_state, state) - * system call. If the device state transition fails, the vendor driver - * should return an appropriate -errno for the fault condition. - * - On the user application side, if the device state transition fails, - * that is, if write(device_state, state) returns an error, read - * device_state again to determine the current state of the device from - * the vendor driver. - * - The vendor driver should return previous state of the device unless - * the vendor driver has encountered an internal error, in which case - * the vendor driver may report the device_state VFIO_DEVICE_STATE_ERROR. - * - The user application must use the device reset ioctl to recover the - * device from VFIO_DEVICE_STATE_ERROR state. If the device is - * indicated to be in a valid device state by reading device_state, the - * user application may attempt to transition the device to any valid - * state reachable from the current state or terminate itself. - * - * device_state consists of 3 bits: - * - If bit 0 is set, it indicates the _RUNNING state. If bit 0 is clear, - * it indicates the _STOP state. When the device state is changed to - * _STOP, driver should stop the device before write() returns. - * - If bit 1 is set, it indicates the _SAVING state, which means that the - * driver should start gathering device state information that will be - * provided to the VFIO user application to save the device's state. - * - If bit 2 is set, it indicates the _RESUMING state, which means that - * the driver should prepare to resume the device. Data provided through - * the migration region should be used to resume the device. - * Bits 3 - 31 are reserved for future use. To preserve them, the user - * application should perform a read-modify-write operation on this - * field when modifying the specified bits. - * - * +------- _RESUMING - * |+------ _SAVING - * ||+----- _RUNNING - * ||| - * 000b => Device Stopped, not saving or resuming - * 001b => Device running, which is the default state - * 010b => Stop the device & save the device state, stop-and-copy state - * 011b => Device running and save the device state, pre-copy state - * 100b => Device stopped and the device state is resuming - * 101b => Invalid state - * 110b => Error state - * 111b => Invalid state - * - * State transitions: - * - * _RESUMING _RUNNING Pre-copy Stop-and-copy _STOP - * (100b) (001b) (011b) (010b) (000b) - * 0. Running or default state - * | - * - * 1. Normal Shutdown (optional) - * |------------------------------------->| - * - * 2. Save the state or suspend - * |------------------------->|---------->| - * - * 3. Save the state during live migration - * |----------->|------------>|---------->| - * - * 4. Resuming - * |<---------| - * - * 5. Resumed - * |--------->| - * - * 0. Default state of VFIO device is _RUNNING when the user application starts. - * 1. During normal shutdown of the user application, the user application may - * optionally change the VFIO device state from _RUNNING to _STOP. This - * transition is optional. The vendor driver must support this transition but - * must not require it. - * 2. When the user application saves state or suspends the application, the - * device state transitions from _RUNNING to stop-and-copy and then to _STOP. - * On state transition from _RUNNING to stop-and-copy, driver must stop the - * device, save the device state and send it to the application through the - * migration region. The sequence to be followed for such transition is given - * below. - * 3. In live migration of user application, the state transitions from _RUNNING - * to pre-copy, to stop-and-copy, and to _STOP. - * On state transition from _RUNNING to pre-copy, the driver should start - * gathering the device state while the application is still running and send - * the device state data to application through the migration region. - * On state transition from pre-copy to stop-and-copy, the driver must stop - * the device, save the device state and send it to the user application - * through the migration region. - * Vendor drivers must support the pre-copy state even for implementations - * where no data is provided to the user before the stop-and-copy state. The - * user must not be required to consume all migration data before the device - * transitions to a new state, including the stop-and-copy state. - * The sequence to be followed for above two transitions is given below. - * 4. To start the resuming phase, the device state should be transitioned from - * the _RUNNING to the _RESUMING state. - * In the _RESUMING state, the driver should use the device state data - * received through the migration region to resume the device. - * 5. After providing saved device data to the driver, the application should - * change the state from _RESUMING to _RUNNING. - * - * reserved: - * Reads on this field return zero and writes are ignored. - * - * pending_bytes: (read only) - * The number of pending bytes still to be migrated from the vendor driver. - * - * data_offset: (read only) - * The user application should read data_offset field from the migration - * region. The user application should read the device data from this - * offset within the migration region during the _SAVING state or write - * the device data during the _RESUMING state. See below for details of - * sequence to be followed. - * - * data_size: (read/write) - * The user application should read data_size to get the size in bytes of - * the data copied in the migration region during the _SAVING state and - * write the size in bytes of the data copied in the migration region - * during the _RESUMING state. - * - * The format of the migration region is as follows: - * ------------------------------------------------------------------ - * |vfio_device_migration_info| data section | - * | | /////////////////////////////// | - * ------------------------------------------------------------------ - * ^ ^ - * offset 0-trapped part data_offset - * - * The structure vfio_device_migration_info is always followed by the data - * section in the region, so data_offset will always be nonzero. The offset - * from where the data is copied is decided by the kernel driver. The data - * section can be trapped, mmapped, or partitioned, depending on how the kernel - * driver defines the data section. The data section partition can be defined - * as mapped by the sparse mmap capability. If mmapped, data_offset must be - * page aligned, whereas initial section which contains the - * vfio_device_migration_info structure, might not end at the offset, which is - * page aligned. The user is not required to access through mmap regardless - * of the capabilities of the region mmap. - * The vendor driver should determine whether and how to partition the data - * section. The vendor driver should return data_offset accordingly. - * - * The sequence to be followed while in pre-copy state and stop-and-copy state - * is as follows: - * a. Read pending_bytes, indicating the start of a new iteration to get device - * data. Repeated read on pending_bytes at this stage should have no side - * effects. - * If pending_bytes == 0, the user application should not iterate to get data - * for that device. - * If pending_bytes > 0, perform the following steps. - * b. Read data_offset, indicating that the vendor driver should make data - * available through the data section. The vendor driver should return this - * read operation only after data is available from (region + data_offset) - * to (region + data_offset + data_size). - * c. Read data_size, which is the amount of data in bytes available through - * the migration region. - * Read on data_offset and data_size should return the offset and size of - * the current buffer if the user application reads data_offset and - * data_size more than once here. - * d. Read data_size bytes of data from (region + data_offset) from the - * migration region. - * e. Process the data. - * f. Read pending_bytes, which indicates that the data from the previous - * iteration has been read. If pending_bytes > 0, go to step b. - * - * The user application can transition from the _SAVING|_RUNNING - * (pre-copy state) to the _SAVING (stop-and-copy) state regardless of the - * number of pending bytes. The user application should iterate in _SAVING - * (stop-and-copy) until pending_bytes is 0. - * - * The sequence to be followed while _RESUMING device state is as follows: - * While data for this device is available, repeat the following steps: - * a. Read data_offset from where the user application should write data. - * b. Write migration data starting at the migration region + data_offset for - * the length determined by data_size from the migration source. - * c. Write data_size, which indicates to the vendor driver that data is - * written in the migration region. Vendor driver must return this write - * operations on consuming data. Vendor driver should apply the - * user-provided migration region data to the device resume state. - * - * If an error occurs during the above sequences, the vendor driver can return - * an error code for next read() or write() operation, which will terminate the - * loop. The user application should then take the next necessary action, for - * example, failing migration or terminating the user application. - * - * For the user application, data is opaque. The user application should write - * data in the same order as the data is received and the data should be of - * same transaction size at the source. - */ +#define VFIO_REGION_SUBTYPE_MIGRATION_DEPRECATED (1) struct vfio_device_migration_info { __u32 device_state; /* VFIO device state */ -- cgit v1.2.3 From 915076f70efad04bf6fc843970a3c7763487011a Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 24 Feb 2022 16:20:23 +0200 Subject: vfio/pci: Expose vfio_pci_core_aer_err_detected() Expose vfio_pci_core_aer_err_detected() to be used by drivers as part of their pci_error_handlers structure. Next patch for mlx5 driver will use it. Link: https://lore.kernel.org/all/20220224142024.147653-15-yishaih@nvidia.com Reviewed-by: Alex Williamson Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/vfio_pci_core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index beba0b2ed87d..9f1bf8e49d43 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -232,6 +232,8 @@ int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf); int vfio_pci_core_enable(struct vfio_pci_core_device *vdev); void vfio_pci_core_disable(struct vfio_pci_core_device *vdev); void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev); +pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev, + pci_channel_state_t state); static inline bool vfio_pci_is_vga(struct pci_dev *pdev) { -- cgit v1.2.3 From 3f8bab174cb26aa5a8053c4457cc733881e3ad88 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 3 Mar 2022 09:08:31 +0100 Subject: serial: make uart_console_write->putchar()'s character an unsigned char MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, uart_console_write->putchar's second parameter (the character) is of type int. It makes little sense, provided uart_console_write() accepts the input string as "const char *s" and passes its content -- the characters -- to putchar(). So switch the character's type to unsigned char. We don't use char as that is signed on some platforms. That would cause troubles for drivers which (implicitly) cast the char to u16 when writing to the device. Sign extension would happen in that case and the value written would be completely different to the provided char. DZ is an example of such a driver -- on MIPS, it uses u16 for dz_out in dz_console_putchar(). Note we do the char -> uchar conversion implicitly in uart_console_write(). Provided we do not change size of the data type, sign extension does not happen there, so the problem is void. This makes the types consistent and unified with the rest of the uart layer, which uses unsigned char in most places already. One exception is xmit_buf, but that is going to be converted later. Cc: Paul Cercueil Cc: Tobias Klauser Cc: Russell King Cc: Vineet Gupta Cc: Nicolas Ferre Cc: Alexandre Belloni Cc: Ludovic Desroches Cc: Florian Fainelli Cc: bcm-kernel-feedback-list@broadcom.com Cc: Alexander Shiyan Cc: Baruch Siach Cc: "Maciej W. Rozycki" Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Shawn Guo Cc: Sascha Hauer Cc: Pengutronix Kernel Team Cc: Fabio Estevam Cc: NXP Linux Team Cc: Karol Gugala Cc: Mateusz Holenko Cc: Vladimir Zapolskiy Cc: Neil Armstrong Cc: Kevin Hilman Cc: Jerome Brunet Cc: Martin Blumenstingl Cc: Taichi Sugaya Cc: Takao Orito Cc: Liviu Dudau Cc: Sudeep Holla Cc: Lorenzo Pieralisi Cc: "Andreas Färber" Cc: Manivannan Sadhasivam Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Andy Gross Cc: Bjorn Andersson Cc: Krzysztof Kozlowski Cc: Orson Zhai Cc: Baolin Wang Cc: Chunyan Zhang Cc: Patrice Chotard Cc: Maxime Coquelin Cc: Alexandre Torgue Cc: "David S. Miller" Cc: Peter Korsgaard Cc: Michal Simek Acked-by: Richard Genoud [atmel_serial] Acked-by: Uwe Kleine-König Acked-by: Paul Cercueil Acked-by: Neil Armstrong # meson_serial Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20220303080831.21783-1-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 31f7fe527395..14ae35f68abb 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -399,7 +399,7 @@ int uart_set_options(struct uart_port *port, struct console *co, int baud, struct tty_driver *uart_console_device(struct console *co, int *index); void uart_console_write(struct uart_port *port, const char *s, unsigned int count, - void (*putchar)(struct uart_port *, int)); + void (*putchar)(struct uart_port *, unsigned char)); /* * Port/driver registration/removal -- cgit v1.2.3 From f9cef64fa23f6c1ff177be5082113c5a94e34e5d Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 2 Mar 2022 21:14:13 +0200 Subject: net: dsa: felix: migrate host FDB and MDB entries when changing tag proto The "ocelot" and "ocelot-8021q" tagging protocols make use of different hardware resources, and host FDB entries have different destination ports in the switch analyzer module, practically speaking. So when the user requests a tagging protocol change, the driver must migrate all host FDB and MDB entries from the NPI port (in fact CPU port module) towards the same physical port, but this time used as a regular port. It is pointless for the felix driver to keep a copy of the host addresses, when we can create and export DSA helpers for walking through the addresses that it already needs to keep on the CPU port, for refcounting purposes. felix_classify_db() is moved up to avoid a forward declaration. We pass "bool change" because dp->fdbs and dp->mdbs are uninitialized lists when felix_setup() first calls felix_set_tag_protocol(), so we need to avoid calling dsa_port_walk_fdbs() during probe time. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/dsa.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index cfedcfb86350..71cc363dbbd4 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -1219,6 +1219,13 @@ struct dsa_switch_driver { struct net_device *dsa_dev_to_net_device(struct device *dev); +typedef int dsa_fdb_walk_cb_t(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid, + struct dsa_db db); + +int dsa_port_walk_fdbs(struct dsa_switch *ds, int port, dsa_fdb_walk_cb_t cb); +int dsa_port_walk_mdbs(struct dsa_switch *ds, int port, dsa_fdb_walk_cb_t cb); + /* Keep inline for faster access in hot path */ static inline bool netdev_uses_dsa(const struct net_device *dev) { -- cgit v1.2.3 From a1ac9c8acec1605c6b43af418f79facafdced680 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 2 Mar 2022 11:55:25 -0800 Subject: net: Add skb->mono_delivery_time to distinguish mono delivery_time from (rcv) timestamp skb->tstamp was first used as the (rcv) timestamp. The major usage is to report it to the user (e.g. SO_TIMESTAMP). Later, skb->tstamp is also set as the (future) delivery_time (e.g. EDT in TCP) during egress and used by the qdisc (e.g. sch_fq) to make decision on when the skb can be passed to the dev. Currently, there is no way to tell skb->tstamp having the (rcv) timestamp or the delivery_time, so it is always reset to 0 whenever forwarded between egress and ingress. While it makes sense to always clear the (rcv) timestamp in skb->tstamp to avoid confusing sch_fq that expects the delivery_time, it is a performance issue [0] to clear the delivery_time if the skb finally egress to a fq@phy-dev. For example, when forwarding from egress to ingress and then finally back to egress: tcp-sender => veth@netns => veth@hostns => fq@eth0@hostns ^ ^ reset rest This patch adds one bit skb->mono_delivery_time to flag the skb->tstamp is storing the mono delivery_time (EDT) instead of the (rcv) timestamp. The current use case is to keep the TCP mono delivery_time (EDT) and to be used with sch_fq. A latter patch will also allow tc-bpf@ingress to read and change the mono delivery_time. In the future, another bit (e.g. skb->user_delivery_time) can be added for the SCM_TXTIME where the clock base is tracked by sk->sk_clockid. [ This patch is a prep work. The following patches will get the other parts of the stack ready first. Then another patch after that will finally set the skb->mono_delivery_time. ] skb_set_delivery_time() function is added. It is used by the tcp_output.c and during ip[6] fragmentation to assign the delivery_time to the skb->tstamp and also set the skb->mono_delivery_time. A note on the change in ip_send_unicast_reply() in ip_output.c. It is only used by TCP to send reset/ack out of a ctl_sk. Like the new skb_set_delivery_time(), this patch sets the skb->mono_delivery_time to 0 for now as a place holder. It will be enabled in a latter patch. A similar case in tcp_ipv6 can be done with skb_set_delivery_time() in tcp_v6_send_response(). [0] (slide 22): https://linuxplumbersconf.org/event/11/contributions/953/attachments/867/1658/LPC_2021_BPF_Datapath_Extensions.pdf Signed-off-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/linux/skbuff.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d67941f78b92..803ffa63dea6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -795,6 +795,10 @@ typedef unsigned char *sk_buff_data_t; * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required + * @mono_delivery_time: When set, skb->tstamp has the + * delivery_time in mono clock base (i.e. EDT). Otherwise, the + * skb->tstamp has the (rcv) timestamp at ingress and + * delivery_time at egress. * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS * @secmark: security marking @@ -965,6 +969,7 @@ struct sk_buff { __u8 decrypted:1; #endif __u8 slow_gro:1; + __u8 mono_delivery_time:1; #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ @@ -3983,6 +3988,14 @@ static inline ktime_t net_timedelta(ktime_t t) return ktime_sub(ktime_get_real(), t); } +static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt, + bool mono) +{ + skb->tstamp = kt; + /* Setting mono_delivery_time will be enabled later */ + skb->mono_delivery_time = 0; +} + static inline u8 skb_metadata_len(const struct sk_buff *skb) { return skb_shinfo(skb)->meta_len; -- cgit v1.2.3 From de799101519aad23c6096041ba2744d7b5517e6a Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 2 Mar 2022 11:55:31 -0800 Subject: net: Add skb_clear_tstamp() to keep the mono delivery_time Right now, skb->tstamp is reset to 0 whenever the skb is forwarded. If skb->tstamp has the mono delivery_time, clearing it can hurt the performance when it finally transmits out to fq@phy-dev. The earlier patch added a skb->mono_delivery_time bit to flag the skb->tstamp carrying the mono delivery_time. This patch adds skb_clear_tstamp() helper which keeps the mono delivery_time and clears everything else. The delivery_time clearing will be postponed until the stack knows the skb will be delivered locally. It will be done in a latter patch. Signed-off-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/linux/skbuff.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 803ffa63dea6..27a28920e7b3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3996,6 +3996,14 @@ static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt, skb->mono_delivery_time = 0; } +static inline void skb_clear_tstamp(struct sk_buff *skb) +{ + if (skb->mono_delivery_time) + return; + + skb->tstamp = 0; +} + static inline u8 skb_metadata_len(const struct sk_buff *skb) { return skb_shinfo(skb)->meta_len; @@ -4852,7 +4860,7 @@ static inline void skb_set_redirected(struct sk_buff *skb, bool from_ingress) #ifdef CONFIG_NET_REDIRECT skb->from_ingress = from_ingress; if (skb->from_ingress) - skb->tstamp = 0; + skb_clear_tstamp(skb); #endif } -- cgit v1.2.3 From 27942a15209f564ed8ee2a9e126cb7b105181355 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 2 Mar 2022 11:55:38 -0800 Subject: net: Handle delivery_time in skb->tstamp during network tapping with af_packet A latter patch will set the skb->mono_delivery_time to flag the skb->tstamp is used as the mono delivery_time (EDT) instead of the (rcv) timestamp. skb_clear_tstamp() will then keep this delivery_time during forwarding. This patch is to make the network tapping (with af_packet) to handle the delivery_time stored in skb->tstamp. Regardless of tapping at the ingress or egress, the tapped skb is received by the af_packet socket, so it is ingress to the af_packet socket and it expects the (rcv) timestamp. When tapping at egress, dev_queue_xmit_nit() is used. It has already expected skb->tstamp may have delivery_time, so it does skb_clone()+net_timestamp_set() to ensure the cloned skb has the (rcv) timestamp before passing to the af_packet sk. This patch only adds to clear the skb->mono_delivery_time bit in net_timestamp_set(). When tapping at ingress, it currently expects the skb->tstamp is either 0 or the (rcv) timestamp. Meaning, the tapping at ingress path has already expected the skb->tstamp could be 0 and it will get the (rcv) timestamp by ktime_get_real() when needed. There are two cases for tapping at ingress: One case is af_packet queues the skb to its sk_receive_queue. The skb is either not shared or new clone created. The newly added skb_clear_delivery_time() is called to clear the delivery_time (if any) and set the (rcv) timestamp if needed before the skb is queued to the sk_receive_queue. Another case, the ingress skb is directly copied to the rx_ring and tpacket_get_timestamp() is used to get the (rcv) timestamp. The newly added skb_tstamp() is used in tpacket_get_timestamp() to check the skb->mono_delivery_time bit before returning skb->tstamp. As mentioned earlier, the tapping@ingress has already expected the skb may not have the (rcv) timestamp (because no sk has asked for it) and has handled this case by directly calling ktime_get_real(). Signed-off-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/linux/skbuff.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 27a28920e7b3..7e2d796ece80 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3996,6 +3996,22 @@ static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt, skb->mono_delivery_time = 0; } +DECLARE_STATIC_KEY_FALSE(netstamp_needed_key); + +/* It is used in the ingress path to clear the delivery_time. + * If needed, set the skb->tstamp to the (rcv) timestamp. + */ +static inline void skb_clear_delivery_time(struct sk_buff *skb) +{ + if (skb->mono_delivery_time) { + skb->mono_delivery_time = 0; + if (static_branch_unlikely(&netstamp_needed_key)) + skb->tstamp = ktime_get_real(); + else + skb->tstamp = 0; + } +} + static inline void skb_clear_tstamp(struct sk_buff *skb) { if (skb->mono_delivery_time) @@ -4004,6 +4020,14 @@ static inline void skb_clear_tstamp(struct sk_buff *skb) skb->tstamp = 0; } +static inline ktime_t skb_tstamp(const struct sk_buff *skb) +{ + if (skb->mono_delivery_time) + return 0; + + return skb->tstamp; +} + static inline u8 skb_metadata_len(const struct sk_buff *skb) { return skb_shinfo(skb)->meta_len; -- cgit v1.2.3 From d93376f503c7a586707925957592c0f16f4db0b1 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 2 Mar 2022 11:55:44 -0800 Subject: net: Clear mono_delivery_time bit in __skb_tstamp_tx() In __skb_tstamp_tx(), it may clone the egress skb and queues the clone to the sk_error_queue. The outgoing skb may have the mono delivery_time while the (rcv) timestamp is expected for the clone, so the skb->mono_delivery_time bit needs to be cleared from the clone. This patch adds the skb->mono_delivery_time clearing to the existing __net_timestamp() and use it in __skb_tstamp_tx(). The __net_timestamp() fast path usage in dev.c is changed to directly call ktime_get_real() since the mono_delivery_time bit is not set at that point. Signed-off-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7e2d796ece80..8e8a4af4f9e2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3981,6 +3981,7 @@ static inline void skb_get_new_timestampns(const struct sk_buff *skb, static inline void __net_timestamp(struct sk_buff *skb) { skb->tstamp = ktime_get_real(); + skb->mono_delivery_time = 0; } static inline ktime_t net_timedelta(ktime_t t) -- cgit v1.2.3 From d98d58a002619b5c165f1eedcd731e2fe2c19088 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 2 Mar 2022 11:55:50 -0800 Subject: net: Set skb->mono_delivery_time and clear it after sch_handle_ingress() The previous patches handled the delivery_time before sch_handle_ingress(). This patch can now set the skb->mono_delivery_time to flag the skb->tstamp is used as the mono delivery_time (EDT) instead of the (rcv) timestamp and also clear it with skb_clear_delivery_time() after sch_handle_ingress(). This will make the bpf_redirect_*() to keep the mono delivery_time and used by a qdisc (fq) of the egress-ing interface. A latter patch will postpone the skb_clear_delivery_time() until the stack learns that the skb is being delivered locally and that will make other kernel forwarding paths (ip[6]_forward) able to keep the delivery_time also. Thus, like the previous patches on using the skb->mono_delivery_time bit, calling skb_clear_delivery_time() is not limited within the CONFIG_NET_INGRESS to avoid too many code churns among this set. Signed-off-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 8e8a4af4f9e2..0f5fd53059cd 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3993,8 +3993,7 @@ static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt, bool mono) { skb->tstamp = kt; - /* Setting mono_delivery_time will be enabled later */ - skb->mono_delivery_time = 0; + skb->mono_delivery_time = kt && mono; } DECLARE_STATIC_KEY_FALSE(netstamp_needed_key); -- cgit v1.2.3 From 8672406eb5d77333ca14e9612e3166704b367c40 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 2 Mar 2022 11:55:57 -0800 Subject: net: ip: Handle delivery_time in ip defrag A latter patch will postpone the delivery_time clearing until the stack knows the skb is being delivered locally. That will allow other kernel forwarding path (e.g. ip[6]_forward) to keep the delivery_time also. An earlier attempt was to do skb_clear_delivery_time() in ip_local_deliver() and ip6_input(). The discussion [0] requested to move it one step later into ip_local_deliver_finish() and ip6_input_finish() so that the delivery_time can be kept for the ip_vs forwarding path also. To do that, this patch also needs to take care of the (rcv) timestamp usecase in ip_is_fragment(). It needs to expect delivery_time in the skb->tstamp, so it needs to save the mono_delivery_time bit in inet_frag_queue such that the delivery_time (if any) can be restored in the final defragmented skb. [Note that it will only happen when the locally generated skb is looping from egress to ingress over a virtual interface (e.g. veth, loopback...), skb->tstamp may have the delivery time before it is known that it will be delivered locally and received by another sk.] [0]: https://lore.kernel.org/netdev/ca728d81-80e8-3767-d5e-d44f6ad96e43@ssi.bg/ Signed-off-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/net/inet_frag.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 63540be0fc34..911ad930867d 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -70,6 +70,7 @@ struct frag_v6_compare_key { * @stamp: timestamp of the last received fragment * @len: total length of the original datagram * @meat: length of received fragments so far + * @mono_delivery_time: stamp has a mono delivery time (EDT) * @flags: fragment queue flags * @max_size: maximum received fragment size * @fqdir: pointer to struct fqdir @@ -90,6 +91,7 @@ struct inet_frag_queue { ktime_t stamp; int len; int meat; + u8 mono_delivery_time; __u8 flags; u16 max_size; struct fqdir *fqdir; -- cgit v1.2.3 From b6561f8491ca899e5a08311796085c9738d631ae Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 2 Mar 2022 11:56:09 -0800 Subject: net: ipv6: Get rcv timestamp if needed when handling hop-by-hop IOAM option IOAM is a hop-by-hop option with a temporary iana allocation (49). Since it is hop-by-hop, it is done before the input routing decision. One of the traced data field is the (rcv) timestamp. When the locally generated skb is looping from egress to ingress over a virtual interface (e.g. veth, loopback...), skb->tstamp may have the delivery time before it is known that it will be delivered locally and received by another sk. Like handling the network tapping (tcpdump) in the earlier patch, this patch gets the timestamp if needed without over-writing the delivery_time in the skb->tstamp. skb_tstamp_cond() is added to do the ktime_get_real() with an extra cond arg to check on top of the netstamp_needed_key static key. skb_tstamp_cond() will also be used in a latter patch and it needs the netstamp_needed_key check. Signed-off-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/linux/skbuff.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0f5fd53059cd..4b5b926a81f2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4028,6 +4028,17 @@ static inline ktime_t skb_tstamp(const struct sk_buff *skb) return skb->tstamp; } +static inline ktime_t skb_tstamp_cond(const struct sk_buff *skb, bool cond) +{ + if (!skb->mono_delivery_time && skb->tstamp) + return skb->tstamp; + + if (static_branch_unlikely(&netstamp_needed_key) || cond) + return ktime_get_real(); + + return 0; +} + static inline u8 skb_metadata_len(const struct sk_buff *skb) { return skb_shinfo(skb)->meta_len; -- cgit v1.2.3 From 7449197d600d30d038b1ce6285ab4747096eac7f Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 2 Mar 2022 11:56:28 -0800 Subject: bpf: Keep the (rcv) timestamp behavior for the existing tc-bpf@ingress The current tc-bpf@ingress reads and writes the __sk_buff->tstamp as a (rcv) timestamp which currently could either be 0 (not available) or ktime_get_real(). This patch is to backward compatible with the (rcv) timestamp expectation at ingress. If the skb->tstamp has the delivery_time, the bpf insn rewrite will read 0 for tc-bpf running at ingress as it is not available. When writing at ingress, it will also clear the skb->mono_delivery_time bit. /* BPF_READ: a = __sk_buff->tstamp */ if (!skb->tc_at_ingress || !skb->mono_delivery_time) a = skb->tstamp; else a = 0 /* BPF_WRITE: __sk_buff->tstamp = a */ if (skb->tc_at_ingress) skb->mono_delivery_time = 0; skb->tstamp = a; [ A note on the BPF_CGROUP_INET_INGRESS which can also access skb->tstamp. At that point, the skb is delivered locally and skb_clear_delivery_time() has already been done, so the skb->tstamp will only have the (rcv) timestamp. ] If the tc-bpf@egress writes 0 to skb->tstamp, the skb->mono_delivery_time has to be cleared also. It could be done together during convert_ctx_access(). However, the latter patch will also expose the skb->mono_delivery_time bit as __sk_buff->delivery_time_type. Changing the delivery_time_type in the background may surprise the user, e.g. the 2nd read on __sk_buff->delivery_time_type may need a READ_ONCE() to avoid compiler optimization. Thus, in expecting the needs in the latter patch, this patch does a check on !skb->tstamp after running the tc-bpf and clears the skb->mono_delivery_time bit if needed. The earlier discussion on v4 [0]. The bpf insn rewrite requires the skb's mono_delivery_time bit and tc_at_ingress bit. They are moved up in sk_buff so that bpf rewrite can be done at a fixed offset. tc_skip_classify is moved together with tc_at_ingress. To get one bit for mono_delivery_time, csum_not_inet is moved down and this bit is currently used by sctp. [0]: https://lore.kernel.org/bpf/20220217015043.khqwqklx45c4m4se@kafai-mbp.dhcp.thefacebook.com/ Signed-off-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/linux/skbuff.h | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4b5b926a81f2..5445860e1ba6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -941,8 +941,12 @@ struct sk_buff { __u8 vlan_present:1; /* See PKT_VLAN_PRESENT_BIT */ __u8 csum_complete_sw:1; __u8 csum_level:2; - __u8 csum_not_inet:1; __u8 dst_pending_confirm:1; + __u8 mono_delivery_time:1; +#ifdef CONFIG_NET_CLS_ACT + __u8 tc_skip_classify:1; + __u8 tc_at_ingress:1; +#endif #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif @@ -953,10 +957,6 @@ struct sk_buff { #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; __u8 offload_l3_fwd_mark:1; -#endif -#ifdef CONFIG_NET_CLS_ACT - __u8 tc_skip_classify:1; - __u8 tc_at_ingress:1; #endif __u8 redirected:1; #ifdef CONFIG_NET_REDIRECT @@ -969,7 +969,7 @@ struct sk_buff { __u8 decrypted:1; #endif __u8 slow_gro:1; - __u8 mono_delivery_time:1; + __u8 csum_not_inet:1; #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ @@ -1047,10 +1047,16 @@ struct sk_buff { /* if you move pkt_vlan_present around you also must adapt these constants */ #ifdef __BIG_ENDIAN_BITFIELD #define PKT_VLAN_PRESENT_BIT 7 +#define TC_AT_INGRESS_MASK (1 << 0) +#define SKB_MONO_DELIVERY_TIME_MASK (1 << 2) #else #define PKT_VLAN_PRESENT_BIT 0 +#define TC_AT_INGRESS_MASK (1 << 7) +#define SKB_MONO_DELIVERY_TIME_MASK (1 << 5) #endif #define PKT_VLAN_PRESENT_OFFSET offsetof(struct sk_buff, __pkt_vlan_present_offset) +#define TC_AT_INGRESS_OFFSET offsetof(struct sk_buff, __pkt_vlan_present_offset) +#define SKB_MONO_DELIVERY_TIME_OFFSET offsetof(struct sk_buff, __pkt_vlan_present_offset) #ifdef __KERNEL__ /* -- cgit v1.2.3 From 8d21ec0e46ed6e39994accff8eb4f2be3d2e76b5 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 2 Mar 2022 11:56:34 -0800 Subject: bpf: Add __sk_buff->delivery_time_type and bpf_skb_set_skb_delivery_time() * __sk_buff->delivery_time_type: This patch adds __sk_buff->delivery_time_type. It tells if the delivery_time is stored in __sk_buff->tstamp or not. It will be most useful for ingress to tell if the __sk_buff->tstamp has the (rcv) timestamp or delivery_time. If delivery_time_type is 0 (BPF_SKB_DELIVERY_TIME_NONE), it has the (rcv) timestamp. Two non-zero types are defined for the delivery_time_type, BPF_SKB_DELIVERY_TIME_MONO and BPF_SKB_DELIVERY_TIME_UNSPEC. For UNSPEC, it can only happen in egress because only mono delivery_time can be forwarded to ingress now. The clock of UNSPEC delivery_time can be deduced from the skb->sk->sk_clockid which is how the sch_etf doing it also. * Provide forwarded delivery_time to tc-bpf@ingress: With the help of the new delivery_time_type, the tc-bpf has a way to tell if the __sk_buff->tstamp has the (rcv) timestamp or the delivery_time. During bpf load time, the verifier will learn if the bpf prog has accessed the new __sk_buff->delivery_time_type. If it does, it means the tc-bpf@ingress is expecting the skb->tstamp could have the delivery_time. The kernel will then read the skb->tstamp as-is during bpf insn rewrite without checking the skb->mono_delivery_time. This is done by adding a new prog->delivery_time_access bit. The same goes for writing skb->tstamp. * bpf_skb_set_delivery_time(): The bpf_skb_set_delivery_time() helper is added to allow setting both delivery_time and the delivery_time_type at the same time. If the tc-bpf does not need to change the delivery_time_type, it can directly write to the __sk_buff->tstamp as the existing tc-bpf has already been doing. It will be most useful at ingress to change the __sk_buff->tstamp from the (rcv) timestamp to a mono delivery_time and then bpf_redirect_*(). bpf only has mono clock helper (bpf_ktime_get_ns), and the current known use case is the mono EDT for fq, and only mono delivery time can be kept during forward now, so bpf_skb_set_delivery_time() only supports setting BPF_SKB_DELIVERY_TIME_MONO. It can be extended later when use cases come up and the forwarding path also supports other clock bases. Signed-off-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/linux/filter.h | 3 ++- include/uapi/linux/bpf.h | 41 ++++++++++++++++++++++++++++++++++++++++- 2 files changed, 42 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 1cb1af917617..9bf26307247f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -572,7 +572,8 @@ struct bpf_prog { has_callchain_buf:1, /* callchain buffer allocated? */ enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ - call_get_func_ip:1; /* Do we call get_func_ip() */ + call_get_func_ip:1, /* Do we call get_func_ip() */ + delivery_time_access:1; /* Accessed __sk_buff->delivery_time_type */ enum bpf_prog_type type; /* Type of BPF program */ enum bpf_attach_type expected_attach_type; /* For some prog types */ u32 len; /* Number of filter blocks */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index afe3d0d7f5f2..4eebea830613 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5086,6 +5086,37 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. On error * *dst* buffer is zeroed out. + * + * long bpf_skb_set_delivery_time(struct sk_buff *skb, u64 dtime, u32 dtime_type) + * Description + * Set a *dtime* (delivery time) to the __sk_buff->tstamp and also + * change the __sk_buff->delivery_time_type to *dtime_type*. + * + * When setting a delivery time (non zero *dtime*) to + * __sk_buff->tstamp, only BPF_SKB_DELIVERY_TIME_MONO *dtime_type* + * is supported. It is the only delivery_time_type that will be + * kept after bpf_redirect_*(). + * + * If there is no need to change the __sk_buff->delivery_time_type, + * the delivery time can be directly written to __sk_buff->tstamp + * instead. + * + * *dtime* 0 and *dtime_type* BPF_SKB_DELIVERY_TIME_NONE + * can be used to clear any delivery time stored in + * __sk_buff->tstamp. + * + * Only IPv4 and IPv6 skb->protocol are supported. + * + * This function is most useful when it needs to set a + * mono delivery time to __sk_buff->tstamp and then + * bpf_redirect_*() to the egress of an iface. For example, + * changing the (rcv) timestamp in __sk_buff->tstamp at + * ingress to a mono delivery time and then bpf_redirect_*() + * to sch_fq@phy-dev. + * Return + * 0 on success. + * **-EINVAL** for invalid input + * **-EOPNOTSUPP** for unsupported delivery_time_type and protocol */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5280,6 +5311,7 @@ union bpf_attr { FN(xdp_load_bytes), \ FN(xdp_store_bytes), \ FN(copy_from_user_task), \ + FN(skb_set_delivery_time), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5469,6 +5501,12 @@ union { \ __u64 :64; \ } __attribute__((aligned(8))) +enum { + BPF_SKB_DELIVERY_TIME_NONE, + BPF_SKB_DELIVERY_TIME_UNSPEC, + BPF_SKB_DELIVERY_TIME_MONO, +}; + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ @@ -5509,7 +5547,8 @@ struct __sk_buff { __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); __u32 gso_size; - __u32 :32; /* Padding, future use. */ + __u8 delivery_time_type; + __u32 :24; /* Padding, future use. */ __u64 hwtstamp; }; -- cgit v1.2.3 From 5c3f1f9cc4cbbf491233982b5975ae2d284de5df Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 16 Feb 2022 15:31:35 +1100 Subject: mm: remove the __KERNEL__ guard from __KERNEL__ ifdefs don't make sense outside of include/uapi/. Link: https://lkml.kernel.org/r/20220210072828.2930359-3-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Logan Gunthorpe Reviewed-by: Jason Gunthorpe Reviewed-by: Chaitanya Kulkarni Reviewed-by: Muchun Song Reviewed-by: Dan Williams Tested-by: "Sierra Guiza, Alejandro (Alex)" Cc: Alex Deucher Cc: Alistair Popple Cc: Ben Skeggs Cc: Christian Knig Cc: Felix Kuehling Cc: Karol Herbst Cc: Lyude Paul Cc: Miaohe Lin Cc: "Pan, Xinhui" Cc: Ralph Campbell Signed-off-by: Andrew Morton Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/mm.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 74ee50c2033b..2cca8cd30186 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3,9 +3,6 @@ #define _LINUX_MM_H #include - -#ifdef __KERNEL__ - #include #include #include @@ -3379,5 +3376,4 @@ madvise_set_anon_name(struct mm_struct *mm, unsigned long start, } #endif -#endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ -- cgit v1.2.3 From 730ff52194cdb324b7680e5054c546f7b52de8a2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 16 Feb 2022 15:31:35 +1100 Subject: mm: remove pointless includes from hmm.h pulls in the world for no good reason at all. Remove the includes and push a few ones into the users instead. Link: https://lkml.kernel.org/r/20220210072828.2930359-4-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Logan Gunthorpe Reviewed-by: Jason Gunthorpe Reviewed-by: Chaitanya Kulkarni Reviewed-by: Muchun Song Tested-by: "Sierra Guiza, Alejandro (Alex)" Cc: Alex Deucher Cc: Alistair Popple Cc: Ben Skeggs Cc: Christian Knig Cc: Dan Williams Cc: Felix Kuehling Cc: Karol Herbst Cc: Lyude Paul Cc: Miaohe Lin Cc: "Pan, Xinhui" Cc: Ralph Campbell Signed-off-by: Andrew Morton Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/hmm.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 2fd2e91d5107..d5a6f101f843 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -9,14 +9,9 @@ #ifndef LINUX_HMM_H #define LINUX_HMM_H -#include -#include +#include -#include -#include -#include -#include -#include +struct mmu_interval_notifier; /* * On output: -- cgit v1.2.3 From 75e55d8a107edb2fd6e02b1fa8a81531209cda04 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 16 Feb 2022 15:31:35 +1100 Subject: mm: move free_devmap_managed_page to memremap.c free_devmap_managed_page has nothing to do with the code in swap.c, move it to live with the rest of the code for devmap handling. Link: https://lkml.kernel.org/r/20220210072828.2930359-5-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Logan Gunthorpe Reviewed-by: Jason Gunthorpe Reviewed-by: Chaitanya Kulkarni Reviewed-by: Muchun Song Reviewed-by: Dan Williams Tested-by: "Sierra Guiza, Alejandro (Alex)" Cc: Alex Deucher Cc: Alistair Popple Cc: Ben Skeggs Cc: Christian Knig Cc: Felix Kuehling Cc: Karol Herbst Cc: Lyude Paul Cc: Miaohe Lin Cc: "Pan, Xinhui" Cc: Ralph Campbell Signed-off-by: Andrew Morton Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2cca8cd30186..a9d6473fc045 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1092,7 +1092,6 @@ static inline bool is_zone_movable_page(const struct page *page) } #ifdef CONFIG_DEV_PAGEMAP_OPS -void free_devmap_managed_page(struct page *page); DECLARE_STATIC_KEY_FALSE(devmap_managed_key); static inline bool page_is_devmap_managed(struct page *page) -- cgit v1.2.3 From 895749455f6054e0c7b40a6ec449a3ab6db51bdd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 16 Feb 2022 15:31:35 +1100 Subject: mm: simplify freeing of devmap managed pages Make put_devmap_managed_page return if it took charge of the page or not and remove the separate page_is_devmap_managed helper. Link: https://lkml.kernel.org/r/20220210072828.2930359-6-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Logan Gunthorpe Reviewed-by: Jason Gunthorpe Reviewed-by: Chaitanya Kulkarni Reviewed-by: Dan Williams Tested-by: "Sierra Guiza, Alejandro (Alex)" Cc: Alex Deucher Cc: Alistair Popple Cc: Ben Skeggs Cc: Christian Knig Cc: Felix Kuehling Cc: Karol Herbst Cc: Lyude Paul Cc: Miaohe Lin Cc: Muchun Song Cc: "Pan, Xinhui" Cc: Ralph Campbell Signed-off-by: Andrew Morton Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/mm.h | 34 ++++++++++------------------------ 1 file changed, 10 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index a9d6473fc045..8a59f0456149 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1094,33 +1094,24 @@ static inline bool is_zone_movable_page(const struct page *page) #ifdef CONFIG_DEV_PAGEMAP_OPS DECLARE_STATIC_KEY_FALSE(devmap_managed_key); -static inline bool page_is_devmap_managed(struct page *page) +bool __put_devmap_managed_page(struct page *page); +static inline bool put_devmap_managed_page(struct page *page) { if (!static_branch_unlikely(&devmap_managed_key)) return false; if (!is_zone_device_page(page)) return false; - switch (page->pgmap->type) { - case MEMORY_DEVICE_PRIVATE: - case MEMORY_DEVICE_FS_DAX: - return true; - default: - break; - } - return false; + if (page->pgmap->type != MEMORY_DEVICE_PRIVATE && + page->pgmap->type != MEMORY_DEVICE_FS_DAX) + return false; + return __put_devmap_managed_page(page); } -void put_devmap_managed_page(struct page *page); - #else /* CONFIG_DEV_PAGEMAP_OPS */ -static inline bool page_is_devmap_managed(struct page *page) +static inline bool put_devmap_managed_page(struct page *page) { return false; } - -static inline void put_devmap_managed_page(struct page *page) -{ -} #endif /* CONFIG_DEV_PAGEMAP_OPS */ static inline bool is_device_private_page(const struct page *page) @@ -1220,16 +1211,11 @@ static inline void put_page(struct page *page) struct folio *folio = page_folio(page); /* - * For devmap managed pages we need to catch refcount transition from - * 2 to 1, when refcount reach one it means the page is free and we - * need to inform the device driver through callback. See - * include/linux/memremap.h and HMM for details. + * For some devmap managed pages we need to catch refcount transition + * from 2 to 1: */ - if (page_is_devmap_managed(&folio->page)) { - put_devmap_managed_page(&folio->page); + if (put_devmap_managed_page(&folio->page)) return; - } - folio_put(folio); } -- cgit v1.2.3 From dc90f0846df4870b6cc8528c31e5c60f18fb68be Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 16 Feb 2022 15:31:36 +1100 Subject: mm: don't include in Move the check for the actual pgmap types that need the free at refcount one behavior into the out of line helper, and thus avoid the need to pull memremap.h into mm.h. Link: https://lkml.kernel.org/r/20220210072828.2930359-7-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Logan Gunthorpe Reviewed-by: Jason Gunthorpe Reviewed-by: Dan Williams Acked-by: Felix Kuehling Tested-by: "Sierra Guiza, Alejandro (Alex)" Cc: Alex Deucher Cc: Alistair Popple Cc: Ben Skeggs Cc: Chaitanya Kulkarni Cc: Karol Herbst Cc: Lyude Paul Cc: Miaohe Lin Cc: Muchun Song Cc: "Pan, Xinhui" Cc: Ralph Campbell Signed-off-by: Andrew Morton Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/memremap.h | 18 ++++++++++++++++++ include/linux/mm.h | 20 -------------------- 2 files changed, 18 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 1fafcc38acba..514ab46f597e 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -1,6 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MEMREMAP_H_ #define _LINUX_MEMREMAP_H_ + +#include #include #include #include @@ -129,6 +131,22 @@ static inline unsigned long pgmap_vmemmap_nr(struct dev_pagemap *pgmap) return 1 << pgmap->vmemmap_shift; } +static inline bool is_device_private_page(const struct page *page) +{ + return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) && + IS_ENABLED(CONFIG_DEVICE_PRIVATE) && + is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_PRIVATE; +} + +static inline bool is_pci_p2pdma_page(const struct page *page) +{ + return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) && + IS_ENABLED(CONFIG_PCI_P2PDMA) && + is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; +} + #ifdef CONFIG_ZONE_DEVICE void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); diff --git a/include/linux/mm.h b/include/linux/mm.h index 8a59f0456149..cb8bee88e70c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -23,7 +23,6 @@ #include #include #include -#include #include #include #include @@ -1101,9 +1100,6 @@ static inline bool put_devmap_managed_page(struct page *page) return false; if (!is_zone_device_page(page)) return false; - if (page->pgmap->type != MEMORY_DEVICE_PRIVATE && - page->pgmap->type != MEMORY_DEVICE_FS_DAX) - return false; return __put_devmap_managed_page(page); } @@ -1114,22 +1110,6 @@ static inline bool put_devmap_managed_page(struct page *page) } #endif /* CONFIG_DEV_PAGEMAP_OPS */ -static inline bool is_device_private_page(const struct page *page) -{ - return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) && - IS_ENABLED(CONFIG_DEVICE_PRIVATE) && - is_zone_device_page(page) && - page->pgmap->type == MEMORY_DEVICE_PRIVATE; -} - -static inline bool is_pci_p2pdma_page(const struct page *page) -{ - return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) && - IS_ENABLED(CONFIG_PCI_P2PDMA) && - is_zone_device_page(page) && - page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; -} - /* 127: arbitrary random number, small enough to assemble well */ #define folio_ref_zero_or_close_to_overflow(folio) \ ((unsigned int) folio_ref_count(folio) + 127u <= 127u) -- cgit v1.2.3 From 27674ef6c73f0c9096a9827dc5d6ba9fc7808422 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 16 Feb 2022 15:31:36 +1100 Subject: mm: remove the extra ZONE_DEVICE struct page refcount ZONE_DEVICE struct pages have an extra reference count that complicates the code for put_page() and several places in the kernel that need to check the reference count to see that a page is not being used (gup, compaction, migration, etc.). Clean up the code so the reference count doesn't need to be treated specially for ZONE_DEVICE pages. Note that this excludes the special idle page wakeup for fsdax pages, which still happens at refcount 1. This is a separate issue and will be sorted out later. Given that only fsdax pages require the notifiacation when the refcount hits 1 now, the PAGEMAP_OPS Kconfig symbol can go away and be replaced with a FS_DAX check for this hook in the put_page fastpath. Based on an earlier patch from Ralph Campbell . Link: https://lkml.kernel.org/r/20220210072828.2930359-8-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Logan Gunthorpe Reviewed-by: Ralph Campbell Reviewed-by: Jason Gunthorpe Reviewed-by: Dan Williams Acked-by: Felix Kuehling Tested-by: "Sierra Guiza, Alejandro (Alex)" Cc: Alex Deucher Cc: Alistair Popple Cc: Ben Skeggs Cc: Chaitanya Kulkarni Cc: Christian Knig Cc: Karol Herbst Cc: Lyude Paul Cc: Miaohe Lin Cc: Muchun Song Cc: "Pan, Xinhui" Signed-off-by: Andrew Morton Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/memremap.h | 12 +++++------- include/linux/mm.h | 6 +++--- 2 files changed, 8 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 514ab46f597e..d6a114dd5ea8 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -68,9 +68,9 @@ enum memory_type { struct dev_pagemap_ops { /* - * Called once the page refcount reaches 1. (ZONE_DEVICE pages never - * reach 0 refcount unless there is a refcount bug. This allows the - * device driver to implement its own memory management.) + * Called once the page refcount reaches 0. The reference count will be + * reset to one by the core code after the method is called to prepare + * for handing out the page again. */ void (*page_free)(struct page *page); @@ -133,16 +133,14 @@ static inline unsigned long pgmap_vmemmap_nr(struct dev_pagemap *pgmap) static inline bool is_device_private_page(const struct page *page) { - return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) && - IS_ENABLED(CONFIG_DEVICE_PRIVATE) && + return IS_ENABLED(CONFIG_DEVICE_PRIVATE) && is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_PRIVATE; } static inline bool is_pci_p2pdma_page(const struct page *page) { - return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) && - IS_ENABLED(CONFIG_PCI_P2PDMA) && + return IS_ENABLED(CONFIG_PCI_P2PDMA) && is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; } diff --git a/include/linux/mm.h b/include/linux/mm.h index cb8bee88e70c..0201d258c646 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1090,7 +1090,7 @@ static inline bool is_zone_movable_page(const struct page *page) return page_zonenum(page) == ZONE_MOVABLE; } -#ifdef CONFIG_DEV_PAGEMAP_OPS +#if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_FS_DAX) DECLARE_STATIC_KEY_FALSE(devmap_managed_key); bool __put_devmap_managed_page(struct page *page); @@ -1103,12 +1103,12 @@ static inline bool put_devmap_managed_page(struct page *page) return __put_devmap_managed_page(page); } -#else /* CONFIG_DEV_PAGEMAP_OPS */ +#else /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ static inline bool put_devmap_managed_page(struct page *page) { return false; } -#endif /* CONFIG_DEV_PAGEMAP_OPS */ +#endif /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ /* 127: arbitrary random number, small enough to assemble well */ #define folio_ref_zero_or_close_to_overflow(folio) \ -- cgit v1.2.3 From dc4e8c07e9e2f69387579c49caca26ba239f7270 Mon Sep 17 00:00:00 2001 From: Shuai Xue Date: Sun, 27 Feb 2022 20:25:45 +0800 Subject: ACPI: APEI: explicit init of HEST and GHES in apci_init() From commit e147133a42cb ("ACPI / APEI: Make hest.c manage the estatus memory pool") was merged, ghes_init() relies on acpi_hest_init() to manage the estatus memory pool. On the other hand, ghes_init() relies on sdei_init() to detect the SDEI version and (un)register events. The dependencies are as follows: ghes_init() => acpi_hest_init() => acpi_bus_init() => acpi_init() ghes_init() => sdei_init() HEST is not PCI-specific and initcall ordering is implicit and not well-defined within a level. Based on above, remove acpi_hest_init() from acpi_pci_root_init() and convert ghes_init() and sdei_init() from initcalls to explicit calls in the following order: acpi_hest_init() ghes_init() sdei_init() Signed-off-by: Shuai Xue Signed-off-by: Rafael J. Wysocki --- include/acpi/apei.h | 4 +++- include/linux/arm_sdei.h | 2 ++ 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/apei.h b/include/acpi/apei.h index ece0a8af2bae..4e60dd73c3bb 100644 --- a/include/acpi/apei.h +++ b/include/acpi/apei.h @@ -27,14 +27,16 @@ extern int hest_disable; extern int erst_disable; #ifdef CONFIG_ACPI_APEI_GHES extern bool ghes_disable; +void __init ghes_init(void); #else #define ghes_disable 1 +static inline void ghes_init(void) { } #endif #ifdef CONFIG_ACPI_APEI void __init acpi_hest_init(void); #else -static inline void acpi_hest_init(void) { return; } +static inline void acpi_hest_init(void) { } #endif int erst_write(const struct cper_record_header *record); diff --git a/include/linux/arm_sdei.h b/include/linux/arm_sdei.h index 0a241c5c911d..14dc461b0e82 100644 --- a/include/linux/arm_sdei.h +++ b/include/linux/arm_sdei.h @@ -46,9 +46,11 @@ int sdei_unregister_ghes(struct ghes *ghes); /* For use by arch code when CPU hotplug notifiers are not appropriate. */ int sdei_mask_local_cpu(void); int sdei_unmask_local_cpu(void); +void __init sdei_init(void); #else static inline int sdei_mask_local_cpu(void) { return 0; } static inline int sdei_unmask_local_cpu(void) { return 0; } +static inline void sdei_init(void) { } #endif /* CONFIG_ARM_SDE_INTERFACE */ -- cgit v1.2.3 From 27e932a31496f75b78ea41fd5ccadd0f75d8e8be Mon Sep 17 00:00:00 2001 From: Shuai Xue Date: Sun, 27 Feb 2022 20:25:46 +0800 Subject: ACPI: APEI: rename ghes_init() with an "acpi_" prefix ghes_init() sticks out in acpi_init() because it is the only functions without an "acpi_" prefix. Rename ghes_init with an "acpi_" prefix, then all looks fine. Signed-off-by: Shuai Xue Signed-off-by: Rafael J. Wysocki --- include/acpi/apei.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/acpi/apei.h b/include/acpi/apei.h index 4e60dd73c3bb..afaca3a075e8 100644 --- a/include/acpi/apei.h +++ b/include/acpi/apei.h @@ -27,10 +27,10 @@ extern int hest_disable; extern int erst_disable; #ifdef CONFIG_ACPI_APEI_GHES extern bool ghes_disable; -void __init ghes_init(void); +void __init acpi_ghes_init(void); #else #define ghes_disable 1 -static inline void ghes_init(void) { } +static inline void acpi_ghes_init(void) { } #endif #ifdef CONFIG_ACPI_APEI -- cgit v1.2.3 From f17bc788f7b97c36b8f3fbef14555a2a16ee3f69 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 13 Jan 2022 17:00:41 +0200 Subject: media: media-entity: Add media_pad_is_streaming() helper function Add a function to test if a pad is part of a pipeline currently streaming, and use it through drivers to replace direct access to the stream_count field. This will help reworking pipeline start/stop without disturbing drivers. Signed-off-by: Laurent Pinchart Signed-off-by: Sakari Ailus --- include/media/media-entity.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/media/media-entity.h b/include/media/media-entity.h index fea489f03d57..8546f13c42a9 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -858,6 +858,18 @@ struct media_link *media_entity_find_link(struct media_pad *source, */ struct media_pad *media_entity_remote_pad(const struct media_pad *pad); +/** + * media_entity_is_streaming - Test if an entity is part of a streaming pipeline + * @entity: The entity + * + * Return: True if the entity is part of a pipeline started with the + * media_pipeline_start() function, false otherwise. + */ +static inline bool media_entity_is_streaming(const struct media_entity *entity) +{ + return entity->stream_count > 0; +} + /** * media_entity_get_fwnode_pad - Get pad number from fwnode * -- cgit v1.2.3 From 3056a8e936bb090865402bfe6f3a730a28790033 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 13 Jan 2022 17:00:42 +0200 Subject: media: media-entity: Simplify media_pipeline_start() The media_pipeline_start() function has two purposes: it constructs a pipeline by recording the entities that are part of it, gathered from a graph walk, and validate the media links. The pipeline pointer is stored in the media_entity structure as part of this process, and the entity's stream count is increased, to record that the entity is streaming. When multiple video nodes are present in a pipeline, media_pipeline_start() is typically called on all of them, with the same pipeline pointer. This is taken into account in media_pipeline_start() by skipping validation for entities that are already part of the pipeline, while returning an error if an entity is part of a different pipeline. It turns out that this process is overly complicated. When media_pipeline_start() is called for the first time, it constructs the full pipeline, adding all entities and validating all the links. Subsequent calls to media_pipeline_start() are then nearly no-ops, they only increase the stream count on the pipeline and on all entities. The media_entity stream_count field is used for two purposes: checking if the entity is streaming, and detecting when a call to media_pipeline_stop() balances needs to reset the entity pipe pointer to NULL. The former can easily be replaced by a check of the pipe pointer. Simplify media_pipeline_start() by avoiding the pipeline walk on all calls but the first one, and drop the media_entity stream_count field. media_pipeline_stop() is updated accordingly. Signed-off-by: Laurent Pinchart [Sakari Ailus: Drop redundant '!= NULL' as discussed] Signed-off-by: Sakari Ailus --- include/media/media-entity.h | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/media/media-entity.h b/include/media/media-entity.h index 8546f13c42a9..33ee595c13f4 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -268,7 +268,6 @@ enum media_entity_type { * @pads: Pads array with the size defined by @num_pads. * @links: List of data links. * @ops: Entity operations. - * @stream_count: Stream count for the entity. * @use_count: Use count for the entity. * @pipe: Pipeline this entity belongs to. * @info: Union with devnode information. Kept just for backward @@ -283,10 +282,9 @@ enum media_entity_type { * * .. note:: * - * @stream_count and @use_count reference counts must never be - * negative, but are signed integers on purpose: a simple ``WARN_ON(<0)`` - * check can be used to detect reference count bugs that would make them - * negative. + * The @use_count reference count must never be negative, but is a signed + * integer on purpose: a simple ``WARN_ON(<0)`` check can be used to detect + * reference count bugs that would make it negative. */ struct media_entity { struct media_gobj graph_obj; /* must be first field in struct */ @@ -305,7 +303,6 @@ struct media_entity { const struct media_entity_operations *ops; - int stream_count; int use_count; struct media_pipeline *pipe; @@ -867,7 +864,7 @@ struct media_pad *media_entity_remote_pad(const struct media_pad *pad); */ static inline bool media_entity_is_streaming(const struct media_entity *entity) { - return entity->stream_count > 0; + return entity->pipe; } /** -- cgit v1.2.3 From 443bf23d0048e014065d1a7fac8144fb0a40805b Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 24 Feb 2022 14:57:47 +0200 Subject: media: media-entity: Clarify media_entity_cleanup() usage Being able to call cleanup functions on objects that haven't been initialized but whose memory has been zeroed simplifies error handling. The media_entity_cleanup() function documentation doesn't tell whether this is allowed or not, and inspection of its implementation doesn't provide any clue as the function is currently empty. Update the documentation to explicitly allow this usage pattern. Signed-off-by: Laurent Pinchart Signed-off-by: Sakari Ailus --- include/media/media-entity.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/media/media-entity.h b/include/media/media-entity.h index 33ee595c13f4..742918962d46 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -654,6 +654,10 @@ int media_entity_pads_init(struct media_entity *entity, u16 num_pads, * * This function must be called during the cleanup phase after unregistering * the entity (currently, it does nothing). + * + * Calling media_entity_cleanup() on a media_entity whose memory has been + * zeroed but that has not been initialized with media_entity_pad_init() is + * valid and is a no-op. */ #if IS_ENABLED(CONFIG_MEDIA_CONTROLLER) static inline void media_entity_cleanup(struct media_entity *entity) {} -- cgit v1.2.3 From 51ef2be546e2e480e56fdb59fdeb9a4406e8d52e Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 17 Feb 2022 16:44:07 +0100 Subject: media: i2c: isl7998x: Add driver for Intersil ISL7998x Add driver for the Intersil ISL7998x Analog to MIPI CSI-2/BT656 decoder. This chip supports 1/2/4 analog video inputs and converts them into 1/2/4 VCs in MIPI CSI2 stream. This driver currently supports ISL79987 and both 720x480 and 720x576 resolutions, however as per specification, all inputs must use the same resolution and standard. The only supported pixel format is now YUYV/YUV422. The chip should support RGB565 on the CSI2 as well, but this is currently unsupported. Signed-off-by: Marek Vasut Cc: Sakari Ailus Cc: Mauro Carvalho Chehab Cc: Rob Herring To: linux-media@vger.kernel.org Signed-off-by: Michael Tretter Acked-by: Hans Verkuil [Sakari Ailus: Always call pm_runtime_get_and_resume in pre_streamon] Signed-off-by: Sakari Ailus --- include/uapi/linux/v4l2-controls.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index c8e0f84d204d..92576ed03fc4 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -219,6 +219,12 @@ enum v4l2_colorfx { */ #define V4L2_CID_USER_ALLEGRO_BASE (V4L2_CID_USER_BASE + 0x1170) +/* + * The base for the isl7998x driver controls. + * We reserve 16 controls for this driver. + */ +#define V4L2_CID_USER_ISL7998X_BASE (V4L2_CID_USER_BASE + 0x1180) + /* MPEG-class control IDs */ /* The MPEG controls are applicable to all codec controls * and the 'MPEG' part of the define is historical */ -- cgit v1.2.3 From b70f5cd874ccf85c20882e12ba75a61a11ce4018 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 24 Feb 2022 01:11:29 +0100 Subject: media: noon010p30: Convert to use GPIO descriptors The noon010pc30 sensor driver is using legacy gpio numbers passed through platform data and open coding reverse polarity on the GPIOs used for reset and standby. Nothing in the kernel defines any platform data for this driver so we can just convert the driver to use GPIO descriptors and requires that these specify the correct polarity instead. Cc: Sylwester Nawrocki Cc: Hans Verkuil Signed-off-by: Linus Walleij Signed-off-by: Sakari Ailus --- include/media/i2c/noon010pc30.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/media/i2c/noon010pc30.h b/include/media/i2c/noon010pc30.h index d1b2e06a1de0..1880dad25cf0 100644 --- a/include/media/i2c/noon010pc30.h +++ b/include/media/i2c/noon010pc30.h @@ -12,14 +12,10 @@ /** * struct noon010pc30_platform_data - platform data * @clk_rate: the clock frequency in Hz - * @gpio_nreset: GPIO driving nRESET pin - * @gpio_nstby: GPIO driving nSTBY pin */ struct noon010pc30_platform_data { unsigned long clk_rate; - int gpio_nreset; - int gpio_nstby; }; #endif /* NOON010PC30_H */ -- cgit v1.2.3 From aaaf357fa61c00376cd8718d36bf06b7f0cbeead Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 24 Feb 2022 01:13:07 +0100 Subject: media: m5mols: Convert to use GPIO descriptors The Fujitsu M5MOLS sensor driver is using a reset GPIO number passed from platform data. No machine/board descriptor file in the kernel is using this so let's replace it with a GPIO descriptor. Cc: Kyungmin Park Cc: Heungjun Kim Signed-off-by: Linus Walleij Signed-off-by: Sakari Ailus --- include/media/i2c/m5mols.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/media/i2c/m5mols.h b/include/media/i2c/m5mols.h index 9cec5a09e125..a56ae353c891 100644 --- a/include/media/i2c/m5mols.h +++ b/include/media/i2c/m5mols.h @@ -14,15 +14,11 @@ /** * struct m5mols_platform_data - platform data for M-5MOLS driver - * @gpio_reset: GPIO driving the reset pin of M-5MOLS - * @reset_polarity: active state for gpio_reset pin, 0 or 1 * @set_power: an additional callback to the board setup code * to be called after enabling and before disabling * the sensor's supply regulators */ struct m5mols_platform_data { - int gpio_reset; - u8 reset_polarity; int (*set_power)(struct device *dev, int on); }; -- cgit v1.2.3 From 2d684f4e155c1e80ff63bd503930171c460eac5b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Martin=20J=C3=BCcker?= Date: Sat, 29 Jan 2022 23:01:53 +0100 Subject: drm/exynos: fimd: add BGR support for exynos4/5 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In the downstream kernels for exynos4 and exynos5 devices, there is an undocumented register that controls the order of the RGB output. It can be set to either normal order or reversed, which enables BGR support for those SoCs. This patch enables the BGR support for all the SoCs that were found to have at least one device with this logic in the corresponding downstream kernels. Signed-off-by: Martin Jücker Signed-off-by: Inki Dae --- include/video/samsung_fimd.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/video/samsung_fimd.h b/include/video/samsung_fimd.h index c4a93ce1de48..e6966d187591 100644 --- a/include/video/samsung_fimd.h +++ b/include/video/samsung_fimd.h @@ -476,6 +476,10 @@ * 1111 -none- -none- -none- -none- -none- */ +#define WIN_RGB_ORDER(_win) (0x2020 + ((_win) * 4)) +#define WIN_RGB_ORDER_FORWARD (0 << 11) +#define WIN_RGB_ORDER_REVERSE (1 << 11) + /* FIMD Version 8 register offset definitions */ #define FIMD_V8_VIDTCON0 0x20010 #define FIMD_V8_VIDTCON1 0x20014 -- cgit v1.2.3 From 31b9887c7258ca47d9c665a80f19f006c86756b1 Mon Sep 17 00:00:00 2001 From: Jamie Iles Date: Mon, 17 Jan 2022 17:48:15 +0000 Subject: i3c: remove i2c board info from i2c_dev_desc I2C board info is only required during adapter setup so there is no requirement to keeping a pointer to it once running. To support dynamic device addition we can't rely on board info - user-space creation through sysfs won't have a boardinfo. Cc: Alexandre Belloni Signed-off-by: Jamie Iles Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20220117174816.1963463-2-quic_jiles@quicinc.com --- include/linux/i3c/master.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h index 9cb39d901cd5..604a126b78c8 100644 --- a/include/linux/i3c/master.h +++ b/include/linux/i3c/master.h @@ -85,7 +85,6 @@ struct i2c_dev_boardinfo { */ struct i2c_dev_desc { struct i3c_i2c_dev_desc common; - const struct i2c_dev_boardinfo *boardinfo; struct i2c_client *dev; u16 addr; u8 lvr; -- cgit v1.2.3 From 98b4d7a4e7374a44c4afd9f08330e72f6ad0d644 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Fri, 4 Mar 2022 14:00:40 +0800 Subject: net: dev: use kfree_skb_reason() for sch_handle_egress() Replace kfree_skb() used in sch_handle_egress() with kfree_skb_reason(). The drop reason SKB_DROP_REASON_TC_EGRESS is introduced. Considering the code path of tc egerss, we make it distinct with the drop reason of SKB_DROP_REASON_QDISC_DROP in the next commit. Signed-off-by: Menglong Dong Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + include/trace/events/skb.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5445860e1ba6..1ffe64616741 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -394,6 +394,7 @@ enum skb_drop_reason { * entry is full */ SKB_DROP_REASON_NEIGH_DEAD, /* neigh entry is dead */ + SKB_DROP_REASON_TC_EGRESS, /* dropped in TC egress HOOK */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 1977f301260d..53755e8191a1 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -45,6 +45,7 @@ EM(SKB_DROP_REASON_NEIGH_FAILED, NEIGH_FAILED) \ EM(SKB_DROP_REASON_NEIGH_QUEUEFULL, NEIGH_QUEUEFULL) \ EM(SKB_DROP_REASON_NEIGH_DEAD, NEIGH_DEAD) \ + EM(SKB_DROP_REASON_TC_EGRESS, TC_EGRESS) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From 215b0f1963d4e34fccac6992b3debe26f78a6eb8 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Fri, 4 Mar 2022 14:00:41 +0800 Subject: net: skb: introduce the function kfree_skb_list_reason() To report reasons of skb drops, introduce the function kfree_skb_list_reason() and make kfree_skb_list() an inline call to it. This function will be used in the next commit in __dev_xmit_skb(). Signed-off-by: Menglong Dong Signed-off-by: David S. Miller --- include/linux/skbuff.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1ffe64616741..1f2de153755c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1202,10 +1202,16 @@ static inline void kfree_skb(struct sk_buff *skb) } void skb_release_head_state(struct sk_buff *skb); -void kfree_skb_list(struct sk_buff *segs); +void kfree_skb_list_reason(struct sk_buff *segs, + enum skb_drop_reason reason); void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt); void skb_tx_error(struct sk_buff *skb); +static inline void kfree_skb_list(struct sk_buff *segs) +{ + kfree_skb_list_reason(segs, SKB_DROP_REASON_NOT_SPECIFIED); +} + #ifdef CONFIG_TRACEPOINTS void consume_skb(struct sk_buff *skb); #else -- cgit v1.2.3 From 7faef0547f4c29031a68d058918b031a8e520d49 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Fri, 4 Mar 2022 14:00:42 +0800 Subject: net: dev: add skb drop reasons to __dev_xmit_skb() Add reasons for skb drops to __dev_xmit_skb() by replacing kfree_skb_list() with kfree_skb_list_reason(). The drop reason of SKB_DROP_REASON_QDISC_DROP is introduced for qdisc enqueue fails. Signed-off-by: Menglong Dong Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++++ include/trace/events/skb.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1f2de153755c..769d54ba2f3b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -395,6 +395,10 @@ enum skb_drop_reason { */ SKB_DROP_REASON_NEIGH_DEAD, /* neigh entry is dead */ SKB_DROP_REASON_TC_EGRESS, /* dropped in TC egress HOOK */ + SKB_DROP_REASON_QDISC_DROP, /* dropped by qdisc when packet + * outputting (failed to enqueue to + * current qdisc) + */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 53755e8191a1..dbf3e2e3c1b4 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -46,6 +46,7 @@ EM(SKB_DROP_REASON_NEIGH_QUEUEFULL, NEIGH_QUEUEFULL) \ EM(SKB_DROP_REASON_NEIGH_DEAD, NEIGH_DEAD) \ EM(SKB_DROP_REASON_TC_EGRESS, TC_EGRESS) \ + EM(SKB_DROP_REASON_QDISC_DROP, QDISC_DROP) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From 44f0bd40803c0e04f1c8cd59df3c7acce783ae9c Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Fri, 4 Mar 2022 14:00:43 +0800 Subject: net: dev: use kfree_skb_reason() for enqueue_to_backlog() Replace kfree_skb() used in enqueue_to_backlog() with kfree_skb_reason(). The skb rop reason SKB_DROP_REASON_CPU_BACKLOG is introduced for the case of failing to enqueue the skb to the per CPU backlog queue. The further reason can be backlog queue full or RPS flow limition, and I think we needn't to make further distinctions. Signed-off-by: Menglong Dong Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ++++++ include/trace/events/skb.h | 1 + 2 files changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 769d54ba2f3b..44ecbfff2b69 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -399,6 +399,12 @@ enum skb_drop_reason { * outputting (failed to enqueue to * current qdisc) */ + SKB_DROP_REASON_CPU_BACKLOG, /* failed to enqueue the skb to + * the per CPU backlog queue. This + * can be caused by backlog queue + * full (see netdev_max_backlog in + * net.rst) or RPS flow limit + */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index dbf3e2e3c1b4..3bb90ca893ae 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -47,6 +47,7 @@ EM(SKB_DROP_REASON_NEIGH_DEAD, NEIGH_DEAD) \ EM(SKB_DROP_REASON_TC_EGRESS, TC_EGRESS) \ EM(SKB_DROP_REASON_QDISC_DROP, QDISC_DROP) \ + EM(SKB_DROP_REASON_CPU_BACKLOG, CPU_BACKLOG) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From 7e726ed81e1ddd5fdc431e02b94fcfe2a9876d42 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Fri, 4 Mar 2022 14:00:44 +0800 Subject: net: dev: use kfree_skb_reason() for do_xdp_generic() Replace kfree_skb() used in do_xdp_generic() with kfree_skb_reason(). The drop reason SKB_DROP_REASON_XDP is introduced for this case. Signed-off-by: Menglong Dong Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + include/trace/events/skb.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 44ecbfff2b69..7a38d0f90cef 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -405,6 +405,7 @@ enum skb_drop_reason { * full (see netdev_max_backlog in * net.rst) or RPS flow limit */ + SKB_DROP_REASON_XDP, /* dropped by XDP in input path */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 3bb90ca893ae..8c4c343c830f 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -48,6 +48,7 @@ EM(SKB_DROP_REASON_TC_EGRESS, TC_EGRESS) \ EM(SKB_DROP_REASON_QDISC_DROP, QDISC_DROP) \ EM(SKB_DROP_REASON_CPU_BACKLOG, CPU_BACKLOG) \ + EM(SKB_DROP_REASON_XDP, XDP) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From a568aff26ac03ee9eb1482683514914a5ec3b4c3 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Fri, 4 Mar 2022 14:00:45 +0800 Subject: net: dev: use kfree_skb_reason() for sch_handle_ingress() Replace kfree_skb() used in sch_handle_ingress() with kfree_skb_reason(). Following drop reasons are introduced: SKB_DROP_REASON_TC_INGRESS Signed-off-by: Menglong Dong Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + include/trace/events/skb.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7a38d0f90cef..6b14b2d297d2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -406,6 +406,7 @@ enum skb_drop_reason { * net.rst) or RPS flow limit */ SKB_DROP_REASON_XDP, /* dropped by XDP in input path */ + SKB_DROP_REASON_TC_INGRESS, /* dropped in TC ingress HOOK */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 8c4c343c830f..514dd2de8776 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -49,6 +49,7 @@ EM(SKB_DROP_REASON_QDISC_DROP, QDISC_DROP) \ EM(SKB_DROP_REASON_CPU_BACKLOG, CPU_BACKLOG) \ EM(SKB_DROP_REASON_XDP, XDP) \ + EM(SKB_DROP_REASON_TC_INGRESS, TC_INGRESS) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From 6c2728b7c14164928cb7cb9c847dead101b2d503 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Fri, 4 Mar 2022 14:00:46 +0800 Subject: net: dev: use kfree_skb_reason() for __netif_receive_skb_core() Add reason for skb drops to __netif_receive_skb_core() when packet_type not found to handle the skb. For this purpose, the drop reason SKB_DROP_REASON_PTYPE_ABSENT is introduced. Take ether packets for example, this case mainly happens when L3 protocol is not supported. Signed-off-by: Menglong Dong Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 +++++ include/trace/events/skb.h | 1 + 2 files changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6b14b2d297d2..2be263184d1e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -407,6 +407,11 @@ enum skb_drop_reason { */ SKB_DROP_REASON_XDP, /* dropped by XDP in input path */ SKB_DROP_REASON_TC_INGRESS, /* dropped in TC ingress HOOK */ + SKB_DROP_REASON_PTYPE_ABSENT, /* not packet_type found to handle + * the skb. For an etner packet, + * this means that L3 protocol is + * not supported + */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 514dd2de8776..c0769d943f8e 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -50,6 +50,7 @@ EM(SKB_DROP_REASON_CPU_BACKLOG, CPU_BACKLOG) \ EM(SKB_DROP_REASON_XDP, XDP) \ EM(SKB_DROP_REASON_TC_INGRESS, TC_INGRESS) \ + EM(SKB_DROP_REASON_PTYPE_ABSENT, PTYPE_ABSENT) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From bf9ad37dc8a30cce22ae95d6c2ca6abf8731d305 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 14 Jul 2015 14:26:34 +0200 Subject: signal, x86: Delay calling signals in atomic on RT enabled kernels On x86_64 we must disable preemption before we enable interrupts for stack faults, int3 and debugging, because the current task is using a per CPU debug stack defined by the IST. If we schedule out, another task can come in and use the same stack and cause the stack to be corrupted and crash the kernel on return. When CONFIG_PREEMPT_RT is enabled, spinlock_t locks become sleeping, and one of these is the spin lock used in signal handling. Some of the debug code (int3) causes do_trap() to send a signal. This function calls a spinlock_t lock that has been converted to a sleeping lock. If this happens, the above issues with the corrupted stack is possible. Instead of calling the signal right away, for PREEMPT_RT and x86, the signal information is stored on the stacks task_struct and TIF_NOTIFY_RESUME is set. Then on exit of the trap, the signal resume code will send the signal when preemption is enabled. [ rostedt: Switched from #ifdef CONFIG_PREEMPT_RT to ARCH_RT_DELAYS_SIGNAL_SEND and added comments to the code. ] [bigeasy: Add on 32bit as per Yang Shi, minor rewording. ] [ tglx: Use a config option ] Signed-off-by: Oleg Nesterov Signed-off-by: Steven Rostedt Signed-off-by: Thomas Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/Ygq5aBB/qMQw6aP5@linutronix.de --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 75ba8aa60248..098e37fd770a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1087,6 +1087,9 @@ struct task_struct { /* Restored if set_restore_sigmask() was used: */ sigset_t saved_sigmask; struct sigpending pending; +#ifdef CONFIG_RT_DELAYED_SIGNALS + struct kernel_siginfo forced_info; +#endif unsigned long sas_ss_sp; size_t sas_ss_size; unsigned int sas_ss_flags; -- cgit v1.2.3 From 92499dec3aa9c251e605b42e1024e805bbaa50ad Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Tue, 11 Jan 2022 15:05:56 +0200 Subject: ARM: dts: at91: sama7g5: Add NAND support Add NAND support. The sama7g5's SMC IP is the same as sama5d2's with a slightly change: it provides a synchronous clock output (SMC clock) that is dedicated to FPGA usage. Since this doesn't interfere with the SMC NAND configuration, thus code will not be added in the current nand driver to address the FPGA usage, use the sama5d2's compatible and choose not to introduce dedicated compatibles for sama7g5. Tested with Micron MT29F4G08ABAEAWP NAND flash. Signed-off-by: Tudor Ambarus [nicolas.ferre@microchip.com: add the definition of PMC_MCK1 in include/dt-bindings/clock/at91.h from another patch] Signed-off-by: Nicolas Ferre Link: https://lore.kernel.org/r/20220111130556.905978-1-tudor.ambarus@microchip.com --- include/dt-bindings/clock/at91.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/clock/at91.h b/include/dt-bindings/clock/at91.h index 98e1b2ab6403..8498c0cd95fe 100644 --- a/include/dt-bindings/clock/at91.h +++ b/include/dt-bindings/clock/at91.h @@ -35,6 +35,7 @@ #define PMC_AUDIOIOPLL (PMC_MAIN + 7) #define PMC_ETHPLL (PMC_MAIN + 8) #define PMC_CPU (PMC_MAIN + 9) +#define PMC_MCK1 (PMC_MAIN + 10) #ifndef AT91_PMC_MOSCS #define AT91_PMC_MOSCS 0 /* MOSCS Flag */ -- cgit v1.2.3 From 9a45081bb1fd5d15253994fcdbed652a56174d5e Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Mon, 28 Feb 2022 10:09:05 +0800 Subject: dt-bindings: clock: add i.MX93 clock definition Add i.MX93 clock definition Reviewed-by: Abel Vesa Acked-by: Krzysztof Kozlowski Acked-by: Rob Herring Reviewed-by: Stephen Boyd Signed-off-by: Peng Fan Link: https://lore.kernel.org/r/20220228020908.2810346-3-peng.fan@oss.nxp.com Signed-off-by: Abel Vesa --- include/dt-bindings/clock/imx93-clock.h | 201 ++++++++++++++++++++++++++++++++ 1 file changed, 201 insertions(+) create mode 100644 include/dt-bindings/clock/imx93-clock.h (limited to 'include') diff --git a/include/dt-bindings/clock/imx93-clock.h b/include/dt-bindings/clock/imx93-clock.h new file mode 100644 index 000000000000..21fda9c5cb5e --- /dev/null +++ b/include/dt-bindings/clock/imx93-clock.h @@ -0,0 +1,201 @@ +/* SPDX-License-Identifier: GPL-2.0+ OR MIT */ +/* + * Copyright 2022 NXP + */ + +#ifndef __DT_BINDINGS_CLOCK_IMX93_CLK_H +#define __DT_BINDINGS_CLOCK_IMX93_CLK_H + +#define IMX93_CLK_DUMMY 0 +#define IMX93_CLK_24M 1 +#define IMX93_CLK_EXT1 2 +#define IMX93_CLK_SYS_PLL_PFD0 3 +#define IMX93_CLK_SYS_PLL_PFD0_DIV2 4 +#define IMX93_CLK_SYS_PLL_PFD1 5 +#define IMX93_CLK_SYS_PLL_PFD1_DIV2 6 +#define IMX93_CLK_SYS_PLL_PFD2 7 +#define IMX93_CLK_SYS_PLL_PFD2_DIV2 8 +#define IMX93_CLK_AUDIO_PLL 9 +#define IMX93_CLK_VIDEO_PLL 10 +#define IMX93_CLK_A55_PERIPH 11 +#define IMX93_CLK_A55_MTR_BUS 12 +#define IMX93_CLK_A55 13 +#define IMX93_CLK_M33 14 +#define IMX93_CLK_BUS_WAKEUP 15 +#define IMX93_CLK_BUS_AON 16 +#define IMX93_CLK_WAKEUP_AXI 17 +#define IMX93_CLK_SWO_TRACE 18 +#define IMX93_CLK_M33_SYSTICK 19 +#define IMX93_CLK_FLEXIO1 20 +#define IMX93_CLK_FLEXIO2 21 +#define IMX93_CLK_LPIT1 22 +#define IMX93_CLK_LPIT2 23 +#define IMX93_CLK_LPTMR1 24 +#define IMX93_CLK_LPTMR2 25 +#define IMX93_CLK_TPM1 26 +#define IMX93_CLK_TPM2 27 +#define IMX93_CLK_TPM3 28 +#define IMX93_CLK_TPM4 29 +#define IMX93_CLK_TPM5 30 +#define IMX93_CLK_TPM6 31 +#define IMX93_CLK_FLEXSPI1 32 +#define IMX93_CLK_CAN1 33 +#define IMX93_CLK_CAN2 34 +#define IMX93_CLK_LPUART1 35 +#define IMX93_CLK_LPUART2 36 +#define IMX93_CLK_LPUART3 37 +#define IMX93_CLK_LPUART4 38 +#define IMX93_CLK_LPUART5 39 +#define IMX93_CLK_LPUART6 40 +#define IMX93_CLK_LPUART7 41 +#define IMX93_CLK_LPUART8 42 +#define IMX93_CLK_LPI2C1 43 +#define IMX93_CLK_LPI2C2 44 +#define IMX93_CLK_LPI2C3 45 +#define IMX93_CLK_LPI2C4 46 +#define IMX93_CLK_LPI2C5 47 +#define IMX93_CLK_LPI2C6 48 +#define IMX93_CLK_LPI2C7 49 +#define IMX93_CLK_LPI2C8 50 +#define IMX93_CLK_LPSPI1 51 +#define IMX93_CLK_LPSPI2 52 +#define IMX93_CLK_LPSPI3 53 +#define IMX93_CLK_LPSPI4 54 +#define IMX93_CLK_LPSPI5 55 +#define IMX93_CLK_LPSPI6 56 +#define IMX93_CLK_LPSPI7 57 +#define IMX93_CLK_LPSPI8 58 +#define IMX93_CLK_I3C1 59 +#define IMX93_CLK_I3C2 60 +#define IMX93_CLK_USDHC1 61 +#define IMX93_CLK_USDHC2 62 +#define IMX93_CLK_USDHC3 63 +#define IMX93_CLK_SAI1 64 +#define IMX93_CLK_SAI2 65 +#define IMX93_CLK_SAI3 66 +#define IMX93_CLK_CCM_CKO1 67 +#define IMX93_CLK_CCM_CKO2 68 +#define IMX93_CLK_CCM_CKO3 69 +#define IMX93_CLK_CCM_CKO4 70 +#define IMX93_CLK_HSIO 71 +#define IMX93_CLK_HSIO_USB_TEST_60M 72 +#define IMX93_CLK_HSIO_ACSCAN_80M 73 +#define IMX93_CLK_HSIO_ACSCAN_480M 74 +#define IMX93_CLK_ML_APB 75 +#define IMX93_CLK_ML 76 +#define IMX93_CLK_MEDIA_AXI 77 +#define IMX93_CLK_MEDIA_APB 78 +#define IMX93_CLK_MEDIA_LDB 79 +#define IMX93_CLK_MEDIA_DISP_PIX 80 +#define IMX93_CLK_CAM_PIX 81 +#define IMX93_CLK_MIPI_TEST_BYTE 82 +#define IMX93_CLK_MIPI_PHY_CFG 83 +#define IMX93_CLK_ADC 84 +#define IMX93_CLK_PDM 85 +#define IMX93_CLK_TSTMR1 86 +#define IMX93_CLK_TSTMR2 87 +#define IMX93_CLK_MQS1 88 +#define IMX93_CLK_MQS2 89 +#define IMX93_CLK_AUDIO_XCVR 90 +#define IMX93_CLK_SPDIF 91 +#define IMX93_CLK_ENET 92 +#define IMX93_CLK_ENET_TIMER1 93 +#define IMX93_CLK_ENET_TIMER2 94 +#define IMX93_CLK_ENET_REF 95 +#define IMX93_CLK_ENET_REF_PHY 96 +#define IMX93_CLK_I3C1_SLOW 97 +#define IMX93_CLK_I3C2_SLOW 98 +#define IMX93_CLK_USB_PHY_BURUNIN 99 +#define IMX93_CLK_PAL_CAME_SCAN 100 +#define IMX93_CLK_A55_GATE 101 +#define IMX93_CLK_CM33_GATE 102 +#define IMX93_CLK_ADC1_GATE 103 +#define IMX93_CLK_WDOG1_GATE 104 +#define IMX93_CLK_WDOG2_GATE 105 +#define IMX93_CLK_WDOG3_GATE 106 +#define IMX93_CLK_WDOG4_GATE 107 +#define IMX93_CLK_WDOG5_GATE 108 +#define IMX93_CLK_SEMA1_GATE 109 +#define IMX93_CLK_SEMA2_GATE 110 +#define IMX93_CLK_MU_A_GATE 111 +#define IMX93_CLK_MU_B_GATE 112 +#define IMX93_CLK_EDMA1_GATE 113 +#define IMX93_CLK_EDMA2_GATE 114 +#define IMX93_CLK_FLEXSPI1_GATE 115 +#define IMX93_CLK_GPIO1_GATE 116 +#define IMX93_CLK_GPIO2_GATE 117 +#define IMX93_CLK_GPIO3_GATE 118 +#define IMX93_CLK_GPIO4_GATE 119 +#define IMX93_CLK_FLEXIO1_GATE 120 +#define IMX93_CLK_FLEXIO2_GATE 121 +#define IMX93_CLK_LPIT1_GATE 122 +#define IMX93_CLK_LPIT2_GATE 123 +#define IMX93_CLK_LPTMR1_GATE 124 +#define IMX93_CLK_LPTMR2_GATE 125 +#define IMX93_CLK_TPM1_GATE 126 +#define IMX93_CLK_TPM2_GATE 127 +#define IMX93_CLK_TPM3_GATE 128 +#define IMX93_CLK_TPM4_GATE 129 +#define IMX93_CLK_TPM5_GATE 130 +#define IMX93_CLK_TPM6_GATE 131 +#define IMX93_CLK_CAN1_GATE 132 +#define IMX93_CLK_CAN2_GATE 133 +#define IMX93_CLK_LPUART1_GATE 134 +#define IMX93_CLK_LPUART2_GATE 135 +#define IMX93_CLK_LPUART3_GATE 136 +#define IMX93_CLK_LPUART4_GATE 137 +#define IMX93_CLK_LPUART5_GATE 138 +#define IMX93_CLK_LPUART6_GATE 139 +#define IMX93_CLK_LPUART7_GATE 140 +#define IMX93_CLK_LPUART8_GATE 141 +#define IMX93_CLK_LPI2C1_GATE 142 +#define IMX93_CLK_LPI2C2_GATE 143 +#define IMX93_CLK_LPI2C3_GATE 144 +#define IMX93_CLK_LPI2C4_GATE 145 +#define IMX93_CLK_LPI2C5_GATE 146 +#define IMX93_CLK_LPI2C6_GATE 147 +#define IMX93_CLK_LPI2C7_GATE 148 +#define IMX93_CLK_LPI2C8_GATE 149 +#define IMX93_CLK_LPSPI1_GATE 150 +#define IMX93_CLK_LPSPI2_GATE 151 +#define IMX93_CLK_LPSPI3_GATE 152 +#define IMX93_CLK_LPSPI4_GATE 153 +#define IMX93_CLK_LPSPI5_GATE 154 +#define IMX93_CLK_LPSPI6_GATE 155 +#define IMX93_CLK_LPSPI7_GATE 156 +#define IMX93_CLK_LPSPI8_GATE 157 +#define IMX93_CLK_I3C1_GATE 158 +#define IMX93_CLK_I3C2_GATE 159 +#define IMX93_CLK_USDHC1_GATE 160 +#define IMX93_CLK_USDHC2_GATE 161 +#define IMX93_CLK_USDHC3_GATE 162 +#define IMX93_CLK_SAI1_GATE 163 +#define IMX93_CLK_SAI2_GATE 164 +#define IMX93_CLK_SAI3_GATE 165 +#define IMX93_CLK_MIPI_CSI_GATE 166 +#define IMX93_CLK_MIPI_DSI_GATE 167 +#define IMX93_CLK_LVDS_GATE 168 +#define IMX93_CLK_LCDIF_GATE 169 +#define IMX93_CLK_PXP_GATE 170 +#define IMX93_CLK_ISI_GATE 171 +#define IMX93_CLK_NIC_MEDIA_GATE 172 +#define IMX93_CLK_USB_CONTROLLER_GATE 173 +#define IMX93_CLK_USB_TEST_60M_GATE 174 +#define IMX93_CLK_HSIO_TROUT_24M_GATE 175 +#define IMX93_CLK_PDM_GATE 176 +#define IMX93_CLK_MQS1_GATE 177 +#define IMX93_CLK_MQS2_GATE 178 +#define IMX93_CLK_AUD_XCVR_GATE 179 +#define IMX93_CLK_SPDIF_GATE 180 +#define IMX93_CLK_HSIO_32K_GATE 181 +#define IMX93_CLK_ENET1_GATE 182 +#define IMX93_CLK_ENET_QOS_GATE 183 +#define IMX93_CLK_SYS_CNT_GATE 184 +#define IMX93_CLK_TSTMR1_GATE 185 +#define IMX93_CLK_TSTMR2_GATE 186 +#define IMX93_CLK_TMC_GATE 187 +#define IMX93_CLK_PMRO_GATE 188 +#define IMX93_CLK_32K 189 +#define IMX93_CLK_END 190 + +#endif -- cgit v1.2.3 From 3a0318140a6f8c3ab60f1f46c3f203923cb01882 Mon Sep 17 00:00:00 2001 From: Changcheng Deng Date: Fri, 21 Jan 2022 01:35:08 +0000 Subject: Bluetooth: mgmt: Replace zero-length array with flexible-array member There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use "flexible array members" for these cases. The older style of one-element or zero-length arrays should no longer be used. Reference: https://www.kernel.org/doc/html/latest/process/deprecated.html#zero-length-and-one-element-arrays Reported-by: Zeal Robot Signed-off-by: Changcheng Deng Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/mgmt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 99266f7aebdc..3d26e6a3478b 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -1112,7 +1112,7 @@ struct mgmt_ev_adv_monitor_device_found { __s8 rssi; __le32 flags; __le16 eir_len; - __u8 eir[0]; + __u8 eir[]; } __packed; #define MGMT_EV_ADV_MONITOR_DEVICE_LOST 0x0030 -- cgit v1.2.3 From 9b392e0e0b6d026da5a62bb79a08f32e27af858e Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Thu, 3 Mar 2022 13:11:57 -0800 Subject: Bluetooth: Fix not checking for valid hdev on bt_dev_{info,warn,err,dbg} This fixes attemting to print hdev->name directly which causes them to print an error: kernel: read_version:367: (efault): sock 000000006a3008f2 Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Marcel Holtmann --- include/net/bluetooth/bluetooth.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index a647e5fabdbd..2aa5e95808a5 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -204,19 +204,21 @@ void bt_err_ratelimited(const char *fmt, ...); #define BT_DBG(fmt, ...) pr_debug(fmt "\n", ##__VA_ARGS__) #endif +#define bt_dev_name(hdev) ((hdev) ? (hdev)->name : "null") + #define bt_dev_info(hdev, fmt, ...) \ - BT_INFO("%s: " fmt, (hdev)->name, ##__VA_ARGS__) + BT_INFO("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__) #define bt_dev_warn(hdev, fmt, ...) \ - BT_WARN("%s: " fmt, (hdev)->name, ##__VA_ARGS__) + BT_WARN("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__) #define bt_dev_err(hdev, fmt, ...) \ - BT_ERR("%s: " fmt, (hdev)->name, ##__VA_ARGS__) + BT_ERR("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__) #define bt_dev_dbg(hdev, fmt, ...) \ - BT_DBG("%s: " fmt, (hdev)->name, ##__VA_ARGS__) + BT_DBG("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__) #define bt_dev_warn_ratelimited(hdev, fmt, ...) \ - bt_warn_ratelimited("%s: " fmt, (hdev)->name, ##__VA_ARGS__) + bt_warn_ratelimited("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__) #define bt_dev_err_ratelimited(hdev, fmt, ...) \ - bt_err_ratelimited("%s: " fmt, (hdev)->name, ##__VA_ARGS__) + bt_err_ratelimited("%s: " fmt, bt_dev_name(hdev), ##__VA_ARGS__) /* Connection and socket states */ enum { -- cgit v1.2.3 From 402e6688a7df482cc57be0b0dd5b443d995073fb Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 1 Mar 2022 10:01:48 +0800 Subject: iommu/vt-d: Remove intel_iommu::domains The "domains" field of the intel_iommu structure keeps the mapping of domain_id to dmar_domain. This information is not used anywhere. Remove and cleanup it to avoid unnecessary memory consumption. Signed-off-by: Lu Baolu Reviewed-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20220214025704.3184654-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20220301020159.633356-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 5cfda90b2cca..8c7591b5f3e2 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -578,7 +578,6 @@ struct intel_iommu { #ifdef CONFIG_INTEL_IOMMU unsigned long *domain_ids; /* bitmap of domains */ - struct dmar_domain ***domains; /* ptr to domains */ spinlock_t lock; /* protect context, domain ids */ struct root_entry *root_entry; /* virtual address */ -- cgit v1.2.3 From 586081d3f6b13ec9dfdfdf3d7842a688b376fa5e Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 1 Mar 2022 10:01:52 +0800 Subject: iommu/vt-d: Remove DEFER_DEVICE_DOMAIN_INFO Allocate and set the per-device iommu private data during iommu device probe. This makes the per-device iommu private data always available during iommu_probe_device() and iommu_release_device(). With this changed, the dummy DEFER_DEVICE_DOMAIN_INFO pointer could be removed. The wrappers for getting the private data and domain are also cleaned. Signed-off-by: Lu Baolu Reviewed-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20220214025704.3184654-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20220301020159.633356-6-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 8c7591b5f3e2..03f1134fc2fe 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -733,8 +733,6 @@ int for_each_device_domain(int (*fn)(struct device_domain_info *info, void *data), void *data); void iommu_flush_write_buffer(struct intel_iommu *iommu); int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev); -struct dmar_domain *find_domain(struct device *dev); -struct device_domain_info *get_domain_info(struct device *dev); struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn); #ifdef CONFIG_INTEL_IOMMU_SVM -- cgit v1.2.3 From 2852631d96a643e0b21a9b14ad38caf465d7225f Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 1 Mar 2022 10:01:56 +0800 Subject: iommu/vt-d: Move intel_iommu_ops to header file Compiler is not happy about hidden declaration of intel_iommu_ops. .../iommu.c:414:24: warning: symbol 'intel_iommu_ops' was not declared. Should it be static? Move declaration to header file to make compiler happy. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20220207141240.8253-1-andriy.shevchenko@linux.intel.com Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20220301020159.633356-10-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 03f1134fc2fe..4909d6c9ac21 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -783,6 +783,8 @@ bool context_present(struct context_entry *context); struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus, u8 devfn, int alloc); +extern const struct iommu_ops intel_iommu_ops; + #ifdef CONFIG_INTEL_IOMMU extern int iommu_calculate_agaw(struct intel_iommu *iommu); extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu); -- cgit v1.2.3 From 97f2f2c5317f55ae3440733a090a96a251da222b Mon Sep 17 00:00:00 2001 From: Yian Chen Date: Tue, 1 Mar 2022 10:01:59 +0800 Subject: iommu/vt-d: Enable ATS for the devices in SATC table Starting from Intel VT-d v3.2, Intel platform BIOS can provide additional SATC table structure. SATC table includes a list of SoC integrated devices that support ATC (Address translation cache). Enabling ATC (via ATS capability) can be a functional requirement for SATC device operation or optional to enhance device performance/functionality. This is determined by the bit of ATC_REQUIRED in SATC table. When IOMMU is working in scalable mode, software chooses to always enable ATS for every device in SATC table because Intel SoC devices in SATC table are trusted to use ATS. On the other hand, if IOMMU is in legacy mode, ATS of SATC capable devices can work transparently to software and be automatically enabled by IOMMU hardware. As the result, there is no need for software to enable ATS on these devices. This also removes dmar_find_matched_atsr_unit() helper as it becomes dead code now. Signed-off-by: Yian Chen Link: https://lore.kernel.org/r/20220222185416.1722611-1-yian.chen@intel.com Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20220301020159.633356-13-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 4909d6c9ac21..2f9891cb3d00 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -693,7 +693,6 @@ static inline int nr_pte_to_next_page(struct dma_pte *pte) } extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev); -extern int dmar_find_matched_atsr_unit(struct pci_dev *dev); extern int dmar_enable_qi(struct intel_iommu *iommu); extern void dmar_disable_qi(struct intel_iommu *iommu); -- cgit v1.2.3 From 26c9da51949916b73d995a2c89412c346903273d Mon Sep 17 00:00:00 2001 From: Puranjay Mohan Date: Wed, 16 Feb 2022 13:42:23 +0530 Subject: remoteproc: Introduce sysfs_read_only flag The remoteproc framework provides sysfs interfaces for changing the firmware name and for starting/stopping a remote processor through the sysfs files 'state' and 'firmware'. The 'coredump' file is used to set the coredump configuration. The 'recovery' sysfs file can also be used similarly to control the error recovery state machine of a remoteproc. These interfaces are currently allowed irrespective of how the remoteprocs were booted (like remoteproc self auto-boot, remoteproc client-driven boot etc). These interfaces can adversely affect a remoteproc and its clients especially when a remoteproc is being controlled by a remoteproc client driver(s). Also, not all remoteproc drivers may want to support the sysfs interfaces by default. Add support to make the remoteproc sysfs files read only by introducing a state flag 'sysfs_read_only' that the individual remoteproc drivers can set based on their usage needs. The default behavior is to allow the sysfs operations as before. Implement attribute_group->is_visible() to make the sysfs entries read only when 'sysfs_read_only' flag is set. Signed-off-by: Puranjay Mohan Link: https://lore.kernel.org/r/20220216081224.9956-2-p-mohan@ti.com Signed-off-by: Mathieu Poirier --- include/linux/remoteproc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index e0600e1e5c17..93a1d0050fbc 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -523,6 +523,7 @@ struct rproc_dump_segment { * @table_sz: size of @cached_table * @has_iommu: flag to indicate if remote processor is behind an MMU * @auto_boot: flag to indicate if remote processor should be auto-started + * @sysfs_read_only: flag to make remoteproc sysfs files read only * @dump_segments: list of segments in the firmware * @nb_vdev: number of vdev currently handled by rproc * @elf_class: firmware ELF class @@ -562,6 +563,7 @@ struct rproc { size_t table_sz; bool has_iommu; bool auto_boot; + bool sysfs_read_only; struct list_head dump_segments; int nb_vdev; u8 elf_class; -- cgit v1.2.3 From b4060db9251f919506e4d672737c6b8ab9a84701 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Wed, 23 Feb 2022 08:34:48 -0800 Subject: PM: runtime: Have devm_pm_runtime_enable() handle pm_runtime_dont_use_autosuspend() The PM Runtime docs say: Drivers in ->remove() callback should undo the runtime PM changes done in ->probe(). Usually this means calling pm_runtime_disable(), pm_runtime_dont_use_autosuspend() etc. From grepping code, it's clear that many people aren't aware of the need to call pm_runtime_dont_use_autosuspend(). When brainstorming solutions, one idea that came up was to leverage the new-ish devm_pm_runtime_enable() function. The idea here is that: * When the devm action is called we know that the driver is being removed. It's the perfect time to undo the use_autosuspend. * The code of pm_runtime_dont_use_autosuspend() already handles the case of being called when autosuspend wasn't enabled. Suggested-by: Laurent Pinchart Signed-off-by: Douglas Anderson Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_runtime.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 9f09601c465a..2bff6a10095d 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -567,6 +567,10 @@ static inline void pm_runtime_disable(struct device *dev) * Allow the runtime PM autosuspend mechanism to be used for @dev whenever * requested (or "autosuspend" will be handled as direct runtime-suspend for * it). + * + * NOTE: It's important to undo this with pm_runtime_dont_use_autosuspend() + * at driver exit time unless your driver initially enabled pm_runtime + * with devm_pm_runtime_enable() (which handles it for you). */ static inline void pm_runtime_use_autosuspend(struct device *dev) { -- cgit v1.2.3 From f7ddbf5581b474fe4a0a29244acaa1bf72234675 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Thu, 3 Mar 2022 16:52:15 -0800 Subject: drm/msm: Add SET_PARAM ioctl It was always expected to have a use for this some day, so we left a placeholder. Now we do. (And I expect another use in the not too distant future when we start allowing userspace to allocate GPU iova.) Signed-off-by: Rob Clark Link: https://lore.kernel.org/r/20220304005317.776110-3-robdclark@gmail.com --- include/uapi/drm/msm_drm.h | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h index 6b8fffc28a50..cf5de53836e7 100644 --- a/include/uapi/drm/msm_drm.h +++ b/include/uapi/drm/msm_drm.h @@ -67,16 +67,20 @@ struct drm_msm_timespec { __s64 tv_nsec; /* nanoseconds */ }; -#define MSM_PARAM_GPU_ID 0x01 -#define MSM_PARAM_GMEM_SIZE 0x02 -#define MSM_PARAM_CHIP_ID 0x03 -#define MSM_PARAM_MAX_FREQ 0x04 -#define MSM_PARAM_TIMESTAMP 0x05 -#define MSM_PARAM_GMEM_BASE 0x06 -#define MSM_PARAM_PRIORITIES 0x07 /* The # of priority levels */ -#define MSM_PARAM_PP_PGTABLE 0x08 /* => 1 for per-process pagetables, else 0 */ -#define MSM_PARAM_FAULTS 0x09 -#define MSM_PARAM_SUSPENDS 0x0a +/* Below "RO" indicates a read-only param, "WO" indicates write-only, and + * "RW" indicates a param that can be both read (GET_PARAM) and written + * (SET_PARAM) + */ +#define MSM_PARAM_GPU_ID 0x01 /* RO */ +#define MSM_PARAM_GMEM_SIZE 0x02 /* RO */ +#define MSM_PARAM_CHIP_ID 0x03 /* RO */ +#define MSM_PARAM_MAX_FREQ 0x04 /* RO */ +#define MSM_PARAM_TIMESTAMP 0x05 /* RO */ +#define MSM_PARAM_GMEM_BASE 0x06 /* RO */ +#define MSM_PARAM_PRIORITIES 0x07 /* RO: The # of priority levels */ +#define MSM_PARAM_PP_PGTABLE 0x08 /* RO: Deprecated, always returns zero */ +#define MSM_PARAM_FAULTS 0x09 /* RO */ +#define MSM_PARAM_SUSPENDS 0x0a /* RO */ /* For backwards compat. The original support for preemption was based on * a single ring per priority level so # of priority levels equals the # @@ -333,9 +337,7 @@ struct drm_msm_submitqueue_query { }; #define DRM_MSM_GET_PARAM 0x00 -/* placeholder: #define DRM_MSM_SET_PARAM 0x01 - */ #define DRM_MSM_GEM_NEW 0x02 #define DRM_MSM_GEM_INFO 0x03 #define DRM_MSM_GEM_CPU_PREP 0x04 @@ -351,6 +353,7 @@ struct drm_msm_submitqueue_query { #define DRM_MSM_SUBMITQUEUE_QUERY 0x0C #define DRM_IOCTL_MSM_GET_PARAM DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GET_PARAM, struct drm_msm_param) +#define DRM_IOCTL_MSM_SET_PARAM DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_SET_PARAM, struct drm_msm_param) #define DRM_IOCTL_MSM_GEM_NEW DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GEM_NEW, struct drm_msm_gem_new) #define DRM_IOCTL_MSM_GEM_INFO DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GEM_INFO, struct drm_msm_gem_info) #define DRM_IOCTL_MSM_GEM_CPU_PREP DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_GEM_CPU_PREP, struct drm_msm_gem_cpu_prep) -- cgit v1.2.3 From fd8be27e50e04f6e80af0f3e327cced525558256 Mon Sep 17 00:00:00 2001 From: Michal Suchanek Date: Fri, 25 Feb 2022 21:51:35 +0100 Subject: efifb: Remove redundant efifb_setup_from_dmi stub efifb is the only user of efifb_setup_from_dmi which is provided by sysfb which is selected by efifb. That makes the stub redundant. Signed-off-by: Michal Suchanek Reviewed-by: Javier Martinez Canillas Signed-off-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/7416c439d68e9e96068ea5c77e05c99c7df41750.1645822213.git.msuchanek@suse.de --- include/linux/efi.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index ccd4d3f91c98..0cbbc4103632 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1329,10 +1329,6 @@ static inline struct efi_mokvar_table_entry *efi_mokvar_entry_find( } #endif -#ifdef CONFIG_SYSFB extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); -#else -static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt) { } -#endif #endif /* _LINUX_EFI_H */ -- cgit v1.2.3 From 90f45c42d7d7b0ec0fd797485c07fc421c474e12 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Thu, 3 Mar 2022 16:52:16 -0800 Subject: drm/msm: Add SYSPROF param (v2) Add a SYSPROF param for system profiling tools like Mesa's pps-producer (perfetto) to control behavior related to system-wide performance counter collection. In particular, for profiling, one wants to ensure that GPU context switches do not effect perfcounter state, and might want to suppress suspend (which would cause counters to lose state). v2: Swap the order in msm_file_private_set_sysprof() [sboyd] and initialize the sysprof_active refcount to one (because the under/ overflow checking in refcount_t doesn't expect a 0->1 transition) meaning that values greater than 1 means sysprof is active. Signed-off-by: Rob Clark Link: https://lore.kernel.org/r/20220304005317.776110-4-robdclark@gmail.com --- include/uapi/drm/msm_drm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h index cf5de53836e7..2ee03ba08681 100644 --- a/include/uapi/drm/msm_drm.h +++ b/include/uapi/drm/msm_drm.h @@ -81,6 +81,7 @@ struct drm_msm_timespec { #define MSM_PARAM_PP_PGTABLE 0x08 /* RO: Deprecated, always returns zero */ #define MSM_PARAM_FAULTS 0x09 /* RO */ #define MSM_PARAM_SUSPENDS 0x0a /* RO */ +#define MSM_PARAM_SYSPROF 0x0b /* WO: 1 preserves perfcntrs, 2 also disables suspend */ /* For backwards compat. The original support for preemption was based on * a single ring per priority level so # of priority levels equals the # -- cgit v1.2.3 From 92c45b63ce22c8898aa41806e8d6692bcd577510 Mon Sep 17 00:00:00 2001 From: Mark Tomlinson Date: Thu, 6 Aug 2020 16:14:55 +1200 Subject: PCI: Reduce warnings on possible RW1C corruption For hardware that only supports 32-bit writes to PCI there is the possibility of clearing RW1C (write-one-to-clear) bits. A rate-limited messages was introduced by fb2659230120, but rate-limiting is not the best choice here. Some devices may not show the warnings they should if another device has just produced a bunch of warnings. Also, the number of messages can be a nuisance on devices which are otherwise working fine. Change the ratelimit to a single warning per bus. This ensures no bus is 'starved' of emitting a warning and also that there isn't a continuous stream of warnings. It would be preferable to have a warning per device, but the pci_dev structure is not available here, and a lookup from devfn would be far too slow. Suggested-by: Bjorn Helgaas Fixes: fb2659230120 ("PCI: Warn on possible RW1C corruption for sub-32 bit config writes") Link: https://lore.kernel.org/r/20200806041455.11070-1-mark.tomlinson@alliedtelesis.co.nz Signed-off-by: Mark Tomlinson Signed-off-by: Bjorn Helgaas Reviewed-by: Florian Fainelli Reviewed-by: Rob Herring Acked-by: Scott Branden --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 8253a5413d7c..678fecdf6b81 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -668,6 +668,7 @@ struct pci_bus { struct bin_attribute *legacy_io; /* Legacy I/O for this bus */ struct bin_attribute *legacy_mem; /* Legacy mem */ unsigned int is_added:1; + unsigned int unsafe_warn:1; /* warned about RW1C config write */ }; #define to_pci_bus(n) container_of(n, struct pci_bus, dev) -- cgit v1.2.3 From 17154addc5c1a175bcf3441ff0d9598efa1f05cd Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Thu, 24 Feb 2022 14:23:21 -0800 Subject: drm/msm: Add MSM_SUBMIT_FENCE_SN_IN Add a way for userspace to specify the sequence number fence used to track completion of the submit. As the seqno fence is simply an incrementing counter which is local to the submitqueue, it is easy for userspace to know the next value. This is useful for native userspace drivers in a vm guest, as the guest to host roundtrip can have high latency. Assigning the fence seqno in the guest userspace allows the guest to continue without waiting for response from the host. Signed-off-by: Rob Clark Link: https://lore.kernel.org/r/20220224222321.60653-1-robdclark@gmail.com --- include/uapi/drm/msm_drm.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h index 2ee03ba08681..07efc8033492 100644 --- a/include/uapi/drm/msm_drm.h +++ b/include/uapi/drm/msm_drm.h @@ -232,6 +232,7 @@ struct drm_msm_gem_submit_bo { #define MSM_SUBMIT_SUDO 0x10000000 /* run submitted cmds from RB */ #define MSM_SUBMIT_SYNCOBJ_IN 0x08000000 /* enable input syncobj */ #define MSM_SUBMIT_SYNCOBJ_OUT 0x04000000 /* enable output syncobj */ +#define MSM_SUBMIT_FENCE_SN_IN 0x02000000 /* userspace passes in seqno fence */ #define MSM_SUBMIT_FLAGS ( \ MSM_SUBMIT_NO_IMPLICIT | \ MSM_SUBMIT_FENCE_FD_IN | \ @@ -239,6 +240,7 @@ struct drm_msm_gem_submit_bo { MSM_SUBMIT_SUDO | \ MSM_SUBMIT_SYNCOBJ_IN | \ MSM_SUBMIT_SYNCOBJ_OUT | \ + MSM_SUBMIT_FENCE_SN_IN | \ 0) #define MSM_SUBMIT_SYNCOBJ_RESET 0x00000001 /* Reset syncobj after wait. */ @@ -258,7 +260,7 @@ struct drm_msm_gem_submit_syncobj { */ struct drm_msm_gem_submit { __u32 flags; /* MSM_PIPE_x | MSM_SUBMIT_x */ - __u32 fence; /* out */ + __u32 fence; /* out (or in with MSM_SUBMIT_FENCE_SN_IN flag) */ __u32 nr_bos; /* in, number of submit_bo's */ __u32 nr_cmds; /* in, number of submit_cmd's */ __u64 bos; /* in, ptr to array of submit_bo's */ -- cgit v1.2.3 From cd87fecdedd7b54c61f5d7c2b7237b43126ac50a Mon Sep 17 00:00:00 2001 From: Luiz Angelo Daros de Luca Date: Wed, 2 Mar 2022 22:52:34 -0300 Subject: net: dsa: tag_rtl8_4: add rtl8_4t trailing variant MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Realtek switches supports the same tag both before ethertype or between payload and the CRC. Signed-off-by: Luiz Angelo Daros de Luca Reviewed-by: Alvin Šipraga Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/dsa.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 71cc363dbbd4..759479fe8573 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -52,6 +52,7 @@ struct phylink_link_state; #define DSA_TAG_PROTO_BRCM_LEGACY_VALUE 22 #define DSA_TAG_PROTO_SJA1110_VALUE 23 #define DSA_TAG_PROTO_RTL8_4_VALUE 24 +#define DSA_TAG_PROTO_RTL8_4T_VALUE 25 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -79,6 +80,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_SEVILLE = DSA_TAG_PROTO_SEVILLE_VALUE, DSA_TAG_PROTO_SJA1110 = DSA_TAG_PROTO_SJA1110_VALUE, DSA_TAG_PROTO_RTL8_4 = DSA_TAG_PROTO_RTL8_4_VALUE, + DSA_TAG_PROTO_RTL8_4T = DSA_TAG_PROTO_RTL8_4T_VALUE, }; struct dsa_switch; -- cgit v1.2.3 From 25b35dd28138f61f9a0fb8b76c0483761fd228bd Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Sat, 5 Mar 2022 04:16:38 +0530 Subject: bpf: Add check_func_arg_reg_off function Lift the list of register types allowed for having fixed and variable offsets when passed as helper function arguments into a common helper, so that they can be reused for kfunc checks in later commits. Keeping a common helper aids maintainability and allows us to follow the same consistent rules across helpers and kfuncs. Also, convert check_func_arg to use this function. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220304224645.3677453-2-memxor@gmail.com --- include/linux/bpf_verifier.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7a7be8c057f2..38b24ee8d8c2 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -521,6 +521,9 @@ bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt); int check_ptr_off_reg(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno); +int check_func_arg_reg_off(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno, + enum bpf_arg_type arg_type); int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno); int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, -- cgit v1.2.3 From 24d5bb806c7e2c0b9972564fd493069f612d90dd Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Sat, 5 Mar 2022 04:16:41 +0530 Subject: bpf: Harden register offset checks for release helpers and kfuncs Let's ensure that the PTR_TO_BTF_ID reg being passed in to release BPF helpers and kfuncs always has its offset set to 0. While not a real problem now, there's a very real possibility this will become a problem when more and more kfuncs are exposed, and more BPF helpers are added which can release PTR_TO_BTF_ID. Previous commits already protected against non-zero var_off. One of the case we are concerned about now is when we have a type that can be returned by e.g. an acquire kfunc: struct foo { int a; int b; struct bar b; }; ... and struct bar is also a type that can be returned by another acquire kfunc. Then, doing the following sequence: struct foo *f = bpf_get_foo(); // acquire kfunc if (!f) return 0; bpf_put_bar(&f->b); // release kfunc ... would work with the current code, since the btf_struct_ids_match takes reg->off into account for matching pointer type with release kfunc argument type, but would obviously be incorrect, and most likely lead to a kernel crash. A test has been included later to prevent regressions in this area. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220304224645.3677453-5-memxor@gmail.com --- include/linux/bpf_verifier.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 38b24ee8d8c2..c1fc4af47f69 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -523,7 +523,8 @@ int check_ptr_off_reg(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno); int check_func_arg_reg_off(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, - enum bpf_arg_type arg_type); + enum bpf_arg_type arg_type, + bool is_release_func); int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno); int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, -- cgit v1.2.3 From f014a00bbeb09cea16017b82448d32a468a6b96f Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Sat, 5 Mar 2022 04:16:42 +0530 Subject: compiler-clang.h: Add __diag infrastructure for clang Add __diag macros similar to those in compiler-gcc.h, so that warnings that need to be adjusted for specific cases but not globally can be ignored when building with clang. Signed-off-by: Nathan Chancellor Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220304224645.3677453-6-memxor@gmail.com [ Kartikeya: wrote commit message ] --- include/linux/compiler-clang.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 3c4de9b6c6e3..f1aa41d520bd 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -68,3 +68,25 @@ #define __nocfi __attribute__((__no_sanitize__("cfi"))) #define __cficanonical __attribute__((__cfi_canonical_jump_table__)) + +/* + * Turn individual warnings and errors on and off locally, depending + * on version. + */ +#define __diag_clang(version, severity, s) \ + __diag_clang_ ## version(__diag_clang_ ## severity s) + +/* Severity used in pragma directives */ +#define __diag_clang_ignore ignored +#define __diag_clang_warn warning +#define __diag_clang_error error + +#define __diag_str1(s) #s +#define __diag_str(s) __diag_str1(s) +#define __diag(s) _Pragma(__diag_str(clang diagnostic s)) + +#if CONFIG_CLANG_VERSION >= 110000 +#define __diag_clang_11(s) __diag(s) +#else +#define __diag_clang_11(s) +#endif -- cgit v1.2.3 From 4d1ea705d797e66edd70ffa708b83888a210a437 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Sat, 5 Mar 2022 04:16:43 +0530 Subject: compiler_types.h: Add unified __diag_ignore_all for GCC/LLVM Add a __diag_ignore_all macro, to ignore warnings for both GCC and LLVM, without having to specify the compiler type and version. By default, GCC 8 and clang 11 are used. This will be used by bpf subsystem to ignore -Wmissing-prototypes warning for functions that are meant to be global functions so that they are in vmlinux BTF, but don't have a prototype. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220304224645.3677453-7-memxor@gmail.com --- include/linux/compiler-clang.h | 3 +++ include/linux/compiler-gcc.h | 3 +++ include/linux/compiler_types.h | 4 ++++ 3 files changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index f1aa41d520bd..babb1347148c 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -90,3 +90,6 @@ #else #define __diag_clang_11(s) #endif + +#define __diag_ignore_all(option, comment) \ + __diag_clang(11, ignore, option) diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index ccbbd31b3aae..d364c98a4a80 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -151,6 +151,9 @@ #define __diag_GCC_8(s) #endif +#define __diag_ignore_all(option, comment) \ + __diag_GCC(8, ignore, option) + /* * Prior to 9.1, -Wno-alloc-size-larger-than (and therefore the "alloc_size" * attribute) do not work, and must be disabled. diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3f31ff400432..8e5d2f50f951 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -371,4 +371,8 @@ struct ftrace_likely_data { #define __diag_error(compiler, version, option, comment) \ __diag_ ## compiler(version, error, option) +#ifndef __diag_ignore_all +#define __diag_ignore_all(option, comment) +#endif + #endif /* __LINUX_COMPILER_TYPES_H */ -- cgit v1.2.3 From 9216c916237805c93d054ed022afb172ddbc3ed1 Mon Sep 17 00:00:00 2001 From: Hao Luo Date: Fri, 4 Mar 2022 11:16:55 -0800 Subject: compiler_types: Define __percpu as __attribute__((btf_type_tag("percpu"))) This is similar to commit 7472d5a642c9 ("compiler_types: define __user as __attribute__((btf_type_tag("user")))"), where a type tag "user" was introduced to identify the pointers that point to user memory. With that change, the newest compile toolchain can encode __user information into vmlinux BTF, which can be used by the BPF verifier to enforce safe program behaviors. Similarly, we have __percpu attribute, which is mainly used to indicate memory is allocated in percpu region. The __percpu pointers in kernel are supposed to be used together with functions like per_cpu_ptr() and this_cpu_ptr(), which perform necessary calculation on the pointer's base address. Without the btf_type_tag introduced in this patch, __percpu pointers will be treated as regular memory pointers in vmlinux BTF and BPF programs are allowed to directly dereference them, generating incorrect behaviors. Now with "percpu" btf_type_tag, the BPF verifier is able to differentiate __percpu pointers from regular pointers and forbids unexpected behaviors like direct load. The following is an example similar to the one given in commit 7472d5a642c9: [$ ~] cat test.c #define __percpu __attribute__((btf_type_tag("percpu"))) int foo(int __percpu *arg) { return *arg; } [$ ~] clang -O2 -g -c test.c [$ ~] pahole -JV test.o ... File test.o: [1] INT int size=4 nr_bits=32 encoding=SIGNED [2] TYPE_TAG percpu type_id=1 [3] PTR (anon) type_id=2 [4] FUNC_PROTO (anon) return=1 args=(3 arg) [5] FUNC foo type_id=4 [$ ~] for the function argument "int __percpu *arg", its type is described as PTR -> TYPE_TAG(percpu) -> INT The kernel can use this information for bpf verification or other use cases. Like commit 7472d5a642c9, this feature requires clang (>= clang14) and pahole (>= 1.23). Signed-off-by: Hao Luo Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20220304191657.981240-3-haoluo@google.com --- include/linux/compiler_types.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 8e5d2f50f951..b9a8ae9440c7 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -38,7 +38,12 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } # define __user # endif # define __iomem -# define __percpu +# if defined(CONFIG_DEBUG_INFO_BTF) && defined(CONFIG_PAHOLE_HAS_BTF_TAG) && \ + __has_attribute(btf_type_tag) +# define __percpu __attribute__((btf_type_tag("percpu"))) +# else +# define __percpu +# endif # define __rcu # define __chk_user_ptr(x) (void)0 # define __chk_io_ptr(x) (void)0 -- cgit v1.2.3 From 5844101a1be9b8636024cb31c865ef13c7cc6db3 Mon Sep 17 00:00:00 2001 From: Hao Luo Date: Fri, 4 Mar 2022 11:16:56 -0800 Subject: bpf: Reject programs that try to load __percpu memory. With the introduction of the btf_type_tag "percpu", we can add a MEM_PERCPU to identify those pointers that point to percpu memory. The ability of differetiating percpu pointers from regular memory pointers have two benefits: 1. It forbids unexpected use of percpu pointers, such as direct loads. In kernel, there are special functions used for accessing percpu memory. Directly loading percpu memory is meaningless. We already have BPF helpers like bpf_per_cpu_ptr() and bpf_this_cpu_ptr() that wrap the kernel percpu functions. So we can now convert percpu pointers into regular pointers in a safe way. 2. Previously, bpf_per_cpu_ptr() and bpf_this_cpu_ptr() only work on PTR_TO_PERCPU_BTF_ID, a special reg_type which describes static percpu variables in kernel (we rely on pahole to encode them into vmlinux BTF). Now, since we can identify __percpu tagged pointers, we can also identify dynamically allocated percpu memory as well. It means we can use bpf_xxx_cpu_ptr() on dynamic percpu memory. This would be very convenient when accessing fields like "cgroup->rstat_cpu". Signed-off-by: Hao Luo Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20220304191657.981240-4-haoluo@google.com --- include/linux/bpf.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f19abc59b6cd..88449fbbe063 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -334,7 +334,15 @@ enum bpf_type_flag { /* MEM is in user address space. */ MEM_USER = BIT(3 + BPF_BASE_TYPE_BITS), - __BPF_TYPE_LAST_FLAG = MEM_USER, + /* MEM is a percpu memory. MEM_PERCPU tags PTR_TO_BTF_ID. When tagged + * with MEM_PERCPU, PTR_TO_BTF_ID _cannot_ be directly accessed. In + * order to drop this tag, it must be passed into bpf_per_cpu_ptr() + * or bpf_this_cpu_ptr(), which will return the pointer corresponding + * to the specified cpu. + */ + MEM_PERCPU = BIT(4 + BPF_BASE_TYPE_BITS), + + __BPF_TYPE_LAST_FLAG = MEM_PERCPU, }; /* Max number of base types. */ @@ -516,7 +524,6 @@ enum bpf_reg_type { */ PTR_TO_MEM, /* reg points to valid memory region */ PTR_TO_BUF, /* reg points to a read/write buffer */ - PTR_TO_PERCPU_BTF_ID, /* reg points to a percpu kernel variable */ PTR_TO_FUNC, /* reg points to a bpf program function */ __BPF_REG_TYPE_MAX, -- cgit v1.2.3 From 736f16de75f9bb32d76f652cb66f04d1bc685057 Mon Sep 17 00:00:00 2001 From: Dongli Zhang Date: Fri, 4 Mar 2022 06:55:05 -0800 Subject: net: tap: track dropped skb via kfree_skb_reason() The TAP can be used as vhost-net backend. E.g., the tap_handle_frame() is the interface to forward the skb from TAP to vhost-net/virtio-net. However, there are many "goto drop" in the TAP driver. Therefore, the kfree_skb_reason() is involved at each "goto drop" to help userspace ftrace/ebpf to track the reason for the loss of packets. The below reasons are introduced: - SKB_DROP_REASON_SKB_CSUM - SKB_DROP_REASON_SKB_GSO_SEG - SKB_DROP_REASON_SKB_UCOPY_FAULT - SKB_DROP_REASON_DEV_HDR - SKB_DROP_REASON_FULL_RING Cc: Joao Martins Cc: Joe Jin Signed-off-by: Dongli Zhang Signed-off-by: David S. Miller --- include/linux/skbuff.h | 13 +++++++++++++ include/trace/events/skb.h | 5 +++++ 2 files changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2be263184d1e..67cfff4065b6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -412,6 +412,19 @@ enum skb_drop_reason { * this means that L3 protocol is * not supported */ + SKB_DROP_REASON_SKB_CSUM, /* sk_buff checksum computation + * error + */ + SKB_DROP_REASON_SKB_GSO_SEG, /* gso segmentation error */ + SKB_DROP_REASON_SKB_UCOPY_FAULT, /* failed to copy data from + * user space, e.g., via + * zerocopy_sg_from_iter() + * or skb_orphan_frags_rx() + */ + SKB_DROP_REASON_DEV_HDR, /* device driver specific + * header/metadata is invalid + */ + SKB_DROP_REASON_FULL_RING, /* ring buffer is full */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index c0769d943f8e..240e7e7591fc 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -51,6 +51,11 @@ EM(SKB_DROP_REASON_XDP, XDP) \ EM(SKB_DROP_REASON_TC_INGRESS, TC_INGRESS) \ EM(SKB_DROP_REASON_PTYPE_ABSENT, PTYPE_ABSENT) \ + EM(SKB_DROP_REASON_SKB_CSUM, SKB_CSUM) \ + EM(SKB_DROP_REASON_SKB_GSO_SEG, SKB_GSO_SEG) \ + EM(SKB_DROP_REASON_SKB_UCOPY_FAULT, SKB_UCOPY_FAULT) \ + EM(SKB_DROP_REASON_DEV_HDR, DEV_HDR) \ + EM(SKB_DROP_REASON_FULL_RING, FULL_RING) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From 4b4f052e2d89c2eb7e13ee28ba9e85f8097aef3d Mon Sep 17 00:00:00 2001 From: Dongli Zhang Date: Fri, 4 Mar 2022 06:55:07 -0800 Subject: net: tun: track dropped skb via kfree_skb_reason() The TUN can be used as vhost-net backend. E.g, the tun_net_xmit() is the interface to forward the skb from TUN to vhost-net/virtio-net. However, there are many "goto drop" in the TUN driver. Therefore, the kfree_skb_reason() is involved at each "goto drop" to help userspace ftrace/ebpf to track the reason for the loss of packets. The below reasons are introduced: - SKB_DROP_REASON_DEV_READY - SKB_DROP_REASON_NOMEM - SKB_DROP_REASON_HDR_TRUNC - SKB_DROP_REASON_TAP_FILTER - SKB_DROP_REASON_TAP_TXFILTER Cc: Joao Martins Cc: Joe Jin Signed-off-by: Dongli Zhang Signed-off-by: David S. Miller --- include/linux/skbuff.h | 18 ++++++++++++++++++ include/trace/events/skb.h | 5 +++++ 2 files changed, 23 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 67cfff4065b6..34f572271c0c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -424,7 +424,25 @@ enum skb_drop_reason { SKB_DROP_REASON_DEV_HDR, /* device driver specific * header/metadata is invalid */ + /* the device is not ready to xmit/recv due to any of its data + * structure that is not up/ready/initialized, e.g., the IFF_UP is + * not set, or driver specific tun->tfiles[txq] is not initialized + */ + SKB_DROP_REASON_DEV_READY, SKB_DROP_REASON_FULL_RING, /* ring buffer is full */ + SKB_DROP_REASON_NOMEM, /* error due to OOM */ + SKB_DROP_REASON_HDR_TRUNC, /* failed to trunc/extract the header + * from networking data, e.g., failed + * to pull the protocol header from + * frags via pskb_may_pull() + */ + SKB_DROP_REASON_TAP_FILTER, /* dropped by (ebpf) filter directly + * attached to tun/tap, e.g., via + * TUNSETFILTEREBPF + */ + SKB_DROP_REASON_TAP_TXFILTER, /* dropped by tx filter implemented + * at tun/tap, e.g., check_filter() + */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 240e7e7591fc..e1670e1e4934 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -55,7 +55,12 @@ EM(SKB_DROP_REASON_SKB_GSO_SEG, SKB_GSO_SEG) \ EM(SKB_DROP_REASON_SKB_UCOPY_FAULT, SKB_UCOPY_FAULT) \ EM(SKB_DROP_REASON_DEV_HDR, DEV_HDR) \ + EM(SKB_DROP_REASON_DEV_READY, DEV_READY) \ EM(SKB_DROP_REASON_FULL_RING, FULL_RING) \ + EM(SKB_DROP_REASON_NOMEM, NOMEM) \ + EM(SKB_DROP_REASON_HDR_TRUNC, HDR_TRUNC) \ + EM(SKB_DROP_REASON_TAP_FILTER, TAP_FILTER) \ + EM(SKB_DROP_REASON_TAP_TXFILTER, TAP_TXFILTER) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From 40b358f6156ac516e33e5252a8769737054da24e Mon Sep 17 00:00:00 2001 From: Shunzhou Jiang Date: Mon, 7 Mar 2022 10:53:56 +0800 Subject: dt-bindings: power: add Amlogic s4 power domains bindings Add the bindings for the Amlogic Secure power domains, controlling the secure power domains. The bindings targets the Amlogic s4, in which the power domains registers are in secure world. Signed-off-by: Shunzhou Jiang Reviewed-by: Martin Blumenstingl Acked-by: Rob Herring Signed-off-by: Neil Armstrong Link: https://lore.kernel.org/r/20220307025357.1368673-2-shunzhou.jiang@amlogic.com --- include/dt-bindings/power/meson-s4-power.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 include/dt-bindings/power/meson-s4-power.h (limited to 'include') diff --git a/include/dt-bindings/power/meson-s4-power.h b/include/dt-bindings/power/meson-s4-power.h new file mode 100644 index 000000000000..462dd2cb938b --- /dev/null +++ b/include/dt-bindings/power/meson-s4-power.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: (GPL-2.0+ or MIT) */ +/* + * Copyright (c) 2021 Amlogic, Inc. + * Author: Shunzhou Jiang + */ + +#ifndef _DT_BINDINGS_MESON_S4_POWER_H +#define _DT_BINDINGS_MESON_S4_POWER_H + +#define PWRC_S4_DOS_HEVC_ID 0 +#define PWRC_S4_DOS_VDEC_ID 1 +#define PWRC_S4_VPU_HDMI_ID 2 +#define PWRC_S4_USB_COMB_ID 3 +#define PWRC_S4_GE2D_ID 4 +#define PWRC_S4_ETH_ID 5 +#define PWRC_S4_DEMOD_ID 6 +#define PWRC_S4_AUDIO_ID 7 + +#endif -- cgit v1.2.3 From 96ba61ee5331eb6e2f4c2baeb994b9ceb01d8266 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Sun, 20 Feb 2022 21:46:16 +0100 Subject: media: v4l2-ctrls: Add new V4L2_H264_DECODE_PARAM_FLAG_P/BFRAME flags Add new V4L2_H264_DECODE_PARAM_FLAG_P/BFRAME flags that are needed by NVIDIA Tegra video decoder. Userspace will have to set these flags in accordance to the type of a decoded frame. Reviewed-by: Nicolas Dufresne Signed-off-by: Dmitry Osipenko Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/v4l2-controls.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index c8e0f84d204d..e3d48d571062 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -1563,6 +1563,8 @@ struct v4l2_h264_dpb_entry { #define V4L2_H264_DECODE_PARAM_FLAG_IDR_PIC 0x01 #define V4L2_H264_DECODE_PARAM_FLAG_FIELD_PIC 0x02 #define V4L2_H264_DECODE_PARAM_FLAG_BOTTOM_FIELD 0x04 +#define V4L2_H264_DECODE_PARAM_FLAG_PFRAME 0x08 +#define V4L2_H264_DECODE_PARAM_FLAG_BFRAME 0x10 #define V4L2_CID_STATELESS_H264_DECODE_PARAMS (V4L2_CID_CODEC_STATELESS_BASE + 7) /** -- cgit v1.2.3 From f72de02ebece2e962462bc0c1e9efd29eaa029b2 Mon Sep 17 00:00:00 2001 From: Kurt Kanzenbach Date: Sat, 5 Mar 2022 12:21:25 +0100 Subject: ptp: Add generic PTP is_sync() function PHY drivers such as micrel or dp83640 need to analyze whether a given skb is a PTP sync message for one step functionality. In order to avoid code duplication introduce a generic function and move it to ptp classify. Signed-off-by: Kurt Kanzenbach Signed-off-by: David S. Miller --- include/linux/ptp_classify.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index 9afd34a2d36c..fefa7790dc46 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -126,6 +126,17 @@ static inline u8 ptp_get_msgtype(const struct ptp_header *hdr, return msgtype; } +/** + * ptp_msg_is_sync - Evaluates whether the given skb is a PTP Sync message + * @skb: packet buffer + * @type: type of the packet (see ptp_classify_raw()) + * + * This function evaluates whether the given skb is a PTP Sync message. + * + * Return: true if sync message, false otherwise + */ +bool ptp_msg_is_sync(struct sk_buff *skb, unsigned int type); + void __init ptp_classifier_init(void); #else static inline void ptp_classifier_init(void) @@ -148,5 +159,9 @@ static inline u8 ptp_get_msgtype(const struct ptp_header *hdr, */ return PTP_MSGTYPE_SYNC; } +static inline bool ptp_msg_is_sync(struct sk_buff *skb, unsigned int type) +{ + return false; +} #endif #endif /* _PTP_CLASSIFY_H_ */ -- cgit v1.2.3 From 2655926aea9beea62c9ba80c032485456fd848f0 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Sun, 6 Mar 2022 22:57:52 +0100 Subject: net: Remove netif_rx_any_context() and netif_rx_ni(). Remove netif_rx_any_context and netif_rx_ni() because there are no more users in tree. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 19a27ac361ef..29a850a8d460 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3718,16 +3718,6 @@ int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb); int netif_rx(struct sk_buff *skb); int __netif_rx(struct sk_buff *skb); -static inline int netif_rx_ni(struct sk_buff *skb) -{ - return netif_rx(skb); -} - -static inline int netif_rx_any_context(struct sk_buff *skb) -{ - return netif_rx(skb); -} - int netif_receive_skb(struct sk_buff *skb); int netif_receive_skb_core(struct sk_buff *skb); void netif_receive_skb_list_internal(struct list_head *head); -- cgit v1.2.3 From 4aaa06b227f737da5c10feb93a6b203920d5a1e7 Mon Sep 17 00:00:00 2001 From: Curtis Malainey Date: Fri, 4 Mar 2022 14:57:31 -0600 Subject: ASoC: SOF: fix 32 signed bit overflow Shifting in a signed 32bit container past the signed bit is technically undefined behaviour. Fix by using unsigned types. Found via cppcheck. Reviewed-by: Ranjani Sridharan Reviewed-by: Liam Girdwood Signed-off-by: Curtis Malainey Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20220304205733.62233-9-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof/header.h | 2 +- include/uapi/sound/sof/abi.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/sound/sof/header.h b/include/sound/sof/header.h index b97a76bcb655..b22e925c70e2 100644 --- a/include/sound/sof/header.h +++ b/include/sound/sof/header.h @@ -31,7 +31,7 @@ /* Global Message - Generic */ #define SOF_GLB_TYPE_SHIFT 28 -#define SOF_GLB_TYPE_MASK (0xfL << SOF_GLB_TYPE_SHIFT) +#define SOF_GLB_TYPE_MASK (0xfUL << SOF_GLB_TYPE_SHIFT) #define SOF_GLB_TYPE(x) ((x) << SOF_GLB_TYPE_SHIFT) /* Command Message - Generic */ diff --git a/include/uapi/sound/sof/abi.h b/include/uapi/sound/sof/abi.h index f4232d289a22..e052653a6e4c 100644 --- a/include/uapi/sound/sof/abi.h +++ b/include/uapi/sound/sof/abi.h @@ -27,7 +27,7 @@ /* SOF ABI version major, minor and patch numbers */ #define SOF_ABI_MAJOR 3 #define SOF_ABI_MINOR 19 -#define SOF_ABI_PATCH 0 +#define SOF_ABI_PATCH 1 /* SOF ABI version number. Format within 32bit word is MMmmmppp */ #define SOF_ABI_MAJOR_SHIFT 24 -- cgit v1.2.3 From 1e974e5b82b3d75069b50445cd248cee0199654e Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Mon, 28 Feb 2022 17:27:54 +0000 Subject: ASoC: audio_graph_card2: Add support for variable slot widths Some audio hardware cannot support the same slot width for all sample widths, or a slot width equal to the sample width for all sample widths. This is usually due either to limitations of the audio serial port or system clocking restrictions. A typical example would be: - 16-bit samples in 16-bit slots - 24-bit samples in 32-bit slots The new dai-tdm-slot-width-map property allows setting a mapping of sample widths and the corresponding tdm slot widths and slot counts. Although the slot count is usually the same for all cases this does allow for adding padding slots to maintain the same bitclk frequency. The property is added to each endpoint node that needs the component DAI to be told the TDM slot width and count. Signed-off-by: Richard Fitzgerald Link: https://lore.kernel.org/r/20220228172754.453783-3-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- include/sound/simple_card_utils.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h index 5ee269c59aac..8faa649f712b 100644 --- a/include/sound/simple_card_utils.h +++ b/include/sound/simple_card_utils.h @@ -16,6 +16,12 @@ #define asoc_simple_init_mic(card, sjack, prefix) \ asoc_simple_init_jack(card, sjack, 0, prefix, NULL) +struct asoc_simple_tdm_width_map { + u8 sample_bits; + u8 slot_count; + u16 slot_width; +}; + struct asoc_simple_dai { const char *name; unsigned int sysclk; @@ -26,6 +32,8 @@ struct asoc_simple_dai { unsigned int rx_slot_mask; struct clk *clk; bool clk_fixed; + struct asoc_simple_tdm_width_map *tdm_width_map; + int n_tdm_widths; }; struct asoc_simple_data { @@ -132,6 +140,9 @@ int asoc_simple_parse_daifmt(struct device *dev, struct device_node *codec, char *prefix, unsigned int *retfmt); +int asoc_simple_parse_tdm_width_map(struct device *dev, struct device_node *np, + struct asoc_simple_dai *dai); + __printf(3, 4) int asoc_simple_set_dailink_name(struct device *dev, struct snd_soc_dai_link *dai_link, -- cgit v1.2.3 From 97939610b893de068c82c347d06319cd231a4602 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Mar 2022 19:01:05 +0100 Subject: block: remove bio_devname All callers are gone, so remove this wrapper. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20220304180105.409765-11-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/bio.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 7523aba4ddf7..4c21f6e69e18 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -491,8 +491,6 @@ static inline void bio_release_pages(struct bio *bio, bool mark_dirty) __bio_release_pages(bio, mark_dirty); } -extern const char *bio_devname(struct bio *bio, char *buffer); - #define bio_dev(bio) \ disk_devt((bio)->bi_bdev->bd_disk) -- cgit v1.2.3 From a26d84633c2ba3c41fd7692986fb2231c9228c4e Mon Sep 17 00:00:00 2001 From: Luca Ceresoli Date: Wed, 23 Feb 2022 18:59:02 +0100 Subject: rtc: max77686: Rename day-of-month defines RTC_DATE and REG_RTC_DATE are used for the registers holding the day of month. Rename these constants to mean what they mean. Signed-off-by: Luca Ceresoli Reviewed-by: Krzysztof Kozlowski Acked-by: Alexandre Belloni Signed-off-by: Lee Jones --- include/linux/mfd/max77686-private.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/max77686-private.h b/include/linux/mfd/max77686-private.h index b1482b3cf353..3acceeedbaba 100644 --- a/include/linux/mfd/max77686-private.h +++ b/include/linux/mfd/max77686-private.h @@ -152,7 +152,7 @@ enum max77686_rtc_reg { MAX77686_RTC_WEEKDAY = 0x0A, MAX77686_RTC_MONTH = 0x0B, MAX77686_RTC_YEAR = 0x0C, - MAX77686_RTC_DATE = 0x0D, + MAX77686_RTC_MONTHDAY = 0x0D, MAX77686_ALARM1_SEC = 0x0E, MAX77686_ALARM1_MIN = 0x0F, MAX77686_ALARM1_HOUR = 0x10, @@ -352,7 +352,7 @@ enum max77802_rtc_reg { MAX77802_RTC_WEEKDAY = 0xCA, MAX77802_RTC_MONTH = 0xCB, MAX77802_RTC_YEAR = 0xCC, - MAX77802_RTC_DATE = 0xCD, + MAX77802_RTC_MONTHDAY = 0xCD, MAX77802_RTC_AE1 = 0xCE, MAX77802_ALARM1_SEC = 0xCF, MAX77802_ALARM1_MIN = 0xD0, -- cgit v1.2.3 From 60b050ff3a60273d56b4017d0f45d5ca71aae5ad Mon Sep 17 00:00:00 2001 From: Luca Ceresoli Date: Wed, 23 Feb 2022 18:59:05 +0100 Subject: mfd: max77714: Add driver for Maxim MAX77714 PMIC Add a simple driver for the Maxim MAX77714 PMIC, supporting RTC and watchdog only. Signed-off-by: Luca Ceresoli Reviewed-by: Krzysztof Kozlowski Signed-off-by: Lee Jones --- include/linux/mfd/max77714.h | 60 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 60 insertions(+) create mode 100644 include/linux/mfd/max77714.h (limited to 'include') diff --git a/include/linux/mfd/max77714.h b/include/linux/mfd/max77714.h new file mode 100644 index 000000000000..a970dc455426 --- /dev/null +++ b/include/linux/mfd/max77714.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Maxim MAX77714 Register and data structures definition. + * + * Copyright (C) 2022 Luca Ceresoli + * Author: Luca Ceresoli + */ + +#ifndef __LINUX_MFD_MAX77714_H_ +#define __LINUX_MFD_MAX77714_H_ + +#include + +#define MAX77714_INT_TOP 0x00 +#define MAX77714_INT_TOPM 0x07 /* Datasheet says "read only", but it is RW */ + +#define MAX77714_INT_TOP_ONOFF BIT(1) +#define MAX77714_INT_TOP_RTC BIT(3) +#define MAX77714_INT_TOP_GPIO BIT(4) +#define MAX77714_INT_TOP_LDO BIT(5) +#define MAX77714_INT_TOP_SD BIT(6) +#define MAX77714_INT_TOP_GLBL BIT(7) + +#define MAX77714_32K_STATUS 0x30 +#define MAX77714_32K_STATUS_SIOSCOK BIT(5) +#define MAX77714_32K_STATUS_XOSCOK BIT(4) +#define MAX77714_32K_STATUS_32KSOURCE BIT(3) +#define MAX77714_32K_STATUS_32KLOAD_MSK 0x3 +#define MAX77714_32K_STATUS_32KLOAD_SHF 1 +#define MAX77714_32K_STATUS_CRYSTAL_CFG BIT(0) + +#define MAX77714_32K_CONFIG 0x31 +#define MAX77714_32K_CONFIG_XOSC_RETRY BIT(4) + +#define MAX77714_CNFG_GLBL2 0x91 +#define MAX77714_WDTEN BIT(2) +#define MAX77714_WDTSLPC BIT(3) +#define MAX77714_TWD_MASK 0x3 +#define MAX77714_TWD_2s 0x0 +#define MAX77714_TWD_16s 0x1 +#define MAX77714_TWD_64s 0x2 +#define MAX77714_TWD_128s 0x3 + +#define MAX77714_CNFG_GLBL3 0x92 +#define MAX77714_WDTC BIT(0) + +#define MAX77714_CNFG2_ONOFF 0x94 +#define MAX77714_WD_RST_WK BIT(5) + +/* Interrupts */ +enum { + MAX77714_IRQ_TOP_ONOFF, + MAX77714_IRQ_TOP_RTC, /* Real-time clock */ + MAX77714_IRQ_TOP_GPIO, /* GPIOs */ + MAX77714_IRQ_TOP_LDO, /* Low-dropout regulators */ + MAX77714_IRQ_TOP_SD, /* Step-down regulators */ + MAX77714_IRQ_TOP_GLBL, /* "Global resources": Low-Battery, overtemp... */ +}; + +#endif /* __LINUX_MFD_MAX77714_H_ */ -- cgit v1.2.3 From c47383f849097c2b3547e28365578cd9e5811378 Mon Sep 17 00:00:00 2001 From: Johnson Wang Date: Thu, 6 Jan 2022 14:54:04 +0800 Subject: mfd: Add support for the MediaTek MT6366 PMIC This adds support for the MediaTek MT6366 PMIC. This is a multifunction device with the following sub modules: - Regulator - RTC - Codec - Interrupt It is interfaced to the host controller using SPI interface by a proprietary hardware called PMIC wrapper or pwrap. MT6366 MFD is a child device of the pwrap. Signed-off-by: Johnson Wang Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20220106065407.16036-2-johnson.wang@mediatek.com --- include/linux/mfd/mt6358/registers.h | 7 +++++++ include/linux/mfd/mt6397/core.h | 1 + 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/mt6358/registers.h b/include/linux/mfd/mt6358/registers.h index 201139b12140..3d33517f178c 100644 --- a/include/linux/mfd/mt6358/registers.h +++ b/include/linux/mfd/mt6358/registers.h @@ -94,6 +94,10 @@ #define MT6358_BUCK_VCORE_CON0 0x1488 #define MT6358_BUCK_VCORE_DBG0 0x149e #define MT6358_BUCK_VCORE_DBG1 0x14a0 +#define MT6358_BUCK_VCORE_SSHUB_CON0 0x14a4 +#define MT6358_BUCK_VCORE_SSHUB_CON1 0x14a6 +#define MT6358_BUCK_VCORE_SSHUB_ELR0 MT6358_BUCK_VCORE_SSHUB_CON1 +#define MT6358_BUCK_VCORE_SSHUB_DBG1 MT6358_BUCK_VCORE_DBG1 #define MT6358_BUCK_VCORE_ELR0 0x14aa #define MT6358_BUCK_VGPU_CON0 0x1508 #define MT6358_BUCK_VGPU_DBG0 0x151e @@ -169,6 +173,9 @@ #define MT6358_LDO_VSRAM_OTHERS_CON0 0x1ba6 #define MT6358_LDO_VSRAM_OTHERS_DBG0 0x1bc0 #define MT6358_LDO_VSRAM_OTHERS_DBG1 0x1bc2 +#define MT6358_LDO_VSRAM_OTHERS_SSHUB_CON0 0x1bc4 +#define MT6358_LDO_VSRAM_OTHERS_SSHUB_CON1 0x1bc6 +#define MT6358_LDO_VSRAM_OTHERS_SSHUB_DBG1 MT6358_LDO_VSRAM_OTHERS_DBG1 #define MT6358_LDO_VSRAM_GPU_CON0 0x1bc8 #define MT6358_LDO_VSRAM_GPU_DBG0 0x1be2 #define MT6358_LDO_VSRAM_GPU_DBG1 0x1be4 diff --git a/include/linux/mfd/mt6397/core.h b/include/linux/mfd/mt6397/core.h index 56f210eebc54..1cf78726503b 100644 --- a/include/linux/mfd/mt6397/core.h +++ b/include/linux/mfd/mt6397/core.h @@ -14,6 +14,7 @@ enum chip_id { MT6323_CHIP_ID = 0x23, MT6358_CHIP_ID = 0x58, MT6359_CHIP_ID = 0x59, + MT6366_CHIP_ID = 0x66, MT6391_CHIP_ID = 0x91, MT6397_CHIP_ID = 0x97, }; -- cgit v1.2.3 From 1092347165cf5ed1453c1f211641a859818a2828 Mon Sep 17 00:00:00 2001 From: Sean Young Date: Wed, 9 Feb 2022 17:03:12 +0100 Subject: media: lirc: remove unused feature LIRC_CAN_SET_REC_DUTY_CYCLE There is no hardware which can filter input on the duty cycle, so no driver implements this. On top of that, LIRC_CAN_SET_REC_DUTY_CYCLE has the same value as LIRC_CAN_MEASURE_CARRIER (0x02000000). Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/lirc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/lirc.h b/include/uapi/linux/lirc.h index 21c69a6a100d..23b0f2c8ba81 100644 --- a/include/uapi/linux/lirc.h +++ b/include/uapi/linux/lirc.h @@ -73,7 +73,6 @@ #define LIRC_CAN_REC_MASK LIRC_MODE2REC(LIRC_CAN_SEND_MASK) #define LIRC_CAN_SET_REC_CARRIER (LIRC_CAN_SET_SEND_CARRIER << 16) -#define LIRC_CAN_SET_REC_DUTY_CYCLE (LIRC_CAN_SET_SEND_DUTY_CYCLE << 16) #define LIRC_CAN_SET_REC_CARRIER_RANGE 0x80000000 #define LIRC_CAN_GET_REC_RESOLUTION 0x20000000 -- cgit v1.2.3 From 72a74c8f0a0df12c7d7ea012aa70d95152858dea Mon Sep 17 00:00:00 2001 From: Ming Qian Date: Thu, 24 Feb 2022 11:10:00 +0800 Subject: media: add nv12m_8l128 and nv12m_10be_8l128 video format. nv12m_8l128 is 8-bit tiled nv12 format used by amphion decoder. nv12m_10be_8l128 is 10-bit tiled format used by amphion decoder. The tile size is 8x128 Signed-off-by: Ming Qian Signed-off-by: Shijie Qin Signed-off-by: Zhou Peng Signed-off-by: Hans Verkuil --- include/uapi/linux/videodev2.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index df8b9c486ba1..3768a0a80830 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -632,6 +632,8 @@ struct v4l2_pix_format { /* Tiled YUV formats, non contiguous planes */ #define V4L2_PIX_FMT_NV12MT v4l2_fourcc('T', 'M', '1', '2') /* 12 Y/CbCr 4:2:0 64x32 tiles */ #define V4L2_PIX_FMT_NV12MT_16X16 v4l2_fourcc('V', 'M', '1', '2') /* 12 Y/CbCr 4:2:0 16x16 tiles */ +#define V4L2_PIX_FMT_NV12M_8L128 v4l2_fourcc('N', 'A', '1', '2') /* Y/CbCr 4:2:0 8x128 tiles */ +#define V4L2_PIX_FMT_NV12M_10BE_8L128 v4l2_fourcc_be('N', 'T', '1', '2') /* Y/CbCr 4:2:0 10-bit 8x128 tiles */ /* Bayer formats - see http://www.siliconimaging.com/RGB%20Bayer.htm */ #define V4L2_PIX_FMT_SBGGR8 v4l2_fourcc('B', 'A', '8', '1') /* 8 BGBG.. GRGR.. */ -- cgit v1.2.3 From 8c4b810a87005eb46564a48a69b5b255e515fa62 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 3 Feb 2022 17:05:02 +0000 Subject: clocksource/drivers/arm_arch_timer: Use event stream scaling when available With FEAT_ECV and the 1GHz counter, it is pretty likely that the event stream divider doesn't fit in the field that holds the divider value (we only have 4 bits to describe counter bits [15:0] Thankfully, FEAT_ECV also provides a scaling mechanism to switch the field to cover counter bits [23:8] instead. Enable this on arm64 when ECV is available (32bit doesn't have any detection infrastructure and is unlikely to be run on an ARMv8.6 system anyway). Signed-off-by: Marc Zyngier Cc: Mark Rutland Cc: Daniel Lezcano Acked-by: Mark Rutland Link: https://lore.kernel.org/r/20220203170502.2694422-1-maz@kernel.org Signed-off-by: Daniel Lezcano --- include/clocksource/arm_arch_timer.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/clocksource/arm_arch_timer.h b/include/clocksource/arm_arch_timer.h index e715bdb720d5..057c8964aefb 100644 --- a/include/clocksource/arm_arch_timer.h +++ b/include/clocksource/arm_arch_timer.h @@ -56,6 +56,7 @@ enum arch_timer_spi_nr { #define ARCH_TIMER_EVT_TRIGGER_MASK (0xF << ARCH_TIMER_EVT_TRIGGER_SHIFT) #define ARCH_TIMER_USR_VT_ACCESS_EN (1 << 8) /* virtual timer registers */ #define ARCH_TIMER_USR_PT_ACCESS_EN (1 << 9) /* physical timer registers */ +#define ARCH_TIMER_EVT_INTERVAL_SCALE (1 << 17) /* EVNTIS in the ARMv8 ARM */ #define ARCH_TIMER_EVT_STREAM_PERIOD_US 100 #define ARCH_TIMER_EVT_STREAM_FREQ \ -- cgit v1.2.3 From c75e707fe1aab32f1dc8e09845533b6542d9aaa9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 4 Mar 2022 18:55:56 +0100 Subject: block: remove the per-bio/request write hint With the NVMe support for this gone, there are no consumers of these hints left, so remove them. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220304175556.407719-2-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 1 - include/linux/blkdev.h | 3 --- 2 files changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 5561e58d158a..ba8cfa57255f 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -250,7 +250,6 @@ struct bio { */ unsigned short bi_flags; /* BIO_* below */ unsigned short bi_ioprio; - unsigned short bi_write_hint; blk_status_t bi_status; atomic_t __bi_remaining; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a12c031af887..226836ccd060 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -518,9 +518,6 @@ struct request_queue { bool mq_sysfs_init_done; -#define BLK_MAX_WRITE_HINTS 5 - u64 write_hints[BLK_MAX_WRITE_HINTS]; - /* * Independent sector access ranges. This is always NULL for * devices that do not have multiple independent access ranges. -- cgit v1.2.3 From c340b990d58c856c1636e0c10abb9e4351ad852a Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 3 Mar 2022 12:13:05 -0800 Subject: block: support pi with extended metadata The nvme spec allows protection information formats with metadata extending beyond the pi field. Use the actual size of the metadata field for incrementing the buffer. Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Martin K. Petersen Signed-off-by: Keith Busch Link: https://lore.kernel.org/r/20220303201312.3255347-2-kbusch@kernel.org Signed-off-by: Jens Axboe --- include/linux/blk-integrity.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h index 8a038ea0717e..378b2459efe2 100644 --- a/include/linux/blk-integrity.h +++ b/include/linux/blk-integrity.h @@ -19,6 +19,7 @@ struct blk_integrity_iter { sector_t seed; unsigned int data_size; unsigned short interval; + unsigned char tuple_size; const char *disk_name; }; -- cgit v1.2.3 From c2ea5fcf53d5f21e6aff0de11d55bc202822df6a Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 3 Mar 2022 12:13:07 -0800 Subject: asm-generic: introduce be48 unaligned accessors The NVMe protocol extended the data integrity fields with unaligned 48-bit reference tags. Provide some helper accessors in preparation for these. Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Hannes Reinecke Reviewed-by: Chaitanya Kulkarni Acked-by: Arnd Bergmann Signed-off-by: Keith Busch Reviewed-by: Bart Van Assche Link: https://lore.kernel.org/r/20220303201312.3255347-4-kbusch@kernel.org Signed-off-by: Jens Axboe --- include/asm-generic/unaligned.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include') diff --git a/include/asm-generic/unaligned.h b/include/asm-generic/unaligned.h index 1c4242416c9f..8fc637379899 100644 --- a/include/asm-generic/unaligned.h +++ b/include/asm-generic/unaligned.h @@ -126,4 +126,30 @@ static inline void put_unaligned_le24(const u32 val, void *p) __put_unaligned_le24(val, p); } +static inline void __put_unaligned_be48(const u64 val, __u8 *p) +{ + *p++ = val >> 40; + *p++ = val >> 32; + *p++ = val >> 24; + *p++ = val >> 16; + *p++ = val >> 8; + *p++ = val; +} + +static inline void put_unaligned_be48(const u64 val, void *p) +{ + __put_unaligned_be48(val, p); +} + +static inline u64 __get_unaligned_be48(const u8 *p) +{ + return (u64)p[0] << 40 | (u64)p[1] << 32 | p[2] << 24 | + p[3] << 16 | p[4] << 8 | p[5]; +} + +static inline u64 get_unaligned_be48(const void *p) +{ + return __get_unaligned_be48(p); +} + #endif /* __ASM_GENERIC_UNALIGNED_H */ -- cgit v1.2.3 From 7ee8809df990d1de379002973baee1681e8d7dd3 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 3 Mar 2022 12:13:08 -0800 Subject: linux/kernel: introduce lower_48_bits function Recent data integrity field enhancements allow reference tags to be up to 48 bits. Introduce an inline helper function since this will be a repeated operation. Suggested-by: Bart Van Assche Signed-off-by: Keith Busch Reviewed-by: Bart Van Assche Link: https://lore.kernel.org/r/20220303201312.3255347-5-kbusch@kernel.org Signed-off-by: Jens Axboe --- include/linux/kernel.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 33f47a996513..3877478681b9 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -63,6 +63,15 @@ } \ ) +/** + * lower_48_bits() - return bits 0-47 of a number + * @n: the number we're accessing + */ +static inline u64 lower_48_bits(u64 n) +{ + return n & ((1ull << 48) - 1); +} + /** * upper_32_bits - return bits 32-63 of a number * @n: the number we're accessing -- cgit v1.2.3 From cbc0a40e17da361a2ada8d669413ccfbd2028f2d Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 3 Mar 2022 12:13:09 -0800 Subject: lib: add rocksoft model crc64 The NVM Express specification extended data integrity fields to 64 bits using the Rocksoft parameters. Add the poly to the crc64 table generation, and provide a generic library routine implementing the algorithm. The Rocksoft 64-bit CRC model parameters are as follows: Poly: 0xAD93D23594C93659 Initial value: 0xFFFFFFFFFFFFFFFF Reflected Input: True Reflected Output: True Xor Final: 0xFFFFFFFFFFFFFFFF Since this model used reflected bits, the implementation generates the reflected table so the result is ordered consistently. Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: Martin K. Petersen Signed-off-by: Keith Busch Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20220303201312.3255347-6-kbusch@kernel.org Signed-off-by: Jens Axboe --- include/linux/crc64.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/crc64.h b/include/linux/crc64.h index c756e65a1b58..9480f38cc7cf 100644 --- a/include/linux/crc64.h +++ b/include/linux/crc64.h @@ -8,4 +8,6 @@ #include u64 __pure crc64_be(u64 crc, const void *p, size_t len); +u64 __pure crc64_rocksoft_generic(u64 crc, const void *p, size_t len); + #endif /* _LINUX_CRC64_H */ -- cgit v1.2.3 From f3813f4b287e480b1fcd62ca798d8556644b8278 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 3 Mar 2022 12:13:10 -0800 Subject: crypto: add rocksoft 64b crc guard tag framework Hardware specific features may be able to calculate a crc64, so provide a framework for drivers to register their implementation. If nothing is registered, fallback to the generic table lookup implementation. The implementation is modeled after the crct10dif equivalent. Signed-off-by: Keith Busch Link: https://lore.kernel.org/r/20220303201312.3255347-7-kbusch@kernel.org Signed-off-by: Jens Axboe --- include/linux/crc64.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/crc64.h b/include/linux/crc64.h index 9480f38cc7cf..e044c60d1e61 100644 --- a/include/linux/crc64.h +++ b/include/linux/crc64.h @@ -7,7 +7,12 @@ #include +#define CRC64_ROCKSOFT_STRING "crc64-rocksoft" + u64 __pure crc64_be(u64 crc, const void *p, size_t len); u64 __pure crc64_rocksoft_generic(u64 crc, const void *p, size_t len); +u64 crc64_rocksoft(const unsigned char *buffer, size_t len); +u64 crc64_rocksoft_update(u64 crc, const unsigned char *buffer, size_t len); + #endif /* _LINUX_CRC64_H */ -- cgit v1.2.3 From a7d4383f17e10f338ea757a849f02298790d24fb Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 3 Mar 2022 12:13:11 -0800 Subject: block: add pi for extended integrity The NVMe specification defines new data integrity formats beyond the t10 tuple. Add support for the specification defined CRC64 formats, assuming the reference tag does not need to be split with the "storage tag". Cc: Hannes Reinecke Cc: "Martin K. Petersen" Signed-off-by: Keith Busch Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20220303201312.3255347-8-kbusch@kernel.org Signed-off-by: Jens Axboe --- include/linux/t10-pi.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index c635c2e014e3..a4b1af581f69 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -53,4 +53,24 @@ extern const struct blk_integrity_profile t10_pi_type1_ip; extern const struct blk_integrity_profile t10_pi_type3_crc; extern const struct blk_integrity_profile t10_pi_type3_ip; +struct crc64_pi_tuple { + __be64 guard_tag; + __be16 app_tag; + __u8 ref_tag[6]; +}; + +static inline u64 ext_pi_ref_tag(struct request *rq) +{ + unsigned int shift = ilog2(queue_logical_block_size(rq->q)); + +#ifdef CONFIG_BLK_DEV_INTEGRITY + if (rq->q->integrity.interval_exp) + shift = rq->q->integrity.interval_exp; +#endif + return lower_48_bits(blk_rq_pos(rq) >> (shift - SECTOR_SHIFT)); +} + +extern const struct blk_integrity_profile ext_pi_type1_crc64; +extern const struct blk_integrity_profile ext_pi_type3_crc64; + #endif -- cgit v1.2.3 From 4020aad85c6785ddac8d51f345ff9e3328ce773a Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 3 Mar 2022 12:13:12 -0800 Subject: nvme: add support for enhanced metadata NVM Express ratified TP 4068 defines new protection information formats. Implement support for the CRC64 guard tags. Since the block layer doesn't support variable length reference tags, driver support for the Storage Tag space is not supported at this time. Cc: Hannes Reinecke Cc: "Martin K. Petersen" Cc: Klaus Jensen Signed-off-by: Keith Busch Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20220303201312.3255347-9-kbusch@kernel.org Signed-off-by: Jens Axboe --- include/linux/nvme.h | 53 ++++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 47 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 9dbc3ef4daf7..4f44f83817a9 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -244,6 +244,7 @@ enum { enum nvme_ctrl_attr { NVME_CTRL_ATTR_HID_128_BIT = (1 << 0), NVME_CTRL_ATTR_TBKAS = (1 << 6), + NVME_CTRL_ATTR_ELBAS = (1 << 15), }; struct nvme_id_ctrl { @@ -399,8 +400,7 @@ struct nvme_id_ns { __le16 endgid; __u8 nguid[16]; __u8 eui64[8]; - struct nvme_lbaf lbaf[16]; - __u8 rsvd192[192]; + struct nvme_lbaf lbaf[64]; __u8 vs[3712]; }; @@ -418,8 +418,7 @@ struct nvme_id_ns_zns { __le32 rrl; __le32 frl; __u8 rsvd20[2796]; - struct nvme_zns_lbafe lbafe[16]; - __u8 rsvd3072[768]; + struct nvme_zns_lbafe lbafe[64]; __u8 vs[256]; }; @@ -428,6 +427,30 @@ struct nvme_id_ctrl_zns { __u8 rsvd1[4095]; }; +struct nvme_id_ns_nvm { + __le64 lbstm; + __u8 pic; + __u8 rsvd9[3]; + __le32 elbaf[64]; + __u8 rsvd268[3828]; +}; + +enum { + NVME_ID_NS_NVM_STS_MASK = 0x3f, + NVME_ID_NS_NVM_GUARD_SHIFT = 7, + NVME_ID_NS_NVM_GUARD_MASK = 0x3, +}; + +static inline __u8 nvme_elbaf_sts(__u32 elbaf) +{ + return elbaf & NVME_ID_NS_NVM_STS_MASK; +} + +static inline __u8 nvme_elbaf_guard_type(__u32 elbaf) +{ + return (elbaf >> NVME_ID_NS_NVM_GUARD_SHIFT) & NVME_ID_NS_NVM_GUARD_MASK; +} + struct nvme_id_ctrl_nvm { __u8 vsl; __u8 wzsl; @@ -478,6 +501,8 @@ enum { NVME_NS_FEAT_IO_OPT = 1 << 4, NVME_NS_ATTR_RO = 1 << 0, NVME_NS_FLBAS_LBA_MASK = 0xf, + NVME_NS_FLBAS_LBA_UMASK = 0x60, + NVME_NS_FLBAS_LBA_SHIFT = 1, NVME_NS_FLBAS_META_EXT = 0x10, NVME_NS_NMIC_SHARED = 1 << 0, NVME_LBAF_RP_BEST = 0, @@ -496,6 +521,18 @@ enum { NVME_NS_DPS_PI_TYPE3 = 3, }; +enum { + NVME_NVM_NS_16B_GUARD = 0, + NVME_NVM_NS_32B_GUARD = 1, + NVME_NVM_NS_64B_GUARD = 2, +}; + +static inline __u8 nvme_lbaf_index(__u8 flbas) +{ + return (flbas & NVME_NS_FLBAS_LBA_MASK) | + ((flbas & NVME_NS_FLBAS_LBA_UMASK) >> NVME_NS_FLBAS_LBA_SHIFT); +} + /* Identify Namespace Metadata Capabilities (MC): */ enum { NVME_MC_EXTENDED_LBA = (1 << 0), @@ -842,7 +879,8 @@ struct nvme_rw_command { __u8 flags; __u16 command_id; __le32 nsid; - __u64 rsvd2; + __le32 cdw2; + __le32 cdw3; __le64 metadata; union nvme_data_ptr dptr; __le64 slba; @@ -996,11 +1034,14 @@ enum { struct nvme_feat_host_behavior { __u8 acre; - __u8 resv1[511]; + __u8 etdas; + __u8 lbafee; + __u8 resv1[509]; }; enum { NVME_ENABLE_ACRE = 1, + NVME_ENABLE_LBAFEE = 1, }; /* Admin commands */ -- cgit v1.2.3 From 2984539959dbaf4e65e19bf90c2419304a81a985 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 8 Feb 2022 17:16:33 +0100 Subject: tick/rcu: Remove obsolete rcu_needs_cpu() parameters With the removal of CONFIG_RCU_FAST_NO_HZ, the parameters in rcu_needs_cpu() are not necessary anymore. Simply remove them. Signed-off-by: Frederic Weisbecker Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Paul E. McKenney Cc: Paul Menzel --- include/linux/rcutiny.h | 3 +-- include/linux/rcutree.h | 2 +- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 858f4d429946..5fed476f977f 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -64,9 +64,8 @@ static inline void rcu_softirq_qs(void) rcu_tasks_qs(current, (preempt)); \ } while (0) -static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt) +static inline int rcu_needs_cpu(void) { - *nextevt = KTIME_MAX; return 0; } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 53209d669400..6cc91291d078 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -19,7 +19,7 @@ void rcu_softirq_qs(void); void rcu_note_context_switch(bool preempt); -int rcu_needs_cpu(u64 basem, u64 *nextevt); +int rcu_needs_cpu(void); void rcu_cpu_stall_reset(void); /* -- cgit v1.2.3 From 0345691b24c076655ce8f0f4bfd24cba3467ccbd Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 8 Feb 2022 17:16:34 +0100 Subject: tick/rcu: Stop allowing RCU_SOFTIRQ in idle RCU_SOFTIRQ used to be special in that it could be raised on purpose within the idle path to prevent from stopping the tick. Some code still prevents from unnecessary warnings related to this specific behaviour while entering in dynticks-idle mode. However the nohz layout has changed quite a bit in ten years, and the removal of CONFIG_RCU_FAST_NO_HZ has been the final straw to this safe-conduct. Now the RCU_SOFTIRQ vector is expected to be raised from sane places. A remaining corner case is admitted though when the vector is invoked in fragile hotplug path. Signed-off-by: Frederic Weisbecker Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Paul E. McKenney Cc: Paul Menzel --- include/linux/interrupt.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 9367f1cb2e3c..9613326d2f8a 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -579,7 +579,13 @@ enum NR_SOFTIRQS }; -#define SOFTIRQ_STOP_IDLE_MASK (~(1 << RCU_SOFTIRQ)) +/* + * Ignoring the RCU vector after ksoftirqd is parked is fine + * because: + * 1) rcutree_migrate_callbacks() takes care of the queue. + * 2) rcu_report_dead() reports the final quiescent states. + */ +#define SOFTIRQ_HOTPLUG_SAFE_MASK (BIT(RCU_SOFTIRQ)) /* map softirq index to softirq name. update 'softirq_to_name' in * kernel/softirq.c when adding a new softirq. -- cgit v1.2.3 From f96272a90d9eaea9933aaab704ddbd258feb3841 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 8 Feb 2022 17:16:35 +0100 Subject: lib/irq_poll: Declare IRQ_POLL softirq vector as ksoftirqd-parking safe The following warning may appear while setting a CPU down: NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #20!!! The IRQ_POLL_SOFTIRQ vector can be raised during the hotplug cpu_down() path after ksoftirqd is parked and before the CPU actually dies. However this is handled afterward at the CPUHP_IRQ_POLL_DEAD stage where the queue gets migrated. Hence this warning can be considered spurious and the vector can join the "hotplug-safe" list. Reported-and-tested-by: Paul Menzel Signed-off-by: Frederic Weisbecker Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Paul E. McKenney Cc: Paul Menzel --- include/linux/interrupt.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 9613326d2f8a..f40754caaefa 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -580,12 +580,15 @@ enum }; /* - * Ignoring the RCU vector after ksoftirqd is parked is fine - * because: - * 1) rcutree_migrate_callbacks() takes care of the queue. + * The following vectors can be safely ignored after ksoftirqd is parked: + * + * _ RCU: + * 1) rcutree_migrate_callbacks() migrates the queue. * 2) rcu_report_dead() reports the final quiescent states. + * + * _ IRQ_POLL: irq_poll_cpu_dead() migrates the queue */ -#define SOFTIRQ_HOTPLUG_SAFE_MASK (BIT(RCU_SOFTIRQ)) +#define SOFTIRQ_HOTPLUG_SAFE_MASK (BIT(RCU_SOFTIRQ) | BIT(IRQ_POLL_SOFTIRQ)) /* map softirq index to softirq name. update 'softirq_to_name' in * kernel/softirq.c when adding a new softirq. -- cgit v1.2.3 From b0e846248de5bd57e4b785791f359ecb8f2d7311 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Mon, 27 Dec 2021 07:48:39 +0100 Subject: mfd: db8500-prcmu: Remove dead code for a non-existing config The config DBX500_PRCMU_QOS_POWER was never introduced in the kernel repository. So, the ifdef in ./include/linux/mfd/dbx500-prcmu.h was never effective. Remove these dead function prototypes. Signed-off-by: Lukas Bulwahn Reviewed-by: Linus Walleij Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211227064839.21405-1-lukas.bulwahn@gmail.com --- include/linux/mfd/dbx500-prcmu.h | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h index cbf9d7619493..2a255362b5ac 100644 --- a/include/linux/mfd/dbx500-prcmu.h +++ b/include/linux/mfd/dbx500-prcmu.h @@ -556,22 +556,6 @@ static inline void prcmu_clear(unsigned int reg, u32 bits) #define PRCMU_QOS_ARM_OPP 3 #define PRCMU_QOS_DEFAULT_VALUE -1 -#ifdef CONFIG_DBX500_PRCMU_QOS_POWER - -unsigned long prcmu_qos_get_cpufreq_opp_delay(void); -void prcmu_qos_set_cpufreq_opp_delay(unsigned long); -void prcmu_qos_force_opp(int, s32); -int prcmu_qos_requirement(int pm_qos_class); -int prcmu_qos_add_requirement(int pm_qos_class, char *name, s32 value); -int prcmu_qos_update_requirement(int pm_qos_class, char *name, s32 new_value); -void prcmu_qos_remove_requirement(int pm_qos_class, char *name); -int prcmu_qos_add_notifier(int prcmu_qos_class, - struct notifier_block *notifier); -int prcmu_qos_remove_notifier(int prcmu_qos_class, - struct notifier_block *notifier); - -#else - static inline unsigned long prcmu_qos_get_cpufreq_opp_delay(void) { return 0; @@ -613,6 +597,4 @@ static inline int prcmu_qos_remove_notifier(int prcmu_qos_class, return 0; } -#endif - #endif /* __MACH_PRCMU_H */ -- cgit v1.2.3 From 56f216d8efbc1212bf5ff8a6ff5e29927965e8db Mon Sep 17 00:00:00 2001 From: Peter Geis Date: Tue, 8 Feb 2022 14:40:23 -0500 Subject: mfd: rk808: Add reboot support to rk808.c This adds reboot support to the rk808 pmic driver and enables it for the rk809 and rk817 devices. This only enables if the rockchip,system-power-controller flag is set. Signed-off-by: Peter Geis Signed-off-by: Frank Wunderlich Reviewed-by: Dmitry Osipenko Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20220208194023.929720-1-pgwipeout@gmail.com --- include/linux/mfd/rk808.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h index a96e6d43ca06..58602032e642 100644 --- a/include/linux/mfd/rk808.h +++ b/include/linux/mfd/rk808.h @@ -373,6 +373,7 @@ enum rk805_reg { #define SWITCH2_EN BIT(6) #define SWITCH1_EN BIT(5) #define DEV_OFF_RST BIT(3) +#define DEV_RST BIT(2) #define DEV_OFF BIT(0) #define RTC_STOP BIT(0) -- cgit v1.2.3 From 68fa55f0e05ce371c4b5de7932d9f570d61bf791 Mon Sep 17 00:00:00 2001 From: Bharat Bhushan Date: Fri, 11 Feb 2022 10:23:46 +0530 Subject: perf/marvell: cn10k DDR perf event core ownership As DDR perf event counters are not per core, so they should be accessed only by one core at a time. Select new core when previously owning core is going offline. Signed-off-by: Bharat Bhushan Reviewed-by: Bhaskara Budiredla Link: https://lore.kernel.org/r/20220211045346.17894-5-bbhushan2@marvell.com Signed-off-by: Will Deacon --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 411a428ace4d..2bc550ac8dc7 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -231,6 +231,7 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_QCOM_L3_ONLINE, CPUHP_AP_PERF_ARM_APM_XGENE_ONLINE, CPUHP_AP_PERF_ARM_CAVIUM_TX2_UNCORE_ONLINE, + CPUHP_AP_PERF_ARM_MARVELL_CN10K_DDR_ONLINE, CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE, -- cgit v1.2.3 From 56edb6c25f11f25df153f4804f2d5bced2b49a9e Mon Sep 17 00:00:00 2001 From: Eric Snowberg Date: Tue, 25 Jan 2022 21:58:30 -0500 Subject: KEYS: store reference to machine keyring Expose the .machine keyring created in integrity code by adding a reference. Store a reference to the machine keyring in system keyring code. The system keyring code needs this to complete the keyring link to the machine keyring. Signed-off-by: Eric Snowberg Reviewed-by: Jarkko Sakkinen Tested-by: Mimi Zohar Signed-off-by: Jarkko Sakkinen --- include/keys/system_keyring.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/keys/system_keyring.h b/include/keys/system_keyring.h index 6acd3cf13a18..98c9b10cdc17 100644 --- a/include/keys/system_keyring.h +++ b/include/keys/system_keyring.h @@ -38,6 +38,14 @@ extern int restrict_link_by_builtin_and_secondary_trusted( #define restrict_link_by_builtin_and_secondary_trusted restrict_link_by_builtin_trusted #endif +#ifdef CONFIG_INTEGRITY_MACHINE_KEYRING +extern void __init set_machine_trusted_keys(struct key *keyring); +#else +static inline void __init set_machine_trusted_keys(struct key *keyring) +{ +} +#endif + extern struct pkcs7_message *pkcs7; #ifdef CONFIG_SYSTEM_BLACKLIST_KEYRING extern int mark_hash_blacklisted(const char *hash); -- cgit v1.2.3 From 087aa4ed379054951cb3c8ccaa0c4dbafd903c01 Mon Sep 17 00:00:00 2001 From: Eric Snowberg Date: Tue, 25 Jan 2022 21:58:31 -0500 Subject: KEYS: Introduce link restriction for machine keys Introduce a new link restriction that includes the trusted builtin, secondary and machine keys. The restriction is based on the key to be added being vouched for by a key in any of these three keyrings. With the introduction of the machine keyring, the end-user may choose to trust Machine Owner Keys (MOK) within the kernel. If they have chosen to trust them, the .machine keyring will contain these keys. If not, the machine keyring will always be empty. Update the restriction check to allow the secondary trusted keyring to also trust machine keys. Allow the .machine keyring to be linked to the secondary_trusted_keys. After the link is created, keys contained in the .machine keyring will automatically be searched when searching secondary_trusted_keys. Suggested-by: Mimi Zohar Signed-off-by: Eric Snowberg Reviewed-by: Jarkko Sakkinen Tested-by: Mimi Zohar Signed-off-by: Jarkko Sakkinen --- include/keys/system_keyring.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/keys/system_keyring.h b/include/keys/system_keyring.h index 98c9b10cdc17..2419a735420f 100644 --- a/include/keys/system_keyring.h +++ b/include/keys/system_keyring.h @@ -39,8 +39,14 @@ extern int restrict_link_by_builtin_and_secondary_trusted( #endif #ifdef CONFIG_INTEGRITY_MACHINE_KEYRING +extern int restrict_link_by_builtin_secondary_and_machine( + struct key *dest_keyring, + const struct key_type *type, + const union key_payload *payload, + struct key *restrict_key); extern void __init set_machine_trusted_keys(struct key *keyring); #else +#define restrict_link_by_builtin_secondary_and_machine restrict_link_by_builtin_trusted static inline void __init set_machine_trusted_keys(struct key *keyring) { } -- cgit v1.2.3 From d3cff4a95ed78ca192fc4bbb2743d13b7a6cc555 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 28 Jan 2022 11:56:55 -0800 Subject: KEYS: remove support for asym_tpm keys asym_tpm keys are tied to TPM v1.2, which uses outdated crypto and has been deprecated in favor of TPM v2.0 for over 7 years. A very quick look at this code also immediately found some memory safety bugs (https://lore.kernel.org/r/20220113235440.90439-2-ebiggers@kernel.org). Note that this code is reachable by unprivileged users. According to Jarkko (one of the keyrings subsystem maintainers), this code has no practical use cases, and he isn't willing to maintain it (https://lore.kernel.org/r/YfFZPbKkgYJGWu1Q@iki.fi). Therefore, let's remove it. Note that this feature didn't have any documentation or tests, so we don't need to worry about removing those. Cc: David Howells Cc: Denis Kenzior Cc: James Morris Cc: Jarkko Sakkinen Cc: Marcel Holtmann Signed-off-by: Eric Biggers Reviewed-by: Jarkko Sakkinen Acked-by: Ard Biesheuvel Signed-off-by: Jarkko Sakkinen --- include/crypto/asym_tpm_subtype.h | 19 ------------------- 1 file changed, 19 deletions(-) delete mode 100644 include/crypto/asym_tpm_subtype.h (limited to 'include') diff --git a/include/crypto/asym_tpm_subtype.h b/include/crypto/asym_tpm_subtype.h deleted file mode 100644 index 48198c36d6b9..000000000000 --- a/include/crypto/asym_tpm_subtype.h +++ /dev/null @@ -1,19 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#ifndef _LINUX_ASYM_TPM_SUBTYPE_H -#define _LINUX_ASYM_TPM_SUBTYPE_H - -#include - -struct tpm_key { - void *blob; - u32 blob_len; - uint16_t key_len; /* Size in bits of the key */ - const void *pub_key; /* pointer inside blob to the public key bytes */ - uint16_t pub_key_len; /* length of the public key */ -}; - -struct tpm_key *tpm_key_create(const void *blob, uint32_t blob_len); - -extern struct asymmetric_key_subtype asym_tpm_subtype; - -#endif /* _LINUX_ASYM_TPM_SUBTYPE_H */ -- cgit v1.2.3 From 64807c2321512f67959e51f09e302c145c336184 Mon Sep 17 00:00:00 2001 From: Arun Ramadoss Date: Mon, 7 Mar 2022 21:45:14 +0530 Subject: net: phy: exported the genphy_read_master_slave function genphy_read_master_slave function allows to configure the master/slave for gigabit phys only. In order to use this function irrespective of speed, moved the speed check to the genphy_read_status call. Signed-off-by: Arun Ramadoss Reviewed-by: Andrew Lunn Signed-off-by: Paolo Abeni --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index cd08cf1a8b0d..20beeaa7443b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1578,6 +1578,7 @@ int genphy_update_link(struct phy_device *phydev); int genphy_read_lpa(struct phy_device *phydev); int genphy_read_status_fixed(struct phy_device *phydev); int genphy_read_status(struct phy_device *phydev); +int genphy_read_master_slave(struct phy_device *phydev); int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); int genphy_loopback(struct phy_device *phydev, bool enable); -- cgit v1.2.3 From 1280f12f56a15abde23503ba876343e5f201c9c2 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 8 Feb 2022 18:56:03 +0000 Subject: drivers/perf: arm_pmu: Handle 47 bit counters The current ARM PMU framework can only deal with 32 or 64bit counters. Teach it about a 47bit flavour. Yes, this is odd. Reviewed-by: Hector Martin Signed-off-by: Marc Zyngier Signed-off-by: Will Deacon --- include/linux/perf/arm_pmu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 2512e2f9cd4e..0407a38b470a 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -26,6 +26,8 @@ */ /* Event uses a 64bit counter */ #define ARMPMU_EVT_64BIT 1 +/* Event uses a 47bit counter */ +#define ARMPMU_EVT_47BIT 2 #define HW_OP_UNSUPPORTED 0xFFFF #define C(_x) PERF_COUNT_HW_CACHE_##_x -- cgit v1.2.3 From 015044e9610c8523794ea6cb55d5388bc00ba96a Mon Sep 17 00:00:00 2001 From: Codrin Ciubotariu Date: Mon, 7 Mar 2022 14:21:58 +0200 Subject: ASoC: dt-bindings: Document Microchip's PDMC Add DT bindings for the new Microchip PDMC embedded in sama7g5 SoCs. Signed-off-by: Codrin Ciubotariu Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220307122202.2251639-3-codrin.ciubotariu@microchip.com Signed-off-by: Mark Brown --- include/dt-bindings/sound/microchip,pdmc.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 include/dt-bindings/sound/microchip,pdmc.h (limited to 'include') diff --git a/include/dt-bindings/sound/microchip,pdmc.h b/include/dt-bindings/sound/microchip,pdmc.h new file mode 100644 index 000000000000..96cde94ce74f --- /dev/null +++ b/include/dt-bindings/sound/microchip,pdmc.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __DT_BINDINGS_MICROCHIP_PDMC_H__ +#define __DT_BINDINGS_MICROCHIP_PDMC_H__ + +/* PDM microphone's pin placement */ +#define MCHP_PDMC_DS0 0 +#define MCHP_PDMC_DS1 1 + +/* PDM microphone clock edge sampling */ +#define MCHP_PDMC_CLK_POSITIVE 0 +#define MCHP_PDMC_CLK_NEGATIVE 1 + +#endif /* __DT_BINDINGS_MICROCHIP_PDMC_H__ */ -- cgit v1.2.3 From a8749a35c39903120ec421ef2525acc8e0daa55c Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 8 Mar 2022 04:47:22 -0500 Subject: mm: vmalloc: introduce array allocation functions Linux has dozens of occurrences of vmalloc(array_size()) and vzalloc(array_size()). Allow to simplify the code by providing vmalloc_array and vcalloc, as well as the underscored variants that let the caller specify the GFP flags. Acked-by: Michal Hocko Signed-off-by: Paolo Bonzini --- include/linux/vmalloc.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 880227b9f044..d1bbd4fd50c5 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -159,6 +159,11 @@ void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) __alloc_size(1); void *vmalloc_no_huge(unsigned long size) __alloc_size(1); +extern void *__vmalloc_array(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); +extern void *vmalloc_array(size_t n, size_t size) __alloc_size(1, 2); +extern void *__vcalloc(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); +extern void *vcalloc(size_t n, size_t size) __alloc_size(1, 2); + extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); -- cgit v1.2.3 From a99a3e2efaf1f4454eb5c9176f47e66de075b134 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 31 Jan 2022 11:50:46 -0600 Subject: coredump: Move definition of struct coredump_params into coredump.h Move the definition of struct coredump_params into coredump.h where it belongs. Remove the slightly errorneous comment explaining why struct coredump_params was declared in binfmts.h. Signed-off-by: "Eric W. Biederman" --- include/linux/binfmts.h | 13 +------------ include/linux/coredump.h | 12 +++++++++++- 2 files changed, 12 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 5d651c219c99..3dc20c4f394c 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -8,6 +8,7 @@ #include struct filename; +struct coredump_params; #define CORENAME_MAX_SIZE 128 @@ -77,18 +78,6 @@ struct linux_binprm { #define BINPRM_FLAGS_PRESERVE_ARGV0_BIT 3 #define BINPRM_FLAGS_PRESERVE_ARGV0 (1 << BINPRM_FLAGS_PRESERVE_ARGV0_BIT) -/* Function parameter for binfmt->coredump */ -struct coredump_params { - const kernel_siginfo_t *siginfo; - struct pt_regs *regs; - struct file *file; - unsigned long limit; - unsigned long mm_flags; - loff_t written; - loff_t pos; - loff_t to_skip; -}; - /* * This structure defines the functions that are used to load the binary formats that * linux accepts. diff --git a/include/linux/coredump.h b/include/linux/coredump.h index 248a68c668b4..2ee1460a1d66 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -14,11 +14,21 @@ struct core_vma_metadata { unsigned long dump_size; }; +struct coredump_params { + const kernel_siginfo_t *siginfo; + struct pt_regs *regs; + struct file *file; + unsigned long limit; + unsigned long mm_flags; + loff_t written; + loff_t pos; + loff_t to_skip; +}; + /* * These are the only things you should do on a core-file: use only these * functions to write out all the necessary info. */ -struct coredump_params; extern void dump_skip_to(struct coredump_params *cprm, unsigned long to); extern void dump_skip(struct coredump_params *cprm, size_t nr); extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr); -- cgit v1.2.3 From 95c5436a4883841588dae86fb0b9325f47ba5ad3 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 8 Mar 2022 12:55:29 -0600 Subject: coredump: Snapshot the vmas in do_coredump Move the call of dump_vma_snapshot and kvfree(vma_meta) out of the individual coredump routines into do_coredump itself. This makes the code less error prone and easier to maintain. Make the vma snapshot available to the coredump routines in struct coredump_params. This makes it easier to change and update what is captures in the vma snapshot and will be needed for fixing fill_file_notes. Reviewed-by: Jann Horn Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- include/linux/coredump.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/coredump.h b/include/linux/coredump.h index 2ee1460a1d66..7d05370e555e 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -23,6 +23,9 @@ struct coredump_params { loff_t written; loff_t pos; loff_t to_skip; + int vma_count; + size_t vma_data_size; + struct core_vma_metadata *vma_meta; }; /* @@ -35,9 +38,6 @@ extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr); extern int dump_align(struct coredump_params *cprm, int align); int dump_user_range(struct coredump_params *cprm, unsigned long start, unsigned long len); -int dump_vma_snapshot(struct coredump_params *cprm, int *vma_count, - struct core_vma_metadata **vma_meta, - size_t *vma_data_size_ptr); extern void do_coredump(const kernel_siginfo_t *siginfo); #else static inline void do_coredump(const kernel_siginfo_t *siginfo) {} -- cgit v1.2.3 From a759de6991b35ad437adba32b5f0cb2fd9e75929 Mon Sep 17 00:00:00 2001 From: Youngjin Jang Date: Tue, 8 Mar 2022 04:07:39 +0900 Subject: PM: sleep: Add device name to suspend_report_result() Currently, suspend_report_result() prints only function information. If any driver uses a common PM function, nobody knows who exactly called the failing function. A device pinter is needed to recognize the failing device. For example: PM: dpm_run_callback(): pnp_bus_suspend+0x0/0x10 returns 0 PM: dpm_run_callback(): pci_pm_suspend+0x0/0x150 returns 0 become after the change: serial 00:05: PM: dpm_run_callback(): pnp_bus_suspend+0x0/0x10 returns 0 pci 0000:00:01.3: PM: dpm_run_callback(): pci_pm_suspend+0x0/0x150 returns 0 Signed-off-by: Youngjin Jang [ rjw: Changelog edits ] Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/pm.h b/include/linux/pm.h index f7d2be686359..e65b3ab28377 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -770,11 +770,11 @@ extern int dpm_suspend_late(pm_message_t state); extern int dpm_suspend(pm_message_t state); extern int dpm_prepare(pm_message_t state); -extern void __suspend_report_result(const char *function, void *fn, int ret); +extern void __suspend_report_result(const char *function, struct device *dev, void *fn, int ret); -#define suspend_report_result(fn, ret) \ +#define suspend_report_result(dev, fn, ret) \ do { \ - __suspend_report_result(__func__, fn, ret); \ + __suspend_report_result(__func__, dev, fn, ret); \ } while (0) extern int device_pm_wait_for_dev(struct device *sub, struct device *dev); @@ -814,7 +814,7 @@ static inline int dpm_suspend_start(pm_message_t state) return 0; } -#define suspend_report_result(fn, ret) do {} while (0) +#define suspend_report_result(dev, fn, ret) do {} while (0) static inline int device_pm_wait_for_dev(struct device *a, struct device *b) { -- cgit v1.2.3 From 390031c942116d4733310f0684beb8db19885fe6 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 8 Mar 2022 13:04:19 -0600 Subject: coredump: Use the vma snapshot in fill_files_note Matthew Wilcox reported that there is a missing mmap_lock in file_files_note that could possibly lead to a user after free. Solve this by using the existing vma snapshot for consistency and to avoid the need to take the mmap_lock anywhere in the coredump code except for dump_vma_snapshot. Update the dump_vma_snapshot to capture vm_pgoff and vm_file that are neeeded by fill_files_note. Add free_vma_snapshot to free the captured values of vm_file. Reported-by: Matthew Wilcox Link: https://lkml.kernel.org/r/20220131153740.2396974-1-willy@infradead.org Cc: stable@vger.kernel.org Fixes: a07279c9a8cd ("binfmt_elf, binfmt_elf_fdpic: use a VMA list snapshot") Fixes: 2aa362c49c31 ("coredump: extend core dump note section to contain file names of mapped files") Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- include/linux/coredump.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/coredump.h b/include/linux/coredump.h index 7d05370e555e..08a1d3e7e46d 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -12,6 +12,8 @@ struct core_vma_metadata { unsigned long start, end; unsigned long flags; unsigned long dump_size; + unsigned long pgoff; + struct file *file; }; struct coredump_params { -- cgit v1.2.3 From dc55e35f9e810f23dd69cfdc91a3d636023f57a2 Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Mon, 14 Feb 2022 19:18:14 +0100 Subject: ipc: Store mqueue sysctls in the ipc namespace Right now, the mqueue sysctls take ipc namespaces into account in a rather hacky way. This works in most cases, but does not respect the user namespace. Within the user namespace, the user cannot change the /proc/sys/fs/mqueue/* parametres. This poses a problem in the rootless containers. To solve this I changed the implementation of the mqueue sysctls just like some other sysctls. So far, the changes do not provide additional access to files. This will be done in a future patch. v3: * Don't implemenet set_permissions to keep the current behavior. v2: * Fixed compilation problem if CONFIG_POSIX_MQUEUE_SYSCTL is not specified. Reported-by: kernel test robot Signed-off-by: Alexey Gladkov Link: https://lkml.kernel.org/r/b0ccbb2489119f1f20c737cf1930c3a9c4e4243a.1644862280.git.legion@kernel.org Signed-off-by: Eric W. Biederman --- include/linux/ipc_namespace.h | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index b75395ec8d52..fa787d97d60a 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -10,6 +10,7 @@ #include #include #include +#include struct user_namespace; @@ -63,6 +64,9 @@ struct ipc_namespace { unsigned int mq_msg_default; unsigned int mq_msgsize_default; + struct ctl_table_set mq_set; + struct ctl_table_header *mq_sysctls; + /* user_ns which owns the ipc ns */ struct user_namespace *user_ns; struct ucounts *ucounts; @@ -169,14 +173,18 @@ static inline void put_ipc_ns(struct ipc_namespace *ns) #ifdef CONFIG_POSIX_MQUEUE_SYSCTL -struct ctl_table_header; -extern struct ctl_table_header *mq_register_sysctl_table(void); +void retire_mq_sysctls(struct ipc_namespace *ns); +bool setup_mq_sysctls(struct ipc_namespace *ns); #else /* CONFIG_POSIX_MQUEUE_SYSCTL */ -static inline struct ctl_table_header *mq_register_sysctl_table(void) +static inline void retire_mq_sysctls(struct ipc_namespace *ns) { - return NULL; +} + +static inline bool setup_mq_sysctls(struct ipc_namespace *ns) +{ + return true; } #endif /* CONFIG_POSIX_MQUEUE_SYSCTL */ -- cgit v1.2.3 From 1f5c135ee509e89e0cc274333a65f73c62cb16e5 Mon Sep 17 00:00:00 2001 From: Alexey Gladkov Date: Mon, 14 Feb 2022 19:18:15 +0100 Subject: ipc: Store ipc sysctls in the ipc namespace The ipc sysctls are not available for modification inside the user namespace. Following the mqueue sysctls, we changed the implementation to be more userns friendly. So far, the changes do not provide additional access to files. This will be done in a future patch. Signed-off-by: Alexey Gladkov Link: https://lkml.kernel.org/r/be6f9d014276f4dddd0c3aa05a86052856c1c555.1644862280.git.legion@kernel.org Signed-off-by: Eric W. Biederman --- include/linux/ipc_namespace.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index fa787d97d60a..e3e8c8662b49 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -67,6 +67,9 @@ struct ipc_namespace { struct ctl_table_set mq_set; struct ctl_table_header *mq_sysctls; + struct ctl_table_set ipc_set; + struct ctl_table_header *ipc_sysctls; + /* user_ns which owns the ipc ns */ struct user_namespace *user_ns; struct ucounts *ucounts; @@ -188,4 +191,22 @@ static inline bool setup_mq_sysctls(struct ipc_namespace *ns) } #endif /* CONFIG_POSIX_MQUEUE_SYSCTL */ + +#ifdef CONFIG_SYSVIPC_SYSCTL + +bool setup_ipc_sysctls(struct ipc_namespace *ns); +void retire_ipc_sysctls(struct ipc_namespace *ns); + +#else /* CONFIG_SYSVIPC_SYSCTL */ + +static inline void retire_ipc_sysctls(struct ipc_namespace *ns) +{ +} + +static inline bool setup_ipc_sysctls(struct ipc_namespace *ns) +{ + return true; +} + +#endif /* CONFIG_SYSVIPC_SYSCTL */ #endif -- cgit v1.2.3 From c57bef0287dd5deeabaea5727950559fb9037cd9 Mon Sep 17 00:00:00 2001 From: Barret Rhoden Date: Thu, 6 Jan 2022 12:20:40 -0500 Subject: prlimit: make do_prlimit() static There are no other callers in the kernel. Fixed up a comment format and whitespace issue when moving do_prlimit() higher in sys.c. Signed-off-by: Barret Rhoden Link: https://lkml.kernel.org/r/20220106172041.522167-3-brho@google.com Signed-off-by: Eric W. Biederman --- include/linux/resource.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/resource.h b/include/linux/resource.h index bdf491cbcab7..4fdbc0c3f315 100644 --- a/include/linux/resource.h +++ b/include/linux/resource.h @@ -8,7 +8,5 @@ struct task_struct; void getrusage(struct task_struct *p, int who, struct rusage *ru); -int do_prlimit(struct task_struct *tsk, unsigned int resource, - struct rlimit *new_rlim, struct rlimit *old_rlim); #endif -- cgit v1.2.3 From 18c91bb2d87268d23868bf13508f5bc9cf04e89a Mon Sep 17 00:00:00 2001 From: Barret Rhoden Date: Thu, 6 Jan 2022 12:20:41 -0500 Subject: prlimit: do not grab the tasklist_lock Unnecessarily grabbing the tasklist_lock can be a scalability bottleneck for workloads that also must grab the tasklist_lock for waiting, killing, and cloning. The tasklist_lock was grabbed to protect tsk->sighand from disappearing (becoming NULL). tsk->signal was already protected by holding a reference to tsk. update_rlimit_cpu() assumed tsk->sighand != NULL. With this commit, it attempts to lock_task_sighand(). However, this means that update_rlimit_cpu() can fail. This only happens when a task is exiting. Note that during exec, sighand may *change*, but it will not be NULL. Prior to this commit, the do_prlimit() ensured that update_rlimit_cpu() would not fail by read locking the tasklist_lock and checking tsk->sighand != NULL. If update_rlimit_cpu() fails, there may be other tasks that are not exiting that share tsk->signal. However, the group_leader is the last task to be released, so if we cannot update_rlimit_cpu(group_leader), then the entire process is exiting. The only other caller of update_rlimit_cpu() is selinux_bprm_committing_creds(). It has tsk == current, so update_rlimit_cpu() cannot fail (current->sighand cannot disappear until current exits). This change resulted in a 14% speedup on a microbenchmark where parents kill and wait on their children, and children getpriority, setpriority, and getrlimit. Signed-off-by: Barret Rhoden Link: https://lkml.kernel.org/r/20220106172041.522167-4-brho@google.com Signed-off-by: Eric W. Biederman --- include/linux/posix-timers.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 5bbcd280bfd2..9cf126c3b27f 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -253,7 +253,7 @@ void posix_cpu_timers_exit_group(struct task_struct *task); void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, u64 *newval, u64 *oldval); -void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); +int update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); void posixtimer_rearm(struct kernel_siginfo *info); #endif -- cgit v1.2.3 From 6914b82f37215ef510f9867bec14d5150fd970e5 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 22 Feb 2022 02:15:28 +0100 Subject: dt-bindings: clock: add QCOM SM6350 display clock bindings Add device tree bindings for display clock controller for Qualcomm Technology Inc's SM6350 SoC. Signed-off-by: Konrad Dybcio Reviewed-by: Rob Herring Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220222011534.3502-1-konrad.dybcio@somainline.org --- include/dt-bindings/clock/qcom,dispcc-sm6350.h | 48 ++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) create mode 100644 include/dt-bindings/clock/qcom,dispcc-sm6350.h (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,dispcc-sm6350.h b/include/dt-bindings/clock/qcom,dispcc-sm6350.h new file mode 100644 index 000000000000..cb54aae2723e --- /dev/null +++ b/include/dt-bindings/clock/qcom,dispcc-sm6350.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2021, The Linux Foundation. All rights reserved. + * Copyright (c) 2021, Konrad Dybcio + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_DISP_CC_SM6350_H +#define _DT_BINDINGS_CLK_QCOM_DISP_CC_SM6350_H + +/* DISP_CC clocks */ +#define DISP_CC_PLL0 0 +#define DISP_CC_MDSS_AHB_CLK 1 +#define DISP_CC_MDSS_AHB_CLK_SRC 2 +#define DISP_CC_MDSS_BYTE0_CLK 3 +#define DISP_CC_MDSS_BYTE0_CLK_SRC 4 +#define DISP_CC_MDSS_BYTE0_DIV_CLK_SRC 5 +#define DISP_CC_MDSS_BYTE0_INTF_CLK 6 +#define DISP_CC_MDSS_DP_AUX_CLK 7 +#define DISP_CC_MDSS_DP_AUX_CLK_SRC 8 +#define DISP_CC_MDSS_DP_CRYPTO_CLK 9 +#define DISP_CC_MDSS_DP_CRYPTO_CLK_SRC 10 +#define DISP_CC_MDSS_DP_LINK_CLK 11 +#define DISP_CC_MDSS_DP_LINK_CLK_SRC 12 +#define DISP_CC_MDSS_DP_LINK_DIV_CLK_SRC 13 +#define DISP_CC_MDSS_DP_LINK_INTF_CLK 14 +#define DISP_CC_MDSS_DP_PIXEL_CLK 15 +#define DISP_CC_MDSS_DP_PIXEL_CLK_SRC 16 +#define DISP_CC_MDSS_ESC0_CLK 17 +#define DISP_CC_MDSS_ESC0_CLK_SRC 18 +#define DISP_CC_MDSS_MDP_CLK 19 +#define DISP_CC_MDSS_MDP_CLK_SRC 20 +#define DISP_CC_MDSS_MDP_LUT_CLK 21 +#define DISP_CC_MDSS_NON_GDSC_AHB_CLK 22 +#define DISP_CC_MDSS_PCLK0_CLK 23 +#define DISP_CC_MDSS_PCLK0_CLK_SRC 24 +#define DISP_CC_MDSS_ROT_CLK 25 +#define DISP_CC_MDSS_ROT_CLK_SRC 26 +#define DISP_CC_MDSS_RSCC_AHB_CLK 27 +#define DISP_CC_MDSS_RSCC_VSYNC_CLK 28 +#define DISP_CC_MDSS_VSYNC_CLK 29 +#define DISP_CC_MDSS_VSYNC_CLK_SRC 30 +#define DISP_CC_SLEEP_CLK 31 +#define DISP_CC_XO_CLK 32 + +/* GDSCs */ +#define MDSS_GDSC 0 + +#endif -- cgit v1.2.3 From 7b91b9d8cc6c374cf41f772dd7191ea48011621f Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 22 Feb 2022 02:15:30 +0100 Subject: dt-bindings: clock: add SM6350 QCOM Graphics clock bindings Add device tree bindings for graphics clock controller for Qualcomm Technology Inc's SM6350 SoCs. Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Konrad Dybcio Reviewed-by: Rob Herring Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220222011534.3502-3-konrad.dybcio@somainline.org --- include/dt-bindings/clock/qcom,gpucc-sm6350.h | 37 +++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) create mode 100644 include/dt-bindings/clock/qcom,gpucc-sm6350.h (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,gpucc-sm6350.h b/include/dt-bindings/clock/qcom,gpucc-sm6350.h new file mode 100644 index 000000000000..68e814fc8acd --- /dev/null +++ b/include/dt-bindings/clock/qcom,gpucc-sm6350.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2021, The Linux Foundation. All rights reserved. + * Copyright (c) 2021, Konrad Dybcio + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_GPU_CC_SM6350_H +#define _DT_BINDINGS_CLK_QCOM_GPU_CC_SM6350_H + +/* GPU_CC clocks */ +#define GPU_CC_PLL0 0 +#define GPU_CC_PLL1 1 +#define GPU_CC_ACD_AHB_CLK 2 +#define GPU_CC_ACD_CXO_CLK 3 +#define GPU_CC_AHB_CLK 4 +#define GPU_CC_CRC_AHB_CLK 5 +#define GPU_CC_CX_GFX3D_CLK 6 +#define GPU_CC_CX_GFX3D_SLV_CLK 7 +#define GPU_CC_CX_GMU_CLK 8 +#define GPU_CC_CX_SNOC_DVM_CLK 9 +#define GPU_CC_CXO_AON_CLK 10 +#define GPU_CC_CXO_CLK 11 +#define GPU_CC_GMU_CLK_SRC 12 +#define GPU_CC_GX_CXO_CLK 13 +#define GPU_CC_GX_GFX3D_CLK 14 +#define GPU_CC_GX_GFX3D_CLK_SRC 15 +#define GPU_CC_GX_GMU_CLK 16 +#define GPU_CC_GX_VSENSE_CLK 17 + +/* CLK_HW */ +#define GPU_CC_CRC_DIV 0 + +/* GDSCs */ +#define GPU_CX_GDSC 0 +#define GPU_GX_GDSC 1 + +#endif -- cgit v1.2.3 From b565d66403e3df303a058c0d8d00d0fc6aeb2ddc Mon Sep 17 00:00:00 2001 From: Ansuel Smith Date: Sat, 26 Feb 2022 14:52:31 +0100 Subject: dt-bindings: clock: add ipq8064 ce5 clk define Add ipq8064 ce5 clk define needed for CryptoEngine in gcc driver. Define CE5_SRC is not used so it's OK to change and we align it to the QSDK naming. Signed-off-by: Ansuel Smith Acked-by: Rob Herring Reviewed-by: Stephen Boyd Tested-by: Jonathan McDowell Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220226135235.10051-12-ansuelsmth@gmail.com --- include/dt-bindings/clock/qcom,gcc-ipq806x.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,gcc-ipq806x.h b/include/dt-bindings/clock/qcom,gcc-ipq806x.h index 7deec14a6dee..02262d2ac899 100644 --- a/include/dt-bindings/clock/qcom,gcc-ipq806x.h +++ b/include/dt-bindings/clock/qcom,gcc-ipq806x.h @@ -240,7 +240,7 @@ #define PLL14 232 #define PLL14_VOTE 233 #define PLL18 234 -#define CE5_SRC 235 +#define CE5_A_CLK 235 #define CE5_H_CLK 236 #define CE5_CORE_CLK 237 #define CE3_SLEEP_CLK 238 @@ -283,5 +283,8 @@ #define EBI2_AON_CLK 281 #define NSSTCM_CLK_SRC 282 #define NSSTCM_CLK 283 +#define CE5_A_CLK_SRC 285 +#define CE5_H_CLK_SRC 286 +#define CE5_CORE_CLK_SRC 287 #endif -- cgit v1.2.3 From 887646c47d5c6fc07d281f6f728270bf04331b69 Mon Sep 17 00:00:00 2001 From: Ansuel Smith Date: Sat, 26 Feb 2022 14:52:33 +0100 Subject: dt-bindings: reset: add ipq8064 ce5 resets Add ipq8064 ce5 resets needed for CryptoEngine gcc driver. Signed-off-by: Ansuel Smith Reviewed-by: Bjorn Andersson Acked-by: Philipp Zabel Acked-by: Rob Herring Reviewed-by: Stephen Boyd Tested-by: Jonathan McDowell Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220226135235.10051-14-ansuelsmth@gmail.com --- include/dt-bindings/reset/qcom,gcc-ipq806x.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/reset/qcom,gcc-ipq806x.h b/include/dt-bindings/reset/qcom,gcc-ipq806x.h index 26b6f9200620..020c9cf18751 100644 --- a/include/dt-bindings/reset/qcom,gcc-ipq806x.h +++ b/include/dt-bindings/reset/qcom,gcc-ipq806x.h @@ -163,5 +163,10 @@ #define NSS_CAL_PRBS_RST_N_RESET 154 #define NSS_LCKDT_RST_N_RESET 155 #define NSS_SRDS_N_RESET 156 +#define CRYPTO_ENG1_RESET 157 +#define CRYPTO_ENG2_RESET 158 +#define CRYPTO_ENG3_RESET 159 +#define CRYPTO_ENG4_RESET 160 +#define CRYPTO_AHB_RESET 161 #endif -- cgit v1.2.3 From 5b2fa289c0d475bcae3a86fa04b81f1f678cc4d2 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Sat, 26 Feb 2022 22:41:24 +0100 Subject: dt-bindings: clock: qcom: rpmcc: Add RPM Modem SubSystem (MSS) clocks Add the missing clock definitions. Signed-off-by: Konrad Dybcio Acked-by: Rob Herring Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220226214126.21209-1-konrad.dybcio@somainline.org --- include/dt-bindings/clock/qcom,rpmcc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,rpmcc.h b/include/dt-bindings/clock/qcom,rpmcc.h index fb624ff39273..015db95303d1 100644 --- a/include/dt-bindings/clock/qcom,rpmcc.h +++ b/include/dt-bindings/clock/qcom,rpmcc.h @@ -165,5 +165,7 @@ #define RPM_SMD_PKA_A_CLK 119 #define RPM_SMD_CPUSS_GNOC_CLK 120 #define RPM_SMD_CPUSS_GNOC_A_CLK 121 +#define RPM_SMD_MSS_CFG_AHB_CLK 122 +#define RPM_SMD_MSS_CFG_AHB_A_CLK 123 #endif -- cgit v1.2.3 From 41d36a9f3e5336f5b48c3adba0777b8e217020d7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 8 Mar 2022 07:05:28 +0100 Subject: fs: remove kiocb.ki_hint This field is entirely unused now except for a tracepoint in f2fs, so remove it. Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220308060529.736277-2-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/fs.h | 12 ------------ include/trace/events/f2fs.h | 3 +-- 2 files changed, 1 insertion(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index e2d892b201b0..d5658ac5d8c6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -327,7 +327,6 @@ struct kiocb { void (*ki_complete)(struct kiocb *iocb, long ret); void *private; int ki_flags; - u16 ki_hint; u16 ki_ioprio; /* See linux/ioprio.h */ struct wait_page_queue *ki_waitq; /* for async buffered IO */ randomized_struct_fields_end @@ -2225,21 +2224,11 @@ static inline enum rw_hint file_write_hint(struct file *file) static inline int iocb_flags(struct file *file); -static inline u16 ki_hint_validate(enum rw_hint hint) -{ - typeof(((struct kiocb *)0)->ki_hint) max_hint = -1; - - if (hint <= max_hint) - return hint; - return 0; -} - static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = iocb_flags(filp), - .ki_hint = ki_hint_validate(file_write_hint(filp)), .ki_ioprio = get_current_ioprio(), }; } @@ -2250,7 +2239,6 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = kiocb_src->ki_flags, - .ki_hint = kiocb_src->ki_hint, .ki_ioprio = kiocb_src->ki_ioprio, .ki_pos = kiocb_src->ki_pos, }; diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index f701bb23f83c..1779e133cea0 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -956,12 +956,11 @@ TRACE_EVENT(f2fs_direct_IO_enter, __entry->rw = rw; ), - TP_printk("dev = (%d,%d), ino = %lu pos = %lld len = %lu ki_flags = %x ki_hint = %x ki_ioprio = %x rw = %d", + TP_printk("dev = (%d,%d), ino = %lu pos = %lld len = %lu ki_flags = %x ki_ioprio = %x rw = %d", show_dev_ino(__entry), __entry->iocb->ki_pos, __entry->len, __entry->iocb->ki_flags, - __entry->iocb->ki_hint, __entry->iocb->ki_ioprio, __entry->rw) ); -- cgit v1.2.3 From 7b12e49669c99f63bc12351c57e581f1f14d4adf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 8 Mar 2022 07:05:29 +0100 Subject: fs: remove fs.f_write_hint The value is now completely unused except for reporting it back through the F_GET_FILE_RW_HINT ioctl, so remove the value and the two ioctls for it. Trying to use the F_SET_FILE_RW_HINT and F_GET_FILE_RW_HINT fcntls will now return EINVAL, just like it would on a kernel that never supported this functionality in the first place. Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220308060529.736277-3-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/fs.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index d5658ac5d8c6..a1fc3b41cd82 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -966,7 +966,6 @@ struct file { * Must not be taken from IRQ context. */ spinlock_t f_lock; - enum rw_hint f_write_hint; atomic_long_t f_count; unsigned int f_flags; fmode_t f_mode; @@ -2214,14 +2213,6 @@ static inline bool HAS_UNMAPPED_ID(struct user_namespace *mnt_userns, !gid_valid(i_gid_into_mnt(mnt_userns, inode)); } -static inline enum rw_hint file_write_hint(struct file *file) -{ - if (file->f_write_hint != WRITE_LIFE_NOT_SET) - return file->f_write_hint; - - return file_inode(file)->i_write_hint; -} - static inline int iocb_flags(struct file *file); static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) -- cgit v1.2.3 From 4e5cc99e1e485954a9c09872e0eeea570fb2b5a5 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 8 Mar 2022 15:32:19 +0800 Subject: blk-mq: manage hctx map via xarray First code becomes more clean by switching to xarray from plain array. Second use-after-free on q->queue_hw_ctx can be fixed because queue_for_each_hw_ctx() may be run when updating nr_hw_queues is in-progress. With this patch, q->hctx_table is defined as xarray, and this structure will share same lifetime with request queue, so queue_for_each_hw_ctx() can use q->hctx_table to lookup hctx reliably. Reported-by: Yu Kuai Signed-off-by: Ming Lei Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220308073219.91173-7-ming.lei@redhat.com [axboe: fix blk_mq_hw_ctx forward declaration] Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 3 +-- include/linux/blkdev.h | 2 +- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 3a41d50b85d3..7aa5c54901a9 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -917,8 +917,7 @@ static inline void *blk_mq_rq_to_pdu(struct request *rq) } #define queue_for_each_hw_ctx(q, hctx, i) \ - for ((i) = 0; (i) < (q)->nr_hw_queues && \ - ({ hctx = (q)->queue_hw_ctx[i]; 1; }); (i)++) + xa_for_each(&(q)->hctx_table, (i), (hctx)) #define hctx_for_each_ctx(hctx, ctx, i) \ for ((i) = 0; (i) < (hctx)->nr_ctx && \ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e19947d84f12..d982171469bc 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -355,7 +355,7 @@ struct request_queue { unsigned int queue_depth; /* hw dispatch queues */ - struct blk_mq_hw_ctx **queue_hw_ctx; + struct xarray hctx_table; unsigned int nr_hw_queues; /* -- cgit v1.2.3 From e7f76552277ca79d9dfe4c59f7b3620a98467f9c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 8 Mar 2022 06:51:49 +0100 Subject: scsi: don't use disk->private_data to find the scsi_driver Requiring every ULP to have the scsi_drive as first member of the private data is rather fragile and not necessary anyway. Just use the driver hanging off the SCSI device instead. Signed-off-by: Christoph Hellwig Reviewed-by: Bart Van Assche Reviewed-by: Chaitanya Kulkarni Reviewed-by: Ming Lei Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20220308055200.735835-4-hch@lst.de Signed-off-by: Jens Axboe --- include/scsi/scsi_cmnd.h | 9 --------- include/scsi/scsi_driver.h | 9 +++++++-- 2 files changed, 7 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index 6794d7322cbd..e3a4c67794b1 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -13,7 +13,6 @@ #include struct Scsi_Host; -struct scsi_driver; /* * MAX_COMMAND_SIZE is: @@ -159,14 +158,6 @@ static inline void *scsi_cmd_priv(struct scsi_cmnd *cmd) return cmd + 1; } -/* make sure not to use it with passthrough commands */ -static inline struct scsi_driver *scsi_cmd_to_driver(struct scsi_cmnd *cmd) -{ - struct request *rq = scsi_cmd_to_rq(cmd); - - return *(struct scsi_driver **)rq->q->disk->private_data; -} - void scsi_done(struct scsi_cmnd *cmd); extern void scsi_finish_command(struct scsi_cmnd *cmd); diff --git a/include/scsi/scsi_driver.h b/include/scsi/scsi_driver.h index 6dffa8555a39..4ce1988b2ba0 100644 --- a/include/scsi/scsi_driver.h +++ b/include/scsi/scsi_driver.h @@ -4,11 +4,10 @@ #include #include +#include struct module; struct request; -struct scsi_cmnd; -struct scsi_device; struct scsi_driver { struct device_driver gendrv; @@ -31,4 +30,10 @@ extern int scsi_register_interface(struct class_interface *); #define scsi_unregister_interface(intf) \ class_interface_unregister(intf) +/* make sure not to use it with passthrough commands */ +static inline struct scsi_driver *scsi_cmd_to_driver(struct scsi_cmnd *cmd) +{ + return to_scsi_driver(cmd->device->sdev_gendev.driver); +} + #endif /* _SCSI_SCSI_DRIVER_H */ -- cgit v1.2.3 From 0eb4e7ee1655b7ffd3204a35d77b809d42613cb9 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Mon, 7 Mar 2022 12:44:31 -0800 Subject: mptcp: add tracepoint in mptcp_sendmsg_frag The tracepoint in get_mapping_status() only dumped the incoming mpext fields. This patch added a new tracepoint in mptcp_sendmsg_frag() to dump the outgoing mpext too. Signed-off-by: Geliang Tang Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- include/trace/events/mptcp.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/trace/events/mptcp.h b/include/trace/events/mptcp.h index 6bf43176f14c..f8e28e686c65 100644 --- a/include/trace/events/mptcp.h +++ b/include/trace/events/mptcp.h @@ -115,6 +115,10 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext, __entry->csum_reqd) ); +DEFINE_EVENT(mptcp_dump_mpext, mptcp_sendmsg_frag, + TP_PROTO(struct mptcp_ext *mpext), + TP_ARGS(mpext)); + DEFINE_EVENT(mptcp_dump_mpext, get_mapping_status, TP_PROTO(struct mptcp_ext *mpext), TP_ARGS(mpext)); -- cgit v1.2.3 From d045b9eb95a9b611c483897a69e7285aefdc66d7 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 7 Mar 2022 12:44:36 -0800 Subject: mptcp: introduce implicit endpoints In some edge scenarios, an MPTCP subflows can use a local address mapped by a "implicit" endpoint created by the in-kernel path manager. Such endpoints presence can be confusing, as it's creation is hard to track and will prevent the later endpoint creation from the user-space using the same address. Define a new endpoint flag to mark implicit endpoints and allow the user-space to replace implicit them with user-provided data at endpoint creation time. Signed-off-by: Paolo Abeni Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index f106a3941cdf..9690efedb5fa 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -81,6 +81,7 @@ enum { #define MPTCP_PM_ADDR_FLAG_SUBFLOW (1 << 1) #define MPTCP_PM_ADDR_FLAG_BACKUP (1 << 2) #define MPTCP_PM_ADDR_FLAG_FULLMESH (1 << 3) +#define MPTCP_PM_ADDR_FLAG_IMPLICIT (1 << 4) enum { MPTCP_PM_CMD_UNSPEC, -- cgit v1.2.3 From 7e580490ac9819dd55a36be2a9b3380d1391f91b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 8 Mar 2022 11:15:15 +0200 Subject: net: dsa: felix: avoid early deletion of host FDB entries The Felix driver declares FDB isolation but puts all standalone ports in VID 0. This is mostly problem-free as discussed with Alvin here: https://patchwork.kernel.org/project/netdevbpf/cover/20220302191417.1288145-1-vladimir.oltean@nxp.com/#24763870 however there is one catch. DSA still thinks that FDB entries are installed on the CPU port as many times as there are user ports, and this is problematic when multiple user ports share the same MAC address. Consider the default case where all user ports inherit their MAC address from the DSA master, and then the user runs: ip link set swp0 address 00:01:02:03:04:05 The above will make dsa_slave_set_mac_address() call dsa_port_standalone_host_fdb_add() for 00:01:02:03:04:05 in port 0's standalone database, and dsa_port_standalone_host_fdb_del() for the old address of swp0, again in swp0's standalone database. Both the ->port_fdb_add() and ->port_fdb_del() will be propagated down to the felix driver, which will end up deleting the old MAC address from the CPU port. But this is still in use by other user ports, so we end up breaking unicast termination for them. There isn't a problem in the fact that DSA keeps track of host standalone addresses in the individual database of each user port: some drivers like sja1105 need this. There also isn't a problem in the fact that some drivers choose the same VID/FID for all standalone ports. It is just that the deletion of these host addresses must be delayed until they are known to not be in use any longer, and only the driver has this knowledge. Since DSA keeps these addresses in &cpu_dp->fdbs and &cpu_db->mdbs, it is just a matter of walking over those lists and see whether the same MAC address is present on the CPU port in the port db of another user port. I have considered reusing the generic dsa_port_walk_fdbs() and dsa_port_walk_mdbs() schemes for this, but locking makes it difficult. In the ->port_fdb_add() method and co, &dp->addr_lists_lock is held, but dsa_port_walk_fdbs() also acquires that lock. Also, even assuming that we introduce an unlocked variant of the address iterator, we'd still need some relatively complex data structures, and a void *ctx in the dsa_fdb_walk_cb_t which we don't currently pass, such that drivers are able to figure out, after iterating, whether the same MAC address is or isn't present in the port db of another port. All the above, plus the fact that I expect other drivers to follow the same model as felix where all standalone ports use the same FID, made me conclude that a generic method provided by DSA is necessary: dsa_fdb_present_in_other_db() and the mdb equivalent. Felix calls this from the ->port_fdb_del() handler for the CPU port, when the database was classified to either a port db, or a LAG db. For symmetry, we also call this from ->port_fdb_add(), because if the address was installed once, then installing it a second time serves no purpose: it's already in hardware in VID 0 and it affects all standalone ports. This change moves dsa_db_equal() from switch.c to dsa.c, since it now has one more caller. Fixes: 54c319846086 ("net: mscc: ocelot: enforce FDB isolation when VLAN-unaware") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/dsa.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 759479fe8573..9d16505fc0e2 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -1227,6 +1227,12 @@ typedef int dsa_fdb_walk_cb_t(struct dsa_switch *ds, int port, int dsa_port_walk_fdbs(struct dsa_switch *ds, int port, dsa_fdb_walk_cb_t cb); int dsa_port_walk_mdbs(struct dsa_switch *ds, int port, dsa_fdb_walk_cb_t cb); +bool dsa_fdb_present_in_other_db(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid, + struct dsa_db db); +bool dsa_mdb_present_in_other_db(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_mdb *mdb, + struct dsa_db db); /* Keep inline for faster access in hot path */ static inline bool netdev_uses_dsa(const struct net_device *dev) -- cgit v1.2.3 From 1330b6ef3313fcec577d2b020c290dc8b9f11f1a Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 7 Mar 2022 16:44:21 -0800 Subject: skb: make drop reason booleanable We have a number of cases where function returns drop/no drop decision as a boolean. Now that we want to report the reason code as well we have to pass extra output arguments. We can make the reason code evaluate correctly as bool. I believe we're good to reorder the reasons as they are reported to user space as strings. Signed-off-by: Jakub Kicinski Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + include/net/tcp.h | 21 +++++++++++---------- 2 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 34f572271c0c..26538ceb4b01 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -314,6 +314,7 @@ struct sk_buff; * used to translate the reason to string. */ enum skb_drop_reason { + SKB_NOT_DROPPED_YET = 0, SKB_DROP_REASON_NOT_SPECIFIED, /* drop reason is not specified */ SKB_DROP_REASON_NO_SOCKET, /* socket not found */ SKB_DROP_REASON_PKT_TOO_SMALL, /* packet size is too small */ diff --git a/include/net/tcp.h b/include/net/tcp.h index d486d7b6112d..ee8237b58e1d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1674,10 +1674,11 @@ tcp_md5_do_lookup(const struct sock *sk, int l3index, return NULL; return __tcp_md5_do_lookup(sk, l3index, addr, family); } -bool tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, - enum skb_drop_reason *reason, - const void *saddr, const void *daddr, - int family, int dif, int sdif); + +enum skb_drop_reason +tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, + const void *saddr, const void *daddr, + int family, int dif, int sdif); #define tcp_twsk_md5_key(twsk) ((twsk)->tw_md5_key) @@ -1688,13 +1689,13 @@ tcp_md5_do_lookup(const struct sock *sk, int l3index, { return NULL; } -static inline bool tcp_inbound_md5_hash(const struct sock *sk, - const struct sk_buff *skb, - enum skb_drop_reason *reason, - const void *saddr, const void *daddr, - int family, int dif, int sdif) + +static inline enum skb_drop_reason +tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, + const void *saddr, const void *daddr, + int family, int dif, int sdif); { - return false; + return SKB_NOT_DROPPED_YET; } #define tcp_twsk_md5_key(twsk) NULL #endif -- cgit v1.2.3 From d8fd5a1e78db375f2246d43df7833fec07a221cd Mon Sep 17 00:00:00 2001 From: Joey Gouly Date: Tue, 1 Mar 2022 15:45:18 +0000 Subject: kasan: fix a missing header include of static_keys.h The kasan-enabled.h header relies on static keys, so make sure to include the header to avoid compilation errors (with JUMP_LABEL=n). It fixes the following: ./include/linux/kasan-enabled.h:9:1: warning: data definition has no type or storage class 9 | DECLARE_STATIC_KEY_FALSE(kasan_flag_enabled); | ^~~~~~~~~~~~~~~~~~~~~~~~ error: type defaults to 'int' in declaration of 'DECLARE_STATIC_KEY_FALSE' [-Werror=implicit-int] Fixes: f9b5e46f4097eb29 ("kasan: split kasan_*enabled() functions into a separate header") Cc: Peter Collingbourne Cc: Mark Rutland Cc: Catalin Marinas Cc: Will Deacon Acked-by: Andrey Konovalov Signed-off-by: Joey Gouly Link: https://lore.kernel.org/r/20220301154518.19456-1-joey.gouly@arm.com Signed-off-by: Will Deacon --- include/linux/kasan-enabled.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/kasan-enabled.h b/include/linux/kasan-enabled.h index 4b6615375022..6f612d69ea0c 100644 --- a/include/linux/kasan-enabled.h +++ b/include/linux/kasan-enabled.h @@ -2,6 +2,8 @@ #ifndef _LINUX_KASAN_ENABLED_H #define _LINUX_KASAN_ENABLED_H +#include + #ifdef CONFIG_KASAN_HW_TAGS DECLARE_STATIC_KEY_FALSE(kasan_flag_enabled); -- cgit v1.2.3 From 1498915233dde830061e008ad639b482fd76f93d Mon Sep 17 00:00:00 2001 From: Rex-BC Chen Date: Wed, 9 Mar 2022 15:36:35 +0800 Subject: drm/dsi: transfer DSI HS packets ending at the same time Since a HS transmission is composed of an arbitrary number of bytes that may not be an integer multiple of lanes, some lanes may run out of data before others. (Defined in 6.1.3 of mipi_DSI_specification_v.01-02-00) However, for some DSI RX devices (for example, anx7625), there is a limitation that packet number should be the same on all DSI lanes. In other words, they need to end a HS at the same time. Because this limitation is for some specific DSI RX devices, it is more reasonable to put the enable control in these DSI RX drivers. If DSI TX driver knows the information, they can adjust the setting for this situation. Signed-off-by: Jitao Shi Signed-off-by: Rex-BC Chen Acked-by: AngeloGioacchino Del Regno Reviewed-by: Andrzej Hajda Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20220309073637.3591-2-rex-bc.chen@mediatek.com --- include/drm/drm_mipi_dsi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/drm/drm_mipi_dsi.h b/include/drm/drm_mipi_dsi.h index 147e51b6d241..51e09a1a106a 100644 --- a/include/drm/drm_mipi_dsi.h +++ b/include/drm/drm_mipi_dsi.h @@ -137,6 +137,8 @@ struct mipi_dsi_host *of_find_mipi_dsi_host_by_node(struct device_node *node); #define MIPI_DSI_CLOCK_NON_CONTINUOUS BIT(10) /* transmit data in low power */ #define MIPI_DSI_MODE_LPM BIT(11) +/* transmit data ending at the same time for all lanes within one hsync */ +#define MIPI_DSI_HS_PKT_END_ALIGNED BIT(12) enum mipi_dsi_pixel_format { MIPI_DSI_FMT_RGB888, -- cgit v1.2.3 From 7a976552a4f264f777be236c0c83263975512f1a Mon Sep 17 00:00:00 2001 From: Ranjani Sridharan Date: Tue, 8 Mar 2022 08:43:37 -0800 Subject: ASoC: SOF: make struct snd_sof_widget IPC agnostic MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Parse the UUID token and save it in the new uuid field in struct snd_sof_widget. struct sof_ipc_comp_ext is no longer needed. So remove it too. Signed-off-by: Ranjani Sridharan Reviewed-by: Bard Liao Reviewed-by: Péter Ujfalusi Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20220308164344.577647-12-ranjani.sridharan@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof/topology.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/sound/sof/topology.h b/include/sound/sof/topology.h index adee6afd1490..88560281d420 100644 --- a/include/sound/sof/topology.h +++ b/include/sound/sof/topology.h @@ -87,9 +87,6 @@ struct sof_ipc_comp { */ #define SOF_BUF_UNDERRUN_PERMITTED BIT(1) -/* the UUID size in bytes, shared between FW and host */ -#define SOF_UUID_SIZE 16 - /* create new component buffer - SOF_IPC_TPLG_BUFFER_NEW */ struct sof_ipc_buffer { struct sof_ipc_comp comp; @@ -303,9 +300,4 @@ enum sof_event_types { SOF_KEYWORD_DETECT_DAPM_EVENT, }; -/* extended data struct for UUID components */ -struct sof_ipc_comp_ext { - uint8_t uuid[SOF_UUID_SIZE]; -} __packed; - #endif -- cgit v1.2.3 From 839e484f9e173309d599e1281eb7221e07f41814 Mon Sep 17 00:00:00 2001 From: Ranjani Sridharan Date: Tue, 8 Mar 2022 08:43:43 -0800 Subject: ASoC: SOF: make struct snd_sof_dai IPC agnostic MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Remove the comp_dai and dai_config members of struct snd_sof_dai and replace it with a void *private field. Introduce a new struct sof_dai_private_data that will contain the pointer to these two fields. The topology parser will populate this structure and save it as part of the "private" member in snd_sof_dai. Change all users of these fields to use the private member instead. Signed-off-by: Ranjani Sridharan Reviewed-by: Bard Liao Reviewed-by: Péter Ujfalusi Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20220308164344.577647-18-ranjani.sridharan@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof/dai.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/sound/sof/dai.h b/include/sound/sof/dai.h index 59ee50ac7705..a818a0f0a226 100644 --- a/include/sound/sof/dai.h +++ b/include/sound/sof/dai.h @@ -116,4 +116,9 @@ struct sof_ipc_dai_config { }; } __packed; +struct sof_dai_private_data { + struct sof_ipc_comp_dai *comp_dai; + struct sof_ipc_dai_config *dai_config; +}; + #endif -- cgit v1.2.3 From 1174442b82b6cf13328a5f9574fac3655c58ae06 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 8 Mar 2022 13:25:51 -0600 Subject: ASoC: soc-acpi: fix kernel-doc descriptor MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add missing dmic_num mention and clarify that 'links' mean 'SoundWire links', not to be used for other links. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Bard Liao Reviewed-by: Péter Ujfalusi Link: https://lore.kernel.org/r/20220308192610.392950-2-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/sound/soc-acpi.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h index fdb536d699ff..a8fd62c00f91 100644 --- a/include/sound/soc-acpi.h +++ b/include/sound/soc-acpi.h @@ -60,9 +60,10 @@ static inline struct snd_soc_acpi_mach *snd_soc_acpi_codec_list(void *arg) * @acpi_ipc_irq_index: used for BYT-CR detection * @platform: string used for HDAudio codec support * @codec_mask: used for HDAudio support + * @dmic_num: number of SoC- or chipset-attached PDM digital microphones * @common_hdmi_codec_drv: use commom HDAudio HDMI codec driver - * @link_mask: links enabled on the board - * @links: array of link _ADR descriptors, null terminated + * @link_mask: SoundWire links enabled on the board + * @links: array of SoundWire link _ADR descriptors, null terminated * @num_dai_drivers: number of elements in @dai_drivers * @dai_drivers: pointer to dai_drivers, used e.g. in nocodec mode */ -- cgit v1.2.3 From 679aa83a0fb70dcbf9e97cbdfd573e6fc8bf9b1a Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 8 Mar 2022 13:25:52 -0600 Subject: ASoC: soc-acpi: add information on I2S/TDM link mask MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The platform driver may have information on which I2S/TDM link(s) to enable in the machine driver. In the case of Intel devices, this may be extracted from NHLT tables in platform firmware. This link information is necessary to make sure machine driver and topology are aligned. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Bard Liao Reviewed-by: Péter Ujfalusi Link: https://lore.kernel.org/r/20220308192610.392950-3-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/sound/soc-acpi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h index a8fd62c00f91..093bbe7f0e1f 100644 --- a/include/sound/soc-acpi.h +++ b/include/sound/soc-acpi.h @@ -64,6 +64,7 @@ static inline struct snd_soc_acpi_mach *snd_soc_acpi_codec_list(void *arg) * @common_hdmi_codec_drv: use commom HDAudio HDMI codec driver * @link_mask: SoundWire links enabled on the board * @links: array of SoundWire link _ADR descriptors, null terminated + * @i2s_link_mask: I2S/TDM links enabled on the board * @num_dai_drivers: number of elements in @dai_drivers * @dai_drivers: pointer to dai_drivers, used e.g. in nocodec mode */ @@ -75,6 +76,7 @@ struct snd_soc_acpi_mach_params { bool common_hdmi_codec_drv; u32 link_mask; const struct snd_soc_acpi_link_adr *links; + u32 i2s_link_mask; u32 num_dai_drivers; struct snd_soc_dai_driver *dai_drivers; }; -- cgit v1.2.3 From 0c470db0399e17310ed2ba54dd1c25cfa16ce0d3 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 8 Mar 2022 13:25:54 -0600 Subject: ALSA: intel-nhlt: add helper to detect SSP link mask MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The NHLT information can be used to figure out which SSPs are enabled in a platform. The 'SSP' link type is too broad for machine drivers, since it can cover the Bluetooth sideband and the analog audio codec connections, so this helper exposes a parameter to filter with the device type (DEVICE_I2S refers to analog audio codec in NHLT parlance). The helper returns a mask, since more than one SSP may be used for analog audio, e.g. the NHLT spec describes the use of SSP0 for amplifiers and SSP1 for headset codec. Note that if more than one bit is set, it's impossible to determine which SSP is connected to what external component. Additional platform-specific information based on e.g. DMI quirks would still be required in the machine driver to configure the relevant dailinks. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Bard Liao Reviewed-by: Péter Ujfalusi Acked-by: Takashi Iwai Link: https://lore.kernel.org/r/20220308192610.392950-5-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/sound/intel-nhlt.h | 22 +++++++++++++++------- 1 file changed, 15 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/sound/intel-nhlt.h b/include/sound/intel-nhlt.h index 089a760d36eb..6fb2d5e378fd 100644 --- a/include/sound/intel-nhlt.h +++ b/include/sound/intel-nhlt.h @@ -18,6 +18,13 @@ enum nhlt_link_type { NHLT_LINK_INVALID }; +enum nhlt_device_type { + NHLT_DEVICE_BT = 0, + NHLT_DEVICE_DMIC = 1, + NHLT_DEVICE_I2S = 4, + NHLT_DEVICE_INVALID +}; + #if IS_ENABLED(CONFIG_ACPI) && IS_ENABLED(CONFIG_SND_INTEL_NHLT) struct wav_fmt { @@ -41,13 +48,6 @@ struct wav_fmt_ext { u8 sub_fmt[16]; } __packed; -enum nhlt_device_type { - NHLT_DEVICE_BT = 0, - NHLT_DEVICE_DMIC = 1, - NHLT_DEVICE_I2S = 4, - NHLT_DEVICE_INVALID -}; - struct nhlt_specific_cfg { u32 size; u8 caps[]; @@ -133,6 +133,9 @@ void intel_nhlt_free(struct nhlt_acpi_table *addr); int intel_nhlt_get_dmic_geo(struct device *dev, struct nhlt_acpi_table *nhlt); bool intel_nhlt_has_endpoint_type(struct nhlt_acpi_table *nhlt, u8 link_type); + +int intel_nhlt_ssp_endpoint_mask(struct nhlt_acpi_table *nhlt, u8 device_type); + struct nhlt_specific_cfg * intel_nhlt_get_endpoint_blob(struct device *dev, struct nhlt_acpi_table *nhlt, u32 bus_id, u8 link_type, u8 vbps, u8 bps, @@ -163,6 +166,11 @@ static inline bool intel_nhlt_has_endpoint_type(struct nhlt_acpi_table *nhlt, return false; } +static inline int intel_nhlt_ssp_endpoint_mask(struct nhlt_acpi_table *nhlt, u8 device_type) +{ + return 0; +} + static inline struct nhlt_specific_cfg * intel_nhlt_get_endpoint_blob(struct device *dev, struct nhlt_acpi_table *nhlt, u32 bus_id, u8 link_type, u8 vbps, u8 bps, -- cgit v1.2.3 From 4694b8382d6b79bcf95995757419d279a3ab375b Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 8 Mar 2022 13:25:56 -0600 Subject: ASoC: Intel: soc-acpi: quirk topology filename dynamically MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Different topology filenames may be required depending on which SSP is used, and whether or not digital mics are present. This patch adds a tplg_quirk_mask and in the case of the SOF driver adds the relevant configurations. This is a short-term solution to the ES8336 support issues. In a long-term solution, we would need an interface where the machine driver or platform driver have the ability to alter the topology hard-coded low-level hardware support, e.g. by substituting an interface for another, or disabling an interface that is not supported on a given skew. BugLink: https://github.com/thesofproject/linux/issues/3248 Signed-off-by: Pierre-Louis Bossart Reviewed-by: Bard Liao Reviewed-by: Péter Ujfalusi Link: https://lore.kernel.org/r/20220308192610.392950-7-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/sound/soc-acpi.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h index 093bbe7f0e1f..d33cf8df14b1 100644 --- a/include/sound/soc-acpi.h +++ b/include/sound/soc-acpi.h @@ -125,6 +125,24 @@ struct snd_soc_acpi_link_adr { const struct snd_soc_acpi_adr_device *adr_d; }; +/* + * when set the topology uses the -ssp suffix, where N is determined based on + * BIOS or DMI information + */ +#define SND_SOC_ACPI_TPLG_INTEL_SSP_NUMBER BIT(0) + +/* + * when more than one SSP is reported in the link mask, use the most significant. + * This choice was found to be valid on platforms with ES8336 codecs. + */ +#define SND_SOC_ACPI_TPLG_INTEL_SSP_MSB BIT(1) + +/* + * when set the topology uses the -dmicch suffix, where N is determined based on + * BIOS or DMI information + */ +#define SND_SOC_ACPI_TPLG_INTEL_DMIC_NUMBER BIT(2) + /** * snd_soc_acpi_mach: ACPI-based machine descriptor. Most of the fields are * related to the hardware, except for the firmware and topology file names. @@ -146,6 +164,7 @@ struct snd_soc_acpi_link_adr { * @pdata: intended for platform data or machine specific-ops. This structure * is not constant since this field may be updated at run-time * @sof_tplg_filename: Sound Open Firmware topology file name, if enabled + * @tplg_quirk_mask: quirks to select different topology files dynamically */ /* Descriptor for SST ASoC machine driver */ struct snd_soc_acpi_mach { @@ -161,6 +180,7 @@ struct snd_soc_acpi_mach { void *pdata; struct snd_soc_acpi_mach_params mach_params; const char *sof_tplg_filename; + const u32 tplg_quirk_mask; }; #define SND_SOC_ACPI_MAX_CODECS 3 -- cgit v1.2.3 From b77e70f6b8f2cc62fba847f3008a430a09ef275d Mon Sep 17 00:00:00 2001 From: ChiYuan Huang Date: Wed, 9 Mar 2022 16:01:42 +0800 Subject: regulator: Add bindings for Richtek RT5190A PMIC Add bindings for Richtek RT5190A PMIC. Signed-off-by: ChiYuan Huang Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/1646812903-32496-2-git-send-email-u0084500@gmail.com Signed-off-by: Mark Brown --- include/dt-bindings/regulator/richtek,rt5190a-regulator.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) create mode 100644 include/dt-bindings/regulator/richtek,rt5190a-regulator.h (limited to 'include') diff --git a/include/dt-bindings/regulator/richtek,rt5190a-regulator.h b/include/dt-bindings/regulator/richtek,rt5190a-regulator.h new file mode 100644 index 000000000000..63f99d4c1cb3 --- /dev/null +++ b/include/dt-bindings/regulator/richtek,rt5190a-regulator.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __DT_BINDINGS_RICHTEK_RT5190A_REGULATOR_H__ +#define __DT_BINDINGS_RICHTEK_RT5190A_REGULATOR_H__ + +/* + * BUCK/LDO mode constants which may be used in devicetree properties + * (eg. regulator-allowed-modes). + * See the manufacturer's datasheet for more information on these modes. + */ + +#define RT5190A_OPMODE_AUTO 0 +#define RT5190A_OPMODE_FPWM 1 + +#endif -- cgit v1.2.3 From f804360bb3a50decbed6e2761247964dca72c080 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Sat, 26 Feb 2022 22:41:25 +0100 Subject: clk: qcom: smd: Add missing RPM clocks for msm8992/4 XO and MSS_CFG were omitted when first adding the clocks for these SoCs. Add them, and while at it, move the XO clock to the top of the definition list, as ideally everyone should start using it sooner or later.. Fixes: b4297844995f ("clk: qcom: smd: Add support for MSM8992/4 rpm clocks") Signed-off-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220226214126.21209-2-konrad.dybcio@somainline.org --- include/linux/soc/qcom/smd-rpm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/soc/qcom/smd-rpm.h b/include/linux/soc/qcom/smd-rpm.h index 860dd8cdf9f3..82c9d489833a 100644 --- a/include/linux/soc/qcom/smd-rpm.h +++ b/include/linux/soc/qcom/smd-rpm.h @@ -40,6 +40,7 @@ struct qcom_smd_rpm; #define QCOM_SMD_RPM_AGGR_CLK 0x72676761 #define QCOM_SMD_RPM_HWKM_CLK 0x6d6b7768 #define QCOM_SMD_RPM_PKA_CLK 0x616b70 +#define QCOM_SMD_RPM_MCFG_CLK 0x6766636d int qcom_rpm_smd_write(struct qcom_smd_rpm *rpm, int state, -- cgit v1.2.3 From 2dc63e768ce2fbf24cb49c858f549596bb30a0a0 Mon Sep 17 00:00:00 2001 From: Bhupesh Sharma Date: Thu, 3 Mar 2022 02:00:41 +0530 Subject: clk: qcom: gcc: Add PCIe0 and PCIe1 GDSC for SM8150 Add the PCIe0 and PCIe1 GDSC defines & driver structures for SM8150. Cc: Stephen Boyd Cc: Bjorn Andersson Signed-off-by: Bhupesh Sharma Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220302203045.184500-4-bhupesh.sharma@linaro.org --- include/dt-bindings/clock/qcom,gcc-sm8150.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,gcc-sm8150.h b/include/dt-bindings/clock/qcom,gcc-sm8150.h index 3e1a91876610..ae9c16410420 100644 --- a/include/dt-bindings/clock/qcom,gcc-sm8150.h +++ b/include/dt-bindings/clock/qcom,gcc-sm8150.h @@ -241,6 +241,8 @@ #define GCC_USB_PHY_CFG_AHB2PHY_BCR 28 /* GCC GDSCRs */ +#define PCIE_0_GDSC 0 +#define PCIE_1_GDSC 1 #define USB30_PRIM_GDSC 4 #define USB30_SEC_GDSC 5 -- cgit v1.2.3 From 2fb605a1a529d366513fd223b4ee7c75db2db7e8 Mon Sep 17 00:00:00 2001 From: Bhupesh Sharma Date: Thu, 3 Mar 2022 13:51:39 +0530 Subject: clk: qcom: gcc: Add UFS_CARD and UFS_PHY GDSCs for SM8150 Add the UFS_CARD and UFS_PHY GDSC defines & driver structures for SM8150. Cc: Stephen Boyd Cc: Bjorn Andersson Signed-off-by: Bhupesh Sharma Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220303082140.240745-2-bhupesh.sharma@linaro.org --- include/dt-bindings/clock/qcom,gcc-sm8150.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,gcc-sm8150.h b/include/dt-bindings/clock/qcom,gcc-sm8150.h index ae9c16410420..d70ab54c44c7 100644 --- a/include/dt-bindings/clock/qcom,gcc-sm8150.h +++ b/include/dt-bindings/clock/qcom,gcc-sm8150.h @@ -243,6 +243,8 @@ /* GCC GDSCRs */ #define PCIE_0_GDSC 0 #define PCIE_1_GDSC 1 +#define UFS_CARD_GDSC 2 +#define UFS_PHY_GDSC 3 #define USB30_PRIM_GDSC 4 #define USB30_SEC_GDSC 5 -- cgit v1.2.3 From d1a16e345578332c31aa4fb7b76e2e38249861ad Mon Sep 17 00:00:00 2001 From: Bhupesh Sharma Date: Thu, 3 Mar 2022 14:18:21 +0530 Subject: clk: qcom: gcc: Add emac GDSC support for SM8150 Add the EMAC GDSC defines and driver structures for SM8150. Cc: Stephen Boyd Cc: Bjorn Andersson Signed-off-by: Bhupesh Sharma Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220303084824.284946-4-bhupesh.sharma@linaro.org --- include/dt-bindings/clock/qcom,gcc-sm8150.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,gcc-sm8150.h b/include/dt-bindings/clock/qcom,gcc-sm8150.h index d70ab54c44c7..dfefd5e8bf6e 100644 --- a/include/dt-bindings/clock/qcom,gcc-sm8150.h +++ b/include/dt-bindings/clock/qcom,gcc-sm8150.h @@ -247,5 +247,6 @@ #define UFS_PHY_GDSC 3 #define USB30_PRIM_GDSC 4 #define USB30_SEC_GDSC 5 +#define EMAC_GDSC 6 #endif -- cgit v1.2.3 From 8397c9c0c26b5129acb623044ecc2d8d1b15d420 Mon Sep 17 00:00:00 2001 From: Martin Botka Date: Thu, 3 Mar 2022 14:18:11 +0100 Subject: dt-bindings: clock: add QCOM SM6125 display clock bindings Add device tree bindings for display clock controller for Qualcomm Technology Inc's SM6125 SoC. Signed-off-by: Martin Botka Signed-off-by: Marijn Suijten Reviewed-by: Krzysztof Kozlowski Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220303131812.302302-3-marijn.suijten@somainline.org --- include/dt-bindings/clock/qcom,dispcc-sm6125.h | 41 ++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) create mode 100644 include/dt-bindings/clock/qcom,dispcc-sm6125.h (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,dispcc-sm6125.h b/include/dt-bindings/clock/qcom,dispcc-sm6125.h new file mode 100644 index 000000000000..4ff974f4fcc3 --- /dev/null +++ b/include/dt-bindings/clock/qcom,dispcc-sm6125.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2021, The Linux Foundation. All rights reserved. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_DISP_CC_SM6125_H +#define _DT_BINDINGS_CLK_QCOM_DISP_CC_SM6125_H + +#define DISP_CC_PLL0 0 +#define DISP_CC_MDSS_AHB_CLK 1 +#define DISP_CC_MDSS_AHB_CLK_SRC 2 +#define DISP_CC_MDSS_BYTE0_CLK 3 +#define DISP_CC_MDSS_BYTE0_CLK_SRC 4 +#define DISP_CC_MDSS_BYTE0_INTF_CLK 5 +#define DISP_CC_MDSS_DP_AUX_CLK 6 +#define DISP_CC_MDSS_DP_AUX_CLK_SRC 7 +#define DISP_CC_MDSS_DP_CRYPTO_CLK 8 +#define DISP_CC_MDSS_DP_CRYPTO_CLK_SRC 9 +#define DISP_CC_MDSS_DP_LINK_CLK 10 +#define DISP_CC_MDSS_DP_LINK_CLK_SRC 11 +#define DISP_CC_MDSS_DP_LINK_INTF_CLK 12 +#define DISP_CC_MDSS_DP_PIXEL_CLK 13 +#define DISP_CC_MDSS_DP_PIXEL_CLK_SRC 14 +#define DISP_CC_MDSS_ESC0_CLK 15 +#define DISP_CC_MDSS_ESC0_CLK_SRC 16 +#define DISP_CC_MDSS_MDP_CLK 17 +#define DISP_CC_MDSS_MDP_CLK_SRC 18 +#define DISP_CC_MDSS_MDP_LUT_CLK 19 +#define DISP_CC_MDSS_NON_GDSC_AHB_CLK 20 +#define DISP_CC_MDSS_PCLK0_CLK 21 +#define DISP_CC_MDSS_PCLK0_CLK_SRC 22 +#define DISP_CC_MDSS_ROT_CLK 23 +#define DISP_CC_MDSS_ROT_CLK_SRC 24 +#define DISP_CC_MDSS_VSYNC_CLK 25 +#define DISP_CC_MDSS_VSYNC_CLK_SRC 26 +#define DISP_CC_XO_CLK 27 + +/* DISP_CC GDSCR */ +#define MDSS_GDSC 0 + +#endif -- cgit v1.2.3 From 24055bb87977e0c687b54ebf7bac8715f3636bc3 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 9 Mar 2022 14:20:12 +0200 Subject: net: tcp: fix shim definition of tcp_inbound_md5_hash When CONFIG_TCP_MD5SIG isn't enabled, there is a compilation bug due to the fact that the static inline definition of tcp_inbound_md5_hash() has an unexpected semicolon. Remove it. Fixes: 1330b6ef3313 ("skb: make drop reason booleanable") Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20220309122012.668986-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index ee8237b58e1d..70ca4a5e330a 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1693,7 +1693,7 @@ tcp_md5_do_lookup(const struct sock *sk, int l3index, static inline enum skb_drop_reason tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, const void *saddr, const void *daddr, - int family, int dif, int sdif); + int family, int dif, int sdif) { return SKB_NOT_DROPPED_YET; } -- cgit v1.2.3 From 69fe0f29892077f14b56e2a479b6bcf533209d53 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 4 Mar 2022 21:08:03 -0500 Subject: block: add ->poll_bio to block_device_operations Prepare for supporting IO polling for bio-based driver. Add ->poll_bio callback so that bio-based driver can provide their own logic for polling bio. Also fix ->submit_bio_bio typo in comment block above __submit_bio_noacct. Reviewed-by: Christoph Hellwig Reviewed-by: Jens Axboe Signed-off-by: Ming Lei Signed-off-by: Mike Snitzer --- include/linux/blkdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f757f9c2871f..51f1b1ddbed2 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1455,6 +1455,8 @@ enum blk_unique_id { struct block_device_operations { void (*submit_bio)(struct bio *bio); + int (*poll_bio)(struct bio *bio, struct io_comp_batch *iob, + unsigned int flags); int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int); -- cgit v1.2.3 From cf220ad6749b8305ba11bdf601c55a17ad2a715d Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 9 Mar 2022 13:12:00 +0000 Subject: arm64/mte: Remove asymmetric mode from the prctl() interface As pointed out by Evgenii Stepanov one potential issue with the new ABI for enabling asymmetric is that if there are multiple places where MTE is configured in a process, some of which were compiled with the old prctl.h and some of which were compiled with the new prctl.h, there may be problems keeping track of which MTE modes are requested. For example some code may disable only sync and async modes leaving asymmetric mode enabled when it intended to fully disable MTE. In order to avoid such mishaps remove asymmetric mode from the prctl(), instead implicitly allowing it if both sync and async modes are requested. This should not disrupt userspace since a process requesting both may already see a mix of sync and async modes due to differing defaults between CPUs or changes in default while the process is running but it does mean that userspace is unable to explicitly request asymmetric mode without changing the system default for CPUs. Reported-by: Evgenii Stepanov Signed-off-by: Mark Brown Reviewed-by: Catalin Marinas Reviewed-by: Evgenii Stepanov Cc: Peter Collingbourne Cc: Joey Gouly Cc: Branislav Rankov Link: https://lore.kernel.org/r/20220309131200.112637-1-broonie@kernel.org Signed-off-by: Will Deacon --- include/uapi/linux/prctl.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 4ae2b21e4066..e998764f0262 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -238,9 +238,7 @@ struct prctl_mm_map { # define PR_MTE_TCF_NONE 0UL # define PR_MTE_TCF_SYNC (1UL << 1) # define PR_MTE_TCF_ASYNC (1UL << 2) -# define PR_MTE_TCF_ASYMM (1UL << 19) -# define PR_MTE_TCF_MASK (PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC | \ - PR_MTE_TCF_ASYMM) +# define PR_MTE_TCF_MASK (PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC) /* MTE tag inclusion mask */ # define PR_MTE_TAG_SHIFT 3 # define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT) -- cgit v1.2.3 From 34f46ae0d4b38e83cfb26fb6f06b5b5efea47fdc Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Thu, 27 Jan 2022 15:22:21 +0200 Subject: net/mlx5: Add command failures data to debugfs Add new counters to command interface debugfs to count command failures. The following counters added: total_failed - number of times command failed (any kind of failure). failed_mbox_status - number of times command failed on bad status returned by FW. In addition, add data about last command failure to command interface debugfs: last_failed_errno - last command failed returned errno. last_failed_mbox_status - last bad status returned by FW. Signed-off-by: Moshe Shemesh Reviewed-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index d3b1a6a1f8d2..f18c1e15a12c 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -264,6 +264,14 @@ enum { struct mlx5_cmd_stats { u64 sum; u64 n; + /* number of times command failed */ + u64 failed; + /* number of times command failed on bad status returned by FW */ + u64 failed_mbox_status; + /* last command failed returned errno */ + u32 last_failed_errno; + /* last bad status returned by FW */ + u8 last_failed_mbox_status; struct dentry *root; /* protect command average calculations */ spinlock_t lock; @@ -955,6 +963,7 @@ typedef void (*mlx5_async_cbk_t)(int status, struct mlx5_async_work *context); struct mlx5_async_work { struct mlx5_async_ctx *ctx; mlx5_async_cbk_t user_callback; + u16 opcode; /* cmd opcode */ void *out; /* pointer to the cmd output buffer */ }; -- cgit v1.2.3 From d2cb8dda214fb75f946ba554a1ecd25da7004b2b Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 26 Jan 2022 07:23:53 +0200 Subject: net/mlx5: Change release_all_pages cap bit location mlx5 FW has changed release_all_pages cap bit by one bit offset to reflect a fix in the FW flow for release_all_pages. The driver should use the new bit to ensure it calls release_all_pages only if the FW fix is there. Signed-off-by: Moshe Shemesh Reviewed-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ea65131835ab..69985e4d8dfe 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1419,8 +1419,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_130[0xa]; u8 log_max_ra_res_dc[0x6]; - u8 reserved_at_140[0x6]; + u8 reserved_at_140[0x5]; u8 release_all_pages[0x1]; + u8 must_not_use[0x1]; u8 reserved_at_147[0x2]; u8 roce_accl[0x1]; u8 log_max_ra_req_qp[0x6]; -- cgit v1.2.3 From 66771a1c729e816dc84e29ba555013b6e722fb22 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Fri, 18 Feb 2022 09:36:20 +0200 Subject: net/mlx5: Move debugfs entries to separate struct Move the debugfs entry pointers under priv to their own struct. Add get function for device debugfs root. Signed-off-by: Moshe Shemesh Reviewed-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f18c1e15a12c..aa539d245a12 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -551,6 +551,14 @@ struct mlx5_adev { int idx; }; +struct mlx5_debugfs_entries { + struct dentry *dbg_root; + struct dentry *qp_debugfs; + struct dentry *eq_debugfs; + struct dentry *cq_debugfs; + struct dentry *cmdif_debugfs; +}; + struct mlx5_ft_pool; struct mlx5_priv { /* IRQ table valid only for real pci devices PF or VF */ @@ -570,12 +578,7 @@ struct mlx5_priv { struct mlx5_core_health health; struct list_head traps; - /* start: qp staff */ - struct dentry *qp_debugfs; - struct dentry *eq_debugfs; - struct dentry *cq_debugfs; - struct dentry *cmdif_debugfs; - /* end: qp staff */ + struct mlx5_debugfs_entries dbg; /* start: alloc staff */ /* protect buffer allocation according to numa node */ @@ -585,7 +588,6 @@ struct mlx5_priv { struct mutex pgdir_mutex; struct list_head pgdir_list; /* end: alloc staff */ - struct dentry *dbg_root; struct list_head ctx_list; spinlock_t ctx_lock; @@ -1038,6 +1040,7 @@ int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn); int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); +struct dentry *mlx5_debugfs_get_dev_root(struct mlx5_core_dev *dev); void mlx5_qp_debugfs_init(struct mlx5_core_dev *dev); void mlx5_qp_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in, -- cgit v1.2.3 From 4e05cbf05c66ca6931ee4f2a5aff0d84f1e65f40 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Thu, 27 Jan 2022 07:03:33 +0200 Subject: net/mlx5: Add pages debugfs Add pages debugfs to expose the following counters for debuggability: fw_pages_total - How many pages were given to FW and not returned yet. vfs_pages - For SRIOV, how many pages were given to FW for virtual functions usage. host_pf_pages - For ECPF, how many pages were given to FW for external hosts physical functions usage. Signed-off-by: Moshe Shemesh Reviewed-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index aa539d245a12..c5f93b5910ed 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -557,6 +557,7 @@ struct mlx5_debugfs_entries { struct dentry *eq_debugfs; struct dentry *cq_debugfs; struct dentry *cmdif_debugfs; + struct dentry *pages_debugfs; }; struct mlx5_ft_pool; @@ -569,11 +570,11 @@ struct mlx5_priv { struct mlx5_nb pg_nb; struct workqueue_struct *pg_wq; struct xarray page_root_xa; - int fw_pages; + u32 fw_pages; atomic_t reg_pages; struct list_head free_list; - int vfs_pages; - int host_pf_pages; + u32 vfs_pages; + u32 host_pf_pages; struct mlx5_core_health health; struct list_head traps; @@ -1026,6 +1027,8 @@ int mlx5_pagealloc_init(struct mlx5_core_dev *dev); void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev); void mlx5_pagealloc_start(struct mlx5_core_dev *dev); void mlx5_pagealloc_stop(struct mlx5_core_dev *dev); +void mlx5_pages_debugfs_init(struct mlx5_core_dev *dev); +void mlx5_pages_debugfs_cleanup(struct mlx5_core_dev *dev); void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id, s32 npages, bool ec_function); int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot); -- cgit v1.2.3 From 32071187e9fb18da62f5be569bd2ea0d7a981ee8 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Thu, 27 Jan 2022 07:51:14 +0200 Subject: net/mlx5: Add debugfs counters for page commands failures Add the following new debugfs counters for debug and verbosity: fw_pages_alloc_failed - number of pages FW requested but driver failed to allocate. give_pages_dropped - number of pages given to FW, but command give pages failed by FW. reclaim_pages_discard - number of pages which were about to reclaim back and FW failed the command. Signed-off-by: Moshe Shemesh Reviewed-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index c5f93b5910ed..00a914b0716e 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -575,6 +575,9 @@ struct mlx5_priv { struct list_head free_list; u32 vfs_pages; u32 host_pf_pages; + u32 fw_pages_alloc_failed; + u32 give_pages_dropped; + u32 reclaim_pages_discard; struct mlx5_core_health health; struct list_head traps; -- cgit v1.2.3 From 5c422bfad2fbab96381273e50c7084465199501d Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Thu, 24 Feb 2022 00:58:58 +0200 Subject: net/mlx5: DR, Add support for matching on Internet Header Length (IHL) Add support for matching on new field - Internet Header Length (IHL). Signed-off-by: Muhammad Sammar Signed-off-by: Yevgeny Kliteynik Reviewed-by: Alex Vesker Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 69985e4d8dfe..1f0c35162b7b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -493,7 +493,10 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 tcp_sport[0x10]; u8 tcp_dport[0x10]; - u8 reserved_at_c0[0x18]; + u8 reserved_at_c0[0x10]; + u8 ipv4_ihl[0x4]; + u8 reserved_at_c4[0x4]; + u8 ttl_hoplimit[0x8]; u8 udp_sport[0x10]; -- cgit v1.2.3 From 6862c787c7e88df490675ed781dc9052dba88a56 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Wed, 23 Feb 2022 18:40:59 +0200 Subject: net/mlx5: DR, Add support for ConnectX-7 steering Add support for a new SW format version that is implemented by ConnectX-7. Except for several differences, the STEv2 is identical to STEv1, so for most callbacks the STEv2 context struct will call STEv1 functions. Signed-off-by: Yevgeny Kliteynik Reviewed-by: Alex Vesker Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 1f0c35162b7b..bcf60ede6fcc 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1346,6 +1346,7 @@ enum mlx5_fc_bulk_alloc_bitmask { enum { MLX5_STEERING_FORMAT_CONNECTX_5 = 0, MLX5_STEERING_FORMAT_CONNECTX_6DX = 1, + MLX5_STEERING_FORMAT_CONNECTX_7 = 2, }; struct mlx5_ifc_cmd_hca_cap_bits { -- cgit v1.2.3 From b530e9e1063ed2b817eae7eec6ed2daa8be11608 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Wed, 9 Mar 2022 11:53:42 +0100 Subject: bpf: Add "live packet" mode for XDP in BPF_PROG_RUN MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This adds support for running XDP programs through BPF_PROG_RUN in a mode that enables live packet processing of the resulting frames. Previous uses of BPF_PROG_RUN for XDP returned the XDP program return code and the modified packet data to userspace, which is useful for unit testing of XDP programs. The existing BPF_PROG_RUN for XDP allows userspace to set the ingress ifindex and RXQ number as part of the context object being passed to the kernel. This patch reuses that code, but adds a new mode with different semantics, which can be selected with the new BPF_F_TEST_XDP_LIVE_FRAMES flag. When running BPF_PROG_RUN in this mode, the XDP program return codes will be honoured: returning XDP_PASS will result in the frame being injected into the networking stack as if it came from the selected networking interface, while returning XDP_TX and XDP_REDIRECT will result in the frame being transmitted out that interface. XDP_TX is translated into an XDP_REDIRECT operation to the same interface, since the real XDP_TX action is only possible from within the network drivers themselves, not from the process context where BPF_PROG_RUN is executed. Internally, this new mode of operation creates a page pool instance while setting up the test run, and feeds pages from that into the XDP program. The setup cost of this is amortised over the number of repetitions specified by userspace. To support the performance testing use case, we further optimise the setup step so that all pages in the pool are pre-initialised with the packet data, and pre-computed context and xdp_frame objects stored at the start of each page. This makes it possible to entirely avoid touching the page content on each XDP program invocation, and enables sending up to 9 Mpps/core on my test box. Because the data pages are recycled by the page pool, and the test runner doesn't re-initialise them for each run, subsequent invocations of the XDP program will see the packet data in the state it was after the last time it ran on that particular page. This means that an XDP program that modifies the packet before redirecting it has to be careful about which assumptions it makes about the packet content, but that is only an issue for the most naively written programs. Enabling the new flag is only allowed when not setting ctx_out and data_out in the test specification, since using it means frames will be redirected somewhere else, so they can't be returned. Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20220309105346.100053-2-toke@redhat.com --- include/uapi/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4eebea830613..bc23020b638d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1232,6 +1232,8 @@ enum { /* If set, run the test on the cpu specified by bpf_attr.test.cpu */ #define BPF_F_TEST_RUN_ON_CPU (1U << 0) +/* If set, XDP frames will be transmitted after processing */ +#define BPF_F_TEST_XDP_LIVE_FRAMES (1U << 1) /* type for BPF_ENABLE_STATS */ enum bpf_stats_type { @@ -1393,6 +1395,7 @@ union bpf_attr { __aligned_u64 ctx_out; __u32 flags; __u32 cpu; + __u32 batch_size; } test; struct { /* anonymous struct used by BPF_*_GET_*_ID */ -- cgit v1.2.3 From 9a61d0838cd0a81529badfba7bfa39e81d5529d3 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Fri, 25 Feb 2022 20:00:21 +0530 Subject: drivers/nvdimm: Add nvdimm pmu structure A structure is added called nvdimm_pmu, for performance stats reporting support of nvdimm devices. It can be used to add device pmu data such as pmu data structure for performance stats, nvdimm device pointer along with cpumask attributes. Acked-by: Peter Zijlstra (Intel) Tested-by: Nageswara R Sastry Signed-off-by: Kajol Jain Reviewed-by: Madhavan Srinivasan Link: https://lore.kernel.org/r/20220225143024.47947-2-kjain@linux.ibm.com Signed-off-by: Dan Williams --- include/linux/nd.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/nd.h b/include/linux/nd.h index 8a8c63edb1b2..ad186e828263 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -8,6 +8,7 @@ #include #include #include +#include enum nvdimm_event { NVDIMM_REVALIDATE_POISON, @@ -23,6 +24,25 @@ enum nvdimm_claim_class { NVDIMM_CCLASS_UNKNOWN, }; +/** + * struct nvdimm_pmu - data structure for nvdimm perf driver + * @pmu: pmu data structure for nvdimm performance stats. + * @dev: nvdimm device pointer. + * @cpu: designated cpu for counter access. + * @node: node for cpu hotplug notifier link. + * @cpuhp_state: state for cpu hotplug notification. + * @arch_cpumask: cpumask to get designated cpu for counter access. + */ +struct nvdimm_pmu { + struct pmu pmu; + struct device *dev; + int cpu; + struct hlist_node node; + enum cpuhp_state cpuhp_state; + /* cpumask provided by arch/platform specific code */ + struct cpumask arch_cpumask; +}; + struct nd_device_driver { struct device_driver drv; unsigned long type; -- cgit v1.2.3 From 0fab1ba6ad6ba1f76380f92ead95c6e861ef8116 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Fri, 25 Feb 2022 20:00:22 +0530 Subject: drivers/nvdimm: Add perf interface to expose nvdimm performance stats A common interface is added to get performance stats reporting support for nvdimm devices. Added interface defines supported event list, config fields for the event attributes and their corresponding bit values which are exported via sysfs. Interface also added support for pmu register/unregister functions, cpu hotplug feature along with macros for handling events addition via sysfs. It adds attribute groups for format, cpumask and events to the pmu structure. User could use the standard perf tool to access perf events exposed via nvdimm pmu. [Declare pmu functions in nd.h file to resolve implicit-function-declaration warning and make hotplug function static as reported by kernel test robot] Acked-by: Peter Zijlstra (Intel) Tested-by: Nageswara R Sastry Signed-off-by: Kajol Jain Link: https://lore.kernel.org/all/202202241242.zqzGkguy-lkp@intel.com/ Reported-by: kernel test robot Reviewed-by: Madhavan Srinivasan Link: https://lore.kernel.org/r/20220225143024.47947-3-kjain@linux.ibm.com Signed-off-by: Dan Williams --- include/linux/nd.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include') diff --git a/include/linux/nd.h b/include/linux/nd.h index ad186e828263..4813c7089e5c 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -9,6 +9,7 @@ #include #include #include +#include enum nvdimm_event { NVDIMM_REVALIDATE_POISON, @@ -24,6 +25,19 @@ enum nvdimm_claim_class { NVDIMM_CCLASS_UNKNOWN, }; +#define NVDIMM_EVENT_VAR(_id) event_attr_##_id +#define NVDIMM_EVENT_PTR(_id) (&event_attr_##_id.attr.attr) + +#define NVDIMM_EVENT_ATTR(_name, _id) \ + PMU_EVENT_ATTR(_name, NVDIMM_EVENT_VAR(_id), _id, \ + nvdimm_events_sysfs_show) + +/* Event attribute array index */ +#define NVDIMM_PMU_FORMAT_ATTR 0 +#define NVDIMM_PMU_EVENT_ATTR 1 +#define NVDIMM_PMU_CPUMASK_ATTR 2 +#define NVDIMM_PMU_NULL_ATTR 3 + /** * struct nvdimm_pmu - data structure for nvdimm perf driver * @pmu: pmu data structure for nvdimm performance stats. @@ -43,6 +57,16 @@ struct nvdimm_pmu { struct cpumask arch_cpumask; }; +extern ssize_t nvdimm_events_sysfs_show(struct device *dev, + struct device_attribute *attr, + char *page); + +int register_nvdimm_pmu(struct nvdimm_pmu *nvdimm, struct platform_device *pdev); +void unregister_nvdimm_pmu(struct nvdimm_pmu *nd_pmu); +void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); +int perf_pmu_register(struct pmu *pmu, const char *name, int type); +void perf_pmu_unregister(struct pmu *pmu); + struct nd_device_driver { struct device_driver drv; unsigned long type; -- cgit v1.2.3 From 013a3e7c79ac51e6cdd84e3580863a562c7597c7 Mon Sep 17 00:00:00 2001 From: Min Li Date: Tue, 8 Mar 2022 09:10:51 -0500 Subject: ptp: idt82p33: use rsmu driver to access i2c/spi bus rsmu (Renesas Synchronization Management Unit ) driver is located in drivers/mfd and responsible for creating multiple devices including idt82p33 phc, which will then use the exposed regmap and mutex handle to access i2c/spi bus. Signed-off-by: Min Li Acked-by: Richard Cochran Link: https://lore.kernel.org/r/1646748651-16811-1-git-send-email-min.li.xe@renesas.com Signed-off-by: Jakub Kicinski --- include/linux/mfd/idt82p33_reg.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/idt82p33_reg.h b/include/linux/mfd/idt82p33_reg.h index 129a6c078221..1db532feeb91 100644 --- a/include/linux/mfd/idt82p33_reg.h +++ b/include/linux/mfd/idt82p33_reg.h @@ -7,6 +7,8 @@ #ifndef HAVE_IDT82P33_REG #define HAVE_IDT82P33_REG +#define REG_ADDR(page, offset) (((page) << 0x7) | ((offset) & 0x7f)) + /* Register address */ #define DPLL1_TOD_CNFG 0x134 #define DPLL2_TOD_CNFG 0x1B4 @@ -41,6 +43,7 @@ #define REG_SOFT_RESET 0X381 #define OUT_MUX_CNFG(outn) REG_ADDR(0x6, (0xC * (outn))) +#define TOD_TRIGGER(wr_trig, rd_trig) ((wr_trig & 0xf) << 4 | (rd_trig & 0xf)) /* Register bit definitions */ #define SYNC_TOD BIT(1) -- cgit v1.2.3 From 77f09e66f613e4801134c64d26a0be593588a42e Mon Sep 17 00:00:00 2001 From: Dimitris Michailidis Date: Tue, 8 Mar 2022 19:40:31 -0800 Subject: net/tls: Provide {__,}tls_driver_ctx() unconditionally Having the definitions of {__,}tls_driver_ctx() under an #if guard means code referencing them also needs to rely on the preprocessor. The protection doesn't appear needed so make the definitions unconditional. Fixes: db37bc177dae ("net/funeth: add the data path") Reported-by: Randy Dunlap Reported-by: kernel test robot Suggested-by: Jakub Kicinski Signed-off-by: Dimitris Michailidis Signed-off-by: Jakub Kicinski --- include/net/tls.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 526cb2c3b724..b6968a5b5538 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -626,7 +626,6 @@ tls_offload_ctx_rx(const struct tls_context *tls_ctx) return (struct tls_offload_context_rx *)tls_ctx->priv_ctx_rx; } -#if IS_ENABLED(CONFIG_TLS_DEVICE) static inline void *__tls_driver_ctx(struct tls_context *tls_ctx, enum tls_offload_ctx_dir direction) { @@ -641,7 +640,6 @@ tls_driver_ctx(const struct sock *sk, enum tls_offload_ctx_dir direction) { return __tls_driver_ctx(tls_get_ctx(sk), direction); } -#endif #define RESYNC_REQ BIT(0) #define RESYNC_REQ_ASYNC BIT(1) -- cgit v1.2.3 From 65466904b015f6eeb9225b51aeb29b01a1d4b59c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 8 Mar 2022 17:57:57 -0800 Subject: tcp: adjust TSO packet sizes based on min_rtt Back when tcp_tso_autosize() and TCP pacing were introduced, our focus was really to reduce burst sizes for long distance flows. The simple heuristic of using sk_pacing_rate/1024 has worked well, but can lead to too small packets for hosts in the same rack/cluster, when thousands of flows compete for the bottleneck. Neal Cardwell had the idea of making the TSO burst size a function of both sk_pacing_rate and tcp_min_rtt() Indeed, for local flows, sending bigger bursts is better to reduce cpu costs, as occasional losses can be repaired quite fast. This patch is based on Neal Cardwell implementation done more than two years ago. bbr is adjusting max_pacing_rate based on measured bandwidth, while cubic would over estimate max_pacing_rate. /proc/sys/net/ipv4/tcp_tso_rtt_log can be used to tune or disable this new feature, in logarithmic steps. Tested: 100Gbit NIC, two hosts in the same rack, 4K MTU. 600 flows rate-limited to 20000000 bytes per second. Before patch: (TSO sizes would be limited to 20000000/1024/4096 -> 4 segments per TSO) ~# echo 0 >/proc/sys/net/ipv4/tcp_tso_rtt_log ~# nstat -n;perf stat ./super_netperf 600 -H otrv6 -l 20 -- -K dctcp -q 20000000;nstat|egrep "TcpInSegs|TcpOutSegs|TcpRetransSegs|Delivered" 96005 Performance counter stats for './super_netperf 600 -H otrv6 -l 20 -- -K dctcp -q 20000000': 65,945.29 msec task-clock # 2.845 CPUs utilized 1,314,632 context-switches # 19935.279 M/sec 5,292 cpu-migrations # 80.249 M/sec 940,641 page-faults # 14264.023 M/sec 201,117,030,926 cycles # 3049769.216 GHz (83.45%) 17,699,435,405 stalled-cycles-frontend # 8.80% frontend cycles idle (83.48%) 136,584,015,071 stalled-cycles-backend # 67.91% backend cycles idle (83.44%) 53,809,530,436 instructions # 0.27 insn per cycle # 2.54 stalled cycles per insn (83.36%) 9,062,315,523 branches # 137422329.563 M/sec (83.22%) 153,008,621 branch-misses # 1.69% of all branches (83.32%) 23.182970846 seconds time elapsed TcpInSegs 15648792 0.0 TcpOutSegs 58659110 0.0 # Average of 3.7 4K segments per TSO packet TcpExtTCPDelivered 58654791 0.0 TcpExtTCPDeliveredCE 19 0.0 After patch: ~# echo 9 >/proc/sys/net/ipv4/tcp_tso_rtt_log ~# nstat -n;perf stat ./super_netperf 600 -H otrv6 -l 20 -- -K dctcp -q 20000000;nstat|egrep "TcpInSegs|TcpOutSegs|TcpRetransSegs|Delivered" 96046 Performance counter stats for './super_netperf 600 -H otrv6 -l 20 -- -K dctcp -q 20000000': 48,982.58 msec task-clock # 2.104 CPUs utilized 186,014 context-switches # 3797.599 M/sec 3,109 cpu-migrations # 63.472 M/sec 941,180 page-faults # 19214.814 M/sec 153,459,763,868 cycles # 3132982.807 GHz (83.56%) 12,069,861,356 stalled-cycles-frontend # 7.87% frontend cycles idle (83.32%) 120,485,917,953 stalled-cycles-backend # 78.51% backend cycles idle (83.24%) 36,803,672,106 instructions # 0.24 insn per cycle # 3.27 stalled cycles per insn (83.18%) 5,947,266,275 branches # 121417383.427 M/sec (83.64%) 87,984,616 branch-misses # 1.48% of all branches (83.43%) 23.281200256 seconds time elapsed TcpInSegs 1434706 0.0 TcpOutSegs 58883378 0.0 # Average of 41 4K segments per TSO packet TcpExtTCPDelivered 58878971 0.0 TcpExtTCPDeliveredCE 9664 0.0 Signed-off-by: Eric Dumazet Reviewed-by: Neal Cardwell Link: https://lore.kernel.org/r/20220309015757.2532973-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/net/netns/ipv4.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index f0687867b5cd..ce0cc4e8d8c7 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -127,6 +127,7 @@ struct netns_ipv4 { u8 sysctl_tcp_synack_retries; u8 sysctl_tcp_syncookies; u8 sysctl_tcp_migrate_req; + u8 sysctl_tcp_comp_sack_nr; int sysctl_tcp_reordering; u8 sysctl_tcp_retries1; u8 sysctl_tcp_retries2; @@ -160,9 +161,9 @@ struct netns_ipv4 { int sysctl_tcp_challenge_ack_limit; int sysctl_tcp_min_rtt_wlen; u8 sysctl_tcp_min_tso_segs; + u8 sysctl_tcp_tso_rtt_log; u8 sysctl_tcp_autocorking; u8 sysctl_tcp_reflect_tos; - u8 sysctl_tcp_comp_sack_nr; int sysctl_tcp_invalid_ratelimit; int sysctl_tcp_pacing_ss_ratio; int sysctl_tcp_pacing_ca_ratio; -- cgit v1.2.3 From 8ddde07a3d285a0f3cec14924446608320fdc013 Mon Sep 17 00:00:00 2001 From: Tian Tao Date: Tue, 8 Mar 2022 16:59:10 +0800 Subject: dma-mapping: benchmark: extract a common header file for map_benchmark definition kernel/dma/map_benchmark.c and selftests/dma/dma_map_benchmark.c have duplicate map_benchmark definitions, which tends to lead to inconsistent changes to map_benchmark on both sides, extract a common header file to avoid this problem. Signed-off-by: Tian Tao Acked-by: Barry Song Reviewed-by: Shuah Khan Signed-off-by: Christoph Hellwig --- include/linux/map_benchmark.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) create mode 100644 include/linux/map_benchmark.h (limited to 'include') diff --git a/include/linux/map_benchmark.h b/include/linux/map_benchmark.h new file mode 100644 index 000000000000..62674c83bde4 --- /dev/null +++ b/include/linux/map_benchmark.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2022 HiSilicon Limited. + */ + +#ifndef _KERNEL_DMA_BENCHMARK_H +#define _KERNEL_DMA_BENCHMARK_H + +#define DMA_MAP_BENCHMARK _IOWR('d', 1, struct map_benchmark) +#define DMA_MAP_MAX_THREADS 1024 +#define DMA_MAP_MAX_SECONDS 300 +#define DMA_MAP_MAX_TRANS_DELAY (10 * NSEC_PER_MSEC) + +#define DMA_MAP_BIDIRECTIONAL 0 +#define DMA_MAP_TO_DEVICE 1 +#define DMA_MAP_FROM_DEVICE 2 + +struct map_benchmark { + __u64 avg_map_100ns; /* average map latency in 100ns */ + __u64 map_stddev; /* standard deviation of map latency */ + __u64 avg_unmap_100ns; /* as above */ + __u64 unmap_stddev; + __u32 threads; /* how many threads will do map/unmap in parallel */ + __u32 seconds; /* how long the test will last */ + __s32 node; /* which numa node this benchmark will run on */ + __u32 dma_bits; /* DMA addressing capability */ + __u32 dma_dir; /* DMA data direction */ + __u32 dma_trans_ns; /* time for DMA transmission in ns */ + __u32 granule; /* how many PAGE_SIZE will do map/unmap once a time */ +}; +#endif /* _KERNEL_DMA_BENCHMARK_H */ -- cgit v1.2.3 From 530e0d46c61314c59ecfdb8d3bcb87edbc0f85d3 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Wed, 9 Mar 2022 13:04:13 +0100 Subject: can: isotp: set default value for N_As to 50 micro seconds The N_As value describes the time a CAN frame needs on the wire when transmitted by the CAN controller. Even very short CAN FD frames need arround 100 usecs (bitrate 1Mbit/s, data bitrate 8Mbit/s). Having N_As to be zero (the former default) leads to 'no CAN frame separation' when STmin is set to zero by the receiving node. This 'burst mode' should not be enabled by default as it could potentially dump a high number of CAN frames into the netdev queue from the soft hrtimer context. This does not affect the system stability but is just not nice and cooperative. With this N_As/frame_txtime value the 'burst mode' is disabled by default. As user space applications usually do not set the frame_txtime element of struct can_isotp_options the new in-kernel default is very likely overwritten with zero when the sockopt() CAN_ISOTP_OPTS is invoked. To make sure that a N_As value of zero is only set intentional the value '0' is now interpreted as 'do not change the current value'. When a frame_txtime of zero is required for testing purposes this CAN_ISOTP_FRAME_TXTIME_ZERO u32 value has to be set in frame_txtime. Link: https://lore.kernel.org/all/20220309120416.83514-2-socketcan@hartkopp.net Signed-off-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/isotp.h | 28 ++++++++++++++++++++++------ 1 file changed, 22 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/can/isotp.h b/include/uapi/linux/can/isotp.h index c55935b64ccc..590f8aea2b6d 100644 --- a/include/uapi/linux/can/isotp.h +++ b/include/uapi/linux/can/isotp.h @@ -137,20 +137,16 @@ struct can_isotp_ll_options { #define CAN_ISOTP_WAIT_TX_DONE 0x400 /* wait for tx completion */ #define CAN_ISOTP_SF_BROADCAST 0x800 /* 1-to-N functional addressing */ -/* default values */ +/* protocol machine default values */ #define CAN_ISOTP_DEFAULT_FLAGS 0 #define CAN_ISOTP_DEFAULT_EXT_ADDRESS 0x00 #define CAN_ISOTP_DEFAULT_PAD_CONTENT 0xCC /* prevent bit-stuffing */ -#define CAN_ISOTP_DEFAULT_FRAME_TXTIME 0 +#define CAN_ISOTP_DEFAULT_FRAME_TXTIME 50000 /* 50 micro seconds */ #define CAN_ISOTP_DEFAULT_RECV_BS 0 #define CAN_ISOTP_DEFAULT_RECV_STMIN 0x00 #define CAN_ISOTP_DEFAULT_RECV_WFTMAX 0 -#define CAN_ISOTP_DEFAULT_LL_MTU CAN_MTU -#define CAN_ISOTP_DEFAULT_LL_TX_DL CAN_MAX_DLEN -#define CAN_ISOTP_DEFAULT_LL_TX_FLAGS 0 - /* * Remark on CAN_ISOTP_DEFAULT_RECV_* values: * @@ -162,4 +158,24 @@ struct can_isotp_ll_options { * consistency and copied directly into the flow control (FC) frame. */ +/* link layer default values => make use of Classical CAN frames */ + +#define CAN_ISOTP_DEFAULT_LL_MTU CAN_MTU +#define CAN_ISOTP_DEFAULT_LL_TX_DL CAN_MAX_DLEN +#define CAN_ISOTP_DEFAULT_LL_TX_FLAGS 0 + +/* + * The CAN_ISOTP_DEFAULT_FRAME_TXTIME has become a non-zero value as + * it only makes sense for isotp implementation tests to run without + * a N_As value. As user space applications usually do not set the + * frame_txtime element of struct can_isotp_options the new in-kernel + * default is very likely overwritten with zero when the sockopt() + * CAN_ISOTP_OPTS is invoked. + * To make sure that a N_As value of zero is only set intentional the + * value '0' is now interpreted as 'do not change the current value'. + * When a frame_txtime of zero is required for testing purposes this + * CAN_ISOTP_FRAME_TXTIME_ZERO u32 value has to be set in frame_txtime. + */ +#define CAN_ISOTP_FRAME_TXTIME_ZERO 0xFFFFFFFF + #endif /* !_UAPI_CAN_ISOTP_H */ -- cgit v1.2.3 From 2757be22c0f4c06d359f802fa1fc57286fa26975 Mon Sep 17 00:00:00 2001 From: Usama Arif Date: Fri, 4 Feb 2022 14:51:13 +0000 Subject: io_uring: remove trace for eventfd The information on whether eventfd is registered is not very useful and would result in the tracepoint being enclosed in an rcu_readlock in a later patch that tries to avoid ring quiesce for registering eventfd. Suggested-by: Jens Axboe Signed-off-by: Usama Arif Link: https://lore.kernel.org/r/20220204145117.1186568-2-usama.arif@bytedance.com Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 7346f0164cf4..098beda7601a 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -57,10 +57,9 @@ TRACE_EVENT(io_uring_create, * @opcode: describes which operation to perform * @nr_user_files: number of registered files * @nr_user_bufs: number of registered buffers - * @cq_ev_fd: whether eventfs registered or not * @ret: return code * - * Allows to trace fixed files/buffers/eventfds, that could be registered to + * Allows to trace fixed files/buffers, that could be registered to * avoid an overhead of getting references to them for every operation. This * event, together with io_uring_file_get, can provide a full picture of how * much overhead one can reduce via fixing. @@ -68,16 +67,15 @@ TRACE_EVENT(io_uring_create, TRACE_EVENT(io_uring_register, TP_PROTO(void *ctx, unsigned opcode, unsigned nr_files, - unsigned nr_bufs, bool eventfd, long ret), + unsigned nr_bufs, long ret), - TP_ARGS(ctx, opcode, nr_files, nr_bufs, eventfd, ret), + TP_ARGS(ctx, opcode, nr_files, nr_bufs, ret), TP_STRUCT__entry ( __field( void *, ctx ) __field( unsigned, opcode ) __field( unsigned, nr_files ) __field( unsigned, nr_bufs ) - __field( bool, eventfd ) __field( long, ret ) ), @@ -86,14 +84,13 @@ TRACE_EVENT(io_uring_register, __entry->opcode = opcode; __entry->nr_files = nr_files; __entry->nr_bufs = nr_bufs; - __entry->eventfd = eventfd; __entry->ret = ret; ), TP_printk("ring %p, opcode %d, nr_user_files %d, nr_user_bufs %d, " - "eventfd %d, ret %ld", + "ret %ld", __entry->ctx, __entry->opcode, __entry->nr_files, - __entry->nr_bufs, __entry->eventfd, __entry->ret) + __entry->nr_bufs, __entry->ret) ); /** -- cgit v1.2.3 From 502c87d65564cbfd65b1621309bcd900390eca81 Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Mon, 14 Feb 2022 10:04:30 -0800 Subject: io-uring: Make tracepoints consistent. This makes the io-uring tracepoints consistent. Where it makes sense the tracepoints start with the following four fields: - context (ring) - request - user_data - opcode. Signed-off-by: Stefan Roesch Link: https://lore.kernel.org/r/20220214180430.70572-3-shr@fb.com Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 318 +++++++++++++++++++--------------------- 1 file changed, 153 insertions(+), 165 deletions(-) (limited to 'include') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 098beda7601a..18d4341c581c 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -29,15 +29,15 @@ TRACE_EVENT(io_uring_create, TP_ARGS(fd, ctx, sq_entries, cq_entries, flags), TP_STRUCT__entry ( - __field( int, fd ) - __field( void *, ctx ) + __field( int, fd ) + __field( void *, ctx ) __field( u32, sq_entries ) __field( u32, cq_entries ) __field( u32, flags ) ), TP_fast_assign( - __entry->fd = fd; + __entry->fd = fd; __entry->ctx = ctx; __entry->sq_entries = sq_entries; __entry->cq_entries = cq_entries; @@ -72,11 +72,11 @@ TRACE_EVENT(io_uring_register, TP_ARGS(ctx, opcode, nr_files, nr_bufs, ret), TP_STRUCT__entry ( - __field( void *, ctx ) - __field( unsigned, opcode ) - __field( unsigned, nr_files ) - __field( unsigned, nr_bufs ) - __field( long, ret ) + __field( void *, ctx ) + __field( unsigned, opcode ) + __field( unsigned, nr_files) + __field( unsigned, nr_bufs ) + __field( long, ret ) ), TP_fast_assign( @@ -97,6 +97,8 @@ TRACE_EVENT(io_uring_register, * io_uring_file_get - called before getting references to an SQE file * * @ctx: pointer to a ring context structure + * @req: pointer to a submitted request + * @user_data: user data associated with the request * @fd: SQE file descriptor * * Allows to trace out how often an SQE file reference is obtained, which can @@ -105,59 +107,71 @@ TRACE_EVENT(io_uring_register, */ TRACE_EVENT(io_uring_file_get, - TP_PROTO(void *ctx, int fd), + TP_PROTO(void *ctx, void *req, unsigned long long user_data, int fd), - TP_ARGS(ctx, fd), + TP_ARGS(ctx, req, user_data, fd), TP_STRUCT__entry ( - __field( void *, ctx ) - __field( int, fd ) + __field( void *, ctx ) + __field( void *, req ) + __field( u64, user_data ) + __field( int, fd ) ), TP_fast_assign( - __entry->ctx = ctx; + __entry->ctx = ctx; + __entry->req = req; + __entry->user_data = user_data; __entry->fd = fd; ), - TP_printk("ring %p, fd %d", __entry->ctx, __entry->fd) + TP_printk("ring %p, req %p, user_data %llu, fd %d", + __entry->ctx, __entry->req, __entry->user_data, __entry->fd) ); /** * io_uring_queue_async_work - called before submitting a new async work * * @ctx: pointer to a ring context structure - * @hashed: type of workqueue, hashed or normal * @req: pointer to a submitted request + * @user_data: user data associated with the request + * @opcode: opcode of request + * @flags request flags * @work: pointer to a submitted io_wq_work + * @rw: type of workqueue, hashed or normal * * Allows to trace asynchronous work submission. */ TRACE_EVENT(io_uring_queue_async_work, - TP_PROTO(void *ctx, int rw, void * req, struct io_wq_work *work, - unsigned int flags), + TP_PROTO(void *ctx, void * req, unsigned long long user_data, u8 opcode, + unsigned int flags, struct io_wq_work *work, int rw), - TP_ARGS(ctx, rw, req, work, flags), + TP_ARGS(ctx, req, user_data, flags, opcode, work, rw), TP_STRUCT__entry ( - __field( void *, ctx ) - __field( int, rw ) - __field( void *, req ) - __field( struct io_wq_work *, work ) - __field( unsigned int, flags ) + __field( void *, ctx ) + __field( void *, req ) + __field( u64, user_data ) + __field( u8, opcode ) + __field( unsigned int, flags ) + __field( struct io_wq_work *, work ) + __field( int, rw ) ), TP_fast_assign( - __entry->ctx = ctx; - __entry->rw = rw; - __entry->req = req; - __entry->work = work; - __entry->flags = flags; + __entry->ctx = ctx; + __entry->req = req; + __entry->user_data = user_data; + __entry->flags = flags; + __entry->opcode = opcode; + __entry->work = work; + __entry->rw = rw; ), - TP_printk("ring %p, request %p, flags %d, %s queue, work %p", - __entry->ctx, __entry->req, __entry->flags, - __entry->rw ? "hashed" : "normal", __entry->work) + TP_printk("ring %p, request %p, user_data %llu, opcode %d, flags %d, %s queue, work %p", + __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, + __entry->flags, __entry->rw ? "hashed" : "normal", __entry->work) ); /** @@ -166,30 +180,33 @@ TRACE_EVENT(io_uring_queue_async_work, * @ctx: pointer to a ring context structure * @req: pointer to a deferred request * @user_data: user data associated with the request + * @opcode: opcode of request * * Allows to track deferred requests, to get an insight about what requests are * not started immediately. */ TRACE_EVENT(io_uring_defer, - TP_PROTO(void *ctx, void *req, unsigned long long user_data), + TP_PROTO(void *ctx, void *req, unsigned long long user_data, u8 opcode), - TP_ARGS(ctx, req, user_data), + TP_ARGS(ctx, req, user_data, opcode), TP_STRUCT__entry ( - __field( void *, ctx ) - __field( void *, req ) - __field( unsigned long long, data ) + __field( void *, ctx ) + __field( void *, req ) + __field( unsigned long long, data ) + __field( u8, opcode ) ), TP_fast_assign( __entry->ctx = ctx; __entry->req = req; __entry->data = user_data; + __entry->opcode = opcode; ), - TP_printk("ring %p, request %p user_data %llu", __entry->ctx, - __entry->req, __entry->data) + TP_printk("ring %p, request %p, user_data %llu, opcode %d", + __entry->ctx, __entry->req, __entry->data, __entry->opcode) ); /** @@ -247,7 +264,7 @@ TRACE_EVENT(io_uring_cqring_wait, ), TP_fast_assign( - __entry->ctx = ctx; + __entry->ctx = ctx; __entry->min_events = min_events; ), @@ -257,7 +274,10 @@ TRACE_EVENT(io_uring_cqring_wait, /** * io_uring_fail_link - called before failing a linked request * + * @ctx: pointer to a ring context structure * @req: request, which links were cancelled + * @user_data: user data associated with the request + * @opcode: opcode of request * @link: cancelled link * * Allows to track linked requests cancellation, to see not only that some work @@ -265,27 +285,36 @@ TRACE_EVENT(io_uring_cqring_wait, */ TRACE_EVENT(io_uring_fail_link, - TP_PROTO(void *req, void *link), + TP_PROTO(void *ctx, void *req, unsigned long long user_data, u8 opcode, void *link), - TP_ARGS(req, link), + TP_ARGS(ctx, req, user_data, opcode, link), TP_STRUCT__entry ( - __field( void *, req ) - __field( void *, link ) + __field( void *, ctx ) + __field( void *, req ) + __field( unsigned long long, user_data ) + __field( u8, opcode ) + __field( void *, link ) ), TP_fast_assign( - __entry->req = req; - __entry->link = link; + __entry->ctx = ctx; + __entry->req = req; + __entry->user_data = user_data; + __entry->opcode = opcode; + __entry->link = link; ), - TP_printk("request %p, link %p", __entry->req, __entry->link) + TP_printk("ring %p, request %p, user_data %llu, opcode %d, link %p", + __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, + __entry->link) ); /** * io_uring_complete - called when completing an SQE * * @ctx: pointer to a ring context structure + * @req: pointer to a submitted request * @user_data: user data associated with the request * @res: result of the request * @cflags: completion flags @@ -293,12 +322,13 @@ TRACE_EVENT(io_uring_fail_link, */ TRACE_EVENT(io_uring_complete, - TP_PROTO(void *ctx, u64 user_data, int res, unsigned cflags), + TP_PROTO(void *ctx, void *req, u64 user_data, int res, unsigned cflags), - TP_ARGS(ctx, user_data, res, cflags), + TP_ARGS(ctx, req, user_data, res, cflags), TP_STRUCT__entry ( __field( void *, ctx ) + __field( void *, req ) __field( u64, user_data ) __field( int, res ) __field( unsigned, cflags ) @@ -306,14 +336,16 @@ TRACE_EVENT(io_uring_complete, TP_fast_assign( __entry->ctx = ctx; + __entry->req = req; __entry->user_data = user_data; __entry->res = res; __entry->cflags = cflags; ), - TP_printk("ring %p, user_data 0x%llx, result %d, cflags %x", - __entry->ctx, (unsigned long long)__entry->user_data, - __entry->res, __entry->cflags) + TP_printk("ring %p, req %p, user_data 0x%llx, result %d, cflags %x", + __entry->ctx, __entry->req, + (unsigned long long)__entry->user_data, + __entry->res, __entry->cflags) ); /** @@ -321,8 +353,8 @@ TRACE_EVENT(io_uring_complete, * * @ctx: pointer to a ring context structure * @req: pointer to a submitted request - * @opcode: opcode of request * @user_data: user data associated with the request + * @opcode: opcode of request * @flags request flags * @force_nonblock: whether a context blocking or not * @sq_thread: true if sq_thread has submitted this SQE @@ -332,34 +364,34 @@ TRACE_EVENT(io_uring_complete, */ TRACE_EVENT(io_uring_submit_sqe, - TP_PROTO(void *ctx, void *req, u8 opcode, u64 user_data, u32 flags, + TP_PROTO(void *ctx, void *req, unsigned long long user_data, u8 opcode, u32 flags, bool force_nonblock, bool sq_thread), - TP_ARGS(ctx, req, opcode, user_data, flags, force_nonblock, sq_thread), + TP_ARGS(ctx, req, user_data, opcode, flags, force_nonblock, sq_thread), TP_STRUCT__entry ( - __field( void *, ctx ) - __field( void *, req ) - __field( u8, opcode ) - __field( u64, user_data ) - __field( u32, flags ) - __field( bool, force_nonblock ) - __field( bool, sq_thread ) + __field( void *, ctx ) + __field( void *, req ) + __field( unsigned long long, user_data ) + __field( u8, opcode ) + __field( u32, flags ) + __field( bool, force_nonblock ) + __field( bool, sq_thread ) ), TP_fast_assign( __entry->ctx = ctx; __entry->req = req; - __entry->opcode = opcode; __entry->user_data = user_data; + __entry->opcode = opcode; __entry->flags = flags; __entry->force_nonblock = force_nonblock; __entry->sq_thread = sq_thread; ), - TP_printk("ring %p, req %p, op %d, data 0x%llx, flags %u, " + TP_printk("ring %p, req %p, user_data %llu, opcode %d, flags %u, " "non block %d, sq_thread %d", __entry->ctx, __entry->req, - __entry->opcode, (unsigned long long)__entry->user_data, + __entry->user_data, __entry->opcode, __entry->flags, __entry->force_nonblock, __entry->sq_thread) ); @@ -368,8 +400,8 @@ TRACE_EVENT(io_uring_submit_sqe, * * @ctx: pointer to a ring context structure * @req: pointer to the armed request - * @opcode: opcode of request * @user_data: user data associated with the request + * @opcode: opcode of request * @mask: request poll events mask * @events: registered events of interest * @@ -378,155 +410,110 @@ TRACE_EVENT(io_uring_submit_sqe, */ TRACE_EVENT(io_uring_poll_arm, - TP_PROTO(void *ctx, void *req, u8 opcode, u64 user_data, + TP_PROTO(void *ctx, void *req, u64 user_data, u8 opcode, int mask, int events), - TP_ARGS(ctx, req, opcode, user_data, mask, events), + TP_ARGS(ctx, req, user_data, opcode, mask, events), TP_STRUCT__entry ( - __field( void *, ctx ) - __field( void *, req ) - __field( u8, opcode ) - __field( u64, user_data ) - __field( int, mask ) - __field( int, events ) + __field( void *, ctx ) + __field( void *, req ) + __field( unsigned long long, user_data ) + __field( u8, opcode ) + __field( int, mask ) + __field( int, events ) ), TP_fast_assign( __entry->ctx = ctx; __entry->req = req; - __entry->opcode = opcode; __entry->user_data = user_data; + __entry->opcode = opcode; __entry->mask = mask; __entry->events = events; ), - TP_printk("ring %p, req %p, op %d, data 0x%llx, mask 0x%x, events 0x%x", - __entry->ctx, __entry->req, __entry->opcode, - (unsigned long long) __entry->user_data, + TP_printk("ring %p, req %p, user_data %llu, opcode %d, mask 0x%x, events 0x%x", + __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, __entry->mask, __entry->events) ); -TRACE_EVENT(io_uring_poll_wake, - - TP_PROTO(void *ctx, u8 opcode, u64 user_data, int mask), - - TP_ARGS(ctx, opcode, user_data, mask), - - TP_STRUCT__entry ( - __field( void *, ctx ) - __field( u8, opcode ) - __field( u64, user_data ) - __field( int, mask ) - ), - - TP_fast_assign( - __entry->ctx = ctx; - __entry->opcode = opcode; - __entry->user_data = user_data; - __entry->mask = mask; - ), - - TP_printk("ring %p, op %d, data 0x%llx, mask 0x%x", - __entry->ctx, __entry->opcode, - (unsigned long long) __entry->user_data, - __entry->mask) -); - -TRACE_EVENT(io_uring_task_add, - - TP_PROTO(void *ctx, u8 opcode, u64 user_data, int mask), - - TP_ARGS(ctx, opcode, user_data, mask), - - TP_STRUCT__entry ( - __field( void *, ctx ) - __field( u8, opcode ) - __field( u64, user_data ) - __field( int, mask ) - ), - - TP_fast_assign( - __entry->ctx = ctx; - __entry->opcode = opcode; - __entry->user_data = user_data; - __entry->mask = mask; - ), - - TP_printk("ring %p, op %d, data 0x%llx, mask %x", - __entry->ctx, __entry->opcode, - (unsigned long long) __entry->user_data, - __entry->mask) -); - /* - * io_uring_task_run - called when task_work_run() executes the poll events - * notification callbacks + * io_uring_task_add - called after adding a task * * @ctx: pointer to a ring context structure - * @req: pointer to the armed request - * @opcode: opcode of request + * @req: pointer to request * @user_data: user data associated with the request + * @opcode: opcode of request + * @mask: request poll events mask * - * Allows to track when notified poll events are processed */ -TRACE_EVENT(io_uring_task_run, +TRACE_EVENT(io_uring_task_add, - TP_PROTO(void *ctx, void *req, u8 opcode, u64 user_data), + TP_PROTO(void *ctx, void *req, unsigned long long user_data, u8 opcode, int mask), - TP_ARGS(ctx, req, opcode, user_data), + TP_ARGS(ctx, req, user_data, opcode, mask), TP_STRUCT__entry ( - __field( void *, ctx ) - __field( void *, req ) - __field( u8, opcode ) - __field( u64, user_data ) + __field( void *, ctx ) + __field( void *, req ) + __field( unsigned long long, user_data ) + __field( u8, opcode ) + __field( int, mask ) ), TP_fast_assign( __entry->ctx = ctx; __entry->req = req; - __entry->opcode = opcode; __entry->user_data = user_data; + __entry->opcode = opcode; + __entry->mask = mask; ), - TP_printk("ring %p, req %p, op %d, data 0x%llx", - __entry->ctx, __entry->req, __entry->opcode, - (unsigned long long) __entry->user_data) + TP_printk("ring %p, req %p, user_data %llu, opcode %d, mask %x", + __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, + __entry->mask) ); /* * io_uring_req_failed - called when an sqe is errored dring submission * * @sqe: pointer to the io_uring_sqe that failed + * @ctx: pointer to a ring context structure + * @req: pointer to request * @error: error it failed with * * Allows easier diagnosing of malformed requests in production systems. */ TRACE_EVENT(io_uring_req_failed, - TP_PROTO(const struct io_uring_sqe *sqe, int error), + TP_PROTO(const struct io_uring_sqe *sqe, void *ctx, void *req, int error), - TP_ARGS(sqe, error), + TP_ARGS(sqe, ctx, req, error), TP_STRUCT__entry ( - __field( u8, opcode ) - __field( u8, flags ) - __field( u8, ioprio ) - __field( u64, off ) - __field( u64, addr ) - __field( u32, len ) - __field( u32, op_flags ) - __field( u64, user_data ) - __field( u16, buf_index ) - __field( u16, personality ) - __field( u32, file_index ) - __field( u64, pad1 ) - __field( u64, pad2 ) - __field( int, error ) + __field( void *, ctx ) + __field( void *, req ) + __field( unsigned long long, user_data ) + __field( u8, opcode ) + __field( u8, flags ) + __field( u8, ioprio ) + __field( u64, off ) + __field( u64, addr ) + __field( u32, len ) + __field( u32, op_flags ) + __field( u16, buf_index ) + __field( u16, personality ) + __field( u32, file_index ) + __field( u64, pad1 ) + __field( u64, pad2 ) + __field( int, error ) ), TP_fast_assign( + __entry->ctx = ctx; + __entry->req = req; + __entry->user_data = sqe->user_data; __entry->opcode = sqe->opcode; __entry->flags = sqe->flags; __entry->ioprio = sqe->ioprio; @@ -534,7 +521,6 @@ TRACE_EVENT(io_uring_req_failed, __entry->addr = sqe->addr; __entry->len = sqe->len; __entry->op_flags = sqe->rw_flags; - __entry->user_data = sqe->user_data; __entry->buf_index = sqe->buf_index; __entry->personality = sqe->personality; __entry->file_index = sqe->file_index; @@ -543,13 +529,15 @@ TRACE_EVENT(io_uring_req_failed, __entry->error = error; ), - TP_printk("op %d, flags=0x%x, prio=%d, off=%llu, addr=%llu, " - "len=%u, rw_flags=0x%x, user_data=0x%llx, buf_index=%d, " + TP_printk("ring %p, req %p, user_data %llu, " + "op %d, flags=0x%x, prio=%d, off=%llu, addr=%llu, " + "len=%u, rw_flags=0x%x, buf_index=%d, " "personality=%d, file_index=%d, pad=0x%llx/%llx, error=%d", + __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, __entry->flags, __entry->ioprio, (unsigned long long)__entry->off, (unsigned long long) __entry->addr, __entry->len, - __entry->op_flags, (unsigned long long) __entry->user_data, + __entry->op_flags, __entry->buf_index, __entry->personality, __entry->file_index, (unsigned long long) __entry->pad1, (unsigned long long) __entry->pad2, __entry->error) -- cgit v1.2.3 From e7a6c00dc77aedf27a601738ea509f1caea6d673 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 4 Mar 2022 08:22:22 -0700 Subject: io_uring: add support for registering ring file descriptors Lots of workloads use multiple threads, in which case the file table is shared between them. This makes getting and putting the ring file descriptor for each io_uring_enter(2) system call more expensive, as it involves an atomic get and put for each call. Similarly to how we allow registering normal file descriptors to avoid this overhead, add support for an io_uring_register(2) API that allows to register the ring fds themselves: 1) IORING_REGISTER_RING_FDS - takes an array of io_uring_rsrc_update structs, and registers them with the task. 2) IORING_UNREGISTER_RING_FDS - takes an array of io_uring_src_update structs, and unregisters them. When a ring fd is registered, it is internally represented by an offset. This offset is returned to the application, and the application then uses this offset and sets IORING_ENTER_REGISTERED_RING for the io_uring_enter(2) system call. This works just like using a registered file descriptor, rather than a real one, in an SQE, where IOSQE_FIXED_FILE gets set to tell io_uring that we're using an internal offset/descriptor rather than a real file descriptor. In initial testing, this provides a nice bump in performance for threaded applications in real world cases where the batch count (eg number of requests submitted per io_uring_enter(2) invocation) is low. In a microbenchmark, submitting NOP requests, we see the following increases in performance: Requests per syscall Baseline Registered Increase ---------------------------------------------------------------- 1 ~7030K ~8080K +15% 2 ~13120K ~14800K +13% 4 ~22740K ~25300K +11% Co-developed-by: Xiaoguang Wang Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 5 ++++- include/uapi/linux/io_uring.h | 13 +++++++++---- 2 files changed, 13 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 649a4d7c241b..1814e698d861 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -9,11 +9,14 @@ struct sock *io_uring_get_socket(struct file *file); void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); +void io_uring_unreg_ringfd(void); static inline void io_uring_files_cancel(void) { - if (current->io_uring) + if (current->io_uring) { + io_uring_unreg_ringfd(); __io_uring_cancel(false); + } } static inline void io_uring_task_cancel(void) { diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 787f491f0d2a..42b2fe84dbcd 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -257,10 +257,11 @@ struct io_cqring_offsets { /* * io_uring_enter(2) flags */ -#define IORING_ENTER_GETEVENTS (1U << 0) -#define IORING_ENTER_SQ_WAKEUP (1U << 1) -#define IORING_ENTER_SQ_WAIT (1U << 2) -#define IORING_ENTER_EXT_ARG (1U << 3) +#define IORING_ENTER_GETEVENTS (1U << 0) +#define IORING_ENTER_SQ_WAKEUP (1U << 1) +#define IORING_ENTER_SQ_WAIT (1U << 2) +#define IORING_ENTER_EXT_ARG (1U << 3) +#define IORING_ENTER_REGISTERED_RING (1U << 4) /* * Passed in for io_uring_setup(2). Copied back with updated info on success @@ -325,6 +326,10 @@ enum { /* set/get max number of io-wq workers */ IORING_REGISTER_IOWQ_MAX_WORKERS = 19, + /* register/unregister io_uring fd with the ring */ + IORING_REGISTER_RING_FDS = 20, + IORING_UNREGISTER_RING_FDS = 21, + /* this goes last */ IORING_REGISTER_LAST }; -- cgit v1.2.3 From 4f57f06ce2186c31c3da52386125dc57b1cd6f96 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 10 Mar 2022 06:27:26 -0700 Subject: io_uring: add support for IORING_OP_MSG_RING command This adds support for IORING_OP_MSG_RING, which allows an SQE to signal another ring. That allows either waking up someone waiting on the ring, or even passing a 64-bit value via the user_data field in the CQE. sqe->fd must contain the fd of a ring that should receive the CQE. sqe->off will be propagated to the cqe->user_data on the target ring, and sqe->len will be propagated to cqe->res. The results CQE will have IORING_CQE_F_MSG set in its flags, to indicate that this CQE was generated from a messaging request rather than a SQE issued locally on that ring. This effectively allows passing a 64-bit and a 32-bit quantify between the two rings. This request type has the following request specific error cases: - -EBADFD. Set if the sqe->fd doesn't point to a file descriptor that is of the io_uring type. - -EOVERFLOW. Set if we were not able to deliver a request to the target ring. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 42b2fe84dbcd..8bd4bfdd9a89 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -143,6 +143,7 @@ enum { IORING_OP_MKDIRAT, IORING_OP_SYMLINKAT, IORING_OP_LINKAT, + IORING_OP_MSG_RING, /* this goes last, obviously */ IORING_OP_LAST, @@ -199,9 +200,11 @@ struct io_uring_cqe { * * IORING_CQE_F_BUFFER If set, the upper 16 bits are the buffer ID * IORING_CQE_F_MORE If set, parent SQE will generate more CQE entries + * IORING_CQE_F_MSG If set, CQE was generated with IORING_OP_MSG_RING */ #define IORING_CQE_F_BUFFER (1U << 0) #define IORING_CQE_F_MORE (1U << 1) +#define IORING_CQE_F_MSG (1U << 2) enum { IORING_CQE_BUFFER_SHIFT = 16, -- cgit v1.2.3 From 382627824afb09cd86192f4b649fca8c5bfe5f40 Mon Sep 17 00:00:00 2001 From: Xiongwei Song Date: Thu, 10 Mar 2022 22:07:00 +0800 Subject: mm: slab: Delete unused SLAB_DEACTIVATED flag Since commit 9855609bde03 ("mm: memcg/slab: use a single set of kmem_caches for all accounted allocations") deleted all SLAB_DEACTIVATED users, therefore this flag is not needed any more, let's delete it. Signed-off-by: Xiongwei Song Acked-by: David Rientjes Reviewed-by: Roman Gushchin Acked-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Signed-off-by: Vlastimil Babka Link: https://lore.kernel.org/r/20220310140701.87908-2-sxwjean@me.com --- include/linux/slab.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/slab.h b/include/linux/slab.h index 37bde99b74af..b6b3eed6c7c4 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -117,9 +117,6 @@ #define SLAB_RECLAIM_ACCOUNT ((slab_flags_t __force)0x00020000U) #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ -/* Slab deactivation flag */ -#define SLAB_DEACTIVATED ((slab_flags_t __force)0x10000000U) - /* * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. * -- cgit v1.2.3 From afcf5441b9ff22ac57244cd45ff102ebc2e32d1a Mon Sep 17 00:00:00 2001 From: Dan Li Date: Wed, 2 Mar 2022 23:43:23 -0800 Subject: arm64: Add gcc Shadow Call Stack support Shadow call stacks will be available in GCC >= 12, this patch makes the corresponding kernel configuration available when compiling the kernel with the gcc. Note that the implementation in GCC is slightly different from Clang. With SCS enabled, functions will only pop x30 once in the epilogue, like: str x30, [x18], #8 stp x29, x30, [sp, #-16]! ...... - ldp x29, x30, [sp], #16 //clang + ldr x29, [sp], #16 //GCC ldr x30, [x18, #-8]! Link: https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=ce09ab17ddd21f73ff2caf6eec3b0ee9b0e1a11e Reviewed-by: Nathan Chancellor Reviewed-by: Kees Cook Reviewed-by: Nick Desaulniers Signed-off-by: Dan Li Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220303074323.86282-1-ashimida@linux.alibaba.com --- include/linux/compiler-gcc.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index ccbbd31b3aae..deff5b308470 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -97,6 +97,10 @@ #define KASAN_ABI_VERSION 4 #endif +#ifdef CONFIG_SHADOW_CALL_STACK +#define __noscs __attribute__((__no_sanitize__("shadow-call-stack"))) +#endif + #if __has_attribute(__no_sanitize_address__) #define __no_sanitize_address __attribute__((no_sanitize_address)) #else -- cgit v1.2.3 From b7f8dff09827c96032c34a945ee7757e394b5952 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 10 Mar 2022 11:45:58 -0500 Subject: dm: simplify dm_sumbit_bio_remap interface Remove the from_wq argument from dm_sumbit_bio_remap(). Eliminates the need for dm_sumbit_bio_remap() callers to know whether they are calling for a workqueue or from the original dm_submit_bio(). Add map_task to dm_io struct, record the map_task in alloc_io and clear it after all target ->map() calls have completed. Update dm_sumbit_bio_remap to check if 'current' matches io->map_task rather than rely on passed 'from_rq' argument. This change really simplifies the chore of porting each DM target to using dm_sumbit_bio_remap() because there is no longer the risk of programming error by not completely knowing all the different contexts a particular method that calls dm_sumbit_bio_remap() might be used in. Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 70cd9449275a..901ec191250c 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -471,7 +471,7 @@ int dm_suspended(struct dm_target *ti); int dm_post_suspending(struct dm_target *ti); int dm_noflush_suspending(struct dm_target *ti); void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors); -void dm_submit_bio_remap(struct bio *clone, struct bio *tgt_clone, bool from_wq); +void dm_submit_bio_remap(struct bio *clone, struct bio *tgt_clone); union map_info *dm_get_rq_mapinfo(struct request *rq); #ifdef CONFIG_BLK_DEV_ZONED -- cgit v1.2.3 From a2a591fb76e6f5461dfd04715b69c317e50c43a5 Mon Sep 17 00:00:00 2001 From: Ilkka Koskinen Date: Tue, 8 Mar 2022 18:07:50 -0800 Subject: ACPI: AGDI: Add driver for Arm Generic Diagnostic Dump and Reset device ACPI for Arm Components 1.1 Platform Design Document v1.1 [0] specifices Arm Generic Diagnostic Device Interface (AGDI). It allows an admin to issue diagnostic dump and reset via an SDEI event or an interrupt. This patch implements SDEI path. [0] https://developer.arm.com/documentation/den0093/latest/ Signed-off-by: Ilkka Koskinen Reviewed-by: Russell King (Oracle) Acked-by: Lorenzo Pieralisi Signed-off-by: Rafael J. Wysocki --- include/linux/acpi_agdi.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 include/linux/acpi_agdi.h (limited to 'include') diff --git a/include/linux/acpi_agdi.h b/include/linux/acpi_agdi.h new file mode 100644 index 000000000000..f477f0b452fa --- /dev/null +++ b/include/linux/acpi_agdi.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ACPI_AGDI_H__ +#define __ACPI_AGDI_H__ + +#include + +#ifdef CONFIG_ACPI_AGDI +void __init acpi_agdi_init(void); +#else +static inline void acpi_agdi_init(void) {} +#endif +#endif /* __ACPI_AGDI_H__ */ -- cgit v1.2.3 From 9924fbb51e0ae30b8d7eec7c1c839d74da9678b3 Mon Sep 17 00:00:00 2001 From: Ionela Voinescu Date: Thu, 10 Mar 2022 14:54:50 +0000 Subject: arch_topology: obtain cpu capacity using information from CPPC Define topology_init_cpu_capacity_cppc() to use highest performance values from _CPC objects to obtain and set maximum capacity information for each CPU. acpi_cppc_processor_probe() is a good point at which to trigger the initialization of CPU (u-arch) capacity values, as at this point the highest performance values can be obtained from each CPU's _CPC objects. Architectures can therefore use this functionality through arch_init_invariance_cppc(). The performance scale used by CPPC is a unified scale for all CPUs in the system. Therefore, by obtaining the raw highest performance values from the _CPC objects, and normalizing them on the [0, 1024] capacity scale, used by the task scheduler, we obtain the CPU capacity of each CPU. While an ACPI Notify(0x85) could alert about a change in the highest performance value, which should in turn retrigger the CPU capacity computations, this notification is not currently handled by the ACPI processor driver. When supported, a call to arch_init_invariance_cppc() would perform the update. Signed-off-by: Ionela Voinescu Acked-by: Sudeep Holla Tested-by: Valentin Schneider Tested-by: Yicong Yang Signed-off-by: Rafael J. Wysocki --- include/linux/arch_topology.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index cce6136b300a..58cbe18d825c 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -11,6 +11,10 @@ void topology_normalize_cpu_scale(void); int topology_update_cpu_topology(void); +#ifdef CONFIG_ACPI_CPPC_LIB +void topology_init_cpu_capacity_cppc(void); +#endif + struct device_node; bool topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu); -- cgit v1.2.3 From 19397e8b546d20226153dafe5dce34c4393752c4 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 27 Jan 2022 11:17:32 -0600 Subject: ptrace: Move ptrace_report_syscall into ptrace.h Move ptrace_report_syscall from tracehook.h into ptrace.h where it belongs. Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20220309162454.123006-1-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/ptrace.h | 27 +++++++++++++++++++++++++++ include/linux/tracehook.h | 26 -------------------------- 2 files changed, 27 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 8aee2945ff08..91b1074edb4c 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -413,4 +413,31 @@ static inline void user_single_step_report(struct pt_regs *regs) extern int task_current_syscall(struct task_struct *target, struct syscall_info *info); extern void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact); + +/* + * ptrace report for syscall entry and exit looks identical. + */ +static inline int ptrace_report_syscall(unsigned long message) +{ + int ptrace = current->ptrace; + + if (!(ptrace & PT_PTRACED)) + return 0; + + current->ptrace_message = message; + ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0)); + + /* + * this isn't the same as continuing with a signal, but it will do + * for normal use. strace only continues with a signal if the + * stopping signal is not SIGTRAP. -brl + */ + if (current->exit_code) { + send_sig(current->exit_code, current, 1); + current->exit_code = 0; + } + + current->ptrace_message = 0; + return fatal_signal_pending(current); +} #endif diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 88c007ab5ebc..998bc3863559 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -51,32 +51,6 @@ #include struct linux_binprm; -/* - * ptrace report for syscall entry and exit looks identical. - */ -static inline int ptrace_report_syscall(unsigned long message) -{ - int ptrace = current->ptrace; - - if (!(ptrace & PT_PTRACED)) - return 0; - - current->ptrace_message = message; - ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0)); - - /* - * this isn't the same as continuing with a signal, but it will do - * for normal use. strace only continues with a signal if the - * stopping signal is not SIGTRAP. -brl - */ - if (current->exit_code) { - send_sig(current->exit_code, current, 1); - current->exit_code = 0; - } - - current->ptrace_message = 0; - return fatal_signal_pending(current); -} /** * tracehook_report_syscall_entry - task is about to attempt a system call -- cgit v1.2.3 From 153474ba1a4aed0a7b797b4c2be8c35c7a4e57bd Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 27 Jan 2022 11:46:37 -0600 Subject: ptrace: Create ptrace_report_syscall_{entry,exit} in ptrace.h Rename tracehook_report_syscall_{entry,exit} to ptrace_report_syscall_{entry,exit} and place them in ptrace.h There is no longer any generic tracehook infractructure so make these ptrace specific functions ptrace specific. Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20220309162454.123006-3-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/asm-generic/syscall.h | 2 +- include/linux/entry-common.h | 6 ++--- include/linux/ptrace.h | 51 +++++++++++++++++++++++++++++++++++++++++++ include/linux/tracehook.h | 51 ------------------------------------------- include/uapi/linux/ptrace.h | 2 +- 5 files changed, 56 insertions(+), 56 deletions(-) (limited to 'include') diff --git a/include/asm-generic/syscall.h b/include/asm-generic/syscall.h index 81695eb02a12..5a80fe728dc8 100644 --- a/include/asm-generic/syscall.h +++ b/include/asm-generic/syscall.h @@ -44,7 +44,7 @@ int syscall_get_nr(struct task_struct *task, struct pt_regs *regs); * * It's only valid to call this when @task is stopped for system * call exit tracing (due to %SYSCALL_WORK_SYSCALL_TRACE or - * %SYSCALL_WORK_SYSCALL_AUDIT), after tracehook_report_syscall_entry() + * %SYSCALL_WORK_SYSCALL_AUDIT), after ptrace_report_syscall_entry() * returned nonzero to prevent the system call from taking place. * * This rolls back the register state in @regs so it's as if the diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index 2e2b8d6140ed..a670e9fba7a9 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -3,7 +3,7 @@ #define __LINUX_ENTRYCOMMON_H #include -#include +#include #include #include #include @@ -95,7 +95,7 @@ static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs #ifndef arch_syscall_enter_tracehook static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs) { - return tracehook_report_syscall_entry(regs); + return ptrace_report_syscall_entry(regs); } #endif @@ -294,7 +294,7 @@ static inline void arch_syscall_exit_tracehook(struct pt_regs *regs, bool step); #ifndef arch_syscall_exit_tracehook static inline void arch_syscall_exit_tracehook(struct pt_regs *regs, bool step) { - tracehook_report_syscall_exit(regs, step); + ptrace_report_syscall_exit(regs, step); } #endif diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 91b1074edb4c..5310f43e4762 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -440,4 +440,55 @@ static inline int ptrace_report_syscall(unsigned long message) current->ptrace_message = 0; return fatal_signal_pending(current); } + +/** + * ptrace_report_syscall_entry - task is about to attempt a system call + * @regs: user register state of current task + * + * This will be called if %SYSCALL_WORK_SYSCALL_TRACE or + * %SYSCALL_WORK_SYSCALL_EMU have been set, when the current task has just + * entered the kernel for a system call. Full user register state is + * available here. Changing the values in @regs can affect the system + * call number and arguments to be tried. It is safe to block here, + * preventing the system call from beginning. + * + * Returns zero normally, or nonzero if the calling arch code should abort + * the system call. That must prevent normal entry so no system call is + * made. If @task ever returns to user mode after this, its register state + * is unspecified, but should be something harmless like an %ENOSYS error + * return. It should preserve enough information so that syscall_rollback() + * can work (see asm-generic/syscall.h). + * + * Called without locks, just after entering kernel mode. + */ +static inline __must_check int ptrace_report_syscall_entry( + struct pt_regs *regs) +{ + return ptrace_report_syscall(PTRACE_EVENTMSG_SYSCALL_ENTRY); +} + +/** + * ptrace_report_syscall_exit - task has just finished a system call + * @regs: user register state of current task + * @step: nonzero if simulating single-step or block-step + * + * This will be called if %SYSCALL_WORK_SYSCALL_TRACE has been set, when + * the current task has just finished an attempted system call. Full + * user register state is available here. It is safe to block here, + * preventing signals from being processed. + * + * If @step is nonzero, this report is also in lieu of the normal + * trap that would follow the system call instruction because + * user_enable_block_step() or user_enable_single_step() was used. + * In this case, %SYSCALL_WORK_SYSCALL_TRACE might not be set. + * + * Called without locks, just before checking for pending signals. + */ +static inline void ptrace_report_syscall_exit(struct pt_regs *regs, int step) +{ + if (step) + user_single_step_report(regs); + else + ptrace_report_syscall(PTRACE_EVENTMSG_SYSCALL_EXIT); +} #endif diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 998bc3863559..819e82ac09bd 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -52,57 +52,6 @@ struct linux_binprm; -/** - * tracehook_report_syscall_entry - task is about to attempt a system call - * @regs: user register state of current task - * - * This will be called if %SYSCALL_WORK_SYSCALL_TRACE or - * %SYSCALL_WORK_SYSCALL_EMU have been set, when the current task has just - * entered the kernel for a system call. Full user register state is - * available here. Changing the values in @regs can affect the system - * call number and arguments to be tried. It is safe to block here, - * preventing the system call from beginning. - * - * Returns zero normally, or nonzero if the calling arch code should abort - * the system call. That must prevent normal entry so no system call is - * made. If @task ever returns to user mode after this, its register state - * is unspecified, but should be something harmless like an %ENOSYS error - * return. It should preserve enough information so that syscall_rollback() - * can work (see asm-generic/syscall.h). - * - * Called without locks, just after entering kernel mode. - */ -static inline __must_check int tracehook_report_syscall_entry( - struct pt_regs *regs) -{ - return ptrace_report_syscall(PTRACE_EVENTMSG_SYSCALL_ENTRY); -} - -/** - * tracehook_report_syscall_exit - task has just finished a system call - * @regs: user register state of current task - * @step: nonzero if simulating single-step or block-step - * - * This will be called if %SYSCALL_WORK_SYSCALL_TRACE has been set, when - * the current task has just finished an attempted system call. Full - * user register state is available here. It is safe to block here, - * preventing signals from being processed. - * - * If @step is nonzero, this report is also in lieu of the normal - * trap that would follow the system call instruction because - * user_enable_block_step() or user_enable_single_step() was used. - * In this case, %SYSCALL_WORK_SYSCALL_TRACE might not be set. - * - * Called without locks, just before checking for pending signals. - */ -static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) -{ - if (step) - user_single_step_report(regs); - else - ptrace_report_syscall(PTRACE_EVENTMSG_SYSCALL_EXIT); -} - /** * tracehook_signal_handler - signal handler setup is complete * @stepping: nonzero if debugger single-step or block-step in use diff --git a/include/uapi/linux/ptrace.h b/include/uapi/linux/ptrace.h index 3747bf816f9a..b7af92e07d1f 100644 --- a/include/uapi/linux/ptrace.h +++ b/include/uapi/linux/ptrace.h @@ -114,7 +114,7 @@ struct ptrace_rseq_configuration { /* * These values are stored in task->ptrace_message - * by tracehook_report_syscall_* to describe the current syscall-stop. + * by ptrace_report_syscall_* to describe the current syscall-stop. */ #define PTRACE_EVENTMSG_SYSCALL_ENTRY 1 #define PTRACE_EVENTMSG_SYSCALL_EXIT 2 -- cgit v1.2.3 From 0cfcb2b9ef48bbcaf5d43b9f1893f63a938e8176 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 27 Jan 2022 12:00:55 -0600 Subject: ptrace: Remove arch_syscall_{enter,exit}_tracehook These functions are alwasy one-to-one wrappers around ptrace_report_syscall_entry and ptrace_report_syscall_exit. So directly call the functions they are wrapping instead. Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20220309162454.123006-4-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/entry-common.h | 43 ++----------------------------------------- 1 file changed, 2 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index a670e9fba7a9..9efbdda61f7a 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -79,26 +79,6 @@ static __always_inline void arch_check_user_regs(struct pt_regs *regs); static __always_inline void arch_check_user_regs(struct pt_regs *regs) {} #endif -/** - * arch_syscall_enter_tracehook - Wrapper around tracehook_report_syscall_entry() - * @regs: Pointer to currents pt_regs - * - * Returns: 0 on success or an error code to skip the syscall. - * - * Defaults to tracehook_report_syscall_entry(). Can be replaced by - * architecture specific code. - * - * Invoked from syscall_enter_from_user_mode() - */ -static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs); - -#ifndef arch_syscall_enter_tracehook -static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs) -{ - return ptrace_report_syscall_entry(regs); -} -#endif - /** * enter_from_user_mode - Establish state when coming from user mode * @@ -157,7 +137,7 @@ void syscall_enter_from_user_mode_prepare(struct pt_regs *regs); * It handles the following work items: * * 1) syscall_work flag dependent invocations of - * arch_syscall_enter_tracehook(), __secure_computing(), trace_sys_enter() + * ptrace_report_syscall_entry(), __secure_computing(), trace_sys_enter() * 2) Invocation of audit_syscall_entry() */ long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall); @@ -279,25 +259,6 @@ static __always_inline void arch_exit_to_user_mode(void) { } */ void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal); -/** - * arch_syscall_exit_tracehook - Wrapper around tracehook_report_syscall_exit() - * @regs: Pointer to currents pt_regs - * @step: Indicator for single step - * - * Defaults to tracehook_report_syscall_exit(). Can be replaced by - * architecture specific code. - * - * Invoked from syscall_exit_to_user_mode() - */ -static inline void arch_syscall_exit_tracehook(struct pt_regs *regs, bool step); - -#ifndef arch_syscall_exit_tracehook -static inline void arch_syscall_exit_tracehook(struct pt_regs *regs, bool step) -{ - ptrace_report_syscall_exit(regs, step); -} -#endif - /** * exit_to_user_mode - Fixup state when exiting to user mode * @@ -347,7 +308,7 @@ void syscall_exit_to_user_mode_work(struct pt_regs *regs); * - rseq syscall exit * - audit * - syscall tracing - * - tracehook (single stepping) + * - ptrace (single stepping) * * 2) Preparatory work * - Exit to user mode loop (common TIF handling). Invokes -- cgit v1.2.3 From c145137dc990fd67b52fbc52faae5ba46f168cca Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 27 Jan 2022 12:04:27 -0600 Subject: ptrace: Remove tracehook_signal_handler The two line function tracehook_signal_handler is only called from signal_delivered. Expand it inline in signal_delivered and remove it. Just to make it easier to understand what is going on. Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20220309162454.123006-5-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/tracehook.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 819e82ac09bd..b77bf4917196 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -52,23 +52,6 @@ struct linux_binprm; -/** - * tracehook_signal_handler - signal handler setup is complete - * @stepping: nonzero if debugger single-step or block-step in use - * - * Called by the arch code after a signal handler has been set up. - * Register and stack state reflects the user handler about to run. - * Signal mask changes have already been made. - * - * Called without locks, shortly before returning to user mode - * (or handling more signals). - */ -static inline void tracehook_signal_handler(int stepping) -{ - if (stepping) - ptrace_notify(SIGTRAP); -} - /** * set_notify_resume - cause tracehook_notify_resume() to be called * @task: task that will call tracehook_notify_resume() -- cgit v1.2.3 From 8ca07e17c9dd4c4afcb4a3f2ea8f0a0d41c0f982 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 28 Jan 2022 13:55:47 -0600 Subject: task_work: Remove unnecessary include from posix_timers.h Break a header file circular dependency by removing the unnecessary include of task_work.h from posix_timers.h. sched.h -> posix-timers.h posix-timers.h -> task_work.h task_work.h -> sched.h Add missing includes of task_work.h to: arch/x86/mm/tlb.c kernel/time/posix-cpu-timers.c Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20220309162454.123006-6-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/posix-timers.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 5bbcd280bfd2..83539bb2f023 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -6,7 +6,6 @@ #include #include #include -#include struct kernel_siginfo; struct task_struct; -- cgit v1.2.3 From 7f62d40d9cb50fd146fe8ff071f98fa3c1855083 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 9 Feb 2022 08:52:41 -0600 Subject: task_work: Introduce task_work_pending Wrap the test of task->task_works in a helper function to make it clear what is being tested. All of the other readers of task->task_work use READ_ONCE and this is even necessary on current as other processes can update task->task_work. So for consistency I have added READ_ONCE into task_work_pending. Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20220309162454.123006-7-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/task_work.h | 5 +++++ include/linux/tracehook.h | 4 ++-- 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/task_work.h b/include/linux/task_work.h index 5b8a93f288bb..897494b597ba 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -19,6 +19,11 @@ enum task_work_notify_mode { TWA_SIGNAL, }; +static inline bool task_work_pending(struct task_struct *task) +{ + return READ_ONCE(task->task_works); +} + int task_work_add(struct task_struct *task, struct callback_head *twork, enum task_work_notify_mode mode); diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index b77bf4917196..fa834a22e86e 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -90,7 +90,7 @@ static inline void tracehook_notify_resume(struct pt_regs *regs) * hlist_add_head(task->task_works); */ smp_mb__after_atomic(); - if (unlikely(current->task_works)) + if (unlikely(task_work_pending(current))) task_work_run(); #ifdef CONFIG_KEYS_REQUEST_CACHE @@ -115,7 +115,7 @@ static inline void tracehook_notify_signal(void) { clear_thread_flag(TIF_NOTIFY_SIGNAL); smp_mb__after_atomic(); - if (current->task_works) + if (task_work_pending(current)) task_work_run(); } -- cgit v1.2.3 From bcbb7bf6ccde7cb969a5642879832bc84ebf06a3 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 10 Mar 2022 12:59:35 -0700 Subject: io_uring: allow submissions to continue on error By default, io_uring will stop submitting a batch of requests if we run into an error submitting a request. This isn't strictly necessary, as the error result is passed out-of-band via a CQE anyway. And it can be a bit confusing for some applications. Provide a way to setup a ring that will continue submitting on error, when the error CQE has been posted. There's still one case that will break out of submission. If we fail allocating a request, then we'll still return -ENOMEM. We could in theory post a CQE for that condition too even if we never got a request. Leave that for a potential followup. Reported-by: Dylan Yudaken Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 8bd4bfdd9a89..d2be4eb22008 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -101,6 +101,7 @@ enum { #define IORING_SETUP_CLAMP (1U << 4) /* clamp SQ/CQ ring sizes */ #define IORING_SETUP_ATTACH_WQ (1U << 5) /* attach to existing wq */ #define IORING_SETUP_R_DISABLED (1U << 6) /* start with ring disabled */ +#define IORING_SETUP_SUBMIT_ALL (1U << 7) /* continue submit on error */ enum { IORING_OP_NOP, -- cgit v1.2.3 From 3b5d4ddf8fe1f60082513f94bae586ac80188a03 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 9 Mar 2022 01:04:50 -0800 Subject: bpf: net: Remove TC_AT_INGRESS_OFFSET and SKB_MONO_DELIVERY_TIME_OFFSET macro This patch removes the TC_AT_INGRESS_OFFSET and SKB_MONO_DELIVERY_TIME_OFFSET macros. Instead, PKT_VLAN_PRESENT_OFFSET is used because all of them are at the same offset. Comment is added to make it clear that changing the position of tc_at_ingress or mono_delivery_time will require to adjust the defined macros. The earlier discussion can be found here: https://lore.kernel.org/bpf/419d994e-ff61-7c11-0ec7-11fefcb0186e@iogearbox.net/ Signed-off-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20220309090450.3710955-1-kafai@fb.com --- include/linux/skbuff.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2be263184d1e..7b0cb10e70cb 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -960,10 +960,10 @@ struct sk_buff { __u8 csum_complete_sw:1; __u8 csum_level:2; __u8 dst_pending_confirm:1; - __u8 mono_delivery_time:1; + __u8 mono_delivery_time:1; /* See SKB_MONO_DELIVERY_TIME_MASK */ #ifdef CONFIG_NET_CLS_ACT __u8 tc_skip_classify:1; - __u8 tc_at_ingress:1; + __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ #endif #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; @@ -1062,7 +1062,9 @@ struct sk_buff { #endif #define PKT_TYPE_OFFSET offsetof(struct sk_buff, __pkt_type_offset) -/* if you move pkt_vlan_present around you also must adapt these constants */ +/* if you move pkt_vlan_present, tc_at_ingress, or mono_delivery_time + * around, you also must adapt these constants. + */ #ifdef __BIG_ENDIAN_BITFIELD #define PKT_VLAN_PRESENT_BIT 7 #define TC_AT_INGRESS_MASK (1 << 0) @@ -1073,8 +1075,6 @@ struct sk_buff { #define SKB_MONO_DELIVERY_TIME_MASK (1 << 5) #endif #define PKT_VLAN_PRESENT_OFFSET offsetof(struct sk_buff, __pkt_vlan_present_offset) -#define TC_AT_INGRESS_OFFSET offsetof(struct sk_buff, __pkt_vlan_present_offset) -#define SKB_MONO_DELIVERY_TIME_OFFSET offsetof(struct sk_buff, __pkt_vlan_present_offset) #ifdef __KERNEL__ /* -- cgit v1.2.3 From 9bb984f28d5bcb917d35d930fcfb89f90f9449fd Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 9 Mar 2022 01:05:09 -0800 Subject: bpf: Remove BPF_SKB_DELIVERY_TIME_NONE and rename s/delivery_time_/tstamp_/ This patch is to simplify the uapi bpf.h regarding to the tstamp type and use a similar way as the kernel to describe the value stored in __sk_buff->tstamp. My earlier thought was to avoid describing the semantic and clock base for the rcv timestamp until there is more clarity on the use case, so the __sk_buff->delivery_time_type naming instead of __sk_buff->tstamp_type. With some thoughts, it can reuse the UNSPEC naming. This patch first removes BPF_SKB_DELIVERY_TIME_NONE and also rename BPF_SKB_DELIVERY_TIME_UNSPEC to BPF_SKB_TSTAMP_UNSPEC and BPF_SKB_DELIVERY_TIME_MONO to BPF_SKB_TSTAMP_DELIVERY_MONO. The semantic of BPF_SKB_TSTAMP_DELIVERY_MONO is the same: __sk_buff->tstamp has delivery time in mono clock base. BPF_SKB_TSTAMP_UNSPEC means __sk_buff->tstamp has the (rcv) tstamp at ingress and the delivery time at egress. At egress, the clock base could be found from skb->sk->sk_clockid. __sk_buff->tstamp == 0 naturally means NONE, so NONE is not needed. With BPF_SKB_TSTAMP_UNSPEC for the rcv tstamp at ingress, the __sk_buff->delivery_time_type is also renamed to __sk_buff->tstamp_type which was also suggested in the earlier discussion: https://lore.kernel.org/bpf/b181acbe-caf8-502d-4b7b-7d96b9fc5d55@iogearbox.net/ The above will then make __sk_buff->tstamp and __sk_buff->tstamp_type the same as its kernel skb->tstamp and skb->mono_delivery_time counter part. The internal kernel function bpf_skb_convert_dtime_type_read() is then renamed to bpf_skb_convert_tstamp_type_read() and it can be simplified with the BPF_SKB_DELIVERY_TIME_NONE gone. A BPF_ALU32_IMM(BPF_AND) insn is also saved by using BPF_JMP32_IMM(BPF_JSET). The bpf helper bpf_skb_set_delivery_time() is also renamed to bpf_skb_set_tstamp(). The arg name is changed from dtime to tstamp also. It only allows setting tstamp 0 for BPF_SKB_TSTAMP_UNSPEC and it could be relaxed later if there is use case to change mono delivery time to non mono. prog->delivery_time_access is also renamed to prog->tstamp_type_access. Signed-off-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20220309090509.3712315-1-kafai@fb.com --- include/linux/filter.h | 2 +- include/uapi/linux/bpf.h | 40 +++++++++++++++++++++------------------- 2 files changed, 22 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 9bf26307247f..05ed9bd31b45 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -573,7 +573,7 @@ struct bpf_prog { enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ call_get_func_ip:1, /* Do we call get_func_ip() */ - delivery_time_access:1; /* Accessed __sk_buff->delivery_time_type */ + tstamp_type_access:1; /* Accessed __sk_buff->tstamp_type */ enum bpf_prog_type type; /* Type of BPF program */ enum bpf_attach_type expected_attach_type; /* For some prog types */ u32 len; /* Number of filter blocks */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bc23020b638d..d288a0a9f797 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5090,23 +5090,22 @@ union bpf_attr { * 0 on success, or a negative error in case of failure. On error * *dst* buffer is zeroed out. * - * long bpf_skb_set_delivery_time(struct sk_buff *skb, u64 dtime, u32 dtime_type) + * long bpf_skb_set_tstamp(struct sk_buff *skb, u64 tstamp, u32 tstamp_type) * Description - * Set a *dtime* (delivery time) to the __sk_buff->tstamp and also - * change the __sk_buff->delivery_time_type to *dtime_type*. + * Change the __sk_buff->tstamp_type to *tstamp_type* + * and set *tstamp* to the __sk_buff->tstamp together. * - * When setting a delivery time (non zero *dtime*) to - * __sk_buff->tstamp, only BPF_SKB_DELIVERY_TIME_MONO *dtime_type* - * is supported. It is the only delivery_time_type that will be - * kept after bpf_redirect_*(). - * - * If there is no need to change the __sk_buff->delivery_time_type, - * the delivery time can be directly written to __sk_buff->tstamp + * If there is no need to change the __sk_buff->tstamp_type, + * the tstamp value can be directly written to __sk_buff->tstamp * instead. * - * *dtime* 0 and *dtime_type* BPF_SKB_DELIVERY_TIME_NONE - * can be used to clear any delivery time stored in - * __sk_buff->tstamp. + * BPF_SKB_TSTAMP_DELIVERY_MONO is the only tstamp that + * will be kept during bpf_redirect_*(). A non zero + * *tstamp* must be used with the BPF_SKB_TSTAMP_DELIVERY_MONO + * *tstamp_type*. + * + * A BPF_SKB_TSTAMP_UNSPEC *tstamp_type* can only be used + * with a zero *tstamp*. * * Only IPv4 and IPv6 skb->protocol are supported. * @@ -5119,7 +5118,7 @@ union bpf_attr { * Return * 0 on success. * **-EINVAL** for invalid input - * **-EOPNOTSUPP** for unsupported delivery_time_type and protocol + * **-EOPNOTSUPP** for unsupported protocol */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5314,7 +5313,7 @@ union bpf_attr { FN(xdp_load_bytes), \ FN(xdp_store_bytes), \ FN(copy_from_user_task), \ - FN(skb_set_delivery_time), \ + FN(skb_set_tstamp), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5505,9 +5504,12 @@ union { \ } __attribute__((aligned(8))) enum { - BPF_SKB_DELIVERY_TIME_NONE, - BPF_SKB_DELIVERY_TIME_UNSPEC, - BPF_SKB_DELIVERY_TIME_MONO, + BPF_SKB_TSTAMP_UNSPEC, + BPF_SKB_TSTAMP_DELIVERY_MONO, /* tstamp has mono delivery time */ + /* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle, + * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC + * and try to deduce it by ingress, egress or skb->sk->sk_clockid. + */ }; /* user accessible mirror of in-kernel sk_buff. @@ -5550,7 +5552,7 @@ struct __sk_buff { __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); __u32 gso_size; - __u8 delivery_time_type; + __u8 tstamp_type; __u32 :24; /* Padding, future use. */ __u64 hwtstamp; }; -- cgit v1.2.3 From 58617014405ad5c9f94f464444f4972dabb71ca7 Mon Sep 17 00:00:00 2001 From: Hengqi Chen Date: Thu, 10 Mar 2022 23:53:35 +0800 Subject: bpf: Fix comment for helper bpf_current_task_under_cgroup() Fix the descriptions of the return values of helper bpf_current_task_under_cgroup(). Fixes: c6b5fb8690fa ("bpf: add documentation for eBPF helpers (42-50)") Signed-off-by: Hengqi Chen Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20220310155335.1278783-1-hengqi.chen@gmail.com --- include/uapi/linux/bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d288a0a9f797..e9978a916c3e 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2302,8 +2302,8 @@ union bpf_attr { * Return * The return value depends on the result of the test, and can be: * - * * 0, if current task belongs to the cgroup2. - * * 1, if current task does not belong to the cgroup2. + * * 1, if current task belongs to the cgroup2. + * * 0, if current task does not belong to the cgroup2. * * A negative error code, if an error occurred. * * long bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) -- cgit v1.2.3 From 8ba62d37949e248c698c26e0d82d72fda5d33ebf Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 9 Feb 2022 09:51:14 -0600 Subject: task_work: Call tracehook_notify_signal from get_signal on all architectures Always handle TIF_NOTIFY_SIGNAL in get_signal. With commit 35d0b389f3b2 ("task_work: unconditionally run task_work from get_signal()") always calling task_work_run all of the work of tracehook_notify_signal is already happening except clearing TIF_NOTIFY_SIGNAL. Factor clear_notify_signal out of tracehook_notify_signal and use it in get_signal so that get_signal only needs one call of task_work_run. To keep the semantics in sync update xfer_to_guest_mode_work (which does not call get_signal) to call tracehook_notify_signal if either _TIF_SIGPENDING or _TIF_NOTIFY_SIGNAL. Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20220309162454.123006-8-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/entry-common.h | 2 +- include/linux/tracehook.h | 9 +++++++-- 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index 9efbdda61f7a..3537fd25f14e 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -257,7 +257,7 @@ static __always_inline void arch_exit_to_user_mode(void) { } * * Invoked from exit_to_user_mode_loop(). */ -void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal); +void arch_do_signal_or_restart(struct pt_regs *regs); /** * exit_to_user_mode - Fixup state when exiting to user mode diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index fa834a22e86e..b44a7820c468 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -106,6 +106,12 @@ static inline void tracehook_notify_resume(struct pt_regs *regs) rseq_handle_notify_resume(NULL, regs); } +static inline void clear_notify_signal(void) +{ + clear_thread_flag(TIF_NOTIFY_SIGNAL); + smp_mb__after_atomic(); +} + /* * called by exit_to_user_mode_loop() if ti_work & _TIF_NOTIFY_SIGNAL. This * is currently used by TWA_SIGNAL based task_work, which requires breaking @@ -113,8 +119,7 @@ static inline void tracehook_notify_resume(struct pt_regs *regs) */ static inline void tracehook_notify_signal(void) { - clear_thread_flag(TIF_NOTIFY_SIGNAL); - smp_mb__after_atomic(); + clear_notify_signal(); if (task_work_pending(current)) task_work_run(); } -- cgit v1.2.3 From 7c5d8fa6fbb12a3f0eefe8762bfede508e147cb3 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 9 Feb 2022 11:18:54 -0600 Subject: task_work: Decouple TIF_NOTIFY_SIGNAL and task_work There are a small handful of reasons besides pending signals that the kernel might want to break out of interruptible sleeps. The flag TIF_NOTIFY_SIGNAL and the helpers that set and clear TIF_NOTIFY_SIGNAL provide that the infrastructure for breaking out of interruptible sleeps and entering the return to user space slow path for those cases. Expand tracehook_notify_signal inline in it's callers and remove it, which makes clear that TIF_NOTIFY_SIGNAL and task_work are separate concepts. Update the comment on set_notify_signal to more accurately describe it's purpose. Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20220309162454.123006-9-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/tracehook.h | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index b44a7820c468..e5d676e841e3 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -113,19 +113,8 @@ static inline void clear_notify_signal(void) } /* - * called by exit_to_user_mode_loop() if ti_work & _TIF_NOTIFY_SIGNAL. This - * is currently used by TWA_SIGNAL based task_work, which requires breaking - * wait loops to ensure that task_work is noticed and run. - */ -static inline void tracehook_notify_signal(void) -{ - clear_notify_signal(); - if (task_work_pending(current)) - task_work_run(); -} - -/* - * Called when we have work to process from exit_to_user_mode_loop() + * Called to break out of interruptible wait loops, and enter the + * exit_to_user_mode_loop(). */ static inline void set_notify_signal(struct task_struct *task) { -- cgit v1.2.3 From 593febb143d17aa2096cd123c9d62b6981eb1d97 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 9 Feb 2022 11:46:54 -0600 Subject: signal: Move set_notify_signal and clear_notify_signal into sched/signal.h The header tracehook.h is no place for code to live. The functions set_notify_signal and clear_notify_signal are not about signals. They are about interruptions that act like signals. The fundamental signal primitives wind up calling set_notify_signal and clear_notify_signal. Which means they need to be maintained with the signal code. Since set_notify_signal and clear_notify_signal must be maintained with the signal subsystem move them into sched/signal.h and claim them as part of the signal subsystem. Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20220309162454.123006-10-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/sched/signal.h | 17 +++++++++++++++++ include/linux/tracehook.h | 17 ----------------- 2 files changed, 17 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index b6ecb9fc4cd2..3c8b34876744 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -349,6 +349,23 @@ extern void sigqueue_free(struct sigqueue *); extern int send_sigqueue(struct sigqueue *, struct pid *, enum pid_type); extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); +static inline void clear_notify_signal(void) +{ + clear_thread_flag(TIF_NOTIFY_SIGNAL); + smp_mb__after_atomic(); +} + +/* + * Called to break out of interruptible wait loops, and enter the + * exit_to_user_mode_loop(). + */ +static inline void set_notify_signal(struct task_struct *task) +{ + if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && + !wake_up_state(task, TASK_INTERRUPTIBLE)) + kick_process(task); +} + static inline int restart_syscall(void) { set_tsk_thread_flag(current, TIF_SIGPENDING); diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index e5d676e841e3..1b7365aef8da 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -106,21 +106,4 @@ static inline void tracehook_notify_resume(struct pt_regs *regs) rseq_handle_notify_resume(NULL, regs); } -static inline void clear_notify_signal(void) -{ - clear_thread_flag(TIF_NOTIFY_SIGNAL); - smp_mb__after_atomic(); -} - -/* - * Called to break out of interruptible wait loops, and enter the - * exit_to_user_mode_loop(). - */ -static inline void set_notify_signal(struct task_struct *task) -{ - if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && - !wake_up_state(task, TASK_INTERRUPTIBLE)) - kick_process(task); -} - #endif /* */ -- cgit v1.2.3 From d3c51a0c8944e3a5bba458358b4c1f9ae2de0133 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 28 Jan 2022 14:36:58 -0600 Subject: resume_user_mode: Remove #ifdef TIF_NOTIFY_RESUME in set_notify_resume Every architecture defines TIF_NOTIFY_RESUME so remove the unnecessary ifdef. Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20220309162454.123006-11-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/tracehook.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 1b7365aef8da..946404ebe10b 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -63,10 +63,8 @@ struct linux_binprm; */ static inline void set_notify_resume(struct task_struct *task) { -#ifdef TIF_NOTIFY_RESUME if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME)) kick_process(task); -#endif } /** -- cgit v1.2.3 From 03248addadf1a5ef0a03cbcd5ec905b49adb9658 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 9 Feb 2022 12:20:45 -0600 Subject: resume_user_mode: Move to resume_user_mode.h Move set_notify_resume and tracehook_notify_resume into resume_user_mode.h. While doing that rename tracehook_notify_resume to resume_user_mode_work. Update all of the places that included tracehook.h for these functions to include resume_user_mode.h instead. Update all of the callers of tracehook_notify_resume to call resume_user_mode_work. Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20220309162454.123006-12-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/entry-kvm.h | 2 +- include/linux/resume_user_mode.h | 64 ++++++++++++++++++++++++++++++++++++++++ include/linux/tracehook.h | 51 -------------------------------- 3 files changed, 65 insertions(+), 52 deletions(-) create mode 100644 include/linux/resume_user_mode.h (limited to 'include') diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h index 07c878d6e323..6813171afccb 100644 --- a/include/linux/entry-kvm.h +++ b/include/linux/entry-kvm.h @@ -3,7 +3,7 @@ #define __LINUX_ENTRYKVM_H #include -#include +#include #include #include #include diff --git a/include/linux/resume_user_mode.h b/include/linux/resume_user_mode.h new file mode 100644 index 000000000000..285189454449 --- /dev/null +++ b/include/linux/resume_user_mode.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef LINUX_RESUME_USER_MODE_H +#define LINUX_RESUME_USER_MODE_H + +#include +#include +#include +#include + +/** + * set_notify_resume - cause resume_user_mode_work() to be called + * @task: task that will call resume_user_mode_work() + * + * Calling this arranges that @task will call resume_user_mode_work() + * before returning to user mode. If it's already running in user mode, + * it will enter the kernel and call resume_user_mode_work() soon. + * If it's blocked, it will not be woken. + */ +static inline void set_notify_resume(struct task_struct *task) +{ + if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME)) + kick_process(task); +} + + +/** + * resume_user_mode_work - Perform work before returning to user mode + * @regs: user-mode registers of @current task + * + * This is called when %TIF_NOTIFY_RESUME has been set. Now we are + * about to return to user mode, and the user state in @regs can be + * inspected or adjusted. The caller in arch code has cleared + * %TIF_NOTIFY_RESUME before the call. If the flag gets set again + * asynchronously, this will be called again before we return to + * user mode. + * + * Called without locks. + */ +static inline void resume_user_mode_work(struct pt_regs *regs) +{ + clear_thread_flag(TIF_NOTIFY_RESUME); + /* + * This barrier pairs with task_work_add()->set_notify_resume() after + * hlist_add_head(task->task_works); + */ + smp_mb__after_atomic(); + if (unlikely(task_work_pending(current))) + task_work_run(); + +#ifdef CONFIG_KEYS_REQUEST_CACHE + if (unlikely(current->cached_requested_key)) { + key_put(current->cached_requested_key); + current->cached_requested_key = NULL; + } +#endif + + mem_cgroup_handle_over_high(); + blkcg_maybe_throttle_current(); + + rseq_handle_notify_resume(NULL, regs); +} + +#endif /* LINUX_RESUME_USER_MODE_H */ diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 946404ebe10b..9f6b3fd1880a 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -52,56 +52,5 @@ struct linux_binprm; -/** - * set_notify_resume - cause tracehook_notify_resume() to be called - * @task: task that will call tracehook_notify_resume() - * - * Calling this arranges that @task will call tracehook_notify_resume() - * before returning to user mode. If it's already running in user mode, - * it will enter the kernel and call tracehook_notify_resume() soon. - * If it's blocked, it will not be woken. - */ -static inline void set_notify_resume(struct task_struct *task) -{ - if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME)) - kick_process(task); -} - -/** - * tracehook_notify_resume - report when about to return to user mode - * @regs: user-mode registers of @current task - * - * This is called when %TIF_NOTIFY_RESUME has been set. Now we are - * about to return to user mode, and the user state in @regs can be - * inspected or adjusted. The caller in arch code has cleared - * %TIF_NOTIFY_RESUME before the call. If the flag gets set again - * asynchronously, this will be called again before we return to - * user mode. - * - * Called without locks. - */ -static inline void tracehook_notify_resume(struct pt_regs *regs) -{ - clear_thread_flag(TIF_NOTIFY_RESUME); - /* - * This barrier pairs with task_work_add()->set_notify_resume() after - * hlist_add_head(task->task_works); - */ - smp_mb__after_atomic(); - if (unlikely(task_work_pending(current))) - task_work_run(); - -#ifdef CONFIG_KEYS_REQUEST_CACHE - if (unlikely(current->cached_requested_key)) { - key_put(current->cached_requested_key); - current->cached_requested_key = NULL; - } -#endif - - mem_cgroup_handle_over_high(); - blkcg_maybe_throttle_current(); - - rseq_handle_notify_resume(NULL, regs); -} #endif /* */ -- cgit v1.2.3 From 355f841a3f8ca980c9682937a5257d3a1f6fc09d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 9 Feb 2022 12:47:08 -0600 Subject: tracehook: Remove tracehook.h Now that all of the definitions have moved out of tracehook.h into ptrace.h, sched/signal.h, resume_user_mode.h there is nothing left in tracehook.h so remove it. Update the few files that were depending upon tracehook.h to bring in definitions to use the headers they need directly. Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/20220309162454.123006-13-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/tracehook.h | 56 ----------------------------------------------- 1 file changed, 56 deletions(-) delete mode 100644 include/linux/tracehook.h (limited to 'include') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h deleted file mode 100644 index 9f6b3fd1880a..000000000000 --- a/include/linux/tracehook.h +++ /dev/null @@ -1,56 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Tracing hooks - * - * Copyright (C) 2008-2009 Red Hat, Inc. All rights reserved. - * - * This file defines hook entry points called by core code where - * user tracing/debugging support might need to do something. These - * entry points are called tracehook_*(). Each hook declared below - * has a detailed kerneldoc comment giving the context (locking et - * al) from which it is called, and the meaning of its return value. - * - * Each function here typically has only one call site, so it is ok - * to have some nontrivial tracehook_*() inlines. In all cases, the - * fast path when no tracing is enabled should be very short. - * - * The purpose of this file and the tracehook_* layer is to consolidate - * the interface that the kernel core and arch code uses to enable any - * user debugging or tracing facility (such as ptrace). The interfaces - * here are carefully documented so that maintainers of core and arch - * code do not need to think about the implementation details of the - * tracing facilities. Likewise, maintainers of the tracing code do not - * need to understand all the calling core or arch code in detail, just - * documented circumstances of each call, such as locking conditions. - * - * If the calling core code changes so that locking is different, then - * it is ok to change the interface documented here. The maintainer of - * core code changing should notify the maintainers of the tracing code - * that they need to work out the change. - * - * Some tracehook_*() inlines take arguments that the current tracing - * implementations might not necessarily use. These function signatures - * are chosen to pass in all the information that is on hand in the - * caller and might conceivably be relevant to a tracer, so that the - * core code won't have to be updated when tracing adds more features. - * If a call site changes so that some of those parameters are no longer - * already on hand without extra work, then the tracehook_* interface - * can change so there is no make-work burden on the core code. The - * maintainer of core code changing should notify the maintainers of the - * tracing code that they need to work out the change. - */ - -#ifndef _LINUX_TRACEHOOK_H -#define _LINUX_TRACEHOOK_H 1 - -#include -#include -#include -#include -#include -#include -struct linux_binprm; - - - -#endif /* */ -- cgit v1.2.3 From 6853fece628c5a968e4c264d26a4f7750de42199 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Wed, 9 Mar 2022 14:23:02 -0800 Subject: dt-bindings: clk: cleanup comments For spdx, first line /* */ for *.h, change tab to space Replacements devider to divider Comunications to Communications periphrals to peripherals supportted to supported wich to which Documentatoin to Documentation Signed-off-by: Tom Rix Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20220309222302.1114561-1-trix@redhat.com --- include/dt-bindings/clock/alphascale,asm9260.h | 2 +- include/dt-bindings/clock/axis,artpec6-clkctrl.h | 2 +- include/dt-bindings/clock/boston-clock.h | 3 +-- include/dt-bindings/clock/marvell,mmp2.h | 4 ++-- include/dt-bindings/clock/marvell,pxa168.h | 4 ++-- include/dt-bindings/clock/marvell,pxa910.h | 4 ++-- include/dt-bindings/clock/nuvoton,npcm7xx-clock.h | 2 +- include/dt-bindings/clock/stm32fx-clock.h | 4 ++-- include/dt-bindings/clock/stratix10-clock.h | 2 +- 9 files changed, 13 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/clock/alphascale,asm9260.h b/include/dt-bindings/clock/alphascale,asm9260.h index d3871c63308b..f53f8b16883d 100644 --- a/include/dt-bindings/clock/alphascale,asm9260.h +++ b/include/dt-bindings/clock/alphascale,asm9260.h @@ -55,7 +55,7 @@ #define CLKID_AHB_I2S1 45 #define CLKID_AHB_MAC1 46 -/* devider */ +/* divider */ #define CLKID_SYS_CPU 47 #define CLKID_SYS_AHB 48 #define CLKID_SYS_I2S0M 49 diff --git a/include/dt-bindings/clock/axis,artpec6-clkctrl.h b/include/dt-bindings/clock/axis,artpec6-clkctrl.h index b1f4971642e6..14e424a7c08c 100644 --- a/include/dt-bindings/clock/axis,artpec6-clkctrl.h +++ b/include/dt-bindings/clock/axis,artpec6-clkctrl.h @@ -2,7 +2,7 @@ /* * ARTPEC-6 clock controller indexes * - * Copyright 2016 Axis Comunications AB. + * Copyright 2016 Axis Communications AB. */ #ifndef DT_BINDINGS_CLK_ARTPEC6_CLKCTRL_H diff --git a/include/dt-bindings/clock/boston-clock.h b/include/dt-bindings/clock/boston-clock.h index a6f009821137..38140fa87b09 100644 --- a/include/dt-bindings/clock/boston-clock.h +++ b/include/dt-bindings/clock/boston-clock.h @@ -1,7 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2016 Imagination Technologies - * - * SPDX-License-Identifier: GPL-2.0 */ #ifndef __DT_BINDINGS_CLOCK_BOSTON_CLOCK_H__ diff --git a/include/dt-bindings/clock/marvell,mmp2.h b/include/dt-bindings/clock/marvell,mmp2.h index 87f5ad5df72f..f0819d66b230 100644 --- a/include/dt-bindings/clock/marvell,mmp2.h +++ b/include/dt-bindings/clock/marvell,mmp2.h @@ -32,7 +32,7 @@ #define MMP2_CLK_I2S0 31 #define MMP2_CLK_I2S1 32 -/* apb periphrals */ +/* apb peripherals */ #define MMP2_CLK_TWSI0 60 #define MMP2_CLK_TWSI1 61 #define MMP2_CLK_TWSI2 62 @@ -60,7 +60,7 @@ #define MMP3_CLK_THERMAL2 84 #define MMP3_CLK_THERMAL3 85 -/* axi periphrals */ +/* axi peripherals */ #define MMP2_CLK_SDH0 101 #define MMP2_CLK_SDH1 102 #define MMP2_CLK_SDH2 103 diff --git a/include/dt-bindings/clock/marvell,pxa168.h b/include/dt-bindings/clock/marvell,pxa168.h index caf90436b848..db2b41f1b127 100644 --- a/include/dt-bindings/clock/marvell,pxa168.h +++ b/include/dt-bindings/clock/marvell,pxa168.h @@ -23,7 +23,7 @@ #define PXA168_CLK_UART_PLL 27 #define PXA168_CLK_USB_PLL 28 -/* apb periphrals */ +/* apb peripherals */ #define PXA168_CLK_TWSI0 60 #define PXA168_CLK_TWSI1 61 #define PXA168_CLK_TWSI2 62 @@ -45,7 +45,7 @@ #define PXA168_CLK_SSP4 78 #define PXA168_CLK_TIMER 79 -/* axi periphrals */ +/* axi peripherals */ #define PXA168_CLK_DFC 100 #define PXA168_CLK_SDH0 101 #define PXA168_CLK_SDH1 102 diff --git a/include/dt-bindings/clock/marvell,pxa910.h b/include/dt-bindings/clock/marvell,pxa910.h index 7bf46238946e..c9018ab354d0 100644 --- a/include/dt-bindings/clock/marvell,pxa910.h +++ b/include/dt-bindings/clock/marvell,pxa910.h @@ -23,7 +23,7 @@ #define PXA910_CLK_UART_PLL 27 #define PXA910_CLK_USB_PLL 28 -/* apb periphrals */ +/* apb peripherals */ #define PXA910_CLK_TWSI0 60 #define PXA910_CLK_TWSI1 61 #define PXA910_CLK_TWSI2 62 @@ -43,7 +43,7 @@ #define PXA910_CLK_TIMER0 76 #define PXA910_CLK_TIMER1 77 -/* axi periphrals */ +/* axi peripherals */ #define PXA910_CLK_DFC 100 #define PXA910_CLK_SDH0 101 #define PXA910_CLK_SDH1 102 diff --git a/include/dt-bindings/clock/nuvoton,npcm7xx-clock.h b/include/dt-bindings/clock/nuvoton,npcm7xx-clock.h index f21522605b94..3e0a9b68933d 100644 --- a/include/dt-bindings/clock/nuvoton,npcm7xx-clock.h +++ b/include/dt-bindings/clock/nuvoton,npcm7xx-clock.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Nuvoton NPCM7xx Clock Generator binding - * clock binding number for all clocks supportted by nuvoton,npcm7xx-clk + * clock binding number for all clocks supported by nuvoton,npcm7xx-clk * * Copyright (C) 2018 Nuvoton Technologies tali.perry@nuvoton.com * diff --git a/include/dt-bindings/clock/stm32fx-clock.h b/include/dt-bindings/clock/stm32fx-clock.h index 1cc89c548578..e5dad050d518 100644 --- a/include/dt-bindings/clock/stm32fx-clock.h +++ b/include/dt-bindings/clock/stm32fx-clock.h @@ -7,10 +7,10 @@ */ /* - * List of clocks wich are not derived from system clock (SYSCLOCK) + * List of clocks which are not derived from system clock (SYSCLOCK) * * The index of these clocks is the secondary index of DT bindings - * (see Documentatoin/devicetree/bindings/clock/st,stm32-rcc.txt) + * (see Documentation/devicetree/bindings/clock/st,stm32-rcc.txt) * * e.g: ; diff --git a/include/dt-bindings/clock/stratix10-clock.h b/include/dt-bindings/clock/stratix10-clock.h index 08b98e20b7cc..636498f9e08e 100644 --- a/include/dt-bindings/clock/stratix10-clock.h +++ b/include/dt-bindings/clock/stratix10-clock.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2017, Intel Corporation */ -- cgit v1.2.3 From 458dad7cac03add9333be9dac803d63ab9587847 Mon Sep 17 00:00:00 2001 From: Emil Renner Berthing Date: Wed, 26 Jan 2022 18:39:49 +0100 Subject: dt-bindings: clock: Add JH7100 audio clock definitions Add all clock outputs for the StarFive JH7100 audio clock generator. Signed-off-by: Emil Renner Berthing Link: https://lore.kernel.org/r/20220126173953.1016706-4-kernel@esmil.dk Acked-by: Rob Herring Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/starfive-jh7100-audio.h | 41 +++++++++++++++++++++++ 1 file changed, 41 insertions(+) create mode 100644 include/dt-bindings/clock/starfive-jh7100-audio.h (limited to 'include') diff --git a/include/dt-bindings/clock/starfive-jh7100-audio.h b/include/dt-bindings/clock/starfive-jh7100-audio.h new file mode 100644 index 000000000000..fbb4eae6572b --- /dev/null +++ b/include/dt-bindings/clock/starfive-jh7100-audio.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* + * Copyright (C) 2021 Emil Renner Berthing + */ + +#ifndef __DT_BINDINGS_CLOCK_STARFIVE_JH7100_AUDIO_H__ +#define __DT_BINDINGS_CLOCK_STARFIVE_JH7100_AUDIO_H__ + +#define JH7100_AUDCLK_ADC_MCLK 0 +#define JH7100_AUDCLK_I2S1_MCLK 1 +#define JH7100_AUDCLK_I2SADC_APB 2 +#define JH7100_AUDCLK_I2SADC_BCLK 3 +#define JH7100_AUDCLK_I2SADC_BCLK_N 4 +#define JH7100_AUDCLK_I2SADC_LRCLK 5 +#define JH7100_AUDCLK_PDM_APB 6 +#define JH7100_AUDCLK_PDM_MCLK 7 +#define JH7100_AUDCLK_I2SVAD_APB 8 +#define JH7100_AUDCLK_SPDIF 9 +#define JH7100_AUDCLK_SPDIF_APB 10 +#define JH7100_AUDCLK_PWMDAC_APB 11 +#define JH7100_AUDCLK_DAC_MCLK 12 +#define JH7100_AUDCLK_I2SDAC_APB 13 +#define JH7100_AUDCLK_I2SDAC_BCLK 14 +#define JH7100_AUDCLK_I2SDAC_BCLK_N 15 +#define JH7100_AUDCLK_I2SDAC_LRCLK 16 +#define JH7100_AUDCLK_I2S1_APB 17 +#define JH7100_AUDCLK_I2S1_BCLK 18 +#define JH7100_AUDCLK_I2S1_BCLK_N 19 +#define JH7100_AUDCLK_I2S1_LRCLK 20 +#define JH7100_AUDCLK_I2SDAC16K_APB 21 +#define JH7100_AUDCLK_APB0_BUS 22 +#define JH7100_AUDCLK_DMA1P_AHB 23 +#define JH7100_AUDCLK_USB_APB 24 +#define JH7100_AUDCLK_USB_LPM 25 +#define JH7100_AUDCLK_USB_STB 26 +#define JH7100_AUDCLK_APB_EN 27 +#define JH7100_AUDCLK_VAD_MEM 28 + +#define JH7100_AUDCLK_END 29 + +#endif /* __DT_BINDINGS_CLOCK_STARFIVE_JH7100_AUDIO_H__ */ -- cgit v1.2.3 From 174b16946e39ebd369097e0f773536c91a8c1a4c Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Wed, 2 Mar 2022 12:13:58 +0100 Subject: bpf-lsm: Introduce new helper bpf_ima_file_hash() ima_file_hash() has been modified to calculate the measurement of a file on demand, if it has not been already performed by IMA or the measurement is not fresh. For compatibility reasons, ima_inode_hash() remains unchanged. Keep the same approach in eBPF and introduce the new helper bpf_ima_file_hash() to take advantage of the modified behavior of ima_file_hash(). Signed-off-by: Roberto Sassu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220302111404.193900-4-roberto.sassu@huawei.com --- include/uapi/linux/bpf.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e9978a916c3e..99fab54ae9c0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5119,6 +5119,16 @@ union bpf_attr { * 0 on success. * **-EINVAL** for invalid input * **-EOPNOTSUPP** for unsupported protocol + * + * long bpf_ima_file_hash(struct file *file, void *dst, u32 size) + * Description + * Returns a calculated IMA hash of the *file*. + * If the hash is larger than *size*, then only *size* + * bytes will be copied to *dst* + * Return + * The **hash_algo** is returned on success, + * **-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if + * invalid arguments are passed. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5314,6 +5324,7 @@ union bpf_attr { FN(xdp_store_bytes), \ FN(copy_from_user_task), \ FN(skb_set_tstamp), \ + FN(ima_file_hash), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 6789ab9668d920d7be636cb994d85be9a816f9d5 Mon Sep 17 00:00:00 2001 From: Hao Luo Date: Thu, 10 Mar 2022 13:16:55 -0800 Subject: compiler_types: Refactor the use of btf_type_tag attribute. Previous patches have introduced the compiler attribute btf_type_tag for __user and __percpu. The availability of this attribute depends on some CONFIGs and compiler support. This patch refactors the use of btf_type_tag by introducing BTF_TYPE_TAG, which hides all the dependencies. No functional change. Suggested-by: Andrii Nakryiko Signed-off-by: Hao Luo Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20220310211655.3173786-1-haoluo@google.com --- include/linux/compiler_types.h | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index b9a8ae9440c7..1bc760ba400c 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -4,6 +4,13 @@ #ifndef __ASSEMBLY__ +#if defined(CONFIG_DEBUG_INFO_BTF) && defined(CONFIG_PAHOLE_HAS_BTF_TAG) && \ + __has_attribute(btf_type_tag) +# define BTF_TYPE_TAG(value) __attribute__((btf_type_tag(#value))) +#else +# define BTF_TYPE_TAG(value) /* nothing */ +#endif + #ifdef __CHECKER__ /* address spaces */ # define __kernel __attribute__((address_space(0))) @@ -31,19 +38,11 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } # define __kernel # ifdef STRUCTLEAK_PLUGIN # define __user __attribute__((user)) -# elif defined(CONFIG_DEBUG_INFO_BTF) && defined(CONFIG_PAHOLE_HAS_BTF_TAG) && \ - __has_attribute(btf_type_tag) -# define __user __attribute__((btf_type_tag("user"))) # else -# define __user +# define __user BTF_TYPE_TAG(user) # endif # define __iomem -# if defined(CONFIG_DEBUG_INFO_BTF) && defined(CONFIG_PAHOLE_HAS_BTF_TAG) && \ - __has_attribute(btf_type_tag) -# define __percpu __attribute__((btf_type_tag("percpu"))) -# else -# define __percpu -# endif +# define __percpu BTF_TYPE_TAG(percpu) # define __rcu # define __chk_user_ptr(x) (void)0 # define __chk_io_ptr(x) (void)0 -- cgit v1.2.3 From 1926407a4ab0e59d5a27bed7b82029b356d80fa0 Mon Sep 17 00:00:00 2001 From: Ilya Maximets Date: Wed, 9 Mar 2022 23:20:33 +0100 Subject: net: openvswitch: fix uAPI incompatibility with existing user space Few years ago OVS user space made a strange choice in the commit [1] to define types only valid for the user space inside the copy of a kernel uAPI header. '#ifndef __KERNEL__' and another attribute was added later. This leads to the inevitable clash between user space and kernel types when the kernel uAPI is extended. The issue was unveiled with the addition of a new type for IPv6 extension header in kernel uAPI. When kernel provides the OVS_KEY_ATTR_IPV6_EXTHDRS attribute to the older user space application, application tries to parse it as OVS_KEY_ATTR_PACKET_TYPE and discards the whole netlink message as malformed. Since OVS_KEY_ATTR_IPV6_EXTHDRS is supplied along with every IPv6 packet that goes to the user space, IPv6 support is fully broken. Fixing that by bringing these user space attributes to the kernel uAPI to avoid the clash. Strictly speaking this is not the problem of the kernel uAPI, but changing it is the only way to avoid breakage of the older user space applications at this point. These 2 types are explicitly rejected now since they should not be passed to the kernel. Additionally, OVS_KEY_ATTR_TUNNEL_INFO moved out from the '#ifdef __KERNEL__' as there is no good reason to hide it from the userspace. And it's also explicitly rejected now, because it's for in-kernel use only. Comments with warnings were added to avoid the problem coming back. (1 << type) converted to (1ULL << type) to avoid integer overflow on OVS_KEY_ATTR_IPV6_EXTHDRS, since it equals 32 now. [1] beb75a40fdc2 ("userspace: Switching of L3 packets in L2 pipeline") Fixes: 28a3f0601727 ("net: openvswitch: IPv6: Add IPv6 extension header support") Link: https://lore.kernel.org/netdev/3adf00c7-fe65-3ef4-b6d7-6d8a0cad8a5f@nvidia.com Link: https://github.com/openvswitch/ovs/commit/beb75a40fdc295bfd6521b0068b4cd12f6de507c Reported-by: Roi Dayan Signed-off-by: Ilya Maximets Acked-by: Nicolas Dichtel Acked-by: Aaron Conole Link: https://lore.kernel.org/r/20220309222033.3018976-1-i.maximets@ovn.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/openvswitch.h | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 9d1710f20505..ce3e1738d427 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -351,11 +351,21 @@ enum ovs_key_attr { OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4, /* struct ovs_key_ct_tuple_ipv4 */ OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6, /* struct ovs_key_ct_tuple_ipv6 */ OVS_KEY_ATTR_NSH, /* Nested set of ovs_nsh_key_* */ - OVS_KEY_ATTR_IPV6_EXTHDRS, /* struct ovs_key_ipv6_exthdr */ -#ifdef __KERNEL__ - OVS_KEY_ATTR_TUNNEL_INFO, /* struct ip_tunnel_info */ -#endif + /* User space decided to squat on types 29 and 30. They are defined + * below, but should not be sent to the kernel. + * + * WARNING: No new types should be added unless they are defined + * for both kernel and user space (no 'ifdef's). It's hard + * to keep compatibility otherwise. + */ + OVS_KEY_ATTR_PACKET_TYPE, /* be32 packet type */ + OVS_KEY_ATTR_ND_EXTENSIONS, /* IPv6 Neighbor Discovery extensions */ + + OVS_KEY_ATTR_TUNNEL_INFO, /* struct ip_tunnel_info. + * For in-kernel use only. + */ + OVS_KEY_ATTR_IPV6_EXTHDRS, /* struct ovs_key_ipv6_exthdr */ __OVS_KEY_ATTR_MAX }; -- cgit v1.2.3 From 271907ee2f29cd1078fd219f0778fd824fb1971c Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Mon, 17 Jan 2022 15:14:44 +0200 Subject: net/mlx5: Query the maximum MCIA register read size from firmware The MCIA register supports either 12 or 32 dwords, use the correct value by querying the capability from the MCAM register. Signed-off-by: Gal Pressman Reviewed-by: Maxim Mikityanskiy Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 4 +++- include/linux/mlx5/port.h | 1 - 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 318fae4b3560..745107ff681d 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -9691,7 +9691,9 @@ struct mlx5_ifc_pcam_reg_bits { }; struct mlx5_ifc_mcam_enhanced_features_bits { - u8 reserved_at_0[0x6a]; + u8 reserved_at_0[0x5d]; + u8 mcia_32dwords[0x1]; + u8 reserved_at_5e[0xc]; u8 reset_state[0x1]; u8 ptpcyc2realtime_modify[0x1]; u8 reserved_at_6c[0x2]; diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 77ea4f9c5265..402413b3e914 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -56,7 +56,6 @@ enum mlx5_an_status { MLX5_AN_LINK_DOWN = 4, }; -#define MLX5_EEPROM_MAX_BYTES 32 #define MLX5_EEPROM_IDENTIFIER_BYTE_MASK 0x000000ff #define MLX5_I2C_ADDR_LOW 0x50 #define MLX5_I2C_ADDR_HIGH 0x51 -- cgit v1.2.3 From fcb610a86c53dfcfbb2aa62e704481112752f367 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Mon, 17 Jan 2022 15:53:06 +0200 Subject: net/mlx5: Parse module mapping using mlx5_ifc The assumption that the first byte in the module mapping dword is the module number shouldn't be hard-coded in the driver, but come from mlx5_ifc structs. While at it, fix the incorrect width for the 'rx_lane' and 'tx_lane' fields. Signed-off-by: Gal Pressman Reviewed-by: Maxim Mikityanskiy Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 8 ++++---- include/linux/mlx5/port.h | 1 - 2 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 745107ff681d..91b7f730ed91 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -9888,10 +9888,10 @@ struct mlx5_ifc_pcmr_reg_bits { }; struct mlx5_ifc_lane_2_module_mapping_bits { - u8 reserved_at_0[0x6]; - u8 rx_lane[0x2]; - u8 reserved_at_8[0x6]; - u8 tx_lane[0x2]; + u8 reserved_at_0[0x4]; + u8 rx_lane[0x4]; + u8 reserved_at_8[0x4]; + u8 tx_lane[0x4]; u8 reserved_at_10[0x8]; u8 module[0x8]; }; diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 402413b3e914..28a928b0684b 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -56,7 +56,6 @@ enum mlx5_an_status { MLX5_AN_LINK_DOWN = 4, }; -#define MLX5_EEPROM_IDENTIFIER_BYTE_MASK 0x000000ff #define MLX5_I2C_ADDR_LOW 0x50 #define MLX5_I2C_ADDR_HIGH 0x51 #define MLX5_EEPROM_PAGE_LENGTH 256 -- cgit v1.2.3 From 286f950545e0d9c8aa802cbfc9676860bbc49179 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Wed, 16 Feb 2022 15:21:58 +0530 Subject: coresight: Drop unused 'none' enum value for each component CORESIGHT_DEV_TYPE_NONE/CORESIGHT_DEV_SUBTYPE_XXXX_NONE values are not used any where. Actual enumeration can start from 0. Just drop these unused enum values. Cc: Mathieu Poirier Cc: Suzuki K Poulose Cc: Mike Leach Cc: Leo Yan Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Anshuman Khandual Link: https://lore.kernel.org/r/1645005118-10561-1-git-send-email-anshuman.khandual@arm.com Signed-off-by: Mathieu Poirier Signed-off-by: Suzuki K Poulose --- include/linux/coresight.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 93a2922b7653..9f445f09fcfe 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -36,7 +36,6 @@ extern struct bus_type coresight_bustype; enum coresight_dev_type { - CORESIGHT_DEV_TYPE_NONE, CORESIGHT_DEV_TYPE_SINK, CORESIGHT_DEV_TYPE_LINK, CORESIGHT_DEV_TYPE_LINKSINK, @@ -46,7 +45,6 @@ enum coresight_dev_type { }; enum coresight_dev_subtype_sink { - CORESIGHT_DEV_SUBTYPE_SINK_NONE, CORESIGHT_DEV_SUBTYPE_SINK_PORT, CORESIGHT_DEV_SUBTYPE_SINK_BUFFER, CORESIGHT_DEV_SUBTYPE_SINK_SYSMEM, @@ -54,21 +52,18 @@ enum coresight_dev_subtype_sink { }; enum coresight_dev_subtype_link { - CORESIGHT_DEV_SUBTYPE_LINK_NONE, CORESIGHT_DEV_SUBTYPE_LINK_MERG, CORESIGHT_DEV_SUBTYPE_LINK_SPLIT, CORESIGHT_DEV_SUBTYPE_LINK_FIFO, }; enum coresight_dev_subtype_source { - CORESIGHT_DEV_SUBTYPE_SOURCE_NONE, CORESIGHT_DEV_SUBTYPE_SOURCE_PROC, CORESIGHT_DEV_SUBTYPE_SOURCE_BUS, CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE, }; enum coresight_dev_subtype_helper { - CORESIGHT_DEV_SUBTYPE_HELPER_NONE, CORESIGHT_DEV_SUBTYPE_HELPER_CATU, }; -- cgit v1.2.3 From 2916b7a9c7c25ecf9be2f37e567a277e861f8e3f Mon Sep 17 00:00:00 2001 From: Veerendranath Jakkam Date: Tue, 22 Feb 2022 20:36:39 +0530 Subject: nl80211: fix typo of NL80211_IF_TYPE_OCB in documentation It should be NL80211_IFTYPE_OCB instead. Signed-off-by: Veerendranath Jakkam Link: https://lore.kernel.org/r/1645542399-4680-1-git-send-email-quic_vjakkam@quicinc.com Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 98ed52663d6b..0568a79097b8 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3259,7 +3259,7 @@ enum nl80211_attrs { * and therefore can't be created in the normal ways, use the * %NL80211_CMD_START_P2P_DEVICE and %NL80211_CMD_STOP_P2P_DEVICE * commands to create and destroy one - * @NL80211_IF_TYPE_OCB: Outside Context of a BSS + * @NL80211_IFTYPE_OCB: Outside Context of a BSS * This mode corresponds to the MIB variable dot11OCBActivated=true * @NL80211_IFTYPE_NAN: NAN device interface type (not a netdev) * @NL80211_IFTYPE_MAX: highest interface type number currently defined -- cgit v1.2.3 From 3af722cb735d212554027ec81e2aa2e6bf1ee34d Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 8 Mar 2022 17:12:10 +0100 Subject: powerpc/net: Implement powerpc specific csum_shift() to remove branch Today's implementation of csum_shift() leads to branching based on parity of 'offset' 000002f8 : 2f8: 70 a5 00 01 andi. r5,r5,1 2fc: 41 a2 00 08 beq 304 300: 54 84 c0 3e rotlwi r4,r4,24 304: 7c 63 20 14 addc r3,r3,r4 308: 7c 63 01 94 addze r3,r3 30c: 4e 80 00 20 blr Use first bit of 'offset' directly as input of the rotation instead of branching. 000002f8 : 2f8: 54 a5 1f 38 rlwinm r5,r5,3,28,28 2fc: 20 a5 00 20 subfic r5,r5,32 300: 5c 84 28 3e rotlw r4,r4,r5 304: 7c 63 20 14 addc r3,r3,r4 308: 7c 63 01 94 addze r3,r3 30c: 4e 80 00 20 blr And change to left shift instead of right shift to skip one more instruction. This has no impact on the final sum. 000002f8 : 2f8: 54 a5 1f 38 rlwinm r5,r5,3,28,28 2fc: 5c 84 28 3e rotlw r4,r4,r5 300: 7c 63 20 14 addc r3,r3,r4 304: 7c 63 01 94 addze r3,r3 308: 4e 80 00 20 blr Seems like only powerpc benefits from a branchless implementation. Other main architectures like ARM or X86 get better code with the generic implementation and its branch. Signed-off-by: Christophe Leroy Signed-off-by: David S. Miller --- include/net/checksum.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/checksum.h b/include/net/checksum.h index 79c67f14c448..6bc783b7a06c 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -80,6 +80,7 @@ static __always_inline __sum16 csum16_sub(__sum16 csum, __be16 addend) return csum16_add(csum, ~addend); } +#ifndef HAVE_ARCH_CSUM_SHIFT static __always_inline __wsum csum_shift(__wsum sum, int offset) { /* rotate sum to align it with a 16b boundary */ @@ -87,6 +88,7 @@ static __always_inline __wsum csum_shift(__wsum sum, int offset) return (__force __wsum)ror32((__force u32)sum, 8); return sum; } +#endif static __always_inline __wsum csum_block_add(__wsum csum, __wsum csum2, int offset) -- cgit v1.2.3 From 7d352ccf1e9935b5222ca84e8baeb07a0c8f94b9 Mon Sep 17 00:00:00 2001 From: Youghandhar Chintala Date: Tue, 8 Mar 2022 17:23:24 +0530 Subject: mac80211: Add support to trigger sta disconnect on hardware restart Currently in case of target hardware restart, we just reconfig and re-enable the security keys and enable the network queues to start data traffic back from where it was interrupted. Many ath10k wifi chipsets have sequence numbers for the data packets assigned by firmware and the mac sequence number will restart from zero after target hardware restart leading to mismatch in the sequence number expected by the remote peer vs the sequence number of the frame sent by the target firmware. This mismatch in sequence number will cause out-of-order packets on the remote peer and all the frames sent by the device are dropped until we reach the sequence number which was sent before we restarted the target hardware In order to fix this, we trigger a sta disconnect, in case of target hw restart. After this there will be a fresh connection and thereby avoiding the dropping of frames by remote peer. The right fix would be to pull the entire data path into the host which is not feasible or would need lots of complex changes and will still be inefficient. Tested on ath10k using WCN3990, QCA6174 Signed-off-by: Youghandhar Chintala Link: https://lore.kernel.org/r/20220308115325.5246-2-youghand@codeaurora.org Signed-off-by: Johannes Berg --- include/net/mac80211.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index f118b8fe667a..b8e8c82b53aa 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -6070,6 +6070,16 @@ void ieee80211_disconnect(struct ieee80211_vif *vif, bool reconnect); */ void ieee80211_resume_disconnect(struct ieee80211_vif *vif); +/** + * ieee80211_hw_restart_disconnect - disconnect from AP after + * hardware restart + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * + * Instructs mac80211 to disconnect from the AP after + * hardware restart. + */ +void ieee80211_hw_restart_disconnect(struct ieee80211_vif *vif); + /** * ieee80211_cqm_rssi_notify - inform a configured connection quality monitoring * rssi threshold triggered -- cgit v1.2.3 From c19bd02e9029f0f75b58f4b8662527da74be8985 Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Fri, 11 Mar 2022 16:35:28 +0100 Subject: ALSA: hda: Add helper macros for DSP capable devices HDAudio drivers make heavy use of I/O operations. Declare a range of update, read and write helpers similar to those available for HDAudio legacy driver. These macros are used by AVS driver to improve code readability. Signed-off-by: Cezary Rojewski Acked-by: Takashi Iwai Link: https://lore.kernel.org/r/20220311153544.136854-2-cezary.rojewski@intel.com Signed-off-by: Mark Brown --- include/sound/hdaudio.h | 3 +++ include/sound/hdaudio_ext.h | 50 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 53 insertions(+) (limited to 'include') diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index 6a90ce405e60..15f15075238d 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -448,6 +449,8 @@ static inline u16 snd_hdac_reg_readw(struct hdac_bus *bus, void __iomem *addr) #define snd_hdac_reg_writel(bus, addr, val) writel(val, addr) #define snd_hdac_reg_readl(bus, addr) readl(addr) +#define snd_hdac_reg_writeq(bus, addr, val) writeq(val, addr) +#define snd_hdac_reg_readq(bus, addr) readq(addr) /* * macros for easy use diff --git a/include/sound/hdaudio_ext.h b/include/sound/hdaudio_ext.h index 77123c3e4095..5a538799ff77 100644 --- a/include/sound/hdaudio_ext.h +++ b/include/sound/hdaudio_ext.h @@ -2,6 +2,8 @@ #ifndef __SOUND_HDAUDIO_EXT_H #define __SOUND_HDAUDIO_EXT_H +#include +#include #include int snd_hdac_ext_bus_init(struct hdac_bus *bus, struct device *dev, @@ -143,6 +145,54 @@ void snd_hdac_ext_bus_link_power(struct hdac_device *codec, bool enable); writew(((readw(addr + reg) & ~(mask)) | (val)), \ addr + reg) +#define snd_hdac_adsp_writeb(chip, reg, value) \ + snd_hdac_reg_writeb(chip, (chip)->dsp_ba + (reg), value) +#define snd_hdac_adsp_readb(chip, reg) \ + snd_hdac_reg_readb(chip, (chip)->dsp_ba + (reg)) +#define snd_hdac_adsp_writew(chip, reg, value) \ + snd_hdac_reg_writew(chip, (chip)->dsp_ba + (reg), value) +#define snd_hdac_adsp_readw(chip, reg) \ + snd_hdac_reg_readw(chip, (chip)->dsp_ba + (reg)) +#define snd_hdac_adsp_writel(chip, reg, value) \ + snd_hdac_reg_writel(chip, (chip)->dsp_ba + (reg), value) +#define snd_hdac_adsp_readl(chip, reg) \ + snd_hdac_reg_readl(chip, (chip)->dsp_ba + (reg)) +#define snd_hdac_adsp_writeq(chip, reg, value) \ + snd_hdac_reg_writeq(chip, (chip)->dsp_ba + (reg), value) +#define snd_hdac_adsp_readq(chip, reg) \ + snd_hdac_reg_readq(chip, (chip)->dsp_ba + (reg)) + +#define snd_hdac_adsp_updateb(chip, reg, mask, val) \ + snd_hdac_adsp_writeb(chip, reg, \ + (snd_hdac_adsp_readb(chip, reg) & ~(mask)) | (val)) +#define snd_hdac_adsp_updatew(chip, reg, mask, val) \ + snd_hdac_adsp_writew(chip, reg, \ + (snd_hdac_adsp_readw(chip, reg) & ~(mask)) | (val)) +#define snd_hdac_adsp_updatel(chip, reg, mask, val) \ + snd_hdac_adsp_writel(chip, reg, \ + (snd_hdac_adsp_readl(chip, reg) & ~(mask)) | (val)) +#define snd_hdac_adsp_updateq(chip, reg, mask, val) \ + snd_hdac_adsp_writeq(chip, reg, \ + (snd_hdac_adsp_readq(chip, reg) & ~(mask)) | (val)) + +#define snd_hdac_adsp_readb_poll(chip, reg, val, cond, delay_us, timeout_us) \ + readb_poll_timeout((chip)->dsp_ba + (reg), val, cond, \ + delay_us, timeout_us) +#define snd_hdac_adsp_readw_poll(chip, reg, val, cond, delay_us, timeout_us) \ + readw_poll_timeout((chip)->dsp_ba + (reg), val, cond, \ + delay_us, timeout_us) +#define snd_hdac_adsp_readl_poll(chip, reg, val, cond, delay_us, timeout_us) \ + readl_poll_timeout((chip)->dsp_ba + (reg), val, cond, \ + delay_us, timeout_us) +#define snd_hdac_adsp_readq_poll(chip, reg, val, cond, delay_us, timeout_us) \ + readq_poll_timeout((chip)->dsp_ba + (reg), val, cond, \ + delay_us, timeout_us) +#define snd_hdac_stream_readb_poll(strm, reg, val, cond, delay_us, timeout_us) \ + readb_poll_timeout((strm)->sd_addr + AZX_REG_ ## reg, val, cond, \ + delay_us, timeout_us) +#define snd_hdac_stream_readl_poll(strm, reg, val, cond, delay_us, timeout_us) \ + readl_poll_timeout((strm)->sd_addr + AZX_REG_ ## reg, val, cond, \ + delay_us, timeout_us) struct hdac_ext_device; -- cgit v1.2.3 From da0398099a83483014adc509a2845c88ccf672af Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Fri, 11 Mar 2022 16:35:29 +0100 Subject: ASoC: Export DAI register and widget ctor and dctor functions To allow for more flexibility i.e. populating component DAIs dynamically during its initialization, without being limited to topology loading procedure, expose snd_soc_register(), snd_soc_dapm_new_dai_widgets() and snd_soc_dapm_free_widget() functions. Allows users to first check available resources e.g. number of PCMs supported by HDAudio codec before allocating the number of DAPM widgets needed. This prevents superfluous objects from being created or allows driver to adjust to situation when resources are limited. Signed-off-by: Cezary Rojewski Link: https://lore.kernel.org/r/20220311153544.136854-3-cezary.rojewski@intel.com Signed-off-by: Mark Brown --- include/sound/soc-dapm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h index c3039e97929a..ebb8e7a7fc29 100644 --- a/include/sound/soc-dapm.h +++ b/include/sound/soc-dapm.h @@ -429,6 +429,7 @@ struct snd_soc_dapm_widget *snd_soc_dapm_new_control_unlocked( const struct snd_soc_dapm_widget *widget); int snd_soc_dapm_new_dai_widgets(struct snd_soc_dapm_context *dapm, struct snd_soc_dai *dai); +void snd_soc_dapm_free_widget(struct snd_soc_dapm_widget *w); int snd_soc_dapm_link_dai_widgets(struct snd_soc_card *card); void snd_soc_dapm_connect_dai_link_widgets(struct snd_soc_card *card); -- cgit v1.2.3 From b20dc3c684580ddc07eb48ee3c3dc7597cd5eebf Mon Sep 17 00:00:00 2001 From: Wojciech Drewek Date: Fri, 4 Mar 2022 17:40:42 +0100 Subject: gtp: Allow to create GTP device without FDs Currently, when the user wants to create GTP device, he has to provide file handles to the sockets created in userspace (IFLA_GTP_FD0, IFLA_GTP_FD1). This behaviour is not ideal, considering the option of adding support for GTP device creation through ip link. Ip link application is not a good place to create such sockets. This patch allows to create GTP device without providing IFLA_GTP_FD0 and IFLA_GTP_FD1 arguments. If the user sets IFLA_GTP_CREATE_SOCKETS attribute, then GTP module takes care of creating UDP sockets by itself. Sockets are created with the commonly known UDP ports used for GTP protocol (GTP0_PORT and GTP1U_PORT). In this case we don't have to provide encap_destroy because no extra deinitialization is needed, everything is covered by udp_tunnel_sock_release. Note: GTP instance created with only this change applied, does not handle GTP Echo Requests. This is implemented in the following patch. Signed-off-by: Wojciech Drewek Signed-off-by: Tony Nguyen --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index ddca20357e7e..ebd2aa3ef809 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -887,6 +887,7 @@ enum { IFLA_GTP_FD1, IFLA_GTP_PDP_HASHSIZE, IFLA_GTP_ROLE, + IFLA_GTP_CREATE_SOCKETS, __IFLA_GTP_MAX, }; #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) -- cgit v1.2.3 From 9af41cc33471ea1efa6f77e188f055cc77d0a5c5 Mon Sep 17 00:00:00 2001 From: Wojciech Drewek Date: Fri, 4 Mar 2022 17:40:43 +0100 Subject: gtp: Implement GTP echo response Adding GTP device through ip link creates the situation where there is no userspace daemon which would handle GTP messages (Echo Request for example). GTP-U instance which would not respond to echo requests would violate GTP specification. When GTP packet arrives with GTP_ECHO_REQ message type, GTP_ECHO_RSP is send to the sender. GTP_ECHO_RSP message should contain information element with GTPIE_RECOVERY tag and restart counter value. For GTPv1 restart counter is not used and should be equal to 0, for GTPv0 restart counter contains information provided from userspace(IFLA_GTP_RESTART_COUNT). Signed-off-by: Wojciech Drewek Suggested-by: Harald Welte Reviewed-by: Harald Welte Tested-by: Harald Welte Signed-off-by: Tony Nguyen --- include/net/gtp.h | 31 +++++++++++++++++++++++++++++++ include/uapi/linux/if_link.h | 1 + 2 files changed, 32 insertions(+) (limited to 'include') diff --git a/include/net/gtp.h b/include/net/gtp.h index 0e16ebb2a82d..0e12c37f2958 100644 --- a/include/net/gtp.h +++ b/include/net/gtp.h @@ -7,8 +7,13 @@ #define GTP0_PORT 3386 #define GTP1U_PORT 2152 +/* GTP messages types */ +#define GTP_ECHO_REQ 1 /* Echo Request */ +#define GTP_ECHO_RSP 2 /* Echo Response */ #define GTP_TPDU 255 +#define GTPIE_RECOVERY 14 + struct gtp0_header { /* According to GSM TS 09.60. */ __u8 flags; __u8 type; @@ -27,6 +32,32 @@ struct gtp1_header { /* According to 3GPP TS 29.060. */ __be32 tid; } __attribute__ ((packed)); +struct gtp1_header_long { /* According to 3GPP TS 29.060. */ + __u8 flags; + __u8 type; + __be16 length; + __be32 tid; + __be16 seq; + __u8 npdu; + __u8 next; +} __packed; + +/* GTP Information Element */ +struct gtp_ie { + __u8 tag; + __u8 val; +} __packed; + +struct gtp0_packet { + struct gtp0_header gtp0_h; + struct gtp_ie ie; +} __packed; + +struct gtp1u_packet { + struct gtp1_header_long gtp1u_h; + struct gtp_ie ie; +} __packed; + #define GTP1_F_NPDU 0x01 #define GTP1_F_SEQ 0x02 #define GTP1_F_EXTHDR 0x04 diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index ebd2aa3ef809..bd24c7dc10a2 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -888,6 +888,7 @@ enum { IFLA_GTP_PDP_HASHSIZE, IFLA_GTP_ROLE, IFLA_GTP_CREATE_SOCKETS, + IFLA_GTP_RESTART_COUNT, __IFLA_GTP_MAX, }; #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) -- cgit v1.2.3 From d33bd757d362699cfce3c68b53cd12b947d196f4 Mon Sep 17 00:00:00 2001 From: Wojciech Drewek Date: Fri, 4 Mar 2022 17:40:44 +0100 Subject: gtp: Implement GTP echo request Adding GTP device through ip link creates the situation where GTP instance is not able to send GTP echo requests. Echo requests are used to check if GTP peer is still alive. With this patch, gtp_genl_ops are extended by new cmd (GTP_CMD_ECHOREQ) which allows to send echo request in the given version of GTP protocol (v0 or v1), from the given ms address to he given peer. TID is not inclued because in all path management messages it should be equal to 0. When GTP echo response is detected, multicast message is send to everyone in the gtp_genl_family. Message contains GTP version, ms address and peer address. Suggested-by: Harald Welte Signed-off-by: Wojciech Drewek Reviewed-by: Harald Welte Signed-off-by: Tony Nguyen --- include/uapi/linux/gtp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h index 79f9191bbb24..2f61298a7b77 100644 --- a/include/uapi/linux/gtp.h +++ b/include/uapi/linux/gtp.h @@ -8,6 +8,7 @@ enum gtp_genl_cmds { GTP_CMD_NEWPDP, GTP_CMD_DELPDP, GTP_CMD_GETPDP, + GTP_CMD_ECHOREQ, GTP_CMD_MAX, }; -- cgit v1.2.3 From e3acda7ade0a36c5cbebc2b54d30b7f08a4ba29b Mon Sep 17 00:00:00 2001 From: Wojciech Drewek Date: Fri, 4 Mar 2022 17:40:45 +0100 Subject: net/sched: Allow flower to match on GTP options Options are as follows: PDU_TYPE:QFI and they refernce to the fields from the PDU Session Protocol. PDU Session data is conveyed in GTP-U Extension Header. GTP-U Extension Header is described in 3GPP TS 29.281. PDU Session Protocol is described in 3GPP TS 38.415. PDU_TYPE - indicates the type of the PDU Session Information (4 bits) QFI - QoS Flow Identifier (6 bits) # ip link add gtp_dev type gtp role sgsn # tc qdisc add dev gtp_dev ingress # tc filter add dev gtp_dev protocol ip parent ffff: \ flower \ enc_key_id 11 \ gtp_opts 1:8/ff:ff \ action mirred egress redirect dev eth0 Signed-off-by: Wojciech Drewek Signed-off-by: Tony Nguyen --- include/net/gtp.h | 5 +++++ include/uapi/linux/if_tunnel.h | 4 +++- include/uapi/linux/pkt_cls.h | 15 +++++++++++++++ 3 files changed, 23 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/gtp.h b/include/net/gtp.h index 0e12c37f2958..23c2aaae8a42 100644 --- a/include/net/gtp.h +++ b/include/net/gtp.h @@ -58,6 +58,11 @@ struct gtp1u_packet { struct gtp_ie ie; } __packed; +struct gtp_pdu_session_info { /* According to 3GPP TS 38.415. */ + u8 pdu_type; + u8 qfi; +}; + #define GTP1_F_NPDU 0x01 #define GTP1_F_SEQ 0x02 #define GTP1_F_EXTHDR 0x04 diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 7d9105533c7b..102119628ff5 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -176,8 +176,10 @@ enum { #define TUNNEL_VXLAN_OPT __cpu_to_be16(0x1000) #define TUNNEL_NOCACHE __cpu_to_be16(0x2000) #define TUNNEL_ERSPAN_OPT __cpu_to_be16(0x4000) +#define TUNNEL_GTP_OPT __cpu_to_be16(0x8000) #define TUNNEL_OPTIONS_PRESENT \ - (TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT | TUNNEL_ERSPAN_OPT) + (TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT | TUNNEL_ERSPAN_OPT | \ + TUNNEL_GTP_OPT) #endif /* _UAPI_IF_TUNNEL_H_ */ diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index ee38b35c3f57..404f97fb239c 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -616,6 +616,10 @@ enum { * TCA_FLOWER_KEY_ENC_OPT_ERSPAN_ * attributes */ + TCA_FLOWER_KEY_ENC_OPTS_GTP, /* Nested + * TCA_FLOWER_KEY_ENC_OPT_GTP_ + * attributes + */ __TCA_FLOWER_KEY_ENC_OPTS_MAX, }; @@ -654,6 +658,17 @@ enum { #define TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX \ (__TCA_FLOWER_KEY_ENC_OPT_ERSPAN_MAX - 1) +enum { + TCA_FLOWER_KEY_ENC_OPT_GTP_UNSPEC, + TCA_FLOWER_KEY_ENC_OPT_GTP_PDU_TYPE, /* u8 */ + TCA_FLOWER_KEY_ENC_OPT_GTP_QFI, /* u8 */ + + __TCA_FLOWER_KEY_ENC_OPT_GTP_MAX, +}; + +#define TCA_FLOWER_KEY_ENC_OPT_GTP_MAX \ + (__TCA_FLOWER_KEY_ENC_OPT_GTP_MAX - 1) + enum { TCA_FLOWER_KEY_MPLS_OPTS_UNSPEC, TCA_FLOWER_KEY_MPLS_OPTS_LSE, -- cgit v1.2.3 From 81dd9849fa4911f76a14f354a048865894b9751e Mon Sep 17 00:00:00 2001 From: Wojciech Drewek Date: Fri, 4 Mar 2022 17:40:46 +0100 Subject: gtp: Add support for checking GTP device type Add a function that checks if a net device type is GTP. Signed-off-by: Wojciech Drewek Reviewed-by: Harald Welte Signed-off-by: Tony Nguyen --- include/net/gtp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/gtp.h b/include/net/gtp.h index 23c2aaae8a42..c1d6169df331 100644 --- a/include/net/gtp.h +++ b/include/net/gtp.h @@ -63,6 +63,12 @@ struct gtp_pdu_session_info { /* According to 3GPP TS 38.415. */ u8 qfi; }; +static inline bool netif_is_gtp(const struct net_device *dev) +{ + return dev->rtnl_link_ops && + !strcmp(dev->rtnl_link_ops->kind, "gtp"); +} + #define GTP1_F_NPDU 0x01 #define GTP1_F_SEQ 0x02 #define GTP1_F_EXTHDR 0x04 -- cgit v1.2.3 From af6b9668e85ffd1502aada8036ccbf4dbd481708 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Thu, 3 Mar 2022 17:05:33 -0500 Subject: tracing: Move the defines to create TRACE_EVENTS into their own files In an effort to add custom event macros that can be used to create your own custom events based on existing tracepoints, move the defines of the special macros used in TRACE_EVENT() into their own files such that they can be reused for TRACE_CUSTOM_EVENT(). Link: https://lkml.kernel.org/r/20220303220625.553406495@goodmis.org Cc: Ingo Molnar Cc: Andrew Morton Cc: Joel Fernandes Cc: Peter Zijlstra Cc: Masami Hiramatsu Cc: Tom Zanussi Signed-off-by: Steven Rostedt (Google) --- include/trace/stages/init.h | 37 +++ include/trace/stages/stage1_defines.h | 45 +++ include/trace/stages/stage2_defines.h | 48 ++++ include/trace/stages/stage3_defines.h | 129 +++++++++ include/trace/stages/stage4_defines.h | 57 ++++ include/trace/stages/stage5_defines.h | 83 ++++++ include/trace/stages/stage6_defines.h | 86 ++++++ include/trace/stages/stage7_defines.h | 34 +++ include/trace/trace_events.h | 499 +--------------------------------- 9 files changed, 527 insertions(+), 491 deletions(-) create mode 100644 include/trace/stages/init.h create mode 100644 include/trace/stages/stage1_defines.h create mode 100644 include/trace/stages/stage2_defines.h create mode 100644 include/trace/stages/stage3_defines.h create mode 100644 include/trace/stages/stage4_defines.h create mode 100644 include/trace/stages/stage5_defines.h create mode 100644 include/trace/stages/stage6_defines.h create mode 100644 include/trace/stages/stage7_defines.h (limited to 'include') diff --git a/include/trace/stages/init.h b/include/trace/stages/init.h new file mode 100644 index 000000000000..000bcfc8dd2e --- /dev/null +++ b/include/trace/stages/init.h @@ -0,0 +1,37 @@ + +#define __app__(x, y) str__##x##y +#define __app(x, y) __app__(x, y) + +#define TRACE_SYSTEM_STRING __app(TRACE_SYSTEM_VAR,__trace_system_name) + +#define TRACE_MAKE_SYSTEM_STR() \ + static const char TRACE_SYSTEM_STRING[] = \ + __stringify(TRACE_SYSTEM) + +TRACE_MAKE_SYSTEM_STR(); + +#undef TRACE_DEFINE_ENUM +#define TRACE_DEFINE_ENUM(a) \ + static struct trace_eval_map __used __initdata \ + __##TRACE_SYSTEM##_##a = \ + { \ + .system = TRACE_SYSTEM_STRING, \ + .eval_string = #a, \ + .eval_value = a \ + }; \ + static struct trace_eval_map __used \ + __section("_ftrace_eval_map") \ + *TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a + +#undef TRACE_DEFINE_SIZEOF +#define TRACE_DEFINE_SIZEOF(a) \ + static struct trace_eval_map __used __initdata \ + __##TRACE_SYSTEM##_##a = \ + { \ + .system = TRACE_SYSTEM_STRING, \ + .eval_string = "sizeof(" #a ")", \ + .eval_value = sizeof(a) \ + }; \ + static struct trace_eval_map __used \ + __section("_ftrace_eval_map") \ + *TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a diff --git a/include/trace/stages/stage1_defines.h b/include/trace/stages/stage1_defines.h new file mode 100644 index 000000000000..8ab88c766d2b --- /dev/null +++ b/include/trace/stages/stage1_defines.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Stage 1 definitions for creating trace events */ + +#undef __field +#define __field(type, item) type item; + +#undef __field_ext +#define __field_ext(type, item, filter_type) type item; + +#undef __field_struct +#define __field_struct(type, item) type item; + +#undef __field_struct_ext +#define __field_struct_ext(type, item, filter_type) type item; + +#undef __array +#define __array(type, item, len) type item[len]; + +#undef __dynamic_array +#define __dynamic_array(type, item, len) u32 __data_loc_##item; + +#undef __string +#define __string(item, src) __dynamic_array(char, item, -1) + +#undef __string_len +#define __string_len(item, src, len) __dynamic_array(char, item, -1) + +#undef __bitmask +#define __bitmask(item, nr_bits) __dynamic_array(char, item, -1) + +#undef __rel_dynamic_array +#define __rel_dynamic_array(type, item, len) u32 __rel_loc_##item; + +#undef __rel_string +#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) + +#undef __rel_string_len +#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) + +#undef __rel_bitmask +#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(char, item, -1) + +#undef TP_STRUCT__entry +#define TP_STRUCT__entry(args...) args diff --git a/include/trace/stages/stage2_defines.h b/include/trace/stages/stage2_defines.h new file mode 100644 index 000000000000..9f2341df40da --- /dev/null +++ b/include/trace/stages/stage2_defines.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Stage 2 definitions for creating trace events */ + +#undef TRACE_DEFINE_ENUM +#define TRACE_DEFINE_ENUM(a) + +#undef TRACE_DEFINE_SIZEOF +#define TRACE_DEFINE_SIZEOF(a) + +#undef __field +#define __field(type, item) + +#undef __field_ext +#define __field_ext(type, item, filter_type) + +#undef __field_struct +#define __field_struct(type, item) + +#undef __field_struct_ext +#define __field_struct_ext(type, item, filter_type) + +#undef __array +#define __array(type, item, len) + +#undef __dynamic_array +#define __dynamic_array(type, item, len) u32 item; + +#undef __string +#define __string(item, src) __dynamic_array(char, item, -1) + +#undef __bitmask +#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1) + +#undef __string_len +#define __string_len(item, src, len) __dynamic_array(char, item, -1) + +#undef __rel_dynamic_array +#define __rel_dynamic_array(type, item, len) u32 item; + +#undef __rel_string +#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) + +#undef __rel_string_len +#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) + +#undef __rel_bitmask +#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1) diff --git a/include/trace/stages/stage3_defines.h b/include/trace/stages/stage3_defines.h new file mode 100644 index 000000000000..0bc131993b7a --- /dev/null +++ b/include/trace/stages/stage3_defines.h @@ -0,0 +1,129 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Stage 3 definitions for creating trace events */ + +#undef __entry +#define __entry field + +#undef TP_printk +#define TP_printk(fmt, args...) fmt "\n", args + +#undef __get_dynamic_array +#define __get_dynamic_array(field) \ + ((void *)__entry + (__entry->__data_loc_##field & 0xffff)) + +#undef __get_dynamic_array_len +#define __get_dynamic_array_len(field) \ + ((__entry->__data_loc_##field >> 16) & 0xffff) + +#undef __get_str +#define __get_str(field) ((char *)__get_dynamic_array(field)) + +#undef __get_rel_dynamic_array +#define __get_rel_dynamic_array(field) \ + ((void *)__entry + \ + offsetof(typeof(*__entry), __rel_loc_##field) + \ + sizeof(__entry->__rel_loc_##field) + \ + (__entry->__rel_loc_##field & 0xffff)) + +#undef __get_rel_dynamic_array_len +#define __get_rel_dynamic_array_len(field) \ + ((__entry->__rel_loc_##field >> 16) & 0xffff) + +#undef __get_rel_str +#define __get_rel_str(field) ((char *)__get_rel_dynamic_array(field)) + +#undef __get_bitmask +#define __get_bitmask(field) \ + ({ \ + void *__bitmask = __get_dynamic_array(field); \ + unsigned int __bitmask_size; \ + __bitmask_size = __get_dynamic_array_len(field); \ + trace_print_bitmask_seq(p, __bitmask, __bitmask_size); \ + }) + +#undef __get_rel_bitmask +#define __get_rel_bitmask(field) \ + ({ \ + void *__bitmask = __get_rel_dynamic_array(field); \ + unsigned int __bitmask_size; \ + __bitmask_size = __get_rel_dynamic_array_len(field); \ + trace_print_bitmask_seq(p, __bitmask, __bitmask_size); \ + }) + +#undef __print_flags +#define __print_flags(flag, delim, flag_array...) \ + ({ \ + static const struct trace_print_flags __flags[] = \ + { flag_array, { -1, NULL }}; \ + trace_print_flags_seq(p, delim, flag, __flags); \ + }) + +#undef __print_symbolic +#define __print_symbolic(value, symbol_array...) \ + ({ \ + static const struct trace_print_flags symbols[] = \ + { symbol_array, { -1, NULL }}; \ + trace_print_symbols_seq(p, value, symbols); \ + }) + +#undef __print_flags_u64 +#undef __print_symbolic_u64 +#if BITS_PER_LONG == 32 +#define __print_flags_u64(flag, delim, flag_array...) \ + ({ \ + static const struct trace_print_flags_u64 __flags[] = \ + { flag_array, { -1, NULL } }; \ + trace_print_flags_seq_u64(p, delim, flag, __flags); \ + }) + +#define __print_symbolic_u64(value, symbol_array...) \ + ({ \ + static const struct trace_print_flags_u64 symbols[] = \ + { symbol_array, { -1, NULL } }; \ + trace_print_symbols_seq_u64(p, value, symbols); \ + }) +#else +#define __print_flags_u64(flag, delim, flag_array...) \ + __print_flags(flag, delim, flag_array) + +#define __print_symbolic_u64(value, symbol_array...) \ + __print_symbolic(value, symbol_array) +#endif + +#undef __print_hex +#define __print_hex(buf, buf_len) \ + trace_print_hex_seq(p, buf, buf_len, false) + +#undef __print_hex_str +#define __print_hex_str(buf, buf_len) \ + trace_print_hex_seq(p, buf, buf_len, true) + +#undef __print_array +#define __print_array(array, count, el_size) \ + ({ \ + BUILD_BUG_ON(el_size != 1 && el_size != 2 && \ + el_size != 4 && el_size != 8); \ + trace_print_array_seq(p, array, count, el_size); \ + }) + +#undef __print_hex_dump +#define __print_hex_dump(prefix_str, prefix_type, \ + rowsize, groupsize, buf, len, ascii) \ + trace_print_hex_dump_seq(p, prefix_str, prefix_type, \ + rowsize, groupsize, buf, len, ascii) + +#undef __print_ns_to_secs +#define __print_ns_to_secs(value) \ + ({ \ + u64 ____val = (u64)(value); \ + do_div(____val, NSEC_PER_SEC); \ + ____val; \ + }) + +#undef __print_ns_without_secs +#define __print_ns_without_secs(value) \ + ({ \ + u64 ____val = (u64)(value); \ + (u32) do_div(____val, NSEC_PER_SEC); \ + }) diff --git a/include/trace/stages/stage4_defines.h b/include/trace/stages/stage4_defines.h new file mode 100644 index 000000000000..780a10fa5279 --- /dev/null +++ b/include/trace/stages/stage4_defines.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Stage 4 definitions for creating trace events */ + +#undef __field_ext +#define __field_ext(_type, _item, _filter_type) { \ + .type = #_type, .name = #_item, \ + .size = sizeof(_type), .align = __alignof__(_type), \ + .is_signed = is_signed_type(_type), .filter_type = _filter_type }, + +#undef __field_struct_ext +#define __field_struct_ext(_type, _item, _filter_type) { \ + .type = #_type, .name = #_item, \ + .size = sizeof(_type), .align = __alignof__(_type), \ + 0, .filter_type = _filter_type }, + +#undef __field +#define __field(type, item) __field_ext(type, item, FILTER_OTHER) + +#undef __field_struct +#define __field_struct(type, item) __field_struct_ext(type, item, FILTER_OTHER) + +#undef __array +#define __array(_type, _item, _len) { \ + .type = #_type"["__stringify(_len)"]", .name = #_item, \ + .size = sizeof(_type[_len]), .align = __alignof__(_type), \ + .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER }, + +#undef __dynamic_array +#define __dynamic_array(_type, _item, _len) { \ + .type = "__data_loc " #_type "[]", .name = #_item, \ + .size = 4, .align = 4, \ + .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER }, + +#undef __string +#define __string(item, src) __dynamic_array(char, item, -1) + +#undef __string_len +#define __string_len(item, src, len) __dynamic_array(char, item, -1) + +#undef __bitmask +#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1) + +#undef __rel_dynamic_array +#define __rel_dynamic_array(_type, _item, _len) { \ + .type = "__rel_loc " #_type "[]", .name = #_item, \ + .size = 4, .align = 4, \ + .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER }, + +#undef __rel_string +#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) + +#undef __rel_string_len +#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) + +#undef __rel_bitmask +#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1) diff --git a/include/trace/stages/stage5_defines.h b/include/trace/stages/stage5_defines.h new file mode 100644 index 000000000000..fb15394aae31 --- /dev/null +++ b/include/trace/stages/stage5_defines.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Stage 5 definitions for creating trace events */ + +/* + * remember the offset of each array from the beginning of the event. + */ + +#undef __entry +#define __entry entry + +#undef __field +#define __field(type, item) + +#undef __field_ext +#define __field_ext(type, item, filter_type) + +#undef __field_struct +#define __field_struct(type, item) + +#undef __field_struct_ext +#define __field_struct_ext(type, item, filter_type) + +#undef __array +#define __array(type, item, len) + +#undef __dynamic_array +#define __dynamic_array(type, item, len) \ + __item_length = (len) * sizeof(type); \ + __data_offsets->item = __data_size + \ + offsetof(typeof(*entry), __data); \ + __data_offsets->item |= __item_length << 16; \ + __data_size += __item_length; + +#undef __string +#define __string(item, src) __dynamic_array(char, item, \ + strlen((src) ? (const char *)(src) : "(null)") + 1) + +#undef __string_len +#define __string_len(item, src, len) __dynamic_array(char, item, (len) + 1) + +#undef __rel_dynamic_array +#define __rel_dynamic_array(type, item, len) \ + __item_length = (len) * sizeof(type); \ + __data_offsets->item = __data_size + \ + offsetof(typeof(*entry), __data) - \ + offsetof(typeof(*entry), __rel_loc_##item) - \ + sizeof(u32); \ + __data_offsets->item |= __item_length << 16; \ + __data_size += __item_length; + +#undef __rel_string +#define __rel_string(item, src) __rel_dynamic_array(char, item, \ + strlen((src) ? (const char *)(src) : "(null)") + 1) + +#undef __rel_string_len +#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, (len) + 1) +/* + * __bitmask_size_in_bytes_raw is the number of bytes needed to hold + * num_possible_cpus(). + */ +#define __bitmask_size_in_bytes_raw(nr_bits) \ + (((nr_bits) + 7) / 8) + +#define __bitmask_size_in_longs(nr_bits) \ + ((__bitmask_size_in_bytes_raw(nr_bits) + \ + ((BITS_PER_LONG / 8) - 1)) / (BITS_PER_LONG / 8)) + +/* + * __bitmask_size_in_bytes is the number of bytes needed to hold + * num_possible_cpus() padded out to the nearest long. This is what + * is saved in the buffer, just to be consistent. + */ +#define __bitmask_size_in_bytes(nr_bits) \ + (__bitmask_size_in_longs(nr_bits) * (BITS_PER_LONG / 8)) + +#undef __bitmask +#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, \ + __bitmask_size_in_longs(nr_bits)) + +#undef __rel_bitmask +#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, \ + __bitmask_size_in_longs(nr_bits)) diff --git a/include/trace/stages/stage6_defines.h b/include/trace/stages/stage6_defines.h new file mode 100644 index 000000000000..b3a1f26026be --- /dev/null +++ b/include/trace/stages/stage6_defines.h @@ -0,0 +1,86 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Stage 6 definitions for creating trace events */ + +#undef __entry +#define __entry entry + +#undef __field +#define __field(type, item) + +#undef __field_struct +#define __field_struct(type, item) + +#undef __array +#define __array(type, item, len) + +#undef __dynamic_array +#define __dynamic_array(type, item, len) \ + __entry->__data_loc_##item = __data_offsets.item; + +#undef __string +#define __string(item, src) __dynamic_array(char, item, -1) + +#undef __string_len +#define __string_len(item, src, len) __dynamic_array(char, item, -1) + +#undef __assign_str +#define __assign_str(dst, src) \ + strcpy(__get_str(dst), (src) ? (const char *)(src) : "(null)"); + +#undef __assign_str_len +#define __assign_str_len(dst, src, len) \ + do { \ + memcpy(__get_str(dst), (src), (len)); \ + __get_str(dst)[len] = '\0'; \ + } while(0) + +#undef __bitmask +#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1) + +#undef __get_bitmask +#define __get_bitmask(field) (char *)__get_dynamic_array(field) + +#undef __assign_bitmask +#define __assign_bitmask(dst, src, nr_bits) \ + memcpy(__get_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits)) + +#undef __rel_dynamic_array +#define __rel_dynamic_array(type, item, len) \ + __entry->__rel_loc_##item = __data_offsets.item; + +#undef __rel_string +#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) + +#undef __rel_string_len +#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) + +#undef __assign_rel_str +#define __assign_rel_str(dst, src) \ + strcpy(__get_rel_str(dst), (src) ? (const char *)(src) : "(null)"); + +#undef __assign_rel_str_len +#define __assign_rel_str_len(dst, src, len) \ + do { \ + memcpy(__get_rel_str(dst), (src), (len)); \ + __get_rel_str(dst)[len] = '\0'; \ + } while (0) + +#undef __rel_bitmask +#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1) + +#undef __get_rel_bitmask +#define __get_rel_bitmask(field) (char *)__get_rel_dynamic_array(field) + +#undef __assign_rel_bitmask +#define __assign_rel_bitmask(dst, src, nr_bits) \ + memcpy(__get_rel_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits)) + +#undef TP_fast_assign +#define TP_fast_assign(args...) args + +#undef __perf_count +#define __perf_count(c) (c) + +#undef __perf_task +#define __perf_task(t) (t) diff --git a/include/trace/stages/stage7_defines.h b/include/trace/stages/stage7_defines.h new file mode 100644 index 000000000000..d65445328f18 --- /dev/null +++ b/include/trace/stages/stage7_defines.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Stage 7 definitions for creating trace events */ + +#undef __entry +#define __entry REC + +#undef __print_flags +#undef __print_symbolic +#undef __print_hex +#undef __print_hex_str +#undef __get_dynamic_array +#undef __get_dynamic_array_len +#undef __get_str +#undef __get_bitmask +#undef __get_rel_dynamic_array +#undef __get_rel_dynamic_array_len +#undef __get_rel_str +#undef __get_rel_bitmask +#undef __print_array +#undef __print_hex_dump + +/* + * The below is not executed in the kernel. It is only what is + * displayed in the print format for userspace to parse. + */ +#undef __print_ns_to_secs +#define __print_ns_to_secs(val) (val) / 1000000000UL + +#undef __print_ns_without_secs +#define __print_ns_without_secs(val) (val) % 1000000000UL + +#undef TP_printk +#define TP_printk(fmt, args...) "\"" fmt "\", " __stringify(args) diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h index 3d29919045af..8a8cd66cc6d5 100644 --- a/include/trace/trace_events.h +++ b/include/trace/trace_events.h @@ -24,42 +24,7 @@ #define TRACE_SYSTEM_VAR TRACE_SYSTEM #endif -#define __app__(x, y) str__##x##y -#define __app(x, y) __app__(x, y) - -#define TRACE_SYSTEM_STRING __app(TRACE_SYSTEM_VAR,__trace_system_name) - -#define TRACE_MAKE_SYSTEM_STR() \ - static const char TRACE_SYSTEM_STRING[] = \ - __stringify(TRACE_SYSTEM) - -TRACE_MAKE_SYSTEM_STR(); - -#undef TRACE_DEFINE_ENUM -#define TRACE_DEFINE_ENUM(a) \ - static struct trace_eval_map __used __initdata \ - __##TRACE_SYSTEM##_##a = \ - { \ - .system = TRACE_SYSTEM_STRING, \ - .eval_string = #a, \ - .eval_value = a \ - }; \ - static struct trace_eval_map __used \ - __section("_ftrace_eval_map") \ - *TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a - -#undef TRACE_DEFINE_SIZEOF -#define TRACE_DEFINE_SIZEOF(a) \ - static struct trace_eval_map __used __initdata \ - __##TRACE_SYSTEM##_##a = \ - { \ - .system = TRACE_SYSTEM_STRING, \ - .eval_string = "sizeof(" #a ")", \ - .eval_value = sizeof(a) \ - }; \ - static struct trace_eval_map __used \ - __section("_ftrace_eval_map") \ - *TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a +#include "stages/init.h" /* * DECLARE_EVENT_CLASS can be used to add a generic function @@ -80,48 +45,7 @@ TRACE_MAKE_SYSTEM_STR(); PARAMS(print)); \ DEFINE_EVENT(name, name, PARAMS(proto), PARAMS(args)); - -#undef __field -#define __field(type, item) type item; - -#undef __field_ext -#define __field_ext(type, item, filter_type) type item; - -#undef __field_struct -#define __field_struct(type, item) type item; - -#undef __field_struct_ext -#define __field_struct_ext(type, item, filter_type) type item; - -#undef __array -#define __array(type, item, len) type item[len]; - -#undef __dynamic_array -#define __dynamic_array(type, item, len) u32 __data_loc_##item; - -#undef __string -#define __string(item, src) __dynamic_array(char, item, -1) - -#undef __string_len -#define __string_len(item, src, len) __dynamic_array(char, item, -1) - -#undef __bitmask -#define __bitmask(item, nr_bits) __dynamic_array(char, item, -1) - -#undef __rel_dynamic_array -#define __rel_dynamic_array(type, item, len) u32 __rel_loc_##item; - -#undef __rel_string -#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) - -#undef __rel_string_len -#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) - -#undef __rel_bitmask -#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(char, item, -1) - -#undef TP_STRUCT__entry -#define TP_STRUCT__entry(args...) args +#include "stages/stage1_defines.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(name, proto, args, tstruct, assign, print) \ @@ -185,50 +109,7 @@ TRACE_MAKE_SYSTEM_STR(); * The size of an array is also encoded, in the higher 16 bits of . */ -#undef TRACE_DEFINE_ENUM -#define TRACE_DEFINE_ENUM(a) - -#undef TRACE_DEFINE_SIZEOF -#define TRACE_DEFINE_SIZEOF(a) - -#undef __field -#define __field(type, item) - -#undef __field_ext -#define __field_ext(type, item, filter_type) - -#undef __field_struct -#define __field_struct(type, item) - -#undef __field_struct_ext -#define __field_struct_ext(type, item, filter_type) - -#undef __array -#define __array(type, item, len) - -#undef __dynamic_array -#define __dynamic_array(type, item, len) u32 item; - -#undef __string -#define __string(item, src) __dynamic_array(char, item, -1) - -#undef __bitmask -#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1) - -#undef __string_len -#define __string_len(item, src, len) __dynamic_array(char, item, -1) - -#undef __rel_dynamic_array -#define __rel_dynamic_array(type, item, len) u32 item; - -#undef __rel_string -#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) - -#undef __rel_string_len -#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) - -#undef __rel_bitmask -#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1) +#include "stages/stage2_defines.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -300,131 +181,7 @@ TRACE_MAKE_SYSTEM_STR(); * in binary. */ -#undef __entry -#define __entry field - -#undef TP_printk -#define TP_printk(fmt, args...) fmt "\n", args - -#undef __get_dynamic_array -#define __get_dynamic_array(field) \ - ((void *)__entry + (__entry->__data_loc_##field & 0xffff)) - -#undef __get_dynamic_array_len -#define __get_dynamic_array_len(field) \ - ((__entry->__data_loc_##field >> 16) & 0xffff) - -#undef __get_str -#define __get_str(field) ((char *)__get_dynamic_array(field)) - -#undef __get_rel_dynamic_array -#define __get_rel_dynamic_array(field) \ - ((void *)__entry + \ - offsetof(typeof(*__entry), __rel_loc_##field) + \ - sizeof(__entry->__rel_loc_##field) + \ - (__entry->__rel_loc_##field & 0xffff)) - -#undef __get_rel_dynamic_array_len -#define __get_rel_dynamic_array_len(field) \ - ((__entry->__rel_loc_##field >> 16) & 0xffff) - -#undef __get_rel_str -#define __get_rel_str(field) ((char *)__get_rel_dynamic_array(field)) - -#undef __get_bitmask -#define __get_bitmask(field) \ - ({ \ - void *__bitmask = __get_dynamic_array(field); \ - unsigned int __bitmask_size; \ - __bitmask_size = __get_dynamic_array_len(field); \ - trace_print_bitmask_seq(p, __bitmask, __bitmask_size); \ - }) - -#undef __get_rel_bitmask -#define __get_rel_bitmask(field) \ - ({ \ - void *__bitmask = __get_rel_dynamic_array(field); \ - unsigned int __bitmask_size; \ - __bitmask_size = __get_rel_dynamic_array_len(field); \ - trace_print_bitmask_seq(p, __bitmask, __bitmask_size); \ - }) - -#undef __print_flags -#define __print_flags(flag, delim, flag_array...) \ - ({ \ - static const struct trace_print_flags __flags[] = \ - { flag_array, { -1, NULL }}; \ - trace_print_flags_seq(p, delim, flag, __flags); \ - }) - -#undef __print_symbolic -#define __print_symbolic(value, symbol_array...) \ - ({ \ - static const struct trace_print_flags symbols[] = \ - { symbol_array, { -1, NULL }}; \ - trace_print_symbols_seq(p, value, symbols); \ - }) - -#undef __print_flags_u64 -#undef __print_symbolic_u64 -#if BITS_PER_LONG == 32 -#define __print_flags_u64(flag, delim, flag_array...) \ - ({ \ - static const struct trace_print_flags_u64 __flags[] = \ - { flag_array, { -1, NULL } }; \ - trace_print_flags_seq_u64(p, delim, flag, __flags); \ - }) - -#define __print_symbolic_u64(value, symbol_array...) \ - ({ \ - static const struct trace_print_flags_u64 symbols[] = \ - { symbol_array, { -1, NULL } }; \ - trace_print_symbols_seq_u64(p, value, symbols); \ - }) -#else -#define __print_flags_u64(flag, delim, flag_array...) \ - __print_flags(flag, delim, flag_array) - -#define __print_symbolic_u64(value, symbol_array...) \ - __print_symbolic(value, symbol_array) -#endif - -#undef __print_hex -#define __print_hex(buf, buf_len) \ - trace_print_hex_seq(p, buf, buf_len, false) - -#undef __print_hex_str -#define __print_hex_str(buf, buf_len) \ - trace_print_hex_seq(p, buf, buf_len, true) - -#undef __print_array -#define __print_array(array, count, el_size) \ - ({ \ - BUILD_BUG_ON(el_size != 1 && el_size != 2 && \ - el_size != 4 && el_size != 8); \ - trace_print_array_seq(p, array, count, el_size); \ - }) - -#undef __print_hex_dump -#define __print_hex_dump(prefix_str, prefix_type, \ - rowsize, groupsize, buf, len, ascii) \ - trace_print_hex_dump_seq(p, prefix_str, prefix_type, \ - rowsize, groupsize, buf, len, ascii) - -#undef __print_ns_to_secs -#define __print_ns_to_secs(value) \ - ({ \ - u64 ____val = (u64)(value); \ - do_div(____val, NSEC_PER_SEC); \ - ____val; \ - }) - -#undef __print_ns_without_secs -#define __print_ns_without_secs(value) \ - ({ \ - u64 ____val = (u64)(value); \ - (u32) do_div(____val, NSEC_PER_SEC); \ - }) +#include "stages/stage3_defines.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -479,59 +236,7 @@ static struct trace_event_functions trace_event_type_funcs_##call = { \ #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) -#undef __field_ext -#define __field_ext(_type, _item, _filter_type) { \ - .type = #_type, .name = #_item, \ - .size = sizeof(_type), .align = __alignof__(_type), \ - .is_signed = is_signed_type(_type), .filter_type = _filter_type }, - -#undef __field_struct_ext -#define __field_struct_ext(_type, _item, _filter_type) { \ - .type = #_type, .name = #_item, \ - .size = sizeof(_type), .align = __alignof__(_type), \ - 0, .filter_type = _filter_type }, - -#undef __field -#define __field(type, item) __field_ext(type, item, FILTER_OTHER) - -#undef __field_struct -#define __field_struct(type, item) __field_struct_ext(type, item, FILTER_OTHER) - -#undef __array -#define __array(_type, _item, _len) { \ - .type = #_type"["__stringify(_len)"]", .name = #_item, \ - .size = sizeof(_type[_len]), .align = __alignof__(_type), \ - .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER }, - -#undef __dynamic_array -#define __dynamic_array(_type, _item, _len) { \ - .type = "__data_loc " #_type "[]", .name = #_item, \ - .size = 4, .align = 4, \ - .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER }, - -#undef __string -#define __string(item, src) __dynamic_array(char, item, -1) - -#undef __string_len -#define __string_len(item, src, len) __dynamic_array(char, item, -1) - -#undef __bitmask -#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1) - -#undef __rel_dynamic_array -#define __rel_dynamic_array(_type, _item, _len) { \ - .type = "__rel_loc " #_type "[]", .name = #_item, \ - .size = 4, .align = 4, \ - .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER }, - -#undef __rel_string -#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) - -#undef __rel_string_len -#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) - -#undef __rel_bitmask -#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1) +#include "stages/stage4_defines.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, func, print) \ @@ -544,85 +249,7 @@ static struct trace_event_fields trace_event_fields_##call[] = { \ #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) -/* - * remember the offset of each array from the beginning of the event. - */ - -#undef __entry -#define __entry entry - -#undef __field -#define __field(type, item) - -#undef __field_ext -#define __field_ext(type, item, filter_type) - -#undef __field_struct -#define __field_struct(type, item) - -#undef __field_struct_ext -#define __field_struct_ext(type, item, filter_type) - -#undef __array -#define __array(type, item, len) - -#undef __dynamic_array -#define __dynamic_array(type, item, len) \ - __item_length = (len) * sizeof(type); \ - __data_offsets->item = __data_size + \ - offsetof(typeof(*entry), __data); \ - __data_offsets->item |= __item_length << 16; \ - __data_size += __item_length; - -#undef __string -#define __string(item, src) __dynamic_array(char, item, \ - strlen((src) ? (const char *)(src) : "(null)") + 1) - -#undef __string_len -#define __string_len(item, src, len) __dynamic_array(char, item, (len) + 1) - -#undef __rel_dynamic_array -#define __rel_dynamic_array(type, item, len) \ - __item_length = (len) * sizeof(type); \ - __data_offsets->item = __data_size + \ - offsetof(typeof(*entry), __data) - \ - offsetof(typeof(*entry), __rel_loc_##item) - \ - sizeof(u32); \ - __data_offsets->item |= __item_length << 16; \ - __data_size += __item_length; - -#undef __rel_string -#define __rel_string(item, src) __rel_dynamic_array(char, item, \ - strlen((src) ? (const char *)(src) : "(null)") + 1) - -#undef __rel_string_len -#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, (len) + 1) -/* - * __bitmask_size_in_bytes_raw is the number of bytes needed to hold - * num_possible_cpus(). - */ -#define __bitmask_size_in_bytes_raw(nr_bits) \ - (((nr_bits) + 7) / 8) - -#define __bitmask_size_in_longs(nr_bits) \ - ((__bitmask_size_in_bytes_raw(nr_bits) + \ - ((BITS_PER_LONG / 8) - 1)) / (BITS_PER_LONG / 8)) - -/* - * __bitmask_size_in_bytes is the number of bytes needed to hold - * num_possible_cpus() padded out to the nearest long. This is what - * is saved in the buffer, just to be consistent. - */ -#define __bitmask_size_in_bytes(nr_bits) \ - (__bitmask_size_in_longs(nr_bits) * (BITS_PER_LONG / 8)) - -#undef __bitmask -#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, \ - __bitmask_size_in_longs(nr_bits)) - -#undef __rel_bitmask -#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, \ - __bitmask_size_in_longs(nr_bits)) +#include "stages/stage5_defines.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -745,88 +372,7 @@ static inline notrace int trace_event_get_offsets_##call( \ #define _TRACE_PERF_INIT(call) #endif /* CONFIG_PERF_EVENTS */ -#undef __entry -#define __entry entry - -#undef __field -#define __field(type, item) - -#undef __field_struct -#define __field_struct(type, item) - -#undef __array -#define __array(type, item, len) - -#undef __dynamic_array -#define __dynamic_array(type, item, len) \ - __entry->__data_loc_##item = __data_offsets.item; - -#undef __string -#define __string(item, src) __dynamic_array(char, item, -1) - -#undef __string_len -#define __string_len(item, src, len) __dynamic_array(char, item, -1) - -#undef __assign_str -#define __assign_str(dst, src) \ - strcpy(__get_str(dst), (src) ? (const char *)(src) : "(null)"); - -#undef __assign_str_len -#define __assign_str_len(dst, src, len) \ - do { \ - memcpy(__get_str(dst), (src), (len)); \ - __get_str(dst)[len] = '\0'; \ - } while(0) - -#undef __bitmask -#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1) - -#undef __get_bitmask -#define __get_bitmask(field) (char *)__get_dynamic_array(field) - -#undef __assign_bitmask -#define __assign_bitmask(dst, src, nr_bits) \ - memcpy(__get_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits)) - -#undef __rel_dynamic_array -#define __rel_dynamic_array(type, item, len) \ - __entry->__rel_loc_##item = __data_offsets.item; - -#undef __rel_string -#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) - -#undef __rel_string_len -#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) - -#undef __assign_rel_str -#define __assign_rel_str(dst, src) \ - strcpy(__get_rel_str(dst), (src) ? (const char *)(src) : "(null)"); - -#undef __assign_rel_str_len -#define __assign_rel_str_len(dst, src, len) \ - do { \ - memcpy(__get_rel_str(dst), (src), (len)); \ - __get_rel_str(dst)[len] = '\0'; \ - } while (0) - -#undef __rel_bitmask -#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1) - -#undef __get_rel_bitmask -#define __get_rel_bitmask(field) (char *)__get_rel_dynamic_array(field) - -#undef __assign_rel_bitmask -#define __assign_rel_bitmask(dst, src, nr_bits) \ - memcpy(__get_rel_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits)) - -#undef TP_fast_assign -#define TP_fast_assign(args...) args - -#undef __perf_count -#define __perf_count(c) (c) - -#undef __perf_task -#define __perf_task(t) (t) +#include "stages/stage6_defines.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -872,36 +418,7 @@ static inline void ftrace_test_probe_##call(void) \ #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) -#undef __entry -#define __entry REC - -#undef __print_flags -#undef __print_symbolic -#undef __print_hex -#undef __print_hex_str -#undef __get_dynamic_array -#undef __get_dynamic_array_len -#undef __get_str -#undef __get_bitmask -#undef __get_rel_dynamic_array -#undef __get_rel_dynamic_array_len -#undef __get_rel_str -#undef __get_rel_bitmask -#undef __print_array -#undef __print_hex_dump - -/* - * The below is not executed in the kernel. It is only what is - * displayed in the print format for userspace to parse. - */ -#undef __print_ns_to_secs -#define __print_ns_to_secs(val) (val) / 1000000000UL - -#undef __print_ns_without_secs -#define __print_ns_without_secs(val) (val) % 1000000000UL - -#undef TP_printk -#define TP_printk(fmt, args...) "\"" fmt "\", " __stringify(args) +#include "stages/stage7_defines.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ -- cgit v1.2.3 From 3a73333fb370f7b65de9d94c53df503642bda789 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Thu, 3 Mar 2022 17:05:34 -0500 Subject: tracing: Add TRACE_CUSTOM_EVENT() macro To make it really easy to add custom events from modules, add a TRACE_CUSTOM_EVENT() macro that acts just like the TRACE_EVENT() macro, but creates a custom event to an already existing tracepoint. The trace_custom_sched.[ch] has been updated to use this new macro to show how simple it is. Link: https://lkml.kernel.org/r/20220303220625.738622494@goodmis.org Cc: Ingo Molnar Cc: Andrew Morton Cc: Joel Fernandes Cc: Peter Zijlstra Cc: Masami Hiramatsu Cc: Tom Zanussi Signed-off-by: Steven Rostedt (Google) --- include/linux/trace_events.h | 24 +++- include/trace/define_custom_trace.h | 77 +++++++++++++ include/trace/trace_custom_events.h | 221 ++++++++++++++++++++++++++++++++++++ 3 files changed, 321 insertions(+), 1 deletion(-) create mode 100644 include/trace/define_custom_trace.h create mode 100644 include/trace/trace_custom_events.h (limited to 'include') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 70c069aef02c..9b09fd633d48 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -315,6 +315,7 @@ enum { TRACE_EVENT_FL_KPROBE_BIT, TRACE_EVENT_FL_UPROBE_BIT, TRACE_EVENT_FL_EPROBE_BIT, + TRACE_EVENT_FL_CUSTOM_BIT, }; /* @@ -328,6 +329,9 @@ enum { * KPROBE - Event is a kprobe * UPROBE - Event is a uprobe * EPROBE - Event is an event probe + * CUSTOM - Event is a custom event (to be attached to an exsiting tracepoint) + * This is set when the custom event has not been attached + * to a tracepoint yet, then it is cleared when it is. */ enum { TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT), @@ -339,6 +343,7 @@ enum { TRACE_EVENT_FL_KPROBE = (1 << TRACE_EVENT_FL_KPROBE_BIT), TRACE_EVENT_FL_UPROBE = (1 << TRACE_EVENT_FL_UPROBE_BIT), TRACE_EVENT_FL_EPROBE = (1 << TRACE_EVENT_FL_EPROBE_BIT), + TRACE_EVENT_FL_CUSTOM = (1 << TRACE_EVENT_FL_CUSTOM_BIT), }; #define TRACE_EVENT_FL_UKPROBE (TRACE_EVENT_FL_KPROBE | TRACE_EVENT_FL_UPROBE) @@ -440,7 +445,9 @@ static inline bool bpf_prog_array_valid(struct trace_event_call *call) static inline const char * trace_event_name(struct trace_event_call *call) { - if (call->flags & TRACE_EVENT_FL_TRACEPOINT) + if (call->flags & TRACE_EVENT_FL_CUSTOM) + return call->name; + else if (call->flags & TRACE_EVENT_FL_TRACEPOINT) return call->tp ? call->tp->name : NULL; else return call->name; @@ -901,3 +908,18 @@ perf_trace_buf_submit(void *raw_data, int size, int rctx, u16 type, #endif #endif /* _LINUX_TRACE_EVENT_H */ + +/* + * Note: we keep the TRACE_CUSTOM_EVENT outside the include file ifdef protection. + * This is due to the way trace custom events work. If a file includes two + * trace event headers under one "CREATE_CUSTOM_TRACE_EVENTS" the first include + * will override the TRACE_CUSTOM_EVENT and break the second include. + */ + +#ifndef TRACE_CUSTOM_EVENT + +#define DECLARE_CUSTOM_EVENT_CLASS(name, proto, args, tstruct, assign, print) +#define DEFINE_CUSTOM_EVENT(template, name, proto, args) +#define TRACE_CUSTOM_EVENT(name, proto, args, struct, assign, print) + +#endif /* ifdef TRACE_CUSTOM_EVENT (see note above) */ diff --git a/include/trace/define_custom_trace.h b/include/trace/define_custom_trace.h new file mode 100644 index 000000000000..5827a4c92c74 --- /dev/null +++ b/include/trace/define_custom_trace.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Trace files that want to automate creation of all tracepoints defined + * in their file should include this file. The following are macros that the + * trace file may define: + * + * TRACE_SYSTEM defines the system the tracepoint is for + * + * TRACE_INCLUDE_FILE if the file name is something other than TRACE_SYSTEM.h + * This macro may be defined to tell define_trace.h what file to include. + * Note, leave off the ".h". + * + * TRACE_INCLUDE_PATH if the path is something other than core kernel include/trace + * then this macro can define the path to use. Note, the path is relative to + * define_trace.h, not the file including it. Full path names for out of tree + * modules must be used. + */ + +#ifdef CREATE_CUSTOM_TRACE_EVENTS + +/* Prevent recursion */ +#undef CREATE_CUSTOM_TRACE_EVENTS + +#include + +#undef TRACE_CUSTOM_EVENT +#define TRACE_CUSTOM_EVENT(name, proto, args, tstruct, assign, print) + +#undef DEFINE_CUSTOM_EVENT +#define DEFINE_CUSTOM_EVENT(template, name, proto, args) + +#undef TRACE_INCLUDE +#undef __TRACE_INCLUDE + +#ifndef TRACE_INCLUDE_FILE +# define TRACE_INCLUDE_FILE TRACE_SYSTEM +# define UNDEF_TRACE_INCLUDE_FILE +#endif + +#ifndef TRACE_INCLUDE_PATH +# define __TRACE_INCLUDE(system) +# define UNDEF_TRACE_INCLUDE_PATH +#else +# define __TRACE_INCLUDE(system) __stringify(TRACE_INCLUDE_PATH/system.h) +#endif + +# define TRACE_INCLUDE(system) __TRACE_INCLUDE(system) + +/* Let the trace headers be reread */ +#define TRACE_CUSTOM_MULTI_READ + +#include TRACE_INCLUDE(TRACE_INCLUDE_FILE) + +#ifdef TRACEPOINTS_ENABLED +#include +#endif + +#undef TRACE_CUSTOM_EVENT +#undef DECLARE_CUSTOM_EVENT_CLASS +#undef DEFINE_CUSTOM_EVENT +#undef TRACE_CUSTOM_MULTI_READ + +/* Only undef what we defined in this file */ +#ifdef UNDEF_TRACE_INCLUDE_FILE +# undef TRACE_INCLUDE_FILE +# undef UNDEF_TRACE_INCLUDE_FILE +#endif + +#ifdef UNDEF_TRACE_INCLUDE_PATH +# undef TRACE_INCLUDE_PATH +# undef UNDEF_TRACE_INCLUDE_PATH +#endif + +/* We may be processing more files */ +#define CREATE_CUSTOM_TRACE_POINTS + +#endif /* CREATE_CUSTOM_TRACE_POINTS */ diff --git a/include/trace/trace_custom_events.h b/include/trace/trace_custom_events.h new file mode 100644 index 000000000000..b567c7202339 --- /dev/null +++ b/include/trace/trace_custom_events.h @@ -0,0 +1,221 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * This is similar to the trace_events.h file, but is to only + * create custom trace events to be attached to existing tracepoints. + * Where as the TRACE_EVENT() macro (from trace_events.h) will create + * both the trace event and the tracepoint it will attach the event to, + * TRACE_CUSTOM_EVENT() is to create only a custom version of an existing + * trace event (created by TRACE_EVENT() or DEFINE_EVENT()), and will + * be placed in the "custom" system. + */ + +#include + +/* All custom events are placed in the custom group */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM custom + +#ifndef TRACE_SYSTEM_VAR +#define TRACE_SYSTEM_VAR TRACE_SYSTEM +#endif + +/* The init stage creates the system string and enum mappings */ + +#include "stages/init.h" + +#undef TRACE_CUSTOM_EVENT +#define TRACE_CUSTOM_EVENT(name, proto, args, tstruct, assign, print) \ + DECLARE_CUSTOM_EVENT_CLASS(name, \ + PARAMS(proto), \ + PARAMS(args), \ + PARAMS(tstruct), \ + PARAMS(assign), \ + PARAMS(print)); \ + DEFINE_CUSTOM_EVENT(name, name, PARAMS(proto), PARAMS(args)); + +/* Stage 1 creates the structure of the recorded event layout */ + +#include "stages/stage1_defines.h" + +#undef DECLARE_CUSTOM_EVENT_CLASS +#define DECLARE_CUSTOM_EVENT_CLASS(name, proto, args, tstruct, assign, print) \ + struct trace_custom_event_raw_##name { \ + struct trace_entry ent; \ + tstruct \ + char __data[]; \ + }; \ + \ + static struct trace_event_class custom_event_class_##name; + +#undef DEFINE_CUSTOM_EVENT +#define DEFINE_CUSTOM_EVENT(template, name, proto, args) \ + static struct trace_event_call __used \ + __attribute__((__aligned__(4))) custom_event_##name + +#include TRACE_INCLUDE(TRACE_INCLUDE_FILE) + +/* Stage 2 creates the custom class */ + +#include "stages/stage2_defines.h" + +#undef DECLARE_CUSTOM_EVENT_CLASS +#define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ + struct trace_custom_event_data_offsets_##call { \ + tstruct; \ + }; + +#undef DEFINE_CUSTOM_EVENT +#define DEFINE_CUSTOM_EVENT(template, name, proto, args) + +#include TRACE_INCLUDE(TRACE_INCLUDE_FILE) + +/* Stage 3 create the way to print the custom event */ + +#include "stages/stage3_defines.h" + +#undef DECLARE_CUSTOM_EVENT_CLASS +#define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ +static notrace enum print_line_t \ +trace_custom_raw_output_##call(struct trace_iterator *iter, int flags, \ + struct trace_event *trace_event) \ +{ \ + struct trace_seq *s = &iter->seq; \ + struct trace_seq __maybe_unused *p = &iter->tmp_seq; \ + struct trace_custom_event_raw_##call *field; \ + int ret; \ + \ + field = (typeof(field))iter->ent; \ + \ + ret = trace_raw_output_prep(iter, trace_event); \ + if (ret != TRACE_TYPE_HANDLED) \ + return ret; \ + \ + trace_event_printf(iter, print); \ + \ + return trace_handle_return(s); \ +} \ +static struct trace_event_functions trace_custom_event_type_funcs_##call = { \ + .trace = trace_custom_raw_output_##call, \ +}; + +#include TRACE_INCLUDE(TRACE_INCLUDE_FILE) + +/* Stage 4 creates the offset layout for the fields */ + +#include "stages/stage4_defines.h" + +#undef DECLARE_CUSTOM_EVENT_CLASS +#define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, func, print) \ +static struct trace_event_fields trace_custom_event_fields_##call[] = { \ + tstruct \ + {} }; + +#include TRACE_INCLUDE(TRACE_INCLUDE_FILE) + +/* Stage 5 creates the helper function for dynamic fields */ + +#include "stages/stage5_defines.h" + +#undef DECLARE_CUSTOM_EVENT_CLASS +#define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ +static inline notrace int trace_custom_event_get_offsets_##call( \ + struct trace_custom_event_data_offsets_##call *__data_offsets, proto) \ +{ \ + int __data_size = 0; \ + int __maybe_unused __item_length; \ + struct trace_custom_event_raw_##call __maybe_unused *entry; \ + \ + tstruct; \ + \ + return __data_size; \ +} + +#include TRACE_INCLUDE(TRACE_INCLUDE_FILE) + +/* Stage 6 creates the probe function that records the event */ + +#include "stages/stage6_defines.h" + +#undef DECLARE_CUSTOM_EVENT_CLASS +#define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ + \ +static notrace void \ +trace_custom_event_raw_event_##call(void *__data, proto) \ +{ \ + struct trace_event_file *trace_file = __data; \ + struct trace_custom_event_data_offsets_##call __maybe_unused __data_offsets; \ + struct trace_event_buffer fbuffer; \ + struct trace_custom_event_raw_##call *entry; \ + int __data_size; \ + \ + if (trace_trigger_soft_disabled(trace_file)) \ + return; \ + \ + __data_size = trace_custom_event_get_offsets_##call(&__data_offsets, args); \ + \ + entry = trace_event_buffer_reserve(&fbuffer, trace_file, \ + sizeof(*entry) + __data_size); \ + \ + if (!entry) \ + return; \ + \ + tstruct \ + \ + { assign; } \ + \ + trace_event_buffer_commit(&fbuffer); \ +} +/* + * The ftrace_test_custom_probe is compiled out, it is only here as a build time check + * to make sure that if the tracepoint handling changes, the ftrace probe will + * fail to compile unless it too is updated. + */ + +#undef DEFINE_CUSTOM_EVENT +#define DEFINE_CUSTOM_EVENT(template, call, proto, args) \ +static inline void ftrace_test_custom_probe_##call(void) \ +{ \ + check_trace_callback_type_##call(trace_custom_event_raw_event_##template); \ +} + +#include TRACE_INCLUDE(TRACE_INCLUDE_FILE) + +/* Stage 7 creates the actual class and event structure for the custom event */ + +#include "stages/stage7_defines.h" + +#undef DECLARE_CUSTOM_EVENT_CLASS +#define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ +static char custom_print_fmt_##call[] = print; \ +static struct trace_event_class __used __refdata custom_event_class_##call = { \ + .system = TRACE_SYSTEM_STRING, \ + .fields_array = trace_custom_event_fields_##call, \ + .fields = LIST_HEAD_INIT(custom_event_class_##call.fields),\ + .raw_init = trace_event_raw_init, \ + .probe = trace_custom_event_raw_event_##call, \ + .reg = trace_event_reg, \ +}; + +#undef DEFINE_CUSTOM_EVENT +#define DEFINE_CUSTOM_EVENT(template, call, proto, args) \ + \ +static struct trace_event_call __used custom_event_##call = { \ + .name = #call, \ + .class = &custom_event_class_##template, \ + .event.funcs = &trace_custom_event_type_funcs_##template, \ + .print_fmt = custom_print_fmt_##template, \ + .flags = TRACE_EVENT_FL_CUSTOM, \ +}; \ +static inline int trace_custom_event_##call##_update(struct tracepoint *tp) \ +{ \ + if (tp->name && strcmp(tp->name, #call) == 0) { \ + custom_event_##call.tp = tp; \ + custom_event_##call.flags = TRACE_EVENT_FL_TRACEPOINT; \ + return 1; \ + } \ + return 0; \ +} \ +static struct trace_event_call __used \ +__section("_ftrace_events") *__custom_event_##call = &custom_event_##call + +#include TRACE_INCLUDE(TRACE_INCLUDE_FILE) -- cgit v1.2.3 From 380af29b8d7670c445965bd573ab219aff0c4c11 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Thu, 10 Mar 2022 21:37:09 -0500 Subject: tracing: Add snapshot at end of kernel boot up Add ftrace_boot_snapshot kernel parameter that will take a snapshot at the end of boot up just before switching over to user space (it happens during the kernel freeing of init memory). This is useful when there's interesting data that can be collected from kernel start up, but gets overridden by user space start up code. With this option, the ring buffer content from the boot up traces gets saved in the snapshot at the end of boot up. This trace can be read from: /sys/kernel/tracing/snapshot Signed-off-by: Steven Rostedt (Google) --- include/linux/ftrace.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 9999e29187de..37b619185ec9 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -30,6 +30,12 @@ #define ARCH_SUPPORTS_FTRACE_OPS 0 #endif +#ifdef CONFIG_TRACING +extern void ftrace_boot_snapshot(void); +#else +static inline void ftrace_boot_snapshot(void) { } +#endif + #ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops; struct ftrace_regs; @@ -215,7 +221,10 @@ struct ftrace_ops_hash { void ftrace_free_init_mem(void); void ftrace_free_mem(struct module *mod, void *start, void *end); #else -static inline void ftrace_free_init_mem(void) { } +static inline void ftrace_free_init_mem(void) +{ + ftrace_boot_snapshot(); +} static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { } #endif -- cgit v1.2.3 From b65700d046a60d0a29f6289e13c62d0c93689f11 Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Tue, 8 Mar 2022 18:25:15 +0100 Subject: remoteproc: move rproc_da_to_va declaration to remoteproc.h The rproc_da_to_va() API is an exported function, so move its declaration from the remoteproc local remoteproc_internal.h to the public remoteproc.h file. This will allow drivers outside of the remoteproc folder to be able to use this API. Signed-off-by: Suman Anna Signed-off-by: Dave Gerlach [adjusted line numbers to apply] Signed-off-by: Drew Fustini Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220308172515.29556-1-dfustini@baylibre.com --- include/linux/remoteproc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 93a1d0050fbc..b2ee325e0af1 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -675,6 +675,7 @@ void rproc_shutdown(struct rproc *rproc); int rproc_detach(struct rproc *rproc); int rproc_set_firmware(struct rproc *rproc, const char *fw_name); void rproc_report_crash(struct rproc *rproc, enum rproc_crash_type type); +void *rproc_da_to_va(struct rproc *rproc, u64 da, size_t len, bool *is_iomem); void rproc_coredump_using_sections(struct rproc *rproc); int rproc_coredump_add_segment(struct rproc *rproc, dma_addr_t da, size_t size); int rproc_coredump_add_custom_segment(struct rproc *rproc, -- cgit v1.2.3 From 23b0e695d4ca92e9ebd97689e2e51e497957cb48 Mon Sep 17 00:00:00 2001 From: Zack Rusin Date: Wed, 2 Mar 2022 10:24:23 -0500 Subject: drm/vmwgfx: Allow querying of the SVGA PCI id from the userspace Mesa3D loaders require knowledge of the devices PCI id. SVGAv2 and v3 have different PCI id's, but the same driver is used to handle them both. To allow Mesa3D svga driver to be loaded automatically for both SVGAv2 and SVGAv3 make the kernel return the PCI id of the currently running device. Signed-off-by: Zack Rusin Reviewed-by: Martin Krastev Reviewed-by: Maaz Mombasawala Link: https://patchwork.freedesktop.org/patch/msgid/20220302152426.885214-6-zack@kde.org --- include/uapi/drm/vmwgfx_drm.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h index 8277644c1144..26549c86a91f 100644 --- a/include/uapi/drm/vmwgfx_drm.h +++ b/include/uapi/drm/vmwgfx_drm.h @@ -1,6 +1,6 @@ /************************************************************************** * - * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA + * Copyright © 2009-2022 VMware, Inc., Palo Alto, CA., USA * All Rights Reserved. * * Permission is hereby granted, free of charge, to any person obtaining a @@ -92,6 +92,12 @@ extern "C" { * * DRM_VMW_PARAM_SM5 * SM5 support is enabled. + * + * DRM_VMW_PARAM_GL43 + * SM5.1+GL4.3 support is enabled. + * + * DRM_VMW_PARAM_DEVICE_ID + * PCI ID of the underlying SVGA device. */ #define DRM_VMW_PARAM_NUM_STREAMS 0 @@ -111,6 +117,7 @@ extern "C" { #define DRM_VMW_PARAM_SM4_1 14 #define DRM_VMW_PARAM_SM5 15 #define DRM_VMW_PARAM_GL43 16 +#define DRM_VMW_PARAM_DEVICE_ID 17 /** * enum drm_vmw_handle_type - handle type for ref ioctls -- cgit v1.2.3 From c13b780c4597e1e6cee3154053a196aa329b1367 Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Sun, 13 Feb 2022 14:12:42 -0600 Subject: remoteproc: Change rproc_shutdown() to return a status The rproc_shutdown() function is currently not returning any error code, and any failures within rproc_stop() are not passed back to the users. Change the signature to return a success value back to the callers. The remoteproc sysfs and cdev interfaces are also updated to return back this status to userspace. Signed-off-by: Suman Anna Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220213201246.25952-2-s-anna@ti.com --- include/linux/remoteproc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index b2ee325e0af1..7c943f0a2fc4 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -671,7 +671,7 @@ rproc_of_resm_mem_entry_init(struct device *dev, u32 of_resm_idx, size_t len, u32 da, const char *name, ...); int rproc_boot(struct rproc *rproc); -void rproc_shutdown(struct rproc *rproc); +int rproc_shutdown(struct rproc *rproc); int rproc_detach(struct rproc *rproc); int rproc_set_firmware(struct rproc *rproc, const char *fw_name); void rproc_report_crash(struct rproc *rproc, enum rproc_crash_type type); -- cgit v1.2.3 From 84bd3690bf54a2f2f3b8449afa022aac1957ba17 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 9 Mar 2022 19:49:37 -0800 Subject: nvdimm/namespace: Delete nd_namespace_blk Now that none of the configuration paths consider BLK namespaces, delete the BLK namespace data and supporting code. Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/164688417727.2879318.11691110761800109662.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/linux/nd.h | 26 -------------------------- 1 file changed, 26 deletions(-) (limited to 'include') diff --git a/include/linux/nd.h b/include/linux/nd.h index 4813c7089e5c..7b2ccbdc1cbc 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -136,27 +136,6 @@ struct nd_namespace_pmem { int id; }; -/** - * struct nd_namespace_blk - namespace for dimm-bounded persistent memory - * @alt_name: namespace name supplied in the dimm label - * @uuid: namespace name supplied in the dimm label - * @id: ida allocated id - * @lbasize: blk namespaces have a native sector size when btt not present - * @size: sum of all the resource ranges allocated to this namespace - * @num_resources: number of dpa extents to claim - * @res: discontiguous dpa extents for given dimm - */ -struct nd_namespace_blk { - struct nd_namespace_common common; - char *alt_name; - uuid_t *uuid; - int id; - unsigned long lbasize; - resource_size_t size; - int num_resources; - struct resource **res; -}; - static inline struct nd_namespace_io *to_nd_namespace_io(const struct device *dev) { return container_of(dev, struct nd_namespace_io, common.dev); @@ -169,11 +148,6 @@ static inline struct nd_namespace_pmem *to_nd_namespace_pmem(const struct device return container_of(nsio, struct nd_namespace_pmem, nsio); } -static inline struct nd_namespace_blk *to_nd_namespace_blk(const struct device *dev) -{ - return container_of(dev, struct nd_namespace_blk, common.dev); -} - /** * nvdimm_read_bytes() - synchronously read bytes from an nvdimm namespace * @ndns: device to read -- cgit v1.2.3 From 3b6c6c039707f6bb7c64af2aa82a437fabb93aee Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 9 Mar 2022 19:49:48 -0800 Subject: nvdimm/region: Delete nd_blk_region infrastructure Now that the nd_namespace_blk infrastructure is removed, delete all the region machinery to coordinate provisioning aliased capacity between PMEM and BLK. Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/164688418803.2879318.1302315202397235855.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/linux/libnvdimm.h | 24 ------------------------ include/uapi/linux/ndctl.h | 2 -- 2 files changed, 26 deletions(-) (limited to 'include') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 7074aa9af525..0d61e07b6827 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -25,8 +25,6 @@ struct badrange { }; enum { - /* when a dimm supports both PMEM and BLK access a label is required */ - NDD_ALIASING = 0, /* unarmed memory devices may not persist writes */ NDD_UNARMED = 1, /* locked memory devices should not be accessed */ @@ -35,8 +33,6 @@ enum { NDD_SECURITY_OVERWRITE = 3, /* tracking whether or not there is a pending device reference */ NDD_WORK_PENDING = 4, - /* ignore / filter NSLABEL_FLAG_LOCAL for this DIMM, i.e. no aliasing */ - NDD_NOBLK = 5, /* dimm supports namespace labels */ NDD_LABELING = 6, @@ -140,21 +136,6 @@ static inline void __iomem *devm_nvdimm_ioremap(struct device *dev, } struct nvdimm_bus; -struct module; -struct nd_blk_region; -struct nd_blk_region_desc { - int (*enable)(struct nvdimm_bus *nvdimm_bus, struct device *dev); - int (*do_io)(struct nd_blk_region *ndbr, resource_size_t dpa, - void *iobuf, u64 len, int rw); - struct nd_region_desc ndr_desc; -}; - -static inline struct nd_blk_region_desc *to_blk_region_desc( - struct nd_region_desc *ndr_desc) -{ - return container_of(ndr_desc, struct nd_blk_region_desc, ndr_desc); - -} /* * Note that separate bits for locked + unlocked are defined so that @@ -257,7 +238,6 @@ struct nvdimm_bus *nvdimm_to_bus(struct nvdimm *nvdimm); struct nvdimm *to_nvdimm(struct device *dev); struct nd_region *to_nd_region(struct device *dev); struct device *nd_region_dev(struct nd_region *nd_region); -struct nd_blk_region *to_nd_blk_region(struct device *dev); struct nvdimm_bus_descriptor *to_nd_desc(struct nvdimm_bus *nvdimm_bus); struct device *to_nvdimm_bus_dev(struct nvdimm_bus *nvdimm_bus); const char *nvdimm_name(struct nvdimm *nvdimm); @@ -295,10 +275,6 @@ struct nd_region *nvdimm_blk_region_create(struct nvdimm_bus *nvdimm_bus, struct nd_region *nvdimm_volatile_region_create(struct nvdimm_bus *nvdimm_bus, struct nd_region_desc *ndr_desc); void *nd_region_provider_data(struct nd_region *nd_region); -void *nd_blk_region_provider_data(struct nd_blk_region *ndbr); -void nd_blk_region_set_provider_data(struct nd_blk_region *ndbr, void *data); -struct nvdimm *nd_blk_region_to_dimm(struct nd_blk_region *ndbr); -unsigned long nd_blk_memremap_flags(struct nd_blk_region *ndbr); unsigned int nd_region_acquire_lane(struct nd_region *nd_region); void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane); u64 nd_fletcher64(void *addr, size_t len, bool le); diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index 8cf1e4884fd5..17e02b64ea2e 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -189,7 +189,6 @@ static inline const char *nvdimm_cmd_name(unsigned cmd) #define ND_DEVICE_REGION_BLK 3 /* nd_region: (parent of BLK namespaces) */ #define ND_DEVICE_NAMESPACE_IO 4 /* legacy persistent memory */ #define ND_DEVICE_NAMESPACE_PMEM 5 /* PMEM namespace (may alias with BLK) */ -#define ND_DEVICE_NAMESPACE_BLK 6 /* BLK namespace (may alias with PMEM) */ #define ND_DEVICE_DAX_PMEM 7 /* Device DAX interface to pmem */ enum nd_driver_flags { @@ -198,7 +197,6 @@ enum nd_driver_flags { ND_DRIVER_REGION_BLK = 1 << ND_DEVICE_REGION_BLK, ND_DRIVER_NAMESPACE_IO = 1 << ND_DEVICE_NAMESPACE_IO, ND_DRIVER_NAMESPACE_PMEM = 1 << ND_DEVICE_NAMESPACE_PMEM, - ND_DRIVER_NAMESPACE_BLK = 1 << ND_DEVICE_NAMESPACE_BLK, ND_DRIVER_DAX_PMEM = 1 << ND_DEVICE_DAX_PMEM, }; -- cgit v1.2.3 From c97448437847bd76116b3a077e44808e946bb1ae Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Fri, 25 Feb 2022 15:35:29 +0100 Subject: clk: Add clk_drop_range In order to reset the range on a clock, we need to call clk_set_rate_range with a minimum of 0 and a maximum of ULONG_MAX. Since it's fairly inconvenient, let's introduce a clk_drop_range() function that will do just this. Suggested-by: Stephen Boyd Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220225143534.405820-8-maxime@cerno.tech Signed-off-by: Stephen Boyd --- include/linux/clk.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/clk.h b/include/linux/clk.h index 266e8de3cb51..39faa54efe88 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -986,6 +986,17 @@ static inline void clk_bulk_disable_unprepare(int num_clks, clk_bulk_unprepare(num_clks, clks); } +/** + * clk_drop_range - Reset any range set on that clock + * @clk: clock source + * + * Returns success (0) or negative errno. + */ +static inline int clk_drop_range(struct clk *clk) +{ + return clk_set_rate_range(clk, 0, ULONG_MAX); +} + /** * clk_get_optional - lookup and obtain a reference to an optional clock * producer. -- cgit v1.2.3 From d3826a95222c44a527f76b011bb5af8c924632e9 Mon Sep 17 00:00:00 2001 From: Dirk van der Merwe Date: Fri, 11 Mar 2022 11:43:06 +0100 Subject: nfp: add support for NFP3800/NFP3803 PCIe devices Enable binding the nfp driver to NFP3800 and NFP3803 devices. The PCIE_SRAM offset is different for the NFP3800 device, which also only supports a single explicit group. Changes to Dirk's work: * 48-bit dma addressing is not ready yet. Keep 40-bit dma addressing for NFP3800. Signed-off-by: Dirk van der Merwe Signed-off-by: Jakub Kicinski Signed-off-by: Fei Qin Signed-off-by: Simon Horman Signed-off-by: Jakub Kicinski --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index c7e6f2043c7d..5462c29f0538 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2531,9 +2531,11 @@ #define PCI_VENDOR_ID_HUAWEI 0x19e5 #define PCI_VENDOR_ID_NETRONOME 0x19ee +#define PCI_DEVICE_ID_NETRONOME_NFP3800 0x3800 #define PCI_DEVICE_ID_NETRONOME_NFP4000 0x4000 #define PCI_DEVICE_ID_NETRONOME_NFP5000 0x5000 #define PCI_DEVICE_ID_NETRONOME_NFP6000 0x6000 +#define PCI_DEVICE_ID_NETRONOME_NFP3800_VF 0x3803 #define PCI_DEVICE_ID_NETRONOME_NFP6000_VF 0x6003 #define PCI_VENDOR_ID_QMI 0x1a32 -- cgit v1.2.3 From 625788b5844511cf4c30cffa7fa0bc3a69cebc82 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 10 Mar 2022 21:14:20 -0800 Subject: net: add per-cpu storage and net->core_stats Before adding yet another possibly contended atomic_long_t, it is time to add per-cpu storage for existing ones: dev->tx_dropped, dev->rx_dropped, and dev->rx_nohandler Because many devices do not have to increment such counters, allocate the per-cpu storage on demand, so that dev_get_stats() does not have to spend considerable time folding zero counters. Note that some drivers have abused these counters which were supposed to be only used by core networking stack. v4: should use per_cpu_ptr() in dev_get_stats() (Jakub) v3: added a READ_ONCE() in netdev_core_stats_alloc() (Paolo) v2: add a missing include (reported by kernel test robot ) Change in netdev_core_stats_alloc() (Jakub) Signed-off-by: Eric Dumazet Cc: jeffreyji Reviewed-by: Brian Vazquez Reviewed-by: Jakub Kicinski Acked-by: Paolo Abeni Link: https://lore.kernel.org/r/20220311051420.2608812-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 46 +++++++++++++++++++++++++++++++++++++--------- include/net/bonding.h | 2 +- 2 files changed, 38 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index acd3cf69b61f..0d994710b335 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -194,6 +195,14 @@ struct net_device_stats { unsigned long tx_compressed; }; +/* per-cpu stats, allocated on demand. + * Try to fit them in a single cache line, for dev_get_stats() sake. + */ +struct net_device_core_stats { + local_t rx_dropped; + local_t tx_dropped; + local_t rx_nohandler; +} __aligned(4 * sizeof(local_t)); #include #include @@ -1735,12 +1744,8 @@ enum netdev_ml_priv_type { * @stats: Statistics struct, which was left as a legacy, use * rtnl_link_stats64 instead * - * @rx_dropped: Dropped packets by core network, - * do not use this in drivers - * @tx_dropped: Dropped packets by core network, + * @core_stats: core networking counters, * do not use this in drivers - * @rx_nohandler: nohandler dropped packets by core network on - * inactive devices, do not use this in drivers * @carrier_up_count: Number of times the carrier has been up * @carrier_down_count: Number of times the carrier has been down * @@ -2023,9 +2028,7 @@ struct net_device { struct net_device_stats stats; /* not used by modern drivers */ - atomic_long_t rx_dropped; - atomic_long_t tx_dropped; - atomic_long_t rx_nohandler; + struct net_device_core_stats __percpu *core_stats; /* Stats to monitor link on/off, flapping */ atomic_t carrier_up_count; @@ -3839,13 +3842,38 @@ static __always_inline bool __is_skb_forwardable(const struct net_device *dev, return false; } +struct net_device_core_stats *netdev_core_stats_alloc(struct net_device *dev); + +static inline struct net_device_core_stats *dev_core_stats(struct net_device *dev) +{ + /* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */ + struct net_device_core_stats __percpu *p = READ_ONCE(dev->core_stats); + + if (likely(p)) + return this_cpu_ptr(p); + + return netdev_core_stats_alloc(dev); +} + +#define DEV_CORE_STATS_INC(FIELD) \ +static inline void dev_core_stats_##FIELD##_inc(struct net_device *dev) \ +{ \ + struct net_device_core_stats *p = dev_core_stats(dev); \ + \ + if (p) \ + local_inc(&p->FIELD); \ +} +DEV_CORE_STATS_INC(rx_dropped) +DEV_CORE_STATS_INC(tx_dropped) +DEV_CORE_STATS_INC(rx_nohandler) + static __always_inline int ____dev_forward_skb(struct net_device *dev, struct sk_buff *skb, const bool check_mtu) { if (skb_orphan_frags(skb, GFP_ATOMIC) || unlikely(!__is_skb_forwardable(dev, skb, check_mtu))) { - atomic_long_inc(&dev->rx_dropped); + dev_core_stats_rx_dropped_inc(dev); kfree_skb(skb); return NET_RX_DROP; } diff --git a/include/net/bonding.h b/include/net/bonding.h index d0dfe727e0b1..b14f4c0b4e9e 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -770,7 +770,7 @@ extern const struct sysfs_ops slave_sysfs_ops; static inline netdev_tx_t bond_tx_drop(struct net_device *dev, struct sk_buff *skb) { - atomic_long_inc(&dev->tx_dropped); + dev_core_stats_tx_dropped_inc(dev); dev_kfree_skb_any(skb); return NET_XMIT_DROP; } -- cgit v1.2.3 From f2aa197e4794bf4c2c0c9570684f86e6fa103e8b Mon Sep 17 00:00:00 2001 From: Chengming Zhou Date: Sat, 5 Mar 2022 11:41:03 +0800 Subject: cgroup: Fix suspicious rcu_dereference_check() usage warning task_css_set_check() will use rcu_dereference_check() to check for rcu_read_lock_held() on the read-side, which is not true after commit dc6e0818bc9a ("sched/cpuacct: Optimize away RCU read lock"). This commit drop explicit rcu_read_lock(), change to RCU-sched read-side critical section. So fix the RCU warning by adding check for rcu_read_lock_sched_held(). Fixes: dc6e0818bc9a ("sched/cpuacct: Optimize away RCU read lock") Reported-by: Linux Kernel Functional Testing Reported-by: syzbot+16e3f2c77e7c5a0113f9@syzkaller.appspotmail.com Signed-off-by: Chengming Zhou Signed-off-by: Peter Zijlstra (Intel) Acked-by: Tejun Heo Tested-by: Zhouyi Zhou Tested-by: Marek Szyprowski Link: https://lore.kernel.org/r/20220305034103.57123-1-zhouchengming@bytedance.com --- include/linux/cgroup.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 1e356c222756..0d1ada8968d7 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -450,6 +450,7 @@ extern struct mutex cgroup_mutex; extern spinlock_t css_set_lock; #define task_css_set_check(task, __c) \ rcu_dereference_check((task)->cgroups, \ + rcu_read_lock_sched_held() || \ lockdep_is_held(&cgroup_mutex) || \ lockdep_is_held(&css_set_lock) || \ ((task)->flags & PF_EXITING) || (__c)) -- cgit v1.2.3 From 6f98a4bfee72c22f50aedb39fb761567969865fe Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Mon, 7 Feb 2022 17:19:24 +0100 Subject: random: block in /dev/urandom This topic has come up countless times, and usually doesn't go anywhere. This time I thought I'd bring it up with a slightly narrower focus, updated for some developments over the last three years: we finally can make /dev/urandom always secure, in light of the fact that our RNG is now always seeded. Ever since Linus' 50ee7529ec45 ("random: try to actively add entropy rather than passively wait for it"), the RNG does a haveged-style jitter dance around the scheduler, in order to produce entropy (and credit it) for the case when we're stuck in wait_for_random_bytes(). How ever you feel about the Linus Jitter Dance is beside the point: it's been there for three years and usually gets the RNG initialized in a second or so. As a matter of fact, this is what happens currently when people use getrandom(). It's already there and working, and most people have been using it for years without realizing. So, given that the kernel has grown this mechanism for seeding itself from nothing, and that this procedure happens pretty fast, maybe there's no point any longer in having /dev/urandom give insecure bytes. In the past we didn't want the boot process to deadlock, which was understandable. But now, in the worst case, a second goes by, and the problem is resolved. It seems like maybe we're finally at a point when we can get rid of the infamous "urandom read hole". The one slight drawback is that the Linus Jitter Dance relies on random_ get_entropy() being implemented. The first lines of try_to_generate_ entropy() are: stack.now = random_get_entropy(); if (stack.now == random_get_entropy()) return; On most platforms, random_get_entropy() is simply aliased to get_cycles(). The number of machines without a cycle counter or some other implementation of random_get_entropy() in 2022, which can also run a mainline kernel, and at the same time have a both broken and out of date userspace that relies on /dev/urandom never blocking at boot is thought to be exceedingly low. And to be clear: those museum pieces without cycle counters will continue to run Linux just fine, and even /dev/urandom will be operable just like before; the RNG just needs to be seeded first through the usual means, which should already be the case now. On systems that really do want unseeded randomness, we already offer getrandom(GRND_INSECURE), which is in use by, e.g., systemd for seeding their hash tables at boot. Nothing in this commit would affect GRND_INSECURE, and it remains the means of getting those types of random numbers. This patch goes a long way toward eliminating a long overdue userspace crypto footgun. After several decades of endless user confusion, we will finally be able to say, "use any single one of our random interfaces and you'll be fine. They're all the same. It doesn't matter." And that, I think, is really something. Finally all of those blog posts and disagreeing forums and contradictory articles will all become correct about whatever they happened to recommend, and along with it, a whole class of vulnerabilities eliminated. With very minimal downside, we're finally in a position where we can make this change. Cc: Dinh Nguyen Cc: Nick Hu Cc: Max Filippov Cc: Palmer Dabbelt Cc: David S. Miller Cc: Yoshinori Sato Cc: Michal Simek Cc: Borislav Petkov Cc: Guo Ren Cc: Geert Uytterhoeven Cc: Joshua Kinard Cc: David Laight Cc: Dominik Brodowski Cc: Eric Biggers Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Thomas Gleixner Cc: Andy Lutomirski Cc: Kees Cook Cc: Lennart Poettering Cc: Konstantin Ryabitsev Cc: Linus Torvalds Cc: Greg Kroah-Hartman Cc: Theodore Ts'o Signed-off-by: Jason A. Donenfeld --- include/linux/random.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index 6148b8d1ccf3..725a4d08c0a0 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -44,7 +44,7 @@ extern void del_random_ready_callback(struct random_ready_callback *rdy); extern size_t __must_check get_random_bytes_arch(void *buf, size_t nbytes); #ifndef MODULE -extern const struct file_operations random_fops, urandom_fops; +extern const struct file_operations random_fops; #endif u32 get_random_u32(void); -- cgit v1.2.3 From ae099e8e98fb01395228628be5a4661e3bd86fe4 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 23 Feb 2022 13:43:44 +0100 Subject: random: add mechanism for VM forks to reinitialize crng When a VM forks, we must immediately mix in additional information to the stream of random output so that two forks or a rollback don't produce the same stream of random numbers, which could have catastrophic cryptographic consequences. This commit adds a simple API, add_vmfork_ randomness(), for that, by force reseeding the crng. This has the added benefit of also draining the entropy pool and setting its timer back, so that any old entropy that was there prior -- which could have already been used by a different fork, or generally gone stale -- does not contribute to the accounting of the next 256 bits. Cc: Dominik Brodowski Cc: Theodore Ts'o Cc: Jann Horn Cc: Eric Biggers Reviewed-by: Ard Biesheuvel Signed-off-by: Jason A. Donenfeld --- include/linux/random.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index 725a4d08c0a0..117468f3a92e 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -34,6 +34,7 @@ extern void add_input_randomness(unsigned int type, unsigned int code, extern void add_interrupt_randomness(int irq) __latent_entropy; extern void add_hwgenerator_randomness(const void *buffer, size_t count, size_t entropy); +extern void add_vmfork_randomness(const void *unique_vm_id, size_t size); extern void get_random_bytes(void *buf, size_t nbytes); extern int wait_for_random_bytes(void); -- cgit v1.2.3 From d273845ecb0e0626842782a4497f0c5876139ec3 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Fri, 25 Feb 2022 16:55:52 +0100 Subject: ACPI: allow longer device IDs We create a list of ACPI "PNP" IDs which contains _HID, _CID, and CLS entries of the respective devices. However, when making structs for matching, we squeeze those IDs into acpi_device_id, which only has 9 bytes space to store the identifier. The subsystem actually captures the full length of the IDs, and the modalias has the full length, but this struct we use for matching is limited. It originally had 16 bytes, but was changed to only have 9 in 6543becf26ff ("mod/file2alias: make modalias generation safe for cross compiling"), presumably on the theory that it would match the ACPI spec so it didn't matter. Unfortunately, while most people adhere to the ACPI specs, Microsoft decided that its VM Generation Counter device [1] should only be identifiable by _CID with a value of "VM_Gen_Counter", which is longer than 9 characters. To allow device drivers to match identifiers that exceed the 9 byte limit, this simply ups the length to 16, just like it was before the aforementioned commit. Empirical testing indicates that this doesn't actually increase vmlinux size on 64-bit, because the ulong in the same struct caused there to be 7 bytes of padding anyway, and when doing a s/M/Y/g i386_defconfig build, the bzImage only increased by 0.0055%, so negligible. This patch is a prerequisite to add support for VMGenID in Linux, the subsequent patch in this series. It has been confirmed to also work on the udev/modalias side in userspace. [1] https://download.microsoft.com/download/3/1/C/31CFC307-98CA-4CA5-914C-D9772691E214/VirtualMachineGenerationID.docx Signed-off-by: Alexander Graf Co-developed-by: Jason A. Donenfeld [Jason: reworked commit message a bit, went with len=16 approach.] Cc: Mika Westerberg Cc: Andy Shevchenko Cc: Len Brown Cc: Greg Kroah-Hartman Reviewed-by: Ard Biesheuvel Acked-by: Hans de Goede Acked-by: Rafael J. Wysocki Signed-off-by: Jason A. Donenfeld --- include/linux/mod_devicetable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 4bb71979a8fd..5da5d990ff58 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -211,7 +211,7 @@ struct css_device_id { kernel_ulong_t driver_data; }; -#define ACPI_ID_LEN 9 +#define ACPI_ID_LEN 16 struct acpi_device_id { __u8 id[ACPI_ID_LEN]; -- cgit v1.2.3 From a4107d34f960df99ca07fa8eb022425a804f59f3 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Tue, 1 Mar 2022 15:14:04 +0100 Subject: random: do not export add_vmfork_randomness() unless needed Since add_vmfork_randomness() is only called from vmgenid.o, we can guard it in CONFIG_VMGENID, similarly to how we do with add_disk_randomness() and CONFIG_BLOCK. If we ever have multiple things calling into add_vmfork_randomness(), we can add another shared Kconfig symbol for that, but for now, this is good enough. Even though add_vmfork_randomess() is a pretty small function, removing it means that there are only calls to crng_reseed(false) and none to crng_reseed(true), which means the compiler can constant propagate the false, removing branches from crng_reseed() and its descendants. Additionally, we don't even need the symbol to be exported if CONFIG_VMGENID is not a module, so conditionalize that too. Cc: Dominik Brodowski Cc: Theodore Ts'o Signed-off-by: Jason A. Donenfeld --- include/linux/random.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index 117468f3a92e..f209f1a78899 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -34,7 +34,9 @@ extern void add_input_randomness(unsigned int type, unsigned int code, extern void add_interrupt_randomness(int irq) __latent_entropy; extern void add_hwgenerator_randomness(const void *buffer, size_t count, size_t entropy); +#if IS_ENABLED(CONFIG_VMGENID) extern void add_vmfork_randomness(const void *unique_vm_id, size_t size); +#endif extern void get_random_bytes(void *buf, size_t nbytes); extern int wait_for_random_bytes(void); -- cgit v1.2.3 From 5acd35487dc911541672b3ffc322851769c32a56 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Tue, 1 Mar 2022 20:03:49 +0100 Subject: random: replace custom notifier chain with standard one We previously rolled our own randomness readiness notifier, which only has two users in the whole kernel. Replace this with a more standard atomic notifier block that serves the same purpose with less code. Also unexport the symbols, because no modules use it, only unconditional builtins. The only drawback is that it's possible for a notification handler returning the "stop" code to prevent further processing, but given that there are only two users, and that we're unexporting this anyway, that doesn't seem like a significant drawback for the simplification we receive here. Cc: Greg Kroah-Hartman Cc: Theodore Ts'o Reviewed-by: Dominik Brodowski Signed-off-by: Jason A. Donenfeld --- include/linux/random.h | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index f209f1a78899..fab1ab0563b4 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -10,11 +10,7 @@ #include -struct random_ready_callback { - struct list_head list; - void (*func)(struct random_ready_callback *rdy); - struct module *owner; -}; +struct notifier_block; extern void add_device_randomness(const void *, size_t); extern void add_bootloader_randomness(const void *, size_t); @@ -42,8 +38,8 @@ extern void get_random_bytes(void *buf, size_t nbytes); extern int wait_for_random_bytes(void); extern int __init rand_initialize(void); extern bool rng_is_initialized(void); -extern int add_random_ready_callback(struct random_ready_callback *rdy); -extern void del_random_ready_callback(struct random_ready_callback *rdy); +extern int register_random_ready_notifier(struct notifier_block *nb); +extern int unregister_random_ready_notifier(struct notifier_block *nb); extern size_t __must_check get_random_bytes_arch(void *buf, size_t nbytes); #ifndef MODULE -- cgit v1.2.3 From f3c2682bad7bc6033c837e9c66e5af881fe8d465 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Tue, 1 Mar 2022 20:22:39 +0100 Subject: random: provide notifier for VM fork Drivers such as WireGuard need to learn when VMs fork in order to clear sessions. This commit provides a simple notifier_block for that, with a register and unregister function. When no VM fork detection is compiled in, this turns into a no-op, similar to how the power notifier works. Cc: Dominik Brodowski Cc: Theodore Ts'o Reviewed-by: Greg Kroah-Hartman Signed-off-by: Jason A. Donenfeld --- include/linux/random.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index fab1ab0563b4..c0baffe7afb1 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -32,6 +32,11 @@ extern void add_hwgenerator_randomness(const void *buffer, size_t count, size_t entropy); #if IS_ENABLED(CONFIG_VMGENID) extern void add_vmfork_randomness(const void *unique_vm_id, size_t size); +extern int register_random_vmfork_notifier(struct notifier_block *nb); +extern int unregister_random_vmfork_notifier(struct notifier_block *nb); +#else +static inline int register_random_vmfork_notifier(struct notifier_block *nb) { return 0; } +static inline int unregister_random_vmfork_notifier(struct notifier_block *nb) { return 0; } #endif extern void get_random_bytes(void *buf, size_t nbytes); -- cgit v1.2.3 From df227dc8a68d81b7fe3416eca16d1f21d0b537f0 Mon Sep 17 00:00:00 2001 From: Dave Gerlach Date: Wed, 9 Feb 2022 22:16:31 -0600 Subject: mailbox: ti-msgmgr: Operate mailbox in polled mode during system suspend During the system suspend path we must set all queues to operate in polled mode as it is possible for any protocol built using this mailbox, such as TISCI, to require communication during the no irq phase of suspend, and we cannot rely on interrupts there. Polled mode is implemented by allowing the mailbox user to define an RX channel as part of the message that is sent which is what gets polled for a response. If polled mode is enabled, this will immediately be polled for a response at the end of the mailbox send_data op before returning success for the data send or timing out if no response is received. Finally, to ensure polled mode is always enabled during system suspend, iterate through all queues to set RX queues to polled mode during system suspend and disable polled mode for all in the resume handler. Signed-off-by: Dave Gerlach Signed-off-by: Jassi Brar --- include/linux/soc/ti/ti-msgmgr.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/soc/ti/ti-msgmgr.h b/include/linux/soc/ti/ti-msgmgr.h index 1f6e76d423cf..69a8d7682c4b 100644 --- a/include/linux/soc/ti/ti-msgmgr.h +++ b/include/linux/soc/ti/ti-msgmgr.h @@ -1,7 +1,7 @@ /* * Texas Instruments' Message Manager * - * Copyright (C) 2015-2016 Texas Instruments Incorporated - https://www.ti.com/ + * Copyright (C) 2015-2022 Texas Instruments Incorporated - https://www.ti.com/ * Nishanth Menon * * This program is free software; you can redistribute it and/or modify @@ -17,10 +17,14 @@ #ifndef TI_MSGMGR_H #define TI_MSGMGR_H +struct mbox_chan; + /** * struct ti_msgmgr_message - Message Manager structure * @len: Length of data in the Buffer * @buf: Buffer pointer + * @chan_rx: Expected channel for response, must be provided to use polled rx + * @timeout_rx_ms: Timeout value to use if polling for response * * This is the structure for data used in mbox_send_message * the length of data buffer used depends on the SoC integration @@ -30,6 +34,8 @@ struct ti_msgmgr_message { size_t len; u8 *buf; + struct mbox_chan *chan_rx; + int timeout_rx_ms; }; #endif /* TI_MSGMGR_H */ -- cgit v1.2.3 From 7af1974af0a9ba8a8ed2e3e947d87dd4d9a78d27 Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Sat, 12 Mar 2022 11:09:47 +0530 Subject: ext4: fix ext4_fc_stats trace point ftrace's __print_symbolic() requires that any enum values used in the symbol to string translation table be wrapped in a TRACE_DEFINE_ENUM so that the enum value can be decoded from the ftrace ring buffer by user space tooling. This patch also fixes few other problems found in this trace point. e.g. dereferencing structures in TP_printk which should not be done at any cost. Also to avoid checkpatch warnings, this patch removes those whitespaces/tab stops issues. Cc: stable@kernel.org Fixes: aa75f4d3daae ("ext4: main fast-commit commit path") Reported-by: Steven Rostedt Signed-off-by: Ritesh Harjani Reviewed-by: Jan Kara Reviewed-by: Steven Rostedt (Google) Reviewed-by: Harshad Shirwadkar Link: https://lore.kernel.org/r/b4b9691414c35c62e570b723e661c80674169f9a.1647057583.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o --- include/trace/events/ext4.h | 78 ++++++++++++++++++++++++++++----------------- 1 file changed, 49 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 19e957b7f941..1a0b7030f72a 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -95,6 +95,17 @@ TRACE_DEFINE_ENUM(ES_REFERENCED_B); { FALLOC_FL_COLLAPSE_RANGE, "COLLAPSE_RANGE"}, \ { FALLOC_FL_ZERO_RANGE, "ZERO_RANGE"}) +TRACE_DEFINE_ENUM(EXT4_FC_REASON_XATTR); +TRACE_DEFINE_ENUM(EXT4_FC_REASON_CROSS_RENAME); +TRACE_DEFINE_ENUM(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE); +TRACE_DEFINE_ENUM(EXT4_FC_REASON_NOMEM); +TRACE_DEFINE_ENUM(EXT4_FC_REASON_SWAP_BOOT); +TRACE_DEFINE_ENUM(EXT4_FC_REASON_RESIZE); +TRACE_DEFINE_ENUM(EXT4_FC_REASON_RENAME_DIR); +TRACE_DEFINE_ENUM(EXT4_FC_REASON_FALLOC_RANGE); +TRACE_DEFINE_ENUM(EXT4_FC_REASON_INODE_JOURNAL_DATA); +TRACE_DEFINE_ENUM(EXT4_FC_REASON_MAX); + #define show_fc_reason(reason) \ __print_symbolic(reason, \ { EXT4_FC_REASON_XATTR, "XATTR"}, \ @@ -2723,41 +2734,50 @@ TRACE_EVENT(ext4_fc_commit_stop, #define FC_REASON_NAME_STAT(reason) \ show_fc_reason(reason), \ - __entry->sbi->s_fc_stats.fc_ineligible_reason_count[reason] + __entry->fc_ineligible_rc[reason] TRACE_EVENT(ext4_fc_stats, - TP_PROTO(struct super_block *sb), - - TP_ARGS(sb), + TP_PROTO(struct super_block *sb), - TP_STRUCT__entry( - __field(dev_t, dev) - __field(struct ext4_sb_info *, sbi) - __field(int, count) - ), + TP_ARGS(sb), - TP_fast_assign( - __entry->dev = sb->s_dev; - __entry->sbi = EXT4_SB(sb); - ), + TP_STRUCT__entry( + __field(dev_t, dev) + __array(unsigned int, fc_ineligible_rc, EXT4_FC_REASON_MAX) + __field(unsigned long, fc_commits) + __field(unsigned long, fc_ineligible_commits) + __field(unsigned long, fc_numblks) + ), - TP_printk("dev %d:%d fc ineligible reasons:\n" - "%s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d; " - "num_commits:%ld, ineligible: %ld, numblks: %ld", - MAJOR(__entry->dev), MINOR(__entry->dev), - FC_REASON_NAME_STAT(EXT4_FC_REASON_XATTR), - FC_REASON_NAME_STAT(EXT4_FC_REASON_CROSS_RENAME), - FC_REASON_NAME_STAT(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE), - FC_REASON_NAME_STAT(EXT4_FC_REASON_NOMEM), - FC_REASON_NAME_STAT(EXT4_FC_REASON_SWAP_BOOT), - FC_REASON_NAME_STAT(EXT4_FC_REASON_RESIZE), - FC_REASON_NAME_STAT(EXT4_FC_REASON_RENAME_DIR), - FC_REASON_NAME_STAT(EXT4_FC_REASON_FALLOC_RANGE), - FC_REASON_NAME_STAT(EXT4_FC_REASON_INODE_JOURNAL_DATA), - __entry->sbi->s_fc_stats.fc_num_commits, - __entry->sbi->s_fc_stats.fc_ineligible_commits, - __entry->sbi->s_fc_stats.fc_numblks) + TP_fast_assign( + int i; + __entry->dev = sb->s_dev; + for (i = 0; i < EXT4_FC_REASON_MAX; i++) { + __entry->fc_ineligible_rc[i] = + EXT4_SB(sb)->s_fc_stats.fc_ineligible_reason_count[i]; + } + __entry->fc_commits = EXT4_SB(sb)->s_fc_stats.fc_num_commits; + __entry->fc_ineligible_commits = + EXT4_SB(sb)->s_fc_stats.fc_ineligible_commits; + __entry->fc_numblks = EXT4_SB(sb)->s_fc_stats.fc_numblks; + ), + + TP_printk("dev %d,%d fc ineligible reasons:\n" + "%s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u " + "num_commits:%lu, ineligible: %lu, numblks: %lu", + MAJOR(__entry->dev), MINOR(__entry->dev), + FC_REASON_NAME_STAT(EXT4_FC_REASON_XATTR), + FC_REASON_NAME_STAT(EXT4_FC_REASON_CROSS_RENAME), + FC_REASON_NAME_STAT(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE), + FC_REASON_NAME_STAT(EXT4_FC_REASON_NOMEM), + FC_REASON_NAME_STAT(EXT4_FC_REASON_SWAP_BOOT), + FC_REASON_NAME_STAT(EXT4_FC_REASON_RESIZE), + FC_REASON_NAME_STAT(EXT4_FC_REASON_RENAME_DIR), + FC_REASON_NAME_STAT(EXT4_FC_REASON_FALLOC_RANGE), + FC_REASON_NAME_STAT(EXT4_FC_REASON_INODE_JOURNAL_DATA), + __entry->fc_commits, __entry->fc_ineligible_commits, + __entry->fc_numblks) ); #define DEFINE_TRACE_DENTRY_EVENT(__type) \ -- cgit v1.2.3 From 8cb5a30372ef5cf2b1d258fce1711d80f834740a Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Sat, 12 Mar 2022 11:09:48 +0530 Subject: ext4: convert ext4_fc_track_dentry type events to use event class One should use DECLARE_EVENT_CLASS for similar event types instead of defining TRACE_EVENT for each event type. This is helpful in reducing the text section footprint for e.g. [1] [1]: https://lwn.net/Articles/381064/ Signed-off-by: Ritesh Harjani Reviewed-by: Harshad Shirwadkar Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/a019cb46219ef4b30e4d98d7ced7d8819a2fc61d.1647057583.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o --- include/trace/events/ext4.h | 56 +++++++++++++++++++++++++-------------------- 1 file changed, 31 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 1a0b7030f72a..3d48fcb62987 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -2780,33 +2780,39 @@ TRACE_EVENT(ext4_fc_stats, __entry->fc_numblks) ); -#define DEFINE_TRACE_DENTRY_EVENT(__type) \ - TRACE_EVENT(ext4_fc_track_##__type, \ - TP_PROTO(struct inode *inode, struct dentry *dentry, int ret), \ - \ - TP_ARGS(inode, dentry, ret), \ - \ - TP_STRUCT__entry( \ - __field(dev_t, dev) \ - __field(int, ino) \ - __field(int, error) \ - ), \ - \ - TP_fast_assign( \ - __entry->dev = inode->i_sb->s_dev; \ - __entry->ino = inode->i_ino; \ - __entry->error = ret; \ - ), \ - \ - TP_printk("dev %d:%d, inode %d, error %d, fc_%s", \ - MAJOR(__entry->dev), MINOR(__entry->dev), \ - __entry->ino, __entry->error, \ - #__type) \ +DECLARE_EVENT_CLASS(ext4_fc_track_dentry, + + TP_PROTO(struct inode *inode, struct dentry *dentry, int ret), + + TP_ARGS(inode, dentry, ret), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, i_ino) + __field(int, error) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->i_ino = inode->i_ino; + __entry->error = ret; + ), + + TP_printk("dev %d,%d, ino %lu, error %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->i_ino, __entry->error ) +); + +#define DEFINE_EVENT_CLASS_DENTRY(__type) \ +DEFINE_EVENT(ext4_fc_track_dentry, ext4_fc_track_##__type, \ + TP_PROTO(struct inode *inode, struct dentry *dentry, int ret), \ + TP_ARGS(inode, dentry, ret) \ +) -DEFINE_TRACE_DENTRY_EVENT(create); -DEFINE_TRACE_DENTRY_EVENT(link); -DEFINE_TRACE_DENTRY_EVENT(unlink); +DEFINE_EVENT_CLASS_DENTRY(create); +DEFINE_EVENT_CLASS_DENTRY(link); +DEFINE_EVENT_CLASS_DENTRY(unlink); TRACE_EVENT(ext4_fc_track_inode, TP_PROTO(struct inode *inode, int ret), -- cgit v1.2.3 From 8109517b394e6deab5fd21cc5460e82ffed229c6 Mon Sep 17 00:00:00 2001 From: Arnaud Pouliquen Date: Mon, 24 Jan 2022 11:25:24 +0100 Subject: rpmsg: ctrl: Introduce new RPMSG_CREATE/RELEASE_DEV_IOCTL controls Allow the user space application to create and release an rpmsg device by adding RPMSG_CREATE_DEV_IOCTL and RPMSG_RELEASE_DEV_IOCTL ioctrls to the /dev/rpmsg_ctrl interface The RPMSG_CREATE_DEV_IOCTL Ioctl can be used to instantiate a local rpmsg device. Depending on the back-end implementation, the associated rpmsg driver is probed and a NS announcement can be sent to the remote processor. The RPMSG_RELEASE_DEV_IOCTL allows the user application to release a rpmsg device created either by the remote processor or with the RPMSG_CREATE_DEV_IOCTL call. Depending on the back-end implementation, the associated rpmsg driver is removed and a NS destroy rpmsg can be sent to the remote processor. Suggested-by: Mathieu Poirier Signed-off-by: Arnaud Pouliquen Reviewed-by: Mathieu Poirier Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220124102524.295783-12-arnaud.pouliquen@foss.st.com --- include/uapi/linux/rpmsg.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/rpmsg.h b/include/uapi/linux/rpmsg.h index f5ca8740f3fb..1637e68177d9 100644 --- a/include/uapi/linux/rpmsg.h +++ b/include/uapi/linux/rpmsg.h @@ -33,4 +33,14 @@ struct rpmsg_endpoint_info { */ #define RPMSG_DESTROY_EPT_IOCTL _IO(0xb5, 0x2) +/** + * Instantiate a new local rpmsg service device. + */ +#define RPMSG_CREATE_DEV_IOCTL _IOW(0xb5, 0x3, struct rpmsg_endpoint_info) + +/** + * Release a local rpmsg device. + */ +#define RPMSG_RELEASE_DEV_IOCTL _IOW(0xb5, 0x4, struct rpmsg_endpoint_info) + #endif -- cgit v1.2.3 From b5fdf66f6eb2560784c6f60131dc567de06267dc Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Tue, 1 Mar 2022 14:37:27 -0500 Subject: NFS: Remove remaining dfprintks related to fscache and remove NFSDBG_FSCACHE The fscache cookie APIs including fscache_acquire_cookie() and fscache_relinquish_cookie() now have very good tracing. Thus, there is no real need for dfprintks in the NFS fscache interface. The NFS fscache interface has removed all dfprintks so remove the NFSDBG_FSCACHE defines. Signed-off-by: Dave Wysochanski Signed-off-by: Trond Myklebust --- include/uapi/linux/nfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/nfs_fs.h b/include/uapi/linux/nfs_fs.h index 3afe3767c55d..ae0de165c014 100644 --- a/include/uapi/linux/nfs_fs.h +++ b/include/uapi/linux/nfs_fs.h @@ -52,7 +52,7 @@ #define NFSDBG_CALLBACK 0x0100 #define NFSDBG_CLIENT 0x0200 #define NFSDBG_MOUNT 0x0400 -#define NFSDBG_FSCACHE 0x0800 +#define NFSDBG_FSCACHE 0x0800 /* unused */ #define NFSDBG_PNFS 0x1000 #define NFSDBG_PNFS_LD 0x2000 #define NFSDBG_STATE 0x4000 -- cgit v1.2.3 From a41b05edfedb939440e83666f23de3ef9af33acf Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 7 Mar 2022 10:41:44 +1100 Subject: SUNRPC/auth: async tasks mustn't block waiting for memory When memory is short, new worker threads cannot be created and we depend on the minimum one rpciod thread to be able to handle everything. So it must not block waiting for memory. mempools are particularly a problem as memory can only be released back to the mempool by an async rpc task running. If all available workqueue threads are waiting on the mempool, no thread is available to return anything. lookup_cred() can block on a mempool or kmalloc - and this can cause deadlocks. So add a new RPCAUTH_LOOKUP flag for async lookups and don't block on memory. If the -ENOMEM gets back to call_refreshresult(), wait a short while and try again. HZ>>4 is chosen as it is used elsewhere for -ENOMEM retries. Signed-off-by: NeilBrown Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 98da816b5fc2..3e6ce288a7fc 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -99,6 +99,7 @@ struct rpc_auth_create_args { /* Flags for rpcauth_lookupcred() */ #define RPCAUTH_LOOKUP_NEW 0x01 /* Accept an uninitialised cred */ +#define RPCAUTH_LOOKUP_ASYNC 0x02 /* Don't block waiting for memory */ /* * Client authentication ops -- cgit v1.2.3 From 89c2be8a951654758dffeaaa6272328d9c8f29be Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 7 Mar 2022 10:41:44 +1100 Subject: NFS: discard NFS_RPC_SWAPFLAGS and RPC_TASK_ROOTCREDS NFS_RPC_SWAPFLAGS is only used for READ requests. It sets RPC_TASK_SWAPPER which gives some memory-allocation priority to requests. This is not needed for swap READ - though it is for writes where it is set via a different mechanism. RPC_TASK_ROOTCREDS causes the 'machine' credential to be used. This is not needed as the root credential is saved when the swap file is opened, and this is used for all IO. So NFS_RPC_SWAPFLAGS isn't needed, and as it is the only user of RPC_TASK_ROOTCREDS, that isn't needed either. Remove both. Signed-off-by: NeilBrown Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 5 ----- include/linux/sunrpc/sched.h | 1 - include/trace/events/sunrpc.h | 1 - 3 files changed, 7 deletions(-) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 3893386ceaed..9074ed0b65aa 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -45,11 +45,6 @@ */ #define NFS_MAX_TRANSPORTS 16 -/* - * These are the default flags for swap requests - */ -#define NFS_RPC_SWAPFLAGS (RPC_TASK_SWAPPER|RPC_TASK_ROOTCREDS) - /* * Size of the NFS directory verifier */ diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index db964bb63912..56710f8056d3 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -124,7 +124,6 @@ struct rpc_task_setup { #define RPC_TASK_MOVEABLE 0x0004 /* nfs4.1+ rpc tasks */ #define RPC_TASK_NULLCREDS 0x0010 /* Use AUTH_NULL credential */ #define RPC_CALL_MAJORSEEN 0x0020 /* major timeout seen */ -#define RPC_TASK_ROOTCREDS 0x0040 /* force root creds */ #define RPC_TASK_DYNAMIC 0x0080 /* task was kmalloc'ed */ #define RPC_TASK_NO_ROUND_ROBIN 0x0100 /* send requests on "main" xprt */ #define RPC_TASK_SOFT 0x0200 /* Use soft timeouts */ diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 29982d60b68a..ac33892da411 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -311,7 +311,6 @@ TRACE_EVENT(rpc_request, { RPC_TASK_MOVEABLE, "MOVEABLE" }, \ { RPC_TASK_NULLCREDS, "NULLCREDS" }, \ { RPC_CALL_MAJORSEEN, "MAJORSEEN" }, \ - { RPC_TASK_ROOTCREDS, "ROOTCREDS" }, \ { RPC_TASK_DYNAMIC, "DYNAMIC" }, \ { RPC_TASK_NO_ROUND_ROBIN, "NO_ROUND_ROBIN" }, \ { RPC_TASK_SOFT, "SOFT" }, \ -- cgit v1.2.3 From 4dc73c679114a2f408567e2e44770ed934190db2 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 7 Mar 2022 10:41:44 +1100 Subject: NFSv4: keep state manager thread active if swap is enabled If we are swapping over NFSv4, we may not be able to allocate memory to start the state-manager thread at the time when we need it. So keep it always running when swap is enabled, and just signal it to start. This requires updating and testing the cl_swapper count on the root rpc_clnt after following all ->cl_parent links. Signed-off-by: NeilBrown Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 82f7c2730b9a..49ba486aea5f 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1797,6 +1797,8 @@ struct nfs_rpc_ops { struct nfs_server *(*clone_server)(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, rpc_authflavor_t); int (*discover_trunking)(struct nfs_server *, struct nfs_fh *); + void (*enable_swap)(struct inode *inode); + void (*disable_swap)(struct inode *inode); }; /* -- cgit v1.2.3 From 64158668ac8b31626a8ce48db4cad08496eb8340 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 7 Mar 2022 10:41:44 +1100 Subject: NFS: swap IO handling is slightly different for O_DIRECT IO 1/ Taking the i_rwsem for swap IO triggers lockdep warnings regarding possible deadlocks with "fs_reclaim". These deadlocks could, I believe, eventuate if a buffered read on the swapfile was attempted. We don't need coherence with the page cache for a swap file, and buffered writes are forbidden anyway. There is no other need for i_rwsem during direct IO. So never take it for swap_rw() 2/ generic_write_checks() explicitly forbids writes to swap, and performs checks that are not needed for swap. So bypass it for swap_rw(). Signed-off-by: NeilBrown Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 9074ed0b65aa..c47c448befc8 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -508,10 +508,10 @@ static inline const struct cred *nfs_file_cred(struct file *file) * linux/fs/nfs/direct.c */ extern ssize_t nfs_direct_IO(struct kiocb *, struct iov_iter *); -extern ssize_t nfs_file_direct_read(struct kiocb *iocb, - struct iov_iter *iter); -extern ssize_t nfs_file_direct_write(struct kiocb *iocb, - struct iov_iter *iter); +ssize_t nfs_file_direct_read(struct kiocb *iocb, + struct iov_iter *iter, bool swap); +ssize_t nfs_file_direct_write(struct kiocb *iocb, + struct iov_iter *iter, bool swap); /* * linux/fs/nfs/dir.c -- cgit v1.2.3 From 1f4a5983d623d6dbda4cc7587a2d9d798e0d4035 Mon Sep 17 00:00:00 2001 From: Ziyang Xuan Date: Fri, 11 Mar 2022 17:04:03 +0800 Subject: net: macvlan: add net device refcount tracker Add net device refcount tracker to macvlan. Signed-off-by: Ziyang Xuan Signed-off-by: David S. Miller --- include/linux/if_macvlan.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 10c94a3936ca..b42294739063 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -21,6 +21,7 @@ struct macvlan_dev { struct hlist_node hlist; struct macvlan_port *port; struct net_device *lowerdev; + netdevice_tracker dev_tracker; void *accel_priv; struct vlan_pcpu_stats __percpu *pcpu_stats; -- cgit v1.2.3 From fbd9a2ceba5c74bbfa19cf257ae4b4b2c820860d Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 11 Mar 2022 16:03:42 +0100 Subject: net: Add lockdep asserts to ____napi_schedule(). ____napi_schedule() needs to be invoked with disabled interrupts due to __raise_softirq_irqoff (in order not to corrupt the per-CPU list). ____napi_schedule() needs also to be invoked from an interrupt context so that the raised-softirq is processed while the interrupt context is left. Add lockdep asserts for both conditions. While this is the second time the irq/softirq check is needed, provide a generic lockdep_assert_softirq_will_run() which is used by both caller. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: David S. Miller --- include/linux/lockdep.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 467b94257105..0cc65d216701 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -329,6 +329,12 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); #define lockdep_assert_none_held_once() \ lockdep_assert_once(!current->lockdep_depth) +/* + * Ensure that softirq is handled within the callchain and not delayed and + * handled by chance. + */ +#define lockdep_assert_softirq_will_run() \ + lockdep_assert_once(hardirq_count() | softirq_count()) #define lockdep_recursing(tsk) ((tsk)->lockdep_recursion) @@ -414,6 +420,7 @@ extern int lockdep_is_held(const void *); #define lockdep_assert_held_read(l) do { (void)(l); } while (0) #define lockdep_assert_held_once(l) do { (void)(l); } while (0) #define lockdep_assert_none_held_once() do { } while (0) +#define lockdep_assert_softirq_will_run() do { } while (0) #define lockdep_recursing(tsk) (0) -- cgit v1.2.3 From d538eca85c2aa6ecb5036e6ff47efc93d9f294da Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 11 Mar 2022 23:15:18 +0200 Subject: net: dsa: report and change port default priority using dcbnl The port-based default QoS class is assigned to packets that lack a VLAN PCP (or the port is configured to not trust the VLAN PCP), an IP DSCP (or the port is configured to not trust IP DSCP), and packets on which no tc-skbedit action has matched. Similar to other drivers, this can be exposed to user space using the DCB Application Priority Table. IEEE 802.1Q-2018 specifies in Table D-8 - Sel field values that when the Selector is 1, the Protocol ID value of 0 denotes the "Default application priority. For use when application priority is not otherwise specified." The way in which the dcbnl integration in DSA has been designed has to do with its requirements. Andrew Lunn explains that SOHO switches are expected to come with some sort of pre-configured QoS profile, and that it is desirable for this to come pre-loaded into the DSA slave interfaces' DCB application priority table. In the dcbnl design, this is possible because calls to dcb_ieee_setapp() can be initiated by anyone including being self-initiated by this device driver. However, what makes this challenging to implement in DSA is that the DSA core manages the net_devices (effectively hiding them from drivers), while drivers manage the hardware. The DSA core has no knowledge of what individual drivers' QoS policies are. DSA could export to drivers a wrapper over dcb_ieee_setapp() and these could call that function to pre-populate the app priority table, however drivers don't have a good moment in time to do this. The dsa_switch_ops :: setup() method gets called before the net_devices are created (dsa_slave_create), and so is dsa_switch_ops :: port_setup(). What remains is dsa_switch_ops :: port_enable(), but this gets called upon each ndo_open. If we add app table entries on every open, we'd need to remove them on close, to avoid duplicate entry errors. But if we delete app priority entries on close, what we delete may not be the initial, driver pre-populated entries, but rather user-added entries. So it is clear that letting drivers choose the timing of the dcb_ieee_setapp() call is inappropriate. The alternative which was chosen is to introduce hardware-specific ops in dsa_switch_ops, and effectively hide dcbnl details from drivers as well. For pre-populating the application table, dsa_slave_dcbnl_init() will call ds->ops->port_get_default_prio() which is supposed to read from hardware. If the operation succeeds, DSA creates a default-prio app table entry. The method is called as soon as the slave_dev is registered, but before we release the rtnl_mutex. This is done such that user space sees the app table entries as soon as it sees the interface being registered. The fact that we populate slave_dev->dcbnl_ops with a non-NULL pointer changes behavior in dcb_doit() from net/dcb/dcbnl.c, which used to return -EOPNOTSUPP for any dcbnl operation where netdev->dcbnl_ops is NULL. Because there are still dcbnl-unaware DSA drivers even if they have dcbnl_ops populated, the way to restore the behavior is to make all dcbnl_ops return -EOPNOTSUPP on absence of the hardware-specific dsa_switch_ops method. The dcbnl framework absurdly allows there to be more than one app table entry for the same selector and protocol (in other words, more than one port-based default priority). In the iproute2 dcb program, there is a "replace" syntactical sugar command which performs an "add" and a "del" to hide this away. But we choose the largest configured priority when we call ds->ops->port_set_default_prio(), using __fls(). When there is no default-prio app table entry left, the port-default priority is restored to 0. Link: https://patchwork.kernel.org/project/netdevbpf/patch/20210113154139.1803705-2-olteanv@gmail.com/ Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/dsa.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 9d16505fc0e2..1220af73151b 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -892,6 +892,13 @@ struct dsa_switch_ops { int (*get_ts_info)(struct dsa_switch *ds, int port, struct ethtool_ts_info *ts); + /* + * DCB ops + */ + int (*port_get_default_prio)(struct dsa_switch *ds, int port); + int (*port_set_default_prio)(struct dsa_switch *ds, int port, + u8 prio); + /* * Suspend and resume */ -- cgit v1.2.3 From 47d75f7822064d024ec9207c0fc1777f983783b7 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 11 Mar 2022 23:15:19 +0200 Subject: net: dsa: report and change port dscp priority using dcbnl Similar to the port-based default priority, IEEE 802.1Q-2018 allows the Application Priority Table to define QoS classes (0 to 7) per IP DSCP value (0 to 63). In the absence of an app table entry for a packet with DSCP value X, QoS classification for that packet falls back to other methods (VLAN PCP or port-based default). The presence of an app table for DSCP value X with priority Y makes the hardware classify the packet to QoS class Y. As opposed to the default-prio where DSA exposes only a "set" in dsa_switch_ops (because the port-based default is the fallback, it always exists, either implicitly or explicitly), for DSCP priorities we expose an "add" and a "del". The addition of a DSCP entry means trusting that DSCP priority, the deletion means ignoring it. Drivers that already trust (at least some) DSCP values can describe their configuration in dsa_switch_ops :: port_get_dscp_prio(), which is called for each DSCP value from 0 to 63. Again, there can be more than one dcbnl app table entry for the same DSCP value, DSA chooses the one with the largest configured priority. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/dsa.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 1220af73151b..9bfe984fcdbf 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -898,6 +898,11 @@ struct dsa_switch_ops { int (*port_get_default_prio)(struct dsa_switch *ds, int port); int (*port_set_default_prio)(struct dsa_switch *ds, int port, u8 prio); + int (*port_get_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp); + int (*port_add_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp, + u8 prio); + int (*port_del_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp, + u8 prio); /* * Suspend and resume -- cgit v1.2.3 From 978777d0fb06663523281aa50a5040c3aa31fbe7 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 11 Mar 2022 23:15:20 +0200 Subject: net: dsa: felix: configure default-prio and dscp priorities Follow the established programming model for this driver and provide shims in the felix DSA driver which call the implementations from the ocelot switch lib. The ocelot switchdev driver wasn't integrated with dcbnl due to lack of hardware availability. The switch doesn't have any fancy QoS classification enabled by default. The provided getters will create a default-prio app table entry of 0, and no dscp entry. However, the getters have been made to actually retrieve the hardware configuration rather than static values, to be future proof in case DSA will need this information from more call paths. For default-prio, there is a single field per port, in ANA_PORT_QOS_CFG, called QOS_DEFAULT_VAL. DSCP classification is enabled per-port, again via ANA_PORT_QOS_CFG (field QOS_DSCP_ENA), and individual DSCP values are configured as trusted or not through register ANA_DSCP_CFG (replicated 64 times). An untrusted DSCP value falls back to other QoS classification methods. If trusted, the selected ANA_DSCP_CFG register also holds the QoS class in the QOS_DSCP_VAL field. The hardware also supports DSCP remapping (DSCP value X is translated to DSCP value Y before the QoS class is determined based on the app table entry for Y) and DSCP packet rewriting. The dcbnl framework, for being so flexible in other useless areas, doesn't appear to support this. So this functionality has been left out. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index ee3c59639d70..4d51e2a7120f 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -869,6 +869,11 @@ int ocelot_port_pre_bridge_flags(struct ocelot *ocelot, int port, struct switchdev_brport_flags val); void ocelot_port_bridge_flags(struct ocelot *ocelot, int port, struct switchdev_brport_flags val); +int ocelot_port_get_default_prio(struct ocelot *ocelot, int port); +int ocelot_port_set_default_prio(struct ocelot *ocelot, int port, u8 prio); +int ocelot_port_get_dscp_prio(struct ocelot *ocelot, int port, u8 dscp); +int ocelot_port_add_dscp_prio(struct ocelot *ocelot, int port, u8 dscp, u8 prio); +int ocelot_port_del_dscp_prio(struct ocelot *ocelot, int port, u8 dscp, u8 prio); int ocelot_port_bridge_join(struct ocelot *ocelot, int port, struct net_device *bridge, int bridge_num, struct netlink_ext_ack *extack); -- cgit v1.2.3 From 2c7d2a230237e7c43fa067d695937b7e484bb92a Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 15 Dec 2021 15:39:58 -0500 Subject: btrfs: add definition for EXTENT_TREE_V2 This adds the initial definition of the EXTENT_TREE_V2 incompat feature flag. This also hides the support behind CONFIG_BTRFS_DEBUG. THIS IS A IN DEVELOPMENT FORMAT CHANGE, DO NOT USE UNLESS YOU ARE A DEVELOPER OR A TESTER. The format is in flux and will be added in stages, any fs will need to be re-made between updates to the format. Signed-off-by: Josef Bacik Signed-off-by: David Sterba --- include/uapi/linux/btrfs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 738619994e26..1cb1a3860f1d 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -309,6 +309,7 @@ struct btrfs_ioctl_fs_info_args { #define BTRFS_FEATURE_INCOMPAT_METADATA_UUID (1ULL << 10) #define BTRFS_FEATURE_INCOMPAT_RAID1C34 (1ULL << 11) #define BTRFS_FEATURE_INCOMPAT_ZONED (1ULL << 12) +#define BTRFS_FEATURE_INCOMPAT_EXTENT_TREE_V2 (1ULL << 13) struct btrfs_ioctl_feature_flags { __u64 compat_flags; -- cgit v1.2.3 From 9c54e80ddc6bd89596a4046d451908700476fd14 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 15 Dec 2021 15:40:07 -0500 Subject: btrfs: add code to support the block group root This code adds the on disk structures for the block group root, which will hold the block group items for extent tree v2. Signed-off-by: Josef Bacik Signed-off-by: David Sterba --- include/trace/events/btrfs.h | 1 + include/uapi/linux/btrfs_tree.h | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 0d729664b4b4..f068ff30d654 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -53,6 +53,7 @@ struct btrfs_space_info; { BTRFS_TREE_RELOC_OBJECTID, "TREE_RELOC" }, \ { BTRFS_UUID_TREE_OBJECTID, "UUID_TREE" }, \ { BTRFS_FREE_SPACE_TREE_OBJECTID, "FREE_SPACE_TREE" }, \ + { BTRFS_BLOCK_GROUP_TREE_OBJECTID, "BLOCK_GROUP_TREE" },\ { BTRFS_DATA_RELOC_TREE_OBJECTID, "DATA_RELOC_TREE" }) #define show_root_type(obj) \ diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index 5416f1f1a77a..b069752a8ecf 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -53,6 +53,9 @@ /* tracks free space in block groups. */ #define BTRFS_FREE_SPACE_TREE_OBJECTID 10ULL +/* Holds the block group items for extent tree v2. */ +#define BTRFS_BLOCK_GROUP_TREE_OBJECTID 11ULL + /* device stats in the device tree */ #define BTRFS_DEV_STATS_OBJECTID 0ULL -- cgit v1.2.3 From 871129332d74c9e94bd110932ac4445833995639 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Wed, 4 Sep 2019 12:13:25 -0700 Subject: fs: export rw_verify_area() I'm adding btrfs ioctls to read and write compressed data, and rather than duplicating the checks in rw_verify_area(), let's just export it. Reviewed-by: Josef Bacik Signed-off-by: Omar Sandoval Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index e2d892b201b0..0ebfc2519212 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3173,6 +3173,7 @@ extern loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size); extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t); extern loff_t no_seek_end_llseek(struct file *, loff_t, int); +int rw_verify_area(int, struct file *, const loff_t *, size_t); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); extern int stream_open(struct inode * inode, struct file * filp); -- cgit v1.2.3 From f6f7a25a650818c61defa97d60a79b216618315f Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Thu, 12 Aug 2021 15:34:57 -0700 Subject: fs: export variant of generic_write_checks without iov_iter Encoded I/O in Btrfs needs to check a write with a given logical size without an iov_iter that matches that size (because the iov_iter we have is for the compressed data). So, factor out the parts of generic_write_check() that don't need an iov_iter into a new generic_write_checks_count() function and export that. Reviewed-by: Nikolay Borisov Signed-off-by: Omar Sandoval Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 0ebfc2519212..27746a3da8fd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3130,6 +3130,7 @@ extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); +int generic_write_checks_count(struct kiocb *iocb, loff_t *count); extern int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count); extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); -- cgit v1.2.3 From dcb77a9ae87dc1ae2c54ea2e629da357e694b664 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Mon, 16 Aug 2021 15:58:29 -0700 Subject: btrfs: add definitions and documentation for encoded I/O ioctls In order to allow sending and receiving compressed data without decompressing it, we need an interface to write pre-compressed data directly to the filesystem and the matching interface to read compressed data without decompressing it. This adds the definitions for ioctls to do that and detailed explanations of how to use them. Reviewed-by: Nikolay Borisov Signed-off-by: Omar Sandoval Signed-off-by: David Sterba --- include/uapi/linux/btrfs.h | 132 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 132 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 1cb1a3860f1d..d956b2993970 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -869,6 +869,134 @@ struct btrfs_ioctl_get_subvol_rootref_args { __u8 align[7]; }; +/* + * Data and metadata for an encoded read or write. + * + * Encoded I/O bypasses any encoding automatically done by the filesystem (e.g., + * compression). This can be used to read the compressed contents of a file or + * write pre-compressed data directly to a file. + * + * BTRFS_IOC_ENCODED_READ and BTRFS_IOC_ENCODED_WRITE are essentially + * preadv/pwritev with additional metadata about how the data is encoded and the + * size of the unencoded data. + * + * BTRFS_IOC_ENCODED_READ fills the given iovecs with the encoded data, fills + * the metadata fields, and returns the size of the encoded data. It reads one + * extent per call. It can also read data which is not encoded. + * + * BTRFS_IOC_ENCODED_WRITE uses the metadata fields, writes the encoded data + * from the iovecs, and returns the size of the encoded data. Note that the + * encoded data is not validated when it is written; if it is not valid (e.g., + * it cannot be decompressed), then a subsequent read may return an error. + * + * Since the filesystem page cache contains decoded data, encoded I/O bypasses + * the page cache. Encoded I/O requires CAP_SYS_ADMIN. + */ +struct btrfs_ioctl_encoded_io_args { + /* Input parameters for both reads and writes. */ + + /* + * iovecs containing encoded data. + * + * For reads, if the size of the encoded data is larger than the sum of + * iov[n].iov_len for 0 <= n < iovcnt, then the ioctl fails with + * ENOBUFS. + * + * For writes, the size of the encoded data is the sum of iov[n].iov_len + * for 0 <= n < iovcnt. This must be less than 128 KiB (this limit may + * increase in the future). This must also be less than or equal to + * unencoded_len. + */ + const struct iovec __user *iov; + /* Number of iovecs. */ + unsigned long iovcnt; + /* + * Offset in file. + * + * For writes, must be aligned to the sector size of the filesystem. + */ + __s64 offset; + /* Currently must be zero. */ + __u64 flags; + + /* + * For reads, the following members are output parameters that will + * contain the returned metadata for the encoded data. + * For writes, the following members must be set to the metadata for the + * encoded data. + */ + + /* + * Length of the data in the file. + * + * Must be less than or equal to unencoded_len - unencoded_offset. For + * writes, must be aligned to the sector size of the filesystem unless + * the data ends at or beyond the current end of the file. + */ + __u64 len; + /* + * Length of the unencoded (i.e., decrypted and decompressed) data. + * + * For writes, must be no more than 128 KiB (this limit may increase in + * the future). If the unencoded data is actually longer than + * unencoded_len, then it is truncated; if it is shorter, then it is + * extended with zeroes. + */ + __u64 unencoded_len; + /* + * Offset from the first byte of the unencoded data to the first byte of + * logical data in the file. + * + * Must be less than unencoded_len. + */ + __u64 unencoded_offset; + /* + * BTRFS_ENCODED_IO_COMPRESSION_* type. + * + * For writes, must not be BTRFS_ENCODED_IO_COMPRESSION_NONE. + */ + __u32 compression; + /* Currently always BTRFS_ENCODED_IO_ENCRYPTION_NONE. */ + __u32 encryption; + /* + * Reserved for future expansion. + * + * For reads, always returned as zero. Users should check for non-zero + * bytes. If there are any, then the kernel has a newer version of this + * structure with additional information that the user definition is + * missing. + * + * For writes, must be zeroed. + */ + __u8 reserved[64]; +}; + +/* Data is not compressed. */ +#define BTRFS_ENCODED_IO_COMPRESSION_NONE 0 +/* Data is compressed as a single zlib stream. */ +#define BTRFS_ENCODED_IO_COMPRESSION_ZLIB 1 +/* + * Data is compressed as a single zstd frame with the windowLog compression + * parameter set to no more than 17. + */ +#define BTRFS_ENCODED_IO_COMPRESSION_ZSTD 2 +/* + * Data is compressed sector by sector (using the sector size indicated by the + * name of the constant) with LZO1X and wrapped in the format documented in + * fs/btrfs/lzo.c. For writes, the compression sector size must match the + * filesystem sector size. + */ +#define BTRFS_ENCODED_IO_COMPRESSION_LZO_4K 3 +#define BTRFS_ENCODED_IO_COMPRESSION_LZO_8K 4 +#define BTRFS_ENCODED_IO_COMPRESSION_LZO_16K 5 +#define BTRFS_ENCODED_IO_COMPRESSION_LZO_32K 6 +#define BTRFS_ENCODED_IO_COMPRESSION_LZO_64K 7 +#define BTRFS_ENCODED_IO_COMPRESSION_TYPES 8 + +/* Data is not encrypted. */ +#define BTRFS_ENCODED_IO_ENCRYPTION_NONE 0 +#define BTRFS_ENCODED_IO_ENCRYPTION_TYPES 1 + /* Error codes as returned by the kernel */ enum btrfs_err_code { BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET = 1, @@ -997,5 +1125,9 @@ enum btrfs_err_code { struct btrfs_ioctl_ino_lookup_user_args) #define BTRFS_IOC_SNAP_DESTROY_V2 _IOW(BTRFS_IOCTL_MAGIC, 63, \ struct btrfs_ioctl_vol_args_v2) +#define BTRFS_IOC_ENCODED_READ _IOR(BTRFS_IOCTL_MAGIC, 64, \ + struct btrfs_ioctl_encoded_io_args) +#define BTRFS_IOC_ENCODED_WRITE _IOW(BTRFS_IOCTL_MAGIC, 64, \ + struct btrfs_ioctl_encoded_io_args) #endif /* _UAPI_LINUX_BTRFS_H */ -- cgit v1.2.3 From 2d3eec8970335148278a6e350bc4840374f06471 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Fri, 18 Feb 2022 12:03:42 +0200 Subject: drm: Add drm_mode_init() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a variant of drm_mode_copy() that explicitly clears out the list head of the destination mode. Helpful to guarantee we don't have stack garbage left in there for on-stack modes. Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20220218100403.7028-2-ville.syrjala@linux.intel.com Reviewed-by: Andrzej Hajda Reviewed-by: Harry Wentland --- include/drm/drm_modes.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/drm/drm_modes.h b/include/drm/drm_modes.h index 2fa6b2c33b3f..a80ae9639e96 100644 --- a/include/drm/drm_modes.h +++ b/include/drm/drm_modes.h @@ -492,6 +492,8 @@ void drm_mode_set_crtcinfo(struct drm_display_mode *p, int adjust_flags); void drm_mode_copy(struct drm_display_mode *dst, const struct drm_display_mode *src); +void drm_mode_init(struct drm_display_mode *dst, + const struct drm_display_mode *src); struct drm_display_mode *drm_mode_duplicate(struct drm_device *dev, const struct drm_display_mode *mode); bool drm_mode_match(const struct drm_display_mode *mode1, -- cgit v1.2.3 From 5f1b97cb9af6c5471825b16306ad7da419cda563 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Fri, 11 Mar 2022 12:06:38 +0200 Subject: x86/gpu: include drm/i915_pciids.h directly in early quirks early-quirks.c is the only user of drm/i915_drm.h that also needs drm/i915_pciids.h. Include the masses of PCI ID macros only where needed. Cc: Bjorn Helgaas Cc: linux-pci@vger.kernel.org Cc: x86@kernel.org Signed-off-by: Jani Nikula Acked-by: Bjorn Helgaas Link: https://patchwork.freedesktop.org/patch/msgid/20220311100639.114685-1-jani.nikula@intel.com --- include/drm/i915_drm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h index 6722005884db..afbf3ef5643e 100644 --- a/include/drm/i915_drm.h +++ b/include/drm/i915_drm.h @@ -26,7 +26,6 @@ #ifndef _I915_DRM_H_ #define _I915_DRM_H_ -#include #include /* For use by IPS driver */ -- cgit v1.2.3 From ec090a0392ff634e9304c19a8578d476a9e0c830 Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Fri, 25 Feb 2022 16:46:56 +0200 Subject: mtd: core: Remove partid and partname debugfs files partid and partname debugfs files were used just by SPI NOR, but they were replaced by sysfs entries. Since these debugfs files are no longer used in mtd, remove dead code. The directory is kept as it is used by nandsim, mtdswap and docg3. Signed-off-by: Tudor Ambarus Reviewed-by: Pratyush Yadav Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20220225144656.634682-1-tudor.ambarus@microchip.com --- include/linux/mtd/mtd.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 1b3fc8c71ab3..151607e9d64a 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -188,9 +188,6 @@ struct module; /* only needed for owner field in mtd_info */ */ struct mtd_debug_info { struct dentry *dfs_dir; - - const char *partname; - const char *partid; }; /** -- cgit v1.2.3 From fc93db153b0187a9047f00bfd5cce75108530593 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 12 Mar 2022 13:45:05 -0800 Subject: net: disable preemption in dev_core_stats_XXX_inc() helpers syzbot was kind enough to remind us that dev->{tx_dropped|rx_dropped} could be increased in process context. BUG: using smp_processor_id() in preemptible [00000000] code: syz-executor413/3593 caller is netdev_core_stats_alloc+0x98/0x110 net/core/dev.c:10298 CPU: 1 PID: 3593 Comm: syz-executor413 Not tainted 5.17.0-rc7-syzkaller-02426-g97aeb877de7f #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 check_preemption_disabled+0x16b/0x170 lib/smp_processor_id.c:49 netdev_core_stats_alloc+0x98/0x110 net/core/dev.c:10298 dev_core_stats include/linux/netdevice.h:3855 [inline] dev_core_stats_rx_dropped_inc include/linux/netdevice.h:3866 [inline] tun_get_user+0x3455/0x3ab0 drivers/net/tun.c:1800 tun_chr_write_iter+0xe1/0x200 drivers/net/tun.c:2015 call_write_iter include/linux/fs.h:2074 [inline] new_sync_write+0x431/0x660 fs/read_write.c:503 vfs_write+0x7cd/0xae0 fs/read_write.c:590 ksys_write+0x12d/0x250 fs/read_write.c:643 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f2cf4f887e3 Code: 5d 41 5c 41 5d 41 5e e9 9b fd ff ff 66 2e 0f 1f 84 00 00 00 00 00 90 64 8b 04 25 18 00 00 00 85 c0 75 14 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 55 c3 0f 1f 40 00 48 83 ec 28 48 89 54 24 18 RSP: 002b:00007ffd50dd5fd8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 00007ffd50dd6000 RCX: 00007f2cf4f887e3 RDX: 000000000000002a RSI: 0000000000000000 RDI: 00000000000000c8 RBP: 0000000000000003 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffd50dd5ff0 R14: 00007ffd50dd5fe8 R15: 00007ffd50dd5fe4 Fixes: 625788b58445 ("net: add per-cpu storage and net->core_stats") Signed-off-by: Eric Dumazet Cc: jeffreyji Cc: Brian Vazquez Acked-by: Paolo Abeni Link: https://lore.kernel.org/r/20220312214505.3294762-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0d994710b335..8cbe96ce0a2c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3858,10 +3858,14 @@ static inline struct net_device_core_stats *dev_core_stats(struct net_device *de #define DEV_CORE_STATS_INC(FIELD) \ static inline void dev_core_stats_##FIELD##_inc(struct net_device *dev) \ { \ - struct net_device_core_stats *p = dev_core_stats(dev); \ + struct net_device_core_stats *p; \ + \ + preempt_disable(); \ + p = dev_core_stats(dev); \ \ if (p) \ local_inc(&p->FIELD); \ + preempt_enable(); \ } DEV_CORE_STATS_INC(rx_dropped) DEV_CORE_STATS_INC(tx_dropped) -- cgit v1.2.3 From c14c6843aeb8cdc8f6b0e49411d230e6f6dfda62 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 9 Feb 2022 20:21:23 +0000 Subject: fs: read_mapping_page() should take a struct file argument While read_cache_page() takes a void *, because you can pass a pointer to anything as the first argument of filler_t, if we are calling read_mapping_page(), it will be passed as the first argument of ->readpage, so we know this must be a struct file pointer, and we should let the compiler enforce that for us. Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Damien Le Moal Acked-by: Damien Le Moal Tested-by: Mike Marshall # orangefs Tested-by: David Howells # afs --- include/linux/pagemap.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 270bf5136c34..55a80d8f0e9c 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -636,15 +636,15 @@ extern int read_cache_pages(struct address_space *mapping, struct list_head *pages, filler_t *filler, void *data); static inline struct page *read_mapping_page(struct address_space *mapping, - pgoff_t index, void *data) + pgoff_t index, struct file *file) { - return read_cache_page(mapping, index, NULL, data); + return read_cache_page(mapping, index, NULL, file); } static inline struct folio *read_mapping_folio(struct address_space *mapping, - pgoff_t index, void *data) + pgoff_t index, struct file *file) { - return read_cache_folio(mapping, index, NULL, data); + return read_cache_folio(mapping, index, NULL, file); } /* -- cgit v1.2.3 From cd1067beeebfe23fc8cab071790fefb273962d51 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 9 Feb 2022 20:21:26 +0000 Subject: buffer: Add folio_buffers() While there is no intent to use large folios in filesystems using buffer heads, converting the filesystems to use single-page folios is still worth doing to remove legacy infrastructure and hidden calls to compound_head(). These helper functions are needed for that conversion to take place. Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Damien Le Moal Acked-by: Damien Le Moal Tested-by: Mike Marshall # orangefs Tested-by: David Howells # afs --- include/linux/buffer_head.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 36f33685c8c0..3451f1fcda12 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -144,6 +144,7 @@ BUFFER_FNS(Defer_Completion, defer_completion) ((struct buffer_head *)page_private(page)); \ }) #define page_has_buffers(page) PagePrivate(page) +#define folio_buffers(folio) folio_get_private(folio) void buffer_check_dirty_writeback(struct page *page, bool *dirty, bool *writeback); -- cgit v1.2.3 From 2e7e80f7e7e9dbbb3c2a85ee923ca32826052816 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 9 Feb 2022 20:21:27 +0000 Subject: fs: Convert is_partially_uptodate to folios Since the uptodate property is maintained on a per-folio basis, the is_partially_uptodate method should also take a folio. Fix the types at the same time so it's clear that it returns true/false and takes the count in bytes, not blocks. Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Damien Le Moal Acked-by: Damien Le Moal Tested-by: Mike Marshall # orangefs Tested-by: David Howells # afs --- include/linux/buffer_head.h | 3 +-- include/linux/fs.h | 4 ++-- include/linux/iomap.h | 3 +-- 3 files changed, 4 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 3451f1fcda12..79d465057889 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -225,8 +225,7 @@ int __block_write_full_page(struct inode *inode, struct page *page, get_block_t *get_block, struct writeback_control *wbc, bh_end_io_t *handler); int block_read_full_page(struct page*, get_block_t*); -int block_is_partially_uptodate(struct page *page, unsigned long from, - unsigned long count); +bool block_is_partially_uptodate(struct folio *, size_t from, size_t count); int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, get_block_t *get_block); int __block_write_begin(struct page *page, loff_t pos, unsigned len, diff --git a/include/linux/fs.h b/include/linux/fs.h index e2d892b201b0..5939e6694ada 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -400,8 +400,8 @@ struct address_space_operations { bool (*isolate_page)(struct page *, isolate_mode_t); void (*putback_page)(struct page *); int (*launder_page) (struct page *); - int (*is_partially_uptodate) (struct page *, unsigned long, - unsigned long); + bool (*is_partially_uptodate) (struct folio *, size_t from, + size_t count); void (*is_dirty_writeback) (struct page *, bool *, bool *); int (*error_remove_page)(struct address_space *, struct page *); diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 97a3a2edb585..3bcbb264f83f 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -227,8 +227,7 @@ ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops); int iomap_readpage(struct page *page, const struct iomap_ops *ops); void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops); -int iomap_is_partially_uptodate(struct page *page, unsigned long from, - unsigned long count); +bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count); int iomap_releasepage(struct page *page, gfp_t gfp_mask); void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len); void iomap_invalidatepage(struct page *page, unsigned int offset, -- cgit v1.2.3 From aa1b46dcdc7baaf5fec0be25782ef24b26aa209e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 13 Mar 2022 21:15:02 -1000 Subject: block: fix rq-qos breakage from skipping rq_qos_done_bio() a647a524a467 ("block: don't call rq_qos_ops->done_bio if the bio isn't tracked") made bio_endio() skip rq_qos_done_bio() if BIO_TRACKED is not set. While this fixed a potential oops, it also broke blk-iocost by skipping the done_bio callback for merged bios. Before, whether a bio goes through rq_qos_throttle() or rq_qos_merge(), rq_qos_done_bio() would be called on the bio on completion with BIO_TRACKED distinguishing the former from the latter. rq_qos_done_bio() is not called for bios which wenth through rq_qos_merge(). This royally confuses blk-iocost as the merged bios never finish and are considered perpetually in-flight. One reliably reproducible failure mode is an intermediate cgroup geting stuck active preventing its children from being activated due to the leaf-only rule, leading to loss of control. The following is from resctl-bench protection scenario which emulates isolating a web server like workload from a memory bomb run on an iocost configuration which should yield a reasonable level of protection. # cat /sys/block/nvme2n1/device/model Samsung SSD 970 PRO 512GB # cat /sys/fs/cgroup/io.cost.model 259:0 ctrl=user model=linear rbps=834913556 rseqiops=93622 rrandiops=102913 wbps=618985353 wseqiops=72325 wrandiops=71025 # cat /sys/fs/cgroup/io.cost.qos 259:0 enable=1 ctrl=user rpct=95.00 rlat=18776 wpct=95.00 wlat=8897 min=60.00 max=100.00 # resctl-bench -m 29.6G -r out.json run protection::scenario=mem-hog,loops=1 ... Memory Hog Summary ================== IO Latency: R p50=242u:336u/2.5m p90=794u:1.4m/7.5m p99=2.7m:8.0m/62.5m max=8.0m:36.4m/350m W p50=221u:323u/1.5m p90=709u:1.2m/5.5m p99=1.5m:2.5m/9.5m max=6.9m:35.9m/350m Isolation and Request Latency Impact Distributions: min p01 p05 p10 p25 p50 p75 p90 p95 p99 max mean stdev isol% 15.90 15.90 15.90 40.05 57.24 59.07 60.01 74.63 74.63 90.35 90.35 58.12 15.82 lat-imp% 0 0 0 0 0 4.55 14.68 15.54 233.5 548.1 548.1 53.88 143.6 Result: isol=58.12:15.82% lat_imp=53.88%:143.6 work_csv=100.0% missing=3.96% The isolation result of 58.12% is close to what this device would show without any IO control. Fix it by introducing a new flag BIO_QOS_MERGED to mark merged bios and calling rq_qos_done_bio() on them too. For consistency and clarity, rename BIO_TRACKED to BIO_QOS_THROTTLED. The flag checks are moved into rq_qos_done_bio() so that it's next to the code paths that set the flags. With the patch applied, the above same benchmark shows: # resctl-bench -m 29.6G -r out.json run protection::scenario=mem-hog,loops=1 ... Memory Hog Summary ================== IO Latency: R p50=123u:84.4u/985u p90=322u:256u/2.5m p99=1.6m:1.4m/9.5m max=11.1m:36.0m/350m W p50=429u:274u/995u p90=1.7m:1.3m/4.5m p99=3.4m:2.7m/11.5m max=7.9m:5.9m/26.5m Isolation and Request Latency Impact Distributions: min p01 p05 p10 p25 p50 p75 p90 p95 p99 max mean stdev isol% 84.91 84.91 89.51 90.73 92.31 94.49 96.36 98.04 98.71 100.0 100.0 94.42 2.81 lat-imp% 0 0 0 0 0 2.81 5.73 11.11 13.92 17.53 22.61 4.10 4.68 Result: isol=94.42:2.81% lat_imp=4.10%:4.68 work_csv=58.34% missing=0% Signed-off-by: Tejun Heo Fixes: a647a524a467 ("block: don't call rq_qos_ops->done_bio if the bio isn't tracked") Cc: stable@vger.kernel.org # v5.15+ Cc: Ming Lei Cc: Yu Kuai Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/Yi7rdrzQEHjJLGKB@slm.duckdns.org Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 5561e58d158a..0c3563b45fe9 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -324,7 +324,8 @@ enum { BIO_TRACE_COMPLETION, /* bio_endio() should trace the final completion * of this bio. */ BIO_CGROUP_ACCT, /* has been accounted to a cgroup */ - BIO_TRACKED, /* set if bio goes through the rq_qos path */ + BIO_QOS_THROTTLED, /* bio went through rq_qos throttle path */ + BIO_QOS_MERGED, /* but went through rq_qos merge path */ BIO_REMAPPED, BIO_ZONE_WRITE_LOCKED, /* Owns a zoned device zone write lock */ BIO_PERCPU_CACHE, /* can participate in per-cpu alloc cache */ -- cgit v1.2.3 From 338e953f1bd1a0ef4c86b5ab44735e1f6519d721 Mon Sep 17 00:00:00 2001 From: Guodong Liu Date: Wed, 16 Feb 2022 11:21:22 +0800 Subject: dt-bindings: pinctrl: mt8186: add pinctrl file and binding document 1. This patch adds pinctrl file for mt8186. 2. This patch adds mt8186 compatible node in binding document. Signed-off-by: Guodong Liu Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20220216032124.28067-2-guodong.liu@mediatek.com Signed-off-by: Linus Walleij --- include/dt-bindings/pinctrl/mt8186-pinfunc.h | 1174 ++++++++++++++++++++++++++ 1 file changed, 1174 insertions(+) create mode 100644 include/dt-bindings/pinctrl/mt8186-pinfunc.h (limited to 'include') diff --git a/include/dt-bindings/pinctrl/mt8186-pinfunc.h b/include/dt-bindings/pinctrl/mt8186-pinfunc.h new file mode 100644 index 000000000000..18d6683c6f65 --- /dev/null +++ b/include/dt-bindings/pinctrl/mt8186-pinfunc.h @@ -0,0 +1,1174 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (C) 2021 MediaTek Inc. + * Author: Guodong Liu + * + */ + +#ifndef __MT8186_PINFUNC_H +#define __MT8186_PINFUNC_H + +#include "mt65xx.h" + +#define PINMUX_GPIO0__FUNC_GPIO0 (MTK_PIN_NO(0) | 0) +#define PINMUX_GPIO0__FUNC_I2S0_MCK (MTK_PIN_NO(0) | 1) +#define PINMUX_GPIO0__FUNC_SPI0_CLK_B (MTK_PIN_NO(0) | 2) +#define PINMUX_GPIO0__FUNC_I2S2_MCK (MTK_PIN_NO(0) | 3) +#define PINMUX_GPIO0__FUNC_CMFLASH0 (MTK_PIN_NO(0) | 4) +#define PINMUX_GPIO0__FUNC_SCP_SPI0_CK (MTK_PIN_NO(0) | 5) +#define PINMUX_GPIO0__FUNC_TP_GPIO0_AO (MTK_PIN_NO(0) | 6) +#define PINMUX_GPIO0__FUNC_DBG_MON_A0 (MTK_PIN_NO(0) | 7) + +#define PINMUX_GPIO1__FUNC_GPIO1 (MTK_PIN_NO(1) | 0) +#define PINMUX_GPIO1__FUNC_I2S0_BCK (MTK_PIN_NO(1) | 1) +#define PINMUX_GPIO1__FUNC_SPI0_CSB_B (MTK_PIN_NO(1) | 2) +#define PINMUX_GPIO1__FUNC_I2S2_BCK (MTK_PIN_NO(1) | 3) +#define PINMUX_GPIO1__FUNC_CMFLASH1 (MTK_PIN_NO(1) | 4) +#define PINMUX_GPIO1__FUNC_SCP_SPI0_CS (MTK_PIN_NO(1) | 5) +#define PINMUX_GPIO1__FUNC_TP_GPIO1_AO (MTK_PIN_NO(1) | 6) + +#define PINMUX_GPIO2__FUNC_GPIO2 (MTK_PIN_NO(2) | 0) +#define PINMUX_GPIO2__FUNC_I2S0_LRCK (MTK_PIN_NO(2) | 1) +#define PINMUX_GPIO2__FUNC_SPI0_MO_B (MTK_PIN_NO(2) | 2) +#define PINMUX_GPIO2__FUNC_I2S2_LRCK (MTK_PIN_NO(2) | 3) +#define PINMUX_GPIO2__FUNC_CMFLASH2 (MTK_PIN_NO(2) | 4) +#define PINMUX_GPIO2__FUNC_SCP_SPI0_MO (MTK_PIN_NO(2) | 5) +#define PINMUX_GPIO2__FUNC_TP_GPIO2_AO (MTK_PIN_NO(2) | 6) + +#define PINMUX_GPIO3__FUNC_GPIO3 (MTK_PIN_NO(3) | 0) +#define PINMUX_GPIO3__FUNC_I2S0_DI (MTK_PIN_NO(3) | 1) +#define PINMUX_GPIO3__FUNC_SPI0_MI_B (MTK_PIN_NO(3) | 2) +#define PINMUX_GPIO3__FUNC_I2S2_DI (MTK_PIN_NO(3) | 3) +#define PINMUX_GPIO3__FUNC_SRCLKENAI1 (MTK_PIN_NO(3) | 4) +#define PINMUX_GPIO3__FUNC_SCP_SPI0_MI (MTK_PIN_NO(3) | 5) +#define PINMUX_GPIO3__FUNC_TP_GPIO3_AO (MTK_PIN_NO(3) | 6) + +#define PINMUX_GPIO4__FUNC_GPIO4 (MTK_PIN_NO(4) | 0) +#define PINMUX_GPIO4__FUNC_I2S3_DO (MTK_PIN_NO(4) | 1) +#define PINMUX_GPIO4__FUNC_I2S1_DO (MTK_PIN_NO(4) | 3) +#define PINMUX_GPIO4__FUNC_TP_GPIO4_AO (MTK_PIN_NO(4) | 6) + +#define PINMUX_GPIO5__FUNC_GPIO5 (MTK_PIN_NO(5) | 0) +#define PINMUX_GPIO5__FUNC_EXT_FRAME_SYNC (MTK_PIN_NO(5) | 1) +#define PINMUX_GPIO5__FUNC_TP_GPIO5_AO (MTK_PIN_NO(5) | 6) + +#define PINMUX_GPIO6__FUNC_GPIO6 (MTK_PIN_NO(6) | 0) +#define PINMUX_GPIO6__FUNC_I2S3_MCK (MTK_PIN_NO(6) | 1) +#define PINMUX_GPIO6__FUNC_SPI1_CLK_B (MTK_PIN_NO(6) | 2) +#define PINMUX_GPIO6__FUNC_I2S1_MCK (MTK_PIN_NO(6) | 3) +#define PINMUX_GPIO6__FUNC_DPI_DATA22 (MTK_PIN_NO(6) | 4) +#define PINMUX_GPIO6__FUNC_TP_GPIO6_AO (MTK_PIN_NO(6) | 6) + +#define PINMUX_GPIO7__FUNC_GPIO7 (MTK_PIN_NO(7) | 0) +#define PINMUX_GPIO7__FUNC_I2S3_BCK (MTK_PIN_NO(7) | 1) +#define PINMUX_GPIO7__FUNC_SPI1_CSB_B (MTK_PIN_NO(7) | 2) +#define PINMUX_GPIO7__FUNC_I2S1_BCK (MTK_PIN_NO(7) | 3) +#define PINMUX_GPIO7__FUNC_DPI_DATA23 (MTK_PIN_NO(7) | 4) +#define PINMUX_GPIO7__FUNC_TP_GPIO7_AO (MTK_PIN_NO(7) | 6) + +#define PINMUX_GPIO8__FUNC_GPIO8 (MTK_PIN_NO(8) | 0) +#define PINMUX_GPIO8__FUNC_I2S3_LRCK (MTK_PIN_NO(8) | 1) +#define PINMUX_GPIO8__FUNC_SPI1_MO_B (MTK_PIN_NO(8) | 2) +#define PINMUX_GPIO8__FUNC_I2S1_LRCK (MTK_PIN_NO(8) | 3) +#define PINMUX_GPIO8__FUNC_CONN_UART0_RXD (MTK_PIN_NO(8) | 4) +#define PINMUX_GPIO8__FUNC_SSPM_URXD_AO (MTK_PIN_NO(8) | 5) +#define PINMUX_GPIO8__FUNC_ADSP_UART_RX (MTK_PIN_NO(8) | 6) +#define PINMUX_GPIO8__FUNC_CONN_MCU_DBGACK_N (MTK_PIN_NO(8) | 7) + +#define PINMUX_GPIO9__FUNC_GPIO9 (MTK_PIN_NO(9) | 0) +#define PINMUX_GPIO9__FUNC_I2S3_DO (MTK_PIN_NO(9) | 1) +#define PINMUX_GPIO9__FUNC_SPI1_MI_B (MTK_PIN_NO(9) | 2) +#define PINMUX_GPIO9__FUNC_I2S1_DO (MTK_PIN_NO(9) | 3) +#define PINMUX_GPIO9__FUNC_CONN_UART0_TXD (MTK_PIN_NO(9) | 4) +#define PINMUX_GPIO9__FUNC_SSPM_UTXD_AO (MTK_PIN_NO(9) | 5) +#define PINMUX_GPIO9__FUNC_ADSP_UART_TX (MTK_PIN_NO(9) | 6) +#define PINMUX_GPIO9__FUNC_CONN_MCU_DBGI_N (MTK_PIN_NO(9) | 7) + +#define PINMUX_GPIO10__FUNC_GPIO10 (MTK_PIN_NO(10) | 0) +#define PINMUX_GPIO10__FUNC_I2S0_MCK (MTK_PIN_NO(10) | 1) +#define PINMUX_GPIO10__FUNC_SPI4_CLK_A (MTK_PIN_NO(10) | 2) +#define PINMUX_GPIO10__FUNC_I2S2_MCK (MTK_PIN_NO(10) | 3) +#define PINMUX_GPIO10__FUNC_SPM_JTAG_TDI (MTK_PIN_NO(10) | 4) +#define PINMUX_GPIO10__FUNC_SCP_JTAG_TDI (MTK_PIN_NO(10) | 5) +#define PINMUX_GPIO10__FUNC_ADSP_JTAG_TDI (MTK_PIN_NO(10) | 6) +#define PINMUX_GPIO10__FUNC_CONN_MCU_TDI (MTK_PIN_NO(10) | 7) + +#define PINMUX_GPIO11__FUNC_GPIO11 (MTK_PIN_NO(11) | 0) +#define PINMUX_GPIO11__FUNC_I2S0_BCK (MTK_PIN_NO(11) | 1) +#define PINMUX_GPIO11__FUNC_SPI4_CSB_A (MTK_PIN_NO(11) | 2) +#define PINMUX_GPIO11__FUNC_I2S2_BCK (MTK_PIN_NO(11) | 3) +#define PINMUX_GPIO11__FUNC_SPM_JTAG_TRSTN (MTK_PIN_NO(11) | 4) +#define PINMUX_GPIO11__FUNC_SCP_JTAG_TRSTN (MTK_PIN_NO(11) | 5) +#define PINMUX_GPIO11__FUNC_ADSP_JTAG_TRSTN (MTK_PIN_NO(11) | 6) +#define PINMUX_GPIO11__FUNC_CONN_MCU_TRST_B (MTK_PIN_NO(11) | 7) + +#define PINMUX_GPIO12__FUNC_GPIO12 (MTK_PIN_NO(12) | 0) +#define PINMUX_GPIO12__FUNC_I2S0_LRCK (MTK_PIN_NO(12) | 1) +#define PINMUX_GPIO12__FUNC_SPI4_MO_A (MTK_PIN_NO(12) | 2) +#define PINMUX_GPIO12__FUNC_I2S2_LRCK (MTK_PIN_NO(12) | 3) +#define PINMUX_GPIO12__FUNC_SPM_JTAG_TCK (MTK_PIN_NO(12) | 4) +#define PINMUX_GPIO12__FUNC_SCP_JTAG_TCK (MTK_PIN_NO(12) | 5) +#define PINMUX_GPIO12__FUNC_ADSP_JTAG_TCK (MTK_PIN_NO(12) | 6) +#define PINMUX_GPIO12__FUNC_CONN_MCU_TCK (MTK_PIN_NO(12) | 7) + +#define PINMUX_GPIO13__FUNC_GPIO13 (MTK_PIN_NO(13) | 0) +#define PINMUX_GPIO13__FUNC_I2S0_DI (MTK_PIN_NO(13) | 1) +#define PINMUX_GPIO13__FUNC_SPI4_MI_A (MTK_PIN_NO(13) | 2) +#define PINMUX_GPIO13__FUNC_I2S2_DI (MTK_PIN_NO(13) | 3) +#define PINMUX_GPIO13__FUNC_SPM_JTAG_TDO (MTK_PIN_NO(13) | 4) +#define PINMUX_GPIO13__FUNC_SCP_JTAG_TDO (MTK_PIN_NO(13) | 5) +#define PINMUX_GPIO13__FUNC_ADSP_JTAG_TDO (MTK_PIN_NO(13) | 6) +#define PINMUX_GPIO13__FUNC_CONN_MCU_TDO (MTK_PIN_NO(13) | 7) + +#define PINMUX_GPIO14__FUNC_GPIO14 (MTK_PIN_NO(14) | 0) +#define PINMUX_GPIO14__FUNC_CLKM0 (MTK_PIN_NO(14) | 3) +#define PINMUX_GPIO14__FUNC_SPM_JTAG_TMS (MTK_PIN_NO(14) | 4) +#define PINMUX_GPIO14__FUNC_SCP_JTAG_TMS (MTK_PIN_NO(14) | 5) +#define PINMUX_GPIO14__FUNC_ADSP_JTAG_TMS (MTK_PIN_NO(14) | 6) +#define PINMUX_GPIO14__FUNC_CONN_MCU_TMS (MTK_PIN_NO(14) | 7) + +#define PINMUX_GPIO15__FUNC_GPIO15 (MTK_PIN_NO(15) | 0) +#define PINMUX_GPIO15__FUNC_EXT_FRAME_SYNC (MTK_PIN_NO(15) | 1) +#define PINMUX_GPIO15__FUNC_SRCLKENAI1 (MTK_PIN_NO(15) | 2) +#define PINMUX_GPIO15__FUNC_CLKM1 (MTK_PIN_NO(15) | 3) +#define PINMUX_GPIO15__FUNC_PWM0 (MTK_PIN_NO(15) | 4) + +#define PINMUX_GPIO16__FUNC_GPIO16 (MTK_PIN_NO(16) | 0) +#define PINMUX_GPIO16__FUNC_CONN_WIFI_TXD (MTK_PIN_NO(16) | 1) +#define PINMUX_GPIO16__FUNC_SRCLKENAI0 (MTK_PIN_NO(16) | 2) +#define PINMUX_GPIO16__FUNC_CLKM2 (MTK_PIN_NO(16) | 3) +#define PINMUX_GPIO16__FUNC_PWM1 (MTK_PIN_NO(16) | 4) + +#define PINMUX_GPIO17__FUNC_GPIO17 (MTK_PIN_NO(17) | 0) +#define PINMUX_GPIO17__FUNC_CLKM3 (MTK_PIN_NO(17) | 3) +#define PINMUX_GPIO17__FUNC_PWM2 (MTK_PIN_NO(17) | 4) +#define PINMUX_GPIO17__FUNC_DBG_MON_A32 (MTK_PIN_NO(17) | 7) + +#define PINMUX_GPIO18__FUNC_GPIO18 (MTK_PIN_NO(18) | 0) +#define PINMUX_GPIO18__FUNC_CMVREF0 (MTK_PIN_NO(18) | 2) +#define PINMUX_GPIO18__FUNC_SPI2_CLK_B (MTK_PIN_NO(18) | 6) +#define PINMUX_GPIO18__FUNC_DBG_MON_A26 (MTK_PIN_NO(18) | 7) + +#define PINMUX_GPIO19__FUNC_GPIO19 (MTK_PIN_NO(19) | 0) +#define PINMUX_GPIO19__FUNC_CMVREF1 (MTK_PIN_NO(19) | 2) +#define PINMUX_GPIO19__FUNC_ANT_SEL3 (MTK_PIN_NO(19) | 5) +#define PINMUX_GPIO19__FUNC_SPI2_CSB_B (MTK_PIN_NO(19) | 6) +#define PINMUX_GPIO19__FUNC_DBG_MON_A2 (MTK_PIN_NO(19) | 7) + +#define PINMUX_GPIO20__FUNC_GPIO20 (MTK_PIN_NO(20) | 0) +#define PINMUX_GPIO20__FUNC_CMVREF2 (MTK_PIN_NO(20) | 2) +#define PINMUX_GPIO20__FUNC_ANT_SEL4 (MTK_PIN_NO(20) | 5) +#define PINMUX_GPIO20__FUNC_SPI2_MO_B (MTK_PIN_NO(20) | 6) +#define PINMUX_GPIO20__FUNC_DBG_MON_A3 (MTK_PIN_NO(20) | 7) + +#define PINMUX_GPIO21__FUNC_GPIO21 (MTK_PIN_NO(21) | 0) +#define PINMUX_GPIO21__FUNC_I2S0_MCK (MTK_PIN_NO(21) | 1) +#define PINMUX_GPIO21__FUNC_I2S1_MCK (MTK_PIN_NO(21) | 2) +#define PINMUX_GPIO21__FUNC_I2S3_MCK (MTK_PIN_NO(21) | 3) +#define PINMUX_GPIO21__FUNC_ANT_SEL5 (MTK_PIN_NO(21) | 5) +#define PINMUX_GPIO21__FUNC_SPI2_MI_B (MTK_PIN_NO(21) | 6) +#define PINMUX_GPIO21__FUNC_DBG_MON_A4 (MTK_PIN_NO(21) | 7) + +#define PINMUX_GPIO22__FUNC_GPIO22 (MTK_PIN_NO(22) | 0) +#define PINMUX_GPIO22__FUNC_I2S0_BCK (MTK_PIN_NO(22) | 1) +#define PINMUX_GPIO22__FUNC_I2S1_BCK (MTK_PIN_NO(22) | 2) +#define PINMUX_GPIO22__FUNC_I2S3_BCK (MTK_PIN_NO(22) | 3) +#define PINMUX_GPIO22__FUNC_TDM_RX_LRCK (MTK_PIN_NO(22) | 4) +#define PINMUX_GPIO22__FUNC_ANT_SEL6 (MTK_PIN_NO(22) | 5) +#define PINMUX_GPIO22__FUNC_DBG_MON_A5 (MTK_PIN_NO(22) | 7) + +#define PINMUX_GPIO23__FUNC_GPIO23 (MTK_PIN_NO(23) | 0) +#define PINMUX_GPIO23__FUNC_I2S0_LRCK (MTK_PIN_NO(23) | 1) +#define PINMUX_GPIO23__FUNC_I2S1_LRCK (MTK_PIN_NO(23) | 2) +#define PINMUX_GPIO23__FUNC_I2S3_LRCK (MTK_PIN_NO(23) | 3) +#define PINMUX_GPIO23__FUNC_TDM_RX_BCK (MTK_PIN_NO(23) | 4) +#define PINMUX_GPIO23__FUNC_ANT_SEL7 (MTK_PIN_NO(23) | 5) +#define PINMUX_GPIO23__FUNC_DBG_MON_A6 (MTK_PIN_NO(23) | 7) + +#define PINMUX_GPIO24__FUNC_GPIO24 (MTK_PIN_NO(24) | 0) +#define PINMUX_GPIO24__FUNC_I2S0_DI (MTK_PIN_NO(24) | 1) +#define PINMUX_GPIO24__FUNC_I2S1_DO (MTK_PIN_NO(24) | 2) +#define PINMUX_GPIO24__FUNC_I2S3_DO (MTK_PIN_NO(24) | 3) +#define PINMUX_GPIO24__FUNC_TDM_RX_MCK (MTK_PIN_NO(24) | 4) +#define PINMUX_GPIO24__FUNC_DBG_MON_A7 (MTK_PIN_NO(24) | 7) + +#define PINMUX_GPIO25__FUNC_GPIO25 (MTK_PIN_NO(25) | 0) +#define PINMUX_GPIO25__FUNC_I2S2_MCK (MTK_PIN_NO(25) | 1) +#define PINMUX_GPIO25__FUNC_PCM_CLK (MTK_PIN_NO(25) | 2) +#define PINMUX_GPIO25__FUNC_SPI4_CLK_B (MTK_PIN_NO(25) | 3) +#define PINMUX_GPIO25__FUNC_TDM_RX_DATA0 (MTK_PIN_NO(25) | 4) +#define PINMUX_GPIO25__FUNC_DBG_MON_A8 (MTK_PIN_NO(25) | 7) + +#define PINMUX_GPIO26__FUNC_GPIO26 (MTK_PIN_NO(26) | 0) +#define PINMUX_GPIO26__FUNC_I2S2_BCK (MTK_PIN_NO(26) | 1) +#define PINMUX_GPIO26__FUNC_PCM_SYNC (MTK_PIN_NO(26) | 2) +#define PINMUX_GPIO26__FUNC_SPI4_CSB_B (MTK_PIN_NO(26) | 3) +#define PINMUX_GPIO26__FUNC_TDM_RX_DATA1 (MTK_PIN_NO(26) | 4) +#define PINMUX_GPIO26__FUNC_DBG_MON_A9 (MTK_PIN_NO(26) | 7) + +#define PINMUX_GPIO27__FUNC_GPIO27 (MTK_PIN_NO(27) | 0) +#define PINMUX_GPIO27__FUNC_I2S2_LRCK (MTK_PIN_NO(27) | 1) +#define PINMUX_GPIO27__FUNC_PCM_DI (MTK_PIN_NO(27) | 2) +#define PINMUX_GPIO27__FUNC_SPI4_MO_B (MTK_PIN_NO(27) | 3) +#define PINMUX_GPIO27__FUNC_TDM_RX_DATA2 (MTK_PIN_NO(27) | 4) +#define PINMUX_GPIO27__FUNC_DBG_MON_A10 (MTK_PIN_NO(27) | 7) + +#define PINMUX_GPIO28__FUNC_GPIO28 (MTK_PIN_NO(28) | 0) +#define PINMUX_GPIO28__FUNC_I2S2_DI (MTK_PIN_NO(28) | 1) +#define PINMUX_GPIO28__FUNC_PCM_DO (MTK_PIN_NO(28) | 2) +#define PINMUX_GPIO28__FUNC_SPI4_MI_B (MTK_PIN_NO(28) | 3) +#define PINMUX_GPIO28__FUNC_TDM_RX_DATA3 (MTK_PIN_NO(28) | 4) + +#define PINMUX_GPIO29__FUNC_GPIO29 (MTK_PIN_NO(29) | 0) +#define PINMUX_GPIO29__FUNC_ANT_SEL0 (MTK_PIN_NO(29) | 1) +#define PINMUX_GPIO29__FUNC_GPS_L1_ELNA_EN (MTK_PIN_NO(29) | 2) + +#define PINMUX_GPIO30__FUNC_GPIO30 (MTK_PIN_NO(30) | 0) +#define PINMUX_GPIO30__FUNC_ANT_SEL1 (MTK_PIN_NO(30) | 1) + +#define PINMUX_GPIO31__FUNC_GPIO31 (MTK_PIN_NO(31) | 0) +#define PINMUX_GPIO31__FUNC_ANT_SEL2 (MTK_PIN_NO(31) | 1) +#define PINMUX_GPIO31__FUNC_EXT_FRAME_SYNC (MTK_PIN_NO(31) | 2) +#define PINMUX_GPIO31__FUNC_SRCLKENAI1 (MTK_PIN_NO(31) | 3) + +#define PINMUX_GPIO32__FUNC_GPIO32 (MTK_PIN_NO(32) | 0) +#define PINMUX_GPIO32__FUNC_URXD0 (MTK_PIN_NO(32) | 1) +#define PINMUX_GPIO32__FUNC_UTXD0 (MTK_PIN_NO(32) | 2) +#define PINMUX_GPIO32__FUNC_ADSP_UART_RX (MTK_PIN_NO(32) | 3) +#define PINMUX_GPIO32__FUNC_TP_URXD1_AO (MTK_PIN_NO(32) | 4) + +#define PINMUX_GPIO33__FUNC_GPIO33 (MTK_PIN_NO(33) | 0) +#define PINMUX_GPIO33__FUNC_UTXD0 (MTK_PIN_NO(33) | 1) +#define PINMUX_GPIO33__FUNC_URXD0 (MTK_PIN_NO(33) | 2) +#define PINMUX_GPIO33__FUNC_ADSP_UART_TX (MTK_PIN_NO(33) | 3) +#define PINMUX_GPIO33__FUNC_TP_UTXD1_AO (MTK_PIN_NO(33) | 4) + +#define PINMUX_GPIO34__FUNC_GPIO34 (MTK_PIN_NO(34) | 0) +#define PINMUX_GPIO34__FUNC_URXD1 (MTK_PIN_NO(34) | 1) +#define PINMUX_GPIO34__FUNC_TP_URXD2_AO (MTK_PIN_NO(34) | 2) +#define PINMUX_GPIO34__FUNC_SSPM_URXD_AO (MTK_PIN_NO(34) | 3) +#define PINMUX_GPIO34__FUNC_ADSP_UART_RX (MTK_PIN_NO(34) | 4) +#define PINMUX_GPIO34__FUNC_CONN_UART0_RXD (MTK_PIN_NO(34) | 5) + +#define PINMUX_GPIO35__FUNC_GPIO35 (MTK_PIN_NO(35) | 0) +#define PINMUX_GPIO35__FUNC_UTXD1 (MTK_PIN_NO(35) | 1) +#define PINMUX_GPIO35__FUNC_TP_UTXD2_AO (MTK_PIN_NO(35) | 2) +#define PINMUX_GPIO35__FUNC_SSPM_UTXD_AO (MTK_PIN_NO(35) | 3) +#define PINMUX_GPIO35__FUNC_ADSP_UART_TX (MTK_PIN_NO(35) | 4) +#define PINMUX_GPIO35__FUNC_CONN_UART0_TXD (MTK_PIN_NO(35) | 5) +#define PINMUX_GPIO35__FUNC_CONN_WIFI_TXD (MTK_PIN_NO(35) | 6) + +#define PINMUX_GPIO36__FUNC_GPIO36 (MTK_PIN_NO(36) | 0) +#define PINMUX_GPIO36__FUNC_SPI0_CLK_A (MTK_PIN_NO(36) | 1) +#define PINMUX_GPIO36__FUNC_CLKM0 (MTK_PIN_NO(36) | 2) +#define PINMUX_GPIO36__FUNC_SCP_SPI0_CK (MTK_PIN_NO(36) | 4) +#define PINMUX_GPIO36__FUNC_SPINOR_CK (MTK_PIN_NO(36) | 5) +#define PINMUX_GPIO36__FUNC_DBG_MON_A11 (MTK_PIN_NO(36) | 7) + +#define PINMUX_GPIO37__FUNC_GPIO37 (MTK_PIN_NO(37) | 0) +#define PINMUX_GPIO37__FUNC_SPI0_CSB_A (MTK_PIN_NO(37) | 1) +#define PINMUX_GPIO37__FUNC_CLKM1 (MTK_PIN_NO(37) | 2) +#define PINMUX_GPIO37__FUNC_PWM0 (MTK_PIN_NO(37) | 3) +#define PINMUX_GPIO37__FUNC_SCP_SPI0_CS (MTK_PIN_NO(37) | 4) +#define PINMUX_GPIO37__FUNC_SPINOR_CS (MTK_PIN_NO(37) | 5) +#define PINMUX_GPIO37__FUNC_DBG_MON_A12 (MTK_PIN_NO(37) | 7) + +#define PINMUX_GPIO38__FUNC_GPIO38 (MTK_PIN_NO(38) | 0) +#define PINMUX_GPIO38__FUNC_SPI0_MO_A (MTK_PIN_NO(38) | 1) +#define PINMUX_GPIO38__FUNC_CLKM2 (MTK_PIN_NO(38) | 2) +#define PINMUX_GPIO38__FUNC_PWM1 (MTK_PIN_NO(38) | 3) +#define PINMUX_GPIO38__FUNC_SCP_SPI0_MO (MTK_PIN_NO(38) | 4) +#define PINMUX_GPIO38__FUNC_SPINOR_IO0 (MTK_PIN_NO(38) | 5) +#define PINMUX_GPIO38__FUNC_DBG_MON_A13 (MTK_PIN_NO(38) | 7) + +#define PINMUX_GPIO39__FUNC_GPIO39 (MTK_PIN_NO(39) | 0) +#define PINMUX_GPIO39__FUNC_SPI0_MI_A (MTK_PIN_NO(39) | 1) +#define PINMUX_GPIO39__FUNC_CLKM3 (MTK_PIN_NO(39) | 2) +#define PINMUX_GPIO39__FUNC_PWM2 (MTK_PIN_NO(39) | 3) +#define PINMUX_GPIO39__FUNC_SCP_SPI0_MI (MTK_PIN_NO(39) | 4) +#define PINMUX_GPIO39__FUNC_SPINOR_IO1 (MTK_PIN_NO(39) | 5) +#define PINMUX_GPIO39__FUNC_DBG_MON_A14 (MTK_PIN_NO(39) | 7) + +#define PINMUX_GPIO40__FUNC_GPIO40 (MTK_PIN_NO(40) | 0) +#define PINMUX_GPIO40__FUNC_SPI1_CLK_A (MTK_PIN_NO(40) | 1) +#define PINMUX_GPIO40__FUNC_SCP_SPI1_CK (MTK_PIN_NO(40) | 2) +#define PINMUX_GPIO40__FUNC_UCTS0 (MTK_PIN_NO(40) | 4) +#define PINMUX_GPIO40__FUNC_SPINOR_IO2 (MTK_PIN_NO(40) | 5) +#define PINMUX_GPIO40__FUNC_TP_UCTS1_AO (MTK_PIN_NO(40) | 6) +#define PINMUX_GPIO40__FUNC_DBG_MON_A15 (MTK_PIN_NO(40) | 7) + +#define PINMUX_GPIO41__FUNC_GPIO41 (MTK_PIN_NO(41) | 0) +#define PINMUX_GPIO41__FUNC_SPI1_CSB_A (MTK_PIN_NO(41) | 1) +#define PINMUX_GPIO41__FUNC_SCP_SPI1_CS (MTK_PIN_NO(41) | 2) +#define PINMUX_GPIO41__FUNC_PWM0 (MTK_PIN_NO(41) | 3) +#define PINMUX_GPIO41__FUNC_URTS0 (MTK_PIN_NO(41) | 4) +#define PINMUX_GPIO41__FUNC_SPINOR_IO3 (MTK_PIN_NO(41) | 5) +#define PINMUX_GPIO41__FUNC_TP_URTS1_AO (MTK_PIN_NO(41) | 6) +#define PINMUX_GPIO41__FUNC_DBG_MON_A16 (MTK_PIN_NO(41) | 7) + +#define PINMUX_GPIO42__FUNC_GPIO42 (MTK_PIN_NO(42) | 0) +#define PINMUX_GPIO42__FUNC_SPI1_MO_A (MTK_PIN_NO(42) | 1) +#define PINMUX_GPIO42__FUNC_SCP_SPI1_MO (MTK_PIN_NO(42) | 2) +#define PINMUX_GPIO42__FUNC_PWM1 (MTK_PIN_NO(42) | 3) +#define PINMUX_GPIO42__FUNC_UCTS1 (MTK_PIN_NO(42) | 4) +#define PINMUX_GPIO42__FUNC_TP_UCTS2_AO (MTK_PIN_NO(42) | 6) +#define PINMUX_GPIO42__FUNC_DBG_MON_A17 (MTK_PIN_NO(42) | 7) + +#define PINMUX_GPIO43__FUNC_GPIO43 (MTK_PIN_NO(43) | 0) +#define PINMUX_GPIO43__FUNC_SPI1_MI_A (MTK_PIN_NO(43) | 1) +#define PINMUX_GPIO43__FUNC_SCP_SPI1_MI (MTK_PIN_NO(43) | 2) +#define PINMUX_GPIO43__FUNC_PWM2 (MTK_PIN_NO(43) | 3) +#define PINMUX_GPIO43__FUNC_URTS1 (MTK_PIN_NO(43) | 4) +#define PINMUX_GPIO43__FUNC_TP_URTS2_AO (MTK_PIN_NO(43) | 6) +#define PINMUX_GPIO43__FUNC_DBG_MON_A18 (MTK_PIN_NO(43) | 7) + +#define PINMUX_GPIO44__FUNC_GPIO44 (MTK_PIN_NO(44) | 0) +#define PINMUX_GPIO44__FUNC_SPI2_CLK_A (MTK_PIN_NO(44) | 1) +#define PINMUX_GPIO44__FUNC_SCP_SPI0_CK (MTK_PIN_NO(44) | 2) +#define PINMUX_GPIO44__FUNC_DBG_MON_A19 (MTK_PIN_NO(44) | 7) + +#define PINMUX_GPIO45__FUNC_GPIO45 (MTK_PIN_NO(45) | 0) +#define PINMUX_GPIO45__FUNC_SPI2_CSB_A (MTK_PIN_NO(45) | 1) +#define PINMUX_GPIO45__FUNC_SCP_SPI0_CS (MTK_PIN_NO(45) | 2) +#define PINMUX_GPIO45__FUNC_DBG_MON_A20 (MTK_PIN_NO(45) | 7) + +#define PINMUX_GPIO46__FUNC_GPIO46 (MTK_PIN_NO(46) | 0) +#define PINMUX_GPIO46__FUNC_SPI2_MO_A (MTK_PIN_NO(46) | 1) +#define PINMUX_GPIO46__FUNC_SCP_SPI0_MO (MTK_PIN_NO(46) | 2) +#define PINMUX_GPIO46__FUNC_DBG_MON_A21 (MTK_PIN_NO(46) | 7) + +#define PINMUX_GPIO47__FUNC_GPIO47 (MTK_PIN_NO(47) | 0) +#define PINMUX_GPIO47__FUNC_SPI2_MI_A (MTK_PIN_NO(47) | 1) +#define PINMUX_GPIO47__FUNC_SCP_SPI0_MI (MTK_PIN_NO(47) | 2) +#define PINMUX_GPIO47__FUNC_DBG_MON_A22 (MTK_PIN_NO(47) | 7) + +#define PINMUX_GPIO48__FUNC_GPIO48 (MTK_PIN_NO(48) | 0) +#define PINMUX_GPIO48__FUNC_SPI3_CLK (MTK_PIN_NO(48) | 1) +#define PINMUX_GPIO48__FUNC_TP_URXD1_AO (MTK_PIN_NO(48) | 2) +#define PINMUX_GPIO48__FUNC_TP_URXD2_AO (MTK_PIN_NO(48) | 3) +#define PINMUX_GPIO48__FUNC_URXD1 (MTK_PIN_NO(48) | 4) +#define PINMUX_GPIO48__FUNC_I2S2_MCK (MTK_PIN_NO(48) | 5) +#define PINMUX_GPIO48__FUNC_SCP_SPI0_CK (MTK_PIN_NO(48) | 6) + +#define PINMUX_GPIO49__FUNC_GPIO49 (MTK_PIN_NO(49) | 0) +#define PINMUX_GPIO49__FUNC_SPI3_CSB (MTK_PIN_NO(49) | 1) +#define PINMUX_GPIO49__FUNC_TP_UTXD1_AO (MTK_PIN_NO(49) | 2) +#define PINMUX_GPIO49__FUNC_TP_UTXD2_AO (MTK_PIN_NO(49) | 3) +#define PINMUX_GPIO49__FUNC_UTXD1 (MTK_PIN_NO(49) | 4) +#define PINMUX_GPIO49__FUNC_I2S2_BCK (MTK_PIN_NO(49) | 5) +#define PINMUX_GPIO49__FUNC_SCP_SPI0_CS (MTK_PIN_NO(49) | 6) + +#define PINMUX_GPIO50__FUNC_GPIO50 (MTK_PIN_NO(50) | 0) +#define PINMUX_GPIO50__FUNC_SPI3_MO (MTK_PIN_NO(50) | 1) +#define PINMUX_GPIO50__FUNC_I2S2_LRCK (MTK_PIN_NO(50) | 5) +#define PINMUX_GPIO50__FUNC_SCP_SPI0_MO (MTK_PIN_NO(50) | 6) + +#define PINMUX_GPIO51__FUNC_GPIO51 (MTK_PIN_NO(51) | 0) +#define PINMUX_GPIO51__FUNC_SPI3_MI (MTK_PIN_NO(51) | 1) +#define PINMUX_GPIO51__FUNC_I2S2_DI (MTK_PIN_NO(51) | 5) +#define PINMUX_GPIO51__FUNC_SCP_SPI0_MI (MTK_PIN_NO(51) | 6) + +#define PINMUX_GPIO52__FUNC_GPIO52 (MTK_PIN_NO(52) | 0) +#define PINMUX_GPIO52__FUNC_SPI5_CLK (MTK_PIN_NO(52) | 1) +#define PINMUX_GPIO52__FUNC_I2S2_MCK (MTK_PIN_NO(52) | 2) +#define PINMUX_GPIO52__FUNC_I2S1_MCK (MTK_PIN_NO(52) | 3) +#define PINMUX_GPIO52__FUNC_SCP_SPI1_CK (MTK_PIN_NO(52) | 4) +#define PINMUX_GPIO52__FUNC_LVTS_26M (MTK_PIN_NO(52) | 5) +#define PINMUX_GPIO52__FUNC_DFD_TCK_XI (MTK_PIN_NO(52) | 6) +#define PINMUX_GPIO52__FUNC_DBG_MON_B30 (MTK_PIN_NO(52) | 7) + +#define PINMUX_GPIO53__FUNC_GPIO53 (MTK_PIN_NO(53) | 0) +#define PINMUX_GPIO53__FUNC_SPI5_CSB (MTK_PIN_NO(53) | 1) +#define PINMUX_GPIO53__FUNC_I2S2_BCK (MTK_PIN_NO(53) | 2) +#define PINMUX_GPIO53__FUNC_I2S1_BCK (MTK_PIN_NO(53) | 3) +#define PINMUX_GPIO53__FUNC_SCP_SPI1_CS (MTK_PIN_NO(53) | 4) +#define PINMUX_GPIO53__FUNC_LVTS_FOUT (MTK_PIN_NO(53) | 5) +#define PINMUX_GPIO53__FUNC_DFD_TDI (MTK_PIN_NO(53) | 6) +#define PINMUX_GPIO53__FUNC_DBG_MON_B31 (MTK_PIN_NO(53) | 7) + +#define PINMUX_GPIO54__FUNC_GPIO54 (MTK_PIN_NO(54) | 0) +#define PINMUX_GPIO54__FUNC_SPI5_MO (MTK_PIN_NO(54) | 1) +#define PINMUX_GPIO54__FUNC_I2S2_LRCK (MTK_PIN_NO(54) | 2) +#define PINMUX_GPIO54__FUNC_I2S1_LRCK (MTK_PIN_NO(54) | 3) +#define PINMUX_GPIO54__FUNC_SCP_SPI1_MO (MTK_PIN_NO(54) | 4) +#define PINMUX_GPIO54__FUNC_LVTS_SCK (MTK_PIN_NO(54) | 5) +#define PINMUX_GPIO54__FUNC_DFD_TDO (MTK_PIN_NO(54) | 6) +#define PINMUX_GPIO54__FUNC_DBG_MON_A1 (MTK_PIN_NO(54) | 7) + +#define PINMUX_GPIO55__FUNC_GPIO55 (MTK_PIN_NO(55) | 0) +#define PINMUX_GPIO55__FUNC_SPI5_MI (MTK_PIN_NO(55) | 1) +#define PINMUX_GPIO55__FUNC_I2S2_DI (MTK_PIN_NO(55) | 2) +#define PINMUX_GPIO55__FUNC_I2S1_DO (MTK_PIN_NO(55) | 3) +#define PINMUX_GPIO55__FUNC_SCP_SPI1_MI (MTK_PIN_NO(55) | 4) +#define PINMUX_GPIO55__FUNC_LVTS_SDO (MTK_PIN_NO(55) | 5) +#define PINMUX_GPIO55__FUNC_DFD_TMS (MTK_PIN_NO(55) | 6) +#define PINMUX_GPIO55__FUNC_DBG_MON_B32 (MTK_PIN_NO(55) | 7) + +#define PINMUX_GPIO56__FUNC_GPIO56 (MTK_PIN_NO(56) | 0) +#define PINMUX_GPIO56__FUNC_I2S1_DO (MTK_PIN_NO(56) | 1) +#define PINMUX_GPIO56__FUNC_I2S3_DO (MTK_PIN_NO(56) | 2) +#define PINMUX_GPIO56__FUNC_DBG_MON_A23 (MTK_PIN_NO(56) | 7) + +#define PINMUX_GPIO57__FUNC_GPIO57 (MTK_PIN_NO(57) | 0) +#define PINMUX_GPIO57__FUNC_I2S1_BCK (MTK_PIN_NO(57) | 1) +#define PINMUX_GPIO57__FUNC_I2S3_BCK (MTK_PIN_NO(57) | 2) +#define PINMUX_GPIO57__FUNC_DBG_MON_A24 (MTK_PIN_NO(57) | 7) + +#define PINMUX_GPIO58__FUNC_GPIO58 (MTK_PIN_NO(58) | 0) +#define PINMUX_GPIO58__FUNC_I2S1_LRCK (MTK_PIN_NO(58) | 1) +#define PINMUX_GPIO58__FUNC_I2S3_LRCK (MTK_PIN_NO(58) | 2) +#define PINMUX_GPIO58__FUNC_DBG_MON_A25 (MTK_PIN_NO(58) | 7) + +#define PINMUX_GPIO59__FUNC_GPIO59 (MTK_PIN_NO(59) | 0) +#define PINMUX_GPIO59__FUNC_I2S1_MCK (MTK_PIN_NO(59) | 1) +#define PINMUX_GPIO59__FUNC_I2S3_MCK (MTK_PIN_NO(59) | 2) +#define PINMUX_GPIO59__FUNC_DBG_MON_A27 (MTK_PIN_NO(59) | 7) + +#define PINMUX_GPIO60__FUNC_GPIO60 (MTK_PIN_NO(60) | 0) +#define PINMUX_GPIO60__FUNC_TDM_RX_LRCK (MTK_PIN_NO(60) | 1) +#define PINMUX_GPIO60__FUNC_ANT_SEL3 (MTK_PIN_NO(60) | 2) +#define PINMUX_GPIO60__FUNC_CONN_MCU_DBGACK_N (MTK_PIN_NO(60) | 5) + +#define PINMUX_GPIO61__FUNC_GPIO61 (MTK_PIN_NO(61) | 0) +#define PINMUX_GPIO61__FUNC_TDM_RX_BCK (MTK_PIN_NO(61) | 1) +#define PINMUX_GPIO61__FUNC_ANT_SEL4 (MTK_PIN_NO(61) | 2) +#define PINMUX_GPIO61__FUNC_SPINOR_CK (MTK_PIN_NO(61) | 4) +#define PINMUX_GPIO61__FUNC_CONN_MCU_DBGI_N (MTK_PIN_NO(61) | 5) + +#define PINMUX_GPIO62__FUNC_GPIO62 (MTK_PIN_NO(62) | 0) +#define PINMUX_GPIO62__FUNC_TDM_RX_MCK (MTK_PIN_NO(62) | 1) +#define PINMUX_GPIO62__FUNC_ANT_SEL5 (MTK_PIN_NO(62) | 2) +#define PINMUX_GPIO62__FUNC_SPINOR_CS (MTK_PIN_NO(62) | 4) +#define PINMUX_GPIO62__FUNC_CONN_MCU_TDI (MTK_PIN_NO(62) | 5) + +#define PINMUX_GPIO63__FUNC_GPIO63 (MTK_PIN_NO(63) | 0) +#define PINMUX_GPIO63__FUNC_TDM_RX_DATA0 (MTK_PIN_NO(63) | 1) +#define PINMUX_GPIO63__FUNC_ANT_SEL6 (MTK_PIN_NO(63) | 2) +#define PINMUX_GPIO63__FUNC_SPINOR_IO0 (MTK_PIN_NO(63) | 4) +#define PINMUX_GPIO63__FUNC_CONN_MCU_TRST_B (MTK_PIN_NO(63) | 5) + +#define PINMUX_GPIO64__FUNC_GPIO64 (MTK_PIN_NO(64) | 0) +#define PINMUX_GPIO64__FUNC_TDM_RX_DATA1 (MTK_PIN_NO(64) | 1) +#define PINMUX_GPIO64__FUNC_ANT_SEL7 (MTK_PIN_NO(64) | 2) +#define PINMUX_GPIO64__FUNC_PWM0 (MTK_PIN_NO(64) | 3) +#define PINMUX_GPIO64__FUNC_SPINOR_IO1 (MTK_PIN_NO(64) | 4) +#define PINMUX_GPIO64__FUNC_CONN_MCU_TCK (MTK_PIN_NO(64) | 5) + +#define PINMUX_GPIO65__FUNC_GPIO65 (MTK_PIN_NO(65) | 0) +#define PINMUX_GPIO65__FUNC_TDM_RX_DATA2 (MTK_PIN_NO(65) | 1) +#define PINMUX_GPIO65__FUNC_UCTS0 (MTK_PIN_NO(65) | 2) +#define PINMUX_GPIO65__FUNC_PWM1 (MTK_PIN_NO(65) | 3) +#define PINMUX_GPIO65__FUNC_SPINOR_IO2 (MTK_PIN_NO(65) | 4) +#define PINMUX_GPIO65__FUNC_CONN_MCU_TDO (MTK_PIN_NO(65) | 5) +#define PINMUX_GPIO65__FUNC_TP_UCTS1_AO (MTK_PIN_NO(65) | 6) +#define PINMUX_GPIO65__FUNC_TP_UCTS2_AO (MTK_PIN_NO(65) | 7) + +#define PINMUX_GPIO66__FUNC_GPIO66 (MTK_PIN_NO(66) | 0) +#define PINMUX_GPIO66__FUNC_TDM_RX_DATA3 (MTK_PIN_NO(66) | 1) +#define PINMUX_GPIO66__FUNC_URTS0 (MTK_PIN_NO(66) | 2) +#define PINMUX_GPIO66__FUNC_PWM2 (MTK_PIN_NO(66) | 3) +#define PINMUX_GPIO66__FUNC_SPINOR_IO3 (MTK_PIN_NO(66) | 4) +#define PINMUX_GPIO66__FUNC_CONN_MCU_TMS (MTK_PIN_NO(66) | 5) +#define PINMUX_GPIO66__FUNC_TP_URTS1_AO (MTK_PIN_NO(66) | 6) +#define PINMUX_GPIO66__FUNC_TP_URTS2_AO (MTK_PIN_NO(66) | 7) + +#define PINMUX_GPIO67__FUNC_GPIO67 (MTK_PIN_NO(67) | 0) +#define PINMUX_GPIO67__FUNC_MSDC0_DSL (MTK_PIN_NO(67) | 1) + +#define PINMUX_GPIO68__FUNC_GPIO68 (MTK_PIN_NO(68) | 0) +#define PINMUX_GPIO68__FUNC_MSDC0_CLK (MTK_PIN_NO(68) | 1) + +#define PINMUX_GPIO69__FUNC_GPIO69 (MTK_PIN_NO(69) | 0) +#define PINMUX_GPIO69__FUNC_MSDC0_CMD (MTK_PIN_NO(69) | 1) + +#define PINMUX_GPIO70__FUNC_GPIO70 (MTK_PIN_NO(70) | 0) +#define PINMUX_GPIO70__FUNC_MSDC0_RSTB (MTK_PIN_NO(70) | 1) + +#define PINMUX_GPIO71__FUNC_GPIO71 (MTK_PIN_NO(71) | 0) +#define PINMUX_GPIO71__FUNC_MSDC0_DAT0 (MTK_PIN_NO(71) | 1) + +#define PINMUX_GPIO72__FUNC_GPIO72 (MTK_PIN_NO(72) | 0) +#define PINMUX_GPIO72__FUNC_MSDC0_DAT1 (MTK_PIN_NO(72) | 1) + +#define PINMUX_GPIO73__FUNC_GPIO73 (MTK_PIN_NO(73) | 0) +#define PINMUX_GPIO73__FUNC_MSDC0_DAT2 (MTK_PIN_NO(73) | 1) + +#define PINMUX_GPIO74__FUNC_GPIO74 (MTK_PIN_NO(74) | 0) +#define PINMUX_GPIO74__FUNC_MSDC0_DAT3 (MTK_PIN_NO(74) | 1) + +#define PINMUX_GPIO75__FUNC_GPIO75 (MTK_PIN_NO(75) | 0) +#define PINMUX_GPIO75__FUNC_MSDC0_DAT4 (MTK_PIN_NO(75) | 1) + +#define PINMUX_GPIO76__FUNC_GPIO76 (MTK_PIN_NO(76) | 0) +#define PINMUX_GPIO76__FUNC_MSDC0_DAT5 (MTK_PIN_NO(76) | 1) + +#define PINMUX_GPIO77__FUNC_GPIO77 (MTK_PIN_NO(77) | 0) +#define PINMUX_GPIO77__FUNC_MSDC0_DAT6 (MTK_PIN_NO(77) | 1) + +#define PINMUX_GPIO78__FUNC_GPIO78 (MTK_PIN_NO(78) | 0) +#define PINMUX_GPIO78__FUNC_MSDC0_DAT7 (MTK_PIN_NO(78) | 1) + +#define PINMUX_GPIO79__FUNC_GPIO79 (MTK_PIN_NO(79) | 0) +#define PINMUX_GPIO79__FUNC_KPCOL0 (MTK_PIN_NO(79) | 1) + +#define PINMUX_GPIO80__FUNC_GPIO80 (MTK_PIN_NO(80) | 0) +#define PINMUX_GPIO80__FUNC_KPCOL1 (MTK_PIN_NO(80) | 1) +#define PINMUX_GPIO80__FUNC_GPS_L1_ELNA_EN (MTK_PIN_NO(80) | 2) +#define PINMUX_GPIO80__FUNC_PWM0 (MTK_PIN_NO(80) | 3) +#define PINMUX_GPIO80__FUNC_CLKM0 (MTK_PIN_NO(80) | 4) + +#define PINMUX_GPIO81__FUNC_GPIO81 (MTK_PIN_NO(81) | 0) +#define PINMUX_GPIO81__FUNC_KPROW0 (MTK_PIN_NO(81) | 1) +#define PINMUX_GPIO81__FUNC_PWM1 (MTK_PIN_NO(81) | 3) +#define PINMUX_GPIO81__FUNC_CLKM1 (MTK_PIN_NO(81) | 4) + +#define PINMUX_GPIO82__FUNC_GPIO82 (MTK_PIN_NO(82) | 0) +#define PINMUX_GPIO82__FUNC_KPROW1 (MTK_PIN_NO(82) | 1) +#define PINMUX_GPIO82__FUNC_PWM2 (MTK_PIN_NO(82) | 3) +#define PINMUX_GPIO82__FUNC_CLKM2 (MTK_PIN_NO(82) | 4) + +#define PINMUX_GPIO83__FUNC_GPIO83 (MTK_PIN_NO(83) | 0) +#define PINMUX_GPIO83__FUNC_AP_GOOD (MTK_PIN_NO(83) | 1) +#define PINMUX_GPIO83__FUNC_GPS_PPS (MTK_PIN_NO(83) | 2) +#define PINMUX_GPIO83__FUNC_EXT_FRAME_SYNC (MTK_PIN_NO(83) | 4) +#define PINMUX_GPIO83__FUNC_DBG_MON_A28 (MTK_PIN_NO(83) | 7) + +#define PINMUX_GPIO84__FUNC_GPIO84 (MTK_PIN_NO(84) | 0) +#define PINMUX_GPIO84__FUNC_MSDC1_CLK (MTK_PIN_NO(84) | 1) +#define PINMUX_GPIO84__FUNC_ADSP_JTAG_TCK (MTK_PIN_NO(84) | 2) +#define PINMUX_GPIO84__FUNC_UDI_TCK (MTK_PIN_NO(84) | 4) +#define PINMUX_GPIO84__FUNC_CONN_DSP_JCK (MTK_PIN_NO(84) | 5) +#define PINMUX_GPIO84__FUNC_SSPM_JTAG_TCK (MTK_PIN_NO(84) | 6) +#define PINMUX_GPIO84__FUNC_DFD_TCK_XI (MTK_PIN_NO(84) | 7) + +#define PINMUX_GPIO85__FUNC_GPIO85 (MTK_PIN_NO(85) | 0) +#define PINMUX_GPIO85__FUNC_MSDC1_CMD (MTK_PIN_NO(85) | 1) +#define PINMUX_GPIO85__FUNC_ADSP_JTAG_TMS (MTK_PIN_NO(85) | 2) +#define PINMUX_GPIO85__FUNC_CONN_MCU_AICE_TMSC (MTK_PIN_NO(85) | 3) +#define PINMUX_GPIO85__FUNC_UDI_TMS (MTK_PIN_NO(85) | 4) +#define PINMUX_GPIO85__FUNC_CONN_DSP_JMS (MTK_PIN_NO(85) | 5) +#define PINMUX_GPIO85__FUNC_SSPM_JTAG_TMS (MTK_PIN_NO(85) | 6) +#define PINMUX_GPIO85__FUNC_DFD_TMS (MTK_PIN_NO(85) | 7) + +#define PINMUX_GPIO86__FUNC_GPIO86 (MTK_PIN_NO(86) | 0) +#define PINMUX_GPIO86__FUNC_MSDC1_DAT0 (MTK_PIN_NO(86) | 1) +#define PINMUX_GPIO86__FUNC_ADSP_JTAG_TDI (MTK_PIN_NO(86) | 2) +#define PINMUX_GPIO86__FUNC_UDI_TDI (MTK_PIN_NO(86) | 4) +#define PINMUX_GPIO86__FUNC_CONN_DSP_JDI (MTK_PIN_NO(86) | 5) +#define PINMUX_GPIO86__FUNC_SSPM_JTAG_TDI (MTK_PIN_NO(86) | 6) +#define PINMUX_GPIO86__FUNC_DFD_TDI (MTK_PIN_NO(86) | 7) + +#define PINMUX_GPIO87__FUNC_GPIO87 (MTK_PIN_NO(87) | 0) +#define PINMUX_GPIO87__FUNC_MSDC1_DAT1 (MTK_PIN_NO(87) | 1) +#define PINMUX_GPIO87__FUNC_ADSP_JTAG_TDO (MTK_PIN_NO(87) | 2) +#define PINMUX_GPIO87__FUNC_UDI_TDO (MTK_PIN_NO(87) | 4) +#define PINMUX_GPIO87__FUNC_CONN_DSP_JDO (MTK_PIN_NO(87) | 5) +#define PINMUX_GPIO87__FUNC_SSPM_JTAG_TDO (MTK_PIN_NO(87) | 6) +#define PINMUX_GPIO87__FUNC_DFD_TDO (MTK_PIN_NO(87) | 7) + +#define PINMUX_GPIO88__FUNC_GPIO88 (MTK_PIN_NO(88) | 0) +#define PINMUX_GPIO88__FUNC_MSDC1_DAT2 (MTK_PIN_NO(88) | 1) +#define PINMUX_GPIO88__FUNC_ADSP_JTAG_TRSTN (MTK_PIN_NO(88) | 2) +#define PINMUX_GPIO88__FUNC_CONN_MCU_AICE_TCKC (MTK_PIN_NO(88) | 3) +#define PINMUX_GPIO88__FUNC_UDI_NTRST (MTK_PIN_NO(88) | 4) +#define PINMUX_GPIO88__FUNC_CONN_WIFI_TXD (MTK_PIN_NO(88) | 5) +#define PINMUX_GPIO88__FUNC_SSPM_JTAG_TRSTN (MTK_PIN_NO(88) | 6) + +#define PINMUX_GPIO89__FUNC_GPIO89 (MTK_PIN_NO(89) | 0) +#define PINMUX_GPIO89__FUNC_MSDC1_DAT3 (MTK_PIN_NO(89) | 1) +#define PINMUX_GPIO89__FUNC_CONN_DSP_JINTP (MTK_PIN_NO(89) | 5) + +#define PINMUX_GPIO90__FUNC_GPIO90 (MTK_PIN_NO(90) | 0) +#define PINMUX_GPIO90__FUNC_IDDIG_P0 (MTK_PIN_NO(90) | 1) +#define PINMUX_GPIO90__FUNC_PGD_HV_HSC_PWR4 (MTK_PIN_NO(90) | 4) +#define PINMUX_GPIO90__FUNC_GDU_SUM_TROOP2_2 (MTK_PIN_NO(90) | 5) + +#define PINMUX_GPIO91__FUNC_GPIO91 (MTK_PIN_NO(91) | 0) +#define PINMUX_GPIO91__FUNC_USB_DRVVBUS_P0 (MTK_PIN_NO(91) | 1) +#define PINMUX_GPIO91__FUNC_PGD_HV_HSC_PWR5 (MTK_PIN_NO(91) | 4) +#define PINMUX_GPIO91__FUNC_GDU_TROOPS_DET0 (MTK_PIN_NO(91) | 5) + +#define PINMUX_GPIO92__FUNC_GPIO92 (MTK_PIN_NO(92) | 0) +#define PINMUX_GPIO92__FUNC_VBUS_VALID_P0 (MTK_PIN_NO(92) | 1) +#define PINMUX_GPIO92__FUNC_PGD_DA_EFUSE_RDY (MTK_PIN_NO(92) | 4) +#define PINMUX_GPIO92__FUNC_GDU_TROOPS_DET1 (MTK_PIN_NO(92) | 5) + +#define PINMUX_GPIO93__FUNC_GPIO93 (MTK_PIN_NO(93) | 0) +#define PINMUX_GPIO93__FUNC_IDDIG_P1 (MTK_PIN_NO(93) | 1) +#define PINMUX_GPIO93__FUNC_PWM0 (MTK_PIN_NO(93) | 2) +#define PINMUX_GPIO93__FUNC_CLKM0 (MTK_PIN_NO(93) | 3) +#define PINMUX_GPIO93__FUNC_PGD_DA_EFUSE_RDY_PRE (MTK_PIN_NO(93) | 4) +#define PINMUX_GPIO93__FUNC_GDU_TROOPS_DET2 (MTK_PIN_NO(93) | 5) + +#define PINMUX_GPIO94__FUNC_GPIO94 (MTK_PIN_NO(94) | 0) +#define PINMUX_GPIO94__FUNC_USB_DRVVBUS_P1 (MTK_PIN_NO(94) | 1) +#define PINMUX_GPIO94__FUNC_PWM1 (MTK_PIN_NO(94) | 2) +#define PINMUX_GPIO94__FUNC_CLKM1 (MTK_PIN_NO(94) | 3) +#define PINMUX_GPIO94__FUNC_PGD_DA_PWRGD_RESET (MTK_PIN_NO(94) | 4) + +#define PINMUX_GPIO95__FUNC_GPIO95 (MTK_PIN_NO(95) | 0) +#define PINMUX_GPIO95__FUNC_VBUS_VALID_P1 (MTK_PIN_NO(95) | 1) +#define PINMUX_GPIO95__FUNC_PWM2 (MTK_PIN_NO(95) | 2) +#define PINMUX_GPIO95__FUNC_CLKM2 (MTK_PIN_NO(95) | 3) +#define PINMUX_GPIO95__FUNC_PGD_DA_PWRGD_ENB (MTK_PIN_NO(95) | 4) + +#define PINMUX_GPIO96__FUNC_GPIO96 (MTK_PIN_NO(96) | 0) +#define PINMUX_GPIO96__FUNC_DSI_TE (MTK_PIN_NO(96) | 1) +#define PINMUX_GPIO96__FUNC_DBG_MON_A29 (MTK_PIN_NO(96) | 7) + +#define PINMUX_GPIO97__FUNC_GPIO97 (MTK_PIN_NO(97) | 0) +#define PINMUX_GPIO97__FUNC_DISP_PWM (MTK_PIN_NO(97) | 1) +#define PINMUX_GPIO97__FUNC_DBG_MON_A30 (MTK_PIN_NO(97) | 7) + +#define PINMUX_GPIO98__FUNC_GPIO98 (MTK_PIN_NO(98) | 0) +#define PINMUX_GPIO98__FUNC_LCM_RST (MTK_PIN_NO(98) | 1) + +#define PINMUX_GPIO99__FUNC_GPIO99 (MTK_PIN_NO(99) | 0) +#define PINMUX_GPIO99__FUNC_DPI_PCLK (MTK_PIN_NO(99) | 1) +#define PINMUX_GPIO99__FUNC_GPS_L1_ELNA_EN (MTK_PIN_NO(99) | 2) +#define PINMUX_GPIO99__FUNC_SSPM_JTAG_TCK (MTK_PIN_NO(99) | 3) +#define PINMUX_GPIO99__FUNC_ANT_SEL0 (MTK_PIN_NO(99) | 5) +#define PINMUX_GPIO99__FUNC_TP_GPIO0_AO (MTK_PIN_NO(99) | 6) +#define PINMUX_GPIO99__FUNC_PGD_LV_LSC_PWR0 (MTK_PIN_NO(99) | 7) + +#define PINMUX_GPIO100__FUNC_GPIO100 (MTK_PIN_NO(100) | 0) +#define PINMUX_GPIO100__FUNC_DPI_VSYNC (MTK_PIN_NO(100) | 1) +#define PINMUX_GPIO100__FUNC_KPCOL2 (MTK_PIN_NO(100) | 2) +#define PINMUX_GPIO100__FUNC_SSPM_JTAG_TMS (MTK_PIN_NO(100) | 3) +#define PINMUX_GPIO100__FUNC_ANT_SEL1 (MTK_PIN_NO(100) | 5) +#define PINMUX_GPIO100__FUNC_TP_GPIO1_AO (MTK_PIN_NO(100) | 6) +#define PINMUX_GPIO100__FUNC_PGD_LV_LSC_PWR1 (MTK_PIN_NO(100) | 7) + +#define PINMUX_GPIO101__FUNC_GPIO101 (MTK_PIN_NO(101) | 0) +#define PINMUX_GPIO101__FUNC_DPI_HSYNC (MTK_PIN_NO(101) | 1) +#define PINMUX_GPIO101__FUNC_KPROW2 (MTK_PIN_NO(101) | 2) +#define PINMUX_GPIO101__FUNC_SSPM_JTAG_TDI (MTK_PIN_NO(101) | 3) +#define PINMUX_GPIO101__FUNC_ANT_SEL2 (MTK_PIN_NO(101) | 5) +#define PINMUX_GPIO101__FUNC_TP_GPIO2_AO (MTK_PIN_NO(101) | 6) +#define PINMUX_GPIO101__FUNC_PGD_LV_LSC_PWR2 (MTK_PIN_NO(101) | 7) + +#define PINMUX_GPIO102__FUNC_GPIO102 (MTK_PIN_NO(102) | 0) +#define PINMUX_GPIO102__FUNC_DPI_DE (MTK_PIN_NO(102) | 1) +#define PINMUX_GPIO102__FUNC_SSPM_JTAG_TDO (MTK_PIN_NO(102) | 3) +#define PINMUX_GPIO102__FUNC_ANT_SEL3 (MTK_PIN_NO(102) | 5) +#define PINMUX_GPIO102__FUNC_TP_GPIO3_AO (MTK_PIN_NO(102) | 6) +#define PINMUX_GPIO102__FUNC_PGD_LV_LSC_PWR3 (MTK_PIN_NO(102) | 7) + +#define PINMUX_GPIO103__FUNC_GPIO103 (MTK_PIN_NO(103) | 0) +#define PINMUX_GPIO103__FUNC_DPI_DATA0 (MTK_PIN_NO(103) | 1) +#define PINMUX_GPIO103__FUNC_SSPM_JTAG_TRSTN (MTK_PIN_NO(103) | 3) +#define PINMUX_GPIO103__FUNC_CLKM0 (MTK_PIN_NO(103) | 4) +#define PINMUX_GPIO103__FUNC_ANT_SEL4 (MTK_PIN_NO(103) | 5) +#define PINMUX_GPIO103__FUNC_TP_GPIO4_AO (MTK_PIN_NO(103) | 6) +#define PINMUX_GPIO103__FUNC_PGD_LV_LSC_PWR4 (MTK_PIN_NO(103) | 7) + +#define PINMUX_GPIO104__FUNC_GPIO104 (MTK_PIN_NO(104) | 0) +#define PINMUX_GPIO104__FUNC_DPI_DATA1 (MTK_PIN_NO(104) | 1) +#define PINMUX_GPIO104__FUNC_GPS_PPS (MTK_PIN_NO(104) | 2) +#define PINMUX_GPIO104__FUNC_UCTS2 (MTK_PIN_NO(104) | 3) +#define PINMUX_GPIO104__FUNC_CLKM1 (MTK_PIN_NO(104) | 4) +#define PINMUX_GPIO104__FUNC_ANT_SEL5 (MTK_PIN_NO(104) | 5) +#define PINMUX_GPIO104__FUNC_TP_GPIO5_AO (MTK_PIN_NO(104) | 6) +#define PINMUX_GPIO104__FUNC_PGD_LV_LSC_PWR5 (MTK_PIN_NO(104) | 7) + +#define PINMUX_GPIO105__FUNC_GPIO105 (MTK_PIN_NO(105) | 0) +#define PINMUX_GPIO105__FUNC_DPI_DATA2 (MTK_PIN_NO(105) | 1) +#define PINMUX_GPIO105__FUNC_CONN_TCXOENA_REQ (MTK_PIN_NO(105) | 2) +#define PINMUX_GPIO105__FUNC_URTS2 (MTK_PIN_NO(105) | 3) +#define PINMUX_GPIO105__FUNC_CLKM2 (MTK_PIN_NO(105) | 4) +#define PINMUX_GPIO105__FUNC_ANT_SEL6 (MTK_PIN_NO(105) | 5) +#define PINMUX_GPIO105__FUNC_TP_GPIO6_AO (MTK_PIN_NO(105) | 6) +#define PINMUX_GPIO105__FUNC_PGD_LV_HSC_PWR0 (MTK_PIN_NO(105) | 7) + +#define PINMUX_GPIO106__FUNC_GPIO106 (MTK_PIN_NO(106) | 0) +#define PINMUX_GPIO106__FUNC_DPI_DATA3 (MTK_PIN_NO(106) | 1) +#define PINMUX_GPIO106__FUNC_TP_UTXD1_AO (MTK_PIN_NO(106) | 2) +#define PINMUX_GPIO106__FUNC_UTXD2 (MTK_PIN_NO(106) | 3) +#define PINMUX_GPIO106__FUNC_PWM0 (MTK_PIN_NO(106) | 4) +#define PINMUX_GPIO106__FUNC_ANT_SEL7 (MTK_PIN_NO(106) | 5) +#define PINMUX_GPIO106__FUNC_TP_GPIO7_AO (MTK_PIN_NO(106) | 6) +#define PINMUX_GPIO106__FUNC_PGD_LV_HSC_PWR1 (MTK_PIN_NO(106) | 7) + +#define PINMUX_GPIO107__FUNC_GPIO107 (MTK_PIN_NO(107) | 0) +#define PINMUX_GPIO107__FUNC_DPI_DATA4 (MTK_PIN_NO(107) | 1) +#define PINMUX_GPIO107__FUNC_TP_URXD1_AO (MTK_PIN_NO(107) | 2) +#define PINMUX_GPIO107__FUNC_URXD2 (MTK_PIN_NO(107) | 3) +#define PINMUX_GPIO107__FUNC_PWM1 (MTK_PIN_NO(107) | 4) +#define PINMUX_GPIO107__FUNC_GDU_SUM_TROOP0_0 (MTK_PIN_NO(107) | 6) +#define PINMUX_GPIO107__FUNC_PGD_LV_HSC_PWR2 (MTK_PIN_NO(107) | 7) + +#define PINMUX_GPIO108__FUNC_GPIO108 (MTK_PIN_NO(108) | 0) +#define PINMUX_GPIO108__FUNC_DPI_DATA5 (MTK_PIN_NO(108) | 1) +#define PINMUX_GPIO108__FUNC_TP_UCTS1_AO (MTK_PIN_NO(108) | 2) +#define PINMUX_GPIO108__FUNC_UCTS0 (MTK_PIN_NO(108) | 3) +#define PINMUX_GPIO108__FUNC_PWM2 (MTK_PIN_NO(108) | 4) +#define PINMUX_GPIO108__FUNC_GDU_SUM_TROOP0_1 (MTK_PIN_NO(108) | 6) +#define PINMUX_GPIO108__FUNC_PGD_LV_HSC_PWR3 (MTK_PIN_NO(108) | 7) + +#define PINMUX_GPIO109__FUNC_GPIO109 (MTK_PIN_NO(109) | 0) +#define PINMUX_GPIO109__FUNC_DPI_DATA6 (MTK_PIN_NO(109) | 1) +#define PINMUX_GPIO109__FUNC_TP_URTS1_AO (MTK_PIN_NO(109) | 2) +#define PINMUX_GPIO109__FUNC_URTS0 (MTK_PIN_NO(109) | 3) +#define PINMUX_GPIO109__FUNC_I2S0_DI (MTK_PIN_NO(109) | 4) +#define PINMUX_GPIO109__FUNC_I2S2_DI (MTK_PIN_NO(109) | 5) +#define PINMUX_GPIO109__FUNC_GDU_SUM_TROOP0_2 (MTK_PIN_NO(109) | 6) +#define PINMUX_GPIO109__FUNC_PGD_LV_HSC_PWR4 (MTK_PIN_NO(109) | 7) + +#define PINMUX_GPIO110__FUNC_GPIO110 (MTK_PIN_NO(110) | 0) +#define PINMUX_GPIO110__FUNC_DPI_DATA7 (MTK_PIN_NO(110) | 1) +#define PINMUX_GPIO110__FUNC_TP_UCTS2_AO (MTK_PIN_NO(110) | 2) +#define PINMUX_GPIO110__FUNC_UCTS1 (MTK_PIN_NO(110) | 3) +#define PINMUX_GPIO110__FUNC_I2S3_BCK (MTK_PIN_NO(110) | 4) +#define PINMUX_GPIO110__FUNC_I2S1_BCK (MTK_PIN_NO(110) | 5) +#define PINMUX_GPIO110__FUNC_GDU_SUM_TROOP1_0 (MTK_PIN_NO(110) | 6) +#define PINMUX_GPIO110__FUNC_PGD_LV_HSC_PWR5 (MTK_PIN_NO(110) | 7) + +#define PINMUX_GPIO111__FUNC_GPIO111 (MTK_PIN_NO(111) | 0) +#define PINMUX_GPIO111__FUNC_DPI_DATA8 (MTK_PIN_NO(111) | 1) +#define PINMUX_GPIO111__FUNC_TP_URTS2_AO (MTK_PIN_NO(111) | 2) +#define PINMUX_GPIO111__FUNC_URTS1 (MTK_PIN_NO(111) | 3) +#define PINMUX_GPIO111__FUNC_I2S3_MCK (MTK_PIN_NO(111) | 4) +#define PINMUX_GPIO111__FUNC_I2S1_MCK (MTK_PIN_NO(111) | 5) +#define PINMUX_GPIO111__FUNC_GDU_SUM_TROOP1_1 (MTK_PIN_NO(111) | 6) +#define PINMUX_GPIO111__FUNC_PGD_HV_HSC_PWR0 (MTK_PIN_NO(111) | 7) + +#define PINMUX_GPIO112__FUNC_GPIO112 (MTK_PIN_NO(112) | 0) +#define PINMUX_GPIO112__FUNC_DPI_DATA9 (MTK_PIN_NO(112) | 1) +#define PINMUX_GPIO112__FUNC_TP_URXD2_AO (MTK_PIN_NO(112) | 2) +#define PINMUX_GPIO112__FUNC_URXD1 (MTK_PIN_NO(112) | 3) +#define PINMUX_GPIO112__FUNC_I2S3_LRCK (MTK_PIN_NO(112) | 4) +#define PINMUX_GPIO112__FUNC_I2S1_LRCK (MTK_PIN_NO(112) | 5) +#define PINMUX_GPIO112__FUNC_GDU_SUM_TROOP1_2 (MTK_PIN_NO(112) | 6) +#define PINMUX_GPIO112__FUNC_PGD_HV_HSC_PWR1 (MTK_PIN_NO(112) | 7) + +#define PINMUX_GPIO113__FUNC_GPIO113 (MTK_PIN_NO(113) | 0) +#define PINMUX_GPIO113__FUNC_DPI_DATA10 (MTK_PIN_NO(113) | 1) +#define PINMUX_GPIO113__FUNC_TP_UTXD2_AO (MTK_PIN_NO(113) | 2) +#define PINMUX_GPIO113__FUNC_UTXD1 (MTK_PIN_NO(113) | 3) +#define PINMUX_GPIO113__FUNC_I2S3_DO (MTK_PIN_NO(113) | 4) +#define PINMUX_GPIO113__FUNC_I2S1_DO (MTK_PIN_NO(113) | 5) +#define PINMUX_GPIO113__FUNC_GDU_SUM_TROOP2_0 (MTK_PIN_NO(113) | 6) +#define PINMUX_GPIO113__FUNC_PGD_HV_HSC_PWR2 (MTK_PIN_NO(113) | 7) + +#define PINMUX_GPIO114__FUNC_GPIO114 (MTK_PIN_NO(114) | 0) +#define PINMUX_GPIO114__FUNC_DPI_DATA11 (MTK_PIN_NO(114) | 1) +#define PINMUX_GPIO114__FUNC_GDU_SUM_TROOP2_1 (MTK_PIN_NO(114) | 6) +#define PINMUX_GPIO114__FUNC_PGD_HV_HSC_PWR3 (MTK_PIN_NO(114) | 7) + +#define PINMUX_GPIO115__FUNC_GPIO115 (MTK_PIN_NO(115) | 0) +#define PINMUX_GPIO115__FUNC_PCM_CLK (MTK_PIN_NO(115) | 1) +#define PINMUX_GPIO115__FUNC_I2S0_BCK (MTK_PIN_NO(115) | 2) +#define PINMUX_GPIO115__FUNC_I2S2_BCK (MTK_PIN_NO(115) | 3) + +#define PINMUX_GPIO116__FUNC_GPIO116 (MTK_PIN_NO(116) | 0) +#define PINMUX_GPIO116__FUNC_PCM_SYNC (MTK_PIN_NO(116) | 1) +#define PINMUX_GPIO116__FUNC_I2S0_LRCK (MTK_PIN_NO(116) | 2) +#define PINMUX_GPIO116__FUNC_I2S2_LRCK (MTK_PIN_NO(116) | 3) + +#define PINMUX_GPIO117__FUNC_GPIO117 (MTK_PIN_NO(117) | 0) +#define PINMUX_GPIO117__FUNC_PCM_DI (MTK_PIN_NO(117) | 1) +#define PINMUX_GPIO117__FUNC_I2S0_DI (MTK_PIN_NO(117) | 2) +#define PINMUX_GPIO117__FUNC_I2S2_DI (MTK_PIN_NO(117) | 3) + +#define PINMUX_GPIO118__FUNC_GPIO118 (MTK_PIN_NO(118) | 0) +#define PINMUX_GPIO118__FUNC_PCM_DO (MTK_PIN_NO(118) | 1) +#define PINMUX_GPIO118__FUNC_I2S0_MCK (MTK_PIN_NO(118) | 2) +#define PINMUX_GPIO118__FUNC_I2S2_MCK (MTK_PIN_NO(118) | 3) +#define PINMUX_GPIO118__FUNC_I2S3_DO (MTK_PIN_NO(118) | 4) +#define PINMUX_GPIO118__FUNC_I2S1_DO (MTK_PIN_NO(118) | 5) + +#define PINMUX_GPIO119__FUNC_GPIO119 (MTK_PIN_NO(119) | 0) +#define PINMUX_GPIO119__FUNC_JTMS_SEL1 (MTK_PIN_NO(119) | 1) +#define PINMUX_GPIO119__FUNC_UDI_TMS (MTK_PIN_NO(119) | 2) +#define PINMUX_GPIO119__FUNC_DFD_TMS (MTK_PIN_NO(119) | 3) +#define PINMUX_GPIO119__FUNC_SPM_JTAG_TMS (MTK_PIN_NO(119) | 4) +#define PINMUX_GPIO119__FUNC_SCP_JTAG_TMS (MTK_PIN_NO(119) | 5) +#define PINMUX_GPIO119__FUNC_ADSP_JTAG_TMS (MTK_PIN_NO(119) | 6) + +#define PINMUX_GPIO120__FUNC_GPIO120 (MTK_PIN_NO(120) | 0) +#define PINMUX_GPIO120__FUNC_JTCK_SEL1 (MTK_PIN_NO(120) | 1) +#define PINMUX_GPIO120__FUNC_UDI_TCK (MTK_PIN_NO(120) | 2) +#define PINMUX_GPIO120__FUNC_DFD_TCK_XI (MTK_PIN_NO(120) | 3) +#define PINMUX_GPIO120__FUNC_SPM_JTAG_TCK (MTK_PIN_NO(120) | 4) +#define PINMUX_GPIO120__FUNC_SCP_JTAG_TCK (MTK_PIN_NO(120) | 5) +#define PINMUX_GPIO120__FUNC_ADSP_JTAG_TCK (MTK_PIN_NO(120) | 6) + +#define PINMUX_GPIO121__FUNC_GPIO121 (MTK_PIN_NO(121) | 0) +#define PINMUX_GPIO121__FUNC_JTDI_SEL1 (MTK_PIN_NO(121) | 1) +#define PINMUX_GPIO121__FUNC_UDI_TDI (MTK_PIN_NO(121) | 2) +#define PINMUX_GPIO121__FUNC_DFD_TDI (MTK_PIN_NO(121) | 3) +#define PINMUX_GPIO121__FUNC_SPM_JTAG_TDI (MTK_PIN_NO(121) | 4) +#define PINMUX_GPIO121__FUNC_SCP_JTAG_TDI (MTK_PIN_NO(121) | 5) +#define PINMUX_GPIO121__FUNC_ADSP_JTAG_TDI (MTK_PIN_NO(121) | 6) + +#define PINMUX_GPIO122__FUNC_GPIO122 (MTK_PIN_NO(122) | 0) +#define PINMUX_GPIO122__FUNC_JTDO_SEL1 (MTK_PIN_NO(122) | 1) +#define PINMUX_GPIO122__FUNC_UDI_TDO (MTK_PIN_NO(122) | 2) +#define PINMUX_GPIO122__FUNC_DFD_TDO (MTK_PIN_NO(122) | 3) +#define PINMUX_GPIO122__FUNC_SPM_JTAG_TDO (MTK_PIN_NO(122) | 4) +#define PINMUX_GPIO122__FUNC_SCP_JTAG_TDO (MTK_PIN_NO(122) | 5) +#define PINMUX_GPIO122__FUNC_ADSP_JTAG_TDO (MTK_PIN_NO(122) | 6) + +#define PINMUX_GPIO123__FUNC_GPIO123 (MTK_PIN_NO(123) | 0) +#define PINMUX_GPIO123__FUNC_JTRSTN_SEL1 (MTK_PIN_NO(123) | 1) +#define PINMUX_GPIO123__FUNC_UDI_NTRST (MTK_PIN_NO(123) | 2) +#define PINMUX_GPIO123__FUNC_SPM_JTAG_TRSTN (MTK_PIN_NO(123) | 4) +#define PINMUX_GPIO123__FUNC_SCP_JTAG_TRSTN (MTK_PIN_NO(123) | 5) +#define PINMUX_GPIO123__FUNC_ADSP_JTAG_TRSTN (MTK_PIN_NO(123) | 6) + +#define PINMUX_GPIO124__FUNC_GPIO124 (MTK_PIN_NO(124) | 0) +#define PINMUX_GPIO124__FUNC_CMMCLK0 (MTK_PIN_NO(124) | 1) +#define PINMUX_GPIO124__FUNC_CLKM0 (MTK_PIN_NO(124) | 2) +#define PINMUX_GPIO124__FUNC_PWM0 (MTK_PIN_NO(124) | 3) + +#define PINMUX_GPIO125__FUNC_GPIO125 (MTK_PIN_NO(125) | 0) +#define PINMUX_GPIO125__FUNC_CMMCLK1 (MTK_PIN_NO(125) | 1) +#define PINMUX_GPIO125__FUNC_CLKM1 (MTK_PIN_NO(125) | 2) +#define PINMUX_GPIO125__FUNC_PWM1 (MTK_PIN_NO(125) | 3) +#define PINMUX_GPIO125__FUNC_DBG_MON_B0 (MTK_PIN_NO(125) | 7) + +#define PINMUX_GPIO126__FUNC_GPIO126 (MTK_PIN_NO(126) | 0) +#define PINMUX_GPIO126__FUNC_CMMCLK2 (MTK_PIN_NO(126) | 1) +#define PINMUX_GPIO126__FUNC_CLKM2 (MTK_PIN_NO(126) | 2) +#define PINMUX_GPIO126__FUNC_PWM2 (MTK_PIN_NO(126) | 3) +#define PINMUX_GPIO126__FUNC_DBG_MON_B1 (MTK_PIN_NO(126) | 7) + +#define PINMUX_GPIO127__FUNC_GPIO127 (MTK_PIN_NO(127) | 0) +#define PINMUX_GPIO127__FUNC_SCL0 (MTK_PIN_NO(127) | 1) +#define PINMUX_GPIO127__FUNC_SCP_SCL0 (MTK_PIN_NO(127) | 4) +#define PINMUX_GPIO127__FUNC_SCP_SCL1 (MTK_PIN_NO(127) | 5) + +#define PINMUX_GPIO128__FUNC_GPIO128 (MTK_PIN_NO(128) | 0) +#define PINMUX_GPIO128__FUNC_SDA0 (MTK_PIN_NO(128) | 1) +#define PINMUX_GPIO128__FUNC_SCP_SDA0 (MTK_PIN_NO(128) | 4) +#define PINMUX_GPIO128__FUNC_SCP_SDA1 (MTK_PIN_NO(128) | 5) + +#define PINMUX_GPIO129__FUNC_GPIO129 (MTK_PIN_NO(129) | 0) +#define PINMUX_GPIO129__FUNC_SCL1 (MTK_PIN_NO(129) | 1) +#define PINMUX_GPIO129__FUNC_SCP_SCL0 (MTK_PIN_NO(129) | 4) +#define PINMUX_GPIO129__FUNC_SCP_SCL1 (MTK_PIN_NO(129) | 5) +#define PINMUX_GPIO129__FUNC_DBG_MON_B4 (MTK_PIN_NO(129) | 7) + +#define PINMUX_GPIO130__FUNC_GPIO130 (MTK_PIN_NO(130) | 0) +#define PINMUX_GPIO130__FUNC_SDA1 (MTK_PIN_NO(130) | 1) +#define PINMUX_GPIO130__FUNC_SCP_SDA0 (MTK_PIN_NO(130) | 4) +#define PINMUX_GPIO130__FUNC_SCP_SDA1 (MTK_PIN_NO(130) | 5) +#define PINMUX_GPIO130__FUNC_DBG_MON_B5 (MTK_PIN_NO(130) | 7) + +#define PINMUX_GPIO131__FUNC_GPIO131 (MTK_PIN_NO(131) | 0) +#define PINMUX_GPIO131__FUNC_SCL2 (MTK_PIN_NO(131) | 1) +#define PINMUX_GPIO131__FUNC_SSPM_UTXD_AO (MTK_PIN_NO(131) | 2) +#define PINMUX_GPIO131__FUNC_CONN_UART0_TXD (MTK_PIN_NO(131) | 3) +#define PINMUX_GPIO131__FUNC_SCP_SCL0 (MTK_PIN_NO(131) | 4) +#define PINMUX_GPIO131__FUNC_SCP_SCL1 (MTK_PIN_NO(131) | 5) +#define PINMUX_GPIO131__FUNC_DBG_MON_B6 (MTK_PIN_NO(131) | 7) + +#define PINMUX_GPIO132__FUNC_GPIO132 (MTK_PIN_NO(132) | 0) +#define PINMUX_GPIO132__FUNC_SDA2 (MTK_PIN_NO(132) | 1) +#define PINMUX_GPIO132__FUNC_SSPM_URXD_AO (MTK_PIN_NO(132) | 2) +#define PINMUX_GPIO132__FUNC_CONN_UART0_RXD (MTK_PIN_NO(132) | 3) +#define PINMUX_GPIO132__FUNC_SCP_SDA0 (MTK_PIN_NO(132) | 4) +#define PINMUX_GPIO132__FUNC_SCP_SDA1 (MTK_PIN_NO(132) | 5) +#define PINMUX_GPIO132__FUNC_DBG_MON_B7 (MTK_PIN_NO(132) | 7) + +#define PINMUX_GPIO133__FUNC_GPIO133 (MTK_PIN_NO(133) | 0) +#define PINMUX_GPIO133__FUNC_SCL3 (MTK_PIN_NO(133) | 1) +#define PINMUX_GPIO133__FUNC_SCP_SCL0 (MTK_PIN_NO(133) | 4) +#define PINMUX_GPIO133__FUNC_SCP_SCL1 (MTK_PIN_NO(133) | 5) +#define PINMUX_GPIO133__FUNC_DBG_MON_B8 (MTK_PIN_NO(133) | 7) + +#define PINMUX_GPIO134__FUNC_GPIO134 (MTK_PIN_NO(134) | 0) +#define PINMUX_GPIO134__FUNC_SDA3 (MTK_PIN_NO(134) | 1) +#define PINMUX_GPIO134__FUNC_GPS_PPS (MTK_PIN_NO(134) | 3) +#define PINMUX_GPIO134__FUNC_SCP_SDA0 (MTK_PIN_NO(134) | 4) +#define PINMUX_GPIO134__FUNC_SCP_SDA1 (MTK_PIN_NO(134) | 5) +#define PINMUX_GPIO134__FUNC_DBG_MON_B9 (MTK_PIN_NO(134) | 7) + +#define PINMUX_GPIO135__FUNC_GPIO135 (MTK_PIN_NO(135) | 0) +#define PINMUX_GPIO135__FUNC_SCL4 (MTK_PIN_NO(135) | 1) +#define PINMUX_GPIO135__FUNC_TP_UTXD1_AO (MTK_PIN_NO(135) | 2) +#define PINMUX_GPIO135__FUNC_UTXD1 (MTK_PIN_NO(135) | 3) +#define PINMUX_GPIO135__FUNC_SCP_SCL0 (MTK_PIN_NO(135) | 4) +#define PINMUX_GPIO135__FUNC_SCP_SCL1 (MTK_PIN_NO(135) | 5) +#define PINMUX_GPIO135__FUNC_DBG_MON_B10 (MTK_PIN_NO(135) | 7) + +#define PINMUX_GPIO136__FUNC_GPIO136 (MTK_PIN_NO(136) | 0) +#define PINMUX_GPIO136__FUNC_SDA4 (MTK_PIN_NO(136) | 1) +#define PINMUX_GPIO136__FUNC_TP_URXD1_AO (MTK_PIN_NO(136) | 2) +#define PINMUX_GPIO136__FUNC_URXD1 (MTK_PIN_NO(136) | 3) +#define PINMUX_GPIO136__FUNC_SCP_SDA0 (MTK_PIN_NO(136) | 4) +#define PINMUX_GPIO136__FUNC_SCP_SDA1 (MTK_PIN_NO(136) | 5) +#define PINMUX_GPIO136__FUNC_DBG_MON_B11 (MTK_PIN_NO(136) | 7) + +#define PINMUX_GPIO137__FUNC_GPIO137 (MTK_PIN_NO(137) | 0) +#define PINMUX_GPIO137__FUNC_SCL5 (MTK_PIN_NO(137) | 1) +#define PINMUX_GPIO137__FUNC_UTXD2 (MTK_PIN_NO(137) | 2) +#define PINMUX_GPIO137__FUNC_UCTS1 (MTK_PIN_NO(137) | 3) +#define PINMUX_GPIO137__FUNC_SCP_SCL0 (MTK_PIN_NO(137) | 4) +#define PINMUX_GPIO137__FUNC_SCP_SCL1 (MTK_PIN_NO(137) | 5) + +#define PINMUX_GPIO138__FUNC_GPIO138 (MTK_PIN_NO(138) | 0) +#define PINMUX_GPIO138__FUNC_SDA5 (MTK_PIN_NO(138) | 1) +#define PINMUX_GPIO138__FUNC_URXD2 (MTK_PIN_NO(138) | 2) +#define PINMUX_GPIO138__FUNC_URTS1 (MTK_PIN_NO(138) | 3) +#define PINMUX_GPIO138__FUNC_SCP_SDA0 (MTK_PIN_NO(138) | 4) +#define PINMUX_GPIO138__FUNC_SCP_SDA1 (MTK_PIN_NO(138) | 5) + +#define PINMUX_GPIO139__FUNC_GPIO139 (MTK_PIN_NO(139) | 0) +#define PINMUX_GPIO139__FUNC_SCL6 (MTK_PIN_NO(139) | 1) +#define PINMUX_GPIO139__FUNC_UTXD1 (MTK_PIN_NO(139) | 2) +#define PINMUX_GPIO139__FUNC_TP_UTXD1_AO (MTK_PIN_NO(139) | 3) +#define PINMUX_GPIO139__FUNC_SCP_SCL0 (MTK_PIN_NO(139) | 4) +#define PINMUX_GPIO139__FUNC_SCP_SCL1 (MTK_PIN_NO(139) | 5) +#define PINMUX_GPIO139__FUNC_DBG_MON_B12 (MTK_PIN_NO(139) | 7) + +#define PINMUX_GPIO140__FUNC_GPIO140 (MTK_PIN_NO(140) | 0) +#define PINMUX_GPIO140__FUNC_SDA6 (MTK_PIN_NO(140) | 1) +#define PINMUX_GPIO140__FUNC_URXD1 (MTK_PIN_NO(140) | 2) +#define PINMUX_GPIO140__FUNC_TP_URXD1_AO (MTK_PIN_NO(140) | 3) +#define PINMUX_GPIO140__FUNC_SCP_SDA0 (MTK_PIN_NO(140) | 4) +#define PINMUX_GPIO140__FUNC_SCP_SDA1 (MTK_PIN_NO(140) | 5) +#define PINMUX_GPIO140__FUNC_DBG_MON_B13 (MTK_PIN_NO(140) | 7) + +#define PINMUX_GPIO141__FUNC_GPIO141 (MTK_PIN_NO(141) | 0) +#define PINMUX_GPIO141__FUNC_SCL7 (MTK_PIN_NO(141) | 1) +#define PINMUX_GPIO141__FUNC_URTS0 (MTK_PIN_NO(141) | 2) +#define PINMUX_GPIO141__FUNC_TP_URTS1_AO (MTK_PIN_NO(141) | 3) +#define PINMUX_GPIO141__FUNC_SCP_SCL0 (MTK_PIN_NO(141) | 4) +#define PINMUX_GPIO141__FUNC_SCP_SCL1 (MTK_PIN_NO(141) | 5) +#define PINMUX_GPIO141__FUNC_UDI_TCK (MTK_PIN_NO(141) | 6) +#define PINMUX_GPIO141__FUNC_DBG_MON_B14 (MTK_PIN_NO(141) | 7) + +#define PINMUX_GPIO142__FUNC_GPIO142 (MTK_PIN_NO(142) | 0) +#define PINMUX_GPIO142__FUNC_SDA7 (MTK_PIN_NO(142) | 1) +#define PINMUX_GPIO142__FUNC_UCTS0 (MTK_PIN_NO(142) | 2) +#define PINMUX_GPIO142__FUNC_TP_UCTS1_AO (MTK_PIN_NO(142) | 3) +#define PINMUX_GPIO142__FUNC_SCP_SDA0 (MTK_PIN_NO(142) | 4) +#define PINMUX_GPIO142__FUNC_SCP_SDA1 (MTK_PIN_NO(142) | 5) + +#define PINMUX_GPIO143__FUNC_GPIO143 (MTK_PIN_NO(143) | 0) +#define PINMUX_GPIO143__FUNC_SCL8 (MTK_PIN_NO(143) | 1) +#define PINMUX_GPIO143__FUNC_SCP_SCL0 (MTK_PIN_NO(143) | 4) +#define PINMUX_GPIO143__FUNC_SCP_SCL1 (MTK_PIN_NO(143) | 5) +#define PINMUX_GPIO143__FUNC_DBG_MON_B16 (MTK_PIN_NO(143) | 7) + +#define PINMUX_GPIO144__FUNC_GPIO144 (MTK_PIN_NO(144) | 0) +#define PINMUX_GPIO144__FUNC_SDA8 (MTK_PIN_NO(144) | 1) +#define PINMUX_GPIO144__FUNC_SCP_SDA0 (MTK_PIN_NO(144) | 4) +#define PINMUX_GPIO144__FUNC_SCP_SDA1 (MTK_PIN_NO(144) | 5) +#define PINMUX_GPIO144__FUNC_DBG_MON_B17 (MTK_PIN_NO(144) | 7) + +#define PINMUX_GPIO145__FUNC_GPIO145 (MTK_PIN_NO(145) | 0) +#define PINMUX_GPIO145__FUNC_SCL9 (MTK_PIN_NO(145) | 1) +#define PINMUX_GPIO145__FUNC_CMVREF1 (MTK_PIN_NO(145) | 2) +#define PINMUX_GPIO145__FUNC_GPS_PPS (MTK_PIN_NO(145) | 3) +#define PINMUX_GPIO145__FUNC_SCP_SCL0 (MTK_PIN_NO(145) | 4) +#define PINMUX_GPIO145__FUNC_SCP_SCL1 (MTK_PIN_NO(145) | 5) +#define PINMUX_GPIO145__FUNC_DBG_MON_B18 (MTK_PIN_NO(145) | 7) + +#define PINMUX_GPIO146__FUNC_GPIO146 (MTK_PIN_NO(146) | 0) +#define PINMUX_GPIO146__FUNC_SDA9 (MTK_PIN_NO(146) | 1) +#define PINMUX_GPIO146__FUNC_CMVREF0 (MTK_PIN_NO(146) | 2) +#define PINMUX_GPIO146__FUNC_SCP_SDA0 (MTK_PIN_NO(146) | 4) +#define PINMUX_GPIO146__FUNC_SCP_SDA1 (MTK_PIN_NO(146) | 5) +#define PINMUX_GPIO146__FUNC_DBG_MON_B19 (MTK_PIN_NO(146) | 7) + +#define PINMUX_GPIO147__FUNC_GPIO147 (MTK_PIN_NO(147) | 0) +#define PINMUX_GPIO147__FUNC_CMFLASH0 (MTK_PIN_NO(147) | 1) +#define PINMUX_GPIO147__FUNC_LVTS_SDI (MTK_PIN_NO(147) | 2) +#define PINMUX_GPIO147__FUNC_DPI_DATA12 (MTK_PIN_NO(147) | 3) +#define PINMUX_GPIO147__FUNC_TP_GPIO0_AO (MTK_PIN_NO(147) | 4) +#define PINMUX_GPIO147__FUNC_ANT_SEL3 (MTK_PIN_NO(147) | 5) +#define PINMUX_GPIO147__FUNC_DFD_TCK_XI (MTK_PIN_NO(147) | 6) +#define PINMUX_GPIO147__FUNC_DBG_MON_B20 (MTK_PIN_NO(147) | 7) + +#define PINMUX_GPIO148__FUNC_GPIO148 (MTK_PIN_NO(148) | 0) +#define PINMUX_GPIO148__FUNC_CMFLASH1 (MTK_PIN_NO(148) | 1) +#define PINMUX_GPIO148__FUNC_LVTS_SCF (MTK_PIN_NO(148) | 2) +#define PINMUX_GPIO148__FUNC_DPI_DATA13 (MTK_PIN_NO(148) | 3) +#define PINMUX_GPIO148__FUNC_TP_GPIO1_AO (MTK_PIN_NO(148) | 4) +#define PINMUX_GPIO148__FUNC_ANT_SEL4 (MTK_PIN_NO(148) | 5) +#define PINMUX_GPIO148__FUNC_DFD_TMS (MTK_PIN_NO(148) | 6) +#define PINMUX_GPIO148__FUNC_DBG_MON_B21 (MTK_PIN_NO(148) | 7) + +#define PINMUX_GPIO149__FUNC_GPIO149 (MTK_PIN_NO(149) | 0) +#define PINMUX_GPIO149__FUNC_CMFLASH2 (MTK_PIN_NO(149) | 1) +#define PINMUX_GPIO149__FUNC_CLKM0 (MTK_PIN_NO(149) | 2) +#define PINMUX_GPIO149__FUNC_DPI_DATA14 (MTK_PIN_NO(149) | 3) +#define PINMUX_GPIO149__FUNC_TP_GPIO2_AO (MTK_PIN_NO(149) | 4) +#define PINMUX_GPIO149__FUNC_ANT_SEL5 (MTK_PIN_NO(149) | 5) +#define PINMUX_GPIO149__FUNC_DFD_TDI (MTK_PIN_NO(149) | 6) +#define PINMUX_GPIO149__FUNC_DBG_MON_B22 (MTK_PIN_NO(149) | 7) + +#define PINMUX_GPIO150__FUNC_GPIO150 (MTK_PIN_NO(150) | 0) +#define PINMUX_GPIO150__FUNC_CLKM1 (MTK_PIN_NO(150) | 2) +#define PINMUX_GPIO150__FUNC_DPI_DATA15 (MTK_PIN_NO(150) | 3) +#define PINMUX_GPIO150__FUNC_TP_GPIO3_AO (MTK_PIN_NO(150) | 4) +#define PINMUX_GPIO150__FUNC_ANT_SEL6 (MTK_PIN_NO(150) | 5) +#define PINMUX_GPIO150__FUNC_DFD_TDO (MTK_PIN_NO(150) | 6) +#define PINMUX_GPIO150__FUNC_DBG_MON_B23 (MTK_PIN_NO(150) | 7) + +#define PINMUX_GPIO151__FUNC_GPIO151 (MTK_PIN_NO(151) | 0) +#define PINMUX_GPIO151__FUNC_GPS_L1_ELNA_EN (MTK_PIN_NO(151) | 1) +#define PINMUX_GPIO151__FUNC_CLKM2 (MTK_PIN_NO(151) | 2) +#define PINMUX_GPIO151__FUNC_DPI_DATA16 (MTK_PIN_NO(151) | 3) +#define PINMUX_GPIO151__FUNC_TP_GPIO4_AO (MTK_PIN_NO(151) | 4) +#define PINMUX_GPIO151__FUNC_ANT_SEL7 (MTK_PIN_NO(151) | 5) +#define PINMUX_GPIO151__FUNC_UDI_TMS (MTK_PIN_NO(151) | 6) +#define PINMUX_GPIO151__FUNC_DBG_MON_B24 (MTK_PIN_NO(151) | 7) + +#define PINMUX_GPIO152__FUNC_GPIO152 (MTK_PIN_NO(152) | 0) +#define PINMUX_GPIO152__FUNC_CLKM3 (MTK_PIN_NO(152) | 2) +#define PINMUX_GPIO152__FUNC_DPI_DATA17 (MTK_PIN_NO(152) | 3) +#define PINMUX_GPIO152__FUNC_TP_GPIO5_AO (MTK_PIN_NO(152) | 4) + +#define PINMUX_GPIO153__FUNC_GPIO153 (MTK_PIN_NO(153) | 0) +#define PINMUX_GPIO153__FUNC_CONN_TCXOENA_REQ (MTK_PIN_NO(153) | 1) +#define PINMUX_GPIO153__FUNC_DPI_DATA18 (MTK_PIN_NO(153) | 3) +#define PINMUX_GPIO153__FUNC_TP_GPIO6_AO (MTK_PIN_NO(153) | 4) +#define PINMUX_GPIO153__FUNC_UDI_TDI (MTK_PIN_NO(153) | 6) +#define PINMUX_GPIO153__FUNC_DBG_MON_B26 (MTK_PIN_NO(153) | 7) + +#define PINMUX_GPIO154__FUNC_GPIO154 (MTK_PIN_NO(154) | 0) +#define PINMUX_GPIO154__FUNC_PWM0 (MTK_PIN_NO(154) | 1) +#define PINMUX_GPIO154__FUNC_CMVREF2 (MTK_PIN_NO(154) | 2) +#define PINMUX_GPIO154__FUNC_DPI_DATA19 (MTK_PIN_NO(154) | 3) +#define PINMUX_GPIO154__FUNC_TP_GPIO7_AO (MTK_PIN_NO(154) | 4) +#define PINMUX_GPIO154__FUNC_UDI_TDO (MTK_PIN_NO(154) | 6) +#define PINMUX_GPIO154__FUNC_DBG_MON_B27 (MTK_PIN_NO(154) | 7) + +#define PINMUX_GPIO155__FUNC_GPIO155 (MTK_PIN_NO(155) | 0) +#define PINMUX_GPIO155__FUNC_PWM1 (MTK_PIN_NO(155) | 1) +#define PINMUX_GPIO155__FUNC_CMVREF1 (MTK_PIN_NO(155) | 2) +#define PINMUX_GPIO155__FUNC_DPI_DATA20 (MTK_PIN_NO(155) | 3) +#define PINMUX_GPIO155__FUNC_UDI_NTRST (MTK_PIN_NO(155) | 6) +#define PINMUX_GPIO155__FUNC_DBG_MON_B28 (MTK_PIN_NO(155) | 7) + +#define PINMUX_GPIO156__FUNC_GPIO156 (MTK_PIN_NO(156) | 0) +#define PINMUX_GPIO156__FUNC_PWM2 (MTK_PIN_NO(156) | 1) +#define PINMUX_GPIO156__FUNC_CMVREF0 (MTK_PIN_NO(156) | 2) +#define PINMUX_GPIO156__FUNC_DPI_DATA21 (MTK_PIN_NO(156) | 3) + +#define PINMUX_GPIO157__FUNC_GPIO157 (MTK_PIN_NO(157) | 0) +#define PINMUX_GPIO157__FUNC_PWRAP_SPI0_CSN (MTK_PIN_NO(157) | 1) + +#define PINMUX_GPIO158__FUNC_GPIO158 (MTK_PIN_NO(158) | 0) +#define PINMUX_GPIO158__FUNC_PWRAP_SPI0_CK (MTK_PIN_NO(158) | 1) + +#define PINMUX_GPIO159__FUNC_GPIO159 (MTK_PIN_NO(159) | 0) +#define PINMUX_GPIO159__FUNC_PWRAP_SPI0_MO (MTK_PIN_NO(159) | 1) +#define PINMUX_GPIO159__FUNC_PWRAP_SPI0_MI (MTK_PIN_NO(159) | 2) + +#define PINMUX_GPIO160__FUNC_GPIO160 (MTK_PIN_NO(160) | 0) +#define PINMUX_GPIO160__FUNC_PWRAP_SPI0_MI (MTK_PIN_NO(160) | 1) +#define PINMUX_GPIO160__FUNC_PWRAP_SPI0_MO (MTK_PIN_NO(160) | 2) + +#define PINMUX_GPIO161__FUNC_GPIO161 (MTK_PIN_NO(161) | 0) +#define PINMUX_GPIO161__FUNC_SRCLKENA0 (MTK_PIN_NO(161) | 1) + +#define PINMUX_GPIO162__FUNC_GPIO162 (MTK_PIN_NO(162) | 0) +#define PINMUX_GPIO162__FUNC_SRCLKENA1 (MTK_PIN_NO(162) | 1) +#define PINMUX_GPIO162__FUNC_DBG_MON_A31 (MTK_PIN_NO(162) | 7) + +#define PINMUX_GPIO163__FUNC_GPIO163 (MTK_PIN_NO(163) | 0) +#define PINMUX_GPIO163__FUNC_SCP_VREQ_VAO (MTK_PIN_NO(163) | 1) +#define PINMUX_GPIO163__FUNC_DVFSRC_EXT_REQ (MTK_PIN_NO(163) | 2) + +#define PINMUX_GPIO164__FUNC_GPIO164 (MTK_PIN_NO(164) | 0) +#define PINMUX_GPIO164__FUNC_RTC32K_CK (MTK_PIN_NO(164) | 1) + +#define PINMUX_GPIO165__FUNC_GPIO165 (MTK_PIN_NO(165) | 0) +#define PINMUX_GPIO165__FUNC_WATCHDOG (MTK_PIN_NO(165) | 1) + +#define PINMUX_GPIO166__FUNC_GPIO166 (MTK_PIN_NO(166) | 0) +#define PINMUX_GPIO166__FUNC_AUD_CLK_MOSI (MTK_PIN_NO(166) | 1) +#define PINMUX_GPIO166__FUNC_AUD_CLK_MISO (MTK_PIN_NO(166) | 2) +#define PINMUX_GPIO166__FUNC_I2S1_MCK (MTK_PIN_NO(166) | 3) + +#define PINMUX_GPIO167__FUNC_GPIO167 (MTK_PIN_NO(167) | 0) +#define PINMUX_GPIO167__FUNC_AUD_SYNC_MOSI (MTK_PIN_NO(167) | 1) +#define PINMUX_GPIO167__FUNC_AUD_SYNC_MISO (MTK_PIN_NO(167) | 2) +#define PINMUX_GPIO167__FUNC_I2S1_BCK (MTK_PIN_NO(167) | 3) + +#define PINMUX_GPIO168__FUNC_GPIO168 (MTK_PIN_NO(168) | 0) +#define PINMUX_GPIO168__FUNC_AUD_DAT_MOSI0 (MTK_PIN_NO(168) | 1) +#define PINMUX_GPIO168__FUNC_AUD_DAT_MISO0 (MTK_PIN_NO(168) | 2) +#define PINMUX_GPIO168__FUNC_I2S1_LRCK (MTK_PIN_NO(168) | 3) + +#define PINMUX_GPIO169__FUNC_GPIO169 (MTK_PIN_NO(169) | 0) +#define PINMUX_GPIO169__FUNC_AUD_DAT_MOSI1 (MTK_PIN_NO(169) | 1) +#define PINMUX_GPIO169__FUNC_AUD_DAT_MISO1 (MTK_PIN_NO(169) | 2) +#define PINMUX_GPIO169__FUNC_I2S1_DO (MTK_PIN_NO(169) | 3) + +#define PINMUX_GPIO170__FUNC_GPIO170 (MTK_PIN_NO(170) | 0) +#define PINMUX_GPIO170__FUNC_AUD_CLK_MISO (MTK_PIN_NO(170) | 1) +#define PINMUX_GPIO170__FUNC_AUD_CLK_MOSI (MTK_PIN_NO(170) | 2) +#define PINMUX_GPIO170__FUNC_I2S2_MCK (MTK_PIN_NO(170) | 3) + +#define PINMUX_GPIO171__FUNC_GPIO171 (MTK_PIN_NO(171) | 0) +#define PINMUX_GPIO171__FUNC_AUD_SYNC_MISO (MTK_PIN_NO(171) | 1) +#define PINMUX_GPIO171__FUNC_AUD_SYNC_MOSI (MTK_PIN_NO(171) | 2) +#define PINMUX_GPIO171__FUNC_I2S2_BCK (MTK_PIN_NO(171) | 3) + +#define PINMUX_GPIO172__FUNC_GPIO172 (MTK_PIN_NO(172) | 0) +#define PINMUX_GPIO172__FUNC_AUD_DAT_MISO0 (MTK_PIN_NO(172) | 1) +#define PINMUX_GPIO172__FUNC_AUD_DAT_MOSI0 (MTK_PIN_NO(172) | 2) +#define PINMUX_GPIO172__FUNC_I2S2_LRCK (MTK_PIN_NO(172) | 3) +#define PINMUX_GPIO172__FUNC_VOW_DAT_MISO (MTK_PIN_NO(172) | 4) + +#define PINMUX_GPIO173__FUNC_GPIO173 (MTK_PIN_NO(173) | 0) +#define PINMUX_GPIO173__FUNC_AUD_DAT_MISO1 (MTK_PIN_NO(173) | 1) +#define PINMUX_GPIO173__FUNC_AUD_DAT_MOSI1 (MTK_PIN_NO(173) | 2) +#define PINMUX_GPIO173__FUNC_I2S2_DI (MTK_PIN_NO(173) | 3) +#define PINMUX_GPIO173__FUNC_VOW_CLK_MISO (MTK_PIN_NO(173) | 4) + +#define PINMUX_GPIO174__FUNC_GPIO174 (MTK_PIN_NO(174) | 0) +#define PINMUX_GPIO174__FUNC_CONN_TOP_CLK (MTK_PIN_NO(174) | 1) +#define PINMUX_GPIO174__FUNC_AUXIF_CLK (MTK_PIN_NO(174) | 2) +#define PINMUX_GPIO174__FUNC_DFD_TCK_XI (MTK_PIN_NO(174) | 3) +#define PINMUX_GPIO174__FUNC_DBG_MON_B3 (MTK_PIN_NO(174) | 7) + +#define PINMUX_GPIO175__FUNC_GPIO175 (MTK_PIN_NO(175) | 0) +#define PINMUX_GPIO175__FUNC_CONN_TOP_DATA (MTK_PIN_NO(175) | 1) +#define PINMUX_GPIO175__FUNC_AUXIF_ST (MTK_PIN_NO(175) | 2) +#define PINMUX_GPIO175__FUNC_DFD_TMS (MTK_PIN_NO(175) | 3) +#define PINMUX_GPIO175__FUNC_DBG_MON_B15 (MTK_PIN_NO(175) | 7) + +#define PINMUX_GPIO176__FUNC_GPIO176 (MTK_PIN_NO(176) | 0) +#define PINMUX_GPIO176__FUNC_CONN_BT_CLK (MTK_PIN_NO(176) | 1) +#define PINMUX_GPIO176__FUNC_DFD_TDI (MTK_PIN_NO(176) | 3) +#define PINMUX_GPIO176__FUNC_DBG_MON_B2 (MTK_PIN_NO(176) | 7) + +#define PINMUX_GPIO177__FUNC_GPIO177 (MTK_PIN_NO(177) | 0) +#define PINMUX_GPIO177__FUNC_CONN_BT_DATA (MTK_PIN_NO(177) | 1) +#define PINMUX_GPIO177__FUNC_DFD_TDO (MTK_PIN_NO(177) | 3) + +#define PINMUX_GPIO178__FUNC_GPIO178 (MTK_PIN_NO(178) | 0) +#define PINMUX_GPIO178__FUNC_CONN_HRST_B (MTK_PIN_NO(178) | 1) +#define PINMUX_GPIO178__FUNC_UDI_TMS (MTK_PIN_NO(178) | 3) +#define PINMUX_GPIO178__FUNC_DBG_MON_B25 (MTK_PIN_NO(178) | 7) + +#define PINMUX_GPIO179__FUNC_GPIO179 (MTK_PIN_NO(179) | 0) +#define PINMUX_GPIO179__FUNC_CONN_WB_PTA (MTK_PIN_NO(179) | 1) +#define PINMUX_GPIO179__FUNC_UDI_TCK (MTK_PIN_NO(179) | 3) +#define PINMUX_GPIO179__FUNC_DBG_MON_B29 (MTK_PIN_NO(179) | 7) + +#define PINMUX_GPIO180__FUNC_GPIO180 (MTK_PIN_NO(180) | 0) +#define PINMUX_GPIO180__FUNC_CONN_WF_CTRL0 (MTK_PIN_NO(180) | 1) +#define PINMUX_GPIO180__FUNC_UDI_TDI (MTK_PIN_NO(180) | 3) + +#define PINMUX_GPIO181__FUNC_GPIO181 (MTK_PIN_NO(181) | 0) +#define PINMUX_GPIO181__FUNC_CONN_WF_CTRL1 (MTK_PIN_NO(181) | 1) +#define PINMUX_GPIO181__FUNC_UDI_TDO (MTK_PIN_NO(181) | 3) + +#define PINMUX_GPIO182__FUNC_GPIO182 (MTK_PIN_NO(182) | 0) +#define PINMUX_GPIO182__FUNC_CONN_WF_CTRL2 (MTK_PIN_NO(182) | 1) +#define PINMUX_GPIO182__FUNC_UDI_NTRST (MTK_PIN_NO(182) | 3) + +#define PINMUX_GPIO183__FUNC_GPIO183 (MTK_PIN_NO(183) | 0) +#define PINMUX_GPIO183__FUNC_SPMI_SCL (MTK_PIN_NO(183) | 1) + +#define PINMUX_GPIO184__FUNC_GPIO184 (MTK_PIN_NO(184) | 0) +#define PINMUX_GPIO184__FUNC_SPMI_SDA (MTK_PIN_NO(184) | 1) + +#endif /* __MT8186_PINFUNC_H */ -- cgit v1.2.3 From 5c9bf3635b66add7d829b4d8d538ae0d770d9d89 Mon Sep 17 00:00:00 2001 From: John Garry Date: Fri, 11 Mar 2022 20:23:49 +0800 Subject: scsi: libsas: Add sas_execute_internal_abort_single() The internal abort feature is common to hisi_sas and pm8001 HBAs, and the driver support is similar also, so add a common handler. Two modes of operation will be supported: - single: Abort a single tagged command - device: Abort all commands associated with a specific domain device A new protocol is added, SAS_PROTOCOL_INTERNAL_ABORT, so the common queue command API may be re-used. Only add "single" support as a first step. Link: https://lore.kernel.org/r/1647001432-239276-2-git-send-email-john.garry@huawei.com Tested-by: Damien Le Moal Acked-by: Jack Wang Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 14 ++++++++++++++ include/scsi/sas.h | 2 ++ 2 files changed, 16 insertions(+) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index df2c8fc43429..2d30d57916e5 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -557,6 +557,16 @@ struct sas_ata_task { int force_phy_id; }; +/* LLDDs rely on these values */ +enum sas_internal_abort { + SAS_INTERNAL_ABORT_SINGLE = 0, +}; + +struct sas_internal_abort_task { + enum sas_internal_abort type; + u16 tag; +}; + struct sas_smp_task { struct scatterlist smp_req; struct scatterlist smp_resp; @@ -596,6 +606,7 @@ struct sas_task { struct sas_ata_task ata_task; struct sas_smp_task smp_task; struct sas_ssp_task ssp_task; + struct sas_internal_abort_task abort_task; }; struct scatterlist *scatter; @@ -683,6 +694,9 @@ extern int sas_slave_configure(struct scsi_device *); extern int sas_change_queue_depth(struct scsi_device *, int new_depth); extern int sas_bios_param(struct scsi_device *, struct block_device *, sector_t capacity, int *hsc); +int sas_execute_internal_abort_single(struct domain_device *device, + u16 tag, unsigned int qid, + void *data); extern struct scsi_transport_template * sas_domain_attach_transport(struct sas_domain_function_template *); extern struct device_attribute dev_attr_phy_event_threshold; diff --git a/include/scsi/sas.h b/include/scsi/sas.h index 332a463d08ef..acfc69fd72d0 100644 --- a/include/scsi/sas.h +++ b/include/scsi/sas.h @@ -95,6 +95,8 @@ enum sas_protocol { SAS_PROTOCOL_SSP = 0x08, SAS_PROTOCOL_ALL = 0x0E, SAS_PROTOCOL_STP_ALL = SAS_PROTOCOL_STP|SAS_PROTOCOL_SATA, + /* these are internal to libsas */ + SAS_PROTOCOL_INTERNAL_ABORT = 0x10, }; /* From the spec; local phys only */ -- cgit v1.2.3 From 6a91c3e31578979a93b500efc76af4d3499f75ad Mon Sep 17 00:00:00 2001 From: John Garry Date: Fri, 11 Mar 2022 20:23:50 +0800 Subject: scsi: libsas: Add sas_execute_internal_abort_dev() Add support for a "device" variant of internal abort, which will abort all pending I/Os for a specific device. Link: https://lore.kernel.org/r/1647001432-239276-3-git-send-email-john.garry@huawei.com Tested-by: Damien Le Moal Acked-by: Jack Wang Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 2d30d57916e5..71f632b2d2bd 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -560,6 +560,7 @@ struct sas_ata_task { /* LLDDs rely on these values */ enum sas_internal_abort { SAS_INTERNAL_ABORT_SINGLE = 0, + SAS_INTERNAL_ABORT_DEV = 1, }; struct sas_internal_abort_task { @@ -641,6 +642,11 @@ extern struct sas_task *sas_alloc_task(gfp_t flags); extern struct sas_task *sas_alloc_slow_task(gfp_t flags); extern void sas_free_task(struct sas_task *task); +static inline bool sas_is_internal_abort(struct sas_task *task) +{ + return task->task_proto == SAS_PROTOCOL_INTERNAL_ABORT; +} + struct sas_domain_function_template { /* The class calls these to notify the LLDD of an event. */ void (*lldd_port_formed)(struct asd_sas_phy *); @@ -697,6 +703,8 @@ extern int sas_bios_param(struct scsi_device *, struct block_device *, int sas_execute_internal_abort_single(struct domain_device *device, u16 tag, unsigned int qid, void *data); +int sas_execute_internal_abort_dev(struct domain_device *device, + unsigned int qid, void *data); extern struct scsi_transport_template * sas_domain_attach_transport(struct sas_domain_function_template *); extern struct device_attribute dev_attr_phy_event_threshold; -- cgit v1.2.3 From 095478a6e5bf590f2bbf341569eb25173c9c5f32 Mon Sep 17 00:00:00 2001 From: John Garry Date: Fri, 11 Mar 2022 20:23:52 +0800 Subject: scsi: hisi_sas: Use libsas internal abort support Use the common libsas internal abort functionality. In addition, this driver has special handling for internal abort timeouts - specifically whether to reset the controller in that instance, so extend the API for that. Timeout is now increased to 20 * Hz from 6 * Hz. We also retry for failure now, but this should not make a difference. Link: https://lore.kernel.org/r/1647001432-239276-5-git-send-email-john.garry@huawei.com Tested-by: Damien Le Moal Acked-by: Jack Wang Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/libsas.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 71f632b2d2bd..ff04eb6d250b 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -565,6 +565,7 @@ enum sas_internal_abort { struct sas_internal_abort_task { enum sas_internal_abort type; + unsigned int qid; u16 tag; }; @@ -671,6 +672,7 @@ struct sas_domain_function_template { /* Special TMF callbacks */ void (*lldd_tmf_exec_complete)(struct domain_device *dev); void (*lldd_tmf_aborted)(struct sas_task *task); + bool (*lldd_abort_timeout)(struct sas_task *task, void *data); /* Port and Adapter management */ int (*lldd_clear_nexus_port)(struct asd_sas_port *); -- cgit v1.2.3 From d72d827f2f2636d8d72f0f3ebe5b661c9a24d343 Mon Sep 17 00:00:00 2001 From: Mingzhe Zou Date: Tue, 1 Mar 2022 15:55:00 +0800 Subject: scsi: target: Add iscsi/cpus_allowed_list in configfs The RX/TX threads for iSCSI connection can be scheduled to any online CPUs, and will not be rescheduled. When binding other heavy load threads along with iSCSI connection RX/TX thread to the same CPU, the iSCSI performance will be worse. Add iscsi/cpus_allowed_list in configfs. The available CPU set of iSCSI connection RX/TX threads is allowed_cpus & online_cpus. If it is modified, all RX/TX threads will be rescheduled. Link: https://lore.kernel.org/r/20220301075500.14266-1-mingzhe.zou@easystack.cn Reviewed-by: Mike Christie Signed-off-by: Mingzhe Zou Signed-off-by: Martin K. Petersen --- include/target/iscsi/iscsi_target_core.h | 31 ++++++------------------------- 1 file changed, 6 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index 1eccb2ac7d02..adc87de0362b 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -580,6 +580,7 @@ struct iscsi_conn { struct ahash_request *conn_tx_hash; /* Used for scheduling TX and RX connection kthreads */ cpumask_var_t conn_cpumask; + cpumask_var_t allowed_cpumask; unsigned int conn_rx_reset_cpumask:1; unsigned int conn_tx_reset_cpumask:1; /* list_head of struct iscsi_cmd for this connection */ @@ -878,6 +879,7 @@ struct iscsit_global { /* Thread Set bitmap pointer */ unsigned long *ts_bitmap; spinlock_t ts_bitmap_lock; + cpumask_var_t allowed_cpumask; /* Used for iSCSI discovery session authentication */ struct iscsi_node_acl discovery_acl; struct iscsi_portal_group *discovery_tpg; @@ -898,29 +900,8 @@ static inline u32 session_get_next_ttt(struct iscsi_session *session) extern struct iscsi_cmd *iscsit_find_cmd_from_itt(struct iscsi_conn *, itt_t); -static inline void iscsit_thread_check_cpumask( - struct iscsi_conn *conn, - struct task_struct *p, - int mode) -{ - /* - * mode == 1 signals iscsi_target_tx_thread() usage. - * mode == 0 signals iscsi_target_rx_thread() usage. - */ - if (mode == 1) { - if (!conn->conn_tx_reset_cpumask) - return; - conn->conn_tx_reset_cpumask = 0; - } else { - if (!conn->conn_rx_reset_cpumask) - return; - conn->conn_rx_reset_cpumask = 0; - } - /* - * Update the CPU mask for this single kthread so that - * both TX and RX kthreads are scheduled to run on the - * same CPU. - */ - set_cpus_allowed_ptr(p, conn->conn_cpumask); -} +extern void iscsit_thread_check_cpumask(struct iscsi_conn *conn, + struct task_struct *p, + int mode); + #endif /* ISCSI_TARGET_CORE_H */ -- cgit v1.2.3 From ad515cada7dac3cdf5e1ad77a0ed696f5f34e0ab Mon Sep 17 00:00:00 2001 From: Wenchao Hao Date: Wed, 9 Mar 2022 20:57:57 -0500 Subject: scsi: iscsi: Add helper functions to manage iscsi_cls_conn - iscsi_alloc_conn(): Allocate and initialize iscsi_cls_conn - iscsi_add_conn(): Expose iscsi_cls_conn to userspace via sysfs - iscsi_remove_conn(): Remove iscsi_cls_conn from sysfs Link: https://lore.kernel.org/r/20220310015759.3296841-2-haowenchao@huawei.com Reviewed-by: Mike Christie Signed-off-by: Wenchao Hao Signed-off-by: Wu Bo Signed-off-by: Martin K. Petersen --- include/scsi/scsi_transport_iscsi.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h index 7a0d24d3b916..ad341835e847 100644 --- a/include/scsi/scsi_transport_iscsi.h +++ b/include/scsi/scsi_transport_iscsi.h @@ -442,6 +442,10 @@ extern struct iscsi_cls_session *iscsi_create_session(struct Scsi_Host *shost, unsigned int target_id); extern void iscsi_remove_session(struct iscsi_cls_session *session); extern void iscsi_free_session(struct iscsi_cls_session *session); +extern struct iscsi_cls_conn *iscsi_alloc_conn(struct iscsi_cls_session *sess, + int dd_size, uint32_t cid); +extern int iscsi_add_conn(struct iscsi_cls_conn *conn); +extern void iscsi_remove_conn(struct iscsi_cls_conn *conn); extern struct iscsi_cls_conn *iscsi_create_conn(struct iscsi_cls_session *sess, int dd_size, uint32_t cid); extern void iscsi_put_conn(struct iscsi_cls_conn *conn); -- cgit v1.2.3 From 7dae459f5e56a89ab01413ae055595c982713349 Mon Sep 17 00:00:00 2001 From: Wenchao Hao Date: Wed, 9 Mar 2022 20:57:58 -0500 Subject: scsi: libiscsi: Add iscsi_cls_conn to sysfs after initialization iscsi_create_conn() exposed iscsi_cls_conn to sysfs prior to initialization of iscsi_conn's dd_data. When userspace tried to access an attribute such as the connect address, a NULL pointer dereference was observed. Do not add iscsi_cls_conn to sysfs until it has been initialized. Remove iscsi_create_conn() since it is no longer used. Link: https://lore.kernel.org/r/20220310015759.3296841-3-haowenchao@huawei.com Reviewed-by: Mike Christie Signed-off-by: Wenchao Hao Signed-off-by: Wu Bo Signed-off-by: Martin K. Petersen --- include/scsi/scsi_transport_iscsi.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h index ad341835e847..97e947962b52 100644 --- a/include/scsi/scsi_transport_iscsi.h +++ b/include/scsi/scsi_transport_iscsi.h @@ -446,8 +446,6 @@ extern struct iscsi_cls_conn *iscsi_alloc_conn(struct iscsi_cls_session *sess, int dd_size, uint32_t cid); extern int iscsi_add_conn(struct iscsi_cls_conn *conn); extern void iscsi_remove_conn(struct iscsi_cls_conn *conn); -extern struct iscsi_cls_conn *iscsi_create_conn(struct iscsi_cls_session *sess, - int dd_size, uint32_t cid); extern void iscsi_put_conn(struct iscsi_cls_conn *conn); extern void iscsi_get_conn(struct iscsi_cls_conn *conn); extern int iscsi_destroy_conn(struct iscsi_cls_conn *conn); -- cgit v1.2.3 From 8709c323091be019f76a49cf783052a5636aca85 Mon Sep 17 00:00:00 2001 From: Wenchao Hao Date: Wed, 9 Mar 2022 20:57:59 -0500 Subject: scsi: libiscsi: Teardown iscsi_cls_conn gracefully Commit 1b8d0300a3e9 ("scsi: libiscsi: Fix UAF in iscsi_conn_get_param()/iscsi_conn_teardown()") fixed an UAF in iscsi_conn_get_param() and introduced 2 tmp_xxx varibles. We can gracefully fix this UAF with the help of device_del(). Calling iscsi_remove_conn() at the beginning of iscsi_conn_teardown would make userspace unable to see iscsi_cls_conn. This way we we can free memory safely. Remove iscsi_destroy_conn() since it is no longer used. Link: https://lore.kernel.org/r/20220310015759.3296841-4-haowenchao@huawei.com Reviewed-by: Mike Christie Signed-off-by: Wenchao Hao Signed-off-by: Wu Bo Signed-off-by: Martin K. Petersen --- include/scsi/scsi_transport_iscsi.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h index 97e947962b52..38e4a67f5922 100644 --- a/include/scsi/scsi_transport_iscsi.h +++ b/include/scsi/scsi_transport_iscsi.h @@ -448,7 +448,6 @@ extern int iscsi_add_conn(struct iscsi_cls_conn *conn); extern void iscsi_remove_conn(struct iscsi_cls_conn *conn); extern void iscsi_put_conn(struct iscsi_cls_conn *conn); extern void iscsi_get_conn(struct iscsi_cls_conn *conn); -extern int iscsi_destroy_conn(struct iscsi_cls_conn *conn); extern void iscsi_unblock_session(struct iscsi_cls_session *session); extern void iscsi_block_session(struct iscsi_cls_session *session); extern struct iscsi_endpoint *iscsi_create_endpoint(int dd_size); -- cgit v1.2.3 From b44544fe0298ee2224960a31f795e317029e2a60 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 8 Mar 2022 16:30:12 +0100 Subject: static_call: Avoid building empty .static_call_sites Without CONFIG_HAVE_STATIC_CALL_INLINE there's no point in creating the .static_call_sites section and it's related symbols. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Josh Poimboeuf Link: https://lore.kernel.org/r/20220308154317.223798256@infradead.org --- include/asm-generic/vmlinux.lds.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 42f3866bca69..a41e62355160 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -404,6 +404,7 @@ KEEP(*(__jump_table)) \ __stop___jump_table = .; +#ifdef CONFIG_HAVE_STATIC_CALL_INLINE #define STATIC_CALL_DATA \ . = ALIGN(8); \ __start_static_call_sites = .; \ @@ -412,6 +413,9 @@ __start_static_call_tramp_key = .; \ KEEP(*(.static_call_tramp_key)) \ __stop_static_call_tramp_key = .; +#else +#define STATIC_CALL_DATA +#endif /* * Allow architectures to handle ro_after_init data on their -- cgit v1.2.3 From c8c301abeae58ec756b8fcb2178a632bd3c9e284 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 8 Mar 2022 16:30:18 +0100 Subject: x86/ibt: Add ANNOTATE_NOENDBR In order to have objtool warn about code references to !ENDBR instruction, we need an annotation to allow this for non-control-flow instances -- consider text range checks, text patching, or return trampolines etc. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Kees Cook Acked-by: Josh Poimboeuf Link: https://lore.kernel.org/r/20220308154317.578968224@infradead.org --- include/linux/objtool.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/objtool.h b/include/linux/objtool.h index aca52db2f3f3..f797368820c8 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -77,6 +77,12 @@ struct unwind_hint { #define STACK_FRAME_NON_STANDARD_FP(func) #endif +#define ANNOTATE_NOENDBR \ + "986: \n\t" \ + ".pushsection .discard.noendbr\n\t" \ + _ASM_PTR " 986b\n\t" \ + ".popsection\n\t" + #else /* __ASSEMBLY__ */ /* @@ -129,6 +135,13 @@ struct unwind_hint { .popsection .endm +.macro ANNOTATE_NOENDBR +.Lhere_\@: + .pushsection .discard.noendbr + .quad .Lhere_\@ + .popsection +.endm + #endif /* __ASSEMBLY__ */ #else /* !CONFIG_STACK_VALIDATION */ @@ -139,12 +152,15 @@ struct unwind_hint { "\n\t" #define STACK_FRAME_NON_STANDARD(func) #define STACK_FRAME_NON_STANDARD_FP(func) +#define ANNOTATE_NOENDBR #else #define ANNOTATE_INTRA_FUNCTION_CALL .macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 .endm .macro STACK_FRAME_NON_STANDARD func:req .endm +.macro ANNOTATE_NOENDBR +.endm #endif #endif /* CONFIG_STACK_VALIDATION */ -- cgit v1.2.3 From cc66bb91457827f62e2b6cb2518666820f0a6c48 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 8 Mar 2022 16:30:32 +0100 Subject: x86/ibt,kprobes: Cure sym+0 equals fentry woes In order to allow kprobes to skip the ENDBR instructions at sym+0 for X86_KERNEL_IBT builds, change _kprobe_addr() to take an architecture callback to inspect the function at hand and modify the offset if needed. This streamlines the existing interface to cover more cases and require less hooks. Once PowerPC gets fully converted there will only be the one arch hook. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Masami Hiramatsu Acked-by: Josh Poimboeuf Link: https://lore.kernel.org/r/20220308154318.405947704@infradead.org --- include/linux/kprobes.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 19b884353b15..9c28f7a0ef42 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -265,7 +265,6 @@ extern int arch_init_kprobes(void); extern void kprobes_inc_nmissed_count(struct kprobe *p); extern bool arch_within_kprobe_blacklist(unsigned long addr); extern int arch_populate_kprobe_blacklist(void); -extern bool arch_kprobe_on_func_entry(unsigned long offset); extern int kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset); extern bool within_kprobe_blacklist(unsigned long addr); @@ -384,6 +383,8 @@ static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void) } kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset); +kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offset, bool *on_func_entry); + int register_kprobe(struct kprobe *p); void unregister_kprobe(struct kprobe *p); int register_kprobes(struct kprobe **kps, int num); -- cgit v1.2.3 From cb9010f87dcbcdbb51cc96b922c6260848cecbd1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 8 Mar 2022 16:30:44 +0100 Subject: x86/ibt: Ensure module init/exit points have references Since the references to the module init/exit points only have external references, a module LTO run will consider them 'unused' and seal them, leading to an immediate fail on module load. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Josh Poimboeuf Link: https://lore.kernel.org/r/20220308154319.113767246@infradead.org --- include/linux/cfi.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/cfi.h b/include/linux/cfi.h index 879744aaa6e0..c6dfc1ed0626 100644 --- a/include/linux/cfi.h +++ b/include/linux/cfi.h @@ -34,8 +34,17 @@ static inline void cfi_module_remove(struct module *mod, unsigned long base_addr #else /* !CONFIG_CFI_CLANG */ -#define __CFI_ADDRESSABLE(fn, __attr) +#ifdef CONFIG_X86_KERNEL_IBT + +#define __CFI_ADDRESSABLE(fn, __attr) \ + const void *__cfi_jt_ ## fn __visible __attr = (void *)&fn + +#endif /* CONFIG_X86_KERNEL_IBT */ #endif /* CONFIG_CFI_CLANG */ +#ifndef __CFI_ADDRESSABLE +#define __CFI_ADDRESSABLE(fn, __attr) +#endif + #endif /* _LINUX_CFI_H */ -- cgit v1.2.3 From eae654f1c21216daa9fbb92591c0d9f5ae46cfc5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 8 Mar 2022 16:30:48 +0100 Subject: exit: Mark do_group_exit() __noreturn vmlinux.o: warning: objtool: get_signal()+0x108: unreachable instruction 0000 000000000007f930 : ... 0103 7fa33: e8 00 00 00 00 call 7fa38 7fa34: R_X86_64_PLT32 do_group_exit-0x4 0108 7fa38: 41 8b 45 74 mov 0x74(%r13),%eax Signed-off-by: Peter Zijlstra (Intel) Acked-by: Josh Poimboeuf Link: https://lore.kernel.org/r/20220308154319.351270711@infradead.org --- include/linux/sched/task.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index e84e54d1b490..719c9a6cac8d 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -79,7 +79,7 @@ static inline void exit_thread(struct task_struct *tsk) { } #endif -extern void do_group_exit(int); +extern __noreturn void do_group_exit(int); extern void exit_files(struct task_struct *); extern void exit_itimers(struct signal_struct *); -- cgit v1.2.3 From 105cd68596392cfe15056a891b0723609dcad247 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 14 Mar 2022 17:58:35 +0100 Subject: x86: Mark __invalid_creds() __noreturn vmlinux.o: warning: objtool: ksys_unshare()+0x36c: unreachable instruction 0000 0000000000067040 : ... 0364 673a4: 4c 89 ef mov %r13,%rdi 0367 673a7: e8 00 00 00 00 call 673ac 673a8: R_X86_64_PLT32 __invalid_creds-0x4 036c 673ac: e9 28 ff ff ff jmp 672d9 0371 673b1: 41 bc f4 ff ff ff mov $0xfffffff4,%r12d 0377 673b7: e9 80 fd ff ff jmp 6713c Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/Yi9gOW9f1GGwwUD6@hirez.programming.kicks-ass.net --- include/linux/cred.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/cred.h b/include/linux/cred.h index fcbc6885cc09..9ed9232af934 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -176,7 +176,7 @@ extern int set_cred_ucounts(struct cred *); * check for validity of credentials */ #ifdef CONFIG_DEBUG_CREDENTIALS -extern void __invalid_creds(const struct cred *, const char *, unsigned); +extern void __noreturn __invalid_creds(const struct cred *, const char *, unsigned); extern void __validate_process_creds(struct task_struct *, const char *, unsigned); -- cgit v1.2.3 From dca5da2abe406168b85f97e22109710ebe0bda08 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 14 Mar 2022 18:05:52 +0100 Subject: x86,objtool: Move the ASM_REACHABLE annotation to objtool.h Because we need a variant for .S files too. Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/Yi9gOW9f1GGwwUD6@hirez.programming.kicks-ass.net --- include/linux/compiler.h | 7 ------- include/linux/objtool.h | 16 ++++++++++++++++ 2 files changed, 16 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 0f7fd205ab7e..219aa5ddbc73 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -125,18 +125,11 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, }) #define annotate_unreachable() __annotate_unreachable(__COUNTER__) -#define ASM_REACHABLE \ - "998:\n\t" \ - ".pushsection .discard.reachable\n\t" \ - ".long 998b - .\n\t" \ - ".popsection\n\t" - /* Annotate a C jump table to allow objtool to follow the code flow */ #define __annotate_jump_table __section(".rodata..c_jump_table") #else #define annotate_unreachable() -# define ASM_REACHABLE #define __annotate_jump_table #endif diff --git a/include/linux/objtool.h b/include/linux/objtool.h index f797368820c8..586d35720f13 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -83,6 +83,12 @@ struct unwind_hint { _ASM_PTR " 986b\n\t" \ ".popsection\n\t" +#define ASM_REACHABLE \ + "998:\n\t" \ + ".pushsection .discard.reachable\n\t" \ + ".long 998b - .\n\t" \ + ".popsection\n\t" + #else /* __ASSEMBLY__ */ /* @@ -142,6 +148,13 @@ struct unwind_hint { .popsection .endm +.macro REACHABLE +.Lhere_\@: + .pushsection .discard.reachable + .long .Lhere_\@ - . + .popsection +.endm + #endif /* __ASSEMBLY__ */ #else /* !CONFIG_STACK_VALIDATION */ @@ -153,6 +166,7 @@ struct unwind_hint { #define STACK_FRAME_NON_STANDARD(func) #define STACK_FRAME_NON_STANDARD_FP(func) #define ANNOTATE_NOENDBR +#define ASM_REACHABLE #else #define ANNOTATE_INTRA_FUNCTION_CALL .macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 @@ -161,6 +175,8 @@ struct unwind_hint { .endm .macro ANNOTATE_NOENDBR .endm +.macro REACHABLE +.endm #endif #endif /* CONFIG_STACK_VALIDATION */ -- cgit v1.2.3 From 2b3171c6fe0af24b5506e061525e08917a2f744a Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Thu, 24 Feb 2022 12:54:58 +0100 Subject: mac80211: MBSSID beacon handling in AP mode Add new fields in struct beacon_data to store all MBSSID elements. Generate a beacon template which includes all MBSSID elements. Move CSA offset to reflect the MBSSID element length. Co-developed-by: Aloka Dixit Signed-off-by: Aloka Dixit Co-developed-by: John Crispin Signed-off-by: John Crispin Signed-off-by: Lorenzo Bianconi Tested-by: Money Wang Link: https://lore.kernel.org/r/5322db3c303f431adaf191ab31c45e151dde5465.1645702516.git.lorenzo@kernel.org [small cleanups] Signed-off-by: Johannes Berg --- include/net/mac80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index b8e8c82b53aa..382ebb862ea8 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -4948,12 +4948,14 @@ void ieee80211_report_low_ack(struct ieee80211_sta *sta, u32 num_packets); * @cntdwn_counter_offs: array of IEEE80211_MAX_CNTDWN_COUNTERS_NUM offsets * to countdown counters. This array can contain zero values which * should be ignored. + * @mbssid_off: position of the multiple bssid element */ struct ieee80211_mutable_offsets { u16 tim_offset; u16 tim_length; u16 cntdwn_counter_offs[IEEE80211_MAX_CNTDWN_COUNTERS_NUM]; + u16 mbssid_off; }; /** -- cgit v1.2.3 From 5ad6b2bdaaea712486145fa5a78ec24d25289071 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 9 Feb 2022 20:21:28 +0000 Subject: fs: Turn do_invalidatepage() into folio_invalidate() Take a folio instead of a page, fix the types of the offset & length, and export it to filesystems. Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Damien Le Moal Acked-by: Damien Le Moal Tested-by: Mike Marshall # orangefs Tested-by: David Howells # afs --- include/linux/mm.h | 3 --- include/linux/pagemap.h | 1 + 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 213cc569b192..7808a7959066 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1939,9 +1939,6 @@ int get_kernel_pages(const struct kvec *iov, int nr_pages, int write, struct page **pages); struct page *get_dump_page(unsigned long addr); -extern void do_invalidatepage(struct page *page, unsigned int offset, - unsigned int length); - bool folio_mark_dirty(struct folio *folio); bool set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 55a80d8f0e9c..4503d5baa252 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -893,6 +893,7 @@ static inline void cancel_dirty_page(struct page *page) } bool folio_clear_dirty_for_io(struct folio *folio); bool clear_page_dirty_for_io(struct page *page); +void folio_invalidate(struct folio *folio, size_t offset, size_t length); int __must_check folio_write_one(struct folio *folio); static inline int __must_check write_one_page(struct page *page) { -- cgit v1.2.3 From 128d1f8241d62ab014eef6dd4ef9bb977dbeadb2 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 9 Feb 2022 20:21:32 +0000 Subject: fs: Add invalidate_folio() aops method This is used in preference to invalidatepage, if defined. Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Damien Le Moal Acked-by: Damien Le Moal Tested-by: Mike Marshall # orangefs Tested-by: David Howells # afs --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 5939e6694ada..bcdb613cd652 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -387,6 +387,7 @@ struct address_space_operations { /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); + void (*invalidate_folio) (struct folio *, size_t offset, size_t len); void (*invalidatepage) (struct page *, unsigned int, unsigned int); int (*releasepage) (struct page *, gfp_t); void (*freepage)(struct page *); -- cgit v1.2.3 From d82354f6b05fc3b35029b3f75ddbf41b82af3bc8 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 9 Feb 2022 20:21:33 +0000 Subject: iomap: Remove iomap_invalidatepage() Use iomap_invalidate_folio() in all the iomap-based filesystems and rename the iomap_invalidatepage tracepoint. Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Damien Le Moal Acked-by: Damien Le Moal Tested-by: Mike Marshall # orangefs Tested-by: David Howells # afs --- include/linux/iomap.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 3bcbb264f83f..b76f0dd149fb 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -230,8 +230,6 @@ void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops); bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count); int iomap_releasepage(struct page *page, gfp_t gfp_mask); void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len); -void iomap_invalidatepage(struct page *page, unsigned int offset, - unsigned int len); #ifdef CONFIG_MIGRATION int iomap_migrate_page(struct address_space *mapping, struct page *newpage, struct page *page, enum migrate_mode mode); -- cgit v1.2.3 From 7ba13abbd31ee9265e88d7dc029c0f786e665192 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 9 Feb 2022 20:21:34 +0000 Subject: fs: Turn block_invalidatepage into block_invalidate_folio Remove special-casing of a NULL invalidatepage, since there is no more block_invalidatepage. Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Damien Le Moal Acked-by: Damien Le Moal Tested-by: Mike Marshall # orangefs Tested-by: David Howells # afs --- include/linux/buffer_head.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 79d465057889..9ee9d003d736 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -217,8 +217,7 @@ extern int buffer_heads_over_limit; * Generic address_space_operations implementations for buffer_head-backed * address_spaces. */ -void block_invalidatepage(struct page *page, unsigned int offset, - unsigned int length); +void block_invalidate_folio(struct folio *folio, size_t offset, size_t length); int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc); int __block_write_full_page(struct inode *inode, struct page *page, -- cgit v1.2.3 From 5660a8630dab61a28e07ec00c42bf605b182d725 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 9 Feb 2022 20:21:35 +0000 Subject: fs: Remove noop_invalidatepage() We used to have to use noop_invalidatepage() to prevent block_invalidatepage() from being called, but that behaviour is now gone. Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Damien Le Moal Acked-by: Damien Le Moal Tested-by: Mike Marshall # orangefs Tested-by: David Howells # afs --- include/linux/fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index bcdb613cd652..a40ea82248da 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3323,8 +3323,6 @@ extern int simple_rename(struct user_namespace *, struct inode *, extern void simple_recursive_removal(struct dentry *, void (*callback)(struct dentry *)); extern int noop_fsync(struct file *, loff_t, loff_t, int); -extern void noop_invalidatepage(struct page *page, unsigned int offset, - unsigned int length); extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); extern int simple_write_begin(struct file *file, struct address_space *mapping, -- cgit v1.2.3 From ccd16945dba091fdf1036d7711b9f6cbd287ae28 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 9 Feb 2022 20:21:43 +0000 Subject: ext4: Convert invalidatepage to invalidate_folio Extensive changes, but fairly mechanical. Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Damien Le Moal Acked-by: Damien Le Moal Tested-by: Mike Marshall # orangefs Tested-by: David Howells # afs --- include/linux/jbd2.h | 4 ++-- include/linux/pagemap.h | 18 ++++++++++++++++++ include/trace/events/ext4.h | 30 +++++++++++++++--------------- 3 files changed, 35 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 9c3ada74ffb1..1b9d1e205a2f 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1530,8 +1530,8 @@ void jbd2_journal_set_triggers(struct buffer_head *, struct jbd2_buffer_trigger_type *type); extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); -extern int jbd2_journal_invalidatepage(journal_t *, - struct page *, unsigned int, unsigned int); +int jbd2_journal_invalidate_folio(journal_t *, struct folio *, + size_t offset, size_t length); extern int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page); extern int jbd2_journal_stop(handle_t *); extern int jbd2_journal_flush(journal_t *journal, unsigned int flags); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 4503d5baa252..6a9617e9c6bc 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -422,6 +422,24 @@ static inline struct folio *filemap_get_folio(struct address_space *mapping, return __filemap_get_folio(mapping, index, 0, 0); } +/** + * filemap_lock_folio - Find and lock a folio. + * @mapping: The address_space to search. + * @index: The page index. + * + * Looks up the page cache entry at @mapping & @index. If a folio is + * present, it is returned locked with an increased refcount. + * + * Context: May sleep. + * Return: A folio or %NULL if there is no folio in the cache for this + * index. Will not return a shadow, swap or DAX entry. + */ +static inline struct folio *filemap_lock_folio(struct address_space *mapping, + pgoff_t index) +{ + return __filemap_get_folio(mapping, index, FGP_LOCK, 0); +} + /** * find_get_page - find and get a page reference * @mapping: the address_space to search diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 19e957b7f941..40cca0e5a811 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -597,44 +597,44 @@ DEFINE_EVENT(ext4__page_op, ext4_releasepage, TP_ARGS(page) ); -DECLARE_EVENT_CLASS(ext4_invalidatepage_op, - TP_PROTO(struct page *page, unsigned int offset, unsigned int length), +DECLARE_EVENT_CLASS(ext4_invalidate_folio_op, + TP_PROTO(struct folio *folio, size_t offset, size_t length), - TP_ARGS(page, offset, length), + TP_ARGS(folio, offset, length), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( pgoff_t, index ) - __field( unsigned int, offset ) - __field( unsigned int, length ) + __field( size_t, offset ) + __field( size_t, length ) ), TP_fast_assign( - __entry->dev = page->mapping->host->i_sb->s_dev; - __entry->ino = page->mapping->host->i_ino; - __entry->index = page->index; + __entry->dev = folio->mapping->host->i_sb->s_dev; + __entry->ino = folio->mapping->host->i_ino; + __entry->index = folio->index; __entry->offset = offset; __entry->length = length; ), - TP_printk("dev %d,%d ino %lu page_index %lu offset %u length %u", + TP_printk("dev %d,%d ino %lu folio_index %lu offset %zu length %zu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned long) __entry->index, __entry->offset, __entry->length) ); -DEFINE_EVENT(ext4_invalidatepage_op, ext4_invalidatepage, - TP_PROTO(struct page *page, unsigned int offset, unsigned int length), +DEFINE_EVENT(ext4_invalidate_folio_op, ext4_invalidate_folio, + TP_PROTO(struct folio *folio, size_t offset, size_t length), - TP_ARGS(page, offset, length) + TP_ARGS(folio, offset, length) ); -DEFINE_EVENT(ext4_invalidatepage_op, ext4_journalled_invalidatepage, - TP_PROTO(struct page *page, unsigned int offset, unsigned int length), +DEFINE_EVENT(ext4_invalidate_folio_op, ext4_journalled_invalidate_folio, + TP_PROTO(struct folio *folio, size_t offset, size_t length), - TP_ARGS(page, offset, length) + TP_ARGS(folio, offset, length) ); TRACE_EVENT(ext4_discard_blocks, -- cgit v1.2.3 From 6d740c76ea86053208b20c41fb5ec1de07acb996 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 9 Feb 2022 20:21:47 +0000 Subject: nfs: Convert from invalidatepage to invalidate_folio Print the folio index instead of the pointer, since this is more useful. We also don't need to use page_file_mapping() as we do not invalidate swapcache pages. Since this is the only caller of nfs_wb_page_cancel(), convert it to nfs_wb_folio_cancel(). Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Damien Le Moal Acked-by: Damien Le Moal Tested-by: Mike Marshall # orangefs Tested-by: David Howells # afs --- include/linux/nfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 68f81d8d36de..784120cc217e 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -583,7 +583,7 @@ extern int nfs_updatepage(struct file *, struct page *, unsigned int, unsigned extern int nfs_sync_inode(struct inode *inode); extern int nfs_wb_all(struct inode *inode); extern int nfs_wb_page(struct inode *inode, struct page *page); -extern int nfs_wb_page_cancel(struct inode *inode, struct page* page); +int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail); extern void nfs_commit_free(struct nfs_commit_data *data); -- cgit v1.2.3 From f50015a596fa106bf642bd85fbf6e6b52cc913d0 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 9 Feb 2022 20:21:51 +0000 Subject: fs: Remove aops->invalidatepage With all users migrated to ->invalidate_folio, remove the old operation. Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Damien Le Moal Acked-by: Damien Le Moal Tested-by: Mike Marshall # orangefs Tested-by: David Howells # afs --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index a40ea82248da..af9ae091bd82 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -388,7 +388,6 @@ struct address_space_operations { /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); void (*invalidate_folio) (struct folio *, size_t offset, size_t len); - void (*invalidatepage) (struct page *, unsigned int, unsigned int); int (*releasepage) (struct page *, gfp_t); void (*freepage)(struct page *); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); -- cgit v1.2.3 From affa80e8c6a1df473694c2087259901872309cc4 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 9 Feb 2022 20:21:52 +0000 Subject: fs: Add aops->launder_folio Since the only difference between ->launder_page and ->launder_folio is the type of the pointer, these can safely use a union without affecting bisectability. Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Damien Le Moal Acked-by: Damien Le Moal Tested-by: Mike Marshall # orangefs Tested-by: David Howells # afs --- include/linux/fs.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index af9ae091bd82..0af3075cdff2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -399,7 +399,10 @@ struct address_space_operations { struct page *, struct page *, enum migrate_mode); bool (*isolate_page)(struct page *, isolate_mode_t); void (*putback_page)(struct page *); - int (*launder_page) (struct page *); + union { + int (*launder_page) (struct page *); + int (*launder_folio) (struct folio *); + }; bool (*is_partially_uptodate) (struct folio *, size_t from, size_t count); void (*is_dirty_writeback) (struct page *, bool *, bool *); -- cgit v1.2.3 From 072acba6d08730beba5bad293c7ce6d0c4b0624c Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 9 Feb 2022 20:21:59 +0000 Subject: fs: Remove aops->launder_page With all users converted to ->launder_folio, remove ->launder_page. Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Damien Le Moal Acked-by: Damien Le Moal Tested-by: Mike Marshall # orangefs Tested-by: David Howells # afs --- include/linux/fs.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 0af3075cdff2..055be40084f1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -399,10 +399,7 @@ struct address_space_operations { struct page *, struct page *, enum migrate_mode); bool (*isolate_page)(struct page *, isolate_mode_t); void (*putback_page)(struct page *); - union { - int (*launder_page) (struct page *); - int (*launder_folio) (struct folio *); - }; + int (*launder_folio)(struct folio *); bool (*is_partially_uptodate) (struct folio *, size_t from, size_t count); void (*is_dirty_writeback) (struct page *, bool *, bool *); -- cgit v1.2.3 From 6f31a5a261dbbe7bf7f585dfe81f8acd4b25ec3b Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 9 Feb 2022 20:22:00 +0000 Subject: fs: Add aops->dirty_folio This replaces ->set_page_dirty(). It returns a bool instead of an int and takes the address_space as a parameter instead of expecting the implementations to retrieve the address_space from the page. This is particularly important for filesystems which use FS_OPS for swap. Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Damien Le Moal Acked-by: Damien Le Moal Tested-by: Mike Marshall # orangefs Tested-by: David Howells # afs --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 055be40084f1..c3d5db8851ae 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -369,6 +369,7 @@ struct address_space_operations { /* Set a page dirty. Return true if this dirtied it */ int (*set_page_dirty)(struct page *page); + bool (*dirty_folio)(struct address_space *, struct folio *); /* * Reads in the requested pages. Unlike ->readpage(), this is -- cgit v1.2.3 From 8fb72b4a76933ae6f86725cc8e4a8190ba84d755 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 9 Feb 2022 20:22:01 +0000 Subject: fscache: Convert fscache_set_page_dirty() to fscache_dirty_folio() Convert all users of fscache_set_page_dirty to use fscache_dirty_folio. Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Damien Le Moal Acked-by: Damien Le Moal Tested-by: Mike Marshall # orangefs Tested-by: David Howells # afs --- include/linux/fscache.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 296c5f1d9f35..d44ff747a657 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -616,9 +616,11 @@ static inline void fscache_write_to_cache(struct fscache_cookie *cookie, } #if __fscache_available -extern int fscache_set_page_dirty(struct page *page, struct fscache_cookie *cookie); +bool fscache_dirty_folio(struct address_space *mapping, struct folio *folio, + struct fscache_cookie *cookie); #else -#define fscache_set_page_dirty(PAGE, COOKIE) (__set_page_dirty_nobuffers((PAGE))) +#define fscache_dirty_folio(MAPPING, FOLIO, COOKIE) \ + filemap_dirty_folio(MAPPING, FOLIO) #endif /** @@ -626,7 +628,7 @@ extern int fscache_set_page_dirty(struct page *page, struct fscache_cookie *cook * @wbc: The writeback control * @cookie: The cookie referring to the cache object * - * Unpin the writeback resources pinned by fscache_set_page_dirty(). This is + * Unpin the writeback resources pinned by fscache_dirty_folio(). This is * intended to be called by the netfs's ->write_inode() method. */ static inline void fscache_unpin_writeback(struct writeback_control *wbc, -- cgit v1.2.3 From 7e63df00cf5e609ebbee5ffbc3df1900d8a4443c Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 9 Feb 2022 20:22:10 +0000 Subject: mm: Convert swap_set_page_dirty() to swap_dirty_folio() Straightforward conversion. Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Damien Le Moal Acked-by: Damien Le Moal Tested-by: Mike Marshall # orangefs Tested-by: David Howells # afs --- include/linux/swap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 1d38d9475c4d..65a37e555124 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -427,7 +427,7 @@ extern int swap_writepage(struct page *page, struct writeback_control *wbc); extern void end_swap_bio_write(struct bio *bio); extern int __swap_writepage(struct page *page, struct writeback_control *wbc, bio_end_io_t end_write_func); -extern int swap_set_page_dirty(struct page *page); +bool swap_dirty_folio(struct address_space *mapping, struct folio *folio); int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block); -- cgit v1.2.3 From 938d3480b92fa5e454b7734294f12a7b75126f09 Mon Sep 17 00:00:00 2001 From: Wang Yufen Date: Fri, 4 Mar 2022 16:11:42 +0800 Subject: bpf, sockmap: Fix memleak in sk_psock_queue_msg If tcp_bpf_sendmsg is running during a tear down operation we may enqueue data on the ingress msg queue while tear down is trying to free it. sk1 (redirect sk2) sk2 ------------------- --------------- tcp_bpf_sendmsg() tcp_bpf_send_verdict() tcp_bpf_sendmsg_redir() bpf_tcp_ingress() sock_map_close() lock_sock() lock_sock() ... blocking sk_psock_stop sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); release_sock(sk); lock_sock() sk_mem_charge() get_page() sk_psock_queue_msg() sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED); drop_sk_msg() release_sock() While drop_sk_msg(), the msg has charged memory form sk by sk_mem_charge and has sg pages need to put. To fix we use sk_msg_free() and then kfee() msg. This issue can cause the following info: WARNING: CPU: 0 PID: 9202 at net/core/stream.c:205 sk_stream_kill_queues+0xc8/0xe0 Call Trace: inet_csk_destroy_sock+0x55/0x110 tcp_rcv_state_process+0xe5f/0xe90 ? sk_filter_trim_cap+0x10d/0x230 ? tcp_v4_do_rcv+0x161/0x250 tcp_v4_do_rcv+0x161/0x250 tcp_v4_rcv+0xc3a/0xce0 ip_protocol_deliver_rcu+0x3d/0x230 ip_local_deliver_finish+0x54/0x60 ip_local_deliver+0xfd/0x110 ? ip_protocol_deliver_rcu+0x230/0x230 ip_rcv+0xd6/0x100 ? ip_local_deliver+0x110/0x110 __netif_receive_skb_one_core+0x85/0xa0 process_backlog+0xa4/0x160 __napi_poll+0x29/0x1b0 net_rx_action+0x287/0x300 __do_softirq+0xff/0x2fc do_softirq+0x79/0x90 WARNING: CPU: 0 PID: 531 at net/ipv4/af_inet.c:154 inet_sock_destruct+0x175/0x1b0 Call Trace: __sk_destruct+0x24/0x1f0 sk_psock_destroy+0x19b/0x1c0 process_one_work+0x1b3/0x3c0 ? process_one_work+0x3c0/0x3c0 worker_thread+0x30/0x350 ? process_one_work+0x3c0/0x3c0 kthread+0xe6/0x110 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x22/0x30 Fixes: 9635720b7c88 ("bpf, sockmap: Fix memleak on ingress msg enqueue") Signed-off-by: Wang Yufen Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20220304081145.2037182-2-wangyufen@huawei.com --- include/linux/skmsg.h | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index fdb5375f0562..c5a2d6f50f25 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -304,21 +304,16 @@ static inline void sock_drop(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); } -static inline void drop_sk_msg(struct sk_psock *psock, struct sk_msg *msg) -{ - if (msg->skb) - sock_drop(psock->sk, msg->skb); - kfree(msg); -} - static inline void sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { spin_lock_bh(&psock->ingress_lock); if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) list_add_tail(&msg->list, &psock->ingress_msg); - else - drop_sk_msg(psock, msg); + else { + sk_msg_free(psock->sk, msg); + kfree(msg); + } spin_unlock_bh(&psock->ingress_lock); } -- cgit v1.2.3 From 23a9dbbe0faf124fc4c139615633b9d12a3a89ef Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 15 Mar 2022 18:34:06 +0300 Subject: NFSD: prevent integer overflow on 32 bit systems On a 32 bit system, the "len * sizeof(*p)" operation can have an integer overflow. Cc: stable@vger.kernel.org Signed-off-by: Dan Carpenter Signed-off-by: Chuck Lever --- include/linux/sunrpc/xdr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index b519609af1d0..4417f667c757 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -731,6 +731,8 @@ xdr_stream_decode_uint32_array(struct xdr_stream *xdr, if (unlikely(xdr_stream_decode_u32(xdr, &len) < 0)) return -EBADMSG; + if (len > SIZE_MAX / sizeof(*p)) + return -EBADMSG; p = xdr_inline_decode(xdr, len * sizeof(*p)); if (unlikely(!p)) return -EBADMSG; -- cgit v1.2.3 From b0ae33a2d2fb6c55117b377ec4ae3f2c84eab6a2 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 4 Mar 2022 16:19:55 +0100 Subject: usb: early: xhci-dbc: Remove duplicate keep parsing The generic earlyprintk= parsing already parses the optional ",keep", no need to duplicate that in the xdbc driver. Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220304152135.975568860@infradead.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/xhci-dbgp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/usb/xhci-dbgp.h b/include/linux/usb/xhci-dbgp.h index 0a37f1283bf0..01fe768873f9 100644 --- a/include/linux/usb/xhci-dbgp.h +++ b/include/linux/usb/xhci-dbgp.h @@ -15,7 +15,7 @@ #define __LINUX_XHCI_DBGP_H #ifdef CONFIG_EARLY_PRINTK_USB_XDBC -int __init early_xdbc_parse_parameter(char *s); +int __init early_xdbc_parse_parameter(char *s, int keep_early); int __init early_xdbc_setup_hardware(void); void __init early_xdbc_register_console(void); #else -- cgit v1.2.3 From ff5812e00d5e7bdeae68784d99686eff67896931 Mon Sep 17 00:00:00 2001 From: Shameer Kolothum Date: Tue, 8 Mar 2022 18:48:54 +0000 Subject: crypto: hisilicon/qm: Move the QM header to include/linux Since we are going to introduce VFIO PCI HiSilicon ACC driver for live migration in subsequent patches, move the ACC QM header file to a common include dir. Acked-by: Zhou Wang Acked-by: Longfang Liu Acked-by: Kai Ye Signed-off-by: Shameer Kolothum Link: https://lore.kernel.org/r/20220308184902.2242-2-shameerali.kolothum.thodi@huawei.com Signed-off-by: Alex Williamson --- include/linux/hisi_acc_qm.h | 441 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 441 insertions(+) create mode 100644 include/linux/hisi_acc_qm.h (limited to 'include') diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h new file mode 100644 index 000000000000..3068093229a5 --- /dev/null +++ b/include/linux/hisi_acc_qm.h @@ -0,0 +1,441 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019 HiSilicon Limited. */ +#ifndef HISI_ACC_QM_H +#define HISI_ACC_QM_H + +#include +#include +#include +#include +#include + +#define QM_QNUM_V1 4096 +#define QM_QNUM_V2 1024 +#define QM_MAX_VFS_NUM_V2 63 + +/* qm user domain */ +#define QM_ARUSER_M_CFG_1 0x100088 +#define AXUSER_SNOOP_ENABLE BIT(30) +#define AXUSER_CMD_TYPE GENMASK(14, 12) +#define AXUSER_CMD_SMMU_NORMAL 1 +#define AXUSER_NS BIT(6) +#define AXUSER_NO BIT(5) +#define AXUSER_FP BIT(4) +#define AXUSER_SSV BIT(0) +#define AXUSER_BASE (AXUSER_SNOOP_ENABLE | \ + FIELD_PREP(AXUSER_CMD_TYPE, \ + AXUSER_CMD_SMMU_NORMAL) | \ + AXUSER_NS | AXUSER_NO | AXUSER_FP) +#define QM_ARUSER_M_CFG_ENABLE 0x100090 +#define ARUSER_M_CFG_ENABLE 0xfffffffe +#define QM_AWUSER_M_CFG_1 0x100098 +#define QM_AWUSER_M_CFG_ENABLE 0x1000a0 +#define AWUSER_M_CFG_ENABLE 0xfffffffe +#define QM_WUSER_M_CFG_ENABLE 0x1000a8 +#define WUSER_M_CFG_ENABLE 0xffffffff + +/* qm cache */ +#define QM_CACHE_CTL 0x100050 +#define SQC_CACHE_ENABLE BIT(0) +#define CQC_CACHE_ENABLE BIT(1) +#define SQC_CACHE_WB_ENABLE BIT(4) +#define SQC_CACHE_WB_THRD GENMASK(10, 5) +#define CQC_CACHE_WB_ENABLE BIT(11) +#define CQC_CACHE_WB_THRD GENMASK(17, 12) +#define QM_AXI_M_CFG 0x1000ac +#define AXI_M_CFG 0xffff +#define QM_AXI_M_CFG_ENABLE 0x1000b0 +#define AM_CFG_SINGLE_PORT_MAX_TRANS 0x300014 +#define AXI_M_CFG_ENABLE 0xffffffff +#define QM_PEH_AXUSER_CFG 0x1000cc +#define QM_PEH_AXUSER_CFG_ENABLE 0x1000d0 +#define PEH_AXUSER_CFG 0x401001 +#define PEH_AXUSER_CFG_ENABLE 0xffffffff + +#define QM_AXI_RRESP BIT(0) +#define QM_AXI_BRESP BIT(1) +#define QM_ECC_MBIT BIT(2) +#define QM_ECC_1BIT BIT(3) +#define QM_ACC_GET_TASK_TIMEOUT BIT(4) +#define QM_ACC_DO_TASK_TIMEOUT BIT(5) +#define QM_ACC_WB_NOT_READY_TIMEOUT BIT(6) +#define QM_SQ_CQ_VF_INVALID BIT(7) +#define QM_CQ_VF_INVALID BIT(8) +#define QM_SQ_VF_INVALID BIT(9) +#define QM_DB_TIMEOUT BIT(10) +#define QM_OF_FIFO_OF BIT(11) +#define QM_DB_RANDOM_INVALID BIT(12) +#define QM_MAILBOX_TIMEOUT BIT(13) +#define QM_FLR_TIMEOUT BIT(14) + +#define QM_BASE_NFE (QM_AXI_RRESP | QM_AXI_BRESP | QM_ECC_MBIT | \ + QM_ACC_GET_TASK_TIMEOUT | QM_DB_TIMEOUT | \ + QM_OF_FIFO_OF | QM_DB_RANDOM_INVALID | \ + QM_MAILBOX_TIMEOUT | QM_FLR_TIMEOUT) +#define QM_BASE_CE QM_ECC_1BIT + +#define QM_Q_DEPTH 1024 +#define QM_MIN_QNUM 2 +#define HISI_ACC_SGL_SGE_NR_MAX 255 +#define QM_SHAPER_CFG 0x100164 +#define QM_SHAPER_ENABLE BIT(30) +#define QM_SHAPER_TYPE1_OFFSET 10 + +/* page number for queue file region */ +#define QM_DOORBELL_PAGE_NR 1 + +/* uacce mode of the driver */ +#define UACCE_MODE_NOUACCE 0 /* don't use uacce */ +#define UACCE_MODE_SVA 1 /* use uacce sva mode */ +#define UACCE_MODE_DESC "0(default) means only register to crypto, 1 means both register to crypto and uacce" + +enum qm_stop_reason { + QM_NORMAL, + QM_SOFT_RESET, + QM_FLR, +}; + +enum qm_state { + QM_INIT = 0, + QM_START, + QM_CLOSE, + QM_STOP, +}; + +enum qp_state { + QP_INIT = 1, + QP_START, + QP_STOP, + QP_CLOSE, +}; + +enum qm_hw_ver { + QM_HW_UNKNOWN = -1, + QM_HW_V1 = 0x20, + QM_HW_V2 = 0x21, + QM_HW_V3 = 0x30, +}; + +enum qm_fun_type { + QM_HW_PF, + QM_HW_VF, +}; + +enum qm_debug_file { + CURRENT_QM, + CURRENT_Q, + CLEAR_ENABLE, + DEBUG_FILE_NUM, +}; + +struct qm_dfx { + atomic64_t err_irq_cnt; + atomic64_t aeq_irq_cnt; + atomic64_t abnormal_irq_cnt; + atomic64_t create_qp_err_cnt; + atomic64_t mb_err_cnt; +}; + +struct debugfs_file { + enum qm_debug_file index; + struct mutex lock; + struct qm_debug *debug; +}; + +struct qm_debug { + u32 curr_qm_qp_num; + u32 sqe_mask_offset; + u32 sqe_mask_len; + struct qm_dfx dfx; + struct dentry *debug_root; + struct dentry *qm_d; + struct debugfs_file files[DEBUG_FILE_NUM]; +}; + +struct qm_shaper_factor { + u32 func_qos; + u64 cir_b; + u64 cir_u; + u64 cir_s; + u64 cbs_s; +}; + +struct qm_dma { + void *va; + dma_addr_t dma; + size_t size; +}; + +struct hisi_qm_status { + u32 eq_head; + bool eqc_phase; + u32 aeq_head; + bool aeqc_phase; + atomic_t flags; + int stop_reason; +}; + +struct hisi_qm; + +struct hisi_qm_err_info { + char *acpi_rst; + u32 msi_wr_port; + u32 ecc_2bits_mask; + u32 dev_ce_mask; + u32 ce; + u32 nfe; + u32 fe; +}; + +struct hisi_qm_err_status { + u32 is_qm_ecc_mbit; + u32 is_dev_ecc_mbit; +}; + +struct hisi_qm_err_ini { + int (*hw_init)(struct hisi_qm *qm); + void (*hw_err_enable)(struct hisi_qm *qm); + void (*hw_err_disable)(struct hisi_qm *qm); + u32 (*get_dev_hw_err_status)(struct hisi_qm *qm); + void (*clear_dev_hw_err_status)(struct hisi_qm *qm, u32 err_sts); + void (*open_axi_master_ooo)(struct hisi_qm *qm); + void (*close_axi_master_ooo)(struct hisi_qm *qm); + void (*open_sva_prefetch)(struct hisi_qm *qm); + void (*close_sva_prefetch)(struct hisi_qm *qm); + void (*log_dev_hw_err)(struct hisi_qm *qm, u32 err_sts); + void (*err_info_init)(struct hisi_qm *qm); +}; + +struct hisi_qm_list { + struct mutex lock; + struct list_head list; + int (*register_to_crypto)(struct hisi_qm *qm); + void (*unregister_from_crypto)(struct hisi_qm *qm); +}; + +struct hisi_qm { + enum qm_hw_ver ver; + enum qm_fun_type fun_type; + const char *dev_name; + struct pci_dev *pdev; + void __iomem *io_base; + void __iomem *db_io_base; + u32 sqe_size; + u32 qp_base; + u32 qp_num; + u32 qp_in_used; + u32 ctrl_qp_num; + u32 max_qp_num; + u32 vfs_num; + u32 db_interval; + struct list_head list; + struct hisi_qm_list *qm_list; + + struct qm_dma qdma; + struct qm_sqc *sqc; + struct qm_cqc *cqc; + struct qm_eqe *eqe; + struct qm_aeqe *aeqe; + dma_addr_t sqc_dma; + dma_addr_t cqc_dma; + dma_addr_t eqe_dma; + dma_addr_t aeqe_dma; + + struct hisi_qm_status status; + const struct hisi_qm_err_ini *err_ini; + struct hisi_qm_err_info err_info; + struct hisi_qm_err_status err_status; + unsigned long misc_ctl; /* driver removing and reset sched */ + + struct rw_semaphore qps_lock; + struct idr qp_idr; + struct hisi_qp *qp_array; + + struct mutex mailbox_lock; + + const struct hisi_qm_hw_ops *ops; + + struct qm_debug debug; + + u32 error_mask; + + struct workqueue_struct *wq; + struct work_struct work; + struct work_struct rst_work; + struct work_struct cmd_process; + + const char *algs; + bool use_sva; + bool is_frozen; + + /* doorbell isolation enable */ + bool use_db_isolation; + resource_size_t phys_base; + resource_size_t db_phys_base; + struct uacce_device *uacce; + int mode; + struct qm_shaper_factor *factor; + u32 mb_qos; + u32 type_rate; +}; + +struct hisi_qp_status { + atomic_t used; + u16 sq_tail; + u16 cq_head; + bool cqc_phase; + atomic_t flags; +}; + +struct hisi_qp_ops { + int (*fill_sqe)(void *sqe, void *q_parm, void *d_parm); +}; + +struct hisi_qp { + u32 qp_id; + u8 alg_type; + u8 req_type; + + struct qm_dma qdma; + void *sqe; + struct qm_cqe *cqe; + dma_addr_t sqe_dma; + dma_addr_t cqe_dma; + + struct hisi_qp_status qp_status; + struct hisi_qp_ops *hw_ops; + void *qp_ctx; + void (*req_cb)(struct hisi_qp *qp, void *data); + void (*event_cb)(struct hisi_qp *qp); + + struct hisi_qm *qm; + bool is_resetting; + bool is_in_kernel; + u16 pasid; + struct uacce_queue *uacce_q; +}; + +static inline int q_num_set(const char *val, const struct kernel_param *kp, + unsigned int device) +{ + struct pci_dev *pdev = pci_get_device(PCI_VENDOR_ID_HUAWEI, + device, NULL); + u32 n, q_num; + int ret; + + if (!val) + return -EINVAL; + + if (!pdev) { + q_num = min_t(u32, QM_QNUM_V1, QM_QNUM_V2); + pr_info("No device found currently, suppose queue number is %u\n", + q_num); + } else { + if (pdev->revision == QM_HW_V1) + q_num = QM_QNUM_V1; + else + q_num = QM_QNUM_V2; + } + + ret = kstrtou32(val, 10, &n); + if (ret || n < QM_MIN_QNUM || n > q_num) + return -EINVAL; + + return param_set_int(val, kp); +} + +static inline int vfs_num_set(const char *val, const struct kernel_param *kp) +{ + u32 n; + int ret; + + if (!val) + return -EINVAL; + + ret = kstrtou32(val, 10, &n); + if (ret < 0) + return ret; + + if (n > QM_MAX_VFS_NUM_V2) + return -EINVAL; + + return param_set_int(val, kp); +} + +static inline int mode_set(const char *val, const struct kernel_param *kp) +{ + u32 n; + int ret; + + if (!val) + return -EINVAL; + + ret = kstrtou32(val, 10, &n); + if (ret != 0 || (n != UACCE_MODE_SVA && + n != UACCE_MODE_NOUACCE)) + return -EINVAL; + + return param_set_int(val, kp); +} + +static inline int uacce_mode_set(const char *val, const struct kernel_param *kp) +{ + return mode_set(val, kp); +} + +static inline void hisi_qm_init_list(struct hisi_qm_list *qm_list) +{ + INIT_LIST_HEAD(&qm_list->list); + mutex_init(&qm_list->lock); +} + +int hisi_qm_init(struct hisi_qm *qm); +void hisi_qm_uninit(struct hisi_qm *qm); +int hisi_qm_start(struct hisi_qm *qm); +int hisi_qm_stop(struct hisi_qm *qm, enum qm_stop_reason r); +struct hisi_qp *hisi_qm_create_qp(struct hisi_qm *qm, u8 alg_type); +int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg); +int hisi_qm_stop_qp(struct hisi_qp *qp); +void hisi_qm_release_qp(struct hisi_qp *qp); +int hisi_qp_send(struct hisi_qp *qp, const void *msg); +int hisi_qm_get_free_qp_num(struct hisi_qm *qm); +int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number); +void hisi_qm_debug_init(struct hisi_qm *qm); +enum qm_hw_ver hisi_qm_get_hw_version(struct pci_dev *pdev); +void hisi_qm_debug_regs_clear(struct hisi_qm *qm); +int hisi_qm_sriov_enable(struct pci_dev *pdev, int max_vfs); +int hisi_qm_sriov_disable(struct pci_dev *pdev, bool is_frozen); +int hisi_qm_sriov_configure(struct pci_dev *pdev, int num_vfs); +void hisi_qm_dev_err_init(struct hisi_qm *qm); +void hisi_qm_dev_err_uninit(struct hisi_qm *qm); +pci_ers_result_t hisi_qm_dev_err_detected(struct pci_dev *pdev, + pci_channel_state_t state); +pci_ers_result_t hisi_qm_dev_slot_reset(struct pci_dev *pdev); +void hisi_qm_reset_prepare(struct pci_dev *pdev); +void hisi_qm_reset_done(struct pci_dev *pdev); + +struct hisi_acc_sgl_pool; +struct hisi_acc_hw_sgl *hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev, + struct scatterlist *sgl, struct hisi_acc_sgl_pool *pool, + u32 index, dma_addr_t *hw_sgl_dma); +void hisi_acc_sg_buf_unmap(struct device *dev, struct scatterlist *sgl, + struct hisi_acc_hw_sgl *hw_sgl); +struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev, + u32 count, u32 sge_nr); +void hisi_acc_free_sgl_pool(struct device *dev, + struct hisi_acc_sgl_pool *pool); +int hisi_qm_alloc_qps_node(struct hisi_qm_list *qm_list, int qp_num, + u8 alg_type, int node, struct hisi_qp **qps); +void hisi_qm_free_qps(struct hisi_qp **qps, int qp_num); +void hisi_qm_dev_shutdown(struct pci_dev *pdev); +void hisi_qm_wait_task_finish(struct hisi_qm *qm, struct hisi_qm_list *qm_list); +int hisi_qm_alg_register(struct hisi_qm *qm, struct hisi_qm_list *qm_list); +void hisi_qm_alg_unregister(struct hisi_qm *qm, struct hisi_qm_list *qm_list); +int hisi_qm_resume(struct device *dev); +int hisi_qm_suspend(struct device *dev); +void hisi_qm_pm_uninit(struct hisi_qm *qm); +void hisi_qm_pm_init(struct hisi_qm *qm); +int hisi_qm_get_dfx_access(struct hisi_qm *qm); +void hisi_qm_put_dfx_access(struct hisi_qm *qm); +void hisi_qm_regs_dump(struct seq_file *s, struct debugfs_regset32 *regset); +#endif -- cgit v1.2.3 From b4b084d7133284e29777ca445e001186259602d4 Mon Sep 17 00:00:00 2001 From: Longfang Liu Date: Tue, 8 Mar 2022 18:48:55 +0000 Subject: crypto: hisilicon/qm: Move few definitions to common header Move Doorbell and Mailbox definitions to common header file. Also export QM mailbox functions. This will be useful when we introduce VFIO PCI HiSilicon ACC live migration driver. Signed-off-by: Longfang Liu Acked-by: Zhou Wang Signed-off-by: Shameer Kolothum Link: https://lore.kernel.org/r/20220308184902.2242-3-shameerali.kolothum.thodi@huawei.com Signed-off-by: Alex Williamson --- include/linux/hisi_acc_qm.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) (limited to 'include') diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index 3068093229a5..6a6477c34666 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -34,6 +34,40 @@ #define QM_WUSER_M_CFG_ENABLE 0x1000a8 #define WUSER_M_CFG_ENABLE 0xffffffff +/* mailbox */ +#define QM_MB_CMD_SQC 0x0 +#define QM_MB_CMD_CQC 0x1 +#define QM_MB_CMD_EQC 0x2 +#define QM_MB_CMD_AEQC 0x3 +#define QM_MB_CMD_SQC_BT 0x4 +#define QM_MB_CMD_CQC_BT 0x5 +#define QM_MB_CMD_SQC_VFT_V2 0x6 +#define QM_MB_CMD_STOP_QP 0x8 +#define QM_MB_CMD_SRC 0xc +#define QM_MB_CMD_DST 0xd + +#define QM_MB_CMD_SEND_BASE 0x300 +#define QM_MB_EVENT_SHIFT 8 +#define QM_MB_BUSY_SHIFT 13 +#define QM_MB_OP_SHIFT 14 +#define QM_MB_CMD_DATA_ADDR_L 0x304 +#define QM_MB_CMD_DATA_ADDR_H 0x308 +#define QM_MB_MAX_WAIT_CNT 6000 + +/* doorbell */ +#define QM_DOORBELL_CMD_SQ 0 +#define QM_DOORBELL_CMD_CQ 1 +#define QM_DOORBELL_CMD_EQ 2 +#define QM_DOORBELL_CMD_AEQ 3 + +#define QM_DOORBELL_SQ_CQ_BASE_V2 0x1000 +#define QM_DOORBELL_EQ_AEQ_BASE_V2 0x2000 +#define QM_QP_MAX_NUM_SHIFT 11 +#define QM_DB_CMD_SHIFT_V2 12 +#define QM_DB_RAND_SHIFT_V2 16 +#define QM_DB_INDEX_SHIFT_V2 32 +#define QM_DB_PRIORITY_SHIFT_V2 48 + /* qm cache */ #define QM_CACHE_CTL 0x100050 #define SQC_CACHE_ENABLE BIT(0) @@ -414,6 +448,10 @@ pci_ers_result_t hisi_qm_dev_slot_reset(struct pci_dev *pdev); void hisi_qm_reset_prepare(struct pci_dev *pdev); void hisi_qm_reset_done(struct pci_dev *pdev); +int hisi_qm_wait_mb_ready(struct hisi_qm *qm); +int hisi_qm_mb(struct hisi_qm *qm, u8 cmd, dma_addr_t dma_addr, u16 queue, + bool op); + struct hisi_acc_sgl_pool; struct hisi_acc_hw_sgl *hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev, struct scatterlist *sgl, struct hisi_acc_sgl_pool *pool, -- cgit v1.2.3 From fae74feacd2dfb6172c4862fc760f969a991c06f Mon Sep 17 00:00:00 2001 From: Shameer Kolothum Date: Tue, 8 Mar 2022 18:48:56 +0000 Subject: hisi_acc_qm: Move VF PCI device IDs to common header Move the PCI Device IDs of HiSilicon ACC VF devices to a common header and also use a uniform naming convention. This will be useful when we introduce the vfio PCI HiSilicon ACC live migration driver in subsequent patches. Cc: Bjorn Helgaas Acked-by: Zhou Wang Acked-by: Longfang Liu Acked-by: Kai Ye Signed-off-by: Shameer Kolothum Acked-by: Bjorn Helgaas # pci_ids.h Link: https://lore.kernel.org/r/20220308184902.2242-4-shameerali.kolothum.thodi@huawei.com Signed-off-by: Alex Williamson --- include/linux/pci_ids.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index aad54c666407..31dee2b65a62 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2529,6 +2529,9 @@ #define PCI_DEVICE_ID_KORENIX_JETCARDF3 0x17ff #define PCI_VENDOR_ID_HUAWEI 0x19e5 +#define PCI_DEVICE_ID_HUAWEI_ZIP_VF 0xa251 +#define PCI_DEVICE_ID_HUAWEI_SEC_VF 0xa256 +#define PCI_DEVICE_ID_HUAWEI_HPRE_VF 0xa259 #define PCI_VENDOR_ID_NETRONOME 0x19ee #define PCI_DEVICE_ID_NETRONOME_NFP4000 0x4000 -- cgit v1.2.3 From 442fbc099b839551f8576723da22c1269cc695ce Mon Sep 17 00:00:00 2001 From: Shameer Kolothum Date: Tue, 8 Mar 2022 18:48:59 +0000 Subject: hisi_acc_vfio_pci: Add helper to retrieve the struct pci_driver struct pci_driver pointer is an input into the pci_iov_get_pf_drvdata(). Introduce helpers to retrieve the ACC PF dev struct pci_driver pointers as we use this in ACC vfio migration driver. Acked-by: Zhou Wang Acked-by: Kai Ye Acked-by: Longfang Liu Signed-off-by: Shameer Kolothum Link: https://lore.kernel.org/r/20220308184902.2242-7-shameerali.kolothum.thodi@huawei.com Signed-off-by: Alex Williamson --- include/linux/hisi_acc_qm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index 6a6477c34666..00f2a4db8723 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -476,4 +476,9 @@ void hisi_qm_pm_init(struct hisi_qm *qm); int hisi_qm_get_dfx_access(struct hisi_qm *qm); void hisi_qm_put_dfx_access(struct hisi_qm *qm); void hisi_qm_regs_dump(struct seq_file *s, struct debugfs_regset32 *regset); + +/* Used by VFIO ACC live migration driver */ +struct pci_driver *hisi_sec_get_pf_driver(void); +struct pci_driver *hisi_hpre_get_pf_driver(void); +struct pci_driver *hisi_zip_get_pf_driver(void); #endif -- cgit v1.2.3 From 1e459b25081d4f939b8a1fb4c71dab0cec8f974a Mon Sep 17 00:00:00 2001 From: Longfang Liu Date: Tue, 8 Mar 2022 18:49:00 +0000 Subject: crypto: hisilicon/qm: Set the VF QM state register We use VF QM state register to record the status of the QM configuration state. This will be used in the ACC migration driver to determine whether we can safely save and restore the QM data. Signed-off-by: Longfang Liu Acked-by: Zhou Wang Signed-off-by: Shameer Kolothum Link: https://lore.kernel.org/r/20220308184902.2242-8-shameerali.kolothum.thodi@huawei.com Signed-off-by: Alex Williamson --- include/linux/hisi_acc_qm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index 00f2a4db8723..177f7b7cd414 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -67,6 +67,7 @@ #define QM_DB_RAND_SHIFT_V2 16 #define QM_DB_INDEX_SHIFT_V2 32 #define QM_DB_PRIORITY_SHIFT_V2 48 +#define QM_VF_STATE 0x60 /* qm cache */ #define QM_CACHE_CTL 0x100050 @@ -162,6 +163,11 @@ enum qm_debug_file { DEBUG_FILE_NUM, }; +enum qm_vf_state { + QM_READY = 0, + QM_NOT_READY, +}; + struct qm_dfx { atomic64_t err_irq_cnt; atomic64_t aeq_irq_cnt; -- cgit v1.2.3 From 8126b1c73108bc691f5643df19071a59a69d0bc6 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Mon, 14 Mar 2022 19:59:53 +0100 Subject: pstore: Don't use semaphores in always-atomic-context code pstore_dump() is *always* invoked in atomic context (nowadays in an RCU read-side critical section, before that under a spinlock). It doesn't make sense to try to use semaphores here. This is mostly a revert of commit ea84b580b955 ("pstore: Convert buf_lock to semaphore"), except that two parts aren't restored back exactly as they were: - keep the lock initialization in pstore_register - in efi_pstore_write(), always set the "block" flag to false - omit "is_locked", that was unnecessary since commit 959217c84c27 ("pstore: Actually give up during locking failure") - fix the bailout message The actual problem that the buggy commit was trying to address may have been that the use of preemptible() in efi_pstore_write() was wrong - it only looks at preempt_count() and the state of IRQs, but __rcu_read_lock() doesn't touch either of those under CONFIG_PREEMPT_RCU. (Sidenote: CONFIG_PREEMPT_RCU means that the scheduler can preempt tasks in RCU read-side critical sections, but you're not allowed to actively block/reschedule.) Lockdep probably never caught the problem because it's very rare that you actually hit the contended case, so lockdep always just sees the down_trylock(), not the down_interruptible(), and so it can't tell that there's a problem. Fixes: ea84b580b955 ("pstore: Convert buf_lock to semaphore") Cc: stable@vger.kernel.org Acked-by: Sebastian Andrzej Siewior Signed-off-by: Jann Horn Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220314185953.2068993-1-jannh@google.com --- include/linux/pstore.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index eb93a54cff31..e97a8188f0fd 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include #include @@ -87,7 +87,7 @@ struct pstore_record { * @owner: module which is responsible for this backend driver * @name: name of the backend driver * - * @buf_lock: semaphore to serialize access to @buf + * @buf_lock: spinlock to serialize access to @buf * @buf: preallocated crash dump buffer * @bufsize: size of @buf available for crash dump bytes (must match * smallest number of bytes available for writing to a @@ -178,7 +178,7 @@ struct pstore_info { struct module *owner; const char *name; - struct semaphore buf_lock; + spinlock_t buf_lock; char *buf; size_t bufsize; -- cgit v1.2.3 From 65722ff6181aa52c3d5b0929004af22a3a63e148 Mon Sep 17 00:00:00 2001 From: David Yat Sin Date: Tue, 8 Mar 2022 14:00:50 -0500 Subject: drm/amdkfd: CRIU export dmabuf handles for GTT BOs Export dmabuf handles for GTT BOs so that their contents can be accessed using SDMA during checkpoint/restore. v2: Squash in fix from David to set dmabuf handle to invalid for BOs that cannot be accessed using SDMA during checkpoint/restore. Signed-off-by: David Yat Sin Reviewed-by : Rajneesh Bhardwaj Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index b40687bf1014..42975e940758 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -33,9 +33,10 @@ * - 1.5 - Add SVM API * - 1.6 - Query clear flags in SVM get_attr API * - 1.7 - Checkpoint Restore (CRIU) API + * - 1.8 - CRIU - Support for SDMA transfers with GTT BOs */ #define KFD_IOCTL_MAJOR_VERSION 1 -#define KFD_IOCTL_MINOR_VERSION 7 +#define KFD_IOCTL_MINOR_VERSION 8 struct kfd_ioctl_get_version_args { __u32 major_version; /* from KFD */ @@ -195,6 +196,8 @@ struct kfd_ioctl_dbg_wave_control_args { __u32 buf_size_in_bytes; /*including gpu_id and buf_size */ }; +#define KFD_INVALID_FD 0xffffffff + /* Matching HSA_EVENTTYPE */ #define KFD_IOC_EVENT_SIGNAL 0 #define KFD_IOC_EVENT_NODECHANGE 1 -- cgit v1.2.3 From 8850c3eae2c7a68ed901432a456ea70bbfef65a4 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Thu, 3 Feb 2022 10:56:16 +0200 Subject: clk: ti: Drop legacy compatibility clocks for am3 We no longer have users for the compatibility clocks and we can drop them. These are old duplicate clocks for what we using. Cc: devicetree@vger.kernel.org Cc: Rob Herring Signed-off-by: Tony Lindgren Link: https://lore.kernel.org/r/20220203085618.16043-2-tony@atomide.com Acked-by: Rob Herring Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/am3.h | 93 ----------------------------------------- 1 file changed, 93 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/clock/am3.h b/include/dt-bindings/clock/am3.h index 894951541276..dfbad5c87933 100644 --- a/include/dt-bindings/clock/am3.h +++ b/include/dt-bindings/clock/am3.h @@ -8,99 +8,6 @@ #define AM3_CLKCTRL_OFFSET 0x0 #define AM3_CLKCTRL_INDEX(offset) ((offset) - AM3_CLKCTRL_OFFSET) -/* XXX: Compatibility part begin, remove this once compatibility support is no longer needed */ - -/* l4_per clocks */ -#define AM3_L4_PER_CLKCTRL_OFFSET 0x14 -#define AM3_L4_PER_CLKCTRL_INDEX(offset) ((offset) - AM3_L4_PER_CLKCTRL_OFFSET) -#define AM3_CPGMAC0_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x14) -#define AM3_LCDC_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x18) -#define AM3_USB_OTG_HS_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x1c) -#define AM3_TPTC0_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x24) -#define AM3_EMIF_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x28) -#define AM3_OCMCRAM_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x2c) -#define AM3_GPMC_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x30) -#define AM3_MCASP0_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x34) -#define AM3_UART6_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x38) -#define AM3_MMC1_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x3c) -#define AM3_ELM_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x40) -#define AM3_I2C3_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x44) -#define AM3_I2C2_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x48) -#define AM3_SPI0_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x4c) -#define AM3_SPI1_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x50) -#define AM3_L4_LS_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x60) -#define AM3_MCASP1_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x68) -#define AM3_UART2_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x6c) -#define AM3_UART3_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x70) -#define AM3_UART4_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x74) -#define AM3_UART5_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x78) -#define AM3_TIMER7_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x7c) -#define AM3_TIMER2_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x80) -#define AM3_TIMER3_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x84) -#define AM3_TIMER4_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x88) -#define AM3_RNG_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x90) -#define AM3_AES_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x94) -#define AM3_SHAM_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0xa0) -#define AM3_GPIO2_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0xac) -#define AM3_GPIO3_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0xb0) -#define AM3_GPIO4_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0xb4) -#define AM3_TPCC_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0xbc) -#define AM3_D_CAN0_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0xc0) -#define AM3_D_CAN1_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0xc4) -#define AM3_EPWMSS1_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0xcc) -#define AM3_EPWMSS0_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0xd4) -#define AM3_EPWMSS2_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0xd8) -#define AM3_L3_INSTR_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0xdc) -#define AM3_L3_MAIN_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0xe0) -#define AM3_PRUSS_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0xe8) -#define AM3_TIMER5_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0xec) -#define AM3_TIMER6_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0xf0) -#define AM3_MMC2_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0xf4) -#define AM3_MMC3_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0xf8) -#define AM3_TPTC1_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0xfc) -#define AM3_TPTC2_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x100) -#define AM3_SPINLOCK_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x10c) -#define AM3_MAILBOX_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x110) -#define AM3_L4_HS_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x120) -#define AM3_OCPWP_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x130) -#define AM3_CLKDIV32K_CLKCTRL AM3_L4_PER_CLKCTRL_INDEX(0x14c) - -/* l4_wkup clocks */ -#define AM3_L4_WKUP_CLKCTRL_OFFSET 0x4 -#define AM3_L4_WKUP_CLKCTRL_INDEX(offset) ((offset) - AM3_L4_WKUP_CLKCTRL_OFFSET) -#define AM3_CONTROL_CLKCTRL AM3_L4_WKUP_CLKCTRL_INDEX(0x4) -#define AM3_GPIO1_CLKCTRL AM3_L4_WKUP_CLKCTRL_INDEX(0x8) -#define AM3_L4_WKUP_CLKCTRL AM3_L4_WKUP_CLKCTRL_INDEX(0xc) -#define AM3_DEBUGSS_CLKCTRL AM3_L4_WKUP_CLKCTRL_INDEX(0x14) -#define AM3_WKUP_M3_CLKCTRL AM3_L4_WKUP_CLKCTRL_INDEX(0xb0) -#define AM3_UART1_CLKCTRL AM3_L4_WKUP_CLKCTRL_INDEX(0xb4) -#define AM3_I2C1_CLKCTRL AM3_L4_WKUP_CLKCTRL_INDEX(0xb8) -#define AM3_ADC_TSC_CLKCTRL AM3_L4_WKUP_CLKCTRL_INDEX(0xbc) -#define AM3_SMARTREFLEX0_CLKCTRL AM3_L4_WKUP_CLKCTRL_INDEX(0xc0) -#define AM3_TIMER1_CLKCTRL AM3_L4_WKUP_CLKCTRL_INDEX(0xc4) -#define AM3_SMARTREFLEX1_CLKCTRL AM3_L4_WKUP_CLKCTRL_INDEX(0xc8) -#define AM3_WD_TIMER2_CLKCTRL AM3_L4_WKUP_CLKCTRL_INDEX(0xd4) - -/* mpu clocks */ -#define AM3_MPU_CLKCTRL_OFFSET 0x4 -#define AM3_MPU_CLKCTRL_INDEX(offset) ((offset) - AM3_MPU_CLKCTRL_OFFSET) -#define AM3_MPU_CLKCTRL AM3_MPU_CLKCTRL_INDEX(0x4) - -/* l4_rtc clocks */ -#define AM3_RTC_CLKCTRL AM3_CLKCTRL_INDEX(0x0) - -/* gfx_l3 clocks */ -#define AM3_GFX_L3_CLKCTRL_OFFSET 0x4 -#define AM3_GFX_L3_CLKCTRL_INDEX(offset) ((offset) - AM3_GFX_L3_CLKCTRL_OFFSET) -#define AM3_GFX_CLKCTRL AM3_GFX_L3_CLKCTRL_INDEX(0x4) - -/* l4_cefuse clocks */ -#define AM3_L4_CEFUSE_CLKCTRL_OFFSET 0x20 -#define AM3_L4_CEFUSE_CLKCTRL_INDEX(offset) ((offset) - AM3_L4_CEFUSE_CLKCTRL_OFFSET) -#define AM3_CEFUSE_CLKCTRL AM3_L4_CEFUSE_CLKCTRL_INDEX(0x20) - -/* XXX: Compatibility part end */ - /* l4ls clocks */ #define AM3_L4LS_CLKCTRL_OFFSET 0x38 #define AM3_L4LS_CLKCTRL_INDEX(offset) ((offset) - AM3_L4LS_CLKCTRL_OFFSET) -- cgit v1.2.3 From e65eb2efc6175392f0e97f515e6e5b179e181cd8 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Thu, 3 Feb 2022 10:56:17 +0200 Subject: clk: ti: Drop legacy compatibility clocks for am4 We no longer have users for the compatibility clocks and we can drop them. These are old duplicate clocks for what we using. Cc: devicetree@vger.kernel.org Cc: Rob Herring Signed-off-by: Tony Lindgren Link: https://lore.kernel.org/r/20220203085618.16043-3-tony@atomide.com Acked-by: Rob Herring Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/am4.h | 98 ----------------------------------------- 1 file changed, 98 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/clock/am4.h b/include/dt-bindings/clock/am4.h index 4be6c5961f34..a65b082e9cff 100644 --- a/include/dt-bindings/clock/am4.h +++ b/include/dt-bindings/clock/am4.h @@ -8,104 +8,6 @@ #define AM4_CLKCTRL_OFFSET 0x20 #define AM4_CLKCTRL_INDEX(offset) ((offset) - AM4_CLKCTRL_OFFSET) -/* XXX: Compatibility part begin, remove this once compatibility support is no longer needed */ - -/* l4_wkup clocks */ -#define AM4_ADC_TSC_CLKCTRL AM4_CLKCTRL_INDEX(0x120) -#define AM4_L4_WKUP_CLKCTRL AM4_CLKCTRL_INDEX(0x220) -#define AM4_WKUP_M3_CLKCTRL AM4_CLKCTRL_INDEX(0x228) -#define AM4_COUNTER_32K_CLKCTRL AM4_CLKCTRL_INDEX(0x230) -#define AM4_TIMER1_CLKCTRL AM4_CLKCTRL_INDEX(0x328) -#define AM4_WD_TIMER2_CLKCTRL AM4_CLKCTRL_INDEX(0x338) -#define AM4_I2C1_CLKCTRL AM4_CLKCTRL_INDEX(0x340) -#define AM4_UART1_CLKCTRL AM4_CLKCTRL_INDEX(0x348) -#define AM4_SMARTREFLEX0_CLKCTRL AM4_CLKCTRL_INDEX(0x350) -#define AM4_SMARTREFLEX1_CLKCTRL AM4_CLKCTRL_INDEX(0x358) -#define AM4_CONTROL_CLKCTRL AM4_CLKCTRL_INDEX(0x360) -#define AM4_GPIO1_CLKCTRL AM4_CLKCTRL_INDEX(0x368) - -/* mpu clocks */ -#define AM4_MPU_CLKCTRL AM4_CLKCTRL_INDEX(0x20) - -/* gfx_l3 clocks */ -#define AM4_GFX_CLKCTRL AM4_CLKCTRL_INDEX(0x20) - -/* l4_rtc clocks */ -#define AM4_RTC_CLKCTRL AM4_CLKCTRL_INDEX(0x20) - -/* l4_per clocks */ -#define AM4_L3_MAIN_CLKCTRL AM4_CLKCTRL_INDEX(0x20) -#define AM4_AES_CLKCTRL AM4_CLKCTRL_INDEX(0x28) -#define AM4_DES_CLKCTRL AM4_CLKCTRL_INDEX(0x30) -#define AM4_L3_INSTR_CLKCTRL AM4_CLKCTRL_INDEX(0x40) -#define AM4_OCMCRAM_CLKCTRL AM4_CLKCTRL_INDEX(0x50) -#define AM4_SHAM_CLKCTRL AM4_CLKCTRL_INDEX(0x58) -#define AM4_VPFE0_CLKCTRL AM4_CLKCTRL_INDEX(0x68) -#define AM4_VPFE1_CLKCTRL AM4_CLKCTRL_INDEX(0x70) -#define AM4_TPCC_CLKCTRL AM4_CLKCTRL_INDEX(0x78) -#define AM4_TPTC0_CLKCTRL AM4_CLKCTRL_INDEX(0x80) -#define AM4_TPTC1_CLKCTRL AM4_CLKCTRL_INDEX(0x88) -#define AM4_TPTC2_CLKCTRL AM4_CLKCTRL_INDEX(0x90) -#define AM4_L4_HS_CLKCTRL AM4_CLKCTRL_INDEX(0xa0) -#define AM4_GPMC_CLKCTRL AM4_CLKCTRL_INDEX(0x220) -#define AM4_MCASP0_CLKCTRL AM4_CLKCTRL_INDEX(0x238) -#define AM4_MCASP1_CLKCTRL AM4_CLKCTRL_INDEX(0x240) -#define AM4_MMC3_CLKCTRL AM4_CLKCTRL_INDEX(0x248) -#define AM4_QSPI_CLKCTRL AM4_CLKCTRL_INDEX(0x258) -#define AM4_USB_OTG_SS0_CLKCTRL AM4_CLKCTRL_INDEX(0x260) -#define AM4_USB_OTG_SS1_CLKCTRL AM4_CLKCTRL_INDEX(0x268) -#define AM4_PRUSS_CLKCTRL AM4_CLKCTRL_INDEX(0x320) -#define AM4_L4_LS_CLKCTRL AM4_CLKCTRL_INDEX(0x420) -#define AM4_D_CAN0_CLKCTRL AM4_CLKCTRL_INDEX(0x428) -#define AM4_D_CAN1_CLKCTRL AM4_CLKCTRL_INDEX(0x430) -#define AM4_EPWMSS0_CLKCTRL AM4_CLKCTRL_INDEX(0x438) -#define AM4_EPWMSS1_CLKCTRL AM4_CLKCTRL_INDEX(0x440) -#define AM4_EPWMSS2_CLKCTRL AM4_CLKCTRL_INDEX(0x448) -#define AM4_EPWMSS3_CLKCTRL AM4_CLKCTRL_INDEX(0x450) -#define AM4_EPWMSS4_CLKCTRL AM4_CLKCTRL_INDEX(0x458) -#define AM4_EPWMSS5_CLKCTRL AM4_CLKCTRL_INDEX(0x460) -#define AM4_ELM_CLKCTRL AM4_CLKCTRL_INDEX(0x468) -#define AM4_GPIO2_CLKCTRL AM4_CLKCTRL_INDEX(0x478) -#define AM4_GPIO3_CLKCTRL AM4_CLKCTRL_INDEX(0x480) -#define AM4_GPIO4_CLKCTRL AM4_CLKCTRL_INDEX(0x488) -#define AM4_GPIO5_CLKCTRL AM4_CLKCTRL_INDEX(0x490) -#define AM4_GPIO6_CLKCTRL AM4_CLKCTRL_INDEX(0x498) -#define AM4_HDQ1W_CLKCTRL AM4_CLKCTRL_INDEX(0x4a0) -#define AM4_I2C2_CLKCTRL AM4_CLKCTRL_INDEX(0x4a8) -#define AM4_I2C3_CLKCTRL AM4_CLKCTRL_INDEX(0x4b0) -#define AM4_MAILBOX_CLKCTRL AM4_CLKCTRL_INDEX(0x4b8) -#define AM4_MMC1_CLKCTRL AM4_CLKCTRL_INDEX(0x4c0) -#define AM4_MMC2_CLKCTRL AM4_CLKCTRL_INDEX(0x4c8) -#define AM4_RNG_CLKCTRL AM4_CLKCTRL_INDEX(0x4e0) -#define AM4_SPI0_CLKCTRL AM4_CLKCTRL_INDEX(0x500) -#define AM4_SPI1_CLKCTRL AM4_CLKCTRL_INDEX(0x508) -#define AM4_SPI2_CLKCTRL AM4_CLKCTRL_INDEX(0x510) -#define AM4_SPI3_CLKCTRL AM4_CLKCTRL_INDEX(0x518) -#define AM4_SPI4_CLKCTRL AM4_CLKCTRL_INDEX(0x520) -#define AM4_SPINLOCK_CLKCTRL AM4_CLKCTRL_INDEX(0x528) -#define AM4_TIMER2_CLKCTRL AM4_CLKCTRL_INDEX(0x530) -#define AM4_TIMER3_CLKCTRL AM4_CLKCTRL_INDEX(0x538) -#define AM4_TIMER4_CLKCTRL AM4_CLKCTRL_INDEX(0x540) -#define AM4_TIMER5_CLKCTRL AM4_CLKCTRL_INDEX(0x548) -#define AM4_TIMER6_CLKCTRL AM4_CLKCTRL_INDEX(0x550) -#define AM4_TIMER7_CLKCTRL AM4_CLKCTRL_INDEX(0x558) -#define AM4_TIMER8_CLKCTRL AM4_CLKCTRL_INDEX(0x560) -#define AM4_TIMER9_CLKCTRL AM4_CLKCTRL_INDEX(0x568) -#define AM4_TIMER10_CLKCTRL AM4_CLKCTRL_INDEX(0x570) -#define AM4_TIMER11_CLKCTRL AM4_CLKCTRL_INDEX(0x578) -#define AM4_UART2_CLKCTRL AM4_CLKCTRL_INDEX(0x580) -#define AM4_UART3_CLKCTRL AM4_CLKCTRL_INDEX(0x588) -#define AM4_UART4_CLKCTRL AM4_CLKCTRL_INDEX(0x590) -#define AM4_UART5_CLKCTRL AM4_CLKCTRL_INDEX(0x598) -#define AM4_UART6_CLKCTRL AM4_CLKCTRL_INDEX(0x5a0) -#define AM4_OCP2SCP0_CLKCTRL AM4_CLKCTRL_INDEX(0x5b8) -#define AM4_OCP2SCP1_CLKCTRL AM4_CLKCTRL_INDEX(0x5c0) -#define AM4_EMIF_CLKCTRL AM4_CLKCTRL_INDEX(0x720) -#define AM4_DSS_CORE_CLKCTRL AM4_CLKCTRL_INDEX(0xa20) -#define AM4_CPGMAC0_CLKCTRL AM4_CLKCTRL_INDEX(0xb20) - -/* XXX: Compatibility part end. */ - /* l3s_tsc clocks */ #define AM4_L3S_TSC_CLKCTRL_OFFSET 0x120 #define AM4_L3S_TSC_CLKCTRL_INDEX(offset) ((offset) - AM4_L3S_TSC_CLKCTRL_OFFSET) -- cgit v1.2.3 From 579cdf58b7e50fa0650324667d240ecf45c7d12f Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Thu, 3 Feb 2022 10:56:18 +0200 Subject: clk: ti: Drop legacy compatibility clocks for dra7 We no longer have users for the compatibility clocks and we can drop them. These are old duplicate clocks for what we using. Depends-on: 31aa7056bbec ("ARM: dts: Don't use legacy clock defines for dra7 clkctrl") Depends-on: 9206a3af4fc0 ("clk: ti: Move dra7 clock devices out of the legacy section") Cc: devicetree@vger.kernel.org Cc: Rob Herring Signed-off-by: Tony Lindgren Link: https://lore.kernel.org/r/20220203085618.16043-4-tony@atomide.com Acked-by: Rob Herring Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/dra7.h | 168 --------------------------------------- 1 file changed, 168 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/clock/dra7.h b/include/dt-bindings/clock/dra7.h index 29ff6b895848..8a903c78c5a5 100644 --- a/include/dt-bindings/clock/dra7.h +++ b/include/dt-bindings/clock/dra7.h @@ -8,174 +8,6 @@ #define DRA7_CLKCTRL_OFFSET 0x20 #define DRA7_CLKCTRL_INDEX(offset) ((offset) - DRA7_CLKCTRL_OFFSET) -/* XXX: Compatibility part begin, remove this once compatibility support is no longer needed */ - -/* mpu clocks */ -#define DRA7_MPU_CLKCTRL DRA7_CLKCTRL_INDEX(0x20) - -/* ipu clocks */ -#define _DRA7_IPU_CLKCTRL_OFFSET 0x40 -#define _DRA7_IPU_CLKCTRL_INDEX(offset) ((offset) - _DRA7_IPU_CLKCTRL_OFFSET) -#define DRA7_MCASP1_CLKCTRL _DRA7_IPU_CLKCTRL_INDEX(0x50) -#define DRA7_TIMER5_CLKCTRL _DRA7_IPU_CLKCTRL_INDEX(0x58) -#define DRA7_TIMER6_CLKCTRL _DRA7_IPU_CLKCTRL_INDEX(0x60) -#define DRA7_TIMER7_CLKCTRL _DRA7_IPU_CLKCTRL_INDEX(0x68) -#define DRA7_TIMER8_CLKCTRL _DRA7_IPU_CLKCTRL_INDEX(0x70) -#define DRA7_I2C5_CLKCTRL _DRA7_IPU_CLKCTRL_INDEX(0x78) -#define DRA7_UART6_CLKCTRL _DRA7_IPU_CLKCTRL_INDEX(0x80) - -/* rtc clocks */ -#define DRA7_RTC_CLKCTRL_OFFSET 0x40 -#define DRA7_RTC_CLKCTRL_INDEX(offset) ((offset) - DRA7_RTC_CLKCTRL_OFFSET) -#define DRA7_RTCSS_CLKCTRL DRA7_RTC_CLKCTRL_INDEX(0x44) - -/* vip clocks */ -#define DRA7_VIP1_CLKCTRL DRA7_CLKCTRL_INDEX(0x20) -#define DRA7_VIP2_CLKCTRL DRA7_CLKCTRL_INDEX(0x28) -#define DRA7_VIP3_CLKCTRL DRA7_CLKCTRL_INDEX(0x30) - -/* vpe clocks */ -#define DRA7_VPE_CLKCTRL_OFFSET 0x60 -#define DRA7_VPE_CLKCTRL_INDEX(offset) ((offset) - DRA7_VPE_CLKCTRL_OFFSET) -#define DRA7_VPE_CLKCTRL DRA7_VPE_CLKCTRL_INDEX(0x64) - -/* coreaon clocks */ -#define DRA7_SMARTREFLEX_MPU_CLKCTRL DRA7_CLKCTRL_INDEX(0x28) -#define DRA7_SMARTREFLEX_CORE_CLKCTRL DRA7_CLKCTRL_INDEX(0x38) - -/* l3main1 clocks */ -#define DRA7_L3_MAIN_1_CLKCTRL DRA7_CLKCTRL_INDEX(0x20) -#define DRA7_GPMC_CLKCTRL DRA7_CLKCTRL_INDEX(0x28) -#define DRA7_TPCC_CLKCTRL DRA7_CLKCTRL_INDEX(0x70) -#define DRA7_TPTC0_CLKCTRL DRA7_CLKCTRL_INDEX(0x78) -#define DRA7_TPTC1_CLKCTRL DRA7_CLKCTRL_INDEX(0x80) -#define DRA7_VCP1_CLKCTRL DRA7_CLKCTRL_INDEX(0x88) -#define DRA7_VCP2_CLKCTRL DRA7_CLKCTRL_INDEX(0x90) - -/* dma clocks */ -#define DRA7_DMA_SYSTEM_CLKCTRL DRA7_CLKCTRL_INDEX(0x20) - -/* emif clocks */ -#define DRA7_DMM_CLKCTRL DRA7_CLKCTRL_INDEX(0x20) - -/* atl clocks */ -#define DRA7_ATL_CLKCTRL_OFFSET 0x0 -#define DRA7_ATL_CLKCTRL_INDEX(offset) ((offset) - DRA7_ATL_CLKCTRL_OFFSET) -#define DRA7_ATL_CLKCTRL DRA7_ATL_CLKCTRL_INDEX(0x0) - -/* l4cfg clocks */ -#define DRA7_L4_CFG_CLKCTRL DRA7_CLKCTRL_INDEX(0x20) -#define DRA7_SPINLOCK_CLKCTRL DRA7_CLKCTRL_INDEX(0x28) -#define DRA7_MAILBOX1_CLKCTRL DRA7_CLKCTRL_INDEX(0x30) -#define DRA7_MAILBOX2_CLKCTRL DRA7_CLKCTRL_INDEX(0x48) -#define DRA7_MAILBOX3_CLKCTRL DRA7_CLKCTRL_INDEX(0x50) -#define DRA7_MAILBOX4_CLKCTRL DRA7_CLKCTRL_INDEX(0x58) -#define DRA7_MAILBOX5_CLKCTRL DRA7_CLKCTRL_INDEX(0x60) -#define DRA7_MAILBOX6_CLKCTRL DRA7_CLKCTRL_INDEX(0x68) -#define DRA7_MAILBOX7_CLKCTRL DRA7_CLKCTRL_INDEX(0x70) -#define DRA7_MAILBOX8_CLKCTRL DRA7_CLKCTRL_INDEX(0x78) -#define DRA7_MAILBOX9_CLKCTRL DRA7_CLKCTRL_INDEX(0x80) -#define DRA7_MAILBOX10_CLKCTRL DRA7_CLKCTRL_INDEX(0x88) -#define DRA7_MAILBOX11_CLKCTRL DRA7_CLKCTRL_INDEX(0x90) -#define DRA7_MAILBOX12_CLKCTRL DRA7_CLKCTRL_INDEX(0x98) -#define DRA7_MAILBOX13_CLKCTRL DRA7_CLKCTRL_INDEX(0xa0) - -/* l3instr clocks */ -#define DRA7_L3_MAIN_2_CLKCTRL DRA7_CLKCTRL_INDEX(0x20) -#define DRA7_L3_INSTR_CLKCTRL DRA7_CLKCTRL_INDEX(0x28) - -/* dss clocks */ -#define DRA7_DSS_CORE_CLKCTRL DRA7_CLKCTRL_INDEX(0x20) -#define DRA7_BB2D_CLKCTRL DRA7_CLKCTRL_INDEX(0x30) - -/* l3init clocks */ -#define DRA7_MMC1_CLKCTRL DRA7_CLKCTRL_INDEX(0x28) -#define DRA7_MMC2_CLKCTRL DRA7_CLKCTRL_INDEX(0x30) -#define DRA7_USB_OTG_SS2_CLKCTRL DRA7_CLKCTRL_INDEX(0x40) -#define DRA7_USB_OTG_SS3_CLKCTRL DRA7_CLKCTRL_INDEX(0x48) -#define DRA7_USB_OTG_SS4_CLKCTRL DRA7_CLKCTRL_INDEX(0x50) -#define DRA7_SATA_CLKCTRL DRA7_CLKCTRL_INDEX(0x88) -#define DRA7_PCIE1_CLKCTRL DRA7_CLKCTRL_INDEX(0xb0) -#define DRA7_PCIE2_CLKCTRL DRA7_CLKCTRL_INDEX(0xb8) -#define DRA7_GMAC_CLKCTRL DRA7_CLKCTRL_INDEX(0xd0) -#define DRA7_OCP2SCP1_CLKCTRL DRA7_CLKCTRL_INDEX(0xe0) -#define DRA7_OCP2SCP3_CLKCTRL DRA7_CLKCTRL_INDEX(0xe8) -#define DRA7_USB_OTG_SS1_CLKCTRL DRA7_CLKCTRL_INDEX(0xf0) - -/* l4per clocks */ -#define _DRA7_L4PER_CLKCTRL_OFFSET 0x0 -#define _DRA7_L4PER_CLKCTRL_INDEX(offset) ((offset) - _DRA7_L4PER_CLKCTRL_OFFSET) -#define DRA7_L4_PER2_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0xc) -#define DRA7_L4_PER3_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x14) -#define DRA7_TIMER10_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x28) -#define DRA7_TIMER11_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x30) -#define DRA7_TIMER2_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x38) -#define DRA7_TIMER3_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x40) -#define DRA7_TIMER4_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x48) -#define DRA7_TIMER9_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x50) -#define DRA7_ELM_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x58) -#define DRA7_GPIO2_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x60) -#define DRA7_GPIO3_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x68) -#define DRA7_GPIO4_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x70) -#define DRA7_GPIO5_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x78) -#define DRA7_GPIO6_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x80) -#define DRA7_HDQ1W_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x88) -#define DRA7_EPWMSS1_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x90) -#define DRA7_EPWMSS2_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x98) -#define DRA7_I2C1_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0xa0) -#define DRA7_I2C2_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0xa8) -#define DRA7_I2C3_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0xb0) -#define DRA7_I2C4_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0xb8) -#define DRA7_L4_PER1_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0xc0) -#define DRA7_EPWMSS0_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0xc4) -#define DRA7_TIMER13_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0xc8) -#define DRA7_TIMER14_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0xd0) -#define DRA7_TIMER15_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0xd8) -#define DRA7_MCSPI1_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0xf0) -#define DRA7_MCSPI2_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0xf8) -#define DRA7_MCSPI3_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x100) -#define DRA7_MCSPI4_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x108) -#define DRA7_GPIO7_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x110) -#define DRA7_GPIO8_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x118) -#define DRA7_MMC3_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x120) -#define DRA7_MMC4_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x128) -#define DRA7_TIMER16_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x130) -#define DRA7_QSPI_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x138) -#define DRA7_UART1_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x140) -#define DRA7_UART2_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x148) -#define DRA7_UART3_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x150) -#define DRA7_UART4_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x158) -#define DRA7_MCASP2_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x160) -#define DRA7_MCASP3_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x168) -#define DRA7_UART5_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x170) -#define DRA7_MCASP5_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x178) -#define DRA7_MCASP8_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x190) -#define DRA7_MCASP4_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x198) -#define DRA7_AES1_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x1a0) -#define DRA7_AES2_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x1a8) -#define DRA7_DES_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x1b0) -#define DRA7_RNG_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x1c0) -#define DRA7_SHAM_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x1c8) -#define DRA7_UART7_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x1d0) -#define DRA7_UART8_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x1e0) -#define DRA7_UART9_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x1e8) -#define DRA7_DCAN2_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x1f0) -#define DRA7_MCASP6_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x204) -#define DRA7_MCASP7_CLKCTRL _DRA7_L4PER_CLKCTRL_INDEX(0x208) - -/* wkupaon clocks */ -#define DRA7_L4_WKUP_CLKCTRL DRA7_CLKCTRL_INDEX(0x20) -#define DRA7_WD_TIMER2_CLKCTRL DRA7_CLKCTRL_INDEX(0x30) -#define DRA7_GPIO1_CLKCTRL DRA7_CLKCTRL_INDEX(0x38) -#define DRA7_TIMER1_CLKCTRL DRA7_CLKCTRL_INDEX(0x40) -#define DRA7_TIMER12_CLKCTRL DRA7_CLKCTRL_INDEX(0x48) -#define DRA7_COUNTER_32K_CLKCTRL DRA7_CLKCTRL_INDEX(0x50) -#define DRA7_UART10_CLKCTRL DRA7_CLKCTRL_INDEX(0x80) -#define DRA7_DCAN1_CLKCTRL DRA7_CLKCTRL_INDEX(0x88) -#define DRA7_ADC_CLKCTRL DRA7_CLKCTRL_INDEX(0xa0) - -/* XXX: Compatibility part end. */ - /* mpu clocks */ #define DRA7_MPU_MPU_CLKCTRL DRA7_CLKCTRL_INDEX(0x20) -- cgit v1.2.3 From 08f4c42abad1b93914a93f9042e2443593bd3137 Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Sat, 12 Mar 2022 11:09:51 +0530 Subject: ext4: add new trace event in ext4_fc_cleanup This adds a new trace event in ext4_fc_cleanup() which is helpful in debugging some fast_commit issues. Signed-off-by: Ritesh Harjani Link: https://lore.kernel.org/r/794cdb1d5d3622f3f80d30c222ff6652ea68c375.1647057583.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o --- include/trace/events/ext4.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include') diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 3d48fcb62987..20654aaf9495 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -2863,6 +2863,32 @@ TRACE_EVENT(ext4_fc_track_range, __entry->end) ); +TRACE_EVENT(ext4_fc_cleanup, + TP_PROTO(journal_t *journal, int full, tid_t tid), + + TP_ARGS(journal, full, tid), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, j_fc_off) + __field(int, full) + __field(tid_t, tid) + ), + + TP_fast_assign( + struct super_block *sb = journal->j_private; + + __entry->dev = sb->s_dev; + __entry->j_fc_off = journal->j_fc_off; + __entry->full = full; + __entry->tid = tid; + ), + + TP_printk("dev %d,%d, j_fc_off %d, full %d, tid %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->j_fc_off, __entry->full, __entry->tid) + ); + TRACE_EVENT(ext4_update_sb, TP_PROTO(struct super_block *sb, ext4_fsblk_t fsblk, unsigned int flags), -- cgit v1.2.3 From 1d2e2440c5191da82b1191298909283a58f0ece8 Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Sat, 12 Mar 2022 11:09:52 +0530 Subject: ext4: add transaction tid info in fc_track events This patch adds the transaction & inode tid info in trace events for callers of ext4_fc_track_template(). This is helpful in debugging race conditions where an inode could belong to two different transaction tids. It also fixes the checkpatch warnings which says use tabs instead of spaces. Signed-off-by: Ritesh Harjani Link: https://lore.kernel.org/r/c203c09dc11bb372803c430f621f25a4b8c2c8b4.1647057583.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o --- include/trace/events/ext4.h | 113 ++++++++++++++++++++++++++------------------ 1 file changed, 68 insertions(+), 45 deletions(-) (limited to 'include') diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 20654aaf9495..6bd90df07b5c 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -2782,32 +2782,41 @@ TRACE_EVENT(ext4_fc_stats, DECLARE_EVENT_CLASS(ext4_fc_track_dentry, - TP_PROTO(struct inode *inode, struct dentry *dentry, int ret), + TP_PROTO(handle_t *handle, struct inode *inode, + struct dentry *dentry, int ret), - TP_ARGS(inode, dentry, ret), + TP_ARGS(handle, inode, dentry, ret), TP_STRUCT__entry( __field(dev_t, dev) + __field(tid_t, t_tid) __field(ino_t, i_ino) + __field(tid_t, i_sync_tid) __field(int, error) ), TP_fast_assign( + struct ext4_inode_info *ei = EXT4_I(inode); + __entry->dev = inode->i_sb->s_dev; + __entry->t_tid = handle->h_transaction->t_tid; __entry->i_ino = inode->i_ino; + __entry->i_sync_tid = ei->i_sync_tid; __entry->error = ret; ), - TP_printk("dev %d,%d, ino %lu, error %d", + TP_printk("dev %d,%d, t_tid %u, ino %lu, i_sync_tid %u, error %d", MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->i_ino, __entry->error + __entry->t_tid, __entry->i_ino, __entry->i_sync_tid, + __entry->error ) ); #define DEFINE_EVENT_CLASS_DENTRY(__type) \ DEFINE_EVENT(ext4_fc_track_dentry, ext4_fc_track_##__type, \ - TP_PROTO(struct inode *inode, struct dentry *dentry, int ret), \ - TP_ARGS(inode, dentry, ret) \ + TP_PROTO(handle_t *handle, struct inode *inode, \ + struct dentry *dentry, int ret), \ + TP_ARGS(handle, inode, dentry, ret) \ ) DEFINE_EVENT_CLASS_DENTRY(create); @@ -2815,52 +2824,66 @@ DEFINE_EVENT_CLASS_DENTRY(link); DEFINE_EVENT_CLASS_DENTRY(unlink); TRACE_EVENT(ext4_fc_track_inode, - TP_PROTO(struct inode *inode, int ret), + TP_PROTO(handle_t *handle, struct inode *inode, int ret), - TP_ARGS(inode, ret), + TP_ARGS(handle, inode, ret), - TP_STRUCT__entry( - __field(dev_t, dev) - __field(int, ino) - __field(int, error) - ), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(tid_t, t_tid) + __field(ino_t, i_ino) + __field(tid_t, i_sync_tid) + __field(int, error) + ), - TP_fast_assign( - __entry->dev = inode->i_sb->s_dev; - __entry->ino = inode->i_ino; - __entry->error = ret; - ), + TP_fast_assign( + struct ext4_inode_info *ei = EXT4_I(inode); - TP_printk("dev %d:%d, inode %d, error %d", - MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->ino, __entry->error) + __entry->dev = inode->i_sb->s_dev; + __entry->t_tid = handle->h_transaction->t_tid; + __entry->i_ino = inode->i_ino; + __entry->i_sync_tid = ei->i_sync_tid; + __entry->error = ret; + ), + + TP_printk("dev %d:%d, t_tid %u, inode %lu, i_sync_tid %u, error %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->t_tid, __entry->i_ino, __entry->i_sync_tid, + __entry->error) ); TRACE_EVENT(ext4_fc_track_range, - TP_PROTO(struct inode *inode, long start, long end, int ret), - - TP_ARGS(inode, start, end, ret), - - TP_STRUCT__entry( - __field(dev_t, dev) - __field(int, ino) - __field(long, start) - __field(long, end) - __field(int, error) - ), - - TP_fast_assign( - __entry->dev = inode->i_sb->s_dev; - __entry->ino = inode->i_ino; - __entry->start = start; - __entry->end = end; - __entry->error = ret; - ), - - TP_printk("dev %d:%d, inode %d, error %d, start %ld, end %ld", - MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->ino, __entry->error, __entry->start, - __entry->end) + TP_PROTO(handle_t *handle, struct inode *inode, + long start, long end, int ret), + + TP_ARGS(handle, inode, start, end, ret), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(tid_t, t_tid) + __field(ino_t, i_ino) + __field(tid_t, i_sync_tid) + __field(long, start) + __field(long, end) + __field(int, error) + ), + + TP_fast_assign( + struct ext4_inode_info *ei = EXT4_I(inode); + + __entry->dev = inode->i_sb->s_dev; + __entry->t_tid = handle->h_transaction->t_tid; + __entry->i_ino = inode->i_ino; + __entry->i_sync_tid = ei->i_sync_tid; + __entry->start = start; + __entry->end = end; + __entry->error = ret; + ), + + TP_printk("dev %d:%d, t_tid %u, inode %lu, i_sync_tid %u, error %d, start %ld, end %ld", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->t_tid, __entry->i_ino, __entry->i_sync_tid, + __entry->error, __entry->start, __entry->end) ); TRACE_EVENT(ext4_fc_cleanup, -- cgit v1.2.3 From 5641ace54471cb5c393e71f33232088602455c6b Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Sat, 12 Mar 2022 11:09:54 +0530 Subject: ext4: add commit tid info in ext4_fc_commit_start/stop trace events This adds commit_tid info in ext4_fc_commit_start/stop which is helpful in debugging fast_commit issues. For e.g. issues where due to jbd2 journal full commit, FC miss to commit updates to a file. Also improves TP_prink format string i.e. all ext4 and jbd2 trace events starts with "dev MAjOR,MINOR". Let's follow the same convention while we are still at it. Signed-off-by: Ritesh Harjani Reviewed-by: Jan Kara Reviewed-by: Harshad Shirwadkar Link: https://lore.kernel.org/r/ebcd6b9ab5b718db30f90854497886801ce38c63.1647057583.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o --- include/trace/events/ext4.h | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 6bd90df07b5c..aad97376e032 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -2686,26 +2686,29 @@ TRACE_EVENT(ext4_fc_replay, ); TRACE_EVENT(ext4_fc_commit_start, - TP_PROTO(struct super_block *sb), + TP_PROTO(struct super_block *sb, tid_t commit_tid), - TP_ARGS(sb), + TP_ARGS(sb, commit_tid), TP_STRUCT__entry( __field(dev_t, dev) + __field(tid_t, tid) ), TP_fast_assign( __entry->dev = sb->s_dev; + __entry->tid = commit_tid; ), - TP_printk("fast_commit started on dev %d,%d", - MAJOR(__entry->dev), MINOR(__entry->dev)) + TP_printk("dev %d,%d tid %u", MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->tid) ); TRACE_EVENT(ext4_fc_commit_stop, - TP_PROTO(struct super_block *sb, int nblks, int reason), + TP_PROTO(struct super_block *sb, int nblks, int reason, + tid_t commit_tid), - TP_ARGS(sb, nblks, reason), + TP_ARGS(sb, nblks, reason, commit_tid), TP_STRUCT__entry( __field(dev_t, dev) @@ -2714,6 +2717,7 @@ TRACE_EVENT(ext4_fc_commit_stop, __field(int, num_fc) __field(int, num_fc_ineligible) __field(int, nblks_agg) + __field(tid_t, tid) ), TP_fast_assign( @@ -2724,12 +2728,13 @@ TRACE_EVENT(ext4_fc_commit_stop, __entry->num_fc_ineligible = EXT4_SB(sb)->s_fc_stats.fc_ineligible_commits; __entry->nblks_agg = EXT4_SB(sb)->s_fc_stats.fc_numblks; + __entry->tid = commit_tid; ), - TP_printk("fc on [%d,%d] nblks %d, reason %d, fc = %d, ineligible = %d, agg_nblks %d", + TP_printk("dev %d,%d nblks %d, reason %d, fc = %d, ineligible = %d, agg_nblks %d, tid %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->nblks, __entry->reason, __entry->num_fc, - __entry->num_fc_ineligible, __entry->nblks_agg) + __entry->num_fc_ineligible, __entry->nblks_agg, __entry->tid) ); #define FC_REASON_NAME_STAT(reason) \ -- cgit v1.2.3 From 163f11b8b3489fbf04be8d8d0e029f1dcd6546d1 Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Sat, 12 Mar 2022 11:09:55 +0530 Subject: ext4: fix remaining two trace events to use same printk convention All ext4 & jbd2 trace events starts with "dev Major:Minor". While we are still improving/adding the ftrace events for FC, let's fix last two remaining trace events to follow the same convention. Signed-off-by: Ritesh Harjani Reviewed-by: Harshad Shirwadkar Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/8f33b163f0f29df2491c03b79f8ac96890ea5184.1647057583.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o --- include/trace/events/ext4.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index aad97376e032..ce2b3ad0ee86 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -2654,7 +2654,7 @@ TRACE_EVENT(ext4_fc_replay_scan, __entry->off = off; ), - TP_printk("FC scan pass on dev %d,%d: error %d, off %d", + TP_printk("dev %d,%d error %d, off %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->error, __entry->off) ); @@ -2680,7 +2680,7 @@ TRACE_EVENT(ext4_fc_replay, __entry->priv2 = priv2; ), - TP_printk("FC Replay %d,%d: tag %d, ino %d, data1 %d, data2 %d", + TP_printk("dev %d,%d: tag %d, ino %d, data1 %d, data2 %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tag, __entry->ino, __entry->priv1, __entry->priv2) ); -- cgit v1.2.3 From 0493692b40d02a74dfb6823754f31951ace2000b Mon Sep 17 00:00:00 2001 From: Zong Li Date: Fri, 4 Mar 2022 18:03:18 +0800 Subject: dt-bindings: change the macro name of prci in header files and example We currently change the macro name for fu540 and fu740 by adding the prefix respectively, the dt-bindings should be modified as well. Signed-off-by: Zong Li Acked-by: Rob Herring Acked-by: Palmer Dabbelt Link: https://lore.kernel.org/r/f9284873c2993a9952d9fe4f8dd5e89f20daab75.1646388139.git.zong.li@sifive.com Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/sifive-fu540-prci.h | 8 ++++---- include/dt-bindings/clock/sifive-fu740-prci.h | 18 +++++++++--------- 2 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/clock/sifive-fu540-prci.h b/include/dt-bindings/clock/sifive-fu540-prci.h index 3b21d0522c91..5af372e8385f 100644 --- a/include/dt-bindings/clock/sifive-fu540-prci.h +++ b/include/dt-bindings/clock/sifive-fu540-prci.h @@ -10,9 +10,9 @@ /* Clock indexes for use by Device Tree data and the PRCI driver */ -#define PRCI_CLK_COREPLL 0 -#define PRCI_CLK_DDRPLL 1 -#define PRCI_CLK_GEMGXLPLL 2 -#define PRCI_CLK_TLCLK 3 +#define FU540_PRCI_CLK_COREPLL 0 +#define FU540_PRCI_CLK_DDRPLL 1 +#define FU540_PRCI_CLK_GEMGXLPLL 2 +#define FU540_PRCI_CLK_TLCLK 3 #endif diff --git a/include/dt-bindings/clock/sifive-fu740-prci.h b/include/dt-bindings/clock/sifive-fu740-prci.h index 7899b7fee7db..672bdadbf6c0 100644 --- a/include/dt-bindings/clock/sifive-fu740-prci.h +++ b/include/dt-bindings/clock/sifive-fu740-prci.h @@ -11,14 +11,14 @@ /* Clock indexes for use by Device Tree data and the PRCI driver */ -#define PRCI_CLK_COREPLL 0 -#define PRCI_CLK_DDRPLL 1 -#define PRCI_CLK_GEMGXLPLL 2 -#define PRCI_CLK_DVFSCOREPLL 3 -#define PRCI_CLK_HFPCLKPLL 4 -#define PRCI_CLK_CLTXPLL 5 -#define PRCI_CLK_TLCLK 6 -#define PRCI_CLK_PCLK 7 -#define PRCI_CLK_PCIE_AUX 8 +#define FU740_PRCI_CLK_COREPLL 0 +#define FU740_PRCI_CLK_DDRPLL 1 +#define FU740_PRCI_CLK_GEMGXLPLL 2 +#define FU740_PRCI_CLK_DVFSCOREPLL 3 +#define FU740_PRCI_CLK_HFPCLKPLL 4 +#define FU740_PRCI_CLK_CLTXPLL 5 +#define FU740_PRCI_CLK_TLCLK 6 +#define FU740_PRCI_CLK_PCLK 7 +#define FU740_PRCI_CLK_PCIE_AUX 8 #endif /* __DT_BINDINGS_CLOCK_SIFIVE_FU740_PRCI_H */ -- cgit v1.2.3 From b0f212633b31ddca99c76aa38f812fe492e8410a Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Fri, 11 Mar 2022 11:34:28 +0100 Subject: xen/grant-table: remove gnttab_*transfer*() functions All grant table operations related to the "transfer" functionality are unused currently. There have been users in the old days of the "Xen-o-Linux" kernel, but those didn't make it upstream. So remove the "transfer" related functions. Signed-off-by: Juergen Gross Link: https://lore.kernel.org/r/20220311103429.12845-2-jgross@suse.com Reviewed-by: Boris Ostrovsky Signed-off-by: Boris Ostrovsky --- include/xen/grant_table.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index c9fea9389ebe..9f9b1a297f0d 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -125,11 +125,6 @@ void gnttab_end_foreign_access(grant_ref_t ref, int readonly, */ int gnttab_try_end_foreign_access(grant_ref_t ref); -int gnttab_grant_foreign_transfer(domid_t domid, unsigned long pfn); - -unsigned long gnttab_end_foreign_transfer_ref(grant_ref_t ref); -unsigned long gnttab_end_foreign_transfer(grant_ref_t ref); - /* * operations on reserved batches of grant references */ @@ -162,9 +157,6 @@ static inline void gnttab_page_grant_foreign_access_ref_one( readonly); } -void gnttab_grant_foreign_transfer_ref(grant_ref_t, domid_t domid, - unsigned long pfn); - static inline void gnttab_set_map_op(struct gnttab_map_grant_ref *map, phys_addr_t addr, uint32_t flags, grant_ref_t ref, domid_t domid) -- cgit v1.2.3 From c94b731da21f10086a9e52d63c21c730e3f6c939 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Fri, 11 Mar 2022 11:34:29 +0100 Subject: xen/grant-table: remove readonly parameter from functions The gnttab_end_foreign_access() family of functions is taking a "readonly" parameter, which isn't used. Remove it from the function parameters. Signed-off-by: Juergen Gross Link: https://lore.kernel.org/r/20220311103429.12845-3-jgross@suse.com Reviewed-by: Jan Beulich Acked-by: Christian Schoenebeck Signed-off-by: Boris Ostrovsky --- include/xen/grant_table.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index 9f9b1a297f0d..dfd5bf31cfb9 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -97,7 +97,7 @@ int gnttab_grant_foreign_access(domid_t domid, unsigned long frame, * longer in use. Return 1 if the grant entry was freed, 0 if it is still in * use. */ -int gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly); +int gnttab_end_foreign_access_ref(grant_ref_t ref); /* * Eventually end access through the given grant reference, and once that @@ -114,8 +114,7 @@ int gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly); * gnttab_end_foreign_access() are done via alloc_pages_exact() (and freeing * via free_pages_exact()) in order to avoid high order pages. */ -void gnttab_end_foreign_access(grant_ref_t ref, int readonly, - unsigned long page); +void gnttab_end_foreign_access(grant_ref_t ref, unsigned long page); /* * End access through the given grant reference, iff the grant entry is -- cgit v1.2.3 From 40867d74c374b235e14d839f3a77f26684feefe5 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 14 Mar 2022 14:45:51 -0600 Subject: net: Add l3mdev index to flow struct and avoid oif reset for port devices The fundamental premise of VRF and l3mdev core code is binding a socket to a device (l3mdev or netdev with an L3 domain) to indicate L3 scope. Legacy code resets flowi_oif to the l3mdev losing any original port device binding. Ben (among others) has demonstrated use cases where the original port device binding is important and needs to be retained. This patch handles that by adding a new entry to the common flow struct that can indicate the l3mdev index for later rule and table matching avoiding the need to reset flowi_oif. In addition to allowing more use cases that require port device binds, this patch brings a few datapath simplications: 1. l3mdev_fib_rule_match is only called when walking fib rules and always after l3mdev_update_flow. That allows an optimization to bail early for non-VRF type uses cases when flowi_l3mdev is not set. Also, only that index needs to be checked for the FIB table id. 2. l3mdev_update_flow can be called with flowi_oif set to a l3mdev (e.g., VRF) device. By resetting flowi_oif only for this case the FLOWI_FLAG_SKIP_NH_OIF flag is not longer needed and can be removed, removing several checks in the datapath. The flowi_iif path can be simplified to only be called if the it is not loopback (loopback can not be assigned to an L3 domain) and the l3mdev index is not already set. 3. Avoid another device lookup in the output path when the fib lookup returns a reject failure. Note: 2 functional tests for local traffic with reject fib rules are updated to reflect the new direct failure at FIB lookup time for ping rather than the failure on packet path. The current code fails like this: HINT: Fails since address on vrf device is out of device scope COMMAND: ip netns exec ns-A ping -c1 -w1 -I eth1 172.16.3.1 ping: Warning: source address might be selected on device other than: eth1 PING 172.16.3.1 (172.16.3.1) from 172.16.3.1 eth1: 56(84) bytes of data. --- 172.16.3.1 ping statistics --- 1 packets transmitted, 0 received, 100% packet loss, time 0ms where the test now directly fails: HINT: Fails since address on vrf device is out of device scope COMMAND: ip netns exec ns-A ping -c1 -w1 -I eth1 172.16.3.1 ping: connect: No route to host Signed-off-by: David Ahern Tested-by: Ben Greear Link: https://lore.kernel.org/r/20220314204551.16369-1-dsahern@kernel.org Signed-off-by: Jakub Kicinski --- include/net/flow.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/flow.h b/include/net/flow.h index 58beb16a49b8..987bd511d652 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -29,6 +29,7 @@ struct flowi_tunnel { struct flowi_common { int flowic_oif; int flowic_iif; + int flowic_l3mdev; __u32 flowic_mark; __u8 flowic_tos; __u8 flowic_scope; @@ -36,7 +37,6 @@ struct flowi_common { __u8 flowic_flags; #define FLOWI_FLAG_ANYSRC 0x01 #define FLOWI_FLAG_KNOWN_NH 0x02 -#define FLOWI_FLAG_SKIP_NH_OIF 0x04 __u32 flowic_secid; kuid_t flowic_uid; struct flowi_tunnel flowic_tun_key; @@ -70,6 +70,7 @@ struct flowi4 { struct flowi_common __fl_common; #define flowi4_oif __fl_common.flowic_oif #define flowi4_iif __fl_common.flowic_iif +#define flowi4_l3mdev __fl_common.flowic_l3mdev #define flowi4_mark __fl_common.flowic_mark #define flowi4_tos __fl_common.flowic_tos #define flowi4_scope __fl_common.flowic_scope @@ -102,6 +103,7 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif, { fl4->flowi4_oif = oif; fl4->flowi4_iif = LOOPBACK_IFINDEX; + fl4->flowi4_l3mdev = 0; fl4->flowi4_mark = mark; fl4->flowi4_tos = tos; fl4->flowi4_scope = scope; @@ -132,6 +134,7 @@ struct flowi6 { struct flowi_common __fl_common; #define flowi6_oif __fl_common.flowic_oif #define flowi6_iif __fl_common.flowic_iif +#define flowi6_l3mdev __fl_common.flowic_l3mdev #define flowi6_mark __fl_common.flowic_mark #define flowi6_scope __fl_common.flowic_scope #define flowi6_proto __fl_common.flowic_proto @@ -177,6 +180,7 @@ struct flowi { } u; #define flowi_oif u.__fl_common.flowic_oif #define flowi_iif u.__fl_common.flowic_iif +#define flowi_l3mdev u.__fl_common.flowic_l3mdev #define flowi_mark u.__fl_common.flowic_mark #define flowi_tos u.__fl_common.flowic_tos #define flowi_scope u.__fl_common.flowic_scope -- cgit v1.2.3 From 0492d857636e1c52cd71594a723c4b26a7b31978 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 16 Mar 2022 11:19:43 +0100 Subject: netfilter: flowtable: Fix QinQ and pppoe support for inet table nf_flow_offload_inet_hook() does not check for 802.1q and PPPoE. Fetch inner ethertype from these encapsulation protocols. Fixes: 72efd585f714 ("netfilter: flowtable: add pppoe support") Fixes: 4cd91f7c290f ("netfilter: flowtable: add vlan support") Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_flow_table.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index bd59e950f4d6..64daafd1fc41 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -10,6 +10,8 @@ #include #include #include +#include +#include struct nf_flowtable; struct nf_flow_rule; @@ -317,4 +319,20 @@ int nf_flow_rule_route_ipv6(struct net *net, const struct flow_offload *flow, int nf_flow_table_offload_init(void); void nf_flow_table_offload_exit(void); +static inline __be16 nf_flow_pppoe_proto(const struct sk_buff *skb) +{ + __be16 proto; + + proto = *((__be16 *)(skb_mac_header(skb) + ETH_HLEN + + sizeof(struct pppoe_hdr))); + switch (proto) { + case htons(PPP_IP): + return htons(ETH_P_IP); + case htons(PPP_IPV6): + return htons(ETH_P_IPV6); + } + + return 0; +} + #endif /* _NF_FLOW_TABLE_H */ -- cgit v1.2.3 From 052ebf1fbb1cab86b145a68d80219c8c57321cbd Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Wed, 16 Mar 2022 02:52:04 -0700 Subject: io_uring: make tracing format consistent Make the tracing formatting for user_data and flags consistent. Having consistent formatting allows one for example to grep for a specific user_data/flags and be able to trace a single sqe through easily. Change user_data to 0x%llx and flags to 0x%x everywhere. The '0x' is useful to disambiguate for example "user_data 100". Additionally remove the '=' for flags in io_uring_req_failed, again for consistency. Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220316095204.2191498-1-dylany@fb.com Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 18d4341c581c..cddf5b6fbeb4 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -44,7 +44,7 @@ TRACE_EVENT(io_uring_create, __entry->flags = flags; ), - TP_printk("ring %p, fd %d sq size %d, cq size %d, flags %d", + TP_printk("ring %p, fd %d sq size %d, cq size %d, flags 0x%x", __entry->ctx, __entry->fd, __entry->sq_entries, __entry->cq_entries, __entry->flags) ); @@ -125,7 +125,7 @@ TRACE_EVENT(io_uring_file_get, __entry->fd = fd; ), - TP_printk("ring %p, req %p, user_data %llu, fd %d", + TP_printk("ring %p, req %p, user_data 0x%llx, fd %d", __entry->ctx, __entry->req, __entry->user_data, __entry->fd) ); @@ -169,7 +169,7 @@ TRACE_EVENT(io_uring_queue_async_work, __entry->rw = rw; ), - TP_printk("ring %p, request %p, user_data %llu, opcode %d, flags %d, %s queue, work %p", + TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d, flags 0x%x, %s queue, work %p", __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, __entry->flags, __entry->rw ? "hashed" : "normal", __entry->work) ); @@ -205,7 +205,7 @@ TRACE_EVENT(io_uring_defer, __entry->opcode = opcode; ), - TP_printk("ring %p, request %p, user_data %llu, opcode %d", + TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d", __entry->ctx, __entry->req, __entry->data, __entry->opcode) ); @@ -305,7 +305,7 @@ TRACE_EVENT(io_uring_fail_link, __entry->link = link; ), - TP_printk("ring %p, request %p, user_data %llu, opcode %d, link %p", + TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d, link %p", __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, __entry->link) ); @@ -342,9 +342,9 @@ TRACE_EVENT(io_uring_complete, __entry->cflags = cflags; ), - TP_printk("ring %p, req %p, user_data 0x%llx, result %d, cflags %x", + TP_printk("ring %p, req %p, user_data 0x%llx, result %d, cflags 0x%x", __entry->ctx, __entry->req, - (unsigned long long)__entry->user_data, + __entry->user_data, __entry->res, __entry->cflags) ); @@ -389,7 +389,7 @@ TRACE_EVENT(io_uring_submit_sqe, __entry->sq_thread = sq_thread; ), - TP_printk("ring %p, req %p, user_data %llu, opcode %d, flags %u, " + TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, flags 0x%x, " "non block %d, sq_thread %d", __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, __entry->flags, __entry->force_nonblock, __entry->sq_thread) @@ -433,7 +433,7 @@ TRACE_EVENT(io_uring_poll_arm, __entry->events = events; ), - TP_printk("ring %p, req %p, user_data %llu, opcode %d, mask 0x%x, events 0x%x", + TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, mask 0x%x, events 0x%x", __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, __entry->mask, __entry->events) ); @@ -470,7 +470,7 @@ TRACE_EVENT(io_uring_task_add, __entry->mask = mask; ), - TP_printk("ring %p, req %p, user_data %llu, opcode %d, mask %x", + TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, mask %x", __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, __entry->mask) ); @@ -529,8 +529,8 @@ TRACE_EVENT(io_uring_req_failed, __entry->error = error; ), - TP_printk("ring %p, req %p, user_data %llu, " - "op %d, flags=0x%x, prio=%d, off=%llu, addr=%llu, " + TP_printk("ring %p, req %p, user_data 0x%llx, " + "op %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, " "len=%u, rw_flags=0x%x, buf_index=%d, " "personality=%d, file_index=%d, pad=0x%llx/%llx, error=%d", __entry->ctx, __entry->req, __entry->user_data, -- cgit v1.2.3 From e621900ad28b748e058b81d6078a5d5eb37b3973 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 9 Feb 2022 20:22:12 +0000 Subject: fs: Convert __set_page_dirty_buffers to block_dirty_folio Convert all callers; mostly this is just changing the aops to point at it, but a few implementations need a little more work. Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Damien Le Moal Acked-by: Damien Le Moal Tested-by: Mike Marshall # orangefs Tested-by: David Howells # afs --- include/linux/buffer_head.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 9ee9d003d736..bcb4fe9b8575 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -397,7 +397,7 @@ __bread(struct block_device *bdev, sector_t block, unsigned size) return __bread_gfp(bdev, block, size, __GFP_MOVABLE); } -extern int __set_page_dirty_buffers(struct page *page); +bool block_dirty_folio(struct address_space *mapping, struct folio *folio); #else /* CONFIG_BLOCK */ -- cgit v1.2.3 From 46de8b979492e1377947700ecb1e3169088668b2 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 9 Feb 2022 20:22:13 +0000 Subject: fs: Convert __set_page_dirty_no_writeback to noop_dirty_folio This is a mechanical change. Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Damien Le Moal Acked-by: Damien Le Moal Tested-by: Mike Marshall # orangefs Tested-by: David Howells # afs --- include/linux/pagemap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 6a9617e9c6bc..ab85d2856a37 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -919,7 +919,7 @@ static inline int __must_check write_one_page(struct page *page) } int __set_page_dirty_nobuffers(struct page *page); -int __set_page_dirty_no_writeback(struct page *page); +bool noop_dirty_folio(struct address_space *mapping, struct folio *folio); void page_endio(struct page *page, bool is_write, int err); -- cgit v1.2.3 From 3a3bae50af5d73fab5da20484029de77ca67bb2e Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 9 Feb 2022 20:22:15 +0000 Subject: fs: Remove aops ->set_page_dirty With all implementations converted to ->dirty_folio, we can stop calling this fallback method and remove it entirely. Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Damien Le Moal Acked-by: Damien Le Moal Tested-by: Mike Marshall # orangefs Tested-by: David Howells # afs --- include/linux/fs.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index c3d5db8851ae..b472d78f00b0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -367,8 +367,7 @@ struct address_space_operations { /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); - /* Set a page dirty. Return true if this dirtied it */ - int (*set_page_dirty)(struct page *page); + /* Mark a folio dirty. Return true if this dirtied it */ bool (*dirty_folio)(struct address_space *, struct folio *); /* -- cgit v1.2.3 From f6c46b1d62f8ffbf2cf6eb43ab0d277bd3f7e948 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Fri, 11 Mar 2022 19:20:17 +0000 Subject: PM: hibernate: Honour ACPI hardware signature by default for virtual guests The ACPI specification says that OSPM should refuse to restore from hibernate if the hardware signature changes, and should boot from scratch. However, real BIOSes often vary the hardware signature in cases where we *do* want to resume from hibernate, so Linux doesn't follow the spec by default. However, in a virtual environment there's no reason for the VMM to vary the hardware signature *unless* it wants to trigger a clean reboot as defined by the ACPI spec. So enable the check by default if a hypervisor is detected. Signed-off-by: David Woodhouse Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 6274758648e3..766dbcb82df1 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -526,7 +526,7 @@ acpi_status acpi_release_memory(acpi_handle handle, struct resource *res, int acpi_resources_are_enforced(void); #ifdef CONFIG_HIBERNATION -void __init acpi_check_s4_hw_signature(int check); +extern int acpi_check_s4_hw_signature; #endif #ifdef CONFIG_PM_SLEEP -- cgit v1.2.3 From 2cb7b4890d6e7f20560dc251e7f8d3cc68b0d554 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 14 Mar 2022 23:00:04 -0700 Subject: devlink: expose instance locking and add locked port registering It should be familiar and beneficial to expose devlink instance lock to the drivers. This way drivers can block devlink from calling them during critical sections without breakneck locking. Add port helpers, port splitting callbacks will be the first target. Use 'devl_' prefix for "explicitly locked" API. Initial RFC used '__devlink' but that's too much typing. devl_lock_is_held() is not defined without lockdep, which is the same behavior as lockdep_is_held() itself. Reviewed-by: Leon Romanovsky Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 8d5349d2fb68..9de0d091aee9 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1479,6 +1479,17 @@ void *devlink_priv(struct devlink *devlink); struct devlink *priv_to_devlink(void *priv); struct device *devlink_to_dev(const struct devlink *devlink); +/* Devlink instance explicit locking */ +void devl_lock(struct devlink *devlink); +void devl_unlock(struct devlink *devlink); +void devl_assert_locked(struct devlink *devlink); +bool devl_lock_is_held(struct devlink *devlink); + +int devl_port_register(struct devlink *devlink, + struct devlink_port *devlink_port, + unsigned int port_index); +void devl_port_unregister(struct devlink_port *devlink_port); + struct ib_device; struct net *devlink_net(const struct devlink *devlink); -- cgit v1.2.3 From 706217c1ceb516c96283a1557a31fe003d0c8052 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 14 Mar 2022 23:00:09 -0700 Subject: devlink: pass devlink_port to port_split / port_unsplit callbacks Now that devlink ports are protected by the instance lock it seems natural to pass devlink_port as an argument to the port_split / port_unsplit callbacks. This should save the drivers from doing a lookup. In theory drivers may have supported unsplitting ports which were not registered prior to this change. Reviewed-by: Ido Schimmel Tested-by: Ido Schimmel Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 9de0d091aee9..fd89a17adea1 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1197,9 +1197,9 @@ struct devlink_ops { struct netlink_ext_ack *extack); int (*port_type_set)(struct devlink_port *devlink_port, enum devlink_port_type port_type); - int (*port_split)(struct devlink *devlink, unsigned int port_index, + int (*port_split)(struct devlink *devlink, struct devlink_port *port, unsigned int count, struct netlink_ext_ack *extack); - int (*port_unsplit)(struct devlink *devlink, unsigned int port_index, + int (*port_unsplit)(struct devlink *devlink, struct devlink_port *port, struct netlink_ext_ack *extack); int (*sb_pool_get)(struct devlink *devlink, unsigned int sb_index, u16 pool_index, -- cgit v1.2.3 From d2a3b7c5becc3992f8e7d2b9bf5eacceeedb9a48 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Wed, 9 Mar 2022 20:33:20 +0800 Subject: bpf: Fix net.core.bpf_jit_harden race It is the bpf_jit_harden counterpart to commit 60b58afc96c9 ("bpf: fix net.core.bpf_jit_enable race"). bpf_jit_harden will be tested twice for each subprog if there are subprogs in bpf program and constant blinding may increase the length of program, so when running "./test_progs -t subprogs" and toggling bpf_jit_harden between 0 and 2, jit_subprogs may fail because constant blinding increases the length of subprog instructions during extra passs. So cache the value of bpf_jit_blinding_enabled() during program allocation, and use the cached value during constant blinding, subprog JITing and args tracking of tail call. Signed-off-by: Hou Tao Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220309123321.2400262-4-houtao1@huawei.com --- include/linux/filter.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 05ed9bd31b45..ed0c0ff42ad5 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -566,6 +566,7 @@ struct bpf_prog { gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ dst_needed:1, /* Do we need dst entry? */ + blinding_requested:1, /* needs constant blinding */ blinded:1, /* Was blinded */ is_func:1, /* program is a bpf function */ kprobe_override:1, /* Do we override a kprobe? */ -- cgit v1.2.3 From ab95465cde2337108252cdf01f064abdc1a67f6c Mon Sep 17 00:00:00 2001 From: Maor Dickman Date: Tue, 15 Mar 2022 13:02:09 +0200 Subject: net/sched: add vlan push_eth and pop_eth action to the hardware IR Add vlan push_eth and pop_eth action to the hardware intermediate representation model which would subsequently allow it to be used by drivers for offload. Signed-off-by: Maor Dickman Reviewed-by: Roi Dayan Signed-off-by: Jakub Kicinski --- include/net/flow_offload.h | 6 ++++++ include/net/tc_act/tc_vlan.h | 10 ++++++++++ 2 files changed, 16 insertions(+) (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 92267d23083e..021778a7e1af 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -150,6 +150,8 @@ enum flow_action_id { FLOW_ACTION_PPPOE_PUSH, FLOW_ACTION_JUMP, FLOW_ACTION_PIPE, + FLOW_ACTION_VLAN_PUSH_ETH, + FLOW_ACTION_VLAN_POP_ETH, NUM_FLOW_ACTIONS, }; @@ -211,6 +213,10 @@ struct flow_action_entry { __be16 proto; u8 prio; } vlan; + struct { /* FLOW_ACTION_VLAN_PUSH_ETH */ + unsigned char dst[ETH_ALEN]; + unsigned char src[ETH_ALEN]; + } vlan_push_eth; struct { /* FLOW_ACTION_MANGLE */ /* FLOW_ACTION_ADD */ enum flow_action_mangle_base htype; diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h index f94b8bc26f9e..a97600f742de 100644 --- a/include/net/tc_act/tc_vlan.h +++ b/include/net/tc_act/tc_vlan.h @@ -78,4 +78,14 @@ static inline u8 tcf_vlan_push_prio(const struct tc_action *a) return tcfv_push_prio; } + +static inline void tcf_vlan_push_eth(unsigned char *src, unsigned char *dest, + const struct tc_action *a) +{ + rcu_read_lock(); + memcpy(dest, rcu_dereference(to_vlan(a)->vlan_p)->tcfv_push_dst, ETH_ALEN); + memcpy(dest, rcu_dereference(to_vlan(a)->vlan_p)->tcfv_push_src, ETH_ALEN); + rcu_read_unlock(); +} + #endif /* __NET_TC_VLAN_H */ -- cgit v1.2.3 From 9b13a3fcd35fc24045d2fd0f0e13ddd8d7985b4b Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 17 Mar 2022 09:18:26 +0100 Subject: drm/format-helper: Rename drm_fb_xrgb8888_to_mono_reversed() There is no "reversed" handling in drm_fb_xrgb8888_to_mono_reversed(): the function just converts from color to grayscale, and reduces the number of grayscale levels from 256 to 2 (i.e. brightness 0-127 is mapped to 0, 128-255 to 1). All "reversed" handling is done in the repaper driver, where this function originated. Hence make this clear by renaming drm_fb_xrgb8888_to_mono_reversed() to drm_fb_xrgb8888_to_mono(), and documenting the black/white pixel mapping. Fixes: bcf8b616deb87941 ("drm/format-helper: Add drm_fb_xrgb8888_to_mono_reversed()") Signed-off-by: Geert Uytterhoeven Acked-by: Javier Martinez Canillas Reviewed-by: Andy Shevchenko Signed-off-by: Javier Martinez Canillas Link: https://patchwork.freedesktop.org/patch/msgid/20220317081830.1211400-2-geert@linux-m68k.org --- include/drm/drm_format_helper.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/drm/drm_format_helper.h b/include/drm/drm_format_helper.h index 0b0937c0b2f6..55145eca0782 100644 --- a/include/drm/drm_format_helper.h +++ b/include/drm/drm_format_helper.h @@ -43,8 +43,7 @@ int drm_fb_blit_toio(void __iomem *dst, unsigned int dst_pitch, uint32_t dst_for const void *vmap, const struct drm_framebuffer *fb, const struct drm_rect *rect); -void drm_fb_xrgb8888_to_mono_reversed(void *dst, unsigned int dst_pitch, const void *src, - const struct drm_framebuffer *fb, - const struct drm_rect *clip); +void drm_fb_xrgb8888_to_mono(void *dst, unsigned int dst_pitch, const void *src, + const struct drm_framebuffer *fb, const struct drm_rect *clip); #endif /* __LINUX_DRM_FORMAT_HELPER_H */ -- cgit v1.2.3 From 435fe1c0c1f74b682dba85641406abf4337aade6 Mon Sep 17 00:00:00 2001 From: Eyal Birger Date: Wed, 16 Mar 2022 08:15:57 +0200 Subject: net: geneve: support IPv4/IPv6 as inner protocol This patch adds support for encapsulating IPv4/IPv6 within GENEVE. In order to use this, a new IFLA_GENEVE_INNER_PROTO_INHERIT flag needs to be provided at device creation. This property cannot be changed for the time being. In case IP traffic is received on a non-tun device the drop count is increased. Signed-off-by: Eyal Birger Link: https://lore.kernel.org/r/20220316061557.431872-1-eyal.birger@gmail.com Signed-off-by: Paolo Abeni --- include/uapi/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index bd24c7dc10a2..cc284c048e69 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -842,6 +842,7 @@ enum { IFLA_GENEVE_LABEL, IFLA_GENEVE_TTL_INHERIT, IFLA_GENEVE_DF, + IFLA_GENEVE_INNER_PROTO_INHERIT, __IFLA_GENEVE_MAX }; #define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) -- cgit v1.2.3 From c42fa24b44751c62c86e98430ef915c0609a2ab8 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 16 Mar 2022 13:39:03 +0100 Subject: ACPI: bus: Avoid using CPPC if not supported by firmware If the platform firmware indicates that it does not support CPPC by clearing the OSC_SB_CPC_SUPPORT and OSC_SB_CPCV2_SUPPORT bits in the platform _OSC capabilities mask, avoid attempting to evaluate _CPC which may fail in that case. Because the OSC_SB_CPC_SUPPORT and OSC_SB_CPCV2_SUPPORT bits are only added to the supported platform capabilities mask on x86, when X86_FEATURE_HWP is supported, allow _CPC to be evaluated regardless in the other cases. Link: https://lore.kernel.org/linux-acpi/CAJZ5v0i=ecAksq0TV+iLVObm-=fUfdqPABzzkgm9K6KxO1ZCcg@mail.gmail.com Signed-off-by: Rafael J. Wysocki Tested-by: Mario Limonciello Acked-by: Huang Rui Reviewed-by: Mika Westerberg --- include/linux/acpi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 6274758648e3..690b0533104a 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -580,6 +580,7 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); extern bool osc_sb_apei_support_acked; extern bool osc_pc_lpi_support_confirmed; extern bool osc_sb_native_usb4_support_confirmed; +extern bool osc_sb_cppc_not_supported; /* USB4 Capabilities */ #define OSC_USB_USB3_TUNNELING 0x00000001 -- cgit v1.2.3 From 109d101e273d81ba079306308e9512a8b1673ca9 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Fri, 11 Mar 2022 12:06:39 +0200 Subject: drm/i915: include uapi/drm/i915_drm.h directly where needed MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Remove the uapi/drm/i915_drm.h include from drm/i915_drm.h, and stop being a proxy for uapi/drm/i915_drm.h. Include uapi/drm/i915_drm.h and drm/i915_drm.h only where needed. Signed-off-by: Jani Nikula Reviewed-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20220311100639.114685-2-jani.nikula@intel.com --- include/drm/i915_drm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h index afbf3ef5643e..7adce327c1c2 100644 --- a/include/drm/i915_drm.h +++ b/include/drm/i915_drm.h @@ -26,7 +26,7 @@ #ifndef _I915_DRM_H_ #define _I915_DRM_H_ -#include +#include /* For use by IPS driver */ unsigned long i915_read_mch_val(void); -- cgit v1.2.3 From 20e1d6402a71dba7ad2b81f332a3c14c7d3b939b Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Thu, 17 Mar 2022 09:14:42 -0500 Subject: ACPI / x86: Add support for LPS0 callback handler Currenty the latest thing run during a suspend to idle attempt is the LPS0 `prepare_late` callback and the earliest thing is the `resume_early` callback. There is a desire for the `amd-pmc` driver to suspend later in the suspend process (ideally the very last thing), so create a callback that it or any other driver can hook into to do this. Signed-off-by: Mario Limonciello Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20220317141445.6498-1-mario.limonciello@amd.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- include/linux/acpi.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 6274758648e3..47c16cdc8e0e 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1023,7 +1023,15 @@ void acpi_os_set_prepare_extended_sleep(int (*func)(u8 sleep_state, acpi_status acpi_os_prepare_extended_sleep(u8 sleep_state, u32 val_a, u32 val_b); - +#ifdef CONFIG_X86 +struct acpi_s2idle_dev_ops { + struct list_head list_node; + void (*prepare)(void); + void (*restore)(void); +}; +int acpi_register_lps0_dev(struct acpi_s2idle_dev_ops *arg); +void acpi_unregister_lps0_dev(struct acpi_s2idle_dev_ops *arg); +#endif /* CONFIG_X86 */ #ifndef CONFIG_IA64 void arch_reserve_mem_area(acpi_physical_address addr, size_t size); #else -- cgit v1.2.3 From 4206fe40b2c01fb5988980cff6ea958b16578026 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Tue, 27 Apr 2021 16:30:32 +0300 Subject: net/mlx5: Remove unused exported contiguous coherent buffer allocation API All WQ types moved to using the fragmented allocation API for coherent memory. Contiguous API is not used anymore. Remove it, reduce the number of exported functions. Signed-off-by: Tariq Toukan Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 00a914b0716e..a386aec1eb65 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1009,9 +1009,6 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev); void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health); void mlx5_drain_health_wq(struct mlx5_core_dev *dev); void mlx5_trigger_health_work(struct mlx5_core_dev *dev); -int mlx5_buf_alloc(struct mlx5_core_dev *dev, - int size, struct mlx5_frag_buf *buf); -void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf); int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size, struct mlx5_frag_buf *buf, int node); void mlx5_frag_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf); -- cgit v1.2.3 From 770c9a3a01af178a90368a78c75eb91707c7233c Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Thu, 20 May 2021 15:34:57 +0300 Subject: net/mlx5: Remove unused fill page array API function mlx5_fill_page_array API function is not used. Remove it, reduce the number of exported functions. Signed-off-by: Tariq Toukan Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a386aec1eb65..96cd740d94a3 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1036,7 +1036,6 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev); void mlx5_register_debugfs(void); void mlx5_unregister_debugfs(void); -void mlx5_fill_page_array(struct mlx5_frag_buf *buf, __be64 *pas); void mlx5_fill_page_frag_array_perm(struct mlx5_frag_buf *buf, __be64 *pas, u8 perm); void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas); int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn); -- cgit v1.2.3 From 5142239a22219921a7863cf00c9ab853c00689d8 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 11 Mar 2022 10:14:18 +0100 Subject: net: veth: Account total xdp_frame len running ndo_xdp_xmit Even if this is a theoretical issue since it is not possible to perform XDP_REDIRECT on a non-linear xdp_frame, veth driver does not account paged area in ndo_xdp_xmit function pointer. Introduce xdp_get_frame_len utility routine to get the xdp_frame full length and account total frame size running XDP_REDIRECT of a non-linear xdp frame into a veth device. Signed-off-by: Lorenzo Bianconi Signed-off-by: Daniel Borkmann Acked-by: Toke Hoiland-Jorgensen Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/54f9fd3bb65d190daf2c0bbae2f852ff16cfbaa0.1646989407.git.lorenzo@kernel.org --- include/net/xdp.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/net/xdp.h b/include/net/xdp.h index b7721c3e4d1f..04c852c7a77f 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -343,6 +343,20 @@ out: __xdp_release_frame(xdpf->data, mem); } +static __always_inline unsigned int xdp_get_frame_len(struct xdp_frame *xdpf) +{ + struct skb_shared_info *sinfo; + unsigned int len = xdpf->len; + + if (likely(!xdp_frame_has_frags(xdpf))) + goto out; + + sinfo = xdp_get_shared_info_from_frame(xdpf); + len += sinfo->xdp_frags_size; +out: + return len; +} + int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index, unsigned int napi_id, u32 frag_size); -- cgit v1.2.3 From ec7328b59176227216c461601c6bd0e922232a9b Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Wed, 16 Mar 2022 16:08:43 +0100 Subject: net: bridge: mst: Multiple Spanning Tree (MST) mode Allow the user to switch from the current per-VLAN STP mode to an MST mode. Up to this point, per-VLAN STP states where always isolated from each other. This is in contrast to the MSTP standard (802.1Q-2018, Clause 13.5), where VLANs are grouped into MST instances (MSTIs), and the state is managed on a per-MSTI level, rather that at the per-VLAN level. Perhaps due to the prevalence of the standard, many switching ASICs are built after the same model. Therefore, add a corresponding MST mode to the bridge, which we can later add offloading support for in a straight-forward way. For now, all VLANs are fixed to MSTI 0, also called the Common Spanning Tree (CST). That is, all VLANs will follow the port-global state. Upcoming changes will make this actually useful by allowing VLANs to be mapped to arbitrary MSTIs and allow individual MSTI states to be changed. Signed-off-by: Tobias Waldekranz Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_bridge.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 2711c3522010..30a242195ced 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -759,6 +759,7 @@ struct br_mcast_stats { enum br_boolopt_id { BR_BOOLOPT_NO_LL_LEARN, BR_BOOLOPT_MCAST_VLAN_SNOOPING, + BR_BOOLOPT_MST_ENABLE, BR_BOOLOPT_MAX }; -- cgit v1.2.3 From 8c678d60562f3e5f6d0a5f5465e27930ffedb8ca Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Wed, 16 Mar 2022 16:08:44 +0100 Subject: net: bridge: mst: Allow changing a VLAN's MSTI Allow a VLAN to move out of the CST (MSTI 0), to an independent tree. The user manages the VID to MSTI mappings via a global VLAN setting. The proposed iproute2 interface would be: bridge vlan global set dev br0 vid msti Changing the state in non-zero MSTIs is still not supported, but will be addressed in upcoming changes. Signed-off-by: Tobias Waldekranz Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_bridge.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 30a242195ced..f60244b747ae 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -564,6 +564,7 @@ enum { BRIDGE_VLANDB_GOPTS_MCAST_QUERIER, BRIDGE_VLANDB_GOPTS_MCAST_ROUTER_PORTS, BRIDGE_VLANDB_GOPTS_MCAST_QUERIER_STATE, + BRIDGE_VLANDB_GOPTS_MSTI, __BRIDGE_VLANDB_GOPTS_MAX }; #define BRIDGE_VLANDB_GOPTS_MAX (__BRIDGE_VLANDB_GOPTS_MAX - 1) -- cgit v1.2.3 From 122c29486e1ff78033c45d0d31c710e7dc8945a5 Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Wed, 16 Mar 2022 16:08:45 +0100 Subject: net: bridge: mst: Support setting and reporting MST port states Make it possible to change the port state in a given MSTI by extending the bridge port netlink interface (RTM_SETLINK on PF_BRIDGE).The proposed iproute2 interface would be: bridge mst set dev msti state Current states in all applicable MSTIs can also be dumped via a corresponding RTM_GETLINK. The proposed iproute interface looks like this: $ bridge mst port msti vb1 0 state forwarding 100 state disabled vb2 0 state forwarding 100 state forwarding The preexisting per-VLAN states are still valid in the MST mode (although they are read-only), and can be queried as usual if one is interested in knowing a particular VLAN's state without having to care about the VID to MSTI mapping (in this example VLAN 20 and 30 are bound to MSTI 100): $ bridge -d vlan port vlan-id vb1 10 state forwarding mcast_router 1 20 state disabled mcast_router 1 30 state disabled mcast_router 1 40 state forwarding mcast_router 1 vb2 10 state forwarding mcast_router 1 20 state forwarding mcast_router 1 30 state forwarding mcast_router 1 40 state forwarding mcast_router 1 Signed-off-by: Tobias Waldekranz Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_bridge.h | 16 ++++++++++++++++ include/uapi/linux/rtnetlink.h | 1 + 2 files changed, 17 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index f60244b747ae..a86a7e7b811f 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -122,6 +122,7 @@ enum { IFLA_BRIDGE_VLAN_TUNNEL_INFO, IFLA_BRIDGE_MRP, IFLA_BRIDGE_CFM, + IFLA_BRIDGE_MST, __IFLA_BRIDGE_MAX, }; #define IFLA_BRIDGE_MAX (__IFLA_BRIDGE_MAX - 1) @@ -453,6 +454,21 @@ enum { #define IFLA_BRIDGE_CFM_CC_PEER_STATUS_MAX (__IFLA_BRIDGE_CFM_CC_PEER_STATUS_MAX - 1) +enum { + IFLA_BRIDGE_MST_UNSPEC, + IFLA_BRIDGE_MST_ENTRY, + __IFLA_BRIDGE_MST_MAX, +}; +#define IFLA_BRIDGE_MST_MAX (__IFLA_BRIDGE_MST_MAX - 1) + +enum { + IFLA_BRIDGE_MST_ENTRY_UNSPEC, + IFLA_BRIDGE_MST_ENTRY_MSTI, + IFLA_BRIDGE_MST_ENTRY_STATE, + __IFLA_BRIDGE_MST_ENTRY_MAX, +}; +#define IFLA_BRIDGE_MST_ENTRY_MAX (__IFLA_BRIDGE_MST_ENTRY_MAX - 1) + struct bridge_stp_xstats { __u64 transition_blk; __u64 transition_fwd; diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 51530aade46e..83849a37db5b 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -817,6 +817,7 @@ enum { #define RTEXT_FILTER_MRP (1 << 4) #define RTEXT_FILTER_CFM_CONFIG (1 << 5) #define RTEXT_FILTER_CFM_STATUS (1 << 6) +#define RTEXT_FILTER_MST (1 << 7) /* End of information exported to user level */ -- cgit v1.2.3 From 87c167bb94ee3fd49569d4aa2038b9b8840d906f Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Wed, 16 Mar 2022 16:08:46 +0100 Subject: net: bridge: mst: Notify switchdev drivers of MST mode changes Trigger a switchdev event whenever the bridge's MST mode is enabled/disabled. This allows constituent ports to either perform any required hardware config, or refuse the change if it not supported. Signed-off-by: Tobias Waldekranz Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/net/switchdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 3e424d40fae3..85dd004dc9ad 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -27,6 +27,7 @@ enum switchdev_attr_id { SWITCHDEV_ATTR_ID_BRIDGE_VLAN_PROTOCOL, SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED, SWITCHDEV_ATTR_ID_BRIDGE_MROUTER, + SWITCHDEV_ATTR_ID_BRIDGE_MST, SWITCHDEV_ATTR_ID_MRP_PORT_ROLE, }; @@ -48,6 +49,7 @@ struct switchdev_attr { clock_t ageing_time; /* BRIDGE_AGEING_TIME */ bool vlan_filtering; /* BRIDGE_VLAN_FILTERING */ u16 vlan_protocol; /* BRIDGE_VLAN_PROTOCOL */ + bool mst; /* BRIDGE_MST */ bool mc_disabled; /* MC_DISABLED */ u8 mrp_port_role; /* MRP_PORT_ROLE */ } u; -- cgit v1.2.3 From 6284c723d9b9995cc27ab3c6368a9d95d67111ff Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Wed, 16 Mar 2022 16:08:47 +0100 Subject: net: bridge: mst: Notify switchdev drivers of VLAN MSTI migrations Whenever a VLAN moves to a new MSTI, send a switchdev notification so that switchdevs can track a bridge's VID to MSTI mappings. Signed-off-by: Tobias Waldekranz Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/net/switchdev.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 85dd004dc9ad..53dfa0f7cf5b 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -29,6 +29,7 @@ enum switchdev_attr_id { SWITCHDEV_ATTR_ID_BRIDGE_MROUTER, SWITCHDEV_ATTR_ID_BRIDGE_MST, SWITCHDEV_ATTR_ID_MRP_PORT_ROLE, + SWITCHDEV_ATTR_ID_VLAN_MSTI, }; struct switchdev_brport_flags { @@ -36,6 +37,11 @@ struct switchdev_brport_flags { unsigned long mask; }; +struct switchdev_vlan_msti { + u16 vid; + u16 msti; +}; + struct switchdev_attr { struct net_device *orig_dev; enum switchdev_attr_id id; @@ -52,6 +58,7 @@ struct switchdev_attr { bool mst; /* BRIDGE_MST */ bool mc_disabled; /* MC_DISABLED */ u8 mrp_port_role; /* MRP_PORT_ROLE */ + struct switchdev_vlan_msti vlan_msti; /* VLAN_MSTI */ } u; }; -- cgit v1.2.3 From 7ae9147f4312903b97eae231c48571bbd95dc63f Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Wed, 16 Mar 2022 16:08:48 +0100 Subject: net: bridge: mst: Notify switchdev drivers of MST state changes Generate a switchdev notification whenever an MST state changes. This notification is keyed by the VLANs MSTI rather than the VID, since multiple VLANs may share the same MST instance. Signed-off-by: Tobias Waldekranz Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/net/switchdev.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 53dfa0f7cf5b..aa0171d5786d 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -19,6 +19,7 @@ enum switchdev_attr_id { SWITCHDEV_ATTR_ID_UNDEFINED, SWITCHDEV_ATTR_ID_PORT_STP_STATE, + SWITCHDEV_ATTR_ID_PORT_MST_STATE, SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS, SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS, SWITCHDEV_ATTR_ID_PORT_MROUTER, @@ -32,6 +33,11 @@ enum switchdev_attr_id { SWITCHDEV_ATTR_ID_VLAN_MSTI, }; +struct switchdev_mst_state { + u16 msti; + u8 state; +}; + struct switchdev_brport_flags { unsigned long val; unsigned long mask; @@ -50,6 +56,7 @@ struct switchdev_attr { void (*complete)(struct net_device *dev, int err, void *priv); union { u8 stp_state; /* PORT_STP_STATE */ + struct switchdev_mst_state mst_state; /* PORT_MST_STATE */ struct switchdev_brport_flags brport_flags; /* PORT_BRIDGE_FLAGS */ bool mrouter; /* PORT_MROUTER */ clock_t ageing_time; /* BRIDGE_AGEING_TIME */ -- cgit v1.2.3 From cceac97afa090284b3ceecd93ea6b7b527116767 Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Wed, 16 Mar 2022 16:08:49 +0100 Subject: net: bridge: mst: Add helper to map an MSTI to a VID set br_mst_get_info answers the question: "On this bridge, which VIDs are mapped to the given MSTI?" This is useful in switchdev drivers, which might have to fan-out operations, relating to an MSTI, per VLAN. An example: When a port's MST state changes from forwarding to blocking, a driver may choose to flush the dynamic FDB entries on that port to get faster reconvergence of the network, but this should only be done in the VLANs that are managed by the MSTI in question. Signed-off-by: Tobias Waldekranz Reviewed-by: Vladimir Oltean Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/linux/if_bridge.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 3aae023a9353..1cf0cc46d90d 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -119,6 +119,7 @@ int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo); int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo); +int br_mst_get_info(const struct net_device *dev, u16 msti, unsigned long *vids); #else static inline bool br_vlan_enabled(const struct net_device *dev) { @@ -151,6 +152,12 @@ static inline int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid, { return -EINVAL; } + +static inline int br_mst_get_info(const struct net_device *dev, u16 msti, + unsigned long *vids) +{ + return -EINVAL; +} #endif #if IS_ENABLED(CONFIG_BRIDGE) -- cgit v1.2.3 From 48d57b2e5f439246c4e12ed7705a5e3241294b03 Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Wed, 16 Mar 2022 16:08:50 +0100 Subject: net: bridge: mst: Add helper to check if MST is enabled This is useful for switchdev drivers that might want to refuse to join a bridge where MST is enabled, if the hardware can't support it. Signed-off-by: Tobias Waldekranz Reviewed-by: Vladimir Oltean Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/linux/if_bridge.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 1cf0cc46d90d..4efd5540279a 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -119,6 +119,7 @@ int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo); int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo); +bool br_mst_enabled(const struct net_device *dev); int br_mst_get_info(const struct net_device *dev, u16 msti, unsigned long *vids); #else static inline bool br_vlan_enabled(const struct net_device *dev) @@ -153,6 +154,11 @@ static inline int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid, return -EINVAL; } +static inline bool br_mst_enabled(const struct net_device *dev) +{ + return false; +} + static inline int br_mst_get_info(const struct net_device *dev, u16 msti, unsigned long *vids) { -- cgit v1.2.3 From f54fd0e163068ced4d0d27db64cd3cbda95b74e4 Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Wed, 16 Mar 2022 16:08:51 +0100 Subject: net: bridge: mst: Add helper to query a port's MST state This is useful for switchdev drivers who are offloading MST states into hardware. As an example, a driver may wish to flush the FDB for a port when it transitions from forwarding to blocking - which means that the previous state must be discoverable. Signed-off-by: Tobias Waldekranz Reviewed-by: Vladimir Oltean Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/linux/if_bridge.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 4efd5540279a..d62ef428e3aa 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -121,6 +121,7 @@ int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo); bool br_mst_enabled(const struct net_device *dev); int br_mst_get_info(const struct net_device *dev, u16 msti, unsigned long *vids); +int br_mst_get_state(const struct net_device *dev, u16 msti, u8 *state); #else static inline bool br_vlan_enabled(const struct net_device *dev) { @@ -164,6 +165,11 @@ static inline int br_mst_get_info(const struct net_device *dev, u16 msti, { return -EINVAL; } +static inline int br_mst_get_state(const struct net_device *dev, u16 msti, + u8 *state) +{ + return -EINVAL; +} #endif #if IS_ENABLED(CONFIG_BRIDGE) -- cgit v1.2.3 From 8e6598a7b0fa834a563392d30017eac1b0102fcd Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Wed, 16 Mar 2022 16:08:53 +0100 Subject: net: dsa: Pass VLAN MSTI migration notifications to driver Add the usual trampoline functionality from the generic DSA layer down to the drivers for VLAN MSTI migrations. Signed-off-by: Tobias Waldekranz Reviewed-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 9bfe984fcdbf..644fda2293a2 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -976,6 +976,9 @@ struct dsa_switch_ops { struct netlink_ext_ack *extack); int (*port_vlan_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); + int (*vlan_msti_set)(struct dsa_switch *ds, struct dsa_bridge bridge, + const struct switchdev_vlan_msti *msti); + /* * Forwarding database */ -- cgit v1.2.3 From 7414af30b7d80f117bed5ad6769e6ffb433573ba Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Wed, 16 Mar 2022 16:08:54 +0100 Subject: net: dsa: Handle MST state changes Add the usual trampoline functionality from the generic DSA layer down to the drivers for MST state changes. When a state changes to disabled/blocking/listening, make sure to fast age any dynamic entries in the affected VLANs (those controlled by the MSTI in question). Signed-off-by: Tobias Waldekranz Reviewed-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 644fda2293a2..06cdefd3b9dd 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -957,7 +957,10 @@ struct dsa_switch_ops { struct dsa_bridge bridge); void (*port_stp_state_set)(struct dsa_switch *ds, int port, u8 state); + int (*port_mst_state_set)(struct dsa_switch *ds, int port, + const struct switchdev_mst_state *state); void (*port_fast_age)(struct dsa_switch *ds, int port); + int (*port_vlan_fast_age)(struct dsa_switch *ds, int port, u16 vid); int (*port_pre_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); -- cgit v1.2.3 From ccb6ed426f10ac4f742efa7d897c266aa10ac64a Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 16 Mar 2022 22:41:40 +0200 Subject: net: mscc: ocelot: add port mirroring support using tc-matchall Ocelot switches perform port-based ingress mirroring if ANA:PORT:PORT_CFG field SRC_MIRROR_ENA is set, and egress mirroring if the port is in ANA:ANA:EMIRRORPORTS. Both ingress-mirrored and egress-mirrored frames are copied to the port mask from ANA:ANA:MIRRORPORTS. So the choice of limiting to a single mirror port via ocelot_mirror_get() and ocelot_mirror_put() may seem bizarre, but the hardware model doesn't map very well to the user space model. If the user wants to mirror the ingress of swp1 towards swp2 and the ingress of swp3 towards swp4, we'd have to program ANA:ANA:MIRRORPORTS with BIT(2) | BIT(4), and that would make swp1 be mirrored towards swp4 too, and swp3 towards swp2. But there are no tc-matchall rules to describe those actions. Now, we could offload a matchall rule with multiple mirred actions, one per desired mirror port, and force the user to stick to the multi-action rule format for subsequent matchall filters. But both DSA and ocelot have the flow_offload_has_one_action() check for the matchall offload, plus the fact that it will get cumbersome to cross-check matchall mirrors with flower mirrors (which will be added in the next patch). As a result, we limit the configuration to a single mirror port, with the possibility of lifting the restriction in the future. Frames injected from the CPU don't get egress-mirrored, since they are sent with the BYPASS bit in the injection frame header, and this bypasses the analyzer module (effectively also the mirroring logic). I don't know what to do/say about this. Functionality was tested with: tc qdisc add dev swp3 clsact tc filter add dev swp3 ingress \ matchall skip_sw \ action mirred egress mirror dev swp1 and pinging through swp3, while seeing that the ICMP replies are mirrored towards swp1. Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 4d51e2a7120f..9b4e6c78d0f4 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -642,6 +642,11 @@ struct ocelot_lag_fdb { struct list_head list; }; +struct ocelot_mirror { + refcount_t refcount; + int to; +}; + struct ocelot_port { struct ocelot *ocelot; @@ -723,6 +728,7 @@ struct ocelot { struct ocelot_vcap_block block[3]; struct ocelot_vcap_policer vcap_pol; struct vcap_props *vcap; + struct ocelot_mirror *mirror; struct ocelot_psfp_list psfp; @@ -908,6 +914,9 @@ int ocelot_get_max_mtu(struct ocelot *ocelot, int port); int ocelot_port_policer_add(struct ocelot *ocelot, int port, struct ocelot_policer *pol); int ocelot_port_policer_del(struct ocelot *ocelot, int port); +int ocelot_port_mirror_add(struct ocelot *ocelot, int from, int to, + bool ingress, struct netlink_ext_ack *extack); +void ocelot_port_mirror_del(struct ocelot *ocelot, int from, bool ingress); int ocelot_cls_flower_replace(struct ocelot *ocelot, int port, struct flow_cls_offload *f, bool ingress); int ocelot_cls_flower_destroy(struct ocelot *ocelot, int port, -- cgit v1.2.3 From f2a0e216bee5d95e2c2d916a8815a659cd3703c2 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 16 Mar 2022 22:41:42 +0200 Subject: net: mscc: ocelot: offload per-flow mirroring using tc-mirred and VCAP IS2 Per-flow mirroring with the VCAP IS2 TCAM (in itself handled as an offload for tc-flower) is done by setting the MIRROR_ENA bit from the action vector of the filter. The packet is mirrored to the port mask configured in the ANA:ANA:MIRRORPORTS register (the same port mask as the destinations for port-based mirroring). Functionality was tested with: tc qdisc add dev swp3 clsact tc filter add dev swp3 ingress protocol ip \ flower skip_sw ip_proto icmp \ action mirred egress mirror dev swp1 and pinging through swp3, while seeing that the ICMP replies are mirrored towards swp1. Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot_vcap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index deb2ad9eb0a5..7b2bf9b1fe69 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -654,6 +654,7 @@ struct ocelot_vcap_action { enum ocelot_mask_mode mask_mode; unsigned long port_mask; bool police_ena; + bool mirror_ena; struct ocelot_policer pol; u32 pol_ix; }; @@ -697,6 +698,7 @@ struct ocelot_vcap_filter { unsigned long ingress_port_mask; /* For VCAP ES0 */ struct ocelot_vcap_port ingress_port; + /* For VCAP IS2 mirrors and ES0 */ struct ocelot_vcap_port egress_port; enum ocelot_vcap_bit dmac_mc; -- cgit v1.2.3 From 0148bb50b8fd51baf357de8b237c0c6011506540 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 16 Mar 2022 22:41:43 +0200 Subject: net: dsa: pass extack to dsa_switch_ops :: port_mirror_add() Drivers might have error messages to propagate to user space, most common being that they support a single mirror port. Propagate the netlink extack so that they can inform user space in a verbal way of their limitations. Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 06cdefd3b9dd..934958fda962 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -1028,7 +1028,7 @@ struct dsa_switch_ops { struct flow_cls_offload *cls, bool ingress); int (*port_mirror_add)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror, - bool ingress); + bool ingress, struct netlink_ext_ack *extack); void (*port_mirror_del)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror); int (*port_policer_add)(struct dsa_switch *ds, int port, -- cgit v1.2.3 From 78e1fb3112c0ac440bf9dce080a4aefbaa547d52 Mon Sep 17 00:00:00 2001 From: Rodrigo Vivi Date: Sun, 6 Mar 2022 15:21:57 -0800 Subject: drm/i915/uapi: Add query for hwconfig blob In this interface i915 is returning a blob of data which it receives from the guc software. This blob provides some useful data about the hardware for drivers. The format of this blob will be documented in the Programmer Reference Manuals when released. Cc: Tvrtko Ursulin Cc: Kenneth Graunke Cc: Michal Wajdeczko Cc: Slawomir Milczarek Cc: Joonas Lahtinen Signed-off-by: Rodrigo Vivi Signed-off-by: John Harrison Reviewed-by: Matthew Brost Acked-by: Jordan Justen Tested-by: Jordan Justen Acked-by: Jon Bloomfield Signed-off-by: John Harrison Link: https://patchwork.freedesktop.org/patch/msgid/20220306232157.1174335-3-jordan.l.justen@intel.com --- include/uapi/drm/i915_drm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 05c3642aaece..071ffd9d51f1 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -2691,6 +2691,7 @@ struct drm_i915_query_item { #define DRM_I915_QUERY_ENGINE_INFO 2 #define DRM_I915_QUERY_PERF_CONFIG 3 #define DRM_I915_QUERY_MEMORY_REGIONS 4 +#define DRM_I915_QUERY_HWCONFIG_BLOB 5 /* Must be kept compact -- no holes and well documented */ /** -- cgit v1.2.3 From 4f554e955614f19425cee86de4669351741a6280 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 15 Mar 2022 23:00:26 +0900 Subject: ftrace: Add ftrace_set_filter_ips function Adding ftrace_set_filter_ips function to be able to set filter on multiple ip addresses at once. With the kprobe multi attach interface we have cases where we need to initialize ftrace_ops object with thousands of functions, so having single function diving into ftrace_hash_move_and_update_ops with ftrace_lock is faster. The functions ips are passed as unsigned long array with count. Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt (Google) Tested-by: Steven Rostedt (Google) Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/164735282673.1084943.18310504594134769804.stgit@devnote2 --- include/linux/ftrace.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 9999e29187de..60847cbce0da 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -512,6 +512,8 @@ struct dyn_ftrace { int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip, int remove, int reset); +int ftrace_set_filter_ips(struct ftrace_ops *ops, unsigned long *ips, + unsigned int cnt, int remove, int reset); int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, int len, int reset); int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, @@ -802,6 +804,7 @@ static inline unsigned long ftrace_location(unsigned long ip) #define ftrace_regex_open(ops, flag, inod, file) ({ -ENODEV; }) #define ftrace_set_early_filter(ops, buf, enable) do { } while (0) #define ftrace_set_filter_ip(ops, ip, remove, reset) ({ -ENODEV; }) +#define ftrace_set_filter_ips(ops, ips, cnt, remove, reset) ({ -ENODEV; }) #define ftrace_set_filter(ops, buf, len, reset) ({ -ENODEV; }) #define ftrace_set_notrace(ops, buf, len, reset) ({ -ENODEV; }) #define ftrace_free_filter(ops) do { } while (0) -- cgit v1.2.3 From cad9931f64dc7f5dbdec12cae9f30063360f9855 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 15 Mar 2022 23:00:38 +0900 Subject: fprobe: Add ftrace based probe APIs The fprobe is a wrapper API for ftrace function tracer. Unlike kprobes, this probes only supports the function entry, but this can probe multiple functions by one fprobe. The usage is similar, user will set their callback to fprobe::entry_handler and call register_fprobe*() with probed functions. There are 3 registration interfaces, - register_fprobe() takes filtering patterns of the functin names. - register_fprobe_ips() takes an array of ftrace-location addresses. - register_fprobe_syms() takes an array of function names. The registered fprobes can be unregistered with unregister_fprobe(). e.g. struct fprobe fp = { .entry_handler = user_handler }; const char *targets[] = { "func1", "func2", "func3"}; ... ret = register_fprobe_syms(&fp, targets, ARRAY_SIZE(targets)); ... unregister_fprobe(&fp); Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (Google) Tested-by: Steven Rostedt (Google) Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/164735283857.1084943.1154436951479395551.stgit@devnote2 --- include/linux/fprobe.h | 87 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 87 insertions(+) create mode 100644 include/linux/fprobe.h (limited to 'include') diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h new file mode 100644 index 000000000000..2ba099aff041 --- /dev/null +++ b/include/linux/fprobe.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Simple ftrace probe wrapper */ +#ifndef _LINUX_FPROBE_H +#define _LINUX_FPROBE_H + +#include +#include + +/** + * struct fprobe - ftrace based probe. + * @ops: The ftrace_ops. + * @nmissed: The counter for missing events. + * @flags: The status flag. + * @entry_handler: The callback function for function entry. + */ +struct fprobe { +#ifdef CONFIG_FUNCTION_TRACER + /* + * If CONFIG_FUNCTION_TRACER is not set, CONFIG_FPROBE is disabled too. + * But user of fprobe may keep embedding the struct fprobe on their own + * code. To avoid build error, this will keep the fprobe data structure + * defined here, but remove ftrace_ops data structure. + */ + struct ftrace_ops ops; +#endif + unsigned long nmissed; + unsigned int flags; + void (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs); +}; + +#define FPROBE_FL_DISABLED 1 + +static inline bool fprobe_disabled(struct fprobe *fp) +{ + return (fp) ? fp->flags & FPROBE_FL_DISABLED : false; +} + +#ifdef CONFIG_FPROBE +int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter); +int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num); +int register_fprobe_syms(struct fprobe *fp, const char **syms, int num); +int unregister_fprobe(struct fprobe *fp); +#else +static inline int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter) +{ + return -EOPNOTSUPP; +} +static inline int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num) +{ + return -EOPNOTSUPP; +} +static inline int register_fprobe_syms(struct fprobe *fp, const char **syms, int num) +{ + return -EOPNOTSUPP; +} +static inline int unregister_fprobe(struct fprobe *fp) +{ + return -EOPNOTSUPP; +} +#endif + +/** + * disable_fprobe() - Disable fprobe + * @fp: The fprobe to be disabled. + * + * This will soft-disable @fp. Note that this doesn't remove the ftrace + * hooks from the function entry. + */ +static inline void disable_fprobe(struct fprobe *fp) +{ + if (fp) + fp->flags |= FPROBE_FL_DISABLED; +} + +/** + * enable_fprobe() - Enable fprobe + * @fp: The fprobe to be enabled. + * + * This will soft-enable @fp. + */ +static inline void enable_fprobe(struct fprobe *fp) +{ + if (fp) + fp->flags &= ~FPROBE_FL_DISABLED; +} + +#endif -- cgit v1.2.3 From 54ecbe6f1ed5138c895bdff55608cf502755b20e Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 15 Mar 2022 23:00:50 +0900 Subject: rethook: Add a generic return hook Add a return hook framework which hooks the function return. Most of the logic came from the kretprobe, but this is independent from kretprobe. Note that this is expected to be used with other function entry hooking feature, like ftrace, fprobe, adn kprobes. Eventually this will replace the kretprobe (e.g. kprobe + rethook = kretprobe), but at this moment, this is just an additional hook. Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (Google) Tested-by: Steven Rostedt (Google) Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/164735285066.1084943.9259661137330166643.stgit@devnote2 --- include/linux/rethook.h | 100 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/sched.h | 3 ++ 2 files changed, 103 insertions(+) create mode 100644 include/linux/rethook.h (limited to 'include') diff --git a/include/linux/rethook.h b/include/linux/rethook.h new file mode 100644 index 000000000000..c8ac1e5afcd1 --- /dev/null +++ b/include/linux/rethook.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Return hooking with list-based shadow stack. + */ +#ifndef _LINUX_RETHOOK_H +#define _LINUX_RETHOOK_H + +#include +#include +#include +#include +#include +#include + +struct rethook_node; + +typedef void (*rethook_handler_t) (struct rethook_node *, void *, struct pt_regs *); + +/** + * struct rethook - The rethook management data structure. + * @data: The user-defined data storage. + * @handler: The user-defined return hook handler. + * @pool: The pool of struct rethook_node. + * @ref: The reference counter. + * @rcu: The rcu_head for deferred freeing. + * + * Don't embed to another data structure, because this is a self-destructive + * data structure when all rethook_node are freed. + */ +struct rethook { + void *data; + rethook_handler_t handler; + struct freelist_head pool; + refcount_t ref; + struct rcu_head rcu; +}; + +/** + * struct rethook_node - The rethook shadow-stack entry node. + * @freelist: The freelist, linked to struct rethook::pool. + * @rcu: The rcu_head for deferred freeing. + * @llist: The llist, linked to a struct task_struct::rethooks. + * @rethook: The pointer to the struct rethook. + * @ret_addr: The storage for the real return address. + * @frame: The storage for the frame pointer. + * + * You can embed this to your extended data structure to store any data + * on each entry of the shadow stack. + */ +struct rethook_node { + union { + struct freelist_node freelist; + struct rcu_head rcu; + }; + struct llist_node llist; + struct rethook *rethook; + unsigned long ret_addr; + unsigned long frame; +}; + +struct rethook *rethook_alloc(void *data, rethook_handler_t handler); +void rethook_free(struct rethook *rh); +void rethook_add_node(struct rethook *rh, struct rethook_node *node); +struct rethook_node *rethook_try_get(struct rethook *rh); +void rethook_recycle(struct rethook_node *node); +void rethook_hook(struct rethook_node *node, struct pt_regs *regs, bool mcount); +unsigned long rethook_find_ret_addr(struct task_struct *tsk, unsigned long frame, + struct llist_node **cur); + +/* Arch dependent code must implement arch_* and trampoline code */ +void arch_rethook_prepare(struct rethook_node *node, struct pt_regs *regs, bool mcount); +void arch_rethook_trampoline(void); + +/** + * is_rethook_trampoline() - Check whether the address is rethook trampoline + * @addr: The address to be checked + * + * Return true if the @addr is the rethook trampoline address. + */ +static inline bool is_rethook_trampoline(unsigned long addr) +{ + return addr == (unsigned long)dereference_symbol_descriptor(arch_rethook_trampoline); +} + +/* If the architecture needs to fixup the return address, implement it. */ +void arch_rethook_fixup_return(struct pt_regs *regs, + unsigned long correct_ret_addr); + +/* Generic trampoline handler, arch code must prepare asm stub */ +unsigned long rethook_trampoline_handler(struct pt_regs *regs, + unsigned long frame); + +#ifdef CONFIG_RETHOOK +void rethook_flush_task(struct task_struct *tk); +#else +#define rethook_flush_task(tsk) do { } while (0) +#endif + +#endif + diff --git a/include/linux/sched.h b/include/linux/sched.h index 75ba8aa60248..7034f53404e3 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1481,6 +1481,9 @@ struct task_struct { #ifdef CONFIG_KRETPROBES struct llist_head kretprobe_instances; #endif +#ifdef CONFIG_RETHOOK + struct llist_head rethooks; +#endif #ifdef CONFIG_ARCH_HAS_PARANOID_L1D_FLUSH /* -- cgit v1.2.3 From 5b0ab78998e32564a011b14c4c7f9c81e2d42b9d Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 15 Mar 2022 23:01:48 +0900 Subject: fprobe: Add exit_handler support Add exit_handler to fprobe. fprobe + rethook allows us to hook the kernel function return. The rethook will be enabled only if the fprobe::exit_handler is set. Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (Google) Tested-by: Steven Rostedt (Google) Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/164735290790.1084943.10601965782208052202.stgit@devnote2 --- include/linux/fprobe.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h index 2ba099aff041..8eefec2b485e 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -5,13 +5,16 @@ #include #include +#include /** * struct fprobe - ftrace based probe. * @ops: The ftrace_ops. * @nmissed: The counter for missing events. * @flags: The status flag. + * @rethook: The rethook data structure. (internal data) * @entry_handler: The callback function for function entry. + * @exit_handler: The callback function for function exit. */ struct fprobe { #ifdef CONFIG_FUNCTION_TRACER @@ -25,7 +28,10 @@ struct fprobe { #endif unsigned long nmissed; unsigned int flags; + struct rethook *rethook; + void (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs); + void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs); }; #define FPROBE_FL_DISABLED 1 -- cgit v1.2.3 From ab51e15d535e07be9839e0df056a4ebe9c5bac83 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 15 Mar 2022 23:02:11 +0900 Subject: fprobe: Introduce FPROBE_FL_KPROBE_SHARED flag for fprobe Introduce FPROBE_FL_KPROBE_SHARED flag for sharing fprobe callback with kprobes safely from the viewpoint of recursion. Since the recursion safety of the fprobe (and ftrace) is a bit different from the kprobes, this may cause an issue if user wants to run the same code from the fprobe and the kprobes. The kprobes has per-cpu 'current_kprobe' variable which protects the kprobe handler from recursion in any case. On the other hand, the fprobe uses only ftrace_test_recursion_trylock(), which will allow interrupt context calls another (or same) fprobe during the fprobe user handler is running. This is not a matter in cases if the common callback shared among the kprobes and the fprobe has its own recursion detection, or it can handle the recursion in the different contexts (normal/interrupt/NMI.) But if it relies on the 'current_kprobe' recursion lock, it has to check kprobe_running() and use kprobe_busy_*() APIs. Fprobe has FPROBE_FL_KPROBE_SHARED flag to do this. If your common callback code will be shared with kprobes, please set FPROBE_FL_KPROBE_SHARED *before* registering the fprobe, like; fprobe.flags = FPROBE_FL_KPROBE_SHARED; register_fprobe(&fprobe, "func*", NULL); This will protect your common callback from the nested call. Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (Google) Tested-by: Steven Rostedt (Google) Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/164735293127.1084943.15687374237275817599.stgit@devnote2 --- include/linux/fprobe.h | 12 ++++++++++++ include/linux/kprobes.h | 3 +++ 2 files changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h index 8eefec2b485e..1c2bde0ead73 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -34,13 +34,25 @@ struct fprobe { void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs); }; +/* This fprobe is soft-disabled. */ #define FPROBE_FL_DISABLED 1 +/* + * This fprobe handler will be shared with kprobes. + * This flag must be set before registering. + */ +#define FPROBE_FL_KPROBE_SHARED 2 + static inline bool fprobe_disabled(struct fprobe *fp) { return (fp) ? fp->flags & FPROBE_FL_DISABLED : false; } +static inline bool fprobe_shared_with_kprobes(struct fprobe *fp) +{ + return (fp) ? fp->flags & FPROBE_FL_KPROBE_SHARED : false; +} + #ifdef CONFIG_FPROBE int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter); int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num); diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 19b884353b15..5f1859836deb 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -427,6 +427,9 @@ static inline struct kprobe *kprobe_running(void) { return NULL; } +#define kprobe_busy_begin() do {} while (0) +#define kprobe_busy_end() do {} while (0) + static inline int register_kprobe(struct kprobe *p) { return -EOPNOTSUPP; -- cgit v1.2.3 From a0019cd7d41a191253859349535d76ee28ab7d96 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 16 Mar 2022 13:24:07 +0100 Subject: lib/sort: Add priv pointer to swap function Adding support to have priv pointer in swap callback function. Following the initial change on cmp callback functions [1] and adding SWAP_WRAPPER macro to identify sort call of sort_r. Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Reviewed-by: Masami Hiramatsu Link: https://lore.kernel.org/bpf/20220316122419.933957-2-jolsa@kernel.org [1] 4333fb96ca10 ("media: lib/sort.c: implement sort() variant taking context argument") --- include/linux/sort.h | 2 +- include/linux/types.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sort.h b/include/linux/sort.h index b5898725fe9d..e163287ac6c1 100644 --- a/include/linux/sort.h +++ b/include/linux/sort.h @@ -6,7 +6,7 @@ void sort_r(void *base, size_t num, size_t size, cmp_r_func_t cmp_func, - swap_func_t swap_func, + swap_r_func_t swap_func, const void *priv); void sort(void *base, size_t num, size_t size, diff --git a/include/linux/types.h b/include/linux/types.h index ac825ad90e44..ea8cf60a8a79 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -226,6 +226,7 @@ struct callback_head { typedef void (*rcu_callback_t)(struct rcu_head *head); typedef void (*call_rcu_func_t)(struct rcu_head *head, rcu_callback_t func); +typedef void (*swap_r_func_t)(void *a, void *b, int size, const void *priv); typedef void (*swap_func_t)(void *a, void *b, int size); typedef int (*cmp_r_func_t)(const void *a, const void *b, const void *priv); -- cgit v1.2.3 From 0dcac272540613d41c05e89679e4ddb978b612f1 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 16 Mar 2022 13:24:09 +0100 Subject: bpf: Add multi kprobe link Adding new link type BPF_LINK_TYPE_KPROBE_MULTI that attaches kprobe program through fprobe API. The fprobe API allows to attach probe on multiple functions at once very fast, because it works on top of ftrace. On the other hand this limits the probe point to the function entry or return. The kprobe program gets the same pt_regs input ctx as when it's attached through the perf API. Adding new attach type BPF_TRACE_KPROBE_MULTI that allows attachment kprobe to multiple function with new link. User provides array of addresses or symbols with count to attach the kprobe program to. The new link_create uapi interface looks like: struct { __u32 flags; __u32 cnt; __aligned_u64 syms; __aligned_u64 addrs; } kprobe_multi; The flags field allows single BPF_TRACE_KPROBE_MULTI bit to create return multi kprobe. Signed-off-by: Masami Hiramatsu Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220316122419.933957-4-jolsa@kernel.org --- include/linux/bpf_types.h | 1 + include/linux/trace_events.h | 7 +++++++ include/uapi/linux/bpf.h | 13 +++++++++++++ 3 files changed, 21 insertions(+) (limited to 'include') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 48a91c51c015..3e24ad0c4b3c 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -140,3 +140,4 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp) #ifdef CONFIG_PERF_EVENTS BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf) #endif +BPF_LINK_TYPE(BPF_LINK_TYPE_KPROBE_MULTI, kprobe_multi) diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index dcea51fb60e2..8f0e9e7cb493 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -15,6 +15,7 @@ struct array_buffer; struct tracer; struct dentry; struct bpf_prog; +union bpf_attr; const char *trace_print_flags_seq(struct trace_seq *p, const char *delim, unsigned long flags, @@ -738,6 +739,7 @@ void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp); int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, u64 *probe_offset, u64 *probe_addr); +int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); #else static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) { @@ -779,6 +781,11 @@ static inline int bpf_get_perf_event_info(const struct perf_event *event, { return -EOPNOTSUPP; } +static inline int +bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} #endif enum { diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 99fab54ae9c0..d77f47af7752 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -997,6 +997,7 @@ enum bpf_attach_type { BPF_SK_REUSEPORT_SELECT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, BPF_PERF_EVENT, + BPF_TRACE_KPROBE_MULTI, __MAX_BPF_ATTACH_TYPE }; @@ -1011,6 +1012,7 @@ enum bpf_link_type { BPF_LINK_TYPE_NETNS = 5, BPF_LINK_TYPE_XDP = 6, BPF_LINK_TYPE_PERF_EVENT = 7, + BPF_LINK_TYPE_KPROBE_MULTI = 8, MAX_BPF_LINK_TYPE, }; @@ -1118,6 +1120,11 @@ enum bpf_link_type { */ #define BPF_F_XDP_HAS_FRAGS (1U << 5) +/* link_create.kprobe_multi.flags used in LINK_CREATE command for + * BPF_TRACE_KPROBE_MULTI attach type to create return probe. + */ +#define BPF_F_KPROBE_MULTI_RETURN (1U << 0) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * @@ -1475,6 +1482,12 @@ union bpf_attr { */ __u64 bpf_cookie; } perf_event; + struct { + __u32 flags; + __u32 cnt; + __aligned_u64 syms; + __aligned_u64 addrs; + } kprobe_multi; }; } link_create; -- cgit v1.2.3 From ca74823c6e16dd42b7cf60d9fdde80e2a81a67bb Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 16 Mar 2022 13:24:12 +0100 Subject: bpf: Add cookie support to programs attached with kprobe multi link Adding support to call bpf_get_attach_cookie helper from kprobe programs attached with kprobe multi link. The cookie is provided by array of u64 values, where each value is paired with provided function address or symbol with the same array index. When cookie array is provided it's sorted together with addresses (check bpf_kprobe_multi_cookie_swap). This way we can find cookie based on the address in bpf_get_attach_cookie helper. Suggested-by: Andrii Nakryiko Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220316122419.933957-7-jolsa@kernel.org --- include/uapi/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d77f47af7752..7604e7d5438f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1487,6 +1487,7 @@ union bpf_attr { __u32 cnt; __aligned_u64 syms; __aligned_u64 addrs; + __aligned_u64 cookies; } kprobe_multi; }; } link_create; -- cgit v1.2.3 From b58b1f563ab78955d37e9e43e02790a85c66ac05 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Mon, 14 Mar 2022 11:38:22 +0100 Subject: xfrm: rework default policy structure This is a follow up of commit f8d858e607b2 ("xfrm: make user policy API complete"). The goal is to align userland API to the internal structures. Signed-off-by: Nicolas Dichtel Reviewed-by: Antony Antony Signed-off-by: Steffen Klassert --- include/net/netns/xfrm.h | 6 +----- include/net/xfrm.h | 48 ++++++++++++++++++------------------------------ 2 files changed, 19 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index 947733a639a6..bd7c3be4af5d 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -66,11 +66,7 @@ struct netns_xfrm { int sysctl_larval_drop; u32 sysctl_acq_expires; - u8 policy_default; -#define XFRM_POL_DEFAULT_IN 1 -#define XFRM_POL_DEFAULT_OUT 2 -#define XFRM_POL_DEFAULT_FWD 4 -#define XFRM_POL_DEFAULT_MASK 7 + u8 policy_default[XFRM_POLICY_MAX]; #ifdef CONFIG_SYSCTL struct ctl_table_header *sysctl_hdr; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index fdb41e8bb626..1541ca0cb13c 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1081,25 +1081,18 @@ xfrm_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, un } #ifdef CONFIG_XFRM -static inline bool -xfrm_default_allow(struct net *net, int dir) -{ - u8 def = net->xfrm.policy_default; - - switch (dir) { - case XFRM_POLICY_IN: - return def & XFRM_POL_DEFAULT_IN ? false : true; - case XFRM_POLICY_OUT: - return def & XFRM_POL_DEFAULT_OUT ? false : true; - case XFRM_POLICY_FWD: - return def & XFRM_POL_DEFAULT_FWD ? false : true; - } - return false; -} - int __xfrm_policy_check(struct sock *, int dir, struct sk_buff *skb, unsigned short family); +static inline bool __xfrm_check_nopolicy(struct net *net, struct sk_buff *skb, + int dir) +{ + if (!net->xfrm.policy_count[dir] && !secpath_exists(skb)) + return net->xfrm.policy_default[dir] == XFRM_USERPOLICY_ACCEPT; + + return false; +} + static inline int __xfrm_policy_check2(struct sock *sk, int dir, struct sk_buff *skb, unsigned int family, int reverse) @@ -1110,13 +1103,9 @@ static inline int __xfrm_policy_check2(struct sock *sk, int dir, if (sk && sk->sk_policy[XFRM_POLICY_IN]) return __xfrm_policy_check(sk, ndir, skb, family); - if (xfrm_default_allow(net, dir)) - return (!net->xfrm.policy_count[dir] && !secpath_exists(skb)) || - (skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY)) || - __xfrm_policy_check(sk, ndir, skb, family); - else - return (skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY)) || - __xfrm_policy_check(sk, ndir, skb, family); + return __xfrm_check_nopolicy(net, skb, dir) || + (skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY)) || + __xfrm_policy_check(sk, ndir, skb, family); } static inline int xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, unsigned short family) @@ -1168,13 +1157,12 @@ static inline int xfrm_route_forward(struct sk_buff *skb, unsigned short family) { struct net *net = dev_net(skb->dev); - if (xfrm_default_allow(net, XFRM_POLICY_OUT)) - return !net->xfrm.policy_count[XFRM_POLICY_OUT] || - (skb_dst(skb)->flags & DST_NOXFRM) || - __xfrm_route_forward(skb, family); - else - return (skb_dst(skb)->flags & DST_NOXFRM) || - __xfrm_route_forward(skb, family); + if (!net->xfrm.policy_count[XFRM_POLICY_OUT] && + net->xfrm.policy_default[XFRM_POLICY_OUT] == XFRM_USERPOLICY_ACCEPT) + return true; + + return (skb_dst(skb)->flags & DST_NOXFRM) || + __xfrm_route_forward(skb, family); } static inline int xfrm4_route_forward(struct sk_buff *skb) -- cgit v1.2.3 From 7a19006b60b129ce2cbe787f4f910dc0ec5a1ec6 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 18 Mar 2022 08:34:52 +0100 Subject: kernfs: remove unneeded #if 0 guard Commit f2eb478f2f32 ("kernfs: move struct kernfs_root out of the public view.") moved kernfs_root out of kernfs.h, but my debugging code of a #if 0 was left in accidentally. Fix that up by removing the guards. Fixes: f2eb478f2f32 ("kernfs: move struct kernfs_root out of the public view.") Cc: Tejun Heo Reported-by: Al Viro Link: https://lore.kernel.org/r/20220318073452.1486568-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/kernfs.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include') diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 62aff082dc3f..e2ae15a6225e 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -185,26 +185,6 @@ struct kernfs_syscall_ops { struct kernfs_root *root); }; -#if 0 -struct kernfs_root { - /* published fields */ - struct kernfs_node *kn; - unsigned int flags; /* KERNFS_ROOT_* flags */ - - /* private fields, do not use outside kernfs proper */ - struct idr ino_idr; - u32 last_id_lowbits; - u32 id_highbits; - struct kernfs_syscall_ops *syscall_ops; - - /* list of kernfs_super_info of this root, protected by kernfs_rwsem */ - struct list_head supers; - - wait_queue_head_t deactivate_waitq; - struct rw_semaphore kernfs_rwsem; -}; -#endif - struct kernfs_node *kernfs_root_to_node(struct kernfs_root *root); struct kernfs_open_file { -- cgit v1.2.3 From e9b57aaae605eb869a628fdc21fe7d2c77a2205d Mon Sep 17 00:00:00 2001 From: Jeffle Xu Date: Wed, 9 Feb 2022 14:00:47 +0800 Subject: fscache: export fscache_end_operation() Export fscache_end_operation() to avoid code duplication. Besides, considering the paired fscache_begin_read_operation() is already exported, it shall make sense to also export fscache_end_operation(). Signed-off-by: Jeffle Xu Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20220302125134.131039-2-jefflexu@linux.alibaba.com/ # Jeffle's v4 Link: https://lore.kernel.org/r/164622971432.3564931.12184135678781328146.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/164678190346.1200972.7453733431978569479.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/164692888334.2099075.5166283293894267365.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/20220316131723.111553-2-jefflexu@linux.alibaba.com/ # v5 --- include/linux/fscache.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 296c5f1d9f35..d2430da8aa67 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -456,6 +456,20 @@ int fscache_begin_read_operation(struct netfs_cache_resources *cres, return -ENOBUFS; } +/** + * fscache_end_operation - End the read operation for the netfs lib + * @cres: The cache resources for the read operation + * + * Clean up the resources at the end of the read request. + */ +static inline void fscache_end_operation(struct netfs_cache_resources *cres) +{ + const struct netfs_cache_ops *ops = fscache_operation_valid(cres); + + if (ops) + ops->end_operation(cres); +} + /** * fscache_read - Start a read from the cache. * @cres: The cache resources to use -- cgit v1.2.3 From 5ac417d24c6cc2fa9ac69d8b9f4510a38ec40486 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 2 Feb 2022 15:12:44 +0000 Subject: netfs: Generate enums from trace symbol mapping lists netfs has a number of lists of symbols for use in tracing, listed in an enum and then listed again in a symbol->string mapping for use with __print_symbolic(). This is, however, redundant. Instead, use the symbol->string mapping list to also generate the enum where the enum is in the same file. Changes ======= ver #3) - #undef EM and E_ at the end of the trace file[1]. Signed-off-by: David Howells Acked-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/c2f4b3dc107b106e04c48f54945a12715cccfdf3.camel@redhat.com/ [1] Link: https://lore.kernel.org/r/164622980839.3564931.5673300162465266909.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/164678192454.1200972.4428834328108580460.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/CALF+zOkB38_MB5QwNUtqTU4WjMaLUJ5+Piwsn3pMxkO3d4J7Kg@mail.gmail.com/ # v2 Link: https://lore.kernel.org/r/164692890614.2099075.12960653141802151575.stgit@warthog.procyon.org.uk/ # v3 --- include/trace/events/netfs.h | 59 ++++++++++++-------------------------------- 1 file changed, 16 insertions(+), 43 deletions(-) (limited to 'include') diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index e6f4ebbb4c69..4d0bf02d490a 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -15,49 +15,6 @@ /* * Define enums for tracing information. */ -#ifndef __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY -#define __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY - -enum netfs_read_trace { - netfs_read_trace_expanded, - netfs_read_trace_readahead, - netfs_read_trace_readpage, - netfs_read_trace_write_begin, -}; - -enum netfs_rreq_trace { - netfs_rreq_trace_assess, - netfs_rreq_trace_done, - netfs_rreq_trace_free, - netfs_rreq_trace_resubmit, - netfs_rreq_trace_unlock, - netfs_rreq_trace_unmark, - netfs_rreq_trace_write, -}; - -enum netfs_sreq_trace { - netfs_sreq_trace_download_instead, - netfs_sreq_trace_free, - netfs_sreq_trace_prepare, - netfs_sreq_trace_resubmit_short, - netfs_sreq_trace_submit, - netfs_sreq_trace_terminated, - netfs_sreq_trace_write, - netfs_sreq_trace_write_skip, - netfs_sreq_trace_write_term, -}; - -enum netfs_failure { - netfs_fail_check_write_begin, - netfs_fail_copy_to_cache, - netfs_fail_read, - netfs_fail_short_readpage, - netfs_fail_short_write_begin, - netfs_fail_prepare_write, -}; - -#endif - #define netfs_read_traces \ EM(netfs_read_trace_expanded, "EXPANDED ") \ EM(netfs_read_trace_readahead, "READAHEAD") \ @@ -98,6 +55,20 @@ enum netfs_failure { EM(netfs_fail_short_write_begin, "short-write-begin") \ E_(netfs_fail_prepare_write, "prep-write") +#ifndef __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY +#define __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY + +#undef EM +#undef E_ +#define EM(a, b) a, +#define E_(a, b) a + +enum netfs_read_trace { netfs_read_traces } __mode(byte); +enum netfs_rreq_trace { netfs_rreq_traces } __mode(byte); +enum netfs_sreq_trace { netfs_sreq_traces } __mode(byte); +enum netfs_failure { netfs_failures } __mode(byte); + +#endif /* * Export enum symbols via userspace. @@ -258,6 +229,8 @@ TRACE_EVENT(netfs_failure, __entry->error) ); +#undef EM +#undef E_ #endif /* _TRACE_NETFS_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 6a19114b8e7f1e24d80b0812e26d78d7ae1ec6dd Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 17 Feb 2022 10:01:23 +0000 Subject: netfs: Rename netfs_read_*request to netfs_io_*request Rename netfs_read_*request to netfs_io_*request so that the same structures can be used for the write helpers too. perl -p -i -e 's/netfs_read_(request|subrequest)/netfs_io_$1/g' \ `git grep -l 'netfs_read_\(sub\|\)request'` perl -p -i -e 's/nr_rd_ops/nr_outstanding/g' \ `git grep -l nr_rd_ops` perl -p -i -e 's/nr_wr_ops/nr_copy_ops/g' \ `git grep -l nr_wr_ops` perl -p -i -e 's/netfs_read_source/netfs_io_source/g' \ `git grep -l 'netfs_read_source'` perl -p -i -e 's/netfs_io_request_ops/netfs_request_ops/g' \ `git grep -l 'netfs_io_request_ops'` perl -p -i -e 's/init_rreq/init_request/g' \ `git grep -l 'init_rreq'` Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/164622988070.3564931.7089670190434315183.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/164678195157.1200972.366609966927368090.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/164692891535.2099075.18435198075367420588.stgit@warthog.procyon.org.uk/ # v3 --- include/linux/netfs.h | 42 +++++++++++++++++++-------------------- include/trace/events/cachefiles.h | 6 +++--- include/trace/events/netfs.h | 14 ++++++------- 3 files changed, 31 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 614f22213e21..a2ca91cb7a68 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -106,7 +106,7 @@ static inline int wait_on_page_fscache_killable(struct page *page) return folio_wait_private_2_killable(page_folio(page)); } -enum netfs_read_source { +enum netfs_io_source { NETFS_FILL_WITH_ZEROES, NETFS_DOWNLOAD_FROM_SERVER, NETFS_READ_FROM_CACHE, @@ -130,8 +130,8 @@ struct netfs_cache_resources { /* * Descriptor for a single component subrequest. */ -struct netfs_read_subrequest { - struct netfs_read_request *rreq; /* Supervising read request */ +struct netfs_io_subrequest { + struct netfs_io_request *rreq; /* Supervising read request */ struct list_head rreq_link; /* Link in rreq->subrequests */ loff_t start; /* Where to start the I/O */ size_t len; /* Size of the I/O */ @@ -139,7 +139,7 @@ struct netfs_read_subrequest { refcount_t usage; short error; /* 0 or error that occurred */ unsigned short debug_index; /* Index in list (for debugging output) */ - enum netfs_read_source source; /* Where to read from */ + enum netfs_io_source source; /* Where to read from */ unsigned long flags; #define NETFS_SREQ_WRITE_TO_CACHE 0 /* Set if should write to cache */ #define NETFS_SREQ_CLEAR_TAIL 1 /* Set if the rest of the read should be cleared */ @@ -152,7 +152,7 @@ struct netfs_read_subrequest { * Descriptor for a read helper request. This is used to make multiple I/O * requests on a variety of sources and then stitch the result together. */ -struct netfs_read_request { +struct netfs_io_request { struct work_struct work; struct inode *inode; /* The file being accessed */ struct address_space *mapping; /* The mapping being accessed */ @@ -160,8 +160,8 @@ struct netfs_read_request { struct list_head subrequests; /* Requests to fetch I/O from disk or net */ void *netfs_priv; /* Private data for the netfs */ unsigned int debug_id; - atomic_t nr_rd_ops; /* Number of read ops in progress */ - atomic_t nr_wr_ops; /* Number of write ops in progress */ + atomic_t nr_outstanding; /* Number of read ops in progress */ + atomic_t nr_copy_ops; /* Number of write ops in progress */ size_t submitted; /* Amount submitted for I/O so far */ size_t len; /* Length of the request */ short error; /* 0 or error that occurred */ @@ -176,23 +176,23 @@ struct netfs_read_request { #define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ #define NETFS_RREQ_FAILED 4 /* The request failed */ #define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes */ - const struct netfs_read_request_ops *netfs_ops; + const struct netfs_request_ops *netfs_ops; }; /* * Operations the network filesystem can/must provide to the helpers. */ -struct netfs_read_request_ops { +struct netfs_request_ops { bool (*is_cache_enabled)(struct inode *inode); - void (*init_rreq)(struct netfs_read_request *rreq, struct file *file); - int (*begin_cache_operation)(struct netfs_read_request *rreq); - void (*expand_readahead)(struct netfs_read_request *rreq); - bool (*clamp_length)(struct netfs_read_subrequest *subreq); - void (*issue_op)(struct netfs_read_subrequest *subreq); - bool (*is_still_valid)(struct netfs_read_request *rreq); + void (*init_request)(struct netfs_io_request *rreq, struct file *file); + int (*begin_cache_operation)(struct netfs_io_request *rreq); + void (*expand_readahead)(struct netfs_io_request *rreq); + bool (*clamp_length)(struct netfs_io_subrequest *subreq); + void (*issue_op)(struct netfs_io_subrequest *subreq); + bool (*is_still_valid)(struct netfs_io_request *rreq); int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, struct folio *folio, void **_fsdata); - void (*done)(struct netfs_read_request *rreq); + void (*done)(struct netfs_io_request *rreq); void (*cleanup)(struct address_space *mapping, void *netfs_priv); }; @@ -235,7 +235,7 @@ struct netfs_cache_ops { /* Prepare a read operation, shortening it to a cached/uncached * boundary as appropriate. */ - enum netfs_read_source (*prepare_read)(struct netfs_read_subrequest *subreq, + enum netfs_io_source (*prepare_read)(struct netfs_io_subrequest *subreq, loff_t i_size); /* Prepare a write operation, working out what part of the write we can @@ -255,19 +255,19 @@ struct netfs_cache_ops { struct readahead_control; extern void netfs_readahead(struct readahead_control *, - const struct netfs_read_request_ops *, + const struct netfs_request_ops *, void *); extern int netfs_readpage(struct file *, struct folio *, - const struct netfs_read_request_ops *, + const struct netfs_request_ops *, void *); extern int netfs_write_begin(struct file *, struct address_space *, loff_t, unsigned int, unsigned int, struct folio **, void **, - const struct netfs_read_request_ops *, + const struct netfs_request_ops *, void *); -extern void netfs_subreq_terminated(struct netfs_read_subrequest *, ssize_t, bool); +extern void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool); extern void netfs_stats_show(struct seq_file *); #endif /* _LINUX_NETFS_H */ diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index c6f5aa74db89..002d0ae4f9bc 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -424,8 +424,8 @@ TRACE_EVENT(cachefiles_vol_coherency, ); TRACE_EVENT(cachefiles_prep_read, - TP_PROTO(struct netfs_read_subrequest *sreq, - enum netfs_read_source source, + TP_PROTO(struct netfs_io_subrequest *sreq, + enum netfs_io_source source, enum cachefiles_prepare_read_trace why, ino_t cache_inode), @@ -435,7 +435,7 @@ TRACE_EVENT(cachefiles_prep_read, __field(unsigned int, rreq ) __field(unsigned short, index ) __field(unsigned short, flags ) - __field(enum netfs_read_source, source ) + __field(enum netfs_io_source, source ) __field(enum cachefiles_prepare_read_trace, why ) __field(size_t, len ) __field(loff_t, start ) diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 4d0bf02d490a..b40809c0bd74 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -94,7 +94,7 @@ netfs_failures; #define E_(a, b) { a, b } TRACE_EVENT(netfs_read, - TP_PROTO(struct netfs_read_request *rreq, + TP_PROTO(struct netfs_io_request *rreq, loff_t start, size_t len, enum netfs_read_trace what), @@ -127,7 +127,7 @@ TRACE_EVENT(netfs_read, ); TRACE_EVENT(netfs_rreq, - TP_PROTO(struct netfs_read_request *rreq, + TP_PROTO(struct netfs_io_request *rreq, enum netfs_rreq_trace what), TP_ARGS(rreq, what), @@ -151,7 +151,7 @@ TRACE_EVENT(netfs_rreq, ); TRACE_EVENT(netfs_sreq, - TP_PROTO(struct netfs_read_subrequest *sreq, + TP_PROTO(struct netfs_io_subrequest *sreq, enum netfs_sreq_trace what), TP_ARGS(sreq, what), @@ -161,7 +161,7 @@ TRACE_EVENT(netfs_sreq, __field(unsigned short, index ) __field(short, error ) __field(unsigned short, flags ) - __field(enum netfs_read_source, source ) + __field(enum netfs_io_source, source ) __field(enum netfs_sreq_trace, what ) __field(size_t, len ) __field(size_t, transferred ) @@ -190,8 +190,8 @@ TRACE_EVENT(netfs_sreq, ); TRACE_EVENT(netfs_failure, - TP_PROTO(struct netfs_read_request *rreq, - struct netfs_read_subrequest *sreq, + TP_PROTO(struct netfs_io_request *rreq, + struct netfs_io_subrequest *sreq, int error, enum netfs_failure what), TP_ARGS(rreq, sreq, error, what), @@ -201,7 +201,7 @@ TRACE_EVENT(netfs_failure, __field(unsigned short, index ) __field(short, error ) __field(unsigned short, flags ) - __field(enum netfs_read_source, source ) + __field(enum netfs_io_source, source ) __field(enum netfs_failure, what ) __field(size_t, len ) __field(size_t, transferred ) -- cgit v1.2.3 From f18a378580a761c8559b7d90afaa157269559c05 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 17 Feb 2022 10:14:32 +0000 Subject: netfs: Finish off rename of netfs_read_request to netfs_io_request Adjust helper function names and comments after mass rename of struct netfs_read_*request to struct netfs_io_*request. Changes ======= ver #2) - Make the changes in the docs also. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/164622992433.3564931.6684311087845150271.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/164678196111.1200972.5001114956865989528.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/164692892567.2099075.13895804222087028813.stgit@warthog.procyon.org.uk/ # v3 --- include/linux/netfs.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index a2ca91cb7a68..f63de27d6f29 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -131,7 +131,7 @@ struct netfs_cache_resources { * Descriptor for a single component subrequest. */ struct netfs_io_subrequest { - struct netfs_io_request *rreq; /* Supervising read request */ + struct netfs_io_request *rreq; /* Supervising I/O request */ struct list_head rreq_link; /* Link in rreq->subrequests */ loff_t start; /* Where to start the I/O */ size_t len; /* Size of the I/O */ @@ -139,29 +139,29 @@ struct netfs_io_subrequest { refcount_t usage; short error; /* 0 or error that occurred */ unsigned short debug_index; /* Index in list (for debugging output) */ - enum netfs_io_source source; /* Where to read from */ + enum netfs_io_source source; /* Where to read from/write to */ unsigned long flags; -#define NETFS_SREQ_WRITE_TO_CACHE 0 /* Set if should write to cache */ +#define NETFS_SREQ_COPY_TO_CACHE 0 /* Set if should copy the data to the cache */ #define NETFS_SREQ_CLEAR_TAIL 1 /* Set if the rest of the read should be cleared */ -#define NETFS_SREQ_SHORT_READ 2 /* Set if there was a short read from the cache */ +#define NETFS_SREQ_SHORT_IO 2 /* Set if the I/O was short */ #define NETFS_SREQ_SEEK_DATA_READ 3 /* Set if ->read() should SEEK_DATA first */ #define NETFS_SREQ_NO_PROGRESS 4 /* Set if we didn't manage to read any data */ }; /* - * Descriptor for a read helper request. This is used to make multiple I/O - * requests on a variety of sources and then stitch the result together. + * Descriptor for an I/O helper request. This is used to make multiple I/O + * operations to a variety of data stores and then stitch the result together. */ struct netfs_io_request { struct work_struct work; struct inode *inode; /* The file being accessed */ struct address_space *mapping; /* The mapping being accessed */ struct netfs_cache_resources cache_resources; - struct list_head subrequests; /* Requests to fetch I/O from disk or net */ + struct list_head subrequests; /* Contributory I/O operations */ void *netfs_priv; /* Private data for the netfs */ unsigned int debug_id; - atomic_t nr_outstanding; /* Number of read ops in progress */ - atomic_t nr_copy_ops; /* Number of write ops in progress */ + atomic_t nr_outstanding; /* Number of ops in progress */ + atomic_t nr_copy_ops; /* Number of copy-to-cache ops in progress */ size_t submitted; /* Amount submitted for I/O so far */ size_t len; /* Length of the request */ short error; /* 0 or error that occurred */ @@ -171,7 +171,7 @@ struct netfs_io_request { refcount_t usage; unsigned long flags; #define NETFS_RREQ_INCOMPLETE_IO 0 /* Some ioreqs terminated short or with error */ -#define NETFS_RREQ_WRITE_TO_CACHE 1 /* Need to write to the cache */ +#define NETFS_RREQ_COPY_TO_CACHE 1 /* Need to write to the cache */ #define NETFS_RREQ_NO_UNLOCK_FOLIO 2 /* Don't unlock no_unlock_folio on completion */ #define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ #define NETFS_RREQ_FAILED 4 /* The request failed */ @@ -188,7 +188,7 @@ struct netfs_request_ops { int (*begin_cache_operation)(struct netfs_io_request *rreq); void (*expand_readahead)(struct netfs_io_request *rreq); bool (*clamp_length)(struct netfs_io_subrequest *subreq); - void (*issue_op)(struct netfs_io_subrequest *subreq); + void (*issue_read)(struct netfs_io_subrequest *subreq); bool (*is_still_valid)(struct netfs_io_request *rreq); int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, struct folio *folio, void **_fsdata); -- cgit v1.2.3 From 18b3ff9fe8b857557fd02bfae0d91834b2c380ca Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 19 Feb 2022 23:05:40 +0000 Subject: netfs: Adjust the netfs_rreq tracepoint slightly Adjust the netfs_rreq tracepoint to include the origin of the request and to increase the size of the "what trace" output strings by a character so that "ENCRYPT" and "DECRYPT" will fit without abbreviation. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/164622996715.3564931.4252319907990358129.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/164678199468.1200972.17275585970238114726.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/164692898684.2099075.12153225958137716567.stgit@warthog.procyon.org.uk/ # v3 --- include/trace/events/netfs.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index b40809c0bd74..0c7a26c4d11c 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -22,13 +22,13 @@ E_(netfs_read_trace_write_begin, "WRITEBEGN") #define netfs_rreq_traces \ - EM(netfs_rreq_trace_assess, "ASSESS") \ - EM(netfs_rreq_trace_done, "DONE ") \ - EM(netfs_rreq_trace_free, "FREE ") \ - EM(netfs_rreq_trace_resubmit, "RESUBM") \ - EM(netfs_rreq_trace_unlock, "UNLOCK") \ - EM(netfs_rreq_trace_unmark, "UNMARK") \ - E_(netfs_rreq_trace_write, "WRITE ") + EM(netfs_rreq_trace_assess, "ASSESS ") \ + EM(netfs_rreq_trace_copy, "COPY ") \ + EM(netfs_rreq_trace_done, "DONE ") \ + EM(netfs_rreq_trace_free, "FREE ") \ + EM(netfs_rreq_trace_resubmit, "RESUBMT") \ + EM(netfs_rreq_trace_unlock, "UNLOCK ") \ + E_(netfs_rreq_trace_unmark, "UNMARK ") #define netfs_sreq_sources \ EM(NETFS_FILL_WITH_ZEROES, "ZERO") \ @@ -134,7 +134,7 @@ TRACE_EVENT(netfs_rreq, TP_STRUCT__entry( __field(unsigned int, rreq ) - __field(unsigned short, flags ) + __field(unsigned int, flags ) __field(enum netfs_rreq_trace, what ) ), @@ -182,8 +182,8 @@ TRACE_EVENT(netfs_sreq, TP_printk("R=%08x[%u] %s %s f=%02x s=%llx %zx/%zx e=%d", __entry->rreq, __entry->index, - __print_symbolic(__entry->what, netfs_sreq_traces), __print_symbolic(__entry->source, netfs_sreq_sources), + __print_symbolic(__entry->what, netfs_sreq_traces), __entry->flags, __entry->start, __entry->transferred, __entry->len, __entry->error) -- cgit v1.2.3 From de74023befa1876f64bc5871a2a4a51850517118 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 17 Feb 2022 21:13:05 +0000 Subject: netfs: Trace refcounting on the netfs_io_request struct Add refcount tracing for the netfs_io_request structure. Changes ======= ver #3) - Switch 'W=' to 'R=' in the traceline to match other request debug IDs. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/164622997668.3564931.14456171619219324968.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/164678200943.1200972.7241495532327787765.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/164692900920.2099075.11847712419940675791.stgit@warthog.procyon.org.uk/ # v3 --- include/linux/netfs.h | 2 +- include/trace/events/netfs.h | 35 +++++++++++++++++++++++++++++++++++ 2 files changed, 36 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index f63de27d6f29..541aebe828f3 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -168,7 +168,7 @@ struct netfs_io_request { loff_t i_size; /* Size of the file */ loff_t start; /* Start position */ pgoff_t no_unlock_folio; /* Don't unlock this folio after read */ - refcount_t usage; + refcount_t ref; unsigned long flags; #define NETFS_RREQ_INCOMPLETE_IO 0 /* Some ioreqs terminated short or with error */ #define NETFS_RREQ_COPY_TO_CACHE 1 /* Need to write to the cache */ diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 0c7a26c4d11c..e35a5ce52eb5 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -55,6 +55,15 @@ EM(netfs_fail_short_write_begin, "short-write-begin") \ E_(netfs_fail_prepare_write, "prep-write") +#define netfs_rreq_ref_traces \ + EM(netfs_rreq_trace_get_hold, "GET HOLD ") \ + EM(netfs_rreq_trace_get_subreq, "GET SUBREQ ") \ + EM(netfs_rreq_trace_put_complete, "PUT COMPLT ") \ + EM(netfs_rreq_trace_put_failed, "PUT FAILED ") \ + EM(netfs_rreq_trace_put_hold, "PUT HOLD ") \ + EM(netfs_rreq_trace_put_subreq, "PUT SUBREQ ") \ + E_(netfs_rreq_trace_new, "NEW ") + #ifndef __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY #define __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY @@ -67,6 +76,7 @@ enum netfs_read_trace { netfs_read_traces } __mode(byte); enum netfs_rreq_trace { netfs_rreq_traces } __mode(byte); enum netfs_sreq_trace { netfs_sreq_traces } __mode(byte); enum netfs_failure { netfs_failures } __mode(byte); +enum netfs_rreq_ref_trace { netfs_rreq_ref_traces } __mode(byte); #endif @@ -83,6 +93,7 @@ netfs_rreq_traces; netfs_sreq_sources; netfs_sreq_traces; netfs_failures; +netfs_rreq_ref_traces; /* * Now redefine the EM() and E_() macros to map the enums to the strings that @@ -229,6 +240,30 @@ TRACE_EVENT(netfs_failure, __entry->error) ); +TRACE_EVENT(netfs_rreq_ref, + TP_PROTO(unsigned int rreq_debug_id, int ref, + enum netfs_rreq_ref_trace what), + + TP_ARGS(rreq_debug_id, ref, what), + + TP_STRUCT__entry( + __field(unsigned int, rreq ) + __field(int, ref ) + __field(enum netfs_rreq_ref_trace, what ) + ), + + TP_fast_assign( + __entry->rreq = rreq_debug_id; + __entry->ref = ref; + __entry->what = what; + ), + + TP_printk("R=%08x %s r=%u", + __entry->rreq, + __print_symbolic(__entry->what, netfs_rreq_ref_traces), + __entry->ref) + ); + #undef EM #undef E_ #endif /* _TRACE_NETFS_H */ -- cgit v1.2.3 From 6cd3d6fd1fe2feae5ff9f6a821081569bb140bf4 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 17 Feb 2022 15:01:24 +0000 Subject: netfs: Trace refcounting on the netfs_io_subrequest struct Add refcount tracing for the netfs_io_subrequest structure. Changes ======= ver #3) - Switch 'W=' to 'R=' in the traceline to match other request debug IDs. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/164622998584.3564931.5052255990645723639.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/164678202603.1200972.14726007419792315578.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/164692901860.2099075.4845820886851239935.stgit@warthog.procyon.org.uk/ # v3 --- include/linux/netfs.h | 8 +++++++- include/trace/events/netfs.h | 40 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 47 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 541aebe828f3..c702bd8ea8da 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -18,6 +18,8 @@ #include #include +enum netfs_sreq_ref_trace; + /* * Overload PG_private_2 to give us PG_fscache - this is used to indicate that * a page is currently backed by a local disk cache @@ -136,7 +138,7 @@ struct netfs_io_subrequest { loff_t start; /* Where to start the I/O */ size_t len; /* Size of the I/O */ size_t transferred; /* Amount of data transferred */ - refcount_t usage; + refcount_t ref; short error; /* 0 or error that occurred */ unsigned short debug_index; /* Index in list (for debugging output) */ enum netfs_io_source source; /* Where to read from/write to */ @@ -268,6 +270,10 @@ extern int netfs_write_begin(struct file *, struct address_space *, void *); extern void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool); +extern void netfs_get_subrequest(struct netfs_io_subrequest *subreq, + enum netfs_sreq_ref_trace what); +extern void netfs_put_subrequest(struct netfs_io_subrequest *subreq, + bool was_async, enum netfs_sreq_ref_trace what); extern void netfs_stats_show(struct seq_file *); #endif /* _LINUX_NETFS_H */ diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index e35a5ce52eb5..dcea5e888fd0 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -64,6 +64,17 @@ EM(netfs_rreq_trace_put_subreq, "PUT SUBREQ ") \ E_(netfs_rreq_trace_new, "NEW ") +#define netfs_sreq_ref_traces \ + EM(netfs_sreq_trace_get_copy_to_cache, "GET COPY2C ") \ + EM(netfs_sreq_trace_get_resubmit, "GET RESUBMIT") \ + EM(netfs_sreq_trace_get_short_read, "GET SHORTRD") \ + EM(netfs_sreq_trace_new, "NEW ") \ + EM(netfs_sreq_trace_put_clear, "PUT CLEAR ") \ + EM(netfs_sreq_trace_put_failed, "PUT FAILED ") \ + EM(netfs_sreq_trace_put_merged, "PUT MERGED ") \ + EM(netfs_sreq_trace_put_no_copy, "PUT NO COPY") \ + E_(netfs_sreq_trace_put_terminated, "PUT TERM ") + #ifndef __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY #define __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY @@ -77,6 +88,7 @@ enum netfs_rreq_trace { netfs_rreq_traces } __mode(byte); enum netfs_sreq_trace { netfs_sreq_traces } __mode(byte); enum netfs_failure { netfs_failures } __mode(byte); enum netfs_rreq_ref_trace { netfs_rreq_ref_traces } __mode(byte); +enum netfs_sreq_ref_trace { netfs_sreq_ref_traces } __mode(byte); #endif @@ -94,6 +106,7 @@ netfs_sreq_sources; netfs_sreq_traces; netfs_failures; netfs_rreq_ref_traces; +netfs_sreq_ref_traces; /* * Now redefine the EM() and E_() macros to map the enums to the strings that @@ -264,6 +277,33 @@ TRACE_EVENT(netfs_rreq_ref, __entry->ref) ); +TRACE_EVENT(netfs_sreq_ref, + TP_PROTO(unsigned int rreq_debug_id, unsigned int subreq_debug_index, + int ref, enum netfs_sreq_ref_trace what), + + TP_ARGS(rreq_debug_id, subreq_debug_index, ref, what), + + TP_STRUCT__entry( + __field(unsigned int, rreq ) + __field(unsigned int, subreq ) + __field(int, ref ) + __field(enum netfs_sreq_ref_trace, what ) + ), + + TP_fast_assign( + __entry->rreq = rreq_debug_id; + __entry->subreq = subreq_debug_index; + __entry->ref = ref; + __entry->what = what; + ), + + TP_printk("R=%08x[%x] %s r=%u", + __entry->rreq, + __entry->subreq, + __print_symbolic(__entry->what, netfs_sreq_ref_traces), + __entry->ref) + ); + #undef EM #undef E_ #endif /* _TRACE_NETFS_H */ -- cgit v1.2.3 From 5c88705e2aeaee5521b8586e68bef47aab359914 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 25 Feb 2022 16:24:03 +0000 Subject: netfs: Adjust the netfs_failure tracepoint to indicate non-subreq lines Adjust the netfs_failure tracepoint to indicate a subrequest number of -1 when it's a full-request failure unrelated to any particular subrequest, such as a failure to encrypt its data buffer. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/164623001948.3564931.2353852999649380059.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/164678204587.1200972.14893513018190383961.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/164692903233.2099075.15414355147237641274.stgit@warthog.procyon.org.uk/ # v3 --- include/trace/events/netfs.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index dcea5e888fd0..556859b0f107 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -222,7 +222,7 @@ TRACE_EVENT(netfs_failure, TP_STRUCT__entry( __field(unsigned int, rreq ) - __field(unsigned short, index ) + __field(short, index ) __field(short, error ) __field(unsigned short, flags ) __field(enum netfs_io_source, source ) @@ -234,17 +234,17 @@ TRACE_EVENT(netfs_failure, TP_fast_assign( __entry->rreq = rreq->debug_id; - __entry->index = sreq ? sreq->debug_index : 0; + __entry->index = sreq ? sreq->debug_index : -1; __entry->error = error; __entry->flags = sreq ? sreq->flags : 0; __entry->source = sreq ? sreq->source : NETFS_INVALID_READ; __entry->what = what; - __entry->len = sreq ? sreq->len : 0; + __entry->len = sreq ? sreq->len : rreq->len; __entry->transferred = sreq ? sreq->transferred : 0; __entry->start = sreq ? sreq->start : 0; ), - TP_printk("R=%08x[%u] %s f=%02x s=%llx %zx/%zx %s e=%d", + TP_printk("R=%08x[%d] %s f=%02x s=%llx %zx/%zx %s e=%d", __entry->rreq, __entry->index, __print_symbolic(__entry->source, netfs_sreq_sources), __entry->flags, -- cgit v1.2.3 From 663dfb65c3b3ea4b8e1944680352992d58f3aa22 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 26 Aug 2021 09:24:42 -0400 Subject: netfs: Refactor arguments for netfs_alloc_read_request Pass start and len to the rreq allocator. This should ensure that the fields are set so that ->init_request() can use them. Also add a parameter to indicates the origin of the request. Ceph can use this to tell whether to get caps. Changes ======= ver #3) - Change the author to me as Jeff feels that most of the patch is my changes now. ver #2) - Show the request origin in the netfs_rreq tracepoint. Signed-off-by: Jeff Layton Co-developed-by: David Howells Signed-off-by: David Howells cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/164622989020.3564931.17517006047854958747.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/164678208569.1200972.12153682697842916557.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/164692904155.2099075.14717645623034355995.stgit@warthog.procyon.org.uk/ # v3 --- include/linux/netfs.h | 7 +++++++ include/trace/events/netfs.h | 11 ++++++++++- 2 files changed, 17 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index c702bd8ea8da..7dc741d9b21b 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -150,6 +150,12 @@ struct netfs_io_subrequest { #define NETFS_SREQ_NO_PROGRESS 4 /* Set if we didn't manage to read any data */ }; +enum netfs_io_origin { + NETFS_READAHEAD, /* This read was triggered by readahead */ + NETFS_READPAGE, /* This read is a synchronous read */ + NETFS_READ_FOR_WRITE, /* This read is to prepare a write */ +} __mode(byte); + /* * Descriptor for an I/O helper request. This is used to make multiple I/O * operations to a variety of data stores and then stitch the result together. @@ -167,6 +173,7 @@ struct netfs_io_request { size_t submitted; /* Amount submitted for I/O so far */ size_t len; /* Length of the request */ short error; /* 0 or error that occurred */ + enum netfs_io_origin origin; /* Origin of the request */ loff_t i_size; /* Size of the file */ loff_t start; /* Start position */ pgoff_t no_unlock_folio; /* Don't unlock this folio after read */ diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 556859b0f107..f00e3e1821c8 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -21,6 +21,11 @@ EM(netfs_read_trace_readpage, "READPAGE ") \ E_(netfs_read_trace_write_begin, "WRITEBEGN") +#define netfs_rreq_origins \ + EM(NETFS_READAHEAD, "RA") \ + EM(NETFS_READPAGE, "RP") \ + E_(NETFS_READ_FOR_WRITE, "RW") + #define netfs_rreq_traces \ EM(netfs_rreq_trace_assess, "ASSESS ") \ EM(netfs_rreq_trace_copy, "COPY ") \ @@ -101,6 +106,7 @@ enum netfs_sreq_ref_trace { netfs_sreq_ref_traces } __mode(byte); #define E_(a, b) TRACE_DEFINE_ENUM(a); netfs_read_traces; +netfs_rreq_origins; netfs_rreq_traces; netfs_sreq_sources; netfs_sreq_traces; @@ -159,17 +165,20 @@ TRACE_EVENT(netfs_rreq, TP_STRUCT__entry( __field(unsigned int, rreq ) __field(unsigned int, flags ) + __field(enum netfs_io_origin, origin ) __field(enum netfs_rreq_trace, what ) ), TP_fast_assign( __entry->rreq = rreq->debug_id; __entry->flags = rreq->flags; + __entry->origin = rreq->origin; __entry->what = what; ), - TP_printk("R=%08x %s f=%02x", + TP_printk("R=%08x %s %s f=%02x", __entry->rreq, + __print_symbolic(__entry->origin, netfs_rreq_origins), __print_symbolic(__entry->what, netfs_rreq_traces), __entry->flags) ); -- cgit v1.2.3 From 2de160417315b8d64455fe03e9bb7d3308ac3281 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 20 Jan 2022 21:55:46 +0000 Subject: netfs: Change ->init_request() to return an error code Change the request initialisation function to return an error code so that the network filesystem can return a failure (ENOMEM, for example). This will also allow ceph to abort a ->readahead() op if the server refuses to give it a cap allowing local caching from within the netfslib framework (errors aren't passed back through ->readahead(), so returning, say, -ENOBUFS will cause the op to be aborted). Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/164678212401.1200972.16537041523832944934.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/164692905398.2099075.5238033621684646524.stgit@warthog.procyon.org.uk/ # v3 --- include/linux/netfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 7dc741d9b21b..4b99e38f73d9 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -193,7 +193,7 @@ struct netfs_io_request { */ struct netfs_request_ops { bool (*is_cache_enabled)(struct inode *inode); - void (*init_request)(struct netfs_io_request *rreq, struct file *file); + int (*init_request)(struct netfs_io_request *rreq, struct file *file); int (*begin_cache_operation)(struct netfs_io_request *rreq); void (*expand_readahead)(struct netfs_io_request *rreq); bool (*clamp_length)(struct netfs_io_subrequest *subreq); -- cgit v1.2.3 From bc899ee1c898e520574ff4d99356eb2e724a9265 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 29 Jun 2021 22:37:05 +0100 Subject: netfs: Add a netfs inode context Add a netfs_i_context struct that should be included in the network filesystem's own inode struct wrapper, directly after the VFS's inode struct, e.g.: struct my_inode { struct { /* These must be contiguous */ struct inode vfs_inode; struct netfs_i_context netfs_ctx; }; }; The netfs_i_context struct so far contains a single field for the network filesystem to use - the cache cookie: struct netfs_i_context { ... struct fscache_cookie *cache; }; Three functions are provided to help with this: (1) void netfs_i_context_init(struct inode *inode, const struct netfs_request_ops *ops); Initialise the netfs context and set the operations. (2) struct netfs_i_context *netfs_i_context(struct inode *inode); Find the netfs context from the VFS inode. (3) struct inode *netfs_inode(struct netfs_i_context *ctx); Find the VFS inode from the netfs context. Changes ======= ver #4) - Fix netfs_is_cache_enabled() to check cookie->cache_priv to see if a cache is present[3]. - Fix netfs_skip_folio_read() to zero out all of the page, not just some of it[3]. ver #3) - Split out the bit to move ceph cap-getting on readahead into ceph_init_request()[1]. - Stick in a comment to the netfs inode structs indicating the contiguity requirements[2]. ver #2) - Adjust documentation to match. - Use "#if IS_ENABLED()" in netfs_i_cookie(), not "#ifdef". - Move the cap check from ceph_readahead() to ceph_init_request() to be called from netfslib. - Remove ceph_readahead() and use netfs_readahead() directly instead. Signed-off-by: David Howells Acked-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/8af0d47f17d89c06bbf602496dd845f2b0bf25b3.camel@kernel.org/ [1] Link: https://lore.kernel.org/r/beaf4f6a6c2575ed489adb14b257253c868f9a5c.camel@kernel.org/ [2] Link: https://lore.kernel.org/r/3536452.1647421585@warthog.procyon.org.uk/ [3] Link: https://lore.kernel.org/r/164622984545.3564931.15691742939278418580.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/164678213320.1200972.16807551936267647470.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/164692909854.2099075.9535537286264248057.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/306388.1647595110@warthog.procyon.org.uk/ # v4 --- include/linux/netfs.h | 81 ++++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 70 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 4b99e38f73d9..8458b30172a5 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -118,6 +118,16 @@ enum netfs_io_source { typedef void (*netfs_io_terminated_t)(void *priv, ssize_t transferred_or_error, bool was_async); +/* + * Per-inode description. This must be directly after the inode struct. + */ +struct netfs_i_context { + const struct netfs_request_ops *ops; +#if IS_ENABLED(CONFIG_FSCACHE) + struct fscache_cookie *cache; +#endif +}; + /* * Resources required to do operations on a cache. */ @@ -192,7 +202,6 @@ struct netfs_io_request { * Operations the network filesystem can/must provide to the helpers. */ struct netfs_request_ops { - bool (*is_cache_enabled)(struct inode *inode); int (*init_request)(struct netfs_io_request *rreq, struct file *file); int (*begin_cache_operation)(struct netfs_io_request *rreq); void (*expand_readahead)(struct netfs_io_request *rreq); @@ -263,18 +272,11 @@ struct netfs_cache_ops { }; struct readahead_control; -extern void netfs_readahead(struct readahead_control *, - const struct netfs_request_ops *, - void *); -extern int netfs_readpage(struct file *, - struct folio *, - const struct netfs_request_ops *, - void *); +extern void netfs_readahead(struct readahead_control *); +extern int netfs_readpage(struct file *, struct page *); extern int netfs_write_begin(struct file *, struct address_space *, loff_t, unsigned int, unsigned int, struct folio **, - void **, - const struct netfs_request_ops *, - void *); + void **); extern void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool); extern void netfs_get_subrequest(struct netfs_io_subrequest *subreq, @@ -283,4 +285,61 @@ extern void netfs_put_subrequest(struct netfs_io_subrequest *subreq, bool was_async, enum netfs_sreq_ref_trace what); extern void netfs_stats_show(struct seq_file *); +/** + * netfs_i_context - Get the netfs inode context from the inode + * @inode: The inode to query + * + * Get the netfs lib inode context from the network filesystem's inode. The + * context struct is expected to directly follow on from the VFS inode struct. + */ +static inline struct netfs_i_context *netfs_i_context(struct inode *inode) +{ + return (struct netfs_i_context *)(inode + 1); +} + +/** + * netfs_inode - Get the netfs inode from the inode context + * @ctx: The context to query + * + * Get the netfs inode from the netfs library's inode context. The VFS inode + * is expected to directly precede the context struct. + */ +static inline struct inode *netfs_inode(struct netfs_i_context *ctx) +{ + return ((struct inode *)ctx) - 1; +} + +/** + * netfs_i_context_init - Initialise a netfs lib context + * @inode: The inode with which the context is associated + * @ops: The netfs's operations list + * + * Initialise the netfs library context struct. This is expected to follow on + * directly from the VFS inode struct. + */ +static inline void netfs_i_context_init(struct inode *inode, + const struct netfs_request_ops *ops) +{ + struct netfs_i_context *ctx = netfs_i_context(inode); + + memset(ctx, 0, sizeof(*ctx)); + ctx->ops = ops; +} + +/** + * netfs_i_cookie - Get the cache cookie from the inode + * @inode: The inode to query + * + * Get the caching cookie (if enabled) from the network filesystem's inode. + */ +static inline struct fscache_cookie *netfs_i_cookie(struct inode *inode) +{ +#if IS_ENABLED(CONFIG_FSCACHE) + struct netfs_i_context *ctx = netfs_i_context(inode); + return ctx->cache; +#else + return NULL; +#endif +} + #endif /* _LINUX_NETFS_H */ -- cgit v1.2.3 From 4090b31422a6f24dfe701e31ffec7ba5804a7e2f Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 2 Mar 2022 10:50:22 +0000 Subject: netfs: Add a function to consolidate beginning a read Add a function to do the steps needed to begin a read request, allowing this code to be removed from several other functions and consolidated. Changes ======= ver #2) - Move before the unstaticking patch so that some functions can be left static. - Set uninitialised return code in netfs_begin_read()[1][2]. - Fixed a refleak caused by non-removal of a get from netfs_write_begin() when the request submission code got moved to netfs_begin_read(). - Use INIT_WORK() to (re-)init the request work_struct[3]. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20220303163826.1120936-1-nathan@kernel.org/ [1] Link: https://lore.kernel.org/r/20220303235647.1297171-1-colin.i.king@gmail.com/ [2] Link: https://lore.kernel.org/r/9d69be49081bccff44260e4c6e0049c63d6d04a1.camel@redhat.com/ [3] Link: https://lore.kernel.org/r/164623004355.3564931.7275693529042495641.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/164678214287.1200972.16734134007649832160.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/164692911113.2099075.1060868473229451371.stgit@warthog.procyon.org.uk/ # v3 --- include/trace/events/netfs.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index f00e3e1821c8..beec534cbaab 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -56,17 +56,18 @@ EM(netfs_fail_check_write_begin, "check-write-begin") \ EM(netfs_fail_copy_to_cache, "copy-to-cache") \ EM(netfs_fail_read, "read") \ - EM(netfs_fail_short_readpage, "short-readpage") \ - EM(netfs_fail_short_write_begin, "short-write-begin") \ + EM(netfs_fail_short_read, "short-read") \ E_(netfs_fail_prepare_write, "prep-write") #define netfs_rreq_ref_traces \ EM(netfs_rreq_trace_get_hold, "GET HOLD ") \ EM(netfs_rreq_trace_get_subreq, "GET SUBREQ ") \ EM(netfs_rreq_trace_put_complete, "PUT COMPLT ") \ + EM(netfs_rreq_trace_put_discard, "PUT DISCARD") \ EM(netfs_rreq_trace_put_failed, "PUT FAILED ") \ EM(netfs_rreq_trace_put_hold, "PUT HOLD ") \ EM(netfs_rreq_trace_put_subreq, "PUT SUBREQ ") \ + EM(netfs_rreq_trace_put_zero_len, "PUT ZEROLEN") \ E_(netfs_rreq_trace_new, "NEW ") #define netfs_sreq_ref_traces \ -- cgit v1.2.3 From 4058f742105ecfcbdf99e1139e6c1f74fb8e6db9 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 5 Nov 2021 13:55:38 +0000 Subject: netfs: Keep track of the actual remote file size Provide a place in which to keep track of the actual remote file size in the netfs context. This is needed because inode->i_size will be updated as we buffer writes in the pagecache, but the server file size won't get updated until we flush them back. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/164623013727.3564931.17659955636985232717.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/164678219305.1200972.6459431995188365134.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/164692921865.2099075.5310757978508056134.stgit@warthog.procyon.org.uk/ # v3 --- include/linux/netfs.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 8458b30172a5..c7bf1eaf51d5 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -126,6 +126,7 @@ struct netfs_i_context { #if IS_ENABLED(CONFIG_FSCACHE) struct fscache_cookie *cache; #endif + loff_t remote_i_size; /* Size of the remote file */ }; /* @@ -324,6 +325,21 @@ static inline void netfs_i_context_init(struct inode *inode, memset(ctx, 0, sizeof(*ctx)); ctx->ops = ops; + ctx->remote_i_size = i_size_read(inode); +} + +/** + * netfs_resize_file - Note that a file got resized + * @inode: The inode being resized + * @new_i_size: The new file size + * + * Inform the netfs lib that a file got resized so that it can adjust its state. + */ +static inline void netfs_resize_file(struct inode *inode, loff_t new_i_size) +{ + struct netfs_i_context *ctx = netfs_i_context(inode); + + ctx->remote_i_size = new_i_size; } /** -- cgit v1.2.3 From 54f586a9153201c6cff55e1f561990c78bd99aa7 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 16 Mar 2022 21:27:51 +0100 Subject: rfkill: make new event layout opt-in Again new complaints surfaced that we had broken the ABI here, although previously all the userspace tools had agreed that it was their mistake and fixed it. Yet now there are cases (e.g. RHEL) that want to run old userspace with newer kernels, and thus are broken. Since this is a bit of a whack-a-mole thing, change the whole extensibility scheme of rfkill to no longer just rely on the message lengths, but instead require userspace to opt in via a new ioctl to a given maximum event size that it is willing to understand. By default, set that to RFKILL_EVENT_SIZE_V1 (8), so that the behaviour for userspace not calling the ioctl will look as if it's just running on an older kernel. Fixes: 14486c82612a ("rfkill: add a reason to the HW rfkill state") Cc: stable@vger.kernel.org # 5.11+ Signed-off-by: Johannes Berg Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20220316212749.16491491b270.Ifcb1950998330a596f29a2a162e00b7546a1d6d0@changeid --- include/uapi/linux/rfkill.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/rfkill.h b/include/uapi/linux/rfkill.h index 9b77cfc42efa..283c5a7b3f2c 100644 --- a/include/uapi/linux/rfkill.h +++ b/include/uapi/linux/rfkill.h @@ -159,8 +159,16 @@ struct rfkill_event_ext { * old behaviour for all userspace, unless it explicitly opts in to the * rules outlined here by using the new &struct rfkill_event_ext. * - * Userspace using &struct rfkill_event_ext must adhere to the following - * rules + * Additionally, some other userspace (bluez, g-s-d) was reading with a + * large size but as streaming reads rather than message-based, or with + * too strict checks for the returned size. So eventually, we completely + * reverted this, and extended messages need to be opted in to by using + * an ioctl: + * + * ioctl(fd, RFKILL_IOCTL_MAX_SIZE, sizeof(struct rfkill_event_ext)); + * + * Userspace using &struct rfkill_event_ext and the ioctl must adhere to + * the following rules: * * 1. accept short writes, optionally using them to detect that it's * running on an older kernel; @@ -175,6 +183,8 @@ struct rfkill_event_ext { #define RFKILL_IOC_MAGIC 'R' #define RFKILL_IOC_NOINPUT 1 #define RFKILL_IOCTL_NOINPUT _IO(RFKILL_IOC_MAGIC, RFKILL_IOC_NOINPUT) +#define RFKILL_IOC_MAX_SIZE 2 +#define RFKILL_IOCTL_MAX_SIZE _IOW(RFKILL_IOC_MAGIC, RFKILL_IOC_EXT_SIZE, __u32) /* and that's all userspace gets */ -- cgit v1.2.3 From f58c252e30cf74f68b0054293adc03b5923b9f0e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 14 Mar 2022 11:14:32 +0200 Subject: serial: 8250: fix XOFF/XON sending when DMA is used MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When 8250 UART is using DMA, x_char (XON/XOFF) is never sent to the wire. After this change, x_char is injected correctly. Create uart_xchar_out() helper for sending the x_char out and accounting related to it. It seems that almost every driver does these same steps with x_char. Except for 8250, however, almost all currently lack .serial_out so they cannot immediately take advantage of this new helper. The downside of this patch is that it might reintroduce the problems some devices faced with mixed DMA/non-DMA transfer which caused revert f967fc8f165f (Revert "serial: 8250_dma: don't bother DMA with small transfers"). However, the impact should be limited to cases with XON/XOFF (that didn't work with DMA capable devices to begin with so this problem is not very likely to cause a major issue, if any at all). Fixes: 9ee4b83e51f74 ("serial: 8250: Add support for dmaengine") Reported-by: Gilles Buloz Tested-by: Gilles Buloz Reviewed-by: Andy Shevchenko Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20220314091432.4288-2-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 14ae35f68abb..d4828e69087a 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -458,6 +458,8 @@ extern void uart_handle_cts_change(struct uart_port *uport, extern void uart_insert_char(struct uart_port *port, unsigned int status, unsigned int overrun, unsigned int ch, unsigned int flag); +void uart_xchar_out(struct uart_port *uport, int offset); + #ifdef CONFIG_MAGIC_SYSRQ_SERIAL #define SYSRQ_TIMEOUT (HZ * 5) -- cgit v1.2.3 From 73799a889262b4675799bec20a2765be6d6a3f98 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Tue, 15 Mar 2022 15:38:54 -0400 Subject: counter: add new COUNTER_EVENT_CHANGE_OF_STATE Add new counter event to notify user space about every new counter pulse. Link: https://lore.kernel.org/r/20220203135727.2374052-2-o.rempel@pengutronix.de Signed-off-by: Oleksij Rempel Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/486a5de67414470449efb84d06a2f2214f4bb31d.1647373009.git.vilhelm.gray@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/counter.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/counter.h b/include/uapi/linux/counter.h index d0aa95aeff7b..96c5ffd368ad 100644 --- a/include/uapi/linux/counter.h +++ b/include/uapi/linux/counter.h @@ -61,6 +61,8 @@ enum counter_event_type { COUNTER_EVENT_THRESHOLD, /* Index signal detected */ COUNTER_EVENT_INDEX, + /* State of counter is changed */ + COUNTER_EVENT_CHANGE_OF_STATE, }; /** -- cgit v1.2.3 From 5c1b97c7d7b736e6439af4f43a65837bc72f56c1 Mon Sep 17 00:00:00 2001 From: Jeya R Date: Mon, 14 Feb 2022 16:09:52 +0000 Subject: misc: fastrpc: add support for FASTRPC_IOCTL_MEM_MAP/UNMAP Add support for IOCTL requests to map and unmap on DSP based on map flags. Signed-off-by: Jeya R Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20220214161002.6831-3-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/uapi/misc/fastrpc.h | 51 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) (limited to 'include') diff --git a/include/uapi/misc/fastrpc.h b/include/uapi/misc/fastrpc.h index 0a89f95463f6..d248eeb20e67 100644 --- a/include/uapi/misc/fastrpc.h +++ b/include/uapi/misc/fastrpc.h @@ -13,6 +13,37 @@ #define FASTRPC_IOCTL_MMAP _IOWR('R', 6, struct fastrpc_req_mmap) #define FASTRPC_IOCTL_MUNMAP _IOWR('R', 7, struct fastrpc_req_munmap) #define FASTRPC_IOCTL_INIT_ATTACH_SNS _IO('R', 8) +#define FASTRPC_IOCTL_MEM_MAP _IOWR('R', 10, struct fastrpc_mem_map) +#define FASTRPC_IOCTL_MEM_UNMAP _IOWR('R', 11, struct fastrpc_mem_unmap) + +/** + * enum fastrpc_map_flags - control flags for mapping memory on DSP user process + * @FASTRPC_MAP_STATIC: Map memory pages with RW- permission and CACHE WRITEBACK. + * The driver is responsible for cache maintenance when passed + * the buffer to FastRPC calls. Same virtual address will be + * assigned for subsequent FastRPC calls. + * @FASTRPC_MAP_RESERVED: Reserved + * @FASTRPC_MAP_FD: Map memory pages with RW- permission and CACHE WRITEBACK. + * Mapping tagged with a file descriptor. User is responsible for + * CPU and DSP cache maintenance for the buffer. Get virtual address + * of buffer on DSP using HAP_mmap_get() and HAP_mmap_put() APIs. + * @FASTRPC_MAP_FD_DELAYED: Mapping delayed until user call HAP_mmap() and HAP_munmap() + * functions on DSP. It is useful to map a buffer with cache modes + * other than default modes. User is responsible for CPU and DSP + * cache maintenance for the buffer. + * @FASTRPC_MAP_FD_NOMAP: This flag is used to skip CPU mapping, + * otherwise behaves similar to FASTRPC_MAP_FD_DELAYED flag. + * @FASTRPC_MAP_MAX: max count for flags + * + */ +enum fastrpc_map_flags { + FASTRPC_MAP_STATIC = 0, + FASTRPC_MAP_RESERVED, + FASTRPC_MAP_FD = 2, + FASTRPC_MAP_FD_DELAYED, + FASTRPC_MAP_FD_NOMAP = 16, + FASTRPC_MAP_MAX, +}; struct fastrpc_invoke_args { __u64 ptr; @@ -49,9 +80,29 @@ struct fastrpc_req_mmap { __u64 vaddrout; /* dsp virtual address */ }; +struct fastrpc_mem_map { + __s32 version; + __s32 fd; /* fd */ + __s32 offset; /* buffer offset */ + __u32 flags; /* flags defined in enum fastrpc_map_flags */ + __u64 vaddrin; /* buffer virtual address */ + __u64 length; /* buffer length */ + __u64 vaddrout; /* [out] remote virtual address */ + __s32 attrs; /* buffer attributes used for SMMU mapping */ + __s32 reserved[4]; +}; + struct fastrpc_req_munmap { __u64 vaddrout; /* address to unmap */ __u64 size; /* size */ }; +struct fastrpc_mem_unmap { + __s32 vesion; + __s32 fd; /* fd */ + __u64 vaddr; /* remote process (dsp) virtual address */ + __u64 length; /* buffer size */ + __s32 reserved[5]; +}; + #endif /* __QCOM_FASTRPC_H__ */ -- cgit v1.2.3 From 6c16fd8bdd4058d4a6aaca9d5a7b40e4cb281d5a Mon Sep 17 00:00:00 2001 From: Jeya R Date: Mon, 14 Feb 2022 16:09:53 +0000 Subject: misc: fastrpc: Add support to get DSP capabilities Add support to get DSP capabilities. The capability information is cached on driver. Signed-off-by: Jeya R Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20220214161002.6831-4-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/uapi/misc/fastrpc.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/uapi/misc/fastrpc.h b/include/uapi/misc/fastrpc.h index d248eeb20e67..7cc9d342078a 100644 --- a/include/uapi/misc/fastrpc.h +++ b/include/uapi/misc/fastrpc.h @@ -15,6 +15,7 @@ #define FASTRPC_IOCTL_INIT_ATTACH_SNS _IO('R', 8) #define FASTRPC_IOCTL_MEM_MAP _IOWR('R', 10, struct fastrpc_mem_map) #define FASTRPC_IOCTL_MEM_UNMAP _IOWR('R', 11, struct fastrpc_mem_unmap) +#define FASTRPC_IOCTL_GET_DSP_INFO _IOWR('R', 13, struct fastrpc_ioctl_capability) /** * enum fastrpc_map_flags - control flags for mapping memory on DSP user process @@ -105,4 +106,11 @@ struct fastrpc_mem_unmap { __s32 reserved[5]; }; +struct fastrpc_ioctl_capability { + __u32 domain; + __u32 attribute_id; + __u32 capability; /* dsp capability */ + __u32 reserved[4]; +}; + #endif /* __QCOM_FASTRPC_H__ */ -- cgit v1.2.3 From 7f1f481263c3ce5387d4fd5ad63ddaa8a295aab2 Mon Sep 17 00:00:00 2001 From: Jeya R Date: Mon, 14 Feb 2022 16:09:56 +0000 Subject: misc: fastrpc: check before loading process to the DSP Reject session if DSP domain is secure, device node is non-secure and signed PD is requested. Secure device node can access DSP without any restriction. Unsigned PD offload is only allowed for the DSP domain that can support unsigned offloading. Signed-off-by: Jeya R Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20220214161002.6831-7-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/uapi/misc/fastrpc.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/uapi/misc/fastrpc.h b/include/uapi/misc/fastrpc.h index 7cc9d342078a..f39edac20305 100644 --- a/include/uapi/misc/fastrpc.h +++ b/include/uapi/misc/fastrpc.h @@ -46,6 +46,23 @@ enum fastrpc_map_flags { FASTRPC_MAP_MAX, }; +enum fastrpc_proc_attr { + /* Macro for Debug attr */ + FASTRPC_MODE_DEBUG = (1 << 0), + /* Macro for Ptrace */ + FASTRPC_MODE_PTRACE = (1 << 1), + /* Macro for CRC Check */ + FASTRPC_MODE_CRC = (1 << 2), + /* Macro for Unsigned PD */ + FASTRPC_MODE_UNSIGNED_MODULE = (1 << 3), + /* Macro for Adaptive QoS */ + FASTRPC_MODE_ADAPTIVE_QOS = (1 << 4), + /* Macro for System Process */ + FASTRPC_MODE_SYSTEM_PROCESS = (1 << 5), + /* Macro for Prvileged Process */ + FASTRPC_MODE_PRIVILEGED = (1 << 6), +}; + struct fastrpc_invoke_args { __u64 ptr; __u64 length; -- cgit v1.2.3 From e90d911906196bf987492c94e38f10ca611dfd7b Mon Sep 17 00:00:00 2001 From: Vamsi Krishna Gattupalli Date: Mon, 14 Feb 2022 16:09:58 +0000 Subject: misc: fastrpc: Add support to secure memory map This patch adds support to secure memory allocations for DSP. It repurposes the reserved field in struct fastrpc_invoke_args to add attributes to invoke request, for example to setup a secure memory map for dsp. Secure memory is assigned to DSP Virtual Machine IDs using Qualcomm SCM calls. Signed-off-by: Vamsi Krishna Gattupalli Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20220214161002.6831-9-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/uapi/misc/fastrpc.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/misc/fastrpc.h b/include/uapi/misc/fastrpc.h index f39edac20305..5e29f2cfa42d 100644 --- a/include/uapi/misc/fastrpc.h +++ b/include/uapi/misc/fastrpc.h @@ -63,11 +63,14 @@ enum fastrpc_proc_attr { FASTRPC_MODE_PRIVILEGED = (1 << 6), }; +/* Fastrpc attribute for memory protection of buffers */ +#define FASTRPC_ATTR_SECUREMAP (1) + struct fastrpc_invoke_args { __u64 ptr; __u64 length; __s32 fd; - __u32 reserved; + __u32 attr; }; struct fastrpc_invoke { -- cgit v1.2.3 From 336d4b814bf078fa698488632c19beca47308896 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 27 Jan 2022 12:15:32 -0600 Subject: ptrace: Move setting/clearing ptrace_message into ptrace_stop Today ptrace_message is easy to overlook as it not a core part of ptrace_stop. It has been overlooked so much that there are places that set ptrace_message and don't clear it, and places that never set it. So if you get an unlucky sequence of events the ptracer may be able to read a ptrace_message that does not apply to the current ptrace stop. Move setting of ptrace_message into ptrace_stop so that it always gets set before the stop, and always gets cleared after the stop. This prevents non-sense from being reported to userspace and makes ptrace_message more visible in the ptrace helper functions so that kernel developers can see it. Link: https://lkml.kernel.org/r/87bky67qfv.fsf_-_@email.froward.int.ebiederm.org Acked-by: Oleg Nesterov Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- include/linux/ptrace.h | 9 +++------ include/uapi/linux/ptrace.h | 2 +- 2 files changed, 4 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 5310f43e4762..3e6b46e2b7be 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -60,7 +60,7 @@ extern int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned extern void ptrace_disable(struct task_struct *); extern int ptrace_request(struct task_struct *child, long request, unsigned long addr, unsigned long data); -extern void ptrace_notify(int exit_code); +extern void ptrace_notify(int exit_code, unsigned long message); extern void __ptrace_link(struct task_struct *child, struct task_struct *new_parent, const struct cred *ptracer_cred); @@ -155,8 +155,7 @@ static inline bool ptrace_event_enabled(struct task_struct *task, int event) static inline void ptrace_event(int event, unsigned long message) { if (unlikely(ptrace_event_enabled(current, event))) { - current->ptrace_message = message; - ptrace_notify((event << 8) | SIGTRAP); + ptrace_notify((event << 8) | SIGTRAP, message); } else if (event == PTRACE_EVENT_EXEC) { /* legacy EXEC report via SIGTRAP */ if ((current->ptrace & (PT_PTRACED|PT_SEIZED)) == PT_PTRACED) @@ -424,8 +423,7 @@ static inline int ptrace_report_syscall(unsigned long message) if (!(ptrace & PT_PTRACED)) return 0; - current->ptrace_message = message; - ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0)); + ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0), message); /* * this isn't the same as continuing with a signal, but it will do @@ -437,7 +435,6 @@ static inline int ptrace_report_syscall(unsigned long message) current->exit_code = 0; } - current->ptrace_message = 0; return fatal_signal_pending(current); } diff --git a/include/uapi/linux/ptrace.h b/include/uapi/linux/ptrace.h index b7af92e07d1f..195ae64a8c87 100644 --- a/include/uapi/linux/ptrace.h +++ b/include/uapi/linux/ptrace.h @@ -114,7 +114,7 @@ struct ptrace_rseq_configuration { /* * These values are stored in task->ptrace_message - * by ptrace_report_syscall_* to describe the current syscall-stop. + * by ptrace_stop to describe the current syscall-stop. */ #define PTRACE_EVENTMSG_SYSCALL_ENTRY 1 #define PTRACE_EVENTMSG_SYSCALL_EXIT 2 -- cgit v1.2.3 From 6487d1dab837214ec2fd3f0ddd5f787e63be7c20 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 27 Jan 2022 12:19:13 -0600 Subject: ptrace: Return the signal to continue with from ptrace_stop The signal a task should continue with after a ptrace stop is inconsistently read, cleared, and sent. Solve this by reading and clearing the signal to be sent in ptrace_stop. In an ideal world everything except ptrace_signal would share a common implementation of continuing with the signal, so ptracers could count on the signal they ask to continue with actually being delivered. For now retain bug compatibility and just return with the signal number the ptracer requested the code continue with. Link: https://lkml.kernel.org/r/875yoe7qdp.fsf_-_@email.froward.int.ebiederm.org Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- include/linux/ptrace.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 3e6b46e2b7be..15b3d176b6b4 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -60,7 +60,7 @@ extern int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned extern void ptrace_disable(struct task_struct *); extern int ptrace_request(struct task_struct *child, long request, unsigned long addr, unsigned long data); -extern void ptrace_notify(int exit_code, unsigned long message); +extern int ptrace_notify(int exit_code, unsigned long message); extern void __ptrace_link(struct task_struct *child, struct task_struct *new_parent, const struct cred *ptracer_cred); @@ -419,21 +419,21 @@ extern void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oa static inline int ptrace_report_syscall(unsigned long message) { int ptrace = current->ptrace; + int signr; if (!(ptrace & PT_PTRACED)) return 0; - ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0), message); + signr = ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0), + message); /* * this isn't the same as continuing with a signal, but it will do * for normal use. strace only continues with a signal if the * stopping signal is not SIGTRAP. -brl */ - if (current->exit_code) { - send_sig(current->exit_code, current, 1); - current->exit_code = 0; - } + if (signr) + send_sig(signr, current, 1); return fatal_signal_pending(current); } -- cgit v1.2.3 From 0eaecfb2e4814d51ab172df3823e35d7c488b6d2 Mon Sep 17 00:00:00 2001 From: Ismael Ferreras Morezuelas Date: Mon, 7 Mar 2022 21:04:44 +0100 Subject: Bluetooth: hci_sync: Add a new quirk to skip HCI_FLT_CLEAR_ALL Some controllers have problems with being sent a command to clear all filtering. While the HCI code does not unconditionally send a clear-all anymore at BR/EDR setup (after the state machine refactor), there might be more ways of hitting these codepaths in the future as the kernel develops. Cc: stable@vger.kernel.org Cc: Hans de Goede Signed-off-by: Ismael Ferreras Morezuelas Reviewed-by: Hans de Goede Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 35c073d44ec5..5cb095b09a94 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -255,6 +255,16 @@ enum { * during the hdev->setup vendor callback. */ HCI_QUIRK_BROKEN_READ_TRANSMIT_POWER, + + /* When this quirk is set, HCI_OP_SET_EVENT_FLT requests with + * HCI_FLT_CLEAR_ALL are ignored and event filtering is + * completely avoided. A subset of the CSR controller + * clones struggle with this and instantly lock up. + * + * Note that devices using this must (separately) disable + * runtime suspend, because event filtering takes place there. + */ + HCI_QUIRK_BROKEN_FILTER_CLEAR_ALL, }; /* HCI device flags */ -- cgit v1.2.3 From da8912176fb0ff9fd60e14fa653108d96422b896 Mon Sep 17 00:00:00 2001 From: Gavin Li Date: Mon, 14 Mar 2022 15:42:52 -0700 Subject: Bluetooth: fix incorrect nonblock bitmask in bt_sock_wait_ready() Callers pass msg->msg_flags as flags, which contains MSG_DONTWAIT instead of O_NONBLOCK. Signed-off-by: Gavin Li Signed-off-by: Marcel Holtmann --- include/net/bluetooth/bluetooth.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 2aa5e95808a5..6b48d9e2aab9 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -345,7 +345,7 @@ int bt_sock_stream_recvmsg(struct socket *sock, struct msghdr *msg, __poll_t bt_sock_poll(struct file *file, struct socket *sock, poll_table *wait); int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo); -int bt_sock_wait_ready(struct sock *sk, unsigned long flags); +int bt_sock_wait_ready(struct sock *sk, unsigned int msg_flags); void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh); void bt_accept_unlink(struct sock *sk); -- cgit v1.2.3 From 86fc59ef818beb0e1945d17f8e734898baba7e4e Mon Sep 17 00:00:00 2001 From: Colin Foster Date: Sun, 13 Mar 2022 15:45:23 -0700 Subject: regmap: add configurable downshift for addresses Add an additional reg_downshift to be applied to register addresses before any register accesses. An example of a device that uses this is a VSC7514 chip, which require each register address to be downshifted by two if the access is performed over a SPI bus. Signed-off-by: Colin Foster Link: https://lore.kernel.org/r/20220313224524.399947-2-colin.foster@in-advantage.com Signed-off-by: Mark Brown --- include/linux/regmap.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 22652e5fbc38..40fb9399add6 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -237,6 +237,8 @@ typedef void (*regmap_unlock)(void *); * @reg_stride: The register address stride. Valid register addresses are a * multiple of this value. If set to 0, a value of 1 will be * used. + * @reg_downshift: The number of bits to downshift the register before + * performing any operations. * @pad_bits: Number of bits of padding between register and value. * @val_bits: Number of bits in a register value, mandatory. * @@ -360,6 +362,7 @@ struct regmap_config { int reg_bits; int reg_stride; + int reg_downshift; int pad_bits; int val_bits; -- cgit v1.2.3 From 0074f3f2b1e43d3cedd97e47fb6980db6d2ba79e Mon Sep 17 00:00:00 2001 From: Colin Foster Date: Sun, 13 Mar 2022 15:45:24 -0700 Subject: regmap: allow a defined reg_base to be added to every address There's an inconsistency that arises when a register set can be accessed internally via MMIO, or externally via SPI. The VSC7514 chip allows both modes of operation. When internally accessed, the system utilizes __iomem, devm_ioremap_resource, and devm_regmap_init_mmio. For SPI it isn't possible to utilize memory-mapped IO. To properly operate, the resource base must be added to the register before every operation. Signed-off-by: Colin Foster Link: https://lore.kernel.org/r/20220313224524.399947-3-colin.foster@in-advantage.com Signed-off-by: Mark Brown --- include/linux/regmap.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 40fb9399add6..de81a94d7b30 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -239,6 +239,8 @@ typedef void (*regmap_unlock)(void *); * used. * @reg_downshift: The number of bits to downshift the register before * performing any operations. + * @reg_base: Value to be added to every register address before performing any + * operation. * @pad_bits: Number of bits of padding between register and value. * @val_bits: Number of bits in a register value, mandatory. * @@ -363,6 +365,7 @@ struct regmap_config { int reg_bits; int reg_stride; int reg_downshift; + unsigned int reg_base; int pad_bits; int val_bits; -- cgit v1.2.3 From 046e1537a3cf0adc68fe865b5dc9a7e731cc63b3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=8D=C3=B1igo=20Huguet?= Date: Tue, 15 Mar 2022 10:18:32 +0100 Subject: net: set default rss queues num to physical cores / 2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Network drivers can call to netif_get_num_default_rss_queues to get the default number of receive queues to use. Right now, this default number is min(8, num_online_cpus()). Instead, as suggested by Jakub, use the number of physical cores divided by 2 as a way to avoid wasting CPU resources and to avoid using both CPU threads, but still allowing to scale for high-end processors with many cores. As an exception, select 2 queues for processors with 2 cores, because otherwise it won't take any advantage of RSS despite being SMP capable. Tested: Processor Intel Xeon E5-2620 (2 sockets, 6 cores/socket, 2 threads/core). NIC Broadcom NetXtreme II BCM57810 (10GBps). Ran some tests with `perf stat iperf3 -R`, with parallelisms of 1, 8 and 24, getting the following results: - Number of queues: 6 (instead of 8) - Network throughput: not affected - CPU usage: utilized 0.05-0.12 CPUs more than before (having 24 CPUs this is only 0.2-0.5% higher) - Reduced the number of context switches by 7-50%, being more noticeable when using a higher number of parallel threads. Suggested-by: Jakub Kicinski Signed-off-by: Íñigo Huguet Link: https://lore.kernel.org/r/20220315091832.13873-1-ihuguet@redhat.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8cbe96ce0a2c..e01a8ce7181f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3664,7 +3664,6 @@ static inline unsigned int get_netdev_rx_queue_index( } #endif -#define DEFAULT_MAX_NUM_RSS_QUEUES (8) int netif_get_num_default_rss_queues(void); enum skb_free_reason { -- cgit v1.2.3 From 0c125f87a84097c182c481be7497af9f816e5db5 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sat, 26 Feb 2022 05:07:22 +0100 Subject: clk: fixed-factor: Introduce devm_clk_hw_register_fixed_factor_index() Add an API for a fixed factor clk that uses an index for the parent instead of a string name. This allows us to move drivers away from the string based method of describing parents and use the DT/firmware based method instead. Signed-off-by: Marek Vasut Cc: Michael Turquette Cc: Rob Herring Cc: Stephen Boyd Cc: devicetree@vger.kernel.org Link: https://lore.kernel.org/r/20220226040723.143705-2-marex@denx.de [sboyd@kernel.org: Expose a new API instead of internal function] Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 2faa6f7aa8a8..b7a7923f6bbb 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1003,6 +1003,9 @@ void clk_hw_unregister_fixed_factor(struct clk_hw *hw); struct clk_hw *devm_clk_hw_register_fixed_factor(struct device *dev, const char *name, const char *parent_name, unsigned long flags, unsigned int mult, unsigned int div); +struct clk_hw *devm_clk_hw_register_fixed_factor_index(struct device *dev, + const char *name, unsigned int index, unsigned long flags, + unsigned int mult, unsigned int div); /** * struct clk_fractional_divider - adjustable fractional divider clock * -- cgit v1.2.3 From d714fb25e755ad96b699993fac47f48c4d6cebe9 Mon Sep 17 00:00:00 2001 From: Jae Hyun Yoo Date: Fri, 18 Mar 2022 13:41:33 -0700 Subject: i2c: add tracepoints for I2C slave events I2C slave events tracepoints can be enabled by: echo 1 > /sys/kernel/tracing/events/i2c_slave/enable and logs in /sys/kernel/tracing/trace will look like: ... i2c_slave: i2c-0 a=010 ret=0 WR_REQ [] ... i2c_slave: i2c-0 a=010 ret=0 WR_RCV [02] ... i2c_slave: i2c-0 a=010 ret=0 WR_RCV [0c] ... i2c_slave: i2c-0 a=010 ret=0 STOP [] ... i2c_slave: i2c-0 a=010 ret=0 RD_REQ [04] ... i2c_slave: i2c-0 a=010 ret=0 RD_PRO [b4] ... i2c_slave: i2c-0 a=010 ret=0 STOP [] formatted as: i2c- a= ret= <- callback return value [] trace printings can be selected by adding a filter like: echo adapter_nr==1 >/sys/kernel/tracing/events/i2c_slave/filter Signed-off-by: Jae Hyun Yoo Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 8 ++--- include/trace/events/i2c_slave.h | 67 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 69 insertions(+), 6 deletions(-) create mode 100644 include/trace/events/i2c_slave.h (limited to 'include') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 7d4f52ceb7b5..fbda5ada2afc 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -392,12 +392,8 @@ enum i2c_slave_event { int i2c_slave_register(struct i2c_client *client, i2c_slave_cb_t slave_cb); int i2c_slave_unregister(struct i2c_client *client); bool i2c_detect_slave_mode(struct device *dev); - -static inline int i2c_slave_event(struct i2c_client *client, - enum i2c_slave_event event, u8 *val) -{ - return client->slave_cb(client, event, val); -} +int i2c_slave_event(struct i2c_client *client, + enum i2c_slave_event event, u8 *val); #else static inline bool i2c_detect_slave_mode(struct device *dev) { return false; } #endif diff --git a/include/trace/events/i2c_slave.h b/include/trace/events/i2c_slave.h new file mode 100644 index 000000000000..811166abbe3a --- /dev/null +++ b/include/trace/events/i2c_slave.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * I2C slave tracepoints + * + * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM i2c_slave + +#if !defined(_TRACE_I2C_SLAVE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_I2C_SLAVE_H + +#include +#include + +TRACE_DEFINE_ENUM(I2C_SLAVE_READ_REQUESTED); +TRACE_DEFINE_ENUM(I2C_SLAVE_WRITE_REQUESTED); +TRACE_DEFINE_ENUM(I2C_SLAVE_READ_PROCESSED); +TRACE_DEFINE_ENUM(I2C_SLAVE_WRITE_RECEIVED); +TRACE_DEFINE_ENUM(I2C_SLAVE_STOP); + +#define show_event_type(type) \ + __print_symbolic(type, \ + { I2C_SLAVE_READ_REQUESTED, "RD_REQ" }, \ + { I2C_SLAVE_WRITE_REQUESTED, "WR_REQ" }, \ + { I2C_SLAVE_READ_PROCESSED, "RD_PRO" }, \ + { I2C_SLAVE_WRITE_RECEIVED, "WR_RCV" }, \ + { I2C_SLAVE_STOP, " STOP" }) + +TRACE_EVENT(i2c_slave, + TP_PROTO(const struct i2c_client *client, enum i2c_slave_event event, + __u8 *val, int cb_ret), + TP_ARGS(client, event, val, cb_ret), + TP_STRUCT__entry( + __field(int, adapter_nr ) + __field(int, ret ) + __field(__u16, addr ) + __field(__u16, len ) + __field(enum i2c_slave_event, event ) + __array(__u8, buf, 1) ), + + TP_fast_assign( + __entry->adapter_nr = client->adapter->nr; + __entry->addr = client->addr; + __entry->event = event; + __entry->ret = cb_ret; + switch (event) { + case I2C_SLAVE_READ_REQUESTED: + case I2C_SLAVE_READ_PROCESSED: + case I2C_SLAVE_WRITE_RECEIVED: + __entry->len = 1; + memcpy(__entry->buf, val, __entry->len); + break; + default: + __entry->len = 0; + break; + } + ), + TP_printk("i2c-%d a=%03x ret=%d %s [%*phD]", + __entry->adapter_nr, __entry->addr, __entry->ret, + show_event_type(__entry->event), __entry->len, __entry->buf + )); + +#endif /* _TRACE_I2C_SLAVE_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From 31d0bb9763efad30377505f3467f958d1ebe1e3d Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Wed, 2 Mar 2022 22:02:55 +0100 Subject: netfilter: conntrack: Add and use nf_ct_set_auto_assign_helper_warned() The function sets the pernet boolean to avoid the spurious warning from nf_ct_lookup_helper() when assigning conntrack helpers via nftables. Fixes: 1a64edf54f55 ("netfilter: nft_ct: add helper set support") Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_helper.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index 37f0fbefb060..9939c366f720 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -177,4 +177,5 @@ void nf_nat_helper_unregister(struct nf_conntrack_nat_helper *nat); int nf_nat_helper_try_module_get(const char *name, u16 l3num, u8 protonum); void nf_nat_helper_put(struct nf_conntrack_helper *helper); +void nf_ct_set_auto_assign_helper_warned(struct net *net); #endif /*_NF_CONNTRACK_HELPER_H*/ -- cgit v1.2.3 From b2d306542ff935a4edf7a88ba8145c108193442a Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 14 Mar 2022 18:23:00 +0100 Subject: netfilter: nf_tables: do not reduce read-only expressions Skip register tracking for expressions that perform read-only operations on the registers. Define and use a cookie pointer NFT_REDUCE_READONLY to avoid defining stubs for these expressions. This patch re-enables register tracking which was disabled in ed5f85d42290 ("netfilter: nf_tables: disable register tracking"). Follow up patches add remaining register tracking for existing expressions. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index c4c0861deac1..edabfb9e97ce 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1633,4 +1633,12 @@ static inline struct nftables_pernet *nft_pernet(const struct net *net) return net_generic(net, nf_tables_net_id); } +#define __NFT_REDUCE_READONLY 1UL +#define NFT_REDUCE_READONLY (void *)__NFT_REDUCE_READONLY + +static inline bool nft_reduce_is_readonly(const struct nft_expr *expr) +{ + return expr->ops->reduce == NFT_REDUCE_READONLY; +} + #endif /* _NET_NF_TABLES_H */ -- cgit v1.2.3 From 34cc9e52884a16c62acbfb309863fb60e4c24f55 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 14 Mar 2022 18:23:01 +0100 Subject: netfilter: nf_tables: cancel tracking for clobbered destination registers Output of expressions might be larger than one single register, this might clobber existing data. Reset tracking for all destination registers that required to store the expression output. This patch adds three new helper functions: - nft_reg_track_update: cancel previous register tracking and update it. - nft_reg_track_cancel: cancel any previous register tracking info. - __nft_reg_track_cancel: cancel only one single register tracking info. Partial register clobbering detection is also supported by checking the .num_reg field which describes the number of register that are used. This patch updates the following expressions: - meta_bridge - bitwise - byteorder - meta - payload to use these helper functions. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 14 ++++++++++++++ include/net/netfilter/nft_meta.h | 1 + 2 files changed, 15 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index edabfb9e97ce..20af9d3557b9 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -126,6 +126,7 @@ struct nft_regs_track { struct { const struct nft_expr *selector; const struct nft_expr *bitwise; + u8 num_reg; } regs[NFT_REG32_NUM]; const struct nft_expr *cur; @@ -1641,4 +1642,17 @@ static inline bool nft_reduce_is_readonly(const struct nft_expr *expr) return expr->ops->reduce == NFT_REDUCE_READONLY; } +void nft_reg_track_update(struct nft_regs_track *track, + const struct nft_expr *expr, u8 dreg, u8 len); +void nft_reg_track_cancel(struct nft_regs_track *track, u8 dreg, u8 len); +void __nft_reg_track_cancel(struct nft_regs_track *track, u8 dreg); + +static inline bool nft_reg_track_cmp(struct nft_regs_track *track, + const struct nft_expr *expr, u8 dreg) +{ + return track->regs[dreg].selector && + track->regs[dreg].selector->ops == expr->ops && + track->regs[dreg].num_reg == 0; +} + #endif /* _NET_NF_TABLES_H */ diff --git a/include/net/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h index 2dce55c736f4..246fd023dcf4 100644 --- a/include/net/netfilter/nft_meta.h +++ b/include/net/netfilter/nft_meta.h @@ -6,6 +6,7 @@ struct nft_meta { enum nft_meta_keys key:8; + u8 len; union { u8 dreg; u8 sreg; -- cgit v1.2.3 From aaa7b20bd4d637fd4ef0d72b6c828c061b9bc5f7 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 14 Mar 2022 18:23:04 +0100 Subject: netfilter: nft_meta: extend reduce support to bridge family its enough to export the meta get reduce helper and then call it from nft_meta_bridge too. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nft_meta.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h index 246fd023dcf4..9b51cc67de54 100644 --- a/include/net/netfilter/nft_meta.h +++ b/include/net/netfilter/nft_meta.h @@ -44,4 +44,6 @@ int nft_meta_set_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data); +bool nft_meta_get_reduce(struct nft_regs_track *track, + const struct nft_expr *expr); #endif -- cgit v1.2.3 From 3c1eb413a45b6c6327fed394705081ec6202b31a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 14 Mar 2022 18:23:12 +0100 Subject: netfilter: nft_fib: add reduce support The fib expression stores to a register, so we can't add empty stub. Check that the register that is being written is in fact redundant. In most cases, this is expected to cancel tracking as re-use is unlikely. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nft_fib.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nft_fib.h b/include/net/netfilter/nft_fib.h index 237f3757637e..eed099eae672 100644 --- a/include/net/netfilter/nft_fib.h +++ b/include/net/netfilter/nft_fib.h @@ -37,4 +37,7 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, void nft_fib_store_result(void *reg, const struct nft_fib *priv, const struct net_device *dev); + +bool nft_fib_reduce(struct nft_regs_track *track, + const struct nft_expr *expr); #endif -- cgit v1.2.3 From b00fa38a9c1cba044a32a601b49a55a18ed719d1 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Thu, 17 Mar 2022 21:55:52 -0700 Subject: bpf: Enable non-atomic allocations in local storage Currently, local storage memory can only be allocated atomically (GFP_ATOMIC). This restriction is too strict for sleepable bpf programs. In this patch, the verifier detects whether the program is sleepable, and passes the corresponding GFP_KERNEL or GFP_ATOMIC flag as a 5th argument to bpf_task/sk/inode_storage_get. This flag will propagate down to the local storage functions that allocate memory. Please note that bpf_task/sk/inode_storage_update_elem functions are invoked by userspace applications through syscalls. Preemption is disabled before bpf_task/sk/inode_storage_update_elem is called, which means they will always have to allocate memory atomically. Signed-off-by: Joanne Koong Signed-off-by: Alexei Starovoitov Acked-by: KP Singh Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20220318045553.3091807-2-joannekoong@fb.com --- include/linux/bpf_local_storage.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 37b3906af8b1..493e63258497 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -154,16 +154,17 @@ void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem); struct bpf_local_storage_elem * bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, - bool charge_mem); + bool charge_mem, gfp_t gfp_flags); int bpf_local_storage_alloc(void *owner, struct bpf_local_storage_map *smap, - struct bpf_local_storage_elem *first_selem); + struct bpf_local_storage_elem *first_selem, + gfp_t gfp_flags); struct bpf_local_storage_data * bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, - void *value, u64 map_flags); + void *value, u64 map_flags, gfp_t gfp_flags); void bpf_local_storage_free_rcu(struct rcu_head *rcu); -- cgit v1.2.3 From ee2a098851bfbe8bcdd964c0121f4246f00ff41e Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 14 Mar 2022 11:20:41 -0700 Subject: bpf: Adjust BPF stack helper functions to accommodate skip > 0 Let's say that the caller has storage for num_elem stack frames. Then, the BPF stack helper functions walk the stack for only num_elem frames. This means that if skip > 0, one keeps only 'num_elem - skip' frames. This is because it sets init_nr in the perf_callchain_entry to the end of the buffer to save num_elem entries only. I believe it was because the perf callchain code unwound the stack frames until it reached the global max size (sysctl_perf_event_max_stack). However it now has perf_callchain_entry_ctx.max_stack to limit the iteration locally. This simplifies the code to handle init_nr in the BPF callstack entries and removes the confusion with the perf_event's __PERF_SAMPLE_CALLCHAIN_EARLY which sets init_nr to 0. Also change the comment on bpf_get_stack() in the header file to be more explicit what the return value means. Fixes: c195651e565a ("bpf: add bpf_get_stack helper") Signed-off-by: Namhyung Kim Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/30a7b5d5-6726-1cc2-eaee-8da2828a9a9c@oracle.com Link: https://lore.kernel.org/bpf/20220314182042.71025-1-namhyung@kernel.org Based-on-patch-by: Eugene Loh --- include/uapi/linux/bpf.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7604e7d5438f..d14b10b85e51 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3009,8 +3009,8 @@ union bpf_attr { * * # sysctl kernel.perf_event_max_stack= * Return - * A non-negative value equal to or less than *size* on success, - * or a negative error in case of failure. + * The non-negative copied *buf* length equal to or less than + * *size* on success, or a negative error in case of failure. * * long bpf_skb_load_bytes_relative(const void *skb, u32 offset, void *to, u32 len, u32 start_header) * Description @@ -4316,8 +4316,8 @@ union bpf_attr { * * # sysctl kernel.perf_event_max_stack= * Return - * A non-negative value equal to or less than *size* on success, - * or a negative error in case of failure. + * The non-negative copied *buf* length equal to or less than + * *size* on success, or a negative error in case of failure. * * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags) * Description -- cgit v1.2.3 From 3387ce4d8a5f2956fab827edf499fe6780e83faa Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 21 Mar 2022 11:05:50 +0100 Subject: headers/prep: Fix header to build standalone: Add the dependency to , because cgroup_move_task() will dereference 'struct css_set'. ( Only older toolchains are affected, due to variations in the implementation of rcu_assign_pointer() et al. ) Cc: Peter Zijlstra Cc: Linus Torvalds Reported-by: Sachin Sant Reported-by: Andrew Morton Reported-by: Borislav Petkov Signed-off-by: Ingo Molnar --- include/linux/psi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/psi.h b/include/linux/psi.h index 7f7d1d88c3bb..89784763d19e 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -6,6 +6,7 @@ #include #include #include +#include struct seq_file; struct css_set; -- cgit v1.2.3 From 6d8491910fcd3324d0f0ece3bd68e85ead3a04d7 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Tue, 1 Mar 2022 06:03:47 +0000 Subject: KVM: x86: Introduce KVM_CAP_DISABLE_QUIRKS2 KVM_CAP_DISABLE_QUIRKS is irrevocably broken. The capability does not advertise the set of quirks which may be disabled to userspace, so it is impossible to predict the behavior of KVM. Worse yet, KVM_CAP_DISABLE_QUIRKS will tolerate any value for cap->args[0], meaning it fails to reject attempts to set invalid quirk bits. The only valid workaround for the quirky quirks API is to add a new CAP. Actually advertise the set of quirks that can be disabled to userspace so it can predict KVM's behavior. Reject values for cap->args[0] that contain invalid bits. Finally, add documentation for the new capability and describe the existing quirks. Signed-off-by: Oliver Upton Message-Id: <20220301060351.442881-5-oupton@google.com> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index d2f1efc3aa35..91a6fe4e02c0 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1143,6 +1143,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_PPC_AIL_MODE_3 210 #define KVM_CAP_S390_MEM_OP_EXTENSION 211 #define KVM_CAP_PMU_CAPABILITY 212 +#define KVM_CAP_DISABLE_QUIRKS2 213 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 8879b32a3a809a183e6e2998725a0f33c4e42d41 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 18 Mar 2022 12:23:41 -0700 Subject: devlink: add explicitly locked flavor of the rate node APIs We'll need an explicitly locked rate node API for netdevsim to switch eswitch mode setting to locked. Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/devlink.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index fd89a17adea1..a30180c0988a 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1490,6 +1490,10 @@ int devl_port_register(struct devlink *devlink, unsigned int port_index); void devl_port_unregister(struct devlink_port *devlink_port); +int devl_rate_leaf_create(struct devlink_port *port, void *priv); +void devl_rate_leaf_destroy(struct devlink_port *devlink_port); +void devl_rate_nodes_destroy(struct devlink *devlink); + struct ib_device; struct net *devlink_net(const struct devlink *devlink); -- cgit v1.2.3 From a43bf604446414103b7535f38e739b65601c4fb2 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Wed, 16 Mar 2022 18:24:26 -0400 Subject: NFSv4.1 provide mount option to toggle trunking discovery Introduce a new mount option -- trunkdiscovery,notrunkdiscovery -- to toggle whether or not the client will engage in actively discovery of trunking locations. v2 make notrunkdiscovery default Signed-off-by: Olga Kornievskaia Fixes: 1976b2b31462 ("NFSv4.1 query for fs_location attr on a new file system") Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index ca0959e51e81..b0e3fd550122 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -151,6 +151,7 @@ struct nfs_server { #define NFS_MOUNT_SOFTREVAL 0x800000 #define NFS_MOUNT_WRITE_EAGER 0x01000000 #define NFS_MOUNT_WRITE_WAIT 0x02000000 +#define NFS_MOUNT_TRUNK_DISCOVERY 0x04000000 unsigned int fattr_valid; /* Valid attributes */ unsigned int caps; /* server capabilities */ -- cgit v1.2.3 From 028152260c5782504995e1fe3910ad39d4e4f34a Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 21 Mar 2022 11:35:29 -0500 Subject: Revert "of: base: Introduce of_alias_get_alias_list() to check alias IDs" This reverts commit b1078c355d76769b5ddefc67d143fbd9b6e52c05. The single user of of_alias_get_alias_list(), drivers/tty/serial/xilinx_uartps.c, has since been refactored and no longer needs this function. It also contained a Smatch checker warning: drivers/of/base.c:2038 of_alias_get_alias_list() warn: passing negative bit value 's32min-(-2),0-s32max' to 'set_bit()' Reported-by: Dan Carpenter Signed-off-by: Rob Herring --- include/linux/of.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/linux/of.h b/include/linux/of.h index 2dc77430a91a..04971e85fbc9 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -388,9 +388,6 @@ extern int of_phandle_iterator_args(struct of_phandle_iterator *it, extern void of_alias_scan(void * (*dt_alloc)(u64 size, u64 align)); extern int of_alias_get_id(struct device_node *np, const char *stem); extern int of_alias_get_highest_id(const char *stem); -extern int of_alias_get_alias_list(const struct of_device_id *matches, - const char *stem, unsigned long *bitmap, - unsigned int nbits); extern int of_machine_is_compatible(const char *compat); @@ -766,13 +763,6 @@ static inline int of_alias_get_highest_id(const char *stem) return -ENOSYS; } -static inline int of_alias_get_alias_list(const struct of_device_id *matches, - const char *stem, unsigned long *bitmap, - unsigned int nbits) -{ - return -ENOSYS; -} - static inline int of_machine_is_compatible(const char *compat) { return 0; -- cgit v1.2.3 From 4c65422901154766e5cee17875ed680366a4a141 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 7 Jan 2022 13:45:25 -0500 Subject: mm/gup: Remove an assumption of a contiguous memmap This assumption needs the inverse of nth_page(), which is temporarily named page_nth() until it's renamed later in this series. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: John Hubbard Reviewed-by: Jason Gunthorpe Reviewed-by: William Kucharski --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0201d258c646..e3f8755f65ed 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -212,8 +212,10 @@ int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *, #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) +#define page_nth(head, tail) (page_to_pfn(tail) - page_to_pfn(head)) #else #define nth_page(page,n) ((page) + (n)) +#define page_nth(head, tail) ((tail) - (head)) #endif /* to align the pointer to the (next) page boundary */ -- cgit v1.2.3 From 5232c63f46fdd779303527ec36c518cc1e9c6b4e Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 6 Jan 2022 16:46:43 -0500 Subject: mm: Make compound_pincount always available Move compound_pincount from the third page to the second page, which means it's available for all compound pages. That lets us delete hpage_pincount_available(). On 32-bit systems, there isn't enough space for both compound_pincount and compound_nr in the second page (it would collide with page->private, which is in use for pages in the swap cache), so revert the optimisation of storing both compound_order and compound_nr on 32-bit systems. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: John Hubbard Reviewed-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: William Kucharski --- include/linux/mm.h | 21 ++++++++------------- include/linux/mm_types.h | 7 +++++-- 2 files changed, 13 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index e3f8755f65ed..c64bd0b67d75 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -887,17 +887,6 @@ static inline void destroy_compound_page(struct page *page) compound_page_dtors[page[1].compound_dtor](page); } -static inline bool hpage_pincount_available(struct page *page) -{ - /* - * Can the page->hpage_pinned_refcount field be used? That field is in - * the 3rd page of the compound page, so the smallest (2-page) compound - * pages cannot support it. - */ - page = compound_head(page); - return PageCompound(page) && compound_order(page) > 1; -} - static inline int head_compound_pincount(struct page *head) { return atomic_read(compound_pincount_ptr(head)); @@ -905,7 +894,7 @@ static inline int head_compound_pincount(struct page *head) static inline int compound_pincount(struct page *page) { - VM_BUG_ON_PAGE(!hpage_pincount_available(page), page); + VM_BUG_ON_PAGE(!PageCompound(page), page); page = compound_head(page); return head_compound_pincount(page); } @@ -913,7 +902,9 @@ static inline int compound_pincount(struct page *page) static inline void set_compound_order(struct page *page, unsigned int order) { page[1].compound_order = order; +#ifdef CONFIG_64BIT page[1].compound_nr = 1U << order; +#endif } /* Returns the number of pages in this potentially compound page. */ @@ -921,7 +912,11 @@ static inline unsigned long compound_nr(struct page *page) { if (!PageHead(page)) return 1; +#ifdef CONFIG_64BIT return page[1].compound_nr; +#else + return 1UL << compound_order(page); +#endif } /* Returns the number of bytes in this potentially compound page. */ @@ -1269,7 +1264,7 @@ void unpin_user_pages(struct page **pages, unsigned long npages); */ static inline bool page_maybe_dma_pinned(struct page *page) { - if (hpage_pincount_available(page)) + if (PageCompound(page)) return compound_pincount(page) > 0; /* diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 475bdb282769..0e274c9b934e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -135,11 +135,14 @@ struct page { unsigned char compound_dtor; unsigned char compound_order; atomic_t compound_mapcount; + atomic_t compound_pincount; +#ifdef CONFIG_64BIT unsigned int compound_nr; /* 1 << compound_order */ +#endif }; struct { /* Second tail page of compound page */ unsigned long _compound_pad_1; /* compound_head */ - atomic_t hpage_pinned_refcount; + unsigned long _compound_pad_2; /* For both global and memcg */ struct list_head deferred_list; }; @@ -300,7 +303,7 @@ static inline atomic_t *compound_mapcount_ptr(struct page *page) static inline atomic_t *compound_pincount_ptr(struct page *page) { - return &page[2].hpage_pinned_refcount; + return &page[1].compound_pincount; } /* -- cgit v1.2.3 From 3d11b225aeb184bc3dc9b4b27b302815a7c531aa Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 27 Dec 2021 18:28:58 -0500 Subject: mm: Add folio_pincount_ptr() This is the folio equivalent of compound_pincount_ptr(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: John Hubbard Reviewed-by: Jason Gunthorpe Reviewed-by: William Kucharski --- include/linux/mm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index c64bd0b67d75..c45739dfdd04 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1544,6 +1544,11 @@ static inline unsigned long folio_pfn(struct folio *folio) return page_to_pfn(&folio->page); } +static inline atomic_t *folio_pincount_ptr(struct folio *folio) +{ + return &folio_page(folio, 1)->compound_pincount; +} + /* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */ #ifdef CONFIG_MIGRATION static inline bool is_pinnable_page(struct page *page) -- cgit v1.2.3 From 0b90ddae13441c43a30d2e2689b8193a81891c92 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 27 Dec 2021 18:40:41 -0500 Subject: mm: Turn page_maybe_dma_pinned() into folio_maybe_dma_pinned() Replace three calls to compound_head() with one. This removes the last user of compound_pincount(), so remove that helper too. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: John Hubbard Reviewed-by: Jason Gunthorpe Reviewed-by: William Kucharski --- include/linux/mm.h | 129 ++++++++++++++++++++++++++--------------------------- 1 file changed, 63 insertions(+), 66 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index c45739dfdd04..35e453ac5c0f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -892,13 +892,6 @@ static inline int head_compound_pincount(struct page *head) return atomic_read(compound_pincount_ptr(head)); } -static inline int compound_pincount(struct page *page) -{ - VM_BUG_ON_PAGE(!PageCompound(page), page); - page = compound_head(page); - return head_compound_pincount(page); -} - static inline void set_compound_order(struct page *page, unsigned int order) { page[1].compound_order = order; @@ -1236,70 +1229,11 @@ void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, bool make_dirty); void unpin_user_pages(struct page **pages, unsigned long npages); -/** - * page_maybe_dma_pinned - Report if a page is pinned for DMA. - * @page: The page. - * - * This function checks if a page has been pinned via a call to - * a function in the pin_user_pages() family. - * - * For non-huge pages, the return value is partially fuzzy: false is not fuzzy, - * because it means "definitely not pinned for DMA", but true means "probably - * pinned for DMA, but possibly a false positive due to having at least - * GUP_PIN_COUNTING_BIAS worth of normal page references". - * - * False positives are OK, because: a) it's unlikely for a page to get that many - * refcounts, and b) all the callers of this routine are expected to be able to - * deal gracefully with a false positive. - * - * For huge pages, the result will be exactly correct. That's because we have - * more tracking data available: the 3rd struct page in the compound page is - * used to track the pincount (instead using of the GUP_PIN_COUNTING_BIAS - * scheme). - * - * For more information, please see Documentation/core-api/pin_user_pages.rst. - * - * Return: True, if it is likely that the page has been "dma-pinned". - * False, if the page is definitely not dma-pinned. - */ -static inline bool page_maybe_dma_pinned(struct page *page) -{ - if (PageCompound(page)) - return compound_pincount(page) > 0; - - /* - * page_ref_count() is signed. If that refcount overflows, then - * page_ref_count() returns a negative value, and callers will avoid - * further incrementing the refcount. - * - * Here, for that overflow case, use the signed bit to count a little - * bit higher via unsigned math, and thus still get an accurate result. - */ - return ((unsigned int)page_ref_count(compound_head(page))) >= - GUP_PIN_COUNTING_BIAS; -} - static inline bool is_cow_mapping(vm_flags_t flags) { return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; } -/* - * This should most likely only be called during fork() to see whether we - * should break the cow immediately for a page on the src mm. - */ -static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, - struct page *page) -{ - if (!is_cow_mapping(vma->vm_flags)) - return false; - - if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) - return false; - - return page_maybe_dma_pinned(page); -} - #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS #endif @@ -1549,6 +1483,69 @@ static inline atomic_t *folio_pincount_ptr(struct folio *folio) return &folio_page(folio, 1)->compound_pincount; } +/** + * folio_maybe_dma_pinned - Report if a folio may be pinned for DMA. + * @folio: The folio. + * + * This function checks if a folio has been pinned via a call to + * a function in the pin_user_pages() family. + * + * For small folios, the return value is partially fuzzy: false is not fuzzy, + * because it means "definitely not pinned for DMA", but true means "probably + * pinned for DMA, but possibly a false positive due to having at least + * GUP_PIN_COUNTING_BIAS worth of normal folio references". + * + * False positives are OK, because: a) it's unlikely for a folio to + * get that many refcounts, and b) all the callers of this routine are + * expected to be able to deal gracefully with a false positive. + * + * For large folios, the result will be exactly correct. That's because + * we have more tracking data available: the compound_pincount is used + * instead of the GUP_PIN_COUNTING_BIAS scheme. + * + * For more information, please see Documentation/core-api/pin_user_pages.rst. + * + * Return: True, if it is likely that the page has been "dma-pinned". + * False, if the page is definitely not dma-pinned. + */ +static inline bool folio_maybe_dma_pinned(struct folio *folio) +{ + if (folio_test_large(folio)) + return atomic_read(folio_pincount_ptr(folio)) > 0; + + /* + * folio_ref_count() is signed. If that refcount overflows, then + * folio_ref_count() returns a negative value, and callers will avoid + * further incrementing the refcount. + * + * Here, for that overflow case, use the sign bit to count a little + * bit higher via unsigned math, and thus still get an accurate result. + */ + return ((unsigned int)folio_ref_count(folio)) >= + GUP_PIN_COUNTING_BIAS; +} + +static inline bool page_maybe_dma_pinned(struct page *page) +{ + return folio_maybe_dma_pinned(page_folio(page)); +} + +/* + * This should most likely only be called during fork() to see whether we + * should break the cow immediately for a page on the src mm. + */ +static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, + struct page *page) +{ + if (!is_cow_mapping(vma->vm_flags)) + return false; + + if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) + return false; + + return page_maybe_dma_pinned(page); +} + /* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */ #ifdef CONFIG_MIGRATION static inline bool is_pinnable_page(struct page *page) -- cgit v1.2.3 From 40fcc7fc2c3838f3afe07a3a72709b45566e6cdb Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 29 Dec 2021 12:23:55 -0500 Subject: mm: Remove page_cache_add_speculative() and page_cache_get_speculative() These wrappers have no more callers, so delete them. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: John Hubbard Reviewed-by: Jason Gunthorpe Reviewed-by: William Kucharski --- include/linux/mm.h | 7 +++---- include/linux/pagemap.h | 10 ---------- 2 files changed, 3 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 35e453ac5c0f..b764057022c8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1215,10 +1215,9 @@ static inline void put_page(struct page *page) * applications that don't have huge page reference counts, this won't be an * issue. * - * Locking: the lockless algorithm described in page_cache_get_speculative() - * and page_cache_gup_pin_speculative() provides safe operation for - * get_user_pages and page_mkclean and other calls that race to set up page - * table entries. + * Locking: the lockless algorithm described in folio_try_get_rcu() + * provides safe operation for get_user_pages(), page_mkclean() and + * other calls that race to set up page table entries. */ #define GUP_PIN_COUNTING_BIAS (1U << 10) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 270bf5136c34..cdb3f118603a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -283,16 +283,6 @@ static inline struct inode *folio_inode(struct folio *folio) return folio->mapping->host; } -static inline bool page_cache_add_speculative(struct page *page, int count) -{ - return folio_ref_try_add_rcu((struct folio *)page, count); -} - -static inline bool page_cache_get_speculative(struct page *page) -{ - return page_cache_add_speculative(page, 1); -} - /** * folio_attach_private - Attach private data to a folio. * @folio: Folio to attach data to. -- cgit v1.2.3 From 822951d84684d7a0c4f45e7231c960e7fe786d8f Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 8 Jan 2022 00:15:04 -0500 Subject: mm/hugetlb: Use try_grab_folio() instead of try_grab_compound_head() follow_hugetlb_page() only cares about success or failure, so it doesn't need to know the type of the returned pointer, only whether it's NULL or not. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: John Hubbard Reviewed-by: Jason Gunthorpe Reviewed-by: William Kucharski --- include/linux/mm.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index b764057022c8..dca5c99395c9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1124,9 +1124,6 @@ static inline void get_page(struct page *page) } bool __must_check try_grab_page(struct page *page, unsigned int flags); -struct page *try_grab_compound_head(struct page *page, int refs, - unsigned int flags); - static inline __must_check bool try_get_page(struct page *page) { -- cgit v1.2.3 From 659508f9c936aa6e3aaf6e9cf6a4a8836b8f8355 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 23 Dec 2021 10:20:12 -0500 Subject: mm/gup: Turn compound_range_next() into gup_folio_range_next() Convert the only caller to work on folios instead of pages. This removes the last caller of put_compound_head(), so delete it. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: John Hubbard Reviewed-by: Jason Gunthorpe Reviewed-by: William Kucharski --- include/linux/mm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index dca5c99395c9..0d3f9057a807 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -212,10 +212,10 @@ int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *, #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) -#define page_nth(head, tail) (page_to_pfn(tail) - page_to_pfn(head)) +#define folio_page_idx(folio, p) (page_to_pfn(p) - folio_pfn(folio)) #else #define nth_page(page,n) ((page) + (n)) -#define page_nth(head, tail) ((tail) - (head)) +#define folio_page_idx(folio, p) ((p) - &(folio)->page) #endif /* to align the pointer to the (next) page boundary */ -- cgit v1.2.3 From 536939ff516382b391a0039262e27fc80c7b3924 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 21 Mar 2022 12:57:38 -0400 Subject: mm: Add three folio wrappers folio_is_zone_device() is equivalent to is_zone_device_page(), folio_is_device_private() is equivalent to is_device_private_page(), and folio_is_pinnable() is equivalent to is_pinnable_page(). All of these tests return the same result for every page in the folio, so we can just pass the head page of the folio to the page variant of the function. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/memremap.h | 5 +++++ include/linux/mm.h | 10 ++++++++++ 2 files changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index d6a114dd5ea8..8af304f6b504 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -138,6 +138,11 @@ static inline bool is_device_private_page(const struct page *page) page->pgmap->type == MEMORY_DEVICE_PRIVATE; } +static inline bool folio_is_device_private(const struct folio *folio) +{ + return is_device_private_page(&folio->page); +} + static inline bool is_pci_p2pdma_page(const struct page *page) { return IS_ENABLED(CONFIG_PCI_P2PDMA) && diff --git a/include/linux/mm.h b/include/linux/mm.h index 0d3f9057a807..2ca10c167f35 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1075,6 +1075,11 @@ static inline bool is_zone_device_page(const struct page *page) } #endif +static inline bool folio_is_zone_device(const struct folio *folio) +{ + return is_zone_device_page(&folio->page); +} + static inline bool is_zone_movable_page(const struct page *page) { return page_zonenum(page) == ZONE_MOVABLE; @@ -1556,6 +1561,11 @@ static inline bool is_pinnable_page(struct page *page) } #endif +static inline bool folio_is_pinnable(struct folio *folio) +{ + return is_pinnable_page(&folio->page); +} + static inline void set_page_zone(struct page *page, enum zone_type zone) { page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT); -- cgit v1.2.3 From 8927f6473e56e32e328ae8ed43736412f7f76a4e Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 23 Dec 2021 16:39:05 -0500 Subject: mm/workingset: Convert workingset_eviction() to take a folio This removes an assumption that THPs are the only kind of compound pages and removes a few hidden calls to compound_head(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/swap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 1d38d9475c4d..de36f140227e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -328,7 +328,7 @@ static inline swp_entry_t folio_swap_entry(struct folio *folio) /* linux/mm/workingset.c */ void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); -void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg); +void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg); void workingset_refault(struct folio *folio, void *shadow); void workingset_activation(struct folio *folio); -- cgit v1.2.3 From 3ecb0087ecee6213544a1e0b838826a0f4831ce5 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 27 Dec 2021 21:11:34 -0500 Subject: mm/memcg: Convert mem_cgroup_swapout() to take a folio This removes an assumption that THPs are the only kind of compound pages and removes a couple of hidden calls to compound_head. It also documents that you can't pass a tail page to mem_cgroup_swapout(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/swap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index de36f140227e..e7cb7a1e6ceb 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -741,7 +741,7 @@ static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) #endif #ifdef CONFIG_MEMCG_SWAP -extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry); +void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry); extern int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry); static inline int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) { @@ -761,7 +761,7 @@ static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_p extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg); extern bool mem_cgroup_swap_full(struct page *page); #else -static inline void mem_cgroup_swapout(struct page *page, swp_entry_t entry) +static inline void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry) { } -- cgit v1.2.3 From 06d20bdb986815a75fb1addf34655756ba922e3a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 17 Jan 2022 14:40:12 -0500 Subject: mm: Add lru_to_folio() Since page->lru occupies the same bytes as compound_head, any page on the LRU list must be a folio. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/mm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2ca10c167f35..a583b7375445 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -225,6 +225,10 @@ int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *, #define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)(addr), PAGE_SIZE) #define lru_to_page(head) (list_entry((head)->prev, struct page, lru)) +static inline struct folio *lru_to_folio(struct list_head *head) +{ + return list_entry((head)->prev, struct folio, lru); +} void setup_initial_init_mm(void *start_code, void *end_code, void *end_data, void *brk); -- cgit v1.2.3 From 5100da38ef3c33d9ad8b60b29c2b671249bf7e1d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 12 Feb 2022 22:48:55 -0500 Subject: mm: Convert remove_mapping() to take a folio Add kernel-doc and return the number of pages removed in order to get the statistics right in __invalidate_mapping_pages(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Miaohe Lin --- include/linux/swap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index e7cb7a1e6ceb..304f174b4d31 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -395,7 +395,7 @@ extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, unsigned long *nr_scanned); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; -extern int remove_mapping(struct address_space *mapping, struct page *page); +long remove_mapping(struct address_space *mapping, struct folio *folio); extern unsigned long reclaim_pages(struct list_head *page_list); #ifdef CONFIG_NUMA -- cgit v1.2.3 From d6c75dc22c755c567838f12f12a16f2a323ebd4e Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 13 Feb 2022 15:22:28 -0500 Subject: mm/truncate: Split invalidate_inode_page() into mapping_evict_folio() Some of the callers already have the address_space and can avoid calling folio_mapping() and checking if the folio was already truncated. Also add kernel-doc and fix the return type (in case we ever support folios larger than 4TB). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Miaohe Lin --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index a583b7375445..dede2eda4d7f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1825,7 +1825,6 @@ extern void truncate_setsize(struct inode *inode, loff_t newsize); void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to); void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); int generic_error_remove_page(struct address_space *mapping, struct page *page); -int invalidate_inode_page(struct page *page); #ifdef CONFIG_MMU extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, -- cgit v1.2.3 From 261b6840ed10419ac2f554e515592d59dd5c82cf Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 13 Feb 2022 16:40:24 -0500 Subject: mm: Turn deactivate_file_page() into deactivate_file_folio() This function has one caller which already has a reference to the page, so we don't need to use get_page_unless_zero(). Also move the prototype to mm/internal.h. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Miaohe Lin --- include/linux/swap.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 304f174b4d31..064e60e9f63f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -372,7 +372,6 @@ extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_cpu_zone(struct zone *zone); extern void lru_add_drain_all(void); -extern void deactivate_file_page(struct page *page); extern void deactivate_page(struct page *page); extern void mark_page_lazyfree(struct page *page); extern void swap_setup(void); -- cgit v1.2.3 From c56109dd35c9204cd6c49d2116ef36e5044ef867 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 13 Feb 2022 17:22:10 -0500 Subject: mm/truncate: Combine invalidate_mapping_pagevec() and __invalidate_mapping_pages() We can save a function call by combining these two functions, which are identical except for the return value. Also move the prototype to mm/internal.h. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Miaohe Lin --- include/linux/fs.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index e2d892b201b0..85c584c5c623 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2749,10 +2749,6 @@ extern bool is_bad_inode(struct inode *); unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end); -void invalidate_mapping_pagevec(struct address_space *mapping, - pgoff_t start, pgoff_t end, - unsigned long *nr_pagevec); - static inline void invalidate_remote_inode(struct inode *inode) { if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || -- cgit v1.2.3 From cbcc268bb1ce5b539e7652d398e08e9b83dc4cef Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 13 Feb 2022 17:23:58 -0500 Subject: fs: Move many prototypes to pagemap.h These functions are page cache functionality and don't need to be declared in fs.h. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Miaohe Lin --- include/linux/fs.h | 116 ------------------------------------------------ include/linux/pagemap.h | 114 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 114 insertions(+), 116 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 85c584c5c623..0961c979e949 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2746,50 +2746,6 @@ extern void init_special_inode(struct inode *, umode_t, dev_t); extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); -unsigned long invalidate_mapping_pages(struct address_space *mapping, - pgoff_t start, pgoff_t end); - -static inline void invalidate_remote_inode(struct inode *inode) -{ - if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || - S_ISLNK(inode->i_mode)) - invalidate_mapping_pages(inode->i_mapping, 0, -1); -} -extern int invalidate_inode_pages2(struct address_space *mapping); -extern int invalidate_inode_pages2_range(struct address_space *mapping, - pgoff_t start, pgoff_t end); -extern int write_inode_now(struct inode *, int); -extern int filemap_fdatawrite(struct address_space *); -extern int filemap_flush(struct address_space *); -extern int filemap_fdatawait_keep_errors(struct address_space *mapping); -extern int filemap_fdatawait_range(struct address_space *, loff_t lstart, - loff_t lend); -extern int filemap_fdatawait_range_keep_errors(struct address_space *mapping, - loff_t start_byte, loff_t end_byte); - -static inline int filemap_fdatawait(struct address_space *mapping) -{ - return filemap_fdatawait_range(mapping, 0, LLONG_MAX); -} - -extern bool filemap_range_has_page(struct address_space *, loff_t lstart, - loff_t lend); -extern int filemap_write_and_wait_range(struct address_space *mapping, - loff_t lstart, loff_t lend); -extern int __filemap_fdatawrite_range(struct address_space *mapping, - loff_t start, loff_t end, int sync_mode); -extern int filemap_fdatawrite_range(struct address_space *mapping, - loff_t start, loff_t end); -extern int filemap_check_errors(struct address_space *mapping); -extern void __filemap_set_wb_err(struct address_space *mapping, int err); -int filemap_fdatawrite_wbc(struct address_space *mapping, - struct writeback_control *wbc); - -static inline int filemap_write_and_wait(struct address_space *mapping) -{ - return filemap_write_and_wait_range(mapping, 0, LLONG_MAX); -} - extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, loff_t lend); extern int __must_check file_check_and_advance_wb_err(struct file *file); @@ -2801,67 +2757,6 @@ static inline int file_write_and_wait(struct file *file) return file_write_and_wait_range(file, 0, LLONG_MAX); } -/** - * filemap_set_wb_err - set a writeback error on an address_space - * @mapping: mapping in which to set writeback error - * @err: error to be set in mapping - * - * When writeback fails in some way, we must record that error so that - * userspace can be informed when fsync and the like are called. We endeavor - * to report errors on any file that was open at the time of the error. Some - * internal callers also need to know when writeback errors have occurred. - * - * When a writeback error occurs, most filesystems will want to call - * filemap_set_wb_err to record the error in the mapping so that it will be - * automatically reported whenever fsync is called on the file. - */ -static inline void filemap_set_wb_err(struct address_space *mapping, int err) -{ - /* Fastpath for common case of no error */ - if (unlikely(err)) - __filemap_set_wb_err(mapping, err); -} - -/** - * filemap_check_wb_err - has an error occurred since the mark was sampled? - * @mapping: mapping to check for writeback errors - * @since: previously-sampled errseq_t - * - * Grab the errseq_t value from the mapping, and see if it has changed "since" - * the given value was sampled. - * - * If it has then report the latest error set, otherwise return 0. - */ -static inline int filemap_check_wb_err(struct address_space *mapping, - errseq_t since) -{ - return errseq_check(&mapping->wb_err, since); -} - -/** - * filemap_sample_wb_err - sample the current errseq_t to test for later errors - * @mapping: mapping to be sampled - * - * Writeback errors are always reported relative to a particular sample point - * in the past. This function provides those sample points. - */ -static inline errseq_t filemap_sample_wb_err(struct address_space *mapping) -{ - return errseq_sample(&mapping->wb_err); -} - -/** - * file_sample_sb_err - sample the current errseq_t to test for later errors - * @file: file pointer to be sampled - * - * Grab the most current superblock-level errseq_t value for the given - * struct file. - */ -static inline errseq_t file_sample_sb_err(struct file *file) -{ - return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err); -} - extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, int datasync); @@ -3604,15 +3499,4 @@ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, extern int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice); -/* - * Flush file data before changing attributes. Caller must hold any locks - * required to prevent further writes to this file until we're done setting - * flags. - */ -static inline int inode_drain_writes(struct inode *inode) -{ - inode_dio_wait(inode); - return filemap_write_and_wait(inode->i_mapping); -} - #endif /* _LINUX_FS_H */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index cdb3f118603a..f968b36ad771 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -18,6 +18,120 @@ struct folio_batch; +unsigned long invalidate_mapping_pages(struct address_space *mapping, + pgoff_t start, pgoff_t end); + +static inline void invalidate_remote_inode(struct inode *inode) +{ + if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + S_ISLNK(inode->i_mode)) + invalidate_mapping_pages(inode->i_mapping, 0, -1); +} +int invalidate_inode_pages2(struct address_space *mapping); +int invalidate_inode_pages2_range(struct address_space *mapping, + pgoff_t start, pgoff_t end); +int write_inode_now(struct inode *, int sync); +int filemap_fdatawrite(struct address_space *); +int filemap_flush(struct address_space *); +int filemap_fdatawait_keep_errors(struct address_space *mapping); +int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); +int filemap_fdatawait_range_keep_errors(struct address_space *mapping, + loff_t start_byte, loff_t end_byte); + +static inline int filemap_fdatawait(struct address_space *mapping) +{ + return filemap_fdatawait_range(mapping, 0, LLONG_MAX); +} + +bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend); +int filemap_write_and_wait_range(struct address_space *mapping, + loff_t lstart, loff_t lend); +int __filemap_fdatawrite_range(struct address_space *mapping, + loff_t start, loff_t end, int sync_mode); +int filemap_fdatawrite_range(struct address_space *mapping, + loff_t start, loff_t end); +int filemap_check_errors(struct address_space *mapping); +void __filemap_set_wb_err(struct address_space *mapping, int err); +int filemap_fdatawrite_wbc(struct address_space *mapping, + struct writeback_control *wbc); + +static inline int filemap_write_and_wait(struct address_space *mapping) +{ + return filemap_write_and_wait_range(mapping, 0, LLONG_MAX); +} + +/** + * filemap_set_wb_err - set a writeback error on an address_space + * @mapping: mapping in which to set writeback error + * @err: error to be set in mapping + * + * When writeback fails in some way, we must record that error so that + * userspace can be informed when fsync and the like are called. We endeavor + * to report errors on any file that was open at the time of the error. Some + * internal callers also need to know when writeback errors have occurred. + * + * When a writeback error occurs, most filesystems will want to call + * filemap_set_wb_err to record the error in the mapping so that it will be + * automatically reported whenever fsync is called on the file. + */ +static inline void filemap_set_wb_err(struct address_space *mapping, int err) +{ + /* Fastpath for common case of no error */ + if (unlikely(err)) + __filemap_set_wb_err(mapping, err); +} + +/** + * filemap_check_wb_err - has an error occurred since the mark was sampled? + * @mapping: mapping to check for writeback errors + * @since: previously-sampled errseq_t + * + * Grab the errseq_t value from the mapping, and see if it has changed "since" + * the given value was sampled. + * + * If it has then report the latest error set, otherwise return 0. + */ +static inline int filemap_check_wb_err(struct address_space *mapping, + errseq_t since) +{ + return errseq_check(&mapping->wb_err, since); +} + +/** + * filemap_sample_wb_err - sample the current errseq_t to test for later errors + * @mapping: mapping to be sampled + * + * Writeback errors are always reported relative to a particular sample point + * in the past. This function provides those sample points. + */ +static inline errseq_t filemap_sample_wb_err(struct address_space *mapping) +{ + return errseq_sample(&mapping->wb_err); +} + +/** + * file_sample_sb_err - sample the current errseq_t to test for later errors + * @file: file pointer to be sampled + * + * Grab the most current superblock-level errseq_t value for the given + * struct file. + */ +static inline errseq_t file_sample_sb_err(struct file *file) +{ + return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err); +} + +/* + * Flush file data before changing attributes. Caller must hold any locks + * required to prevent further writes to this file until we're done setting + * flags. + */ +static inline int inode_drain_writes(struct inode *inode) +{ + inode_dio_wait(inode); + return filemap_write_and_wait(inode->i_mapping); +} + static inline bool mapping_empty(struct address_space *mapping) { return xa_empty(&mapping->i_pages); -- cgit v1.2.3 From 74e8ee4708a8edabbbc7ab8c12ec24d7a561bb41 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 18 Jan 2022 10:50:48 -0500 Subject: mm: Turn head_compound_mapcount() into folio_entire_mapcount() Adjust documentation to be more clear. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/mm.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index dede2eda4d7f..70f0ca217962 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -776,21 +776,26 @@ static inline int is_vmalloc_or_module_addr(const void *x) } #endif -static inline int head_compound_mapcount(struct page *head) +/* + * How many times the entire folio is mapped as a single unit (eg by a + * PMD or PUD entry). This is probably not what you want, except for + * debugging purposes; look at folio_mapcount() or page_mapcount() + * instead. + */ +static inline int folio_entire_mapcount(struct folio *folio) { - return atomic_read(compound_mapcount_ptr(head)) + 1; + VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); + return atomic_read(folio_mapcount_ptr(folio)) + 1; } /* * Mapcount of compound page as a whole, does not include mapped sub-pages. * - * Must be called only for compound pages or any their tail sub-pages. + * Must be called only for compound pages. */ static inline int compound_mapcount(struct page *page) { - VM_BUG_ON_PAGE(!PageCompound(page), page); - page = compound_head(page); - return head_compound_mapcount(page); + return folio_entire_mapcount(page_folio(page)); } /* -- cgit v1.2.3 From 4ba1119cd53166d853050ff1a9d76079cd8f8e06 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 17 Jan 2022 16:33:26 -0500 Subject: mm: Add folio_mapcount() This implements the same algorithm as total_mapcount(), which is transformed into a wrapper function. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/mm.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 70f0ca217962..0d380dc26847 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -825,8 +825,14 @@ static inline int page_mapcount(struct page *page) return atomic_read(&page->_mapcount) + 1; } +int folio_mapcount(struct folio *folio); + #ifdef CONFIG_TRANSPARENT_HUGEPAGE -int total_mapcount(struct page *page); +static inline int total_mapcount(struct page *page) +{ + return folio_mapcount(page_folio(page)); +} + int page_trans_huge_mapcount(struct page *page); #else static inline int total_mapcount(struct page *page) -- cgit v1.2.3 From 346cf61311f6e348337e95aa2febe29e86137f42 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 18 Jan 2022 08:56:47 -0500 Subject: mm: Add split_folio_to_list() This is a convenience function; split_huge_page_to_list() can take any page in a folio (and does so on purpose because that page will be the one which keeps the refcount). But it's convenient for the callers to pass the folio instead of the first page in the folio. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/huge_mm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index e4c18ba8d3bf..71c073d411ac 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -483,6 +483,12 @@ static inline bool thp_migration_supported(void) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +static inline int split_folio_to_list(struct folio *folio, + struct list_head *list) +{ + return split_huge_page_to_list(&folio->page, list); +} + /** * thp_size - Size of a transparent huge page. * @page: Head page of a transparent huge page. -- cgit v1.2.3 From f087b903fc2e4975bff9742a66ee7a837a2f545b Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 2 Feb 2022 23:29:45 -0500 Subject: mm: Add folio_pgoff() This is the folio equivalent of page_to_pgoff(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/pagemap.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index f968b36ad771..a73c928e1d74 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -817,6 +817,17 @@ static inline loff_t folio_file_pos(struct folio *folio) return page_file_offset(&folio->page); } +/* + * Get the offset in PAGE_SIZE (even for hugetlb folios). + * (TODO: hugetlb folios should have ->index in PAGE_SIZE) + */ +static inline pgoff_t folio_pgoff(struct folio *folio) +{ + if (unlikely(folio_test_hugetlb(folio))) + return hugetlb_basepage_index(&folio->page); + return folio->index; +} + extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma, unsigned long address); -- cgit v1.2.3 From eed05e54d275b3cfc5d8c79843c5276a5878e94a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 3 Feb 2022 09:06:08 -0500 Subject: mm: Add DEFINE_PAGE_VMA_WALK and DEFINE_FOLIO_VMA_WALK Instead of declaring a struct page_vma_mapped_walk directly, use these helpers to allow us to transition to a PFN approach in the following patches. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/rmap.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index ac29b076082b..0d894a2bfaa1 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -214,6 +214,22 @@ struct page_vma_mapped_walk { unsigned int flags; }; +#define DEFINE_PAGE_VMA_WALK(name, _page, _vma, _address, _flags) \ + struct page_vma_mapped_walk name = { \ + .page = _page, \ + .vma = _vma, \ + .address = _address, \ + .flags = _flags, \ + } + +#define DEFINE_FOLIO_VMA_WALK(name, _folio, _vma, _address, _flags) \ + struct page_vma_mapped_walk name = { \ + .page = &_folio->page, \ + .vma = _vma, \ + .address = _address, \ + .flags = _flags, \ + } + static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw) { /* HugeTLB pte is set to the relevant page table entry without pte_mapped. */ -- cgit v1.2.3 From 2aff7a4755bed2870ee23b75bc88cdc8d76cdd03 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 3 Feb 2022 11:40:17 -0500 Subject: mm: Convert page_vma_mapped_walk to work on PFNs page_mapped_in_vma() really just wants to walk one page, but as the code stands, if passed the head page of a compound page, it will walk every page in the compound page. Extract pfn/nr_pages/pgoff from the struct page early, so they can be overridden by page_mapped_in_vma(). Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/hugetlb.h | 5 +++++ include/linux/rmap.h | 17 ++++++++++++----- 2 files changed, 17 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index d1897a69c540..6ba2f8e74fbb 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -970,6 +970,11 @@ static inline struct hstate *page_hstate(struct page *page) return NULL; } +static inline struct hstate *size_to_hstate(unsigned long size) +{ + return NULL; +} + static inline unsigned long huge_page_size(struct hstate *h) { return PAGE_SIZE; diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 0d894a2bfaa1..0c838ba1a8ee 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -11,6 +11,7 @@ #include #include #include +#include /* * The anon_vma heads a list of private "related" vmas, to scan if @@ -201,11 +202,13 @@ int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, /* Avoid racy checks */ #define PVMW_SYNC (1 << 0) -/* Look for migarion entries rather than present PTEs */ +/* Look for migration entries rather than present PTEs */ #define PVMW_MIGRATION (1 << 1) struct page_vma_mapped_walk { - struct page *page; + unsigned long pfn; + unsigned long nr_pages; + pgoff_t pgoff; struct vm_area_struct *vma; unsigned long address; pmd_t *pmd; @@ -216,7 +219,9 @@ struct page_vma_mapped_walk { #define DEFINE_PAGE_VMA_WALK(name, _page, _vma, _address, _flags) \ struct page_vma_mapped_walk name = { \ - .page = _page, \ + .pfn = page_to_pfn(_page), \ + .nr_pages = compound_nr(page), \ + .pgoff = page_to_pgoff(page), \ .vma = _vma, \ .address = _address, \ .flags = _flags, \ @@ -224,7 +229,9 @@ struct page_vma_mapped_walk { #define DEFINE_FOLIO_VMA_WALK(name, _folio, _vma, _address, _flags) \ struct page_vma_mapped_walk name = { \ - .page = &_folio->page, \ + .pfn = folio_pfn(_folio), \ + .nr_pages = folio_nr_pages(_folio), \ + .pgoff = folio_pgoff(_folio), \ .vma = _vma, \ .address = _address, \ .flags = _flags, \ @@ -233,7 +240,7 @@ struct page_vma_mapped_walk { static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw) { /* HugeTLB pte is set to the relevant page table entry without pte_mapped. */ - if (pvmw->pte && !PageHuge(pvmw->page)) + if (pvmw->pte && !is_vm_hugetlb_page(pvmw->vma)) pte_unmap(pvmw->pte); if (pvmw->ptl) spin_unlock(pvmw->ptl); -- cgit v1.2.3 From b3ac04132c4b9bc5c9c14608424d410e7ca3b400 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 21 Jan 2022 11:27:31 -0500 Subject: mm/rmap: Turn page_referenced() into folio_referenced() Both its callers pass a page which was previously on an LRU list, so were passing a folio by definition. Use the type system to enforce that and remove a few calls to compound_head(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/rmap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 0c838ba1a8ee..69a1664216de 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -190,7 +190,7 @@ static inline void page_dup_rmap(struct page *page, bool compound) /* * Called from mm/vmscan.c to handle paging out */ -int page_referenced(struct page *, int is_locked, +int folio_referenced(struct folio *, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags); void try_to_migrate(struct page *page, enum ttu_flags flags); @@ -301,7 +301,7 @@ void rmap_walk_locked(struct page *page, struct rmap_walk_control *rwc); #define anon_vma_prepare(vma) (0) #define anon_vma_link(vma) do {} while (0) -static inline int page_referenced(struct page *page, int is_locked, +static inline int folio_referenced(struct folio *folio, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags) { -- cgit v1.2.3 From af28a988b313a601c12c410a42e485ca46adcfee Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 21 Jan 2022 10:44:52 -0500 Subject: mm/huge_memory: Convert __split_huge_pmd() to take a folio Convert split_huge_pmd_address() at the same time since it only passes the folio through, and its two callers already have a folio on hand. Removes numerous calls to compound_head() and removes an assumption that a page cannot be larger than a PMD. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/huge_mm.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 71c073d411ac..4368b314d9c8 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -194,7 +194,7 @@ static inline int split_huge_page(struct page *page) void deferred_split_huge_page(struct page *page); void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long address, bool freeze, struct page *page); + unsigned long address, bool freeze, struct folio *folio); #define split_huge_pmd(__vma, __pmd, __address) \ do { \ @@ -207,7 +207,7 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, - bool freeze, struct page *page); + bool freeze, struct folio *folio); void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, unsigned long address); @@ -406,9 +406,9 @@ static inline void deferred_split_huge_page(struct page *page) {} do { } while (0) static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long address, bool freeze, struct page *page) {} + unsigned long address, bool freeze, struct folio *folio) {} static inline void split_huge_pmd_address(struct vm_area_struct *vma, - unsigned long address, bool freeze, struct page *page) {} + unsigned long address, bool freeze, struct folio *folio) {} #define split_huge_pud(__vma, __pmd, __address) \ do { } while (0) -- cgit v1.2.3 From 869f7ee6f6477341f859c8b0949ae81caf9ca7f3 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 15 Feb 2022 09:28:49 -0500 Subject: mm/rmap: Convert try_to_unmap() to take a folio Change all three callers and the worker function try_to_unmap_one(). Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/rmap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 69a1664216de..a0c5c38c733f 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -194,7 +194,7 @@ int folio_referenced(struct folio *, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags); void try_to_migrate(struct page *page, enum ttu_flags flags); -void try_to_unmap(struct page *, enum ttu_flags flags); +void try_to_unmap(struct folio *, enum ttu_flags flags); int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, unsigned long end, struct page **pages, @@ -309,7 +309,7 @@ static inline int folio_referenced(struct folio *folio, int is_locked, return 0; } -static inline void try_to_unmap(struct page *page, enum ttu_flags flags) +static inline void try_to_unmap(struct folio *folio, enum ttu_flags flags) { } -- cgit v1.2.3 From 4b8554c527f3cfa183f6c06d231a9387873205a0 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 28 Jan 2022 14:29:43 -0500 Subject: mm/rmap: Convert try_to_migrate() to folios Convert the callers to pass a folio and the try_to_migrate_one() worker to use a folio throughout. Fixes an assumption that a folio must be <= PMD size. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/rmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index a0c5c38c733f..e6e935c81414 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -193,7 +193,7 @@ static inline void page_dup_rmap(struct page *page, bool compound) int folio_referenced(struct folio *, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags); -void try_to_migrate(struct page *page, enum ttu_flags flags); +void try_to_migrate(struct folio *folio, enum ttu_flags flags); void try_to_unmap(struct folio *, enum ttu_flags flags); int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, -- cgit v1.2.3 From 4eecb8b9163df82c87c91764a02fff228ef25f6d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 28 Jan 2022 23:32:59 -0500 Subject: mm/migrate: Convert remove_migration_ptes() to folios Convert the implementation and all callers. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/rmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index e6e935c81414..21af80d5b711 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -261,7 +261,7 @@ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *); */ int folio_mkclean(struct folio *); -void remove_migration_ptes(struct page *old, struct page *new, bool locked); +void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked); /* * Called by memory-failure.c to kill processes. -- cgit v1.2.3 From 9595d76942b8714627d670a7e7ae543812c731ae Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 1 Feb 2022 23:33:08 -0500 Subject: mm/rmap: Turn page_lock_anon_vma_read() into folio_lock_anon_vma_read() Add back page_lock_anon_vma_read() as a wrapper. This saves a few calls to compound_head(). If any callers were passing a tail page before, this would have failed to lock the anon VMA as page->mapping is not valid for tail pages. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/rmap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 21af80d5b711..be020d38b0a5 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -267,6 +267,7 @@ void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked); * Called by memory-failure.c to kill processes. */ struct anon_vma *page_lock_anon_vma_read(struct page *page); +struct anon_vma *folio_lock_anon_vma_read(struct folio *folio); void page_unlock_anon_vma_read(struct anon_vma *anon_vma); int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); -- cgit v1.2.3 From e05b34539d008ab819388f699b25eae962ba24ac Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 29 Jan 2022 11:52:52 -0500 Subject: mm: Turn page_anon_vma() into folio_anon_vma() Move the prototype from mm.h to mm/internal.h and convert all callers to pass a folio. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0d380dc26847..a879c583f665 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1730,7 +1730,6 @@ static inline void *folio_address(const struct folio *folio) } extern void *page_rmapping(struct page *page); -extern struct anon_vma *page_anon_vma(struct page *page); extern pgoff_t __page_file_index(struct page *page); /* -- cgit v1.2.3 From 2f031c6f042cb8a9b221a8b6b80e69de5170f830 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 29 Jan 2022 16:06:53 -0500 Subject: mm/rmap: Convert rmap_walk() to take a folio This ripples all the way through to every calling and called function from rmap. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/ksm.h | 4 ++-- include/linux/rmap.h | 11 +++++------ 2 files changed, 7 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/ksm.h b/include/linux/ksm.h index a38a5bca1ba5..0b4f17418f64 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -51,7 +51,7 @@ static inline void ksm_exit(struct mm_struct *mm) struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address); -void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc); +void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); #else /* !CONFIG_KSM */ @@ -78,7 +78,7 @@ static inline struct page *ksm_might_need_to_copy(struct page *page, return page; } -static inline void rmap_walk_ksm(struct page *page, +static inline void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc) { } diff --git a/include/linux/rmap.h b/include/linux/rmap.h index be020d38b0a5..a74d811c5b3f 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -266,7 +266,6 @@ void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked); /* * Called by memory-failure.c to kill processes. */ -struct anon_vma *page_lock_anon_vma_read(struct page *page); struct anon_vma *folio_lock_anon_vma_read(struct folio *folio); void page_unlock_anon_vma_read(struct anon_vma *anon_vma); int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); @@ -286,15 +285,15 @@ struct rmap_walk_control { * Return false if page table scanning in rmap_walk should be stopped. * Otherwise, return true. */ - bool (*rmap_one)(struct page *page, struct vm_area_struct *vma, + bool (*rmap_one)(struct folio *folio, struct vm_area_struct *vma, unsigned long addr, void *arg); - int (*done)(struct page *page); - struct anon_vma *(*anon_lock)(struct page *page); + int (*done)(struct folio *folio); + struct anon_vma *(*anon_lock)(struct folio *folio); bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; -void rmap_walk(struct page *page, struct rmap_walk_control *rwc); -void rmap_walk_locked(struct page *page, struct rmap_walk_control *rwc); +void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc); +void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc); #else /* !CONFIG_MMU */ -- cgit v1.2.3 From 84fbbe21894bb9be8e16df408cbfbb9466fe396d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 29 Jan 2022 16:16:54 -0500 Subject: mm/rmap: Constify the rmap_walk_control argument The rmap walking functions do not modify the rmap_walk_control, and page_idle_clear_pte_refs() takes advantage of that to move construction of the rmap_walk_control to compile time. This lets us remove an unclean cast. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/ksm.h | 4 ++-- include/linux/rmap.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 0b4f17418f64..0630e545f4cb 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -51,7 +51,7 @@ static inline void ksm_exit(struct mm_struct *mm) struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address); -void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); +void rmap_walk_ksm(struct folio *folio, const struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); #else /* !CONFIG_KSM */ @@ -79,7 +79,7 @@ static inline struct page *ksm_might_need_to_copy(struct page *page, } static inline void rmap_walk_ksm(struct folio *folio, - struct rmap_walk_control *rwc) + const struct rmap_walk_control *rwc) { } diff --git a/include/linux/rmap.h b/include/linux/rmap.h index a74d811c5b3f..17230c458341 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -292,8 +292,8 @@ struct rmap_walk_control { bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; -void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc); -void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc); +void rmap_walk(struct folio *folio, const struct rmap_walk_control *rwc); +void rmap_walk_locked(struct folio *folio, const struct rmap_walk_control *rwc); #else /* !CONFIG_MMU */ -- cgit v1.2.3 From e0cd5e7ffa549487cf1a85452f371274cbf0a8f1 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 17 Jan 2022 23:35:57 -0500 Subject: mm/vmscan: Convert pageout() to take a folio We always write out an entire folio at once. This conversion removes a few calls to compound_head() and gets the NR_VMSCAN_WRITE statistic right when writing out a large folio. Signed-off-by: Matthew Wilcox (Oracle) --- include/trace/events/vmscan.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index ca2e9009a651..de136dbd623a 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -327,11 +327,11 @@ TRACE_EVENT(mm_vmscan_lru_isolate, __print_symbolic(__entry->lru, LRU_NAMES)) ); -TRACE_EVENT(mm_vmscan_writepage, +TRACE_EVENT(mm_vmscan_write_folio, - TP_PROTO(struct page *page), + TP_PROTO(struct folio *folio), - TP_ARGS(page), + TP_ARGS(folio), TP_STRUCT__entry( __field(unsigned long, pfn) @@ -339,9 +339,9 @@ TRACE_EVENT(mm_vmscan_writepage, ), TP_fast_assign( - __entry->pfn = page_to_pfn(page); + __entry->pfn = folio_pfn(folio); __entry->reclaim_flags = trace_reclaim_flags( - page_is_file_lru(page)); + folio_is_file_lru(folio)); ), TP_printk("page=%p pfn=0x%lx flags=%s", -- cgit v1.2.3 From d4b4084ac3154c51ff5fa71f669264cc44429be2 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 4 Feb 2022 14:13:31 -0500 Subject: mm: Turn can_split_huge_page() into can_split_folio() This function already required a head page to be passed, so this just adds type-safety and removes a few implicit calls to compound_head(). Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/huge_mm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 4368b314d9c8..e0348bca3d66 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -185,7 +185,7 @@ void prep_transhuge_page(struct page *page); void free_transhuge_page(struct page *page); bool is_transparent_hugepage(struct page *page); -bool can_split_huge_page(struct page *page, int *pextra_pins); +bool can_split_folio(struct folio *folio, int *pextra_pins); int split_huge_page_to_list(struct page *page, struct list_head *list); static inline int split_huge_page(struct page *page) { @@ -387,7 +387,7 @@ static inline bool is_transparent_hugepage(struct page *page) #define thp_get_unmapped_area NULL static inline bool -can_split_huge_page(struct page *page, int *pextra_pins) +can_split_folio(struct folio *folio, int *pextra_pins) { BUILD_BUG(); return false; -- cgit v1.2.3 From 06d44142d49dc2e02d255ea9d72dc4c20f20388f Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 10 Oct 2020 11:47:55 -0400 Subject: mm: Fix READ_ONLY_THP warning These counters only exist if CONFIG_READ_ONLY_THP_FOR_FS is defined, but we do not need to warn if the filesystem natively supports large folios. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/pagemap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index a73c928e1d74..0a2417fc531c 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -326,7 +326,7 @@ static inline void filemap_nr_thps_inc(struct address_space *mapping) if (!mapping_large_folio_support(mapping)) atomic_inc(&mapping->nr_thps); #else - WARN_ON_ONCE(1); + WARN_ON_ONCE(mapping_large_folio_support(mapping) == 0); #endif } @@ -336,7 +336,7 @@ static inline void filemap_nr_thps_dec(struct address_space *mapping) if (!mapping_large_folio_support(mapping)) atomic_dec(&mapping->nr_thps); #else - WARN_ON_ONCE(1); + WARN_ON_ONCE(mapping_large_folio_support(mapping) == 0); #endif } -- cgit v1.2.3 From 421f1ab48452af48b64e205de1caca3d1ba415f4 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 15 Jan 2022 23:27:08 -0500 Subject: mm: Make large folios depend on THP Some parts of the VM still depend on THP to handle large folios correctly. Until those are fixed, prevent creating large folios if THP are disabled. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/pagemap.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 0a2417fc531c..20d7cbabf654 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -306,9 +306,14 @@ static inline void mapping_set_large_folios(struct address_space *mapping) __set_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); } +/* + * Large folio support currently depends on THP. These dependencies are + * being worked on but are not yet fixed. + */ static inline bool mapping_large_folio_support(struct address_space *mapping) { - return test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); + return IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && + test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); } static inline int filemap_nr_thps(struct address_space *mapping) -- cgit v1.2.3 From 18788cfa236967741b83db1035ab24539e2a21bb Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 May 2020 20:54:38 -0400 Subject: mm: Support arbitrary THP sizes For code which has not yet been converted from THP to folios, use the compound size of the page instead of assuming PTE or PMD size. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/huge_mm.h | 47 ----------------------------------------------- include/linux/mm.h | 31 +++++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+), 47 deletions(-) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index e0348bca3d66..0734aff8fa19 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -250,30 +250,6 @@ static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, return NULL; } -/** - * thp_order - Order of a transparent huge page. - * @page: Head page of a transparent huge page. - */ -static inline unsigned int thp_order(struct page *page) -{ - VM_BUG_ON_PGFLAGS(PageTail(page), page); - if (PageHead(page)) - return HPAGE_PMD_ORDER; - return 0; -} - -/** - * thp_nr_pages - The number of regular pages in this huge page. - * @page: The head page of a huge page. - */ -static inline int thp_nr_pages(struct page *page) -{ - VM_BUG_ON_PGFLAGS(PageTail(page), page); - if (PageHead(page)) - return HPAGE_PMD_NR; - return 1; -} - /** * folio_test_pmd_mappable - Can we map this folio with a PMD? * @folio: The folio to test @@ -336,18 +312,6 @@ static inline struct list_head *page_deferred_list(struct page *page) #define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; }) #define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; }) -static inline unsigned int thp_order(struct page *page) -{ - VM_BUG_ON_PGFLAGS(PageTail(page), page); - return 0; -} - -static inline int thp_nr_pages(struct page *page) -{ - VM_BUG_ON_PGFLAGS(PageTail(page), page); - return 1; -} - static inline bool folio_test_pmd_mappable(struct folio *folio) { return false; @@ -489,15 +453,4 @@ static inline int split_folio_to_list(struct folio *folio, return split_huge_page_to_list(&folio->page, list); } -/** - * thp_size - Size of a transparent huge page. - * @page: Head page of a transparent huge page. - * - * Return: Number of bytes in this page. - */ -static inline unsigned long thp_size(struct page *page) -{ - return PAGE_SIZE << thp_order(page); -} - #endif /* _LINUX_HUGE_MM_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index a879c583f665..c1966ad34142 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -939,6 +939,37 @@ static inline unsigned int page_shift(struct page *page) return PAGE_SHIFT + compound_order(page); } +/** + * thp_order - Order of a transparent huge page. + * @page: Head page of a transparent huge page. + */ +static inline unsigned int thp_order(struct page *page) +{ + VM_BUG_ON_PGFLAGS(PageTail(page), page); + return compound_order(page); +} + +/** + * thp_nr_pages - The number of regular pages in this huge page. + * @page: The head page of a huge page. + */ +static inline int thp_nr_pages(struct page *page) +{ + VM_BUG_ON_PGFLAGS(PageTail(page), page); + return compound_nr(page); +} + +/** + * thp_size - Size of a transparent huge page. + * @page: Head page of a transparent huge page. + * + * Return: Number of bytes in this page. + */ +static inline unsigned long thp_size(struct page *page) +{ + return PAGE_SIZE << thp_order(page); +} + void free_compound_page(struct page *page); #ifdef CONFIG_MMU -- cgit v1.2.3 From 351bdbb6419ca988802882badadc321d384d0254 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 21 Mar 2022 10:22:37 +0100 Subject: net: Revert the softirq will run annotation in ____napi_schedule(). The lockdep annotation lockdep_assert_softirq_will_run() expects that either hard or soft interrupts are disabled because both guaranty that the "raised" soft-interrupts will be processed once the context is left. This triggers in flush_smp_call_function_from_idle() but it this case it explicitly calls do_softirq() in case of pending softirqs. Revert the "softirq will run" annotation in ____napi_schedule() and move the check back to __netif_rx() as it was. Keep the IRQ-off assert in ____napi_schedule() because this is always required. Fixes: fbd9a2ceba5c7 ("net: Add lockdep asserts to ____napi_schedule().") Signed-off-by: Sebastian Andrzej Siewior Reviewed-by: Jason A. Donenfeld Link: https://lore.kernel.org/r/YjhD3ZKWysyw8rc6@linutronix.de Signed-off-by: Jakub Kicinski --- include/linux/lockdep.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 0cc65d216701..467b94257105 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -329,12 +329,6 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); #define lockdep_assert_none_held_once() \ lockdep_assert_once(!current->lockdep_depth) -/* - * Ensure that softirq is handled within the callchain and not delayed and - * handled by chance. - */ -#define lockdep_assert_softirq_will_run() \ - lockdep_assert_once(hardirq_count() | softirq_count()) #define lockdep_recursing(tsk) ((tsk)->lockdep_recursion) @@ -420,7 +414,6 @@ extern int lockdep_is_held(const void *); #define lockdep_assert_held_read(l) do { (void)(l); } while (0) #define lockdep_assert_held_once(l) do { (void)(l); } while (0) #define lockdep_assert_none_held_once() do { } while (0) -#define lockdep_assert_softirq_will_run() do { } while (0) #define lockdep_recursing(tsk) (0) -- cgit v1.2.3 From f5bfa23f576fdcc8e0b7fbff44cf70bd69ff9bdb Mon Sep 17 00:00:00 2001 From: Atish Patra Date: Fri, 18 Feb 2022 16:46:54 -0800 Subject: RISC-V: Add a perf core library for pmu drivers Implement a perf core library that can support all the essential perf features in future. It can also accommodate any type of PMU implementation in future. Currently, both SBI based perf driver and legacy driver implemented uses the library. Most of the common perf functionalities are kept in this core library wile PMU specific driver can implement PMU specific features. For example, the SBI specific functionality will be implemented in the SBI specific driver. Reviewed-by: Anup Patel Signed-off-by: Atish Patra Signed-off-by: Atish Patra Signed-off-by: Palmer Dabbelt --- include/linux/perf/riscv_pmu.h | 65 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 65 insertions(+) create mode 100644 include/linux/perf/riscv_pmu.h (limited to 'include') diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h new file mode 100644 index 000000000000..0d8979765d79 --- /dev/null +++ b/include/linux/perf/riscv_pmu.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2018 SiFive + * Copyright (C) 2018 Andes Technology Corporation + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + * + */ + +#ifndef _ASM_RISCV_PERF_EVENT_H +#define _ASM_RISCV_PERF_EVENT_H + +#include +#include +#include + +#ifdef CONFIG_RISCV_PMU + +/* + * The RISCV_MAX_COUNTERS parameter should be specified. + */ + +#define RISCV_MAX_COUNTERS 64 +#define RISCV_OP_UNSUPP (-EOPNOTSUPP) +#define RISCV_PMU_PDEV_NAME "riscv-pmu" + +#define RISCV_PMU_STOP_FLAG_RESET 1 + +struct cpu_hw_events { + /* currently enabled events */ + int n_events; + /* currently enabled events */ + struct perf_event *events[RISCV_MAX_COUNTERS]; + /* currently enabled counters */ + DECLARE_BITMAP(used_event_ctrs, RISCV_MAX_COUNTERS); +}; + +struct riscv_pmu { + struct pmu pmu; + char *name; + + irqreturn_t (*handle_irq)(int irq_num, void *dev); + + int num_counters; + u64 (*ctr_read)(struct perf_event *event); + int (*ctr_get_idx)(struct perf_event *event); + int (*ctr_get_width)(int idx); + void (*ctr_clear_idx)(struct perf_event *event); + void (*ctr_start)(struct perf_event *event, u64 init_val); + void (*ctr_stop)(struct perf_event *event, unsigned long flag); + int (*event_map)(struct perf_event *event, u64 *config); + + struct cpu_hw_events __percpu *hw_events; + struct hlist_node node; +}; + +#define to_riscv_pmu(p) (container_of(p, struct riscv_pmu, pmu)) +unsigned long riscv_pmu_ctr_read_csr(unsigned long csr); +int riscv_pmu_event_set_period(struct perf_event *event); +uint64_t riscv_pmu_ctr_get_width_mask(struct perf_event *event); +u64 riscv_pmu_event_update(struct perf_event *event); +struct riscv_pmu *riscv_pmu_alloc(void); + +#endif /* CONFIG_RISCV_PMU */ + +#endif /* _ASM_RISCV_PERF_EVENT_H */ -- cgit v1.2.3 From 9b3e150e310ee71d7bae1e31c38a300cfa5e951b Mon Sep 17 00:00:00 2001 From: Atish Patra Date: Fri, 18 Feb 2022 16:46:55 -0800 Subject: RISC-V: Add a simple platform driver for RISC-V legacy perf The old RISC-V perf implementation allowed counting of only cycle/instruction counters using perf. Restore that feature by implementing a simple platform driver under a separate config to provide backward compatibility. Any existing software stack will continue to work as it is. However, it provides an easy way out in future where we can remove the legacy driver. Reviewed-by: Anup Patel Signed-off-by: Atish Patra Signed-off-by: Atish Patra Signed-off-by: Palmer Dabbelt --- include/linux/perf/riscv_pmu.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h index 0d8979765d79..9140c491fc54 100644 --- a/include/linux/perf/riscv_pmu.h +++ b/include/linux/perf/riscv_pmu.h @@ -22,6 +22,7 @@ #define RISCV_MAX_COUNTERS 64 #define RISCV_OP_UNSUPP (-EOPNOTSUPP) #define RISCV_PMU_PDEV_NAME "riscv-pmu" +#define RISCV_PMU_LEGACY_PDEV_NAME "riscv-pmu-legacy" #define RISCV_PMU_STOP_FLAG_RESET 1 @@ -58,6 +59,11 @@ unsigned long riscv_pmu_ctr_read_csr(unsigned long csr); int riscv_pmu_event_set_period(struct perf_event *event); uint64_t riscv_pmu_ctr_get_width_mask(struct perf_event *event); u64 riscv_pmu_event_update(struct perf_event *event); +#ifdef CONFIG_RISCV_PMU_LEGACY +void riscv_pmu_legacy_skip_init(void); +#else +static inline void riscv_pmu_legacy_skip_init(void) {}; +#endif struct riscv_pmu *riscv_pmu_alloc(void); #endif /* CONFIG_RISCV_PMU */ -- cgit v1.2.3 From e9991434596f5373dfd75857b445eb92a9253c56 Mon Sep 17 00:00:00 2001 From: Atish Patra Date: Fri, 18 Feb 2022 16:46:57 -0800 Subject: RISC-V: Add perf platform driver based on SBI PMU extension RISC-V SBI specification added a PMU extension that allows to configure start/stop any pmu counter. The RISC-V perf can use most of the generic perf features except interrupt overflow and event filtering based on privilege mode which will be added in future. It also allows to monitor a handful of firmware counters that can provide insights into firmware activity during a performance analysis. Signed-off-by: Atish Patra Signed-off-by: Atish Patra Signed-off-by: Palmer Dabbelt --- include/linux/cpuhotplug.h | 1 + include/linux/perf/riscv_pmu.h | 6 ++++-- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 411a428ace4d..51c7e4929df7 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -165,6 +165,7 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING, CPUHP_AP_PERF_ARM_ACPI_STARTING, CPUHP_AP_PERF_ARM_STARTING, + CPUHP_AP_PERF_RISCV_STARTING, CPUHP_AP_ARM_L2X0_STARTING, CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING, CPUHP_AP_ARM_ARCH_TIMER_STARTING, diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h index 9140c491fc54..0f226948c0ca 100644 --- a/include/linux/perf/riscv_pmu.h +++ b/include/linux/perf/riscv_pmu.h @@ -31,8 +31,10 @@ struct cpu_hw_events { int n_events; /* currently enabled events */ struct perf_event *events[RISCV_MAX_COUNTERS]; - /* currently enabled counters */ - DECLARE_BITMAP(used_event_ctrs, RISCV_MAX_COUNTERS); + /* currently enabled hardware counters */ + DECLARE_BITMAP(used_hw_ctrs, RISCV_MAX_COUNTERS); + /* currently enabled firmware counters */ + DECLARE_BITMAP(used_fw_ctrs, RISCV_MAX_COUNTERS); }; struct riscv_pmu { -- cgit v1.2.3 From 4905ec2fb7e6421c14c9fb7276f5aa92f60f2b98 Mon Sep 17 00:00:00 2001 From: Atish Patra Date: Fri, 18 Feb 2022 16:46:58 -0800 Subject: RISC-V: Add sscofpmf extension support The sscofpmf extension allows counter overflow and filtering for programmable counters. Enable the perf driver to handle the overflow interrupt. The overflow interrupt is a hart local interrupt. Thus, per cpu overflow interrupts are setup as a child under the root INTC irq domain. Signed-off-by: Atish Patra Signed-off-by: Atish Patra Signed-off-by: Palmer Dabbelt --- include/linux/perf/riscv_pmu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h index 0f226948c0ca..46f9b6fe306e 100644 --- a/include/linux/perf/riscv_pmu.h +++ b/include/linux/perf/riscv_pmu.h @@ -29,6 +29,8 @@ struct cpu_hw_events { /* currently enabled events */ int n_events; + /* Counter overflow interrupt */ + int irq; /* currently enabled events */ struct perf_event *events[RISCV_MAX_COUNTERS]; /* currently enabled hardware counters */ -- cgit v1.2.3 From 863a66cdb4df25fd146d9851c3289072298566d5 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 16 Mar 2022 09:27:08 +0800 Subject: lib/sbitmap: allocate sb->map via kvzalloc_node sbitmap has been used in scsi for replacing atomic operations on sdev->device_busy, so IOPS on some fast scsi storage can be improved. However, sdev->device_busy can be changed in fast path, so we have to allocate the sb->map statically. sdev->device_busy has been capped to 1024, but some drivers may configure the default depth as < 8, then cause each sbitmap word to hold only one bit. Finally 1024 * 128( sizeof(sbitmap_word)) bytes is needed for sb->map, given it is order 5 allocation, sometimes it may fail. Avoid the issue by using kvzalloc_node() for allocating sb->map. Cc: Ewan D. Milne Signed-off-by: Ming Lei Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220316012708.354668-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- include/linux/sbitmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index dffeb8281c2d..8f5a86e210b9 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -174,7 +174,7 @@ static inline unsigned int __map_depth(const struct sbitmap *sb, int index) static inline void sbitmap_free(struct sbitmap *sb) { free_percpu(sb->alloc_hint); - kfree(sb->map); + kvfree(sb->map); sb->map = NULL; } -- cgit v1.2.3 From 4a0cb83ba6e0cd73a50fa4f84736846bf0029f2b Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 21 Mar 2022 22:10:53 -0700 Subject: netdevice: add missing dm_private kdoc Building htmldocs complains: include/linux/netdevice.h:2295: warning: Function parameter or member 'dm_private' not described in 'net_device' Fixes: b26ef81c46ed ("drop_monitor: remove quadratic behavior") Signed-off-by: Jakub Kicinski Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20220322051053.1883186-1-kuba@kernel.org Signed-off-by: Paolo Abeni --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e01a8ce7181f..cd7a597c55b1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1899,6 +1899,8 @@ enum netdev_ml_priv_type { * @garp_port: GARP * @mrp_port: MRP * + * @dm_private: Drop monitor private + * * @dev: Class/net/name entry * @sysfs_groups: Space for optional device, statistics and wireless * sysfs groups -- cgit v1.2.3 From 0313bc278dac7cd9ce83a8d384581dc043156965 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 22 Mar 2022 09:17:20 -0700 Subject: Revert "random: block in /dev/urandom" This reverts commit 6f98a4bfee72c22f50aedb39fb761567969865fe. It turns out we still can't do this. Way too many platforms that don't have any real source of randomness at boot and no jitter entropy because they don't even have a cycle counter. As reported by Guenter Roeck: "This causes a large number of qemu boot test failures for various architectures (arm, m68k, microblaze, sparc32, xtensa are the ones I observed). Common denominator is that boot hangs at 'Saving random seed:'" This isn't hugely unexpected - we tried it, it failed, so now we'll revert it. Link: https://lore.kernel.org/all/20220322155820.GA1745955@roeck-us.net/ Reported-and-bisected-by: Guenter Roeck Cc: Jason Donenfeld Signed-off-by: Linus Torvalds --- include/linux/random.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index c0baffe7afb1..f673fbb838b3 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -48,7 +48,7 @@ extern int unregister_random_ready_notifier(struct notifier_block *nb); extern size_t __must_check get_random_bytes_arch(void *buf, size_t nbytes); #ifndef MODULE -extern const struct file_operations random_fops; +extern const struct file_operations random_fops, urandom_fops; #endif u32 get_random_u32(void); -- cgit v1.2.3 From 89f42494f92f448747bd8a7ab1ae8b5d5520577d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 16 Mar 2022 19:10:43 -0400 Subject: SUNRPC: Don't call connect() more than once on a TCP socket Avoid socket state races due to repeated calls to ->connect() using the same socket. If connect() returns 0 due to the connection having completed, but we are in fact in a closing state, then we may leave the XPRT_CONNECTING flag set on the transport. Reported-by: Enrico Scholz Fixes: 3be232f11a3c ("SUNRPC: Prevent immediate close+reconnect") Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprtsock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 8c2a712cb242..689062afdd61 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -89,5 +89,6 @@ struct sock_xprt { #define XPRT_SOCK_WAKE_WRITE (5) #define XPRT_SOCK_WAKE_PENDING (6) #define XPRT_SOCK_WAKE_DISCONNECT (7) +#define XPRT_SOCK_CONNECT_SENT (8) #endif /* _LINUX_SUNRPC_XPRTSOCK_H */ -- cgit v1.2.3 From 2790a624d43084de590884934969e19c7a82316a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 15 Mar 2022 08:12:40 -0400 Subject: SUNRPC: Replace internal use of SOCKWQ_ASYNC_NOSPACE The socket's SOCKWQ_ASYNC_NOSPACE can be cleared by various actors in the socket layer, so replace it with our own flag in the transport sock_state field. Reported-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprtsock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 689062afdd61..3eb0079669c5 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -90,5 +90,6 @@ struct sock_xprt { #define XPRT_SOCK_WAKE_PENDING (6) #define XPRT_SOCK_WAKE_DISCONNECT (7) #define XPRT_SOCK_CONNECT_SENT (8) +#define XPRT_SOCK_NOSPACE (9) #endif /* _LINUX_SUNRPC_XPRTSOCK_H */ -- cgit v1.2.3 From 33e5c765bc1ea5e06ea7603637f14d727e6fcdf3 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 14 Mar 2022 22:02:22 -0400 Subject: NFS: Fix memory allocation in rpc_malloc() When in a low memory situation, we do want rpciod to kick off direct reclaim in the case where that helps, however we don't want it looping forever in mempool_alloc(). So first try allocating from the slab using GFP_KERNEL | __GFP_NORETRY, and then fall back to a GFP_NOWAIT allocation from the mempool. Ditto for rpc_alloc_task() Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 56710f8056d3..1d7a3e51b795 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -262,6 +262,7 @@ void rpc_destroy_mempool(void); extern struct workqueue_struct *rpciod_workqueue; extern struct workqueue_struct *xprtiod_workqueue; void rpc_prepare_task(struct rpc_task *task); +gfp_t rpc_task_gfp_mask(void); static inline int rpc_wait_for_completion_task(struct rpc_task *task) { -- cgit v1.2.3 From 515dcdcd48736576c6f5c197814da6f81c60a21e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 21 Mar 2022 12:34:19 -0400 Subject: NFS: nfsiod should not block forever in mempool_alloc() The concern is that since nfsiod is sometimes required to kick off a commit, it can get locked up waiting forever in mempool_alloc() instead of failing gracefully and leaving the commit until later. Try to allocate from the slab first, with GFP_KERNEL | __GFP_NORETRY, then fall back to a non-blocking attempt to allocate from the memory pool. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index c47c448befc8..db305abafc9e 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -580,7 +580,7 @@ extern int nfs_wb_all(struct inode *inode); extern int nfs_wb_page(struct inode *inode, struct page *page); extern int nfs_wb_page_cancel(struct inode *inode, struct page* page); extern int nfs_commit_inode(struct inode *, int); -extern struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail); +extern struct nfs_commit_data *nfs_commitdata_alloc(void); extern void nfs_commit_free(struct nfs_commit_data *data); bool nfs_commit_end(struct nfs_mds_commit_info *cinfo); -- cgit v1.2.3 From 92ee3c60ec9fe64404dc035e7c41277d74aa26cb Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 22 Mar 2022 18:07:17 +0100 Subject: ALSA: pcm: Fix races among concurrent hw_params and hw_free calls Currently we have neither proper check nor protection against the concurrent calls of PCM hw_params and hw_free ioctls, which may result in a UAF. Since the existing PCM stream lock can't be used for protecting the whole ioctl operations, we need a new mutex to protect those racy calls. This patch introduced a new mutex, runtime->buffer_mutex, and applies it to both hw_params and hw_free ioctl code paths. Along with it, the both functions are slightly modified (the mmap_count check is moved into the state-check block) for code simplicity. Reported-by: Hu Jiahui Cc: Reviewed-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20220322170720.3529-2-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/sound/pcm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/sound/pcm.h b/include/sound/pcm.h index 36da42cd0774..314f2779cab5 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -401,6 +401,7 @@ struct snd_pcm_runtime { wait_queue_head_t tsleep; /* transfer sleep */ struct fasync_struct *fasync; bool stop_operating; /* sync_stop will be called */ + struct mutex buffer_mutex; /* protect for buffer changes */ /* -- private section -- */ void *private_data; -- cgit v1.2.3 From 62eb29526b48d20704668a2fdf97a49d01bf52ce Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 22 Mar 2022 14:38:33 -0700 Subject: linux/kthread.h: remove unused macros Ever since these macros were introduced in commit b56c0d8937e6 ("kthread: implement kthread_worker"), there has been precisely one user (commit 4d115420707a, "NVMe: Async IO queue deletion"), and that user went away in 2016 with db3cbfff5bcc ("NVMe: IO queue deletion re-write"). Apart from being unused, these macros are also awkward to use (which may contribute to them not being used): Having a way to statically (or on-stack) allocating the storage for the struct kthread_worker itself doesn't help much, since obviously one needs to have some code for actually _spawning_ the worker thread, which must have error checking. And these days we have the kthread_create_worker() interface which both allocates the struct kthread_worker and spawns the kthread. Link: https://lkml.kernel.org/r/20220314145343.494694-1-linux@rasmusvillemoes.dk Signed-off-by: Rasmus Villemoes Acked-by: Tejun Heo Cc: "Eric W. Biederman" Cc: Petr Mladek Cc: David Hildenbrand Cc: Yafang Shao Cc: Cai Huoqing Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kthread.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 3df4ea04716f..de5d75bafd66 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -141,12 +141,6 @@ struct kthread_delayed_work { struct timer_list timer; }; -#define KTHREAD_WORKER_INIT(worker) { \ - .lock = __RAW_SPIN_LOCK_UNLOCKED((worker).lock), \ - .work_list = LIST_HEAD_INIT((worker).work_list), \ - .delayed_work_list = LIST_HEAD_INIT((worker).delayed_work_list),\ - } - #define KTHREAD_WORK_INIT(work, fn) { \ .node = LIST_HEAD_INIT((work).node), \ .func = (fn), \ @@ -158,9 +152,6 @@ struct kthread_delayed_work { TIMER_IRQSAFE), \ } -#define DEFINE_KTHREAD_WORKER(worker) \ - struct kthread_worker worker = KTHREAD_WORKER_INIT(worker) - #define DEFINE_KTHREAD_WORK(work, fn) \ struct kthread_work work = KTHREAD_WORK_INIT(work, fn) @@ -168,19 +159,6 @@ struct kthread_delayed_work { struct kthread_delayed_work dwork = \ KTHREAD_DELAYED_WORK_INIT(dwork, fn) -/* - * kthread_worker.lock needs its own lockdep class key when defined on - * stack with lockdep enabled. Use the following macros in such cases. - */ -#ifdef CONFIG_LOCKDEP -# define KTHREAD_WORKER_INIT_ONSTACK(worker) \ - ({ kthread_init_worker(&worker); worker; }) -# define DEFINE_KTHREAD_WORKER_ONSTACK(worker) \ - struct kthread_worker worker = KTHREAD_WORKER_INIT_ONSTACK(worker) -#else -# define DEFINE_KTHREAD_WORKER_ONSTACK(worker) DEFINE_KTHREAD_WORKER(worker) -#endif - extern void __kthread_init_worker(struct kthread_worker *worker, const char *name, struct lock_class_key *key); -- cgit v1.2.3 From bf507030f312c68fdbb17c2d33f317cda109a484 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 22 Mar 2022 14:38:48 -0700 Subject: doc: convert 'subsection' to 'section' in gfp.h Patch series "Remove remaining parts of congestion tracking code", v2. This patch (of 11): Various DOC: sections in gfp.h have subsection headers (~~~) but the place where they are included in mm-api.rst does not have section, only chapters. So convert to section headers (---) to avoid confusion. Specifically if sections are added later in mm-api.rst, an error results. Link: https://lkml.kernel.org/r/164549971112.9187.16871723439770288255.stgit@noble.brown Link: https://lkml.kernel.org/r/164549983733.9187.17894407453436115822.stgit@noble.brown Signed-off-by: NeilBrown Cc: Jan Kara Cc: Wu Fengguang Cc: Jaegeuk Kim Cc: Chao Yu Cc: Jeff Layton Cc: Ilya Dryomov Cc: Miklos Szeredi Cc: Trond Myklebust Cc: Anna Schumaker Cc: Ryusuke Konishi Cc: Darrick J. Wong Cc: Philipp Reisner Cc: Lars Ellenberg Cc: Paolo Valente Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 80f63c862be5..20f6fbe12993 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -79,7 +79,7 @@ struct vm_area_struct; * DOC: Page mobility and placement hints * * Page mobility and placement hints - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * --------------------------------- * * These flags provide hints about how mobile the page is. Pages with similar * mobility are placed within the same pageblocks to minimise problems due @@ -112,7 +112,7 @@ struct vm_area_struct; * DOC: Watermark modifiers * * Watermark modifiers -- controls access to emergency reserves - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * ------------------------------------------------------------ * * %__GFP_HIGH indicates that the caller is high-priority and that granting * the request is necessary before the system can make forward progress. @@ -144,7 +144,7 @@ struct vm_area_struct; * DOC: Reclaim modifiers * * Reclaim modifiers - * ~~~~~~~~~~~~~~~~~ + * ----------------- * Please note that all the following flags are only applicable to sleepable * allocations (e.g. %GFP_NOWAIT and %GFP_ATOMIC will ignore them). * @@ -224,7 +224,7 @@ struct vm_area_struct; * DOC: Action modifiers * * Action modifiers - * ~~~~~~~~~~~~~~~~ + * ---------------- * * %__GFP_NOWARN suppresses allocation failure reports. * @@ -256,7 +256,7 @@ struct vm_area_struct; * DOC: Useful GFP flag combinations * * Useful GFP flag combinations - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * ---------------------------- * * Useful GFP flag combinations that are commonly used. It is recommended * that subsystems start with one of these combinations and then set/clear -- cgit v1.2.3 From 84dacdbd5352bfef82423760fa2e8bffaeef9e05 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 22 Mar 2022 14:38:51 -0700 Subject: mm: document and polish read-ahead code Add some "big-picture" documentation for read-ahead and polish the code to make it fit this documentation. The meaning of ->async_size is clarified to match its name. i.e. Any request to ->readahead() has a sync part and an async part. The caller will wait for the sync pages to complete, but will not wait for the async pages. The first async page is still marked PG_readahead Note that the current function names page_cache_sync_ra() and page_cache_async_ra() are misleading. All ra request are partly sync and partly async, so either part can be empty. A page_cache_sync_ra() request will usually set ->async_size non-zero, implying it is not all synchronous. When a non-zero req_count is passed to page_cache_async_ra(), the implication is that some prefix of the request is synchronous, though the calculation made there is incorrect - I haven't tried to fix it. Link: https://lkml.kernel.org/r/164549983734.9187.11586890887006601405.stgit@noble.brown Signed-off-by: NeilBrown Cc: Anna Schumaker Cc: Chao Yu Cc: Darrick J. Wong Cc: Ilya Dryomov Cc: Jaegeuk Kim Cc: Jan Kara Cc: Jeff Layton Cc: Jens Axboe Cc: Lars Ellenberg Cc: Miklos Szeredi Cc: Paolo Valente Cc: Philipp Reisner Cc: Ryusuke Konishi Cc: Trond Myklebust Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index e2d892b201b0..8b5c486bd4a2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -930,10 +930,15 @@ struct fown_struct { * struct file_ra_state - Track a file's readahead state. * @start: Where the most recent readahead started. * @size: Number of pages read in the most recent readahead. - * @async_size: Start next readahead when this many pages are left. - * @ra_pages: Maximum size of a readahead request. + * @async_size: Numer of pages that were/are not needed immediately + * and so were/are genuinely "ahead". Start next readahead when + * the first of these pages is accessed. + * @ra_pages: Maximum size of a readahead request, copied from the bdi. * @mmap_miss: How many mmap accesses missed in the page cache. * @prev_pos: The last byte in the most recent read request. + * + * When this structure is passed to ->readahead(), the "most recent" + * readahead means the current readahead. */ struct file_ra_state { pgoff_t start; -- cgit v1.2.3 From 6df25e58532be7a4cd6fb15bcd85805947402d91 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 22 Mar 2022 14:39:01 -0700 Subject: nfs: remove reliance on bdi congestion The bdi congestion tracking in not widely used and will be removed. NFS is one of a small number of filesystems that uses it, setting just the async (write) congestion flag at what it determines are appropriate times. The only remaining effect of the async flag is to cause (some) WB_SYNC_NONE writes to be skipped. So instead of setting the flag, set an internal flag and change: - .writepages to do nothing if WB_SYNC_NONE and the flag is set - .writepage to return AOP_WRITEPAGE_ACTIVATE if WB_SYNC_NONE and the flag is set. The writepages change causes a behavioural change in that pageout() can now return PAGE_ACTIVATE instead of PAGE_KEEP, so SetPageActive() will be called on the page which (I think) wil further delay the next attempt at writeout. This might be a good thing. Link: https://lkml.kernel.org/r/164549983738.9187.3972219847989393182.stgit@noble.brown Signed-off-by: NeilBrown Cc: Anna Schumaker Cc: Chao Yu Cc: Darrick J. Wong Cc: Ilya Dryomov Cc: Jaegeuk Kim Cc: Jan Kara Cc: Jeff Layton Cc: Jens Axboe Cc: Lars Ellenberg Cc: Miklos Szeredi Cc: Paolo Valente Cc: Philipp Reisner Cc: Ryusuke Konishi Cc: Trond Myklebust Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfs_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index ca0959e51e81..6aa2a200676a 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -138,6 +138,7 @@ struct nfs_server { struct nlm_host *nlm_host; /* NLM client handle */ struct nfs_iostats __percpu *io_stats; /* I/O statistics */ atomic_long_t writeback; /* number of writeback pages */ + unsigned int write_congested;/* flag set when writeback gets too high */ unsigned int flags; /* various flags */ /* The following are for internal use only. Also see uapi/linux/nfs_mount.h */ -- cgit v1.2.3 From fe55d563d4174f13839a9b7ef7309da5031b5d93 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 22 Mar 2022 14:39:07 -0700 Subject: remove inode_congested() inode_congested() reports if the backing-device for the inode is congested. No bdi reports congestion any more, so this always returns 'false'. So remove inode_congested() and related functions, and remove the call sites, assuming that inode_congested() always returns 'false'. Link: https://lkml.kernel.org/r/164549983741.9187.2174285592262191311.stgit@noble.brown Signed-off-by: NeilBrown Cc: Anna Schumaker Cc: Chao Yu Cc: Darrick J. Wong Cc: Ilya Dryomov Cc: Jaegeuk Kim Cc: Jan Kara Cc: Jeff Layton Cc: Jens Axboe Cc: Lars Ellenberg Cc: Miklos Szeredi Cc: Paolo Valente Cc: Philipp Reisner Cc: Ryusuke Konishi Cc: Trond Myklebust Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 483979c1b9f4..860b675c2929 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -162,7 +162,6 @@ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, gfp_t gfp); void wb_memcg_offline(struct mem_cgroup *memcg); void wb_blkcg_offline(struct blkcg *blkcg); -int inode_congested(struct inode *inode, int cong_bits); /** * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode @@ -390,29 +389,8 @@ static inline void wb_blkcg_offline(struct blkcg *blkcg) { } -static inline int inode_congested(struct inode *inode, int cong_bits) -{ - return wb_congested(&inode_to_bdi(inode)->wb, cong_bits); -} - #endif /* CONFIG_CGROUP_WRITEBACK */ -static inline int inode_read_congested(struct inode *inode) -{ - return inode_congested(inode, 1 << WB_sync_congested); -} - -static inline int inode_write_congested(struct inode *inode) -{ - return inode_congested(inode, 1 << WB_async_congested); -} - -static inline int inode_rw_congested(struct inode *inode) -{ - return inode_congested(inode, (1 << WB_sync_congested) | - (1 << WB_async_congested)); -} - static inline int bdi_congested(struct backing_dev_info *bdi, int cong_bits) { return wb_congested(&bdi->wb, cong_bits); -- cgit v1.2.3 From b9b1335e640308acc1b8f26c739b804c80a6c147 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 22 Mar 2022 14:39:10 -0700 Subject: remove bdi_congested() and wb_congested() and related functions These functions are no longer useful as no BDIs report congestions any more. Removing the test on bdi_write_contested() in current_may_throttle() could cause a small change in behaviour, but only when PF_LOCAL_THROTTLE is set. So replace the calls by 'false' and simplify the code - and remove the functions. [akpm@linux-foundation.org: fix build] Link: https://lkml.kernel.org/r/164549983742.9187.2570198746005819592.stgit@noble.brown Signed-off-by: NeilBrown Acked-by: Ryusuke Konishi [nilfs] Cc: Anna Schumaker Cc: Chao Yu Cc: Darrick J. Wong Cc: Ilya Dryomov Cc: Jaegeuk Kim Cc: Jan Kara Cc: Jeff Layton Cc: Jens Axboe Cc: Lars Ellenberg Cc: Miklos Szeredi Cc: Paolo Valente Cc: Philipp Reisner Cc: Trond Myklebust Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev.h | 26 -------------------------- 1 file changed, 26 deletions(-) (limited to 'include') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 860b675c2929..2d764566280c 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -135,11 +135,6 @@ static inline bool writeback_in_progress(struct bdi_writeback *wb) struct backing_dev_info *inode_to_bdi(struct inode *inode); -static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) -{ - return wb->congested & cong_bits; -} - long congestion_wait(int sync, long timeout); static inline bool mapping_can_writeback(struct address_space *mapping) @@ -391,27 +386,6 @@ static inline void wb_blkcg_offline(struct blkcg *blkcg) #endif /* CONFIG_CGROUP_WRITEBACK */ -static inline int bdi_congested(struct backing_dev_info *bdi, int cong_bits) -{ - return wb_congested(&bdi->wb, cong_bits); -} - -static inline int bdi_read_congested(struct backing_dev_info *bdi) -{ - return bdi_congested(bdi, 1 << WB_sync_congested); -} - -static inline int bdi_write_congested(struct backing_dev_info *bdi) -{ - return bdi_congested(bdi, 1 << WB_async_congested); -} - -static inline int bdi_rw_congested(struct backing_dev_info *bdi) -{ - return bdi_congested(bdi, (1 << WB_sync_congested) | - (1 << WB_async_congested)); -} - const char *bdi_dev_name(struct backing_dev_info *bdi); #endif /* _LINUX_BACKING_DEV_H */ -- cgit v1.2.3 From a88f2096d5a2d91179db5dd9aa8f60dc3df9bb3e Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 22 Mar 2022 14:39:19 -0700 Subject: remove congestion tracking framework This framework is no longer used - so discard it. Link: https://lkml.kernel.org/r/164549983747.9187.6171768583526866601.stgit@noble.brown Signed-off-by: NeilBrown Cc: Anna Schumaker Cc: Chao Yu Cc: Darrick J. Wong Cc: Ilya Dryomov Cc: Jaegeuk Kim Cc: Jan Kara Cc: Jeff Layton Cc: Jens Axboe Cc: Lars Ellenberg Cc: Miklos Szeredi Cc: Paolo Valente Cc: Philipp Reisner Cc: Ryusuke Konishi Cc: Trond Myklebust Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev-defs.h | 8 -------- include/linux/backing-dev.h | 2 -- include/trace/events/writeback.h | 28 ---------------------------- 3 files changed, 38 deletions(-) (limited to 'include') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 993c5628a726..e863c88df95f 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -207,14 +207,6 @@ struct backing_dev_info { #endif }; -enum { - BLK_RW_ASYNC = 0, - BLK_RW_SYNC = 1, -}; - -void clear_bdi_congested(struct backing_dev_info *bdi, int sync); -void set_bdi_congested(struct backing_dev_info *bdi, int sync); - struct wb_lock_cookie { bool locked; unsigned long flags; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 2d764566280c..87ce24d238f3 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -135,8 +135,6 @@ static inline bool writeback_in_progress(struct bdi_writeback *wb) struct backing_dev_info *inode_to_bdi(struct inode *inode); -long congestion_wait(int sync, long timeout); - static inline bool mapping_can_writeback(struct address_space *mapping) { return inode_to_bdi(mapping->host)->capabilities & BDI_CAP_WRITEBACK; diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index a345b1e12daf..86b2a82da546 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -735,34 +735,6 @@ TRACE_EVENT(writeback_sb_inodes_requeue, ) ); -DECLARE_EVENT_CLASS(writeback_congest_waited_template, - - TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed), - - TP_ARGS(usec_timeout, usec_delayed), - - TP_STRUCT__entry( - __field( unsigned int, usec_timeout ) - __field( unsigned int, usec_delayed ) - ), - - TP_fast_assign( - __entry->usec_timeout = usec_timeout; - __entry->usec_delayed = usec_delayed; - ), - - TP_printk("usec_timeout=%u usec_delayed=%u", - __entry->usec_timeout, - __entry->usec_delayed) -); - -DEFINE_EVENT(writeback_congest_waited_template, writeback_congestion_wait, - - TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed), - - TP_ARGS(usec_timeout, usec_delayed) -); - DECLARE_EVENT_CLASS(writeback_single_inode_template, TP_PROTO(struct inode *inode, -- cgit v1.2.3 From a128b054ce029554a4a52fc3abb8c1df8bafcaef Mon Sep 17 00:00:00 2001 From: Anthony Iliopoulos Date: Tue, 22 Mar 2022 14:39:22 -0700 Subject: mount: warn only once about timestamp range expiration Commit f8b92ba67c5d ("mount: Add mount warning for impending timestamp expiry") introduced a mount warning regarding filesystem timestamp limits, that is printed upon each writable mount or remount. This can result in a lot of unnecessary messages in the kernel log in setups where filesystems are being frequently remounted (or mounted multiple times). Avoid this by setting a superblock flag which indicates that the warning has been emitted at least once for any particular mount, as suggested in [1]. Link: https://lore.kernel.org/CAHk-=wim6VGnxQmjfK_tDg6fbHYKL4EFkmnTjVr9QnRqjDBAeA@mail.gmail.com/ [1] Link: https://lkml.kernel.org/r/20220119202934.26495-1-ailiop@suse.com Signed-off-by: Anthony Iliopoulos Reviewed-by: Christoph Hellwig Acked-by: Christian Brauner Reviewed-by: Darrick J. Wong Cc: Alexander Viro Cc: Deepa Dinamani Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 8b5c486bd4a2..ca9445f6cf3d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1440,6 +1440,7 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ #define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ +#define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */ /* Possible states of 'frozen' field */ enum { -- cgit v1.2.3 From eb5279fb7e41804ecc15ed3cf716a9e2b419af57 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Tue, 22 Mar 2022 14:39:28 -0700 Subject: filemap: remove find_get_pages() It's unused now. Remove it and clean up the relevant comment. Link: https://lkml.kernel.org/r/20220208134149.47299-1-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox (Oracle) Cc: David Howells Cc: William Kucharski Cc: Vlastimil Babka Cc: Kirill A. Shutemov Cc: Johannes Weiner Cc: Andreas Gruenbacher Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 270bf5136c34..dc31eb981ea2 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -594,13 +594,6 @@ static inline struct page *find_subpage(struct page *head, pgoff_t index) unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, pgoff_t end, unsigned int nr_pages, struct page **pages); -static inline unsigned find_get_pages(struct address_space *mapping, - pgoff_t *start, unsigned int nr_pages, - struct page **pages) -{ - return find_get_pages_range(mapping, start, (pgoff_t)-1, nr_pages, - pages); -} unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, -- cgit v1.2.3 From ad6c441266dcd50be080a47e1178a1b15369923c Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Tue, 22 Mar 2022 14:39:43 -0700 Subject: mm/gup: remove unused pin_user_pages_locked() This routine was used for a short while, but then the calling code was refactored and the only caller was removed. Link: https://lkml.kernel.org/r/20220204020010.68930-4-jhubbard@nvidia.com Signed-off-by: John Hubbard Reviewed-by: David Hildenbrand Reviewed-by: Jason Gunthorpe Reviewed-by: Jan Kara Reviewed-by: Christoph Hellwig Reviewed-by: Claudio Imbrenda Cc: Alex Williamson Cc: Andrea Arcangeli Cc: Jason Gunthorpe Cc: Kirill A. Shutemov Cc: Lukas Bulwahn Cc: Matthew Wilcox (Oracle) Cc: Peter Xu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5744a3fc4716..d4a2b40066fa 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1918,8 +1918,6 @@ long pin_user_pages(unsigned long start, unsigned long nr_pages, struct vm_area_struct **vmas); long get_user_pages_locked(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); -long pin_user_pages_locked(unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, int *locked); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, -- cgit v1.2.3 From 73fd16d8080f7b1537ba7aa29917f64d6fffa664 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Tue, 22 Mar 2022 14:39:50 -0700 Subject: mm/gup: remove unused get_user_pages_locked() Now that the last caller of get_user_pages_locked() is gone, remove it. Link: https://lkml.kernel.org/r/20220204020010.68930-6-jhubbard@nvidia.com Signed-off-by: John Hubbard Reviewed-by: Jan Kara Reviewed-by: Jason Gunthorpe Reviewed-by: Claudio Imbrenda Reviewed-by: Christoph Hellwig Cc: Alex Williamson Cc: Andrea Arcangeli Cc: David Hildenbrand Cc: Jason Gunthorpe Cc: Kirill A. Shutemov Cc: Lukas Bulwahn Cc: Matthew Wilcox (Oracle) Cc: Peter Xu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index d4a2b40066fa..c02a8cc16e4f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1916,8 +1916,6 @@ long get_user_pages(unsigned long start, unsigned long nr_pages, long pin_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas); -long get_user_pages_locked(unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, int *locked); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, -- cgit v1.2.3 From f7cd16a55837f37b4c3835a2c646023e4d0f0e04 Mon Sep 17 00:00:00 2001 From: Xavier Roche Date: Tue, 22 Mar 2022 14:39:55 -0700 Subject: tmpfs: support for file creation time Various filesystems (including ext4) now support file creation time. This adds such support for tmpfs-based filesystems. Note that using shmem_getattr() on other file types than regular requires that shmem_is_huge() check type, to stop incorrect HPAGE_PMD_SIZE blksize. [hughd@google.com: three tweaks to creation time patch] Link: https://lkml.kernel.org/r/b954973a-b8d1-cab8-63bd-6ea8063de3@google.com Link: https://lkml.kernel.org/r/20220314211150.GA123458@xavier-xps Link: https://lkml.kernel.org/r/b954973a-b8d1-cab8-63bd-6ea8063de3@google.com Link: https://lkml.kernel.org/r/20220211213628.GA1919658@xavier-xps Signed-off-by: Xavier Roche Signed-off-by: Hugh Dickins Tested-by: Jean Delvare Tested-by: Sylvain Bellone Reported-by: Xavier Grand Reviewed-by: Jean Delvare Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index e65b80ed09e7..ab51d3cd39bd 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -24,6 +24,7 @@ struct shmem_inode_info { struct shared_policy policy; /* NUMA memory alloc policy */ struct simple_xattrs xattrs; /* list of xattrs */ atomic_t stop_eviction; /* hold when working on inode */ + struct timespec64 i_crtime; /* file creation time */ struct inode vfs_inode; }; -- cgit v1.2.3 From a8c49af3be5f0b4e105ef678bcf14ef102c270be Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Tue, 22 Mar 2022 14:40:10 -0700 Subject: memcg: add per-memcg total kernel memory stat Currently memcg stats show several types of kernel memory: kernel stack, page tables, sock, vmalloc, and slab. However, there are other allocations with __GFP_ACCOUNT (or supersets such as GFP_KERNEL_ACCOUNT) that are not accounted in any of those stats, a few examples are: - various kvm allocations (e.g. allocated pages to create vcpus) - io_uring - tmp_page in pipes during pipe_write() - bpf ringbuffers - unix sockets Keeping track of the total kernel memory is essential for the ease of migration from cgroup v1 to v2 as there are large discrepancies between v1's kmem.usage_in_bytes and the sum of the available kernel memory stats in v2. Adding separate memcg stats for all __GFP_ACCOUNT kernel allocations is an impractical maintenance burden as there a lot of those all over the kernel code, with more use cases likely to show up in the future. Therefore, add a "kernel" memcg stat that is analogous to kmem page counter, with added benefits such as using rstat infrastructure which aggregates stats more efficiently. Additionally, this provides a lighter alternative in case the legacy kmem is deprecated in the future [yosryahmed@google.com: v2] Link: https://lkml.kernel.org/r/20220203193856.972500-1-yosryahmed@google.com Link: https://lkml.kernel.org/r/20220201200823.3283171-1-yosryahmed@google.com Signed-off-by: Yosry Ahmed Acked-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 0abbd685703b..8612d7dd0859 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -34,6 +34,7 @@ enum memcg_stat_item { MEMCG_SOCK, MEMCG_PERCPU_B, MEMCG_VMALLOC, + MEMCG_KMEM, MEMCG_NR_STAT, }; -- cgit v1.2.3 From 486bc7060cb510fa60cb85a013d5ed51ce0fe456 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Tue, 22 Mar 2022 14:40:16 -0700 Subject: mm/memcg: retrieve parent memcg from css.parent The parent we get from page_counter is correct, while this is two different hierarchy. Let's retrieve the parent memcg from css.parent just like parent_cs(), blkcg_parent(), etc. Link: https://lkml.kernel.org/r/20220201004643.8391-2-richard.weiyang@gmail.com Signed-off-by: Wei Yang Reviewed-by: Muchun Song Acked-by: Michal Hocko Reviewed-by: Roman Gushchin Reviewed-by: Shakeel Butt Cc: Roman Gushchin Cc: Johannes Weiner Cc: Vladimir Davydov Cc: Yang Shi Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Mike Rapoport Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 8612d7dd0859..ef4b445392a9 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -842,9 +842,7 @@ static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) */ static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { - if (!memcg->memory.parent) - return NULL; - return mem_cgroup_from_counter(memcg->memory.parent, memory); + return mem_cgroup_from_css(memcg->css.parent); } static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, -- cgit v1.2.3 From 6a6b7b77cc0fdc13f50c66c219c8c05500a8dfce Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 22 Mar 2022 14:40:53 -0700 Subject: mm: list_lru: transpose the array of per-node per-memcg lru lists Patch series "Optimize list lru memory consumption", v6. In our server, we found a suspected memory leak problem. The kmalloc-32 consumes more than 6GB of memory. Other kmem_caches consume less than 2GB memory. After our in-depth analysis, the memory consumption of kmalloc-32 slab cache is the cause of list_lru_one allocation. crash> p memcg_nr_cache_ids memcg_nr_cache_ids = $2 = 24574 memcg_nr_cache_ids is very large and memory consumption of each list_lru can be calculated with the following formula. num_numa_node * memcg_nr_cache_ids * 32 (kmalloc-32) There are 4 numa nodes in our system, so each list_lru consumes ~3MB. crash> list super_blocks | wc -l 952 Every mount will register 2 list lrus, one is for inode, another is for dentry. There are 952 super_blocks. So the total memory is 952 * 2 * 3 MB (~5.6GB). But now the number of memory cgroups is less than 500. So I guess more than 12286 memory cgroups have been created on this machine (I do not know why there are so many cgroups, it may be a user's bug or the user really want to do that). Because memcg_nr_cache_ids has not been reduced to a suitable value. It leads to waste a lot of memory. If we want to reduce memcg_nr_cache_ids, we have to *reboot* the server. This is not what we want. In order to reduce memcg_nr_cache_ids, I had posted a patchset [1] to do this. But this did not fundamentally solve the problem. We currently allocate scope for every memcg to be able to tracked on every superblock instantiated in the system, regardless of whether that superblock is even accessible to that memcg. These huge memcg counts come from container hosts where memcgs are confined to just a small subset of the total number of superblocks that instantiated at any given point in time. For these systems with huge container counts, list_lru does not need the capability of tracking every memcg on every superblock. What it comes down to is that the list_lru is only needed for a given memcg if that memcg is instatiating and freeing objects on a given list_lru. As Dave said, "Which makes me think we should be moving more towards 'add the memcg to the list_lru at the first insert' model rather than 'instantiate all at memcg init time just in case'." This patchset aims to optimize the list lru memory consumption from different aspects. I had done a easy test to show the optimization. I create 10k memory cgroups and mount 10k filesystems in the systems. We use free command to show how many memory does the systems comsumes after this operation (There are 2 numa nodes in the system). +-----------------------+------------------------+ | condition | memory consumption | +-----------------------+------------------------+ | without this patchset | 24464 MB | +-----------------------+------------------------+ | after patch 1 | 21957 MB | <--------+ +-----------------------+------------------------+ | | after patch 10 | 6895 MB | | +-----------------------+------------------------+ | | after patch 12 | 4367 MB | | +-----------------------+------------------------+ | | The more the number of nodes, the more obvious the effect---+ BTW, there was a recent discussion [2] on the same issue. [1] https://lore.kernel.org/all/20210428094949.43579-1-songmuchun@bytedance.com/ [2] https://lore.kernel.org/all/20210405054848.GA1077931@in.ibm.com/ This series not only optimizes the memory usage of list_lru but also simplifies the code. This patch (of 16): The current scheme of maintaining per-node per-memcg lru lists looks like: struct list_lru { struct list_lru_node *node; (for each node) struct list_lru_memcg *memcg_lrus; struct list_lru_one *lru[]; (for each memcg) } By effectively transposing the two-dimension array of list_lru_one's structures (per-node per-memcg => per-memcg per-node) it's possible to save some memory and simplify alloc/dealloc paths. The new scheme looks like: struct list_lru { struct list_lru_memcg *mlrus; struct list_lru_per_memcg *mlru[]; (for each memcg) struct list_lru_one node[0]; (for each node) } Memory savings are coming from not only 'struct rcu_head' but also some pointer arrays used to store the pointer to 'struct list_lru_one'. The array is per node and its size is 8 (a pointer) * num_memcgs. So the total size of the arrays is 8 * num_nodes * memcg_nr_cache_ids. After this patch, the size becomes 8 * memcg_nr_cache_ids. Link: https://lkml.kernel.org/r/20220228122126.37293-1-songmuchun@bytedance.com Link: https://lkml.kernel.org/r/20220228122126.37293-2-songmuchun@bytedance.com Signed-off-by: Muchun Song Acked-by: Johannes Weiner Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Vladimir Davydov Cc: Shakeel Butt Cc: Yang Shi Cc: Alex Shi Cc: Wei Yang Cc: Dave Chinner Cc: Trond Myklebust Cc: Anna Schumaker Cc: Jaegeuk Kim Cc: Chao Yu Cc: Kari Argillander Cc: Vlastimil Babka Cc: Qi Zheng Cc: Xiongchun Duan Cc: Fam Zheng Cc: Roman Gushchin Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list_lru.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 1b5fceb565df..729a27b6ff53 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -31,10 +31,15 @@ struct list_lru_one { long nr_items; }; +struct list_lru_per_memcg { + /* array of per cgroup per node lists, indexed by node id */ + struct list_lru_one node[0]; +}; + struct list_lru_memcg { - struct rcu_head rcu; + struct rcu_head rcu; /* array of per cgroup lists, indexed by memcg_cache_id */ - struct list_lru_one *lru[]; + struct list_lru_per_memcg *mlru[]; }; struct list_lru_node { @@ -42,11 +47,7 @@ struct list_lru_node { spinlock_t lock; /* global list, used for the root cgroup in cgroup aware lrus */ struct list_lru_one lru; -#ifdef CONFIG_MEMCG_KMEM - /* for cgroup aware lrus points to per cgroup lists, otherwise NULL */ - struct list_lru_memcg __rcu *memcg_lrus; -#endif - long nr_items; + long nr_items; } ____cacheline_aligned_in_smp; struct list_lru { @@ -55,6 +56,8 @@ struct list_lru { struct list_head list; int shrinker_id; bool memcg_aware; + /* for cgroup aware lrus points to per cgroup lists, otherwise NULL */ + struct list_lru_memcg __rcu *mlrus; #endif }; -- cgit v1.2.3 From 88f2ef73fd66491a2f9a82373d22ca6540f23c62 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 22 Mar 2022 14:40:56 -0700 Subject: mm: introduce kmem_cache_alloc_lru We currently allocate scope for every memcg to be able to tracked on every superblock instantiated in the system, regardless of whether that superblock is even accessible to that memcg. These huge memcg counts come from container hosts where memcgs are confined to just a small subset of the total number of superblocks that instantiated at any given point in time. For these systems with huge container counts, list_lru does not need the capability of tracking every memcg on every superblock. What it comes down to is that adding the memcg to the list_lru at the first insert. So introduce kmem_cache_alloc_lru to allocate objects and its list_lru. In the later patch, we will convert all inode and dentry allocation from kmem_cache_alloc to kmem_cache_alloc_lru. Link: https://lkml.kernel.org/r/20220228122126.37293-3-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Alex Shi Cc: Anna Schumaker Cc: Chao Yu Cc: Dave Chinner Cc: Fam Zheng Cc: Jaegeuk Kim Cc: Johannes Weiner Cc: Kari Argillander Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Qi Zheng Cc: Roman Gushchin Cc: Shakeel Butt Cc: Theodore Ts'o Cc: Trond Myklebust Cc: Vladimir Davydov Cc: Vlastimil Babka Cc: Wei Yang Cc: Xiongchun Duan Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list_lru.h | 4 ++++ include/linux/memcontrol.h | 14 ++++++++++++++ include/linux/slab.h | 3 +++ 3 files changed, 21 insertions(+) (limited to 'include') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 729a27b6ff53..ab912c49334f 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -56,6 +56,8 @@ struct list_lru { struct list_head list; int shrinker_id; bool memcg_aware; + /* protects ->mlrus->mlru[i] */ + spinlock_t lock; /* for cgroup aware lrus points to per cgroup lists, otherwise NULL */ struct list_lru_memcg __rcu *mlrus; #endif @@ -72,6 +74,8 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware, #define list_lru_init_memcg(lru, shrinker) \ __list_lru_init((lru), true, NULL, shrinker) +int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, + gfp_t gfp); int memcg_update_all_list_lrus(int num_memcgs); void memcg_drain_all_list_lrus(int src_idx, struct mem_cgroup *dst_memcg); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index ef4b445392a9..b636732f0c14 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -524,6 +524,20 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page) return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); } +static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg) +{ + struct mem_cgroup *memcg; + + rcu_read_lock(); +retry: + memcg = obj_cgroup_memcg(objcg); + if (unlikely(!css_tryget(&memcg->css))) + goto retry; + rcu_read_unlock(); + + return memcg; +} + #ifdef CONFIG_MEMCG_KMEM /* * folio_memcg_kmem - Check if the folio has the memcg_kmem flag set. diff --git a/include/linux/slab.h b/include/linux/slab.h index 5b6193fd8bd9..e6addaf91afd 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -135,6 +135,7 @@ #include +struct list_lru; struct mem_cgroup; /* * struct kmem_cache related prototypes @@ -416,6 +417,8 @@ static __always_inline unsigned int __kmalloc_index(size_t size, void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1); void *kmem_cache_alloc(struct kmem_cache *s, gfp_t flags) __assume_slab_alignment __malloc; +void *kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru, + gfp_t gfpflags) __assume_slab_alignment __malloc; void kmem_cache_free(struct kmem_cache *s, void *objp); /* -- cgit v1.2.3 From 8b9f3ac5b01db85c6cf74c2c3a71280cc3045c9c Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 22 Mar 2022 14:41:00 -0700 Subject: fs: introduce alloc_inode_sb() to allocate filesystems specific inode The allocated inode cache is supposed to be added to its memcg list_lru which should be allocated as well in advance. That can be done by kmem_cache_alloc_lru() which allocates object and list_lru. The file systems is main user of it. So introduce alloc_inode_sb() to allocate file system specific inodes and set up the inode reclaim context properly. The file system is supposed to use alloc_inode_sb() to allocate inodes. In later patches, we will convert all users to the new API. Link: https://lkml.kernel.org/r/20220228122126.37293-4-songmuchun@bytedance.com Signed-off-by: Muchun Song Reviewed-by: Roman Gushchin Cc: Alex Shi Cc: Anna Schumaker Cc: Chao Yu Cc: Dave Chinner Cc: Fam Zheng Cc: Jaegeuk Kim Cc: Johannes Weiner Cc: Kari Argillander Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Qi Zheng Cc: Shakeel Butt Cc: Theodore Ts'o Cc: Trond Myklebust Cc: Vladimir Davydov Cc: Vlastimil Babka Cc: Wei Yang Cc: Xiongchun Duan Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index ca9445f6cf3d..58a73e59e4c0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -42,6 +42,7 @@ #include #include #include +#include #include #include @@ -3114,6 +3115,16 @@ extern void free_inode_nonrcu(struct inode *inode); extern int should_remove_suid(struct dentry *); extern int file_remove_privs(struct file *); +/* + * This must be used for allocating filesystems specific inodes to set + * up the inode reclaim context correctly. + */ +static inline void * +alloc_inode_sb(struct super_block *sb, struct kmem_cache *cache, gfp_t gfp) +{ + return kmem_cache_alloc_lru(cache, &sb->s_inode_lru, gfp); +} + extern void __insert_inode_hash(struct inode *, unsigned long hashval); static inline void insert_inode_hash(struct inode *inode) { -- cgit v1.2.3 From 9bbdc0f324097f72b2354c2f8be4cdffd32679b6 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 22 Mar 2022 14:41:12 -0700 Subject: xarray: use kmem_cache_alloc_lru to allocate xa_node The workingset will add the xa_node to the shadow_nodes list. So the allocation of xa_node should be done by kmem_cache_alloc_lru(). Using xas_set_lru() to pass the list_lru which we want to insert xa_node into to set up the xa_node reclaim context correctly. Link: https://lkml.kernel.org/r/20220228122126.37293-9-songmuchun@bytedance.com Signed-off-by: Muchun Song Acked-by: Johannes Weiner Acked-by: Roman Gushchin Cc: Alex Shi Cc: Anna Schumaker Cc: Chao Yu Cc: Dave Chinner Cc: Fam Zheng Cc: Jaegeuk Kim Cc: Kari Argillander Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Qi Zheng Cc: Shakeel Butt Cc: Theodore Ts'o Cc: Trond Myklebust Cc: Vladimir Davydov Cc: Vlastimil Babka Cc: Wei Yang Cc: Xiongchun Duan Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 5 ++++- include/linux/xarray.h | 9 ++++++++- 2 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 1d38d9475c4d..3db431276d82 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -334,9 +334,12 @@ void workingset_activation(struct folio *folio); /* Only track the nodes of mappings with shadow entries */ void workingset_update_node(struct xa_node *node); +extern struct list_lru shadow_nodes; #define mapping_set_update(xas, mapping) do { \ - if (!dax_mapping(mapping) && !shmem_mapping(mapping)) \ + if (!dax_mapping(mapping) && !shmem_mapping(mapping)) { \ xas_set_update(xas, workingset_update_node); \ + xas_set_lru(xas, &shadow_nodes); \ + } \ } while (0) /* linux/mm/page_alloc.c */ diff --git a/include/linux/xarray.h b/include/linux/xarray.h index d6d5da6ed735..bb52b786be1b 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -1317,6 +1317,7 @@ struct xa_state { struct xa_node *xa_node; struct xa_node *xa_alloc; xa_update_node_t xa_update; + struct list_lru *xa_lru; }; /* @@ -1336,7 +1337,8 @@ struct xa_state { .xa_pad = 0, \ .xa_node = XAS_RESTART, \ .xa_alloc = NULL, \ - .xa_update = NULL \ + .xa_update = NULL, \ + .xa_lru = NULL, \ } /** @@ -1631,6 +1633,11 @@ static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update) xas->xa_update = update; } +static inline void xas_set_lru(struct xa_state *xas, struct list_lru *lru) +{ + xas->xa_lru = lru; +} + /** * xas_next_entry() - Advance iterator to next present entry. * @xas: XArray operation state. -- cgit v1.2.3 From 5abc1e37afa0335c52608d640fd30910b2eeda21 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 22 Mar 2022 14:41:19 -0700 Subject: mm: list_lru: allocate list_lru_one only when needed In our server, we found a suspected memory leak problem. The kmalloc-32 consumes more than 6GB of memory. Other kmem_caches consume less than 2GB memory. After our in-depth analysis, the memory consumption of kmalloc-32 slab cache is the cause of list_lru_one allocation. crash> p memcg_nr_cache_ids memcg_nr_cache_ids = $2 = 24574 memcg_nr_cache_ids is very large and memory consumption of each list_lru can be calculated with the following formula. num_numa_node * memcg_nr_cache_ids * 32 (kmalloc-32) There are 4 numa nodes in our system, so each list_lru consumes ~3MB. crash> list super_blocks | wc -l 952 Every mount will register 2 list lrus, one is for inode, another is for dentry. There are 952 super_blocks. So the total memory is 952 * 2 * 3 MB (~5.6GB). But the number of memory cgroup is less than 500. So I guess more than 12286 containers have been deployed on this machine (I do not know why there are so many containers, it may be a user's bug or the user really want to do that). And memcg_nr_cache_ids has not been reduced to a suitable value. This can waste a lot of memory. Now the infrastructure for dynamic list_lru_one allocation is ready, so remove statically allocated memory code to save memory. Link: https://lkml.kernel.org/r/20220228122126.37293-11-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Alex Shi Cc: Anna Schumaker Cc: Chao Yu Cc: Dave Chinner Cc: Fam Zheng Cc: Jaegeuk Kim Cc: Johannes Weiner Cc: Kari Argillander Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Qi Zheng Cc: Roman Gushchin Cc: Shakeel Butt Cc: Theodore Ts'o Cc: Trond Myklebust Cc: Vladimir Davydov Cc: Vlastimil Babka Cc: Wei Yang Cc: Xiongchun Duan Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list_lru.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index ab912c49334f..c36db6dc2a65 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -32,14 +32,15 @@ struct list_lru_one { }; struct list_lru_per_memcg { + struct rcu_head rcu; /* array of per cgroup per node lists, indexed by node id */ - struct list_lru_one node[0]; + struct list_lru_one node[]; }; struct list_lru_memcg { struct rcu_head rcu; /* array of per cgroup lists, indexed by memcg_cache_id */ - struct list_lru_per_memcg *mlru[]; + struct list_lru_per_memcg __rcu *mlru[]; }; struct list_lru_node { @@ -77,7 +78,7 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware, int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, gfp_t gfp); int memcg_update_all_list_lrus(int num_memcgs); -void memcg_drain_all_list_lrus(int src_idx, struct mem_cgroup *dst_memcg); +void memcg_drain_all_list_lrus(struct mem_cgroup *src, struct mem_cgroup *dst); /** * list_lru_add: add an element to the lru list's tail -- cgit v1.2.3 From 1f391eb270791359ee79031945dbe3afeaec6ce3 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 22 Mar 2022 14:41:22 -0700 Subject: mm: list_lru: rename memcg_drain_all_list_lrus to memcg_reparent_list_lrus The purpose of the memcg_drain_all_list_lrus() is list_lrus reparenting. It is very similar to memcg_reparent_objcgs(). Rename it to memcg_reparent_list_lrus() so that the name can more consistent with memcg_reparent_objcgs(). Link: https://lkml.kernel.org/r/20220228122126.37293-12-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Alex Shi Cc: Anna Schumaker Cc: Chao Yu Cc: Dave Chinner Cc: Fam Zheng Cc: Jaegeuk Kim Cc: Johannes Weiner Cc: Kari Argillander Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Qi Zheng Cc: Roman Gushchin Cc: Shakeel Butt Cc: Theodore Ts'o Cc: Trond Myklebust Cc: Vladimir Davydov Cc: Vlastimil Babka Cc: Wei Yang Cc: Xiongchun Duan Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list_lru.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index c36db6dc2a65..4b00fd8cb373 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -78,7 +78,7 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware, int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, gfp_t gfp); int memcg_update_all_list_lrus(int num_memcgs); -void memcg_drain_all_list_lrus(struct mem_cgroup *src, struct mem_cgroup *dst); +void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *parent); /** * list_lru_add: add an element to the lru list's tail -- cgit v1.2.3 From bbca91cca9a902de2e9907370e9c1e0a3d1aab0f Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 22 Mar 2022 14:41:25 -0700 Subject: mm: list_lru: replace linear array with xarray If we run 10k containers in the system, the size of the list_lru_memcg->lrus can be ~96KB per list_lru. When we decrease the number containers, the size of the array will not be shrinked. It is not scalable. The xarray is a good choice for this case. We can save a lot of memory when there are tens of thousands continers in the system. If we use xarray, we also can remove the logic code of resizing array, which can simplify the code. [akpm@linux-foundation.org: remove unused local] Link: https://lkml.kernel.org/r/20220228122126.37293-13-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Alex Shi Cc: Anna Schumaker Cc: Chao Yu Cc: Dave Chinner Cc: Fam Zheng Cc: Jaegeuk Kim Cc: Johannes Weiner Cc: Kari Argillander Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Qi Zheng Cc: Roman Gushchin Cc: Shakeel Butt Cc: Theodore Ts'o Cc: Trond Myklebust Cc: Vladimir Davydov Cc: Vlastimil Babka Cc: Wei Yang Cc: Xiongchun Duan Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list_lru.h | 13 ++----------- include/linux/memcontrol.h | 23 ----------------------- 2 files changed, 2 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 4b00fd8cb373..572c263561ac 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -11,6 +11,7 @@ #include #include #include +#include struct mem_cgroup; @@ -37,12 +38,6 @@ struct list_lru_per_memcg { struct list_lru_one node[]; }; -struct list_lru_memcg { - struct rcu_head rcu; - /* array of per cgroup lists, indexed by memcg_cache_id */ - struct list_lru_per_memcg __rcu *mlru[]; -}; - struct list_lru_node { /* protects all lists on the node, including per cgroup */ spinlock_t lock; @@ -57,10 +52,7 @@ struct list_lru { struct list_head list; int shrinker_id; bool memcg_aware; - /* protects ->mlrus->mlru[i] */ - spinlock_t lock; - /* for cgroup aware lrus points to per cgroup lists, otherwise NULL */ - struct list_lru_memcg __rcu *mlrus; + struct xarray xa; #endif }; @@ -77,7 +69,6 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware, int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, gfp_t gfp); -int memcg_update_all_list_lrus(int num_memcgs); void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *parent); /** diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b636732f0c14..066b7a3b8a9e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1685,18 +1685,6 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size); extern struct static_key_false memcg_kmem_enabled_key; -extern int memcg_nr_cache_ids; -void memcg_get_cache_ids(void); -void memcg_put_cache_ids(void); - -/* - * Helper macro to loop through all memcg-specific caches. Callers must still - * check if the cache is valid (it is either valid or NULL). - * the slab_mutex must be held when looping through those caches - */ -#define for_each_memcg_cache_index(_idx) \ - for ((_idx) = 0; (_idx) < memcg_nr_cache_ids; (_idx)++) - static inline bool memcg_kmem_enabled(void) { return static_branch_likely(&memcg_kmem_enabled_key); @@ -1753,9 +1741,6 @@ static inline void __memcg_kmem_uncharge_page(struct page *page, int order) { } -#define for_each_memcg_cache_index(_idx) \ - for (; NULL; ) - static inline bool memcg_kmem_enabled(void) { return false; @@ -1766,14 +1751,6 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg) return -1; } -static inline void memcg_get_cache_ids(void) -{ -} - -static inline void memcg_put_cache_ids(void) -{ -} - static inline struct mem_cgroup *mem_cgroup_from_obj(void *p) { return NULL; -- cgit v1.2.3 From d70110704d2d52a65a9fe43be409d8c3acce79fe Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 22 Mar 2022 14:41:35 -0700 Subject: mm: list_lru: rename list_lru_per_memcg to list_lru_memcg The name of list_lru_memcg was occupied before and became free since last commit. Rename list_lru_per_memcg to list_lru_memcg since the name is brief. Link: https://lkml.kernel.org/r/20220228122126.37293-16-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Alex Shi Cc: Anna Schumaker Cc: Chao Yu Cc: Dave Chinner Cc: Fam Zheng Cc: Jaegeuk Kim Cc: Johannes Weiner Cc: Kari Argillander Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Qi Zheng Cc: Roman Gushchin Cc: Shakeel Butt Cc: Theodore Ts'o Cc: Trond Myklebust Cc: Vladimir Davydov Cc: Vlastimil Babka Cc: Wei Yang Cc: Xiongchun Duan Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list_lru.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 572c263561ac..b35968ee9fb5 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -32,7 +32,7 @@ struct list_lru_one { long nr_items; }; -struct list_lru_per_memcg { +struct list_lru_memcg { struct rcu_head rcu; /* array of per cgroup per node lists, indexed by node id */ struct list_lru_one node[]; -- cgit v1.2.3 From 7c52f65de40ff0e44f821559eb61931d368a4c48 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 22 Mar 2022 14:41:38 -0700 Subject: mm: memcontrol: rename memcg_cache_id to memcg_kmem_id The memcg_cache_id() introduced by commit 2633d7a02823 ("slab/slub: consider a memcg parameter in kmem_create_cache") is used to index in the kmem_cache->memcg_params->memcg_caches array. Since kmem_cache->memcg_params.memcg_caches has been removed by commit 9855609bde03 ("mm: memcg/slab: use a single set of kmem_caches for all accounted allocations"). So the name does not need to reflect cache related. Just rename it to memcg_kmem_id. And it can reflect kmem related. Link: https://lkml.kernel.org/r/20220228122126.37293-17-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Alex Shi Cc: Anna Schumaker Cc: Chao Yu Cc: Dave Chinner Cc: Fam Zheng Cc: Jaegeuk Kim Cc: Johannes Weiner Cc: Kari Argillander Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Qi Zheng Cc: Roman Gushchin Cc: Shakeel Butt Cc: Theodore Ts'o Cc: Trond Myklebust Cc: Vladimir Davydov Cc: Vlastimil Babka Cc: Wei Yang Cc: Xiongchun Duan Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 066b7a3b8a9e..a68dce3873fc 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1708,7 +1708,7 @@ static inline void memcg_kmem_uncharge_page(struct page *page, int order) * A helper for accessing memcg's kmem_id, used for getting * corresponding LRU lists. */ -static inline int memcg_cache_id(struct mem_cgroup *memcg) +static inline int memcg_kmem_id(struct mem_cgroup *memcg) { return memcg ? memcg->kmemcg_id : -1; } @@ -1746,7 +1746,7 @@ static inline bool memcg_kmem_enabled(void) return false; } -static inline int memcg_cache_id(struct mem_cgroup *memcg) +static inline int memcg_kmem_id(struct mem_cgroup *memcg) { return -1; } -- cgit v1.2.3 From 16785bd7743104d57257a455001172b75afa7614 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Tue, 22 Mar 2022 14:41:47 -0700 Subject: mm: merge pte_mkhuge() call into arch_make_huge_pte() Each call into pte_mkhuge() is invariably followed by arch_make_huge_pte(). Instead arch_make_huge_pte() can accommodate pte_mkhuge() at the beginning. This updates generic fallback stub for arch_make_huge_pte() and available platforms definitions. This makes huge pte creation much cleaner and easier to follow. Link: https://lkml.kernel.org/r/1643860669-26307-1-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Reviewed-by: Christophe Leroy Acked-by: Mike Kravetz Acked-by: Catalin Marinas Cc: Will Deacon Cc: Michael Ellerman Cc: Paul Mackerras Cc: "David S. Miller" Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index d1897a69c540..52c462390aee 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -754,7 +754,7 @@ static inline void arch_clear_hugepage_flags(struct page *page) { } static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) { - return entry; + return pte_mkhuge(entry); } #endif -- cgit v1.2.3 From ff11a7ce1f0f8c1e7870de26860024b4ddbf5755 Mon Sep 17 00:00:00 2001 From: Bang Li Date: Tue, 22 Mar 2022 14:43:02 -0700 Subject: mm/vmalloc: fix comments about vmap_area struct The vmap_area_root should be in the "busy" tree and the free_vmap_area_root should be in the "free" tree. Link: https://lkml.kernel.org/r/20220305011510.33596-1-libang.linuxer@gmail.com Fixes: 688fcbfc06e4 ("mm/vmalloc: modify struct vmap_area to reduce its size") Signed-off-by: Bang Li Reviewed-by: Uladzislau Rezki (Sony) Cc: Pengfei Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 880227b9f044..05065915edd7 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -80,8 +80,8 @@ struct vmap_area { /* * The following two variables can be packed, because * a vmap_area object can be either: - * 1) in "free" tree (root is vmap_area_root) - * 2) or "busy" tree (root is free_vmap_area_root) + * 1) in "free" tree (root is free_vmap_area_root) + * 2) or "busy" tree (root is vmap_area_root) */ union { unsigned long subtree_max_size; /* in "free" tree */ -- cgit v1.2.3 From 1dd214b8f21ca46d5431be9b2db8513c59e07a26 Mon Sep 17 00:00:00 2001 From: Zi Yan Date: Tue, 22 Mar 2022 14:43:05 -0700 Subject: mm: page_alloc: avoid merging non-fallbackable pageblocks with others This is done in addition to MIGRATE_ISOLATE pageblock merge avoidance. It prepares for the upcoming removal of the MAX_ORDER-1 alignment requirement for CMA and alloc_contig_range(). MIGRATE_HIGHATOMIC should not merge with other migratetypes like MIGRATE_ISOLATE and MIGRARTE_CMA[1], so this commit prevents that too. Remove MIGRATE_CMA and MIGRATE_ISOLATE from fallbacks list, since they are never used. [1] https://lore.kernel.org/linux-mm/20211130100853.GP3366@techsingularity.net/ Link: https://lkml.kernel.org/r/20220124175957.1261961-1-zi.yan@sent.com Signed-off-by: Zi Yan Acked-by: Mel Gorman Acked-by: David Hildenbrand Acked-by: Vlastimil Babka Acked-by: Mike Rapoport Reviewed-by: Oscar Salvador Cc: Mike Rapoport Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index aed44e9b5d89..71b77aab748d 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -83,6 +83,17 @@ static inline bool is_migrate_movable(int mt) return is_migrate_cma(mt) || mt == MIGRATE_MOVABLE; } +/* + * Check whether a migratetype can be merged with another migratetype. + * + * It is only mergeable when it can fall back to other migratetypes for + * allocation. See fallbacks[MIGRATE_TYPES][3] in page_alloc.c. + */ +static inline bool migratetype_is_mergeable(int mt) +{ + return mt < MIGRATE_PCPTYPES; +} + #define for_each_migratetype_order(order, type) \ for (order = 0; order < MAX_ORDER; order++) \ for (type = 0; type < MIGRATE_TYPES; type++) -- cgit v1.2.3 From 7f37e49cbd60ef71b82d25cd55b039a65d06387c Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Tue, 22 Mar 2022 14:43:11 -0700 Subject: mm/mmzone.h: remove unused macros Remove pgdat_page_nr, nid_page_nr and NODE_MEM_MAP. They are unused now. Link: https://lkml.kernel.org/r/20220127093210.62293-1-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: David Hildenbrand Reviewed-by: Mike Rapoport Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 71b77aab748d..c9e6a50109b9 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -931,12 +931,6 @@ typedef struct pglist_data { #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) #define node_spanned_pages(nid) (NODE_DATA(nid)->node_spanned_pages) -#ifdef CONFIG_FLATMEM -#define pgdat_page_nr(pgdat, pagenr) ((pgdat)->node_mem_map + (pagenr)) -#else -#define pgdat_page_nr(pgdat, pagenr) pfn_to_page((pgdat)->node_start_pfn + (pagenr)) -#endif -#define nid_page_nr(nid, pagenr) pgdat_page_nr(NODE_DATA(nid),(pagenr)) #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid)) @@ -1112,7 +1106,6 @@ static inline struct pglist_data *NODE_DATA(int nid) { return &contig_page_data; } -#define NODE_MEM_MAP(nid) mem_map #else /* CONFIG_NUMA */ -- cgit v1.2.3 From e16faf26780fc0c8dd693ea9ee8420a7706cb2f5 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 22 Mar 2022 14:43:17 -0700 Subject: cma: factor out minimum alignment requirement Patch series "mm: enforce pageblock_order < MAX_ORDER". Having pageblock_order >= MAX_ORDER seems to be able to happen in corner cases and some parts of the kernel are not prepared for it. For example, Aneesh has shown [1] that such kernels can be compiled on ppc64 with 64k base pages by setting FORCE_MAX_ZONEORDER=8, which will run into a WARN_ON_ONCE(order >= MAX_ORDER) in comapction code right during boot. We can get pageblock_order >= MAX_ORDER when the default hugetlb size is bigger than the maximum allocation granularity of the buddy, in which case we are no longer talking about huge pages but instead gigantic pages. Having pageblock_order >= MAX_ORDER can only make alloc_contig_range() of such gigantic pages more likely to succeed. Reliable use of gigantic pages either requires boot time allcoation or CMA, no need to overcomplicate some places in the kernel to optimize for corner cases that are broken in other areas of the kernel. This patch (of 2): Let's enforce pageblock_order < MAX_ORDER and simplify. Especially patch #1 can be regarded a cleanup before: [PATCH v5 0/6] Use pageblock_order for cma and alloc_contig_range alignment. [2] [1] https://lkml.kernel.org/r/87r189a2ks.fsf@linux.ibm.com [2] https://lkml.kernel.org/r/20220211164135.1803616-1-zi.yan@sent.com Link: https://lkml.kernel.org/r/20220214174132.219303-2-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Zi Yan Acked-by: Rob Herring Cc: Aneesh Kumar K.V Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Frank Rowand Cc: Michael S. Tsirkin Cc: Christoph Hellwig Cc: Marek Szyprowski Cc: Robin Murphy Cc: Minchan Kim Cc: Vlastimil Babka Cc: John Garry via iommu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cma.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/cma.h b/include/linux/cma.h index bd801023504b..75fe188ec4a1 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -20,6 +20,15 @@ #define CMA_MAX_NAME 64 +/* + * TODO: once the buddy -- especially pageblock merging and alloc_contig_range() + * -- can deal with only some pageblocks of a higher-order page being + * MIGRATE_CMA, we can use pageblock_nr_pages. + */ +#define CMA_MIN_ALIGNMENT_PAGES max_t(phys_addr_t, MAX_ORDER_NR_PAGES, \ + pageblock_nr_pages) +#define CMA_MIN_ALIGNMENT_BYTES (PAGE_SIZE * CMA_MIN_ALIGNMENT_PAGES) + struct cma; extern unsigned long totalcma_pages; -- cgit v1.2.3 From b3d40a2b6d10c9d0424d2b398bf962fb6adad87e Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 22 Mar 2022 14:43:20 -0700 Subject: mm: enforce pageblock_order < MAX_ORDER Some places in the kernel don't really expect pageblock_order >= MAX_ORDER, and it looks like this is only possible in corner cases: 1) CONFIG_DEFERRED_STRUCT_PAGE_INIT we'll end up freeing pageblock_order pages via __free_pages_core(), which cannot possibly work. 2) find_zone_movable_pfns_for_nodes() will roundup the ZONE_MOVABLE start PFN to MAX_ORDER_NR_PAGES. Consequently with a bigger pageblock_order, we could have a single pageblock partially managed by two zones. 3) compaction code runs into __fragmentation_index() with order >= MAX_ORDER, when checking WARN_ON_ONCE(order >= MAX_ORDER). [1] 4) mm/page_reporting.c won't be reporting any pages with default page_reporting_order == pageblock_order, as we'll be skipping the reporting loop inside page_reporting_process_zone(). 5) __rmqueue_fallback() will never be able to steal with ALLOC_NOFRAGMENT. pageblock_order >= MAX_ORDER is weird either way: it's a pure optimization for making alloc_contig_range(), as used for allcoation of gigantic pages, a little more reliable to succeed. However, if there is demand for somewhat reliable allocation of gigantic pages, affected setups should be using CMA or boottime allocations instead. So let's make sure that pageblock_order < MAX_ORDER and simplify. [1] https://lkml.kernel.org/r/87r189a2ks.fsf@linux.ibm.com Link: https://lkml.kernel.org/r/20220214174132.219303-3-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Zi Yan Cc: Aneesh Kumar K.V Cc: Benjamin Herrenschmidt Cc: Christoph Hellwig Cc: Frank Rowand Cc: John Garry via iommu Cc: Marek Szyprowski Cc: Michael Ellerman Cc: Michael S. Tsirkin Cc: Minchan Kim Cc: Paul Mackerras Cc: Rob Herring Cc: Robin Murphy Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cma.h | 3 +-- include/linux/pageblock-flags.h | 7 +++++-- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/cma.h b/include/linux/cma.h index 75fe188ec4a1..b1ba94f1cc9c 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -25,8 +25,7 @@ * -- can deal with only some pageblocks of a higher-order page being * MIGRATE_CMA, we can use pageblock_nr_pages. */ -#define CMA_MIN_ALIGNMENT_PAGES max_t(phys_addr_t, MAX_ORDER_NR_PAGES, \ - pageblock_nr_pages) +#define CMA_MIN_ALIGNMENT_PAGES MAX_ORDER_NR_PAGES #define CMA_MIN_ALIGNMENT_BYTES (PAGE_SIZE * CMA_MIN_ALIGNMENT_PAGES) struct cma; diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index 973fd731a520..83c7248053a1 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -37,8 +37,11 @@ extern unsigned int pageblock_order; #else /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ -/* Huge pages are a constant size */ -#define pageblock_order HUGETLB_PAGE_ORDER +/* + * Huge pages are a constant size, but don't exceed the maximum allocation + * granularity. + */ +#define pageblock_order min_t(unsigned int, HUGETLB_PAGE_ORDER, MAX_ORDER - 1) #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ -- cgit v1.2.3 From 1ca75fa7f19d694c58af681fa023295072b03120 Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Tue, 22 Mar 2022 14:43:51 -0700 Subject: arch/x86/mm/numa: Do not initialize nodes twice On x86, prior to ("mm: handle uninitialized numa nodes gracecully"), NUMA nodes could be allocated at three different places. - numa_register_memblks - init_cpu_to_node - init_gi_nodes All these calls happen at setup_arch, and have the following order: setup_arch ... x86_numa_init numa_init numa_register_memblks ... init_cpu_to_node init_memory_less_node alloc_node_data free_area_init_memoryless_node init_gi_nodes init_memory_less_node alloc_node_data free_area_init_memoryless_node numa_register_memblks() is only interested in those nodes which have memory, so it skips over any memoryless node it founds. Later on, when we have read ACPI's SRAT table, we call init_cpu_to_node() and init_gi_nodes(), which initialize any memoryless node we might have that have either CPU or Initiator affinity, meaning we allocate pg_data_t struct for them and we mark them as ONLINE. So far so good, but the thing is that after ("mm: handle uninitialized numa nodes gracefully"), we allocate all possible NUMA nodes in free_area_init(), meaning we have a picture like the following: setup_arch x86_numa_init numa_init numa_register_memblks <-- allocate non-memoryless node x86_init.paging.pagetable_init ... free_area_init free_area_init_memoryless <-- allocate memoryless node init_cpu_to_node alloc_node_data <-- allocate memoryless node with CPU free_area_init_memoryless_node init_gi_nodes alloc_node_data <-- allocate memoryless node with Initiator free_area_init_memoryless_node free_area_init() already allocates all possible NUMA nodes, but init_cpu_to_node() and init_gi_nodes() are clueless about that, so they go ahead and allocate a new pg_data_t struct without checking anything, meaning we end up allocating twice. It should be mad clear that this only happens in the case where memoryless NUMA node happens to have a CPU/Initiator affinity. So get rid of init_memory_less_node() and just set the node online. Note that setting the node online is needed, otherwise we choke down the chain when bringup_nonboot_cpus() ends up calling __try_online_node()->register_one_node()->... and we blow up in bus_add_device(). As can be seen here: BUG: kernel NULL pointer dereference, address: 0000000000000060 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC PTI CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.17.0-rc4-1-default+ #45 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.0.0-prebuilt.qemu-project.org 04/4 RIP: 0010:bus_add_device+0x5a/0x140 Code: 8b 74 24 20 48 89 df e8 84 96 ff ff 85 c0 89 c5 75 38 48 8b 53 50 48 85 d2 0f 84 bb 00 004 RSP: 0000:ffffc9000022bd10 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff888100987400 RCX: ffff8881003e4e19 RDX: ffff8881009a5e00 RSI: ffff888100987400 RDI: ffff888100987400 RBP: 0000000000000000 R08: ffff8881003e4e18 R09: ffff8881003e4c98 R10: 0000000000000000 R11: ffff888100402bc0 R12: ffffffff822ceba0 R13: 0000000000000000 R14: ffff888100987400 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88853fc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000060 CR3: 000000000200a001 CR4: 00000000001706b0 Call Trace: device_add+0x4c0/0x910 __register_one_node+0x97/0x2d0 __try_online_node+0x85/0xc0 try_online_node+0x25/0x40 cpu_up+0x4f/0x100 bringup_nonboot_cpus+0x4f/0x60 smp_init+0x26/0x79 kernel_init_freeable+0x130/0x2f1 kernel_init+0x17/0x150 ret_from_fork+0x22/0x30 The reason is simple, by the time bringup_nonboot_cpus() gets called, we did not register the node_subsys bus yet, so we crash when bus_add_device() tries to dereference bus()->p. The following shows the order of the calls: kernel_init_freeable smp_init bringup_nonboot_cpus ... bus_add_device() <- we did not register node_subsys yet do_basic_setup do_initcalls postcore_initcall(register_node_type); register_node_type subsys_system_register subsys_register bus_register <- register node_subsys bus Why setting the node online saves us then? Well, simply because __try_online_node() backs off when the node is online, meaning we do not end up calling register_one_node() in the first place. This is subtle, broken and deserves a deep analysis and thought about how to put this into shape, but for now let us have this easy fix for the leaking memory issue. [osalvador@suse.de: add comments] Link: https://lkml.kernel.org/r/20220221142649.3457-1-osalvador@suse.de Link: https://lkml.kernel.org/r/20220218224302.5282-2-osalvador@suse.de Fixes: da4490c958ad ("mm: handle uninitialized numa nodes gracefully") Signed-off-by: Oscar Salvador Acked-by: Michal Hocko Cc: David Hildenbrand Cc: Rafael Aquini Cc: Dave Hansen Cc: Wei Yang Cc: Dennis Zhou Cc: Alexey Makhalov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index c02a8cc16e4f..d0978235775f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2449,7 +2449,6 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) } extern void __init pagecache_init(void); -extern void __init free_area_init_memoryless_node(int nid); extern void free_initmem(void); /* -- cgit v1.2.3 From 888af2701db79b9b27c7e37f9ede528a5ca53b76 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Tue, 22 Mar 2022 14:44:44 -0700 Subject: mm/memory-failure.c: fix race with changing page compound again Patch series "A few fixup patches for memory failure", v2. This series contains a few patches to fix the race with changing page compound page, make non-LRU movable pages unhandlable and so on. More details can be found in the respective changelogs. There is a race window where we got the compound_head, the hugetlb page could be freed to buddy, or even changed to another compound page just before we try to get hwpoison page. Think about the below race window: CPU 1 CPU 2 memory_failure_hugetlb struct page *head = compound_head(p); hugetlb page might be freed to buddy, or even changed to another compound page. get_hwpoison_page -- page is not what we want now... If this race happens, just bail out. Also MF_MSG_DIFFERENT_PAGE_SIZE is introduced to record this event. [akpm@linux-foundation.org: s@/**@/*@, per Naoya Horiguchi] Link: https://lkml.kernel.org/r/20220312074613.4798-1-linmiaohe@huawei.com Link: https://lkml.kernel.org/r/20220312074613.4798-2-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Acked-by: Naoya Horiguchi Cc: Tony Luck Cc: Borislav Petkov Cc: Mike Kravetz Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + include/ras/ras_event.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index d0978235775f..45a449e8c209 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3239,6 +3239,7 @@ enum mf_action_page_type { MF_MSG_BUDDY, MF_MSG_DAX, MF_MSG_UNSPLIT_THP, + MF_MSG_DIFFERENT_PAGE_SIZE, MF_MSG_UNKNOWN, }; diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h index d0337a41141c..1e694fd239b9 100644 --- a/include/ras/ras_event.h +++ b/include/ras/ras_event.h @@ -374,6 +374,7 @@ TRACE_EVENT(aer_event, EM ( MF_MSG_BUDDY, "free buddy page" ) \ EM ( MF_MSG_DAX, "dax page" ) \ EM ( MF_MSG_UNSPLIT_THP, "unsplit thp" ) \ + EM ( MF_MSG_DIFFERENT_PAGE_SIZE, "different page size" ) \ EMe ( MF_MSG_UNKNOWN, "unknown page" ) /* -- cgit v1.2.3 From 1e7a8181640a620300e98e22223ca3445b349840 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 22 Mar 2022 14:44:53 -0700 Subject: mm, fault-injection: declare should_fail_alloc_page() The mm/ directory can almost fully be built with W=1, which would help in local development. One remaining issue is missing prototype for should_fail_alloc_page(). Thus add it next to the should_failslab() prototype. Note the previous attempt by commit f7173090033c ("mm/page_alloc: make should_fail_alloc_page() static") had to be reverted by commit 54aa386661fe as it caused an unresolved symbol error with CONFIG_DEBUG_INFO_BTF=y Link: https://lkml.kernel.org/r/20220314165724.16071-1-vbabka@suse.cz Signed-off-by: Vlastimil Babka Cc: Mel Gorman Cc: Matthew Wilcox Cc: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fault-inject.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index e525f6957c49..2d04f6448cde 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -64,6 +64,8 @@ static inline struct dentry *fault_create_debugfs_attr(const char *name, struct kmem_cache; +bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order); + int should_failslab(struct kmem_cache *s, gfp_t gfpflags); #ifdef CONFIG_FAILSLAB extern bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags); -- cgit v1.2.3 From e7d324850bfcb30df563d144c0363cc44595277d Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 22 Mar 2022 14:45:00 -0700 Subject: mm: hugetlb: free the 2nd vmemmap page associated with each HugeTLB page Patch series "Free the 2nd vmemmap page associated with each HugeTLB page", v7. This series can minimize the overhead of struct page for 2MB HugeTLB pages significantly. It further reduces the overhead of struct page by 12.5% for a 2MB HugeTLB compared to the previous approach, which means 2GB per 1TB HugeTLB. It is a nice gain. Comments and reviews are welcome. Thanks. The main implementation and details can refer to the commit log of patch 1. In this series, I have changed the following four helpers, the following table shows the impact of the overhead of those helpers. +------------------+-----------------------+ | APIs | head page | tail page | +------------------+-----------+-----------+ | PageHead() | Y | N | +------------------+-----------+-----------+ | PageTail() | Y | N | +------------------+-----------+-----------+ | PageCompound() | N | N | +------------------+-----------+-----------+ | compound_head() | Y | N | +------------------+-----------+-----------+ Y: Overhead is increased. N: Overhead is _NOT_ increased. It shows that the overhead of those helpers on a tail page don't change between "hugetlb_free_vmemmap=on" and "hugetlb_free_vmemmap=off". But the overhead on a head page will be increased when "hugetlb_free_vmemmap=on" (except PageCompound()). So I believe that Matthew Wilcox's folio series will help with this. The users of PageHead() and PageTail() are much less than compound_head() and most users of PageTail() are VM_BUG_ON(), so I have done some tests about the overhead of compound_head() on head pages. I have tested the overhead of calling compound_head() on a head page, which is 2.11ns (Measure the call time of 10 million times compound_head(), and then average). For a head page whose address is not aligned with PAGE_SIZE or a non-compound page, the overhead of compound_head() is 2.54ns which is increased by 20%. For a head page whose address is aligned with PAGE_SIZE, the overhead of compound_head() is 2.97ns which is increased by 40%. Most pages are the former. I do not think the overhead is significant since the overhead of compound_head() itself is low. This patch (of 5): This patch minimizes the overhead of struct page for 2MB HugeTLB pages significantly. It further reduces the overhead of struct page by 12.5% for a 2MB HugeTLB compared to the previous approach, which means 2GB per 1TB HugeTLB (2MB type). After the feature of "Free sonme vmemmap pages of HugeTLB page" is enabled, the mapping of the vmemmap addresses associated with a 2MB HugeTLB page becomes the figure below. HugeTLB struct pages(8 pages) page frame(8 pages) +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+---> PG_head | | | 0 | -------------> | 0 | | | +-----------+ +-----------+ | | | 1 | -------------> | 1 | | | +-----------+ +-----------+ | | | 2 | ----------------^ ^ ^ ^ ^ ^ | | +-----------+ | | | | | | | | 3 | ------------------+ | | | | | | +-----------+ | | | | | | | 4 | --------------------+ | | | | 2MB | +-----------+ | | | | | | 5 | ----------------------+ | | | | +-----------+ | | | | | 6 | ------------------------+ | | | +-----------+ | | | | 7 | --------------------------+ | | +-----------+ | | | | | | +-----------+ As we can see, the 2nd vmemmap page frame (indexed by 1) is reused and remaped. However, the 2nd vmemmap page frame is also can be freed to the buddy allocator, then we can change the mapping from the figure above to the figure below. HugeTLB struct pages(8 pages) page frame(8 pages) +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+---> PG_head | | | 0 | -------------> | 0 | | | +-----------+ +-----------+ | | | 1 | ---------------^ ^ ^ ^ ^ ^ ^ | | +-----------+ | | | | | | | | | 2 | -----------------+ | | | | | | | +-----------+ | | | | | | | | 3 | -------------------+ | | | | | | +-----------+ | | | | | | | 4 | ---------------------+ | | | | 2MB | +-----------+ | | | | | | 5 | -----------------------+ | | | | +-----------+ | | | | | 6 | -------------------------+ | | | +-----------+ | | | | 7 | ---------------------------+ | | +-----------+ | | | | | | +-----------+ After we do this, all tail vmemmap pages (1-7) are mapped to the head vmemmap page frame (0). In other words, there are more than one page struct with PG_head associated with each HugeTLB page. We __know__ that there is only one head page struct, the tail page structs with PG_head are fake head page structs. We need an approach to distinguish between those two different types of page structs so that compound_head(), PageHead() and PageTail() can work properly if the parameter is the tail page struct but with PG_head. The following code snippet describes how to distinguish between real and fake head page struct. if (test_bit(PG_head, &page->flags)) { unsigned long head = READ_ONCE(page[1].compound_head); if (head & 1) { if (head == (unsigned long)page + 1) ==> head page struct else ==> tail page struct } else ==> head page struct } We can safely access the field of the @page[1] with PG_head because the @page is a compound page composed with at least two contiguous pages. [songmuchun@bytedance.com: restore lost comment changes] Link: https://lkml.kernel.org/r/20211101031651.75851-1-songmuchun@bytedance.com Link: https://lkml.kernel.org/r/20211101031651.75851-2-songmuchun@bytedance.com Signed-off-by: Muchun Song Reviewed-by: Barry Song Cc: Mike Kravetz Cc: Oscar Salvador Cc: Michal Hocko Cc: David Hildenbrand Cc: Chen Huang Cc: Bodeddula Balasubramaniam Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Xiongchun Duan Cc: Fam Zheng Cc: Qi Zheng Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 78 +++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 74 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 1c3b6e5c8bfd..111e453f23d2 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -190,13 +190,69 @@ enum pageflags { #ifndef __GENERATING_BOUNDS_H +#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP +extern bool hugetlb_free_vmemmap_enabled; + +/* + * If the feature of freeing some vmemmap pages associated with each HugeTLB + * page is enabled, the head vmemmap page frame is reused and all of the tail + * vmemmap addresses map to the head vmemmap page frame (furture details can + * refer to the figure at the head of the mm/hugetlb_vmemmap.c). In other + * words, there are more than one page struct with PG_head associated with each + * HugeTLB page. We __know__ that there is only one head page struct, the tail + * page structs with PG_head are fake head page structs. We need an approach + * to distinguish between those two different types of page structs so that + * compound_head() can return the real head page struct when the parameter is + * the tail page struct but with PG_head. + * + * The page_fixed_fake_head() returns the real head page struct if the @page is + * fake page head, otherwise, returns @page which can either be a true page + * head or tail. + */ +static __always_inline const struct page *page_fixed_fake_head(const struct page *page) +{ + if (!hugetlb_free_vmemmap_enabled) + return page; + + /* + * Only addresses aligned with PAGE_SIZE of struct page may be fake head + * struct page. The alignment check aims to avoid access the fields ( + * e.g. compound_head) of the @page[1]. It can avoid touch a (possibly) + * cold cacheline in some cases. + */ + if (IS_ALIGNED((unsigned long)page, PAGE_SIZE) && + test_bit(PG_head, &page->flags)) { + /* + * We can safely access the field of the @page[1] with PG_head + * because the @page is a compound page composed with at least + * two contiguous pages. + */ + unsigned long head = READ_ONCE(page[1].compound_head); + + if (likely(head & 1)) + return (const struct page *)(head - 1); + } + return page; +} +#else +static inline const struct page *page_fixed_fake_head(const struct page *page) +{ + return page; +} +#endif + +static __always_inline int page_is_fake_head(struct page *page) +{ + return page_fixed_fake_head(page) != page; +} + static inline unsigned long _compound_head(const struct page *page) { unsigned long head = READ_ONCE(page->compound_head); if (unlikely(head & 1)) return head - 1; - return (unsigned long)page; + return (unsigned long)page_fixed_fake_head(page); } #define compound_head(page) ((typeof(page))_compound_head(page)) @@ -231,12 +287,13 @@ static inline unsigned long _compound_head(const struct page *page) static __always_inline int PageTail(struct page *page) { - return READ_ONCE(page->compound_head) & 1; + return READ_ONCE(page->compound_head) & 1 || page_is_fake_head(page); } static __always_inline int PageCompound(struct page *page) { - return test_bit(PG_head, &page->flags) || PageTail(page); + return test_bit(PG_head, &page->flags) || + READ_ONCE(page->compound_head) & 1; } #define PAGE_POISON_PATTERN -1l @@ -695,7 +752,20 @@ static inline bool test_set_page_writeback(struct page *page) return set_page_writeback(page); } -__PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY) +static __always_inline bool folio_test_head(struct folio *folio) +{ + return test_bit(PG_head, folio_flags(folio, FOLIO_PF_ANY)); +} + +static __always_inline int PageHead(struct page *page) +{ + PF_POISONED_CHECK(page); + return test_bit(PG_head, &page->flags) && !page_is_fake_head(page); +} + +__SETPAGEFLAG(Head, head, PF_ANY) +__CLEARPAGEFLAG(Head, head, PF_ANY) +CLEARPAGEFLAG(Head, head, PF_ANY) /** * folio_test_large() - Does this folio contain more than one page? -- cgit v1.2.3 From a6b40850c442bf996e729e1d441d3dbc37cea171 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 22 Mar 2022 14:45:03 -0700 Subject: mm: hugetlb: replace hugetlb_free_vmemmap_enabled with a static_key The page_fixed_fake_head() is used throughout memory management and the conditional check requires checking a global variable, although the overhead of this check may be small, it increases when the memory cache comes under pressure. Also, the global variable will not be modified after system boot, so it is very appropriate to use static key machanism. Link: https://lkml.kernel.org/r/20211101031651.75851-3-songmuchun@bytedance.com Signed-off-by: Muchun Song Reviewed-by: Barry Song Cc: Bodeddula Balasubramaniam Cc: Chen Huang Cc: David Hildenbrand Cc: Fam Zheng Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Michal Hocko Cc: Mike Kravetz Cc: Oscar Salvador Cc: Qi Zheng Cc: Xiongchun Duan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 6 ------ include/linux/page-flags.h | 16 ++++++++++++++-- 2 files changed, 14 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 52c462390aee..08357b4c7be7 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -1075,12 +1075,6 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr } #endif /* CONFIG_HUGETLB_PAGE */ -#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP -extern bool hugetlb_free_vmemmap_enabled; -#else -#define hugetlb_free_vmemmap_enabled false -#endif - static inline spinlock_t *huge_pte_lock(struct hstate *h, struct mm_struct *mm, pte_t *pte) { diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 111e453f23d2..340cb8156568 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -191,7 +191,14 @@ enum pageflags { #ifndef __GENERATING_BOUNDS_H #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP -extern bool hugetlb_free_vmemmap_enabled; +DECLARE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON, + hugetlb_free_vmemmap_enabled_key); + +static __always_inline bool hugetlb_free_vmemmap_enabled(void) +{ + return static_branch_maybe(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON, + &hugetlb_free_vmemmap_enabled_key); +} /* * If the feature of freeing some vmemmap pages associated with each HugeTLB @@ -211,7 +218,7 @@ extern bool hugetlb_free_vmemmap_enabled; */ static __always_inline const struct page *page_fixed_fake_head(const struct page *page) { - if (!hugetlb_free_vmemmap_enabled) + if (!hugetlb_free_vmemmap_enabled()) return page; /* @@ -239,6 +246,11 @@ static inline const struct page *page_fixed_fake_head(const struct page *page) { return page; } + +static inline bool hugetlb_free_vmemmap_enabled(void) +{ + return false; +} #endif static __always_inline int page_is_fake_head(struct page *page) -- cgit v1.2.3 From e54084173487804f5e2f23facf107fd9336e637e Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 22 Mar 2022 14:45:12 -0700 Subject: mm: sparsemem: move vmemmap related to HugeTLB to CONFIG_HUGETLB_PAGE_FREE_VMEMMAP The vmemmap_remap_free/alloc are relevant to HugeTLB, so move those functiongs to the scope of CONFIG_HUGETLB_PAGE_FREE_VMEMMAP. Link: https://lkml.kernel.org/r/20211101031651.75851-6-songmuchun@bytedance.com Signed-off-by: Muchun Song Reviewed-by: Barry Song Cc: Bodeddula Balasubramaniam Cc: Chen Huang Cc: David Hildenbrand Cc: Fam Zheng Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Michal Hocko Cc: Mike Kravetz Cc: Oscar Salvador Cc: Qi Zheng Cc: Xiongchun Duan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 45a449e8c209..9d58321386cc 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3146,10 +3146,12 @@ static inline void print_vma_addr(char *prefix, unsigned long rip) } #endif +#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP int vmemmap_remap_free(unsigned long start, unsigned long end, unsigned long reuse); int vmemmap_remap_alloc(unsigned long start, unsigned long end, unsigned long reuse, gfp_t gfp_mask); +#endif void *sparse_buffer_alloc(unsigned long size); struct page * __populate_section_memmap(unsigned long pfn, -- cgit v1.2.3 From 824ddc601adc2cc48efb7f58b57997986c1c1276 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Tue, 22 Mar 2022 14:45:32 -0700 Subject: userfaultfd: provide unmasked address on page-fault Userfaultfd is supposed to provide the full address (i.e., unmasked) of the faulting access back to userspace. However, that is not the case for quite some time. Even running "userfaultfd_demo" from the userfaultfd man page provides the wrong output (and contradicts the man page). Notice that "UFFD_EVENT_PAGEFAULT event" shows the masked address (7fc5e30b3000) and not the first read address (0x7fc5e30b300f). Address returned by mmap() = 0x7fc5e30b3000 fault_handler_thread(): poll() returns: nready = 1; POLLIN = 1; POLLERR = 0 UFFD_EVENT_PAGEFAULT event: flags = 0; address = 7fc5e30b3000 (uffdio_copy.copy returned 4096) Read address 0x7fc5e30b300f in main(): A Read address 0x7fc5e30b340f in main(): A Read address 0x7fc5e30b380f in main(): A Read address 0x7fc5e30b3c0f in main(): A The exact address is useful for various reasons and specifically for prefetching decisions. If it is known that the memory is populated by certain objects whose size is not page-aligned, then based on the faulting address, the uffd-monitor can decide whether to prefetch and prefault the adjacent page. This bug has been for quite some time in the kernel: since commit 1a29d85eb0f1 ("mm: use vmf->address instead of of vmf->virtual_address") vmf->virtual_address"), which dates back to 2016. A concern has been raised that existing userspace application might rely on the old/wrong behavior in which the address is masked. Therefore, it was suggested to provide the masked address unless the user explicitly asks for the exact address. Add a new userfaultfd feature UFFD_FEATURE_EXACT_ADDRESS to direct userfaultfd to provide the exact address. Add a new "real_address" field to vmf to hold the unmasked address. Provide the address to userspace accordingly. Initialize real_address in various code-paths to be consistent with address, even when it is not used, to be on the safe side. [namit@vmware.com: initialize real_address on all code paths, per Jan] Link: https://lkml.kernel.org/r/20220226022655.350562-1-namit@vmware.com [akpm@linux-foundation.org: fix typo in comment, per Jan] Link: https://lkml.kernel.org/r/20220218041003.3508-1-namit@vmware.com Signed-off-by: Nadav Amit Acked-by: Peter Xu Reviewed-by: David Hildenbrand Acked-by: Mike Rapoport Reviewed-by: Jan Kara Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 ++- include/uapi/linux/userfaultfd.h | 8 +++++++- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9d58321386cc..0e4fd101616e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -478,7 +478,8 @@ struct vm_fault { struct vm_area_struct *vma; /* Target VMA */ gfp_t gfp_mask; /* gfp mask to be used for allocations */ pgoff_t pgoff; /* Logical page offset based on vma */ - unsigned long address; /* Faulting virtual address */ + unsigned long address; /* Faulting virtual address - masked */ + unsigned long real_address; /* Faulting virtual address - unmasked */ }; enum fault_flag flags; /* FAULT_FLAG_xxx flags * XXX: should really be 'const' */ diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index 05b31d60acf6..ef739054cb1c 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -32,7 +32,8 @@ UFFD_FEATURE_SIGBUS | \ UFFD_FEATURE_THREAD_ID | \ UFFD_FEATURE_MINOR_HUGETLBFS | \ - UFFD_FEATURE_MINOR_SHMEM) + UFFD_FEATURE_MINOR_SHMEM | \ + UFFD_FEATURE_EXACT_ADDRESS) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -189,6 +190,10 @@ struct uffdio_api { * * UFFD_FEATURE_MINOR_SHMEM indicates the same support as * UFFD_FEATURE_MINOR_HUGETLBFS, but for shmem-backed pages instead. + * + * UFFD_FEATURE_EXACT_ADDRESS indicates that the exact address of page + * faults would be provided and the offset within the page would not be + * masked. */ #define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) #define UFFD_FEATURE_EVENT_FORK (1<<1) @@ -201,6 +206,7 @@ struct uffdio_api { #define UFFD_FEATURE_THREAD_ID (1<<8) #define UFFD_FEATURE_MINOR_HUGETLBFS (1<<9) #define UFFD_FEATURE_MINOR_SHMEM (1<<10) +#define UFFD_FEATURE_EXACT_ADDRESS (1<<11) __u64 features; __u64 ioctls; -- cgit v1.2.3 From b698f0a1773f7df73f2bb4bfe0e597ea1bb3881f Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 22 Mar 2022 14:45:38 -0700 Subject: mm/fs: delete PF_SWAPWRITE PF_SWAPWRITE has been redundant since v3.2 commit ee72886d8ed5 ("mm: vmscan: do not writeback filesystem pages in direct reclaim"). Coincidentally, NeilBrown's current patch "remove inode_congested()" deletes may_write_to_inode(), which appeared to be the one function which took notice of PF_SWAPWRITE. But if you study the old logic, and the conditions under which may_write_to_inode() was called, you discover that flag and function have been pointless for a decade. Link: https://lkml.kernel.org/r/75e80e7-742d-e3bd-531-614db8961e4@google.com Signed-off-by: Hugh Dickins Cc: NeilBrown Cc: Jan Kara Cc: "Darrick J. Wong" Cc: Dave Chinner Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 75ba8aa60248..c3c841a02a00 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1689,7 +1689,6 @@ extern struct pid *cad_pid; * I am cleaning dirty pages from some other bdi. */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ -#define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_PIN 0x10000000 /* Allocation context constrained to zones which allow long term pinning. */ -- cgit v1.2.3 From 89f6c88a6ab4a11deb14c270f7f1454cda4f73d6 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 22 Mar 2022 14:45:41 -0700 Subject: mm: __isolate_lru_page_prepare() in isolate_migratepages_block() __isolate_lru_page_prepare() conflates two unrelated functions, with the flags to one disjoint from the flags to the other; and hides some of the important checks outside of isolate_migratepages_block(), where the sequence is better to be visible. It comes from the days of lumpy reclaim, before compaction, when the combination made more sense. Move what's needed by mm/compaction.c isolate_migratepages_block() inline there, and what's needed by mm/vmscan.c isolate_lru_pages() inline there. Shorten "isolate_mode" to "mode", so the sequence of conditions is easier to read. Declare a "mapping" variable, to save one call to page_mapping() (but not another: calling again after page is locked is necessary). Simplify isolate_lru_pages() with a "move_to" list pointer. Link: https://lkml.kernel.org/r/879d62a8-91cc-d3c6-fb3b-69768236df68@google.com Signed-off-by: Hugh Dickins Acked-by: David Rientjes Reviewed-by: Alex Shi Cc: Alexander Duyck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 3db431276d82..a246c137678e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -387,7 +387,6 @@ extern void lru_cache_add_inactive_or_unevictable(struct page *page, extern unsigned long zone_reclaimable_pages(struct zone *zone); extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); -extern bool __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode); extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, -- cgit v1.2.3 From abd4349ff9b8d242376b67711254221f64f447c7 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Tue, 22 Mar 2022 14:45:56 -0700 Subject: mm: compaction: cleanup the compaction trace events As Steven suggested [1], we should access the pointers from the trace event to avoid dereferencing them to the tracepoint function when the tracepoint is disabled. [1] https://lkml.org/lkml/2021/11/3/409 Link: https://lkml.kernel.org/r/4cd393b4d57f8f01ed72c001509b28e3a3b1a8c1.1646985115.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Cc: Steven Rostedt (Google) Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/compaction.h | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h index 7d48e7079e48..c6d5d70dc7a5 100644 --- a/include/trace/events/compaction.h +++ b/include/trace/events/compaction.h @@ -67,10 +67,10 @@ DEFINE_EVENT(mm_compaction_isolate_template, mm_compaction_isolate_freepages, #ifdef CONFIG_COMPACTION TRACE_EVENT(mm_compaction_migratepages, - TP_PROTO(unsigned long nr_all, + TP_PROTO(struct compact_control *cc, unsigned int nr_succeeded), - TP_ARGS(nr_all, nr_succeeded), + TP_ARGS(cc, nr_succeeded), TP_STRUCT__entry( __field(unsigned long, nr_migrated) @@ -79,7 +79,7 @@ TRACE_EVENT(mm_compaction_migratepages, TP_fast_assign( __entry->nr_migrated = nr_succeeded; - __entry->nr_failed = nr_all - nr_succeeded; + __entry->nr_failed = cc->nr_migratepages - nr_succeeded; ), TP_printk("nr_migrated=%lu nr_failed=%lu", @@ -88,10 +88,10 @@ TRACE_EVENT(mm_compaction_migratepages, ); TRACE_EVENT(mm_compaction_begin, - TP_PROTO(unsigned long zone_start, unsigned long migrate_pfn, - unsigned long free_pfn, unsigned long zone_end, bool sync), + TP_PROTO(struct compact_control *cc, unsigned long zone_start, + unsigned long zone_end, bool sync), - TP_ARGS(zone_start, migrate_pfn, free_pfn, zone_end, sync), + TP_ARGS(cc, zone_start, zone_end, sync), TP_STRUCT__entry( __field(unsigned long, zone_start) @@ -103,8 +103,8 @@ TRACE_EVENT(mm_compaction_begin, TP_fast_assign( __entry->zone_start = zone_start; - __entry->migrate_pfn = migrate_pfn; - __entry->free_pfn = free_pfn; + __entry->migrate_pfn = cc->migrate_pfn; + __entry->free_pfn = cc->free_pfn; __entry->zone_end = zone_end; __entry->sync = sync; ), @@ -118,11 +118,11 @@ TRACE_EVENT(mm_compaction_begin, ); TRACE_EVENT(mm_compaction_end, - TP_PROTO(unsigned long zone_start, unsigned long migrate_pfn, - unsigned long free_pfn, unsigned long zone_end, bool sync, + TP_PROTO(struct compact_control *cc, unsigned long zone_start, + unsigned long zone_end, bool sync, int status), - TP_ARGS(zone_start, migrate_pfn, free_pfn, zone_end, sync, status), + TP_ARGS(cc, zone_start, zone_end, sync, status), TP_STRUCT__entry( __field(unsigned long, zone_start) @@ -135,8 +135,8 @@ TRACE_EVENT(mm_compaction_end, TP_fast_assign( __entry->zone_start = zone_start; - __entry->migrate_pfn = migrate_pfn; - __entry->free_pfn = free_pfn; + __entry->migrate_pfn = cc->migrate_pfn; + __entry->free_pfn = cc->free_pfn; __entry->zone_end = zone_end; __entry->sync = sync; __entry->status = status; -- cgit v1.2.3 From 356ea3865687926e5da7579d1f3351d3f0a322a1 Mon Sep 17 00:00:00 2001 From: "andrew.yang" Date: Tue, 22 Mar 2022 14:46:08 -0700 Subject: mm/migrate: fix race between lock page and clear PG_Isolated When memory is tight, system may start to compact memory for large continuous memory demands. If one process tries to lock a memory page that is being locked and isolated for compaction, it may wait a long time or even forever. This is because compaction will perform non-atomic PG_Isolated clear while holding page lock, this may overwrite PG_waiters set by the process that can't obtain the page lock and add itself to the waiting queue to wait for the lock to be unlocked. CPU1 CPU2 lock_page(page); (successful) lock_page(); (failed) __ClearPageIsolated(page); SetPageWaiters(page) (may be overwritten) unlock_page(page); The solution is to not perform non-atomic operation on page flags while holding page lock. Link: https://lkml.kernel.org/r/20220315030515.20263-1-andrew.yang@mediatek.com Signed-off-by: andrew.yang Cc: Matthias Brugger Cc: Matthew Wilcox Cc: "Vlastimil Babka" Cc: David Howells Cc: "William Kucharski" Cc: David Hildenbrand Cc: Yang Shi Cc: Marc Zyngier Cc: Nicholas Tang Cc: Kuan-Ying Lee Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 340cb8156568..88fe1d759cdd 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -1000,7 +1000,7 @@ PAGE_TYPE_OPS(Guard, guard) extern bool is_free_buddy_page(struct page *page); -__PAGEFLAG(Isolated, isolated, PF_ANY); +PAGEFLAG(Isolated, isolated, PF_ANY); #ifdef CONFIG_MMU #define __PG_MLOCKED (1UL << PG_mlocked) -- cgit v1.2.3 From 27d121d0ec6d604d0147c5b579e4181b688a2d64 Mon Sep 17 00:00:00 2001 From: Hari Bathini Date: Tue, 22 Mar 2022 14:46:14 -0700 Subject: mm/cma: provide option to opt out from exposing pages on activation failure Patch series "powerpc/fadump: handle CMA activation failure appropriately", v3. Commit 072355c1cf2d ("mm/cma: expose all pages to the buddy if activation of an area fails") started exposing all pages to buddy allocator on CMA activation failure. But there can be CMA users that want to handle the reserved memory differently on CMA allocation failure. Provide an option to opt out from exposing pages to buddy for such cases. Link: https://lkml.kernel.org/r/20220117075246.36072-1-hbathini@linux.ibm.com Link: https://lkml.kernel.org/r/20220117075246.36072-2-hbathini@linux.ibm.com Signed-off-by: Hari Bathini Reviewed-by: David Hildenbrand Cc: Oscar Salvador Cc: Mike Kravetz Cc: Mahesh Salgaonkar Cc: Sourabh Jain Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cma.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/cma.h b/include/linux/cma.h index b1ba94f1cc9c..90fd742fd1ef 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -58,4 +58,6 @@ extern bool cma_pages_valid(struct cma *cma, const struct page *pages, unsigned extern bool cma_release(struct cma *cma, const struct page *pages, unsigned long count); extern int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data); + +extern void cma_reserve_pages_on_error(struct cma *cma); #endif -- cgit v1.2.3 From e39bb6be9f2b39a6dbaeff484361de76021b175d Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Tue, 22 Mar 2022 14:46:20 -0700 Subject: NUMA Balancing: add page promotion counter Patch series "NUMA balancing: optimize memory placement for memory tiering system", v13 With the advent of various new memory types, some machines will have multiple types of memory, e.g. DRAM and PMEM (persistent memory). The memory subsystem of these machines can be called memory tiering system, because the performance of the different types of memory are different. After commit c221c0b0308f ("device-dax: "Hotplug" persistent memory for use like normal RAM"), the PMEM could be used as the cost-effective volatile memory in separate NUMA nodes. In a typical memory tiering system, there are CPUs, DRAM and PMEM in each physical NUMA node. The CPUs and the DRAM will be put in one logical node, while the PMEM will be put in another (faked) logical node. To optimize the system overall performance, the hot pages should be placed in DRAM node. To do that, we need to identify the hot pages in the PMEM node and migrate them to DRAM node via NUMA migration. In the original NUMA balancing, there are already a set of existing mechanisms to identify the pages recently accessed by the CPUs in a node and migrate the pages to the node. So we can reuse these mechanisms to build the mechanisms to optimize the page placement in the memory tiering system. This is implemented in this patchset. At the other hand, the cold pages should be placed in PMEM node. So, we also need to identify the cold pages in the DRAM node and migrate them to PMEM node. In commit 26aa2d199d6f ("mm/migrate: demote pages during reclaim"), a mechanism to demote the cold DRAM pages to PMEM node under memory pressure is implemented. Based on that, the cold DRAM pages can be demoted to PMEM node proactively to free some memory space on DRAM node to accommodate the promoted hot PMEM pages. This is implemented in this patchset too. We have tested the solution with the pmbench memory accessing benchmark with the 80:20 read/write ratio and the Gauss access address distribution on a 2 socket Intel server with Optane DC Persistent Memory Model. The test results shows that the pmbench score can improve up to 95.9%. This patch (of 3): In a system with multiple memory types, e.g. DRAM and PMEM, the CPU and DRAM in one socket will be put in one NUMA node as before, while the PMEM will be put in another NUMA node as described in the description of the commit c221c0b0308f ("device-dax: "Hotplug" persistent memory for use like normal RAM"). So, the NUMA balancing mechanism will identify all PMEM accesses as remote access and try to promote the PMEM pages to DRAM. To distinguish the number of the inter-type promoted pages from that of the inter-socket migrated pages. A new vmstat count is added. The counter is per-node (count in the target node). So this can be used to identify promotion imbalance among the NUMA nodes. Link: https://lkml.kernel.org/r/20220301085329.3210428-1-ying.huang@intel.com Link: https://lkml.kernel.org/r/20220221084529.1052339-1-ying.huang@intel.com Link: https://lkml.kernel.org/r/20220221084529.1052339-2-ying.huang@intel.com Signed-off-by: "Huang, Ying" Reviewed-by: Yang Shi Tested-by: Baolin Wang Reviewed-by: Baolin Wang Acked-by: Johannes Weiner Reviewed-by: Oscar Salvador Cc: Michal Hocko Cc: Rik van Riel Cc: Mel Gorman Cc: Peter Zijlstra Cc: Dave Hansen Cc: Zi Yan Cc: Wei Xu Cc: Shakeel Butt Cc: zhongjiang-ali Cc: Feng Tang Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 3 +++ include/linux/node.h | 5 +++++ 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c9e6a50109b9..310b6e7ce58a 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -221,6 +221,9 @@ enum node_stat_item { NR_PAGETABLE, /* used for pagetables */ #ifdef CONFIG_SWAP NR_SWAPCACHE, +#endif +#ifdef CONFIG_NUMA_BALANCING + PGPROMOTE_SUCCESS, /* promote successfully */ #endif NR_VM_NODE_STAT_ITEMS }; diff --git a/include/linux/node.h b/include/linux/node.h index bb21fd631b16..81bbf1c0afd3 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -181,4 +181,9 @@ static inline void register_hugetlbfs_with_node(node_registration_func_t reg, #define to_node(device) container_of(device, struct node, dev) +static inline bool node_is_toptier(int node) +{ + return node_state(node, N_CPU); +} + #endif /* _LINUX_NODE_H_ */ -- cgit v1.2.3 From c574bbe917036c8968b984c82c7b13194fe5ce98 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Tue, 22 Mar 2022 14:46:23 -0700 Subject: NUMA balancing: optimize page placement for memory tiering system With the advent of various new memory types, some machines will have multiple types of memory, e.g. DRAM and PMEM (persistent memory). The memory subsystem of these machines can be called memory tiering system, because the performance of the different types of memory are usually different. In such system, because of the memory accessing pattern changing etc, some pages in the slow memory may become hot globally. So in this patch, the NUMA balancing mechanism is enhanced to optimize the page placement among the different memory types according to hot/cold dynamically. In a typical memory tiering system, there are CPUs, fast memory and slow memory in each physical NUMA node. The CPUs and the fast memory will be put in one logical node (called fast memory node), while the slow memory will be put in another (faked) logical node (called slow memory node). That is, the fast memory is regarded as local while the slow memory is regarded as remote. So it's possible for the recently accessed pages in the slow memory node to be promoted to the fast memory node via the existing NUMA balancing mechanism. The original NUMA balancing mechanism will stop to migrate pages if the free memory of the target node becomes below the high watermark. This is a reasonable policy if there's only one memory type. But this makes the original NUMA balancing mechanism almost do not work to optimize page placement among different memory types. Details are as follows. It's the common cases that the working-set size of the workload is larger than the size of the fast memory nodes. Otherwise, it's unnecessary to use the slow memory at all. So, there are almost always no enough free pages in the fast memory nodes, so that the globally hot pages in the slow memory node cannot be promoted to the fast memory node. To solve the issue, we have 2 choices as follows, a. Ignore the free pages watermark checking when promoting hot pages from the slow memory node to the fast memory node. This will create some memory pressure in the fast memory node, thus trigger the memory reclaiming. So that, the cold pages in the fast memory node will be demoted to the slow memory node. b. Define a new watermark called wmark_promo which is higher than wmark_high, and have kswapd reclaiming pages until free pages reach such watermark. The scenario is as follows: when we want to promote hot-pages from a slow memory to a fast memory, but fast memory's free pages would go lower than high watermark with such promotion, we wake up kswapd with wmark_promo watermark in order to demote cold pages and free us up some space. So, next time we want to promote hot-pages we might have a chance of doing so. The choice "a" may create high memory pressure in the fast memory node. If the memory pressure of the workload is high, the memory pressure may become so high that the memory allocation latency of the workload is influenced, e.g. the direct reclaiming may be triggered. The choice "b" works much better at this aspect. If the memory pressure of the workload is high, the hot pages promotion will stop earlier because its allocation watermark is higher than that of the normal memory allocation. So in this patch, choice "b" is implemented. A new zone watermark (WMARK_PROMO) is added. Which is larger than the high watermark and can be controlled via watermark_scale_factor. In addition to the original page placement optimization among sockets, the NUMA balancing mechanism is extended to be used to optimize page placement according to hot/cold among different memory types. So the sysctl user space interface (numa_balancing) is extended in a backward compatible way as follow, so that the users can enable/disable these functionality individually. The sysctl is converted from a Boolean value to a bits field. The definition of the flags is, - 0: NUMA_BALANCING_DISABLED - 1: NUMA_BALANCING_NORMAL - 2: NUMA_BALANCING_MEMORY_TIERING We have tested the patch with the pmbench memory accessing benchmark with the 80:20 read/write ratio and the Gauss access address distribution on a 2 socket Intel server with Optane DC Persistent Memory Model. The test results shows that the pmbench score can improve up to 95.9%. Thanks Andrew Morton to help fix the document format error. Link: https://lkml.kernel.org/r/20220221084529.1052339-3-ying.huang@intel.com Signed-off-by: "Huang, Ying" Tested-by: Baolin Wang Reviewed-by: Baolin Wang Acked-by: Johannes Weiner Reviewed-by: Oscar Salvador Reviewed-by: Yang Shi Cc: Michal Hocko Cc: Rik van Riel Cc: Mel Gorman Cc: Peter Zijlstra Cc: Dave Hansen Cc: Zi Yan Cc: Wei Xu Cc: Shakeel Butt Cc: zhongjiang-ali Cc: Randy Dunlap Cc: Feng Tang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + include/linux/sched/sysctl.h | 10 ++++++++++ 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 310b6e7ce58a..962b14d403e8 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -353,6 +353,7 @@ enum zone_watermarks { WMARK_MIN, WMARK_LOW, WMARK_HIGH, + WMARK_PROMO, NR_WMARK }; diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index c19dd5a2c05c..b5eec8854c5a 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -23,6 +23,16 @@ enum sched_tunable_scaling { SCHED_TUNABLESCALING_END, }; +#define NUMA_BALANCING_DISABLED 0x0 +#define NUMA_BALANCING_NORMAL 0x1 +#define NUMA_BALANCING_MEMORY_TIERING 0x2 + +#ifdef CONFIG_NUMA_BALANCING +extern int sysctl_numa_balancing_mode; +#else +#define sysctl_numa_balancing_mode 0 +#endif + /* * control realtime throttling: * -- cgit v1.2.3 From 4d45c3aff5ebf80d329eba0f90544d20224f612d Mon Sep 17 00:00:00 2001 From: Yang Yang Date: Tue, 22 Mar 2022 14:46:33 -0700 Subject: mm/vmstat: add event for ksm swapping in copy When faults in from swap what used to be a KSM page and that page had been swapped in before, system has to make a copy, and leaves remerging the pages to a later pass of ksmd. That is not good for performace, we'd better to reduce this kind of copy. There are some ways to reduce it, for example lessen swappiness or madvise(, , MADV_MERGEABLE) range. So add this event to support doing this tuning. Just like this patch: "mm, THP, swap: add THP swapping out fallback counting". Link: https://lkml.kernel.org/r/20220113023839.758845-1-yang.yang29@zte.com.cn Signed-off-by: Yang Yang Reviewed-by: Ran Xiaokai Cc: Hugh Dickins Cc: Yang Shi Cc: Dave Hansen Cc: Saravanan D Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vm_event_item.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 7b2363388bfa..16a0a4fd000b 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -129,6 +129,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_SWAP SWAP_RA, SWAP_RA_HIT, +#ifdef CONFIG_KSM + KSM_SWPIN_COPY, +#endif #endif #ifdef CONFIG_X86 DIRECT_MAP_LEVEL2_SPLIT, -- cgit v1.2.3 From e930d999715073a70d306fb59a394ea8b84d0b45 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 22 Mar 2022 14:46:51 -0700 Subject: mm, memory_hotplug: make arch_alloc_nodedata independent on CONFIG_MEMORY_HOTPLUG Patch series "mm, memory_hotplug: handle unitialized numa node gracefully". The core of the fix is patch 2 which also links existing bug reports. The high level goal is to have all possible numa nodes have their pgdat allocated and initialized so for_each_possible_node(nid) NODE_DATA(nid) will never return garbage. This has proven to be problem in several places when an offline numa node is used for an allocation just to realize that node_data and therefore allocation fallback zonelists are not initialized and such an allocation request blows up. There were attempts to address that by checking node_online in several places including the page allocator. This patchset approaches the problem from a different perspective and instead of special casing, which just adds a runtime overhead, it allocates pglist_data for each possible node. This can add some memory overhead for platforms with high number of possible nodes if they do not contain any memory. This should be a rather rare configuration though. How to test this? David has provided and excellent howto: http://lkml.kernel.org/r/6e5ebc19-890c-b6dd-1924-9f25c441010d@redhat.com Patches 1 and 3-6 are mostly cleanups. The patchset has been reviewed by Rafael (thanks!) and the core fix tested by Rafael and Alexey (thanks to both). David has tested as per instructions above and hasn't found any fallouts in the memory hotplug scenarios. This patch (of 6): This is a preparatory patch and it doesn't introduce any functional change. It merely pulls out arch_alloc_nodedata (and co) outside of CONFIG_MEMORY_HOTPLUG because the following patch will need to call this from the generic MM code. Link: https://lkml.kernel.org/r/20220127085305.20890-1-mhocko@kernel.org Link: https://lkml.kernel.org/r/20220127085305.20890-2-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Rafael Aquini Acked-by: David Hildenbrand Acked-by: Mike Rapoport Reviewed-by: Oscar Salvador Reviewed-by: Wei Yang Cc: Alexey Makhalov Cc: Christoph Lameter Cc: Dennis Zhou Cc: Eric Dumazet Cc: Nico Pache Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 119 ++++++++++++++++++++--------------------- 1 file changed, 59 insertions(+), 60 deletions(-) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index be48e003a518..4355983b364d 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -16,6 +16,65 @@ struct memory_group; struct resource; struct vmem_altmap; +#ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION +/* + * For supporting node-hotadd, we have to allocate a new pgdat. + * + * If an arch has generic style NODE_DATA(), + * node_data[nid] = kzalloc() works well. But it depends on the architecture. + * + * In general, generic_alloc_nodedata() is used. + * Now, arch_free_nodedata() is just defined for error path of node_hot_add. + * + */ +extern pg_data_t *arch_alloc_nodedata(int nid); +extern void arch_free_nodedata(pg_data_t *pgdat); +extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat); + +#else /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ + +#define arch_alloc_nodedata(nid) generic_alloc_nodedata(nid) +#define arch_free_nodedata(pgdat) generic_free_nodedata(pgdat) + +#ifdef CONFIG_NUMA +/* + * XXX: node aware allocation can't work well to get new node's memory at this time. + * Because, pgdat for the new node is not allocated/initialized yet itself. + * To use new node's memory, more consideration will be necessary. + */ +#define generic_alloc_nodedata(nid) \ +({ \ + kzalloc(sizeof(pg_data_t), GFP_KERNEL); \ +}) +/* + * This definition is just for error path in node hotadd. + * For node hotremove, we have to replace this. + */ +#define generic_free_nodedata(pgdat) kfree(pgdat) + +extern pg_data_t *node_data[]; +static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) +{ + node_data[nid] = pgdat; +} + +#else /* !CONFIG_NUMA */ + +/* never called */ +static inline pg_data_t *generic_alloc_nodedata(int nid) +{ + BUG(); + return NULL; +} +static inline void generic_free_nodedata(pg_data_t *pgdat) +{ +} +static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) +{ +} +#endif /* CONFIG_NUMA */ +#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ + #ifdef CONFIG_MEMORY_HOTPLUG struct page *pfn_to_online_page(unsigned long pfn); @@ -154,66 +213,6 @@ int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, struct mhp_params *params); #endif /* ARCH_HAS_ADD_PAGES */ -#ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION -/* - * For supporting node-hotadd, we have to allocate a new pgdat. - * - * If an arch has generic style NODE_DATA(), - * node_data[nid] = kzalloc() works well. But it depends on the architecture. - * - * In general, generic_alloc_nodedata() is used. - * Now, arch_free_nodedata() is just defined for error path of node_hot_add. - * - */ -extern pg_data_t *arch_alloc_nodedata(int nid); -extern void arch_free_nodedata(pg_data_t *pgdat); -extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat); - -#else /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ - -#define arch_alloc_nodedata(nid) generic_alloc_nodedata(nid) -#define arch_free_nodedata(pgdat) generic_free_nodedata(pgdat) - -#ifdef CONFIG_NUMA -/* - * If ARCH_HAS_NODEDATA_EXTENSION=n, this func is used to allocate pgdat. - * XXX: kmalloc_node() can't work well to get new node's memory at this time. - * Because, pgdat for the new node is not allocated/initialized yet itself. - * To use new node's memory, more consideration will be necessary. - */ -#define generic_alloc_nodedata(nid) \ -({ \ - kzalloc(sizeof(pg_data_t), GFP_KERNEL); \ -}) -/* - * This definition is just for error path in node hotadd. - * For node hotremove, we have to replace this. - */ -#define generic_free_nodedata(pgdat) kfree(pgdat) - -extern pg_data_t *node_data[]; -static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) -{ - node_data[nid] = pgdat; -} - -#else /* !CONFIG_NUMA */ - -/* never called */ -static inline pg_data_t *generic_alloc_nodedata(int nid) -{ - BUG(); - return NULL; -} -static inline void generic_free_nodedata(pg_data_t *pgdat) -{ -} -static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) -{ -} -#endif /* CONFIG_NUMA */ -#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ - void get_online_mems(void); void put_online_mems(void); -- cgit v1.2.3 From 09f49dca570a917a8c6bccd7e8c61f5141534e3a Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 22 Mar 2022 14:46:54 -0700 Subject: mm: handle uninitialized numa nodes gracefully We have had several reports [1][2][3] that page allocator blows up when an allocation from a possible node is requested. The underlying reason is that NODE_DATA for the specific node is not allocated. NUMA specific initialization is arch specific and it can vary a lot. E.g. x86 tries to initialize all nodes that have some cpu affinity (see init_cpu_to_node) but this can be insufficient because the node might be cpuless for example. One way to address this problem would be to check for !node_online nodes when trying to get a zonelist and silently fall back to another node. That is unfortunately adding a branch into allocator hot path and it doesn't handle any other potential NODE_DATA users. This patch takes a different approach (following a lead of [3]) and it pre allocates pgdat for all possible nodes in an arch indipendent code - free_area_init. All uninitialized nodes are treated as memoryless nodes. node_state of the node is not changed because that would lead to other side effects - e.g. sysfs representation of such a node and from past discussions [4] it is known that some tools might have problems digesting that. Newly allocated pgdat only gets a minimal initialization and the rest of the work is expected to be done by the memory hotplug - hotadd_new_pgdat (renamed to hotadd_init_pgdat). generic_alloc_nodedata is changed to use the memblock allocator because neither page nor slab allocators are available at the stage when all pgdats are allocated. Hotplug doesn't allocate pgdat anymore so we can use the early boot allocator. The only arch specific implementation is ia64 and that is changed to use the early allocator as well. [1] http://lkml.kernel.org/r/20211101201312.11589-1-amakhalov@vmware.com [2] http://lkml.kernel.org/r/20211207224013.880775-1-npache@redhat.com [3] http://lkml.kernel.org/r/20190114082416.30939-1-mhocko@kernel.org [4] http://lkml.kernel.org/r/20200428093836.27190-1-srikar@linux.vnet.ibm.com [akpm@linux-foundation.org: replace comment, per Mike] Link: https://lkml.kernel.org/r/Yfe7RBeLCijnWBON@dhcp22.suse.cz Reported-by: Alexey Makhalov Tested-by: Alexey Makhalov Reported-by: Nico Pache Acked-by: Rafael Aquini Tested-by: Rafael Aquini Acked-by: David Hildenbrand Reviewed-by: Oscar Salvador Acked-by: Mike Rapoport Signed-off-by: Michal Hocko Cc: Christoph Lameter Cc: Dennis Zhou Cc: Eric Dumazet Cc: Tejun Heo Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 4355983b364d..cdd66bfdf855 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -44,7 +44,7 @@ extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat); */ #define generic_alloc_nodedata(nid) \ ({ \ - kzalloc(sizeof(pg_data_t), GFP_KERNEL); \ + memblock_alloc(sizeof(*pgdat), SMP_CACHE_BYTES); \ }) /* * This definition is just for error path in node hotadd. -- cgit v1.2.3 From 390511e1476eb1cc41d420a7661b33f4d8584c3f Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 22 Mar 2022 14:46:57 -0700 Subject: mm, memory_hotplug: drop arch_free_nodedata Prior to "mm: handle uninitialized numa nodes gracefully" memory hotplug used to allocate pgdat when memory has been added to a node (hotadd_init_pgdat) arch_free_nodedata has been only used in the failure path because once the pgdat is exported (to be visible by NODA_DATA(nid)) it cannot really be freed because there is no synchronization available for that. pgdat is allocated for each possible nodes now so the memory hotplug doesn't need to do the ever use arch_free_nodedata so drop it. This patch doesn't introduce any functional change. Link: https://lkml.kernel.org/r/20220127085305.20890-4-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Rafael Aquini Acked-by: David Hildenbrand Acked-by: Mike Rapoport Reviewed-by: Oscar Salvador Cc: Alexey Makhalov Cc: Christoph Lameter Cc: Dennis Zhou Cc: Eric Dumazet Cc: Nico Pache Cc: Tejun Heo Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index cdd66bfdf855..60f09d3ebb3d 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -24,17 +24,14 @@ struct vmem_altmap; * node_data[nid] = kzalloc() works well. But it depends on the architecture. * * In general, generic_alloc_nodedata() is used. - * Now, arch_free_nodedata() is just defined for error path of node_hot_add. * */ extern pg_data_t *arch_alloc_nodedata(int nid); -extern void arch_free_nodedata(pg_data_t *pgdat); extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat); #else /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ #define arch_alloc_nodedata(nid) generic_alloc_nodedata(nid) -#define arch_free_nodedata(pgdat) generic_free_nodedata(pgdat) #ifdef CONFIG_NUMA /* -- cgit v1.2.3 From 70b5b46a754245d383811b4d2f2c76c34bb7e145 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 22 Mar 2022 14:47:00 -0700 Subject: mm, memory_hotplug: reorganize new pgdat initialization When a !node_online node is brought up it needs a hotplug specific initialization because the node could be either uninitialized yet or it could have been recycled after previous hotremove. hotadd_init_pgdat is responsible for that. Internal pgdat state is initialized at two places currently - hotadd_init_pgdat - free_area_init_core_hotplug There is no real clear cut what should go where but this patch's chosen to move the whole internal state initialization into free_area_init_core_hotplug. hotadd_init_pgdat is still responsible to pull all the parts together - most notably to initialize zonelists because those depend on the overall topology. This patch doesn't introduce any functional change. Link: https://lkml.kernel.org/r/20220127085305.20890-5-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Rafael Aquini Acked-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Alexey Makhalov Cc: Christoph Lameter Cc: Dennis Zhou Cc: Eric Dumazet Cc: Mike Rapoport Cc: Nico Pache Cc: Tejun Heo Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 60f09d3ebb3d..76bf2de86def 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -319,7 +319,7 @@ extern void set_zone_contiguous(struct zone *zone); extern void clear_zone_contiguous(struct zone *zone); #ifdef CONFIG_MEMORY_HOTPLUG -extern void __ref free_area_init_core_hotplug(int nid); +extern void __ref free_area_init_core_hotplug(struct pglist_data *pgdat); extern int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags); extern int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags); extern int add_memory_resource(int nid, struct resource *resource, -- cgit v1.2.3 From 2848a28b0a6052a4c8450397d2647d7d8e3f6f06 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 22 Mar 2022 14:47:13 -0700 Subject: drivers/base/node: consolidate node device subsystem initialization in node_dev_init() ... and call node_dev_init() after memory_dev_init() from driver_init(), so before any of the existing arch/subsys calls. All online nodes should be known at that point: early during boot, arch code determines node and zone ranges and sets the relevant nodes online; usually this happens in setup_arch(). This is in line with memory_dev_init(), which initializes the memory device subsystem and creates all memory block devices. Similar to memory_dev_init(), panic() if anything goes wrong, we don't want to continue with such basic initialization errors. The important part is that node_dev_init() gets called after memory_dev_init() and after cpu_dev_init(), but before any of the relevant archs call register_cpu() to register the new cpu device under the node device. The latter should be the case for the current users of topology_init(). Link: https://lkml.kernel.org/r/20220203105212.30385-1-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Oscar Salvador Tested-by: Anatoly Pugachev (sparc64) Cc: Greg Kroah-Hartman Cc: Michal Hocko Cc: Oscar Salvador Cc: Mike Rapoport Cc: Catalin Marinas Cc: Will Deacon Cc: Thomas Bogendoerfer Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Yoshinori Sato Cc: Rich Felker Cc: "David S. Miller" Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: "Rafael J. Wysocki" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/node.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/node.h b/include/linux/node.h index 81bbf1c0afd3..7f876d48af11 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -112,6 +112,7 @@ static inline void link_mem_sections(int nid, unsigned long start_pfn, extern void unregister_node(struct node *node); #ifdef CONFIG_NUMA +extern void node_dev_init(void); /* Core of the node registration - only memory hotplug should use this */ extern int __register_one_node(int nid); @@ -149,6 +150,9 @@ extern void register_hugetlbfs_with_node(node_registration_func_t doregister, node_registration_func_t unregister); #endif #else +static inline void node_dev_init(void) +{ +} static inline int __register_one_node(int nid) { return 0; -- cgit v1.2.3 From cc6515591b25f08ce199e9379844a964f52a27f2 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 22 Mar 2022 14:47:28 -0700 Subject: drivers/base/node: rename link_mem_sections() to register_memory_block_under_node() Patch series "drivers/base/memory: determine and store zone for single-zone memory blocks", v2. I remember talking to Michal in the past about removing test_pages_in_a_zone(), which we use for: * verifying that a memory block we intend to offline is really only managed by a single zone. We don't support offlining of memory blocks that are managed by multiple zones (e.g., multiple nodes, DMA and DMA32) * exposing that zone to user space via /sys/devices/system/memory/memory*/valid_zones Now that I identified some more cases where test_pages_in_a_zone() might go wrong, and we received an UBSAN report (see patch #3), let's get rid of this PFN walker. So instead of detecting the zone at runtime with test_pages_in_a_zone() by scanning the memmap, let's determine and remember for each memory block if it's managed by a single zone. The stored zone can then be used for the above two cases, avoiding a manual lookup using test_pages_in_a_zone(). This avoids eventually stumbling over uninitialized memmaps in corner cases, especially when ZONE_DEVICE ranges partly fall into memory block (that are responsible for managing System RAM). Handling memory onlining is easy, because we online to exactly one zone. Handling boot memory is more tricky, because we want to avoid scanning all zones of all nodes to detect possible zones that overlap with the physical memory region of interest. Fortunately, we already have code that determines the applicable nodes for a memory block, to create sysfs links -- we'll hook into that. Patch #1 is a simple cleanup I had laying around for a longer time. Patch #2 contains the main logic to remove test_pages_in_a_zone() and further details. [1] https://lkml.kernel.org/r/20220128144540.153902-1-david@redhat.com [2] https://lkml.kernel.org/r/20220203105212.30385-1-david@redhat.com This patch (of 2): Let's adjust the stale terminology, making it match unregister_memory_block_under_nodes() and do_register_memory_block_under_node(). We're dealing with memory block devices, which span 1..X memory sections. Link: https://lkml.kernel.org/r/20220210184359.235565-1-david@redhat.com Link: https://lkml.kernel.org/r/20220210184359.235565-2-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Oscar Salvador Cc: Greg Kroah-Hartman Cc: Michal Hocko Cc: "Rafael J. Wysocki" Cc: Rafael Parra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/node.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/node.h b/include/linux/node.h index 7f876d48af11..40d641a8bfb0 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -99,13 +99,13 @@ extern struct node *node_devices[]; typedef void (*node_registration_func_t)(struct node *); #if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_NUMA) -void link_mem_sections(int nid, unsigned long start_pfn, - unsigned long end_pfn, - enum meminit_context context); +void register_memory_blocks_under_node(int nid, unsigned long start_pfn, + unsigned long end_pfn, + enum meminit_context context); #else -static inline void link_mem_sections(int nid, unsigned long start_pfn, - unsigned long end_pfn, - enum meminit_context context) +static inline void register_memory_blocks_under_node(int nid, unsigned long start_pfn, + unsigned long end_pfn, + enum meminit_context context) { } #endif @@ -129,8 +129,8 @@ static inline int register_one_node(int nid) error = __register_one_node(nid); if (error) return error; - /* link memory sections under this node */ - link_mem_sections(nid, start_pfn, end_pfn, MEMINIT_EARLY); + register_memory_blocks_under_node(nid, start_pfn, end_pfn, + MEMINIT_EARLY); } return error; -- cgit v1.2.3 From 395f6081bad49f9c54abafebab49ee23aa985bbd Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 22 Mar 2022 14:47:31 -0700 Subject: drivers/base/memory: determine and store zone for single-zone memory blocks test_pages_in_a_zone() is just another nasty PFN walker that can easily stumble over ZONE_DEVICE memory ranges falling into the same memory block as ordinary system RAM: the memmap of parts of these ranges might possibly be uninitialized. In fact, we observed (on an older kernel) with UBSAN: UBSAN: Undefined behaviour in ./include/linux/mm.h:1133:50 index 7 is out of range for type 'zone [5]' CPU: 121 PID: 35603 Comm: read_all Kdump: loaded Tainted: [...] Hardware name: Dell Inc. PowerEdge R7425/08V001, BIOS 1.12.2 11/15/2019 Call Trace: dump_stack+0x9a/0xf0 ubsan_epilogue+0x9/0x7a __ubsan_handle_out_of_bounds+0x13a/0x181 test_pages_in_a_zone+0x3c4/0x500 show_valid_zones+0x1fa/0x380 dev_attr_show+0x43/0xb0 sysfs_kf_seq_show+0x1c5/0x440 seq_read+0x49d/0x1190 vfs_read+0xff/0x300 ksys_read+0xb8/0x170 do_syscall_64+0xa5/0x4b0 entry_SYSCALL_64_after_hwframe+0x6a/0xdf RIP: 0033:0x7f01f4439b52 We seem to stumble over a memmap that contains a garbage zone id. While we could try inserting pfn_to_online_page() calls, it will just make memory offlining slower, because we use test_pages_in_a_zone() to make sure we're offlining pages that all belong to the same zone. Let's just get rid of this PFN walker and determine the single zone of a memory block -- if any -- for early memory blocks during boot. For memory onlining, we know the single zone already. Let's avoid any additional memmap scanning and just rely on the zone information available during boot. For memory hot(un)plug, we only really care about memory blocks that: * span a single zone (and, thereby, a single node) * are completely System RAM (IOW, no holes, no ZONE_DEVICE) If one of these conditions is not met, we reject memory offlining. Hotplugged memory blocks (starting out offline), always meet both conditions. There are three scenarios to handle: (1) Memory hot(un)plug A memory block with zone == NULL cannot be offlined, corresponding to our previous test_pages_in_a_zone() check. After successful memory onlining/offlining, we simply set the zone accordingly. * Memory onlining: set the zone we just used for onlining * Memory offlining: set zone = NULL So a hotplugged memory block starts with zone = NULL. Once memory onlining is done, we set the proper zone. (2) Boot memory with !CONFIG_NUMA We know that there is just a single pgdat, so we simply scan all zones of that pgdat for an intersection with our memory block PFN range when adding the memory block. If more than one zone intersects (e.g., DMA and DMA32 on x86 for the first memory block) we set zone = NULL and consequently mimic what test_pages_in_a_zone() used to do. (3) Boot memory with CONFIG_NUMA At the point in time we create the memory block devices during boot, we don't know yet which nodes *actually* span a memory block. While we could scan all zones of all nodes for intersections, overlapping nodes complicate the situation and scanning all nodes is possibly expensive. But that problem has already been solved by the code that sets the node of a memory block and creates the link in the sysfs -- do_register_memory_block_under_node(). So, we hook into the code that sets the node id for a memory block. If we already have a different node id set for the memory block, we know that multiple nodes *actually* have PFNs falling into our memory block: we set zone = NULL and consequently mimic what test_pages_in_a_zone() used to do. If there is no node id set, we do the same as (2) for the given node. Note that the call order in driver_init() is: -> memory_dev_init(): create memory block devices -> node_dev_init(): link memory block devices to the node and set the node id So in summary, we detect if there is a single zone responsible for this memory block and we consequently store the zone in that case in the memory block, updating it during memory onlining/offlining. Link: https://lkml.kernel.org/r/20220210184359.235565-3-david@redhat.com Signed-off-by: David Hildenbrand Reported-by: Rafael Parra Reviewed-by: Oscar Salvador Cc: "Rafael J. Wysocki" Cc: Greg Kroah-Hartman Cc: Michal Hocko Cc: Rafael Parra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 12 ++++++++++++ include/linux/memory_hotplug.h | 6 ++---- 2 files changed, 14 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/memory.h b/include/linux/memory.h index 88eb587b5143..aa619464a1df 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -70,6 +70,13 @@ struct memory_block { unsigned long state; /* serialized by the dev->lock */ int online_type; /* for passing data to online routine */ int nid; /* NID for this memory block */ + /* + * The single zone of this memory block if all PFNs of this memory block + * that are System RAM (not a memory hole, not ZONE_DEVICE ranges) are + * managed by a single zone. NULL if multiple zones (including nodes) + * apply. + */ + struct zone *zone; struct device dev; /* * Number of vmemmap pages. These pages @@ -161,6 +168,11 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, }) #define register_hotmemory_notifier(nb) register_memory_notifier(nb) #define unregister_hotmemory_notifier(nb) unregister_memory_notifier(nb) + +#ifdef CONFIG_NUMA +void memory_block_add_nid(struct memory_block *mem, int nid, + enum meminit_context context); +#endif /* CONFIG_NUMA */ #endif /* CONFIG_MEMORY_HOTPLUG */ /* diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 76bf2de86def..1ce6f8044f1e 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -163,8 +163,6 @@ extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages); extern int online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group); -extern struct zone *test_pages_in_a_zone(unsigned long start_pfn, - unsigned long end_pfn); extern void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn); @@ -293,7 +291,7 @@ static inline void pgdat_resize_init(struct pglist_data *pgdat) {} extern void try_offline_node(int nid); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages, - struct memory_group *group); + struct zone *zone, struct memory_group *group); extern int remove_memory(u64 start, u64 size); extern void __remove_memory(u64 start, u64 size); extern int offline_and_remove_memory(u64 start, u64 size); @@ -302,7 +300,7 @@ extern int offline_and_remove_memory(u64 start, u64 size); static inline void try_offline_node(int nid) {} static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages, - struct memory_group *group) + struct zone *zone, struct memory_group *group) { return -EINVAL; } -- cgit v1.2.3 From 734c15700cdf9062ae98d8b131c6fe873dfad26d Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Tue, 22 Mar 2022 14:47:37 -0700 Subject: mm: only re-generate demotion targets when a numa node changes its N_CPU state Abhishek reported that after patch [1], hotplug operations are taking roughly double the expected time. [2] The reason behind is that the CPU callbacks that migrate_on_reclaim_init() sets always call set_migration_target_nodes() whenever a CPU is brought up/down. But we only care about numa nodes going from having cpus to become cpuless, and vice versa, as that influences the demotion_target order. We do already have two CPU callbacks (vmstat_cpu_online() and vmstat_cpu_dead()) that check exactly that, so get rid of the CPU callbacks in migrate_on_reclaim_init() and only call set_migration_target_nodes() from vmstat_cpu_{dead,online}() whenever a numa node change its N_CPU state. [1] https://lore.kernel.org/linux-mm/20210721063926.3024591-2-ying.huang@intel.com/ [2] https://lore.kernel.org/linux-mm/eb438ddd-2919-73d4-bd9f-b7eecdd9577a@linux.vnet.ibm.com/ [osalvador@suse.de: add feedback from Huang Ying] Link: https://lkml.kernel.org/r/20220314150945.12694-1-osalvador@suse.de Link: https://lkml.kernel.org/r/20220310120749.23077-1-osalvador@suse.de Fixes: 884a6e5d1f93b ("mm/migrate: update node demotion order on hotplug events") Signed-off-by: Oscar Salvador Reviewed-by: Baolin Wang Tested-by: Baolin Wang Reported-by: Abhishek Goel Cc: Dave Hansen Cc: "Huang, Ying" Cc: Abhishek Goel Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index db96e10eb8da..90e75d5a54d6 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -48,7 +48,15 @@ int folio_migrate_mapping(struct address_space *mapping, struct folio *newfolio, struct folio *folio, int extra_count); extern bool numa_demotion_enabled; +extern void migrate_on_reclaim_init(void); +#ifdef CONFIG_HOTPLUG_CPU +extern void set_migration_target_nodes(void); #else +static inline void set_migration_target_nodes(void) {} +#endif +#else + +static inline void set_migration_target_nodes(void) {} static inline void putback_movable_pages(struct list_head *l) {} static inline int migrate_pages(struct list_head *l, new_page_t new, -- cgit v1.2.3 From 6eada26ffc80bfe1f2db088be0c44ec82b5cd3dc Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 22 Mar 2022 14:47:46 -0700 Subject: mm: remove usercopy_warn() Users of usercopy_warn() were removed by commit 53944f171a89 ("mm: remove HARDENED_USERCOPY_FALLBACK") Remove it. Link: https://lkml.kernel.org/r/5f26643fc70b05f8455b60b99c30c17d635fa640.1644231910.git.christophe.leroy@csgroup.eu Signed-off-by: Christophe Leroy Reviewed-by: Miaohe Lin Reviewed-by: Stephen Kitt Reviewed-by: Muchun Song Cc: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index ac0394087f7d..bca27b4e5eb2 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -401,8 +401,6 @@ static inline void user_access_restore(unsigned long flags) { } #endif #ifdef CONFIG_HARDENED_USERCOPY -void usercopy_warn(const char *name, const char *detail, bool to_user, - unsigned long offset, unsigned long len); void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len); -- cgit v1.2.3 From ad7489d5262d2aa775b5e5a1782793925fa90065 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 22 Mar 2022 14:47:49 -0700 Subject: mm: uninline copy_overflow() While building a small config with CONFIG_CC_OPTIMISE_FOR_SIZE, I ended up with more than 50 times the following function in vmlinux because GCC doesn't honor the 'inline' keyword: c00243bc : c00243bc: 94 21 ff f0 stwu r1,-16(r1) c00243c0: 7c 85 23 78 mr r5,r4 c00243c4: 7c 64 1b 78 mr r4,r3 c00243c8: 3c 60 c0 62 lis r3,-16286 c00243cc: 7c 08 02 a6 mflr r0 c00243d0: 38 63 5e e5 addi r3,r3,24293 c00243d4: 90 01 00 14 stw r0,20(r1) c00243d8: 4b ff 82 45 bl c001c61c <__warn_printk> c00243dc: 0f e0 00 00 twui r0,0 c00243e0: 80 01 00 14 lwz r0,20(r1) c00243e4: 38 21 00 10 addi r1,r1,16 c00243e8: 7c 08 03 a6 mtlr r0 c00243ec: 4e 80 00 20 blr With -Winline, GCC tells: /include/linux/thread_info.h:212:20: warning: inlining failed in call to 'copy_overflow': call is unlikely and code size would grow [-Winline] copy_overflow() is a non conditional warning called by check_copy_size() on an error path. check_copy_size() have to remain inlined in order to benefit from constant folding, but copy_overflow() is not worth inlining. Uninline the warning when CONFIG_BUG is selected. When CONFIG_BUG is not selected, WARN() does nothing so skip it. This reduces the size of vmlinux by almost 4kbytes. Link: https://lkml.kernel.org/r/e1723b9cfa924bcefcd41f69d0025b38e4c9364e.1644819985.git.christophe.leroy@csgroup.eu Signed-off-by: Christophe Leroy Cc: David Laight Cc: Anshuman Khandual Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/thread_info.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 73a6f34b3847..9f392ec76f2b 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -209,9 +209,12 @@ __bad_copy_from(void); extern void __compiletime_error("copy destination size is too small") __bad_copy_to(void); +void __copy_overflow(int size, unsigned long count); + static inline void copy_overflow(int size, unsigned long count) { - WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); + if (IS_ENABLED(CONFIG_BUG)) + __copy_overflow(size, count); } static __always_inline __must_check bool -- cgit v1.2.3 From d7ca25c53e25a9a628aaa19b5a031f115d8c353d Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Tue, 22 Mar 2022 14:47:58 -0700 Subject: highmem: document kunmap_local() Some users of kmap() add an offset to the kmap() address to be used during the mapping. When converting to kmap_local_page() the base address does not need to be stored because any address within the page can be used in kunmap_local(). However, this was not clear from the documentation and cause some questions.[1] Document that any address in the page can be used in kunmap_local() to clarify this for future users. [1] https://lore.kernel.org/lkml/20211213154543.GM3538886@iweiny-DESK2.sc.intel.com/ [ira.weiny@intel.com: updates per Christoph] Link: https://lkml.kernel.org/r/20220124182138.816693-1-ira.weiny@intel.com Link: https://lkml.kernel.org/r/20220124013045.806718-1-ira.weiny@intel.com Signed-off-by: Ira Weiny Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/highmem-internal.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index 0a0b2b09b1b8..a77be5630209 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -246,6 +246,16 @@ do { \ __kunmap_atomic(__addr); \ } while (0) +/** + * kunmap_local - Unmap a page mapped via kmap_local_page(). + * @__addr: An address within the page mapped + * + * @__addr can be any address within the mapped page. Commonly it is the + * address return from kmap_local_page(), but it can also include offsets. + * + * Unmapping should be done in the reverse order of the mapping. See + * kmap_local_page() for details. + */ #define kunmap_local(__addr) \ do { \ BUILD_BUG_ON(__same_type((__addr), struct page *)); \ -- cgit v1.2.3 From 436428255d5981e49ff015fc8e398ecf2ba10c24 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 22 Mar 2022 14:48:37 -0700 Subject: mm/damon/core: move damon_set_targets() into dbgfs damon_set_targets() function is defined in the core for general use cases, but called from only dbgfs. Also, because the function is for general use cases, dbgfs does additional handling of pid type target id case. To make the situation simpler, this commit moves the function into dbgfs and makes it to do the pid type case handling on its own. Link: https://lkml.kernel.org/r/20211230100723.2238-4-sj@kernel.org Signed-off-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/damon.h b/include/linux/damon.h index 5e1e3a128b77..bd021af5db3d 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -484,8 +484,6 @@ unsigned int damon_nr_regions(struct damon_target *t); struct damon_ctx *damon_new_ctx(void); void damon_destroy_ctx(struct damon_ctx *ctx); -int damon_set_targets(struct damon_ctx *ctx, - unsigned long *ids, ssize_t nr_ids); int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, unsigned long aggr_int, unsigned long primitive_upd_int, unsigned long min_nr_reg, unsigned long max_nr_reg); -- cgit v1.2.3 From 1971bd630452e943380429336a851c55b027eed1 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 22 Mar 2022 14:48:40 -0700 Subject: mm/damon: remove the target id concept DAMON asks each monitoring target ('struct damon_target') to have one 'unsigned long' integer called 'id', which should be unique among the targets of same monitoring context. Meaning of it is, however, totally up to the monitoring primitives that registered to the monitoring context. For example, the virtual address spaces monitoring primitives treats the id as a 'struct pid' pointer. This makes the code flexible, but ugly, not well-documented, and type-unsafe[1]. Also, identification of each target can be done via its index. For the reason, this commit removes the concept and uses clear type definition. For now, only 'struct pid' pointer is used for the virtual address spaces monitoring. If DAMON is extended in future so that we need to put another identifier field in the struct, we will use a union for such primitives-dependent fields and document which primitives are using which type. [1] https://lore.kernel.org/linux-mm/20211013154535.4aaeaaf9d0182922e405dd1e@linux-foundation.org/ Link: https://lkml.kernel.org/r/20211230100723.2238-5-sj@kernel.org Signed-off-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/damon.h b/include/linux/damon.h index bd021af5db3d..7c1d915b3587 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -60,19 +60,18 @@ struct damon_region { /** * struct damon_target - Represents a monitoring target. - * @id: Unique identifier for this target. + * @pid: The PID of the virtual address space to monitor. * @nr_regions: Number of monitoring target regions of this target. * @regions_list: Head of the monitoring target regions of this target. * @list: List head for siblings. * * Each monitoring context could have multiple targets. For example, a context * for virtual memory address spaces could have multiple target processes. The - * @id of each target should be unique among the targets of the context. For - * example, in the virtual address monitoring context, it could be a pidfd or - * an address of an mm_struct. + * @pid should be set for appropriate address space monitoring primitives + * including the virtual address spaces monitoring primitives. */ struct damon_target { - unsigned long id; + struct pid *pid; unsigned int nr_regions; struct list_head regions_list; struct list_head list; @@ -475,7 +474,7 @@ struct damos *damon_new_scheme( void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); void damon_destroy_scheme(struct damos *s); -struct damon_target *damon_new_target(unsigned long id); +struct damon_target *damon_new_target(void); void damon_add_target(struct damon_ctx *ctx, struct damon_target *t); bool damon_targets_empty(struct damon_ctx *ctx); void damon_free_target(struct damon_target *t); -- cgit v1.2.3 From f7d911c39cbbb88d625216a0cfd0517a3047c46e Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 22 Mar 2022 14:48:46 -0700 Subject: mm/damon: rename damon_primitives to damon_operations Patch series "Allow DAMON user code independent of monitoring primitives". In-kernel DAMON user code is required to configure the monitoring context (struct damon_ctx) with proper monitoring primitives (struct damon_primitive). This makes the user code dependent to all supporting monitoring primitives. For example, DAMON debugfs interface depends on both DAMON_VADDR and DAMON_PADDR, though some users have interest in only one use case. As more monitoring primitives are introduced, the problem will be bigger. To minimize such unnecessary dependency, this patchset makes monitoring primitives can be registered by the implemnting code and later dynamically searched and selected by the user code. In addition to that, this patchset renames monitoring primitives to monitoring operations, which is more easy to intuitively understand what it means and how it would be structed. This patch (of 8): DAMON has a set of callback functions called monitoring primitives and let it can be configured with various implementations for easy extension for different address spaces and usages. However, the word 'primitive' is not so explicit. Meanwhile, many other structs resembles similar purpose calls themselves 'operations'. To make the code easier to be understood, this commit renames 'damon_primitives' to 'damon_operations' before it is too late to rename. Link: https://lkml.kernel.org/r/20220215184603.1479-1-sj@kernel.org Link: https://lkml.kernel.org/r/20220215184603.1479-2-sj@kernel.org Signed-off-by: SeongJae Park Cc: Xin Hao Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 48 ++++++++++++++++++++++++------------------------ 1 file changed, 24 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/linux/damon.h b/include/linux/damon.h index 7c1d915b3587..00baeb42c18e 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -67,8 +67,8 @@ struct damon_region { * * Each monitoring context could have multiple targets. For example, a context * for virtual memory address spaces could have multiple target processes. The - * @pid should be set for appropriate address space monitoring primitives - * including the virtual address spaces monitoring primitives. + * @pid should be set for appropriate &struct damon_operations including the + * virtual address spaces monitoring operations. */ struct damon_target { struct pid *pid; @@ -120,9 +120,9 @@ enum damos_action { * uses smaller one as the effective quota. * * For selecting regions within the quota, DAMON prioritizes current scheme's - * target memory regions using the &struct damon_primitive->get_scheme_score. + * target memory regions using the &struct damon_operations->get_scheme_score. * You could customize the prioritization logic by setting &weight_sz, - * &weight_nr_accesses, and &weight_age, because monitoring primitives are + * &weight_nr_accesses, and &weight_age, because monitoring operations are * encouraged to respect those. */ struct damos_quota { @@ -256,10 +256,10 @@ struct damos { struct damon_ctx; /** - * struct damon_primitive - Monitoring primitives for given use cases. + * struct damon_operations - Monitoring operations for given use cases. * - * @init: Initialize primitive-internal data structures. - * @update: Update primitive-internal data structures. + * @init: Initialize operations-related data structures. + * @update: Update operations-related data structures. * @prepare_access_checks: Prepare next access check of target regions. * @check_accesses: Check the accesses to target regions. * @reset_aggregated: Reset aggregated accesses monitoring results. @@ -269,18 +269,18 @@ struct damon_ctx; * @cleanup: Clean up the context. * * DAMON can be extended for various address spaces and usages. For this, - * users should register the low level primitives for their target address - * space and usecase via the &damon_ctx.primitive. Then, the monitoring thread + * users should register the low level operations for their target address + * space and usecase via the &damon_ctx.ops. Then, the monitoring thread * (&damon_ctx.kdamond) calls @init and @prepare_access_checks before starting - * the monitoring, @update after each &damon_ctx.primitive_update_interval, and + * the monitoring, @update after each &damon_ctx.ops_update_interval, and * @check_accesses, @target_valid and @prepare_access_checks after each * &damon_ctx.sample_interval. Finally, @reset_aggregated is called after each * &damon_ctx.aggr_interval. * - * @init should initialize primitive-internal data structures. For example, + * @init should initialize operations-related data structures. For example, * this could be used to construct proper monitoring target regions and link * those to @damon_ctx.adaptive_targets. - * @update should update the primitive-internal data structures. For example, + * @update should update the operations-related data structures. For example, * this could be used to update monitoring target regions for current status. * @prepare_access_checks should manipulate the monitoring regions to be * prepared for the next access check. @@ -300,7 +300,7 @@ struct damon_ctx; * monitoring. * @cleanup is called from @kdamond just before its termination. */ -struct damon_primitive { +struct damon_operations { void (*init)(struct damon_ctx *context); void (*update)(struct damon_ctx *context); void (*prepare_access_checks)(struct damon_ctx *context); @@ -354,15 +354,15 @@ struct damon_callback { * * @sample_interval: The time between access samplings. * @aggr_interval: The time between monitor results aggregations. - * @primitive_update_interval: The time between monitoring primitive updates. + * @ops_update_interval: The time between monitoring operations updates. * * For each @sample_interval, DAMON checks whether each region is accessed or * not. It aggregates and keeps the access information (number of accesses to * each region) for @aggr_interval time. DAMON also checks whether the target * memory regions need update (e.g., by ``mmap()`` calls from the application, * in case of virtual memory monitoring) and applies the changes for each - * @primitive_update_interval. All time intervals are in micro-seconds. - * Please refer to &struct damon_primitive and &struct damon_callback for more + * @ops_update_interval. All time intervals are in micro-seconds. + * Please refer to &struct damon_operations and &struct damon_callback for more * detail. * * @kdamond: Kernel thread who does the monitoring. @@ -374,7 +374,7 @@ struct damon_callback { * * Once started, the monitoring thread runs until explicitly required to be * terminated or every monitoring target is invalid. The validity of the - * targets is checked via the &damon_primitive.target_valid of @primitive. The + * targets is checked via the &damon_operations.target_valid of @ops. The * termination can also be explicitly requested by writing non-zero to * @kdamond_stop. The thread sets @kdamond to NULL when it terminates. * Therefore, users can know whether the monitoring is ongoing or terminated by @@ -384,7 +384,7 @@ struct damon_callback { * Note that the monitoring thread protects only @kdamond and @kdamond_stop via * @kdamond_lock. Accesses to other fields must be protected by themselves. * - * @primitive: Set of monitoring primitives for given use cases. + * @ops: Set of monitoring operations for given use cases. * @callback: Set of callbacks for monitoring events notifications. * * @min_nr_regions: The minimum number of adaptive monitoring regions. @@ -395,17 +395,17 @@ struct damon_callback { struct damon_ctx { unsigned long sample_interval; unsigned long aggr_interval; - unsigned long primitive_update_interval; + unsigned long ops_update_interval; /* private: internal use only */ struct timespec64 last_aggregation; - struct timespec64 last_primitive_update; + struct timespec64 last_ops_update; /* public: */ struct task_struct *kdamond; struct mutex kdamond_lock; - struct damon_primitive primitive; + struct damon_operations ops; struct damon_callback callback; unsigned long min_nr_regions; @@ -484,7 +484,7 @@ unsigned int damon_nr_regions(struct damon_target *t); struct damon_ctx *damon_new_ctx(void); void damon_destroy_ctx(struct damon_ctx *ctx); int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, - unsigned long aggr_int, unsigned long primitive_upd_int, + unsigned long aggr_int, unsigned long ops_upd_int, unsigned long min_nr_reg, unsigned long max_nr_reg); int damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes, ssize_t nr_schemes); @@ -497,12 +497,12 @@ int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); #ifdef CONFIG_DAMON_VADDR bool damon_va_target_valid(void *t); -void damon_va_set_primitives(struct damon_ctx *ctx); +void damon_va_set_operations(struct damon_ctx *ctx); #endif /* CONFIG_DAMON_VADDR */ #ifdef CONFIG_DAMON_PADDR bool damon_pa_target_valid(void *t); -void damon_pa_set_primitives(struct damon_ctx *ctx); +void damon_pa_set_operations(struct damon_ctx *ctx); #endif /* CONFIG_DAMON_PADDR */ #endif /* _DAMON_H */ -- cgit v1.2.3 From 9f7b053a0f6121f89e00d1688bfca0bf278caa25 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 22 Mar 2022 14:48:49 -0700 Subject: mm/damon: let monitoring operations can be registered and selected In-kernel DAMON user code like DAMON debugfs interface should set 'struct damon_operations' of its 'struct damon_ctx' on its own. Therefore, the client code should depend on all supporting monitoring operations implementations that it could use. For example, DAMON debugfs interface depends on both vaddr and paddr, while some of the users are not always interested in both. To minimize such unnecessary dependencies, this commit makes the monitoring operations can be registered by implementing code and then dynamically selected by the user code without build-time dependency. Link: https://lkml.kernel.org/r/20220215184603.1479-3-sj@kernel.org Signed-off-by: SeongJae Park Cc: David Rientjes Cc: Xin Hao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/damon.h b/include/linux/damon.h index 00baeb42c18e..076da277b249 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -253,11 +253,24 @@ struct damos { struct list_head list; }; +/** + * enum damon_ops_id - Identifier for each monitoring operations implementation + * + * @DAMON_OPS_VADDR: Monitoring operations for virtual address spaces + * @DAMON_OPS_PADDR: Monitoring operations for the physical address space + */ +enum damon_ops_id { + DAMON_OPS_VADDR, + DAMON_OPS_PADDR, + NR_DAMON_OPS, +}; + struct damon_ctx; /** * struct damon_operations - Monitoring operations for given use cases. * + * @id: Identifier of this operations set. * @init: Initialize operations-related data structures. * @update: Update operations-related data structures. * @prepare_access_checks: Prepare next access check of target regions. @@ -277,6 +290,8 @@ struct damon_ctx; * &damon_ctx.sample_interval. Finally, @reset_aggregated is called after each * &damon_ctx.aggr_interval. * + * Each &struct damon_operations instance having valid @id can be registered + * via damon_register_ops() and selected by damon_select_ops() later. * @init should initialize operations-related data structures. For example, * this could be used to construct proper monitoring target regions and link * those to @damon_ctx.adaptive_targets. @@ -301,6 +316,7 @@ struct damon_ctx; * @cleanup is called from @kdamond just before its termination. */ struct damon_operations { + enum damon_ops_id id; void (*init)(struct damon_ctx *context); void (*update)(struct damon_ctx *context); void (*prepare_access_checks)(struct damon_ctx *context); @@ -489,6 +505,8 @@ int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, int damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes, ssize_t nr_schemes); int damon_nr_running_ctxs(void); +int damon_register_ops(struct damon_operations *ops); +int damon_select_ops(struct damon_ctx *ctx, enum damon_ops_id id); int damon_start(struct damon_ctx **ctxs, int nr_ctxs); int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); -- cgit v1.2.3 From 851040566a008f7248cb754d5bb9a3e34f2effe5 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 22 Mar 2022 14:49:07 -0700 Subject: mm/damon/paddr,vaddr: remove damon_{p,v}a_{target_valid,set_operations}() Because DAMON debugfs interface and DAMON-based proactive reclaim are now using monitoring operations via registration mechanism, damon_{p,v}a_{target_valid,set_operations}() functions have no user. This commit clean them up. Link: https://lkml.kernel.org/r/20220215184603.1479-9-sj@kernel.org Signed-off-by: SeongJae Park Cc: David Rientjes Cc: Xin Hao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/linux/damon.h b/include/linux/damon.h index 076da277b249..49c4a11ecf20 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -513,14 +513,4 @@ int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); #endif /* CONFIG_DAMON */ -#ifdef CONFIG_DAMON_VADDR -bool damon_va_target_valid(void *t); -void damon_va_set_operations(struct damon_ctx *ctx); -#endif /* CONFIG_DAMON_VADDR */ - -#ifdef CONFIG_DAMON_PADDR -bool damon_pa_target_valid(void *t); -void damon_pa_set_operations(struct damon_ctx *ctx); -#endif /* CONFIG_DAMON_PADDR */ - #endif /* _DAMON_H */ -- cgit v1.2.3 From 8b9b0d335a345cbc590baa5aa8aa02c467c1e4e8 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 22 Mar 2022 14:49:21 -0700 Subject: mm/damon/core: allow non-exclusive DAMON start/stop MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "Introduce DAMON sysfs interface", v3. Introduction ============ DAMON's debugfs-based user interface (DAMON_DBGFS) served very well, so far. However, it unnecessarily depends on debugfs, while DAMON is not aimed to be used for only debugging. Also, the interface receives multiple values via one file. For example, schemes file receives 18 values. As a result, it is inefficient, hard to be used, and difficult to be extended. Especially, keeping backward compatibility of user space tools is getting only challenging. It would be better to implement another reliable and flexible interface and deprecate DAMON_DBGFS in long term. For the reason, this patchset introduces a sysfs-based new user interface of DAMON. The idea of the new interface is, using directory hierarchies and having one dedicated file for each value. For a short example, users can do the virtual address monitoring via the interface as below: # cd /sys/kernel/mm/damon/admin/ # echo 1 > kdamonds/nr_kdamonds # echo 1 > kdamonds/0/contexts/nr_contexts # echo vaddr > kdamonds/0/contexts/0/operations # echo 1 > kdamonds/0/contexts/0/targets/nr_targets # echo $(pidof ) > kdamonds/0/contexts/0/targets/0/pid_target # echo on > kdamonds/0/state A brief representation of the files hierarchy of DAMON sysfs interface is as below. Childs are represented with indentation, directories are having '/' suffix, and files in each directory are separated by comma. /sys/kernel/mm/damon/admin │ kdamonds/nr_kdamonds │ │ 0/state,pid │ │ │ contexts/nr_contexts │ │ │ │ 0/operations │ │ │ │ │ monitoring_attrs/ │ │ │ │ │ │ intervals/sample_us,aggr_us,update_us │ │ │ │ │ │ nr_regions/min,max │ │ │ │ │ targets/nr_targets │ │ │ │ │ │ 0/pid_target │ │ │ │ │ │ │ regions/nr_regions │ │ │ │ │ │ │ │ 0/start,end │ │ │ │ │ │ │ │ ... │ │ │ │ │ │ ... │ │ │ │ │ schemes/nr_schemes │ │ │ │ │ │ 0/action │ │ │ │ │ │ │ access_pattern/ │ │ │ │ │ │ │ │ sz/min,max │ │ │ │ │ │ │ │ nr_accesses/min,max │ │ │ │ │ │ │ │ age/min,max │ │ │ │ │ │ │ quotas/ms,bytes,reset_interval_ms │ │ │ │ │ │ │ │ weights/sz_permil,nr_accesses_permil,age_permil │ │ │ │ │ │ │ watermarks/metric,interval_us,high,mid,low │ │ │ │ │ │ │ stats/nr_tried,sz_tried,nr_applied,sz_applied,qt_exceeds │ │ │ │ │ │ ... │ │ │ │ ... │ │ ... Detailed usage of the files will be described in the final Documentation patch of this patchset. Main Difference Between DAMON_DBGFS and DAMON_SYSFS --------------------------------------------------- At the moment, DAMON_DBGFS and DAMON_SYSFS provides same features. One important difference between them is their exclusiveness. DAMON_DBGFS works in an exclusive manner, so that no DAMON worker thread (kdamond) in the system can run concurrently and interfere somehow. For the reason, DAMON_DBGFS asks users to construct all monitoring contexts and start them at once. It's not a big problem but makes the operation a little bit complex and unflexible. For more flexible usage, DAMON_SYSFS moves the responsibility of preventing any possible interference to the admins and work in a non-exclusive manner. That is, users can configure and start contexts one by one. Note that DAMON respects both exclusive groups and non-exclusive groups of contexts, in a manner similar to that of reader-writer locks. That is, if any exclusive monitoring contexts (e.g., contexts that started via DAMON_DBGFS) are running, DAMON_SYSFS does not start new contexts, and vice versa. Future Plan of DAMON_DBGFS Deprecation ====================================== Once this patchset is merged, DAMON_DBGFS development will be frozen. That is, we will maintain it to work as is now so that no users will be break. But, it will not be extended to provide any new feature of DAMON. The support will be continued only until next LTS release. After that, we will drop DAMON_DBGFS. User-space Tooling Compatibility -------------------------------- As DAMON_SYSFS provides all features of DAMON_DBGFS, all user space tooling can move to DAMON_SYSFS. As we will continue supporting DAMON_DBGFS until next LTS kernel release, user space tools would have enough time to move to DAMON_SYSFS. The official user space tool, damo[1], is already supporting both DAMON_SYSFS and DAMON_DBGFS. Both correctness tests[2] and performance tests[3] of DAMON using DAMON_SYSFS also passed. [1] https://github.com/awslabs/damo [2] https://github.com/awslabs/damon-tests/tree/master/corr [3] https://github.com/awslabs/damon-tests/tree/master/perf Sequence of Patches =================== First two patches (patches 1-2) make core changes for DAMON_SYSFS. The first one (patch 1) allows non-exclusive DAMON contexts so that DAMON_SYSFS can work in non-exclusive mode, while the second one (patch 2) adds size of DAMON enum types so that DAMON API users can safely iterate the enums. Third patch (patch 3) implements basic sysfs stub for virtual address spaces monitoring. Note that this implements only sysfs files and DAMON is not linked. Fourth patch (patch 4) links the DAMON_SYSFS to DAMON so that users can control DAMON using the sysfs files. Following six patches (patches 5-10) implements other DAMON features that DAMON_DBGFS supports one by one (physical address space monitoring, DAMON-based operation schemes, schemes quotas, schemes prioritization weights, schemes watermarks, and schemes stats). Following patch (patch 11) adds a simple selftest for DAMON_SYSFS, and the final one (patch 12) documents DAMON_SYSFS. This patch (of 13): To avoid interference between DAMON contexts monitoring overlapping memory regions, damon_start() works in an exclusive manner. That is, damon_start() does nothing bug fails if any context that started by another instance of the function is still running. This makes its usage a little bit restrictive. However, admins could aware each DAMON usage and address such interferences on their own in some cases. This commit hence implements non-exclusive mode of the function and allows the callers to select the mode. Note that the exclusive groups and non-exclusive groups of contexts will respect each other in a manner similar to that of reader-writer locks. Therefore, this commit will not cause any behavioral change to the exclusive groups. Link: https://lkml.kernel.org/r/20220228081314.5770-1-sj@kernel.org Link: https://lkml.kernel.org/r/20220228081314.5770-2-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Corbet Cc: Shuah Khan Cc: David Rientjes Cc: Xin Hao Cc: Greg Kroah-Hartman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/damon.h b/include/linux/damon.h index 49c4a11ecf20..f8e99e47d747 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -508,7 +508,7 @@ int damon_nr_running_ctxs(void); int damon_register_ops(struct damon_operations *ops); int damon_select_ops(struct damon_ctx *ctx, enum damon_ops_id id); -int damon_start(struct damon_ctx **ctxs, int nr_ctxs); +int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive); int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); #endif /* CONFIG_DAMON */ -- cgit v1.2.3 From 5257f36ec289d544532f2889cbed11abbb06cf0c Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 22 Mar 2022 14:49:24 -0700 Subject: mm/damon/core: add number of each enum type values This commit declares the number of legal values for each DAMON enum types to make traversals of such DAMON enum types easy and safe. Link: https://lkml.kernel.org/r/20220228081314.5770-3-sj@kernel.org Signed-off-by: SeongJae Park Cc: David Rientjes Cc: Greg Kroah-Hartman Cc: Jonathan Corbet Cc: Shuah Khan Cc: Xin Hao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/damon.h b/include/linux/damon.h index f8e99e47d747..f23cbfa4248d 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -87,6 +87,7 @@ struct damon_target { * @DAMOS_HUGEPAGE: Call ``madvise()`` for the region with MADV_HUGEPAGE. * @DAMOS_NOHUGEPAGE: Call ``madvise()`` for the region with MADV_NOHUGEPAGE. * @DAMOS_STAT: Do nothing but count the stat. + * @NR_DAMOS_ACTIONS: Total number of DAMOS actions */ enum damos_action { DAMOS_WILLNEED, @@ -95,6 +96,7 @@ enum damos_action { DAMOS_HUGEPAGE, DAMOS_NOHUGEPAGE, DAMOS_STAT, /* Do nothing but only record the stat */ + NR_DAMOS_ACTIONS, }; /** @@ -157,10 +159,12 @@ struct damos_quota { * * @DAMOS_WMARK_NONE: Ignore the watermarks of the given scheme. * @DAMOS_WMARK_FREE_MEM_RATE: Free memory rate of the system in [0,1000]. + * @NR_DAMOS_WMARK_METRICS: Total number of DAMOS watermark metrics */ enum damos_wmark_metric { DAMOS_WMARK_NONE, DAMOS_WMARK_FREE_MEM_RATE, + NR_DAMOS_WMARK_METRICS, }; /** -- cgit v1.2.3 From 2af7e566a8616c278e1d7287ce86cd3900bed943 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Tue, 22 Mar 2022 10:22:24 -0700 Subject: net/mlx5e: Fix build warning, detected write beyond size of field When merged with Linus tree, the cited patch below will cause the following build warning: In function 'fortify_memset_chk', inlined from 'mlx5e_xmit_xdp_frame' at drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c:438:3: include/linux/fortify-string.h:242:25: error: call to '__write_overflow_field' declared with attribute warning: detected write beyond size of field (1st parameter); maybe use struct_group()? [-Werror=attribute-warning] 242 | __write_overflow_field(p_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Fix that by grouping the fields to memeset in struct_group() to avoid the false alarm. Fixes: 9ded70fa1d81 ("net/mlx5e: Don't prefill WQEs in XDP SQ in the multi buffer mode") Reported-by: Stephen Rothwell Suggested-by: Stephen Rothwell Signed-off-by: Saeed Mahameed Link: https://lore.kernel.org/r/20220322172224.31849-1-saeed@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/mlx5/qp.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 61e48d459b23..8bda3ba5b109 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -202,6 +202,9 @@ struct mlx5_wqe_fmr_seg { struct mlx5_wqe_ctrl_seg { __be32 opmod_idx_opcode; __be32 qpn_ds; + + struct_group(trailer, + u8 signature; u8 rsvd[2]; u8 fm_ce_se; @@ -211,6 +214,8 @@ struct mlx5_wqe_ctrl_seg { __be32 umr_mkey; __be32 tis_tir_num; }; + + ); /* end of trailer group */ }; #define MLX5_WQE_CTRL_DS_MASK 0x3f -- cgit v1.2.3 From d578c770c85233af592e54537f93f3831bde7e9a Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 23 Mar 2022 09:13:08 +0800 Subject: block: avoid calling blkg_free() in atomic context blkg_free() can currently be called in atomic context, either spin lock is held, or run in rcu callback. Meantime either request queue's release handler or ->pd_free_fn can sleep. Fix the issue by scheduling a work function for freeing blkcg_gq the instance. [ 148.553894] BUG: sleeping function called from invalid context at block/blk-sysfs.c:767 [ 148.557381] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 0, name: swapper/13 [ 148.560741] preempt_count: 101, expected: 0 [ 148.562577] RCU nest depth: 0, expected: 0 [ 148.564379] 1 lock held by swapper/13/0: [ 148.566127] #0: ffffffff82615f80 (rcu_callback){....}-{0:0}, at: rcu_lock_acquire+0x0/0x1b [ 148.569640] Preemption disabled at: [ 148.569642] [] ___slab_alloc+0x554/0x661 [ 148.573559] CPU: 13 PID: 0 Comm: swapper/13 Kdump: loaded Not tainted 5.17.0_up+ #110 [ 148.576834] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.14.0-1.fc33 04/01/2014 [ 148.579768] Call Trace: [ 148.580567] [ 148.581262] dump_stack_lvl+0x56/0x7c [ 148.582367] ? ___slab_alloc+0x554/0x661 [ 148.583526] __might_resched+0x1af/0x1c8 [ 148.584678] blk_release_queue+0x24/0x109 [ 148.585861] kobject_cleanup+0xc9/0xfe [ 148.586979] blkg_free+0x46/0x63 [ 148.587962] rcu_do_batch+0x1c5/0x3db [ 148.589057] rcu_core+0x14a/0x184 [ 148.590065] __do_softirq+0x14d/0x2c7 [ 148.591167] __irq_exit_rcu+0x7a/0xd4 [ 148.592264] sysvec_apic_timer_interrupt+0x82/0xa5 [ 148.593649] [ 148.594354] [ 148.595058] asm_sysvec_apic_timer_interrupt+0x12/0x20 Cc: Tejun Heo Fixes: 0a9a25ca7843 ("block: let blkcg_gq grab request queue's refcnt") Reported-by: Christoph Hellwig Link: https://lore.kernel.org/linux-block/20220322093322.GA27283@lst.de/ Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20220323011308.2010380-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index f2ad8ed8f777..652cd05b0924 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -95,7 +95,10 @@ struct blkcg_gq { spinlock_t async_bio_lock; struct bio_list async_bios; - struct work_struct async_bio_work; + union { + struct work_struct async_bio_work; + struct work_struct free_work; + }; atomic_t use_delay; atomic64_t delay_nsec; -- cgit v1.2.3 From 553f685ebf9689e701ec6b95c0ca3595cf1a743f Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Fri, 11 Mar 2022 20:55:18 +0800 Subject: mfd: db8500-prcmu: Remove unused inline function commit b0e846248de5 ("mfd: db8500-prcmu: Remove dead code for a non-existing config") left behind this, remove it. Signed-off-by: YueHaibing Reviewed-by: Linus Walleij Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20220311125518.31064-1-yuehaibing@huawei.com --- include/linux/mfd/dbx500-prcmu.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h index 2a255362b5ac..e7a7e70fdb38 100644 --- a/include/linux/mfd/dbx500-prcmu.h +++ b/include/linux/mfd/dbx500-prcmu.h @@ -561,10 +561,6 @@ static inline unsigned long prcmu_qos_get_cpufreq_opp_delay(void) return 0; } -static inline void prcmu_qos_set_cpufreq_opp_delay(unsigned long n) {} - -static inline void prcmu_qos_force_opp(int prcmu_qos_class, s32 i) {} - static inline int prcmu_qos_requirement(int prcmu_qos_class) { return 0; -- cgit v1.2.3 From 30d024b5058e0433914022f87d917a97a9527632 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 23 Mar 2022 15:35:10 +1200 Subject: cacheflush.h: Add forward declaration for struct folio The struct folio is not declared in cacheflush.h so we need to provide a forward declaration as otherwise users of this header file may get warnings. Reported-by: Guenter Roeck Fixes: 522a0032af00 ("Add linux/cacheflush.h") Signed-off-by: Herbert Xu Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Linus Torvalds --- include/linux/cacheflush.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/cacheflush.h b/include/linux/cacheflush.h index fef8b607f97e..a6189d21f2ba 100644 --- a/include/linux/cacheflush.h +++ b/include/linux/cacheflush.h @@ -4,6 +4,8 @@ #include +struct folio; + #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE #ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO void flush_dcache_folio(struct folio *folio); -- cgit v1.2.3 From 054d5575cd6ed2792611a7cbb8c88663cc873780 Mon Sep 17 00:00:00 2001 From: Louis Peens Date: Wed, 23 Mar 2022 11:25:06 +0200 Subject: net/sched: fix incorrect vlan_push_eth dest field Seems like a potential copy-paste bug slipped in here, the second memcpy should of course be populating src and not dest. Fixes: ab95465cde23 ("net/sched: add vlan push_eth and pop_eth action to the hardware IR") Signed-off-by: Louis Peens Link: https://lore.kernel.org/r/20220323092506.21639-1-louis.peens@corigine.com Signed-off-by: Jakub Kicinski --- include/net/tc_act/tc_vlan.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h index a97600f742de..904eddfc1826 100644 --- a/include/net/tc_act/tc_vlan.h +++ b/include/net/tc_act/tc_vlan.h @@ -84,7 +84,7 @@ static inline void tcf_vlan_push_eth(unsigned char *src, unsigned char *dest, { rcu_read_lock(); memcpy(dest, rcu_dereference(to_vlan(a)->vlan_p)->tcfv_push_dst, ETH_ALEN); - memcpy(dest, rcu_dereference(to_vlan(a)->vlan_p)->tcfv_push_src, ETH_ALEN); + memcpy(src, rcu_dereference(to_vlan(a)->vlan_p)->tcfv_push_src, ETH_ALEN); rcu_read_unlock(); } -- cgit v1.2.3 From d91612d7f01aca454469976d25db761c5085ae4d Mon Sep 17 00:00:00 2001 From: Samuel Holland Date: Wed, 2 Feb 2022 20:17:35 -0600 Subject: clk: sunxi-ng: Add support for the sun6i RTC clocks The RTC power domain in sun6i and newer SoCs manages the 16 MHz RC oscillator (called "IOSC" or "osc16M") and the optional 32 kHz crystal oscillator (called "LOSC" or "osc32k"). Starting with the H6, this power domain also handles the 24 MHz DCXO (called variously "HOSC", "dcxo24M", or "osc24M") as well. The H6 also adds a calibration circuit for IOSC. Later SoCs introduce further variations on the design: - H616 adds an additional mux for the 32 kHz fanout source. - R329 adds an additional mux for the RTC timekeeping clock, a clock for the SPI bus between power domains inside the RTC, and removes the IOSC calibration functionality. Take advantage of the CCU framework to handle this increased complexity. This driver is intended to be a drop-in replacement for the existing RTC clock provider. So some runtime adjustment of the clock parents is needed, both to handle hardware differences, and to support the old binding which omitted some of the input clocks. Signed-off-by: Samuel Holland Acked-by: Stephen Boyd Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20220203021736.13434-6-samuel@sholland.org --- include/linux/clk/sunxi-ng.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/clk/sunxi-ng.h b/include/linux/clk/sunxi-ng.h index cf32123b39f5..57c8ec44ab4e 100644 --- a/include/linux/clk/sunxi-ng.h +++ b/include/linux/clk/sunxi-ng.h @@ -9,4 +9,6 @@ int sunxi_ccu_set_mmc_timing_mode(struct clk *clk, bool new_mode); int sunxi_ccu_get_mmc_timing_mode(struct clk *clk); +int sun6i_rtc_ccu_probe(struct device *dev, void __iomem *reg); + #endif -- cgit v1.2.3 From 5c0a04a663019dd14cb000d370cff0ced6df7ef1 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Wed, 9 Mar 2022 17:22:33 +0100 Subject: rtc: ds1685: drop no_irq No platforms are currently setting no_irq. Anyway, letting platform_get_irq fail is fine as this means that there is no IRQ. In that case, clear RTC_FEATURE_ALARM so the core knows there are no alarms. Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20220309162301.61679-2-alexandre.belloni@bootlin.com --- include/linux/rtc/ds1685.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/rtc/ds1685.h b/include/linux/rtc/ds1685.h index 67ee9d20cc5a..5a41c3bbcbe3 100644 --- a/include/linux/rtc/ds1685.h +++ b/include/linux/rtc/ds1685.h @@ -46,7 +46,6 @@ struct ds1685_priv { u32 regstep; int irq_num; bool bcd_mode; - bool no_irq; u8 (*read)(struct ds1685_priv *, int); void (*write)(struct ds1685_priv *, int, u8); void (*prepare_poweroff)(void); -- cgit v1.2.3 From e99653afeb9585350644c5ae4b0ca987cbe8d053 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Wed, 9 Mar 2022 17:22:53 +0100 Subject: rtc: add new RTC_FEATURE_ALARM_WAKEUP_ONLY feature Some RTCs have an IRQ pin that is not connected to a CPU interrupt but rather directly to a PMIC or power supply. In that case, it is still useful to be able to set alarms but we shouldn't expect interrupts. Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20220309162301.61679-22-alexandre.belloni@bootlin.com --- include/uapi/linux/rtc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/rtc.h b/include/uapi/linux/rtc.h index 03e5b776e597..97aca4503a6a 100644 --- a/include/uapi/linux/rtc.h +++ b/include/uapi/linux/rtc.h @@ -133,7 +133,8 @@ struct rtc_param { #define RTC_FEATURE_UPDATE_INTERRUPT 4 #define RTC_FEATURE_CORRECTION 5 #define RTC_FEATURE_BACKUP_SWITCH_MODE 6 -#define RTC_FEATURE_CNT 7 +#define RTC_FEATURE_ALARM_WAKEUP_ONLY 7 +#define RTC_FEATURE_CNT 8 /* parameter list */ #define RTC_PARAM_FEATURES 0 -- cgit v1.2.3 From 1a31d63632553a54af6c0c3c5b5930e931a94ee4 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Wed, 9 Mar 2022 17:23:00 +0100 Subject: rtc: remove uie_unsupported uie_unsupported is not used by any drivers anymore, remove it. Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20220309162301.61679-29-alexandre.belloni@bootlin.com --- include/linux/rtc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 47fd1c2d3a57..1fd9c6a21ebe 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -110,8 +110,6 @@ struct rtc_device { struct hrtimer pie_timer; /* sub second exp, so needs hrtimer */ int pie_enabled; struct work_struct irqwork; - /* Some hardware can't support UIE mode */ - int uie_unsupported; /* * This offset specifies the update timing of the RTC. -- cgit v1.2.3 From de7a9e949f4f094741f708cd05572f932d009d02 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Wed, 23 Mar 2022 22:15:49 +0530 Subject: drivers/nvdimm: Fix build failure when CONFIG_PERF_EVENTS is not set The following build failure occurs when CONFIG_PERF_EVENTS is not set as generic pmu functions are not visible in that scenario. |-- s390-randconfig-r044-20220313 | |-- nd_perf.c:(.text):undefined-reference-to-perf_pmu_migrate_context | |-- nd_perf.c:(.text):undefined-reference-to-perf_pmu_register | `-- nd_perf.c:(.text):undefined-reference-to-perf_pmu_unregister Similar build failure in nds32 architecture: nd_perf.c:(.text+0x21e): undefined reference to `perf_pmu_migrate_context' nd_perf.c:(.text+0x434): undefined reference to `perf_pmu_register' nd_perf.c:(.text+0x57c): undefined reference to `perf_pmu_unregister' Fix this issue by adding check for CONFIG_PERF_EVENTS config option and disabling the nvdimm perf interface incase this config is not set. Also remove function declaration of perf_pmu_migrate_context, perf_pmu_register, perf_pmu_unregister functions from nd.h as these are common pmu functions which are part of perf_event.h and since we are disabling nvdimm perf interface incase CONFIG_PERF_EVENTS option is not set, we not need to declare them in nd.h Also move the platform_device header file addition part from nd.h to nd_perf.c and add stub functions for register_nvdimm_pmu and unregister_nvdimm_pmu functions to handle CONFIG_PERF_EVENTS=n case. Fixes: 0fab1ba6ad6b ("drivers/nvdimm: Add perf interface to expose nvdimm performance stats") (Commit id based on libnvdimm-for-next tree) Signed-off-by: Kajol Jain Link: https://lore.kernel.org/all/62317124.YBQFU33+s%2FwdvWGj%25lkp@intel.com/ Reported-by: kernel test robot Link: https://lore.kernel.org/r/20220323164550.109768-1-kjain@linux.ibm.com Signed-off-by: Dan Williams --- include/linux/nd.h | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/nd.h b/include/linux/nd.h index 7b2ccbdc1cbc..b9771ba1ef87 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -9,7 +9,6 @@ #include #include #include -#include enum nvdimm_event { NVDIMM_REVALIDATE_POISON, @@ -57,15 +56,24 @@ struct nvdimm_pmu { struct cpumask arch_cpumask; }; +struct platform_device; + +#ifdef CONFIG_PERF_EVENTS extern ssize_t nvdimm_events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page); int register_nvdimm_pmu(struct nvdimm_pmu *nvdimm, struct platform_device *pdev); void unregister_nvdimm_pmu(struct nvdimm_pmu *nd_pmu); -void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); -int perf_pmu_register(struct pmu *pmu, const char *name, int type); -void perf_pmu_unregister(struct pmu *pmu); + +#else +static inline int register_nvdimm_pmu(struct nvdimm_pmu *nvdimm, struct platform_device *pdev) +{ + return -ENXIO; +} + +static inline void unregister_nvdimm_pmu(struct nvdimm_pmu *nd_pmu) { } +#endif struct nd_device_driver { struct device_driver drv; -- cgit v1.2.3 From c724c866bb70cb8c607081a26823a1f0ebde4387 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 23 Mar 2022 16:05:29 -0700 Subject: linux/types.h: remove unnecessary __bitwise__ There are no users of "__bitwise__" except the definition of "__bitwise". Remove __bitwise__ and define __bitwise directly. This is a follow-up to 05de97003c77 ("linux/types.h: enable endian checks for all sparse builds"). [akpm@linux-foundation.org: change the tools/include/linux/types.h definition also] Link: https://lkml.kernel.org/r/20220310220927.245704-2-helgaas@kernel.org Signed-off-by: Bjorn Helgaas Cc: Michael S. Tsirkin Cc: Jonathan Corbet Cc: Nathan Chancellor Cc: Nick Desaulniers Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/types.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/types.h b/include/uapi/linux/types.h index f6d2f83cbe29..71696f424ac8 100644 --- a/include/uapi/linux/types.h +++ b/include/uapi/linux/types.h @@ -20,11 +20,10 @@ */ #ifdef __CHECKER__ -#define __bitwise__ __attribute__((bitwise)) +#define __bitwise __attribute__((bitwise)) #else -#define __bitwise__ +#define __bitwise #endif -#define __bitwise __bitwise__ typedef __u16 __bitwise __le16; typedef __u16 __bitwise __be16; -- cgit v1.2.3 From 179fd6ba3bacbf7b19cbdf9b14be109d54318394 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 23 Mar 2022 16:05:32 -0700 Subject: Documentation/sparse: add hints about __CHECKER__ Several attributes depend on __CHECKER__, but previously there was no clue in the tree about when __CHECKER__ might be defined. Add hints at the most common places (__kernel, __user, __iomem, __bitwise) and in the sparse documentation. Link: https://lkml.kernel.org/r/20220310220927.245704-3-helgaas@kernel.org Signed-off-by: Bjorn Helgaas Cc: Jonathan Corbet Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: "Michael S . Tsirkin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compiler_types.h | 1 + include/uapi/linux/types.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3c1795fdb568..4b3915ce38a4 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -4,6 +4,7 @@ #ifndef __ASSEMBLY__ +/* sparse defines __CHECKER__; see Documentation/dev-tools/sparse.rst */ #ifdef __CHECKER__ /* address spaces */ # define __kernel __attribute__((address_space(0))) diff --git a/include/uapi/linux/types.h b/include/uapi/linux/types.h index 71696f424ac8..c4dc597f3dcf 100644 --- a/include/uapi/linux/types.h +++ b/include/uapi/linux/types.h @@ -19,6 +19,7 @@ * any application/library that wants linux/types.h. */ +/* sparse defines __CHECKER__; see Documentation/dev-tools/sparse.rst */ #ifdef __CHECKER__ #define __bitwise __attribute__((bitwise)) #else -- cgit v1.2.3 From 14e83077d55ff4b88fe39f5e98fb8230c2ccb4fb Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Wed, 23 Mar 2022 16:05:41 -0700 Subject: include: drop pointless __compiler_offsetof indirection (1) compiler_types.h is unconditionally included via an -include flag (see scripts/Makefile.lib), and it defines __compiler_offsetof unconditionally. So testing for definedness of __compiler_offsetof is mostly pointless. (2) Every relevant compiler provides __builtin_offsetof (even sparse has had that for 14 years), and if for whatever reason one would end up picking up the poor man's fallback definition (C file compiler with completely custom CFLAGS?), newer clang versions won't treat the result as an Integer Constant Expression, so if used in place where such is required (static initializer or static_assert), one would get errors like t.c:11:16: error: static_assert expression is not an integral constant expression t.c:11:16: note: cast that performs the conversions of a reinterpret_cast is not allowed in a constant expression t.c:4:33: note: expanded from macro 'offsetof' #define offsetof(TYPE, MEMBER) ((size_t)&((TYPE *)0)->MEMBER) So just define offsetof unconditionally and directly in terms of __builtin_offsetof. Link: https://lkml.kernel.org/r/20220202102147.326672-1-linux@rasmusvillemoes.dk Signed-off-by: Rasmus Villemoes Reviewed-by: Miguel Ojeda Reviewed-by: Nathan Chancellor Reviewed-by: Kees Cook Acked-by: Nick Desaulniers Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compiler_types.h | 2 -- include/linux/stddef.h | 6 +----- 2 files changed, 1 insertion(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 4b3915ce38a4..232dbd97f8b1 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -138,8 +138,6 @@ struct ftrace_likely_data { */ #define __naked __attribute__((__naked__)) notrace -#define __compiler_offsetof(a, b) __builtin_offsetof(a, b) - /* * Prefer gnu_inline, so that extern inline functions do not emit an * externally visible function. This makes extern inline behave as per gnu89 diff --git a/include/linux/stddef.h b/include/linux/stddef.h index ca507bd5f808..929d67710cc5 100644 --- a/include/linux/stddef.h +++ b/include/linux/stddef.h @@ -13,11 +13,7 @@ enum { }; #undef offsetof -#ifdef __compiler_offsetof -#define offsetof(TYPE, MEMBER) __compiler_offsetof(TYPE, MEMBER) -#else -#define offsetof(TYPE, MEMBER) ((size_t)&((TYPE *)0)->MEMBER) -#endif +#define offsetof(TYPE, MEMBER) __builtin_offsetof(TYPE, MEMBER) /** * sizeof_field() - Report the size of a struct field in bytes -- cgit v1.2.3 From f334f5668bedf7307f6df1d98b14f55902931926 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Wed, 23 Mar 2022 16:05:44 -0700 Subject: ilog2: force inlining of __ilog2_u32() and __ilog2_u64() Building a kernel with CONFIG_CC_OPTIMISE_FOR_SIZE leads to __ilog2_u32() being duplicated 50 times and __ilog2_u64() 3 times in vmlinux on a tiny powerpc32 config. __ilog2_u32() being 2 instructions it is not worth being kept out of line, so force inlining. Allthough the u64 version is a bit bigger, there is still a small benefit in keeping it inlined. On a 64 bits config there's a real benefit. With this change the size of vmlinux text is reduced by 1 kbytes, which is approx 50% more than the size of the removed functions. Before the patch there is for instance: c00d2a94 <__ilog2_u32>: c00d2a94: 7c 63 00 34 cntlzw r3,r3 c00d2a98: 20 63 00 1f subfic r3,r3,31 c00d2a9c: 4e 80 00 20 blr c00d36d8 <__order_base_2>: c00d36d8: 28 03 00 01 cmplwi r3,1 c00d36dc: 40 81 00 2c ble c00d3708 <__order_base_2+0x30> c00d36e0: 94 21 ff f0 stwu r1,-16(r1) c00d36e4: 7c 08 02 a6 mflr r0 c00d36e8: 38 63 ff ff addi r3,r3,-1 c00d36ec: 90 01 00 14 stw r0,20(r1) c00d36f0: 4b ff f3 a5 bl c00d2a94 <__ilog2_u32> c00d36f4: 80 01 00 14 lwz r0,20(r1) c00d36f8: 38 63 00 01 addi r3,r3,1 c00d36fc: 7c 08 03 a6 mtlr r0 c00d3700: 38 21 00 10 addi r1,r1,16 c00d3704: 4e 80 00 20 blr c00d3708: 38 60 00 00 li r3,0 c00d370c: 4e 80 00 20 blr With the patch it has become: c00d356c <__order_base_2>: c00d356c: 28 03 00 01 cmplwi r3,1 c00d3570: 40 81 00 14 ble c00d3584 <__order_base_2+0x18> c00d3574: 38 63 ff ff addi r3,r3,-1 c00d3578: 7c 63 00 34 cntlzw r3,r3 c00d357c: 20 63 00 20 subfic r3,r3,32 c00d3580: 4e 80 00 20 blr c00d3584: 38 60 00 00 li r3,0 c00d3588: 4e 80 00 20 blr No more need for __order_base_2() to setup a stack frame and save/restore caller address. And the following 'add 1' is merged in the subtract. Another typical use of it: c080ff28 : ... c080fff8: 7f c3 f3 78 mr r3,r30 c080fffc: 4b 8f 81 f1 bl c01081ec <__ilog2_u32> c0810000: 38 63 ff f2 addi r3,r3,-14 ... Becomes c080ff1c : ... c080ffec: 7f c3 00 34 cntlzw r3,r30 c080fff0: 20 63 00 11 subfic r3,r3,17 ... Here no need to move r30 argument to r3 then substract 14 to result. Just work on r30 and merge the 'sub 14' with the 'sub from 31'. Link: https://lkml.kernel.org/r/803a2ac3d923ebcfd0dd40f5886b05cae7bb0aba.1644243860.git.christophe.leroy@csgroup.eu Signed-off-by: Christophe Leroy Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/log2.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/log2.h b/include/linux/log2.h index df0b155c2141..9f30d087a128 100644 --- a/include/linux/log2.h +++ b/include/linux/log2.h @@ -18,7 +18,7 @@ * - the arch is not required to handle n==0 if implementing the fallback */ #ifndef CONFIG_ARCH_HAS_ILOG2_U32 -static inline __attribute__((const)) +static __always_inline __attribute__((const)) int __ilog2_u32(u32 n) { return fls(n) - 1; @@ -26,7 +26,7 @@ int __ilog2_u32(u32 n) #endif #ifndef CONFIG_ARCH_HAS_ILOG2_U64 -static inline __attribute__((const)) +static __always_inline __attribute__((const)) int __ilog2_u64(u64 n) { return fls64(n) - 1; -- cgit v1.2.3 From 25cb5b7ac6a7f7943e22a6831b74a6aa964d2a0c Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 23 Mar 2022 16:05:47 -0700 Subject: bitfield: add explicit inclusions to the example MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It's not obvious that bitfield.h doesn't guarantee the bits.h inclusion and the example in the former is confusing. Some developers think that it's okay to just include bitfield.h to get it working. Change example to explicitly include necessary headers in order to avoid confusion. Link: https://lkml.kernel.org/r/20220207123341.47533-1-andriy.shevchenko@linux.intel.com Fixes: 3e9b3112ec74 ("add basic register-field manipulation macros") Depends-on: 8bd9cb51daac ("locking/atomics, asm-generic: Move some macros from to a new file") Signed-off-by: Andy Shevchenko Reported-by: Jan Dąbroś Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitfield.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h index 6093fa6db260..c9be1657f03d 100644 --- a/include/linux/bitfield.h +++ b/include/linux/bitfield.h @@ -19,6 +19,9 @@ * * Example: * + * #include + * #include + * * #define REG_FIELD_A GENMASK(6, 0) * #define REG_FIELD_B BIT(7) * #define REG_FIELD_C GENMASK(15, 8) -- cgit v1.2.3 From abc7da58c4b388ab9f6a756c0f297c29d3af665f Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 23 Mar 2022 16:06:11 -0700 Subject: init.h: improve __setup and early_param documentation Igor noted in [1] that there are quite a few __setup() handling functions that return incorrect values. Doing this can be harmless, but it can also cause strings to be added to init's argument or environment list, polluting them. Since __setup() handling and return values are not documented, first add documentation for that. Also add more documentation for early_param() handling and return values. For __setup() functions, returning 0 (not handled) has questionable value if it is just a malformed option value, as in rodata=junk since returning 0 would just cause "rodata=junk" to be added to init's environment unnecessarily: Run /sbin/init as init process with arguments: /sbin/init with environment: HOME=/ TERM=linux splash=native rodata=junk Also, there are no recommendations on whether to print a warning when an unknown parameter value is seen. I am not addressing that here. [1] lore.kernel.org/r/64644a2f-4a20-bab3-1e15-3b2cdd0defe3@omprussia.ru Link: https://lkml.kernel.org/r/20220221050852.1147-1-rdunlap@infradead.org Signed-off-by: Randy Dunlap Reported-by: Igor Zhbanov Cc: Ingo Molnar Cc: Greg Kroah-Hartman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/init.h b/include/linux/init.h index d82b4b2e1d25..baf0b29a7010 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -320,12 +320,19 @@ struct obs_kernel_param { __aligned(__alignof__(struct obs_kernel_param)) \ = { __setup_str_##unique_id, fn, early } +/* + * NOTE: __setup functions return values: + * @fn returns 1 (or non-zero) if the option argument is "handled" + * and returns 0 if the option argument is "not handled". + */ #define __setup(str, fn) \ __setup_param(str, fn, fn, 0) /* - * NOTE: fn is as per module_param, not __setup! - * Emits warning if fn returns non-zero. + * NOTE: @fn is as per module_param, not __setup! + * I.e., @fn returns 0 for no error or non-zero for error + * (possibly @fn returns a -errno value, but it does not matter). + * Emits warning if @fn returns non-zero. */ #define early_param(str, fn) \ __setup_param(str, fn, fn, 1) -- cgit v1.2.3 From f05fa10901aa4b11a84257ecb7ac7f8fe7c4ee1b Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Wed, 23 Mar 2022 16:06:33 -0700 Subject: kexec: make crashk_res, crashk_low_res and crash_notes symbols always visible Patch series "kexec: use IS_ENABLED(CONFIG_KEXEC_CORE) instead of #ifdef", v2. Replace the conditional compilation using "#ifdef CONFIG_KEXEC_CORE" by a check for "IS_ENABLED(CONFIG_KEXEC_CORE)", to simplify the code and increase compile coverage. I only modified x86, arm, arm64 and riscv, other architectures such as sh, powerpc and s390 are better to be kept kexec code as-is so they are not touched. This patch (of 5): Make the forward declarations of crashk_res, crashk_low_res and crash_notes always visible. Code referring to these symbols can then just check for IS_ENABLED(CONFIG_KEXEC_CORE), instead of requiring conditional compilation using an #ifdef, thus preparing to increase compile coverage and simplify the code. Link: https://lkml.kernel.org/r/20211206160514.2000-1-jszhang@kernel.org Link: https://lkml.kernel.org/r/20211206160514.2000-2-jszhang@kernel.org Signed-off-by: Jisheng Zhang Acked-by: Baoquan He Cc: Russell King Cc: Catalin Marinas Cc: Will Deacon Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: H. Peter Anvin Cc: Eric W. Biederman Cc: Alexandre Ghiti Cc: Palmer Dabbelt Cc: Russell King (Oracle) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 0c994ae37729..58d1b58a971e 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -20,6 +20,12 @@ #include +/* Location of a reserved region to hold the crash kernel. + */ +extern struct resource crashk_res; +extern struct resource crashk_low_res; +extern note_buf_t __percpu *crash_notes; + #ifdef CONFIG_KEXEC_CORE #include #include @@ -350,12 +356,6 @@ extern int kexec_load_disabled; #define KEXEC_FILE_FLAGS (KEXEC_FILE_UNLOAD | KEXEC_FILE_ON_CRASH | \ KEXEC_FILE_NO_INITRAMFS) -/* Location of a reserved region to hold the crash kernel. - */ -extern struct resource crashk_res; -extern struct resource crashk_low_res; -extern note_buf_t __percpu *crash_notes; - /* flag to track if kexec reboot is in progress */ extern bool kexec_in_progress; -- cgit v1.2.3 From 548e7432dc2da475a18077b612e8d55b8ff51891 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Fri, 24 Sep 2021 10:55:45 +0200 Subject: dma-buf: add dma_resv_replace_fences v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This function allows to replace fences from the shared fence list when we can gurantee that the operation represented by the original fence has finished or no accesses to the resources protected by the dma_resv object any more when the new fence finishes. Then use this function in the amdkfd code when BOs are unmapped from the process. v2: add an example when this is usefull. Signed-off-by: Christian König Reviewed-by: Felix Kuehling Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220321135856.1331-1-christian.koenig@amd.com --- include/linux/dma-resv.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index afdfdfac729f..3f53177bdb46 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -468,6 +468,8 @@ void dma_resv_init(struct dma_resv *obj); void dma_resv_fini(struct dma_resv *obj); int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences); void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence); +void dma_resv_replace_fences(struct dma_resv *obj, uint64_t context, + struct dma_fence *fence); void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence); int dma_resv_get_fences(struct dma_resv *obj, bool write, unsigned int *num_fences, struct dma_fence ***fences); -- cgit v1.2.3 From 8938d48451f5d7cb565dfa68aa0bd0e81985da09 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Fri, 24 Sep 2021 14:19:22 +0200 Subject: dma-buf: finally make the dma_resv_list private v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Drivers should never touch this directly. v2: drop kerneldoc for now internal handling Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220321135856.1331-2-christian.koenig@amd.com --- include/linux/dma-resv.h | 26 +------------------------- 1 file changed, 1 insertion(+), 25 deletions(-) (limited to 'include') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 3f53177bdb46..202cc65d0621 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -47,18 +47,7 @@ extern struct ww_class reservation_ww_class; -/** - * struct dma_resv_list - a list of shared fences - * @rcu: for internal use - * @shared_count: table of shared fences - * @shared_max: for growing shared fence table - * @shared: shared fence table - */ -struct dma_resv_list { - struct rcu_head rcu; - u32 shared_count, shared_max; - struct dma_fence __rcu *shared[]; -}; +struct dma_resv_list; /** * struct dma_resv - a reservation object manages fences for a buffer @@ -451,19 +440,6 @@ dma_resv_excl_fence(struct dma_resv *obj) return rcu_dereference_check(obj->fence_excl, dma_resv_held(obj)); } -/** - * dma_resv_shared_list - get the reservation object's shared fence list - * @obj: the reservation object - * - * Returns the shared fence list. Caller must either hold the objects - * through dma_resv_lock() or the RCU read side lock through rcu_read_lock(), - * or one of the variants of each - */ -static inline struct dma_resv_list *dma_resv_shared_list(struct dma_resv *obj) -{ - return rcu_dereference_check(obj->fence, dma_resv_held(obj)); -} - void dma_resv_init(struct dma_resv *obj); void dma_resv_fini(struct dma_resv *obj); int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences); -- cgit v1.2.3 From 7ef66d186eb95f987a97fb3329b65c840e2dc9bf Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 24 Mar 2022 06:53:18 -0600 Subject: io_uring: remove IORING_CQE_F_MSG This was introduced with the message ring opcode, but isn't strictly required for the request itself. The sender can encode what is needed in user_data, which is passed to the receiver. It's unclear if having a separate flag that essentially says "This CQE did not originate from an SQE on this ring" provides any real utility to applications. While we can always re-introduce a flag to provide this information, we cannot take it away at a later point in time. Remove the flag while we still can, before it's in a released kernel. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index d2be4eb22008..784adc6f6ed2 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -201,11 +201,9 @@ struct io_uring_cqe { * * IORING_CQE_F_BUFFER If set, the upper 16 bits are the buffer ID * IORING_CQE_F_MORE If set, parent SQE will generate more CQE entries - * IORING_CQE_F_MSG If set, CQE was generated with IORING_OP_MSG_RING */ #define IORING_CQE_F_BUFFER (1U << 0) #define IORING_CQE_F_MORE (1U << 1) -#define IORING_CQE_F_MSG (1U << 2) enum { IORING_CQE_BUFFER_SHIFT = 16, -- cgit v1.2.3 From d645552e9bd96671079b27015294ec7f9748fa2b Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Thu, 24 Mar 2022 15:02:40 +0100 Subject: netfilter: egress: Report interface as outgoing Otherwise packets in egress chains seem like they are being received by the interface, not sent out via it. Fixes: 42df6e1d221dd ("netfilter: Introduce egress hook") Signed-off-by: Phil Sutter Signed-off-by: Florian Westphal --- include/linux/netfilter_netdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfilter_netdev.h b/include/linux/netfilter_netdev.h index e6487a691136..8676316547cc 100644 --- a/include/linux/netfilter_netdev.h +++ b/include/linux/netfilter_netdev.h @@ -99,7 +99,7 @@ static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, return skb; nf_hook_state_init(&state, NF_NETDEV_EGRESS, - NFPROTO_NETDEV, dev, NULL, NULL, + NFPROTO_NETDEV, NULL, dev, NULL, dev_net(dev), NULL); /* nf assumes rcu_read_lock, not just read_lock_bh */ -- cgit v1.2.3 From bb43b14b576228c580bdc7e1aeeded54d540b5ef Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 24 Mar 2022 18:09:49 -0700 Subject: mm: delete __ClearPageWaiters() The PG_waiters bit is not included in PAGE_FLAGS_CHECK_AT_FREE, and vmscan.c's free_unref_page_list() callers rely on that not to generate bad_page() alerts. So __page_cache_release(), put_pages_list() and release_pages() (and presumably copy-and-pasted free_zone_device_page()) are redundant and misleading to make a special point of clearing it (as the "__" implies, it could only safely be used on the freeing path). Delete __ClearPageWaiters(). Remark on this in one of the "possible" comments in folio_wake_bit(), and delete the superfluous comments. Link: https://lkml.kernel.org/r/3eafa969-5b1a-accf-88fe-318784c791a@google.com Signed-off-by: Hugh Dickins Tested-by: Yu Zhao Reviewed-by: Yang Shi Reviewed-by: David Hildenbrand Cc: Matthew Wilcox Cc: Nicholas Piggin Cc: Yu Zhao Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 88fe1d759cdd..9d8eeaa67d05 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -481,7 +481,7 @@ static inline int TestClearPage##uname(struct page *page) { return 0; } TESTSETFLAG_FALSE(uname, lname) TESTCLEARFLAG_FALSE(uname, lname) __PAGEFLAG(Locked, locked, PF_NO_TAIL) -PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) __CLEARPAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) +PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) PAGEFLAG(Error, error, PF_NO_TAIL) TESTCLEARFLAG(Error, error, PF_NO_TAIL) PAGEFLAG(Referenced, referenced, PF_HEAD) TESTCLEARFLAG(Referenced, referenced, PF_HEAD) -- cgit v1.2.3 From 283fd6fe0528ae2fe0222a35ecfdfcbbaeee8159 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 24 Mar 2022 18:09:58 -0700 Subject: mm/migration: add trace events for THP migrations Patch series "mm/migration: Add trace events", v3. This adds trace events for all migration scenarios including base page, THP and HugeTLB. This patch (of 3): This adds two trace events for PMD based THP migration without split. These events closely follow the implementation details like setting and removing of PMD migration entries, which are essential operations for THP migration. This moves CREATE_TRACE_POINTS into generic THP from powerpc for these new trace events to be available on other platforms as well. Link: https://lkml.kernel.org/r/1643368182-9588-1-git-send-email-anshuman.khandual@arm.com Link: https://lkml.kernel.org/r/1643368182-9588-2-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Cc: Steven Rostedt Cc: Ingo Molnar Cc: Zi Yan Cc: Naoya Horiguchi Cc: John Hubbard Cc: Matthew Wilcox Cc: Michael Ellerman Cc: Paul Mackerras Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/thp.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include') diff --git a/include/trace/events/thp.h b/include/trace/events/thp.h index ca3f2767828a..202b3e3e67ff 100644 --- a/include/trace/events/thp.h +++ b/include/trace/events/thp.h @@ -48,6 +48,33 @@ TRACE_EVENT(hugepage_update, TP_printk("hugepage update at addr 0x%lx and pte = 0x%lx clr = 0x%lx, set = 0x%lx", __entry->addr, __entry->pte, __entry->clr, __entry->set) ); +DECLARE_EVENT_CLASS(migration_pmd, + + TP_PROTO(unsigned long addr, unsigned long pmd), + + TP_ARGS(addr, pmd), + + TP_STRUCT__entry( + __field(unsigned long, addr) + __field(unsigned long, pmd) + ), + + TP_fast_assign( + __entry->addr = addr; + __entry->pmd = pmd; + ), + TP_printk("addr=%lx, pmd=%lx", __entry->addr, __entry->pmd) +); + +DEFINE_EVENT(migration_pmd, set_migration_pmd, + TP_PROTO(unsigned long addr, unsigned long pmd), + TP_ARGS(addr, pmd) +); + +DEFINE_EVENT(migration_pmd, remove_migration_pmd, + TP_PROTO(unsigned long addr, unsigned long pmd), + TP_ARGS(addr, pmd) +); #endif /* _TRACE_THP_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 4cc79b3303f224a920f3aff21f3d231749d73384 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 24 Mar 2022 18:10:01 -0700 Subject: mm/migration: add trace events for base page and HugeTLB migrations This adds two trace events for base page and HugeTLB page migrations. These events, closely follow the implementation details like setting and removing of PTE migration entries, which are essential operations for migration. The new CREATE_TRACE_POINTS in covers both and based trace events. Hence drop redundant CREATE_TRACE_POINTS from other places which could have otherwise conflicted during build. Link: https://lkml.kernel.org/r/1643368182-9588-3-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Reported-by: kernel test robot Cc: Steven Rostedt Cc: Ingo Molnar Cc: Zi Yan Cc: Naoya Horiguchi Cc: John Hubbard Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/migrate.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include') diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h index 779f3fad9ecd..061b5128f335 100644 --- a/include/trace/events/migrate.h +++ b/include/trace/events/migrate.h @@ -105,6 +105,37 @@ TRACE_EVENT(mm_migrate_pages_start, __print_symbolic(__entry->reason, MIGRATE_REASON)) ); +DECLARE_EVENT_CLASS(migration_pte, + + TP_PROTO(unsigned long addr, unsigned long pte, int order), + + TP_ARGS(addr, pte, order), + + TP_STRUCT__entry( + __field(unsigned long, addr) + __field(unsigned long, pte) + __field(int, order) + ), + + TP_fast_assign( + __entry->addr = addr; + __entry->pte = pte; + __entry->order = order; + ), + + TP_printk("addr=%lx, pte=%lx order=%d", __entry->addr, __entry->pte, __entry->order) +); + +DEFINE_EVENT(migration_pte, set_migration_pte, + TP_PROTO(unsigned long addr, unsigned long pte, int order), + TP_ARGS(addr, pte, order) +); + +DEFINE_EVENT(migration_pte, remove_migration_pte, + TP_PROTO(unsigned long addr, unsigned long pte, int order), + TP_ARGS(addr, pte, order) +); + #endif /* _TRACE_MIGRATE_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 7c13c163e036c646b77753deacfe2f5478b654bc Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 24 Mar 2022 18:10:10 -0700 Subject: kasan, page_alloc: merge kasan_free_pages into free_pages_prepare Currently, the code responsible for initializing and poisoning memory in free_pages_prepare() is scattered across two locations: kasan_free_pages() for HW_TAGS KASAN and free_pages_prepare() itself. This is confusing. This and a few following patches combine the code from these two locations. Along the way, these patches also simplify the performed checks to make them easier to follow. Replaces the only caller of kasan_free_pages() with its implementation. As kasan_has_integrated_init() is only true when CONFIG_KASAN_HW_TAGS is enabled, moving the code does no functional changes. This patch is not useful by itself but makes the simplifications in the following patches easier to follow. Link: https://lkml.kernel.org/r/303498d15840bb71905852955c6e2390ecc87139.1643047180.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Alexander Potapenko Acked-by: Marco Elver Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Mark Rutland Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index b6a93261c92a..dd2161af84e9 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -85,7 +85,6 @@ static inline void kasan_disable_current(void) {} #ifdef CONFIG_KASAN_HW_TAGS void kasan_alloc_pages(struct page *page, unsigned int order, gfp_t flags); -void kasan_free_pages(struct page *page, unsigned int order); #else /* CONFIG_KASAN_HW_TAGS */ @@ -96,13 +95,6 @@ static __always_inline void kasan_alloc_pages(struct page *page, BUILD_BUG(); } -static __always_inline void kasan_free_pages(struct page *page, - unsigned int order) -{ - /* Only available for integrated init. */ - BUILD_BUG(); -} - #endif /* CONFIG_KASAN_HW_TAGS */ static inline bool kasan_has_integrated_init(void) -- cgit v1.2.3 From c82ce3195fd17e57a370e4dc8f36c195b8807b95 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 24 Mar 2022 18:10:22 -0700 Subject: mm: clarify __GFP_ZEROTAGS comment __GFP_ZEROTAGS is intended as an optimization: if memory is zeroed during allocation, it's possible to set memory tags at the same time with little performance impact. Clarify this intention of __GFP_ZEROTAGS in the comment. Link: https://lkml.kernel.org/r/cdffde013973c5634a447513e10ec0d21e8eee29.1643047180.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Acked-by: Marco Elver Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Mark Rutland Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 20f6fbe12993..72dc4ca75cf3 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -232,8 +232,10 @@ struct vm_area_struct; * * %__GFP_ZERO returns a zeroed page on success. * - * %__GFP_ZEROTAGS returns a page with zeroed memory tags on success, if - * __GFP_ZERO is set. + * %__GFP_ZEROTAGS zeroes memory tags at allocation time if the memory itself + * is being zeroed (either via __GFP_ZERO or via init_on_alloc). This flag is + * intended for optimization: setting memory tags at the same time as zeroing + * memory has minimal additional performace impact. * * %__GFP_SKIP_KASAN_POISON returns a page which does not need to be poisoned * on deallocation. Typically used for userspace pages. Currently only has an -- cgit v1.2.3 From b42090ae6f3aa07b0a39403545d688489548a6a8 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 24 Mar 2022 18:10:31 -0700 Subject: kasan, page_alloc: merge kasan_alloc_pages into post_alloc_hook Currently, the code responsible for initializing and poisoning memory in post_alloc_hook() is scattered across two locations: kasan_alloc_pages() hook for HW_TAGS KASAN and post_alloc_hook() itself. This is confusing. This and a few following patches combine the code from these two locations. Along the way, these patches do a step-by-step restructure the many performed checks to make them easier to follow. Replace the only caller of kasan_alloc_pages() with its implementation. As kasan_has_integrated_init() is only true when CONFIG_KASAN_HW_TAGS is enabled, moving the code does no functional changes. Also move init and init_tags variables definitions out of kasan_has_integrated_init() clause in post_alloc_hook(), as they have the same values regardless of what the if condition evaluates to. This patch is not useful by itself but makes the simplifications in the following patches easier to follow. Link: https://lkml.kernel.org/r/5ac7e0b30f5cbb177ec363ddd7878a3141289592.1643047180.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Acked-by: Marco Elver Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Mark Rutland Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index dd2161af84e9..4ed94616c8f0 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -84,17 +84,8 @@ static inline void kasan_disable_current(void) {} #ifdef CONFIG_KASAN_HW_TAGS -void kasan_alloc_pages(struct page *page, unsigned int order, gfp_t flags); - #else /* CONFIG_KASAN_HW_TAGS */ -static __always_inline void kasan_alloc_pages(struct page *page, - unsigned int order, gfp_t flags) -{ - /* Only available for integrated init. */ - BUILD_BUG(); -} - #endif /* CONFIG_KASAN_HW_TAGS */ static inline bool kasan_has_integrated_init(void) -- cgit v1.2.3 From 63840de296472f3914bb933b11ba2b764590755e Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 24 Mar 2022 18:10:52 -0700 Subject: kasan, x86, arm64, s390: rename functions for modules shadow Rename kasan_free_shadow to kasan_free_module_shadow and kasan_module_alloc to kasan_alloc_module_shadow. These functions are used to allocate/free shadow memory for kernel modules when KASAN_VMALLOC is not enabled. The new names better reflect their purpose. Also reword the comment next to their declaration to improve clarity. Link: https://lkml.kernel.org/r/36db32bde765d5d0b856f77d2d806e838513fe84.1643047180.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Acked-by: Catalin Marinas Acked-by: Marco Elver Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Mark Rutland Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 4ed94616c8f0..b450c7653137 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -433,17 +433,17 @@ static inline void kasan_populate_early_vm_area_shadow(void *start, !defined(CONFIG_KASAN_VMALLOC) /* - * These functions provide a special case to support backing module - * allocations with real shadow memory. With KASAN vmalloc, the special - * case is unnecessary, as the work is handled in the generic case. + * These functions allocate and free shadow memory for kernel modules. + * They are only required when KASAN_VMALLOC is not supported, as otherwise + * shadow memory is allocated by the generic vmalloc handlers. */ -int kasan_module_alloc(void *addr, size_t size, gfp_t gfp_mask); -void kasan_free_shadow(const struct vm_struct *vm); +int kasan_alloc_module_shadow(void *addr, size_t size, gfp_t gfp_mask); +void kasan_free_module_shadow(const struct vm_struct *vm); #else /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */ -static inline int kasan_module_alloc(void *addr, size_t size, gfp_t gfp_mask) { return 0; } -static inline void kasan_free_shadow(const struct vm_struct *vm) {} +static inline int kasan_alloc_module_shadow(void *addr, size_t size, gfp_t gfp_mask) { return 0; } +static inline void kasan_free_module_shadow(const struct vm_struct *vm) {} #endif /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */ -- cgit v1.2.3 From 0b7ccc70ee1d5b499d1626c9d28f729507b1c036 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 24 Mar 2022 18:10:55 -0700 Subject: kasan, vmalloc: drop outdated VM_KASAN comment The comment about VM_KASAN in include/linux/vmalloc.c is outdated. VM_KASAN is currently only used to mark vm_areas allocated for kernel modules when CONFIG_KASAN_VMALLOC is disabled. Drop the comment. Link: https://lkml.kernel.org/r/780395afea83a147b3b5acc36cf2e38f7f8479f9.1643047180.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Alexander Potapenko Acked-by: Marco Elver Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Mark Rutland Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 5a0c3b556848..2ca95c7db463 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -35,17 +35,6 @@ struct notifier_block; /* in notifier.h */ #define VM_DEFER_KMEMLEAK 0 #endif -/* - * VM_KASAN is used slightly differently depending on CONFIG_KASAN_VMALLOC. - * - * If IS_ENABLED(CONFIG_KASAN_VMALLOC), VM_KASAN is set on a vm_struct after - * shadow memory has been mapped. It's used to handle allocation errors so that - * we don't try to poison shadow on free if it was never allocated. - * - * Otherwise, VM_KASAN is set for kasan_module_alloc() allocations and used to - * determine which allocations need the module shadow freed. - */ - /* bits [20..32] reserved for arch specific ioremap internals */ /* -- cgit v1.2.3 From 5bd9bae22a455321327982d0b595a7e76d425fd0 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 24 Mar 2022 18:10:58 -0700 Subject: kasan: reorder vmalloc hooks Group functions that [de]populate shadow memory for vmalloc. Group functions that [un]poison memory for vmalloc. This patch does no functional changes but prepares KASAN code for adding vmalloc support to HW_TAGS KASAN. Link: https://lkml.kernel.org/r/aeef49eb249c206c4c9acce2437728068da74c28.1643047180.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Alexander Potapenko Acked-by: Marco Elver Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Mark Rutland Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 20 +++++++++----------- 1 file changed, 9 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index b450c7653137..5f9ed1372eef 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -397,34 +397,32 @@ static inline void kasan_init_hw_tags(void) { } #ifdef CONFIG_KASAN_VMALLOC +void kasan_populate_early_vm_area_shadow(void *start, unsigned long size); int kasan_populate_vmalloc(unsigned long addr, unsigned long size); -void kasan_poison_vmalloc(const void *start, unsigned long size); -void kasan_unpoison_vmalloc(const void *start, unsigned long size); void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end); -void kasan_populate_early_vm_area_shadow(void *start, unsigned long size); +void kasan_unpoison_vmalloc(const void *start, unsigned long size); +void kasan_poison_vmalloc(const void *start, unsigned long size); #else /* CONFIG_KASAN_VMALLOC */ +static inline void kasan_populate_early_vm_area_shadow(void *start, + unsigned long size) { } static inline int kasan_populate_vmalloc(unsigned long start, unsigned long size) { return 0; } - -static inline void kasan_poison_vmalloc(const void *start, unsigned long size) -{ } -static inline void kasan_unpoison_vmalloc(const void *start, unsigned long size) -{ } static inline void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, - unsigned long free_region_end) {} + unsigned long free_region_end) { } -static inline void kasan_populate_early_vm_area_shadow(void *start, - unsigned long size) +static inline void kasan_unpoison_vmalloc(const void *start, unsigned long size) +{ } +static inline void kasan_poison_vmalloc(const void *start, unsigned long size) { } #endif /* CONFIG_KASAN_VMALLOC */ -- cgit v1.2.3 From 579fb0ac085be2015529a5f7bd1061899a6374de Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 24 Mar 2022 18:11:01 -0700 Subject: kasan: add wrappers for vmalloc hooks Add wrappers around functions that [un]poison memory for vmalloc allocations. These functions will be used by HW_TAGS KASAN and therefore need to be disabled when kasan=off command line argument is provided. This patch does no functional changes for software KASAN modes. Link: https://lkml.kernel.org/r/3b8728eac438c55389fb0f9a8a2145d71dd77487.1643047180.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Alexander Potapenko Acked-by: Marco Elver Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Mark Rutland Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 5f9ed1372eef..a6d6fdefb278 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -403,8 +403,21 @@ void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end); -void kasan_unpoison_vmalloc(const void *start, unsigned long size); -void kasan_poison_vmalloc(const void *start, unsigned long size); +void __kasan_unpoison_vmalloc(const void *start, unsigned long size); +static __always_inline void kasan_unpoison_vmalloc(const void *start, + unsigned long size) +{ + if (kasan_enabled()) + __kasan_unpoison_vmalloc(start, size); +} + +void __kasan_poison_vmalloc(const void *start, unsigned long size); +static __always_inline void kasan_poison_vmalloc(const void *start, + unsigned long size) +{ + if (kasan_enabled()) + __kasan_poison_vmalloc(start, size); +} #else /* CONFIG_KASAN_VMALLOC */ -- cgit v1.2.3 From 1d96320f8d5320423737da61e6e6937f6b475b5c Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 24 Mar 2022 18:11:13 -0700 Subject: kasan, vmalloc: add vmalloc tagging for SW_TAGS Add vmalloc tagging support to SW_TAGS KASAN. - __kasan_unpoison_vmalloc() now assigns a random pointer tag, poisons the virtual mapping accordingly, and embeds the tag into the returned pointer. - __get_vm_area_node() (used by vmalloc() and vmap()) and pcpu_get_vm_areas() save the tagged pointer into vm_struct->addr (note: not into vmap_area->addr). This requires putting kasan_unpoison_vmalloc() after setup_vmalloc_vm[_locked](); otherwise the latter will overwrite the tagged pointer. The tagged pointer then is naturally propagateed to vmalloc() and vmap(). - vm_map_ram() returns the tagged pointer directly. As a result of this change, vm_struct->addr is now tagged. Enabling KASAN_VMALLOC with SW_TAGS is not yet allowed. Link: https://lkml.kernel.org/r/4a78f3c064ce905e9070c29733aca1dd254a74f1.1643047180.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Acked-by: Marco Elver Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Mark Rutland Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index a6d6fdefb278..d3efb6cbd0f5 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -403,12 +403,13 @@ void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end); -void __kasan_unpoison_vmalloc(const void *start, unsigned long size); -static __always_inline void kasan_unpoison_vmalloc(const void *start, - unsigned long size) +void *__kasan_unpoison_vmalloc(const void *start, unsigned long size); +static __always_inline void *kasan_unpoison_vmalloc(const void *start, + unsigned long size) { if (kasan_enabled()) - __kasan_unpoison_vmalloc(start, size); + return __kasan_unpoison_vmalloc(start, size); + return (void *)start; } void __kasan_poison_vmalloc(const void *start, unsigned long size); @@ -433,8 +434,11 @@ static inline void kasan_release_vmalloc(unsigned long start, unsigned long free_region_start, unsigned long free_region_end) { } -static inline void kasan_unpoison_vmalloc(const void *start, unsigned long size) -{ } +static inline void *kasan_unpoison_vmalloc(const void *start, + unsigned long size) +{ + return (void *)start; +} static inline void kasan_poison_vmalloc(const void *start, unsigned long size) { } -- cgit v1.2.3 From 01d92c7f358ce892279ca830cf6ccf2862a17d1c Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 24 Mar 2022 18:11:16 -0700 Subject: kasan, vmalloc, arm64: mark vmalloc mappings as pgprot_tagged HW_TAGS KASAN relies on ARM Memory Tagging Extension (MTE). With MTE, a memory region must be mapped as MT_NORMAL_TAGGED to allow setting memory tags via MTE-specific instructions. Add proper protection bits to vmalloc() allocations. These allocations are always backed by page_alloc pages, so the tags will actually be getting set on the corresponding physical memory. Link: https://lkml.kernel.org/r/983fc33542db2f6b1e77b34ca23448d4640bbb9e.1643047180.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Co-developed-by: Vincenzo Frascino Signed-off-by: Vincenzo Frascino Acked-by: Marco Elver Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Mark Rutland Cc: Peter Collingbourne Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 2ca95c7db463..3b1df7da402d 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -115,6 +115,13 @@ static inline int arch_vmap_pte_supported_shift(unsigned long size) } #endif +#ifndef arch_vmap_pgprot_tagged +static inline pgprot_t arch_vmap_pgprot_tagged(pgprot_t prot) +{ + return prot; +} +#endif + /* * Highlevel APIs for driver use */ -- cgit v1.2.3 From f49d9c5bb15cc5c470097078ec1f26ff605ae1a2 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 24 Mar 2022 18:11:23 -0700 Subject: kasan, mm: only define ___GFP_SKIP_KASAN_POISON with HW_TAGS Only define the ___GFP_SKIP_KASAN_POISON flag when CONFIG_KASAN_HW_TAGS is enabled. This patch it not useful by itself, but it prepares the code for additions of new KASAN-specific GFP patches. Link: https://lkml.kernel.org/r/44e5738a584c11801b2b8f1231898918efc8634a.1643047180.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Acked-by: Marco Elver Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Mark Rutland Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 8 +++++++- include/trace/events/mmflags.h | 12 +++++++++--- 2 files changed, 16 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 72dc4ca75cf3..75abf8d5bc9b 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -54,7 +54,11 @@ struct vm_area_struct; #define ___GFP_THISNODE 0x200000u #define ___GFP_ACCOUNT 0x400000u #define ___GFP_ZEROTAGS 0x800000u +#ifdef CONFIG_KASAN_HW_TAGS #define ___GFP_SKIP_KASAN_POISON 0x1000000u +#else +#define ___GFP_SKIP_KASAN_POISON 0 +#endif #ifdef CONFIG_LOCKDEP #define ___GFP_NOLOCKDEP 0x2000000u #else @@ -251,7 +255,9 @@ struct vm_area_struct; #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) /* Room for N __GFP_FOO bits */ -#define __GFP_BITS_SHIFT (25 + IS_ENABLED(CONFIG_LOCKDEP)) +#define __GFP_BITS_SHIFT (24 + \ + IS_ENABLED(CONFIG_KASAN_HW_TAGS) + \ + IS_ENABLED(CONFIG_LOCKDEP)) #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /** diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 116ed4d5d0f8..cb4520374e2c 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -49,12 +49,18 @@ {(unsigned long)__GFP_RECLAIM, "__GFP_RECLAIM"}, \ {(unsigned long)__GFP_DIRECT_RECLAIM, "__GFP_DIRECT_RECLAIM"},\ {(unsigned long)__GFP_KSWAPD_RECLAIM, "__GFP_KSWAPD_RECLAIM"},\ - {(unsigned long)__GFP_ZEROTAGS, "__GFP_ZEROTAGS"}, \ - {(unsigned long)__GFP_SKIP_KASAN_POISON,"__GFP_SKIP_KASAN_POISON"}\ + {(unsigned long)__GFP_ZEROTAGS, "__GFP_ZEROTAGS"} \ + +#ifdef CONFIG_KASAN_HW_TAGS +#define __def_gfpflag_names_kasan \ + , {(unsigned long)__GFP_SKIP_KASAN_POISON, "__GFP_SKIP_KASAN_POISON"} +#else +#define __def_gfpflag_names_kasan +#endif #define show_gfp_flags(flags) \ (flags) ? __print_flags(flags, "|", \ - __def_gfpflag_names \ + __def_gfpflag_names __def_gfpflag_names_kasan \ ) : "none" #ifdef CONFIG_MMU -- cgit v1.2.3 From 53ae233c30a623ff44ff2f83854e92530c5d9fc2 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 24 Mar 2022 18:11:26 -0700 Subject: kasan, page_alloc: allow skipping unpoisoning for HW_TAGS Add a new GFP flag __GFP_SKIP_KASAN_UNPOISON that allows skipping KASAN poisoning for page_alloc allocations. The flag is only effective with HW_TAGS KASAN. This flag will be used by vmalloc code for page_alloc allocations backing vmalloc() mappings in a following patch. The reason to skip KASAN poisoning for these pages in page_alloc is because vmalloc code will be poisoning them instead. Also reword the comment for __GFP_SKIP_KASAN_POISON. Link: https://lkml.kernel.org/r/35c97d77a704f6ff971dd3bfe4be95855744108e.1643047180.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Acked-by: Marco Elver Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Mark Rutland Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 21 +++++++++++++-------- include/trace/events/mmflags.h | 5 +++-- 2 files changed, 16 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 75abf8d5bc9b..688a39fde43e 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -55,12 +55,14 @@ struct vm_area_struct; #define ___GFP_ACCOUNT 0x400000u #define ___GFP_ZEROTAGS 0x800000u #ifdef CONFIG_KASAN_HW_TAGS -#define ___GFP_SKIP_KASAN_POISON 0x1000000u +#define ___GFP_SKIP_KASAN_UNPOISON 0x1000000u +#define ___GFP_SKIP_KASAN_POISON 0x2000000u #else +#define ___GFP_SKIP_KASAN_UNPOISON 0 #define ___GFP_SKIP_KASAN_POISON 0 #endif #ifdef CONFIG_LOCKDEP -#define ___GFP_NOLOCKDEP 0x2000000u +#define ___GFP_NOLOCKDEP 0x4000000u #else #define ___GFP_NOLOCKDEP 0 #endif @@ -241,22 +243,25 @@ struct vm_area_struct; * intended for optimization: setting memory tags at the same time as zeroing * memory has minimal additional performace impact. * - * %__GFP_SKIP_KASAN_POISON returns a page which does not need to be poisoned - * on deallocation. Typically used for userspace pages. Currently only has an - * effect in HW tags mode. + * %__GFP_SKIP_KASAN_UNPOISON makes KASAN skip unpoisoning on page allocation. + * Only effective in HW_TAGS mode. + * + * %__GFP_SKIP_KASAN_POISON makes KASAN skip poisoning on page deallocation. + * Typically, used for userspace pages. Only effective in HW_TAGS mode. */ #define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) #define __GFP_COMP ((__force gfp_t)___GFP_COMP) #define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) #define __GFP_ZEROTAGS ((__force gfp_t)___GFP_ZEROTAGS) -#define __GFP_SKIP_KASAN_POISON ((__force gfp_t)___GFP_SKIP_KASAN_POISON) +#define __GFP_SKIP_KASAN_UNPOISON ((__force gfp_t)___GFP_SKIP_KASAN_UNPOISON) +#define __GFP_SKIP_KASAN_POISON ((__force gfp_t)___GFP_SKIP_KASAN_POISON) /* Disable lockdep for GFP context tracking */ #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) /* Room for N __GFP_FOO bits */ -#define __GFP_BITS_SHIFT (24 + \ - IS_ENABLED(CONFIG_KASAN_HW_TAGS) + \ +#define __GFP_BITS_SHIFT (24 + \ + 2 * IS_ENABLED(CONFIG_KASAN_HW_TAGS) + \ IS_ENABLED(CONFIG_LOCKDEP)) #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index cb4520374e2c..134c45e62d91 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -52,8 +52,9 @@ {(unsigned long)__GFP_ZEROTAGS, "__GFP_ZEROTAGS"} \ #ifdef CONFIG_KASAN_HW_TAGS -#define __def_gfpflag_names_kasan \ - , {(unsigned long)__GFP_SKIP_KASAN_POISON, "__GFP_SKIP_KASAN_POISON"} +#define __def_gfpflag_names_kasan , \ + {(unsigned long)__GFP_SKIP_KASAN_POISON, "__GFP_SKIP_KASAN_POISON"}, \ + {(unsigned long)__GFP_SKIP_KASAN_UNPOISON, "__GFP_SKIP_KASAN_UNPOISON"} #else #define __def_gfpflag_names_kasan #endif -- cgit v1.2.3 From 9353ffa6e9e90d2b6348209cf2b95a8ffee18711 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 24 Mar 2022 18:11:29 -0700 Subject: kasan, page_alloc: allow skipping memory init for HW_TAGS Add a new GFP flag __GFP_SKIP_ZERO that allows to skip memory initialization. The flag is only effective with HW_TAGS KASAN. This flag will be used by vmalloc code for page_alloc allocations backing vmalloc() mappings in a following patch. The reason to skip memory initialization for these pages in page_alloc is because vmalloc code will be initializing them instead. With the current implementation, when __GFP_SKIP_ZERO is provided, __GFP_ZEROTAGS is ignored. This doesn't matter, as these two flags are never provided at the same time. However, if this is changed in the future, this particular implementation detail can be changed as well. Link: https://lkml.kernel.org/r/0d53efeff345de7d708e0baa0d8829167772521e.1643047180.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Acked-by: Marco Elver Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Mark Rutland Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 18 +++++++++++------- include/trace/events/mmflags.h | 1 + 2 files changed, 12 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 688a39fde43e..0fa17fb85de5 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -55,14 +55,16 @@ struct vm_area_struct; #define ___GFP_ACCOUNT 0x400000u #define ___GFP_ZEROTAGS 0x800000u #ifdef CONFIG_KASAN_HW_TAGS -#define ___GFP_SKIP_KASAN_UNPOISON 0x1000000u -#define ___GFP_SKIP_KASAN_POISON 0x2000000u +#define ___GFP_SKIP_ZERO 0x1000000u +#define ___GFP_SKIP_KASAN_UNPOISON 0x2000000u +#define ___GFP_SKIP_KASAN_POISON 0x4000000u #else +#define ___GFP_SKIP_ZERO 0 #define ___GFP_SKIP_KASAN_UNPOISON 0 #define ___GFP_SKIP_KASAN_POISON 0 #endif #ifdef CONFIG_LOCKDEP -#define ___GFP_NOLOCKDEP 0x4000000u +#define ___GFP_NOLOCKDEP 0x8000000u #else #define ___GFP_NOLOCKDEP 0 #endif @@ -239,9 +241,10 @@ struct vm_area_struct; * %__GFP_ZERO returns a zeroed page on success. * * %__GFP_ZEROTAGS zeroes memory tags at allocation time if the memory itself - * is being zeroed (either via __GFP_ZERO or via init_on_alloc). This flag is - * intended for optimization: setting memory tags at the same time as zeroing - * memory has minimal additional performace impact. + * is being zeroed (either via __GFP_ZERO or via init_on_alloc, provided that + * __GFP_SKIP_ZERO is not set). This flag is intended for optimization: setting + * memory tags at the same time as zeroing memory has minimal additional + * performace impact. * * %__GFP_SKIP_KASAN_UNPOISON makes KASAN skip unpoisoning on page allocation. * Only effective in HW_TAGS mode. @@ -253,6 +256,7 @@ struct vm_area_struct; #define __GFP_COMP ((__force gfp_t)___GFP_COMP) #define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) #define __GFP_ZEROTAGS ((__force gfp_t)___GFP_ZEROTAGS) +#define __GFP_SKIP_ZERO ((__force gfp_t)___GFP_SKIP_ZERO) #define __GFP_SKIP_KASAN_UNPOISON ((__force gfp_t)___GFP_SKIP_KASAN_UNPOISON) #define __GFP_SKIP_KASAN_POISON ((__force gfp_t)___GFP_SKIP_KASAN_POISON) @@ -261,7 +265,7 @@ struct vm_area_struct; /* Room for N __GFP_FOO bits */ #define __GFP_BITS_SHIFT (24 + \ - 2 * IS_ENABLED(CONFIG_KASAN_HW_TAGS) + \ + 3 * IS_ENABLED(CONFIG_KASAN_HW_TAGS) + \ IS_ENABLED(CONFIG_LOCKDEP)) #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 134c45e62d91..6532119a6bf1 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -53,6 +53,7 @@ #ifdef CONFIG_KASAN_HW_TAGS #define __def_gfpflag_names_kasan , \ + {(unsigned long)__GFP_SKIP_ZERO, "__GFP_SKIP_ZERO"}, \ {(unsigned long)__GFP_SKIP_KASAN_POISON, "__GFP_SKIP_KASAN_POISON"}, \ {(unsigned long)__GFP_SKIP_KASAN_UNPOISON, "__GFP_SKIP_KASAN_UNPOISON"} #else -- cgit v1.2.3 From 23689e91fb22c15b84ac6c22ad9942039792f3af Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 24 Mar 2022 18:11:32 -0700 Subject: kasan, vmalloc: add vmalloc tagging for HW_TAGS Add vmalloc tagging support to HW_TAGS KASAN. The key difference between HW_TAGS and the other two KASAN modes when it comes to vmalloc: HW_TAGS KASAN can only assign tags to physical memory. The other two modes have shadow memory covering every mapped virtual memory region. Make __kasan_unpoison_vmalloc() for HW_TAGS KASAN: - Skip non-VM_ALLOC mappings as HW_TAGS KASAN can only tag a single mapping of normal physical memory; see the comment in the function. - Generate a random tag, tag the returned pointer and the allocation, and initialize the allocation at the same time. - Propagate the tag into the page stucts to allow accesses through page_address(vmalloc_to_page()). The rest of vmalloc-related KASAN hooks are not needed: - The shadow-related ones are fully skipped. - __kasan_poison_vmalloc() is kept as a no-op with a comment. Poisoning and zeroing of physical pages that are backing vmalloc() allocations are skipped via __GFP_SKIP_KASAN_UNPOISON and __GFP_SKIP_ZERO: __kasan_unpoison_vmalloc() does that instead. Enabling CONFIG_KASAN_VMALLOC with HW_TAGS is not yet allowed. Link: https://lkml.kernel.org/r/d19b2e9e59a9abc59d05b72dea8429dcaea739c6.1643047180.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Co-developed-by: Vincenzo Frascino Signed-off-by: Vincenzo Frascino Acked-by: Marco Elver Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Mark Rutland Cc: Peter Collingbourne Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 36 ++++++++++++++++++++++++++++++++---- 1 file changed, 32 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index d3efb6cbd0f5..65fc5285bb59 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -26,6 +26,12 @@ struct kunit_kasan_expectation { #endif +typedef unsigned int __bitwise kasan_vmalloc_flags_t; + +#define KASAN_VMALLOC_NONE 0x00u +#define KASAN_VMALLOC_INIT 0x01u +#define KASAN_VMALLOC_VM_ALLOC 0x02u + #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) #include @@ -397,18 +403,39 @@ static inline void kasan_init_hw_tags(void) { } #ifdef CONFIG_KASAN_VMALLOC +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) + void kasan_populate_early_vm_area_shadow(void *start, unsigned long size); int kasan_populate_vmalloc(unsigned long addr, unsigned long size); void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end); -void *__kasan_unpoison_vmalloc(const void *start, unsigned long size); +#else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ + +static inline void kasan_populate_early_vm_area_shadow(void *start, + unsigned long size) +{ } +static inline int kasan_populate_vmalloc(unsigned long start, + unsigned long size) +{ + return 0; +} +static inline void kasan_release_vmalloc(unsigned long start, + unsigned long end, + unsigned long free_region_start, + unsigned long free_region_end) { } + +#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ + +void *__kasan_unpoison_vmalloc(const void *start, unsigned long size, + kasan_vmalloc_flags_t flags); static __always_inline void *kasan_unpoison_vmalloc(const void *start, - unsigned long size) + unsigned long size, + kasan_vmalloc_flags_t flags) { if (kasan_enabled()) - return __kasan_unpoison_vmalloc(start, size); + return __kasan_unpoison_vmalloc(start, size, flags); return (void *)start; } @@ -435,7 +462,8 @@ static inline void kasan_release_vmalloc(unsigned long start, unsigned long free_region_end) { } static inline void *kasan_unpoison_vmalloc(const void *start, - unsigned long size) + unsigned long size, + kasan_vmalloc_flags_t flags) { return (void *)start; } -- cgit v1.2.3 From f6e39794f4b6da7ca9b77f2f9ad11fd6f0ac83e5 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 24 Mar 2022 18:11:35 -0700 Subject: kasan, vmalloc: only tag normal vmalloc allocations The kernel can use to allocate executable memory. The only supported way to do that is via __vmalloc_node_range() with the executable bit set in the prot argument. (vmap() resets the bit via pgprot_nx()). Once tag-based KASAN modes start tagging vmalloc allocations, executing code from such allocations will lead to the PC register getting a tag, which is not tolerated by the kernel. Only tag the allocations for normal kernel pages. [andreyknvl@google.com: pass KASAN_VMALLOC_PROT_NORMAL to kasan_unpoison_vmalloc()] Link: https://lkml.kernel.org/r/9230ca3d3e40ffca041c133a524191fd71969a8d.1646233925.git.andreyknvl@google.com [andreyknvl@google.com: support tagged vmalloc mappings] Link: https://lkml.kernel.org/r/2f6605e3a358cf64d73a05710cb3da356886ad29.1646233925.git.andreyknvl@google.com [andreyknvl@google.com: don't unintentionally disabled poisoning] Link: https://lkml.kernel.org/r/de4587d6a719232e83c760113e46ed2d4d8da61e.1646757322.git.andreyknvl@google.com Link: https://lkml.kernel.org/r/fbfd9939a4dc375923c9a5c6b9e7ab05c26b8c6b.1643047180.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Acked-by: Marco Elver Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Mark Rutland Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 65fc5285bb59..903b9453931d 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -28,9 +28,10 @@ struct kunit_kasan_expectation { typedef unsigned int __bitwise kasan_vmalloc_flags_t; -#define KASAN_VMALLOC_NONE 0x00u -#define KASAN_VMALLOC_INIT 0x01u -#define KASAN_VMALLOC_VM_ALLOC 0x02u +#define KASAN_VMALLOC_NONE 0x00u +#define KASAN_VMALLOC_INIT 0x01u +#define KASAN_VMALLOC_VM_ALLOC 0x02u +#define KASAN_VMALLOC_PROT_NORMAL 0x04u #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) -- cgit v1.2.3 From ed6d74446cbfb88c747d4b32477a9d46132694db Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 24 Mar 2022 18:12:02 -0700 Subject: kasan: test: support async (again) and asymm modes for HW_TAGS Async mode support has already been implemented in commit e80a76aa1a91 ("kasan, arm64: tests supports for HW_TAGS async mode") but then got accidentally broken in commit 99734b535d9b ("kasan: detect false-positives in tests"). Restore the changes removed by the latter patch and adapt them for asymm mode: add a sync_fault flag to kunit_kasan_expectation that only get set if the MTE fault was synchronous, and reenable MTE on such faults in tests. Also rename kunit_kasan_expectation to kunit_kasan_status and move its definition to mm/kasan/kasan.h from include/linux/kasan.h, as this structure is only internally used by KASAN. Also put the structure definition under IS_ENABLED(CONFIG_KUNIT). Link: https://lkml.kernel.org/r/133970562ccacc93ba19d754012c562351d4a8c8.1645033139.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Cc: Marco Elver Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Andrey Ryabinin Cc: Vincenzo Frascino Cc: Catalin Marinas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 903b9453931d..fe36215807f7 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -19,11 +19,6 @@ struct task_struct; #include #include -/* kasan_data struct is used in KUnit tests for KASAN expected failures */ -struct kunit_kasan_expectation { - bool report_found; -}; - #endif typedef unsigned int __bitwise kasan_vmalloc_flags_t; -- cgit v1.2.3 From 80207910cd71b4e0e87140d165d82b5d3ff69e53 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 24 Mar 2022 18:13:12 -0700 Subject: kasan: move and hide kasan_save_enable/restore_multi_shot - Move kasan_save_enable/restore_multi_shot() declarations to mm/kasan/kasan.h, as there is no need for them to be visible outside of KASAN implementation. - Only define and export these functions when KASAN tests are enabled. - Move their definitions closer to other test-related code in report.c. Link: https://lkml.kernel.org/r/6ba637333b78447f027d775f2d55ab1a40f63c99.1646237226.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Marco Elver Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index fe36215807f7..ceebcb9de7bf 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -267,10 +267,6 @@ static __always_inline bool kasan_check_byte(const void *addr) return true; } - -bool kasan_save_enable_multi_shot(void); -void kasan_restore_multi_shot(bool enabled); - #else /* CONFIG_KASAN */ static inline slab_flags_t kasan_never_merge(void) -- cgit v1.2.3 From 562beb7235abfebdd8366e0664a5c3d1e597b990 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 24 Mar 2022 18:13:27 -0700 Subject: mm/huge_memory: make is_transparent_hugepage() static It's only used inside the huge_memory.c now. Don't export it and make it static. We can thus reduce the size of huge_memory.o a bit. Without this patch: text data bss dec hex filename 32319 2965 4 35288 89d8 mm/huge_memory.o With this patch: text data bss dec hex filename 32042 2957 4 35003 88bb mm/huge_memory.o Link: https://lkml.kernel.org/r/20220302082145.12028-1-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: Muchun Song Reviewed-by: Yang Shi Cc: Matthew Wilcox Cc: William Kucharski Cc: Hugh Dickins Cc: Peter Xu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 0734aff8fa19..2999190adc22 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -183,7 +183,6 @@ unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, void prep_transhuge_page(struct page *page); void free_transhuge_page(struct page *page); -bool is_transparent_hugepage(struct page *page); bool can_split_folio(struct folio *folio, int *pextra_pins); int split_huge_page_to_list(struct page *page, struct list_head *list); @@ -341,11 +340,6 @@ static inline bool transhuge_vma_enabled(struct vm_area_struct *vma, static inline void prep_transhuge_page(struct page *page) {} -static inline bool is_transparent_hugepage(struct page *page) -{ - return false; -} - #define transparent_hugepage_flags 0UL #define thp_get_unmapped_area NULL -- cgit v1.2.3 From 363106c4cefe7d08ca67cc77f3d38d4213190f31 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 24 Mar 2022 18:13:46 -0700 Subject: mm/khugepaged: remove reuse_swap_page() usage reuse_swap_page() currently indicates if we can write to an anon page without COW. A COW is required if the page is shared by multiple processes (either already mapped or via swap entries) or if there is concurrent writeback that cannot tolerate concurrent page modifications. However, in the context of khugepaged we're not actually going to write to a read-only mapped page, we'll copy the page content to our newly allocated THP and map that THP writable. All we have to make sure is that the read-only mapped page we're about to copy won't get reused by another process sharing the page, otherwise, page content would get modified. But that is already guaranteed via multiple mechanisms (e.g., holding a reference, holding the page lock, removing the rmap after copying the page). The swapcache handling was introduced in commit 10359213d05a ("mm: incorporate read-only pages into transparent huge pages") and it sounds like it merely wanted to mimic what do_swap_page() would do when trying to map a page obtained via the swapcache writable. As that logic is unnecessary, let's just remove it, removing the last user of reuse_swap_page(). Link: https://lkml.kernel.org/r/20220131162940.210846-7-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Yang Shi Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Kirill A. Shutemov Cc: Liang Zhang Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oleg Nesterov Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/huge_memory.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index 4fdb14a81108..d651f3437367 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -29,7 +29,6 @@ EM( SCAN_VMA_NULL, "vma_null") \ EM( SCAN_VMA_CHECK, "vma_check_failed") \ EM( SCAN_ADDRESS_RANGE, "not_suitable_address_range") \ - EM( SCAN_SWAP_CACHE_PAGE, "page_swap_cache") \ EM( SCAN_DEL_PAGE_LRU, "could_not_delete_page_from_lru")\ EM( SCAN_ALLOC_HUGE_PAGE_FAIL, "alloc_huge_page_failed") \ EM( SCAN_CGROUP_CHARGE_FAIL, "ccgroup_charge_failed") \ -- cgit v1.2.3 From 03104c2c5db8918030788e607e4af980b2f42bb3 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 24 Mar 2022 18:13:50 -0700 Subject: mm/swapfile: remove stale reuse_swap_page() All users are gone, let's remove it. We'll let SWP_STABLE_WRITES stick around for now, as it might come in handy in the near future. Link: https://lkml.kernel.org/r/20220131162940.210846-8-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Kirill A. Shutemov Cc: Liang Zhang Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oleg Nesterov Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index f37837c614c5..27093b477c5f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -515,7 +515,6 @@ extern int __swp_swapcount(swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); extern struct swap_info_struct *page_swap_info(struct page *); extern struct swap_info_struct *swp_swap_info(swp_entry_t entry); -extern bool reuse_swap_page(struct page *); extern int try_to_free_swap(struct page *); struct backing_dev_info; extern int init_swap_address_space(unsigned int type, unsigned long nr_pages); @@ -681,9 +680,6 @@ static inline int swp_swapcount(swp_entry_t entry) return 0; } -#define reuse_swap_page(page) \ - (page_trans_huge_mapcount(page) == 1) - static inline int try_to_free_swap(struct page *page) { return 0; -- cgit v1.2.3 From 55c62fa7c53368a9011cd1276c001a1469078c6a Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 24 Mar 2022 18:13:53 -0700 Subject: mm/huge_memory: remove stale page_trans_huge_mapcount() All users are gone, let's remove it. Link: https://lkml.kernel.org/r/20220131162940.210846-9-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Kirill A. Shutemov Cc: Liang Zhang Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oleg Nesterov Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7a3dd7e617e4..e34edb775334 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -834,16 +834,11 @@ static inline int total_mapcount(struct page *page) return folio_mapcount(page_folio(page)); } -int page_trans_huge_mapcount(struct page *page); #else static inline int total_mapcount(struct page *page) { return page_mapcount(page); } -static inline int page_trans_huge_mapcount(struct page *page) -{ - return page_mapcount(page); -} #endif static inline struct page *virt_to_head_page(const void *x) -- cgit v1.2.3 From 566d3362885aab04d6b0f885f12db3176ca3a032 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 24 Mar 2022 18:13:59 -0700 Subject: mm: warn on deleting redirtied only if accounted filemap_unaccount_folio() has a WARN_ON_ONCE(folio_test_dirty(folio)). It is good to warn of late dirtying on a persistent filesystem, but late dirtying on tmpfs can only lose data which is expected to be thrown away; and it's a pity if that warning comes ONCE on tmpfs, then hides others which really matter. Make it conditional on mapping_cap_writeback(). Cleanup: then folio_account_cleaned() no longer needs to check that for itself, and so no longer needs to know the mapping. Link: https://lkml.kernel.org/r/b5a1106c-7226-a5c6-ad41-ad4832cae1f@google.com Signed-off-by: Hugh Dickins Cc: Matthew Wilcox Cc: Jan Kara Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 58f395f3febe..a8d0b327b066 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1009,8 +1009,7 @@ static inline void __set_page_dirty(struct page *page, { __folio_mark_dirty(page_folio(page), mapping, warn); } -void folio_account_cleaned(struct folio *folio, struct address_space *mapping, - struct bdi_writeback *wb); +void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb); void __folio_cancel_dirty(struct folio *folio); static inline void folio_cancel_dirty(struct folio *folio) { -- cgit v1.2.3 From 9457056ac426e5ed0671356509c8dcce69f8dee0 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 24 Mar 2022 18:14:12 -0700 Subject: mm: madvise: MADV_DONTNEED_LOCKED MADV_DONTNEED historically rejects mlocked ranges, but with MLOCK_ONFAULT and MCL_ONFAULT allowing to mlock without populating, there are valid use cases for depopulating locked ranges as well. Users mlock memory to protect secrets. There are allocators for secure buffers that want in-use memory generally mlocked, but cleared and invalidated memory to give up the physical pages. This could be done with explicit munlock -> mlock calls on free -> alloc of course, but that adds two unnecessary syscalls, heavy mmap_sem write locks, vma splits and re-merges - only to get rid of the backing pages. Users also mlockall(MCL_ONFAULT) to suppress sustained paging, but are okay with on-demand initial population. It seems valid to selectively free some memory during the lifetime of such a process, without having to mess with its overall policy. Why add a separate flag? Isn't this a pretty niche usecase? - MADV_DONTNEED has been bailing on locked vmas forever. It's at least conceivable that someone, somewhere is relying on mlock to protect data from perhaps broader invalidation calls. Changing this behavior now could lead to quiet data corruption. - It also clarifies expectations around MADV_FREE and maybe MADV_REMOVE. It avoids the situation where one quietly behaves different than the others. MADV_FREE_LOCKED can be added later. - The combination of mlock() and madvise() in the first place is probably niche. But where it happens, I'd say that dropping pages from a locked region once they don't contain secrets or won't page anymore is much saner than relying on mlock to protect memory from speculative or errant invalidation calls. It's just that we can't change the default behavior because of the two previous points. Given that, an explicit new flag seems to make the most sense. [hannes@cmpxchg.org: fix mips build] Link: https://lkml.kernel.org/r/20220304171912.305060-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Reviewed-by: Mike Kravetz Reviewed-by: Shakeel Butt Acked-by: Vlastimil Babka Cc: Nadav Amit Cc: David Hildenbrand Cc: Dr. David Alan Gilbert Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/asm-generic/mman-common.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h index 1567a3294c3d..6c1aa92a92e4 100644 --- a/include/uapi/asm-generic/mman-common.h +++ b/include/uapi/asm-generic/mman-common.h @@ -75,6 +75,8 @@ #define MADV_POPULATE_READ 22 /* populate (prefault) page tables readable */ #define MADV_POPULATE_WRITE 23 /* populate (prefault) page tables writable */ +#define MADV_DONTNEED_LOCKED 24 /* like DONTNEED, but drop locked pages too */ + /* compatibility flags */ #define MAP_FILE 0 -- cgit v1.2.3 From caaf2ae712b7cc3c7717898fe267dbf882a502ef Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Mon, 24 Jan 2022 14:03:24 +0100 Subject: dma-buf: Add dma_fence_array_for_each (v2) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a helper to iterate over all fences in a dma_fence_array object. v2 (Jason Ekstrand) - Return NULL from dma_fence_array_first if head == NULL. This matches the iterator behavior of dma_fence_chain_for_each in that it iterates zero times if head == NULL. - Return NULL from dma_fence_array_next if index > array->num_fences. Signed-off-by: Jason Ekstrand Reviewed-by: Jason Ekstrand Reviewed-by: Christian König Cc: Daniel Vetter Cc: Maarten Lankhorst Link: https://patchwork.freedesktop.org/patch/msgid/20210610210925.642582-2-jason@jlekstrand.net Signed-off-by: Christian König --- include/linux/dma-fence-array.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/linux/dma-fence-array.h b/include/linux/dma-fence-array.h index fec374f69e12..e34dcb0bb462 100644 --- a/include/linux/dma-fence-array.h +++ b/include/linux/dma-fence-array.h @@ -61,6 +61,19 @@ to_dma_fence_array(struct dma_fence *fence) return container_of(fence, struct dma_fence_array, base); } +/** + * dma_fence_array_for_each - iterate over all fences in array + * @fence: current fence + * @index: index into the array + * @head: potential dma_fence_array object + * + * Test if @array is a dma_fence_array object and if yes iterate over all fences + * in the array. If not just iterate over the fence in @array itself. + */ +#define dma_fence_array_for_each(fence, index, head) \ + for (index = 0, fence = dma_fence_array_first(head); fence; \ + ++(index), fence = dma_fence_array_next(head, index)) + struct dma_fence_array *dma_fence_array_create(int num_fences, struct dma_fence **fences, u64 context, unsigned seqno, @@ -68,4 +81,8 @@ struct dma_fence_array *dma_fence_array_create(int num_fences, bool dma_fence_match_context(struct dma_fence *fence, u64 context); +struct dma_fence *dma_fence_array_first(struct dma_fence *head); +struct dma_fence *dma_fence_array_next(struct dma_fence *head, + unsigned int index); + #endif /* __LINUX_DMA_FENCE_ARRAY_H */ -- cgit v1.2.3 From 64a8f92fd783e750cdb81af75942dcd53bbf61bd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Fri, 11 Mar 2022 10:27:53 +0100 Subject: dma-buf: add dma_fence_unwrap v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a general purpose helper to deep dive into dma_fence_chain/dma_fence_array structures and iterate over all the fences in them. This is useful when we need to flatten out all fences in those structures. v2: some selftests cleanup, improved function naming and documentation Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220311110244.1245-1-christian.koenig@amd.com --- include/linux/dma-fence-array.h | 2 + include/linux/dma-fence-chain.h | 2 + include/linux/dma-fence-unwrap.h | 95 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 99 insertions(+) create mode 100644 include/linux/dma-fence-unwrap.h (limited to 'include') diff --git a/include/linux/dma-fence-array.h b/include/linux/dma-fence-array.h index e34dcb0bb462..ec7f25def392 100644 --- a/include/linux/dma-fence-array.h +++ b/include/linux/dma-fence-array.h @@ -69,6 +69,8 @@ to_dma_fence_array(struct dma_fence *fence) * * Test if @array is a dma_fence_array object and if yes iterate over all fences * in the array. If not just iterate over the fence in @array itself. + * + * For a deep dive iterator see dma_fence_unwrap_for_each(). */ #define dma_fence_array_for_each(fence, index, head) \ for (index = 0, fence = dma_fence_array_first(head); fence; \ diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index 10d51bcdf7b7..4bdf0b96da28 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -112,6 +112,8 @@ static inline void dma_fence_chain_free(struct dma_fence_chain *chain) * * Iterate over all fences in the chain. We keep a reference to the current * fence while inside the loop which must be dropped when breaking out. + * + * For a deep dive iterator see dma_fence_unwrap_for_each(). */ #define dma_fence_chain_for_each(iter, head) \ for (iter = dma_fence_get(head); iter; \ diff --git a/include/linux/dma-fence-unwrap.h b/include/linux/dma-fence-unwrap.h new file mode 100644 index 000000000000..77e335a1bcac --- /dev/null +++ b/include/linux/dma-fence-unwrap.h @@ -0,0 +1,95 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * fence-chain: chain fences together in a timeline + * + * Copyright (C) 2022 Advanced Micro Devices, Inc. + * Authors: + * Christian König + */ + +#ifndef __LINUX_DMA_FENCE_UNWRAP_H +#define __LINUX_DMA_FENCE_UNWRAP_H + +#include +#include + +/** + * struct dma_fence_unwrap - cursor into the container structure + * + * Should be used with dma_fence_unwrap_for_each() iterator macro. + */ +struct dma_fence_unwrap { + /** + * @chain: potential dma_fence_chain, but can be other fence as well + */ + struct dma_fence *chain; + /** + * @array: potential dma_fence_array, but can be other fence as well + */ + struct dma_fence *array; + /** + * @index: last returned index if @array is really a dma_fence_array + */ + unsigned int index; +}; + +/* Internal helper to start new array iteration, don't use directly */ +static inline struct dma_fence * +__dma_fence_unwrap_array(struct dma_fence_unwrap * cursor) +{ + cursor->array = dma_fence_chain_contained(cursor->chain); + cursor->index = 0; + return dma_fence_array_first(cursor->array); +} + +/** + * dma_fence_unwrap_first - return the first fence from fence containers + * @head: the entrypoint into the containers + * @cursor: current position inside the containers + * + * Unwraps potential dma_fence_chain/dma_fence_array containers and return the + * first fence. + */ +static inline struct dma_fence * +dma_fence_unwrap_first(struct dma_fence *head, struct dma_fence_unwrap *cursor) +{ + cursor->chain = dma_fence_get(head); + return __dma_fence_unwrap_array(cursor); +} + +/** + * dma_fence_unwrap_next - return the next fence from a fence containers + * @cursor: current position inside the containers + * + * Continue unwrapping the dma_fence_chain/dma_fence_array containers and return + * the next fence from them. + */ +static inline struct dma_fence * +dma_fence_unwrap_next(struct dma_fence_unwrap *cursor) +{ + struct dma_fence *tmp; + + ++cursor->index; + tmp = dma_fence_array_next(cursor->array, cursor->index); + if (tmp) + return tmp; + + cursor->chain = dma_fence_chain_walk(cursor->chain); + return __dma_fence_unwrap_array(cursor); +} + +/** + * dma_fence_unwrap_for_each - iterate over all fences in containers + * @fence: current fence + * @cursor: current position inside the containers + * @head: starting point for the iterator + * + * Unwrap dma_fence_chain and dma_fence_array containers and deep dive into all + * potential fences in them. If @head is just a normal fence only that one is + * returned. + */ +#define dma_fence_unwrap_for_each(fence, cursor, head) \ + for (fence = dma_fence_unwrap_first(head, cursor); fence; \ + fence = dma_fence_unwrap_next(cursor)) + +#endif -- cgit v1.2.3 From 034d47b25b2ce627f1e1b04242d72db4180f3525 Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Fri, 25 Mar 2022 09:49:16 +0000 Subject: drm/i915/uapi: Document DRM_I915_QUERY_HWCONFIG_BLOB UAPI with absolutely no documentation should not have been added - clarify blob format and content will be described externally. Fixes: 78e1fb3112c0 ("drm/i915/uapi: Add query for hwconfig blob") Signed-off-by: Tvrtko Ursulin Co-developed-by: Jordan Justen Cc: Jon Bloomfield Cc: Daniel Vetter Cc: John Harrison Cc: Jon Ewins Cc: Joonas Lahtinen Cc: Rodrigo Vivi Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220325094916.2186367-1-tvrtko.ursulin@linux.intel.com [tursulin: Fixed spelling s/meading/meaning/.] --- include/uapi/drm/i915_drm.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 071ffd9d51f1..9ab021c4d632 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -2683,6 +2683,9 @@ struct drm_i915_perf_oa_config { * * The behaviour is determined by the @query_id. Note that exactly what * @data_ptr is also depends on the specific @query_id. + * + * For specific queries see: + * * `GuC HWCONFIG blob uAPI`_ */ struct drm_i915_query_item { /** @query_id: The id for this query */ @@ -3135,6 +3138,16 @@ struct drm_i915_query_memory_regions { struct drm_i915_memory_region_info regions[]; }; +/** + * DOC: GuC HWCONFIG blob uAPI + * + * The GuC produces a blob with information about the current device. + * i915 reads this blob from GuC and makes it available via this uAPI. + * + * The format and meaning of the blob content are documented in the + * Programmer's Reference Manual. + */ + /** * struct drm_i915_gem_create_ext - Existing gem_create behaviour, with added * extension support using struct i915_user_extension. -- cgit v1.2.3 From 421ab1be43bd015ffe744f4ea25df4f19d1ce6fe Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 25 Mar 2022 10:37:31 -0400 Subject: SUNRPC: Do not dereference non-socket transports in sysfs Do not cast the struct xprt to a sock_xprt unless we know it is a UDP or TCP transport. Otherwise the call to lock the mutex will scribble over whatever structure is actually there. This has been seen to cause hard system lockups when the underlying transport was RDMA. Fixes: b49ea673e119 ("SUNRPC: lock against ->sock changing during sysfs read") Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 3 +++ include/linux/sunrpc/xprtsock.h | 1 - 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 955ea4d7af0b..eef5e87c03b4 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -139,6 +139,9 @@ struct rpc_xprt_ops { void (*rpcbind)(struct rpc_task *task); void (*set_port)(struct rpc_xprt *xprt, unsigned short port); void (*connect)(struct rpc_xprt *xprt, struct rpc_task *task); + int (*get_srcaddr)(struct rpc_xprt *xprt, char *buf, + size_t buflen); + unsigned short (*get_srcport)(struct rpc_xprt *xprt); int (*buf_alloc)(struct rpc_task *task); void (*buf_free)(struct rpc_task *task); void (*prepare_request)(struct rpc_rqst *req); diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 3eb0079669c5..38284f25eddf 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -10,7 +10,6 @@ int init_socket_xprt(void); void cleanup_socket_xprt(void); -unsigned short get_srcport(struct rpc_xprt *); #define RPC_MIN_RESVPORT (1U) #define RPC_MAX_RESVPORT (65535U) -- cgit v1.2.3 From bddac7c1e02ba47f0570e494c9289acea3062cc1 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 26 Mar 2022 10:42:04 -0700 Subject: Revert "swiotlb: rework "fix info leak with DMA_FROM_DEVICE"" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit aa6f8dcbab473f3a3c7454b74caa46d36cdc5d13. It turns out this breaks at least the ath9k wireless driver, and possibly others. What the ath9k driver does on packet receive is to set up the DMA transfer with: int ath_rx_init(..) .. bf->bf_buf_addr = dma_map_single(sc->dev, skb->data, common->rx_bufsize, DMA_FROM_DEVICE); and then the receive logic (through ath_rx_tasklet()) will fetch incoming packets static bool ath_edma_get_buffers(..) .. dma_sync_single_for_cpu(sc->dev, bf->bf_buf_addr, common->rx_bufsize, DMA_FROM_DEVICE); ret = ath9k_hw_process_rxdesc_edma(ah, rs, skb->data); if (ret == -EINPROGRESS) { /*let device gain the buffer again*/ dma_sync_single_for_device(sc->dev, bf->bf_buf_addr, common->rx_bufsize, DMA_FROM_DEVICE); return false; } and it's worth noting how that first DMA sync: dma_sync_single_for_cpu(..DMA_FROM_DEVICE); is there to make sure the CPU can read the DMA buffer (possibly by copying it from the bounce buffer area, or by doing some cache flush). The iommu correctly turns that into a "copy from bounce bufer" so that the driver can look at the state of the packets. In the meantime, the device may continue to write to the DMA buffer, but we at least have a snapshot of the state due to that first DMA sync. But that _second_ DMA sync: dma_sync_single_for_device(..DMA_FROM_DEVICE); is telling the DMA mapping that the CPU wasn't interested in the area because the packet wasn't there. In the case of a DMA bounce buffer, that is a no-op. Note how it's not a sync for the CPU (the "for_device()" part), and it's not a sync for data written by the CPU (the "DMA_FROM_DEVICE" part). Or rather, it _should_ be a no-op. That's what commit aa6f8dcbab47 broke: it made the code bounce the buffer unconditionally, and changed the DMA_FROM_DEVICE to just unconditionally and illogically be DMA_TO_DEVICE. [ Side note: purely within the confines of the swiotlb driver it wasn't entirely illogical: The reason it did that odd DMA_FROM_DEVICE -> DMA_TO_DEVICE conversion thing is because inside the swiotlb driver, it uses just a swiotlb_bounce() helper that doesn't care about the whole distinction of who the sync is for - only which direction to bounce. So it took the "sync for device" to mean that the CPU must have been the one writing, and thought it meant DMA_TO_DEVICE. ] Also note how the commentary in that commit was wrong, probably due to that whole confusion, claiming that the commit makes the swiotlb code "bounce unconditionally (that is, also when dir == DMA_TO_DEVICE) in order do avoid synchronising back stale data from the swiotlb buffer" which is nonsensical for two reasons: - that "also when dir == DMA_TO_DEVICE" is nonsensical, as that was exactly when it always did - and should do - the bounce. - since this is a sync for the device (not for the CPU), we're clearly fundamentally not coping back stale data from the bounce buffers at all, because we'd be copying *to* the bounce buffers. So that commit was just very confused. It confused the direction of the synchronization (to the device, not the cpu) with the direction of the DMA (from the device). Reported-and-bisected-by: Oleksandr Natalenko Reported-by: Olha Cherevyk Cc: Halil Pasic Cc: Christoph Hellwig Cc: Kalle Valo Cc: Robin Murphy Cc: Toke Høiland-Jørgensen Cc: Maxime Bizon Cc: Johannes Berg Signed-off-by: Linus Torvalds --- include/linux/dma-mapping.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index dca2b1355bb1..6150d11a607e 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -61,6 +61,14 @@ */ #define DMA_ATTR_PRIVILEGED (1UL << 9) +/* + * This is a hint to the DMA-mapping subsystem that the device is expected + * to overwrite the entire mapped size, thus the caller does not require any + * of the previous buffer contents to be preserved. This allows + * bounce-buffering implementations to optimise DMA_FROM_DEVICE transfers. + */ +#define DMA_ATTR_OVERWRITE (1UL << 10) + /* * A dma_addr_t can hold any valid DMA or bus address for the platform. It can * be given to a device to use as a DMA source or target. It is specific to a -- cgit v1.2.3 From e795df5bbcf27abd6250a0fb9fa8ad7a9748959f Mon Sep 17 00:00:00 2001 From: Andrey Grodzovsky Date: Mon, 28 Mar 2022 09:25:32 -0400 Subject: drm/sched: Fix htmldoc warning. Fixes the warning. Signed-off-by: Andrey Grodzovsky Reported-by: Stephen Rothwell Reviewed-by: Alex Deucher Link: https://patchwork.freedesktop.org/patch/msgid/20220328132532.406572-1-andrey.grodzovsky@amd.com --- include/drm/gpu_scheduler.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 944f83ef9f2e..0fca8f38bee4 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -270,6 +270,7 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f); * @sched: the scheduler instance on which this job is scheduled. * @s_fence: contains the fences for the scheduling of job. * @finish_cb: the callback for the finished fence. + * @work: Helper to reschdeule job kill to different context. * @id: a unique id assigned to each job scheduled on the scheduler. * @karma: increment on every hang caused by this job. If this exceeds the hang * limit of the scheduler then the job is marked guilty and will not -- cgit v1.2.3 From 6a9b028994025f5033f10d1da30b29dfdc713384 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Fri, 16 Jul 2021 14:00:10 +0200 Subject: drm/ttm: move the LRU into resource handling v4 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This way we finally fix the problem that new resource are not immediately evict-able after allocation. That has caused numerous problems including OOM on GDS handling and not being able to use TTM as general resource manager. v2: stop assuming in ttm_resource_fini that res->bo is still valid. v3: cleanup kerneldoc, add more lockdep annotation v4: consistently use res->num_pages Signed-off-by: Christian König Tested-by: Bas Nieuwenhuizen Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220321132601.2161-1-christian.koenig@amd.com --- include/drm/ttm/ttm_bo_api.h | 16 ---------------- include/drm/ttm/ttm_bo_driver.h | 29 +---------------------------- include/drm/ttm/ttm_resource.h | 40 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 41 insertions(+), 44 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index c17b2df9178b..3da77fc54552 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -55,8 +55,6 @@ struct ttm_placement; struct ttm_place; -struct ttm_lru_bulk_move; - /** * enum ttm_bo_type * @@ -94,7 +92,6 @@ struct ttm_tt; * @ttm: TTM structure holding system pages. * @evicted: Whether the object was evicted without user-space knowing. * @deleted: True if the object is only a zombie and already deleted. - * @lru: List head for the lru list. * @ddestroy: List head for the delayed destroy list. * @swap: List head for swap LRU list. * @moving: Fence set when BO is moving @@ -143,7 +140,6 @@ struct ttm_buffer_object { * Members protected by the bdev::lru_lock. */ - struct list_head lru; struct list_head ddestroy; /** @@ -295,7 +291,6 @@ void ttm_bo_put(struct ttm_buffer_object *bo); * ttm_bo_move_to_lru_tail * * @bo: The buffer object. - * @mem: Resource object. * @bulk: optional bulk move structure to remember BO positions * * Move this BO to the tail of all lru lists used to lookup and reserve an @@ -303,19 +298,8 @@ void ttm_bo_put(struct ttm_buffer_object *bo); * held, and is used to make a BO less likely to be considered for eviction. */ void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo, - struct ttm_resource *mem, struct ttm_lru_bulk_move *bulk); -/** - * ttm_bo_bulk_move_lru_tail - * - * @bulk: bulk move structure - * - * Bulk move BOs to the LRU tail, only valid to use when driver makes sure that - * BO order never changes. Should be called with ttm_global::lru_lock held. - */ -void ttm_bo_bulk_move_lru_tail(struct ttm_lru_bulk_move *bulk); - /** * ttm_bo_lock_delayed_workqueue * diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 5f087575194b..6c7352e13708 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -45,33 +45,6 @@ #include "ttm_tt.h" #include "ttm_pool.h" -/** - * struct ttm_lru_bulk_move_pos - * - * @first: first BO in the bulk move range - * @last: last BO in the bulk move range - * - * Positions for a lru bulk move. - */ -struct ttm_lru_bulk_move_pos { - struct ttm_buffer_object *first; - struct ttm_buffer_object *last; -}; - -/** - * struct ttm_lru_bulk_move - * - * @tt: first/last lru entry for BOs in the TT domain - * @vram: first/last lru entry for BOs in the VRAM domain - * @swap: first/last lru entry for BOs on the swap list - * - * Helper structure for bulk moves on the LRU list. - */ -struct ttm_lru_bulk_move { - struct ttm_lru_bulk_move_pos tt[TTM_MAX_BO_PRIORITY]; - struct ttm_lru_bulk_move_pos vram[TTM_MAX_BO_PRIORITY]; -}; - /* * ttm_bo.c */ @@ -182,7 +155,7 @@ static inline void ttm_bo_move_to_lru_tail_unlocked(struct ttm_buffer_object *bo) { spin_lock(&bo->bdev->lru_lock); - ttm_bo_move_to_lru_tail(bo, bo->resource, NULL); + ttm_bo_move_to_lru_tail(bo, NULL); spin_unlock(&bo->bdev->lru_lock); } diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index 323c14a30c6b..f8f766b092a6 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -26,10 +26,12 @@ #define _TTM_RESOURCE_H_ #include +#include #include #include #include #include + #include #include #include @@ -179,6 +181,38 @@ struct ttm_resource { uint32_t placement; struct ttm_bus_placement bus; struct ttm_buffer_object *bo; + + /** + * @lru: Least recently used list, see &ttm_resource_manager.lru + */ + struct list_head lru; +}; + +/** + * struct ttm_lru_bulk_move_pos + * + * @first: first res in the bulk move range + * @last: last res in the bulk move range + * + * Positions for a lru bulk move. + */ +struct ttm_lru_bulk_move_pos { + struct ttm_resource *first; + struct ttm_resource *last; +}; + +/** + * struct ttm_lru_bulk_move + * + * @tt: first/last lru entry for resources in the TT domain + * @vram: first/last lru entry for resources in the VRAM domain + * + * Container for the current bulk move state. Should be used with + * ttm_lru_bulk_move_init() and ttm_bo_move_to_lru_tail(). + */ +struct ttm_lru_bulk_move { + struct ttm_lru_bulk_move_pos tt[TTM_MAX_BO_PRIORITY]; + struct ttm_lru_bulk_move_pos vram[TTM_MAX_BO_PRIORITY]; }; /** @@ -267,6 +301,12 @@ ttm_resource_manager_cleanup(struct ttm_resource_manager *man) man->move = NULL; } +void ttm_lru_bulk_move_init(struct ttm_lru_bulk_move *bulk); +void ttm_lru_bulk_move_tail(struct ttm_lru_bulk_move *bulk); + +void ttm_resource_move_to_lru_tail(struct ttm_resource *res, + struct ttm_lru_bulk_move *bulk); + void ttm_resource_init(struct ttm_buffer_object *bo, const struct ttm_place *place, struct ttm_resource *res); -- cgit v1.2.3 From 5d05b988f1c0fddc4aaffa5fa3c3f5a9e7b84d5b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Tue, 8 Jun 2021 11:13:21 +0200 Subject: drm/ttm: add resource iterator v4 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Instead of duplicating that at different places add an iterator over all the resources in a resource manager. v2: add lockdep annotation and kerneldoc v3: fix various bugs pointed out by Felix v4: simplify the code a bit more Signed-off-by: Christian König Tested-by: Bas Nieuwenhuizen Reviewed-by: Daniel Vetter (v2) Reviewed-by: Felix Kuehling Link: https://patchwork.freedesktop.org/patch/msgid/20220321132601.2161-2-christian.koenig@amd.com --- include/drm/ttm/ttm_resource.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index f8f766b092a6..d8e880110dc6 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -188,6 +188,17 @@ struct ttm_resource { struct list_head lru; }; +/** + * struct ttm_resource_cursor + * + * @priority: the current priority + * + * Cursor to iterate over the resources in a manager. + */ +struct ttm_resource_cursor { + unsigned int priority; +}; + /** * struct ttm_lru_bulk_move_pos * @@ -333,6 +344,18 @@ uint64_t ttm_resource_manager_usage(struct ttm_resource_manager *man); void ttm_resource_manager_debug(struct ttm_resource_manager *man, struct drm_printer *p); +struct ttm_resource * +ttm_resource_manager_first(struct ttm_resource_manager *man, + struct ttm_resource_cursor *cursor); +struct ttm_resource * +ttm_resource_manager_next(struct ttm_resource_manager *man, + struct ttm_resource_cursor *cursor, + struct ttm_resource *res); + +#define ttm_resource_manager_for_each_res(man, cursor, res) \ + for (res = ttm_resource_manager_first(man, cursor); res; \ + res = ttm_resource_manager_next(man, cursor, res)) + struct ttm_kmap_iter * ttm_kmap_iter_iomap_init(struct ttm_kmap_iter_iomap *iter_io, struct io_mapping *iomap, -- cgit v1.2.3 From b0e2c9ea5afc769476fd85a6a28cc370ddd44ee8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Mon, 24 Jan 2022 09:37:43 +0100 Subject: drm/ttm: allow bulk moves for all domains MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Not just TT and VRAM. Signed-off-by: Christian König Reviewed-by: Daniel Vetter Tested-by: Bas Nieuwenhuizen Link: https://patchwork.freedesktop.org/patch/msgid/20220321132601.2161-3-christian.koenig@amd.com --- include/drm/ttm/ttm_device.h | 2 -- include/drm/ttm/ttm_resource.h | 4 ++-- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_device.h b/include/drm/ttm/ttm_device.h index 0a4ddec78d8f..425150f35fbe 100644 --- a/include/drm/ttm/ttm_device.h +++ b/include/drm/ttm/ttm_device.h @@ -30,8 +30,6 @@ #include #include -#define TTM_NUM_MEM_TYPES 8 - struct ttm_device; struct ttm_placement; struct ttm_buffer_object; diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index d8e880110dc6..62e7bb782596 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -37,6 +37,7 @@ #include #define TTM_MAX_BO_PRIORITY 4U +#define TTM_NUM_MEM_TYPES 8 struct ttm_device; struct ttm_resource_manager; @@ -222,8 +223,7 @@ struct ttm_lru_bulk_move_pos { * ttm_lru_bulk_move_init() and ttm_bo_move_to_lru_tail(). */ struct ttm_lru_bulk_move { - struct ttm_lru_bulk_move_pos tt[TTM_MAX_BO_PRIORITY]; - struct ttm_lru_bulk_move_pos vram[TTM_MAX_BO_PRIORITY]; + struct ttm_lru_bulk_move_pos pos[TTM_NUM_MEM_TYPES][TTM_MAX_BO_PRIORITY]; }; /** -- cgit v1.2.3 From 901c7280ca0d5e2b4a8929fbe0bfb007ac2a6544 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 28 Mar 2022 11:37:05 -0700 Subject: Reinstate some of "swiotlb: rework "fix info leak with DMA_FROM_DEVICE"" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Halil Pasic points out [1] that the full revert of that commit (revert in bddac7c1e02b), and that a partial revert that only reverts the problematic case, but still keeps some of the cleanups is probably better.  And that partial revert [2] had already been verified by Oleksandr Natalenko to also fix the issue, I had just missed that in the long discussion. So let's reinstate the cleanups from commit aa6f8dcbab47 ("swiotlb: rework "fix info leak with DMA_FROM_DEVICE""), and effectively only revert the part that caused problems. Link: https://lore.kernel.org/all/20220328013731.017ae3e3.pasic@linux.ibm.com/ [1] Link: https://lore.kernel.org/all/20220324055732.GB12078@lst.de/ [2] Link: https://lore.kernel.org/all/4386660.LvFx2qVVIh@natalenko.name/ [3] Suggested-by: Halil Pasic Tested-by: Oleksandr Natalenko Cc: Christoph Hellwig" Signed-off-by: Linus Torvalds --- include/linux/dma-mapping.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 6150d11a607e..dca2b1355bb1 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -61,14 +61,6 @@ */ #define DMA_ATTR_PRIVILEGED (1UL << 9) -/* - * This is a hint to the DMA-mapping subsystem that the device is expected - * to overwrite the entire mapped size, thus the caller does not require any - * of the previous buffer contents to be preserved. This allows - * bounce-buffering implementations to optimise DMA_FROM_DEVICE transfers. - */ -#define DMA_ATTR_OVERWRITE (1UL << 10) - /* * A dma_addr_t can hold any valid DMA or bus address for the platform. It can * be given to a device to use as a DMA source or target. It is specific to a -- cgit v1.2.3 From 504c1cabe325df65c18ef38365ddd1a41c6b591b Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Tue, 25 Jan 2022 21:22:21 +0800 Subject: mm/balloon_compaction: make balloon page compaction callbacks static Since commit b1123ea6d3b3 ("mm: balloon: use general non-lru movable page feature"), these functions are called via balloon_aops callbacks. They're not called directly outside this file. So make them static and clean up the relevant code. Signed-off-by: Miaohe Lin Link: https://lore.kernel.org/r/20220125132221.2220-1-linmiaohe@huawei.com Signed-off-by: Michael S. Tsirkin Reviewed-by: Muchun Song --- include/linux/balloon_compaction.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include') diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h index 338aa27e4773..edb7f6d41faa 100644 --- a/include/linux/balloon_compaction.h +++ b/include/linux/balloon_compaction.h @@ -80,12 +80,6 @@ static inline void balloon_devinfo_init(struct balloon_dev_info *balloon) #ifdef CONFIG_BALLOON_COMPACTION extern const struct address_space_operations balloon_aops; -extern bool balloon_page_isolate(struct page *page, - isolate_mode_t mode); -extern void balloon_page_putback(struct page *page); -extern int balloon_page_migrate(struct address_space *mapping, - struct page *newpage, - struct page *page, enum migrate_mode mode); /* * balloon_page_insert - insert a page into the balloon's page list and make @@ -155,22 +149,6 @@ static inline void balloon_page_delete(struct page *page) list_del(&page->lru); } -static inline bool balloon_page_isolate(struct page *page) -{ - return false; -} - -static inline void balloon_page_putback(struct page *page) -{ - return; -} - -static inline int balloon_page_migrate(struct page *newpage, - struct page *page, enum migrate_mode mode) -{ - return 0; -} - static inline gfp_t balloon_mapping_gfp_mask(void) { return GFP_HIGHUSER; -- cgit v1.2.3 From 90a6951b58e935124eeb7ecd9fbc2426f841ac0c Mon Sep 17 00:00:00 2001 From: Gautam Dawar Date: Tue, 15 Feb 2022 11:04:29 +0530 Subject: Add definition of VIRTIO_F_IN_ORDER feature bit This patch adds the definition of VIRTIO_F_IN_ORDER feature bit in the relevant header file to make it available in QEMU's linux standard header file virtio_config.h, which is updated using scripts/update-linux-headers.sh Signed-off-by: Gautam Dawar Link: https://lore.kernel.org/r/20220215053430.24650-1-gdawar@xilinx.com Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- include/uapi/linux/virtio_config.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h index b5eda06f0d57..f0fb0ae021c0 100644 --- a/include/uapi/linux/virtio_config.h +++ b/include/uapi/linux/virtio_config.h @@ -82,6 +82,12 @@ /* This feature indicates support for the packed virtqueue layout. */ #define VIRTIO_F_RING_PACKED 34 +/* + * Inorder feature indicates that all buffers are used by the device + * in the same order in which they have been made available. + */ +#define VIRTIO_F_IN_ORDER 35 + /* * This feature indicates that memory accesses by the driver and the * device are ordered in a way described by the platform. -- cgit v1.2.3 From 13d640a3e9a3ac7ec694843d3d3b785e85fb8cb8 Mon Sep 17 00:00:00 2001 From: zhenwei pi Date: Wed, 2 Mar 2022 11:39:14 +0800 Subject: virtio_crypto: Introduce VIRTIO_CRYPTO_NOSPC Base on the lastest virtio crypto spec, define VIRTIO_CRYPTO_NOSPC. Reviewed-by: Gonglei Signed-off-by: zhenwei pi Link: https://lore.kernel.org/r/20220302033917.1295334-2-pizhenwei@bytedance.com Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_crypto.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/virtio_crypto.h b/include/uapi/linux/virtio_crypto.h index a03932f10565..1166a49084b0 100644 --- a/include/uapi/linux/virtio_crypto.h +++ b/include/uapi/linux/virtio_crypto.h @@ -408,6 +408,7 @@ struct virtio_crypto_op_data_req { #define VIRTIO_CRYPTO_BADMSG 2 #define VIRTIO_CRYPTO_NOTSUPP 3 #define VIRTIO_CRYPTO_INVSESS 4 /* Invalid session id */ +#define VIRTIO_CRYPTO_NOSPC 5 /* no free session ID */ /* The accelerator hardware is ready */ #define VIRTIO_CRYPTO_S_HW_READY (1 << 0) -- cgit v1.2.3 From 24e19590628b58578748eeaec8140bf9c9dc00d9 Mon Sep 17 00:00:00 2001 From: zhenwei pi Date: Wed, 2 Mar 2022 11:39:15 +0800 Subject: virtio-crypto: introduce akcipher service Introduce asymmetric service definition, asymmetric operations and several well known algorithms. Co-developed-by: lei he Signed-off-by: lei he Signed-off-by: zhenwei pi Link: https://lore.kernel.org/r/20220302033917.1295334-3-pizhenwei@bytedance.com Signed-off-by: Michael S. Tsirkin Reviewed-by: Gonglei --- include/uapi/linux/virtio_crypto.h | 81 +++++++++++++++++++++++++++++++++++++- 1 file changed, 80 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/virtio_crypto.h b/include/uapi/linux/virtio_crypto.h index 1166a49084b0..71a54a6849ca 100644 --- a/include/uapi/linux/virtio_crypto.h +++ b/include/uapi/linux/virtio_crypto.h @@ -37,6 +37,7 @@ #define VIRTIO_CRYPTO_SERVICE_HASH 1 #define VIRTIO_CRYPTO_SERVICE_MAC 2 #define VIRTIO_CRYPTO_SERVICE_AEAD 3 +#define VIRTIO_CRYPTO_SERVICE_AKCIPHER 4 #define VIRTIO_CRYPTO_OPCODE(service, op) (((service) << 8) | (op)) @@ -57,6 +58,10 @@ struct virtio_crypto_ctrl_header { VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AEAD, 0x02) #define VIRTIO_CRYPTO_AEAD_DESTROY_SESSION \ VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AEAD, 0x03) +#define VIRTIO_CRYPTO_AKCIPHER_CREATE_SESSION \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AKCIPHER, 0x04) +#define VIRTIO_CRYPTO_AKCIPHER_DESTROY_SESSION \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AKCIPHER, 0x05) __le32 opcode; __le32 algo; __le32 flag; @@ -180,6 +185,58 @@ struct virtio_crypto_aead_create_session_req { __u8 padding[32]; }; +struct virtio_crypto_rsa_session_para { +#define VIRTIO_CRYPTO_RSA_RAW_PADDING 0 +#define VIRTIO_CRYPTO_RSA_PKCS1_PADDING 1 + __le32 padding_algo; + +#define VIRTIO_CRYPTO_RSA_NO_HASH 0 +#define VIRTIO_CRYPTO_RSA_MD2 1 +#define VIRTIO_CRYPTO_RSA_MD3 2 +#define VIRTIO_CRYPTO_RSA_MD4 3 +#define VIRTIO_CRYPTO_RSA_MD5 4 +#define VIRTIO_CRYPTO_RSA_SHA1 5 +#define VIRTIO_CRYPTO_RSA_SHA256 6 +#define VIRTIO_CRYPTO_RSA_SHA384 7 +#define VIRTIO_CRYPTO_RSA_SHA512 8 +#define VIRTIO_CRYPTO_RSA_SHA224 9 + __le32 hash_algo; +}; + +struct virtio_crypto_ecdsa_session_para { +#define VIRTIO_CRYPTO_CURVE_UNKNOWN 0 +#define VIRTIO_CRYPTO_CURVE_NIST_P192 1 +#define VIRTIO_CRYPTO_CURVE_NIST_P224 2 +#define VIRTIO_CRYPTO_CURVE_NIST_P256 3 +#define VIRTIO_CRYPTO_CURVE_NIST_P384 4 +#define VIRTIO_CRYPTO_CURVE_NIST_P521 5 + __le32 curve_id; + __le32 padding; +}; + +struct virtio_crypto_akcipher_session_para { +#define VIRTIO_CRYPTO_NO_AKCIPHER 0 +#define VIRTIO_CRYPTO_AKCIPHER_RSA 1 +#define VIRTIO_CRYPTO_AKCIPHER_DSA 2 +#define VIRTIO_CRYPTO_AKCIPHER_ECDSA 3 + __le32 algo; + +#define VIRTIO_CRYPTO_AKCIPHER_KEY_TYPE_PUBLIC 1 +#define VIRTIO_CRYPTO_AKCIPHER_KEY_TYPE_PRIVATE 2 + __le32 keytype; + __le32 keylen; + + union { + struct virtio_crypto_rsa_session_para rsa; + struct virtio_crypto_ecdsa_session_para ecdsa; + } u; +}; + +struct virtio_crypto_akcipher_create_session_req { + struct virtio_crypto_akcipher_session_para para; + __u8 padding[36]; +}; + struct virtio_crypto_alg_chain_session_para { #define VIRTIO_CRYPTO_SYM_ALG_CHAIN_ORDER_HASH_THEN_CIPHER 1 #define VIRTIO_CRYPTO_SYM_ALG_CHAIN_ORDER_CIPHER_THEN_HASH 2 @@ -247,6 +304,8 @@ struct virtio_crypto_op_ctrl_req { mac_create_session; struct virtio_crypto_aead_create_session_req aead_create_session; + struct virtio_crypto_akcipher_create_session_req + akcipher_create_session; struct virtio_crypto_destroy_session_req destroy_session; __u8 padding[56]; @@ -266,6 +325,14 @@ struct virtio_crypto_op_header { VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AEAD, 0x00) #define VIRTIO_CRYPTO_AEAD_DECRYPT \ VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AEAD, 0x01) +#define VIRTIO_CRYPTO_AKCIPHER_ENCRYPT \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AKCIPHER, 0x00) +#define VIRTIO_CRYPTO_AKCIPHER_DECRYPT \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AKCIPHER, 0x01) +#define VIRTIO_CRYPTO_AKCIPHER_SIGN \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AKCIPHER, 0x02) +#define VIRTIO_CRYPTO_AKCIPHER_VERIFY \ + VIRTIO_CRYPTO_OPCODE(VIRTIO_CRYPTO_SERVICE_AKCIPHER, 0x03) __le32 opcode; /* algo should be service-specific algorithms */ __le32 algo; @@ -390,6 +457,16 @@ struct virtio_crypto_aead_data_req { __u8 padding[32]; }; +struct virtio_crypto_akcipher_para { + __le32 src_data_len; + __le32 dst_data_len; +}; + +struct virtio_crypto_akcipher_data_req { + struct virtio_crypto_akcipher_para para; + __u8 padding[40]; +}; + /* The request of the data virtqueue's packet */ struct virtio_crypto_op_data_req { struct virtio_crypto_op_header header; @@ -399,6 +476,7 @@ struct virtio_crypto_op_data_req { struct virtio_crypto_hash_data_req hash_req; struct virtio_crypto_mac_data_req mac_req; struct virtio_crypto_aead_data_req aead_req; + struct virtio_crypto_akcipher_data_req akcipher_req; __u8 padding[48]; } u; }; @@ -409,6 +487,7 @@ struct virtio_crypto_op_data_req { #define VIRTIO_CRYPTO_NOTSUPP 3 #define VIRTIO_CRYPTO_INVSESS 4 /* Invalid session id */ #define VIRTIO_CRYPTO_NOSPC 5 /* no free session ID */ +#define VIRTIO_CRYPTO_KEY_REJECTED 6 /* Signature verification failed */ /* The accelerator hardware is ready */ #define VIRTIO_CRYPTO_S_HW_READY (1 << 0) @@ -439,7 +518,7 @@ struct virtio_crypto_config { __le32 max_cipher_key_len; /* Maximum length of authenticated key */ __le32 max_auth_key_len; - __le32 reserve; + __le32 akcipher_algo; /* Maximum size of each crypto request's content */ __le64 max_size; }; -- cgit v1.2.3 From a61280ddddaa45f95b60dd54c05f8e0e5b6810b7 Mon Sep 17 00:00:00 2001 From: Longpeng Date: Tue, 15 Mar 2022 11:25:51 +0800 Subject: vdpa: support exposing the config size to userspace - GET_CONFIG_SIZE: return the size of the virtio config space. The size contains the fields which are conditional on feature bits. Acked-by: Jason Wang Signed-off-by: Longpeng Link: https://lore.kernel.org/r/20220315032553.455-2-longpeng2@huawei.com Signed-off-by: Michael S. Tsirkin Reviewed-by: Stefano Garzarella --- include/linux/vdpa.h | 3 ++- include/uapi/linux/vhost.h | 4 ++++ 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 721089bb4c84..a5269191edda 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -207,7 +207,8 @@ struct vdpa_map_file { * @reset: Reset device * @vdev: vdpa device * Returns integer: success (0) or error (< 0) - * @get_config_size: Get the size of the configuration space + * @get_config_size: Get the size of the configuration space includes + * fields that are conditional on feature bits. * @vdev: vdpa device * Returns size_t: configuration size * @get_config: Read from device specific configuration space diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index c998860d7bbc..bc74e95a273a 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -150,4 +150,8 @@ /* Get the valid iova range */ #define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \ struct vhost_vdpa_iova_range) + +/* Get the config size */ +#define VHOST_VDPA_GET_CONFIG_SIZE _IOR(VHOST_VIRTIO, 0x79, __u32) + #endif -- cgit v1.2.3 From 81d46d693173a5c86a9b0c648eca1817ad5c0ae5 Mon Sep 17 00:00:00 2001 From: Longpeng Date: Tue, 15 Mar 2022 11:25:52 +0800 Subject: vdpa: change the type of nvqs to u32 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Change vdpa_device.nvqs and vhost_vdpa.nvqs to use u32 Signed-off-by: Longpeng Link: https://lore.kernel.org/r/20220315032553.455-3-longpeng2@huawei.com Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang Signed-off-by: Longpeng <longpeng2@huawei.com>

Acked-by: Jason Wang <jasowang@redhat.com>
 
Reviewed-by: Stefano Garzarella --- include/linux/vdpa.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index a5269191edda..8943a209202e 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -83,7 +83,7 @@ struct vdpa_device { unsigned int index; bool features_valid; bool use_va; - int nvqs; + u32 nvqs; struct vdpa_mgmt_dev *mdev; }; @@ -338,10 +338,10 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, dev_struct, member)), name, use_va), \ dev_struct, member) -int vdpa_register_device(struct vdpa_device *vdev, int nvqs); +int vdpa_register_device(struct vdpa_device *vdev, u32 nvqs); void vdpa_unregister_device(struct vdpa_device *vdev); -int _vdpa_register_device(struct vdpa_device *vdev, int nvqs); +int _vdpa_register_device(struct vdpa_device *vdev, u32 nvqs); void _vdpa_unregister_device(struct vdpa_device *vdev); /** -- cgit v1.2.3 From b04d910af330b55e1d5d6eb9ecd53a375a9cf81c Mon Sep 17 00:00:00 2001 From: Longpeng Date: Tue, 15 Mar 2022 11:25:53 +0800 Subject: vdpa: support exposing the count of vqs to userspace - GET_VQS_COUNT: the count of virtqueues that exposed Signed-off-by: Longpeng Link: https://lore.kernel.org/r/20220315032553.455-4-longpeng2@huawei.com Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang Signed-off-by: Longpeng <longpeng2@huawei.com>
Reviewed-by: Stefano Garzarella --- include/uapi/linux/vhost.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index bc74e95a273a..5d99e7c242a2 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -154,4 +154,7 @@ /* Get the config size */ #define VHOST_VDPA_GET_CONFIG_SIZE _IOR(VHOST_VIRTIO, 0x79, __u32) +/* Get the count of all virtqueues */ +#define VHOST_VDPA_GET_VQS_COUNT _IOR(VHOST_VIRTIO, 0x80, __u32) + #endif -- cgit v1.2.3 From f32404ae1bb9a7428a3c77419672a28895d185bf Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 25 Mar 2022 22:50:23 +0100 Subject: net: move net_unlink_todo() out of the header There's no reason for this to be in netdevice.h, it's all just used in dev.c. Also make it no longer inline and let the compiler decide to do that by itself. Signed-off-by: Johannes Berg Link: https://lore.kernel.org/r/20220325225023.f49b9056fe1c.I6b901a2df00000837a9bd251a8dd259bd23f5ded@changeid Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cd7a597c55b1..59e27a2b7bf0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4601,16 +4601,6 @@ bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter); -#ifdef CONFIG_LOCKDEP -static LIST_HEAD(net_unlink_list); - -static inline void net_unlink_todo(struct net_device *dev) -{ - if (list_empty(&dev->unlink_list)) - list_add_tail(&dev->unlink_list, &net_unlink_list); -} -#endif - /* iterate through upper list, must be called under RCU read lock */ #define netdev_for_each_upper_dev_rcu(dev, updev, iter) \ for (iter = &(dev)->adj_list.upper, \ -- cgit v1.2.3 From 73f9b911faa74ac5107879de05c9489c419f41bb Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Sat, 26 Mar 2022 11:27:05 +0900 Subject: kprobes: Use rethook for kretprobe if possible Use rethook for kretprobe function return hooking if the arch sets CONFIG_HAVE_RETHOOK=y. In this case, CONFIG_KRETPROBE_ON_RETHOOK is set to 'y' automatically, and the kretprobe internal data fields switches to use rethook. If not, it continues to use kretprobe specific function return hooks. Suggested-by: Peter Zijlstra Signed-off-by: Masami Hiramatsu Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/164826162556.2455864.12255833167233452047.stgit@devnote2 --- include/linux/kprobes.h | 51 +++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 49 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 312ff997c743..157168769fc2 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -28,6 +28,7 @@ #include #include #include +#include #include #ifdef CONFIG_KPROBES @@ -149,13 +150,20 @@ struct kretprobe { int maxactive; int nmissed; size_t data_size; +#ifdef CONFIG_KRETPROBE_ON_RETHOOK + struct rethook *rh; +#else struct freelist_head freelist; struct kretprobe_holder *rph; +#endif }; #define KRETPROBE_MAX_DATA_SIZE 4096 struct kretprobe_instance { +#ifdef CONFIG_KRETPROBE_ON_RETHOOK + struct rethook_node node; +#else union { struct freelist_node freelist; struct rcu_head rcu; @@ -164,6 +172,7 @@ struct kretprobe_instance { struct kretprobe_holder *rph; kprobe_opcode_t *ret_addr; void *fp; +#endif char data[]; }; @@ -186,10 +195,24 @@ extern void kprobe_busy_begin(void); extern void kprobe_busy_end(void); #ifdef CONFIG_KRETPROBES -extern void arch_prepare_kretprobe(struct kretprobe_instance *ri, - struct pt_regs *regs); +/* Check whether @p is used for implementing a trampoline. */ extern int arch_trampoline_kprobe(struct kprobe *p); +#ifdef CONFIG_KRETPROBE_ON_RETHOOK +static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance *ri) +{ + RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(), + "Kretprobe is accessed from instance under preemptive context"); + + return (struct kretprobe *)READ_ONCE(ri->node.rethook->data); +} +static nokprobe_inline unsigned long get_kretprobe_retaddr(struct kretprobe_instance *ri) +{ + return ri->node.ret_addr; +} +#else +extern void arch_prepare_kretprobe(struct kretprobe_instance *ri, + struct pt_regs *regs); void arch_kretprobe_fixup_return(struct pt_regs *regs, kprobe_opcode_t *correct_ret_addr); @@ -232,6 +255,12 @@ static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance return READ_ONCE(ri->rph->rp); } +static nokprobe_inline unsigned long get_kretprobe_retaddr(struct kretprobe_instance *ri) +{ + return (unsigned long)ri->ret_addr; +} +#endif /* CONFIG_KRETPROBE_ON_RETHOOK */ + #else /* !CONFIG_KRETPROBES */ static inline void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs) @@ -395,7 +424,11 @@ void unregister_kretprobe(struct kretprobe *rp); int register_kretprobes(struct kretprobe **rps, int num); void unregister_kretprobes(struct kretprobe **rps, int num); +#ifdef CONFIG_KRETPROBE_ON_RETHOOK +#define kprobe_flush_task(tk) do {} while (0) +#else void kprobe_flush_task(struct task_struct *tk); +#endif void kprobe_free_init_mem(void); @@ -509,6 +542,19 @@ static inline bool is_kprobe_optinsn_slot(unsigned long addr) #endif /* !CONFIG_OPTPROBES */ #ifdef CONFIG_KRETPROBES +#ifdef CONFIG_KRETPROBE_ON_RETHOOK +static nokprobe_inline bool is_kretprobe_trampoline(unsigned long addr) +{ + return is_rethook_trampoline(addr); +} + +static nokprobe_inline +unsigned long kretprobe_find_ret_addr(struct task_struct *tsk, void *fp, + struct llist_node **cur) +{ + return rethook_find_ret_addr(tsk, (unsigned long)fp, cur); +} +#else static nokprobe_inline bool is_kretprobe_trampoline(unsigned long addr) { return (void *)addr == kretprobe_trampoline_addr(); @@ -516,6 +562,7 @@ static nokprobe_inline bool is_kretprobe_trampoline(unsigned long addr) unsigned long kretprobe_find_ret_addr(struct task_struct *tsk, void *fp, struct llist_node **cur); +#endif #else static nokprobe_inline bool is_kretprobe_trampoline(unsigned long addr) { -- cgit v1.2.3 From 5974ea7ce0f9a5987fc8cf5e08ad6e3e70bb542e Mon Sep 17 00:00:00 2001 From: Sungup Moon Date: Mon, 14 Mar 2022 20:05:45 +0900 Subject: nvme: allow duplicate NSIDs for private namespaces A NVMe subsystem with multiple controller can have private namespaces that use the same NSID under some conditions: "If Namespace Management, ANA Reporting, or NVM Sets are supported, the NSIDs shall be unique within the NVM subsystem. If the Namespace Management, ANA Reporting, and NVM Sets are not supported, then NSIDs: a) for shared namespace shall be unique; and b) for private namespace are not required to be unique." Reference: Section 6.1.6 NSID and Namespace Usage; NVM Express 1.4c spec. Make sure this specific setup is supported in Linux. Fixes: 9ad1927a3bc2 ("nvme: always search for namespace head") Signed-off-by: Sungup Moon [hch: refactored and fixed the controller vs subsystem based naming conflict] Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg --- include/linux/nvme.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 9dbc3ef4daf7..2dcee34d467d 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -345,6 +345,7 @@ enum { NVME_CTRL_ONCS_TIMESTAMP = 1 << 6, NVME_CTRL_VWC_PRESENT = 1 << 0, NVME_CTRL_OACS_SEC_SUPP = 1 << 0, + NVME_CTRL_OACS_NS_MNGT_SUPP = 1 << 3, NVME_CTRL_OACS_DIRECTIVES = 1 << 5, NVME_CTRL_OACS_DBBUF_SUPP = 1 << 8, NVME_CTRL_LPA_CMD_EFFECTS_LOG = 1 << 1, -- cgit v1.2.3 From 7842cf65b0401814a9df518a86a41641255c84d3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Tue, 15 Feb 2022 17:29:59 +0100 Subject: drm/ttm: de-inline ttm_bo_pin/unpin MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Those functions are going to become more complex, don't inline them any more. Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220321132601.2161-4-christian.koenig@amd.com --- include/drm/ttm/ttm_bo_api.h | 30 ++---------------------------- 1 file changed, 2 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index 3da77fc54552..885b7698fd65 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -524,34 +524,8 @@ ssize_t ttm_bo_io(struct ttm_device *bdev, struct file *filp, int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, gfp_t gfp_flags); -/** - * ttm_bo_pin - Pin the buffer object. - * @bo: The buffer object to pin - * - * Make sure the buffer is not evicted any more during memory pressure. - */ -static inline void ttm_bo_pin(struct ttm_buffer_object *bo) -{ - dma_resv_assert_held(bo->base.resv); - WARN_ON_ONCE(!kref_read(&bo->kref)); - ++bo->pin_count; -} - -/** - * ttm_bo_unpin - Unpin the buffer object. - * @bo: The buffer object to unpin - * - * Allows the buffer object to be evicted again during memory pressure. - */ -static inline void ttm_bo_unpin(struct ttm_buffer_object *bo) -{ - dma_resv_assert_held(bo->base.resv); - WARN_ON_ONCE(!kref_read(&bo->kref)); - if (bo->pin_count) - --bo->pin_count; - else - WARN_ON_ONCE(true); -} +void ttm_bo_pin(struct ttm_buffer_object *bo); +void ttm_bo_unpin(struct ttm_buffer_object *bo); int ttm_mem_evict_first(struct ttm_device *bdev, struct ttm_resource_manager *man, -- cgit v1.2.3 From fee2ede155423b0f7a559050a39750b98fe9db69 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Mon, 24 Jan 2022 11:07:15 +0100 Subject: drm/ttm: rework bulk move handling v5 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Instead of providing the bulk move structure for each LRU update set this as property of the BO. This should avoid costly bulk move rebuilds with some games under RADV. v2: some name polishing, add a few more kerneldoc words. v3: add some lockdep v4: fix bugs, handle pin/unpin as well v5: improve kerneldoc Signed-off-by: Christian König Tested-by: Bas Nieuwenhuizen Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220321132601.2161-5-christian.koenig@amd.com --- include/drm/ttm/ttm_bo_api.h | 16 ++++------------ include/drm/ttm/ttm_bo_driver.h | 2 +- include/drm/ttm/ttm_device.h | 9 --------- include/drm/ttm/ttm_resource.h | 11 +++++++---- 4 files changed, 12 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index 885b7698fd65..c61e1e5ceb83 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -135,6 +135,7 @@ struct ttm_buffer_object { struct ttm_resource *resource; struct ttm_tt *ttm; bool deleted; + struct ttm_lru_bulk_move *bulk_move; /** * Members protected by the bdev::lru_lock. @@ -287,18 +288,9 @@ int ttm_bo_validate(struct ttm_buffer_object *bo, */ void ttm_bo_put(struct ttm_buffer_object *bo); -/** - * ttm_bo_move_to_lru_tail - * - * @bo: The buffer object. - * @bulk: optional bulk move structure to remember BO positions - * - * Move this BO to the tail of all lru lists used to lookup and reserve an - * object. This function must be called with struct ttm_global::lru_lock - * held, and is used to make a BO less likely to be considered for eviction. - */ -void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo, - struct ttm_lru_bulk_move *bulk); +void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo); +void ttm_bo_set_bulk_move(struct ttm_buffer_object *bo, + struct ttm_lru_bulk_move *bulk); /** * ttm_bo_lock_delayed_workqueue diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 6c7352e13708..059a595e14e5 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -155,7 +155,7 @@ static inline void ttm_bo_move_to_lru_tail_unlocked(struct ttm_buffer_object *bo) { spin_lock(&bo->bdev->lru_lock); - ttm_bo_move_to_lru_tail(bo, NULL); + ttm_bo_move_to_lru_tail(bo); spin_unlock(&bo->bdev->lru_lock); } diff --git a/include/drm/ttm/ttm_device.h b/include/drm/ttm/ttm_device.h index 425150f35fbe..95b3c04b1ab9 100644 --- a/include/drm/ttm/ttm_device.h +++ b/include/drm/ttm/ttm_device.h @@ -198,15 +198,6 @@ struct ttm_device_funcs { int (*access_memory)(struct ttm_buffer_object *bo, unsigned long offset, void *buf, int len, int write); - /** - * struct ttm_bo_driver member del_from_lru_notify - * - * @bo: the buffer object deleted from lru - * - * notify driver that a BO was deleted from LRU. - */ - void (*del_from_lru_notify)(struct ttm_buffer_object *bo); - /** * Notify the driver that we're about to release a BO * diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index 62e7bb782596..4ca960b5cde1 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -206,7 +206,7 @@ struct ttm_resource_cursor { * @first: first res in the bulk move range * @last: last res in the bulk move range * - * Positions for a lru bulk move. + * Range of resources for a lru bulk move. */ struct ttm_lru_bulk_move_pos { struct ttm_resource *first; @@ -220,7 +220,7 @@ struct ttm_lru_bulk_move_pos { * @vram: first/last lru entry for resources in the VRAM domain * * Container for the current bulk move state. Should be used with - * ttm_lru_bulk_move_init() and ttm_bo_move_to_lru_tail(). + * ttm_lru_bulk_move_init() and ttm_bo_set_bulk_move(). */ struct ttm_lru_bulk_move { struct ttm_lru_bulk_move_pos pos[TTM_NUM_MEM_TYPES][TTM_MAX_BO_PRIORITY]; @@ -313,10 +313,13 @@ ttm_resource_manager_cleanup(struct ttm_resource_manager *man) } void ttm_lru_bulk_move_init(struct ttm_lru_bulk_move *bulk); +void ttm_lru_bulk_move_add(struct ttm_lru_bulk_move *bulk, + struct ttm_resource *res); +void ttm_lru_bulk_move_del(struct ttm_lru_bulk_move *bulk, + struct ttm_resource *res); void ttm_lru_bulk_move_tail(struct ttm_lru_bulk_move *bulk); -void ttm_resource_move_to_lru_tail(struct ttm_resource *res, - struct ttm_lru_bulk_move *bulk); +void ttm_resource_move_to_lru_tail(struct ttm_resource *res); void ttm_resource_init(struct ttm_buffer_object *bo, const struct ttm_place *place, -- cgit v1.2.3 From 77ef271faee9c3be65fc5e5dcd66c45d4ffbe494 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Fri, 16 Jul 2021 14:37:14 +0200 Subject: drm/amdgpu: drop amdgpu_gtt_node MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We have the BO pointer in the base structure now as well. Signed-off-by: Christian König Reviewed-by: Daniel Vetter Tested-by: Bas Nieuwenhuizen Link: https://patchwork.freedesktop.org/patch/msgid/20220321132601.2161-6-christian.koenig@amd.com --- include/drm/ttm/ttm_resource.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index 4ca960b5cde1..4428a62e5f0e 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -355,6 +355,14 @@ ttm_resource_manager_next(struct ttm_resource_manager *man, struct ttm_resource_cursor *cursor, struct ttm_resource *res); +/** + * ttm_resource_manager_for_each_res - iterate over all resources + * @man: the resource manager + * @cursor: struct ttm_resource_cursor for the current position + * @res: the current resource + * + * Iterate over all the evictable resources in a resource manager. + */ #define ttm_resource_manager_for_each_res(man, cursor, res) \ for (res = ttm_resource_manager_first(man, cursor); res; \ res = ttm_resource_manager_next(man, cursor, res)) -- cgit v1.2.3 From 657586e474bd025d534d4ea355ec3211d9883cd8 Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Tue, 22 Mar 2022 16:38:44 +0200 Subject: drm/i915: Add a DP1.2 compatible way to read LTTPR capabilities MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit At least some DELL monitors (P2715Q) with DPCD_REV 1.2 return corrupted DPCD register values when reading from the 0xF0000- LTTPR range with an AUX transaction block size bigger than 1. The DP standard requires 0 to be returned - as for any other reserved/invalid addresses - but these monitors return the DPCD_REV register value repeated in each byte of the read buffer. This will in turn corrupt the values returned by the LTTPRs between the source and the monitor: LTTPRs must adjust the values they read from the downstream DPRX, for instance right-shift/init the downstream DP_PHY_REPEATER_CNT value. Since the value returned by the monitor's DPRX is non-zero the adjusted values will be corrupt. Reading the LTTPR registers one-by-one instead of reading all of them with a single AUX transfer works around the issue. According to the DP standard's 0xF0000 register description: "LTTPR-related registers at DPCD Addresses F0000h through F02FFh are valid only for DPCD r1.4 (or higher)." While it's unclear if DPCD r1.4 refers to the DPCD_REV or to the LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV register (tickets filed at the VESA site to clarify this haven't been addressed), one possibility is that it's a restriction due to non-compliant monitors described above. Disabling the non-transparent LTTPR mode for all such monitors is not a viable solution: the transparent LTTPR mode has its own issue causing link training failures and this would affect a lot of monitors in use with DPCD_REV < 1.4. Instead this patch works around the problem by reading the LTTPR common and PHY cap registers one-by-one for any monitor with a DPCD_REV < 1.4. The standard requires the DPCD capabilities to be read after the LTTPR common capabilities are read, so re-read the DPCD capabilities after the LTTPR common and PHY caps were read out. v2: - Use for instead of a while loop. (Ville) - Add to code comment the monitor model with the problem. Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/4531 Cc: Ville Syrjälä Signed-off-by: Imre Deak Reviewed-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20220322143844.42616-1-imre.deak@intel.com --- include/drm/dp/drm_dp_helper.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/drm/dp/drm_dp_helper.h b/include/drm/dp/drm_dp_helper.h index 69487bd8ed56..8c0d22faad9a 100644 --- a/include/drm/dp/drm_dp_helper.h +++ b/include/drm/dp/drm_dp_helper.h @@ -2150,8 +2150,10 @@ bool drm_dp_read_sink_count_cap(struct drm_connector *connector, int drm_dp_read_sink_count(struct drm_dp_aux *aux); int drm_dp_read_lttpr_common_caps(struct drm_dp_aux *aux, + const u8 dpcd[DP_RECEIVER_CAP_SIZE], u8 caps[DP_LTTPR_COMMON_CAP_SIZE]); int drm_dp_read_lttpr_phy_caps(struct drm_dp_aux *aux, + const u8 dpcd[DP_RECEIVER_CAP_SIZE], enum drm_dp_phy dp_phy, u8 caps[DP_LTTPR_PHY_CAP_SIZE]); int drm_dp_lttpr_count(const u8 cap[DP_LTTPR_COMMON_CAP_SIZE]); -- cgit v1.2.3 From f4e558ec9d9fb9484c30221a41cc5bfa73d33e6c Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Mon, 28 Mar 2022 17:34:32 +0300 Subject: drm/edid: add more general struct edid constness in the interfaces MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With this, the remaining non-const parts are the ones that actually modify the EDID, for example to fix corrupt EDID. Cc: Ville Syrjälä Signed-off-by: Jani Nikula Reviewed-by: Ville Syrjälä Reviewed-by: Emil Velikov Link: https://patchwork.freedesktop.org/patch/msgid/c7156f22494b585c55a00a6732462bde0cc19dbf.1648477901.git.jani.nikula@intel.com --- include/drm/drm_edid.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h index 144c495b99c4..48b1bf9c315a 100644 --- a/include/drm/drm_edid.h +++ b/include/drm/drm_edid.h @@ -372,8 +372,8 @@ struct drm_connector; struct drm_connector_state; struct drm_display_mode; -int drm_edid_to_sad(struct edid *edid, struct cea_sad **sads); -int drm_edid_to_speaker_allocation(struct edid *edid, u8 **sadb); +int drm_edid_to_sad(const struct edid *edid, struct cea_sad **sads); +int drm_edid_to_speaker_allocation(const struct edid *edid, u8 **sadb); int drm_av_sync_delay(struct drm_connector *connector, const struct drm_display_mode *mode); @@ -569,8 +569,8 @@ int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid); int drm_add_override_edid_modes(struct drm_connector *connector); u8 drm_match_cea_mode(const struct drm_display_mode *to_match); -bool drm_detect_hdmi_monitor(struct edid *edid); -bool drm_detect_monitor_audio(struct edid *edid); +bool drm_detect_hdmi_monitor(const struct edid *edid); +bool drm_detect_monitor_audio(const struct edid *edid); enum hdmi_quantization_range drm_default_rgb_quant_range(const struct drm_display_mode *mode); int drm_add_modes_noedid(struct drm_connector *connector, @@ -582,7 +582,7 @@ int drm_edid_header_is_valid(const u8 *raw_edid); bool drm_edid_block_valid(u8 *raw_edid, int block, bool print_bad_edid, bool *edid_corrupt); bool drm_edid_is_valid(struct edid *edid); -void drm_edid_get_monitor_name(struct edid *edid, char *name, +void drm_edid_get_monitor_name(const struct edid *edid, char *name, int buflen); struct drm_display_mode *drm_mode_find_dmt(struct drm_device *dev, int hsize, int vsize, int fresh, -- cgit v1.2.3 From 37200078ed6aa2ac3c88a01a64996133dccfdd34 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Thu, 24 Mar 2022 09:14:51 -0700 Subject: Drivers: hv: vmbus: Propagate VMbus coherence to each VMbus device VMbus synthetic devices are not represented in the ACPI DSDT -- only the top level VMbus device is represented. As a result, on ARM64 coherence information in the _CCA method is not specified for synthetic devices, so they default to not hardware coherent. Drivers for some of these synthetic devices have been recently updated to use the standard DMA APIs, and they are incurring extra overhead of unneeded software coherence management. Fix this by propagating coherence information from the VMbus node in ACPI to the individual synthetic devices. There's no effect on x86/x64 where devices are always hardware coherent. Signed-off-by: Michael Kelley Acked-by: Robin Murphy Link: https://lore.kernel.org/r/1648138492-2191-2-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- include/asm-generic/mshyperv.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index c08758b6b364..c05d2ce9b6cd 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -269,6 +269,7 @@ bool hv_isolation_type_snp(void); u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size); void hyperv_cleanup(void); bool hv_query_ext_cap(u64 cap_query); +void hv_setup_dma_ops(struct device *dev, bool coherent); void *hv_map_memory(void *addr, unsigned long size); void hv_unmap_memory(void *addr); #else /* CONFIG_HYPERV */ -- cgit v1.2.3 From 756b807f6a3e01d238c346925006cdfd6a59e341 Mon Sep 17 00:00:00 2001 From: Tejas Upadhyay Date: Tue, 22 Mar 2022 09:36:16 +0530 Subject: drm/i915: Add RPL-S PCI IDs Add couple of RPL-S device ids Bspec : 53655 Cc: Matt Roper Signed-off-by: Tejas Upadhyay Reviewed-by: Anshuman Gupta Signed-off-by: Matt Roper Link: https://patchwork.freedesktop.org/patch/msgid/20220322040616.1078009-1-tejaskumarx.surendrakumar.upadhyay@intel.com --- include/drm/i915_pciids.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h index 533890dc9da1..0800dc8b98b3 100644 --- a/include/drm/i915_pciids.h +++ b/include/drm/i915_pciids.h @@ -679,6 +679,8 @@ INTEL_VGA_DEVICE(0xA782, info), \ INTEL_VGA_DEVICE(0xA783, info), \ INTEL_VGA_DEVICE(0xA788, info), \ - INTEL_VGA_DEVICE(0xA789, info) + INTEL_VGA_DEVICE(0xA789, info), \ + INTEL_VGA_DEVICE(0xA78A, info), \ + INTEL_VGA_DEVICE(0xA78B, info) #endif /* _I915_PCIIDS_H */ -- cgit v1.2.3 From 3ae8fd41573af4fb3a490c9ed947fc936ba87190 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Tue, 11 Jan 2022 16:57:50 -0600 Subject: rtc: mc146818-lib: Fix the AltCentury for AMD platforms Setting the century forward has been failing on AMD platforms. There was a previous attempt at fixing this for family 0x17 as part of commit 7ad295d5196a ("rtc: Fix the AltCentury value on AMD/Hygon platform") but this was later reverted due to some problems reported that appeared to stem from an FW bug on a family 0x17 desktop system. The same comments mentioned in the previous commit continue to apply to the newer platforms as well. ``` MC146818 driver use function mc146818_set_time() to set register RTC_FREQ_SELECT(RTC_REG_A)'s bit4-bit6 field which means divider stage reset value on Intel platform to 0x7. While AMD/Hygon RTC_REG_A(0Ah)'s bit4 is defined as DV0 [Reference]: DV0 = 0 selects Bank 0, DV0 = 1 selects Bank 1. Bit5-bit6 is defined as reserved. DV0 is set to 1, it will select Bank 1, which will disable AltCentury register(0x32) access. As UEFI pass acpi_gbl_FADT.century 0x32 (AltCentury), the CMOS write will be failed on code: CMOS_WRITE(century, acpi_gbl_FADT.century). Correct RTC_REG_A bank select bit(DV0) to 0 on AMD/Hygon CPUs, it will enable AltCentury(0x32) register writing and finally setup century as expected. ``` However in closer examination the change previously submitted was also modifying bits 5 & 6 which are declared reserved in the AMD documentation. So instead modify just the DV0 bank selection bit. Being cognizant that there was a failure reported before, split the code change out to a static function that can also be used for exclusions if any regressions such as Mikhail's pop up again. Cc: Jinke Fan Cc: Mikhail Gavrilov Link: https://lore.kernel.org/all/CABXGCsMLob0DC25JS8wwAYydnDoHBSoMh2_YLPfqm3TTvDE-Zw@mail.gmail.com/ Link: https://www.amd.com/system/files/TechDocs/51192_Bolton_FCH_RRG.pdf Signed-off-by: Raul E Rangel Signed-off-by: Mario Limonciello Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20220111225750.1699-1-mario.limonciello@amd.com --- include/linux/mc146818rtc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mc146818rtc.h b/include/linux/mc146818rtc.h index 808bb4cee230..b0da04fe087b 100644 --- a/include/linux/mc146818rtc.h +++ b/include/linux/mc146818rtc.h @@ -86,6 +86,8 @@ struct cmos_rtc_board_info { /* 2 values for divider stage reset, others for "testing purposes only" */ # define RTC_DIV_RESET1 0x60 # define RTC_DIV_RESET2 0x70 + /* In AMD BKDG bit 5 and 6 are reserved, bit 4 is for select dv0 bank */ +# define RTC_AMD_BANK_SELECT 0x10 /* Periodic intr. / Square wave rate select. 0=none, 1=32.8kHz,... 15=2Hz */ # define RTC_RATE_SELECT 0x0F -- cgit v1.2.3 From eb07d5a4da041fd2e30e386e5fd12d23bb31cf9e Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 30 Mar 2022 11:48:37 +1100 Subject: SUNRPC: handle malloc failure in ->request_prepare If ->request_prepare() detects an error, it sets ->rq_task->tk_status. This is easy for callers to ignore. The only caller is xprt_request_enqueue_receive() and it does ignore the error, as does call_encode() which calls it. This can result in a request being queued to receive a reply without an allocated receive buffer. So instead of setting rq_task->tk_status, return an error, and store in ->tk_status only in call_encode(); The call to xprt_request_enqueue_receive() is now earlier in call_encode(), where the error can still be handled. Signed-off-by: NeilBrown Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index eef5e87c03b4..f171f8c09e13 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -144,7 +144,7 @@ struct rpc_xprt_ops { unsigned short (*get_srcport)(struct rpc_xprt *xprt); int (*buf_alloc)(struct rpc_task *task); void (*buf_free)(struct rpc_task *task); - void (*prepare_request)(struct rpc_rqst *req); + int (*prepare_request)(struct rpc_rqst *req); int (*send_request)(struct rpc_rqst *req); void (*wait_for_reply_request)(struct rpc_task *task); void (*timer)(struct rpc_xprt *xprt, struct rpc_task *task); @@ -357,10 +357,9 @@ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req); -void xprt_request_prepare(struct rpc_rqst *req); bool xprt_prepare_transmit(struct rpc_task *task); void xprt_request_enqueue_transmit(struct rpc_task *task); -void xprt_request_enqueue_receive(struct rpc_task *task); +int xprt_request_enqueue_receive(struct rpc_task *task); void xprt_request_wait_receive(struct rpc_task *task); void xprt_request_dequeue_xprt(struct rpc_task *task); bool xprt_request_need_retransmit(struct rpc_task *task); -- cgit v1.2.3 From 7968778914e53788a01c2dee2692cab157de9ac0 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 9 Mar 2022 20:50:39 +0100 Subject: PCI: Remove the deprecated "pci-dma-compat.h" API Now that all usages of the functions defined in "pci-dma-compat.h" have been removed, it is time to remove this file as well. In order not to break builds, move the "#include " that was in "pci-dma-compat.h" into "include/linux/pci.h" Signed-off-by: Christophe JAILLET Acked-by: Bjorn Helgaas Signed-off-by: Christoph Hellwig --- include/linux/pci-dma-compat.h | 129 ----------------------------------------- include/linux/pci.h | 3 +- 2 files changed, 1 insertion(+), 131 deletions(-) delete mode 100644 include/linux/pci-dma-compat.h (limited to 'include') diff --git a/include/linux/pci-dma-compat.h b/include/linux/pci-dma-compat.h deleted file mode 100644 index 249d4d7fbf18..000000000000 --- a/include/linux/pci-dma-compat.h +++ /dev/null @@ -1,129 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* include this file if the platform implements the dma_ DMA Mapping API - * and wants to provide the pci_ DMA Mapping API in terms of it */ - -#ifndef _ASM_GENERIC_PCI_DMA_COMPAT_H -#define _ASM_GENERIC_PCI_DMA_COMPAT_H - -#include - -/* This defines the direction arg to the DMA mapping routines. */ -#define PCI_DMA_BIDIRECTIONAL DMA_BIDIRECTIONAL -#define PCI_DMA_TODEVICE DMA_TO_DEVICE -#define PCI_DMA_FROMDEVICE DMA_FROM_DEVICE -#define PCI_DMA_NONE DMA_NONE - -static inline void * -pci_alloc_consistent(struct pci_dev *hwdev, size_t size, - dma_addr_t *dma_handle) -{ - return dma_alloc_coherent(&hwdev->dev, size, dma_handle, GFP_ATOMIC); -} - -static inline void * -pci_zalloc_consistent(struct pci_dev *hwdev, size_t size, - dma_addr_t *dma_handle) -{ - return dma_alloc_coherent(&hwdev->dev, size, dma_handle, GFP_ATOMIC); -} - -static inline void -pci_free_consistent(struct pci_dev *hwdev, size_t size, - void *vaddr, dma_addr_t dma_handle) -{ - dma_free_coherent(&hwdev->dev, size, vaddr, dma_handle); -} - -static inline dma_addr_t -pci_map_single(struct pci_dev *hwdev, void *ptr, size_t size, int direction) -{ - return dma_map_single(&hwdev->dev, ptr, size, (enum dma_data_direction)direction); -} - -static inline void -pci_unmap_single(struct pci_dev *hwdev, dma_addr_t dma_addr, - size_t size, int direction) -{ - dma_unmap_single(&hwdev->dev, dma_addr, size, (enum dma_data_direction)direction); -} - -static inline dma_addr_t -pci_map_page(struct pci_dev *hwdev, struct page *page, - unsigned long offset, size_t size, int direction) -{ - return dma_map_page(&hwdev->dev, page, offset, size, (enum dma_data_direction)direction); -} - -static inline void -pci_unmap_page(struct pci_dev *hwdev, dma_addr_t dma_address, - size_t size, int direction) -{ - dma_unmap_page(&hwdev->dev, dma_address, size, (enum dma_data_direction)direction); -} - -static inline int -pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sg, - int nents, int direction) -{ - return dma_map_sg(&hwdev->dev, sg, nents, (enum dma_data_direction)direction); -} - -static inline void -pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sg, - int nents, int direction) -{ - dma_unmap_sg(&hwdev->dev, sg, nents, (enum dma_data_direction)direction); -} - -static inline void -pci_dma_sync_single_for_cpu(struct pci_dev *hwdev, dma_addr_t dma_handle, - size_t size, int direction) -{ - dma_sync_single_for_cpu(&hwdev->dev, dma_handle, size, (enum dma_data_direction)direction); -} - -static inline void -pci_dma_sync_single_for_device(struct pci_dev *hwdev, dma_addr_t dma_handle, - size_t size, int direction) -{ - dma_sync_single_for_device(&hwdev->dev, dma_handle, size, (enum dma_data_direction)direction); -} - -static inline void -pci_dma_sync_sg_for_cpu(struct pci_dev *hwdev, struct scatterlist *sg, - int nelems, int direction) -{ - dma_sync_sg_for_cpu(&hwdev->dev, sg, nelems, (enum dma_data_direction)direction); -} - -static inline void -pci_dma_sync_sg_for_device(struct pci_dev *hwdev, struct scatterlist *sg, - int nelems, int direction) -{ - dma_sync_sg_for_device(&hwdev->dev, sg, nelems, (enum dma_data_direction)direction); -} - -static inline int -pci_dma_mapping_error(struct pci_dev *pdev, dma_addr_t dma_addr) -{ - return dma_mapping_error(&pdev->dev, dma_addr); -} - -#ifdef CONFIG_PCI -static inline int pci_set_dma_mask(struct pci_dev *dev, u64 mask) -{ - return dma_set_mask(&dev->dev, mask); -} - -static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) -{ - return dma_set_coherent_mask(&dev->dev, mask); -} -#else -static inline int pci_set_dma_mask(struct pci_dev *dev, u64 mask) -{ return -EIO; } -static inline int pci_set_consistent_dma_mask(struct pci_dev *dev, u64 mask) -{ return -EIO; } -#endif - -#endif diff --git a/include/linux/pci.h b/include/linux/pci.h index b957eeb89c7a..60adf42460ab 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2473,8 +2473,7 @@ static inline bool pci_is_thunderbolt_attached(struct pci_dev *pdev) void pci_uevent_ers(struct pci_dev *pdev, enum pci_ers_result err_type); #endif -/* Provide the legacy pci_dma_* API */ -#include +#include #define pci_printk(level, pdev, fmt, arg...) \ dev_printk(level, &(pdev)->dev, fmt, ##arg) -- cgit v1.2.3 From c18c86808b78c4c2dc69f27f37c57abab14ee387 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 30 Mar 2022 02:22:17 -0400 Subject: Revert "virtio_config: introduce a new .enable_cbs method" This reverts commit d50497eb4e554e1f0351e1836ee7241c059592e6. The new callback ended up not being used, and it's asymmetrical: just enable, no disable. Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- include/linux/virtio_config.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index dafdc7f48c01..b341dd62aa4d 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -23,8 +23,6 @@ struct virtio_shm_region { * any of @get/@set, @get_status/@set_status, or @get_features/ * @finalize_features are NOT safe to be called from an atomic * context. - * @enable_cbs: enable the callbacks - * vdev: the virtio_device * @get: read the value of a configuration field * vdev: the virtio_device * offset: the offset of the configuration field @@ -78,7 +76,6 @@ struct virtio_shm_region { */ typedef void vq_callback_t(struct virtqueue *); struct virtio_config_ops { - void (*enable_cbs)(struct virtio_device *vdev); void (*get)(struct virtio_device *vdev, unsigned offset, void *buf, unsigned len); void (*set)(struct virtio_device *vdev, unsigned offset, @@ -233,9 +230,6 @@ void virtio_device_ready(struct virtio_device *dev) { unsigned status = dev->config->get_status(dev); - if (dev->config->enable_cbs) - dev->config->enable_cbs(dev); - BUG_ON(status & VIRTIO_CONFIG_S_DRIVER_OK); dev->config->set_status(dev, status | VIRTIO_CONFIG_S_DRIVER_OK); } -- cgit v1.2.3 From bc55cfd5718c7c23e5524582e9fa70b4d10f2433 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 30 Mar 2022 14:09:03 +0200 Subject: ALSA: pcm: Fix potential AB/BA lock with buffer_mutex and mmap_lock syzbot caught a potential deadlock between the PCM runtime->buffer_mutex and the mm->mmap_lock. It was brought by the recent fix to cover the racy read/write and other ioctls, and in that commit, I overlooked a (hopefully only) corner case that may take the revert lock, namely, the OSS mmap. The OSS mmap operation exceptionally allows to re-configure the parameters inside the OSS mmap syscall, where mm->mmap_mutex is already held. Meanwhile, the copy_from/to_user calls at read/write operations also take the mm->mmap_lock internally, hence it may lead to a AB/BA deadlock. A similar problem was already seen in the past and we fixed it with a refcount (in commit b248371628aa). The former fix covered only the call paths with OSS read/write and OSS ioctls, while we need to cover the concurrent access via both ALSA and OSS APIs now. This patch addresses the problem above by replacing the buffer_mutex lock in the read/write operations with a refcount similar as we've used for OSS. The new field, runtime->buffer_accessing, keeps the number of concurrent read/write operations. Unlike the former buffer_mutex protection, this protects only around the copy_from/to_user() calls; the other codes are basically protected by the PCM stream lock. The refcount can be a negative, meaning blocked by the ioctls. If a negative value is seen, the read/write aborts with -EBUSY. In the ioctl side, OTOH, they check this refcount, too, and set to a negative value for blocking unless it's already being accessed. Reported-by: syzbot+6e5c88838328e99c7e1c@syzkaller.appspotmail.com Fixes: dca947d4d26d ("ALSA: pcm: Fix races among concurrent read/write and buffer changes") Cc: Link: https://lore.kernel.org/r/000000000000381a0d05db622a81@google.com Link: https://lore.kernel.org/r/20220330120903.4738-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/sound/pcm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/sound/pcm.h b/include/sound/pcm.h index 314f2779cab5..6b99310b5b88 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -402,6 +402,7 @@ struct snd_pcm_runtime { struct fasync_struct *fasync; bool stop_operating; /* sync_stop will be called */ struct mutex buffer_mutex; /* protect for buffer changes */ + atomic_t buffer_accessing; /* >0: in r/w operation, <0: blocked */ /* -- private section -- */ void *private_data; -- cgit v1.2.3 From f941c51eeac7ebe0f8ec30943bf78e7f60aad039 Mon Sep 17 00:00:00 2001 From: Carlos Llamas Date: Tue, 29 Mar 2022 20:18:15 +0000 Subject: loop: fix ioctl calls using compat_loop_info Support for cryptoloop was deleted in commit 47e9624616c8 ("block: remove support for cryptoloop and the xor transfer"), making the usage of loop_info->lo_encrypt_type obsolete. However, this member was also removed from the compat_loop_info definition and this breaks userspace ioctl calls for 32-bit binaries and CONFIG_COMPAT=y. This patch restores the compat_loop_info->lo_encrypt_type member and marks it obsolete as well as in the uapi header definitions. Fixes: 47e9624616c8 ("block: remove support for cryptoloop and the xor transfer") Signed-off-by: Carlos Llamas Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220329201815.1347500-1-cmllamas@google.com Signed-off-by: Jens Axboe --- include/uapi/linux/loop.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h index 24a1c45bd1ae..98e60801195e 100644 --- a/include/uapi/linux/loop.h +++ b/include/uapi/linux/loop.h @@ -45,7 +45,7 @@ struct loop_info { unsigned long lo_inode; /* ioctl r/o */ __kernel_old_dev_t lo_rdevice; /* ioctl r/o */ int lo_offset; - int lo_encrypt_type; + int lo_encrypt_type; /* obsolete, ignored */ int lo_encrypt_key_size; /* ioctl w/o */ int lo_flags; char lo_name[LO_NAME_SIZE]; @@ -61,7 +61,7 @@ struct loop_info64 { __u64 lo_offset; __u64 lo_sizelimit;/* bytes, 0 == max available */ __u32 lo_number; /* ioctl r/o */ - __u32 lo_encrypt_type; + __u32 lo_encrypt_type; /* obsolete, ignored */ __u32 lo_encrypt_key_size; /* ioctl w/o */ __u32 lo_flags; __u8 lo_file_name[LO_NAME_SIZE]; -- cgit v1.2.3 From 4a9c7bbe2ed4d2b240674b1fb606c41d3940c412 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 29 Mar 2022 18:14:56 -0700 Subject: bpf: Resolve to prog->aux->dst_prog->type only for BPF_PROG_TYPE_EXT The commit 7e40781cc8b7 ("bpf: verifier: Use target program's type for access verifications") fixes the verifier checking for BPF_PROG_TYPE_EXT (extension) prog such that the verifier looks for things based on the target prog type that it is extending instead of the BPF_PROG_TYPE_EXT itself. The current resolve_prog_type() returns the target prog type. It checks for nullness on prog->aux->dst_prog. However, when loading a BPF_PROG_TYPE_TRACING prog and it is tracing another bpf prog instead of a kernel function, prog->aux->dst_prog is not NULL also. In this case, the verifier should still verify as the BPF_PROG_TYPE_TRACING type instead of the traced prog type in prog->aux->dst_prog->type. An oops has been reported when tracing a struct_ops prog. A NULL dereference happened in check_return_code() when accessing the prog->aux->attach_func_proto->type and prog->aux->attach_func_proto is NULL here because the traced struct_ops prog has the "unreliable" set. This patch is to change the resolve_prog_type() to only return the target prog type if the prog being verified is BPF_PROG_TYPE_EXT. Fixes: 7e40781cc8b7 ("bpf: verifier: Use target program's type for access verifications") Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20220330011456.2984509-1-kafai@fb.com --- include/linux/bpf_verifier.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index c1fc4af47f69..3a9d2d7cc6b7 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -570,9 +570,11 @@ static inline u32 type_flag(u32 type) return type & ~BPF_BASE_TYPE_MASK; } +/* only use after check_attach_btf_id() */ static inline enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog) { - return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type; + return prog->type == BPF_PROG_TYPE_EXT ? + prog->aux->dst_prog->type : prog->type; } #endif /* _LINUX_BPF_VERIFIER_H */ -- cgit v1.2.3 From 97a1f01b3f2f734bd3982aa5639b2b54632f8f7d Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Mon, 28 Mar 2022 14:43:02 +0200 Subject: drm/atomic: Add atomic_print_state to private objects A number of drivers (amdgpu, komeda, vc4, etc.) leverage the drm_private_state structure, but we don't have any infrastructure to provide debugging like we do for the other components state. Let's add an atomic_print_state hook to be consistent. Reviewed-by: Daniel Vetter Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220328124304.2309418-3-maxime@cerno.tech --- include/drm/drm_atomic.h | 27 +++++++++++++++++++++++---- 1 file changed, 23 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h index 1701c2128a5c..0777725085df 100644 --- a/include/drm/drm_atomic.h +++ b/include/drm/drm_atomic.h @@ -227,6 +227,18 @@ struct drm_private_state_funcs { */ void (*atomic_destroy_state)(struct drm_private_obj *obj, struct drm_private_state *state); + + /** + * @atomic_print_state: + * + * If driver subclasses &struct drm_private_state, it should implement + * this optional hook for printing additional driver specific state. + * + * Do not call this directly, use drm_atomic_private_obj_print_state() + * instead. + */ + void (*atomic_print_state)(struct drm_printer *p, + const struct drm_private_state *state); }; /** @@ -311,14 +323,21 @@ struct drm_private_obj { /** * struct drm_private_state - base struct for driver private object state - * @state: backpointer to global drm_atomic_state * - * Currently only contains a backpointer to the overall atomic update, but in - * the future also might hold synchronization information similar to e.g. - * &drm_crtc.commit. + * Currently only contains a backpointer to the overall atomic update, + * and the relevant private object but in the future also might hold + * synchronization information similar to e.g. &drm_crtc.commit. */ struct drm_private_state { + /** + * @state: backpointer to global drm_atomic_state + */ struct drm_atomic_state *state; + + /** + * @obj: backpointer to the private object + */ + struct drm_private_obj *obj; }; struct __drm_private_objs_state { -- cgit v1.2.3 From 7dd5ad2d3e82fb55229e3fe18e09160878e77e20 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 31 Mar 2022 10:36:55 +0200 Subject: Revert "signal, x86: Delay calling signals in atomic on RT enabled kernels" Revert commit bf9ad37dc8a. It needs to be better encapsulated and generalized. Signed-off-by: Thomas Gleixner Cc: "Eric W. Biederman" Cc: Oleg Nesterov Cc: Sebastian Andrzej Siewior --- include/linux/sched.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4a6fdd2a679f..d5e3c00b74e1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1090,9 +1090,6 @@ struct task_struct { /* Restored if set_restore_sigmask() was used: */ sigset_t saved_sigmask; struct sigpending pending; -#ifdef CONFIG_RT_DELAYED_SIGNALS - struct kernel_siginfo forced_info; -#endif unsigned long sas_ss_sp; size_t sas_ss_size; unsigned int sas_ss_flags; -- cgit v1.2.3 From 4a7f62f91933c8ae5308f9127fd8ea48188b6bc3 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 30 Mar 2022 15:39:16 +0100 Subject: rxrpc: Fix call timer start racing with call destruction The rxrpc_call struct has a timer used to handle various timed events relating to a call. This timer can get started from the packet input routines that are run in softirq mode with just the RCU read lock held. Unfortunately, because only the RCU read lock is held - and neither ref or other lock is taken - the call can start getting destroyed at the same time a packet comes in addressed to that call. This causes the timer - which was already stopped - to get restarted. Later, the timer dispatch code may then oops if the timer got deallocated first. Fix this by trying to take a ref on the rxrpc_call struct and, if successful, passing that ref along to the timer. If the timer was already running, the ref is discarded. The timer completion routine can then pass the ref along to the call's work item when it queues it. If the timer or work item where already queued/running, the extra ref is discarded. Fixes: a158bdd3247b ("rxrpc: Fix call timeouts") Reported-by: Marc Dionne Signed-off-by: David Howells Reviewed-by: Marc Dionne Tested-by: Marc Dionne cc: linux-afs@lists.infradead.org Link: http://lists.infradead.org/pipermail/linux-afs/2022-March/005073.html Link: https://lore.kernel.org/r/164865115696.2943015.11097991776647323586.stgit@warthog.procyon.org.uk Signed-off-by: Paolo Abeni --- include/trace/events/rxrpc.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index e70c90116eda..4a3ab0ed6e06 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -83,12 +83,15 @@ enum rxrpc_call_trace { rxrpc_call_error, rxrpc_call_got, rxrpc_call_got_kernel, + rxrpc_call_got_timer, rxrpc_call_got_userid, rxrpc_call_new_client, rxrpc_call_new_service, rxrpc_call_put, rxrpc_call_put_kernel, rxrpc_call_put_noqueue, + rxrpc_call_put_notimer, + rxrpc_call_put_timer, rxrpc_call_put_userid, rxrpc_call_queued, rxrpc_call_queued_ref, @@ -278,12 +281,15 @@ enum rxrpc_tx_point { EM(rxrpc_call_error, "*E*") \ EM(rxrpc_call_got, "GOT") \ EM(rxrpc_call_got_kernel, "Gke") \ + EM(rxrpc_call_got_timer, "GTM") \ EM(rxrpc_call_got_userid, "Gus") \ EM(rxrpc_call_new_client, "NWc") \ EM(rxrpc_call_new_service, "NWs") \ EM(rxrpc_call_put, "PUT") \ EM(rxrpc_call_put_kernel, "Pke") \ - EM(rxrpc_call_put_noqueue, "PNQ") \ + EM(rxrpc_call_put_noqueue, "PnQ") \ + EM(rxrpc_call_put_notimer, "PnT") \ + EM(rxrpc_call_put_timer, "PTM") \ EM(rxrpc_call_put_userid, "Pus") \ EM(rxrpc_call_queued, "QUE") \ EM(rxrpc_call_queued_ref, "QUR") \ -- cgit v1.2.3 From 48ec13d36d3ff716a8a08e6583a925def7a2564d Mon Sep 17 00:00:00 2001 From: Joey Gouly Date: Fri, 18 Mar 2022 12:12:33 +0000 Subject: gpio: Properly document parent data union Suppress a warning in the html docs by documenting these fields separately. Signed-off-by: Joey Gouly Link: https://lore.kernel.org/lkml/20211027220118.71a229ab@canb.auug.org.au/ Cc: Linus Walleij Cc: Bartosz Golaszewski Cc: Marc Zyngier Cc: Stephen Rothwell Reviewed-by: Linus Walleij Signed-off-by: Bartosz Golaszewski --- include/linux/gpio/driver.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index b0728c8ad90c..98c93510640e 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -168,13 +168,16 @@ struct gpio_irq_chip { /** * @parent_handler_data: + * + * If @per_parent_data is false, @parent_handler_data is a single + * pointer used as the data associated with every parent interrupt. + * * @parent_handler_data_array: * - * Data associated, and passed to, the handler for the parent - * interrupt. Can either be a single pointer if @per_parent_data - * is false, or an array of @num_parents pointers otherwise. If - * @per_parent_data is true, @parent_handler_data_array cannot be - * NULL. + * If @per_parent_data is true, @parent_handler_data_array is + * an array of @num_parents pointers, and is used to associate + * different data for each parent. This cannot be NULL if + * @per_parent_data is true. */ union { void *parent_handler_data; -- cgit v1.2.3 From 229a08a4f4e4f9949801cc39b6480ddc9c487183 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 9 Mar 2022 09:37:31 -0800 Subject: ARM/dma-mapping: Remove CMA code when not built with CMA The MAX_CMA_AREAS could be set to 0, which would result in code that would attempt to operate beyond the end of a zero-sized array. If CONFIG_CMA is disabled, just remove this code entirely. Found when building arm on GCC 10.x for several defconfigs (e.g. axm55xx_defconfig) under -Warray-bounds: arch/arm/mm/dma-mapping.c:396:22: warning: array subscript is outside array bounds of 'struct dma_contig_early_reserve[0]' [-Warray-bounds] 396 | dma_mmu_remap[dma_mmu_remap_num].size = size; | ~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~ arch/arm/mm/dma-mapping.c:389:40: note: while referencing 'dma_mmu_remap' 389 | static struct dma_contig_early_reserve dma_mmu_remap[MAX_CMA_AREAS] __initdata; | ^~~~~~~~~~~~~ Cc: Russell King Cc: Logan Gunthorpe Cc: Martin Oliveira Cc: David Hildenbrand Cc: Andrew Morton Cc: Stephen Rothwell Cc: Zi Yan Cc: Hari Bathini Cc: Minchan Kim Cc: Mike Kravetz Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/all/6243ee60.1c69fb81.16de6.7dbf@mx.google.com/ Signed-off-by: Kees Cook Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/lkml/20220310070041.GA24874@lst.de Reviewed-by: David Hildenbrand Link: https://lore.kernel.org/lkml/9059fa71-330f-f04f-b155-2850abb72a71@redhat.com --- include/linux/cma.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/cma.h b/include/linux/cma.h index bd801023504b..2c2ede7f0724 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -12,10 +12,6 @@ */ #ifdef CONFIG_CMA_AREAS #define MAX_CMA_AREAS (1 + CONFIG_CMA_AREAS) - -#else -#define MAX_CMA_AREAS (0) - #endif #define CMA_MAX_NAME 64 -- cgit v1.2.3 From 55037ed7bdc62151a726f5685f88afa6a82959b1 Mon Sep 17 00:00:00 2001 From: Tadeusz Struk Date: Tue, 29 Mar 2022 10:12:52 -0700 Subject: uapi/linux/stddef.h: Add include guards Add include guard wrapper define to uapi/linux/stddef.h to prevent macro redefinition errors when stddef.h is included more than once. This was not needed before since the only contents already used a redefinition test. Signed-off-by: Tadeusz Struk Link: https://lore.kernel.org/r/20220329171252.57279-1-tadeusz.struk@linaro.org Fixes: 50d7bd38c3aa ("stddef: Introduce struct_group() helper macro") Cc: stable@vger.kernel.org Signed-off-by: Kees Cook --- include/uapi/linux/stddef.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index 3021ea25a284..7837ba4fe728 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -1,4 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_STDDEF_H +#define _UAPI_LINUX_STDDEF_H + #include #ifndef __always_inline @@ -41,3 +44,4 @@ struct { } __empty_ ## NAME; \ TYPE NAME[]; \ } +#endif -- cgit v1.2.3 From 4a9dda1c1da65beee994f0977a56a9a21c5db2a7 Mon Sep 17 00:00:00 2001 From: Matt Johnston Date: Fri, 1 Apr 2022 10:48:44 +0800 Subject: mctp: Use output netdev to allocate skb headroom Previously the skb was allocated with headroom MCTP_HEADER_MAXLEN, but that isn't sufficient if we are using devs that are not MCTP specific. This also adds a check that the smctp_halen provided to sendmsg for extended addressing is the correct size for the netdev. Fixes: 833ef3b91de6 ("mctp: Populate socket implementation") Reported-by: Matthew Rinaldi Signed-off-by: Matt Johnston Signed-off-by: David S. Miller --- include/net/mctp.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/mctp.h b/include/net/mctp.h index d37268fe6825..82800d521c3d 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -36,8 +36,6 @@ struct mctp_hdr { #define MCTP_HDR_TAG_SHIFT 0 #define MCTP_HDR_TAG_MASK GENMASK(2, 0) -#define MCTP_HEADER_MAXLEN 4 - #define MCTP_INITIAL_DEFAULT_NET 1 static inline bool mctp_address_unicast(mctp_eid_t eid) -- cgit v1.2.3 From 15325e3c1013035c2e3e266ba79a0c3bef905f25 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Thu, 11 Nov 2021 15:18:34 +0100 Subject: dma-buf: drop the DAG approach for the dma_resv object v3 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit So far we had the approach of using a directed acyclic graph with the dma_resv obj. This turned out to have many downsides, especially it means that every single driver and user of this interface needs to be aware of this restriction when adding fences. If the rules for the DAG are not followed then we end up with potential hard to debug memory corruption, information leaks or even elephant big security holes because we allow userspace to access freed up memory. Since we already took a step back from that by always looking at all fences we now go a step further and stop dropping the shared fences when a new exclusive one is added. v2: Drop some now superflous documentation v3: Add some more documentation for the new handling. Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220321135856.1331-11-christian.koenig@amd.com --- include/linux/dma-buf.h | 4 +--- include/linux/dma-resv.h | 22 +++++----------------- 2 files changed, 6 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 7ab50076e7a6..85ab5554425e 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -424,9 +424,7 @@ struct dma_buf { * IMPORTANT: * * All drivers must obey the struct dma_resv rules, specifically the - * rules for updating fences, see &dma_resv.fence_excl and - * &dma_resv.fence. If these dependency rules are broken access tracking - * can be lost resulting in use after free issues. + * rules for updating and obeying fences. */ struct dma_resv *resv; diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 202cc65d0621..dccaf7b1663e 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -93,23 +93,11 @@ struct dma_resv { * * The exclusive fence, if there is one currently. * - * There are two ways to update this fence: - * - * - First by calling dma_resv_add_excl_fence(), which replaces all - * fences attached to the reservation object. To guarantee that no - * fences are lost, this new fence must signal only after all previous - * fences, both shared and exclusive, have signalled. In some cases it - * is convenient to achieve that by attaching a struct dma_fence_array - * with all the new and old fences. - * - * - Alternatively the fence can be set directly, which leaves the - * shared fences unchanged. To guarantee that no fences are lost, this - * new fence must signal only after the previous exclusive fence has - * signalled. Since the shared fences are staying intact, it is not - * necessary to maintain any ordering against those. If semantically - * only a new access is added without actually treating the previous - * one as a dependency the exclusive fences can be strung together - * using struct dma_fence_chain. + * To guarantee that no fences are lost, this new fence must signal + * only after the previous exclusive fence has signalled. If + * semantically only a new access is added without actually treating the + * previous one as a dependency the exclusive fences can be strung + * together using struct dma_fence_chain. * * Note that actual semantics of what an exclusive or shared fence mean * is defined by the user, for reservation objects shared across drivers -- cgit v1.2.3 From 6d987ddd68434bf60650dfdd05343d642643ee44 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Thu, 31 Mar 2022 21:45:01 +0300 Subject: drm/edid: make drm_edid_header_is_valid() accept void pointer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It will be useful to accept a struct edid *, but for compatibility with existing usage accept void *. Cc: Ville Syrjälä Signed-off-by: Jani Nikula Reviewed-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/33fbe1615a3bd82112eaf4077bbb521793cbb91a.1648752228.git.jani.nikula@intel.com --- include/drm/drm_edid.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h index 48b1bf9c315a..b7e170584000 100644 --- a/include/drm/drm_edid.h +++ b/include/drm/drm_edid.h @@ -578,7 +578,7 @@ int drm_add_modes_noedid(struct drm_connector *connector, void drm_set_preferred_mode(struct drm_connector *connector, int hpref, int vpref); -int drm_edid_header_is_valid(const u8 *raw_edid); +int drm_edid_header_is_valid(const void *edid); bool drm_edid_block_valid(u8 *raw_edid, int block, bool print_bad_edid, bool *edid_corrupt); bool drm_edid_is_valid(struct edid *edid); -- cgit v1.2.3 From aad5b23ebf21573a32b6f07644f028d64492a5d6 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Mon, 28 Mar 2022 12:34:31 -0400 Subject: dm: fix dm_io and dm_target_io flags race condition on Alpha Early alpha processors cannot write a single byte or short; they read 8 bytes, modify the value in registers and write back 8 bytes. This could cause race condition in the structure dm_io - if the fields flags and io_count are modified simultaneously. Fix this bug by using 32-bit flags if we are on Alpha and if we are compiling for a processor that doesn't have the byte-word-extension. Signed-off-by: Mikulas Patocka Fixes: bd4a6dd241ae ("dm: reduce size of dm_io and dm_target_io structs") [snitzer: Jens allowed this change since Mikulas owns a relevant Alpha!] Acked-by: Jens Axboe Signed-off-by: Mike Snitzer --- include/linux/blk_types.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index dd0763a1c674..1973ef9bd40f 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -85,8 +85,10 @@ struct block_device { */ #if defined(CONFIG_ALPHA) && !defined(__alpha_bwx__) typedef u32 __bitwise blk_status_t; +typedef u32 blk_short_t; #else typedef u8 __bitwise blk_status_t; +typedef u16 blk_short_t; #endif #define BLK_STS_OK 0 #define BLK_STS_NOTSUPP ((__force blk_status_t)1) -- cgit v1.2.3 From ebf921a9fac38560e0fc3a4381e163a6969efd5a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 22 Jan 2022 15:46:22 -0500 Subject: readahead: Remove read_cache_pages() With no remaining users, remove this function and the related infrastructure. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Al Viro Acked-by: Al Viro --- include/linux/pagemap.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index a8d0b327b066..993994cd943a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -752,8 +752,6 @@ struct page *read_cache_page(struct address_space *, pgoff_t index, filler_t *filler, void *data); extern struct page * read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); -extern int read_cache_pages(struct address_space *mapping, - struct list_head *pages, filler_t *filler, void *data); static inline struct page *read_mapping_page(struct address_space *mapping, pgoff_t index, struct file *file) -- cgit v1.2.3 From 704528d895dd3e7b173e672116b4eb2b0a0fceb0 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 23 Mar 2022 21:29:04 -0400 Subject: fs: Remove ->readpages address space operation All filesystems have now been converted to use ->readahead, so remove the ->readpages operation and fix all the comments that used to refer to it. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Al Viro Acked-by: Al Viro --- include/linux/fs.h | 6 ------ include/linux/fsverity.h | 2 +- 2 files changed, 1 insertion(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 183160872133..7c81887cc7e8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -370,12 +370,6 @@ struct address_space_operations { /* Mark a folio dirty. Return true if this dirtied it */ bool (*dirty_folio)(struct address_space *, struct folio *); - /* - * Reads in the requested pages. Unlike ->readpage(), this is - * PURELY used for read-ahead!. - */ - int (*readpages)(struct file *filp, struct address_space *mapping, - struct list_head *pages, unsigned nr_pages); void (*readahead)(struct readahead_control *); int (*write_begin)(struct file *, struct address_space *mapping, diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index b568b3c7d095..a7afc800bd8d 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -221,7 +221,7 @@ static inline void fsverity_enqueue_verify_work(struct work_struct *work) * * This checks whether ->i_verity_info has been set. * - * Filesystems call this from ->readpages() to check whether the pages need to + * Filesystems call this from ->readahead() to check whether the pages need to * be verified or not. Don't use IS_VERITY() for this purpose; it's subject to * a race condition where the file is being read concurrently with * FS_IOC_ENABLE_VERITY completing. (S_VERITY is set before ->i_verity_info.) -- cgit v1.2.3 From a9fcd89d67bb8c4ad613b54ab691fc603c94a03a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 14 Feb 2022 09:13:43 -0500 Subject: fs: Remove read_actor_t This typedef is not used any more. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Al Viro Acked-by: Al Viro --- include/linux/fs.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7c81887cc7e8..7588d3a0ced8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -357,9 +357,6 @@ typedef struct { int error; } read_descriptor_t; -typedef int (*read_actor_t)(read_descriptor_t *, struct page *, - unsigned long, unsigned long); - struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); int (*readpage)(struct file *, struct page *); -- cgit v1.2.3 From b2403a61308533c576c9dd783fcb73a9186e0b37 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 14 Feb 2022 09:15:34 -0500 Subject: fs, net: Move read_descriptor_t to net.h fs.h has no more need for this typedef; networking is now the sole user of the read_descriptor_t. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Al Viro Acked-by: Al Viro --- include/linux/fs.h | 19 ------------------- include/linux/net.h | 19 +++++++++++++++++++ 2 files changed, 19 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7588d3a0ced8..8ff28939de60 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -338,25 +338,6 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb) return kiocb->ki_complete == NULL; } -/* - * "descriptor" for what we're up to with a read. - * This allows us to use the same read code yet - * have multiple different users of the data that - * we read from a file. - * - * The simplest case just copies the data to user - * mode. - */ -typedef struct { - size_t written; - size_t count; - union { - char __user *buf; - void *data; - } arg; - int error; -} read_descriptor_t; - struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); int (*readpage)(struct file *, struct page *); diff --git a/include/linux/net.h b/include/linux/net.h index ba736b457a06..12093f4db50c 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -125,6 +125,25 @@ struct socket { struct socket_wq wq; }; +/* + * "descriptor" for what we're up to with a read. + * This allows us to use the same read code yet + * have multiple different users of the data that + * we read from a file. + * + * The simplest case just copies the data to user + * mode. + */ +typedef struct { + size_t written; + size_t count; + union { + char __user *buf; + void *data; + } arg; + int error; +} read_descriptor_t; + struct vm_area_struct; struct page; struct sockaddr; -- cgit v1.2.3 From 800ba29547e16d5fbe67ca764ba660e049e9f1bf Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 19 Feb 2022 23:19:49 -0500 Subject: fs: Pass an iocb to generic_perform_write() We can extract both the file pointer and the pos from the iocb. This simplifies each caller as well as allowing generic_perform_write() to see more of the iocb contents in the future. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Christian Brauner Reviewed-by: Al Viro Acked-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 8ff28939de60..468dc7ec821f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2999,7 +2999,7 @@ extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *); -extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t); +ssize_t generic_perform_write(struct kiocb *, struct iov_iter *); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); -- cgit v1.2.3 From d7414ba14a3a67f81321069219dc7dbc095022c3 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 20 Feb 2022 22:28:03 -0500 Subject: filemap: Remove AOP_FLAG_CONT_EXPAND This flag is no longer used, so remove it. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Al Viro Acked-by: Al Viro --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 468dc7ec821f..bbde95387a23 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -275,7 +275,6 @@ enum positive_aop_returns { AOP_TRUNCATED_PAGE = 0x80001, }; -#define AOP_FLAG_CONT_EXPAND 0x0001 /* called from cont_expand */ #define AOP_FLAG_NOFS 0x0002 /* used by filesystem to direct * helper code (eg buffer layer) * to clear GFP_FS from alloc */ -- cgit v1.2.3 From ada543af3bfe3d953986eca118601b9612382c13 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Fri, 1 Apr 2022 11:28:45 -0700 Subject: mm, kasan: fix __GFP_BITS_SHIFT definition breaking LOCKDEP KASAN changes that added new GFP flags mistakenly updated __GFP_BITS_SHIFT as the total number of GFP bits instead of as a shift used to define __GFP_BITS_MASK. This broke LOCKDEP, as __GFP_BITS_MASK now gets the 25th bit enabled instead of the 28th for __GFP_NOLOCKDEP. Update __GFP_BITS_SHIFT to always count KASAN GFP bits. In the future, we could handle all combinations of KASAN and LOCKDEP to occupy as few bits as possible. For now, we have enough GFP bits to be inefficient in this quick fix. Link: https://lkml.kernel.org/r/462ff52742a1fcc95a69778685737f723ee4dfb3.1648400273.git.andreyknvl@google.com Fixes: 9353ffa6e9e9 ("kasan, page_alloc: allow skipping memory init for HW_TAGS") Fixes: 53ae233c30a6 ("kasan, page_alloc: allow skipping unpoisoning for HW_TAGS") Fixes: f49d9c5bb15c ("kasan, mm: only define ___GFP_SKIP_KASAN_POISON with HW_TAGS") Signed-off-by: Andrey Konovalov Reported-by: Sebastian Andrzej Siewior Tested-by: Sebastian Andrzej Siewior Acked-by: Vlastimil Babka Cc: Marco Elver Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Andrey Ryabinin Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 0fa17fb85de5..761f8f1885c7 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -264,9 +264,7 @@ struct vm_area_struct; #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) /* Room for N __GFP_FOO bits */ -#define __GFP_BITS_SHIFT (24 + \ - 3 * IS_ENABLED(CONFIG_KASAN_HW_TAGS) + \ - IS_ENABLED(CONFIG_LOCKDEP)) +#define __GFP_BITS_SHIFT (27 + IS_ENABLED(CONFIG_LOCKDEP)) #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /** -- cgit v1.2.3 From e36764ecf87cb86051f26cc8e5a9a665784a9f39 Mon Sep 17 00:00:00 2001 From: Ramalingam C Date: Fri, 1 Apr 2022 18:07:49 +0530 Subject: drm/ttm: Add a parameter to add extra pages into ttm_tt Add a parameter called "extra_pages" for ttm_tt_init, to indicate that driver needs extra pages in ttm_tt. v2: Used imperative wording [Thomas and Christian] Signed-off-by: Ramalingam C cc: Christian Koenig cc: Hellstrom Thomas Reviewed-by: Thomas Hellstrom Reviewed-by: Christian Konig Reviewed-by: Nirmoy Das Link: https://patchwork.freedesktop.org/patch/msgid/20220401123751.27771-8-ramalingam.c@intel.com --- include/drm/ttm/ttm_tt.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index f20832139815..17a0310e8aaa 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -140,6 +140,7 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc); * @bo: The buffer object we create the ttm for. * @page_flags: Page flags as identified by TTM_TT_FLAG_XX flags. * @caching: the desired caching state of the pages + * @extra_pages: Extra pages needed for the driver. * * Create a struct ttm_tt to back data with system memory pages. * No pages are actually allocated. @@ -147,7 +148,8 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc); * NULL: Out of memory. */ int ttm_tt_init(struct ttm_tt *ttm, struct ttm_buffer_object *bo, - uint32_t page_flags, enum ttm_caching caching); + uint32_t page_flags, enum ttm_caching caching, + unsigned long extra_pages); int ttm_sg_tt_init(struct ttm_tt *ttm_dma, struct ttm_buffer_object *bo, uint32_t page_flags, enum ttm_caching caching); -- cgit v1.2.3 From df06dae3f2a8bfb83683abf88d3dcde23fc8093d Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 23 Feb 2022 16:53:02 +0000 Subject: KVM: Don't actually set a request when evicting vCPUs for GFN cache invd Don't actually set a request bit in vcpu->requests when making a request purely to force a vCPU to exit the guest. Logging a request but not actually consuming it would cause the vCPU to get stuck in an infinite loop during KVM_RUN because KVM would see the pending request and bail from VM-Enter to service the request. Note, it's currently impossible for KVM to set KVM_REQ_GPC_INVALIDATE as nothing in KVM is wired up to set guest_uses_pa=true. But, it'd be all too easy for arch code to introduce use of kvm_gfn_to_pfn_cache_init() without implementing handling of the request, especially since getting test coverage of MMU notifier interaction with specific KVM features usually requires a directed test. Opportunistically rename gfn_to_pfn_cache_invalidate_start()'s wake_vcpus to evict_vcpus. The purpose of the request is to get vCPUs out of guest mode, it's supposed to _avoid_ waking vCPUs that are blocking. Opportunistically rename KVM_REQ_GPC_INVALIDATE to be more specific as to what it wants to accomplish, and to genericize the name so that it can used for similar but unrelated scenarios, should they arise in the future. Add a comment and documentation to explain why the "no action" request exists. Add compile-time assertions to help detect improper usage. Use the inner assertless helper in the one s390 path that makes requests without a hardcoded request. Cc: David Woodhouse Signed-off-by: Sean Christopherson Message-Id: <20220223165302.3205276-1-seanjc@google.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 38 +++++++++++++++++++++++++++++++------- 1 file changed, 31 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9536ffa0473b..678fd7914521 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -148,6 +148,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQUEST_MASK GENMASK(7,0) #define KVM_REQUEST_NO_WAKEUP BIT(8) #define KVM_REQUEST_WAIT BIT(9) +#define KVM_REQUEST_NO_ACTION BIT(10) /* * Architecture-independent vcpu->requests bit members * Bits 4-7 are reserved for more arch-independent bits. @@ -156,9 +157,18 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_VM_DEAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_UNBLOCK 2 #define KVM_REQ_UNHALT 3 -#define KVM_REQ_GPC_INVALIDATE (5 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQUEST_ARCH_BASE 8 +/* + * KVM_REQ_OUTSIDE_GUEST_MODE exists is purely as way to force the vCPU to + * OUTSIDE_GUEST_MODE. KVM_REQ_OUTSIDE_GUEST_MODE differs from a vCPU "kick" + * in that it ensures the vCPU has reached OUTSIDE_GUEST_MODE before continuing + * on. A kick only guarantees that the vCPU is on its way out, e.g. a previous + * kick may have set vcpu->mode to EXITING_GUEST_MODE, and so there's no + * guarantee the vCPU received an IPI and has actually exited guest mode. + */ +#define KVM_REQ_OUTSIDE_GUEST_MODE (KVM_REQUEST_NO_ACTION | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) + #define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \ BUILD_BUG_ON((unsigned)(nr) >= (sizeof_field(struct kvm_vcpu, requests) * 8) - KVM_REQUEST_ARCH_BASE); \ (unsigned)(((nr) + KVM_REQUEST_ARCH_BASE) | (flags)); \ @@ -1222,7 +1232,9 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); * @vcpu: vCPU to be used for marking pages dirty and to be woken on * invalidation. * @guest_uses_pa: indicates that the resulting host physical PFN is used while - * @vcpu is IN_GUEST_MODE so invalidations should wake it. + * @vcpu is IN_GUEST_MODE; invalidations of the cache from MMU + * notifiers (but not for KVM memslot changes!) will also force + * @vcpu to exit the guest to refresh the cache. * @kernel_map: requests a kernel virtual mapping (kmap / memremap). * @gpa: guest physical address to map. * @len: sanity check; the range being access must fit a single page. @@ -1233,10 +1245,9 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); * -EFAULT for an untranslatable guest physical address. * * This primes a gfn_to_pfn_cache and links it into the @kvm's list for - * invalidations to be processed. Invalidation callbacks to @vcpu using - * %KVM_REQ_GPC_INVALIDATE will occur only for MMU notifiers, not for KVM - * memslot changes. Callers are required to use kvm_gfn_to_pfn_cache_check() - * to ensure that the cache is valid before accessing the target page. + * invalidations to be processed. Callers are required to use + * kvm_gfn_to_pfn_cache_check() to ensure that the cache is valid before + * accessing the target page. */ int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, struct kvm_vcpu *vcpu, bool guest_uses_pa, @@ -1984,7 +1995,7 @@ static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) void kvm_arch_irq_routing_update(struct kvm *kvm); -static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) +static inline void __kvm_make_request(int req, struct kvm_vcpu *vcpu) { /* * Ensure the rest of the request is published to kvm_check_request's @@ -1994,6 +2005,19 @@ static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) set_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests); } +static __always_inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) +{ + /* + * Request that don't require vCPU action should never be logged in + * vcpu->requests. The vCPU won't clear the request, so it will stay + * logged indefinitely and prevent the vCPU from entering the guest. + */ + BUILD_BUG_ON(!__builtin_constant_p(req) || + (req & KVM_REQUEST_NO_ACTION)); + + __kvm_make_request(req, vcpu); +} + static inline bool kvm_request_pending(struct kvm_vcpu *vcpu) { return READ_ONCE(vcpu->requests); -- cgit v1.2.3 From d0d96121d03d6d9cf608d948247a9f24f5a02da9 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 3 Mar 2022 15:41:11 +0000 Subject: KVM: Use enum to track if cached PFN will be used in guest and/or host Replace the guest_uses_pa and kernel_map booleans in the PFN cache code with a unified enum/bitmask. Using explicit names makes it easier to review and audit call sites. Opportunistically add a WARN to prevent passing garbage; instantating a cache without declaring its usage is either buggy or pointless. Signed-off-by: Sean Christopherson Signed-off-by: David Woodhouse Signed-off-by: Paolo Bonzini Message-Id: <20220303154127.202856-2-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 16 ++++++++-------- include/linux/kvm_types.h | 10 ++++++++-- 2 files changed, 16 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 678fd7914521..be9bbc0c6200 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1231,11 +1231,12 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); * @gpc: struct gfn_to_pfn_cache object. * @vcpu: vCPU to be used for marking pages dirty and to be woken on * invalidation. - * @guest_uses_pa: indicates that the resulting host physical PFN is used while - * @vcpu is IN_GUEST_MODE; invalidations of the cache from MMU - * notifiers (but not for KVM memslot changes!) will also force - * @vcpu to exit the guest to refresh the cache. - * @kernel_map: requests a kernel virtual mapping (kmap / memremap). + * @usage: indicates if the resulting host physical PFN is used while + * the @vcpu is IN_GUEST_MODE (in which case invalidation of + * the cache from MMU notifiers---but not for KVM memslot + * changes!---will also force @vcpu to exit the guest and + * refresh the cache); and/or if the PFN used directly + * by KVM (and thus needs a kernel virtual mapping). * @gpa: guest physical address to map. * @len: sanity check; the range being access must fit a single page. * @dirty: mark the cache dirty immediately. @@ -1250,9 +1251,8 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); * accessing the target page. */ int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, - struct kvm_vcpu *vcpu, bool guest_uses_pa, - bool kernel_map, gpa_t gpa, unsigned long len, - bool dirty); + struct kvm_vcpu *vcpu, enum pfn_cache_usage usage, + gpa_t gpa, unsigned long len, bool dirty); /** * kvm_gfn_to_pfn_cache_check - check validity of a gfn_to_pfn_cache. diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index dceac12c1ce5..784f37cbf33e 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -18,6 +18,7 @@ struct kvm_memslots; enum kvm_mr_change; +#include #include #include @@ -46,6 +47,12 @@ typedef u64 hfn_t; typedef hfn_t kvm_pfn_t; +enum pfn_cache_usage { + KVM_GUEST_USES_PFN = BIT(0), + KVM_HOST_USES_PFN = BIT(1), + KVM_GUEST_AND_HOST_USE_PFN = KVM_GUEST_USES_PFN | KVM_HOST_USES_PFN, +}; + struct gfn_to_hva_cache { u64 generation; gpa_t gpa; @@ -64,11 +71,10 @@ struct gfn_to_pfn_cache { rwlock_t lock; void *khva; kvm_pfn_t pfn; + enum pfn_cache_usage usage; bool active; bool valid; bool dirty; - bool kernel_map; - bool guest_uses_pa; }; #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE -- cgit v1.2.3 From cf1d88b36ba7e83bdaa50bccc4c47864e8f08cbe Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 3 Mar 2022 15:41:12 +0000 Subject: KVM: Remove dirty handling from gfn_to_pfn_cache completely It isn't OK to cache the dirty status of a page in internal structures for an indefinite period of time. Any time a vCPU exits the run loop to userspace might be its last; the VMM might do its final check of the dirty log, flush the last remaining dirty pages to the destination and complete a live migration. If we have internal 'dirty' state which doesn't get flushed until the vCPU is finally destroyed on the source after migration is complete, then we have lost data because that will escape the final copy. This problem already exists with the use of kvm_vcpu_unmap() to mark pages dirty in e.g. VMX nesting. Note that the actual Linux MM already considers the page to be dirty since we have a writeable mapping of it. This is just about the KVM dirty logging. For the nesting-style use cases (KVM_GUEST_USES_PFN) we will need to track which gfn_to_pfn_caches have been used and explicitly mark the corresponding pages dirty before returning to userspace. But we would have needed external tracking of that anyway, rather than walking the full list of GPCs to find those belonging to this vCPU which are dirty. So let's rely *solely* on that external tracking, and keep it simple rather than laying a tempting trap for callers to fall into. Signed-off-by: David Woodhouse Signed-off-by: Paolo Bonzini Message-Id: <20220303154127.202856-3-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 14 +++++--------- include/linux/kvm_types.h | 1 - 2 files changed, 5 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index be9bbc0c6200..3f9b22c4983a 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1239,7 +1239,6 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); * by KVM (and thus needs a kernel virtual mapping). * @gpa: guest physical address to map. * @len: sanity check; the range being access must fit a single page. - * @dirty: mark the cache dirty immediately. * * @return: 0 for success. * -EINVAL for a mapping which would cross a page boundary. @@ -1252,7 +1251,7 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); */ int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, struct kvm_vcpu *vcpu, enum pfn_cache_usage usage, - gpa_t gpa, unsigned long len, bool dirty); + gpa_t gpa, unsigned long len); /** * kvm_gfn_to_pfn_cache_check - check validity of a gfn_to_pfn_cache. @@ -1261,7 +1260,6 @@ int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, * @gpc: struct gfn_to_pfn_cache object. * @gpa: current guest physical address to map. * @len: sanity check; the range being access must fit a single page. - * @dirty: mark the cache dirty immediately. * * @return: %true if the cache is still valid and the address matches. * %false if the cache is not valid. @@ -1283,7 +1281,6 @@ bool kvm_gfn_to_pfn_cache_check(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, * @gpc: struct gfn_to_pfn_cache object. * @gpa: updated guest physical address to map. * @len: sanity check; the range being access must fit a single page. - * @dirty: mark the cache dirty immediately. * * @return: 0 for success. * -EINVAL for a mapping which would cross a page boundary. @@ -1296,7 +1293,7 @@ bool kvm_gfn_to_pfn_cache_check(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, * with the lock still held to permit access. */ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, - gpa_t gpa, unsigned long len, bool dirty); + gpa_t gpa, unsigned long len); /** * kvm_gfn_to_pfn_cache_unmap - temporarily unmap a gfn_to_pfn_cache. @@ -1304,10 +1301,9 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, * @kvm: pointer to kvm instance. * @gpc: struct gfn_to_pfn_cache object. * - * This unmaps the referenced page and marks it dirty, if appropriate. The - * cache is left in the invalid state but at least the mapping from GPA to - * userspace HVA will remain cached and can be reused on a subsequent - * refresh. + * This unmaps the referenced page. The cache is left in the invalid state + * but at least the mapping from GPA to userspace HVA will remain cached + * and can be reused on a subsequent refresh. */ void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc); diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 784f37cbf33e..ac1ebb37a0ff 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -74,7 +74,6 @@ struct gfn_to_pfn_cache { enum pfn_cache_usage usage; bool active; bool valid; - bool dirty; }; #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE -- cgit v1.2.3 From 8733068b9bdbc7a54f02dcc59eb0e4789cd60942 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 3 Mar 2022 15:41:17 +0000 Subject: KVM: x86/xen: Make kvm_xen_set_evtchn() reusable from other places Clean it up to return -errno on error consistently, while still being compatible with the return conventions for kvm_arch_set_irq_inatomic() and the kvm_set_irq() callback. We use -ENOTCONN to indicate when the port is masked. No existing users care, except that it's negative. Also allow it to optimise the vCPU lookup. Unless we abuse the lapic map, there is no quick lookup from APIC ID to a vCPU; the logic in kvm_get_vcpu_by_id() will just iterate over all vCPUs till it finds the one it wants. So do that just once and stash the result in the struct kvm_xen_evtchn for next time. Signed-off-by: David Woodhouse Signed-off-by: Paolo Bonzini Message-Id: <20220303154127.202856-8-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3f9b22c4983a..252ee4a61b58 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -611,7 +611,8 @@ struct kvm_hv_sint { struct kvm_xen_evtchn { u32 port; - u32 vcpu; + u32 vcpu_id; + int vcpu_idx; u32 priority; }; -- cgit v1.2.3 From 35025735a79eaa894c43837b94fd33c9d6b122df Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 3 Mar 2022 15:41:18 +0000 Subject: KVM: x86/xen: Support direct injection of event channel events This adds a KVM_XEN_HVM_EVTCHN_SEND ioctl which allows direct injection of events given an explicit { vcpu, port, priority } in precisely the same form that those fields are given in the IRQ routing table. Userspace is currently able to inject 2-level events purely by setting the bits in the shared_info and vcpu_info, but FIFO event channels are harder to deal with; we will need the kernel to take sole ownership of delivery when we support those. A patch advertising this feature with a new bit in the KVM_CAP_XEN_HVM ioctl will be added in a subsequent patch. Signed-off-by: David Woodhouse Signed-off-by: Paolo Bonzini Message-Id: <20220303154127.202856-9-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 91a6fe4e02c0..49cd2e9e0f6a 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1699,6 +1699,9 @@ struct kvm_xen_hvm_attr { #define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) #define KVM_XEN_VCPU_SET_ATTR _IOW(KVMIO, 0xcb, struct kvm_xen_vcpu_attr) +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_HVM_EVTCHN_SEND _IOW(KVMIO, 0xd0, struct kvm_irq_routing_xen_evtchn) + #define KVM_GET_SREGS2 _IOR(KVMIO, 0xcc, struct kvm_sregs2) #define KVM_SET_SREGS2 _IOW(KVMIO, 0xcd, struct kvm_sregs2) -- cgit v1.2.3 From 2fd6df2f2b47d4301b1ee0fe9d627d1c061a5988 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Thu, 3 Mar 2022 15:41:19 +0000 Subject: KVM: x86/xen: intercept EVTCHNOP_send from guests Userspace registers a sending @port to either deliver to an @eventfd or directly back to a local event channel port. After binding events the guest or host may wish to bind those events to a particular vcpu. This is usually done for unbound and and interdomain events. Update requests are handled via the KVM_XEN_EVTCHN_UPDATE flag. Unregistered ports are handled by the emulator. Co-developed-by: Ankur Arora Co-developed-By: David Woodhouse Signed-off-by: Joao Martins Signed-off-by: Ankur Arora Signed-off-by: David Woodhouse Signed-off-by: Paolo Bonzini Message-Id: <20220303154127.202856-10-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 49cd2e9e0f6a..623ed2cb228f 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1686,6 +1686,32 @@ struct kvm_xen_hvm_attr { struct { __u64 gfn; } shared_info; + struct { + __u32 send_port; + __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */ + __u32 flags; +#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0) +#define KVM_XEN_EVTCHN_UPDATE (1 << 1) +#define KVM_XEN_EVTCHN_RESET (1 << 2) + /* + * Events sent by the guest are either looped back to + * the guest itself (potentially on a different port#) + * or signalled via an eventfd. + */ + union { + struct { + __u32 port; + __u32 vcpu; + __u32 priority; + } port; + struct { + __u32 port; /* Zero for eventfd */ + __s32 fd; + } eventfd; + __u32 padding[4]; + } deliver; + } evtchn; + __u64 pad[8]; } u; }; @@ -1694,6 +1720,8 @@ struct kvm_xen_hvm_attr { #define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 #define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 #define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3 /* Per-vCPU Xen attributes */ #define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) -- cgit v1.2.3 From 942c2490c23f2800ad8143f5eb84a79b859aa743 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 3 Mar 2022 15:41:21 +0000 Subject: KVM: x86/xen: Add KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID In order to intercept hypercalls such as VCPUOP_set_singleshot_timer, we need to be aware of the Xen CPU numbering. This looks a lot like the Hyper-V handling of vpidx, for obvious reasons. Signed-off-by: David Woodhouse Signed-off-by: Paolo Bonzini Message-Id: <20220303154127.202856-12-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 623ed2cb228f..4b65e9f0a4d9 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1747,6 +1747,7 @@ struct kvm_xen_vcpu_attr { __u64 time_blocked; __u64 time_offline; } runstate; + __u32 vcpu_id; } u; }; @@ -1757,6 +1758,8 @@ struct kvm_xen_vcpu_attr { #define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3 #define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4 #define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 /* Secure Encrypted Virtualization command */ enum sev_cmd_id { -- cgit v1.2.3 From 536395260582be7443b0b35b0bbb89ffe3947f62 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Thu, 3 Mar 2022 15:41:22 +0000 Subject: KVM: x86/xen: handle PV timers oneshot mode If the guest has offloaded the timer virq, handle the following hypercalls for programming the timer: VCPUOP_set_singleshot_timer VCPUOP_stop_singleshot_timer set_timer_op(timestamp_ns) The event channel corresponding to the timer virq is then used to inject events once timer deadlines are met. For now we back the PV timer with hrtimer. [ dwmw2: Add save/restore, 32-bit compat mode, immediate delivery, don't check timer in kvm_vcpu_has_event() ] Signed-off-by: Joao Martins Signed-off-by: David Woodhouse Signed-off-by: Paolo Bonzini Message-Id: <20220303154127.202856-13-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 4b65e9f0a4d9..cb223e425223 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1748,6 +1748,11 @@ struct kvm_xen_vcpu_attr { __u64 time_offline; } runstate; __u32 vcpu_id; + struct { + __u32 port; + __u32 priority; + __u64 expires_ns; + } timer; } u; }; @@ -1760,6 +1765,7 @@ struct kvm_xen_vcpu_attr { #define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5 /* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ #define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 +#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7 /* Secure Encrypted Virtualization command */ enum sev_cmd_id { -- cgit v1.2.3 From 28d1629f751c4a5f9437fbaa0ee4ed81d1a8e587 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 3 Mar 2022 15:41:23 +0000 Subject: KVM: x86/xen: Kernel acceleration for XENVER_version Turns out this is a fast path for PV guests because they use it to trigger the event channel upcall. So letting it bounce all the way up to userspace is not great. Signed-off-by: David Woodhouse Signed-off-by: Paolo Bonzini Message-Id: <20220303154127.202856-14-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index cb223e425223..4dda3896ed71 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1711,7 +1711,7 @@ struct kvm_xen_hvm_attr { __u32 padding[4]; } deliver; } evtchn; - + __u32 xen_version; __u64 pad[8]; } u; }; @@ -1722,6 +1722,7 @@ struct kvm_xen_hvm_attr { #define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 /* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ #define KVM_XEN_ATTR_TYPE_EVTCHN 0x3 +#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4 /* Per-vCPU Xen attributes */ #define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) -- cgit v1.2.3 From fde0451be8fb3208d4d146b8602d99ee8139e515 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 3 Mar 2022 15:41:24 +0000 Subject: KVM: x86/xen: Support per-vCPU event channel upcall via local APIC Windows uses a per-vCPU vector, and it's delivered via the local APIC basically like an MSI (with associated EOI) unlike the traditional guest-wide vector which is just magically asserted by Xen (and in the KVM case by kvm_xen_has_interrupt() / kvm_cpu_get_extint()). Now that the kernel is able to raise event channel events for itself, being able to do so for Windows guests is also going to be useful. Signed-off-by: David Woodhouse Signed-off-by: Paolo Bonzini Message-Id: <20220303154127.202856-15-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 4dda3896ed71..a9ba690c4f37 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1754,6 +1754,7 @@ struct kvm_xen_vcpu_attr { __u32 priority; __u64 expires_ns; } timer; + __u8 vector; } u; }; @@ -1767,6 +1768,7 @@ struct kvm_xen_vcpu_attr { /* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ #define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 #define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7 +#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8 /* Secure Encrypted Virtualization command */ enum sev_cmd_id { -- cgit v1.2.3 From 661a20fab7d156cf6b9a407c946a1e558a633151 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 3 Mar 2022 15:41:25 +0000 Subject: KVM: x86/xen: Advertise and document KVM_XEN_HVM_CONFIG_EVTCHN_SEND MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit At the end of the patch series adding this batch of event channel acceleration features, finally add the feature bit which advertises them and document it all. For SCHEDOP_poll we need to wake a polling vCPU when a given port is triggered, even when it's masked — and we want to implement that in the kernel, for efficiency. So we want the kernel to know that it has sole ownership of event channel delivery. Thus, we allow userspace to make the 'promise' by setting the corresponding feature bit in its KVM_XEN_HVM_CONFIG call. As we implement SCHEDOP_poll bypass later, we will do so only if that promise has been made by userspace. Signed-off-by: David Woodhouse Signed-off-by: Paolo Bonzini Message-Id: <20220303154127.202856-16-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index a9ba690c4f37..ee5cc9e2a837 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1232,6 +1232,7 @@ struct kvm_x86_mce { #define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) #define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) +#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) struct kvm_xen_hvm_config { __u32 flags; -- cgit v1.2.3 From ffbb61d09fc56c85e28b110494f3788d0ed4d1f8 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Fri, 25 Feb 2022 14:53:02 +0000 Subject: KVM: x86: Accept KVM_[GS]ET_TSC_KHZ as a VM ioctl. This sets the default TSC frequency for subsequently created vCPUs. Signed-off-by: David Woodhouse Message-Id: <20220225145304.36166-2-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index ee5cc9e2a837..8616af85dc5d 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1144,6 +1144,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_MEM_OP_EXTENSION 211 #define KVM_CAP_PMU_CAPABILITY 212 #define KVM_CAP_DISABLE_QUIRKS2 213 +#define KVM_CAP_VM_TSC_CONTROL 214 #ifdef KVM_CAP_IRQ_ROUTING @@ -1471,7 +1472,8 @@ struct kvm_s390_ucas_mapping { #define KVM_SET_PIT2 _IOW(KVMIO, 0xa0, struct kvm_pit_state2) /* Available with KVM_CAP_PPC_GET_PVINFO */ #define KVM_PPC_GET_PVINFO _IOW(KVMIO, 0xa1, struct kvm_ppc_pvinfo) -/* Available with KVM_CAP_TSC_CONTROL */ +/* Available with KVM_CAP_TSC_CONTROL for a vCPU, or with +* KVM_CAP_VM_TSC_CONTROL to set defaults for a VM */ #define KVM_SET_TSC_KHZ _IO(KVMIO, 0xa2) #define KVM_GET_TSC_KHZ _IO(KVMIO, 0xa3) /* Available with KVM_CAP_PCI_2_3 */ -- cgit v1.2.3 From 84055411d861d3a2b485ad629fce7d2179d72c1e Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 29 Mar 2022 16:50:44 -0400 Subject: tracing: Rename the staging files for trace_events When looking for implementation of different phases of the creation of the TRACE_EVENT() macro, it is pretty useless when all helper macro redefinitions are in files labeled "stageX_defines.h". Rename them to state which phase the files are for. For instance, when looking for the defines that are used to create the event fields, seeing "stage4_event_fields.h" gives the developer a good idea that the defines are in that file. Signed-off-by: Steven Rostedt (Google) --- include/trace/stages/stage1_defines.h | 51 ---------- include/trace/stages/stage1_struct_define.h | 51 ++++++++++ include/trace/stages/stage2_data_offsets.h | 54 +++++++++++ include/trace/stages/stage2_defines.h | 54 ----------- include/trace/stages/stage3_defines.h | 135 --------------------------- include/trace/stages/stage3_trace_output.h | 135 +++++++++++++++++++++++++++ include/trace/stages/stage4_defines.h | 63 ------------- include/trace/stages/stage4_event_fields.h | 63 +++++++++++++ include/trace/stages/stage5_defines.h | 89 ------------------ include/trace/stages/stage5_get_offsets.h | 89 ++++++++++++++++++ include/trace/stages/stage6_defines.h | 106 --------------------- include/trace/stages/stage6_event_callback.h | 106 +++++++++++++++++++++ include/trace/stages/stage7_class_define.h | 36 +++++++ include/trace/stages/stage7_defines.h | 36 ------- include/trace/trace_custom_events.h | 14 +-- include/trace/trace_events.h | 14 +-- 16 files changed, 548 insertions(+), 548 deletions(-) delete mode 100644 include/trace/stages/stage1_defines.h create mode 100644 include/trace/stages/stage1_struct_define.h create mode 100644 include/trace/stages/stage2_data_offsets.h delete mode 100644 include/trace/stages/stage2_defines.h delete mode 100644 include/trace/stages/stage3_defines.h create mode 100644 include/trace/stages/stage3_trace_output.h delete mode 100644 include/trace/stages/stage4_defines.h create mode 100644 include/trace/stages/stage4_event_fields.h delete mode 100644 include/trace/stages/stage5_defines.h create mode 100644 include/trace/stages/stage5_get_offsets.h delete mode 100644 include/trace/stages/stage6_defines.h create mode 100644 include/trace/stages/stage6_event_callback.h create mode 100644 include/trace/stages/stage7_class_define.h delete mode 100644 include/trace/stages/stage7_defines.h (limited to 'include') diff --git a/include/trace/stages/stage1_defines.h b/include/trace/stages/stage1_defines.h deleted file mode 100644 index a16783419687..000000000000 --- a/include/trace/stages/stage1_defines.h +++ /dev/null @@ -1,51 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -/* Stage 1 definitions for creating trace events */ - -#undef __field -#define __field(type, item) type item; - -#undef __field_ext -#define __field_ext(type, item, filter_type) type item; - -#undef __field_struct -#define __field_struct(type, item) type item; - -#undef __field_struct_ext -#define __field_struct_ext(type, item, filter_type) type item; - -#undef __array -#define __array(type, item, len) type item[len]; - -#undef __dynamic_array -#define __dynamic_array(type, item, len) u32 __data_loc_##item; - -#undef __string -#define __string(item, src) __dynamic_array(char, item, -1) - -#undef __string_len -#define __string_len(item, src, len) __dynamic_array(char, item, -1) - -#undef __bitmask -#define __bitmask(item, nr_bits) __dynamic_array(char, item, -1) - -#undef __sockaddr -#define __sockaddr(field, len) __dynamic_array(u8, field, len) - -#undef __rel_dynamic_array -#define __rel_dynamic_array(type, item, len) u32 __rel_loc_##item; - -#undef __rel_string -#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) - -#undef __rel_string_len -#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) - -#undef __rel_bitmask -#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(char, item, -1) - -#undef __rel_sockaddr -#define __rel_sockaddr(field, len) __rel_dynamic_array(u8, field, len) - -#undef TP_STRUCT__entry -#define TP_STRUCT__entry(args...) args diff --git a/include/trace/stages/stage1_struct_define.h b/include/trace/stages/stage1_struct_define.h new file mode 100644 index 000000000000..a16783419687 --- /dev/null +++ b/include/trace/stages/stage1_struct_define.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Stage 1 definitions for creating trace events */ + +#undef __field +#define __field(type, item) type item; + +#undef __field_ext +#define __field_ext(type, item, filter_type) type item; + +#undef __field_struct +#define __field_struct(type, item) type item; + +#undef __field_struct_ext +#define __field_struct_ext(type, item, filter_type) type item; + +#undef __array +#define __array(type, item, len) type item[len]; + +#undef __dynamic_array +#define __dynamic_array(type, item, len) u32 __data_loc_##item; + +#undef __string +#define __string(item, src) __dynamic_array(char, item, -1) + +#undef __string_len +#define __string_len(item, src, len) __dynamic_array(char, item, -1) + +#undef __bitmask +#define __bitmask(item, nr_bits) __dynamic_array(char, item, -1) + +#undef __sockaddr +#define __sockaddr(field, len) __dynamic_array(u8, field, len) + +#undef __rel_dynamic_array +#define __rel_dynamic_array(type, item, len) u32 __rel_loc_##item; + +#undef __rel_string +#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) + +#undef __rel_string_len +#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) + +#undef __rel_bitmask +#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(char, item, -1) + +#undef __rel_sockaddr +#define __rel_sockaddr(field, len) __rel_dynamic_array(u8, field, len) + +#undef TP_STRUCT__entry +#define TP_STRUCT__entry(args...) args diff --git a/include/trace/stages/stage2_data_offsets.h b/include/trace/stages/stage2_data_offsets.h new file mode 100644 index 000000000000..42fd1e8813ec --- /dev/null +++ b/include/trace/stages/stage2_data_offsets.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Stage 2 definitions for creating trace events */ + +#undef TRACE_DEFINE_ENUM +#define TRACE_DEFINE_ENUM(a) + +#undef TRACE_DEFINE_SIZEOF +#define TRACE_DEFINE_SIZEOF(a) + +#undef __field +#define __field(type, item) + +#undef __field_ext +#define __field_ext(type, item, filter_type) + +#undef __field_struct +#define __field_struct(type, item) + +#undef __field_struct_ext +#define __field_struct_ext(type, item, filter_type) + +#undef __array +#define __array(type, item, len) + +#undef __dynamic_array +#define __dynamic_array(type, item, len) u32 item; + +#undef __string +#define __string(item, src) __dynamic_array(char, item, -1) + +#undef __string_len +#define __string_len(item, src, len) __dynamic_array(char, item, -1) + +#undef __bitmask +#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1) + +#undef __sockaddr +#define __sockaddr(field, len) __dynamic_array(u8, field, len) + +#undef __rel_dynamic_array +#define __rel_dynamic_array(type, item, len) u32 item; + +#undef __rel_string +#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) + +#undef __rel_string_len +#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) + +#undef __rel_bitmask +#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1) + +#undef __rel_sockaddr +#define __rel_sockaddr(field, len) __rel_dynamic_array(u8, field, len) diff --git a/include/trace/stages/stage2_defines.h b/include/trace/stages/stage2_defines.h deleted file mode 100644 index 42fd1e8813ec..000000000000 --- a/include/trace/stages/stage2_defines.h +++ /dev/null @@ -1,54 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -/* Stage 2 definitions for creating trace events */ - -#undef TRACE_DEFINE_ENUM -#define TRACE_DEFINE_ENUM(a) - -#undef TRACE_DEFINE_SIZEOF -#define TRACE_DEFINE_SIZEOF(a) - -#undef __field -#define __field(type, item) - -#undef __field_ext -#define __field_ext(type, item, filter_type) - -#undef __field_struct -#define __field_struct(type, item) - -#undef __field_struct_ext -#define __field_struct_ext(type, item, filter_type) - -#undef __array -#define __array(type, item, len) - -#undef __dynamic_array -#define __dynamic_array(type, item, len) u32 item; - -#undef __string -#define __string(item, src) __dynamic_array(char, item, -1) - -#undef __string_len -#define __string_len(item, src, len) __dynamic_array(char, item, -1) - -#undef __bitmask -#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1) - -#undef __sockaddr -#define __sockaddr(field, len) __dynamic_array(u8, field, len) - -#undef __rel_dynamic_array -#define __rel_dynamic_array(type, item, len) u32 item; - -#undef __rel_string -#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) - -#undef __rel_string_len -#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) - -#undef __rel_bitmask -#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1) - -#undef __rel_sockaddr -#define __rel_sockaddr(field, len) __rel_dynamic_array(u8, field, len) diff --git a/include/trace/stages/stage3_defines.h b/include/trace/stages/stage3_defines.h deleted file mode 100644 index e3b183e9d18e..000000000000 --- a/include/trace/stages/stage3_defines.h +++ /dev/null @@ -1,135 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -/* Stage 3 definitions for creating trace events */ - -#undef __entry -#define __entry field - -#undef TP_printk -#define TP_printk(fmt, args...) fmt "\n", args - -#undef __get_dynamic_array -#define __get_dynamic_array(field) \ - ((void *)__entry + (__entry->__data_loc_##field & 0xffff)) - -#undef __get_dynamic_array_len -#define __get_dynamic_array_len(field) \ - ((__entry->__data_loc_##field >> 16) & 0xffff) - -#undef __get_str -#define __get_str(field) ((char *)__get_dynamic_array(field)) - -#undef __get_rel_dynamic_array -#define __get_rel_dynamic_array(field) \ - ((void *)__entry + \ - offsetof(typeof(*__entry), __rel_loc_##field) + \ - sizeof(__entry->__rel_loc_##field) + \ - (__entry->__rel_loc_##field & 0xffff)) - -#undef __get_rel_dynamic_array_len -#define __get_rel_dynamic_array_len(field) \ - ((__entry->__rel_loc_##field >> 16) & 0xffff) - -#undef __get_rel_str -#define __get_rel_str(field) ((char *)__get_rel_dynamic_array(field)) - -#undef __get_bitmask -#define __get_bitmask(field) \ - ({ \ - void *__bitmask = __get_dynamic_array(field); \ - unsigned int __bitmask_size; \ - __bitmask_size = __get_dynamic_array_len(field); \ - trace_print_bitmask_seq(p, __bitmask, __bitmask_size); \ - }) - -#undef __get_rel_bitmask -#define __get_rel_bitmask(field) \ - ({ \ - void *__bitmask = __get_rel_dynamic_array(field); \ - unsigned int __bitmask_size; \ - __bitmask_size = __get_rel_dynamic_array_len(field); \ - trace_print_bitmask_seq(p, __bitmask, __bitmask_size); \ - }) - -#undef __get_sockaddr -#define __get_sockaddr(field) ((struct sockaddr *)__get_dynamic_array(field)) - -#undef __get_rel_sockaddr -#define __get_rel_sockaddr(field) ((struct sockaddr *)__get_rel_dynamic_array(field)) - -#undef __print_flags -#define __print_flags(flag, delim, flag_array...) \ - ({ \ - static const struct trace_print_flags __flags[] = \ - { flag_array, { -1, NULL }}; \ - trace_print_flags_seq(p, delim, flag, __flags); \ - }) - -#undef __print_symbolic -#define __print_symbolic(value, symbol_array...) \ - ({ \ - static const struct trace_print_flags symbols[] = \ - { symbol_array, { -1, NULL }}; \ - trace_print_symbols_seq(p, value, symbols); \ - }) - -#undef __print_flags_u64 -#undef __print_symbolic_u64 -#if BITS_PER_LONG == 32 -#define __print_flags_u64(flag, delim, flag_array...) \ - ({ \ - static const struct trace_print_flags_u64 __flags[] = \ - { flag_array, { -1, NULL } }; \ - trace_print_flags_seq_u64(p, delim, flag, __flags); \ - }) - -#define __print_symbolic_u64(value, symbol_array...) \ - ({ \ - static const struct trace_print_flags_u64 symbols[] = \ - { symbol_array, { -1, NULL } }; \ - trace_print_symbols_seq_u64(p, value, symbols); \ - }) -#else -#define __print_flags_u64(flag, delim, flag_array...) \ - __print_flags(flag, delim, flag_array) - -#define __print_symbolic_u64(value, symbol_array...) \ - __print_symbolic(value, symbol_array) -#endif - -#undef __print_hex -#define __print_hex(buf, buf_len) \ - trace_print_hex_seq(p, buf, buf_len, false) - -#undef __print_hex_str -#define __print_hex_str(buf, buf_len) \ - trace_print_hex_seq(p, buf, buf_len, true) - -#undef __print_array -#define __print_array(array, count, el_size) \ - ({ \ - BUILD_BUG_ON(el_size != 1 && el_size != 2 && \ - el_size != 4 && el_size != 8); \ - trace_print_array_seq(p, array, count, el_size); \ - }) - -#undef __print_hex_dump -#define __print_hex_dump(prefix_str, prefix_type, \ - rowsize, groupsize, buf, len, ascii) \ - trace_print_hex_dump_seq(p, prefix_str, prefix_type, \ - rowsize, groupsize, buf, len, ascii) - -#undef __print_ns_to_secs -#define __print_ns_to_secs(value) \ - ({ \ - u64 ____val = (u64)(value); \ - do_div(____val, NSEC_PER_SEC); \ - ____val; \ - }) - -#undef __print_ns_without_secs -#define __print_ns_without_secs(value) \ - ({ \ - u64 ____val = (u64)(value); \ - (u32) do_div(____val, NSEC_PER_SEC); \ - }) diff --git a/include/trace/stages/stage3_trace_output.h b/include/trace/stages/stage3_trace_output.h new file mode 100644 index 000000000000..e3b183e9d18e --- /dev/null +++ b/include/trace/stages/stage3_trace_output.h @@ -0,0 +1,135 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Stage 3 definitions for creating trace events */ + +#undef __entry +#define __entry field + +#undef TP_printk +#define TP_printk(fmt, args...) fmt "\n", args + +#undef __get_dynamic_array +#define __get_dynamic_array(field) \ + ((void *)__entry + (__entry->__data_loc_##field & 0xffff)) + +#undef __get_dynamic_array_len +#define __get_dynamic_array_len(field) \ + ((__entry->__data_loc_##field >> 16) & 0xffff) + +#undef __get_str +#define __get_str(field) ((char *)__get_dynamic_array(field)) + +#undef __get_rel_dynamic_array +#define __get_rel_dynamic_array(field) \ + ((void *)__entry + \ + offsetof(typeof(*__entry), __rel_loc_##field) + \ + sizeof(__entry->__rel_loc_##field) + \ + (__entry->__rel_loc_##field & 0xffff)) + +#undef __get_rel_dynamic_array_len +#define __get_rel_dynamic_array_len(field) \ + ((__entry->__rel_loc_##field >> 16) & 0xffff) + +#undef __get_rel_str +#define __get_rel_str(field) ((char *)__get_rel_dynamic_array(field)) + +#undef __get_bitmask +#define __get_bitmask(field) \ + ({ \ + void *__bitmask = __get_dynamic_array(field); \ + unsigned int __bitmask_size; \ + __bitmask_size = __get_dynamic_array_len(field); \ + trace_print_bitmask_seq(p, __bitmask, __bitmask_size); \ + }) + +#undef __get_rel_bitmask +#define __get_rel_bitmask(field) \ + ({ \ + void *__bitmask = __get_rel_dynamic_array(field); \ + unsigned int __bitmask_size; \ + __bitmask_size = __get_rel_dynamic_array_len(field); \ + trace_print_bitmask_seq(p, __bitmask, __bitmask_size); \ + }) + +#undef __get_sockaddr +#define __get_sockaddr(field) ((struct sockaddr *)__get_dynamic_array(field)) + +#undef __get_rel_sockaddr +#define __get_rel_sockaddr(field) ((struct sockaddr *)__get_rel_dynamic_array(field)) + +#undef __print_flags +#define __print_flags(flag, delim, flag_array...) \ + ({ \ + static const struct trace_print_flags __flags[] = \ + { flag_array, { -1, NULL }}; \ + trace_print_flags_seq(p, delim, flag, __flags); \ + }) + +#undef __print_symbolic +#define __print_symbolic(value, symbol_array...) \ + ({ \ + static const struct trace_print_flags symbols[] = \ + { symbol_array, { -1, NULL }}; \ + trace_print_symbols_seq(p, value, symbols); \ + }) + +#undef __print_flags_u64 +#undef __print_symbolic_u64 +#if BITS_PER_LONG == 32 +#define __print_flags_u64(flag, delim, flag_array...) \ + ({ \ + static const struct trace_print_flags_u64 __flags[] = \ + { flag_array, { -1, NULL } }; \ + trace_print_flags_seq_u64(p, delim, flag, __flags); \ + }) + +#define __print_symbolic_u64(value, symbol_array...) \ + ({ \ + static const struct trace_print_flags_u64 symbols[] = \ + { symbol_array, { -1, NULL } }; \ + trace_print_symbols_seq_u64(p, value, symbols); \ + }) +#else +#define __print_flags_u64(flag, delim, flag_array...) \ + __print_flags(flag, delim, flag_array) + +#define __print_symbolic_u64(value, symbol_array...) \ + __print_symbolic(value, symbol_array) +#endif + +#undef __print_hex +#define __print_hex(buf, buf_len) \ + trace_print_hex_seq(p, buf, buf_len, false) + +#undef __print_hex_str +#define __print_hex_str(buf, buf_len) \ + trace_print_hex_seq(p, buf, buf_len, true) + +#undef __print_array +#define __print_array(array, count, el_size) \ + ({ \ + BUILD_BUG_ON(el_size != 1 && el_size != 2 && \ + el_size != 4 && el_size != 8); \ + trace_print_array_seq(p, array, count, el_size); \ + }) + +#undef __print_hex_dump +#define __print_hex_dump(prefix_str, prefix_type, \ + rowsize, groupsize, buf, len, ascii) \ + trace_print_hex_dump_seq(p, prefix_str, prefix_type, \ + rowsize, groupsize, buf, len, ascii) + +#undef __print_ns_to_secs +#define __print_ns_to_secs(value) \ + ({ \ + u64 ____val = (u64)(value); \ + do_div(____val, NSEC_PER_SEC); \ + ____val; \ + }) + +#undef __print_ns_without_secs +#define __print_ns_without_secs(value) \ + ({ \ + u64 ____val = (u64)(value); \ + (u32) do_div(____val, NSEC_PER_SEC); \ + }) diff --git a/include/trace/stages/stage4_defines.h b/include/trace/stages/stage4_defines.h deleted file mode 100644 index e80cdc397a43..000000000000 --- a/include/trace/stages/stage4_defines.h +++ /dev/null @@ -1,63 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -/* Stage 4 definitions for creating trace events */ - -#undef __field_ext -#define __field_ext(_type, _item, _filter_type) { \ - .type = #_type, .name = #_item, \ - .size = sizeof(_type), .align = __alignof__(_type), \ - .is_signed = is_signed_type(_type), .filter_type = _filter_type }, - -#undef __field_struct_ext -#define __field_struct_ext(_type, _item, _filter_type) { \ - .type = #_type, .name = #_item, \ - .size = sizeof(_type), .align = __alignof__(_type), \ - 0, .filter_type = _filter_type }, - -#undef __field -#define __field(type, item) __field_ext(type, item, FILTER_OTHER) - -#undef __field_struct -#define __field_struct(type, item) __field_struct_ext(type, item, FILTER_OTHER) - -#undef __array -#define __array(_type, _item, _len) { \ - .type = #_type"["__stringify(_len)"]", .name = #_item, \ - .size = sizeof(_type[_len]), .align = __alignof__(_type), \ - .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER }, - -#undef __dynamic_array -#define __dynamic_array(_type, _item, _len) { \ - .type = "__data_loc " #_type "[]", .name = #_item, \ - .size = 4, .align = 4, \ - .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER }, - -#undef __string -#define __string(item, src) __dynamic_array(char, item, -1) - -#undef __string_len -#define __string_len(item, src, len) __dynamic_array(char, item, -1) - -#undef __bitmask -#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1) - -#undef __sockaddr -#define __sockaddr(field, len) __dynamic_array(u8, field, len) - -#undef __rel_dynamic_array -#define __rel_dynamic_array(_type, _item, _len) { \ - .type = "__rel_loc " #_type "[]", .name = #_item, \ - .size = 4, .align = 4, \ - .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER }, - -#undef __rel_string -#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) - -#undef __rel_string_len -#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) - -#undef __rel_bitmask -#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1) - -#undef __rel_sockaddr -#define __rel_sockaddr(field, len) __rel_dynamic_array(u8, field, len) diff --git a/include/trace/stages/stage4_event_fields.h b/include/trace/stages/stage4_event_fields.h new file mode 100644 index 000000000000..e80cdc397a43 --- /dev/null +++ b/include/trace/stages/stage4_event_fields.h @@ -0,0 +1,63 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Stage 4 definitions for creating trace events */ + +#undef __field_ext +#define __field_ext(_type, _item, _filter_type) { \ + .type = #_type, .name = #_item, \ + .size = sizeof(_type), .align = __alignof__(_type), \ + .is_signed = is_signed_type(_type), .filter_type = _filter_type }, + +#undef __field_struct_ext +#define __field_struct_ext(_type, _item, _filter_type) { \ + .type = #_type, .name = #_item, \ + .size = sizeof(_type), .align = __alignof__(_type), \ + 0, .filter_type = _filter_type }, + +#undef __field +#define __field(type, item) __field_ext(type, item, FILTER_OTHER) + +#undef __field_struct +#define __field_struct(type, item) __field_struct_ext(type, item, FILTER_OTHER) + +#undef __array +#define __array(_type, _item, _len) { \ + .type = #_type"["__stringify(_len)"]", .name = #_item, \ + .size = sizeof(_type[_len]), .align = __alignof__(_type), \ + .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER }, + +#undef __dynamic_array +#define __dynamic_array(_type, _item, _len) { \ + .type = "__data_loc " #_type "[]", .name = #_item, \ + .size = 4, .align = 4, \ + .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER }, + +#undef __string +#define __string(item, src) __dynamic_array(char, item, -1) + +#undef __string_len +#define __string_len(item, src, len) __dynamic_array(char, item, -1) + +#undef __bitmask +#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1) + +#undef __sockaddr +#define __sockaddr(field, len) __dynamic_array(u8, field, len) + +#undef __rel_dynamic_array +#define __rel_dynamic_array(_type, _item, _len) { \ + .type = "__rel_loc " #_type "[]", .name = #_item, \ + .size = 4, .align = 4, \ + .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER }, + +#undef __rel_string +#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) + +#undef __rel_string_len +#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) + +#undef __rel_bitmask +#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1) + +#undef __rel_sockaddr +#define __rel_sockaddr(field, len) __rel_dynamic_array(u8, field, len) diff --git a/include/trace/stages/stage5_defines.h b/include/trace/stages/stage5_defines.h deleted file mode 100644 index 7ee5931300e6..000000000000 --- a/include/trace/stages/stage5_defines.h +++ /dev/null @@ -1,89 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -/* Stage 5 definitions for creating trace events */ - -/* - * remember the offset of each array from the beginning of the event. - */ - -#undef __entry -#define __entry entry - -#undef __field -#define __field(type, item) - -#undef __field_ext -#define __field_ext(type, item, filter_type) - -#undef __field_struct -#define __field_struct(type, item) - -#undef __field_struct_ext -#define __field_struct_ext(type, item, filter_type) - -#undef __array -#define __array(type, item, len) - -#undef __dynamic_array -#define __dynamic_array(type, item, len) \ - __item_length = (len) * sizeof(type); \ - __data_offsets->item = __data_size + \ - offsetof(typeof(*entry), __data); \ - __data_offsets->item |= __item_length << 16; \ - __data_size += __item_length; - -#undef __string -#define __string(item, src) __dynamic_array(char, item, \ - strlen((src) ? (const char *)(src) : "(null)") + 1) - -#undef __string_len -#define __string_len(item, src, len) __dynamic_array(char, item, (len) + 1) - -#undef __rel_dynamic_array -#define __rel_dynamic_array(type, item, len) \ - __item_length = (len) * sizeof(type); \ - __data_offsets->item = __data_size + \ - offsetof(typeof(*entry), __data) - \ - offsetof(typeof(*entry), __rel_loc_##item) - \ - sizeof(u32); \ - __data_offsets->item |= __item_length << 16; \ - __data_size += __item_length; - -#undef __rel_string -#define __rel_string(item, src) __rel_dynamic_array(char, item, \ - strlen((src) ? (const char *)(src) : "(null)") + 1) - -#undef __rel_string_len -#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, (len) + 1) -/* - * __bitmask_size_in_bytes_raw is the number of bytes needed to hold - * num_possible_cpus(). - */ -#define __bitmask_size_in_bytes_raw(nr_bits) \ - (((nr_bits) + 7) / 8) - -#define __bitmask_size_in_longs(nr_bits) \ - ((__bitmask_size_in_bytes_raw(nr_bits) + \ - ((BITS_PER_LONG / 8) - 1)) / (BITS_PER_LONG / 8)) - -/* - * __bitmask_size_in_bytes is the number of bytes needed to hold - * num_possible_cpus() padded out to the nearest long. This is what - * is saved in the buffer, just to be consistent. - */ -#define __bitmask_size_in_bytes(nr_bits) \ - (__bitmask_size_in_longs(nr_bits) * (BITS_PER_LONG / 8)) - -#undef __bitmask -#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, \ - __bitmask_size_in_longs(nr_bits)) - -#undef __rel_bitmask -#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, \ - __bitmask_size_in_longs(nr_bits)) - -#undef __sockaddr -#define __sockaddr(field, len) __dynamic_array(u8, field, len) - -#undef __rel_sockaddr -#define __rel_sockaddr(field, len) __rel_dynamic_array(u8, field, len) diff --git a/include/trace/stages/stage5_get_offsets.h b/include/trace/stages/stage5_get_offsets.h new file mode 100644 index 000000000000..7ee5931300e6 --- /dev/null +++ b/include/trace/stages/stage5_get_offsets.h @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Stage 5 definitions for creating trace events */ + +/* + * remember the offset of each array from the beginning of the event. + */ + +#undef __entry +#define __entry entry + +#undef __field +#define __field(type, item) + +#undef __field_ext +#define __field_ext(type, item, filter_type) + +#undef __field_struct +#define __field_struct(type, item) + +#undef __field_struct_ext +#define __field_struct_ext(type, item, filter_type) + +#undef __array +#define __array(type, item, len) + +#undef __dynamic_array +#define __dynamic_array(type, item, len) \ + __item_length = (len) * sizeof(type); \ + __data_offsets->item = __data_size + \ + offsetof(typeof(*entry), __data); \ + __data_offsets->item |= __item_length << 16; \ + __data_size += __item_length; + +#undef __string +#define __string(item, src) __dynamic_array(char, item, \ + strlen((src) ? (const char *)(src) : "(null)") + 1) + +#undef __string_len +#define __string_len(item, src, len) __dynamic_array(char, item, (len) + 1) + +#undef __rel_dynamic_array +#define __rel_dynamic_array(type, item, len) \ + __item_length = (len) * sizeof(type); \ + __data_offsets->item = __data_size + \ + offsetof(typeof(*entry), __data) - \ + offsetof(typeof(*entry), __rel_loc_##item) - \ + sizeof(u32); \ + __data_offsets->item |= __item_length << 16; \ + __data_size += __item_length; + +#undef __rel_string +#define __rel_string(item, src) __rel_dynamic_array(char, item, \ + strlen((src) ? (const char *)(src) : "(null)") + 1) + +#undef __rel_string_len +#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, (len) + 1) +/* + * __bitmask_size_in_bytes_raw is the number of bytes needed to hold + * num_possible_cpus(). + */ +#define __bitmask_size_in_bytes_raw(nr_bits) \ + (((nr_bits) + 7) / 8) + +#define __bitmask_size_in_longs(nr_bits) \ + ((__bitmask_size_in_bytes_raw(nr_bits) + \ + ((BITS_PER_LONG / 8) - 1)) / (BITS_PER_LONG / 8)) + +/* + * __bitmask_size_in_bytes is the number of bytes needed to hold + * num_possible_cpus() padded out to the nearest long. This is what + * is saved in the buffer, just to be consistent. + */ +#define __bitmask_size_in_bytes(nr_bits) \ + (__bitmask_size_in_longs(nr_bits) * (BITS_PER_LONG / 8)) + +#undef __bitmask +#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, \ + __bitmask_size_in_longs(nr_bits)) + +#undef __rel_bitmask +#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, \ + __bitmask_size_in_longs(nr_bits)) + +#undef __sockaddr +#define __sockaddr(field, len) __dynamic_array(u8, field, len) + +#undef __rel_sockaddr +#define __rel_sockaddr(field, len) __rel_dynamic_array(u8, field, len) diff --git a/include/trace/stages/stage6_defines.h b/include/trace/stages/stage6_defines.h deleted file mode 100644 index e1724f73594b..000000000000 --- a/include/trace/stages/stage6_defines.h +++ /dev/null @@ -1,106 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -/* Stage 6 definitions for creating trace events */ - -#undef __entry -#define __entry entry - -#undef __field -#define __field(type, item) - -#undef __field_struct -#define __field_struct(type, item) - -#undef __array -#define __array(type, item, len) - -#undef __dynamic_array -#define __dynamic_array(type, item, len) \ - __entry->__data_loc_##item = __data_offsets.item; - -#undef __string -#define __string(item, src) __dynamic_array(char, item, -1) - -#undef __string_len -#define __string_len(item, src, len) __dynamic_array(char, item, -1) - -#undef __assign_str -#define __assign_str(dst, src) \ - strcpy(__get_str(dst), (src) ? (const char *)(src) : "(null)"); - -#undef __assign_str_len -#define __assign_str_len(dst, src, len) \ - do { \ - memcpy(__get_str(dst), (src), (len)); \ - __get_str(dst)[len] = '\0'; \ - } while(0) - -#undef __bitmask -#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1) - -#undef __get_bitmask -#define __get_bitmask(field) (char *)__get_dynamic_array(field) - -#undef __assign_bitmask -#define __assign_bitmask(dst, src, nr_bits) \ - memcpy(__get_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits)) - -#undef __sockaddr -#define __sockaddr(field, len) __dynamic_array(u8, field, len) - -#undef __get_sockaddr -#define __get_sockaddr(field) ((struct sockaddr *)__get_dynamic_array(field)) - -#undef __assign_sockaddr -#define __assign_sockaddr(dest, src, len) \ - memcpy(__get_dynamic_array(dest), src, len) - -#undef __rel_dynamic_array -#define __rel_dynamic_array(type, item, len) \ - __entry->__rel_loc_##item = __data_offsets.item; - -#undef __rel_string -#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) - -#undef __rel_string_len -#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) - -#undef __assign_rel_str -#define __assign_rel_str(dst, src) \ - strcpy(__get_rel_str(dst), (src) ? (const char *)(src) : "(null)"); - -#undef __assign_rel_str_len -#define __assign_rel_str_len(dst, src, len) \ - do { \ - memcpy(__get_rel_str(dst), (src), (len)); \ - __get_rel_str(dst)[len] = '\0'; \ - } while (0) - -#undef __rel_bitmask -#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1) - -#undef __get_rel_bitmask -#define __get_rel_bitmask(field) (char *)__get_rel_dynamic_array(field) - -#undef __assign_rel_bitmask -#define __assign_rel_bitmask(dst, src, nr_bits) \ - memcpy(__get_rel_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits)) - -#undef __rel_sockaddr -#define __rel_sockaddr(field, len) __rel_dynamic_array(u8, field, len) - -#undef __get_rel_sockaddr -#define __get_rel_sockaddr(field) ((struct sockaddr *)__get_rel_dynamic_array(field)) - -#undef __assign_rel_sockaddr -#define __assign_rel_sockaddr(dest, src, len) \ - memcpy(__get_rel_dynamic_array(dest), src, len) - -#undef TP_fast_assign -#define TP_fast_assign(args...) args - -#undef __perf_count -#define __perf_count(c) (c) - -#undef __perf_task -#define __perf_task(t) (t) diff --git a/include/trace/stages/stage6_event_callback.h b/include/trace/stages/stage6_event_callback.h new file mode 100644 index 000000000000..e1724f73594b --- /dev/null +++ b/include/trace/stages/stage6_event_callback.h @@ -0,0 +1,106 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Stage 6 definitions for creating trace events */ + +#undef __entry +#define __entry entry + +#undef __field +#define __field(type, item) + +#undef __field_struct +#define __field_struct(type, item) + +#undef __array +#define __array(type, item, len) + +#undef __dynamic_array +#define __dynamic_array(type, item, len) \ + __entry->__data_loc_##item = __data_offsets.item; + +#undef __string +#define __string(item, src) __dynamic_array(char, item, -1) + +#undef __string_len +#define __string_len(item, src, len) __dynamic_array(char, item, -1) + +#undef __assign_str +#define __assign_str(dst, src) \ + strcpy(__get_str(dst), (src) ? (const char *)(src) : "(null)"); + +#undef __assign_str_len +#define __assign_str_len(dst, src, len) \ + do { \ + memcpy(__get_str(dst), (src), (len)); \ + __get_str(dst)[len] = '\0'; \ + } while(0) + +#undef __bitmask +#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1) + +#undef __get_bitmask +#define __get_bitmask(field) (char *)__get_dynamic_array(field) + +#undef __assign_bitmask +#define __assign_bitmask(dst, src, nr_bits) \ + memcpy(__get_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits)) + +#undef __sockaddr +#define __sockaddr(field, len) __dynamic_array(u8, field, len) + +#undef __get_sockaddr +#define __get_sockaddr(field) ((struct sockaddr *)__get_dynamic_array(field)) + +#undef __assign_sockaddr +#define __assign_sockaddr(dest, src, len) \ + memcpy(__get_dynamic_array(dest), src, len) + +#undef __rel_dynamic_array +#define __rel_dynamic_array(type, item, len) \ + __entry->__rel_loc_##item = __data_offsets.item; + +#undef __rel_string +#define __rel_string(item, src) __rel_dynamic_array(char, item, -1) + +#undef __rel_string_len +#define __rel_string_len(item, src, len) __rel_dynamic_array(char, item, -1) + +#undef __assign_rel_str +#define __assign_rel_str(dst, src) \ + strcpy(__get_rel_str(dst), (src) ? (const char *)(src) : "(null)"); + +#undef __assign_rel_str_len +#define __assign_rel_str_len(dst, src, len) \ + do { \ + memcpy(__get_rel_str(dst), (src), (len)); \ + __get_rel_str(dst)[len] = '\0'; \ + } while (0) + +#undef __rel_bitmask +#define __rel_bitmask(item, nr_bits) __rel_dynamic_array(unsigned long, item, -1) + +#undef __get_rel_bitmask +#define __get_rel_bitmask(field) (char *)__get_rel_dynamic_array(field) + +#undef __assign_rel_bitmask +#define __assign_rel_bitmask(dst, src, nr_bits) \ + memcpy(__get_rel_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits)) + +#undef __rel_sockaddr +#define __rel_sockaddr(field, len) __rel_dynamic_array(u8, field, len) + +#undef __get_rel_sockaddr +#define __get_rel_sockaddr(field) ((struct sockaddr *)__get_rel_dynamic_array(field)) + +#undef __assign_rel_sockaddr +#define __assign_rel_sockaddr(dest, src, len) \ + memcpy(__get_rel_dynamic_array(dest), src, len) + +#undef TP_fast_assign +#define TP_fast_assign(args...) args + +#undef __perf_count +#define __perf_count(c) (c) + +#undef __perf_task +#define __perf_task(t) (t) diff --git a/include/trace/stages/stage7_class_define.h b/include/trace/stages/stage7_class_define.h new file mode 100644 index 000000000000..8a7ec24c246d --- /dev/null +++ b/include/trace/stages/stage7_class_define.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Stage 7 definitions for creating trace events */ + +#undef __entry +#define __entry REC + +#undef __print_flags +#undef __print_symbolic +#undef __print_hex +#undef __print_hex_str +#undef __get_dynamic_array +#undef __get_dynamic_array_len +#undef __get_str +#undef __get_bitmask +#undef __get_sockaddr +#undef __get_rel_dynamic_array +#undef __get_rel_dynamic_array_len +#undef __get_rel_str +#undef __get_rel_bitmask +#undef __get_rel_sockaddr +#undef __print_array +#undef __print_hex_dump + +/* + * The below is not executed in the kernel. It is only what is + * displayed in the print format for userspace to parse. + */ +#undef __print_ns_to_secs +#define __print_ns_to_secs(val) (val) / 1000000000UL + +#undef __print_ns_without_secs +#define __print_ns_without_secs(val) (val) % 1000000000UL + +#undef TP_printk +#define TP_printk(fmt, args...) "\"" fmt "\", " __stringify(args) diff --git a/include/trace/stages/stage7_defines.h b/include/trace/stages/stage7_defines.h deleted file mode 100644 index 8a7ec24c246d..000000000000 --- a/include/trace/stages/stage7_defines.h +++ /dev/null @@ -1,36 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -/* Stage 7 definitions for creating trace events */ - -#undef __entry -#define __entry REC - -#undef __print_flags -#undef __print_symbolic -#undef __print_hex -#undef __print_hex_str -#undef __get_dynamic_array -#undef __get_dynamic_array_len -#undef __get_str -#undef __get_bitmask -#undef __get_sockaddr -#undef __get_rel_dynamic_array -#undef __get_rel_dynamic_array_len -#undef __get_rel_str -#undef __get_rel_bitmask -#undef __get_rel_sockaddr -#undef __print_array -#undef __print_hex_dump - -/* - * The below is not executed in the kernel. It is only what is - * displayed in the print format for userspace to parse. - */ -#undef __print_ns_to_secs -#define __print_ns_to_secs(val) (val) / 1000000000UL - -#undef __print_ns_without_secs -#define __print_ns_without_secs(val) (val) % 1000000000UL - -#undef TP_printk -#define TP_printk(fmt, args...) "\"" fmt "\", " __stringify(args) diff --git a/include/trace/trace_custom_events.h b/include/trace/trace_custom_events.h index b567c7202339..6e492dba96bf 100644 --- a/include/trace/trace_custom_events.h +++ b/include/trace/trace_custom_events.h @@ -35,7 +35,7 @@ /* Stage 1 creates the structure of the recorded event layout */ -#include "stages/stage1_defines.h" +#include "stages/stage1_struct_define.h" #undef DECLARE_CUSTOM_EVENT_CLASS #define DECLARE_CUSTOM_EVENT_CLASS(name, proto, args, tstruct, assign, print) \ @@ -56,7 +56,7 @@ /* Stage 2 creates the custom class */ -#include "stages/stage2_defines.h" +#include "stages/stage2_data_offsets.h" #undef DECLARE_CUSTOM_EVENT_CLASS #define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -71,7 +71,7 @@ /* Stage 3 create the way to print the custom event */ -#include "stages/stage3_defines.h" +#include "stages/stage3_trace_output.h" #undef DECLARE_CUSTOM_EVENT_CLASS #define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -102,7 +102,7 @@ static struct trace_event_functions trace_custom_event_type_funcs_##call = { \ /* Stage 4 creates the offset layout for the fields */ -#include "stages/stage4_defines.h" +#include "stages/stage4_event_fields.h" #undef DECLARE_CUSTOM_EVENT_CLASS #define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, func, print) \ @@ -114,7 +114,7 @@ static struct trace_event_fields trace_custom_event_fields_##call[] = { \ /* Stage 5 creates the helper function for dynamic fields */ -#include "stages/stage5_defines.h" +#include "stages/stage5_get_offsets.h" #undef DECLARE_CUSTOM_EVENT_CLASS #define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -134,7 +134,7 @@ static inline notrace int trace_custom_event_get_offsets_##call( \ /* Stage 6 creates the probe function that records the event */ -#include "stages/stage6_defines.h" +#include "stages/stage6_event_callback.h" #undef DECLARE_CUSTOM_EVENT_CLASS #define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -182,7 +182,7 @@ static inline void ftrace_test_custom_probe_##call(void) \ /* Stage 7 creates the actual class and event structure for the custom event */ -#include "stages/stage7_defines.h" +#include "stages/stage7_class_define.h" #undef DECLARE_CUSTOM_EVENT_CLASS #define DECLARE_CUSTOM_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h index 8a8cd66cc6d5..c2f9cabf154d 100644 --- a/include/trace/trace_events.h +++ b/include/trace/trace_events.h @@ -45,7 +45,7 @@ PARAMS(print)); \ DEFINE_EVENT(name, name, PARAMS(proto), PARAMS(args)); -#include "stages/stage1_defines.h" +#include "stages/stage1_struct_define.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(name, proto, args, tstruct, assign, print) \ @@ -109,7 +109,7 @@ * The size of an array is also encoded, in the higher 16 bits of . */ -#include "stages/stage2_defines.h" +#include "stages/stage2_data_offsets.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -181,7 +181,7 @@ * in binary. */ -#include "stages/stage3_defines.h" +#include "stages/stage3_trace_output.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -236,7 +236,7 @@ static struct trace_event_functions trace_event_type_funcs_##call = { \ #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) -#include "stages/stage4_defines.h" +#include "stages/stage4_event_fields.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, func, print) \ @@ -249,7 +249,7 @@ static struct trace_event_fields trace_event_fields_##call[] = { \ #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) -#include "stages/stage5_defines.h" +#include "stages/stage5_get_offsets.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -372,7 +372,7 @@ static inline notrace int trace_event_get_offsets_##call( \ #define _TRACE_PERF_INIT(call) #endif /* CONFIG_PERF_EVENTS */ -#include "stages/stage6_defines.h" +#include "stages/stage6_event_callback.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ @@ -418,7 +418,7 @@ static inline void ftrace_test_probe_##call(void) \ #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) -#include "stages/stage7_defines.h" +#include "stages/stage7_class_define.h" #undef DECLARE_EVENT_CLASS #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ -- cgit v1.2.3 From 768c1e7f1de03afd0b55e0e951efc272309eeb52 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 29 Mar 2022 10:30:51 -0700 Subject: tracing/user_events: Remove eBPF interfaces Remove eBPF interfaces within user_events to ensure they are fully reviewed. Link: https://lore.kernel.org/all/20220329165718.GA10381@kbox/ Link: https://lkml.kernel.org/r/20220329173051.10087-1-beaub@linux.microsoft.com Suggested-by: Alexei Starovoitov Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- include/uapi/linux/user_events.h | 53 ---------------------------------------- 1 file changed, 53 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/user_events.h b/include/uapi/linux/user_events.h index e570840571e1..736e05603463 100644 --- a/include/uapi/linux/user_events.h +++ b/include/uapi/linux/user_events.h @@ -32,9 +32,6 @@ /* Create dynamic location entry within a 32-bit value */ #define DYN_LOC(offset, size) ((size) << 16 | (offset)) -/* Use raw iterator for attached BPF program(s), no affect on ftrace/perf */ -#define FLAG_BPF_ITER (1 << 0) - /* * Describes an event registration and stores the results of the registration. * This structure is passed to the DIAG_IOCSREG ioctl, callers at a minimum @@ -63,54 +60,4 @@ struct user_reg { /* Requests to delete a user_event */ #define DIAG_IOCSDEL _IOW(DIAG_IOC_MAGIC, 1, char*) -/* Data type that was passed to the BPF program */ -enum { - /* Data resides in kernel space */ - USER_BPF_DATA_KERNEL, - - /* Data resides in user space */ - USER_BPF_DATA_USER, - - /* Data is a pointer to a user_bpf_iter structure */ - USER_BPF_DATA_ITER, -}; - -/* - * Describes an iovec iterator that BPF programs can use to access data for - * a given user_event write() / writev() call. - */ -struct user_bpf_iter { - - /* Offset of the data within the first iovec */ - __u32 iov_offset; - - /* Number of iovec structures */ - __u32 nr_segs; - - /* Pointer to iovec structures */ - const struct iovec *iov; -}; - -/* Context that BPF programs receive when attached to a user_event */ -struct user_bpf_context { - - /* Data type being passed (see union below) */ - __u32 data_type; - - /* Length of the data */ - __u32 data_len; - - /* Pointer to data, varies by data type */ - union { - /* Kernel data (data_type == USER_BPF_DATA_KERNEL) */ - void *kdata; - - /* User data (data_type == USER_BPF_DATA_USER) */ - void *udata; - - /* Direct iovec (data_type == USER_BPF_DATA_ITER) */ - struct user_bpf_iter *iter; - }; -}; - #endif /* _UAPI_LINUX_USER_EVENTS_H */ -- cgit v1.2.3 From 18bfee3216fa6f28d55ebf88d824a539d2bec3c7 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Wed, 30 Mar 2022 09:00:19 +0200 Subject: ftrace: Make ftrace_graph_is_dead() a static branch ftrace_graph_is_dead() is used on hot paths, it just reads a variable in memory and is not worth suffering function call constraints. For instance, at entry of prepare_ftrace_return(), inlining it avoids saving prepare_ftrace_return() parameters to stack and restoring them after calling ftrace_graph_is_dead(). While at it using a static branch is even more performant and is rather well adapted considering that the returned value will almost never change. Inline ftrace_graph_is_dead() and replace 'kill_ftrace_graph' bool by a static branch. The performance improvement is noticeable. Link: https://lkml.kernel.org/r/e0411a6a0ed3eafff0ad2bc9cd4b0e202b4617df.1648623570.git.christophe.leroy@csgroup.eu Signed-off-by: Christophe Leroy Signed-off-by: Steven Rostedt (Google) --- include/linux/ftrace.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 37b619185ec9..f15a4b76cbfc 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -9,6 +9,7 @@ #include #include +#include #include #include #include @@ -1015,7 +1016,20 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, extern int register_ftrace_graph(struct fgraph_ops *ops); extern void unregister_ftrace_graph(struct fgraph_ops *ops); -extern bool ftrace_graph_is_dead(void); +/** + * ftrace_graph_is_dead - returns true if ftrace_graph_stop() was called + * + * ftrace_graph_stop() is called when a severe error is detected in + * the function graph tracing. This function is called by the critical + * paths of function graph to keep those paths from doing any more harm. + */ +DECLARE_STATIC_KEY_FALSE(kill_ftrace_graph); + +static inline bool ftrace_graph_is_dead(void) +{ + return static_branch_unlikely(&kill_ftrace_graph); +} + extern void ftrace_graph_stop(void); /* The current handlers in use */ -- cgit v1.2.3 From 5cfff569cab8bf544bab62c911c5d6efd5af5e05 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Fri, 1 Apr 2022 14:39:03 -0400 Subject: tracing: Move user_events.h temporarily out of include/uapi While user_events API is under development and has been marked for broken to not let the API become fixed, move the header file out of the uapi directory. This is to prevent it from being installed, then later changed, and then have an old distro user space update with a new kernel, where applications see the user_events being available, but the old header is in place, and then they get compiled incorrectly. Also, surround the include with CONFIG_COMPILE_TEST to the current location, but when the BROKEN tag is taken off, it will use the uapi directory, and fail to compile. This is a good way to remind us to move the header back. Link: https://lore.kernel.org/all/20220330155835.5e1f6669@gandalf.local.home Link: https://lkml.kernel.org/r/20220330201755.29319-1-mathieu.desnoyers@efficios.com Link: https://lkml.kernel.org/r/20220401143903.188384f3@gandalf.local.home Suggested-by: Mathieu Desnoyers Signed-off-by: Steven Rostedt (Google) --- include/linux/user_events.h | 63 ++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/user_events.h | 63 ---------------------------------------- 2 files changed, 63 insertions(+), 63 deletions(-) create mode 100644 include/linux/user_events.h delete mode 100644 include/uapi/linux/user_events.h (limited to 'include') diff --git a/include/linux/user_events.h b/include/linux/user_events.h new file mode 100644 index 000000000000..736e05603463 --- /dev/null +++ b/include/linux/user_events.h @@ -0,0 +1,63 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright (c) 2021, Microsoft Corporation. + * + * Authors: + * Beau Belgrave + */ +#ifndef _UAPI_LINUX_USER_EVENTS_H +#define _UAPI_LINUX_USER_EVENTS_H + +#include +#include + +#ifdef __KERNEL__ +#include +#else +#include +#endif + +#define USER_EVENTS_SYSTEM "user_events" +#define USER_EVENTS_PREFIX "u:" + +/* Bits 0-6 are for known probe types, Bit 7 is for unknown probes */ +#define EVENT_BIT_FTRACE 0 +#define EVENT_BIT_PERF 1 +#define EVENT_BIT_OTHER 7 + +#define EVENT_STATUS_FTRACE (1 << EVENT_BIT_FTRACE) +#define EVENT_STATUS_PERF (1 << EVENT_BIT_PERF) +#define EVENT_STATUS_OTHER (1 << EVENT_BIT_OTHER) + +/* Create dynamic location entry within a 32-bit value */ +#define DYN_LOC(offset, size) ((size) << 16 | (offset)) + +/* + * Describes an event registration and stores the results of the registration. + * This structure is passed to the DIAG_IOCSREG ioctl, callers at a minimum + * must set the size and name_args before invocation. + */ +struct user_reg { + + /* Input: Size of the user_reg structure being used */ + __u32 size; + + /* Input: Pointer to string with event name, description and flags */ + __u64 name_args; + + /* Output: Byte index of the event within the status page */ + __u32 status_index; + + /* Output: Index of the event to use when writing data */ + __u32 write_index; +}; + +#define DIAG_IOC_MAGIC '*' + +/* Requests to register a user_event */ +#define DIAG_IOCSREG _IOWR(DIAG_IOC_MAGIC, 0, struct user_reg*) + +/* Requests to delete a user_event */ +#define DIAG_IOCSDEL _IOW(DIAG_IOC_MAGIC, 1, char*) + +#endif /* _UAPI_LINUX_USER_EVENTS_H */ diff --git a/include/uapi/linux/user_events.h b/include/uapi/linux/user_events.h deleted file mode 100644 index 736e05603463..000000000000 --- a/include/uapi/linux/user_events.h +++ /dev/null @@ -1,63 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * Copyright (c) 2021, Microsoft Corporation. - * - * Authors: - * Beau Belgrave - */ -#ifndef _UAPI_LINUX_USER_EVENTS_H -#define _UAPI_LINUX_USER_EVENTS_H - -#include -#include - -#ifdef __KERNEL__ -#include -#else -#include -#endif - -#define USER_EVENTS_SYSTEM "user_events" -#define USER_EVENTS_PREFIX "u:" - -/* Bits 0-6 are for known probe types, Bit 7 is for unknown probes */ -#define EVENT_BIT_FTRACE 0 -#define EVENT_BIT_PERF 1 -#define EVENT_BIT_OTHER 7 - -#define EVENT_STATUS_FTRACE (1 << EVENT_BIT_FTRACE) -#define EVENT_STATUS_PERF (1 << EVENT_BIT_PERF) -#define EVENT_STATUS_OTHER (1 << EVENT_BIT_OTHER) - -/* Create dynamic location entry within a 32-bit value */ -#define DYN_LOC(offset, size) ((size) << 16 | (offset)) - -/* - * Describes an event registration and stores the results of the registration. - * This structure is passed to the DIAG_IOCSREG ioctl, callers at a minimum - * must set the size and name_args before invocation. - */ -struct user_reg { - - /* Input: Size of the user_reg structure being used */ - __u32 size; - - /* Input: Pointer to string with event name, description and flags */ - __u64 name_args; - - /* Output: Byte index of the event within the status page */ - __u32 status_index; - - /* Output: Index of the event to use when writing data */ - __u32 write_index; -}; - -#define DIAG_IOC_MAGIC '*' - -/* Requests to register a user_event */ -#define DIAG_IOCSREG _IOWR(DIAG_IOC_MAGIC, 0, struct user_reg*) - -/* Requests to delete a user_event */ -#define DIAG_IOCSDEL _IOW(DIAG_IOC_MAGIC, 1, char*) - -#endif /* _UAPI_LINUX_USER_EVENTS_H */ -- cgit v1.2.3 From 1cd927ad6f62f27d8908498dcbf61395c5dd5fe2 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Fri, 1 Apr 2022 14:39:03 -0400 Subject: tracing: mark user_events as BROKEN After being merged, user_events become more visible to a wider audience that have concerns with the current API. It is too late to fix this for this release, but instead of a full revert, just mark it as BROKEN (which prevents it from being selected in make config). Then we can work finding a better API. If that fails, then it will need to be completely reverted. To not have the code silently bitrot, still allow building it with COMPILE_TEST. And to prevent the uapi header from being installed, then later changed, and then have an old distro user space see the old version, move the header file out of the uapi directory. Surround the include with CONFIG_COMPILE_TEST to the current location, but when the BROKEN tag is taken off, it will use the uapi directory, and fail to compile. This is a good way to remind us to move the header back. Link: https://lore.kernel.org/all/20220330155835.5e1f6669@gandalf.local.home Link: https://lkml.kernel.org/r/20220330201755.29319-1-mathieu.desnoyers@efficios.com Suggested-by: Mathieu Desnoyers Signed-off-by: Steven Rostedt (Google) Signed-off-by: Linus Torvalds --- include/linux/user_events.h | 116 +++++++++++++++++++++++++++++++++++++++ include/uapi/linux/user_events.h | 116 --------------------------------------- 2 files changed, 116 insertions(+), 116 deletions(-) create mode 100644 include/linux/user_events.h delete mode 100644 include/uapi/linux/user_events.h (limited to 'include') diff --git a/include/linux/user_events.h b/include/linux/user_events.h new file mode 100644 index 000000000000..e570840571e1 --- /dev/null +++ b/include/linux/user_events.h @@ -0,0 +1,116 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright (c) 2021, Microsoft Corporation. + * + * Authors: + * Beau Belgrave + */ +#ifndef _UAPI_LINUX_USER_EVENTS_H +#define _UAPI_LINUX_USER_EVENTS_H + +#include +#include + +#ifdef __KERNEL__ +#include +#else +#include +#endif + +#define USER_EVENTS_SYSTEM "user_events" +#define USER_EVENTS_PREFIX "u:" + +/* Bits 0-6 are for known probe types, Bit 7 is for unknown probes */ +#define EVENT_BIT_FTRACE 0 +#define EVENT_BIT_PERF 1 +#define EVENT_BIT_OTHER 7 + +#define EVENT_STATUS_FTRACE (1 << EVENT_BIT_FTRACE) +#define EVENT_STATUS_PERF (1 << EVENT_BIT_PERF) +#define EVENT_STATUS_OTHER (1 << EVENT_BIT_OTHER) + +/* Create dynamic location entry within a 32-bit value */ +#define DYN_LOC(offset, size) ((size) << 16 | (offset)) + +/* Use raw iterator for attached BPF program(s), no affect on ftrace/perf */ +#define FLAG_BPF_ITER (1 << 0) + +/* + * Describes an event registration and stores the results of the registration. + * This structure is passed to the DIAG_IOCSREG ioctl, callers at a minimum + * must set the size and name_args before invocation. + */ +struct user_reg { + + /* Input: Size of the user_reg structure being used */ + __u32 size; + + /* Input: Pointer to string with event name, description and flags */ + __u64 name_args; + + /* Output: Byte index of the event within the status page */ + __u32 status_index; + + /* Output: Index of the event to use when writing data */ + __u32 write_index; +}; + +#define DIAG_IOC_MAGIC '*' + +/* Requests to register a user_event */ +#define DIAG_IOCSREG _IOWR(DIAG_IOC_MAGIC, 0, struct user_reg*) + +/* Requests to delete a user_event */ +#define DIAG_IOCSDEL _IOW(DIAG_IOC_MAGIC, 1, char*) + +/* Data type that was passed to the BPF program */ +enum { + /* Data resides in kernel space */ + USER_BPF_DATA_KERNEL, + + /* Data resides in user space */ + USER_BPF_DATA_USER, + + /* Data is a pointer to a user_bpf_iter structure */ + USER_BPF_DATA_ITER, +}; + +/* + * Describes an iovec iterator that BPF programs can use to access data for + * a given user_event write() / writev() call. + */ +struct user_bpf_iter { + + /* Offset of the data within the first iovec */ + __u32 iov_offset; + + /* Number of iovec structures */ + __u32 nr_segs; + + /* Pointer to iovec structures */ + const struct iovec *iov; +}; + +/* Context that BPF programs receive when attached to a user_event */ +struct user_bpf_context { + + /* Data type being passed (see union below) */ + __u32 data_type; + + /* Length of the data */ + __u32 data_len; + + /* Pointer to data, varies by data type */ + union { + /* Kernel data (data_type == USER_BPF_DATA_KERNEL) */ + void *kdata; + + /* User data (data_type == USER_BPF_DATA_USER) */ + void *udata; + + /* Direct iovec (data_type == USER_BPF_DATA_ITER) */ + struct user_bpf_iter *iter; + }; +}; + +#endif /* _UAPI_LINUX_USER_EVENTS_H */ diff --git a/include/uapi/linux/user_events.h b/include/uapi/linux/user_events.h deleted file mode 100644 index e570840571e1..000000000000 --- a/include/uapi/linux/user_events.h +++ /dev/null @@ -1,116 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * Copyright (c) 2021, Microsoft Corporation. - * - * Authors: - * Beau Belgrave - */ -#ifndef _UAPI_LINUX_USER_EVENTS_H -#define _UAPI_LINUX_USER_EVENTS_H - -#include -#include - -#ifdef __KERNEL__ -#include -#else -#include -#endif - -#define USER_EVENTS_SYSTEM "user_events" -#define USER_EVENTS_PREFIX "u:" - -/* Bits 0-6 are for known probe types, Bit 7 is for unknown probes */ -#define EVENT_BIT_FTRACE 0 -#define EVENT_BIT_PERF 1 -#define EVENT_BIT_OTHER 7 - -#define EVENT_STATUS_FTRACE (1 << EVENT_BIT_FTRACE) -#define EVENT_STATUS_PERF (1 << EVENT_BIT_PERF) -#define EVENT_STATUS_OTHER (1 << EVENT_BIT_OTHER) - -/* Create dynamic location entry within a 32-bit value */ -#define DYN_LOC(offset, size) ((size) << 16 | (offset)) - -/* Use raw iterator for attached BPF program(s), no affect on ftrace/perf */ -#define FLAG_BPF_ITER (1 << 0) - -/* - * Describes an event registration and stores the results of the registration. - * This structure is passed to the DIAG_IOCSREG ioctl, callers at a minimum - * must set the size and name_args before invocation. - */ -struct user_reg { - - /* Input: Size of the user_reg structure being used */ - __u32 size; - - /* Input: Pointer to string with event name, description and flags */ - __u64 name_args; - - /* Output: Byte index of the event within the status page */ - __u32 status_index; - - /* Output: Index of the event to use when writing data */ - __u32 write_index; -}; - -#define DIAG_IOC_MAGIC '*' - -/* Requests to register a user_event */ -#define DIAG_IOCSREG _IOWR(DIAG_IOC_MAGIC, 0, struct user_reg*) - -/* Requests to delete a user_event */ -#define DIAG_IOCSDEL _IOW(DIAG_IOC_MAGIC, 1, char*) - -/* Data type that was passed to the BPF program */ -enum { - /* Data resides in kernel space */ - USER_BPF_DATA_KERNEL, - - /* Data resides in user space */ - USER_BPF_DATA_USER, - - /* Data is a pointer to a user_bpf_iter structure */ - USER_BPF_DATA_ITER, -}; - -/* - * Describes an iovec iterator that BPF programs can use to access data for - * a given user_event write() / writev() call. - */ -struct user_bpf_iter { - - /* Offset of the data within the first iovec */ - __u32 iov_offset; - - /* Number of iovec structures */ - __u32 nr_segs; - - /* Pointer to iovec structures */ - const struct iovec *iov; -}; - -/* Context that BPF programs receive when attached to a user_event */ -struct user_bpf_context { - - /* Data type being passed (see union below) */ - __u32 data_type; - - /* Length of the data */ - __u32 data_len; - - /* Pointer to data, varies by data type */ - union { - /* Kernel data (data_type == USER_BPF_DATA_KERNEL) */ - void *kdata; - - /* User data (data_type == USER_BPF_DATA_USER) */ - void *udata; - - /* Direct iovec (data_type == USER_BPF_DATA_ITER) */ - struct user_bpf_iter *iter; - }; -}; - -#endif /* _UAPI_LINUX_USER_EVENTS_H */ -- cgit v1.2.3 From 92cedee6a6a3e6fcc3ffc0e3866baae5f6f76ac1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Wed, 3 Nov 2021 10:02:08 +0100 Subject: dma-buf: add dma_resv_get_singleton v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a function to simplify getting a single fence for all the fences in the dma_resv object. v2: fix ref leak in error handling Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220321135856.1331-3-christian.koenig@amd.com --- include/linux/dma-resv.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index dccaf7b1663e..233ed4f14d9e 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -437,6 +437,8 @@ void dma_resv_replace_fences(struct dma_resv *obj, uint64_t context, void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence); int dma_resv_get_fences(struct dma_resv *obj, bool write, unsigned int *num_fences, struct dma_fence ***fences); +int dma_resv_get_singleton(struct dma_resv *obj, bool write, + struct dma_fence **fence); int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src); long dma_resv_wait_timeout(struct dma_resv *obj, bool wait_all, bool intr, unsigned long timeout); -- cgit v1.2.3 From 66df0fdb5981052f3ad97c9879eda93712bdefc2 Mon Sep 17 00:00:00 2001 From: Haiyue Wang Date: Sun, 3 Apr 2022 19:53:26 +0800 Subject: bpf: Correct the comment for BTF kind bitfield The commit 8fd886911a6a ("bpf: Add BTF_KIND_FLOAT to uapi") has extended the BTF kind bitfield from 4 to 5 bits, correct the comment. Signed-off-by: Haiyue Wang Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220403115327.205964-1-haiyue.wang@intel.com --- include/uapi/linux/btf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index b0d8fea1951d..a9162a6c0284 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -33,8 +33,8 @@ struct btf_type { /* "info" bits arrangement * bits 0-15: vlen (e.g. # of struct's members) * bits 16-23: unused - * bits 24-27: kind (e.g. int, ptr, array...etc) - * bits 28-30: unused + * bits 24-28: kind (e.g. int, ptr, array...etc) + * bits 29-30: unused * bit 31: kind_flag, currently used by * struct, union and fwd */ -- cgit v1.2.3 From f56b919fa4f1b27c589e71f7d90e9785f9196bf1 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 16 Feb 2022 09:39:22 +0100 Subject: linux/fb.h: Spelling s/palette/palette/ Fix a misspelling of "palette" in a comment. Signed-off-by: Geert Uytterhoeven Reviewed-by: Pekka Paalanen Signed-off-by: Helge Deller --- include/uapi/linux/fb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/fb.h b/include/uapi/linux/fb.h index 4c14e8be7267..3a49913d006c 100644 --- a/include/uapi/linux/fb.h +++ b/include/uapi/linux/fb.h @@ -182,7 +182,7 @@ struct fb_fix_screeninfo { * * For pseudocolor: offset and length should be the same for all color * components. Offset specifies the position of the least significant bit - * of the pallette index in a pixel value. Length indicates the number + * of the palette index in a pixel value. Length indicates the number * of available palette entries (i.e. # of entries = 1 << length). */ struct fb_bitfield { -- cgit v1.2.3 From 8bea9af887de4c99a95f93f2ce400ef63e8b4e9b Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Tue, 22 Mar 2022 12:50:27 +0200 Subject: iio: adc: ad_sigma_delta: Add sequencer support Some sigma-delta chips support sampling of multiple channels in continuous mode. When the operating with more than one channel enabled, the channel sequencer cycles through the enabled channels in sequential order, from first channel to the last one. If a channel is disabled, it is skipped by the sequencer. If more than one channel is used in continuous mode, instruct the device to append the status to the SPI transfer (1 extra byte) every time we receive a sample. All sigma-delta chips possessing a sampling sequencer have this ability. Inside the status register there will be the number of the converted channel. In this way, even if the CPU won't keep up with the sampling rate, it won't send to userspace wrong channel samples. When multiple channels are enabled in continuous mode, the device needs to perform a measurement on all slots before we can push to userspace the sample. If, during sequencing and data reading, a channel measurement is lost, a desync occurred. In this case, ad_sigma_delta drops the incomplete sample and waits for the device to send the measurement on the first active slot. Co-developed-by: Alexandru Tachici Signed-off-by: Alexandru Tachici Signed-off-by: Lars-Peter Clausen Link: https://lore.kernel.org/r/20220322105029.86389-5-alexandru.tachici@analog.com Signed-off-by: Jonathan Cameron --- include/linux/iio/adc/ad_sigma_delta.h | 38 ++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) (limited to 'include') diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index c525fd51652f..7852f6c9a714 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -32,26 +32,34 @@ struct iio_dev; /** * struct ad_sigma_delta_info - Sigma Delta driver specific callbacks and options * @set_channel: Will be called to select the current channel, may be NULL. + * @append_status: Will be called to enable status append at the end of the sample, may be NULL. * @set_mode: Will be called to select the current mode, may be NULL. + * @disable_all: Will be called to disable all channels, may be NULL. * @postprocess_sample: Is called for each sampled data word, can be used to * modify or drop the sample data, it, may be NULL. * @has_registers: true if the device has writable and readable registers, false * if there is just one read-only sample data shift register. * @addr_shift: Shift of the register address in the communications register. * @read_mask: Mask for the communications register having the read bit set. + * @status_ch_mask: Mask for the channel number stored in status register. * @data_reg: Address of the data register, if 0 the default address of 0x3 will * be used. * @irq_flags: flags for the interrupt used by the triggered buffer + * @num_slots: Number of sequencer slots */ struct ad_sigma_delta_info { int (*set_channel)(struct ad_sigma_delta *, unsigned int channel); + int (*append_status)(struct ad_sigma_delta *, bool append); int (*set_mode)(struct ad_sigma_delta *, enum ad_sigma_delta_mode mode); + int (*disable_all)(struct ad_sigma_delta *); int (*postprocess_sample)(struct ad_sigma_delta *, unsigned int raw_sample); bool has_registers; unsigned int addr_shift; unsigned int read_mask; + unsigned int status_ch_mask; unsigned int data_reg; unsigned long irq_flags; + unsigned int num_slots; }; /** @@ -76,6 +84,13 @@ struct ad_sigma_delta { uint8_t comm; const struct ad_sigma_delta_info *info; + unsigned int active_slots; + unsigned int current_slot; + unsigned int num_slots; + bool status_appended; + /* map slots to channels in order to know what to expect from devices */ + unsigned int *slots; + uint8_t *samples_buf; /* * DMA (thus cache coherency maintenance) requires the @@ -97,6 +112,29 @@ static inline int ad_sigma_delta_set_channel(struct ad_sigma_delta *sd, return 0; } +static inline int ad_sigma_delta_append_status(struct ad_sigma_delta *sd, bool append) +{ + int ret; + + if (sd->info->append_status) { + ret = sd->info->append_status(sd, append); + if (ret < 0) + return ret; + + sd->status_appended = append; + } + + return 0; +} + +static inline int ad_sigma_delta_disable_all(struct ad_sigma_delta *sd) +{ + if (sd->info->disable_all) + return sd->info->disable_all(sd); + + return 0; +} + static inline int ad_sigma_delta_set_mode(struct ad_sigma_delta *sd, unsigned int mode) { -- cgit v1.2.3 From e87f4152e542610d0b4c6c8548964a68a59d2040 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 23 Mar 2022 20:02:41 +0100 Subject: task_stack, x86/cea: Force-inline stack helpers Force-inline two stack helpers to fix the following objtool warnings: vmlinux.o: warning: objtool: in_task_stack()+0xc: call to task_stack_page() leaves .noinstr.text section vmlinux.o: warning: objtool: in_entry_stack()+0x10: call to cpu_entry_stack() leaves .noinstr.text section Signed-off-by: Borislav Petkov Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220324183607.31717-2-bp@alien8.de --- include/linux/sched/task_stack.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index 892562ebbd3a..5e799a47431e 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -16,7 +16,7 @@ * try_get_task_stack() instead. task_stack_page will return a pointer * that could get freed out from under you. */ -static inline void *task_stack_page(const struct task_struct *task) +static __always_inline void *task_stack_page(const struct task_struct *task) { return task->stack; } -- cgit v1.2.3 From 19c66219e4d5b813ebbd28621cfe9c450659ded7 Mon Sep 17 00:00:00 2001 From: Allen-KH Cheng Date: Fri, 18 Mar 2022 22:45:31 +0800 Subject: arm64: dts: mt8192: Add the mmsys reset bit to reset the dsi0 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reset the DSI hardware is needed to prevent different settings between the bootloader and the kernel. Signed-off-by: Allen-KH Cheng Reviewed-by: Nícolas F. R. A. Prado Reviewed-by: AngeloGioacchino Del Regno Acked-by: Rob Herring Link: https://lore.kernel.org/r/20220318144534.17996-20-allen-kh.cheng@mediatek.com Signed-off-by: Matthias Brugger --- include/dt-bindings/reset/mt8192-resets.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/reset/mt8192-resets.h b/include/dt-bindings/reset/mt8192-resets.h index be9a7ca245b9..764ca9910fa9 100644 --- a/include/dt-bindings/reset/mt8192-resets.h +++ b/include/dt-bindings/reset/mt8192-resets.h @@ -27,4 +27,7 @@ #define MT8192_TOPRGU_SW_RST_NUM 23 +/* MMSYS resets */ +#define MT8192_MMSYS_SW0_RST_B_DISP_DSI0 15 + #endif /* _DT_BINDINGS_RESET_CONTROLLER_MT8192 */ -- cgit v1.2.3 From 5467801f1fcbdc46bc7298a84dbf3ca1ff2a7320 Mon Sep 17 00:00:00 2001 From: Shreeya Patel Date: Mon, 21 Mar 2022 19:02:41 +0530 Subject: gpio: Restrict usage of GPIO chip irq members before initialization GPIO chip irq members are exposed before they could be completely initialized and this leads to race conditions. One such issue was observed for the gc->irq.domain variable which was accessed through the I2C interface in gpiochip_to_irq() before it could be initialized by gpiochip_add_irqchip(). This resulted in Kernel NULL pointer dereference. Following are the logs for reference :- kernel: Call Trace: kernel: gpiod_to_irq+0x53/0x70 kernel: acpi_dev_gpio_irq_get_by+0x113/0x1f0 kernel: i2c_acpi_get_irq+0xc0/0xd0 kernel: i2c_device_probe+0x28a/0x2a0 kernel: really_probe+0xf2/0x460 kernel: RIP: 0010:gpiochip_to_irq+0x47/0xc0 To avoid such scenarios, restrict usage of GPIO chip irq members before they are completely initialized. Signed-off-by: Shreeya Patel Cc: stable@vger.kernel.org Reviewed-by: Andy Shevchenko Reviewed-by: Linus Walleij Signed-off-by: Bartosz Golaszewski --- include/linux/gpio/driver.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 98c93510640e..874aabd270c9 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -221,6 +221,15 @@ struct gpio_irq_chip { */ bool per_parent_data; + /** + * @initialized: + * + * Flag to track GPIO chip irq member's initialization. + * This flag will make sure GPIO chip irq members are not used + * before they are initialized. + */ + bool initialized; + /** * @init_hw: optional routine to initialize hardware before * an IRQ chip will be added. This is quite useful when -- cgit v1.2.3 From 30ad63e784dd71cbc608a0d039a88e6df12aa258 Mon Sep 17 00:00:00 2001 From: Xiao Yang Date: Thu, 31 Mar 2022 11:24:18 +0800 Subject: IB/uverbs: Move enum ib_raw_packet_caps to uapi This enum is used by ibv_query_device_ex(3) so it should be defined in include/uapi/rdma/ib_user_verbs.h. Link: https://lore.kernel.org/r/20220331032419.313904-1-yangx.jy@fujitsu.com Signed-off-by: Xiao Yang Reviewed-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 18 +++++++++++------- include/uapi/rdma/ib_user_verbs.h | 7 +++++++ 2 files changed, 18 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 69d883f7fb41..dfd467469622 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1621,19 +1621,23 @@ struct ib_srq { }; enum ib_raw_packet_caps { - /* Strip cvlan from incoming packet and report it in the matching work + /* + * Strip cvlan from incoming packet and report it in the matching work * completion is supported. */ - IB_RAW_PACKET_CAP_CVLAN_STRIPPING = (1 << 0), - /* Scatter FCS field of an incoming packet to host memory is supported. + IB_RAW_PACKET_CAP_CVLAN_STRIPPING = + IB_UVERBS_RAW_PACKET_CAP_CVLAN_STRIPPING, + /* + * Scatter FCS field of an incoming packet to host memory is supported. */ - IB_RAW_PACKET_CAP_SCATTER_FCS = (1 << 1), + IB_RAW_PACKET_CAP_SCATTER_FCS = IB_UVERBS_RAW_PACKET_CAP_SCATTER_FCS, /* Checksum offloads are supported (for both send and receive). */ - IB_RAW_PACKET_CAP_IP_CSUM = (1 << 2), - /* When a packet is received for an RQ with no receive WQEs, the + IB_RAW_PACKET_CAP_IP_CSUM = IB_UVERBS_RAW_PACKET_CAP_IP_CSUM, + /* + * When a packet is received for an RQ with no receive WQEs, the * packet processing is delayed. */ - IB_RAW_PACKET_CAP_DELAY_DROP = (1 << 3), + IB_RAW_PACKET_CAP_DELAY_DROP = IB_UVERBS_RAW_PACKET_CAP_DELAY_DROP, }; enum ib_wq_type { diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index 7ee73a0652f1..ff549695f1ba 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -1298,4 +1298,11 @@ struct ib_uverbs_ex_modify_cq { #define IB_DEVICE_NAME_MAX 64 +enum ib_uverbs_raw_packet_caps { + IB_UVERBS_RAW_PACKET_CAP_CVLAN_STRIPPING = 1 << 0, + IB_UVERBS_RAW_PACKET_CAP_SCATTER_FCS = 1 << 1, + IB_UVERBS_RAW_PACKET_CAP_IP_CSUM = 1 << 2, + IB_UVERBS_RAW_PACKET_CAP_DELAY_DROP = 1 << 3, +}; + #endif /* IB_USER_VERBS_H */ -- cgit v1.2.3 From f543a3e82bb275349961f8507ee195f34132ffb4 Mon Sep 17 00:00:00 2001 From: Xiao Yang Date: Thu, 31 Mar 2022 11:24:19 +0800 Subject: IB/uverbs: Move part of enum ib_device_cap_flags to uapi 1) Part of enum ib_device_cap_flags are used by ibv_query_device(3) or ibv_query_device_ex(3), so we define them in include/uapi/rdma/ib_user_verbs.h and only expose them to userspace. 2) Reformat enum ib_device_cap_flags by removing the indent before '='. Link: https://lore.kernel.org/r/20220331032419.313904-2-yangx.jy@fujitsu.com Signed-off-by: Xiao Yang Reviewed-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 104 ++++++++++++++++++++++++-------------- include/uapi/rdma/ib_user_verbs.h | 31 ++++++++++++ 2 files changed, 97 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index dfd467469622..ada4a5226dbd 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -220,21 +220,21 @@ enum rdma_link_layer { }; enum ib_device_cap_flags { - IB_DEVICE_RESIZE_MAX_WR = (1 << 0), - IB_DEVICE_BAD_PKEY_CNTR = (1 << 1), - IB_DEVICE_BAD_QKEY_CNTR = (1 << 2), - IB_DEVICE_RAW_MULTI = (1 << 3), - IB_DEVICE_AUTO_PATH_MIG = (1 << 4), - IB_DEVICE_CHANGE_PHY_PORT = (1 << 5), - IB_DEVICE_UD_AV_PORT_ENFORCE = (1 << 6), - IB_DEVICE_CURR_QP_STATE_MOD = (1 << 7), - IB_DEVICE_SHUTDOWN_PORT = (1 << 8), - /* Not in use, former INIT_TYPE = (1 << 9),*/ - IB_DEVICE_PORT_ACTIVE_EVENT = (1 << 10), - IB_DEVICE_SYS_IMAGE_GUID = (1 << 11), - IB_DEVICE_RC_RNR_NAK_GEN = (1 << 12), - IB_DEVICE_SRQ_RESIZE = (1 << 13), - IB_DEVICE_N_NOTIFY_CQ = (1 << 14), + IB_DEVICE_RESIZE_MAX_WR = IB_UVERBS_DEVICE_RESIZE_MAX_WR, + IB_DEVICE_BAD_PKEY_CNTR = IB_UVERBS_DEVICE_BAD_PKEY_CNTR, + IB_DEVICE_BAD_QKEY_CNTR = IB_UVERBS_DEVICE_BAD_QKEY_CNTR, + IB_DEVICE_RAW_MULTI = IB_UVERBS_DEVICE_RAW_MULTI, + IB_DEVICE_AUTO_PATH_MIG = IB_UVERBS_DEVICE_AUTO_PATH_MIG, + IB_DEVICE_CHANGE_PHY_PORT = IB_UVERBS_DEVICE_CHANGE_PHY_PORT, + IB_DEVICE_UD_AV_PORT_ENFORCE = IB_UVERBS_DEVICE_UD_AV_PORT_ENFORCE, + IB_DEVICE_CURR_QP_STATE_MOD = IB_UVERBS_DEVICE_CURR_QP_STATE_MOD, + IB_DEVICE_SHUTDOWN_PORT = IB_UVERBS_DEVICE_SHUTDOWN_PORT, + /* IB_DEVICE_INIT_TYPE = IB_UVERBS_DEVICE_INIT_TYPE, (not in use) */ + IB_DEVICE_PORT_ACTIVE_EVENT = IB_UVERBS_DEVICE_PORT_ACTIVE_EVENT, + IB_DEVICE_SYS_IMAGE_GUID = IB_UVERBS_DEVICE_SYS_IMAGE_GUID, + IB_DEVICE_RC_RNR_NAK_GEN = IB_UVERBS_DEVICE_RC_RNR_NAK_GEN, + IB_DEVICE_SRQ_RESIZE = IB_UVERBS_DEVICE_SRQ_RESIZE, + IB_DEVICE_N_NOTIFY_CQ = IB_UVERBS_DEVICE_N_NOTIFY_CQ, /* * This device supports a per-device lkey or stag that can be @@ -243,9 +243,9 @@ enum ib_device_cap_flags { * instead of use the local_dma_lkey flag in the ib_pd structure, * which will always contain a usable lkey. */ - IB_DEVICE_LOCAL_DMA_LKEY = (1 << 15), - /* Reserved, old SEND_W_INV = (1 << 16),*/ - IB_DEVICE_MEM_WINDOW = (1 << 17), + IB_DEVICE_LOCAL_DMA_LKEY = 1 << 15, + /* Reserved, old SEND_W_INV = 1 << 16,*/ + IB_DEVICE_MEM_WINDOW = IB_UVERBS_DEVICE_MEM_WINDOW, /* * Devices should set IB_DEVICE_UD_IP_SUM if they support * insertion of UDP and TCP checksum on outgoing UD IPoIB @@ -253,9 +253,9 @@ enum ib_device_cap_flags { * incoming messages. Setting this flag implies that the * IPoIB driver may set NETIF_F_IP_CSUM for datagram mode. */ - IB_DEVICE_UD_IP_CSUM = (1 << 18), - IB_DEVICE_UD_TSO = (1 << 19), - IB_DEVICE_XRC = (1 << 20), + IB_DEVICE_UD_IP_CSUM = IB_UVERBS_DEVICE_UD_IP_CSUM, + IB_DEVICE_UD_TSO = 1 << 19, + IB_DEVICE_XRC = IB_UVERBS_DEVICE_XRC, /* * This device supports the IB "base memory management extension", @@ -266,32 +266,60 @@ enum ib_device_cap_flags { * IB_WR_RDMA_READ_WITH_INV verb for RDMA READs that invalidate the * stag. */ - IB_DEVICE_MEM_MGT_EXTENSIONS = (1 << 21), - IB_DEVICE_BLOCK_MULTICAST_LOOPBACK = (1 << 22), - IB_DEVICE_MEM_WINDOW_TYPE_2A = (1 << 23), - IB_DEVICE_MEM_WINDOW_TYPE_2B = (1 << 24), - IB_DEVICE_RC_IP_CSUM = (1 << 25), + IB_DEVICE_MEM_MGT_EXTENSIONS = IB_UVERBS_DEVICE_MEM_MGT_EXTENSIONS, + IB_DEVICE_BLOCK_MULTICAST_LOOPBACK = 1 << 22, + IB_DEVICE_MEM_WINDOW_TYPE_2A = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2A, + IB_DEVICE_MEM_WINDOW_TYPE_2B = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2B, + IB_DEVICE_RC_IP_CSUM = IB_UVERBS_DEVICE_RC_IP_CSUM, /* Deprecated. Please use IB_RAW_PACKET_CAP_IP_CSUM. */ - IB_DEVICE_RAW_IP_CSUM = (1 << 26), + IB_DEVICE_RAW_IP_CSUM = IB_UVERBS_DEVICE_RAW_IP_CSUM, /* * Devices should set IB_DEVICE_CROSS_CHANNEL if they * support execution of WQEs that involve synchronization * of I/O operations with single completion queue managed * by hardware. */ - IB_DEVICE_CROSS_CHANNEL = (1 << 27), - IB_DEVICE_MANAGED_FLOW_STEERING = (1 << 29), - IB_DEVICE_INTEGRITY_HANDOVER = (1 << 30), - IB_DEVICE_ON_DEMAND_PAGING = (1ULL << 31), - IB_DEVICE_SG_GAPS_REG = (1ULL << 32), - IB_DEVICE_VIRTUAL_FUNCTION = (1ULL << 33), + IB_DEVICE_CROSS_CHANNEL = 1 << 27, + IB_DEVICE_MANAGED_FLOW_STEERING = + IB_UVERBS_DEVICE_MANAGED_FLOW_STEERING, + IB_DEVICE_INTEGRITY_HANDOVER = 1 << 30, + IB_DEVICE_ON_DEMAND_PAGING = 1ULL << 31, + IB_DEVICE_SG_GAPS_REG = 1ULL << 32, + IB_DEVICE_VIRTUAL_FUNCTION = 1ULL << 33, /* Deprecated. Please use IB_RAW_PACKET_CAP_SCATTER_FCS. */ - IB_DEVICE_RAW_SCATTER_FCS = (1ULL << 34), - IB_DEVICE_RDMA_NETDEV_OPA = (1ULL << 35), + IB_DEVICE_RAW_SCATTER_FCS = IB_UVERBS_DEVICE_RAW_SCATTER_FCS, + IB_DEVICE_RDMA_NETDEV_OPA = 1ULL << 35, /* The device supports padding incoming writes to cacheline. */ - IB_DEVICE_PCI_WRITE_END_PADDING = (1ULL << 36), - IB_DEVICE_ALLOW_USER_UNREG = (1ULL << 37), -}; + IB_DEVICE_PCI_WRITE_END_PADDING = + IB_UVERBS_DEVICE_PCI_WRITE_END_PADDING, + IB_DEVICE_ALLOW_USER_UNREG = 1ULL << 37, +}; + +#define IB_UVERBS_DEVICE_CAP_FLAGS_MASK (IB_UVERBS_DEVICE_RESIZE_MAX_WR | \ + IB_UVERBS_DEVICE_BAD_PKEY_CNTR | \ + IB_UVERBS_DEVICE_BAD_QKEY_CNTR | \ + IB_UVERBS_DEVICE_RAW_MULTI | \ + IB_UVERBS_DEVICE_AUTO_PATH_MIG | \ + IB_UVERBS_DEVICE_CHANGE_PHY_PORT | \ + IB_UVERBS_DEVICE_UD_AV_PORT_ENFORCE | \ + IB_UVERBS_DEVICE_CURR_QP_STATE_MOD | \ + IB_UVERBS_DEVICE_SHUTDOWN_PORT | \ + IB_UVERBS_DEVICE_PORT_ACTIVE_EVENT | \ + IB_UVERBS_DEVICE_SYS_IMAGE_GUID | \ + IB_UVERBS_DEVICE_RC_RNR_NAK_GEN | \ + IB_UVERBS_DEVICE_SRQ_RESIZE | \ + IB_UVERBS_DEVICE_N_NOTIFY_CQ | \ + IB_UVERBS_DEVICE_MEM_WINDOW | \ + IB_UVERBS_DEVICE_UD_IP_CSUM | \ + IB_UVERBS_DEVICE_XRC | \ + IB_UVERBS_DEVICE_MEM_MGT_EXTENSIONS | \ + IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2A | \ + IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2B | \ + IB_UVERBS_DEVICE_RC_IP_CSUM | \ + IB_UVERBS_DEVICE_RAW_IP_CSUM | \ + IB_UVERBS_DEVICE_MANAGED_FLOW_STEERING | \ + IB_UVERBS_DEVICE_RAW_SCATTER_FCS | \ + IB_UVERBS_DEVICE_PCI_WRITE_END_PADDING) enum ib_atomic_cap { IB_ATOMIC_NONE, diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index ff549695f1ba..06a4897c4958 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -1298,6 +1298,37 @@ struct ib_uverbs_ex_modify_cq { #define IB_DEVICE_NAME_MAX 64 +enum ib_uverbs_device_cap_flags { + IB_UVERBS_DEVICE_RESIZE_MAX_WR = 1 << 0, + IB_UVERBS_DEVICE_BAD_PKEY_CNTR = 1 << 1, + IB_UVERBS_DEVICE_BAD_QKEY_CNTR = 1 << 2, + IB_UVERBS_DEVICE_RAW_MULTI = 1 << 3, + IB_UVERBS_DEVICE_AUTO_PATH_MIG = 1 << 4, + IB_UVERBS_DEVICE_CHANGE_PHY_PORT = 1 << 5, + IB_UVERBS_DEVICE_UD_AV_PORT_ENFORCE = 1 << 6, + IB_UVERBS_DEVICE_CURR_QP_STATE_MOD = 1 << 7, + IB_UVERBS_DEVICE_SHUTDOWN_PORT = 1 << 8, + /* IB_UVERBS_DEVICE_INIT_TYPE = 1 << 9, (not in use) */ + IB_UVERBS_DEVICE_PORT_ACTIVE_EVENT = 1 << 10, + IB_UVERBS_DEVICE_SYS_IMAGE_GUID = 1 << 11, + IB_UVERBS_DEVICE_RC_RNR_NAK_GEN = 1 << 12, + IB_UVERBS_DEVICE_SRQ_RESIZE = 1 << 13, + IB_UVERBS_DEVICE_N_NOTIFY_CQ = 1 << 14, + IB_UVERBS_DEVICE_MEM_WINDOW = 1 << 17, + IB_UVERBS_DEVICE_UD_IP_CSUM = 1 << 18, + IB_UVERBS_DEVICE_XRC = 1 << 20, + IB_UVERBS_DEVICE_MEM_MGT_EXTENSIONS = 1 << 21, + IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2A = 1 << 23, + IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2B = 1 << 24, + IB_UVERBS_DEVICE_RC_IP_CSUM = 1 << 25, + /* Deprecated. Please use IB_UVERBS_RAW_PACKET_CAP_IP_CSUM. */ + IB_UVERBS_DEVICE_RAW_IP_CSUM = 1 << 26, + IB_UVERBS_DEVICE_MANAGED_FLOW_STEERING = 1 << 29, + /* Deprecated. Please use IB_UVERBS_RAW_PACKET_CAP_SCATTER_FCS. */ + IB_UVERBS_DEVICE_RAW_SCATTER_FCS = 1ULL << 34, + IB_UVERBS_DEVICE_PCI_WRITE_END_PADDING = 1ULL << 36, +}; + enum ib_uverbs_raw_packet_caps { IB_UVERBS_RAW_PACKET_CAP_CVLAN_STRIPPING = 1 << 0, IB_UVERBS_RAW_PACKET_CAP_SCATTER_FCS = 1 << 1, -- cgit v1.2.3 From f0e3c6261af183f0c2246cfe691abec78377622c Mon Sep 17 00:00:00 2001 From: Johnson Wang Date: Fri, 1 Apr 2022 16:02:11 +0800 Subject: regulator: mt6366: Add support for MT6366 regulator The MT6366 is a regulator found on boards based on MediaTek MT8186 and probably other SoCs. It is a so called pmic and connects as a slave to SoC using SPI, wrapped inside the pmic-wrapper. Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Johnson Wang Link: https://lore.kernel.org/r/20220401080212.27383-2-johnson.wang@mediatek.com Signed-off-by: Mark Brown --- include/linux/regulator/mt6358-regulator.h | 45 ++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) (limited to 'include') diff --git a/include/linux/regulator/mt6358-regulator.h b/include/linux/regulator/mt6358-regulator.h index 1cc304946d09..bdcf83cd719e 100644 --- a/include/linux/regulator/mt6358-regulator.h +++ b/include/linux/regulator/mt6358-regulator.h @@ -48,9 +48,54 @@ enum { MT6358_ID_VLDO28, MT6358_ID_VAUD28, MT6358_ID_VSIM2, + MT6358_ID_VCORE_SSHUB, + MT6358_ID_VSRAM_OTHERS_SSHUB, MT6358_ID_RG_MAX, }; +enum { + MT6366_ID_VDRAM1 = 0, + MT6366_ID_VCORE, + MT6366_ID_VPA, + MT6366_ID_VPROC11, + MT6366_ID_VPROC12, + MT6366_ID_VGPU, + MT6366_ID_VS2, + MT6366_ID_VMODEM, + MT6366_ID_VS1, + MT6366_ID_VDRAM2, + MT6366_ID_VSIM1, + MT6366_ID_VIBR, + MT6366_ID_VRF12, + MT6366_ID_VIO18, + MT6366_ID_VUSB, + MT6366_ID_VCN18, + MT6366_ID_VFE28, + MT6366_ID_VSRAM_PROC11, + MT6366_ID_VCN28, + MT6366_ID_VSRAM_OTHERS, + MT6366_ID_VSRAM_GPU, + MT6366_ID_VXO22, + MT6366_ID_VEFUSE, + MT6366_ID_VAUX18, + MT6366_ID_VMCH, + MT6366_ID_VBIF28, + MT6366_ID_VSRAM_PROC12, + MT6366_ID_VEMC, + MT6366_ID_VIO28, + MT6366_ID_VA12, + MT6366_ID_VRF18, + MT6366_ID_VCN33_BT, + MT6366_ID_VCN33_WIFI, + MT6366_ID_VMC, + MT6366_ID_VAUD28, + MT6366_ID_VSIM2, + MT6366_ID_VCORE_SSHUB, + MT6366_ID_VSRAM_OTHERS_SSHUB, + MT6366_ID_RG_MAX, +}; + #define MT6358_MAX_REGULATOR MT6358_ID_RG_MAX +#define MT6366_MAX_REGULATOR MT6366_ID_RG_MAX #endif /* __LINUX_REGULATOR_MT6358_H */ -- cgit v1.2.3 From d44c2642c40b6c11e4a0afc76d491287c074376c Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 31 Mar 2022 22:46:49 +0200 Subject: drm/gem: Delete gem array fencing helpers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Integrated into the scheduler now and all users converted over. v2: Rebased over changes from König. Acked-by: Christian König Signed-off-by: Daniel Vetter Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Thomas Zimmermann Cc: David Airlie Cc: Daniel Vetter Cc: Sumit Semwal Cc: "Christian König" Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20220331204651.2699107-3-daniel.vetter@ffwll.ch --- include/drm/drm_gem.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h index 35e7f44c2a75..e55a767188af 100644 --- a/include/drm/drm_gem.h +++ b/include/drm/drm_gem.h @@ -407,11 +407,6 @@ int drm_gem_lock_reservations(struct drm_gem_object **objs, int count, struct ww_acquire_ctx *acquire_ctx); void drm_gem_unlock_reservations(struct drm_gem_object **objs, int count, struct ww_acquire_ctx *acquire_ctx); -int drm_gem_fence_array_add(struct xarray *fence_array, - struct dma_fence *fence); -int drm_gem_fence_array_add_implicit(struct xarray *fence_array, - struct drm_gem_object *obj, - bool write); int drm_gem_dumb_map_offset(struct drm_file *file, struct drm_device *dev, u32 handle, u64 *offset); -- cgit v1.2.3 From 353520811fe70fb720a29ffd8833778d88ae9dee Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 3 Apr 2022 16:10:40 -0700 Subject: drm: fix a kernel-doc typo Fix a build warning from 'make htmldocs' by correcting the lock name in the kernel-doc comment. include/drm/drm_file.h:369: warning: Function parameter or member 'master_lookup_lock' not described in 'drm_file' Signed-off-by: Randy Dunlap Cc: David Airlie Cc: Daniel Vetter Cc: dri-devel@lists.freedesktop.org Reviewed-by: Simon Ser Signed-off-by: Simon Ser Link: https://patchwork.freedesktop.org/patch/msgid/20220403231040.18540-1-rdunlap@infradead.org --- include/drm/drm_file.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_file.h b/include/drm/drm_file.h index a3acb7ac3550..e0a73a1e2df7 100644 --- a/include/drm/drm_file.h +++ b/include/drm/drm_file.h @@ -248,7 +248,7 @@ struct drm_file { */ struct drm_master *master; - /** @master_lock: Serializes @master. */ + /** @master_lookup_lock: Serializes @master. */ spinlock_t master_lookup_lock; /** @pid: Process that opened this file. */ -- cgit v1.2.3 From caae9458db3aef14b96921cf02c6093340350c4a Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Fri, 11 Feb 2022 17:42:41 +0100 Subject: kunit: Introduce _NULL and _NOT_NULL macros Today, when we want to check if a pointer is NULL and not ERR we have two options: KUNIT_EXPECT_TRUE(test, ptr == NULL); or KUNIT_EXPECT_PTR_NE(test, ptr, (struct mystruct *)NULL); Create a new set of macros that take care of NULL checks. Reviewed-by: Brendan Higgins Reviewed-by: Daniel Latypov Signed-off-by: Ricardo Ribalda Signed-off-by: Shuah Khan --- include/kunit/test.h | 84 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 84 insertions(+) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index 00b9ff7783ab..e6c18b609b47 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -1218,6 +1218,48 @@ do { \ fmt, \ ##__VA_ARGS__) +/** + * KUNIT_EXPECT_NULL() - Expects that @ptr is null. + * @test: The test context object. + * @ptr: an arbitrary pointer. + * + * Sets an expectation that the value that @ptr evaluates to is null. This is + * semantically equivalent to KUNIT_EXPECT_PTR_EQ(@test, ptr, NULL). + * See KUNIT_EXPECT_TRUE() for more information. + */ +#define KUNIT_EXPECT_NULL(test, ptr) \ + KUNIT_EXPECT_NULL_MSG(test, \ + ptr, \ + NULL) + +#define KUNIT_EXPECT_NULL_MSG(test, ptr, fmt, ...) \ + KUNIT_BINARY_PTR_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + ptr, ==, NULL, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_EXPECT_NOT_NULL() - Expects that @ptr is not null. + * @test: The test context object. + * @ptr: an arbitrary pointer. + * + * Sets an expectation that the value that @ptr evaluates to is not null. This + * is semantically equivalent to KUNIT_EXPECT_PTR_NE(@test, ptr, NULL). + * See KUNIT_EXPECT_TRUE() for more information. + */ +#define KUNIT_EXPECT_NOT_NULL(test, ptr) \ + KUNIT_EXPECT_NOT_NULL_MSG(test, \ + ptr, \ + NULL) + +#define KUNIT_EXPECT_NOT_NULL_MSG(test, ptr, fmt, ...) \ + KUNIT_BINARY_PTR_ASSERTION(test, \ + KUNIT_EXPECTATION, \ + ptr, !=, NULL, \ + fmt, \ + ##__VA_ARGS__) + /** * KUNIT_EXPECT_NOT_ERR_OR_NULL() - Expects that @ptr is not null and not err. * @test: The test context object. @@ -1485,6 +1527,48 @@ do { \ fmt, \ ##__VA_ARGS__) +/** + * KUNIT_ASSERT_NULL() - Asserts that pointers @ptr is null. + * @test: The test context object. + * @ptr: an arbitrary pointer. + * + * Sets an assertion that the values that @ptr evaluates to is null. This is + * the same as KUNIT_EXPECT_NULL(), except it causes an assertion + * failure (see KUNIT_ASSERT_TRUE()) when the assertion is not met. + */ +#define KUNIT_ASSERT_NULL(test, ptr) \ + KUNIT_ASSERT_NULL_MSG(test, \ + ptr, \ + NULL) + +#define KUNIT_ASSERT_NULL_MSG(test, ptr, fmt, ...) \ + KUNIT_BINARY_PTR_ASSERTION(test, \ + KUNIT_ASSERTION, \ + ptr, ==, NULL, \ + fmt, \ + ##__VA_ARGS__) + +/** + * KUNIT_ASSERT_NOT_NULL() - Asserts that pointers @ptr is not null. + * @test: The test context object. + * @ptr: an arbitrary pointer. + * + * Sets an assertion that the values that @ptr evaluates to is not null. This + * is the same as KUNIT_EXPECT_NOT_NULL(), except it causes an assertion + * failure (see KUNIT_ASSERT_TRUE()) when the assertion is not met. + */ +#define KUNIT_ASSERT_NOT_NULL(test, ptr) \ + KUNIT_ASSERT_NOT_NULL_MSG(test, \ + ptr, \ + NULL) + +#define KUNIT_ASSERT_NOT_NULL_MSG(test, ptr, fmt, ...) \ + KUNIT_BINARY_PTR_ASSERTION(test, \ + KUNIT_ASSERTION, \ + ptr, !=, NULL, \ + fmt, \ + ##__VA_ARGS__) + /** * KUNIT_ASSERT_NOT_ERR_OR_NULL() - Assertion that @ptr is not null and not err. * @test: The test context object. -- cgit v1.2.3 From 61695f8c5d5190db11aece403304f06d22c90597 Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Mon, 28 Mar 2022 10:41:42 -0700 Subject: kunit: split resource API from test.h into new resource.h Background: Currently, a reader looking at kunit/test.h will find the file is quite long, and the first meaty comment is a doc comment about struct kunit_resource. Most users will not ever use the KUnit resource API directly. They'll use kunit_kmalloc() and friends, or decide it's simpler to do cleanups via labels (it often can be) instead of figuring out how to use the API. It's also logically separate from everything else in test.h. Removing it from the file doesn't cause any compilation errors (since struct kunit has `struct list_head resources` to store them). This commit: Let's move it into a kunit/resource.h file and give it a separate page in the docs, kunit/api/resource.rst. We include resource.h at the bottom of test.h since * don't want to force existing users to add a new include if they use the API * it accesses `lock` inside `struct kunit` in a inline func * so we can't just forward declare, and the alternatives require uninlining the func, adding hepers to lock/unlock, or other more invasive changes. Now the first big comment in test.h is about kunit_case, which is a lot more relevant to what a new user wants to know. A side effect of this is git blame won't properly track history by default, users need to run $ git blame -L ,1 -C17 include/kunit/resource.h Signed-off-by: Daniel Latypov Reviewed-by: David Gow Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- include/kunit/resource.h | 318 +++++++++++++++++++++++++++++++++++++++++++++++ include/kunit/test.h | 303 +------------------------------------------- 2 files changed, 322 insertions(+), 299 deletions(-) create mode 100644 include/kunit/resource.h (limited to 'include') diff --git a/include/kunit/resource.h b/include/kunit/resource.h new file mode 100644 index 000000000000..7ab1fd83972b --- /dev/null +++ b/include/kunit/resource.h @@ -0,0 +1,318 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * KUnit resource API for test managed resources (allocations, etc.). + * + * Copyright (C) 2022, Google LLC. + * Author: Daniel Latypov + */ + +#ifndef _KUNIT_RESOURCE_H +#define _KUNIT_RESOURCE_H + +#include + +#include +#include +#include +#include + +struct kunit_resource; + +typedef int (*kunit_resource_init_t)(struct kunit_resource *, void *); +typedef void (*kunit_resource_free_t)(struct kunit_resource *); + +/** + * struct kunit_resource - represents a *test managed resource* + * @data: for the user to store arbitrary data. + * @name: optional name + * @free: a user supplied function to free the resource. Populated by + * kunit_resource_alloc(). + * + * Represents a *test managed resource*, a resource which will automatically be + * cleaned up at the end of a test case. + * + * Resources are reference counted so if a resource is retrieved via + * kunit_alloc_and_get_resource() or kunit_find_resource(), we need + * to call kunit_put_resource() to reduce the resource reference count + * when finished with it. Note that kunit_alloc_resource() does not require a + * kunit_resource_put() because it does not retrieve the resource itself. + * + * Example: + * + * .. code-block:: c + * + * struct kunit_kmalloc_params { + * size_t size; + * gfp_t gfp; + * }; + * + * static int kunit_kmalloc_init(struct kunit_resource *res, void *context) + * { + * struct kunit_kmalloc_params *params = context; + * res->data = kmalloc(params->size, params->gfp); + * + * if (!res->data) + * return -ENOMEM; + * + * return 0; + * } + * + * static void kunit_kmalloc_free(struct kunit_resource *res) + * { + * kfree(res->data); + * } + * + * void *kunit_kmalloc(struct kunit *test, size_t size, gfp_t gfp) + * { + * struct kunit_kmalloc_params params; + * + * params.size = size; + * params.gfp = gfp; + * + * return kunit_alloc_resource(test, kunit_kmalloc_init, + * kunit_kmalloc_free, ¶ms); + * } + * + * Resources can also be named, with lookup/removal done on a name + * basis also. kunit_add_named_resource(), kunit_find_named_resource() + * and kunit_destroy_named_resource(). Resource names must be + * unique within the test instance. + */ +struct kunit_resource { + void *data; + const char *name; + kunit_resource_free_t free; + + /* private: internal use only. */ + struct kref refcount; + struct list_head node; +}; + +/* + * Like kunit_alloc_resource() below, but returns the struct kunit_resource + * object that contains the allocation. This is mostly for testing purposes. + */ +struct kunit_resource *kunit_alloc_and_get_resource(struct kunit *test, + kunit_resource_init_t init, + kunit_resource_free_t free, + gfp_t internal_gfp, + void *context); + +/** + * kunit_get_resource() - Hold resource for use. Should not need to be used + * by most users as we automatically get resources + * retrieved by kunit_find_resource*(). + * @res: resource + */ +static inline void kunit_get_resource(struct kunit_resource *res) +{ + kref_get(&res->refcount); +} + +/* + * Called when refcount reaches zero via kunit_put_resource(); + * should not be called directly. + */ +static inline void kunit_release_resource(struct kref *kref) +{ + struct kunit_resource *res = container_of(kref, struct kunit_resource, + refcount); + + /* If free function is defined, resource was dynamically allocated. */ + if (res->free) { + res->free(res); + kfree(res); + } +} + +/** + * kunit_put_resource() - When caller is done with retrieved resource, + * kunit_put_resource() should be called to drop + * reference count. The resource list maintains + * a reference count on resources, so if no users + * are utilizing a resource and it is removed from + * the resource list, it will be freed via the + * associated free function (if any). Only + * needs to be used if we alloc_and_get() or + * find() resource. + * @res: resource + */ +static inline void kunit_put_resource(struct kunit_resource *res) +{ + kref_put(&res->refcount, kunit_release_resource); +} + +/** + * kunit_add_resource() - Add a *test managed resource*. + * @test: The test context object. + * @init: a user-supplied function to initialize the result (if needed). If + * none is supplied, the resource data value is simply set to @data. + * If an init function is supplied, @data is passed to it instead. + * @free: a user-supplied function to free the resource (if needed). + * @res: The resource. + * @data: value to pass to init function or set in resource data field. + */ +int kunit_add_resource(struct kunit *test, + kunit_resource_init_t init, + kunit_resource_free_t free, + struct kunit_resource *res, + void *data); + +/** + * kunit_add_named_resource() - Add a named *test managed resource*. + * @test: The test context object. + * @init: a user-supplied function to initialize the resource data, if needed. + * @free: a user-supplied function to free the resource data, if needed. + * @res: The resource. + * @name: name to be set for resource. + * @data: value to pass to init function or set in resource data field. + */ +int kunit_add_named_resource(struct kunit *test, + kunit_resource_init_t init, + kunit_resource_free_t free, + struct kunit_resource *res, + const char *name, + void *data); + +/** + * kunit_alloc_resource() - Allocates a *test managed resource*. + * @test: The test context object. + * @init: a user supplied function to initialize the resource. + * @free: a user supplied function to free the resource. + * @internal_gfp: gfp to use for internal allocations, if unsure, use GFP_KERNEL + * @context: for the user to pass in arbitrary data to the init function. + * + * Allocates a *test managed resource*, a resource which will automatically be + * cleaned up at the end of a test case. See &struct kunit_resource for an + * example. + * + * Note: KUnit needs to allocate memory for a kunit_resource object. You must + * specify an @internal_gfp that is compatible with the use context of your + * resource. + */ +static inline void *kunit_alloc_resource(struct kunit *test, + kunit_resource_init_t init, + kunit_resource_free_t free, + gfp_t internal_gfp, + void *context) +{ + struct kunit_resource *res; + + res = kzalloc(sizeof(*res), internal_gfp); + if (!res) + return NULL; + + if (!kunit_add_resource(test, init, free, res, context)) + return res->data; + + return NULL; +} + +typedef bool (*kunit_resource_match_t)(struct kunit *test, + struct kunit_resource *res, + void *match_data); + +/** + * kunit_resource_instance_match() - Match a resource with the same instance. + * @test: Test case to which the resource belongs. + * @res: The resource. + * @match_data: The resource pointer to match against. + * + * An instance of kunit_resource_match_t that matches a resource whose + * allocation matches @match_data. + */ +static inline bool kunit_resource_instance_match(struct kunit *test, + struct kunit_resource *res, + void *match_data) +{ + return res->data == match_data; +} + +/** + * kunit_resource_name_match() - Match a resource with the same name. + * @test: Test case to which the resource belongs. + * @res: The resource. + * @match_name: The name to match against. + */ +static inline bool kunit_resource_name_match(struct kunit *test, + struct kunit_resource *res, + void *match_name) +{ + return res->name && strcmp(res->name, match_name) == 0; +} + +/** + * kunit_find_resource() - Find a resource using match function/data. + * @test: Test case to which the resource belongs. + * @match: match function to be applied to resources/match data. + * @match_data: data to be used in matching. + */ +static inline struct kunit_resource * +kunit_find_resource(struct kunit *test, + kunit_resource_match_t match, + void *match_data) +{ + struct kunit_resource *res, *found = NULL; + unsigned long flags; + + spin_lock_irqsave(&test->lock, flags); + + list_for_each_entry_reverse(res, &test->resources, node) { + if (match(test, res, (void *)match_data)) { + found = res; + kunit_get_resource(found); + break; + } + } + + spin_unlock_irqrestore(&test->lock, flags); + + return found; +} + +/** + * kunit_find_named_resource() - Find a resource using match name. + * @test: Test case to which the resource belongs. + * @name: match name. + */ +static inline struct kunit_resource * +kunit_find_named_resource(struct kunit *test, + const char *name) +{ + return kunit_find_resource(test, kunit_resource_name_match, + (void *)name); +} + +/** + * kunit_destroy_resource() - Find a kunit_resource and destroy it. + * @test: Test case to which the resource belongs. + * @match: Match function. Returns whether a given resource matches @match_data. + * @match_data: Data passed into @match. + * + * RETURNS: + * 0 if kunit_resource is found and freed, -ENOENT if not found. + */ +int kunit_destroy_resource(struct kunit *test, + kunit_resource_match_t match, + void *match_data); + +static inline int kunit_destroy_named_resource(struct kunit *test, + const char *name) +{ + return kunit_destroy_resource(test, kunit_resource_name_match, + (void *)name); +} + +/** + * kunit_remove_resource() - remove resource from resource list associated with + * test. + * @test: The test context object. + * @res: The resource to be removed. + * + * Note that the resource will not be immediately freed since it is likely + * the caller has a reference to it via alloc_and_get() or find(); + * in this case a final call to kunit_put_resource() is required. + */ +void kunit_remove_resource(struct kunit *test, struct kunit_resource *res); + +#endif /* _KUNIT_RESOURCE_H */ diff --git a/include/kunit/test.h b/include/kunit/test.h index e6c18b609b47..97cd76461886 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -27,78 +27,6 @@ #include -struct kunit_resource; - -typedef int (*kunit_resource_init_t)(struct kunit_resource *, void *); -typedef void (*kunit_resource_free_t)(struct kunit_resource *); - -/** - * struct kunit_resource - represents a *test managed resource* - * @data: for the user to store arbitrary data. - * @name: optional name - * @free: a user supplied function to free the resource. Populated by - * kunit_resource_alloc(). - * - * Represents a *test managed resource*, a resource which will automatically be - * cleaned up at the end of a test case. - * - * Resources are reference counted so if a resource is retrieved via - * kunit_alloc_and_get_resource() or kunit_find_resource(), we need - * to call kunit_put_resource() to reduce the resource reference count - * when finished with it. Note that kunit_alloc_resource() does not require a - * kunit_resource_put() because it does not retrieve the resource itself. - * - * Example: - * - * .. code-block:: c - * - * struct kunit_kmalloc_params { - * size_t size; - * gfp_t gfp; - * }; - * - * static int kunit_kmalloc_init(struct kunit_resource *res, void *context) - * { - * struct kunit_kmalloc_params *params = context; - * res->data = kmalloc(params->size, params->gfp); - * - * if (!res->data) - * return -ENOMEM; - * - * return 0; - * } - * - * static void kunit_kmalloc_free(struct kunit_resource *res) - * { - * kfree(res->data); - * } - * - * void *kunit_kmalloc(struct kunit *test, size_t size, gfp_t gfp) - * { - * struct kunit_kmalloc_params params; - * - * params.size = size; - * params.gfp = gfp; - * - * return kunit_alloc_resource(test, kunit_kmalloc_init, - * kunit_kmalloc_free, ¶ms); - * } - * - * Resources can also be named, with lookup/removal done on a name - * basis also. kunit_add_named_resource(), kunit_find_named_resource() - * and kunit_destroy_named_resource(). Resource names must be - * unique within the test instance. - */ -struct kunit_resource { - void *data; - const char *name; - kunit_resource_free_t free; - - /* private: internal use only. */ - struct kref refcount; - struct list_head node; -}; - struct kunit; /* Size of log associated with test. */ @@ -385,233 +313,6 @@ static inline int kunit_run_all_tests(void) enum kunit_status kunit_suite_has_succeeded(struct kunit_suite *suite); -/* - * Like kunit_alloc_resource() below, but returns the struct kunit_resource - * object that contains the allocation. This is mostly for testing purposes. - */ -struct kunit_resource *kunit_alloc_and_get_resource(struct kunit *test, - kunit_resource_init_t init, - kunit_resource_free_t free, - gfp_t internal_gfp, - void *context); - -/** - * kunit_get_resource() - Hold resource for use. Should not need to be used - * by most users as we automatically get resources - * retrieved by kunit_find_resource*(). - * @res: resource - */ -static inline void kunit_get_resource(struct kunit_resource *res) -{ - kref_get(&res->refcount); -} - -/* - * Called when refcount reaches zero via kunit_put_resources(); - * should not be called directly. - */ -static inline void kunit_release_resource(struct kref *kref) -{ - struct kunit_resource *res = container_of(kref, struct kunit_resource, - refcount); - - /* If free function is defined, resource was dynamically allocated. */ - if (res->free) { - res->free(res); - kfree(res); - } -} - -/** - * kunit_put_resource() - When caller is done with retrieved resource, - * kunit_put_resource() should be called to drop - * reference count. The resource list maintains - * a reference count on resources, so if no users - * are utilizing a resource and it is removed from - * the resource list, it will be freed via the - * associated free function (if any). Only - * needs to be used if we alloc_and_get() or - * find() resource. - * @res: resource - */ -static inline void kunit_put_resource(struct kunit_resource *res) -{ - kref_put(&res->refcount, kunit_release_resource); -} - -/** - * kunit_add_resource() - Add a *test managed resource*. - * @test: The test context object. - * @init: a user-supplied function to initialize the result (if needed). If - * none is supplied, the resource data value is simply set to @data. - * If an init function is supplied, @data is passed to it instead. - * @free: a user-supplied function to free the resource (if needed). - * @res: The resource. - * @data: value to pass to init function or set in resource data field. - */ -int kunit_add_resource(struct kunit *test, - kunit_resource_init_t init, - kunit_resource_free_t free, - struct kunit_resource *res, - void *data); - -/** - * kunit_add_named_resource() - Add a named *test managed resource*. - * @test: The test context object. - * @init: a user-supplied function to initialize the resource data, if needed. - * @free: a user-supplied function to free the resource data, if needed. - * @res: The resource. - * @name: name to be set for resource. - * @data: value to pass to init function or set in resource data field. - */ -int kunit_add_named_resource(struct kunit *test, - kunit_resource_init_t init, - kunit_resource_free_t free, - struct kunit_resource *res, - const char *name, - void *data); - -/** - * kunit_alloc_resource() - Allocates a *test managed resource*. - * @test: The test context object. - * @init: a user supplied function to initialize the resource. - * @free: a user supplied function to free the resource. - * @internal_gfp: gfp to use for internal allocations, if unsure, use GFP_KERNEL - * @context: for the user to pass in arbitrary data to the init function. - * - * Allocates a *test managed resource*, a resource which will automatically be - * cleaned up at the end of a test case. See &struct kunit_resource for an - * example. - * - * Note: KUnit needs to allocate memory for a kunit_resource object. You must - * specify an @internal_gfp that is compatible with the use context of your - * resource. - */ -static inline void *kunit_alloc_resource(struct kunit *test, - kunit_resource_init_t init, - kunit_resource_free_t free, - gfp_t internal_gfp, - void *context) -{ - struct kunit_resource *res; - - res = kzalloc(sizeof(*res), internal_gfp); - if (!res) - return NULL; - - if (!kunit_add_resource(test, init, free, res, context)) - return res->data; - - return NULL; -} - -typedef bool (*kunit_resource_match_t)(struct kunit *test, - struct kunit_resource *res, - void *match_data); - -/** - * kunit_resource_instance_match() - Match a resource with the same instance. - * @test: Test case to which the resource belongs. - * @res: The resource. - * @match_data: The resource pointer to match against. - * - * An instance of kunit_resource_match_t that matches a resource whose - * allocation matches @match_data. - */ -static inline bool kunit_resource_instance_match(struct kunit *test, - struct kunit_resource *res, - void *match_data) -{ - return res->data == match_data; -} - -/** - * kunit_resource_name_match() - Match a resource with the same name. - * @test: Test case to which the resource belongs. - * @res: The resource. - * @match_name: The name to match against. - */ -static inline bool kunit_resource_name_match(struct kunit *test, - struct kunit_resource *res, - void *match_name) -{ - return res->name && strcmp(res->name, match_name) == 0; -} - -/** - * kunit_find_resource() - Find a resource using match function/data. - * @test: Test case to which the resource belongs. - * @match: match function to be applied to resources/match data. - * @match_data: data to be used in matching. - */ -static inline struct kunit_resource * -kunit_find_resource(struct kunit *test, - kunit_resource_match_t match, - void *match_data) -{ - struct kunit_resource *res, *found = NULL; - unsigned long flags; - - spin_lock_irqsave(&test->lock, flags); - - list_for_each_entry_reverse(res, &test->resources, node) { - if (match(test, res, (void *)match_data)) { - found = res; - kunit_get_resource(found); - break; - } - } - - spin_unlock_irqrestore(&test->lock, flags); - - return found; -} - -/** - * kunit_find_named_resource() - Find a resource using match name. - * @test: Test case to which the resource belongs. - * @name: match name. - */ -static inline struct kunit_resource * -kunit_find_named_resource(struct kunit *test, - const char *name) -{ - return kunit_find_resource(test, kunit_resource_name_match, - (void *)name); -} - -/** - * kunit_destroy_resource() - Find a kunit_resource and destroy it. - * @test: Test case to which the resource belongs. - * @match: Match function. Returns whether a given resource matches @match_data. - * @match_data: Data passed into @match. - * - * RETURNS: - * 0 if kunit_resource is found and freed, -ENOENT if not found. - */ -int kunit_destroy_resource(struct kunit *test, - kunit_resource_match_t match, - void *match_data); - -static inline int kunit_destroy_named_resource(struct kunit *test, - const char *name) -{ - return kunit_destroy_resource(test, kunit_resource_name_match, - (void *)name); -} - -/** - * kunit_remove_resource() - remove resource from resource list associated with - * test. - * @test: The test context object. - * @res: The resource to be removed. - * - * Note that the resource will not be immediately freed since it is likely - * the caller has a reference to it via alloc_and_get() or find(); - * in this case a final call to kunit_put_resource() is required. - */ -void kunit_remove_resource(struct kunit *test, struct kunit_resource *res); - /** * kunit_kmalloc_array() - Like kmalloc_array() except the allocation is *test managed*. * @test: The test context object. @@ -1610,4 +1311,8 @@ do { \ return NULL; \ } +// TODO(dlatypov@google.com): consider eventually migrating users to explicitly +// include resource.h themselves if they need it. +#include + #endif /* _KUNIT_TEST_H */ -- cgit v1.2.3 From 71d637823cac7748079a912e0373476c7cf6f985 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Wed, 3 Nov 2021 13:35:14 +0100 Subject: dma-buf: finally make dma_resv_excl_fence private v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Drivers should never touch this directly. v2: fix rebase clash Signed-off-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20220321135856.1331-10-christian.koenig@amd.com Reviewed-by: Daniel Vetter --- include/linux/dma-resv.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 233ed4f14d9e..ecb697d4d861 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -411,23 +411,6 @@ static inline void dma_resv_unlock(struct dma_resv *obj) ww_mutex_unlock(&obj->lock); } -/** - * dma_resv_excl_fence - return the object's exclusive fence - * @obj: the reservation object - * - * Returns the exclusive fence (if any). Caller must either hold the objects - * through dma_resv_lock() or the RCU read side lock through rcu_read_lock(), - * or one of the variants of each - * - * RETURNS - * The exclusive fence or NULL - */ -static inline struct dma_fence * -dma_resv_excl_fence(struct dma_resv *obj) -{ - return rcu_dereference_check(obj->fence_excl, dma_resv_held(obj)); -} - void dma_resv_init(struct dma_resv *obj); void dma_resv_fini(struct dma_resv *obj); int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences); -- cgit v1.2.3 From 8fd4ddda2f49a66bf5dd3d0c01966c4b1971308b Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 14 Mar 2022 12:49:36 +0100 Subject: static_call: Don't make __static_call_return0 static System.map shows that vmlinux contains several instances of __static_call_return0(): c0004fc0 t __static_call_return0 c0011518 t __static_call_return0 c00d8160 t __static_call_return0 arch_static_call_transform() uses the middle one to check whether we are setting a call to __static_call_return0 or not: c0011520 : c0011520: 3d 20 c0 01 lis r9,-16383 <== r9 = 0xc001 << 16 c0011524: 39 29 15 18 addi r9,r9,5400 <== r9 += 0x1518 c0011528: 7c 05 48 00 cmpw r5,r9 <== r9 has value 0xc0011518 here So if static_call_update() is called with one of the other instances of __static_call_return0(), arch_static_call_transform() won't recognise it. In order to work properly, global single instance of __static_call_return0() is required. Fixes: 3f2a8fc4b15d ("static_call/x86: Add __static_call_return0()") Signed-off-by: Christophe Leroy Signed-off-by: Peter Zijlstra (Intel) Acked-by: Josh Poimboeuf Link: https://lkml.kernel.org/r/30821468a0e7d28251954b578e5051dc09300d04.1647258493.git.christophe.leroy@csgroup.eu --- include/linux/static_call.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 3e56a9751c06..fcc5b48989b3 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -248,10 +248,7 @@ static inline int static_call_text_reserved(void *start, void *end) return 0; } -static inline long __static_call_return0(void) -{ - return 0; -} +extern long __static_call_return0(void); #define EXPORT_STATIC_CALL(name) \ EXPORT_SYMBOL(STATIC_CALL_KEY(name)); \ -- cgit v1.2.3 From 5517d500829c683a358a8de04ecb2e28af629ae5 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 14 Mar 2022 11:27:35 +0100 Subject: static_call: Properly initialise DEFINE_STATIC_CALL_RET0() When a static call is updated with __static_call_return0() as target, arch_static_call_transform() set it to use an optimised set of instructions which are meant to lay in the same cacheline. But when initialising a static call with DEFINE_STATIC_CALL_RET0(), we get a branch to the real __static_call_return0() function instead of getting the optimised setup: c00d8120 <__SCT__perf_snapshot_branch_stack>: c00d8120: 4b ff ff f4 b c00d8114 <__static_call_return0> c00d8124: 3d 80 c0 0e lis r12,-16370 c00d8128: 81 8c 81 3c lwz r12,-32452(r12) c00d812c: 7d 89 03 a6 mtctr r12 c00d8130: 4e 80 04 20 bctr c00d8134: 38 60 00 00 li r3,0 c00d8138: 4e 80 00 20 blr c00d813c: 00 00 00 00 .long 0x0 Add ARCH_DEFINE_STATIC_CALL_RET0_TRAMP() defined by each architecture to setup the optimised configuration, and rework DEFINE_STATIC_CALL_RET0() to call it: c00d8120 <__SCT__perf_snapshot_branch_stack>: c00d8120: 48 00 00 14 b c00d8134 <__SCT__perf_snapshot_branch_stack+0x14> c00d8124: 3d 80 c0 0e lis r12,-16370 c00d8128: 81 8c 81 3c lwz r12,-32452(r12) c00d812c: 7d 89 03 a6 mtctr r12 c00d8130: 4e 80 04 20 bctr c00d8134: 38 60 00 00 li r3,0 c00d8138: 4e 80 00 20 blr c00d813c: 00 00 00 00 .long 0x0 Signed-off-by: Christophe Leroy Signed-off-by: Peter Zijlstra (Intel) Acked-by: Josh Poimboeuf Link: https://lore.kernel.org/r/1e0a61a88f52a460f62a58ffc2a5f847d1f7d9d8.1647253456.git.christophe.leroy@csgroup.eu --- include/linux/static_call.h | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/static_call.h b/include/linux/static_call.h index fcc5b48989b3..3c50b0fdda16 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -196,6 +196,14 @@ extern long __static_call_return0(void); }; \ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + DECLARE_STATIC_CALL(name, _func); \ + struct static_call_key STATIC_CALL_KEY(name) = { \ + .func = __static_call_return0, \ + .type = 1, \ + }; \ + ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) + #define static_call_cond(name) (void)__static_call(name) #define EXPORT_STATIC_CALL(name) \ @@ -231,6 +239,12 @@ static inline int static_call_init(void) { return 0; } }; \ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + DECLARE_STATIC_CALL(name, _func); \ + struct static_call_key STATIC_CALL_KEY(name) = { \ + .func = __static_call_return0, \ + }; \ + ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) #define static_call_cond(name) (void)__static_call(name) @@ -284,6 +298,9 @@ static inline long __static_call_return0(void) .func = NULL, \ } +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + __DEFINE_STATIC_CALL(name, _func, __static_call_return0) + static inline void __static_call_nop(void) { } /* @@ -327,7 +344,4 @@ static inline int static_call_text_reserved(void *start, void *end) #define DEFINE_STATIC_CALL(name, _func) \ __DEFINE_STATIC_CALL(name, _func, _func) -#define DEFINE_STATIC_CALL_RET0(name, _func) \ - __DEFINE_STATIC_CALL(name, _func, __static_call_return0) - #endif /* _LINUX_STATIC_CALL_H */ -- cgit v1.2.3 From df21c0d7a94db64a4e1a0d070e26fb02e60fefab Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 14 Mar 2022 11:27:36 +0100 Subject: static_call: Remove __DEFINE_STATIC_CALL macro Only DEFINE_STATIC_CALL use __DEFINE_STATIC_CALL macro now when CONFIG_HAVE_STATIC_CALL is selected. Only keep __DEFINE_STATIC_CALL() for the generic fallback, and also use it to implement DEFINE_STATIC_CALL_NULL() in that case. Signed-off-by: Christophe Leroy Signed-off-by: Peter Zijlstra (Intel) Acked-by: Josh Poimboeuf Link: https://lore.kernel.org/r/329074f92d96e3220ebe15da7bbe2779beee31eb.1647253456.git.christophe.leroy@csgroup.eu --- include/linux/static_call.h | 23 ++++++++++------------- 1 file changed, 10 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 3c50b0fdda16..df53bed9d71f 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -180,13 +180,13 @@ extern int static_call_text_reserved(void *start, void *end); extern long __static_call_return0(void); -#define __DEFINE_STATIC_CALL(name, _func, _func_init) \ +#define DEFINE_STATIC_CALL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = _func_init, \ + .func = _func, \ .type = 1, \ }; \ - ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func_init) + ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) #define DEFINE_STATIC_CALL_NULL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ @@ -225,12 +225,12 @@ extern long __static_call_return0(void); static inline int static_call_init(void) { return 0; } -#define __DEFINE_STATIC_CALL(name, _func, _func_init) \ +#define DEFINE_STATIC_CALL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = _func_init, \ + .func = _func, \ }; \ - ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func_init) + ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) #define DEFINE_STATIC_CALL_NULL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ @@ -292,11 +292,11 @@ static inline long __static_call_return0(void) .func = _func_init, \ } +#define DEFINE_STATIC_CALL(name, _func) \ + __DEFINE_STATIC_CALL(name, _func, _func) + #define DEFINE_STATIC_CALL_NULL(name, _func) \ - DECLARE_STATIC_CALL(name, _func); \ - struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = NULL, \ - } + __DEFINE_STATIC_CALL(name, _func, NULL) #define DEFINE_STATIC_CALL_RET0(name, _func) \ __DEFINE_STATIC_CALL(name, _func, __static_call_return0) @@ -341,7 +341,4 @@ static inline int static_call_text_reserved(void *start, void *end) #endif /* CONFIG_HAVE_STATIC_CALL */ -#define DEFINE_STATIC_CALL(name, _func) \ - __DEFINE_STATIC_CALL(name, _func, _func) - #endif /* _LINUX_STATIC_CALL_H */ -- cgit v1.2.3 From 2d2f8f083ef29e9b7adfe5cb421368331543473f Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 28 Mar 2022 16:58:09 +0200 Subject: Revert "locking/local_lock: Make the empty local_lock_*() function a macro." With volatile removed from arch_raw_cpu_ptr() the compiler no longer creates the per-CPU reference. The usage of the macro can be reverted now. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220328145810.86783-3-bigeasy@linutronix.de --- include/linux/local_lock_internal.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index 6d635e8306d6..975e33b793a7 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -44,9 +44,9 @@ static inline void local_lock_debug_init(local_lock_t *l) } #else /* CONFIG_DEBUG_LOCK_ALLOC */ # define LOCAL_LOCK_DEBUG_INIT(lockname) -# define local_lock_acquire(__ll) do { typecheck(local_lock_t *, __ll); } while (0) -# define local_lock_release(__ll) do { typecheck(local_lock_t *, __ll); } while (0) -# define local_lock_debug_init(__ll) do { typecheck(local_lock_t *, __ll); } while (0) +static inline void local_lock_acquire(local_lock_t *l) { } +static inline void local_lock_release(local_lock_t *l) { } +static inline void local_lock_debug_init(local_lock_t *l) { } #endif /* !CONFIG_DEBUG_LOCK_ALLOC */ #define INIT_LOCAL_LOCK(lockname) { LOCAL_LOCK_DEBUG_INIT(lockname) } -- cgit v1.2.3 From 8b023accc8df70e72f7704d29fead7ca914d6837 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Mon, 14 Mar 2022 15:19:03 -0700 Subject: lockdep: Fix -Wunused-parameter for _THIS_IP_ While looking into a bug related to the compiler's handling of addresses of labels, I noticed some uses of _THIS_IP_ seemed unused in lockdep. Drive by cleanup. -Wunused-parameter: kernel/locking/lockdep.c:1383:22: warning: unused parameter 'ip' kernel/locking/lockdep.c:4246:48: warning: unused parameter 'ip' kernel/locking/lockdep.c:4844:19: warning: unused parameter 'ip' Signed-off-by: Nick Desaulniers Signed-off-by: Peter Zijlstra (Intel) Acked-by: Waiman Long Link: https://lore.kernel.org/r/20220314221909.2027027-1-ndesaulniers@google.com --- include/linux/irqflags.h | 4 ++-- include/linux/kvm_host.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 4b140938b03e..5ec0fa71399e 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -20,13 +20,13 @@ #ifdef CONFIG_PROVE_LOCKING extern void lockdep_softirqs_on(unsigned long ip); extern void lockdep_softirqs_off(unsigned long ip); - extern void lockdep_hardirqs_on_prepare(unsigned long ip); + extern void lockdep_hardirqs_on_prepare(void); extern void lockdep_hardirqs_on(unsigned long ip); extern void lockdep_hardirqs_off(unsigned long ip); #else static inline void lockdep_softirqs_on(unsigned long ip) { } static inline void lockdep_softirqs_off(unsigned long ip) { } - static inline void lockdep_hardirqs_on_prepare(unsigned long ip) { } + static inline void lockdep_hardirqs_on_prepare(void) { } static inline void lockdep_hardirqs_on(unsigned long ip) { } static inline void lockdep_hardirqs_off(unsigned long ip) { } #endif diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3f9b22c4983a..e1b2413750c0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -450,7 +450,7 @@ static __always_inline void guest_state_enter_irqoff(void) { instrumentation_begin(); trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(CALLER_ADDR0); + lockdep_hardirqs_on_prepare(); instrumentation_end(); guest_context_enter_irqoff(); -- cgit v1.2.3 From 16edd9b511a13e7760ed4b92ba4e39bacda5c86f Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 22 Mar 2022 11:57:08 -0700 Subject: locking: Add lock contention tracepoints This adds two new lock contention tracepoints like below: * lock:contention_begin * lock:contention_end The lock:contention_begin takes a flags argument to classify locks. I found it useful to identify what kind of locks it's tracing like if it's spinning or sleeping, reader-writer lock, real-time, and per-cpu. Move tracepoint definitions into mutex.c so that we can use them without lockdep. Signed-off-by: Namhyung Kim Signed-off-by: Peter Zijlstra (Intel) Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Link: https://lkml.kernel.org/r/20220322185709.141236-2-namhyung@kernel.org --- include/trace/events/lock.h | 61 ++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 58 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h index d7512129a324..b9b6e3edd518 100644 --- a/include/trace/events/lock.h +++ b/include/trace/events/lock.h @@ -5,11 +5,21 @@ #if !defined(_TRACE_LOCK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_LOCK_H -#include +#include #include +/* flags for lock:contention_begin */ +#define LCB_F_SPIN (1U << 0) +#define LCB_F_READ (1U << 1) +#define LCB_F_WRITE (1U << 2) +#define LCB_F_RT (1U << 3) +#define LCB_F_PERCPU (1U << 4) + + #ifdef CONFIG_LOCKDEP +#include + TRACE_EVENT(lock_acquire, TP_PROTO(struct lockdep_map *lock, unsigned int subclass, @@ -78,8 +88,53 @@ DEFINE_EVENT(lock, lock_acquired, TP_ARGS(lock, ip) ); -#endif -#endif +#endif /* CONFIG_LOCK_STAT */ +#endif /* CONFIG_LOCKDEP */ + +TRACE_EVENT(contention_begin, + + TP_PROTO(void *lock, unsigned int flags), + + TP_ARGS(lock, flags), + + TP_STRUCT__entry( + __field(void *, lock_addr) + __field(unsigned int, flags) + ), + + TP_fast_assign( + __entry->lock_addr = lock; + __entry->flags = flags; + ), + + TP_printk("%p (flags=%s)", __entry->lock_addr, + __print_flags(__entry->flags, "|", + { LCB_F_SPIN, "SPIN" }, + { LCB_F_READ, "READ" }, + { LCB_F_WRITE, "WRITE" }, + { LCB_F_RT, "RT" }, + { LCB_F_PERCPU, "PERCPU" } + )) +); + +TRACE_EVENT(contention_end, + + TP_PROTO(void *lock, int ret), + + TP_ARGS(lock, ret), + + TP_STRUCT__entry( + __field(void *, lock_addr) + __field(int, ret) + ), + + TP_fast_assign( + __entry->lock_addr = lock; + __entry->ret = ret; + ), + + TP_printk("%p (ret=%d)", __entry->lock_addr, __entry->ret) +); #endif /* _TRACE_LOCK_H */ -- cgit v1.2.3 From bfe4daf850f45d92dcd3da477f0b0456620294c3 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Tue, 22 Mar 2022 15:15:05 -0700 Subject: perf/core: Add perf_clear_branch_entry_bitfields() helper Make it simpler to reset all the info fields on the perf_branch_entry by adding a helper inline function. The goal is to centralize the initialization to avoid missing a field in case more are added. Signed-off-by: Stephane Eranian Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220322221517.2510440-2-eranian@google.com --- include/linux/perf_event.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index af97dd427501..a411080d5169 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1063,6 +1063,22 @@ static inline void perf_sample_data_init(struct perf_sample_data *data, data->txn = 0; } +/* + * Clear all bitfields in the perf_branch_entry. + * The to and from fields are not cleared because they are + * systematically modified by caller. + */ +static inline void perf_clear_branch_entry_bitfields(struct perf_branch_entry *br) +{ + br->mispred = 0; + br->predicted = 0; + br->in_tx = 0; + br->abort = 0; + br->cycles = 0; + br->type = 0; + br->reserved = 0; +} + extern void perf_output_sample(struct perf_output_handle *handle, struct perf_event_header *header, struct perf_sample_data *data, -- cgit v1.2.3 From dc1f7893a70fe403983bd8492f177bf993940e2c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 30 Mar 2022 13:06:54 +0200 Subject: locking/mutex: Make contention tracepoints more consistent wrt adaptive spinning Have the trace_contention_*() tracepoints consistently include adaptive spinning. In order to differentiate between the spinning and non-spinning states add LCB_F_MUTEX and combine with LCB_F_SPIN. The consequence is that a mutex contention can now triggler multiple _begin() tracepoints before triggering an _end(). Additionally, this fixes one path where mutex would trigger _end() without ever seeing a _begin(). Signed-off-by: Peter Zijlstra (Intel) --- include/trace/events/lock.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h index b9b6e3edd518..9ebd081e057e 100644 --- a/include/trace/events/lock.h +++ b/include/trace/events/lock.h @@ -14,6 +14,7 @@ #define LCB_F_WRITE (1U << 2) #define LCB_F_RT (1U << 3) #define LCB_F_PERCPU (1U << 4) +#define LCB_F_MUTEX (1U << 5) #ifdef CONFIG_LOCKDEP @@ -113,7 +114,8 @@ TRACE_EVENT(contention_begin, { LCB_F_READ, "READ" }, { LCB_F_WRITE, "WRITE" }, { LCB_F_RT, "RT" }, - { LCB_F_PERCPU, "PERCPU" } + { LCB_F_PERCPU, "PERCPU" }, + { LCB_F_MUTEX, "MUTEX" } )) ); -- cgit v1.2.3 From 2a606a18cd672a16343d146a126721b34cc6adbd Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Tue, 22 Mar 2022 15:15:12 -0700 Subject: ACPI: Add perf low power callback Add an optional callback needed by some PMU features, e.g., AMD BRS, to give a chance to the perf_events code to change its state before a CPU goes to low power and after it comes back. The callback is void when the PERF_NEEDS_LOPWR_CB flag is not set. This flag must be set in arch specific perf_event.h header whenever needed. When not set, there is no impact on the ACPI code. Signed-off-by: Stephane Eranian [peterz: build fix] Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220322221517.2510440-9-eranian@google.com --- include/linux/perf_event.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index a411080d5169..da759560eec5 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1676,4 +1676,10 @@ typedef int (perf_snapshot_branch_stack_t)(struct perf_branch_entry *entries, unsigned int cnt); DECLARE_STATIC_CALL(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t); +#ifndef PERF_NEEDS_LOPWR_CB +static inline void perf_lopwr_cb(bool mode) +{ +} +#endif + #endif /* _LINUX_PERF_EVENT_H */ -- cgit v1.2.3 From cfe43f478b79ba45573ca22d52d0d8823be068fa Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Fri, 12 Nov 2021 18:52:01 +0000 Subject: preempt/dynamic: Introduce preemption model accessors CONFIG_PREEMPT{_NONE, _VOLUNTARY} designate either: o The build-time preemption model when !PREEMPT_DYNAMIC o The default boot-time preemption model when PREEMPT_DYNAMIC IOW, using those on PREEMPT_DYNAMIC kernels is meaningless - the actual model could have been set to something else by the "preempt=foo" cmdline parameter. Same problem applies to CONFIG_PREEMPTION. Introduce a set of helpers to determine the actual preemption model used by the live kernel. Suggested-by: Marco Elver Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Marco Elver Acked-by: Frederic Weisbecker Link: https://lore.kernel.org/r/20211112185203.280040-3-valentin.schneider@arm.com --- include/linux/sched.h | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index d5e3c00b74e1..67f06f72c50e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2117,6 +2117,47 @@ static inline void cond_resched_rcu(void) #endif } +#ifdef CONFIG_PREEMPT_DYNAMIC + +extern bool preempt_model_none(void); +extern bool preempt_model_voluntary(void); +extern bool preempt_model_full(void); + +#else + +static inline bool preempt_model_none(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_NONE); +} +static inline bool preempt_model_voluntary(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY); +} +static inline bool preempt_model_full(void) +{ + return IS_ENABLED(CONFIG_PREEMPT); +} + +#endif + +static inline bool preempt_model_rt(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_RT); +} + +/* + * Does the preemption model allow non-cooperative preemption? + * + * For !CONFIG_PREEMPT_DYNAMIC kernels this is an exact match with + * CONFIG_PREEMPTION; for CONFIG_PREEMPT_DYNAMIC this doesn't work as the + * kernel is *built* with CONFIG_PREEMPTION=y but may run with e.g. the + * PREEMPT_NONE model. + */ +static inline bool preempt_model_preemptible(void) +{ + return preempt_model_full() || preempt_model_rt(); +} + /* * Does a critical section need to be broken due to another * task waiting?: (technically does not depend on CONFIG_PREEMPTION, -- cgit v1.2.3 From 900dedd7e47cc3f8d93dfa0ae6ac6cf49eda0c97 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Martin=20Povi=C5=A1er?= Date: Thu, 31 Mar 2022 02:04:48 +0200 Subject: ASoC: Introduce snd_soc_of_get_dai_link_cpus MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This function is an analogue of snd_soc_of_get_dai_link_codecs to help machine drivers read CPU DAI lists from devicetrees. Signed-off-by: Martin Povišer Link: https://lore.kernel.org/r/20220331000449.41062-5-povik+lin@cutebit.org Signed-off-by: Mark Brown --- include/sound/soc.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index 7a1650b303f1..d3d3a26e8867 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -1263,6 +1263,10 @@ int snd_soc_of_get_dai_link_codecs(struct device *dev, struct device_node *of_node, struct snd_soc_dai_link *dai_link); void snd_soc_of_put_dai_link_codecs(struct snd_soc_dai_link *dai_link); +int snd_soc_of_get_dai_link_cpus(struct device *dev, + struct device_node *of_node, + struct snd_soc_dai_link *dai_link); +void snd_soc_of_put_dai_link_cpus(struct snd_soc_dai_link *dai_link); int snd_soc_add_pcm_runtime(struct snd_soc_card *card, struct snd_soc_dai_link *dai_link); -- cgit v1.2.3 From 9f342904216f378e88008bb0ce1ae200a4b99fe8 Mon Sep 17 00:00:00 2001 From: Hui Wang Date: Mon, 28 Mar 2022 20:35:35 +0800 Subject: ASoC: cs35l41: Fix an out-of-bounds access in otp_packed_element_t The CS35L41_NUM_OTP_ELEM is 100, but only 99 entries are defined in the array otp_map_1/2[CS35L41_NUM_OTP_ELEM], this will trigger UBSAN to report a shift-out-of-bounds warning in the cs35l41_otp_unpack() since the last entry in the array will result in GENMASK(-1, 0). UBSAN reports this problem: UBSAN: shift-out-of-bounds in /home/hwang4/build/jammy/jammy/sound/soc/codecs/cs35l41-lib.c:836:8 shift exponent 64 is too large for 64-bit type 'long unsigned int' CPU: 10 PID: 595 Comm: systemd-udevd Not tainted 5.15.0-23-generic #23 Hardware name: LENOVO \x02MFG_IN_GO/\x02MFG_IN_GO, BIOS N3GET19W (1.00 ) 03/11/2022 Call Trace: show_stack+0x52/0x58 dump_stack_lvl+0x4a/0x5f dump_stack+0x10/0x12 ubsan_epilogue+0x9/0x45 __ubsan_handle_shift_out_of_bounds.cold+0x61/0xef ? regmap_unlock_mutex+0xe/0x10 cs35l41_otp_unpack.cold+0x1c6/0x2b2 [snd_soc_cs35l41_lib] cs35l41_hda_probe+0x24f/0x33a [snd_hda_scodec_cs35l41] cs35l41_hda_i2c_probe+0x65/0x90 [snd_hda_scodec_cs35l41_i2c] ? cs35l41_hda_i2c_remove+0x20/0x20 [snd_hda_scodec_cs35l41_i2c] i2c_device_probe+0x252/0x2b0 Fixes: 6450ef559056 ("ASoC: cs35l41: CS35L41 Boosted Smart Amplifier") Reviewed-by: Lucas Tanure Acked-by: Charles Keepax Signed-off-by: Hui Wang Link: https://lore.kernel.org/r/20220328123535.50000-2-hui.wang@canonical.com Signed-off-by: Mark Brown --- include/sound/cs35l41.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index bf7f9a9aeba0..9341130257ea 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -536,7 +536,6 @@ #define CS35L41_MAX_CACHE_REG 36 #define CS35L41_OTP_SIZE_WORDS 32 -#define CS35L41_NUM_OTP_ELEM 100 #define CS35L41_VALID_PDATA 0x80000000 #define CS35L41_NUM_SUPPLIES 2 -- cgit v1.2.3 From 8c756a0a2de17f1535ef885ac7e556e016735eb2 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Thu, 31 Mar 2022 15:54:47 +0300 Subject: device property: Convert device_{dma_supported,get_dma_attr} to fwnode Make the device_dma_supported and device_get_dma_attr functions to use the fwnode ops, and move the implementation to ACPI and OF frameworks. Signed-off-by: Sakari Ailus Acked-by: Rob Herring Reviewed-by: Andy Shevchenko Reviewed-by: Heikki Krogerus Signed-off-by: Rafael J. Wysocki --- include/linux/fwnode.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 3a532ba66f6c..6f307f21fc65 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -113,6 +113,9 @@ struct fwnode_operations { bool (*device_is_available)(const struct fwnode_handle *fwnode); const void *(*device_get_match_data)(const struct fwnode_handle *fwnode, const struct device *dev); + bool (*device_dma_supported)(const struct fwnode_handle *fwnode); + enum dev_dma_attr + (*device_get_dma_attr)(const struct fwnode_handle *fwnode); bool (*property_present)(const struct fwnode_handle *fwnode, const char *propname); int (*property_read_int_array)(const struct fwnode_handle *fwnode, -- cgit v1.2.3 From 68b979d068d3d0dceb14c446f664433d96f20a7e Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Thu, 31 Mar 2022 15:54:49 +0300 Subject: device property: Add iomap to fwnode operations Add iomap() fwnode operation to implement fwnode_iomap() through fwnode operations, moving the code in fwnode_iomap() to OF framework. Note that the IS_ENABLED(CONFIG_OF_ADDRESS) && is_of_node(fwnode) check is needed for Sparc that has its own implementation of of_iomap anyway. Let the pre-compiler to handle that check. Signed-off-by: Sakari Ailus Reviewed-by: Andy Shevchenko Reviewed-by: Heikki Krogerus Signed-off-by: Rafael J. Wysocki --- include/linux/fwnode.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 6f307f21fc65..ebbc3bf03f95 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -148,6 +148,7 @@ struct fwnode_operations { (*graph_get_port_parent)(struct fwnode_handle *fwnode); int (*graph_parse_endpoint)(const struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint); + void __iomem *(*iomap)(struct fwnode_handle *fwnode, int index); int (*add_links)(struct fwnode_handle *fwnode); }; -- cgit v1.2.3 From 99c63707bafd15bcf97fbd6bef1c92d5bfa01d28 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Thu, 31 Mar 2022 15:54:50 +0300 Subject: device property: Add irq_get to fwnode operation Add irq_get() fwnode operation to implement fwnode_irq_get() through fwnode operations, moving the code in fwnode_irq_get() to OF and ACPI frameworks. Signed-off-by: Sakari Ailus Acked-by: Rob Herring Reviewed-by: Andy Shevchenko Reviewed-by: Heikki Krogerus Signed-off-by: Rafael J. Wysocki --- include/linux/fwnode.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index ebbc3bf03f95..6ab69871b06d 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -149,6 +149,7 @@ struct fwnode_operations { int (*graph_parse_endpoint)(const struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint); void __iomem *(*iomap)(struct fwnode_handle *fwnode, int index); + int (*irq_get)(const struct fwnode_handle *fwnode, unsigned int index); int (*add_links)(struct fwnode_handle *fwnode); }; -- cgit v1.2.3 From cdb4f26a63c391317e335e6e683a614358e70aeb Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 6 Jan 2022 14:31:51 +0100 Subject: kobject: kobj_type: remove default_attrs Now that all in-kernel users of default_attrs for the kobj_type are gone and converted to properly use the default_groups pointer instead, it can be safely removed. There is one standard way to create sysfs files in a kobj_type, and not two like before, causing confusion as to which should be used. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20220106133151.607703-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index c7b47399b36a..57fb972fea05 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -120,7 +120,6 @@ extern char *kobject_get_path(struct kobject *kobj, gfp_t flag); struct kobj_type { void (*release)(struct kobject *kobj); const struct sysfs_ops *sysfs_ops; - struct attribute **default_attrs; /* use default_groups instead */ const struct attribute_group **default_groups; const struct kobj_ns_type_operations *(*child_ns_type)(struct kobject *kobj); const void *(*namespace)(struct kobject *kobj); -- cgit v1.2.3 From 1be9473e31ab87ad1b6ecf9fd11df461930ede85 Mon Sep 17 00:00:00 2001 From: Aaron Tomlin Date: Tue, 22 Mar 2022 14:03:34 +0000 Subject: module: Move livepatch support to a separate file No functional change. This patch migrates livepatch support (i.e. used during module add/or load and remove/or deletion) from core module code into kernel/module/livepatch.c. At the moment it contains code to persist Elf information about a given livepatch module, only. The new file was added to MAINTAINERS. Reviewed-by: Petr Mladek Tested-by: Petr Mladek Signed-off-by: Aaron Tomlin Signed-off-by: Luis Chamberlain --- include/linux/module.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index 1e135fd5c076..7ec9715de7dc 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -663,17 +663,14 @@ static inline bool module_requested_async_probing(struct module *module) return module && module->async_probe_requested; } -#ifdef CONFIG_LIVEPATCH static inline bool is_livepatch_module(struct module *mod) { +#ifdef CONFIG_LIVEPATCH return mod->klp; -} -#else /* !CONFIG_LIVEPATCH */ -static inline bool is_livepatch_module(struct module *mod) -{ +#else return false; +#endif } -#endif /* CONFIG_LIVEPATCH */ bool is_module_sig_enforced(void); void set_module_sig_enforced(void); -- cgit v1.2.3 From 0c1e42805c25c87eb7a6f3b18bdbf3b3b7840aff Mon Sep 17 00:00:00 2001 From: Aaron Tomlin Date: Tue, 22 Mar 2022 14:03:37 +0000 Subject: module: Move extra signature support out of core code No functional change. This patch migrates additional module signature check code from core module code into kernel/module/signing.c. Reviewed-by: Christophe Leroy Signed-off-by: Aaron Tomlin Signed-off-by: Luis Chamberlain --- include/linux/module.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index 7ec9715de7dc..5e2059f3afc7 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -672,7 +672,6 @@ static inline bool is_livepatch_module(struct module *mod) #endif } -bool is_module_sig_enforced(void); void set_module_sig_enforced(void); #else /* !CONFIG_MODULES... */ @@ -799,10 +798,6 @@ static inline bool module_requested_async_probing(struct module *module) return false; } -static inline bool is_module_sig_enforced(void) -{ - return false; -} static inline void set_module_sig_enforced(void) { @@ -854,11 +849,18 @@ static inline bool retpoline_module_ok(bool has_retpoline) #endif #ifdef CONFIG_MODULE_SIG +bool is_module_sig_enforced(void); + static inline bool module_sig_ok(struct module *module) { return module->sig_ok; } #else /* !CONFIG_MODULE_SIG */ +static inline bool is_module_sig_enforced(void) +{ + return false; +} + static inline bool module_sig_ok(struct module *module) { return true; -- cgit v1.2.3 From f64205a42046d3802c423fa2059e7fca39af127c Mon Sep 17 00:00:00 2001 From: Aaron Tomlin Date: Tue, 22 Mar 2022 14:03:43 +0000 Subject: module: Move kdb module related code out of main kdb code No functional change. This patch migrates the kdb 'lsmod' command support out of main kdb code into its own file under kernel/module. In addition to the above, a minor style warning i.e. missing a blank line after declarations, was resolved too. The new file was added to MAINTAINERS. Finally we remove linux/module.h as it is entirely redundant. Reviewed-by: Daniel Thompson Acked-by: Daniel Thompson Signed-off-by: Aaron Tomlin Signed-off-by: Luis Chamberlain --- include/linux/kdb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/kdb.h b/include/linux/kdb.h index ea0f5e580fac..07dfb6a20a1c 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -222,5 +222,6 @@ enum { extern int kdbgetintenv(const char *, int *); extern int kdb_set(int, const char **); +int kdb_lsmod(int argc, const char **argv); #endif /* !_KDB_H */ -- cgit v1.2.3 From 01dc0386efb769056257410ba5754558384006a7 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Wed, 23 Feb 2022 13:02:14 +0100 Subject: module: Add CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC Add CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC to allow architectures to request having modules data in vmalloc area instead of module area. This is required on powerpc book3s/32 in order to set data non executable, because it is not possible to set executability on page basis, this is done per 256 Mbytes segments. The module area has exec right, vmalloc area has noexec. This can also be useful on other powerpc/32 in order to maximize the chance of code being close enough to kernel core to avoid branch trampolines. Cc: Jason Wessel Acked-by: Daniel Thompson Cc: Douglas Anderson Signed-off-by: Christophe Leroy [mcgrof: rebased in light of kernel/module/kdb.c move] Signed-off-by: Luis Chamberlain --- include/linux/module.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index 5e2059f3afc7..46d4d5f2516e 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -422,6 +422,9 @@ struct module { /* Core layout: rbtree is accessed frequently, so keep together. */ struct module_layout core_layout __module_layout_align; struct module_layout init_layout; +#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC + struct module_layout data_layout; +#endif /* Arch-specific module values */ struct mod_arch_specific arch; @@ -569,6 +572,11 @@ bool is_module_text_address(unsigned long addr); static inline bool within_module_core(unsigned long addr, const struct module *mod) { +#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC + if ((unsigned long)mod->data_layout.base <= addr && + addr < (unsigned long)mod->data_layout.base + mod->data_layout.size) + return true; +#endif return (unsigned long)mod->core_layout.base <= addr && addr < (unsigned long)mod->core_layout.base + mod->core_layout.size; } -- cgit v1.2.3 From baa914cd81f51f4e4f3bae5bb59764b32ad8c353 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Tue, 5 Apr 2022 16:22:20 +0900 Subject: firewire: add kernel API to access CYCLE_TIME register 1394 OHCI specification defined Isochronous Cycle Timer Register to get value of CYCLE_TIME register defined by IEEE 1394 for CSR architecture defined by ISO/IEC 13213. Unit driver can calculate packet time by compute with the value of CYCLE_TIME and timeStamp field in descriptor of each isochronous and asynchronous context. The resolution of CYCLE_TIME is 49.576 MHz, while the one of timeStamp is 8,000 Hz. Current implementation of Linux FireWire subsystem allows the driver to get the value of CYCLE_TIMER CSR register by transaction service. The transaction service has overhead in regard of access to MMIO register. This commit adds kernel API for unit driver to access the register directly. Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20220405072221.226217-3-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- include/linux/firewire.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 07967a450eaa..2f467c52bdec 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -150,6 +150,8 @@ static inline void fw_card_put(struct fw_card *card) kref_put(&card->kref, fw_card_release); } +int fw_card_read_cycle_time(struct fw_card *card, u32 *cycle_time); + struct fw_attribute_group { struct attribute_group *groups[2]; struct attribute_group group; -- cgit v1.2.3 From b2405aa948b95afc5246fa56fc05c3512cd6185c Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Tue, 5 Apr 2022 16:22:21 +0900 Subject: firewire: add kernel API to access packet structure in request structure for AR context In 1394 OHCI specification, descriptor of Asynchronous Receive DMA context has timeStamp field in its trailer quadlet. The field is written by the host controller for the time to receive asynchronous request subaction in isochronous cycle time. In Linux FireWire subsystem, the value of field is stored to fw_packet structure and copied to fw_request structure as the part. The fw_request structure is hidden from unit driver and passed as opaque pointer when calling registered handler. It's inconvenient to the unit driver which needs timestamp of packet. This commit adds kernel API to pick up timestamp from opaque pointer to fw_request structure. Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20220405072221.226217-4-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- include/linux/firewire.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 2f467c52bdec..980019053e54 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -354,6 +354,7 @@ void fw_core_remove_address_handler(struct fw_address_handler *handler); void fw_send_response(struct fw_card *card, struct fw_request *request, int rcode); int fw_get_request_speed(struct fw_request *request); +u32 fw_request_get_timestamp(const struct fw_request *request); void fw_send_request(struct fw_card *card, struct fw_transaction *t, int tcode, int destination_id, int generation, int speed, unsigned long long offset, void *payload, size_t length, -- cgit v1.2.3 From bc8cb02976cd602b8d7631a6f4a54a9cf305d38c Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Tue, 5 Apr 2022 14:54:15 +0100 Subject: ASoC: soc.h: Add SOC_SINGLE_S_TLV() macro Add a convenience macro for defining a single (mono) TLV control with a signed value. This can already be done by using SOC_DOUBLE_R_S_TLV() with the same address for left and right registers, but a dedicated macro is more readable. Signed-off-by: Richard Fitzgerald Link: https://lore.kernel.org/r/20220405135419.1230088-2-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- include/sound/soc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index d3d3a26e8867..55fb6a6d7d25 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -176,6 +176,8 @@ .get = snd_soc_get_volsw, .put = snd_soc_put_volsw, \ .private_value = SOC_DOUBLE_R_S_VALUE(reg_left, reg_right, xshift, \ xmin, xmax, xsign_bit, xinvert) } +#define SOC_SINGLE_S_TLV(xname, xreg, xshift, xmin, xmax, xsign_bit, xinvert, tlv_array) \ + SOC_DOUBLE_R_S_TLV(xname, xreg, xreg, xshift, xmin, xmax, xsign_bit, xinvert, tlv_array) #define SOC_SINGLE_S8_TLV(xname, xreg, xmin, xmax, tlv_array) \ { .iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = (xname), \ .access = SNDRV_CTL_ELEM_ACCESS_TLV_READ | \ -- cgit v1.2.3 From 1ef34dd2b90d78a9830398441801658ef86eee9d Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Tue, 5 Apr 2022 14:54:16 +0100 Subject: ASoC: soc-utils: Add helper to calculate BCLK from TDM info Add a helper function snd_soc_tdm_params_to_bclk() to calculate the bclk from params info and the tdm sots configuration. When using a TDM frame of N slots of width W bits: bclk = sample_rate * N * W As a convenience to simplify calling code, if the slot count or slot width are 0 a value will be obtained from the params. This allows calling code to use this one function to handle cases of TDM where only one parameter is fixed, or I2S where the slot width is fixed (for example to set a 32-bit slot for 24-bit samples). Also as a convenience the slot count can optionally be rounded up to a multiple. This is mainly useful for I2S systems, since I2S has two phases of LRCLK the number of slots is always a multiple of 2. Signed-off-by: Richard Fitzgerald Link: https://lore.kernel.org/r/20220405135419.1230088-3-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- include/sound/soc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index 55fb6a6d7d25..2d3261799d2c 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -487,6 +487,8 @@ int snd_soc_calc_frame_size(int sample_size, int channels, int tdm_slots); int snd_soc_params_to_frame_size(struct snd_pcm_hw_params *params); int snd_soc_calc_bclk(int fs, int sample_size, int channels, int tdm_slots); int snd_soc_params_to_bclk(struct snd_pcm_hw_params *parms); +int snd_soc_tdm_params_to_bclk(struct snd_pcm_hw_params *params, + int tdm_width, int tdm_slots, int slot_multiple); /* set runtime hw params */ int snd_soc_set_runtime_hwparams(struct snd_pcm_substream *substream, -- cgit v1.2.3 From 72661ff7662acc00d51976d4b2d2d13eb5628385 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Tue, 5 Apr 2022 14:54:18 +0100 Subject: ASoC: dt-bindings: cs35l45: Cirrus Logic CS35L45 Smart Amp This adds the schema binding for the Cirrus Logic CS35L45 Smart Amp and associated header file. Signed-off-by: Richard Fitzgerald Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20220405135419.1230088-5-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- include/dt-bindings/sound/cs35l45.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100644 include/dt-bindings/sound/cs35l45.h (limited to 'include') diff --git a/include/dt-bindings/sound/cs35l45.h b/include/dt-bindings/sound/cs35l45.h new file mode 100644 index 000000000000..076da4b2c28d --- /dev/null +++ b/include/dt-bindings/sound/cs35l45.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* + * cs35l45.h -- CS35L45 ALSA SoC audio driver DT bindings header + * + * Copyright 2022 Cirrus Logic, Inc. + */ + +#ifndef DT_CS35L45_H +#define DT_CS35L45_H + +/* + * cirrus,asp-sdout-hiz-ctrl + * + * TX_HIZ_UNUSED: TX pin high-impedance during unused slots. + * TX_HIZ_DISABLED: TX pin high-impedance when all channels disabled. + */ +#define CS35L45_ASP_TX_HIZ_UNUSED 0x1 +#define CS35L45_ASP_TX_HIZ_DISABLED 0x2 + +#endif /* DT_CS35L45_H */ -- cgit v1.2.3 From ac2a3feefad549814f5e7cca30be07a255c8494a Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 5 Apr 2022 19:49:26 +0200 Subject: ACPI: bus: Eliminate acpi_bus_get_device() Replace the last instance of acpi_bus_get_device(), added recently by commit 87e59b36e5e2 ("spi: Support selection of the index of the ACPI Spi Resource before alloc"), with acpi_fetch_acpi_dev() and finally drop acpi_bus_get_device() that has no more users. Signed-off-by: Rafael J. Wysocki Acked-by: Mark Brown --- include/acpi/acpi_bus.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 3f7f01f03869..c4b78c21d793 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -509,7 +509,6 @@ extern int unregister_acpi_notifier(struct notifier_block *); * External Functions */ -int acpi_bus_get_device(acpi_handle handle, struct acpi_device **device); struct acpi_device *acpi_fetch_acpi_dev(acpi_handle handle); acpi_status acpi_bus_get_status_handle(acpi_handle handle, unsigned long long *sta); -- cgit v1.2.3 From d462f6ed2aeac30c0b440a91fb05d964956935f9 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 9 Mar 2022 21:21:55 +0100 Subject: ASoC: soc-core: add debugfs_prefix member to snd_soc_component_driver Allow the component debugfs_prefix to be set from snd_soc_component_driver. First use case is avoiding a duplicate debugfs entry error in case a device has multiple components which have the same name therefore. Note that we don't set component->debugfs_prefix if it's set already. That's needed because partially component->debugfs_prefix is set before calling snd_soc_component_initialize(). Signed-off-by: Heiner Kallweit Link: https://lore.kernel.org/r/d18bff6a-1df1-5f95-0cf8-10dbaa62d7be@gmail.com Signed-off-by: Mark Brown --- include/sound/soc-component.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/sound/soc-component.h b/include/sound/soc-component.h index a52080407b98..766dc6f009c0 100644 --- a/include/sound/soc-component.h +++ b/include/sound/soc-component.h @@ -179,6 +179,10 @@ struct snd_soc_component_driver { struct snd_pcm_hw_params *params); bool use_dai_pcm_id; /* use DAI link PCM ID as PCM device number */ int be_pcm_base; /* base device ID for all BE PCMs */ + +#ifdef CONFIG_DEBUG_FS + const char *debugfs_prefix; +#endif }; struct snd_soc_component { -- cgit v1.2.3 From a8e2512efc65892a1cbf608d9c03c8bcbe5a623a Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Fri, 1 Apr 2022 15:06:04 +0100 Subject: PM: core: Add NS varients of EXPORT[_GPL]_SIMPLE_DEV_PM_OPS and runtime pm equiv As more drivers start to use namespaces, we need to have varients of these useful macros that allow the export to be in a particular namespace. Signed-off-by: Jonathan Cameron Cc: Paul Cercueil Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 14 +++++++++----- include/linux/pm_runtime.h | 10 ++++++++-- 2 files changed, 17 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/pm.h b/include/linux/pm.h index e65b3ab28377..ffe941958501 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -368,13 +368,13 @@ const struct dev_pm_ops name = { \ #ifdef CONFIG_PM #define _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ - runtime_resume_fn, idle_fn, sec) \ + runtime_resume_fn, idle_fn, sec, ns) \ _DEFINE_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ runtime_resume_fn, idle_fn); \ - _EXPORT_SYMBOL(name, sec) + __EXPORT_SYMBOL(name, sec, ns) #else #define _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ - runtime_resume_fn, idle_fn, sec) \ + runtime_resume_fn, idle_fn, sec, ns) \ static __maybe_unused _DEFINE_DEV_PM_OPS(__static_##name, suspend_fn, \ resume_fn, runtime_suspend_fn, \ runtime_resume_fn, idle_fn) @@ -391,9 +391,13 @@ static __maybe_unused _DEFINE_DEV_PM_OPS(__static_##name, suspend_fn, \ _DEFINE_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL) #define EXPORT_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ - _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "") + _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "", "") #define EXPORT_GPL_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ - _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "_gpl") + _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "_gpl", "") +#define EXPORT_NS_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn, ns) \ + _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "", #ns) +#define EXPORT_NS_GPL_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn, ns) \ + _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "_gpl", #ns) /* Deprecated. Use DEFINE_SIMPLE_DEV_PM_OPS() instead. */ #define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 2bff6a10095d..9e4d056967c6 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -41,10 +41,16 @@ #define EXPORT_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ - suspend_fn, resume_fn, idle_fn, "") + suspend_fn, resume_fn, idle_fn, "", "") #define EXPORT_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ - suspend_fn, resume_fn, idle_fn, "_gpl") + suspend_fn, resume_fn, idle_fn, "_gpl", "") +#define EXPORT_NS_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ + _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ + suspend_fn, resume_fn, idle_fn, "", #ns) +#define EXPORT_NS_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ + _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ + suspend_fn, resume_fn, idle_fn, "_gpl", #ns) #ifdef CONFIG_PM extern struct workqueue_struct *pm_wq; -- cgit v1.2.3 From 0b5c21bbc01e92745ca1ca4f6fd87d878fa3ea5e Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 4 Apr 2022 11:38:47 +0200 Subject: net: ensure net_todo_list is processed quickly In [1], Will raised a potential issue that the cfg80211 code, which does (from a locking perspective) rtnl_lock() wiphy_lock() rtnl_unlock() might be suspectible to ABBA deadlocks, because rtnl_unlock() calls netdev_run_todo(), which might end up calling rtnl_lock() again, which could then deadlock (see the comment in the code added here for the scenario). Some back and forth and thinking ensued, but clearly this can't happen if the net_todo_list is empty at the rtnl_unlock() here. Clearly, the code here cannot actually put an entry on it, and all other users of rtnl_unlock() will empty it since that will always go through netdev_run_todo(), emptying the list. So the only other way to get there would be to add to the list and then unlock the RTNL without going through rtnl_unlock(), which is only possible through __rtnl_unlock(). However, this isn't exported and not used in many places, and none of them seem to be able to unregister before using it. Therefore, add a WARN_ON() in the code to ensure this invariant won't be broken, so that the cfg80211 (or any similar) code stays safe. [1] https://lore.kernel.org/r/Yjzpo3TfZxtKPMAG@google.com Signed-off-by: Johannes Berg Link: https://lore.kernel.org/r/20220404113847.0ee02e4a70da.Ic73d206e217db20fd22dcec14fe5442ca732804b@changeid Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 59e27a2b7bf0..b6a1e7f643da 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3894,7 +3894,8 @@ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev); extern int netdev_budget; extern unsigned int netdev_budget_usecs; -/* Called by rtnetlink.c:rtnl_unlock() */ +/* Used by rtnetlink.c:__rtnl_unlock()/rtnl_unlock() */ +extern struct list_head net_todo_list; void netdev_run_todo(void); static inline void __dev_put(struct net_device *dev) -- cgit v1.2.3 From 40379a0084c2f65eb62c102f5bbf5cdc14a50410 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 4 Apr 2022 15:08:15 +0300 Subject: net/mlx5_fpga: Drop INNOVA TLS support Mellanox INNOVA TLS cards are EOL in May, 2018 [1]. As such, the code is unmaintained, untested and not in-use by any upstream/distro oriented customers. In order to reduce code complexity, drop the kernel code. [1] https://network.nvidia.com/related-docs/eol/LCR-000286.pdf Link: https://lore.kernel.org/r/b88add368def721ea9d054cb69def72d9e3f67aa.1649073691.git.leonro@nvidia.com Reviewed-by: Tariq Toukan Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc_fpga.h | 63 -------------------------------------- 1 file changed, 63 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc_fpga.h b/include/linux/mlx5/mlx5_ifc_fpga.h index 07d77323f78a..e3d824f6a309 100644 --- a/include/linux/mlx5/mlx5_ifc_fpga.h +++ b/include/linux/mlx5/mlx5_ifc_fpga.h @@ -54,7 +54,6 @@ enum { enum { MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_IPSEC = 0x2, - MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_TLS = 0x3, }; struct mlx5_ifc_fpga_shell_caps_bits { @@ -387,27 +386,6 @@ struct mlx5_ifc_fpga_destroy_qp_out_bits { u8 reserved_at_40[0x40]; }; -struct mlx5_ifc_tls_extended_cap_bits { - u8 aes_gcm_128[0x1]; - u8 aes_gcm_256[0x1]; - u8 reserved_at_2[0x1e]; - u8 reserved_at_20[0x20]; - u8 context_capacity_total[0x20]; - u8 context_capacity_rx[0x20]; - u8 context_capacity_tx[0x20]; - u8 reserved_at_a0[0x10]; - u8 tls_counter_size[0x10]; - u8 tls_counters_addr_low[0x20]; - u8 tls_counters_addr_high[0x20]; - u8 rx[0x1]; - u8 tx[0x1]; - u8 tls_v12[0x1]; - u8 tls_v13[0x1]; - u8 lro[0x1]; - u8 ipv6[0x1]; - u8 reserved_at_106[0x1a]; -}; - struct mlx5_ifc_ipsec_extended_cap_bits { u8 encapsulation[0x20]; @@ -572,45 +550,4 @@ struct mlx5_ifc_fpga_ipsec_sa { __be16 vid; /* only 12 bits, rest is reserved */ __be16 reserved2; } __packed; - -enum fpga_tls_cmds { - CMD_SETUP_STREAM = 0x1001, - CMD_TEARDOWN_STREAM = 0x1002, - CMD_RESYNC_RX = 0x1003, -}; - -#define MLX5_TLS_1_2 (0) - -#define MLX5_TLS_ALG_AES_GCM_128 (0) -#define MLX5_TLS_ALG_AES_GCM_256 (1) - -struct mlx5_ifc_tls_cmd_bits { - u8 command_type[0x20]; - u8 ipv6[0x1]; - u8 direction_sx[0x1]; - u8 tls_version[0x2]; - u8 reserved[0x1c]; - u8 swid[0x20]; - u8 src_port[0x10]; - u8 dst_port[0x10]; - union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits src_ipv4_src_ipv6; - union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits dst_ipv4_dst_ipv6; - u8 tls_rcd_sn[0x40]; - u8 tcp_sn[0x20]; - u8 tls_implicit_iv[0x20]; - u8 tls_xor_iv[0x40]; - u8 encryption_key[0x100]; - u8 alg[4]; - u8 reserved2[0x1c]; - u8 reserved3[0x4a0]; -}; - -struct mlx5_ifc_tls_resp_bits { - u8 syndrome[0x20]; - u8 stream_id[0x20]; - u8 reserved[0x40]; -}; - -#define MLX5_TLS_COMMAND_SIZE (0x100) - #endif /* MLX5_IFC_FPGA_H */ -- cgit v1.2.3 From 0276bd3a94c072de3f69b5afe6224e488cc76635 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 5 Apr 2022 17:15:16 +0200 Subject: IB/mlx5: Fix undefined behavior due to shift overflowing the constant MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix: drivers/infiniband/hw/mlx5/main.c: In function ‘translate_eth_legacy_proto_oper’: drivers/infiniband/hw/mlx5/main.c:370:2: error: case label does not reduce to an integer constant case MLX5E_PROT_MASK(MLX5E_50GBASE_KR2): ^~~~ See https://lore.kernel.org/r/YkwQ6%2BtIH8GQpuct@zn.tnic for the gory details as to why it triggers with older gccs only. Link: https://lore.kernel.org/all/20220405151517.29753-11-bp@alien8.de Signed-off-by: Borislav Petkov Cc: Leon Romanovsky Cc: Saeed Mahameed Cc: linux-rdma@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Leon Romanovsky --- include/linux/mlx5/port.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 28a928b0684b..e96ee1e348cb 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -141,7 +141,7 @@ enum mlx5_ptys_width { MLX5_PTYS_WIDTH_12X = 1 << 4, }; -#define MLX5E_PROT_MASK(link_mode) (1 << link_mode) +#define MLX5E_PROT_MASK(link_mode) (1U << link_mode) #define MLX5_GET_ETH_PROTO(reg, out, ext, field) \ (ext ? MLX5_GET(reg, out, ext_##field) : \ MLX5_GET(reg, out, field)) -- cgit v1.2.3 From a285909f471d6703a04b2b3942c352e27131c92b Mon Sep 17 00:00:00 2001 From: Hyeonggon Yoo <42.hyeyoo@gmail.com> Date: Wed, 6 Apr 2022 15:00:03 +0900 Subject: mm/slub, kunit: Make slub_kunit unaffected by user specified flags slub_kunit does not expect other debugging flags to be set when running tests. When SLAB_RED_ZONE flag is set globally, test fails because the flag affects number of errors reported. To make slub_kunit unaffected by user specified debugging flags, introduce SLAB_NO_USER_FLAGS to ignore them. With this flag, only flags specified in the code are used and others are ignored. Suggested-by: Vlastimil Babka Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Signed-off-by: Vlastimil Babka Link: https://lore.kernel.org/r/Yk0sY9yoJhFEXWOg@hyeyoo --- include/linux/slab.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/slab.h b/include/linux/slab.h index 373b3ef99f4e..11ceddcae9f4 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -112,6 +112,13 @@ #define SLAB_KASAN 0 #endif +/* + * Ignore user specified debugging flags. + * Intended for caches created for self-tests so they have only flags + * specified in the code and other flags are ignored. + */ +#define SLAB_NO_USER_FLAGS ((slab_flags_t __force)0x10000000U) + /* The following flags affect the page allocator grouping pages by mobility */ /* Objects are reclaimable */ #define SLAB_RECLAIM_ACCOUNT ((slab_flags_t __force)0x00020000U) -- cgit v1.2.3 From a5f1783be29adae15666fd803efd7d2979130869 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Wed, 2 Mar 2022 12:02:22 +0100 Subject: lib/stackdepot: allow requesting early initialization dynamically In a later patch we want to add stackdepot support for object owner tracking in slub caches, which is enabled by slub_debug boot parameter. This creates a bootstrap problem as some caches are created early in boot when slab_is_available() is false and thus stack_depot_init() tries to use memblock. But, as reported by Hyeonggon Yoo [1] we are already beyond memblock_free_all(). Ideally memblock allocation should fail, yet it succeeds, but later the system crashes, which is a separately handled issue. To resolve this boostrap issue in a robust way, this patch adds another way to request stack_depot_early_init(), which happens at a well-defined point of time. In addition to build-time CONFIG_STACKDEPOT_ALWAYS_INIT, code that's e.g. processing boot parameters (which happens early enough) can call a new function stack_depot_want_early_init(), which sets a flag that stack_depot_early_init() will check. In this patch we also convert page_owner to this approach. While it doesn't have the bootstrap issue as slub, it's also a functionality enabled by a boot param and can thus request stack_depot_early_init() with memblock allocation instead of later initialization with kvmalloc(). As suggested by Mike, make stack_depot_early_init() only attempt memblock allocation and stack_depot_init() only attempt kvmalloc(). Also change the latter to kvcalloc(). In both cases we can lose the explicit array zeroing, which the allocations do already. As suggested by Marco, provide empty implementations of the init functions for !CONFIG_STACKDEPOT builds to simplify the callers. [1] https://lore.kernel.org/all/YhnUcqyeMgCrWZbd@ip-172-31-19-208.ap-northeast-1.compute.internal/ Reported-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Suggested-by: Mike Rapoport Suggested-by: Marco Elver Signed-off-by: Vlastimil Babka Reviewed-by: Marco Elver Reviewed-and-tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Reviewed-by: Mike Rapoport Acked-by: David Rientjes --- include/linux/stackdepot.h | 26 ++++++++++++++++++++++---- 1 file changed, 22 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 17f992fe6355..bc2797955de9 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -20,18 +20,36 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries, gfp_t gfp_flags, bool can_alloc); /* - * Every user of stack depot has to call this during its own init when it's - * decided that it will be calling stack_depot_save() later. + * Every user of stack depot has to call stack_depot_init() during its own init + * when it's decided that it will be calling stack_depot_save() later. This is + * recommended for e.g. modules initialized later in the boot process, when + * slab_is_available() is true. * * The alternative is to select STACKDEPOT_ALWAYS_INIT to have stack depot * enabled as part of mm_init(), for subsystems where it's known at compile time * that stack depot will be used. + * + * Another alternative is to call stack_depot_want_early_init(), when the + * decision to use stack depot is taken e.g. when evaluating kernel boot + * parameters, which precedes the enablement point in mm_init(). + * + * stack_depot_init() and stack_depot_want_early_init() can be called regardless + * of CONFIG_STACKDEPOT and are no-op when disabled. The actual save/fetch/print + * functions should only be called from code that makes sure CONFIG_STACKDEPOT + * is enabled. */ +#ifdef CONFIG_STACKDEPOT int stack_depot_init(void); -#ifdef CONFIG_STACKDEPOT_ALWAYS_INIT -static inline int stack_depot_early_init(void) { return stack_depot_init(); } +void __init stack_depot_want_early_init(void); + +/* This is supposed to be called only from mm_init() */ +int __init stack_depot_early_init(void); #else +static inline int stack_depot_init(void) { return 0; } + +static inline void stack_depot_want_early_init(void) { } + static inline int stack_depot_early_init(void) { return 0; } #endif -- cgit v1.2.3 From f742b90e61bb53b27771f64bdae05db03a6ab1f2 Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Thu, 24 Feb 2022 10:55:49 -0600 Subject: x86/mm: Extend cc_attr to include AMD SEV-SNP The CC_ATTR_GUEST_SEV_SNP can be used by the guest to query whether the SNP (Secure Nested Paging) feature is active. Signed-off-by: Brijesh Singh Signed-off-by: Borislav Petkov Link: https://lore.kernel.org/r/20220307213356.2797205-10-brijesh.singh@amd.com --- include/linux/cc_platform.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h index efd8205282da..d08dd65b5c43 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -72,6 +72,14 @@ enum cc_attr { * Examples include TDX guest & SEV. */ CC_ATTR_GUEST_UNROLL_STRING_IO, + + /** + * @CC_ATTR_SEV_SNP: Guest SNP is active. + * + * The platform/OS is running as a guest/virtual machine and actively + * using AMD SEV-SNP features. + */ + CC_ATTR_GUEST_SEV_SNP, }; #ifdef CONFIG_ARCH_HAS_CC_PLATFORM -- cgit v1.2.3 From 697a1d44af8ba0477ee729e632f4ade37999249a Mon Sep 17 00:00:00 2001 From: Steve Capper Date: Wed, 30 Mar 2022 12:25:43 +0100 Subject: tlb: hugetlb: Add more sizes to tlb_remove_huge_tlb_entry tlb_remove_huge_tlb_entry only considers PMD_SIZE and PUD_SIZE when updating the mmu_gather structure. Unfortunately on arm64 there are two additional huge page sizes that need to be covered: CONT_PTE_SIZE and CONT_PMD_SIZE. Where an end-user attempts to employ contiguous huge pages, a VM_BUG_ON can be experienced due to the fact that the tlb structure hasn't been correctly updated by the relevant tlb_flush_p.._range() call from tlb_remove_huge_tlb_entry. This patch adds inequality logic to the generic implementation of tlb_remove_huge_tlb_entry s.t. CONT_PTE_SIZE and CONT_PMD_SIZE are effectively covered on arm64. Also, as well as ptes, pmds and puds; p4ds are now considered too. Reported-by: David Hildenbrand Suggested-by: Peter Zijlstra (Intel) Cc: Anshuman Khandual Cc: Catalin Marinas Cc: Will Deacon Link: https://lore.kernel.org/linux-mm/811c5c8e-b3a2-85d2-049c-717f17c3a03a@redhat.com/ Signed-off-by: Steve Capper Acked-by: David Hildenbrand Reviewed-by: Anshuman Khandual Reviewed-by: Catalin Marinas Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220330112543.863-1-steve.capper@arm.com Signed-off-by: Will Deacon --- include/asm-generic/tlb.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index fd7feb5c7894..eee6f7763a39 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -565,10 +565,14 @@ static inline void tlb_flush_p4d_range(struct mmu_gather *tlb, #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \ do { \ unsigned long _sz = huge_page_size(h); \ - if (_sz == PMD_SIZE) \ - tlb_flush_pmd_range(tlb, address, _sz); \ - else if (_sz == PUD_SIZE) \ + if (_sz >= P4D_SIZE) \ + tlb_flush_p4d_range(tlb, address, _sz); \ + else if (_sz >= PUD_SIZE) \ tlb_flush_pud_range(tlb, address, _sz); \ + else if (_sz >= PMD_SIZE) \ + tlb_flush_pmd_range(tlb, address, _sz); \ + else \ + tlb_flush_pte_range(tlb, address, _sz); \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) -- cgit v1.2.3 From f4b41f062c424209e3939a81e6da022e049a45f2 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Mon, 4 Apr 2022 18:30:22 +0200 Subject: net: remove noblock parameter from skb_recv_datagram() skb_recv_datagram() has two parameters 'flags' and 'noblock' that are merged inside skb_recv_datagram() by 'flags | (noblock ? MSG_DONTWAIT : 0)' As 'flags' may contain MSG_DONTWAIT as value most callers split the 'flags' into 'flags' and 'noblock' with finally obsolete bit operations like this: skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &rc); And this is not even done consistently with the 'flags' parameter. This patch removes the obsolete and costly splitting into two parameters and only performs bit operations when really needed on the caller side. One missing conversion thankfully reported by kernel test robot. I missed to enable kunit tests to build the mctp code. Reported-by: kernel test robot Signed-off-by: Oliver Hartkopp Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3a30cae8b0a5..2394441fa3dd 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3836,8 +3836,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, struct sk_buff *__skb_recv_datagram(struct sock *sk, struct sk_buff_head *sk_queue, unsigned int flags, int *off, int *err); -struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock, - int *err); +struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, int *err); __poll_t datagram_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int skb_copy_datagram_iter(const struct sk_buff *from, int offset, -- cgit v1.2.3 From 1ee375d77bb944321c969b456aa73994566cecf6 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Mon, 4 Apr 2022 10:54:47 -0700 Subject: net, uapi: remove inclusion of arpa/inet.h In include/uapi/linux/tipc_config.h, there's a comment that it includes arpa/inet.h for ntohs; but ntohs is not defined in any UAPI header. For now, reuse the definitions from include/linux/byteorder/generic.h, since the various conversion functions do exist in UAPI headers: include/uapi/linux/byteorder/big_endian.h include/uapi/linux/byteorder/little_endian.h We would like to get to the point where we can build UAPI header tests with -nostdinc, meaning that kernel UAPI headers should not have a circular dependency on libc headers. Link: https://android-review.googlesource.com/c/platform/bionic/+/2048127 Suggested-by: Jakub Kicinski Signed-off-by: Nick Desaulniers Signed-off-by: David S. Miller --- include/uapi/linux/tipc_config.h | 28 ++++++++++++---------------- 1 file changed, 12 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/tipc_config.h b/include/uapi/linux/tipc_config.h index 4dfc05651c98..c00adf2fe868 100644 --- a/include/uapi/linux/tipc_config.h +++ b/include/uapi/linux/tipc_config.h @@ -43,10 +43,6 @@ #include #include -#ifndef __KERNEL__ -#include /* for ntohs etc. */ -#endif - /* * Configuration * @@ -269,33 +265,33 @@ static inline int TLV_OK(const void *tlv, __u16 space) */ return (space >= TLV_SPACE(0)) && - (ntohs(((struct tlv_desc *)tlv)->tlv_len) <= space); + (__be16_to_cpu(((struct tlv_desc *)tlv)->tlv_len) <= space); } static inline int TLV_CHECK(const void *tlv, __u16 space, __u16 exp_type) { return TLV_OK(tlv, space) && - (ntohs(((struct tlv_desc *)tlv)->tlv_type) == exp_type); + (__be16_to_cpu(((struct tlv_desc *)tlv)->tlv_type) == exp_type); } static inline int TLV_GET_LEN(struct tlv_desc *tlv) { - return ntohs(tlv->tlv_len); + return __be16_to_cpu(tlv->tlv_len); } static inline void TLV_SET_LEN(struct tlv_desc *tlv, __u16 len) { - tlv->tlv_len = htons(len); + tlv->tlv_len = __cpu_to_be16(len); } static inline int TLV_CHECK_TYPE(struct tlv_desc *tlv, __u16 type) { - return (ntohs(tlv->tlv_type) == type); + return (__be16_to_cpu(tlv->tlv_type) == type); } static inline void TLV_SET_TYPE(struct tlv_desc *tlv, __u16 type) { - tlv->tlv_type = htons(type); + tlv->tlv_type = __cpu_to_be16(type); } static inline int TLV_SET(void *tlv, __u16 type, void *data, __u16 len) @@ -305,8 +301,8 @@ static inline int TLV_SET(void *tlv, __u16 type, void *data, __u16 len) tlv_len = TLV_LENGTH(len); tlv_ptr = (struct tlv_desc *)tlv; - tlv_ptr->tlv_type = htons(type); - tlv_ptr->tlv_len = htons(tlv_len); + tlv_ptr->tlv_type = __cpu_to_be16(type); + tlv_ptr->tlv_len = __cpu_to_be16(tlv_len); if (len && data) { memcpy(TLV_DATA(tlv_ptr), data, len); memset((char *)TLV_DATA(tlv_ptr) + len, 0, TLV_SPACE(len) - tlv_len); @@ -348,7 +344,7 @@ static inline void *TLV_LIST_DATA(struct tlv_list_desc *list) static inline void TLV_LIST_STEP(struct tlv_list_desc *list) { - __u16 tlv_space = TLV_ALIGN(ntohs(list->tlv_ptr->tlv_len)); + __u16 tlv_space = TLV_ALIGN(__be16_to_cpu(list->tlv_ptr->tlv_len)); list->tlv_ptr = (struct tlv_desc *)((char *)list->tlv_ptr + tlv_space); list->tlv_space -= tlv_space; @@ -404,9 +400,9 @@ static inline int TCM_SET(void *msg, __u16 cmd, __u16 flags, msg_len = TCM_LENGTH(data_len); tcm_hdr = (struct tipc_cfg_msg_hdr *)msg; - tcm_hdr->tcm_len = htonl(msg_len); - tcm_hdr->tcm_type = htons(cmd); - tcm_hdr->tcm_flags = htons(flags); + tcm_hdr->tcm_len = __cpu_to_be32(msg_len); + tcm_hdr->tcm_type = __cpu_to_be16(cmd); + tcm_hdr->tcm_flags = __cpu_to_be16(flags); if (data_len && data) { memcpy(TCM_DATA(msg), data, data_len); memset((char *)TCM_DATA(msg) + data_len, 0, TCM_SPACE(data_len) - msg_len); -- cgit v1.2.3 From fe696ccb277d332dc4e625b5b20b988b04d16c04 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 3 Apr 2022 15:53:54 -0700 Subject: gpu: host1x: Fix a kernel-doc warning Add @cache description to eliminate a kernel-doc warning. include/linux/host1x.h:104: warning: Function parameter or member 'cache' not described in 'host1x_client' Fixes: 1f39b1dfa53c ("drm/tegra: Implement buffer object cache") Signed-off-by: Randy Dunlap Cc: Thierry Reding Cc: linux-tegra@vger.kernel.org Cc: David Airlie Cc: Daniel Vetter Cc: dri-devel@lists.freedesktop.org Signed-off-by: Thierry Reding --- include/linux/host1x.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/host1x.h b/include/linux/host1x.h index e8dc5bc41f79..00278853eadf 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -81,6 +81,7 @@ struct host1x_client_ops { * @parent: pointer to parent structure * @usecount: reference count for this structure * @lock: mutex for mutually exclusive concurrency + * @cache: host1x buffer object cache */ struct host1x_client { struct list_head list; -- cgit v1.2.3 From 804775dfc2885e93a0a4b35db1914c2cc25172b5 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Tue, 5 Apr 2022 21:57:47 +0200 Subject: net: ethernet: mtk_eth_soc: add support for Wireless Ethernet Dispatch (WED) The Wireless Ethernet Dispatch subsystem on the MT7622 SoC can be configured to intercept and handle access to the DMA queues and PCIe interrupts for a MT7615/MT7915 wireless card. It can manage the internal WDMA (Wireless DMA) controller, which allows ethernet packets to be passed from the packet switch engine (PSE) to the wireless card, bypassing the CPU entirely. This can be used to implement hardware flow offloading from ethernet to WLAN. Signed-off-by: Felix Fietkau Signed-off-by: David S. Miller --- include/linux/soc/mediatek/mtk_wed.h | 131 +++++++++++++++++++++++++++++++++++ 1 file changed, 131 insertions(+) create mode 100644 include/linux/soc/mediatek/mtk_wed.h (limited to 'include') diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h new file mode 100644 index 000000000000..7e00cca06709 --- /dev/null +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -0,0 +1,131 @@ +#ifndef __MTK_WED_H +#define __MTK_WED_H + +#include +#include +#include +#include + +#define MTK_WED_TX_QUEUES 2 + +struct mtk_wed_hw; +struct mtk_wdma_desc; + +struct mtk_wed_ring { + struct mtk_wdma_desc *desc; + dma_addr_t desc_phys; + int size; + + u32 reg_base; + void __iomem *wpdma; +}; + +struct mtk_wed_device { +#ifdef CONFIG_NET_MEDIATEK_SOC_WED + const struct mtk_wed_ops *ops; + struct device *dev; + struct mtk_wed_hw *hw; + bool init_done, running; + int wdma_idx; + int irq; + + struct mtk_wed_ring tx_ring[MTK_WED_TX_QUEUES]; + struct mtk_wed_ring txfree_ring; + struct mtk_wed_ring tx_wdma[MTK_WED_TX_QUEUES]; + + struct { + int size; + void **pages; + struct mtk_wdma_desc *desc; + dma_addr_t desc_phys; + } buf_ring; + + /* filled by driver: */ + struct { + struct pci_dev *pci_dev; + + u32 wpdma_phys; + + u16 token_start; + unsigned int nbuf; + + u32 (*init_buf)(void *ptr, dma_addr_t phys, int token_id); + int (*offload_enable)(struct mtk_wed_device *wed); + void (*offload_disable)(struct mtk_wed_device *wed); + } wlan; +#endif +}; + +struct mtk_wed_ops { + int (*attach)(struct mtk_wed_device *dev); + int (*tx_ring_setup)(struct mtk_wed_device *dev, int ring, + void __iomem *regs); + int (*txfree_ring_setup)(struct mtk_wed_device *dev, + void __iomem *regs); + void (*detach)(struct mtk_wed_device *dev); + + void (*stop)(struct mtk_wed_device *dev); + void (*start)(struct mtk_wed_device *dev, u32 irq_mask); + void (*reset_dma)(struct mtk_wed_device *dev); + + u32 (*reg_read)(struct mtk_wed_device *dev, u32 reg); + void (*reg_write)(struct mtk_wed_device *dev, u32 reg, u32 val); + + u32 (*irq_get)(struct mtk_wed_device *dev, u32 mask); + void (*irq_set_mask)(struct mtk_wed_device *dev, u32 mask); +}; + +extern const struct mtk_wed_ops __rcu *mtk_soc_wed_ops; + +static inline int +mtk_wed_device_attach(struct mtk_wed_device *dev) +{ + int ret = -ENODEV; + +#ifdef CONFIG_NET_MEDIATEK_SOC_WED + rcu_read_lock(); + dev->ops = rcu_dereference(mtk_soc_wed_ops); + if (dev->ops) + ret = dev->ops->attach(dev); + else + rcu_read_unlock(); + + if (ret) + dev->ops = NULL; +#endif + + return ret; +} + +#ifdef CONFIG_NET_MEDIATEK_SOC_WED +#define mtk_wed_device_active(_dev) !!(_dev)->ops +#define mtk_wed_device_detach(_dev) (_dev)->ops->detach(_dev) +#define mtk_wed_device_start(_dev, _mask) (_dev)->ops->start(_dev, _mask) +#define mtk_wed_device_tx_ring_setup(_dev, _ring, _regs) \ + (_dev)->ops->tx_ring_setup(_dev, _ring, _regs) +#define mtk_wed_device_txfree_ring_setup(_dev, _regs) \ + (_dev)->ops->txfree_ring_setup(_dev, _regs) +#define mtk_wed_device_reg_read(_dev, _reg) \ + (_dev)->ops->reg_read(_dev, _reg) +#define mtk_wed_device_reg_write(_dev, _reg, _val) \ + (_dev)->ops->reg_write(_dev, _reg, _val) +#define mtk_wed_device_irq_get(_dev, _mask) \ + (_dev)->ops->irq_get(_dev, _mask) +#define mtk_wed_device_irq_set_mask(_dev, _mask) \ + (_dev)->ops->irq_set_mask(_dev, _mask) +#else +static inline bool mtk_wed_device_active(struct mtk_wed_device *dev) +{ + return false; +} +#define mtk_wed_device_detach(_dev) do {} while (0) +#define mtk_wed_device_start(_dev, _mask) do {} while (0) +#define mtk_wed_device_tx_ring_setup(_dev, _ring, _regs) -ENODEV +#define mtk_wed_device_txfree_ring_setup(_dev, _ring, _regs) -ENODEV +#define mtk_wed_device_reg_read(_dev, _reg) 0 +#define mtk_wed_device_reg_write(_dev, _reg, _val) do {} while (0) +#define mtk_wed_device_irq_get(_dev, _mask) 0 +#define mtk_wed_device_irq_set_mask(_dev, _mask) do {} while (0) +#endif + +#endif -- cgit v1.2.3 From a333215e10cb5d3b1e0685ca117f0e9452215485 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Tue, 5 Apr 2022 21:57:48 +0200 Subject: net: ethernet: mtk_eth_soc: implement flow offloading to WED devices This allows hardware flow offloading from Ethernet to WLAN on MT7622 SoC Co-developed-by: Lorenzo Bianconi Signed-off-by: Lorenzo Bianconi Signed-off-by: Felix Fietkau Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b6a1e7f643da..7b2a0b739684 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -862,6 +862,7 @@ enum net_device_path_type { DEV_PATH_BRIDGE, DEV_PATH_PPPOE, DEV_PATH_DSA, + DEV_PATH_MTK_WDMA, }; struct net_device_path { @@ -887,6 +888,12 @@ struct net_device_path { int port; u16 proto; } dsa; + struct { + u8 wdma_idx; + u8 queue; + u16 wcid; + u8 bss; + } mtk_wdma; }; }; -- cgit v1.2.3 From 3e9c4584336149146fe15cb5703fc10a2ca2d2a0 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 24 Mar 2022 11:30:25 +0100 Subject: gpu: host1x: Do not use mapping cache for job submissions Buffer mappings used in job submissions are usually small and not rapidly reused as opposed to framebuffers (which are usually large and rapidly reused, for example when page-flipping between double-buffered framebuffers). Avoid going through the mapping cache for these buffers since the cache would also lead to leaks if nobody is ever releasing the cache's last reference. For DRM/KMS these last references are dropped when the framebuffers are removed and therefore no longer needed. While at it, also add a note about the need to explicitly remove the final reference to the mapping in the cache. Reviewed-by: Jon Hunter Tested-by: Jon Hunter Signed-off-by: Thierry Reding --- include/linux/host1x.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 00278853eadf..c0bf4e581fe9 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -31,6 +31,11 @@ u64 host1x_get_dma_mask(struct host1x *host1x); * struct host1x_bo_cache - host1x buffer object cache * @mappings: list of mappings * @lock: synchronizes accesses to the list of mappings + * + * Note that entries are not periodically evicted from this cache and instead need to be + * explicitly released. This is used primarily for DRM/KMS where the cache's reference is + * released when the last reference to a buffer object represented by a mapping in this + * cache is dropped. */ struct host1x_bo_cache { struct list_head mappings; -- cgit v1.2.3 From 20b734c11243ecf97030345b51ff37fcb7dd060f Mon Sep 17 00:00:00 2001 From: Sui Jingfeng <15330273260@189.cn> Date: Wed, 6 Apr 2022 15:30:36 +0800 Subject: drm/drm_modeset_helper_vtables.h: fix a typo change upate to update Signed-off-by: Sui Jingfeng <15330273260@189.cn> Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220406073036.276288-1-15330273260@189.cn --- include/drm/drm_modeset_helper_vtables.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h index fdfa9f37ce05..fafa70ac1337 100644 --- a/include/drm/drm_modeset_helper_vtables.h +++ b/include/drm/drm_modeset_helper_vtables.h @@ -1384,7 +1384,7 @@ struct drm_mode_config_helper_funcs { * starting to commit the update to the hardware. * * After the atomic update is committed to the hardware this hook needs - * to call drm_atomic_helper_commit_hw_done(). Then wait for the upate + * to call drm_atomic_helper_commit_hw_done(). Then wait for the update * to be executed by the hardware, for example using * drm_atomic_helper_wait_for_vblanks() or * drm_atomic_helper_wait_for_flip_done(), and then clean up the old -- cgit v1.2.3 From 71f69ffa0129bf04205edf0e7dc73dc4777b2588 Mon Sep 17 00:00:00 2001 From: Ashish Singhal Date: Wed, 9 Mar 2022 00:00:26 +0530 Subject: arm64: tegra: Add QSPI controllers on Tegra234 This adds the QSPI controllers on the Tegra234 SoC and populates the SPI NOR flash device for the Jetson AGX Orin platform. Signed-off-by: Ashish Singhal Signed-off-by: Jon Hunter Signed-off-by: Krishna Yarlagadda Reviewed-by: Jon Hunter Acked-by: Rob Herring Signed-off-by: Thierry Reding --- include/dt-bindings/clock/tegra234-clock.h | 8 ++++++++ include/dt-bindings/reset/tegra234-reset.h | 2 ++ 2 files changed, 10 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/clock/tegra234-clock.h b/include/dt-bindings/clock/tegra234-clock.h index 8cae969e8cba..bd4c3086a2da 100644 --- a/include/dt-bindings/clock/tegra234-clock.h +++ b/include/dt-bindings/clock/tegra234-clock.h @@ -140,6 +140,14 @@ #define TEGRA234_CLK_PEX2_C9_CORE 173U /** @brief output of gate CLK_ENB_PEX2_CORE_10 */ #define TEGRA234_CLK_PEX2_C10_CORE 187U +/** @brief CLK_RST_CONTROLLER_CLK_SOURCE_QSPI0 switch divider output */ +#define TEGRA234_CLK_QSPI0_2X_PM 192U +/** @brief CLK_RST_CONTROLLER_CLK_SOURCE_QSPI1 switch divider output */ +#define TEGRA234_CLK_QSPI1_2X_PM 193U +/** @brief output of the divider QSPI_CLK_DIV2_SEL in CLK_RST_CONTROLLER_CLK_SOURCE_QSPI0 */ +#define TEGRA234_CLK_QSPI0_PM 194U +/** @brief output of the divider QSPI_CLK_DIV2_SEL in CLK_RST_CONTROLLER_CLK_SOURCE_QSPI1 */ +#define TEGRA234_CLK_QSPI1_PM 195U /** @brief CLK_RST_CONTROLLER_CLK_SOURCE_SDMMC_LEGACY_TM switch divider output */ #define TEGRA234_CLK_SDMMC_LEGACY_TM 219U /** @brief output of gate CLK_ENB_PEX0_CORE_0 */ diff --git a/include/dt-bindings/reset/tegra234-reset.h b/include/dt-bindings/reset/tegra234-reset.h index 1362cd5e03f0..547ca3b60caa 100644 --- a/include/dt-bindings/reset/tegra234-reset.h +++ b/include/dt-bindings/reset/tegra234-reset.h @@ -40,6 +40,8 @@ #define TEGRA234_RESET_PWM6 73U #define TEGRA234_RESET_PWM7 74U #define TEGRA234_RESET_PWM8 75U +#define TEGRA234_RESET_QSPI0 76U +#define TEGRA234_RESET_QSPI1 77U #define TEGRA234_RESET_SDMMC4 85U #define TEGRA234_RESET_UARTA 100U #define TEGRA234_RESET_PEX0_CORE_0 116U -- cgit v1.2.3 From c8d4c18bfbc4ab467188dbe45cc8155759f49d9e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Tue, 16 Nov 2021 15:20:45 +0100 Subject: dma-buf/drivers: make reserving a shared slot mandatory v4 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Audit all the users of dma_resv_add_excl_fence() and make sure they reserve a shared slot also when only trying to add an exclusive fence. This is the next step towards handling the exclusive fence like a shared one. v2: fix missed case in amdgpu v3: and two more radeon, rename function v4: add one more case to TTM, fix i915 after rebase Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220406075132.3263-2-christian.koenig@amd.com --- include/linux/dma-resv.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index ecb697d4d861..5fa04d0fccad 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -117,7 +117,7 @@ struct dma_resv { * A new fence is added by calling dma_resv_add_shared_fence(). Since * this often needs to be done past the point of no return in command * submission it cannot fail, and therefore sufficient slots need to be - * reserved by calling dma_resv_reserve_shared(). + * reserved by calling dma_resv_reserve_fences(). * * Note that actual semantics of what an exclusive or shared fence mean * is defined by the user, for reservation objects shared across drivers @@ -413,7 +413,7 @@ static inline void dma_resv_unlock(struct dma_resv *obj) void dma_resv_init(struct dma_resv *obj); void dma_resv_fini(struct dma_resv *obj); -int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences); +int dma_resv_reserve_fences(struct dma_resv *obj, unsigned int num_fences); void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence); void dma_resv_replace_fences(struct dma_resv *obj, uint64_t context, struct dma_fence *fence); -- cgit v1.2.3 From 773f91b2cf3f52df0d7508fdbf60f37567cdaee4 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 1 Apr 2022 17:08:21 -0400 Subject: SUNRPC: Fix NFSD's request deferral on RDMA transports Trond Myklebust reports an NFSD crash in svc_rdma_sendto(). Further investigation shows that the crash occurred while NFSD was handling a deferred request. This patch addresses two inter-related issues that prevent request deferral from working correctly for RPC/RDMA requests: 1. Prevent the crash by ensuring that the original svc_rqst::rq_xprt_ctxt value is available when the request is revisited. Otherwise svc_rdma_sendto() does not have a Receive context available with which to construct its reply. 2. Possibly since before commit 71641d99ce03 ("svcrdma: Properly compute .len and .buflen for received RPC Calls"), svc_rdma_recvfrom() did not include the transport header in the returned xdr_buf. There should have been no need for svc_defer() and friends to save and restore that header, as of that commit. This issue is addressed in a backport-friendly way by simply having svc_rdma_recvfrom() set rq_xprt_hlen to zero unconditionally, just as svc_tcp_recvfrom() does. This enables svc_deferred_recv() to correctly reconstruct an RPC message received via RPC/RDMA. Reported-by: Trond Myklebust Link: https://lore.kernel.org/linux-nfs/82662b7190f26fb304eb0ab1bb04279072439d4e.camel@hammerspace.com/ Signed-off-by: Chuck Lever Cc: --- include/linux/sunrpc/svc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index a5dda4987e8b..217711fc9cac 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -395,6 +395,7 @@ struct svc_deferred_req { size_t addrlen; struct sockaddr_storage daddr; /* where reply must come from */ size_t daddrlen; + void *xprt_ctxt; struct cache_deferred_req handle; size_t xprt_hlen; int argslen; -- cgit v1.2.3 From e945c653c8e972d1b81a88e474d79f801b60213a Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 4 Apr 2022 12:26:42 -0300 Subject: RDMA: Split kernel-only global device caps from uverbs device caps Split out flags from ib_device::device_cap_flags that are only used internally to the kernel into kernel_cap_flags that is not part of the uapi. This limits the device_cap_flags to being the same bitmap that will be copied to userspace. This cleanly splits out the uverbs flags from the kernel flags to avoid confusion in the flags bitmap. Add some short comments describing which each of the kernel flags is connected to. Remove unused kernel flags. Link: https://lore.kernel.org/r/0-v2-22c19e565eef+139a-kern_caps_jgg@nvidia.com Reviewed-by: Christoph Hellwig Reviewed-by: Max Gurtovoy Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 88 ++++++++++++++++----------------------- include/rdma/opa_vnic.h | 3 +- include/uapi/rdma/ib_user_verbs.h | 4 ++ 3 files changed, 42 insertions(+), 53 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index ada4a5226dbd..b3bb4dd068b6 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -236,14 +236,6 @@ enum ib_device_cap_flags { IB_DEVICE_SRQ_RESIZE = IB_UVERBS_DEVICE_SRQ_RESIZE, IB_DEVICE_N_NOTIFY_CQ = IB_UVERBS_DEVICE_N_NOTIFY_CQ, - /* - * This device supports a per-device lkey or stag that can be - * used without performing a memory registration for the local - * memory. Note that ULPs should never check this flag, but - * instead of use the local_dma_lkey flag in the ib_pd structure, - * which will always contain a usable lkey. - */ - IB_DEVICE_LOCAL_DMA_LKEY = 1 << 15, /* Reserved, old SEND_W_INV = 1 << 16,*/ IB_DEVICE_MEM_WINDOW = IB_UVERBS_DEVICE_MEM_WINDOW, /* @@ -254,7 +246,6 @@ enum ib_device_cap_flags { * IPoIB driver may set NETIF_F_IP_CSUM for datagram mode. */ IB_DEVICE_UD_IP_CSUM = IB_UVERBS_DEVICE_UD_IP_CSUM, - IB_DEVICE_UD_TSO = 1 << 19, IB_DEVICE_XRC = IB_UVERBS_DEVICE_XRC, /* @@ -267,59 +258,53 @@ enum ib_device_cap_flags { * stag. */ IB_DEVICE_MEM_MGT_EXTENSIONS = IB_UVERBS_DEVICE_MEM_MGT_EXTENSIONS, - IB_DEVICE_BLOCK_MULTICAST_LOOPBACK = 1 << 22, IB_DEVICE_MEM_WINDOW_TYPE_2A = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2A, IB_DEVICE_MEM_WINDOW_TYPE_2B = IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2B, IB_DEVICE_RC_IP_CSUM = IB_UVERBS_DEVICE_RC_IP_CSUM, /* Deprecated. Please use IB_RAW_PACKET_CAP_IP_CSUM. */ IB_DEVICE_RAW_IP_CSUM = IB_UVERBS_DEVICE_RAW_IP_CSUM, - /* - * Devices should set IB_DEVICE_CROSS_CHANNEL if they - * support execution of WQEs that involve synchronization - * of I/O operations with single completion queue managed - * by hardware. - */ - IB_DEVICE_CROSS_CHANNEL = 1 << 27, IB_DEVICE_MANAGED_FLOW_STEERING = IB_UVERBS_DEVICE_MANAGED_FLOW_STEERING, - IB_DEVICE_INTEGRITY_HANDOVER = 1 << 30, - IB_DEVICE_ON_DEMAND_PAGING = 1ULL << 31, - IB_DEVICE_SG_GAPS_REG = 1ULL << 32, - IB_DEVICE_VIRTUAL_FUNCTION = 1ULL << 33, /* Deprecated. Please use IB_RAW_PACKET_CAP_SCATTER_FCS. */ IB_DEVICE_RAW_SCATTER_FCS = IB_UVERBS_DEVICE_RAW_SCATTER_FCS, - IB_DEVICE_RDMA_NETDEV_OPA = 1ULL << 35, /* The device supports padding incoming writes to cacheline. */ IB_DEVICE_PCI_WRITE_END_PADDING = IB_UVERBS_DEVICE_PCI_WRITE_END_PADDING, - IB_DEVICE_ALLOW_USER_UNREG = 1ULL << 37, -}; - -#define IB_UVERBS_DEVICE_CAP_FLAGS_MASK (IB_UVERBS_DEVICE_RESIZE_MAX_WR | \ - IB_UVERBS_DEVICE_BAD_PKEY_CNTR | \ - IB_UVERBS_DEVICE_BAD_QKEY_CNTR | \ - IB_UVERBS_DEVICE_RAW_MULTI | \ - IB_UVERBS_DEVICE_AUTO_PATH_MIG | \ - IB_UVERBS_DEVICE_CHANGE_PHY_PORT | \ - IB_UVERBS_DEVICE_UD_AV_PORT_ENFORCE | \ - IB_UVERBS_DEVICE_CURR_QP_STATE_MOD | \ - IB_UVERBS_DEVICE_SHUTDOWN_PORT | \ - IB_UVERBS_DEVICE_PORT_ACTIVE_EVENT | \ - IB_UVERBS_DEVICE_SYS_IMAGE_GUID | \ - IB_UVERBS_DEVICE_RC_RNR_NAK_GEN | \ - IB_UVERBS_DEVICE_SRQ_RESIZE | \ - IB_UVERBS_DEVICE_N_NOTIFY_CQ | \ - IB_UVERBS_DEVICE_MEM_WINDOW | \ - IB_UVERBS_DEVICE_UD_IP_CSUM | \ - IB_UVERBS_DEVICE_XRC | \ - IB_UVERBS_DEVICE_MEM_MGT_EXTENSIONS | \ - IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2A | \ - IB_UVERBS_DEVICE_MEM_WINDOW_TYPE_2B | \ - IB_UVERBS_DEVICE_RC_IP_CSUM | \ - IB_UVERBS_DEVICE_RAW_IP_CSUM | \ - IB_UVERBS_DEVICE_MANAGED_FLOW_STEERING | \ - IB_UVERBS_DEVICE_RAW_SCATTER_FCS | \ - IB_UVERBS_DEVICE_PCI_WRITE_END_PADDING) +}; + +enum ib_kernel_cap_flags { + /* + * This device supports a per-device lkey or stag that can be + * used without performing a memory registration for the local + * memory. Note that ULPs should never check this flag, but + * instead of use the local_dma_lkey flag in the ib_pd structure, + * which will always contain a usable lkey. + */ + IBK_LOCAL_DMA_LKEY = 1 << 0, + /* IB_QP_CREATE_INTEGRITY_EN is supported to implement T10-PI */ + IBK_INTEGRITY_HANDOVER = 1 << 1, + /* IB_ACCESS_ON_DEMAND is supported during reg_user_mr() */ + IBK_ON_DEMAND_PAGING = 1 << 2, + /* IB_MR_TYPE_SG_GAPS is supported */ + IBK_SG_GAPS_REG = 1 << 3, + /* Driver supports RDMA_NLDEV_CMD_DELLINK */ + IBK_ALLOW_USER_UNREG = 1 << 4, + + /* ipoib will use IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK */ + IBK_BLOCK_MULTICAST_LOOPBACK = 1 << 5, + /* iopib will use IB_QP_CREATE_IPOIB_UD_LSO for its QPs */ + IBK_UD_TSO = 1 << 6, + /* iopib will use the device ops: + * get_vf_config + * get_vf_guid + * get_vf_stats + * set_vf_guid + * set_vf_link_state + */ + IBK_VIRTUAL_FUNCTION = 1 << 7, + /* ipoib will use IB_QP_CREATE_NETDEV_USE for its QPs */ + IBK_RDMA_NETDEV_OPA = 1 << 8, +}; enum ib_atomic_cap { IB_ATOMIC_NONE, @@ -417,6 +402,7 @@ struct ib_device_attr { int max_qp; int max_qp_wr; u64 device_cap_flags; + u64 kernel_cap_flags; int max_send_sge; int max_recv_sge; int max_sge_rd; @@ -4344,7 +4330,7 @@ static inline int ib_check_mr_access(struct ib_device *ib_dev, return -EINVAL; if (flags & IB_ACCESS_ON_DEMAND && - !(ib_dev->attrs.device_cap_flags & IB_DEVICE_ON_DEMAND_PAGING)) + !(ib_dev->attrs.kernel_cap_flags & IBK_ON_DEMAND_PAGING)) return -EINVAL; return 0; } diff --git a/include/rdma/opa_vnic.h b/include/rdma/opa_vnic.h index cbe3c2811455..f3d5377b217a 100644 --- a/include/rdma/opa_vnic.h +++ b/include/rdma/opa_vnic.h @@ -90,8 +90,7 @@ struct opa_vnic_stats { static inline bool rdma_cap_opa_vnic(struct ib_device *device) { - return !!(device->attrs.device_cap_flags & - IB_DEVICE_RDMA_NETDEV_OPA); + return !!(device->attrs.kernel_cap_flags & IBK_RDMA_NETDEV_OPA); } #endif /* _OPA_VNIC_H */ diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index 06a4897c4958..7dd903d932e5 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -1298,6 +1298,10 @@ struct ib_uverbs_ex_modify_cq { #define IB_DEVICE_NAME_MAX 64 +/* + * bits 9, 15, 16, 19, 22, 27, 30, 31, 32, 33, 35 and 37 may be set by old + * kernels and should not be used. + */ enum ib_uverbs_device_cap_flags { IB_UVERBS_DEVICE_RESIZE_MAX_WR = 1 << 0, IB_UVERBS_DEVICE_BAD_PKEY_CNTR = 1 << 1, -- cgit v1.2.3 From 40570375356c874b1578e05c1dcc3ff7c1322dbe Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 5 Apr 2022 16:35:38 -0700 Subject: tcp: add accessors to read/set tp->snd_cwnd We had various bugs over the years with code breaking the assumption that tp->snd_cwnd is greater than zero. Lately, syzbot reported the WARN_ON_ONCE(!tp->prior_cwnd) added in commit 8b8a321ff72c ("tcp: fix zero cwnd in tcp_cwnd_reduction") can trigger, and without a repro we would have to spend considerable time finding the bug. Instead of complaining too late, we want to catch where and when tp->snd_cwnd is set to an illegal value. Signed-off-by: Eric Dumazet Suggested-by: Yuchung Cheng Cc: Neal Cardwell Acked-by: Yuchung Cheng Link: https://lore.kernel.org/r/20220405233538.947344-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 19 +++++++++++++++---- include/trace/events/tcp.h | 2 +- 2 files changed, 16 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 70ca4a5e330a..54aa2f02bb63 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1207,9 +1207,20 @@ static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp) #define TCP_INFINITE_SSTHRESH 0x7fffffff +static inline u32 tcp_snd_cwnd(const struct tcp_sock *tp) +{ + return tp->snd_cwnd; +} + +static inline void tcp_snd_cwnd_set(struct tcp_sock *tp, u32 val) +{ + WARN_ON_ONCE((int)val <= 0); + tp->snd_cwnd = val; +} + static inline bool tcp_in_slow_start(const struct tcp_sock *tp) { - return tp->snd_cwnd < tp->snd_ssthresh; + return tcp_snd_cwnd(tp) < tp->snd_ssthresh; } static inline bool tcp_in_initial_slowstart(const struct tcp_sock *tp) @@ -1235,8 +1246,8 @@ static inline __u32 tcp_current_ssthresh(const struct sock *sk) return tp->snd_ssthresh; else return max(tp->snd_ssthresh, - ((tp->snd_cwnd >> 1) + - (tp->snd_cwnd >> 2))); + ((tcp_snd_cwnd(tp) >> 1) + + (tcp_snd_cwnd(tp) >> 2))); } /* Use define here intentionally to get WARN_ON location shown at the caller */ @@ -1278,7 +1289,7 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk) /* If in slow start, ensure cwnd grows to twice what was ACKed. */ if (tcp_in_slow_start(tp)) - return tp->snd_cwnd < 2 * tp->max_packets_out; + return tcp_snd_cwnd(tp) < 2 * tp->max_packets_out; return tp->is_cwnd_limited; } diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index 521059d8dc0a..edcd6369de10 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -279,7 +279,7 @@ TRACE_EVENT(tcp_probe, __entry->data_len = skb->len - __tcp_hdrlen(th); __entry->snd_nxt = tp->snd_nxt; __entry->snd_una = tp->snd_una; - __entry->snd_cwnd = tp->snd_cwnd; + __entry->snd_cwnd = tcp_snd_cwnd(tp); __entry->snd_wnd = tp->snd_wnd; __entry->rcv_wnd = tp->rcv_wnd; __entry->ssthresh = tcp_current_ssthresh(sk); -- cgit v1.2.3 From a60707d74bd1d119cf7bcc5101cda912fc46d5e3 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:45:57 +0800 Subject: sched: Move child_runs_first sysctls to fair.c move child_runs_first sysctls to fair.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index c1076b5e17fb..1d2ff3cd1728 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -14,8 +14,6 @@ extern unsigned long sysctl_hung_task_timeout_secs; enum { sysctl_hung_task_timeout_secs = 0 }; #endif -extern unsigned int sysctl_sched_child_runs_first; - enum sched_tunable_scaling { SCHED_TUNABLESCALING_NONE, SCHED_TUNABLESCALING_LOG, -- cgit v1.2.3 From f5ef06d58be8311a9425e6a54a053ecb350952f3 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:45:58 +0800 Subject: sched: Move schedstats sysctls to core.c move schedstats sysctls to core.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 1d2ff3cd1728..6c7a6850559b 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -64,8 +64,6 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos); #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) extern unsigned int sysctl_sched_energy_aware; -- cgit v1.2.3 From d9ab0e63fa7f8405fbb19e28c5191e0880a7f2db Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:45:59 +0800 Subject: sched: Move rt_period/runtime sysctls to rt.c move rt_period/runtime sysctls to rt.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 6c7a6850559b..4391c1307945 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -31,15 +31,6 @@ extern int sysctl_numa_balancing_mode; #define sysctl_numa_balancing_mode 0 #endif -/* - * control realtime throttling: - * - * /proc/sys/kernel/sched_rt_period_us - * /proc/sys/kernel/sched_rt_runtime_us - */ -extern unsigned int sysctl_sched_rt_period; -extern int sysctl_sched_rt_runtime; - extern unsigned int sysctl_sched_dl_period_max; extern unsigned int sysctl_sched_dl_period_min; @@ -58,8 +49,6 @@ extern int sched_rr_timeslice; int sched_rr_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int sched_rt_handler(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos); int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, -- cgit v1.2.3 From 84227c12888b1105725cd2de14705b029bcbb4b2 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:46:00 +0800 Subject: sched: Move deadline_period sysctls to deadline.c move deadline_period sysctls to deadline.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 4391c1307945..7da9b94c5e1c 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -31,9 +31,6 @@ extern int sysctl_numa_balancing_mode; #define sysctl_numa_balancing_mode 0 #endif -extern unsigned int sysctl_sched_dl_period_max; -extern unsigned int sysctl_sched_dl_period_min; - #ifdef CONFIG_UCLAMP_TASK extern unsigned int sysctl_sched_uclamp_util_min; extern unsigned int sysctl_sched_uclamp_util_max; -- cgit v1.2.3 From dafd7a9dad22fadcb290b24dff54e2eae3b89776 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:46:01 +0800 Subject: sched: Move rr_timeslice sysctls to rt.c move rr_timeslice sysctls to rt.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 7da9b94c5e1c..3d307e512d1f 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -41,11 +41,6 @@ extern unsigned int sysctl_sched_uclamp_util_min_rt_default; extern unsigned int sysctl_sched_cfs_bandwidth_slice; #endif -extern int sysctl_sched_rr_timeslice; -extern int sched_rr_timeslice; - -int sched_rr_handler(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos); int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, -- cgit v1.2.3 From 3267e0156c3341ac25b37a0f60551cdae1634b60 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:46:02 +0800 Subject: sched: Move uclamp_util sysctls to core.c move uclamp_util sysctls to core.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 3d307e512d1f..0934b21a57a4 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -31,18 +31,10 @@ extern int sysctl_numa_balancing_mode; #define sysctl_numa_balancing_mode 0 #endif -#ifdef CONFIG_UCLAMP_TASK -extern unsigned int sysctl_sched_uclamp_util_min; -extern unsigned int sysctl_sched_uclamp_util_max; -extern unsigned int sysctl_sched_uclamp_util_min_rt_default; -#endif - #ifdef CONFIG_CFS_BANDWIDTH extern unsigned int sysctl_sched_cfs_bandwidth_slice; #endif -int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -- cgit v1.2.3 From d4ae80ffa64f87b9c355692b680b603add084e96 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:46:03 +0800 Subject: sched: Move cfs_bandwidth_slice sysctls to fair.c move cfs_bandwidth_slice sysctls to fair.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 0934b21a57a4..198f77c8a873 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -31,10 +31,6 @@ extern int sysctl_numa_balancing_mode; #define sysctl_numa_balancing_mode 0 #endif -#ifdef CONFIG_CFS_BANDWIDTH -extern unsigned int sysctl_sched_cfs_bandwidth_slice; -#endif - int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -- cgit v1.2.3 From 8a0441415b3f9b9a920a6a5086580ea3daa7b884 Mon Sep 17 00:00:00 2001 From: Zhen Ni Date: Tue, 15 Feb 2022 19:46:04 +0800 Subject: sched: Move energy_aware sysctls to topology.c move energy_aware sysctls to topology.c and use the new register_sysctl_init() to register the sysctl interface. Signed-off-by: Zhen Ni Signed-off-by: Luis Chamberlain --- include/linux/sched/sysctl.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 198f77c8a873..e650946816d0 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -34,10 +34,4 @@ extern int sysctl_numa_balancing_mode; int sysctl_numa_balancing(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) -extern unsigned int sysctl_sched_energy_aware; -int sched_energy_aware_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -#endif - #endif /* _LINUX_SCHED_SYSCTL_H */ -- cgit v1.2.3 From 06d177662fb86b80c7fc2290667b9a14cb0bd925 Mon Sep 17 00:00:00 2001 From: tangmeng Date: Thu, 17 Feb 2022 12:23:21 +0800 Subject: kernel/reboot: move reboot sysctls to its own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. All filesystem syctls now get reviewed by fs folks. This commit follows the commit of fs, move the poweroff_cmd and ctrl-alt-del sysctls to its own file, kernel/reboot.c. Signed-off-by: tangmeng Signed-off-by: Luis Chamberlain --- include/linux/reboot.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/reboot.h b/include/linux/reboot.h index af907a3d68d1..a2429648d831 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -71,12 +71,8 @@ extern void kernel_restart(char *cmd); extern void kernel_halt(void); extern void kernel_power_off(void); -extern int C_A_D; /* for sysctl */ void ctrl_alt_del(void); -#define POWEROFF_CMD_PATH_LEN 256 -extern char poweroff_cmd[POWEROFF_CMD_PATH_LEN]; - extern void orderly_poweroff(bool force); extern void orderly_reboot(void); void hw_protection_shutdown(const char *reason, int ms_until_forced); -- cgit v1.2.3 From 43fe219aa56a2fdd8f0623c9470a32b14b0617a5 Mon Sep 17 00:00:00 2001 From: sujiaxun Date: Thu, 17 Feb 2022 18:51:48 -0800 Subject: mm: move oom_kill sysctls to their own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. So move the oom_kill sysctls to their own file, mm/oom_kill.c [sfr@canb.auug.org.au: null-terminate the array] Link: https://lkml.kernel.org/r/20220216193202.28838626@canb.auug.org.au Link: https://lkml.kernel.org/r/20220215093203.31032-1-sujiaxun@uniontech.com Signed-off-by: sujiaxun Signed-off-by: Stephen Rothwell Cc: Kees Cook Cc: Iurii Zaikin Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Luis Chamberlain --- include/linux/oom.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/oom.h b/include/linux/oom.h index 2db9a1432511..02d1e7bbd8cd 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -123,8 +123,4 @@ extern void oom_killer_enable(void); extern struct task_struct *find_lock_task_mm(struct task_struct *p); -/* sysctls */ -extern int sysctl_oom_dump_tasks; -extern int sysctl_oom_kill_allocating_task; -extern int sysctl_panic_on_oom; #endif /* _INCLUDE_LINUX_OOM_H */ -- cgit v1.2.3 From aa779e5102195e1d9ade95dcbc0bfbd8f916eb59 Mon Sep 17 00:00:00 2001 From: zhanglianjie Date: Thu, 17 Feb 2022 18:51:51 -0800 Subject: mm: move page-writeback sysctls to their own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. So move the page-writeback sysctls to its own file. [akpm@linux-foundation.org: coding-style cleanups] akpm@linux-foundation.org: fix CONFIG_SYSCTL=n warnings] Link: https://lkml.kernel.org/r/20220129012955.26594-1-zhanglianjie@uniontech.com Signed-off-by: zhanglianjie Cc: Kees Cook Cc: Iurii Zaikin Cc: Luis Chamberlain Signed-off-by: Andrew Morton Signed-off-by: Luis Chamberlain --- include/linux/writeback.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index fec248ab1fec..dc2b94e6a94f 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -345,28 +345,13 @@ void wb_domain_exit(struct wb_domain *dom); extern struct wb_domain global_wb_domain; /* These are exported to sysctl. */ -extern int dirty_background_ratio; -extern unsigned long dirty_background_bytes; -extern int vm_dirty_ratio; -extern unsigned long vm_dirty_bytes; extern unsigned int dirty_writeback_interval; extern unsigned int dirty_expire_interval; extern unsigned int dirtytime_expire_interval; -extern int vm_highmem_is_dirtyable; extern int laptop_mode; -int dirty_background_ratio_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -int dirty_background_bytes_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -int dirty_ratio_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -int dirty_bytes_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); int dirtytime_interval_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int dirty_writeback_centisecs_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh); -- cgit v1.2.3 From f79c9b8ae8bde10126586c1bb55b5fd027276d8e Mon Sep 17 00:00:00 2001 From: tangmeng Date: Fri, 18 Feb 2022 18:58:57 +0800 Subject: kernel/lockdep: move lockdep sysctls to its own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. All filesystem syctls now get reviewed by fs folks. This commit follows the commit of fs, move the prove_locking and lock_stat sysctls to its own file, kernel/lockdep.c. Signed-off-by: tangmeng Signed-off-by: Luis Chamberlain --- include/linux/lockdep.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 467b94257105..37951c17908e 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -16,10 +16,6 @@ struct task_struct; -/* for sysctl */ -extern int prove_locking; -extern int lock_stat; - #ifdef CONFIG_LOCKDEP #include -- cgit v1.2.3 From 9df918698408fd914493aba0b7858fef50eba63a Mon Sep 17 00:00:00 2001 From: tangmeng Date: Fri, 18 Feb 2022 18:59:12 +0800 Subject: kernel/panic: move panic sysctls to its own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. All filesystem syctls now get reviewed by fs folks. This commit follows the commit of fs, move the oops_all_cpu_backtrace sysctl to its own file, kernel/panic.c. Signed-off-by: tangmeng Signed-off-by: Luis Chamberlain --- include/linux/panic.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/panic.h b/include/linux/panic.h index f5844908a089..e71161da69c4 100644 --- a/include/linux/panic.h +++ b/include/linux/panic.h @@ -15,12 +15,6 @@ extern void oops_enter(void); extern void oops_exit(void); extern bool oops_may_print(void); -#ifdef CONFIG_SMP -extern unsigned int sysctl_oops_all_cpu_backtrace; -#else -#define sysctl_oops_all_cpu_backtrace 0 -#endif /* CONFIG_SMP */ - extern int panic_timeout; extern unsigned long panic_print; extern int panic_on_oops; -- cgit v1.2.3 From 801b501439d1b366d524dee4fc1e6b3473a95b9a Mon Sep 17 00:00:00 2001 From: tangmeng Date: Fri, 18 Feb 2022 18:59:23 +0800 Subject: kernel/acct: move acct sysctls to its own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. All filesystem syctls now get reviewed by fs folks. This commit follows the commit of fs, move the acct sysctl to its own file, kernel/acct.c. Signed-off-by: tangmeng Signed-off-by: Luis Chamberlain --- include/linux/acct.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/acct.h b/include/linux/acct.h index bc70e81895c0..2718c4854815 100644 --- a/include/linux/acct.h +++ b/include/linux/acct.h @@ -21,7 +21,6 @@ #ifdef CONFIG_BSD_PROCESS_ACCT struct pid_namespace; -extern int acct_parm[]; /* for sysctl */ extern void acct_collect(long exitcode, int group_dead); extern void acct_process(void); extern void acct_exit_ns(struct pid_namespace *); -- cgit v1.2.3 From 1186618a6a35d43a865448472a261184b608d13c Mon Sep 17 00:00:00 2001 From: tangmeng Date: Fri, 18 Feb 2022 18:59:36 +0800 Subject: kernel/delayacct: move delayacct sysctls to its own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. All filesystem syctls now get reviewed by fs folks. This commit follows the commit of fs, move the delayacct sysctl to its own file, kernel/delayacct.c. Signed-off-by: tangmeng Signed-off-by: Luis Chamberlain --- include/linux/delayacct.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 3e03d010bd2e..6b16a6930a19 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -61,9 +61,6 @@ extern int delayacct_on; /* Delay accounting turned on/off */ extern struct kmem_cache *delayacct_cache; extern void delayacct_init(void); -extern int sysctl_delayacct(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos); - extern void __delayacct_tsk_init(struct task_struct *); extern void __delayacct_tsk_exit(struct task_struct *); extern void __delayacct_blkio_start(void); -- cgit v1.2.3 From d772cc2c321900f3f463a124eebeb7218e66dda6 Mon Sep 17 00:00:00 2001 From: tangmeng Date: Fri, 18 Feb 2022 18:59:49 +0800 Subject: kernel/do_mount_initrd: move real_root_dev sysctls to its own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. All filesystem syctls now get reviewed by fs folks. This commit follows the commit of fs, move the real_root_dev sysctl to its own file, kernel/do_mount_initrd.c. Signed-off-by: tangmeng Signed-off-by: Luis Chamberlain --- include/linux/initrd.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/initrd.h b/include/linux/initrd.h index 1bbe9af48dc3..f1a1f4c92ded 100644 --- a/include/linux/initrd.h +++ b/include/linux/initrd.h @@ -29,8 +29,6 @@ static inline void wait_for_initramfs(void) {} extern phys_addr_t phys_initrd_start; extern unsigned long phys_initrd_size; -extern unsigned int real_root_dev; - extern char __initramfs_start[]; extern unsigned long __initramfs_size; -- cgit v1.2.3 From 8e4e83b2278bdfb55cb2b13de07cf0a721ce8af7 Mon Sep 17 00:00:00 2001 From: Wei Xiao Date: Wed, 23 Feb 2022 19:11:53 +0800 Subject: ftrace: move sysctl_ftrace_enabled to ftrace.c This moves ftrace_enabled to trace/ftrace.c. We move sysctls to places where features actually belong to improve the readability of the code and reduce the risk of code merge conflicts. At the same time, the proc-sysctl maintainers do not want to know what sysctl knobs you wish to add for your owner piece of code, we just care about the core logic. Signed-off-by: Wei Xiao Acked-by: Steven Rostedt (Google) Signed-off-by: Luis Chamberlain --- include/linux/ftrace.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 4816b7e11047..088b915853dd 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -101,9 +101,6 @@ static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *val #ifdef CONFIG_FUNCTION_TRACER extern int ftrace_enabled; -extern int -ftrace_enable_sysctl(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); #ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS -- cgit v1.2.3 From 51454ea42c1ab4e0c2828bb0d4d53957976980de Mon Sep 17 00:00:00 2001 From: Niels Dossche Date: Mon, 4 Apr 2022 01:15:24 +0200 Subject: ipv6: fix locking issues with loops over idev->addr_list idev->addr_list needs to be protected by idev->lock. However, it is not always possible to do so while iterating and performing actions on inet6_ifaddr instances. For example, multiple functions (like addrconf_{join,leave}_anycast) eventually call down to other functions that acquire the idev->lock. The current code temporarily unlocked the idev->lock during the loops, which can cause race conditions. Moving the locks up is also not an appropriate solution as the ordering of lock acquisition will be inconsistent with for example mc_lock. This solution adds an additional field to inet6_ifaddr that is used to temporarily add the instances to a temporary list while holding idev->lock. The temporary list can then be traversed without holding idev->lock. This change was done in two places. In addrconf_ifdown, the list_for_each_entry_safe variant of the list loop is also no longer necessary as there is no deletion within that specific loop. Suggested-by: Paolo Abeni Signed-off-by: Niels Dossche Acked-by: Paolo Abeni Link: https://lore.kernel.org/r/20220403231523.45843-1-dossche.niels@gmail.com Signed-off-by: Jakub Kicinski --- include/net/if_inet6.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 4cfdef6ca4f6..c8490729b4ae 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -64,6 +64,14 @@ struct inet6_ifaddr { struct hlist_node addr_lst; struct list_head if_list; + /* + * Used to safely traverse idev->addr_list in process context + * if the idev->lock needed to protect idev->addr_list cannot be held. + * In that case, add the items to this list temporarily and iterate + * without holding idev->lock. + * See addrconf_ifdown and dev_forward_change. + */ + struct list_head if_list_aux; struct list_head tmp_list; struct inet6_ifaddr *ifpub; -- cgit v1.2.3 From 7bc80a5462c37eab58a9ea386064307c0f447fd1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Tue, 9 Nov 2021 11:08:18 +0100 Subject: dma-buf: add enum dma_resv_usage v4 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This change adds the dma_resv_usage enum and allows us to specify why a dma_resv object is queried for its containing fences. Additional to that a dma_resv_usage_rw() helper function is added to aid retrieving the fences for a read or write userspace submission. This is then deployed to the different query functions of the dma_resv object and all of their users. When the write paratermer was previously true we now use DMA_RESV_USAGE_WRITE and DMA_RESV_USAGE_READ otherwise. v2: add KERNEL/OTHER in separate patch v3: some kerneldoc suggestions by Daniel v4: some more kerneldoc suggestions by Daniel, fix missing cases lost in the rebase pointed out by Bas. Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220407085946.744568-2-christian.koenig@amd.com --- include/linux/dma-buf.h | 8 ++++-- include/linux/dma-resv.h | 73 +++++++++++++++++++++++++++++++++++++++--------- 2 files changed, 66 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 6fb91956ab8d..a297397743a2 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -408,6 +408,9 @@ struct dma_buf { * pipelining across drivers. These do not set any fences for their * access. An example here is v4l. * + * - Driver should use dma_resv_usage_rw() when retrieving fences as + * dependency for implicit synchronization. + * * DYNAMIC IMPORTER RULES: * * Dynamic importers, see dma_buf_attachment_is_dynamic(), have @@ -423,8 +426,9 @@ struct dma_buf { * * IMPORTANT: * - * All drivers must obey the struct dma_resv rules, specifically the - * rules for updating and obeying fences. + * All drivers and memory management related functions must obey the + * struct dma_resv rules, specifically the rules for updating and + * obeying fences. See enum dma_resv_usage for further descriptions. */ struct dma_resv *resv; diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 5fa04d0fccad..92cd8023980f 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -49,6 +49,53 @@ extern struct ww_class reservation_ww_class; struct dma_resv_list; +/** + * enum dma_resv_usage - how the fences from a dma_resv obj are used + * + * This enum describes the different use cases for a dma_resv object and + * controls which fences are returned when queried. + * + * An important fact is that there is the order WRITEobj = obj; - cursor->all_fences = all_fences; + cursor->usage = usage; cursor->fence = NULL; } @@ -241,7 +288,7 @@ static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor) * dma_resv_for_each_fence - fence iterator * @cursor: a struct dma_resv_iter pointer * @obj: a dma_resv object pointer - * @all_fences: true if all fences should be returned + * @usage: controls which fences to return * @fence: the current fence * * Iterate over the fences in a struct dma_resv object while holding the @@ -250,8 +297,8 @@ static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor) * valid as long as the lock is held and so no extra reference to the fence is * taken. */ -#define dma_resv_for_each_fence(cursor, obj, all_fences, fence) \ - for (dma_resv_iter_begin(cursor, obj, all_fences), \ +#define dma_resv_for_each_fence(cursor, obj, usage, fence) \ + for (dma_resv_iter_begin(cursor, obj, usage), \ fence = dma_resv_iter_first(cursor); fence; \ fence = dma_resv_iter_next(cursor)) @@ -418,14 +465,14 @@ void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence); void dma_resv_replace_fences(struct dma_resv *obj, uint64_t context, struct dma_fence *fence); void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence); -int dma_resv_get_fences(struct dma_resv *obj, bool write, +int dma_resv_get_fences(struct dma_resv *obj, enum dma_resv_usage usage, unsigned int *num_fences, struct dma_fence ***fences); -int dma_resv_get_singleton(struct dma_resv *obj, bool write, +int dma_resv_get_singleton(struct dma_resv *obj, enum dma_resv_usage usage, struct dma_fence **fence); int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src); -long dma_resv_wait_timeout(struct dma_resv *obj, bool wait_all, bool intr, - unsigned long timeout); -bool dma_resv_test_signaled(struct dma_resv *obj, bool test_all); +long dma_resv_wait_timeout(struct dma_resv *obj, enum dma_resv_usage usage, + bool intr, unsigned long timeout); +bool dma_resv_test_signaled(struct dma_resv *obj, enum dma_resv_usage usage); void dma_resv_describe(struct dma_resv *obj, struct seq_file *seq); #endif /* _LINUX_RESERVATION_H */ -- cgit v1.2.3 From 73511edf8b196e6f1ccda0fdf294ff57aa2dc9db Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Tue, 9 Nov 2021 11:08:18 +0100 Subject: dma-buf: specify usage while adding fences to dma_resv obj v7 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Instead of distingting between shared and exclusive fences specify the fence usage while adding fences. Rework all drivers to use this interface instead and deprecate the old one. v2: some kerneldoc comments suggested by Daniel v3: fix a missing case in radeon v4: rebase on nouveau changes, fix lockdep and temporary disable warning v5: more documentation updates v6: separate internal dma_resv changes from this patch, avoids to disable warning temporary, rebase on upstream changes v7: fix missed case in lima driver, minimize changes to i915_gem_busy_ioctl Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220407085946.744568-3-christian.koenig@amd.com --- include/linux/dma-buf.h | 16 ++++++++-------- include/linux/dma-resv.h | 25 +++++++++++++++---------- 2 files changed, 23 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index a297397743a2..71731796c8c3 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -393,15 +393,15 @@ struct dma_buf { * e.g. exposed in `Implicit Fence Poll Support`_ must follow the * below rules. * - * - Drivers must add a shared fence through dma_resv_add_shared_fence() - * for anything the userspace API considers a read access. This highly - * depends upon the API and window system. + * - Drivers must add a read fence through dma_resv_add_fence() with the + * DMA_RESV_USAGE_READ flag for anything the userspace API considers a + * read access. This highly depends upon the API and window system. * - * - Similarly drivers must set the exclusive fence through - * dma_resv_add_excl_fence() for anything the userspace API considers - * write access. + * - Similarly drivers must add a write fence through + * dma_resv_add_fence() with the DMA_RESV_USAGE_WRITE flag for + * anything the userspace API considers write access. * - * - Drivers may just always set the exclusive fence, since that only + * - Drivers may just always add a write fence, since that only * causes unecessarily synchronization, but no correctness issues. * * - Some drivers only expose a synchronous userspace API with no @@ -416,7 +416,7 @@ struct dma_buf { * Dynamic importers, see dma_buf_attachment_is_dynamic(), have * additional constraints on how they set up fences: * - * - Dynamic importers must obey the exclusive fence and wait for it to + * - Dynamic importers must obey the write fences and wait for them to * signal before allowing access to the buffer's underlying storage * through the device. * diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 92cd8023980f..98dc5234b487 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -195,6 +195,9 @@ struct dma_resv_iter { /** @fence: the currently handled fence */ struct dma_fence *fence; + /** @fence_usage: the usage of the current fence */ + enum dma_resv_usage fence_usage; + /** @seq: sequence number to check for modifications */ unsigned int seq; @@ -244,14 +247,15 @@ static inline void dma_resv_iter_end(struct dma_resv_iter *cursor) } /** - * dma_resv_iter_is_exclusive - test if the current fence is the exclusive one + * dma_resv_iter_usage - Return the usage of the current fence * @cursor: the cursor of the current position * - * Returns true if the currently returned fence is the exclusive one. + * Returns the usage of the currently processed fence. */ -static inline bool dma_resv_iter_is_exclusive(struct dma_resv_iter *cursor) +static inline enum dma_resv_usage +dma_resv_iter_usage(struct dma_resv_iter *cursor) { - return cursor->index == 0; + return cursor->fence_usage; } /** @@ -306,9 +310,9 @@ static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor) #define dma_resv_assert_held(obj) lockdep_assert_held(&(obj)->lock.base) #ifdef CONFIG_DEBUG_MUTEXES -void dma_resv_reset_shared_max(struct dma_resv *obj); +void dma_resv_reset_max_fences(struct dma_resv *obj); #else -static inline void dma_resv_reset_shared_max(struct dma_resv *obj) {} +static inline void dma_resv_reset_max_fences(struct dma_resv *obj) {} #endif /** @@ -454,17 +458,18 @@ static inline struct ww_acquire_ctx *dma_resv_locking_ctx(struct dma_resv *obj) */ static inline void dma_resv_unlock(struct dma_resv *obj) { - dma_resv_reset_shared_max(obj); + dma_resv_reset_max_fences(obj); ww_mutex_unlock(&obj->lock); } void dma_resv_init(struct dma_resv *obj); void dma_resv_fini(struct dma_resv *obj); int dma_resv_reserve_fences(struct dma_resv *obj, unsigned int num_fences); -void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence); +void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence, + enum dma_resv_usage usage); void dma_resv_replace_fences(struct dma_resv *obj, uint64_t context, - struct dma_fence *fence); -void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence); + struct dma_fence *fence, + enum dma_resv_usage usage); int dma_resv_get_fences(struct dma_resv *obj, enum dma_resv_usage usage, unsigned int *num_fences, struct dma_fence ***fences); int dma_resv_get_singleton(struct dma_resv *obj, enum dma_resv_usage usage, -- cgit v1.2.3 From 047a1b877ed48098bed71fcfb1d4891e1b54441d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Tue, 23 Nov 2021 09:33:07 +0100 Subject: dma-buf & drm/amdgpu: remove dma_resv workaround MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rework the internals of the dma_resv object to allow adding more than one write fence and remember for each fence what purpose it had. This allows removing the workaround from amdgpu which used a container for this instead. Signed-off-by: Christian König Reviewed-by: Daniel Vetter Cc: amd-gfx@lists.freedesktop.org Link: https://patchwork.freedesktop.org/patch/msgid/20220407085946.744568-4-christian.koenig@amd.com --- include/linux/dma-resv.h | 47 +++++++++++------------------------------------ 1 file changed, 11 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 98dc5234b487..7bb7e7edbb6f 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -99,8 +99,8 @@ static inline enum dma_resv_usage dma_resv_usage_rw(bool write) /** * struct dma_resv - a reservation object manages fences for a buffer * - * There are multiple uses for this, with sometimes slightly different rules in - * how the fence slots are used. + * This is a container for dma_fence objects which needs to handle multiple use + * cases. * * One use is to synchronize cross-driver access to a struct dma_buf, either for * dynamic buffer management or just to handle implicit synchronization between @@ -130,47 +130,22 @@ struct dma_resv { * @seq: * * Sequence count for managing RCU read-side synchronization, allows - * read-only access to @fence_excl and @fence while ensuring we take a - * consistent snapshot. + * read-only access to @fences while ensuring we take a consistent + * snapshot. */ seqcount_ww_mutex_t seq; /** - * @fence_excl: + * @fences: * - * The exclusive fence, if there is one currently. + * Array of fences which where added to the dma_resv object * - * To guarantee that no fences are lost, this new fence must signal - * only after the previous exclusive fence has signalled. If - * semantically only a new access is added without actually treating the - * previous one as a dependency the exclusive fences can be strung - * together using struct dma_fence_chain. - * - * Note that actual semantics of what an exclusive or shared fence mean - * is defined by the user, for reservation objects shared across drivers - * see &dma_buf.resv. - */ - struct dma_fence __rcu *fence_excl; - - /** - * @fence: - * - * List of current shared fences. - * - * There are no ordering constraints of shared fences against the - * exclusive fence slot. If a waiter needs to wait for all access, it - * has to wait for both sets of fences to signal. - * - * A new fence is added by calling dma_resv_add_shared_fence(). Since - * this often needs to be done past the point of no return in command + * A new fence is added by calling dma_resv_add_fence(). Since this + * often needs to be done past the point of no return in command * submission it cannot fail, and therefore sufficient slots need to be * reserved by calling dma_resv_reserve_fences(). - * - * Note that actual semantics of what an exclusive or shared fence mean - * is defined by the user, for reservation objects shared across drivers - * see &dma_buf.resv. */ - struct dma_resv_list __rcu *fence; + struct dma_resv_list __rcu *fences; }; /** @@ -207,8 +182,8 @@ struct dma_resv_iter { /** @fences: the shared fences; private, *MUST* not dereference */ struct dma_resv_list *fences; - /** @shared_count: number of shared fences */ - unsigned int shared_count; + /** @num_fences: number of fences */ + unsigned int num_fences; /** @is_restarted: true if this is the first returned fence */ bool is_restarted; -- cgit v1.2.3 From b29895e18304feb7e8afc6388db7ece60327b23c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Fri, 26 Nov 2021 14:12:42 +0100 Subject: dma-buf: add DMA_RESV_USAGE_KERNEL v3 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add an usage for kernel submissions. Waiting for those are mandatory for dynamic DMA-bufs. As a precaution this patch also changes all occurrences where fences are added as part of memory management in TTM, VMWGFX and i915 to use the new value because it now becomes possible for drivers to ignore fences with the WRITE usage. v2: use "must" in documentation, fix whitespaces v3: separate out some driver changes and better document why some changes should still be part of this patch. Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220407085946.744568-5-christian.koenig@amd.com --- include/linux/dma-resv.h | 24 +++++++++++++++++++++--- 1 file changed, 21 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 7bb7e7edbb6f..a749f229ae91 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -55,11 +55,29 @@ struct dma_resv_list; * This enum describes the different use cases for a dma_resv object and * controls which fences are returned when queried. * - * An important fact is that there is the order WRITE Date: Tue, 9 Nov 2021 11:08:18 +0100 Subject: dma-buf: add DMA_RESV_USAGE_BOOKKEEP v3 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add an usage for submissions independent of implicit sync but still interesting for memory management. v2: cleanup the kerneldoc a bit v3: separate amdgpu changes from this Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220407085946.744568-10-christian.koenig@amd.com --- include/linux/dma-resv.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index a749f229ae91..1db759eacc98 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -55,7 +55,7 @@ struct dma_resv_list; * This enum describes the different use cases for a dma_resv object and * controls which fences are returned when queried. * - * An important fact is that there is the order KERNEL Date: Tue, 23 Nov 2021 11:30:35 +0100 Subject: drm/ttm: remove bo->moving MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is now handled by the DMA-buf framework in the dma_resv obj. Also remove the workaround inside VMWGFX to update the moving fence. Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220407085946.744568-14-christian.koenig@amd.com --- include/drm/ttm/ttm_bo_api.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index c76932b68a33..2d524f8b0802 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -94,7 +94,6 @@ struct ttm_tt; * @deleted: True if the object is only a zombie and already deleted. * @ddestroy: List head for the delayed destroy list. * @swap: List head for swap LRU list. - * @moving: Fence set when BO is moving * @offset: The current GPU offset, which can have different meanings * depending on the memory type. For SYSTEM type memory, it should be 0. * @cur_placement: Hint of current placement. @@ -147,7 +146,6 @@ struct ttm_buffer_object { * Members protected by a bo reservation. */ - struct dma_fence *moving; unsigned priority; unsigned pin_count; -- cgit v1.2.3 From 8f94eda39952a8c7323bad2bf752bdfe78101b20 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Mon, 4 Apr 2022 14:58:37 +0200 Subject: dma-buf: drop seq count based update MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This should be possible now since we don't have the distinction between exclusive and shared fences any more. The only possible pitfall is that a dma_fence would be reused during the RCU grace period, but even that could be handled with a single extra check. Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220407085946.744568-15-christian.koenig@amd.com --- include/linux/dma-resv.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 1db759eacc98..c8ccbc94d5d2 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -155,15 +155,6 @@ struct dma_resv { */ struct ww_mutex lock; - /** - * @seq: - * - * Sequence count for managing RCU read-side synchronization, allows - * read-only access to @fences while ensuring we take a consistent - * snapshot. - */ - seqcount_ww_mutex_t seq; - /** * @fences: * @@ -202,9 +193,6 @@ struct dma_resv_iter { /** @fence_usage: the usage of the current fence */ enum dma_resv_usage fence_usage; - /** @seq: sequence number to check for modifications */ - unsigned int seq; - /** @index: index into the shared fences */ unsigned int index; -- cgit v1.2.3 From e84815cbbc767617221e6891e77f2486c9199dfa Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Thu, 7 Apr 2022 10:20:55 +0200 Subject: seqlock: drop seqcount_ww_mutex_t MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Daniel pointed out that this series removes the last user of seqcount_ww_mutex_t, so let's drop this. Signed-off-by: Christian König Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Will Deacon Cc: Waiman Long Cc: Boqun Feng Cc: linux-kernel@vger.kernel.org Acked-by: Peter Zijlstra (Intel) Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220407085946.744568-16-christian.koenig@amd.com --- include/linux/seqlock.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 37ded6b8fee6..3926e9027947 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -17,7 +17,6 @@ #include #include #include -#include #include #include @@ -164,7 +163,7 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) * static initializer or init function. This enables lockdep to validate * that the write side critical section is properly serialized. * - * LOCKNAME: raw_spinlock, spinlock, rwlock, mutex, or ww_mutex. + * LOCKNAME: raw_spinlock, spinlock, rwlock or mutex */ /* @@ -184,7 +183,6 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) #define seqcount_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, spinlock) #define seqcount_rwlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, rwlock) #define seqcount_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, mutex) -#define seqcount_ww_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, ww_mutex) /* * SEQCOUNT_LOCKNAME() - Instantiate seqcount_LOCKNAME_t and helpers @@ -277,7 +275,6 @@ SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t, false, s->lock, raw_s SEQCOUNT_LOCKNAME(spinlock, spinlock_t, __SEQ_RT, s->lock, spin, spin_lock(s->lock)) SEQCOUNT_LOCKNAME(rwlock, rwlock_t, __SEQ_RT, s->lock, read, read_lock(s->lock)) SEQCOUNT_LOCKNAME(mutex, struct mutex, true, s->lock, mutex, mutex_lock(s->lock)) -SEQCOUNT_LOCKNAME(ww_mutex, struct ww_mutex, true, &s->lock->base, ww_mutex, ww_mutex_lock(s->lock, NULL)) /* * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t @@ -304,8 +301,7 @@ SEQCOUNT_LOCKNAME(ww_mutex, struct ww_mutex, true, &s->lock->base, ww_mu __seqprop_case((s), raw_spinlock, prop), \ __seqprop_case((s), spinlock, prop), \ __seqprop_case((s), rwlock, prop), \ - __seqprop_case((s), mutex, prop), \ - __seqprop_case((s), ww_mutex, prop)) + __seqprop_case((s), mutex, prop)) #define seqprop_ptr(s) __seqprop(s, ptr) #define seqprop_sequence(s) __seqprop(s, sequence) -- cgit v1.2.3 From f584b68005ac782097d63a691740cb0dfed072ed Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 4 Apr 2022 15:11:04 -0400 Subject: mm: Add vma_alloc_folio() This wrapper around alloc_pages_vma() calls prep_transhuge_page(), removing the obligation from the caller. This is in the same spirit as __folio_alloc(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Zi Yan Reviewed-by: William Kucharski --- include/linux/gfp.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 761f8f1885c7..3e3d36fc2109 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -613,9 +613,11 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, #ifdef CONFIG_NUMA struct page *alloc_pages(gfp_t gfp, unsigned int order); struct folio *folio_alloc(gfp_t gfp, unsigned order); -extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, +struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, bool hugepage); +struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, + unsigned long addr, bool hugepage); #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages_vma(gfp_mask, order, vma, addr, true) #else @@ -627,8 +629,10 @@ static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order) { return __folio_alloc_node(gfp, order, numa_node_id()); } -#define alloc_pages_vma(gfp_mask, order, vma, addr, false)\ +#define alloc_pages_vma(gfp_mask, order, vma, addr, hugepage) \ alloc_pages(gfp_mask, order) +#define vma_alloc_folio(gfp, order, vma, addr, hugepage) \ + folio_alloc(gfp, order) #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages(gfp_mask, order) #endif -- cgit v1.2.3 From 4d5004451ab2218eab94a30e1841462c9316ba19 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 6 Apr 2022 13:51:32 -0400 Subject: SUNRPC: Fix the svc_deferred_event trace class Fix a NULL deref crash that occurs when an svc_rqst is deferred while the sunrpc tracing subsystem is enabled. svc_revisit() sets dr->xprt to NULL, so it can't be relied upon in the tracepoint to provide the remote's address. Unfortunately we can't revert the "svc_deferred_class" hunk in commit ece200ddd54b ("sunrpc: Save remote presentation address in svc_xprt for trace events") because there is now a specific check of event format specifiers for unsafe dereferences. The warning that check emits is: event svc_defer_recv has unsafe dereference of argument 1 A "%pISpc" format specifier with a "struct sockaddr *" is indeed flagged by this check. Instead, take the brute-force approach used by the svcrdma_qp_error tracepoint. Convert the dr::addr field into a presentation address in the TP_fast_assign() arm of the trace event, and store that as a string. This fix can be backported to -stable kernels. In the meantime, commit c6ced22997ad ("tracing: Update print fmt check to handle new __get_sockaddr() macro") is now in v5.18, so this wonky fix can be replaced with __sockaddr() and friends properly during the v5.19 merge window. Fixes: ece200ddd54b ("sunrpc: Save remote presentation address in svc_xprt for trace events") Signed-off-by: Chuck Lever --- include/trace/events/sunrpc.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index ab8ae1f6ba84..4eb706fa5825 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -2017,17 +2017,18 @@ DECLARE_EVENT_CLASS(svc_deferred_event, TP_STRUCT__entry( __field(const void *, dr) __field(u32, xid) - __string(addr, dr->xprt->xpt_remotebuf) + __array(__u8, addr, INET6_ADDRSTRLEN + 10) ), TP_fast_assign( __entry->dr = dr; __entry->xid = be32_to_cpu(*(__be32 *)(dr->args + (dr->xprt_hlen>>2))); - __assign_str(addr, dr->xprt->xpt_remotebuf); + snprintf(__entry->addr, sizeof(__entry->addr) - 1, + "%pISpc", (struct sockaddr *)&dr->addr); ), - TP_printk("addr=%s dr=%p xid=0x%08x", __get_str(addr), __entry->dr, + TP_printk("addr=%s dr=%p xid=0x%08x", __entry->addr, __entry->dr, __entry->xid) ); -- cgit v1.2.3 From 5ea98e01ab524cbc53dad8aebd27b434ebe5d074 Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Mon, 7 Mar 2022 15:33:39 -0600 Subject: x86/boot: Add Confidential Computing type to setup_data While launching encrypted guests, the hypervisor may need to provide some additional information during the guest boot. When booting under an EFI-based BIOS, the EFI configuration table contains an entry for the confidential computing blob that contains the required information. To support booting encrypted guests on non-EFI VMs, the hypervisor needs to pass this additional information to the guest kernel using a different method. For this purpose, introduce SETUP_CC_BLOB type in setup_data to hold the physical address of the confidential computing blob location. The boot loader or hypervisor may choose to use this method instead of an EFI configuration table. The CC blob location scanning should give preference to a setup_data blob over an EFI configuration table. In AMD SEV-SNP, the CC blob contains the address of the secrets and CPUID pages. The secrets page includes information such as a VM to PSP communication key and the CPUID page contains PSP-filtered CPUID values. Define the AMD SEV confidential computing blob structure. While at it, define the EFI GUID for the confidential computing blob. [ bp: Massage commit message, mark struct __packed. ] Signed-off-by: Brijesh Singh Signed-off-by: Borislav Petkov Acked-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20220307213356.2797205-30-brijesh.singh@amd.com --- include/linux/efi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index ccd4d3f91c98..984aa688997a 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -390,6 +390,7 @@ void efi_native_runtime_setup(void); #define EFI_CERT_SHA256_GUID EFI_GUID(0xc1c41626, 0x504c, 0x4092, 0xac, 0xa9, 0x41, 0xf9, 0x36, 0x93, 0x43, 0x28) #define EFI_CERT_X509_GUID EFI_GUID(0xa5c059a1, 0x94e4, 0x4aa7, 0x87, 0xb5, 0xab, 0x15, 0x5c, 0x2b, 0xf0, 0x72) #define EFI_CERT_X509_SHA256_GUID EFI_GUID(0x3bd2a492, 0x96c0, 0x4079, 0xb4, 0x20, 0xfc, 0xf9, 0x8e, 0xf1, 0x03, 0xed) +#define EFI_CC_BLOB_GUID EFI_GUID(0x067b1f5f, 0xcf26, 0x44c5, 0x85, 0x54, 0x93, 0xd7, 0x77, 0x91, 0x2d, 0x42) /* * This GUID is used to pass to the kernel proper the struct screen_info -- cgit v1.2.3 From fce96cf0443083e37455eff8f78fd240c621dae3 Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Mon, 7 Mar 2022 15:33:53 -0600 Subject: virt: Add SEV-SNP guest driver The SEV-SNP specification provides the guest a mechanism to communicate with the PSP without risk from a malicious hypervisor who wishes to read, alter, drop or replay the messages sent. The driver uses snp_issue_guest_request() to issue GHCB SNP_GUEST_REQUEST or SNP_EXT_GUEST_REQUEST NAE events to submit the request to PSP. The PSP requires that all communication should be encrypted using key specified through a struct snp_guest_platform_data descriptor. Userspace can use SNP_GET_REPORT ioctl() to query the guest attestation report. See SEV-SNP spec section Guest Messages for more details. [ bp: Remove the "what" from the commit message, massage. ] Signed-off-by: Brijesh Singh Signed-off-by: Borislav Petkov Link: https://lore.kernel.org/r/20220307213356.2797205-44-brijesh.singh@amd.com --- include/uapi/linux/sev-guest.h | 50 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) create mode 100644 include/uapi/linux/sev-guest.h (limited to 'include') diff --git a/include/uapi/linux/sev-guest.h b/include/uapi/linux/sev-guest.h new file mode 100644 index 000000000000..38f11d723c68 --- /dev/null +++ b/include/uapi/linux/sev-guest.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * Userspace interface for AMD SEV and SNP guest driver. + * + * Copyright (C) 2021 Advanced Micro Devices, Inc. + * + * Author: Brijesh Singh + * + * SEV API specification is available at: https://developer.amd.com/sev/ + */ + +#ifndef __UAPI_LINUX_SEV_GUEST_H_ +#define __UAPI_LINUX_SEV_GUEST_H_ + +#include + +struct snp_report_req { + /* user data that should be included in the report */ + __u8 user_data[64]; + + /* The vmpl level to be included in the report */ + __u32 vmpl; + + /* Must be zero filled */ + __u8 rsvd[28]; +}; + +struct snp_report_resp { + /* response data, see SEV-SNP spec for the format */ + __u8 data[4000]; +}; + +struct snp_guest_request_ioctl { + /* message version number (must be non-zero) */ + __u8 msg_version; + + /* Request and response structure address */ + __u64 req_data; + __u64 resp_data; + + /* firmware error code on failure (see psp-sev.h) */ + __u64 fw_err; +}; + +#define SNP_GUEST_REQ_IOC_TYPE 'S' + +/* Get SNP attestation report */ +#define SNP_GET_REPORT _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x0, struct snp_guest_request_ioctl) + +#endif /* __UAPI_LINUX_SEV_GUEST_H_ */ -- cgit v1.2.3 From 68de0b2f938642079c0c853b219bdb88c4dc4d13 Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Thu, 24 Feb 2022 10:56:23 -0600 Subject: virt: sevguest: Add support to derive key The SNP_GET_DERIVED_KEY ioctl interface can be used by the SNP guest to ask the firmware to provide a key derived from a root key. The derived key may be used by the guest for any purposes it chooses, such as a sealing key or communicating with the external entities. See SEV-SNP firmware spec for more information. [ bp: No need to memset "req" - it will get overwritten. ] Signed-off-by: Brijesh Singh Signed-off-by: Borislav Petkov Reviewed-by: Liam Merwick Link: https://lore.kernel.org/r/20220307213356.2797205-45-brijesh.singh@amd.com --- include/uapi/linux/sev-guest.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/sev-guest.h b/include/uapi/linux/sev-guest.h index 38f11d723c68..598367f12064 100644 --- a/include/uapi/linux/sev-guest.h +++ b/include/uapi/linux/sev-guest.h @@ -30,6 +30,20 @@ struct snp_report_resp { __u8 data[4000]; }; +struct snp_derived_key_req { + __u32 root_key_select; + __u32 rsvd; + __u64 guest_field_select; + __u32 vmpl; + __u32 guest_svn; + __u64 tcb_version; +}; + +struct snp_derived_key_resp { + /* response data, see SEV-SNP spec for the format */ + __u8 data[64]; +}; + struct snp_guest_request_ioctl { /* message version number (must be non-zero) */ __u8 msg_version; @@ -47,4 +61,7 @@ struct snp_guest_request_ioctl { /* Get SNP attestation report */ #define SNP_GET_REPORT _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x0, struct snp_guest_request_ioctl) +/* Get a derived key from the root */ +#define SNP_GET_DERIVED_KEY _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x1, struct snp_guest_request_ioctl) + #endif /* __UAPI_LINUX_SEV_GUEST_H_ */ -- cgit v1.2.3 From d80b494f712317493d464a55652698c4d1b7bb0f Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Mon, 7 Mar 2022 15:33:55 -0600 Subject: virt: sevguest: Add support to get extended report Version 2 of GHCB specification defines Non-Automatic-Exit (NAE) to get extended guest report which is similar to the SNP_GET_REPORT ioctl. The main difference is related to the additional data that will be returned. That additional data returned is a certificate blob that can be used by the SNP guest user. The certificate blob layout is defined in the GHCB specification. The driver simply treats the blob as a opaque data and copies it to userspace. [ bp: Massage commit message, cast 1st arg of access_ok() ] Signed-off-by: Brijesh Singh Signed-off-by: Borislav Petkov Link: https://lore.kernel.org/r/20220307213356.2797205-46-brijesh.singh@amd.com --- include/uapi/linux/sev-guest.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/sev-guest.h b/include/uapi/linux/sev-guest.h index 598367f12064..256aaeff7e65 100644 --- a/include/uapi/linux/sev-guest.h +++ b/include/uapi/linux/sev-guest.h @@ -56,6 +56,16 @@ struct snp_guest_request_ioctl { __u64 fw_err; }; +struct snp_ext_report_req { + struct snp_report_req data; + + /* where to copy the certificate blob */ + __u64 certs_address; + + /* length of the certificate blob */ + __u32 certs_len; +}; + #define SNP_GUEST_REQ_IOC_TYPE 'S' /* Get SNP attestation report */ @@ -64,4 +74,7 @@ struct snp_guest_request_ioctl { /* Get a derived key from the root */ #define SNP_GET_DERIVED_KEY _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x1, struct snp_guest_request_ioctl) +/* Get SNP extended report as defined in the GHCB specification version 2. */ +#define SNP_GET_EXT_REPORT _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x2, struct snp_guest_request_ioctl) + #endif /* __UAPI_LINUX_SEV_GUEST_H_ */ -- cgit v1.2.3 From 6b2060cf9138a2cd5f3468a949d3869abed049ef Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Tue, 5 Apr 2022 23:03:26 +0200 Subject: fb: Delete fb_info->queue It was only used by fbcon, and that now switched to its own, private work. Acked-by: Sam Ravnborg Acked-by: Thomas Zimmermann Signed-off-by: Daniel Vetter Cc: Helge Deller Cc: linux-fbdev@vger.kernel.org Link: https://patchwork.freedesktop.org/patch/msgid/20220405210335.3434130-9-daniel.vetter@ffwll.ch --- include/linux/fb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/fb.h b/include/linux/fb.h index 9a77ab615c36..f95da1af9ff6 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -450,7 +450,6 @@ struct fb_info { struct fb_var_screeninfo var; /* Current var */ struct fb_fix_screeninfo fix; /* Current fix */ struct fb_monspecs monspecs; /* Current Monitor specs */ - struct work_struct queue; /* Framebuffer event queue */ struct fb_pixmap pixmap; /* Image hardware mapper */ struct fb_pixmap sprite; /* Cursor hardware mapper */ struct fb_cmap cmap; /* Current cmap */ -- cgit v1.2.3 From bae1a962ac2c5e6be08319ff3f7d6df542584fce Mon Sep 17 00:00:00 2001 From: Kuppuswamy Sathyanarayanan Date: Wed, 6 Apr 2022 02:29:33 +0300 Subject: x86/topology: Disable CPU online/offline control for TDX guests Unlike regular VMs, TDX guests use the firmware hand-off wakeup method to wake up the APs during the boot process. This wakeup model uses a mailbox to communicate with firmware to bring up the APs. As per the design, this mailbox can only be used once for the given AP, which means after the APs are booted, the same mailbox cannot be used to offline/online the given AP. More details about this requirement can be found in Intel TDX Virtual Firmware Design Guide, sec titled "AP initialization in OS" and in sec titled "Hotplug Device". Since the architecture does not support any method of offlining the CPUs, disable CPU hotplug support in the kernel. Since this hotplug disable feature can be re-used by other VM guests, add a new CC attribute CC_ATTR_HOTPLUG_DISABLED and use it to disable the hotplug support. Attempt to offline CPU will fail with -EOPNOTSUPP. Signed-off-by: Kuppuswamy Sathyanarayanan Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Reviewed-by: Andi Kleen Reviewed-by: Tony Luck Reviewed-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20220405232939.73860-25-kirill.shutemov@linux.intel.com --- include/linux/cc_platform.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h index efd8205282da..691494bbaf5a 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -72,6 +72,16 @@ enum cc_attr { * Examples include TDX guest & SEV. */ CC_ATTR_GUEST_UNROLL_STRING_IO, + + /** + * @CC_ATTR_HOTPLUG_DISABLED: Hotplug is not supported or disabled. + * + * The platform/OS is running as a guest/virtual machine does not + * support CPU hotplug feature. + * + * Examples include TDX Guest. + */ + CC_ATTR_HOTPLUG_DISABLED, }; #ifdef CONFIG_ARCH_HAS_CC_PLATFORM -- cgit v1.2.3 From f00432063db1a0db484e85193eccc6845435b80e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 3 Apr 2022 15:58:11 -0400 Subject: SUNRPC: Ensure we flush any closed sockets before xs_xprt_free() We must ensure that all sockets are closed before we call xprt_free() and release the reference to the net namespace. The problem is that calling fput() will defer closing the socket until delayed_fput() gets called. Let's fix the situation by allowing rpciod and the transport teardown code (which runs on the system wq) to call __fput_sync(), and directly close the socket. Reported-by: Felix Fu Acked-by: Al Viro Fixes: a73881c96d73 ("SUNRPC: Fix an Oops in udp_poll()") Cc: stable@vger.kernel.org # 5.1.x: 3be232f11a3c: SUNRPC: Prevent immediate close+reconnect Cc: stable@vger.kernel.org # 5.1.x: 89f42494f92f: SUNRPC: Don't call connect() more than once on a TCP socket Cc: stable@vger.kernel.org # 5.1.x Signed-off-by: Trond Myklebust --- include/trace/events/sunrpc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index ac33892da411..a4848c7bab80 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -1004,7 +1004,6 @@ DEFINE_RPC_XPRT_LIFETIME_EVENT(connect); DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_auto); DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_done); DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_force); -DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_cleanup); DEFINE_RPC_XPRT_LIFETIME_EVENT(destroy); DECLARE_EVENT_CLASS(rpc_xprt_event, -- cgit v1.2.3 From 88dee0cc93adcd83db9d089c1163dc88edafd1c1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 6 Apr 2022 22:34:35 -0400 Subject: NFS: Ensure rpc_run_task() cannot fail in nfs_async_rename() Ensure the call to rpc_run_task() cannot fail by preallocating the rpc_task. Fixes: 910ad38697d9 ("NFS: Fix memory allocation in rpc_alloc_task()") Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 49ba486aea5f..2863e5a69c6a 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1694,6 +1694,7 @@ struct nfs_unlinkdata { struct nfs_renamedata { struct nfs_renameargs args; struct nfs_renameres res; + struct rpc_task task; const struct cred *cred; struct inode *old_dir; struct dentry *old_dentry; -- cgit v1.2.3 From ccc706353d1b89d8ff1726e575dd4a10f8550fb7 Mon Sep 17 00:00:00 2001 From: Rohit Agarwal Date: Wed, 16 Mar 2022 11:37:14 +0530 Subject: dt-bindings: power: Add rpm power domain bindings for SDX65 Add RPM power domain bindings for the SDX65 SoC. Signed-off-by: Rohit Agarwal Acked-by: Krzysztof Kozlowski Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/1647410837-22537-4-git-send-email-quic_rohiagar@quicinc.com --- include/dt-bindings/power/qcom-rpmpd.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/power/qcom-rpmpd.h b/include/dt-bindings/power/qcom-rpmpd.h index c002cc6ddf55..0a8978d0c78c 100644 --- a/include/dt-bindings/power/qcom-rpmpd.h +++ b/include/dt-bindings/power/qcom-rpmpd.h @@ -20,6 +20,14 @@ #define SDX55_MX 1 #define SDX55_CX 2 +/* SDX65 Power Domain Indexes */ +#define SDX65_MSS 0 +#define SDX65_MX 1 +#define SDX65_MX_AO 2 +#define SDX65_CX 3 +#define SDX65_CX_AO 4 +#define SDX65_MXC 5 + /* SM6350 Power Domain Indexes */ #define SM6350_CX 0 #define SM6350_GFX 1 -- cgit v1.2.3 From 6264f58ca0e54e41d63c2d00334a48bac28fbf30 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 6 Apr 2022 14:37:54 -0700 Subject: net: extract a few internals from netdevice.h There's a number of functions and static variables used under net/core/ but not from the outside. We currently dump most of them into netdevice.h. That bad for many reasons: - netdevice.h is very cluttered, hard to figure out what the APIs are; - netdevice.h is very long; - we have to touch netdevice.h more which causes expensive incremental builds. Create a header under net/core/ and move some declarations. The new header is also a bit of a catch-all but that's fine, if we create more specific headers people will likely over-think where their declaration fit best. And end up putting them in netdevice.h, again. More work should be done on splitting netdevice.h into more targeted headers, but that'd be more time consuming so small steps. Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 72 ++--------------------------------------------- 1 file changed, 2 insertions(+), 70 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7b2a0b739684..7e7b2a72e473 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -59,7 +59,8 @@ struct dsa_port; struct ip_tunnel_parm; struct macsec_context; struct macsec_ops; - +struct netdev_name_node; +struct sd_flow_limit; struct sfp_bus; /* 802.11 specific */ struct wireless_dev; @@ -1020,16 +1021,6 @@ struct dev_ifalias { struct devlink; struct tlsdev_ops; -struct netdev_name_node { - struct hlist_node hlist; - struct list_head list; - struct net_device *dev; - const char *name; -}; - -int netdev_name_node_alt_create(struct net_device *dev, const char *name); -int netdev_name_node_alt_destroy(struct net_device *dev, const char *name); - struct netdev_net_notifier { struct list_head list; struct notifier_block *nb; @@ -2975,7 +2966,6 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex); struct net_device *__dev_get_by_index(struct net *net, int ifindex); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); struct net_device *dev_get_by_napi_id(unsigned int napi_id); -int netdev_get_name(struct net *net, char *name, int ifindex); int dev_restart(struct net_device *dev); @@ -3034,19 +3024,6 @@ static inline bool dev_has_header(const struct net_device *dev) return dev->header_ops && dev->header_ops->create; } -#ifdef CONFIG_NET_FLOW_LIMIT -#define FLOW_LIMIT_HISTORY (1 << 7) /* must be ^2 and !overflow buckets */ -struct sd_flow_limit { - u64 count; - unsigned int num_buckets; - unsigned int history_head; - u16 history[FLOW_LIMIT_HISTORY]; - u8 buckets[]; -}; - -extern int netdev_flow_limit_table_len; -#endif /* CONFIG_NET_FLOW_LIMIT */ - /* * Incoming packets are placed on per-CPU queues */ @@ -3770,7 +3747,6 @@ int dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack); void __dev_notify_flags(struct net_device *, unsigned int old_flags, unsigned int gchanges); -int dev_change_name(struct net_device *, const char *); int dev_set_alias(struct net_device *, const char *, size_t); int dev_get_alias(const struct net_device *, char *, size_t); int __dev_change_net_namespace(struct net_device *dev, struct net *net, @@ -3782,13 +3758,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, return __dev_change_net_namespace(dev, net, pat, 0); } int __dev_set_mtu(struct net_device *, int); -int dev_validate_mtu(struct net_device *dev, int mtu, - struct netlink_ext_ack *extack); -int dev_set_mtu_ext(struct net_device *dev, int mtu, - struct netlink_ext_ack *extack); int dev_set_mtu(struct net_device *, int); -int dev_change_tx_queue_len(struct net_device *, unsigned long); -void dev_set_group(struct net_device *, int); int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr, struct netlink_ext_ack *extack); int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, @@ -3796,24 +3766,13 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa, struct netlink_ext_ack *extack); int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name); -int dev_change_carrier(struct net_device *, bool new_carrier); -int dev_get_phys_port_id(struct net_device *dev, - struct netdev_phys_item_id *ppid); -int dev_get_phys_port_name(struct net_device *dev, - char *name, size_t len); int dev_get_port_parent_id(struct net_device *dev, struct netdev_phys_item_id *ppid, bool recurse); bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b); -int dev_change_proto_down(struct net_device *dev, bool proto_down); -void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask, - u32 value); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); -typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf); -int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, - int fd, int expected_fd, u32 flags); int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); u8 dev_xdp_prog_count(struct net_device *dev); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); @@ -3898,13 +3857,6 @@ static __always_inline int ____dev_forward_skb(struct net_device *dev, bool dev_nit_active(struct net_device *dev); void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev); -extern int netdev_budget; -extern unsigned int netdev_budget_usecs; - -/* Used by rtnetlink.c:__rtnl_unlock()/rtnl_unlock() */ -extern struct list_head net_todo_list; -void netdev_run_todo(void); - static inline void __dev_put(struct net_device *dev) { if (dev) { @@ -4021,10 +3973,7 @@ static inline void dev_replace_track(struct net_device *odev, * called netif_lowerlayer_*() because they represent the state of any * kind of lower layer not just hardware media. */ - -void linkwatch_init_dev(struct net_device *dev); void linkwatch_fire_event(struct net_device *dev); -void linkwatch_forget_dev(struct net_device *dev); /** * netif_carrier_ok - test if carrier present @@ -4470,9 +4419,6 @@ int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); int dev_addr_del(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); -void dev_addr_flush(struct net_device *dev); -int dev_addr_init(struct net_device *dev); -void dev_addr_check(struct net_device *dev); /* Functions used for unicast addresses handling */ int dev_uc_add(struct net_device *dev, const unsigned char *addr); @@ -4562,7 +4508,6 @@ static inline void __dev_mc_unsync(struct net_device *dev, /* Functions used for secondary unicast and multicast support */ void dev_set_rx_mode(struct net_device *dev); -void __dev_set_rx_mode(struct net_device *dev); int dev_set_promiscuity(struct net_device *dev, int inc); int dev_set_allmulti(struct net_device *dev, int inc); void netdev_state_change(struct net_device *dev); @@ -4580,11 +4525,6 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s); extern int netdev_max_backlog; -extern int netdev_tstamp_prequeue; -extern int netdev_unregister_timeout_secs; -extern int weight_p; -extern int dev_weight_rx_bias; -extern int dev_weight_tx_bias; extern int dev_rx_weight; extern int dev_tx_weight; extern int gro_normal_batch; @@ -4772,12 +4712,6 @@ static inline void netdev_rx_csum_fault(struct net_device *dev, void net_enable_timestamp(void); void net_disable_timestamp(void); -#ifdef CONFIG_PROC_FS -int __init dev_proc_init(void); -#else -#define dev_proc_init() 0 -#endif - static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops, struct sk_buff *skb, struct net_device *dev, bool more) @@ -4813,8 +4747,6 @@ extern const struct kobj_ns_type_operations net_ns_type_operations; const char *netdev_drivername(const struct net_device *dev); -void linkwatch_run_queue(void); - static inline netdev_features_t netdev_intersect_features(netdev_features_t f1, netdev_features_t f2) { -- cgit v1.2.3 From 794c24e9921f32ded4422833a990ccf11dc3c00e Mon Sep 17 00:00:00 2001 From: Jeffrey Ji Date: Wed, 6 Apr 2022 17:26:00 +0000 Subject: net-core: rx_otherhost_dropped to core_stats Increment rx_otherhost_dropped counter when packet dropped due to mismatched dest MAC addr. An example when this drop can occur is when manually crafting raw packets that will be consumed by a user space application via a tap device. For testing purposes local traffic was generated using trafgen for the client and netcat to start a server Tested: Created 2 netns, sent 1 packet using trafgen from 1 to the other with "{eth(daddr=$INCORRECT_MAC...}", verified that iproute2 showed the counter was incremented. (Also had to modify iproute2 to show the stat, additional patch for that coming next.) Signed-off-by: Jeffrey Ji Reviewed-by: Brian Vazquez Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20220406172600.1141083-1-jeffreyjilinux@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 2 ++ include/uapi/linux/if_link.h | 5 +++++ 2 files changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7e7b2a72e473..28ea4f8269d4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -203,6 +203,7 @@ struct net_device_core_stats { local_t rx_dropped; local_t tx_dropped; local_t rx_nohandler; + local_t rx_otherhost_dropped; } __aligned(4 * sizeof(local_t)); #include @@ -3837,6 +3838,7 @@ static inline void dev_core_stats_##FIELD##_inc(struct net_device *dev) \ DEV_CORE_STATS_INC(rx_dropped) DEV_CORE_STATS_INC(tx_dropped) DEV_CORE_STATS_INC(rx_nohandler) +DEV_CORE_STATS_INC(rx_otherhost_dropped) static __always_inline int ____dev_forward_skb(struct net_device *dev, struct sk_buff *skb, diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index cc284c048e69..d1e600816b82 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -211,6 +211,9 @@ struct rtnl_link_stats { * @rx_nohandler: Number of packets received on the interface * but dropped by the networking stack because the device is * not designated to receive packets (e.g. backup link in a bond). + * + * @rx_otherhost_dropped: Number of packets dropped due to mismatch + * in destination MAC address. */ struct rtnl_link_stats64 { __u64 rx_packets; @@ -243,6 +246,8 @@ struct rtnl_link_stats64 { __u64 rx_compressed; __u64 tx_compressed; __u64 rx_nohandler; + + __u64 rx_otherhost_dropped; }; /* Subset of link stats useful for in-HW collection. Meaning of the fields is as -- cgit v1.2.3 From 15fcdf6ae116d1e8da4ff76c6fd82514f5ea501b Mon Sep 17 00:00:00 2001 From: Ping Gan Date: Wed, 6 Apr 2022 09:09:56 +0800 Subject: tcp: Add tracepoint for tcp_set_ca_state The congestion status of a tcp flow may be updated since there is congestion between tcp sender and receiver. It makes sense to add tracepoint for congestion status set function to summate cc status duration and evaluate the performance of network and congestion algorithm. the backgound of this patch is below. Link: https://github.com/iovisor/bcc/pull/3899 Signed-off-by: Ping Gan Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20220406010956.19656-1-jacky_gam_2001@163.com Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 12 +++--------- include/trace/events/tcp.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 54aa2f02bb63..6d50a662bf89 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1139,15 +1139,6 @@ static inline bool tcp_ca_needs_ecn(const struct sock *sk) return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN; } -static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - - if (icsk->icsk_ca_ops->set_state) - icsk->icsk_ca_ops->set_state(sk, ca_state); - icsk->icsk_ca_state = ca_state; -} - static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) { const struct inet_connection_sock *icsk = inet_csk(sk); @@ -1156,6 +1147,9 @@ static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) icsk->icsk_ca_ops->cwnd_event(sk, event); } +/* From tcp_cong.c */ +void tcp_set_ca_state(struct sock *sk, const u8 ca_state); + /* From tcp_rate.c */ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb); void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index edcd6369de10..901b440238d5 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -371,6 +371,51 @@ DEFINE_EVENT(tcp_event_skb, tcp_bad_csum, TP_ARGS(skb) ); +TRACE_EVENT(tcp_cong_state_set, + + TP_PROTO(struct sock *sk, const u8 ca_state), + + TP_ARGS(sk, ca_state), + + TP_STRUCT__entry( + __field(const void *, skaddr) + __field(__u16, sport) + __field(__u16, dport) + __array(__u8, saddr, 4) + __array(__u8, daddr, 4) + __array(__u8, saddr_v6, 16) + __array(__u8, daddr_v6, 16) + __field(__u8, cong_state) + ), + + TP_fast_assign( + struct inet_sock *inet = inet_sk(sk); + __be32 *p32; + + __entry->skaddr = sk; + + __entry->sport = ntohs(inet->inet_sport); + __entry->dport = ntohs(inet->inet_dport); + + p32 = (__be32 *) __entry->saddr; + *p32 = inet->inet_saddr; + + p32 = (__be32 *) __entry->daddr; + *p32 = inet->inet_daddr; + + TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, + sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); + + __entry->cong_state = ca_state; + ), + + TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c cong_state=%u", + __entry->sport, __entry->dport, + __entry->saddr, __entry->daddr, + __entry->saddr_v6, __entry->daddr_v6, + __entry->cong_state) +); + #endif /* _TRACE_TCP_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 73c919d314ad57be900437fd329990b1d846b763 Mon Sep 17 00:00:00 2001 From: Tianjia Zhang Date: Tue, 15 Mar 2022 17:44:51 +0800 Subject: crypto: sm4 - export sm4 constant arrays Export the constant arrays fk, ck, sbox of the SM4 algorithm, and add the 'crypto_sm4_' prefix, where sbox is used in the SM4 NEON implementation for the tbl/tbx instruction to replace the S-BOX, and the fk, ck arrays are used in the SM4 CE implementation. Use the sm4ekey instruction to speed up key expansion operations. Signed-off-by: Tianjia Zhang Signed-off-by: Herbert Xu --- include/crypto/sm4.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/crypto/sm4.h b/include/crypto/sm4.h index 709f286e7b25..9656a9a40326 100644 --- a/include/crypto/sm4.h +++ b/include/crypto/sm4.h @@ -21,6 +21,10 @@ struct sm4_ctx { u32 rkey_dec[SM4_RKEY_WORDS]; }; +extern const u32 crypto_sm4_fk[]; +extern const u32 crypto_sm4_ck[]; +extern const u8 crypto_sm4_sbox[]; + /** * sm4_expandkey - Expands the SM4 key as described in GB/T 32907-2016 * @ctx: The location where the computed key will be stored. -- cgit v1.2.3 From b71597edfaade119157ded98991bac7160be80c2 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Fri, 8 Apr 2022 10:00:42 +0200 Subject: mmc: core: improve API to make clear mmc_hw_reset is for cards To make it unambiguous that mmc_hw_reset() is for cards and not for controllers, we make the function argument mmc_card instead of mmc_host. Also, all users are converted. Suggested-by: Ulf Hansson Signed-off-by: Wolfram Sang Acked-by: Kalle Valo Link: https://lore.kernel.org/r/20220408080045.6497-2-wsa+renesas@sang-engineering.com Signed-off-by: Ulf Hansson --- include/linux/mmc/core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 71101d1ec825..de5c64bbdb72 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -175,7 +175,7 @@ void mmc_wait_for_req(struct mmc_host *host, struct mmc_request *mrq); int mmc_wait_for_cmd(struct mmc_host *host, struct mmc_command *cmd, int retries); -int mmc_hw_reset(struct mmc_host *host); +int mmc_hw_reset(struct mmc_card *card); int mmc_sw_reset(struct mmc_host *host); void mmc_set_data_timeout(struct mmc_data *data, const struct mmc_card *card); -- cgit v1.2.3 From bdae79651453df0bca20963fc2ab970146ef2a37 Mon Sep 17 00:00:00 2001 From: Shuai Xue Date: Tue, 8 Mar 2022 22:40:51 +0800 Subject: efi/cper: Add a cper_mem_err_status_str() to decode error description Introduce a new helper function cper_mem_err_status_str() to decode the error status value into a human readable string. [ bp: Massage. ] Signed-off-by: Shuai Xue Signed-off-by: Borislav Petkov Acked-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20220308144053.49090-2-xueshuai@linux.alibaba.com --- include/linux/cper.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cper.h b/include/linux/cper.h index 6a511a1078ca..5b1dd27b317d 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -558,6 +558,7 @@ extern const char *const cper_proc_error_type_strs[4]; u64 cper_next_record_id(void); const char *cper_severity_str(unsigned int); const char *cper_mem_err_type_str(unsigned int); +const char *cper_mem_err_status_str(u64 status); void cper_print_bits(const char *prefix, unsigned int bits, const char * const strs[], unsigned int strs_size); void cper_mem_err_pack(const struct cper_sec_mem_err *, -- cgit v1.2.3 From ed27b5df3877458eb24615fd9c202178660db009 Mon Sep 17 00:00:00 2001 From: Shuai Xue Date: Tue, 8 Mar 2022 22:40:52 +0800 Subject: EDAC/ghes: Unify CPER memory error location reporting Switch the GHES EDAC memory error reporting functions to use the common CPER ones and get rid of code duplication. [ bp: - rewrite commit message, remove useless text - rip out useless reformatting - align function params on the opening brace - rename function to a more descriptive name - drop useless function exports - handle buffer lengths properly when printing other detail - remove useless casting ] Signed-off-by: Shuai Xue Signed-off-by: Borislav Petkov Link: https://lore.kernel.org/r/20220308144053.49090-3-xueshuai@linux.alibaba.com --- include/linux/cper.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/cper.h b/include/linux/cper.h index 5b1dd27b317d..eacb7dd7b3af 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -569,5 +569,7 @@ void cper_print_proc_arm(const char *pfx, const struct cper_sec_proc_arm *proc); void cper_print_proc_ia(const char *pfx, const struct cper_sec_proc_ia *proc); +int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg); +int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg); #endif -- cgit v1.2.3 From 9027ce0b071a1bbd046682907fc2e23ca3592883 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 23 Mar 2022 14:22:01 +0100 Subject: netfilter: ecache: move to separate structure This makes it easier for a followup patch to only expose ecache related parts of nf_conntrack_net structure. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index b08b70989d2c..69e6c6a218be 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -43,6 +43,11 @@ union nf_conntrack_expect_proto { /* insert expect proto private data here */ }; +struct nf_conntrack_net_ecache { + struct delayed_work dwork; + struct netns_ct *ct_net; +}; + struct nf_conntrack_net { /* only used when new connection is allocated: */ atomic_t count; @@ -58,8 +63,7 @@ struct nf_conntrack_net { struct ctl_table_header *sysctl_header; #endif #ifdef CONFIG_NF_CONNTRACK_EVENTS - struct delayed_work ecache_dwork; - struct netns_ct *ct_net; + struct nf_conntrack_net_ecache ecache; #endif }; -- cgit v1.2.3 From c3f6bb74137c68b515b7e2ff123a80611e801013 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 7 Apr 2022 20:38:16 -0700 Subject: tls: rx: don't store the record type in socket context Original TLS implementation was handling one record at a time. It stashed the type of the record inside tls context (per socket structure) for convenience. When async crypto support was added [1] the author had to use skb->cb to store the type per-message. The use of skb->cb overlaps with strparser, however, so a hybrid approach was taken where type is stored in context while parsing (since we parse a message at a time) but once parsed its copied to skb->cb. Recently a workaround for sockmaps [2] exposed the previously private struct _strp_msg and started a trend of adding user fields directly in strparser's header. This is cleaner than storing information about an skb in the context. This change is not strictly necessary, but IMHO the ownership of the context field is confusing. Information naturally belongs to the skb. [1] commit 94524d8fc965 ("net/tls: Add support for async decryption of tls records") [2] commit b2c4618162ec ("bpf, sockmap: sk_skb data_end access incorrect when src_reg = dst_reg") Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/strparser.h | 3 +++ include/net/tls.h | 10 +++------- 2 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/strparser.h b/include/net/strparser.h index 732b7097d78e..c271543076cf 100644 --- a/include/net/strparser.h +++ b/include/net/strparser.h @@ -70,6 +70,9 @@ struct sk_skb_cb { * when dst_reg == src_reg. */ u64 temp_reg; + struct tls_msg { + u8 control; + } tls; }; static inline struct strp_msg *strp_msg(struct sk_buff *skb) diff --git a/include/net/tls.h b/include/net/tls.h index b6968a5b5538..c3717cd1f1cd 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -117,11 +117,6 @@ struct tls_rec { u8 aead_req_ctx[]; }; -struct tls_msg { - struct strp_msg rxm; - u8 control; -}; - struct tx_work { struct delayed_work work; struct sock *sk; @@ -152,7 +147,6 @@ struct tls_sw_context_rx { void (*saved_data_ready)(struct sock *sk); struct sk_buff *recv_pkt; - u8 control; u8 async_capable:1; u8 decrypted:1; atomic_t decrypt_pending; @@ -411,7 +405,9 @@ void tls_free_partial_record(struct sock *sk, struct tls_context *ctx); static inline struct tls_msg *tls_msg(struct sk_buff *skb) { - return (struct tls_msg *)strp_msg(skb); + struct sk_skb_cb *scb = (struct sk_skb_cb *)skb->cb; + + return &scb->tls; } static inline bool tls_is_partially_sent_record(struct tls_context *ctx) -- cgit v1.2.3 From 7dc59c33d62c4520a119051d4486c214ef5caa23 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 7 Apr 2022 20:38:17 -0700 Subject: tls: rx: don't store the decryption status in socket context Similar justification to previous change, the information about decryption status belongs in the skb. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/strparser.h | 1 + include/net/tls.h | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/strparser.h b/include/net/strparser.h index c271543076cf..a191486eb1e4 100644 --- a/include/net/strparser.h +++ b/include/net/strparser.h @@ -72,6 +72,7 @@ struct sk_skb_cb { u64 temp_reg; struct tls_msg { u8 control; + u8 decrypted; } tls; }; diff --git a/include/net/tls.h b/include/net/tls.h index c3717cd1f1cd..f040edc97c50 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -148,7 +148,6 @@ struct tls_sw_context_rx { struct sk_buff *recv_pkt; u8 async_capable:1; - u8 decrypted:1; atomic_t decrypt_pending; /* protect crypto_wait with decrypt_pending*/ spinlock_t decrypt_compl_lock; -- cgit v1.2.3 From a8340cc02beed4ffbb5e7b1b0eadca445323fc6a Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 7 Apr 2022 20:38:19 -0700 Subject: tls: rx: use a define for tag length TLS 1.3 has to strip padding, and it starts out 16 bytes from the end of the record. Make it clear this is because of the auth tag. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/tls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index f040edc97c50..a01c264e5f15 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -64,6 +64,7 @@ #define TLS_AAD_SPACE_SIZE 13 #define MAX_IV_SIZE 16 +#define TLS_TAG_SIZE 16 #define TLS_MAX_REC_SEQ_SIZE 8 /* For CCM mode, the full 16-bytes of IV is made of '4' fields of given sizes. -- cgit v1.2.3 From 2105f700b53c24aa48b65c15652acc386044d26a Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Wed, 6 Apr 2022 14:22:41 +0300 Subject: net/sched: flower: fix parsing of ethertype following VLAN header A tc flower filter matching TCA_FLOWER_KEY_VLAN_ETH_TYPE is expected to match the L2 ethertype following the first VLAN header, as confirmed by linked discussion with the maintainer. However, such rule also matches packets that have additional second VLAN header, even though filter has both eth_type and vlan_ethtype set to "ipv4". Looking at the code this seems to be mostly an artifact of the way flower uses flow dissector. First, even though looking at the uAPI eth_type and vlan_ethtype appear like a distinct fields, in flower they are all mapped to the same key->basic.n_proto. Second, flow dissector skips following VLAN header as no keys for FLOW_DISSECTOR_KEY_CVLAN are set and eventually assigns the value of n_proto to last parsed header. With these, such filters ignore any headers present between first VLAN header and first "non magic" header (ipv4 in this case) that doesn't result FLOW_DISSECT_RET_PROTO_AGAIN. Fix the issue by extending flow dissector VLAN key structure with new 'vlan_eth_type' field that matches first ethertype following previously parsed VLAN header. Modify flower classifier to set the new flow_dissector_key_vlan->vlan_eth_type with value obtained from TCA_FLOWER_KEY_VLAN_ETH_TYPE/TCA_FLOWER_KEY_CVLAN_ETH_TYPE uAPIs. Link: https://lore.kernel.org/all/Yjhgi48BpTGh6dig@nanopsycho/ Fixes: 9399ae9a6cb2 ("net_sched: flower: Add vlan support") Fixes: d64efd0926ba ("net/sched: flower: Add supprt for matching on QinQ vlan headers") Signed-off-by: Vlad Buslov Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/flow_dissector.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index aa33e1092e2c..9f65f1bfbd24 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -59,6 +59,8 @@ struct flow_dissector_key_vlan { __be16 vlan_tci; }; __be16 vlan_tpid; + __be16 vlan_eth_type; + u16 padding; }; struct flow_dissector_mpls_lse { -- cgit v1.2.3 From 0c2cae09a765b1c1d842eb9328982976ec735926 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 17 Mar 2022 11:33:11 +0200 Subject: gpiolib: acpi: Convert type for pin to be unsigned A pin that comes from ACPI tables is of unsigned type. This also applies to the internal APIs which use unsigned int to store the pin. Convert type for pin to be unsigned in the places where it's not yet true. While at it, add a stub for acpi_get_and_request_gpiod() for the sake of consistency in the APIs. Signed-off-by: Andy Shevchenko --- include/linux/gpio/consumer.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index c3aa8b330e1c..e71f6e1bfafe 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -688,7 +688,7 @@ void acpi_dev_remove_driver_gpios(struct acpi_device *adev); int devm_acpi_dev_add_driver_gpios(struct device *dev, const struct acpi_gpio_mapping *gpios); -struct gpio_desc *acpi_get_and_request_gpiod(char *path, int pin, char *label); +struct gpio_desc *acpi_get_and_request_gpiod(char *path, unsigned int pin, char *label); #else /* CONFIG_GPIOLIB && CONFIG_ACPI */ @@ -705,6 +705,12 @@ static inline int devm_acpi_dev_add_driver_gpios(struct device *dev, return -ENXIO; } +static inline struct gpio_desc *acpi_get_and_request_gpiod(char *path, unsigned int pin, + char *label) +{ + return ERR_PTR(-ENOSYS); +} + #endif /* CONFIG_GPIOLIB && CONFIG_ACPI */ -- cgit v1.2.3 From c2ccf84ecb715bb81dc7f51e69d680a95bf055ae Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 7 Apr 2022 10:35:22 +0300 Subject: net/sched: act_api: Add extack to offload_act_setup() callback The callback is used by various actions to populate the flow action structure prior to offload. Pass extack to this callback so that the various actions will be able to report accurate error messages to user space. Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Signed-off-by: David S. Miller --- include/net/act_api.h | 3 ++- include/net/pkt_cls.h | 6 ++++-- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index 3049cb69c025..9cf6870b526e 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -134,7 +134,8 @@ struct tc_action_ops { (*get_psample_group)(const struct tc_action *a, tc_action_priv_destructor *destructor); int (*offload_act_setup)(struct tc_action *act, void *entry_data, - u32 *index_inc, bool bind); + u32 *index_inc, bool bind, + struct netlink_ext_ack *extack); }; struct tc_action_net { diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index a3b57a93228a..8cf001aed858 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -547,10 +547,12 @@ tcf_match_indev(struct sk_buff *skb, int ifindex) } int tc_setup_offload_action(struct flow_action *flow_action, - const struct tcf_exts *exts); + const struct tcf_exts *exts, + struct netlink_ext_ack *extack); void tc_cleanup_offload_action(struct flow_action *flow_action); int tc_setup_action(struct flow_action *flow_action, - struct tc_action *actions[]); + struct tc_action *actions[], + struct netlink_ext_ack *extack); int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, void *type_data, bool err_stop, bool rtnl_held); -- cgit v1.2.3 From 69642c2ab2f553fd8c4c121fcdf3b3054c727e86 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 7 Apr 2022 10:35:23 +0300 Subject: net/sched: act_gact: Add extack messages for offload failure For better error reporting to user space, add extack messages when gact action offload fails. Example: # echo 1 > /sys/kernel/tracing/events/netlink/netlink_extack/enable # tc filter add dev dummy0 ingress pref 1 proto all matchall skip_sw action continue Error: cls_matchall: Failed to setup flow action. We have an error talking to the kernel # cat /sys/kernel/tracing/trace_pipe tc-181 [002] b..1. 105.493450: netlink_extack: msg=act_gact: Offload of "continue" action is not supported tc-181 [002] ..... 105.493466: netlink_extack: msg=cls_matchall: Failed to setup flow action # tc filter add dev dummy0 ingress pref 1 proto all matchall skip_sw action reclassify Error: cls_matchall: Failed to setup flow action. We have an error talking to the kernel # cat /sys/kernel/tracing/trace_pipe tc-183 [002] b..1. 124.126477: netlink_extack: msg=act_gact: Offload of "reclassify" action is not supported tc-183 [002] ..... 124.126489: netlink_extack: msg=cls_matchall: Failed to setup flow action # tc filter add dev dummy0 ingress pref 1 proto all matchall skip_sw action pipe action drop Error: cls_matchall: Failed to setup flow action. We have an error talking to the kernel # cat /sys/kernel/tracing/trace_pipe tc-185 [002] b..1. 137.097791: netlink_extack: msg=act_gact: Offload of "pipe" action is not supported tc-185 [002] ..... 137.097804: netlink_extack: msg=cls_matchall: Failed to setup flow action Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Signed-off-by: David S. Miller --- include/net/tc_act/tc_gact.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h index eb8f01c819e6..832efd40e023 100644 --- a/include/net/tc_act/tc_gact.h +++ b/include/net/tc_act/tc_gact.h @@ -59,4 +59,19 @@ static inline u32 tcf_gact_goto_chain_index(const struct tc_action *a) return READ_ONCE(a->tcfa_action) & TC_ACT_EXT_VAL_MASK; } +static inline bool is_tcf_gact_continue(const struct tc_action *a) +{ + return __is_tcf_gact_act(a, TC_ACT_UNSPEC, false); +} + +static inline bool is_tcf_gact_reclassify(const struct tc_action *a) +{ + return __is_tcf_gact_act(a, TC_ACT_RECLASSIFY, false); +} + +static inline bool is_tcf_gact_pipe(const struct tc_action *a) +{ + return __is_tcf_gact_act(a, TC_ACT_PIPE, false); +} + #endif /* __NET_TC_GACT_H */ -- cgit v1.2.3 From a9c64939b669b3c83cc54738d1986430e6beaff2 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 7 Apr 2022 10:35:28 +0300 Subject: net/sched: act_skbedit: Add extack messages for offload failure For better error reporting to user space, add extack messages when skbedit action offload fails. Example: # echo 1 > /sys/kernel/tracing/events/netlink/netlink_extack/enable # tc filter add dev dummy0 ingress pref 1 proto all matchall skip_sw action skbedit queue_mapping 1234 Error: cls_matchall: Failed to setup flow action. We have an error talking to the kernel # cat /sys/kernel/tracing/trace_pipe tc-185 [002] b..1. 31.802414: netlink_extack: msg=act_skbedit: Offload not supported when "queue_mapping" option is used tc-185 [002] ..... 31.802418: netlink_extack: msg=cls_matchall: Failed to setup flow action # tc filter add dev dummy0 ingress pref 1 proto all matchall skip_sw action skbedit inheritdsfield Error: cls_matchall: Failed to setup flow action. We have an error talking to the kernel # cat /sys/kernel/tracing/trace_pipe tc-187 [002] b..1. 45.985145: netlink_extack: msg=act_skbedit: Offload not supported when "inheritdsfield" option is used tc-187 [002] ..... 45.985160: netlink_extack: msg=cls_matchall: Failed to setup flow action Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Signed-off-by: David S. Miller --- include/net/tc_act/tc_skbedit.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h index 00bfee70609e..cab8229b9bed 100644 --- a/include/net/tc_act/tc_skbedit.h +++ b/include/net/tc_act/tc_skbedit.h @@ -94,4 +94,16 @@ static inline u32 tcf_skbedit_priority(const struct tc_action *a) return priority; } +/* Return true iff action is queue_mapping */ +static inline bool is_tcf_skbedit_queue_mapping(const struct tc_action *a) +{ + return is_tcf_skbedit_with_flag(a, SKBEDIT_F_QUEUE_MAPPING); +} + +/* Return true iff action is inheritdsfield */ +static inline bool is_tcf_skbedit_inheritdsfield(const struct tc_action *a) +{ + return is_tcf_skbedit_with_flag(a, SKBEDIT_F_INHERITDSFIELD); +} + #endif /* __NET_TC_SKBEDIT_H */ -- cgit v1.2.3 From 85ebb1a6bd62147ebcfa70500d513331a8daf9e0 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 1 Apr 2022 13:35:52 +0300 Subject: gpiolib: Introduce for_each_gpiochip_node() loop helper Introduce for_each_gpiochip_node() loop helper which iterates over the GPIO controller child nodes of a given device. Signed-off-by: Andy Shevchenko Reviewed-by: Geert Uytterhoeven Tested-by: Geert Uytterhoeven Acked-by: Bartosz Golaszewski --- include/linux/gpio/driver.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 98c93510640e..bfc91f122d5f 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -3,13 +3,14 @@ #define __LINUX_GPIO_DRIVER_H #include -#include #include #include #include #include #include #include +#include +#include struct gpio_desc; struct of_phandle_args; @@ -750,4 +751,8 @@ static inline void gpiochip_unlock_as_irq(struct gpio_chip *gc, } #endif /* CONFIG_GPIOLIB */ +#define for_each_gpiochip_node(dev, child) \ + device_for_each_child_node(dev, child) \ + if (!fwnode_property_present(child, "gpio-controller")) {} else + #endif /* __LINUX_GPIO_DRIVER_H */ -- cgit v1.2.3 From 0b19dde90ad004592792a928c75e80612be3e2e8 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 1 Apr 2022 13:35:53 +0300 Subject: gpiolib: Introduce gpiochip_node_count() helper The gpiochip_node_count() helper iterates over the device child nodes that have the "gpio-controller" property set. It returns the number of such nodes under a given device. Signed-off-by: Andy Shevchenko Reviewed-by: Geert Uytterhoeven Tested-by: Geert Uytterhoeven Acked-by: Bartosz Golaszewski --- include/linux/gpio/driver.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index bfc91f122d5f..12de0b22b4ef 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -755,4 +755,15 @@ static inline void gpiochip_unlock_as_irq(struct gpio_chip *gc, device_for_each_child_node(dev, child) \ if (!fwnode_property_present(child, "gpio-controller")) {} else +static inline unsigned int gpiochip_node_count(struct device *dev) +{ + struct fwnode_handle *child; + unsigned int count = 0; + + for_each_gpiochip_node(dev, child) + count++; + + return count; +} + #endif /* __LINUX_GPIO_DRIVER_H */ -- cgit v1.2.3 From 2c547f299827c12244d613eb2ee3616d88f56088 Mon Sep 17 00:00:00 2001 From: Yue Hu Date: Wed, 6 Apr 2022 11:50:17 +0800 Subject: fscache: Remove the cookie parameter from fscache_clear_page_bits() The cookie is not used at all, remove it and update the usage in io.c and afs/write.c (which is the only user outside of fscache currently) at the same time. [DH: Amended the documentation also] Signed-off-by: Yue Hu Signed-off-by: David Howells cc: linux-cachefs@redhat.com Link: https://listman.redhat.com/archives/linux-cachefs/2022-April/006659.html --- include/linux/fscache.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 6727fb0db619..e25539072463 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -573,7 +573,6 @@ int fscache_write(struct netfs_cache_resources *cres, /** * fscache_clear_page_bits - Clear the PG_fscache bits from a set of pages - * @cookie: The cookie representing the cache object * @mapping: The netfs inode to use as the source * @start: The start position in @mapping * @len: The amount of data to unlock @@ -582,8 +581,7 @@ int fscache_write(struct netfs_cache_resources *cres, * Clear the PG_fscache flag from a sequence of pages and wake up anyone who's * waiting. */ -static inline void fscache_clear_page_bits(struct fscache_cookie *cookie, - struct address_space *mapping, +static inline void fscache_clear_page_bits(struct address_space *mapping, loff_t start, size_t len, bool caching) { -- cgit v1.2.3 From a431dbbc540532b7465eae4fc8b56a85a9fc7d17 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Fri, 8 Apr 2022 13:09:01 -0700 Subject: mm/sparsemem: fix 'mem_section' will never be NULL gcc 12 warning The gcc 12 compiler reports a "'mem_section' will never be NULL" warning on the following code: static inline struct mem_section *__nr_to_section(unsigned long nr) { #ifdef CONFIG_SPARSEMEM_EXTREME if (!mem_section) return NULL; #endif if (!mem_section[SECTION_NR_TO_ROOT(nr)]) return NULL; : It happens with CONFIG_SPARSEMEM_EXTREME off. The mem_section definition is #ifdef CONFIG_SPARSEMEM_EXTREME extern struct mem_section **mem_section; #else extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]; #endif In the !CONFIG_SPARSEMEM_EXTREME case, mem_section is a static 2-dimensional array and so the check "!mem_section[SECTION_NR_TO_ROOT(nr)]" doesn't make sense. Fix this warning by moving the "!mem_section[SECTION_NR_TO_ROOT(nr)]" check up inside the CONFIG_SPARSEMEM_EXTREME block and adding an explicit NR_SECTION_ROOTS check to make sure that there is no out-of-bound array access. Link: https://lkml.kernel.org/r/20220331180246.2746210-1-longman@redhat.com Fixes: 3e347261a80b ("sparsemem extreme implementation") Signed-off-by: Waiman Long Reported-by: Justin Forbes Cc: "Kirill A . Shutemov" Cc: Ingo Molnar Cc: Rafael Aquini Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 962b14d403e8..46ffab808f03 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1397,13 +1397,16 @@ static inline unsigned long *section_to_usemap(struct mem_section *ms) static inline struct mem_section *__nr_to_section(unsigned long nr) { + unsigned long root = SECTION_NR_TO_ROOT(nr); + + if (unlikely(root >= NR_SECTION_ROOTS)) + return NULL; + #ifdef CONFIG_SPARSEMEM_EXTREME - if (!mem_section) + if (!mem_section || !mem_section[root]) return NULL; #endif - if (!mem_section[SECTION_NR_TO_ROOT(nr)]) - return NULL; - return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK]; + return &mem_section[root][nr & SECTION_ROOT_MASK]; } extern size_t mem_section_usage_size(void); -- cgit v1.2.3 From 2fa33b3518a8da0a5345b7ae0064223b5e4e156f Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 6 Apr 2022 11:25:36 +0300 Subject: net/mlx5_fpga: Drop INNOVA IPsec support Mellanox INNOVA IPsec cards are EOL in Nov, 2019 [1]. As such, the code is unmaintained, untested and not in-use by any upstream/distro oriented customers. In order to reduce code complexity, drop the kernel code. [1] https://network.nvidia.com/related-docs/eol/LCR-000535.pdf Link: https://lore.kernel.org/r/2afe88ec5020a491079eacf6fe3c89b64d65195c.1649232994.git.leonro@nvidia.com Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc_fpga.h | 148 ------------------------------------- 1 file changed, 148 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc_fpga.h b/include/linux/mlx5/mlx5_ifc_fpga.h index e3d824f6a309..45c7c0d67635 100644 --- a/include/linux/mlx5/mlx5_ifc_fpga.h +++ b/include/linux/mlx5/mlx5_ifc_fpga.h @@ -386,68 +386,6 @@ struct mlx5_ifc_fpga_destroy_qp_out_bits { u8 reserved_at_40[0x40]; }; -struct mlx5_ifc_ipsec_extended_cap_bits { - u8 encapsulation[0x20]; - - u8 reserved_0[0x12]; - u8 v2_command[0x1]; - u8 udp_encap[0x1]; - u8 rx_no_trailer[0x1]; - u8 ipv4_fragment[0x1]; - u8 ipv6[0x1]; - u8 esn[0x1]; - u8 lso[0x1]; - u8 transport_and_tunnel_mode[0x1]; - u8 tunnel_mode[0x1]; - u8 transport_mode[0x1]; - u8 ah_esp[0x1]; - u8 esp[0x1]; - u8 ah[0x1]; - u8 ipv4_options[0x1]; - - u8 auth_alg[0x20]; - - u8 enc_alg[0x20]; - - u8 sa_cap[0x20]; - - u8 reserved_1[0x10]; - u8 number_of_ipsec_counters[0x10]; - - u8 ipsec_counters_addr_low[0x20]; - u8 ipsec_counters_addr_high[0x20]; -}; - -struct mlx5_ifc_ipsec_counters_bits { - u8 dec_in_packets[0x40]; - - u8 dec_out_packets[0x40]; - - u8 dec_bypass_packets[0x40]; - - u8 enc_in_packets[0x40]; - - u8 enc_out_packets[0x40]; - - u8 enc_bypass_packets[0x40]; - - u8 drop_dec_packets[0x40]; - - u8 failed_auth_dec_packets[0x40]; - - u8 drop_enc_packets[0x40]; - - u8 success_add_sa[0x40]; - - u8 fail_add_sa[0x40]; - - u8 success_delete_sa[0x40]; - - u8 fail_delete_sa[0x40]; - - u8 dropped_cmd[0x40]; -}; - enum { MLX5_FPGA_QP_ERROR_EVENT_SYNDROME_RETRY_COUNTER_EXPIRED = 0x1, MLX5_FPGA_QP_ERROR_EVENT_SYNDROME_RNR_EXPIRED = 0x2, @@ -464,90 +402,4 @@ struct mlx5_ifc_fpga_qp_error_event_bits { u8 reserved_at_c0[0x8]; u8 fpga_qpn[0x18]; }; -enum mlx5_ifc_fpga_ipsec_response_syndrome { - MLX5_FPGA_IPSEC_RESPONSE_SUCCESS = 0, - MLX5_FPGA_IPSEC_RESPONSE_ILLEGAL_REQUEST = 1, - MLX5_FPGA_IPSEC_RESPONSE_SADB_ISSUE = 2, - MLX5_FPGA_IPSEC_RESPONSE_WRITE_RESPONSE_ISSUE = 3, -}; - -struct mlx5_ifc_fpga_ipsec_cmd_resp { - __be32 syndrome; - union { - __be32 sw_sa_handle; - __be32 flags; - }; - u8 reserved[24]; -} __packed; - -enum mlx5_ifc_fpga_ipsec_cmd_opcode { - MLX5_FPGA_IPSEC_CMD_OP_ADD_SA = 0, - MLX5_FPGA_IPSEC_CMD_OP_DEL_SA = 1, - MLX5_FPGA_IPSEC_CMD_OP_ADD_SA_V2 = 2, - MLX5_FPGA_IPSEC_CMD_OP_DEL_SA_V2 = 3, - MLX5_FPGA_IPSEC_CMD_OP_MOD_SA_V2 = 4, - MLX5_FPGA_IPSEC_CMD_OP_SET_CAP = 5, -}; - -enum mlx5_ifc_fpga_ipsec_cap { - MLX5_FPGA_IPSEC_CAP_NO_TRAILER = BIT(0), -}; - -struct mlx5_ifc_fpga_ipsec_cmd_cap { - __be32 cmd; - __be32 flags; - u8 reserved[24]; -} __packed; - -enum mlx5_ifc_fpga_ipsec_sa_flags { - MLX5_FPGA_IPSEC_SA_ESN_EN = BIT(0), - MLX5_FPGA_IPSEC_SA_ESN_OVERLAP = BIT(1), - MLX5_FPGA_IPSEC_SA_IPV6 = BIT(2), - MLX5_FPGA_IPSEC_SA_DIR_SX = BIT(3), - MLX5_FPGA_IPSEC_SA_SPI_EN = BIT(4), - MLX5_FPGA_IPSEC_SA_SA_VALID = BIT(5), - MLX5_FPGA_IPSEC_SA_IP_ESP = BIT(6), - MLX5_FPGA_IPSEC_SA_IP_AH = BIT(7), -}; - -enum mlx5_ifc_fpga_ipsec_sa_enc_mode { - MLX5_FPGA_IPSEC_SA_ENC_MODE_NONE = 0, - MLX5_FPGA_IPSEC_SA_ENC_MODE_AES_GCM_128_AUTH_128 = 1, - MLX5_FPGA_IPSEC_SA_ENC_MODE_AES_GCM_256_AUTH_128 = 3, -}; - -struct mlx5_ifc_fpga_ipsec_sa_v1 { - __be32 cmd; - u8 key_enc[32]; - u8 key_auth[32]; - __be32 sip[4]; - __be32 dip[4]; - union { - struct { - __be32 reserved; - u8 salt_iv[8]; - __be32 salt; - } __packed gcm; - struct { - u8 salt[16]; - } __packed cbc; - }; - __be32 spi; - __be32 sw_sa_handle; - __be16 tfclen; - u8 enc_mode; - u8 reserved1[2]; - u8 flags; - u8 reserved2[2]; -}; - -struct mlx5_ifc_fpga_ipsec_sa { - struct mlx5_ifc_fpga_ipsec_sa_v1 ipsec_sa_v1; - __be16 udp_sp; - __be16 udp_dp; - u8 reserved1[4]; - __be32 esn; - __be16 vid; /* only 12 bits, rest is reserved */ - __be16 reserved2; -} __packed; #endif /* MLX5_IFC_FPGA_H */ -- cgit v1.2.3 From de8bdb476908e64805df4bfbad20618cbb1f9ffa Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 6 Apr 2022 11:25:42 +0300 Subject: RDMA/mlx5: Drop crypto flow steering API The mlx5 flow steering crypto API was intended to be used in FPGA devices, which is not supported for years already. The removal of mlx5 crypto FPGA code together with inability to configure encryption keys makes the low steering API completely unusable. So delete the code, so any ESP flow steering requests will fail with not supported error, as it is happening now anyway as no device support this type of API. Link: https://lore.kernel.org/r/634a5face7734381463d809bfb89850f6998deac.1649232994.git.leonro@nvidia.com Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky --- include/linux/mlx5/accel.h | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h index dacf69516002..af67d51308cf 100644 --- a/include/linux/mlx5/accel.h +++ b/include/linux/mlx5/accel.h @@ -111,10 +111,6 @@ struct mlx5_accel_esp_xfrm { struct mlx5_accel_esp_xfrm_attrs attrs; }; -enum { - MLX5_ACCEL_XFRM_FLAG_REQUIRE_METADATA = 1UL << 0, -}; - enum mlx5_accel_ipsec_cap { MLX5_ACCEL_IPSEC_CAP_DEVICE = 1 << 0, MLX5_ACCEL_IPSEC_CAP_REQUIRED_METADATA = 1 << 1, @@ -132,8 +128,7 @@ u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev); struct mlx5_accel_esp_xfrm * mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev, - const struct mlx5_accel_esp_xfrm_attrs *attrs, - u32 flags); + const struct mlx5_accel_esp_xfrm_attrs *attrs); void mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm); int mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, const struct mlx5_accel_esp_xfrm_attrs *attrs); @@ -144,8 +139,10 @@ static inline u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev) { ret static inline struct mlx5_accel_esp_xfrm * mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev, - const struct mlx5_accel_esp_xfrm_attrs *attrs, - u32 flags) { return ERR_PTR(-EOPNOTSUPP); } + const struct mlx5_accel_esp_xfrm_attrs *attrs) +{ + return ERR_PTR(-EOPNOTSUPP); +} static inline void mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm) {} static inline int -- cgit v1.2.3 From 32313c6ae622ed7aa553fa1ee22d8e5f24146f0e Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 6 Apr 2022 11:25:43 +0300 Subject: RDMA/core: Delete IPsec flow action logic from the core The removal of mlx5 flow steering logic, left the kernel without any RDMA drivers that implements flow action callbacks supplied by RDMA/core. Any user access to them caused to EOPNOTSUPP error, which can be achieved by simply removing ioctl implementation. Link: https://lore.kernel.org/r/a638e376314a2eb1c66f597c0bbeeab2e5de7faf.1649232994.git.leonro@nvidia.com Reviewed-by: Raed Salem Acked-by: Jason Gunthorpe Signed-off-by: Leon Romanovsky --- include/rdma/ib_verbs.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 69d883f7fb41..11ee4eaf84bd 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2497,15 +2497,7 @@ struct ib_device_ops { struct ib_flow_attr *flow_attr, struct ib_udata *udata); int (*destroy_flow)(struct ib_flow *flow_id); - struct ib_flow_action *(*create_flow_action_esp)( - struct ib_device *device, - const struct ib_flow_action_attrs_esp *attr, - struct uverbs_attr_bundle *attrs); int (*destroy_flow_action)(struct ib_flow_action *action); - int (*modify_flow_action_esp)( - struct ib_flow_action *action, - const struct ib_flow_action_attrs_esp *attr, - struct uverbs_attr_bundle *attrs); int (*set_vf_link_state)(struct ib_device *device, int vf, u32 port, int state); int (*get_vf_config)(struct ib_device *device, int vf, u32 port, -- cgit v1.2.3 From 2451da081a343e079d9f5a7b063fcdf0bc439aa8 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 6 Apr 2022 11:25:46 +0300 Subject: net/mlx5: Unify device IPsec capabilities check Merge two different function to one in order to provide coherent picture if the device is IPsec capable or not. Link: https://lore.kernel.org/r/8f10ea06ad19c6f651e9fb33921009658f01e1d5.1649232994.git.leonro@nvidia.com Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky --- include/linux/mlx5/accel.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h index af67d51308cf..9145e2d37c0e 100644 --- a/include/linux/mlx5/accel.h +++ b/include/linux/mlx5/accel.h @@ -124,7 +124,7 @@ enum mlx5_accel_ipsec_cap { #ifdef CONFIG_MLX5_ACCEL -u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev); +u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev); struct mlx5_accel_esp_xfrm * mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev, @@ -135,7 +135,10 @@ int mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, #else -static inline u32 mlx5_accel_ipsec_device_caps(struct mlx5_core_dev *mdev) { return 0; } +static inline u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev) +{ + return 0; +} static inline struct mlx5_accel_esp_xfrm * mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev, -- cgit v1.2.3 From 54deb0e77561973f4ca4515e18ab972c281eea1d Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 6 Apr 2022 11:25:48 +0300 Subject: net/mlx5: Remove not-needed IPsec config In current code, the CONFIG_MLX5_IPSEC and CONFIG_MLX5_EN_IPSEC are the same. So remove useless indirection. Link: https://lore.kernel.org/r/fd14492cbc01a0d51a5bfedde02bcd2154123fde.1649232994.git.leonro@nvidia.com Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky --- include/linux/mlx5/accel.h | 4 ++-- include/linux/mlx5/driver.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h index 9145e2d37c0e..73e4d50a9f02 100644 --- a/include/linux/mlx5/accel.h +++ b/include/linux/mlx5/accel.h @@ -122,7 +122,7 @@ enum mlx5_accel_ipsec_cap { MLX5_ACCEL_IPSEC_CAP_TX_IV_IS_ESN = 1 << 7, }; -#ifdef CONFIG_MLX5_ACCEL +#ifdef CONFIG_MLX5_EN_IPSEC u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev); @@ -152,5 +152,5 @@ static inline int mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, const struct mlx5_accel_esp_xfrm_attrs *attrs) { return -EOPNOTSUPP; } -#endif /* CONFIG_MLX5_ACCEL */ +#endif /* CONFIG_MLX5_EN_IPSEC */ #endif /* __MLX5_ACCEL_H__ */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 9424503eb8d3..5af53c035949 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -778,7 +778,7 @@ struct mlx5_core_dev { #ifdef CONFIG_MLX5_FPGA struct mlx5_fpga_device *fpga; #endif -#ifdef CONFIG_MLX5_ACCEL +#ifdef CONFIG_MLX5_EN_IPSEC const struct mlx5_accel_ipsec_ops *ipsec_ops; #endif struct mlx5_clock clock; -- cgit v1.2.3 From f2b41b32cde8453a0a26875261f0e26809c2805a Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 6 Apr 2022 11:25:51 +0300 Subject: net/mlx5: Remove ipsec_ops function table There is only one IPsec implementation and ipsec_ops is not needed at all in this situation. Together with removal of ipsec_ops, we can drop the entry checks as these functions are called for IPsec devices only. Link: https://lore.kernel.org/r/bc8dd1c8a77b65dbf5e2cf92c813ffaca2505c5f.1649232994.git.leonro@nvidia.com Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 5af53c035949..ff47d49d8be4 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -777,9 +777,6 @@ struct mlx5_core_dev { } roce; #ifdef CONFIG_MLX5_FPGA struct mlx5_fpga_device *fpga; -#endif -#ifdef CONFIG_MLX5_EN_IPSEC - const struct mlx5_accel_ipsec_ops *ipsec_ops; #endif struct mlx5_clock clock; struct mlx5_ib_clock_info *clock_info; -- cgit v1.2.3 From 2984287c4c19949d7eb451dcad0bd5c54a2a376f Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 6 Apr 2022 11:25:52 +0300 Subject: net/mlx5: Remove not-implemented IPsec capabilities Clean a capabilities enum to remove not-implemented bits. Link: https://lore.kernel.org/r/1044bb7b779107ff38e48e3f6553421104f3f819.1649232994.git.leonro@nvidia.com Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky --- include/linux/mlx5/accel.h | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h index 73e4d50a9f02..0f2596297f6a 100644 --- a/include/linux/mlx5/accel.h +++ b/include/linux/mlx5/accel.h @@ -113,13 +113,10 @@ struct mlx5_accel_esp_xfrm { enum mlx5_accel_ipsec_cap { MLX5_ACCEL_IPSEC_CAP_DEVICE = 1 << 0, - MLX5_ACCEL_IPSEC_CAP_REQUIRED_METADATA = 1 << 1, - MLX5_ACCEL_IPSEC_CAP_ESP = 1 << 2, - MLX5_ACCEL_IPSEC_CAP_IPV6 = 1 << 3, - MLX5_ACCEL_IPSEC_CAP_LSO = 1 << 4, - MLX5_ACCEL_IPSEC_CAP_RX_NO_TRAILER = 1 << 5, - MLX5_ACCEL_IPSEC_CAP_ESN = 1 << 6, - MLX5_ACCEL_IPSEC_CAP_TX_IV_IS_ESN = 1 << 7, + MLX5_ACCEL_IPSEC_CAP_ESP = 1 << 1, + MLX5_ACCEL_IPSEC_CAP_IPV6 = 1 << 2, + MLX5_ACCEL_IPSEC_CAP_LSO = 1 << 3, + MLX5_ACCEL_IPSEC_CAP_ESN = 1 << 4, }; #ifdef CONFIG_MLX5_EN_IPSEC -- cgit v1.2.3 From efaa0227f6c6a5073951b20cf2f8c63c4155306c Mon Sep 17 00:00:00 2001 From: tangmeng Date: Tue, 15 Feb 2022 14:50:19 +0800 Subject: timers: Move timer sysctl into the timer code This is part of the effort to reduce kernel/sysctl.c to only contain the core logic. Signed-off-by: tangmeng Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20220215065019.7520-1-tangmeng@uniontech.com --- include/linux/timer.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/timer.h b/include/linux/timer.h index fda13c9d1256..648f00105f58 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -196,14 +196,6 @@ extern void init_timers(void); struct hrtimer; extern enum hrtimer_restart it_real_fn(struct hrtimer *); -#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) -struct ctl_table; - -extern unsigned int sysctl_timer_migration; -int timer_migration_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -#endif - unsigned long __round_jiffies(unsigned long j, int cpu); unsigned long __round_jiffies_relative(unsigned long j, int cpu); unsigned long round_jiffies(unsigned long j); -- cgit v1.2.3 From a8b6d6708bb682108d8c899bc0cb7873240daf8a Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 7 Feb 2022 15:38:28 +0100 Subject: iio: core: Enhance the kernel doc of modes and currentmodes iio_dev entries Let's provide more details about these two variables because their understanding may not be straightforward for someone not used to the IIO subsystem internal logic. The different modes will soon be also be more documented for the same reason. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/r/20220207143840.707510-2-miquel.raynal@bootlin.com Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index faf00f2c0be6..f191b80466cd 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -488,8 +488,15 @@ struct iio_buffer_setup_ops { /** * struct iio_dev - industrial I/O device - * @modes: [DRIVER] operating modes supported by device - * @currentmode: [INTERN] current operating mode + * @modes: [DRIVER] bitmask listing all the operating modes + * supported by the IIO device. This list should be + * initialized before registering the IIO device. It can + * also be filed up by the IIO core, as a result of + * enabling particular features in the driver + * (see iio_triggered_event_setup()). + * @currentmode: [INTERN] operating mode currently in use, may be + * eventually checked by device drivers but should be + * considered read-only as this is a core internal bit * @dev: [DRIVER] device structure, should be assigned a parent * and owner * @buffer: [DRIVER] any buffer present -- cgit v1.2.3 From 474010127e2505fc463236470908e1ff5ddb3578 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 7 Feb 2022 15:38:33 +0100 Subject: iio: st_sensors: Add a local lock for protecting odr Right now the (framework) mlock lock is (ab)used for multiple purposes: 1- protecting concurrent accesses over the odr local cache 2- avoid changing samplig frequency whilst buffer is running Let's start by handling situation #1 with a local lock. Suggested-by: Jonathan Cameron Cc: Denis Ciocca Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/r/20220207143840.707510-7-miquel.raynal@bootlin.com Signed-off-by: Jonathan Cameron --- include/linux/iio/common/st_sensors.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 22f67845cdd3..db4a1b260348 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -237,6 +237,7 @@ struct st_sensor_settings { * @hw_irq_trigger: if we're using the hardware interrupt on the sensor. * @hw_timestamp: Latest timestamp from the interrupt handler, when in use. * @buffer_data: Data used by buffer part. + * @odr_lock: Local lock for preventing concurrent ODR accesses/changes */ struct st_sensor_data { struct iio_trigger *trig; @@ -261,6 +262,8 @@ struct st_sensor_data { s64 hw_timestamp; char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] ____cacheline_aligned; + + struct mutex odr_lock; }; #ifdef CONFIG_IIO_BUFFER -- cgit v1.2.3 From 2f53b4adfede66f1bc1c8bb7efd7ced2bad1191a Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 7 Feb 2022 15:38:36 +0100 Subject: iio: Un-inline iio_buffer_enabled() As we are going to hide the currentmode inside the opaque structure, this helper would soon need to call a non-inline function which would simply drop the benefit of having the helper defined inline in a header. One alternative is to move this helper in the core as there is no more interest in defining it inline in a header. We will pay the minor cost either way. Let's do like the iio_device_id() helper which also refers to the opaque structure and gets defined in the core. Suggested-by: Jonathan Cameron Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/r/20220207143840.707510-10-miquel.raynal@bootlin.com Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index f191b80466cd..faabb852128a 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -550,6 +550,7 @@ struct iio_dev { }; int iio_device_id(struct iio_dev *indio_dev); +bool iio_buffer_enabled(struct iio_dev *indio_dev); const struct iio_chan_spec *iio_find_channel_from_si(struct iio_dev *indio_dev, int si); @@ -679,16 +680,6 @@ struct iio_dev *devm_iio_device_alloc(struct device *parent, int sizeof_priv); __printf(2, 3) struct iio_trigger *devm_iio_trigger_alloc(struct device *parent, const char *fmt, ...); -/** - * iio_buffer_enabled() - helper function to test if the buffer is enabled - * @indio_dev: IIO device structure for device - **/ -static inline bool iio_buffer_enabled(struct iio_dev *indio_dev) -{ - return indio_dev->currentmode - & (INDIO_BUFFER_TRIGGERED | INDIO_BUFFER_HARDWARE | - INDIO_BUFFER_SOFTWARE); -} /** * iio_get_debugfs_dentry() - helper function to get the debugfs_dentry -- cgit v1.2.3 From 8c576f87ad7eb639b8bd4472a9bb830e0696dda5 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 7 Feb 2022 15:38:37 +0100 Subject: iio: core: Hide read accesses to iio_dev->currentmode In order to later move this variable within the opaque structure, let's create a helper for accessing it in read-only mode. This helper will be exposed to device drivers and kept accessible for the few that could need it. The write access to this variable however should be fully reserved to the core so in a second step we will hide this variable into the opaque structure. Cc: Eugen Hristev Cc: Nicolas Ferre Cc: Alexandre Belloni Cc: Ludovic Desroches Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/r/20220207143840.707510-11-miquel.raynal@bootlin.com Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index faabb852128a..31098ffa7dc9 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -550,6 +550,7 @@ struct iio_dev { }; int iio_device_id(struct iio_dev *indio_dev); +int iio_device_get_current_mode(struct iio_dev *indio_dev); bool iio_buffer_enabled(struct iio_dev *indio_dev); const struct iio_chan_spec -- cgit v1.2.3 From 51570c9d4b3a678f77a50ac139f67290e946ec86 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 7 Feb 2022 15:38:38 +0100 Subject: iio: core: Move the currentmode entry to the opaque structure This entry should, under no situation, be modified by device drivers. Now that we have limited its read access to device drivers really needing it and did so through a dedicated helper, we can easily move this variable to the opaque structure in order to prevent any further modification from non-authorized code (out of the core, basically). Signed-off-by: Miquel Raynal Reviewed-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20220207143840.707510-12-miquel.raynal@bootlin.com Signed-off-by: Jonathan Cameron --- include/linux/iio/iio-opaque.h | 4 ++++ include/linux/iio/iio.h | 4 ---- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h index 2be12b7b5dc5..6b3586b3f952 100644 --- a/include/linux/iio/iio-opaque.h +++ b/include/linux/iio/iio-opaque.h @@ -7,6 +7,9 @@ * struct iio_dev_opaque - industrial I/O device opaque information * @indio_dev: public industrial I/O device information * @id: used to identify device internally + * @currentmode: operating mode currently in use, may be eventually + * checked by device drivers but should be considered + * read-only as this is a core internal bit * @driver_module: used to make it harder to undercut users * @info_exist_lock: lock to prevent use during removal * @trig_readonly: mark the current trigger immutable @@ -36,6 +39,7 @@ */ struct iio_dev_opaque { struct iio_dev indio_dev; + int currentmode; int id; struct module *driver_module; struct mutex info_exist_lock; diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 31098ffa7dc9..85cb924debd9 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -494,9 +494,6 @@ struct iio_buffer_setup_ops { * also be filed up by the IIO core, as a result of * enabling particular features in the driver * (see iio_triggered_event_setup()). - * @currentmode: [INTERN] operating mode currently in use, may be - * eventually checked by device drivers but should be - * considered read-only as this is a core internal bit * @dev: [DRIVER] device structure, should be assigned a parent * and owner * @buffer: [DRIVER] any buffer present @@ -523,7 +520,6 @@ struct iio_buffer_setup_ops { */ struct iio_dev { int modes; - int currentmode; struct device dev; struct iio_buffer *buffer; -- cgit v1.2.3 From f67c6c73cb07a4778425a2064640333ef7bfa42b Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 7 Feb 2022 15:38:39 +0100 Subject: iio: core: Simplify the registration of kfifo buffers Among all the users of the kfifo buffers, no one uses the INDIO_BUFFER_HARDWARE mode. So let's take this as a general rule and simplify a little bit the internals - overall the documentation - by eliminating unused specific cases. Use the INDIO_BUFFER_SOFTWARE mode by default with kfifo buffers, which will basically mimic what all the "non direct" modes do. Cc: Benson Leung Cc: Guenter Roeck Cc: Jyoti Bhayana Cc: Jean-Baptiste Maneyrol Cc: Lorenzo Bianconi Cc: Michael Hennerich Cc: Greg Kroah-Hartman Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/r/20220207143840.707510-13-miquel.raynal@bootlin.com Signed-off-by: Jonathan Cameron --- include/linux/iio/kfifo_buf.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/iio/kfifo_buf.h b/include/linux/iio/kfifo_buf.h index ccd2ceae7b25..8a83fb58232d 100644 --- a/include/linux/iio/kfifo_buf.h +++ b/include/linux/iio/kfifo_buf.h @@ -12,11 +12,10 @@ void iio_kfifo_free(struct iio_buffer *r); int devm_iio_kfifo_buffer_setup_ext(struct device *dev, struct iio_dev *indio_dev, - int mode_flags, const struct iio_buffer_setup_ops *setup_ops, const struct attribute **buffer_attrs); -#define devm_iio_kfifo_buffer_setup(dev, indio_dev, mode_flags, setup_ops) \ - devm_iio_kfifo_buffer_setup_ext((dev), (indio_dev), (mode_flags), (setup_ops), NULL) +#define devm_iio_kfifo_buffer_setup(dev, indio_dev, setup_ops) \ + devm_iio_kfifo_buffer_setup_ext((dev), (indio_dev), (setup_ops), NULL) #endif -- cgit v1.2.3 From 37943f047bfb88ba4dfc7a522563f57c86d088a0 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 8 Apr 2022 11:31:27 -0700 Subject: tls: rx: simplify async wait Since we are protected from async completions by decrypt_compl_lock we can drop the async_notify and reinit the completion before we start waiting. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/tls.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index a01c264e5f15..6fe78361c8c8 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -152,7 +152,6 @@ struct tls_sw_context_rx { atomic_t decrypt_pending; /* protect crypto_wait with decrypt_pending*/ spinlock_t decrypt_compl_lock; - bool async_notify; }; struct tls_record_info { -- cgit v1.2.3 From 4f1a22ee7b576a38dc5705837c9b0de0c7b5b064 Mon Sep 17 00:00:00 2001 From: John Garry Date: Fri, 8 Apr 2022 17:04:12 +0800 Subject: libata: Improve ATA queued command allocation Improve ATA queued command allocation as follows: - For attaining a qc tag for a SAS host we need to allocate a bit in ata_port.sas_tag_allocated bitmap. However we already have a unique tag per device in range [0, ATA_MAX_QUEUE -1] in the scsi cmnd budget token, so just use that instead. - It is a bit pointless to have ata_qc_new_init() in libata-core.c since it pokes scsi internals, so inline it in ata_scsi_qc_new() (in libata-scsi.c). Also update Doc accordingly. - Use standard SCSI helpers set_host_byte() and set_status_byte() in ata_scsi_qc_new(). Christoph Hellwig originally contributed the change to inline ata_qc_new_init(). Signed-off-by: John Garry Reviewed-by: Christoph Hellwig Signed-off-by: Damien Le Moal --- include/linux/libata.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/libata.h b/include/linux/libata.h index 9b1d3d8b1252..16107122e587 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -820,7 +820,6 @@ struct ata_port { unsigned int cbl; /* cable type; ATA_CBL_xxx */ struct ata_queued_cmd qcmd[ATA_MAX_QUEUE + 1]; - unsigned long sas_tag_allocated; /* for sas tag allocation only */ u64 qc_active; int nr_active_links; /* #links with active qcs */ unsigned int sas_last_tag; /* track next tag hw expects */ -- cgit v1.2.3 From c4212f3eb89fd5654f0a6ed2ee1d13fcb86cb664 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 10 Apr 2022 15:13:24 -0600 Subject: io_uring: flag the fact that linked file assignment is sane Give applications a way to tell if the kernel supports sane linked files, as in files being assigned at the right time to be able to reliably do while using IOSQE_IO_LINK to order them. Not really a bug fix, but flag it as such so that it gets pulled in with backports of the deferred file assignment. Fixes: 6bf9c47a3989 ("io_uring: defer file assignment") Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 784adc6f6ed2..1845cf7c80ba 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -296,6 +296,7 @@ struct io_uring_params { #define IORING_FEAT_NATIVE_WORKERS (1U << 9) #define IORING_FEAT_RSRC_TAGS (1U << 10) #define IORING_FEAT_CQE_SKIP (1U << 11) +#define IORING_FEAT_LINKED_FILE (1U << 12) /* * io_uring_register(2) opcodes and arguments -- cgit v1.2.3 From c1b8a56755ee121f9fa374de9eec36c91a7da25f Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Thu, 7 Apr 2022 14:20:49 +0800 Subject: net: sock: introduce sock_queue_rcv_skb_reason() In order to report the reasons of skb drops in 'sock_queue_rcv_skb()', introduce the function 'sock_queue_rcv_skb_reason()'. As the return value of 'sock_queue_rcv_skb()' is used as the error code, we can't make it as drop reason and have to pass extra output argument. 'sock_queue_rcv_skb()' is used in many places, so we can't change it directly. Introduce the new function 'sock_queue_rcv_skb_reason()' and make 'sock_queue_rcv_skb()' an inline call to it. Reviewed-by: Hao Peng Reviewed-by: Jiang Biao Signed-off-by: Menglong Dong Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/sock.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index c4b91fc19b9c..1a988e605f09 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2392,7 +2392,14 @@ int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue, void (*destructor)(struct sock *sk, struct sk_buff *skb)); int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); -int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); + +int sock_queue_rcv_skb_reason(struct sock *sk, struct sk_buff *skb, + enum skb_drop_reason *reason); + +static inline int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +{ + return sock_queue_rcv_skb_reason(sk, skb, NULL); +} int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb); struct sk_buff *sock_dequeue_err_skb(struct sock *sk); -- cgit v1.2.3 From 9f8ed577c28813410614b418bad42285840c1a00 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Thu, 7 Apr 2022 14:20:50 +0800 Subject: net: skb: rename SKB_DROP_REASON_PTYPE_ABSENT As David Ahern suggested, the reasons for skb drops should be more general and not be code based. Therefore, rename SKB_DROP_REASON_PTYPE_ABSENT to SKB_DROP_REASON_UNHANDLED_PROTO, which is used for the cases of no L3 protocol handler, no L4 protocol handler, version extensions, etc. From previous discussion, now we have the aim to make these reasons more abstract and users based, avoiding code based. Signed-off-by: Menglong Dong Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 8 +++----- include/trace/events/skb.h | 2 +- 2 files changed, 4 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2394441fa3dd..173bc35a10a3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -408,11 +408,9 @@ enum skb_drop_reason { */ SKB_DROP_REASON_XDP, /* dropped by XDP in input path */ SKB_DROP_REASON_TC_INGRESS, /* dropped in TC ingress HOOK */ - SKB_DROP_REASON_PTYPE_ABSENT, /* not packet_type found to handle - * the skb. For an etner packet, - * this means that L3 protocol is - * not supported - */ + SKB_DROP_REASON_UNHANDLED_PROTO, /* protocol not implemented + * or not supported + */ SKB_DROP_REASON_SKB_CSUM, /* sk_buff checksum computation * error */ diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index e1670e1e4934..85abd7cbd221 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -50,7 +50,7 @@ EM(SKB_DROP_REASON_CPU_BACKLOG, CPU_BACKLOG) \ EM(SKB_DROP_REASON_XDP, XDP) \ EM(SKB_DROP_REASON_TC_INGRESS, TC_INGRESS) \ - EM(SKB_DROP_REASON_PTYPE_ABSENT, PTYPE_ABSENT) \ + EM(SKB_DROP_REASON_UNHANDLED_PROTO, UNHANDLED_PROTO) \ EM(SKB_DROP_REASON_SKB_CSUM, SKB_CSUM) \ EM(SKB_DROP_REASON_SKB_GSO_SEG, SKB_GSO_SEG) \ EM(SKB_DROP_REASON_SKB_UCOPY_FAULT, SKB_UCOPY_FAULT) \ -- cgit v1.2.3 From b384c95a861eebf47e88695cf6a29f34e0b10b0f Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Thu, 7 Apr 2022 14:20:52 +0800 Subject: net: icmp: add skb drop reasons to icmp protocol Replace kfree_skb() used in icmp_rcv() and icmpv6_rcv() with kfree_skb_reason(). In order to get the reasons of the skb drops after icmp message handle, we change the return type of 'handler()' in 'struct icmp_control' from 'bool' to 'enum skb_drop_reason'. This may change its original intention, as 'false' means failure, but 'SKB_NOT_DROPPED_YET' means success now. Therefore, all 'handler' and the call of them need to be handled. Following 'handler' functions are involved: icmp_unreach() icmp_redirect() icmp_echo() icmp_timestamp() icmp_discard() And following new drop reasons are added: SKB_DROP_REASON_ICMP_CSUM SKB_DROP_REASON_INVALID_PROTO The reason 'INVALID_PROTO' is introduced for the case that the packet doesn't follow rfc 1122 and is dropped. This is not a common case, and I believe we can locate the problem from the data in the packet. For now, this 'INVALID_PROTO' is used for the icmp broadcasts with wrong types. Maybe there should be a document file for these reasons. For example, list all the case that causes the 'UNHANDLED_PROTO' and 'INVALID_PROTO' drop reason. Therefore, users can locate their problems according to the document. Reviewed-by: Hao Peng Reviewed-by: Jiang Biao Signed-off-by: Menglong Dong Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 +++++ include/net/ping.h | 2 +- include/trace/events/skb.h | 2 ++ 3 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 173bc35a10a3..9b81ba497665 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -442,6 +442,11 @@ enum skb_drop_reason { SKB_DROP_REASON_TAP_TXFILTER, /* dropped by tx filter implemented * at tun/tap, e.g., check_filter() */ + SKB_DROP_REASON_ICMP_CSUM, /* ICMP checksum error */ + SKB_DROP_REASON_INVALID_PROTO, /* the packet doesn't follow RFC + * 2211, such as a broadcasts + * ICMP_TIMESTAMP + */ SKB_DROP_REASON_MAX, }; diff --git a/include/net/ping.h b/include/net/ping.h index 2fe78874318c..b68fbfdb606f 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -76,7 +76,7 @@ int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, void *user_icmph, size_t icmph_len); int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); -bool ping_rcv(struct sk_buff *skb); +enum skb_drop_reason ping_rcv(struct sk_buff *skb); #ifdef CONFIG_PROC_FS void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family); diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 85abd7cbd221..42647114fffe 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -61,6 +61,8 @@ EM(SKB_DROP_REASON_HDR_TRUNC, HDR_TRUNC) \ EM(SKB_DROP_REASON_TAP_FILTER, TAP_FILTER) \ EM(SKB_DROP_REASON_TAP_TXFILTER, TAP_TXFILTER) \ + EM(SKB_DROP_REASON_ICMP_CSUM, ICMP_CSUM) \ + EM(SKB_DROP_REASON_INVALID_PROTO, INVALID_PROTO) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From 2e2ac4a3327479f7e2744cdd88a5c823f2057bad Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Wed, 6 Apr 2022 22:15:20 +0200 Subject: tty: goldfish: Introduce gf_ioread32()/gf_iowrite32() The goldfish TTY device was clearly defined as having little-endian registers, but the switch to __raw_{read,write}l(() broke its driver when running on big-endian kernels (if anyone ever tried this). The m68k qemu implementation got this wrong, and assumed native-endian registers. While this is a bug in qemu, it is probably impossible to fix that since there is no way of knowing which other operating systems have started relying on that bug over the years. Hence revert commit da31de35cd2f ("tty: goldfish: use __raw_writel()/__raw_readl()", and define gf_ioread32()/gf_iowrite32() to be able to use accessors defined by the architecture. Cc: stable@vger.kernel.org # v5.11+ Fixes: da31de35cd2fb78f ("tty: goldfish: use __raw_writel()/__raw_readl()") Signed-off-by: Laurent Vivier Link: https://lore.kernel.org/r/20220406201523.243733-2-laurent@vivier.eu [geert: Add rationale based on Arnd's comments] Signed-off-by: Geert Uytterhoeven --- include/linux/goldfish.h | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/goldfish.h b/include/linux/goldfish.h index 12be1601fd84..bcc17f95b906 100644 --- a/include/linux/goldfish.h +++ b/include/linux/goldfish.h @@ -8,14 +8,21 @@ /* Helpers for Goldfish virtual platform */ +#ifndef gf_ioread32 +#define gf_ioread32 ioread32 +#endif +#ifndef gf_iowrite32 +#define gf_iowrite32 iowrite32 +#endif + static inline void gf_write_ptr(const void *ptr, void __iomem *portl, void __iomem *porth) { const unsigned long addr = (unsigned long)ptr; - __raw_writel(lower_32_bits(addr), portl); + gf_iowrite32(lower_32_bits(addr), portl); #ifdef CONFIG_64BIT - __raw_writel(upper_32_bits(addr), porth); + gf_iowrite32(upper_32_bits(addr), porth); #endif } @@ -23,9 +30,9 @@ static inline void gf_write_dma_addr(const dma_addr_t addr, void __iomem *portl, void __iomem *porth) { - __raw_writel(lower_32_bits(addr), portl); + gf_iowrite32(lower_32_bits(addr), portl); #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT - __raw_writel(upper_32_bits(addr), porth); + gf_iowrite32(upper_32_bits(addr), porth); #endif } -- cgit v1.2.3 From c92e7ef16400bf035e8b49c7dd091bfce4f99773 Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Wed, 6 Apr 2022 22:15:22 +0200 Subject: clocksource/drivers: Add a goldfish-timer clocksource Add a clocksource based on the goldfish-rtc device. Move the timer register definition to This kernel implementation is based on the QEMU upstream implementation: https://git.qemu.org/?p=qemu.git;a=blob_plain;f=hw/rtc/goldfish_rtc.c goldfish-timer is a high-precision signed 64-bit nanosecond timer. It is part of the 'goldfish' virtual hardware platform used to run some emulated Android systems under QEMU. This timer only supports oneshot event. Signed-off-by: Laurent Vivier Acked-by: Daniel Lezcano Link: https://lore.kernel.org/r/20220406201523.243733-4-laurent@vivier.eu Signed-off-by: Geert Uytterhoeven --- include/clocksource/timer-goldfish.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) create mode 100644 include/clocksource/timer-goldfish.h (limited to 'include') diff --git a/include/clocksource/timer-goldfish.h b/include/clocksource/timer-goldfish.h new file mode 100644 index 000000000000..05a3a4f610d6 --- /dev/null +++ b/include/clocksource/timer-goldfish.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * goldfish-timer clocksource + * Registers definition for the goldfish-timer device + */ + +#ifndef _CLOCKSOURCE_TIMER_GOLDFISH_H +#define _CLOCKSOURCE_TIMER_GOLDFISH_H + +/* + * TIMER_TIME_LOW get low bits of current time and update TIMER_TIME_HIGH + * TIMER_TIME_HIGH get high bits of time at last TIMER_TIME_LOW read + * TIMER_ALARM_LOW set low bits of alarm and activate it + * TIMER_ALARM_HIGH set high bits of next alarm + * TIMER_IRQ_ENABLED enable alarm interrupt + * TIMER_CLEAR_ALARM disarm an existing alarm + * TIMER_ALARM_STATUS alarm status (running or not) + * TIMER_CLEAR_INTERRUPT clear interrupt + */ +#define TIMER_TIME_LOW 0x00 +#define TIMER_TIME_HIGH 0x04 +#define TIMER_ALARM_LOW 0x08 +#define TIMER_ALARM_HIGH 0x0c +#define TIMER_IRQ_ENABLED 0x10 +#define TIMER_CLEAR_ALARM 0x14 +#define TIMER_ALARM_STATUS 0x18 +#define TIMER_CLEAR_INTERRUPT 0x1c + +extern int goldfish_timer_init(int irq, void __iomem *base); + +#endif /* _CLOCKSOURCE_TIMER_GOLDFISH_H */ -- cgit v1.2.3 From e5c95ca094cfe59a4013d711f87ff034cba30f80 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Mon, 4 Apr 2022 23:01:08 +0200 Subject: mac80211: Improve confusing comment around tx_info clearing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The comment above the ieee80211_tx_info_clear_status() helper was somewhat confusing as to which fields it was or wasn't clearing. So replace it by something that is hopefully more, well, clear. Signed-off-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/r/20220404210108.2684907-1-toke@toke.dk Signed-off-by: Johannes Berg --- include/net/mac80211.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 382ebb862ea8..db992f71604d 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1201,9 +1201,9 @@ static inline struct ieee80211_rx_status *IEEE80211_SKB_RXCB(struct sk_buff *skb * in the TX status but the rate control information (it does clear * the count since you need to fill that in anyway). * - * NOTE: You can only use this function if you do NOT use - * info->driver_data! Use info->rate_driver_data - * instead if you need only the less space that allows. + * NOTE: While the rates array is kept intact, this will wipe all of the + * driver_data fields in info, so it's up to the driver to restore + * any fields it needs after calling this helper. */ static inline void ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) -- cgit v1.2.3 From 6d945a33f2b0aa24fc210dadaa0af3e8218e7002 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 25 Mar 2022 11:42:41 +0100 Subject: mac80211: introduce BSS color collision detection Add ieee80211_rx_check_bss_color_collision routine in order to introduce BSS color collision detection in mac80211 if it is not supported in HW/FW (e.g. for mt7915 chipset). Add IEEE80211_HW_DETECTS_COLOR_COLLISION flag to let the driver notify BSS color collision detection is supported in HW/FW. Set this for ath11k which apparently didn't need this code. Tested-by: Peter Chiu Co-developed-by: Ryder Lee Signed-off-by: Ryder Lee Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/a05eeeb1841a84560dc5aaec77894fcb69a54f27.1648204871.git.lorenzo@kernel.org [clarify commit message a bit, move flag to mac80211] Signed-off-by: Johannes Berg --- include/net/mac80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index db992f71604d..0943b2626f4d 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2434,6 +2434,9 @@ struct ieee80211_txq { * usage and 802.11 frames with %RX_FLAG_ONLY_MONITOR set for monitor to * the stack. * + * @IEEE80211_HW_DETECTS_COLOR_COLLISION: HW/driver has support for BSS color + * collision detection and doesn't need it in software. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2489,6 +2492,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_TX_ENCAP_OFFLOAD, IEEE80211_HW_SUPPORTS_RX_DECAP_OFFLOAD, IEEE80211_HW_SUPPORTS_CONC_MON_RX_DECAP, + IEEE80211_HW_DETECTS_COLOR_COLLISION, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS -- cgit v1.2.3 From 2d7991fe867974a8e5065ee9691451a406b9320d Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 11 Mar 2022 16:23:22 -0700 Subject: dmaengine: idxd: update IAA definitions for user header Add additional structure definitions for Intel In-memory Analytics Accelerator (IAA/IAX). See specification (1) for more details. 1: https://cdrdv2.intel.com/v1/dl/getContent/721858 Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/164704100212.1373038.18362680016033557757.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul --- include/uapi/linux/idxd.h | 31 ++++++++++++++++++++++++++++--- 1 file changed, 28 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index a8f0ff75c430..bce7c43657d5 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -53,6 +53,11 @@ enum idxd_scmd_stat { /* IAX */ #define IDXD_OP_FLAG_RD_SRC2_AECS 0x010000 +#define IDXD_OP_FLAG_RD_SRC2_2ND 0x020000 +#define IDXD_OP_FLAG_WR_SRC2_AECS_COMP 0x040000 +#define IDXD_OP_FLAG_WR_SRC2_AECS_OVFL 0x080000 +#define IDXD_OP_FLAG_SRC2_STS 0x100000 +#define IDXD_OP_FLAG_CRC_RFC3720 0x200000 /* Opcode */ enum dsa_opcode { @@ -81,6 +86,18 @@ enum iax_opcode { IAX_OPCODE_MEMMOVE, IAX_OPCODE_DECOMPRESS = 0x42, IAX_OPCODE_COMPRESS, + IAX_OPCODE_CRC64, + IAX_OPCODE_ZERO_DECOMP_32 = 0x48, + IAX_OPCODE_ZERO_DECOMP_16, + IAX_OPCODE_DECOMP_32 = 0x4c, + IAX_OPCODE_DECOMP_16, + IAX_OPCODE_SCAN = 0x50, + IAX_OPCODE_SET_MEMBER, + IAX_OPCODE_EXTRACT, + IAX_OPCODE_SELECT, + IAX_OPCODE_RLE_BURST, + IAX_OPCDE_FIND_UNIQUE, + IAX_OPCODE_EXPAND, }; /* Completion record status */ @@ -120,6 +137,7 @@ enum iax_completion_status { IAX_COMP_NONE = 0, IAX_COMP_SUCCESS, IAX_COMP_PAGE_FAULT_IR = 0x04, + IAX_COMP_ANALYTICS_ERROR = 0x0a, IAX_COMP_OUTBUF_OVERFLOW, IAX_COMP_BAD_OPCODE = 0x10, IAX_COMP_INVALID_FLAGS, @@ -140,7 +158,10 @@ enum iax_completion_status { IAX_COMP_WATCHDOG, IAX_COMP_INVALID_COMP_FLAG = 0x30, IAX_COMP_INVALID_FILTER_FLAG, - IAX_COMP_INVALID_NUM_ELEMS = 0x33, + IAX_COMP_INVALID_INPUT_SIZE, + IAX_COMP_INVALID_NUM_ELEMS, + IAX_COMP_INVALID_SRC1_WIDTH, + IAX_COMP_INVALID_INVERT_OUT, }; #define DSA_COMP_STATUS_MASK 0x7f @@ -319,8 +340,12 @@ struct iax_completion_record { uint32_t output_size; uint8_t output_bits; uint8_t rsvd3; - uint16_t rsvd4; - uint64_t rsvd5[4]; + uint16_t xor_csum; + uint32_t crc; + uint32_t min; + uint32_t max; + uint32_t sum; + uint64_t rsvd4[2]; } __attribute__((packed)); struct iax_raw_completion_record { -- cgit v1.2.3 From 52126d4c03798cc55aa927fea4c776ab26b5a5f0 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 6 Feb 2022 10:47:45 +0100 Subject: dmaengine: Remove a useless mutex According to lib/idr.c, The IDA handles its own locking. It is safe to call any of the IDA functions without synchronisation in your code. so the 'chan_mutex' mutex can just be removed. It is here only to protect some ida_alloc()/ida_free() calls. Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/7180452c1d77b039e27b6f9418e0e7d9dd33c431.1644140845.git.christophe.jaillet@wanadoo.fr Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 842d4f7ca752..6db9e03afd0b 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -870,7 +870,6 @@ struct dma_device { struct device *dev; struct module *owner; struct ida chan_ida; - struct mutex chan_mutex; /* to protect chan_ida */ u32 src_addr_widths; u32 dst_addr_widths; -- cgit v1.2.3 From 046d2e7c50e3087a32a85fd384c21f896dbccf83 Mon Sep 17 00:00:00 2001 From: Sriram R Date: Mon, 4 Apr 2022 21:11:23 +0530 Subject: mac80211: prepare sta handling for MLO support Currently in mac80211 each STA object is represented using sta_info datastructure with the associated STA specific information and drivers access ieee80211_sta part of it. With MLO (Multi Link Operation) support being added in 802.11be standard, though the association is logically with a single Multi Link capable STA, at the physical level communication can happen via different advertised links (uniquely identified by Channel, operating class, BSSID) and hence the need to handle multiple link STA parameters within a composite sta_info object called the MLD STA. The different link STA part of MLD STA are identified using the link address which can be same or different as the MLD STA address and unique link id based on the link vif. To support extension of such a model, the sta_info datastructure is modified to hold multiple link STA objects with link specific params currently within sta_info moved to this new structure. Similarly this is done for ieee80211_sta as well which will be accessed within mac80211 as well as by drivers, hence trivial driver changes are expected to support this. For current non MLO supported drivers, only one link STA is present and link information is accessed via 'deflink' member. For MLO drivers, we still need to define the APIs etc. to get the correct link ID and access the correct part of the station info. Currently in mac80211, all link STA info are accessed directly via deflink. These will be updated to access via link pointers indexed by link id with MLO support patches, with link id being 0 for non MLO supported cases. Except for couple of macro related changes, below spatch takes care of updating mac80211 and driver code to access to the link STA info via deflink. @ieee80211_sta@ struct ieee80211_sta *s; struct sta_info *si; identifier var = {supp_rates, ht_cap, vht_cap, he_cap, he_6ghz_capa, eht_cap, rx_nss, bandwidth, txpwr}; @@ ( s-> - var + deflink.var | si->sta. - var + deflink.var ) @sta_info@ struct sta_info *si; identifier var = {gtk, pcpu_rx_stats, rx_stats, rx_stats_avg, status_stats, tx_stats, cur_max_bandwidth}; @@ ( si-> - var + deflink.var ) Signed-off-by: Sriram R Link: https://lore.kernel.org/r/1649086883-13246-1-git-send-email-quic_srirrama@quicinc.com [remove MLO-drivers notes from commit message, not clear yet; run spatch] Signed-off-by: Johannes Berg --- include/net/mac80211.h | 80 ++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 58 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 0943b2626f4d..75880fc70700 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2056,6 +2056,45 @@ struct ieee80211_sta_txpwr { enum nl80211_tx_power_setting type; }; +#define MAX_STA_LINKS 15 + +/** + * struct ieee80211_link_sta - station Link specific info + * All link specific info for a STA link for a non MLD STA(single) + * or a MLD STA(multiple entries) are stored here. + * + * @addr: MAC address of the Link STA. For non-MLO STA this is same as the addr + * in ieee80211_sta. For MLO Link STA this addr can be same or different + * from addr in ieee80211_sta (representing MLD STA addr) + * @supp_rates: Bitmap of supported rates + * @ht_cap: HT capabilities of this STA; restricted to our own capabilities + * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities + * @he_cap: HE capabilities of this STA + * @he_6ghz_capa: on 6 GHz, holds the HE 6 GHz band capabilities + * @eht_cap: EHT capabilities of this STA + * @bandwidth: current bandwidth the station can receive with + * @rx_nss: in HT/VHT, the maximum number of spatial streams the + * station can receive at the moment, changed by operating mode + * notifications and capabilities. The value is only valid after + * the station moves to associated state. + * @txpwr: the station tx power configuration + * + */ +struct ieee80211_link_sta { + u8 addr[ETH_ALEN]; + + u32 supp_rates[NUM_NL80211_BANDS]; + struct ieee80211_sta_ht_cap ht_cap; + struct ieee80211_sta_vht_cap vht_cap; + struct ieee80211_sta_he_cap he_cap; + struct ieee80211_he_6ghz_capa he_6ghz_capa; + struct ieee80211_sta_eht_cap eht_cap; + + u8 rx_nss; + enum ieee80211_sta_rx_bandwidth bandwidth; + struct ieee80211_sta_txpwr txpwr; +}; + /** * struct ieee80211_sta - station table entry * @@ -2065,15 +2104,11 @@ struct ieee80211_sta_txpwr { * either be protected by rcu_read_lock() explicitly or implicitly, * or you must take good care to not use such a pointer after a * call to your sta_remove callback that removed it. + * This also represents the MLD STA in case of MLO association + * and holds pointers to various link STA's * * @addr: MAC address * @aid: AID we assigned to the station if we're an AP - * @supp_rates: Bitmap of supported rates (per band) - * @ht_cap: HT capabilities of this STA; restricted to our own capabilities - * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities - * @he_cap: HE capabilities of this STA - * @he_6ghz_capa: on 6 GHz, holds the HE 6 GHz band capabilities - * @eht_cap: EHT capabilities of this STA * @max_rx_aggregation_subframes: maximal amount of frames in a single AMPDU * that this station is allowed to transmit to us. * Can be modified by driver. @@ -2085,11 +2120,6 @@ struct ieee80211_sta_txpwr { * if wme is supported. The bits order is like in * IEEE80211_WMM_IE_STA_QOSINFO_AC_*. * @max_sp: max Service Period. Only valid if wme is supported. - * @bandwidth: current bandwidth the station can receive with - * @rx_nss: in HT/VHT, the maximum number of spatial streams the - * station can receive at the moment, changed by operating mode - * notifications and capabilities. The value is only valid after - * the station moves to associated state. * @smps_mode: current SMPS mode (off, static or dynamic) * @rates: rate control selection table * @tdls: indicates whether the STA is a TDLS peer @@ -2102,25 +2132,28 @@ struct ieee80211_sta_txpwr { * @support_p2p_ps: indicates whether the STA supports P2P PS mechanism or not. * @max_rc_amsdu_len: Maximum A-MSDU size in bytes recommended by rate control. * @max_tid_amsdu_len: Maximum A-MSDU size in bytes for this TID - * @txpwr: the station tx power configuration * @txq: per-TID data TX queues (if driver uses the TXQ abstraction); note that * the last entry (%IEEE80211_NUM_TIDS) is used for non-data frames + * @multi_link_sta: Identifies if this sta is a MLD STA + * @deflink: This holds the default link STA information, for non MLO STA all link + * specific STA information is accessed through @deflink or through + * link[0] which points to address of @deflink. For MLO Link STA + * the first added link STA will point to deflink. + * @link: reference to Link Sta entries. For Non MLO STA, except 1st link, + * i.e link[0] all links would be assigned to NULL by default and + * would access link information via @deflink or link[0]. For MLO + * STA, first link STA being added will point its link pointer to + * @deflink address and remaining would be allocated and the address + * would be assigned to link[link_id] where link_id is the id assigned + * by the AP. */ struct ieee80211_sta { - u32 supp_rates[NUM_NL80211_BANDS]; u8 addr[ETH_ALEN]; u16 aid; - struct ieee80211_sta_ht_cap ht_cap; - struct ieee80211_sta_vht_cap vht_cap; - struct ieee80211_sta_he_cap he_cap; - struct ieee80211_he_6ghz_capa he_6ghz_capa; - struct ieee80211_sta_eht_cap eht_cap; u16 max_rx_aggregation_subframes; bool wme; u8 uapsd_queues; u8 max_sp; - u8 rx_nss; - enum ieee80211_sta_rx_bandwidth bandwidth; enum ieee80211_smps_mode smps_mode; struct ieee80211_sta_rates __rcu *rates; bool tdls; @@ -2147,10 +2180,13 @@ struct ieee80211_sta { bool support_p2p_ps; u16 max_rc_amsdu_len; u16 max_tid_amsdu_len[IEEE80211_NUM_TIDS]; - struct ieee80211_sta_txpwr txpwr; struct ieee80211_txq *txq[IEEE80211_NUM_TIDS + 1]; + bool multi_link_sta; + struct ieee80211_link_sta deflink; + struct ieee80211_link_sta *link[MAX_STA_LINKS]; + /* must be last */ u8 drv_priv[] __aligned(sizeof(void *)); }; @@ -6371,7 +6407,7 @@ static inline int rate_supported(struct ieee80211_sta *sta, enum nl80211_band band, int index) { - return (sta == NULL || sta->supp_rates[band] & BIT(index)); + return (sta == NULL || sta->deflink.supp_rates[band] & BIT(index)); } static inline s8 -- cgit v1.2.3 From 95ebe80d99de3cb849c522a1f768e5e8befa0b7c Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 20 Jan 2022 13:16:18 -0800 Subject: srcu: Fix s/is/if/ typo in srcu_node comment This commit fixed a typo in the srcu_node structure's ->srcu_have_cbs comment. While in the area, redo a couple of comments to take advantage of 100-character line lengths. Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index cb1f4351e8ba..4025840ba9a3 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -47,11 +47,9 @@ struct srcu_data { */ struct srcu_node { spinlock_t __private lock; - unsigned long srcu_have_cbs[4]; /* GP seq for children */ - /* having CBs, but only */ - /* is > ->srcu_gq_seq. */ - unsigned long srcu_data_have_cbs[4]; /* Which srcu_data structs */ - /* have CBs for given GP? */ + unsigned long srcu_have_cbs[4]; /* GP seq for children having CBs, but only */ + /* if greater than ->srcu_gq_seq. */ + unsigned long srcu_data_have_cbs[4]; /* Which srcu_data structs have CBs for given GP? */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ struct srcu_node *srcu_parent; /* Next up in tree. */ int grplo; /* Least CPU for node. */ -- cgit v1.2.3 From 994f706872e6ce080506bd795ecf783d5b617de6 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 24 Jan 2022 09:46:57 -0800 Subject: srcu: Make Tree SRCU able to operate without snp_node array This commit makes Tree SRCU able to operate without an snp_node array, that is, when the srcu_data structures' ->mynode pointers are NULL. This can result in high contention on the srcu_struct structure's ->lock, but only when there are lots of call_srcu(), synchronize_srcu(), and synchronize_srcu_expedited() calls. Note that when there is no snp_node array, all SRCU callbacks use CPU 0's callback queue. This is optimal in the common case of low update-side load because it removes the need to search each CPU for the single callback that made the grace period happen. Co-developed-by: Neeraj Upadhyay Signed-off-by: Neeraj Upadhyay Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 4025840ba9a3..8d1da136a93a 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -63,8 +63,9 @@ struct srcu_struct { struct srcu_node node[NUM_RCU_NODES]; /* Combining tree. */ struct srcu_node *level[RCU_NUM_LVLS + 1]; /* First node at each level. */ + int srcu_size_state; /* Small-to-big transition state. */ struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ - spinlock_t __private lock; /* Protect counters */ + spinlock_t __private lock; /* Protect counters and size state. */ struct mutex srcu_gp_mutex; /* Serialize GP work. */ unsigned int srcu_idx; /* Current rdr array element. */ unsigned long srcu_gp_seq; /* Grace-period seq #. */ @@ -83,6 +84,17 @@ struct srcu_struct { struct lockdep_map dep_map; }; +/* Values for size state variable (->srcu_size_state). */ +#define SRCU_SIZE_SMALL 0 +#define SRCU_SIZE_ALLOC 1 +#define SRCU_SIZE_WAIT_BARRIER 2 +#define SRCU_SIZE_WAIT_CALL 3 +#define SRCU_SIZE_WAIT_CBS1 4 +#define SRCU_SIZE_WAIT_CBS2 5 +#define SRCU_SIZE_WAIT_CBS3 6 +#define SRCU_SIZE_WAIT_CBS4 7 +#define SRCU_SIZE_BIG 8 + /* Values for state variable (bottom bits of ->srcu_gp_seq). */ #define SRCU_STATE_IDLE 0 #define SRCU_STATE_SCAN1 1 -- cgit v1.2.3 From 2ec303113d978931ef368886c4c6bc854493e8bf Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 21 Jan 2022 16:13:52 -0800 Subject: srcu: Dynamically allocate srcu_node array This commit shrinks the srcu_struct structure by converting its ->node field from a fixed-size compile-time array to a pointer to a dynamically allocated array. In kernels built with large values of NR_CPUS that boot on systems with smaller numbers of CPUs, this can save significant memory. [ paulmck: Apply kernel test robot feedback. ] Reported-by: A cast of thousands Co-developed-by: Neeraj Upadhyay Signed-off-by: Neeraj Upadhyay Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 8d1da136a93a..8501b6b45941 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -60,7 +60,7 @@ struct srcu_node { * Per-SRCU-domain structure, similar in function to rcu_state. */ struct srcu_struct { - struct srcu_node node[NUM_RCU_NODES]; /* Combining tree. */ + struct srcu_node *node; /* Combining tree. */ struct srcu_node *level[RCU_NUM_LVLS + 1]; /* First node at each level. */ int srcu_size_state; /* Small-to-big transition state. */ -- cgit v1.2.3 From db8f1471c61336477e2bf74dcb00e67d650e6dea Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 26 Jan 2022 10:03:54 -0500 Subject: srcu: Use export for srcu_struct defined by DEFINE_STATIC_SRCU() If an srcu_struct structure defined by tree SRCU's DEFINE_STATIC_SRCU() is used by a module, sparse will give the following diagnostic: sparse: symbol '__srcu_struct_nodes_srcu' was not declared. Should it be static? The problem is that a within-module DEFINE_STATIC_SRCU() must define a non-static srcu_struct because it is exported by referencing it in a special '__section("___srcu_struct_ptrs")'. This reference is needed so that module load and unloading can invoke init_srcu_struct() and cleanup_srcu_struct(), respectively. Unfortunately, sparse is unaware of '__section("___srcu_struct_ptrs")', resulting in the above false-positive diagnostic. To avoid this false positive, this commit therefore creates a prototype of the srcu_struct with an "extern" keyword. Signed-off-by: Alexander Aring Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 8501b6b45941..44e998643f48 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -131,6 +131,7 @@ struct srcu_struct { #ifdef MODULE # define __DEFINE_SRCU(name, is_static) \ is_static struct srcu_struct name; \ + extern struct srcu_struct * const __srcu_struct_##name; \ struct srcu_struct * const __srcu_struct_##name \ __section("___srcu_struct_ptrs") = &name #else -- cgit v1.2.3 From 46470cf85d2b61abd37c6f66c4dacc1bc510d10f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 27 Jan 2022 13:20:49 -0800 Subject: srcu: Prevent cleanup_srcu_struct() from freeing non-dynamic ->sda When an srcu_struct structure is created (but not in a kernel module) by DEFINE_SRCU() and friends, the per-CPU srcu_data structure is statically allocated. In all other cases, that structure is obtained from alloc_percpu(), in which case cleanup_srcu_struct() must invoke free_percpu() on the resulting ->sda pointer in the srcu_struct pointer. Which it does. Except that it also invokes free_percpu() on the ->sda pointer referencing the statically allocated per-CPU srcu_data structures. Which free_percpu() is surprisingly OK with. This commit nevertheless stops cleanup_srcu_struct() from freeing statically allocated per-CPU srcu_data structures. Co-developed-by: Neeraj Upadhyay Signed-off-by: Neeraj Upadhyay Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 44e998643f48..44bd204498a1 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -73,6 +73,7 @@ struct srcu_struct { unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ unsigned long srcu_last_gp_end; /* Last GP end timestamp (ns) */ struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ + bool sda_is_static; /* May ->sda be passed to free_percpu()? */ unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */ struct mutex srcu_barrier_mutex; /* Serialize barrier ops. */ struct completion srcu_barrier_completion; -- cgit v1.2.3 From 9f2e91d94c91558e3764fe4e01c5e6281a90f239 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 27 Jan 2022 20:32:05 -0800 Subject: srcu: Add contention-triggered addition of srcu_node tree This commit instruments the acquisitions of the srcu_struct structure's ->lock, enabling the initiation of a transition from SRCU_SIZE_SMALL to SRCU_SIZE_BIG when sufficient contention is experienced. The instrumentation counts the number of trylock failures within the confines of a single jiffy. If that number exceeds the value specified by the srcutree.small_contention_lim kernel boot parameter (which defaults to 100), and if the value specified by the srcutree.convert_to_big kernel boot parameter has the 0x10 bit set (defaults to 0), then a transition will be automatically initiated. By default, there will never be any transitions, so that none of the srcu_struct structures ever gains an srcu_node array. The useful values for srcutree.convert_to_big are: 0x00: Never convert. 0x01: Always convert at init_srcu_struct() time. 0x02: Convert when rcutorture prints its first round of statistics. 0x03: Decide conversion approach at boot given system size. 0x10: Convert if contention is encountered. 0x12: Convert if contention is encountered or when rcutorture prints its first round of statistics, whichever comes first. The value 0x11 acts the same as 0x01 because the conversion happens before there is any chance of contention. [ paulmck: Apply "static" feedback from kernel test robot. ] Co-developed-by: Neeraj Upadhyay Signed-off-by: Neeraj Upadhyay Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 44bd204498a1..1b9ff4ed37e4 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -72,6 +72,8 @@ struct srcu_struct { unsigned long srcu_gp_seq_needed; /* Latest gp_seq needed. */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ unsigned long srcu_last_gp_end; /* Last GP end timestamp (ns) */ + unsigned long srcu_size_jiffies; /* Current contention-measurement interval. */ + unsigned long srcu_n_lock_retries; /* Contention events in current interval. */ struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ bool sda_is_static; /* May ->sda be passed to free_percpu()? */ unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */ -- cgit v1.2.3 From 5d90070816534882b9158f14154b7e2cdef1194a Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 4 Mar 2022 10:41:44 -0800 Subject: rcu-tasks: Make Tasks RCU account for userspace execution The main Tasks RCU quiescent state is voluntary context switch. However, userspace execution is also a valid quiescent state, and is a valuable one for userspace applications that spin repeatedly executing light-weight non-sleeping system calls. Currently, such an application can delay a Tasks RCU grace period for many tens of seconds. This commit therefore enlists the aid of the scheduler-clock interrupt to provide a Tasks RCU quiescent state when it interrupted a task executing in userspace. [ paulmck: Apply feedback from kernel test robot. ] Cc: Martin KaFai Lau Cc: Neil Spring Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index e7c39c200e2b..1a32036c918c 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -196,6 +196,7 @@ void synchronize_rcu_tasks_rude(void); void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ +#define rcu_tasks_classic_qs(t, preempt) do { } while (0) #define rcu_tasks_qs(t, preempt) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu -- cgit v1.2.3 From bd6c375b92c3f367e184d164e12952e4b9d9fb4f Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 15 Mar 2022 16:33:38 +0100 Subject: rcutorture: Call preempt_schedule() through static call/key The rcutorture test suite sometimess triggers a random scheduler preemption call while simulating a read delay. Unfortunately, its direct call to preempt_schedule() bypasses the static call/key filter used by CONFIG_PREEMPT_DYNAMIC. This breaks the no-preempt assumption when the dynamic preemption mode is "none". For example, rcu_blocking_is_gp() is fooled and abbreviates grace periods when the CPU runs in no-preempt UP mode. Fix this by making torture_preempt_schedule() call __preempt_schedule(), which uses the static call/key. Reported-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney --- include/linux/torture.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/torture.h b/include/linux/torture.h index 63fa4196e51c..7038104463e4 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -118,7 +118,7 @@ void _torture_stop_kthread(char *m, struct task_struct **tp); _torture_stop_kthread("Stopping " #n " task", &(tp)) #ifdef CONFIG_PREEMPTION -#define torture_preempt_schedule() preempt_schedule() +#define torture_preempt_schedule() __preempt_schedule() #else #define torture_preempt_schedule() do { } while (0) #endif -- cgit v1.2.3 From a28c1ab312712c26a8d004af1f68628d625dafac Mon Sep 17 00:00:00 2001 From: Sergey Shtylyov Date: Sat, 9 Apr 2022 22:13:56 +0300 Subject: ata: libata-core: fix parameter type in ata_xfer_mode2shift() The data transfer mode that corresponds to the 'xfer_mode' parameter for ata_xfer_mode2shift() is a 8-bit *unsigned* value. Using *unsigned long* to declare the parameter leads to a problematic implicit *int* to *unsigned long* cast and was most probably a result of a copy/paste mistake -- use the 'u8' type instead, as in ata_xfer_mode2mask()... Found by Linux Verification Center (linuxtesting.org) with the SVACE static analysis tool. Signed-off-by: Sergey Shtylyov Signed-off-by: Damien Le Moal --- include/linux/libata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/libata.h b/include/linux/libata.h index 16107122e587..732de9014626 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1110,7 +1110,7 @@ extern void ata_unpack_xfermask(unsigned long xfer_mask, unsigned long *udma_mask); extern u8 ata_xfer_mask2mode(unsigned long xfer_mask); extern unsigned long ata_xfer_mode2mask(u8 xfer_mode); -extern int ata_xfer_mode2shift(unsigned long xfer_mode); +extern int ata_xfer_mode2shift(u8 xfer_mode); extern const char *ata_mode_string(unsigned long xfer_mask); extern unsigned long ata_id_xfermask(const u16 *id); extern int ata_std_qc_defer(struct ata_queued_cmd *qc); -- cgit v1.2.3 From 888ade8f90d7dbbdc8552ae9b23d311f9e61ab0e Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 8 Apr 2022 22:08:37 +0200 Subject: ipv4: Use dscp_t in struct fib_rt_info Use the new dscp_t type to replace the tos field of struct fib_rt_info. This ensures ECN bits are ignored and makes it compatible with the fa_dscp field of struct fib_alias. This also allows sparse to flag potential incorrect uses of DSCP and ECN bits. Signed-off-by: Guillaume Nault Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- include/net/ip_fib.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 6a82bcb8813b..f08ba531ac08 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -212,7 +212,7 @@ struct fib_rt_info { u32 tb_id; __be32 dst; int dst_len; - u8 tos; + dscp_t dscp; u8 type; u8 offload:1, trap:1, -- cgit v1.2.3 From 568a3f33b4273833f1b1e4a39d4a3410c4770c32 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 8 Apr 2022 22:08:40 +0200 Subject: ipv4: Use dscp_t in struct fib_entry_notifier_info Use the new dscp_t type to replace the tos field of struct fib_entry_notifier_info. This ensures ECN bits are ignored and makes it compatible with the dscp field of struct fib_rt_info. This also allows sparse to flag potential incorrect uses of DSCP and ECN bits. Signed-off-by: Guillaume Nault Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- include/net/ip_fib.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index f08ba531ac08..a378eff827c7 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -225,7 +225,7 @@ struct fib_entry_notifier_info { u32 dst; int dst_len; struct fib_info *fi; - u8 tos; + dscp_t dscp; u8 type; u32 tb_id; }; -- cgit v1.2.3 From 868e6139c5212e7d9de8332806aacfeafb349320 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Sun, 27 Mar 2022 11:33:16 -0600 Subject: block: move lower_48_bits() to block The function is not generally applicable enough to be included in the core kernel header. Move it to block since it's the only subsystem using it. Suggested-by: Linus Torvalds Signed-off-by: Keith Busch Link: https://lore.kernel.org/r/20220327173316.315-1-kbusch@kernel.org Signed-off-by: Jens Axboe --- include/linux/kernel.h | 9 --------- include/linux/t10-pi.h | 9 +++++++++ 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 08ba5995aa8b..a890428bcc1a 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -63,15 +63,6 @@ } \ ) -/** - * lower_48_bits() - return bits 0-47 of a number - * @n: the number we're accessing - */ -static inline u64 lower_48_bits(u64 n) -{ - return n & ((1ull << 48) - 1); -} - /** * upper_32_bits - return bits 32-63 of a number * @n: the number we're accessing diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index a4b1af581f69..248f4ac95642 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -59,6 +59,15 @@ struct crc64_pi_tuple { __u8 ref_tag[6]; }; +/** + * lower_48_bits() - return bits 0-47 of a number + * @n: the number we're accessing + */ +static inline u64 lower_48_bits(u64 n) +{ + return n & ((1ull << 48) - 1); +} + static inline u64 ext_pi_ref_tag(struct request *rq) { unsigned int shift = ilog2(queue_logical_block_size(rq->q)); -- cgit v1.2.3 From 3c6ae371b8a1ffba1fc415989fd581ebf841ed0a Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Thu, 7 Apr 2022 19:13:07 -0500 Subject: scsi: iscsi: Release endpoint ID when its freed We can't release the endpoint ID until all references to the endpoint have been dropped or it could be allocated while in use. This has us use an idr instead of looping over all conns to find a free ID and then free the ID when all references have been dropped instead of when the device is only deleted. Link: https://lore.kernel.org/r/20220408001314.5014-4-michael.christie@oracle.com Tested-by: Manish Rangankar Reviewed-by: Lee Duncan Reviewed-by: Chris Leech Reviewed-by: Wu Bo Signed-off-by: Mike Christie Signed-off-by: Martin K. Petersen --- include/scsi/scsi_transport_iscsi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h index 38e4a67f5922..fdd486047404 100644 --- a/include/scsi/scsi_transport_iscsi.h +++ b/include/scsi/scsi_transport_iscsi.h @@ -295,7 +295,7 @@ extern void iscsi_host_for_each_session(struct Scsi_Host *shost, struct iscsi_endpoint { void *dd_data; /* LLD private data */ struct device dev; - uint64_t id; + int id; struct iscsi_cls_conn *conn; }; -- cgit v1.2.3 From 7c6e99c18167ed89729bf167ccb4a7e3ab3115ba Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Thu, 7 Apr 2022 19:13:09 -0500 Subject: scsi: iscsi: Fix conn cleanup and stop race during iscsid restart If iscsid is doing a stop_conn at the same time the kernel is starting error recovery we can hit a race that allows the cleanup work to run on a valid connection. In the race, iscsi_if_stop_conn sees the cleanup bit set, but it calls flush_work on the clean_work before iscsi_conn_error_event has queued it. The flush then returns before the queueing and so the cleanup_work can run later and disconnect/stop a conn while it's in a connected state. The patch: Commit 0ab710458da1 ("scsi: iscsi: Perform connection failure entirely in kernel space") added the late stop_conn call bug originally, and the patch: Commit 23d6fefbb3f6 ("scsi: iscsi: Fix in-kernel conn failure handling") attempted to fix it but only fixed the normal EH case and left the above race for the iscsid restart case. For the normal EH case we don't hit the race because we only signal userspace to start recovery after we have done the queueing, so the flush will always catch the queued work or see it completed. For iscsid restart cases like boot, we can hit the race because iscsid will call down to the kernel before the kernel has signaled any error, so both code paths can be running at the same time. This adds a lock around the setting of the cleanup bit and queueing so they happen together. Link: https://lore.kernel.org/r/20220408001314.5014-6-michael.christie@oracle.com Fixes: 0ab710458da1 ("scsi: iscsi: Perform connection failure entirely in kernel space") Tested-by: Manish Rangankar Reviewed-by: Lee Duncan Reviewed-by: Chris Leech Signed-off-by: Mike Christie Signed-off-by: Martin K. Petersen --- include/scsi/scsi_transport_iscsi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h index fdd486047404..9acb8422f680 100644 --- a/include/scsi/scsi_transport_iscsi.h +++ b/include/scsi/scsi_transport_iscsi.h @@ -211,6 +211,8 @@ struct iscsi_cls_conn { struct mutex ep_mutex; struct iscsi_endpoint *ep; + /* Used when accessing flags and queueing work. */ + spinlock_t lock; unsigned long flags; struct work_struct cleanup_work; -- cgit v1.2.3 From 5bd856256f8c03e329f8ff36d8c8efcb111fe6df Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Thu, 7 Apr 2022 19:13:11 -0500 Subject: scsi: iscsi: Merge suspend fields Move the tx and rx suspend fields into one flags field. Link: https://lore.kernel.org/r/20220408001314.5014-8-michael.christie@oracle.com Tested-by: Manish Rangankar Reviewed-by: Lee Duncan Reviewed-by: Chris Leech Signed-off-by: Mike Christie Signed-off-by: Martin K. Petersen --- include/scsi/libiscsi.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index e76c94697c1b..84086c240228 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -53,8 +53,10 @@ enum { #define ISID_SIZE 6 -/* Connection suspend "bit" */ -#define ISCSI_SUSPEND_BIT 1 +/* Connection flags */ +#define ISCSI_CONN_FLAG_SUSPEND_TX BIT(0) +#define ISCSI_CONN_FLAG_SUSPEND_RX BIT(1) + #define ISCSI_ITT_MASK 0x1fff #define ISCSI_TOTAL_CMDS_MAX 4096 @@ -211,8 +213,7 @@ struct iscsi_conn { struct list_head cmdqueue; /* data-path cmd queue */ struct list_head requeue; /* tasks needing another run */ struct work_struct xmitwork; /* per-conn. xmit workqueue */ - unsigned long suspend_tx; /* suspend Tx */ - unsigned long suspend_rx; /* suspend Rx */ + unsigned long flags; /* ISCSI_CONN_FLAGs */ /* negotiated params */ unsigned max_recv_dlength; /* initiator_max_recv_dsl*/ -- cgit v1.2.3 From 44ac97109e42f87b1a34954704b81b6c8eca80c4 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Thu, 7 Apr 2022 19:13:12 -0500 Subject: scsi: iscsi: Fix NOP handling during conn recovery If a offload driver doesn't use the xmit workqueue, then when we are doing ep_disconnect libiscsi can still inject PDUs to the driver. This adds a check for if the connection is bound before trying to inject PDUs. Link: https://lore.kernel.org/r/20220408001314.5014-9-michael.christie@oracle.com Tested-by: Manish Rangankar Reviewed-by: Lee Duncan Reviewed-by: Chris Leech Signed-off-by: Mike Christie Signed-off-by: Martin K. Petersen --- include/scsi/libiscsi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index 84086c240228..d0a24779c52d 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -56,7 +56,7 @@ enum { /* Connection flags */ #define ISCSI_CONN_FLAG_SUSPEND_TX BIT(0) #define ISCSI_CONN_FLAG_SUSPEND_RX BIT(1) - +#define ISCSI_CONN_FLAG_BOUND BIT(2) #define ISCSI_ITT_MASK 0x1fff #define ISCSI_TOTAL_CMDS_MAX 4096 -- cgit v1.2.3 From b33115bd05afda6fe16fdd142779a9ff95d63317 Mon Sep 17 00:00:00 2001 From: Mohan Kumar Date: Mon, 11 Apr 2022 13:02:09 +0530 Subject: ALSA: hda: Jack detection poll in suspend state HDA Jack detection logic doesn't work when the HDACODEC in runtime suspended state as unsol event won't be triggered during D3 state. As pulseaudio server in userspace rely on the jack mixer control status to show the audio devices in gui and any display sink device hotplug event during D3 state will never updates the jack status which will result in no audio device option available in userspace settings. The possible option available to resolve this issue is to run Jack polling worker thread even after codec suspend state. The choice can be made based on compromise between power saving or Jack detection in suspend state. Signed-off-by: Mohan Kumar Link: https://lore.kernel.org/r/20220411073210.23445-2-mkumard@nvidia.com Signed-off-by: Takashi Iwai --- include/sound/hda_codec.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/sound/hda_codec.h b/include/sound/hda_codec.h index 77426ff58338..b7be300b6b18 100644 --- a/include/sound/hda_codec.h +++ b/include/sound/hda_codec.h @@ -59,6 +59,9 @@ struct hda_bus { unsigned int no_response_fallback:1; /* don't fallback at RIRB error */ unsigned int bus_probing :1; /* during probing process */ unsigned int keep_power:1; /* keep power up for notification */ + unsigned int jackpoll_in_suspend:1; /* keep jack polling during + * runtime suspend + */ int primary_dig_out_type; /* primary digital out PCM type */ unsigned int mixer_assigned; /* codec addr for mixer name */ -- cgit v1.2.3 From 764b2668cffafdfde47f51f22b0949315bd0b96a Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Mon, 11 Apr 2022 17:34:02 +0300 Subject: drm/fourcc: Introduce format modifiers for DG2 render and media compression The render/media engines on DG2 unify render compression and media compression into a single format for the first time, using the Tile 4 layout for main surfaces. The compression algorithm is different from any previous platform and the display engine must still be configured to decompress either a render or media compressed surface; as such, we need new RC and MC framebuffer modifiers to represent buffers in this format. v2: Clarify modifier layout description. Cc: dri-devel@lists.freedesktop.org Signed-off-by: Matt Roper Signed-off-by: Imre Deak Acked-by: Nanley Chery Reviewed-by: Juha-Pekka Heikkila Acked-by: Maarten Lankhorst Link: https://patchwork.freedesktop.org/patch/msgid/20220411143405.1073845-2-imre.deak@intel.com --- include/uapi/drm/drm_fourcc.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index b73fe6797fc3..4a5117715db3 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -583,6 +583,28 @@ extern "C" { */ #define I915_FORMAT_MOD_4_TILED fourcc_mod_code(INTEL, 9) +/* + * Intel color control surfaces (CCS) for DG2 render compression. + * + * The main surface is Tile 4 and at plane index 0. The CCS data is stored + * outside of the GEM object in a reserved memory area dedicated for the + * storage of the CCS data for all RC/RC_CC/MC compressible GEM objects. The + * main surface pitch is required to be a multiple of four Tile 4 widths. + */ +#define I915_FORMAT_MOD_4_TILED_DG2_RC_CCS fourcc_mod_code(INTEL, 10) + +/* + * Intel color control surfaces (CCS) for DG2 media compression. + * + * The main surface is Tile 4 and at plane index 0. For semi-planar formats + * like NV12, the Y and UV planes are Tile 4 and are located at plane indices + * 0 and 1, respectively. The CCS for all planes are stored outside of the + * GEM object in a reserved memory area dedicated for the storage of the + * CCS data for all RC/RC_CC/MC compressible GEM objects. The main surface + * pitch is required to be a multiple of four Tile 4 widths. + */ +#define I915_FORMAT_MOD_4_TILED_DG2_MC_CCS fourcc_mod_code(INTEL, 11) + /* * Tiled, NV12MT, grouped in 64 (pixels) x 32 (lines) -sized macroblocks * -- cgit v1.2.3 From 9035039e1ed691cd893777a42e048003a2f349d6 Mon Sep 17 00:00:00 2001 From: Mika Kahola Date: Mon, 11 Apr 2022 17:34:04 +0300 Subject: drm/fourcc: Introduce format modifier for DG2 clear color MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit DG2 clear color render compression uses Tile4 layout. Therefore, we need to define a new format modifier for uAPI to support clear color rendering. v2: Display version is fixed. [Imre] KDoc is enhanced for cc modifier. [Nanley & Lionel] v3: Split out the modifier addition to a separate patch. Clarify the modifier layout description. Cc: dri-devel@lists.freedesktop.org Signed-off-by: Mika Kahola cc: Anshuman Gupta Signed-off-by: Juha-Pekka Heikkilä Signed-off-by: Ramalingam C Signed-off-by: Imre Deak Acked-by: Nanley Chery Reviewed-by: Juha-Pekka Heikkila Acked-by: Maarten Lankhorst Link: https://patchwork.freedesktop.org/patch/msgid/20220411143405.1073845-4-imre.deak@intel.com --- include/uapi/drm/drm_fourcc.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index 4a5117715db3..e5074162bcdd 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -605,6 +605,20 @@ extern "C" { */ #define I915_FORMAT_MOD_4_TILED_DG2_MC_CCS fourcc_mod_code(INTEL, 11) +/* + * Intel Color Control Surface with Clear Color (CCS) for DG2 render compression. + * + * The main surface is Tile 4 and at plane index 0. The CCS data is stored + * outside of the GEM object in a reserved memory area dedicated for the + * storage of the CCS data for all RC/RC_CC/MC compressible GEM objects. The + * main surface pitch is required to be a multiple of four Tile 4 widths. The + * clear color is stored at plane index 1 and the pitch should be ignored. The + * format of the 256 bits of clear color data matches the one used for the + * I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC modifier, see its description + * for details. + */ +#define I915_FORMAT_MOD_4_TILED_DG2_RC_CCS_CC fourcc_mod_code(INTEL, 12) + /* * Tiled, NV12MT, grouped in 64 (pixels) x 32 (lines) -sized macroblocks * -- cgit v1.2.3 From fee2b871d8d6389c9b4bdf9346a99ccc1c98c9b8 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 12 Apr 2022 11:31:40 +0200 Subject: ALSA: core: Add snd_card_free_on_error() helper This is a small helper function to handle the error path more easily when an error happens during the probe for the device with the device-managed card. Since devres releases in the reverser order of the creations, usually snd_card_free() gets called at the last in the probe error path unless it already reached snd_card_register() calls. Due to this nature, when a driver expects the resource releases in card->private_free, this might be called too lately. As a workaround, one should call the probe like: static int __some_probe(...) { // do real probe.... } static int some_probe(...) { return snd_card_free_on_error(dev, __some_probe(dev, ...)); } so that the snd_card_free() is called explicitly at the beginning of the error path from the probe. This function will be used in the upcoming fixes to address the regressions by devres usages. Fixes: e8ad415b7a55 ("ALSA: core: Add managed card creation") Cc: Link: https://lore.kernel.org/r/20220412093141.8008-2-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/sound/core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/sound/core.h b/include/sound/core.h index b7e9b58d3c78..6d4cc49584c6 100644 --- a/include/sound/core.h +++ b/include/sound/core.h @@ -284,6 +284,7 @@ int snd_card_disconnect(struct snd_card *card); void snd_card_disconnect_sync(struct snd_card *card); int snd_card_free(struct snd_card *card); int snd_card_free_when_closed(struct snd_card *card); +int snd_card_free_on_error(struct device *dev, int ret); void snd_card_set_id(struct snd_card *card, const char *id); int snd_card_register(struct snd_card *card); int snd_card_info_init(void); -- cgit v1.2.3 From 1b6a6fc5280e97559287b61eade2d4b363e836f2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Amadeusz=20S=C5=82awi=C5=84ski?= Date: Tue, 12 Apr 2022 11:16:28 +0200 Subject: ALSA: jack: Access input_dev under mutex MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It is possible when using ASoC that input_dev is unregistered while calling snd_jack_report, which causes NULL pointer dereference. In order to prevent this serialize access to input_dev using mutex lock. Signed-off-by: Amadeusz Sławiński Reviewed-by: Cezary Rojewski Link: https://lore.kernel.org/r/20220412091628.3056922-1-amadeuszx.slawinski@linux.intel.com Signed-off-by: Takashi Iwai --- include/sound/jack.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/sound/jack.h b/include/sound/jack.h index 1181f536557e..1ed90e2109e9 100644 --- a/include/sound/jack.h +++ b/include/sound/jack.h @@ -62,6 +62,7 @@ struct snd_jack { const char *id; #ifdef CONFIG_SND_JACK_INPUT_DEV struct input_dev *input_dev; + struct mutex input_dev_lock; int registered; int type; char name[100]; -- cgit v1.2.3 From 9b30501949f773777f3632d891e6defbb363daf5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Alvin=20=C5=A0ipraga?= Date: Thu, 17 Mar 2022 23:35:58 +0100 Subject: dt-bindings: imx: add clock bindings for i.MX8MN GPT MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The i.MX8MN has a General Purpose Timer (GPT) just like the i.MX8MM, which already has such bindings. Add the relevant bindings for the Nano SoC too. Signed-off-by: Alvin Šipraga Acked-by: Krzysztof Kozlowski Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20220317223600.175894-1-alvin@pqrs.dk Signed-off-by: Abel Vesa --- include/dt-bindings/clock/imx8mn-clock.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/clock/imx8mn-clock.h b/include/dt-bindings/clock/imx8mn-clock.h index 01e8bab1d767..07b8a282c268 100644 --- a/include/dt-bindings/clock/imx8mn-clock.h +++ b/include/dt-bindings/clock/imx8mn-clock.h @@ -243,6 +243,20 @@ #define IMX8MN_CLK_M7_CORE 221 -#define IMX8MN_CLK_END 222 +#define IMX8MN_CLK_GPT_3M 222 +#define IMX8MN_CLK_GPT1 223 +#define IMX8MN_CLK_GPT1_ROOT 224 +#define IMX8MN_CLK_GPT2 225 +#define IMX8MN_CLK_GPT2_ROOT 226 +#define IMX8MN_CLK_GPT3 227 +#define IMX8MN_CLK_GPT3_ROOT 228 +#define IMX8MN_CLK_GPT4 229 +#define IMX8MN_CLK_GPT4_ROOT 230 +#define IMX8MN_CLK_GPT5 231 +#define IMX8MN_CLK_GPT5_ROOT 232 +#define IMX8MN_CLK_GPT6 233 +#define IMX8MN_CLK_GPT6_ROOT 234 + +#define IMX8MN_CLK_END 235 #endif -- cgit v1.2.3 From c63462184b35316fed7657d3c92dc5099ad5fab2 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Mon, 11 Apr 2022 09:56:03 +0100 Subject: drm/ttm: stop passing NULL fence in ttm_bo_move_sync_cleanup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If we hit the sync case, like when skipping clearing for kernel internal objects, or when falling back to cpu clearing, like in i915, we end up trying to add a NULL fence, but with some recent changes in this area this now just results in NULL deref in dma_resv_add_fence: <1>[ 5.466383] BUG: kernel NULL pointer dereference, address: 0000000000000008 <1>[ 5.466384] #PF: supervisor read access in kernel mode <1>[ 5.466385] #PF: error_code(0x0000) - not-present page <6>[ 5.466386] PGD 0 P4D 0 <4>[ 5.466387] Oops: 0000 [#1] PREEMPT SMP NOPTI <4>[ 5.466389] CPU: 5 PID: 267 Comm: modprobe Not tainted 5.18.0-rc2-CI-CI_DRM_11481+ #1 <4>[ 5.466391] RIP: 0010:dma_resv_add_fence+0x63/0x260 <4>[ 5.466395] Code: 38 85 c0 0f 84 df 01 00 00 0f 88 e8 01 00 00 83 c0 01 0f 88 df 01 00 00 8b 05 35 89 10 01 49 8d 5e 68 85 c0 0f 85 45 01 00 00 <48> 8b 45 08 48 3d c0 a5 0a 82 0f 84 5c 01 00 00 48 3d 60 a5 0a 82 <4>[ 5.466396] RSP: 0018:ffffc90000e974f8 EFLAGS: 00010202 <4>[ 5.466397] RAX: 0000000000000001 RBX: ffff888123e88b28 RCX: 00000000ffffffff <4>[ 5.466398] RDX: 0000000000000001 RSI: ffffffff822e4f50 RDI: ffffffff8233f087 <4>[ 5.466399] RBP: 0000000000000000 R08: ffff8881313dbc80 R09: 0000000000000001 <4>[ 5.466399] R10: 0000000000000001 R11: 00000000da354294 R12: 0000000000000000 <4>[ 5.466400] R13: ffff88810927dc58 R14: ffff888123e88ac0 R15: ffff88810a88d600 <4>[ 5.466401] FS: 00007f5fa1193540(0000) GS:ffff88845d880000(0000) knlGS:0000000000000000 <4>[ 5.466402] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4>[ 5.466402] CR2: 0000000000000008 CR3: 0000000106dd6003 CR4: 00000000003706e0 <4>[ 5.466403] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 <4>[ 5.466404] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 <4>[ 5.466404] Call Trace: <4>[ 5.466405] <4>[ 5.466406] ttm_bo_move_accel_cleanup+0x62/0x270 [ttm] <4>[ 5.466411] ? i915_rsgt_from_buddy_resource+0x185/0x1e0 [i915] <4>[ 5.466529] i915_ttm_move+0xfd/0x430 [i915] <4>[ 5.466833] ? dma_resv_reserve_fences+0x4e/0x320 <4>[ 5.466836] ? ttm_bo_add_move_fence.constprop.20+0xf7/0x140 [ttm] <4>[ 5.466841] ttm_bo_handle_move_mem+0xa1/0x140 [ttm] <4>[ 5.466845] ttm_bo_validate+0xee/0x160 [ttm] <4>[ 5.466849] __i915_ttm_get_pages+0x4f/0x210 [i915] <4>[ 5.466976] i915_ttm_get_pages+0xad/0x140 [i915] <4>[ 5.467094] ____i915_gem_object_get_pages+0x32/0xf0 [i915] <4>[ 5.467210] __i915_gem_object_get_pages+0x89/0xa0 [i915] <4>[ 5.467323] i915_vma_get_pages+0x114/0x1d0 [i915] <4>[ 5.467446] i915_vma_pin_ww+0xd3/0xa90 [i915] <4>[ 5.467570] i915_vma_pin.constprop.10+0x119/0x1b0 [i915] <4>[ 5.467700] ? __mutex_unlock_slowpath+0x3e/0x2b0 <4>[ 5.467704] intel_alloc_initial_plane_obj.isra.6+0x1a9/0x390 [i915] <4>[ 5.467833] intel_crtc_initial_plane_config+0x83/0x340 [i915] In the ttm_bo_move_sync_cleanup() case it seems we only really care about calling ttm_bo_wait_free_node(), so let's instead just call that directly. Signed-off-by: Matthew Auld Cc: Thomas Hellström Cc: Christian König Cc: Lucas De Marchi Cc: Nirmoy Das Reviewed-by: Christian König Signed-off-by: Christian König Link: https://patchwork.freedesktop.org/patch/msgid/20220411085603.58156-1-matthew.auld@intel.com --- include/drm/ttm/ttm_bo_driver.h | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 059a595e14e5..897b88f0bd59 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -245,7 +245,7 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo, struct ttm_resource *new_mem); /** - * ttm_bo_move_accel_cleanup. + * ttm_bo_move_sync_cleanup. * * @bo: A pointer to a struct ttm_buffer_object. * @new_mem: struct ttm_resource indicating where to move. @@ -253,13 +253,8 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo, * Special case of ttm_bo_move_accel_cleanup where the bo is guaranteed * by the caller to be idle. Typically used after memcpy buffer moves. */ -static inline void ttm_bo_move_sync_cleanup(struct ttm_buffer_object *bo, - struct ttm_resource *new_mem) -{ - int ret = ttm_bo_move_accel_cleanup(bo, NULL, true, false, new_mem); - - WARN_ON(ret); -} +void ttm_bo_move_sync_cleanup(struct ttm_buffer_object *bo, + struct ttm_resource *new_mem); /** * ttm_bo_pipeline_gutting. -- cgit v1.2.3 From ec095263a965720e1ca39db1d9c5cd47846c789b Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Mon, 11 Apr 2022 14:49:55 +0200 Subject: net: remove noblock parameter from recvmsg() entities The internal recvmsg() functions have two parameters 'flags' and 'noblock' that were merged inside skb_recv_datagram(). As a follow up patch to commit f4b41f062c42 ("net: remove noblock parameter from skb_recv_datagram()") this patch removes the separate 'noblock' parameter for recvmsg(). Analogue to the referenced patch for skb_recv_datagram() the 'flags' and 'noblock' parameters are unnecessarily split up with e.g. err = sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT, flags & ~MSG_DONTWAIT, &addr_len); or in err = INDIRECT_CALL_2(sk->sk_prot->recvmsg, tcp_recvmsg, udp_recvmsg, sk, msg, size, flags & MSG_DONTWAIT, flags & ~MSG_DONTWAIT, &addr_len); instead of simply using only flags all the time and check for MSG_DONTWAIT where needed (to preserve for the formerly separated no(n)block condition). Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/r/20220411124955.154876-1-socketcan@hartkopp.net Signed-off-by: Paolo Abeni --- include/net/ping.h | 2 +- include/net/sctp/sctp.h | 2 +- include/net/sock.h | 3 +-- include/net/tcp.h | 2 +- include/net/tls.h | 2 +- include/net/udp.h | 8 ++++---- 6 files changed, 9 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/ping.h b/include/net/ping.h index b68fbfdb606f..e4ff3911cbf5 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -71,7 +71,7 @@ void ping_err(struct sk_buff *skb, int offset, u32 info); int ping_getfrag(void *from, char *to, int offset, int fraglen, int odd, struct sk_buff *); -int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, +int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len); int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, void *user_icmph, size_t icmph_len); diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index bf3716fe83e0..a04999ee99b0 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -103,7 +103,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, struct sctp_association *asoc); extern struct percpu_counter sctp_sockets_allocated; int sctp_asconf_mgmt(struct sctp_sock *, struct sctp_sockaddr_entry *); -struct sk_buff *sctp_skb_recv_datagram(struct sock *, int, int, int *); +struct sk_buff *sctp_skb_recv_datagram(struct sock *, int, int *); typedef int (*sctp_callback_t)(struct sctp_endpoint *, struct sctp_transport *, void *); void sctp_transport_walk_start(struct rhashtable_iter *iter); diff --git a/include/net/sock.h b/include/net/sock.h index 1a988e605f09..a01d6c421aa2 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1202,8 +1202,7 @@ struct proto { int (*sendmsg)(struct sock *sk, struct msghdr *msg, size_t len); int (*recvmsg)(struct sock *sk, struct msghdr *msg, - size_t len, int noblock, int flags, - int *addr_len); + size_t len, int flags, int *addr_len); int (*sendpage)(struct sock *sk, struct page *page, int offset, size_t size, int flags); int (*bind)(struct sock *sk, diff --git a/include/net/tcp.h b/include/net/tcp.h index 6d50a662bf89..679b1964d494 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -407,7 +407,7 @@ int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); void tcp_set_keepalive(struct sock *sk, int val); void tcp_syn_ack_timeout(const struct request_sock *req); -int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, +int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len); int tcp_set_rcvlowat(struct sock *sk, int val); int tcp_set_window_clamp(struct sock *sk, int val); diff --git a/include/net/tls.h b/include/net/tls.h index 6fe78361c8c8..b59f0a63292b 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -371,7 +371,7 @@ void tls_sw_free_resources_rx(struct sock *sk); void tls_sw_release_resources_rx(struct sock *sk); void tls_sw_free_ctx_rx(struct tls_context *tls_ctx); int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, - int nonblock, int flags, int *addr_len); + int flags, int *addr_len); bool tls_sw_sock_is_readable(struct sock *sk); ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, diff --git a/include/net/udp.h b/include/net/udp.h index f1c2a88c9005..b83a00330566 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -250,14 +250,14 @@ void udp_destruct_sock(struct sock *sk); void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len); int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb); void udp_skb_destructor(struct sock *sk, struct sk_buff *skb); -struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, - int noblock, int *off, int *err); +struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, int *off, + int *err); static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags, - int noblock, int *err) + int *err) { int off = 0; - return __skb_recv_udp(sk, flags, noblock, &off, err); + return __skb_recv_udp(sk, flags, &off, err); } int udp_v4_early_demux(struct sk_buff *skb); -- cgit v1.2.3 From b97687527be85a55e12804c98745c5619eadcc32 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Tue, 12 Apr 2022 21:59:16 +0000 Subject: asm-generic: fix __get_unaligned_be48() on 32 bit platforms While testing the new macros for working with 48 bit containers, I faced a weird problem: 32 + 16: 0x2ef6e8da 0x79e60000 48: 0xffffe8da + 0x79e60000 All the bits starting from the 32nd were getting 1d in 9/10 cases. The debug showed: p[0]: 0x00002e0000000000 p[1]: 0x00002ef600000000 p[2]: 0xffffffffe8000000 p[3]: 0xffffffffe8da0000 p[4]: 0xffffffffe8da7900 p[5]: 0xffffffffe8da79e6 that the value becomes a garbage after the third OR, i.e. on `p[2] << 24`. When the 31st bit is 1 and there's no explicit cast to an unsigned, it's being considered as a signed int and getting sign-extended on OR, so `e8000000` becomes `ffffffffe8000000` and messes up the result. Cast the @p[2] to u64 as well to avoid this. Now: 32 + 16: 0x7ef6a490 0xddc10000 48: 0x7ef6a490 + 0xddc10000 p[0]: 0x00007e0000000000 p[1]: 0x00007ef600000000 p[2]: 0x00007ef6a4000000 p[3]: 0x00007ef6a4900000 p[4]: 0x00007ef6a490dd00 p[5]: 0x00007ef6a490ddc1 Fixes: c2ea5fcf53d5 ("asm-generic: introduce be48 unaligned accessors") Signed-off-by: Alexander Lobakin Link: https://lore.kernel.org/r/20220412215220.75677-1-alobakin@pm.me Signed-off-by: Jens Axboe --- include/asm-generic/unaligned.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/unaligned.h b/include/asm-generic/unaligned.h index 8fc637379899..df30f11b4a46 100644 --- a/include/asm-generic/unaligned.h +++ b/include/asm-generic/unaligned.h @@ -143,7 +143,7 @@ static inline void put_unaligned_be48(const u64 val, void *p) static inline u64 __get_unaligned_be48(const u8 *p) { - return (u64)p[0] << 40 | (u64)p[1] << 32 | p[2] << 24 | + return (u64)p[0] << 40 | (u64)p[1] << 32 | (u64)p[2] << 24 | p[3] << 16 | p[4] << 8 | p[5]; } -- cgit v1.2.3 From 4185b27b3bef9ce724a3dafd8193c935e845fcdc Mon Sep 17 00:00:00 2001 From: Taniya Das Date: Wed, 23 Feb 2022 22:52:47 +0530 Subject: dt-bindings: clock: Add YAML schemas for LPASS clocks on SC7280 The LPASS(Low Power Audio Subsystem) clock provider have a bunch of generic properties that are needed in a device tree. Also add clock ids for LPASS core clocks and audio clock IDs for LPASS client to request for the clocks. Reviewed-by: Rob Herring Reviewed-by: Stephen Boyd Signed-off-by: Taniya Das Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220223172248.18877-1-tdas@codeaurora.org --- .../dt-bindings/clock/qcom,lpassaudiocc-sc7280.h | 43 ++++++++++++++++++++++ .../dt-bindings/clock/qcom,lpasscorecc-sc7280.h | 26 +++++++++++++ 2 files changed, 69 insertions(+) create mode 100644 include/dt-bindings/clock/qcom,lpassaudiocc-sc7280.h create mode 100644 include/dt-bindings/clock/qcom,lpasscorecc-sc7280.h (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,lpassaudiocc-sc7280.h b/include/dt-bindings/clock/qcom,lpassaudiocc-sc7280.h new file mode 100644 index 000000000000..20ef2ea673f3 --- /dev/null +++ b/include/dt-bindings/clock/qcom,lpassaudiocc-sc7280.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2021, The Linux Foundation. All rights reserved. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_LPASS_AUDIO_CC_SC7280_H +#define _DT_BINDINGS_CLK_QCOM_LPASS_AUDIO_CC_SC7280_H + +/* LPASS_AUDIO_CC clocks */ +#define LPASS_AUDIO_CC_PLL 0 +#define LPASS_AUDIO_CC_PLL_OUT_AUX2 1 +#define LPASS_AUDIO_CC_PLL_OUT_AUX2_DIV_CLK_SRC 2 +#define LPASS_AUDIO_CC_PLL_OUT_MAIN_DIV_CLK_SRC 3 +#define LPASS_AUDIO_CC_CDIV_RX_MCLK_DIV_CLK_SRC 4 +#define LPASS_AUDIO_CC_CODEC_MEM0_CLK 5 +#define LPASS_AUDIO_CC_CODEC_MEM1_CLK 6 +#define LPASS_AUDIO_CC_CODEC_MEM2_CLK 7 +#define LPASS_AUDIO_CC_CODEC_MEM_CLK 8 +#define LPASS_AUDIO_CC_EXT_MCLK0_CLK 9 +#define LPASS_AUDIO_CC_EXT_MCLK0_CLK_SRC 10 +#define LPASS_AUDIO_CC_EXT_MCLK1_CLK 11 +#define LPASS_AUDIO_CC_EXT_MCLK1_CLK_SRC 12 +#define LPASS_AUDIO_CC_RX_MCLK_2X_CLK 13 +#define LPASS_AUDIO_CC_RX_MCLK_CLK 14 +#define LPASS_AUDIO_CC_RX_MCLK_CLK_SRC 15 + +/* LPASS_AON_CC clocks */ +#define LPASS_AON_CC_PLL 0 +#define LPASS_AON_CC_PLL_OUT_EVEN 1 +#define LPASS_AON_CC_PLL_OUT_MAIN_CDIV_DIV_CLK_SRC 2 +#define LPASS_AON_CC_PLL_OUT_ODD 3 +#define LPASS_AON_CC_AUDIO_HM_H_CLK 4 +#define LPASS_AON_CC_CDIV_TX_MCLK_DIV_CLK_SRC 5 +#define LPASS_AON_CC_MAIN_RCG_CLK_SRC 6 +#define LPASS_AON_CC_TX_MCLK_2X_CLK 7 +#define LPASS_AON_CC_TX_MCLK_CLK 8 +#define LPASS_AON_CC_TX_MCLK_RCG_CLK_SRC 9 +#define LPASS_AON_CC_VA_MEM0_CLK 10 + +/* LPASS_AON_CC power domains */ +#define LPASS_AON_CC_LPASS_AUDIO_HM_GDSC 0 + +#endif diff --git a/include/dt-bindings/clock/qcom,lpasscorecc-sc7280.h b/include/dt-bindings/clock/qcom,lpasscorecc-sc7280.h new file mode 100644 index 000000000000..28ed2a07aacc --- /dev/null +++ b/include/dt-bindings/clock/qcom,lpasscorecc-sc7280.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2021, The Linux Foundation. All rights reserved. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_LPASS_CORE_CC_SC7280_H +#define _DT_BINDINGS_CLK_QCOM_LPASS_CORE_CC_SC7280_H + +/* LPASS_CORE_CC clocks */ +#define LPASS_CORE_CC_DIG_PLL 0 +#define LPASS_CORE_CC_DIG_PLL_OUT_MAIN_DIV_CLK_SRC 1 +#define LPASS_CORE_CC_DIG_PLL_OUT_ODD 2 +#define LPASS_CORE_CC_CORE_CLK 3 +#define LPASS_CORE_CC_CORE_CLK_SRC 4 +#define LPASS_CORE_CC_EXT_IF0_CLK_SRC 5 +#define LPASS_CORE_CC_EXT_IF0_IBIT_CLK 6 +#define LPASS_CORE_CC_EXT_IF1_CLK_SRC 7 +#define LPASS_CORE_CC_EXT_IF1_IBIT_CLK 8 +#define LPASS_CORE_CC_LPM_CORE_CLK 9 +#define LPASS_CORE_CC_LPM_MEM0_CORE_CLK 10 +#define LPASS_CORE_CC_SYSNOC_MPORT_CORE_CLK 11 + +/* LPASS_CORE_CC power domains */ +#define LPASS_CORE_CC_LPASS_CORE_HM_GDSC 0 + +#endif -- cgit v1.2.3 From 925ca893b4a65177394581737b95d03fea2660f2 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 13 Apr 2022 07:48:08 +0200 Subject: ALSA: memalloc: Add fallback SG-buffer allocations for x86 The recent change for memory allocator replaced the SG-buffer handling helper for x86 with the standard non-contiguous page handler. This works for most cases, but there is a corner case I obviously overlooked, namely, the fallback of non-contiguous handler without IOMMU. When the system runs without IOMMU, the core handler tries to use the continuous pages with a single SGL entry. It works nicely for most cases, but when the system memory gets fragmented, the large allocation may fail frequently. Ideally the non-contig handler could deal with the proper SG pages, it's cumbersome to extend for now. As a workaround, here we add new types for (minimalistic) SG allocations, instead, so that the allocator falls back to those types automatically when the allocation with the standard API failed. BTW, one better (but pretty minor) improvement from the previous SG-buffer code is that this provides the proper mmap support without the PCM's page fault handling. Fixes: 2c95b92ecd92 ("ALSA: memalloc: Unify x86 SG-buffer handling (take#3)") BugLink: https://gitlab.freedesktop.org/pipewire/pipewire/-/issues/2272 BugLink: https://bugzilla.suse.com/show_bug.cgi?id=1198248 Cc: Link: https://lore.kernel.org/r/20220413054808.7547-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- include/sound/memalloc.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/sound/memalloc.h b/include/sound/memalloc.h index 653dfffb3ac8..8d79cebf95f3 100644 --- a/include/sound/memalloc.h +++ b/include/sound/memalloc.h @@ -51,6 +51,11 @@ struct snd_dma_device { #define SNDRV_DMA_TYPE_DEV_SG SNDRV_DMA_TYPE_DEV /* no SG-buf support */ #define SNDRV_DMA_TYPE_DEV_WC_SG SNDRV_DMA_TYPE_DEV_WC #endif +/* fallback types, don't use those directly */ +#ifdef CONFIG_SND_DMA_SGBUF +#define SNDRV_DMA_TYPE_DEV_SG_FALLBACK 10 +#define SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK 11 +#endif /* * info for buffer allocation -- cgit v1.2.3 From 5bd8baab087dff657e05387aee802e70304cc813 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Wed, 13 Apr 2022 10:10:50 +0200 Subject: esp: limit skb_page_frag_refill use to a single page Commit ebe48d368e97 ("esp: Fix possible buffer overflow in ESP transformation") tried to fix skb_page_frag_refill usage in ESP by capping allocsize to 32k, but that doesn't completely solve the issue, as skb_page_frag_refill may return a single page. If that happens, we will write out of bounds, despite the check introduced in the previous patch. This patch forces COW in cases where we would end up calling skb_page_frag_refill with a size larger than a page (first in esp_output_head with tailen, then in esp_output_tail with skb->data_len). Fixes: cac2661c53f3 ("esp4: Avoid skb_cow_data whenever possible") Fixes: 03e2a30f6a27 ("esp6: Avoid skb_cow_data whenever possible") Signed-off-by: Sabrina Dubroca Signed-off-by: Steffen Klassert --- include/net/esp.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/esp.h b/include/net/esp.h index 90cd02ff77ef..9c5637d41d95 100644 --- a/include/net/esp.h +++ b/include/net/esp.h @@ -4,8 +4,6 @@ #include -#define ESP_SKB_FRAG_MAXSIZE (PAGE_SIZE << SKB_FRAG_PAGE_ORDER) - struct ip_esp_hdr; static inline struct ip_esp_hdr *ip_esp_hdr(const struct sk_buff *skb) -- cgit v1.2.3 From f7f207375d4e6eb9acc78d312eed8806b37d101a Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Wed, 13 Apr 2022 09:37:13 +0100 Subject: ALSA: cs35l41: Unify hardware configuration Both ASoC and HDA require to configure the GPIOs and Boost, so create a single shared struct for hardware configuration. Signed-off-by: Lucas Tanure Acked-by: Charles Keepax Link: https://lore.kernel.org/r/20220413083728.10730-2-tanureal@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs35l41.h | 41 +++++++++++++++++++++++++++++++---------- 1 file changed, 31 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index bf7f9a9aeba0..abcf850f7110 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -701,9 +701,6 @@ #define CS35L41_GPIO1_CTRL_SHIFT 16 #define CS35L41_GPIO2_CTRL_MASK 0x07000000 #define CS35L41_GPIO2_CTRL_SHIFT 24 -#define CS35L41_GPIO_CTRL_OPEN_INT 2 -#define CS35L41_GPIO_CTRL_ACTV_LO 4 -#define CS35L41_GPIO_CTRL_ACTV_HI 5 #define CS35L41_GPIO_POL_MASK 0x1000 #define CS35L41_GPIO_POL_SHIFT 12 @@ -735,19 +732,43 @@ enum cs35l41_clk_ids { CS35L41_CLKID_MCLK = 4, }; -struct cs35l41_irq_cfg { - bool irq_pol_inv; - bool irq_out_en; - int irq_src_sel; +enum cs35l41_gpio1_func { + CS35L41_GPIO1_HIZ, + CS35L41_GPIO1_GPIO, + CS35L41_GPIO1_MDSYNC, + CS35L41_GPIO1_MCLK, + CS35L41_GPIO1_PDM_CLK, + CS35L41_GPIO1_PDM_DATA, }; -struct cs35l41_platform_data { +enum cs35l41_gpio2_func { + CS35L41_GPIO2_HIZ, + CS35L41_GPIO2_GPIO, + CS35L41_GPIO2_INT_OPEN_DRAIN, + CS35L41_GPIO2_MCLK, + CS35L41_GPIO2_INT_PUSH_PULL_LOW, + CS35L41_GPIO2_INT_PUSH_PULL_HIGH, + CS35L41_GPIO2_PDM_CLK, + CS35L41_GPIO2_PDM_DATA, +}; + +struct cs35l41_gpio_cfg { + bool pol_inv; + bool out_en; + unsigned int func; +}; + +struct cs35l41_hw_cfg { int bst_ind; int bst_ipk; int bst_cap; int dout_hiz; - struct cs35l41_irq_cfg irq_config1; - struct cs35l41_irq_cfg irq_config2; + struct cs35l41_gpio_cfg gpio1; + struct cs35l41_gpio_cfg gpio2; + unsigned int spk_pos; + + /* Don't put the AMP in reset if VSPK can not be turned off */ + bool vspk_always_on; }; struct cs35l41_otp_packed_element_t { -- cgit v1.2.3 From 2603c974b45dbfeece80474ee32173756aac3ba1 Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Wed, 13 Apr 2022 09:37:14 +0100 Subject: ALSA: cs35l41: Check hw_config before using it The driver can receive an empty hw_config, so mark as valid if successfully read from device tree/ACPI or set by the driver itself. Platforms not marked with a valid hw config will not be supported. Signed-off-by: Lucas Tanure Acked-by: Charles Keepax Link: https://lore.kernel.org/r/20220413083728.10730-3-tanureal@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs35l41.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index abcf850f7110..4200379e0c26 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -538,7 +538,6 @@ #define CS35L41_OTP_SIZE_WORDS 32 #define CS35L41_NUM_OTP_ELEM 100 -#define CS35L41_VALID_PDATA 0x80000000 #define CS35L41_NUM_SUPPLIES 2 #define CS35L41_SCLK_MSTR_MASK 0x10 @@ -753,12 +752,14 @@ enum cs35l41_gpio2_func { }; struct cs35l41_gpio_cfg { + bool valid; bool pol_inv; bool out_en; unsigned int func; }; struct cs35l41_hw_cfg { + bool valid; int bst_ind; int bst_ipk; int bst_cap; -- cgit v1.2.3 From fcad8950a50dec5962b1b7b18a285daf7c137178 Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Wed, 13 Apr 2022 09:37:15 +0100 Subject: ALSA: cs35l41: Move cs35l41_gpio_config to shared lib ASoC and HDA can use a single function to configure the chip gpios. Signed-off-by: Lucas Tanure Acked-by: Charles Keepax Link: https://lore.kernel.org/r/20220413083728.10730-4-tanureal@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs35l41.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index 4200379e0c26..e312eb1f6e48 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -798,5 +798,6 @@ int cs35l41_set_channels(struct device *dev, struct regmap *reg, unsigned int rx_num, unsigned int *rx_slot); int cs35l41_boost_config(struct device *dev, struct regmap *regmap, int boost_ind, int boost_cap, int boost_ipk); +int cs35l41_gpio_config(struct regmap *regmap, struct cs35l41_hw_cfg *hw_cfg); #endif /* __CS35L41_H */ -- cgit v1.2.3 From b8388a1aba32bef84884c06c8270efa9eec91267 Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Wed, 13 Apr 2022 09:37:18 +0100 Subject: ALSA: hda: cs35l41: Add Boost type flag Replace vspk_always_on by a enum that better characterizes the boost type, as there is 3 types of boost hardware. And with the new boost type other parts of the driver can better handle the configuration of the chip. Signed-off-by: Lucas Tanure Link: https://lore.kernel.org/r/20220413083728.10730-7-tanureal@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs35l41.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index e312eb1f6e48..64d98cbd5c0e 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -725,6 +725,12 @@ #define CS35L41_SPI_MAX_FREQ 4000000 #define CS35L41_REGSTRIDE 4 +enum cs35l41_boost_type { + CS35L41_INT_BOOST, + CS35L41_EXT_BOOST, + CS35L41_EXT_BOOST_NO_VSPK_SWITCH, +}; + enum cs35l41_clk_ids { CS35L41_CLKID_SCLK = 0, CS35L41_CLKID_LRCLK = 1, @@ -768,8 +774,7 @@ struct cs35l41_hw_cfg { struct cs35l41_gpio_cfg gpio2; unsigned int spk_pos; - /* Don't put the AMP in reset if VSPK can not be turned off */ - bool vspk_always_on; + enum cs35l41_boost_type bst_type; }; struct cs35l41_otp_packed_element_t { -- cgit v1.2.3 From 5fdb68a7618e3c25816d458e07fd102803493400 Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Wed, 13 Apr 2022 09:37:22 +0100 Subject: ALSA: hda: cs35l41: Move boost config to initialization code Having CS35L41_PWR_CTRL2 on cs35l41_hda_config overwrites the boost configuration for internal boost. So move it to the initialization part and use regmap_update_bits to only change the correct bits. Signed-off-by: Lucas Tanure Link: https://lore.kernel.org/r/20220413083728.10730-11-tanureal@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs35l41.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index 64d98cbd5c0e..7d892c97b1e8 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -661,6 +661,7 @@ #define CS35L41_GLOBAL_EN_SHIFT 0 #define CS35L41_BST_EN_MASK 0x0030 #define CS35L41_BST_EN_SHIFT 4 +#define CS35L41_BST_DIS_FET_OFF 0x00 #define CS35L41_BST_EN_DEFAULT 0x2 #define CS35L41_AMP_EN_SHIFT 0 #define CS35L41_AMP_EN_MASK 1 -- cgit v1.2.3 From 5577dd2329d03ef88a7c87c17d4c127f3d666192 Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Wed, 13 Apr 2022 09:37:26 +0100 Subject: ALSA: hda: cs35l41: Move external boost handling to lib for ASoC use To add support for external boost for ASoC move the HDA external boost implementation to the shared lib. Signed-off-by: Lucas Tanure Link: https://lore.kernel.org/r/20220413083728.10730-15-tanureal@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs35l41.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index 7d892c97b1e8..ac629f852f2a 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -805,5 +805,9 @@ int cs35l41_set_channels(struct device *dev, struct regmap *reg, int cs35l41_boost_config(struct device *dev, struct regmap *regmap, int boost_ind, int boost_cap, int boost_ipk); int cs35l41_gpio_config(struct regmap *regmap, struct cs35l41_hw_cfg *hw_cfg); +int cs35l41_init_boost(struct device *dev, struct regmap *regmap, + struct cs35l41_hw_cfg *hw_cfg); +bool cs35l41_safe_reset(struct regmap *regmap, enum cs35l41_boost_type b_type); +int cs35l41_global_enable(struct regmap *regmap, enum cs35l41_boost_type b_type, int enable); #endif /* __CS35L41_H */ -- cgit v1.2.3 From bb06c203f86766fc2c37cbce0e20e9daae786f6e Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Wed, 13 Apr 2022 09:37:28 +0100 Subject: ASoC: cs35l41: Support external boost Add support for external boost voltage, where GPIO1 must control a switch to isolate CS35L41 from the external Boost Voltage Signed-off-by: Lucas Tanure Acked-by: Charles Keepax Acked-by: Mark Brown Link: https://lore.kernel.org/r/20220413083728.10730-17-tanureal@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs35l41.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index ac629f852f2a..dbe8d9c0191b 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -701,6 +701,8 @@ #define CS35L41_GPIO1_CTRL_SHIFT 16 #define CS35L41_GPIO2_CTRL_MASK 0x07000000 #define CS35L41_GPIO2_CTRL_SHIFT 24 +#define CS35L41_GPIO_LVL_SHIFT 15 +#define CS35L41_GPIO_LVL_MASK BIT(CS35L41_GPIO_LVL_SHIFT) #define CS35L41_GPIO_POL_MASK 0x1000 #define CS35L41_GPIO_POL_SHIFT 12 @@ -802,8 +804,6 @@ int cs35l41_register_errata_patch(struct device *dev, struct regmap *reg, unsign int cs35l41_set_channels(struct device *dev, struct regmap *reg, unsigned int tx_num, unsigned int *tx_slot, unsigned int rx_num, unsigned int *rx_slot); -int cs35l41_boost_config(struct device *dev, struct regmap *regmap, int boost_ind, int boost_cap, - int boost_ipk); int cs35l41_gpio_config(struct regmap *regmap, struct cs35l41_hw_cfg *hw_cfg); int cs35l41_init_boost(struct device *dev, struct regmap *regmap, struct cs35l41_hw_cfg *hw_cfg); -- cgit v1.2.3 From 84ab41db1734c7764a4f29a99d3106586495638c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Wed, 13 Apr 2022 11:11:36 +0200 Subject: drm/ttm: fix kerneldoc for ttm_lru_bulk_move MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Update the kerneldoc for the members as well. Signed-off-by: Christian König Fixes: b0e2c9ea5afc ("drm/ttm: allow bulk moves for all domains") Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220413091242.638413-1-christian.koenig@amd.com --- include/drm/ttm/ttm_resource.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index 314f73de4280..f82fee18c07f 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -215,8 +215,7 @@ struct ttm_lru_bulk_move_pos { /** * struct ttm_lru_bulk_move * - * @tt: first/last lru entry for resources in the TT domain - * @vram: first/last lru entry for resources in the VRAM domain + * @pos: first/last lru entry for resources in the each domain/priority * * Container for the current bulk move state. Should be used with * ttm_lru_bulk_move_init() and ttm_bo_set_bulk_move(). -- cgit v1.2.3 From eb2789785428e2dbc3d5f413b16c67ff90d828c1 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Sat, 2 Apr 2022 08:30:34 +0100 Subject: dt-bindings: clock: Add R9A07G043 CPG Clock and Reset Definitions Define RZ/G2UL (R9A07G043U) Clock Pulse Generator Core Clock and module clock outputs, as listed in Table 7.1.4.2 ("Clock List r0.51") and also add Reset definitions referring to registers CPG_RST_* in Section 7.2.3 ("Register configuration") of the RZ/G2UL Hardware User's Manual (Rev. 0.51, Nov. 2021). Signed-off-by: Biju Das Reviewed-by: Lad Prabhakar Acked-by: Rob Herring Link: https://lore.kernel.org/r/20220402073037.23947-3-biju.das.jz@bp.renesas.com Signed-off-by: Geert Uytterhoeven --- include/dt-bindings/clock/r9a07g043-cpg.h | 184 ++++++++++++++++++++++++++++++ 1 file changed, 184 insertions(+) create mode 100644 include/dt-bindings/clock/r9a07g043-cpg.h (limited to 'include') diff --git a/include/dt-bindings/clock/r9a07g043-cpg.h b/include/dt-bindings/clock/r9a07g043-cpg.h new file mode 100644 index 000000000000..27e232733096 --- /dev/null +++ b/include/dt-bindings/clock/r9a07g043-cpg.h @@ -0,0 +1,184 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + * + * Copyright (C) 2022 Renesas Electronics Corp. + */ +#ifndef __DT_BINDINGS_CLOCK_R9A07G043_CPG_H__ +#define __DT_BINDINGS_CLOCK_R9A07G043_CPG_H__ + +#include + +/* R9A07G043 CPG Core Clocks */ +#define R9A07G043_CLK_I 0 +#define R9A07G043_CLK_I2 1 +#define R9A07G043_CLK_S0 2 +#define R9A07G043_CLK_SPI0 3 +#define R9A07G043_CLK_SPI1 4 +#define R9A07G043_CLK_SD0 5 +#define R9A07G043_CLK_SD1 6 +#define R9A07G043_CLK_M0 7 +#define R9A07G043_CLK_M2 8 +#define R9A07G043_CLK_M3 9 +#define R9A07G043_CLK_HP 10 +#define R9A07G043_CLK_TSU 11 +#define R9A07G043_CLK_ZT 12 +#define R9A07G043_CLK_P0 13 +#define R9A07G043_CLK_P1 14 +#define R9A07G043_CLK_P2 15 +#define R9A07G043_CLK_AT 16 +#define R9A07G043_OSCCLK 17 +#define R9A07G043_CLK_P0_DIV2 18 + +/* R9A07G043 Module Clocks */ +#define R9A07G043_CA55_SCLK 0 /* RZ/G2UL Only */ +#define R9A07G043_CA55_PCLK 1 /* RZ/G2UL Only */ +#define R9A07G043_CA55_ATCLK 2 /* RZ/G2UL Only */ +#define R9A07G043_CA55_GICCLK 3 /* RZ/G2UL Only */ +#define R9A07G043_CA55_PERICLK 4 /* RZ/G2UL Only */ +#define R9A07G043_CA55_ACLK 5 /* RZ/G2UL Only */ +#define R9A07G043_CA55_TSCLK 6 /* RZ/G2UL Only */ +#define R9A07G043_GIC600_GICCLK 7 /* RZ/G2UL Only */ +#define R9A07G043_IA55_CLK 8 /* RZ/G2UL Only */ +#define R9A07G043_IA55_PCLK 9 /* RZ/G2UL Only */ +#define R9A07G043_MHU_PCLK 10 /* RZ/G2UL Only */ +#define R9A07G043_SYC_CNT_CLK 11 +#define R9A07G043_DMAC_ACLK 12 +#define R9A07G043_DMAC_PCLK 13 +#define R9A07G043_OSTM0_PCLK 14 +#define R9A07G043_OSTM1_PCLK 15 +#define R9A07G043_OSTM2_PCLK 16 +#define R9A07G043_MTU_X_MCK_MTU3 17 +#define R9A07G043_POE3_CLKM_POE 18 +#define R9A07G043_WDT0_PCLK 19 +#define R9A07G043_WDT0_CLK 20 +#define R9A07G043_WDT2_PCLK 21 /* RZ/G2UL Only */ +#define R9A07G043_WDT2_CLK 22 /* RZ/G2UL Only */ +#define R9A07G043_SPI_CLK2 23 +#define R9A07G043_SPI_CLK 24 +#define R9A07G043_SDHI0_IMCLK 25 +#define R9A07G043_SDHI0_IMCLK2 26 +#define R9A07G043_SDHI0_CLK_HS 27 +#define R9A07G043_SDHI0_ACLK 28 +#define R9A07G043_SDHI1_IMCLK 29 +#define R9A07G043_SDHI1_IMCLK2 30 +#define R9A07G043_SDHI1_CLK_HS 31 +#define R9A07G043_SDHI1_ACLK 32 +#define R9A07G043_ISU_ACLK 33 /* RZ/G2UL Only */ +#define R9A07G043_ISU_PCLK 34 /* RZ/G2UL Only */ +#define R9A07G043_CRU_SYSCLK 35 /* RZ/G2UL Only */ +#define R9A07G043_CRU_VCLK 36 /* RZ/G2UL Only */ +#define R9A07G043_CRU_PCLK 37 /* RZ/G2UL Only */ +#define R9A07G043_CRU_ACLK 38 /* RZ/G2UL Only */ +#define R9A07G043_LCDC_CLK_A 39 /* RZ/G2UL Only */ +#define R9A07G043_LCDC_CLK_P 40 /* RZ/G2UL Only */ +#define R9A07G043_LCDC_CLK_D 41 /* RZ/G2UL Only */ +#define R9A07G043_SSI0_PCLK2 42 +#define R9A07G043_SSI0_PCLK_SFR 43 +#define R9A07G043_SSI1_PCLK2 44 +#define R9A07G043_SSI1_PCLK_SFR 45 +#define R9A07G043_SSI2_PCLK2 46 +#define R9A07G043_SSI2_PCLK_SFR 47 +#define R9A07G043_SSI3_PCLK2 48 +#define R9A07G043_SSI3_PCLK_SFR 49 +#define R9A07G043_SRC_CLKP 50 /* RZ/G2UL Only */ +#define R9A07G043_USB_U2H0_HCLK 51 +#define R9A07G043_USB_U2H1_HCLK 52 +#define R9A07G043_USB_U2P_EXR_CPUCLK 53 +#define R9A07G043_USB_PCLK 54 +#define R9A07G043_ETH0_CLK_AXI 55 +#define R9A07G043_ETH0_CLK_CHI 56 +#define R9A07G043_ETH1_CLK_AXI 57 +#define R9A07G043_ETH1_CLK_CHI 58 +#define R9A07G043_I2C0_PCLK 59 +#define R9A07G043_I2C1_PCLK 60 +#define R9A07G043_I2C2_PCLK 61 +#define R9A07G043_I2C3_PCLK 62 +#define R9A07G043_SCIF0_CLK_PCK 63 +#define R9A07G043_SCIF1_CLK_PCK 64 +#define R9A07G043_SCIF2_CLK_PCK 65 +#define R9A07G043_SCIF3_CLK_PCK 66 +#define R9A07G043_SCIF4_CLK_PCK 67 +#define R9A07G043_SCI0_CLKP 68 +#define R9A07G043_SCI1_CLKP 69 +#define R9A07G043_IRDA_CLKP 70 +#define R9A07G043_RSPI0_CLKB 71 +#define R9A07G043_RSPI1_CLKB 72 +#define R9A07G043_RSPI2_CLKB 73 +#define R9A07G043_CANFD_PCLK 74 +#define R9A07G043_GPIO_HCLK 75 +#define R9A07G043_ADC_ADCLK 76 +#define R9A07G043_ADC_PCLK 77 +#define R9A07G043_TSU_PCLK 78 + +/* R9A07G043 Resets */ +#define R9A07G043_CA55_RST_1_0 0 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_1_1 1 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_3_0 2 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_3_1 3 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_4 4 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_5 5 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_6 6 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_7 7 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_8 8 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_9 9 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_10 10 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_11 11 /* RZ/G2UL Only */ +#define R9A07G043_CA55_RST_12 12 /* RZ/G2UL Only */ +#define R9A07G043_GIC600_GICRESET_N 13 /* RZ/G2UL Only */ +#define R9A07G043_GIC600_DBG_GICRESET_N 14 /* RZ/G2UL Only */ +#define R9A07G043_IA55_RESETN 15 /* RZ/G2UL Only */ +#define R9A07G043_MHU_RESETN 16 /* RZ/G2UL Only */ +#define R9A07G043_DMAC_ARESETN 17 +#define R9A07G043_DMAC_RST_ASYNC 18 +#define R9A07G043_SYC_RESETN 19 +#define R9A07G043_OSTM0_PRESETZ 20 +#define R9A07G043_OSTM1_PRESETZ 21 +#define R9A07G043_OSTM2_PRESETZ 22 +#define R9A07G043_MTU_X_PRESET_MTU3 23 +#define R9A07G043_POE3_RST_M_REG 24 +#define R9A07G043_WDT0_PRESETN 25 +#define R9A07G043_WDT2_PRESETN 26 /* RZ/G2UL Only */ +#define R9A07G043_SPI_RST 27 +#define R9A07G043_SDHI0_IXRST 28 +#define R9A07G043_SDHI1_IXRST 29 +#define R9A07G043_ISU_ARESETN 30 /* RZ/G2UL Only */ +#define R9A07G043_ISU_PRESETN 31 /* RZ/G2UL Only */ +#define R9A07G043_CRU_CMN_RSTB 32 /* RZ/G2UL Only */ +#define R9A07G043_CRU_PRESETN 33 /* RZ/G2UL Only */ +#define R9A07G043_CRU_ARESETN 34 /* RZ/G2UL Only */ +#define R9A07G043_LCDC_RESET_N 35 /* RZ/G2UL Only */ +#define R9A07G043_SSI0_RST_M2_REG 36 +#define R9A07G043_SSI1_RST_M2_REG 37 +#define R9A07G043_SSI2_RST_M2_REG 38 +#define R9A07G043_SSI3_RST_M2_REG 39 +#define R9A07G043_SRC_RST 40 /* RZ/G2UL Only */ +#define R9A07G043_USB_U2H0_HRESETN 41 +#define R9A07G043_USB_U2H1_HRESETN 42 +#define R9A07G043_USB_U2P_EXL_SYSRST 43 +#define R9A07G043_USB_PRESETN 44 +#define R9A07G043_ETH0_RST_HW_N 45 +#define R9A07G043_ETH1_RST_HW_N 46 +#define R9A07G043_I2C0_MRST 47 +#define R9A07G043_I2C1_MRST 48 +#define R9A07G043_I2C2_MRST 49 +#define R9A07G043_I2C3_MRST 50 +#define R9A07G043_SCIF0_RST_SYSTEM_N 51 +#define R9A07G043_SCIF1_RST_SYSTEM_N 52 +#define R9A07G043_SCIF2_RST_SYSTEM_N 53 +#define R9A07G043_SCIF3_RST_SYSTEM_N 54 +#define R9A07G043_SCIF4_RST_SYSTEM_N 55 +#define R9A07G043_SCI0_RST 56 +#define R9A07G043_SCI1_RST 57 +#define R9A07G043_IRDA_RST 58 +#define R9A07G043_RSPI0_RST 59 +#define R9A07G043_RSPI1_RST 60 +#define R9A07G043_RSPI2_RST 61 +#define R9A07G043_CANFD_RSTP_N 62 +#define R9A07G043_CANFD_RSTC_N 63 +#define R9A07G043_GPIO_RSTN 64 +#define R9A07G043_GPIO_PORT_RESETN 65 +#define R9A07G043_GPIO_SPARE_RESETN 66 +#define R9A07G043_ADC_PRESETN 67 +#define R9A07G043_ADC_ADRST_N 68 +#define R9A07G043_TSU_PRESETN 69 + +#endif /* __DT_BINDINGS_CLOCK_R9A07G043_CPG_H__ */ -- cgit v1.2.3 From 1a95e04e29a116c3424988c70c441ca8ec2779ff Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Tue, 12 Apr 2022 11:24:00 +0100 Subject: net: phylink: remove phylink_helper_basex_speed() As there are now no users of phylink_helper_basex_speed(), we can remove this obsolete functionality. Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- include/linux/phylink.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 223781622b33..6d06896fc20d 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -160,11 +160,6 @@ struct phylink_mac_ops { * clearing unsupported speeds and duplex settings. The port modes * should not be cleared; phylink_set_port_modes() will help with this. * - * If the @state->interface mode is %PHY_INTERFACE_MODE_1000BASEX - * or %PHY_INTERFACE_MODE_2500BASEX, select the appropriate mode - * based on @state->advertising and/or @state->speed and update - * @state->interface accordingly. See phylink_helper_basex_speed(). - * * When @config->supported_interfaces has been set, phylink will iterate * over the supported interfaces to determine the full capability of the * MAC. The validation function must not print errors if @state->interface @@ -579,7 +574,6 @@ int phylink_speed_up(struct phylink *pl); #define phylink_test(bm, mode) __phylink_do_bit(test_bit, bm, mode) void phylink_set_port_modes(unsigned long *bits); -void phylink_helper_basex_speed(struct phylink_link_state *state); void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state, u16 bmsr, u16 lpa); -- cgit v1.2.3 From 12dc5c2cb7b269c5a1c6d02844f40bfce942a7a6 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 13 Apr 2022 13:51:51 +0300 Subject: net: rtnetlink: add msg kind names Add rtnl kind names instead of using raw values. We'll need to check for DEL kind later to validate bulk flag support. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/net/rtnetlink.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 9f48733bfd21..78712b51f3da 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -13,6 +13,13 @@ enum rtnl_link_flags { RTNL_FLAG_DOIT_UNLOCKED = 1, }; +enum rtnl_kinds { + RTNL_KIND_NEW, + RTNL_KIND_DEL, + RTNL_KIND_GET, + RTNL_KIND_SET +}; + void rtnl_register(int protocol, int msgtype, rtnl_doit_func, rtnl_dumpit_func, unsigned int flags); int rtnl_register_module(struct module *owner, int protocol, int msgtype, -- cgit v1.2.3 From 2e9ea3e30f696fd438319c07836422bb0bbb4608 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 13 Apr 2022 13:51:52 +0300 Subject: net: rtnetlink: add helper to extract msg type's kind Add a helper which extracts the msg type's kind using the kind mask (0x3). Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/net/rtnetlink.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 78712b51f3da..c51c5ff7f7e2 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -19,6 +19,12 @@ enum rtnl_kinds { RTNL_KIND_GET, RTNL_KIND_SET }; +#define RTNL_KIND_MASK 0x3 + +static inline enum rtnl_kinds rtnl_msgtype_kind(int msgtype) +{ + return msgtype & RTNL_KIND_MASK; +} void rtnl_register(int protocol, int msgtype, rtnl_doit_func, rtnl_dumpit_func, unsigned int flags); -- cgit v1.2.3 From 0569e31f1bc2f50613ba4c219f3ecc0d1174d841 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 13 Apr 2022 13:51:53 +0300 Subject: net: rtnetlink: use BIT for flag values Use BIT to define flag values. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/net/rtnetlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index c51c5ff7f7e2..0bf622409aaa 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -10,7 +10,7 @@ typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *, typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *); enum rtnl_link_flags { - RTNL_FLAG_DOIT_UNLOCKED = 1, + RTNL_FLAG_DOIT_UNLOCKED = BIT(0), }; enum rtnl_kinds { -- cgit v1.2.3 From 545528d788556c724eeb5400757f828ef27782a8 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 13 Apr 2022 13:51:54 +0300 Subject: net: netlink: add NLM_F_BULK delete request modifier Add a new delete request modifier called NLM_F_BULK which, when supported, would cause the request to delete multiple objects. The flag is a convenient way to signal that a multiple delete operation is requested which can be gradually added to different delete requests. In order to make sure older kernels will error out if the operation is not supported instead of doing something unintended we have to break a required condition when implementing support for this flag, f.e. for neighbors we will omit the mandatory mac address attribute. Initially it will be used to add flush with filtering support for bridge fdbs, but it also opens the door to add similar support to others. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index 4c0cde075c27..855dffb4c1c3 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -72,6 +72,7 @@ struct nlmsghdr { /* Modifiers to DELETE request */ #define NLM_F_NONREC 0x100 /* Do not delete recursively */ +#define NLM_F_BULK 0x200 /* Delete multiple objects */ /* Flags for ACK message */ #define NLM_F_CAPPED 0x100 /* request was capped */ -- cgit v1.2.3 From a6cec0bcd34264be8887791594be793b3f12719f Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 13 Apr 2022 13:51:55 +0300 Subject: net: rtnetlink: add bulk delete support flag Add a new rtnl flag (RTNL_FLAG_BULK_DEL_SUPPORTED) which is used to verify that the delete operation allows bulk object deletion. Also emit a warning if anyone tries to set it for non-delete kind. Suggested-by: David Ahern Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/net/rtnetlink.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 0bf622409aaa..bf8bb3357825 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -10,7 +10,8 @@ typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *, typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *); enum rtnl_link_flags { - RTNL_FLAG_DOIT_UNLOCKED = BIT(0), + RTNL_FLAG_DOIT_UNLOCKED = BIT(0), + RTNL_FLAG_BULK_DEL_SUPPORTED = BIT(1), }; enum rtnl_kinds { -- cgit v1.2.3 From 1306d5362a591493a2d07f685ed2cc480dcda320 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 13 Apr 2022 13:51:56 +0300 Subject: net: add ndo_fdb_del_bulk Add a new netdev op called ndo_fdb_del_bulk, it will be later used for driver-specific bulk delete implementation dispatched from rtnetlink. The first user will be the bridge, we need it to signal to rtnetlink from the driver that we support bulk delete operation (NLM_F_BULK). Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/netdevice.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 28ea4f8269d4..a602f29365b0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1260,6 +1260,10 @@ struct netdev_net_notifier { * struct net_device *dev, * const unsigned char *addr, u16 vid) * Deletes the FDB entry from dev coresponding to addr. + * int (*ndo_fdb_del_bulk)(struct ndmsg *ndm, struct nlattr *tb[], + * struct net_device *dev, + * u16 vid, + * struct netlink_ext_ack *extack); * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, * struct net_device *dev, struct net_device *filter_dev, * int *idx) @@ -1510,6 +1514,11 @@ struct net_device_ops { struct net_device *dev, const unsigned char *addr, u16 vid); + int (*ndo_fdb_del_bulk)(struct ndmsg *ndm, + struct nlattr *tb[], + struct net_device *dev, + u16 vid, + struct netlink_ext_ack *extack); int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, -- cgit v1.2.3 From ea2c0f9e3fc2f94f090d693b7235c02af1289629 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 13 Apr 2022 13:52:00 +0300 Subject: net: rtnetlink: add ndm flags and state mask attributes Add ndm flags/state masks which will be used for bulk delete filtering. All of these are used by the bridge and vxlan drivers. Also minimal attr policy validation is added, it is up to ndo_fdb_del_bulk implementers to further validate them. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/neighbour.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index db05fb55055e..39c565e460c7 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -32,6 +32,8 @@ enum { NDA_NH_ID, NDA_FDB_EXT_ATTRS, NDA_FLAGS_EXT, + NDA_NDM_STATE_MASK, + NDA_NDM_FLAGS_MASK, __NDA_MAX }; -- cgit v1.2.3 From b0c3e796f24b588b862b61ce235d3c9417dc8983 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Fri, 8 Apr 2022 18:14:57 +0200 Subject: random: make random_get_entropy() return an unsigned long Some implementations were returning type `unsigned long`, while others that fell back to get_cycles() were implicitly returning a `cycles_t` or an untyped constant int literal. That makes for weird and confusing code, and basically all code in the kernel already handled it like it was an `unsigned long`. I recently tried to handle it as the largest type it could be, a `cycles_t`, but doing so doesn't really help with much. Instead let's just make random_get_entropy() return an unsigned long all the time. This also matches the commonly used `arch_get_random_long()` function, so now RDRAND and RDTSC return the same sized integer, which means one can fallback to the other more gracefully. Cc: Dominik Brodowski Cc: Theodore Ts'o Acked-by: Thomas Gleixner Signed-off-by: Jason A. Donenfeld --- include/linux/timex.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/timex.h b/include/linux/timex.h index 059b18eb1f1f..5745c90c8800 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -75,7 +75,7 @@ * By default we use get_cycles() for this purpose, but individual * architectures may override this in their asm/timex.h header file. */ -#define random_get_entropy() get_cycles() +#define random_get_entropy() ((unsigned long)get_cycles()) #endif /* -- cgit v1.2.3 From d6d3146ce532268ad0ffd8d92d2b7492898decf1 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Wed, 13 Apr 2022 16:15:52 +0800 Subject: skb: add some helpers for skb drop reasons In order to simply the definition and assignment for 'enum skb_drop_reason', introduce some helpers. SKB_DR() is used to define a variable of type 'enum skb_drop_reason' with the 'SKB_DROP_REASON_NOT_SPECIFIED' initial value. SKB_DR_SET() is used to set the value of the variable. Seems it is a little useless? But it makes the code shorter. SKB_DR_OR() is used to set the value of the variable if it is not set yet, which means its value is SKB_DROP_REASON_NOT_SPECIFIED. Signed-off-by: Menglong Dong Reviewed-by: Jiang Biao Reviewed-by: Hao Peng Signed-off-by: David S. Miller --- include/linux/skbuff.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9b81ba497665..0cbd6ada957c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -450,6 +450,18 @@ enum skb_drop_reason { SKB_DROP_REASON_MAX, }; +#define SKB_DR_INIT(name, reason) \ + enum skb_drop_reason name = SKB_DROP_REASON_##reason +#define SKB_DR(name) \ + SKB_DR_INIT(name, NOT_SPECIFIED) +#define SKB_DR_SET(name, reason) \ + (name = SKB_DROP_REASON_##reason) +#define SKB_DR_OR(name, reason) \ + do { \ + if (name == SKB_DROP_REASON_NOT_SPECIFIED) \ + SKB_DR_SET(name, reason); \ + } while (0) + /* To allow 64K frame to be packed as single skb without frag_list we * require 64K/PAGE_SIZE pages plus 1 additional page to allow for * buffers which do not start on a page boundary. -- cgit v1.2.3 From c4eb664191b4a5ff6856478f903924176697719e Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Wed, 13 Apr 2022 16:15:53 +0800 Subject: net: ipv4: add skb drop reasons to ip_error() Eventually, I find out the handler function for inputting route lookup fail: ip_error(). The drop reasons we used in ip_error() are almost corresponding to IPSTATS_MIB_*, and following new reasons are introduced: SKB_DROP_REASON_IP_INADDRERRORS SKB_DROP_REASON_IP_INNOROUTES Isn't the name SKB_DROP_REASON_IP_HOSTUNREACH and SKB_DROP_REASON_IP_NETUNREACH more accurate? To make them corresponding to IPSTATS_MIB_*, we keep their name still. Signed-off-by: Menglong Dong Reviewed-by: Jiang Biao Reviewed-by: Hao Peng Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ++++++ include/trace/events/skb.h | 2 ++ 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0cbd6ada957c..886e83ac4b70 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -447,6 +447,12 @@ enum skb_drop_reason { * 2211, such as a broadcasts * ICMP_TIMESTAMP */ + SKB_DROP_REASON_IP_INADDRERRORS, /* host unreachable, corresponding + * to IPSTATS_MIB_INADDRERRORS + */ + SKB_DROP_REASON_IP_INNOROUTES, /* network unreachable, corresponding + * to IPSTATS_MIB_INADDRERRORS + */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 42647114fffe..0acac7e5a019 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -63,6 +63,8 @@ EM(SKB_DROP_REASON_TAP_TXFILTER, TAP_TXFILTER) \ EM(SKB_DROP_REASON_ICMP_CSUM, ICMP_CSUM) \ EM(SKB_DROP_REASON_INVALID_PROTO, INVALID_PROTO) \ + EM(SKB_DROP_REASON_IP_INADDRERRORS, IP_INADDRERRORS) \ + EM(SKB_DROP_REASON_IP_INNOROUTES, IP_INNOROUTES) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From 2edc1a383fda8d2f580216292dfd9daeae691e47 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Wed, 13 Apr 2022 16:15:55 +0800 Subject: net: ip: add skb drop reasons to ip forwarding Replace kfree_skb() which is used in ip6_forward() and ip_forward() with kfree_skb_reason(). The new drop reason 'SKB_DROP_REASON_PKT_TOO_BIG' is introduced for the case that the length of the packet exceeds MTU and can't fragment. Signed-off-by: Menglong Dong Reviewed-by: Jiang Biao Reviewed-by: Hao Peng Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +++ include/trace/events/skb.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 886e83ac4b70..0ef11df1bc67 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -453,6 +453,9 @@ enum skb_drop_reason { SKB_DROP_REASON_IP_INNOROUTES, /* network unreachable, corresponding * to IPSTATS_MIB_INADDRERRORS */ + SKB_DROP_REASON_PKT_TOO_BIG, /* packet size is too big (maybe exceed + * the MTU) + */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 0acac7e5a019..2da72a9a5764 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -65,6 +65,7 @@ EM(SKB_DROP_REASON_INVALID_PROTO, INVALID_PROTO) \ EM(SKB_DROP_REASON_IP_INADDRERRORS, IP_INADDRERRORS) \ EM(SKB_DROP_REASON_IP_INNOROUTES, IP_INNOROUTES) \ + EM(SKB_DROP_REASON_PKT_TOO_BIG, PKT_TOO_BIG) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM -- cgit v1.2.3 From 1ad6d548e2a452f21bcee4606ee4ec7afcde5f37 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Wed, 13 Apr 2022 16:15:56 +0800 Subject: net: icmp: introduce function icmpv6_param_prob_reason() In order to add the skb drop reasons support to icmpv6_param_prob(), introduce the function icmpv6_param_prob_reason() and make icmpv6_param_prob() an inline call to it. This new function will be used in the following patches. Signed-off-by: Menglong Dong Reviewed-by: Jiang Biao Reviewed-by: Hao Peng Signed-off-by: David S. Miller --- include/linux/icmpv6.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index 9055cb380ee2..db0f4fcfdaf4 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -79,8 +79,9 @@ extern int icmpv6_init(void); extern int icmpv6_err_convert(u8 type, u8 code, int *err); extern void icmpv6_cleanup(void); -extern void icmpv6_param_prob(struct sk_buff *skb, - u8 code, int pos); +extern void icmpv6_param_prob_reason(struct sk_buff *skb, + u8 code, int pos, + enum skb_drop_reason reason); struct flowi6; struct in6_addr; @@ -91,6 +92,12 @@ extern void icmpv6_flow_init(struct sock *sk, const struct in6_addr *daddr, int oif); +static inline void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos) +{ + icmpv6_param_prob_reason(skb, code, pos, + SKB_DROP_REASON_NOT_SPECIFIED); +} + static inline bool icmpv6_is_err(int type) { switch (type) { -- cgit v1.2.3 From 72907bff3bd346ef4879bd1dfc89ba12133da368 Mon Sep 17 00:00:00 2001 From: David Zhang Date: Thu, 31 Mar 2022 11:55:49 -0400 Subject: drm: add PSR2 support and capability definition as per eDP 1.5 [why & how] As per eDP 1.5 spec, add the below two DPCD bit fields for PSR-SU support and capability: 1. DP_PSR2_WITH_Y_COORD_ET_SUPPORTED 2. DP_PSR2_SU_AUX_FRAME_SYNC_NOT_NEEDED changes in v2 ------------------ * fixed the typo * explicitly list what DPCD bit fields are added Signed-off-by: David Zhang Reviewed-by: Harry Wentland Signed-off-by: Alex Deucher --- include/drm/dp/drm_dp_helper.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/drm/dp/drm_dp_helper.h b/include/drm/dp/drm_dp_helper.h index 51e02cf75277..77a27b1b98a6 100644 --- a/include/drm/dp/drm_dp_helper.h +++ b/include/drm/dp/drm_dp_helper.h @@ -361,6 +361,7 @@ struct drm_panel; # define DP_PSR_IS_SUPPORTED 1 # define DP_PSR2_IS_SUPPORTED 2 /* eDP 1.4 */ # define DP_PSR2_WITH_Y_COORD_IS_SUPPORTED 3 /* eDP 1.4a */ +# define DP_PSR2_WITH_Y_COORD_ET_SUPPORTED 4 /* eDP 1.5, adopted eDP 1.4b SCR */ #define DP_PSR_CAPS 0x071 /* XXX 1.2? */ # define DP_PSR_NO_TRAIN_ON_EXIT 1 @@ -375,6 +376,7 @@ struct drm_panel; # define DP_PSR_SETUP_TIME_SHIFT 1 # define DP_PSR2_SU_Y_COORDINATE_REQUIRED (1 << 4) /* eDP 1.4a */ # define DP_PSR2_SU_GRANULARITY_REQUIRED (1 << 5) /* eDP 1.4b */ +# define DP_PSR2_SU_AUX_FRAME_SYNC_NOT_NEEDED (1 << 6)/* eDP 1.5, adopted eDP 1.4b SCR */ #define DP_PSR2_SU_X_GRANULARITY 0x072 /* eDP 1.4b */ #define DP_PSR2_SU_Y_GRANULARITY 0x074 /* eDP 1.4b */ -- cgit v1.2.3 From f8e6b7babfeb40987e946bc1427609a9976017fa Mon Sep 17 00:00:00 2001 From: Karol Herbst Date: Mon, 11 Apr 2022 15:44:04 +0200 Subject: dma-buf-map: remove renamed header file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 7938f4218168 ("dma-buf-map: Rename to iosys-map") already renamed this file, but it got brought back by a merge. Delete it for real this time. Fixes: 30424ebae8df ("Merge tag 'drm-intel-gt-next-2022-02-17' of git://anongit.freedesktop.org/drm/drm-intel into drm-intel-next") Cc: Rodrigo Vivi Cc: Lucas De Marchi Cc: dri-devel@lists.freedesktop.org Signed-off-by: Karol Herbst Reviewed-by: Michel Dänzer Reviewed-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20220411134404.524776-1-kherbst@redhat.com --- include/linux/dma-buf-map.h | 266 -------------------------------------------- 1 file changed, 266 deletions(-) delete mode 100644 include/linux/dma-buf-map.h (limited to 'include') diff --git a/include/linux/dma-buf-map.h b/include/linux/dma-buf-map.h deleted file mode 100644 index 19fa0b5ae5ec..000000000000 --- a/include/linux/dma-buf-map.h +++ /dev/null @@ -1,266 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Pointer to dma-buf-mapped memory, plus helpers. - */ - -#ifndef __DMA_BUF_MAP_H__ -#define __DMA_BUF_MAP_H__ - -#include -#include - -/** - * DOC: overview - * - * Calling dma-buf's vmap operation returns a pointer to the buffer's memory. - * Depending on the location of the buffer, users may have to access it with - * I/O operations or memory load/store operations. For example, copying to - * system memory could be done with memcpy(), copying to I/O memory would be - * done with memcpy_toio(). - * - * .. code-block:: c - * - * void *vaddr = ...; // pointer to system memory - * memcpy(vaddr, src, len); - * - * void *vaddr_iomem = ...; // pointer to I/O memory - * memcpy_toio(vaddr, _iomem, src, len); - * - * When using dma-buf's vmap operation, the returned pointer is encoded as - * :c:type:`struct dma_buf_map `. - * :c:type:`struct dma_buf_map ` stores the buffer's address in - * system or I/O memory and a flag that signals the required method of - * accessing the buffer. Use the returned instance and the helper functions - * to access the buffer's memory in the correct way. - * - * The type :c:type:`struct dma_buf_map ` and its helpers are - * actually independent from the dma-buf infrastructure. When sharing buffers - * among devices, drivers have to know the location of the memory to access - * the buffers in a safe way. :c:type:`struct dma_buf_map ` - * solves this problem for dma-buf and its users. If other drivers or - * sub-systems require similar functionality, the type could be generalized - * and moved to a more prominent header file. - * - * Open-coding access to :c:type:`struct dma_buf_map ` is - * considered bad style. Rather then accessing its fields directly, use one - * of the provided helper functions, or implement your own. For example, - * instances of :c:type:`struct dma_buf_map ` can be initialized - * statically with DMA_BUF_MAP_INIT_VADDR(), or at runtime with - * dma_buf_map_set_vaddr(). These helpers will set an address in system memory. - * - * .. code-block:: c - * - * struct dma_buf_map map = DMA_BUF_MAP_INIT_VADDR(0xdeadbeaf); - * - * dma_buf_map_set_vaddr(&map, 0xdeadbeaf); - * - * To set an address in I/O memory, use dma_buf_map_set_vaddr_iomem(). - * - * .. code-block:: c - * - * dma_buf_map_set_vaddr_iomem(&map, 0xdeadbeaf); - * - * Instances of struct dma_buf_map do not have to be cleaned up, but - * can be cleared to NULL with dma_buf_map_clear(). Cleared mappings - * always refer to system memory. - * - * .. code-block:: c - * - * dma_buf_map_clear(&map); - * - * Test if a mapping is valid with either dma_buf_map_is_set() or - * dma_buf_map_is_null(). - * - * .. code-block:: c - * - * if (dma_buf_map_is_set(&map) != dma_buf_map_is_null(&map)) - * // always true - * - * Instances of :c:type:`struct dma_buf_map ` can be compared - * for equality with dma_buf_map_is_equal(). Mappings the point to different - * memory spaces, system or I/O, are never equal. That's even true if both - * spaces are located in the same address space, both mappings contain the - * same address value, or both mappings refer to NULL. - * - * .. code-block:: c - * - * struct dma_buf_map sys_map; // refers to system memory - * struct dma_buf_map io_map; // refers to I/O memory - * - * if (dma_buf_map_is_equal(&sys_map, &io_map)) - * // always false - * - * A set up instance of struct dma_buf_map can be used to access or manipulate - * the buffer memory. Depending on the location of the memory, the provided - * helpers will pick the correct operations. Data can be copied into the memory - * with dma_buf_map_memcpy_to(). The address can be manipulated with - * dma_buf_map_incr(). - * - * .. code-block:: c - * - * const void *src = ...; // source buffer - * size_t len = ...; // length of src - * - * dma_buf_map_memcpy_to(&map, src, len); - * dma_buf_map_incr(&map, len); // go to first byte after the memcpy - */ - -/** - * struct dma_buf_map - Pointer to vmap'ed dma-buf memory. - * @vaddr_iomem: The buffer's address if in I/O memory - * @vaddr: The buffer's address if in system memory - * @is_iomem: True if the dma-buf memory is located in I/O - * memory, or false otherwise. - */ -struct dma_buf_map { - union { - void __iomem *vaddr_iomem; - void *vaddr; - }; - bool is_iomem; -}; - -/** - * DMA_BUF_MAP_INIT_VADDR - Initializes struct dma_buf_map to an address in system memory - * @vaddr_: A system-memory address - */ -#define DMA_BUF_MAP_INIT_VADDR(vaddr_) \ - { \ - .vaddr = (vaddr_), \ - .is_iomem = false, \ - } - -/** - * dma_buf_map_set_vaddr - Sets a dma-buf mapping structure to an address in system memory - * @map: The dma-buf mapping structure - * @vaddr: A system-memory address - * - * Sets the address and clears the I/O-memory flag. - */ -static inline void dma_buf_map_set_vaddr(struct dma_buf_map *map, void *vaddr) -{ - map->vaddr = vaddr; - map->is_iomem = false; -} - -/** - * dma_buf_map_set_vaddr_iomem - Sets a dma-buf mapping structure to an address in I/O memory - * @map: The dma-buf mapping structure - * @vaddr_iomem: An I/O-memory address - * - * Sets the address and the I/O-memory flag. - */ -static inline void dma_buf_map_set_vaddr_iomem(struct dma_buf_map *map, - void __iomem *vaddr_iomem) -{ - map->vaddr_iomem = vaddr_iomem; - map->is_iomem = true; -} - -/** - * dma_buf_map_is_equal - Compares two dma-buf mapping structures for equality - * @lhs: The dma-buf mapping structure - * @rhs: A dma-buf mapping structure to compare with - * - * Two dma-buf mapping structures are equal if they both refer to the same type of memory - * and to the same address within that memory. - * - * Returns: - * True is both structures are equal, or false otherwise. - */ -static inline bool dma_buf_map_is_equal(const struct dma_buf_map *lhs, - const struct dma_buf_map *rhs) -{ - if (lhs->is_iomem != rhs->is_iomem) - return false; - else if (lhs->is_iomem) - return lhs->vaddr_iomem == rhs->vaddr_iomem; - else - return lhs->vaddr == rhs->vaddr; -} - -/** - * dma_buf_map_is_null - Tests for a dma-buf mapping to be NULL - * @map: The dma-buf mapping structure - * - * Depending on the state of struct dma_buf_map.is_iomem, tests if the - * mapping is NULL. - * - * Returns: - * True if the mapping is NULL, or false otherwise. - */ -static inline bool dma_buf_map_is_null(const struct dma_buf_map *map) -{ - if (map->is_iomem) - return !map->vaddr_iomem; - return !map->vaddr; -} - -/** - * dma_buf_map_is_set - Tests is the dma-buf mapping has been set - * @map: The dma-buf mapping structure - * - * Depending on the state of struct dma_buf_map.is_iomem, tests if the - * mapping has been set. - * - * Returns: - * True if the mapping is been set, or false otherwise. - */ -static inline bool dma_buf_map_is_set(const struct dma_buf_map *map) -{ - return !dma_buf_map_is_null(map); -} - -/** - * dma_buf_map_clear - Clears a dma-buf mapping structure - * @map: The dma-buf mapping structure - * - * Clears all fields to zero; including struct dma_buf_map.is_iomem. So - * mapping structures that were set to point to I/O memory are reset for - * system memory. Pointers are cleared to NULL. This is the default. - */ -static inline void dma_buf_map_clear(struct dma_buf_map *map) -{ - if (map->is_iomem) { - map->vaddr_iomem = NULL; - map->is_iomem = false; - } else { - map->vaddr = NULL; - } -} - -/** - * dma_buf_map_memcpy_to - Memcpy into dma-buf mapping - * @dst: The dma-buf mapping structure - * @src: The source buffer - * @len: The number of byte in src - * - * Copies data into a dma-buf mapping. The source buffer is in system - * memory. Depending on the buffer's location, the helper picks the correct - * method of accessing the memory. - */ -static inline void dma_buf_map_memcpy_to(struct dma_buf_map *dst, const void *src, size_t len) -{ - if (dst->is_iomem) - memcpy_toio(dst->vaddr_iomem, src, len); - else - memcpy(dst->vaddr, src, len); -} - -/** - * dma_buf_map_incr - Increments the address stored in a dma-buf mapping - * @map: The dma-buf mapping structure - * @incr: The number of bytes to increment - * - * Increments the address stored in a dma-buf mapping. Depending on the - * buffer's location, the correct value will be updated. - */ -static inline void dma_buf_map_incr(struct dma_buf_map *map, size_t incr) -{ - if (map->is_iomem) - map->vaddr_iomem += incr; - else - map->vaddr += incr; -} - -#endif /* __DMA_BUF_MAP_H__ */ -- cgit v1.2.3 From bdc21a4d286c6917fe966fd765de99411095b1b4 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Mon, 21 Mar 2022 09:57:22 +0000 Subject: PM: EM: Add .get_cost() callback The Energy Model (EM) supports devices which report abstract power scale, not only real Watts. The primary goal for EM is to enable the Energy Aware Scheduler (EAS) for a given platform. Some of the platforms might not be able to deliver proper power values. The only information that they might have is the relative efficiency between CPU types. Thus, it makes sense to remove some restrictions in the EM framework and introduce a mechanism which would support those platforms. What is crucial for EAS to operate is the 'cost' field in the EM. The 'cost' is calculated internally in EM framework based on knowledge from 'power' values. The 'cost' values must be strictly increasing. The existing API with its 'power' value size restrictions cannot guarantee that the 'cost' will meet this requirement. Since the platform is missing this detailed information, but has only efficiency details, introduce a new custom callback in the EM framework. The new callback would allow to provide the 'cost' values which reflect efficiency of the CPUs. This would allow to provide EAS information which has different relation than what would be forced by the EM internal formulas calculating 'cost' values. Thanks to this new callback it is possible to create a system view for EAS which has no overlapping performance states across many Performance Domains. Signed-off-by: Lukasz Luba Reviewed-by: Ionela Voinescu Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 9f3c400bc52d..0a3a5663177b 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -114,9 +114,30 @@ struct em_data_callback { */ int (*active_power)(unsigned long *power, unsigned long *freq, struct device *dev); + + /** + * get_cost() - Provide the cost at the given performance state of + * a device + * @dev : Device for which we do this operation (can be a CPU) + * @freq : Frequency at the performance state in kHz + * @cost : The cost value for the performance state + * (modified) + * + * In case of CPUs, the cost is the one of a single CPU in the domain. + * It is expected to fit in the [0, EM_MAX_POWER] range due to internal + * usage in EAS calculation. + * + * Return 0 on success, or appropriate error value in case of failure. + */ + int (*get_cost)(struct device *dev, unsigned long freq, + unsigned long *cost); }; -#define EM_DATA_CB(_active_power_cb) { .active_power = &_active_power_cb } #define EM_SET_ACTIVE_POWER_CB(em_cb, cb) ((em_cb).active_power = cb) +#define EM_ADV_DATA_CB(_active_power_cb, _cost_cb) \ + { .active_power = _active_power_cb, \ + .get_cost = _cost_cb } +#define EM_DATA_CB(_active_power_cb) \ + EM_ADV_DATA_CB(_active_power_cb, NULL) struct em_perf_domain *em_cpu_get(int cpu); struct em_perf_domain *em_pd_get(struct device *dev); @@ -264,6 +285,7 @@ static inline int em_pd_nr_perf_states(struct em_perf_domain *pd) #else struct em_data_callback {}; +#define EM_ADV_DATA_CB(_active_power_cb, _cost_cb) { } #define EM_DATA_CB(_active_power_cb) { } #define EM_SET_ACTIVE_POWER_CB(em_cb, cb) do { } while (0) -- cgit v1.2.3 From fc3a9a9858478ab5f8441765a3f9552a0ceba10c Mon Sep 17 00:00:00 2001 From: Pierre Gondois Date: Mon, 21 Mar 2022 09:57:23 +0000 Subject: PM: EM: Add artificial EM flag The Energy Model (EM) can be used on platforms which are missing real power information. Those platforms would implement .get_cost() which populates needed values for the Energy Aware Scheduler (EAS). The EAS doesn't use 'power' fields from EM, but other frameworks might use them. Thus, to avoid miss-usage of this specific type of EM, introduce a new flags which can be checked by other frameworks. Signed-off-by: Pierre Gondois Signed-off-by: Lukasz Luba Reviewed-by: Ionela Voinescu Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 0a3a5663177b..92e82a322859 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -67,11 +67,16 @@ struct em_perf_domain { * * EM_PERF_DOMAIN_SKIP_INEFFICIENCIES: Skip inefficient states when estimating * energy consumption. + * + * EM_PERF_DOMAIN_ARTIFICIAL: The power values are artificial and might be + * created by platform missing real power information */ #define EM_PERF_DOMAIN_MILLIWATTS BIT(0) #define EM_PERF_DOMAIN_SKIP_INEFFICIENCIES BIT(1) +#define EM_PERF_DOMAIN_ARTIFICIAL BIT(2) #define em_span_cpus(em) (to_cpumask((em)->cpus)) +#define em_is_artificial(em) ((em)->flags & EM_PERF_DOMAIN_ARTIFICIAL) #ifdef CONFIG_ENERGY_MODEL #define EM_MAX_POWER 0xFFFF -- cgit v1.2.3 From 75a3a99a5a9886af13be44e640cb415ebda80db2 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Mon, 21 Mar 2022 09:57:25 +0000 Subject: PM: EM: Change the order of arguments in the .active_power() callback The .active_power() callback passes the device pointer when it's called. Aligned with a convetion present in other subsystems and pass the 'dev' as a first argument. It looks more cleaner. Adjust all affected drivers which implement that API callback. Suggested-by: Ionela Voinescu Signed-off-by: Lukasz Luba Reviewed-by: Ionela Voinescu Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 92e82a322859..8419bffb4398 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -101,11 +101,11 @@ struct em_data_callback { /** * active_power() - Provide power at the next performance state of * a device + * @dev : Device for which we do this operation (can be a CPU) * @power : Active power at the performance state * (modified) * @freq : Frequency at the performance state in kHz * (modified) - * @dev : Device for which we do this operation (can be a CPU) * * active_power() must find the lowest performance state of 'dev' above * 'freq' and update 'power' and 'freq' to the matching active power @@ -117,8 +117,8 @@ struct em_data_callback { * * Return 0 on success. */ - int (*active_power)(unsigned long *power, unsigned long *freq, - struct device *dev); + int (*active_power)(struct device *dev, unsigned long *power, + unsigned long *freq); /** * get_cost() - Provide the cost at the given performance state of -- cgit v1.2.3 From ce1cb680ff1c5b88505f878137796b1723e00193 Mon Sep 17 00:00:00 2001 From: David Cohen Date: Thu, 24 Mar 2022 08:07:30 +0000 Subject: PM: sleep: enable dynamic debug support within pm_pr_dbg() Currently pm_pr_dbg() is used to filter kernel pm debug messages based on pm_debug_messages_on flag. The problem is if we enable/disable this flag it will affect all pm_pr_dbg() calls at once, so we can't individually control them. This patch changes pm_pr_dbg() implementation as such: - If pm_debug_messages_on is enabled, print the message. - If pm_debug_messages_on is disabled and CONFIG_DYNAMIC_DEBUG is enabled, only print the messages explicitly enabled on /sys/kernel/debug/dynamic_debug/control. - If pm_debug_messages_on is disabled and CONFIG_DYNAMIC_DEBUG is disabled, don't print the message. Signed-off-by: David Cohen Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 44 +++++++++++++++++++++++++++++++++++++++----- 1 file changed, 39 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 300273ff40cc..70f2921e2e70 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -542,22 +542,56 @@ static inline void unlock_system_sleep(void) {} #ifdef CONFIG_PM_SLEEP_DEBUG extern bool pm_print_times_enabled; extern bool pm_debug_messages_on; -extern __printf(2, 3) void __pm_pr_dbg(bool defer, const char *fmt, ...); +static inline int pm_dyn_debug_messages_on(void) +{ +#ifdef CONFIG_DYNAMIC_DEBUG + return 1; +#else + return 0; +#endif +} +#ifndef pr_fmt +#define pr_fmt(fmt) "PM: " fmt +#endif +#define __pm_pr_dbg(fmt, ...) \ + do { \ + if (pm_debug_messages_on) \ + printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ + else if (pm_dyn_debug_messages_on()) \ + pr_debug(fmt, ##__VA_ARGS__); \ + } while (0) +#define __pm_deferred_pr_dbg(fmt, ...) \ + do { \ + if (pm_debug_messages_on) \ + printk_deferred(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ + } while (0) #else #define pm_print_times_enabled (false) #define pm_debug_messages_on (false) #include -#define __pm_pr_dbg(defer, fmt, ...) \ - no_printk(KERN_DEBUG fmt, ##__VA_ARGS__) +#define __pm_pr_dbg(fmt, ...) \ + no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) +#define __pm_deferred_pr_dbg(fmt, ...) \ + no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif +/** + * pm_pr_dbg - print pm sleep debug messages + * + * If pm_debug_messages_on is enabled, print message. + * If pm_debug_messages_on is disabled and CONFIG_DYNAMIC_DEBUG is enabled, + * print message only from instances explicitly enabled on dynamic debug's + * control. + * If pm_debug_messages_on is disabled and CONFIG_DYNAMIC_DEBUG is disabled, + * don't print message. + */ #define pm_pr_dbg(fmt, ...) \ - __pm_pr_dbg(false, fmt, ##__VA_ARGS__) + __pm_pr_dbg(fmt, ##__VA_ARGS__) #define pm_deferred_pr_dbg(fmt, ...) \ - __pm_pr_dbg(true, fmt, ##__VA_ARGS__) + __pm_deferred_pr_dbg(fmt, ##__VA_ARGS__) #ifdef CONFIG_PM_AUTOSLEEP -- cgit v1.2.3 From cf6ba0750a22a54f5101986401271429995cc4a0 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 4 Apr 2022 17:21:50 +0200 Subject: ACPI: bus: Introduce acpi_dev_for_each_child() Introduce a wrapper around device_for_each_child() to iterate over the children of a given ACPI device object. This function will be used in subsequent change sets. Signed-off-by: Rafael J. Wysocki Reviewed-by: Mika Westerberg --- include/acpi/acpi_bus.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index c4b78c21d793..c616f3d8506b 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -481,6 +481,8 @@ void acpi_initialize_hp_context(struct acpi_device *adev, extern struct bus_type acpi_bus_type; int acpi_bus_for_each_dev(int (*fn)(struct device *, void *), void *data); +int acpi_dev_for_each_child(struct acpi_device *adev, + int (*fn)(struct device *, void *), void *data); /* * Events -- cgit v1.2.3 From b7dd6298db81ea6dd902f1787eaf9a43228e2707 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 4 Apr 2022 17:23:13 +0200 Subject: ACPI: PM: Introduce acpi_dev_power_up_children_with_adr() Introduce a function powering up all of the children of a given ACPI device object that are power-manageable and hold valid _ADR ACPI objects so as to make it possible to prepare the corresponding "physical" devices for enumeration carried out by a bus type driver, like PCI. This function will be used in a subsequent change set. Signed-off-by: Rafael J. Wysocki Reviewed-by: Mika Westerberg --- include/acpi/acpi_bus.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index c616f3d8506b..b44aaffedb91 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -524,6 +524,7 @@ int acpi_device_fix_up_power(struct acpi_device *device); int acpi_bus_update_power(acpi_handle handle, int *state_p); int acpi_device_update_power(struct acpi_device *device, int *state_p); bool acpi_bus_power_manageable(acpi_handle handle); +void acpi_dev_power_up_children_with_adr(struct acpi_device *adev); int acpi_device_power_add_dependent(struct acpi_device *adev, struct device *dev); void acpi_device_power_remove_dependent(struct acpi_device *adev, -- cgit v1.2.3 From 1227418989346af3af179742cf42ce842e0ad484 Mon Sep 17 00:00:00 2001 From: Dov Murik Date: Tue, 12 Apr 2022 21:21:24 +0000 Subject: efi: Save location of EFI confidential computing area Confidential computing (coco) hardware such as AMD SEV (Secure Encrypted Virtualization) allows a guest owner to inject secrets into the VMs memory without the host/hypervisor being able to read them. Firmware support for secret injection is available in OVMF, which reserves a memory area for secret injection and includes a pointer to it the in EFI config table entry LINUX_EFI_COCO_SECRET_TABLE_GUID. If EFI exposes such a table entry, uefi_init() will keep a pointer to the EFI config table entry in efi.coco_secret, so it can be used later by the kernel (specifically drivers/virt/coco/efi_secret). It will also appear in the kernel log as "CocoSecret=ADDRESS"; for example: [ 0.000000] efi: EFI v2.70 by EDK II [ 0.000000] efi: CocoSecret=0x7f22e680 SMBIOS=0x7f541000 ACPI=0x7f77e000 ACPI 2.0=0x7f77e014 MEMATTR=0x7ea0c018 The new functionality can be enabled with CONFIG_EFI_COCO_SECRET=y. Signed-off-by: Dov Murik Reviewed-by: Gerd Hoffmann Link: https://lore.kernel.org/r/20220412212127.154182-2-dovmurik@linux.ibm.com Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index ccd4d3f91c98..771d4cd06b56 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -405,6 +405,7 @@ void efi_native_runtime_setup(void); #define LINUX_EFI_MEMRESERVE_TABLE_GUID EFI_GUID(0x888eb0c6, 0x8ede, 0x4ff5, 0xa8, 0xf0, 0x9a, 0xee, 0x5c, 0xb9, 0x77, 0xc2) #define LINUX_EFI_INITRD_MEDIA_GUID EFI_GUID(0x5568e427, 0x68fc, 0x4f3d, 0xac, 0x74, 0xca, 0x55, 0x52, 0x31, 0xcc, 0x68) #define LINUX_EFI_MOK_VARIABLE_TABLE_GUID EFI_GUID(0xc451ed2b, 0x9694, 0x45d3, 0xba, 0xba, 0xed, 0x9f, 0x89, 0x88, 0xa3, 0x89) +#define LINUX_EFI_COCO_SECRET_AREA_GUID EFI_GUID(0xadf956ad, 0xe98c, 0x484c, 0xae, 0x11, 0xb5, 0x1c, 0x7d, 0x33, 0x64, 0x47) /* OEM GUIDs */ #define DELLEMC_EFI_RCI2_TABLE_GUID EFI_GUID(0x2d9f28a2, 0xa886, 0x456a, 0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55) @@ -596,6 +597,7 @@ extern struct efi { unsigned long tpm_log; /* TPM2 Event Log table */ unsigned long tpm_final_log; /* TPM2 Final Events Log table */ unsigned long mokvar_table; /* MOK variable config table */ + unsigned long coco_secret; /* Confidential computing secret table */ efi_get_time_t *get_time; efi_set_time_t *set_time; @@ -1335,4 +1337,12 @@ extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt) { } #endif +struct linux_efi_coco_secret_area { + u64 base_pa; + u64 size; +}; + +/* Header of a populated EFI secret area */ +#define EFI_SECRET_TABLE_HEADER_GUID EFI_GUID(0x1e74f542, 0x71dd, 0x4d66, 0x96, 0x3e, 0xef, 0x42, 0x87, 0xff, 0x17, 0x3b) + #endif /* _LINUX_EFI_H */ -- cgit v1.2.3 From aa480379d8bdb33920d68acfd90f823c8af32578 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Fri, 4 Mar 2022 07:36:37 +0100 Subject: efi: Add missing prototype for efi_capsule_setup_info Fixes "no previous declaration for 'efi_capsule_setup_info'" warnings under W=1. Fixes: 2959c95d510c ("efi/capsule: Add support for Quark security header") Signed-off-by: Jan Kiszka Link: https://lore.kernel.org/r/c28d3f86-dd72-27d1-e2c2-40971b8da6bd@siemens.com Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index 771d4cd06b56..fd266198f9d8 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -213,6 +213,8 @@ struct capsule_info { size_t page_bytes_remain; }; +int efi_capsule_setup_info(struct capsule_info *cap_info, void *kbuff, + size_t hdr_bytes); int __efi_capsule_setup_info(struct capsule_info *cap_info); /* -- cgit v1.2.3 From 1ef3342a934e235aca72b4bcc0d6854d80a65077 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 13 Apr 2022 10:10:36 -0300 Subject: vfio/pci: Fix vf_token mechanism when device-specific VF drivers are used get_pf_vdev() tries to check if a PF is a VFIO PF by looking at the driver: if (pci_dev_driver(physfn) != pci_dev_driver(vdev->pdev)) { However now that we have multiple VF and PF drivers this is no longer reliable. This means that security tests realted to vf_token can be skipped by mixing and matching different VFIO PCI drivers. Instead of trying to use the driver core to find the PF devices maintain a linked list of all PF vfio_pci_core_device's that we have called pci_enable_sriov() on. When registering a VF just search the list to see if the PF is present and record the match permanently in the struct. PCI core locking prevents a PF from passing pci_disable_sriov() while VF drivers are attached so the VFIO owned PF becomes a static property of the VF. In common cases where vfio does not own the PF the global list remains empty and the VF's pointer is statically NULL. This also fixes a lockdep splat from recursive locking of the vfio_group::device_lock between vfio_device_get_from_name() and vfio_device_get_from_dev(). If the VF and PF share the same group this would deadlock. Fixes: ff53edf6d6ab ("vfio/pci: Split the pci_driver code out of vfio_pci_core.c") Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/0-v3-876570980634+f2e8-vfio_vf_token_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio_pci_core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 74a4a0f17b28..48f2dd3c568c 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -133,6 +133,8 @@ struct vfio_pci_core_device { struct mutex ioeventfds_lock; struct list_head ioeventfds_list; struct vfio_pci_vf_token *vf_token; + struct list_head sriov_pfs_item; + struct vfio_pci_core_device *sriov_pf_core_dev; struct notifier_block nb; struct mutex vma_lock; struct list_head vma_list; -- cgit v1.2.3 From c24a950ec7d60c4da91dc3f273295c7f438b531e Mon Sep 17 00:00:00 2001 From: Peter Gonda Date: Thu, 7 Apr 2022 14:02:33 -0700 Subject: KVM, SEV: Add KVM_EXIT_SHUTDOWN metadata for SEV-ES If an SEV-ES guest requests termination, exit to userspace with KVM_EXIT_SYSTEM_EVENT and a dedicated SEV_TERM type instead of -EINVAL so that userspace can take appropriate action. See AMD's GHCB spec section '4.1.13 Termination Request' for more details. Suggested-by: Sean Christopherson Suggested-by: Paolo Bonzini Cc: kvm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Peter Gonda Reported-by: kernel test robot Message-Id: <20220407210233.782250-1-pgonda@google.com> [Add documentatino. - Paolo] Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 8616af85dc5d..dd1d8167e71f 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -444,8 +444,11 @@ struct kvm_run { #define KVM_SYSTEM_EVENT_SHUTDOWN 1 #define KVM_SYSTEM_EVENT_RESET 2 #define KVM_SYSTEM_EVENT_CRASH 3 +#define KVM_SYSTEM_EVENT_SEV_TERM 4 +#define KVM_SYSTEM_EVENT_NDATA_VALID (1u << 31) __u32 type; - __u64 flags; + __u32 ndata; + __u64 data[16]; } system_event; /* KVM_EXIT_S390_STSI */ struct { -- cgit v1.2.3 From 002752af7b89b74c64fe6bec8c5fde3d3a7810d8 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 8 Apr 2022 21:48:40 +0300 Subject: device property: Allow error pointer to be passed to fwnode APIs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some of the fwnode APIs might return an error pointer instead of NULL or valid fwnode handle. The result of such API call may be considered optional and hence the test for it is usually done in a form of fwnode = fwnode_find_reference(...); if (IS_ERR(fwnode)) ...error handling... Nevertheless the resulting fwnode may have bumped the reference count and hence caller of the above API is obliged to call fwnode_handle_put(). Since fwnode may be not valid either as NULL or error pointer the check has to be performed there. This approach uglifies the code and adds a point of making a mistake, i.e. forgetting about error point case. To prevent this, allow an error pointer to be passed to the fwnode APIs. Fixes: 83b34afb6b79 ("device property: Introduce fwnode_find_reference()") Reported-by: Nuno Sá Tested-by: Nuno Sá Acked-by: Nuno Sá Reviewed-by: Sakari Ailus Reviewed-by: Heikki Krogerus Signed-off-by: Andy Shevchenko Tested-by: Michael Walle Signed-off-by: Rafael J. Wysocki --- include/linux/fwnode.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 6ab69871b06d..9a81c4410b9f 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -153,12 +153,12 @@ struct fwnode_operations { int (*add_links)(struct fwnode_handle *fwnode); }; -#define fwnode_has_op(fwnode, op) \ - ((fwnode) && (fwnode)->ops && (fwnode)->ops->op) +#define fwnode_has_op(fwnode, op) \ + (!IS_ERR_OR_NULL(fwnode) && (fwnode)->ops && (fwnode)->ops->op) + #define fwnode_call_int_op(fwnode, op, ...) \ - (fwnode ? (fwnode_has_op(fwnode, op) ? \ - (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : -ENXIO) : \ - -EINVAL) + (fwnode_has_op(fwnode, op) ? \ + (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : (IS_ERR_OR_NULL(fwnode) ? -EINVAL : -ENXIO)) #define fwnode_call_bool_op(fwnode, op, ...) \ (fwnode_has_op(fwnode, op) ? \ -- cgit v1.2.3 From 87ffea09470d94c93dd6a5a22d4b2216b395d1ea Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 8 Apr 2022 21:48:41 +0300 Subject: device property: Introduce fwnode_for_each_parent_node() In a few cases the functionality of fwnode_for_each_parent_node() is already in use. Introduce a common helper macro for it. It may be used by others as well in the future. Signed-off-by: Andy Shevchenko Reviewed-by: Sakari Ailus Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/property.h b/include/linux/property.h index 4cd4b326941f..15d6863ae962 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -83,9 +83,14 @@ struct fwnode_handle *fwnode_find_reference(const struct fwnode_handle *fwnode, const char *fwnode_get_name(const struct fwnode_handle *fwnode); const char *fwnode_get_name_prefix(const struct fwnode_handle *fwnode); + struct fwnode_handle *fwnode_get_parent(const struct fwnode_handle *fwnode); -struct fwnode_handle *fwnode_get_next_parent( - struct fwnode_handle *fwnode); +struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode); + +#define fwnode_for_each_parent_node(fwnode, parent) \ + for (parent = fwnode_get_parent(fwnode); parent; \ + parent = fwnode_get_next_parent(parent)) + struct device *fwnode_get_next_parent_dev(struct fwnode_handle *fwnode); unsigned int fwnode_count_parents(const struct fwnode_handle *fwn); struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwn, -- cgit v1.2.3 From 022fe6bc8f3bd0f2b1f9bc778bacc38020dfd420 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 8 Apr 2022 21:48:42 +0300 Subject: device property: Drop 'test' prefix in parameters of fwnode_is_ancestor_of() The part 'is' in the function name implies the test against something. Drop unnecessary 'test' prefix in the fwnode_is_ancestor_of() parameters. No functional change intended. Signed-off-by: Andy Shevchenko Reviewed-by: Sakari Ailus Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/property.h b/include/linux/property.h index 15d6863ae962..fc24d45632eb 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -95,8 +95,7 @@ struct device *fwnode_get_next_parent_dev(struct fwnode_handle *fwnode); unsigned int fwnode_count_parents(const struct fwnode_handle *fwn); struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwn, unsigned int depth); -bool fwnode_is_ancestor_of(struct fwnode_handle *test_ancestor, - struct fwnode_handle *test_child); +bool fwnode_is_ancestor_of(struct fwnode_handle *ancestor, struct fwnode_handle *child); struct fwnode_handle *fwnode_get_next_child_node( const struct fwnode_handle *fwnode, struct fwnode_handle *child); struct fwnode_handle *fwnode_get_next_available_child_node( -- cgit v1.2.3 From 62b32fd961cf2d8b2c9fdcd8d58abeb184bb439b Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Mon, 11 Apr 2022 20:47:00 +0200 Subject: ACPICA: Add support for the Windows 11 _OSI string ACPICA commit f2e9fb8345b9146a67f8c63474b65ccfc06d962a See https://github.com/microsoft_docs/windows-driver-docs/commit/a061e31fd77c20cc8e6eb0234e5d3a83e417f48 Link: https://github.com/acpica/acpica/commit/f2e9fb83 Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/actypes.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index 02c1fa16e638..362037fc63a6 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -1303,6 +1303,7 @@ typedef enum { #define ACPI_OSI_WIN_10_RS5 0x13 #define ACPI_OSI_WIN_10_19H1 0x14 #define ACPI_OSI_WIN_10_20H1 0x15 +#define ACPI_OSI_WIN_11 0x16 /* Definitions of getopt */ -- cgit v1.2.3 From a95d2fb08538f29f6e9f54a803dffc303b5263cd Mon Sep 17 00:00:00 2001 From: Lawrence Hileman Date: Mon, 11 Apr 2022 20:47:40 +0200 Subject: ACPICA: Add the subtable CFMWS to the CEDT table ACPICA commit 19b11f91660b1a38a8e9655b0b1a4ad51ec4db1e Link: https://github.com/acpica/acpica/commit/19b11f91 Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl1.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index 159070edd031..0ccda7b7814d 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -373,6 +373,10 @@ struct acpi_cedt_cfmws { u32 interleave_targets[]; }; +struct acpi_cedt_cfmws_target_element { + u32 interleave_target; +}; + /* Values for Interleave Arithmetic field above */ #define ACPI_CEDT_CFMWS_ARITHMETIC_MODULO (0) -- cgit v1.2.3 From 90037551c68d08facd6fb56a971352a9cd189c44 Mon Sep 17 00:00:00 2001 From: Piotr Maziarz Date: Mon, 11 Apr 2022 20:48:21 +0200 Subject: ACPICA: iASL: NHLT: Treat Terminator as specific_config ACPICA commit 23a659e190cf3ed0edd46cddf12bbbcfeaa09396 specific_config has 4 bytes of size and then an amount of bytes specified by size. All of the terminators that I've seen had a size equal to 4, but theoretically it can vary. Link: https://github.com/acpica/acpica/commit/23a659e1 Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl2.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index 16847c8d9d5f..a57853f2bb0b 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -1689,11 +1689,6 @@ struct acpi_nhlt_linux_specific_data_b { u8 specific_data[18]; }; -struct acpi_nhlt_table_terminator { - u32 terminator_value; - u32 terminator_signature; -}; - /******************************************************************************* * * PCCT - Platform Communications Channel Table (ACPI 5.0) -- cgit v1.2.3 From ab1ba87bd71a507286781b8a7f5c64e1eb7a2d34 Mon Sep 17 00:00:00 2001 From: Piotr Maziarz Date: Mon, 11 Apr 2022 20:49:08 +0200 Subject: ACPICA: iASL: NHLT: Fix parsing undocumented bytes at the end of Endpoint Descriptor ACPICA commit 961221a76814ffa0ecc92219ddf857579b0f7d54 Undocumented bytes at the end of Endpoint Descriptor can be present independently of Linux-specific structures. Their size can also vary. Link: https://github.com/acpica/acpica/commit/961221a7 Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl2.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index a57853f2bb0b..757db244e220 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -1685,10 +1685,6 @@ struct acpi_nhlt_linux_specific_data { u8 device_port_id; }; -struct acpi_nhlt_linux_specific_data_b { - u8 specific_data[18]; -}; - /******************************************************************************* * * PCCT - Platform Communications Channel Table (ACPI 5.0) -- cgit v1.2.3 From 8bd24835db1781685f9abd0d1b628eaaac20d7c1 Mon Sep 17 00:00:00 2001 From: Piotr Maziarz Date: Mon, 11 Apr 2022 20:50:25 +0200 Subject: ACPICA: iASL: NHLT: Rename linux specific strucures to device_info ACPICA commit 68c7e542075319d57129467872fcbe98906f2b2c Those structures aren't used by Linux drivers, and in other NHLT related tools they are called device_info. Link: https://github.com/acpica/acpica/commit/68c7e542 Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl2.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index 757db244e220..fe6d01aedb1f 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -1673,13 +1673,13 @@ struct acpi_nhlt_render_feedback_device_specific_config { u16 feedback_valid_bits_per_sample; }; -/* Linux-specific structures */ +/* Non documented structures */ -struct acpi_nhlt_linux_specific_count { +struct acpi_nhlt_device_info_count { u8 structure_count; }; -struct acpi_nhlt_linux_specific_data { +struct acpi_nhlt_device_info { u8 device_id[16]; u8 device_instance_id; u8 device_port_id; -- cgit v1.2.3 From 487ea80a2848b7147eede3b73a4ee160c150f567 Mon Sep 17 00:00:00 2001 From: Bob Moore Date: Mon, 11 Apr 2022 20:54:22 +0200 Subject: ACPICA: Update copyright notices to the year 2022 ACPICA commit 738d7b0726e6c0458ef93c0a01c0377490888d1e Affects all source modules and utility signons. Link: https://github.com/acpica/acpica/commit/738d7b07 Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/acbuffer.h | 2 +- include/acpi/acconfig.h | 2 +- include/acpi/acexcep.h | 2 +- include/acpi/acnames.h | 2 +- include/acpi/acoutput.h | 2 +- include/acpi/acpi.h | 2 +- include/acpi/acpiosxf.h | 2 +- include/acpi/acpixf.h | 2 +- include/acpi/acrestyp.h | 2 +- include/acpi/actbl.h | 2 +- include/acpi/actbl1.h | 2 +- include/acpi/actbl2.h | 2 +- include/acpi/actbl3.h | 2 +- include/acpi/actypes.h | 2 +- include/acpi/acuuid.h | 2 +- include/acpi/platform/acenv.h | 2 +- include/acpi/platform/acenvex.h | 2 +- include/acpi/platform/acgcc.h | 2 +- include/acpi/platform/acgccex.h | 2 +- include/acpi/platform/acintel.h | 2 +- include/acpi/platform/aclinux.h | 2 +- include/acpi/platform/aclinuxex.h | 2 +- 22 files changed, 22 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/acpi/acbuffer.h b/include/acpi/acbuffer.h index 3e8d969b22fe..8cbfcbca7b7e 100644 --- a/include/acpi/acbuffer.h +++ b/include/acpi/acbuffer.h @@ -3,7 +3,7 @@ * * Name: acbuffer.h - Support for buffers returned by ACPI predefined names * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acconfig.h b/include/acpi/acconfig.h index 0362cbb72359..c3ae3ea88e17 100644 --- a/include/acpi/acconfig.h +++ b/include/acpi/acconfig.h @@ -3,7 +3,7 @@ * * Name: acconfig.h - Global configuration constants * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acexcep.h b/include/acpi/acexcep.h index ea3b1c41bc79..28943c900be7 100644 --- a/include/acpi/acexcep.h +++ b/include/acpi/acexcep.h @@ -3,7 +3,7 @@ * * Name: acexcep.h - Exception codes returned by the ACPI subsystem * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acnames.h b/include/acpi/acnames.h index 30869ab77fba..6f22e92b1744 100644 --- a/include/acpi/acnames.h +++ b/include/acpi/acnames.h @@ -3,7 +3,7 @@ * * Name: acnames.h - Global names and strings * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acoutput.h b/include/acpi/acoutput.h index 5a3875744678..73781aae2119 100644 --- a/include/acpi/acoutput.h +++ b/include/acpi/acoutput.h @@ -3,7 +3,7 @@ * * Name: acoutput.h -- debug output * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acpi.h b/include/acpi/acpi.h index 6f6282a862bc..416e59bcf149 100644 --- a/include/acpi/acpi.h +++ b/include/acpi/acpi.h @@ -3,7 +3,7 @@ * * Name: acpi.h - Master public include file used to interface to ACPICA * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h index 690c369b717a..52844cc5eeb5 100644 --- a/include/acpi/acpiosxf.h +++ b/include/acpi/acpiosxf.h @@ -5,7 +5,7 @@ * interfaces must be implemented by OSL to interface the * ACPI components to the host operating system. * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 7417731472b7..56362c419cd4 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -3,7 +3,7 @@ * * Name: acpixf.h - External interfaces to the ACPI subsystem * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acrestyp.h b/include/acpi/acrestyp.h index 8e2319bbd0a2..a7fb8ddb3dc6 100644 --- a/include/acpi/acrestyp.h +++ b/include/acpi/acrestyp.h @@ -3,7 +3,7 @@ * * Name: acrestyp.h - Defines, types, and structures for resource descriptors * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h index f9cda909f92c..c6af579f74f4 100644 --- a/include/acpi/actbl.h +++ b/include/acpi/actbl.h @@ -3,7 +3,7 @@ * * Name: actbl.h - Basic ACPI Table Definitions * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index 0ccda7b7814d..9f1acc6ff15b 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -3,7 +3,7 @@ * * Name: actbl1.h - Additional ACPI table definitions * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index fe6d01aedb1f..6db7525588c5 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -3,7 +3,7 @@ * * Name: actbl2.h - ACPI Table Definitions (tables not in ACPI spec) * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/actbl3.h b/include/acpi/actbl3.h index edbf1ad8206d..7b9571e00cc4 100644 --- a/include/acpi/actbl3.h +++ b/include/acpi/actbl3.h @@ -3,7 +3,7 @@ * * Name: actbl3.h - ACPI Table Definitions * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index 362037fc63a6..d62f36bc90b2 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -3,7 +3,7 @@ * * Name: actypes.h - Common data types for the entire ACPI subsystem * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/acuuid.h b/include/acpi/acuuid.h index bc24388ce94e..8f1e7c489df5 100644 --- a/include/acpi/acuuid.h +++ b/include/acpi/acuuid.h @@ -3,7 +3,7 @@ * * Name: acuuid.h - ACPI-related UUID/GUID definitions * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/acenv.h b/include/acpi/platform/acenv.h index e8958e0d1646..03eb3d977075 100644 --- a/include/acpi/platform/acenv.h +++ b/include/acpi/platform/acenv.h @@ -3,7 +3,7 @@ * * Name: acenv.h - Host and compiler configuration * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/acenvex.h b/include/acpi/platform/acenvex.h index 277fe2fa4d9b..3a6b1db9a984 100644 --- a/include/acpi/platform/acenvex.h +++ b/include/acpi/platform/acenvex.h @@ -3,7 +3,7 @@ * * Name: acenvex.h - Extra host and compiler configuration * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/acgcc.h b/include/acpi/platform/acgcc.h index 33ad282bd338..ac80111f503c 100644 --- a/include/acpi/platform/acgcc.h +++ b/include/acpi/platform/acgcc.h @@ -3,7 +3,7 @@ * * Name: acgcc.h - GCC specific defines, etc. * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/acgccex.h b/include/acpi/platform/acgccex.h index 738d52865e0a..302ea1b724b9 100644 --- a/include/acpi/platform/acgccex.h +++ b/include/acpi/platform/acgccex.h @@ -3,7 +3,7 @@ * * Name: acgccex.h - Extra GCC specific defines, etc. * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/acintel.h b/include/acpi/platform/acintel.h index 550fe9a8cd6c..85b1ae86ee63 100644 --- a/include/acpi/platform/acintel.h +++ b/include/acpi/platform/acintel.h @@ -3,7 +3,7 @@ * * Name: acintel.h - VC specific defines, etc. * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h index cec41e004ecf..a5550dd4d507 100644 --- a/include/acpi/platform/aclinux.h +++ b/include/acpi/platform/aclinux.h @@ -3,7 +3,7 @@ * * Name: aclinux.h - OS specific defines, etc. for Linux * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ diff --git a/include/acpi/platform/aclinuxex.h b/include/acpi/platform/aclinuxex.h index 5f642b07ad64..28c72744decf 100644 --- a/include/acpi/platform/aclinuxex.h +++ b/include/acpi/platform/aclinuxex.h @@ -3,7 +3,7 @@ * * Name: aclinuxex.h - Extra OS specific defines, etc. for Linux * - * Copyright (C) 2000 - 2021, Intel Corp. + * Copyright (C) 2000 - 2022, Intel Corp. * *****************************************************************************/ -- cgit v1.2.3 From 45882a817d4bae5a3b63c3861cb62b9b9a025de5 Mon Sep 17 00:00:00 2001 From: Bob Moore Date: Mon, 11 Apr 2022 20:55:10 +0200 Subject: ACPICA: Removed some tabs and // comments ACPICA commit 0914618b553d6f3366e568409cebf2656891ca69 Automated cleanup; No functional changes. Link: https://github.com/acpica/acpica/commit/0914618b Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl1.h | 12 ++++++------ include/acpi/actbl2.h | 40 ++++++++++++++++++++-------------------- include/acpi/actypes.h | 16 ++++++++-------- 3 files changed, 34 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index 9f1acc6ff15b..15c78678c5d3 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -379,15 +379,15 @@ struct acpi_cedt_cfmws_target_element { /* Values for Interleave Arithmetic field above */ -#define ACPI_CEDT_CFMWS_ARITHMETIC_MODULO (0) +#define ACPI_CEDT_CFMWS_ARITHMETIC_MODULO (0) /* Values for Restrictions field above */ -#define ACPI_CEDT_CFMWS_RESTRICT_TYPE2 (1) -#define ACPI_CEDT_CFMWS_RESTRICT_TYPE3 (1<<1) -#define ACPI_CEDT_CFMWS_RESTRICT_VOLATILE (1<<2) -#define ACPI_CEDT_CFMWS_RESTRICT_PMEM (1<<3) -#define ACPI_CEDT_CFMWS_RESTRICT_FIXED (1<<4) +#define ACPI_CEDT_CFMWS_RESTRICT_TYPE2 (1) +#define ACPI_CEDT_CFMWS_RESTRICT_TYPE3 (1<<1) +#define ACPI_CEDT_CFMWS_RESTRICT_VOLATILE (1<<2) +#define ACPI_CEDT_CFMWS_RESTRICT_PMEM (1<<3) +#define ACPI_CEDT_CFMWS_RESTRICT_FIXED (1<<4) /******************************************************************************* * diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index 6db7525588c5..fda066de5764 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -978,8 +978,8 @@ struct acpi_madt_multiproc_wakeup { u64 base_address; }; -#define ACPI_MULTIPROC_WAKEUP_MB_OS_SIZE 2032 -#define ACPI_MULTIPROC_WAKEUP_MB_FIRMWARE_SIZE 2048 +#define ACPI_MULTIPROC_WAKEUP_MB_OS_SIZE 2032 +#define ACPI_MULTIPROC_WAKEUP_MB_FIRMWARE_SIZE 2048 struct acpi_madt_multiproc_wakeup_mailbox { u16 command; @@ -1597,7 +1597,7 @@ struct acpi_nhlt_mic_device_specific_config { /* Values for array_type_ext above */ -#define ACPI_NHLT_ARRAY_TYPE_RESERVED 0x09 // 9 and below are reserved +#define ACPI_NHLT_ARRAY_TYPE_RESERVED 0x09 /* 9 and below are reserved */ #define ACPI_NHLT_SMALL_LINEAR_2ELEMENT 0x0A #define ACPI_NHLT_BIG_LINEAR_2ELEMENT 0x0B #define ACPI_NHLT_FIRST_GEOMETRY_LINEAR_4ELEMENT 0x0C @@ -1617,17 +1617,17 @@ struct acpi_nhlt_vendor_mic_count { struct acpi_nhlt_vendor_mic_config { u8 type; u8 panel; - u16 speaker_position_distance; // mm - u16 horizontal_offset; // mm - u16 vertical_offset; // mm - u8 frequency_low_band; // 5*hz - u8 frequency_high_band; // 500*hz - u16 direction_angle; // -180 - + 180 - u16 elevation_angle; // -180 - + 180 - u16 work_vertical_angle_begin; // -180 - + 180 with 2 deg step - u16 work_vertical_angle_end; // -180 - + 180 with 2 deg step - u16 work_horizontal_angle_begin; // -180 - + 180 with 2 deg step - u16 work_horizontal_angle_end; // -180 - + 180 with 2 deg step + u16 speaker_position_distance; /* mm */ + u16 horizontal_offset; /* mm */ + u16 vertical_offset; /* mm */ + u8 frequency_low_band; /* 5*Hz */ + u8 frequency_high_band; /* 500*Hz */ + u16 direction_angle; /* -180 - + 180 */ + u16 elevation_angle; /* -180 - + 180 */ + u16 work_vertical_angle_begin; /* -180 - + 180 with 2 deg step */ + u16 work_vertical_angle_end; /* -180 - + 180 with 2 deg step */ + u16 work_horizontal_angle_begin; /* -180 - + 180 with 2 deg step */ + u16 work_horizontal_angle_end; /* -180 - + 180 with 2 deg step */ }; /* Values for Type field above */ @@ -1638,9 +1638,9 @@ struct acpi_nhlt_vendor_mic_config { #define ACPI_NHLT_MIC_SUPER_CARDIOID 3 #define ACPI_NHLT_MIC_HYPER_CARDIOID 4 #define ACPI_NHLT_MIC_8_SHAPED 5 -#define ACPI_NHLT_MIC_RESERVED6 6 // 6 is reserved +#define ACPI_NHLT_MIC_RESERVED6 6 /* 6 is reserved */ #define ACPI_NHLT_MIC_VENDOR_DEFINED 7 -#define ACPI_NHLT_MIC_RESERVED 8 // 8 and above are reserved +#define ACPI_NHLT_MIC_RESERVED 8 /* 8 and above are reserved */ /* Values for Panel field above */ @@ -1650,12 +1650,12 @@ struct acpi_nhlt_vendor_mic_config { #define ACPI_NHLT_MIC_POSITION_RIGHT 3 #define ACPI_NHLT_MIC_POSITION_FRONT 4 #define ACPI_NHLT_MIC_POSITION_BACK 5 -#define ACPI_NHLT_MIC_POSITION_RESERVED 6 // 6 and above are reserved +#define ACPI_NHLT_MIC_POSITION_RESERVED 6 /* 6 and above are reserved */ struct acpi_nhlt_vendor_mic_device_specific_config { struct acpi_nhlt_mic_device_specific_config mic_array_device_config; u8 number_of_microphones; - struct acpi_nhlt_vendor_mic_config mic_config[]; // indexed by number_of_microphones + struct acpi_nhlt_vendor_mic_config mic_config[]; /* Indexed by number_of_microphones */ }; /* Microphone SNR and Sensitivity extension */ @@ -1668,8 +1668,8 @@ struct acpi_nhlt_mic_snr_sensitivity_extension { /* Render device with feedback */ struct acpi_nhlt_render_feedback_device_specific_config { - u8 feedback_virtual_slot; // render slot in case of capture - u16 feedback_channels; // informative only + u8 feedback_virtual_slot; /* Render slot in case of capture */ + u16 feedback_channels; /* Informative only */ u16 feedback_valid_bits_per_sample; }; diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index d62f36bc90b2..3491e454b2ab 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -539,14 +539,14 @@ typedef u64 acpi_integer; * Can be used with access_width of struct acpi_generic_address and access_size of * struct acpi_resource_generic_register. */ -#define ACPI_ACCESS_BIT_SHIFT 2 -#define ACPI_ACCESS_BYTE_SHIFT -1 -#define ACPI_ACCESS_BIT_MAX (31 - ACPI_ACCESS_BIT_SHIFT) -#define ACPI_ACCESS_BYTE_MAX (31 - ACPI_ACCESS_BYTE_SHIFT) -#define ACPI_ACCESS_BIT_DEFAULT (8 - ACPI_ACCESS_BIT_SHIFT) -#define ACPI_ACCESS_BYTE_DEFAULT (8 - ACPI_ACCESS_BYTE_SHIFT) -#define ACPI_ACCESS_BIT_WIDTH(size) (1 << ((size) + ACPI_ACCESS_BIT_SHIFT)) -#define ACPI_ACCESS_BYTE_WIDTH(size) (1 << ((size) + ACPI_ACCESS_BYTE_SHIFT)) +#define ACPI_ACCESS_BIT_SHIFT 2 +#define ACPI_ACCESS_BYTE_SHIFT -1 +#define ACPI_ACCESS_BIT_MAX (31 - ACPI_ACCESS_BIT_SHIFT) +#define ACPI_ACCESS_BYTE_MAX (31 - ACPI_ACCESS_BYTE_SHIFT) +#define ACPI_ACCESS_BIT_DEFAULT (8 - ACPI_ACCESS_BIT_SHIFT) +#define ACPI_ACCESS_BYTE_DEFAULT (8 - ACPI_ACCESS_BYTE_SHIFT) +#define ACPI_ACCESS_BIT_WIDTH(size) (1 << ((size) + ACPI_ACCESS_BIT_SHIFT)) +#define ACPI_ACCESS_BYTE_WIDTH(size) (1 << ((size) + ACPI_ACCESS_BYTE_SHIFT)) /******************************************************************************* * -- cgit v1.2.3 From aa29b2083e11722a0ceedfa2a87de74cc7cfa676 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 11 Apr 2022 20:56:15 +0200 Subject: ACPICA: Headers: Replace zero-length array with flexible-array member MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ACPICA commit 98835f452c698b015d4da999944405ecb90da670 There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://www.kernel.org/doc/html/v5.16/process/deprecated.html#zero-length-and-one-element-arrays Link: https://github.com/acpica/acpica/commit/98835f45 Link: https://github.com/KSPP/linux/issues/78 Signed-off-by: Gustavo A. R. Silva Reviewed-by: Kees Cook Signed-off-by: Rafael J. Wysocki Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index fda066de5764..3e92d15a0cd6 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -2310,7 +2310,7 @@ struct acpi_table_rgrt { u16 version; u8 image_type; u8 reserved; - u8 image[0]; + u8 image[]; }; /* image_type values */ -- cgit v1.2.3 From 1c5d62f5dd979dbe7f4b16a5bd3c64fbecb7d92a Mon Sep 17 00:00:00 2001 From: Besar Wicaksono Date: Mon, 11 Apr 2022 20:58:04 +0200 Subject: ACPICA: Add support for ARM Performance Monitoring Unit Table. ACPICA commit 002165ecc0a3dc703bb24c789aaa02fdada01675 The specification of this table is described in "ARM Performance Monitoring Unit Architecture 1.0 Platform Design Document" ARM DEN0117. This patch adds the necessary types and support for compiling/disassembling APMT. Link: https://github.com/acpica/acpica/commit/002165ec Signed-off-by: Besar Wicaksono Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl2.h | 80 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 80 insertions(+) (limited to 'include') diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index 3e92d15a0cd6..8298b106aa40 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -25,6 +25,7 @@ * the wrong signature. */ #define ACPI_SIG_AGDI "AGDI" /* Arm Generic Diagnostic Dump and Reset Device Interface */ +#define ACPI_SIG_APMT "APMT" /* Arm Performance Monitoring Unit table */ #define ACPI_SIG_BDAT "BDAT" /* BIOS Data ACPI Table */ #define ACPI_SIG_IORT "IORT" /* IO Remapping Table */ #define ACPI_SIG_IVRS "IVRS" /* I/O Virtualization Reporting Structure */ @@ -258,6 +259,85 @@ struct acpi_table_agdi { #define ACPI_AGDI_SIGNALING_MODE (1) +/******************************************************************************* + * + * APMT - ARM Performance Monitoring Unit Table + * + * Conforms to: + * ARM Performance Monitoring Unit Architecture 1.0 Platform Design Document + * ARM DEN0117 v1.0 November 25, 2021 + * + ******************************************************************************/ + +struct acpi_table_apmt { + struct acpi_table_header header; /* Common ACPI table header */ +}; + +#define ACPI_APMT_NODE_ID_LENGTH 4 + +/* + * APMT subtables + */ +struct acpi_apmt_node { + u16 length; + u8 flags; + u8 type; + u32 id; + u64 inst_primary; + u32 inst_secondary; + u64 base_address0; + u64 base_address1; + u32 ovflw_irq; + u32 reserved; + u32 ovflw_irq_flags; + u32 proc_affinity; + u32 impl_id; +}; + +/* Masks for Flags field above */ + +#define ACPI_APMT_FLAGS_DUAL_PAGE (1<<0) +#define ACPI_APMT_FLAGS_AFFINITY (1<<1) +#define ACPI_APMT_FLAGS_ATOMIC (1<<2) + +/* Values for Flags dual page field above */ + +#define ACPI_APMT_FLAGS_DUAL_PAGE_NSUPP (0<<0) +#define ACPI_APMT_FLAGS_DUAL_PAGE_SUPP (1<<0) + +/* Values for Flags processor affinity field above */ +#define ACPI_APMT_FLAGS_AFFINITY_PROC (0<<1) +#define ACPI_APMT_FLAGS_AFFINITY_PROC_CONTAINER (1<<1) + +/* Values for Flags 64-bit atomic field above */ +#define ACPI_APMT_FLAGS_ATOMIC_NSUPP (0<<2) +#define ACPI_APMT_FLAGS_ATOMIC_SUPP (1<<2) + +/* Values for Type field above */ + +enum acpi_apmt_node_type { + ACPI_APMT_NODE_TYPE_MC = 0x00, + ACPI_APMT_NODE_TYPE_SMMU = 0x01, + ACPI_APMT_NODE_TYPE_PCIE_ROOT = 0x02, + ACPI_APMT_NODE_TYPE_ACPI = 0x03, + ACPI_APMT_NODE_TYPE_CACHE = 0x04, + ACPI_APMT_NODE_TYPE_COUNT +}; + +/* Masks for ovflw_irq_flags field above */ + +#define ACPI_APMT_OVFLW_IRQ_FLAGS_MODE (1<<0) +#define ACPI_APMT_OVFLW_IRQ_FLAGS_TYPE (1<<1) + +/* Values for ovflw_irq_flags mode field above */ + +#define ACPI_APMT_OVFLW_IRQ_FLAGS_MODE_LEVEL (0<<0) +#define ACPI_APMT_OVFLW_IRQ_FLAGS_MODE_EDGE (1<<0) + +/* Values for ovflw_irq_flags type field above */ + +#define ACPI_APMT_OVFLW_IRQ_FLAGS_TYPE_WIRED (0<<1) + /******************************************************************************* * * BDAT - BIOS Data ACPI Table -- cgit v1.2.3 From da6a9bbedc79c49ba94a6ca746580a9b43931641 Mon Sep 17 00:00:00 2001 From: Bob Moore Date: Mon, 11 Apr 2022 21:00:45 +0200 Subject: ACPICA: iASL/MADT: Add OEM-defined subtable ACPICA commit 4450b89b596a2b54b0cdfe2357b49a63445c2e03 Adds support for the "reserved for OEM use" subtable (types 0x80 to 0xFF). Link: https://github.com/acpica/acpica/commit/4450b89b Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl2.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index 8298b106aa40..42b5753dd78c 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -842,7 +842,8 @@ enum acpi_madt_type { ACPI_MADT_TYPE_GENERIC_REDISTRIBUTOR = 14, ACPI_MADT_TYPE_GENERIC_TRANSLATOR = 15, ACPI_MADT_TYPE_MULTIPROC_WAKEUP = 16, - ACPI_MADT_TYPE_RESERVED = 17 /* 17 and greater are reserved */ + ACPI_MADT_TYPE_RESERVED = 17, /* 17 to 0x7F are reserved */ + ACPI_MADT_TYPE_OEM_RESERVED = 0x80 /* 0x80 to 0xFF are reserved for OEM use */ }; /* @@ -1072,6 +1073,12 @@ struct acpi_madt_multiproc_wakeup_mailbox { #define ACPI_MP_WAKE_COMMAND_WAKEUP 1 +/* 17: OEM data */ + +struct acpi_madt_oem_data { + u8 oem_data[0]; +}; + /* * Common flags fields for MADT subtables */ -- cgit v1.2.3 From 4fd147530edd44439a099dda6b22f1a390f306ab Mon Sep 17 00:00:00 2001 From: Shameer Kolothum Date: Mon, 11 Apr 2022 21:02:33 +0200 Subject: ACPICA: IORT: Updates for revision E.d ACPICA commit 87a2e39b8abdfedfb86b0a105708e37e895becd9 IORT revision is now updated to E.d (ARM DEN 0049E.d) and contains a few additions like, -Added descriptor in the root complex node for specifying PASID width supported by the root complex. -Updated RMR node Flags field. -Introduced memory access attributes in the RMR node. Please note that IORT Rev E.c is deprecated and not supported. Link: https://github.com/acpica/acpica/commit/87a2e39b Signed-off-by: Shameer Kolothum Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl2.h | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index 42b5753dd78c..655102bc6d14 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -357,7 +357,7 @@ struct acpi_table_bdat { * IORT - IO Remapping Table * * Conforms to "IO Remapping Table System Software on ARM Platforms", - * Document number: ARM DEN 0049E.b, Feb 2021 + * Document number: ARM DEN 0049E.d, Feb 2022 * ******************************************************************************/ @@ -454,7 +454,8 @@ struct acpi_iort_root_complex { u32 ats_attribute; u32 pci_segment_number; u8 memory_address_limit; /* Memory address size limit */ - u8 reserved[3]; /* Reserved, must be zero */ + u16 pasid_capabilities; /* PASID Capabilities */ + u8 reserved[1]; /* Reserved, must be zero */ }; /* Masks for ats_attribute field above */ @@ -463,6 +464,9 @@ struct acpi_iort_root_complex { #define ACPI_IORT_PRI_SUPPORTED (1<<1) /* The root complex PRI support */ #define ACPI_IORT_PASID_FWD_SUPPORTED (1<<2) /* The root complex PASID forward support */ +/* Masks for pasid_capabilities field above */ +#define ACPI_IORT_PASID_MAX_WIDTH (0x1F) /* Bits 0-4 */ + struct acpi_iort_smmu { u64 base_address; /* SMMU base address */ u64 span; /* Length of memory range */ @@ -538,6 +542,25 @@ struct acpi_iort_rmr { u32 rmr_offset; }; +/* Masks for Flags field above */ +#define ACPI_IORT_RMR_REMAP_PERMITTED (1) +#define ACPI_IORT_RMR_ACCESS_PRIVILEGE (1<<1) + +/* + * Macro to access the Access Attributes in flags field above: + * Access Attributes is encoded in bits 9:2 + */ +#define ACPI_IORT_RMR_ACCESS_ATTRIBUTES(flags) (((flags) >> 2) & 0xFF) + +/* Values for above Access Attributes */ + +#define ACPI_IORT_RMR_ATTR_DEVICE_NGNRNE 0x00 +#define ACPI_IORT_RMR_ATTR_DEVICE_NGNRE 0x01 +#define ACPI_IORT_RMR_ATTR_DEVICE_NGRE 0x02 +#define ACPI_IORT_RMR_ATTR_DEVICE_GRE 0x03 +#define ACPI_IORT_RMR_ATTR_NORMAL_NC 0x04 +#define ACPI_IORT_RMR_ATTR_NORMAL_IWB_OWB 0x05 + struct acpi_iort_rmr_desc { u64 base_address; u64 length; -- cgit v1.2.3 From 0076ca940e3f1a1eae6b5e39b6594c96934713a2 Mon Sep 17 00:00:00 2001 From: Bob Moore Date: Mon, 11 Apr 2022 21:04:03 +0200 Subject: ACPICA: Update version to 20220331 ACPICA commit ada5b805eaa7480930082af9bc3d689c6f181329 Version 20220331. Link: https://github.com/acpica/acpica/commit/ada5b805 Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/acpixf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 56362c419cd4..67c0b9e734b6 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -12,7 +12,7 @@ /* Current ACPICA subsystem version in YYYYMMDD format */ -#define ACPI_CA_VERSION 0x20211217 +#define ACPI_CA_VERSION 0x20220331 #include #include -- cgit v1.2.3 From a090931524d03a4975c84b89a32210420d852313 Mon Sep 17 00:00:00 2001 From: Liu Xinpeng Date: Tue, 12 Apr 2022 11:05:19 +0800 Subject: ACPI: APEI: Fix missing ERST record id Read a record is cleared by others, but the deleted record cache entry is still created by erst_get_record_id_next. When next enumerate the records, get the cached deleted record, then erst_read() return -ENOENT and try to get next record, loop back to first ID will return 0 in function __erst_record_id_cache_add_one and then set record_id as APEI_ERST_INVALID_RECORD_ID, finished this time read operation. It will result in read the records just in the cache hereafter. This patch cleared the deleted record cache, fix the issue that "./erst-inject -p" shows record counts not equal to "./erst-inject -n". A reproducer of the problem(retry many times): [root@localhost erst-inject]# ./erst-inject -c 0xaaaaa00011 [root@localhost erst-inject]# ./erst-inject -p rc: 273 rcd sig: CPER rcd id: 0xaaaaa00012 rc: 273 rcd sig: CPER rcd id: 0xaaaaa00013 rc: 273 rcd sig: CPER rcd id: 0xaaaaa00014 [root@localhost erst-inject]# ./erst-inject -i 0xaaaaa000006 [root@localhost erst-inject]# ./erst-inject -i 0xaaaaa000007 [root@localhost erst-inject]# ./erst-inject -i 0xaaaaa000008 [root@localhost erst-inject]# ./erst-inject -p rc: 273 rcd sig: CPER rcd id: 0xaaaaa00012 rc: 273 rcd sig: CPER rcd id: 0xaaaaa00013 rc: 273 rcd sig: CPER rcd id: 0xaaaaa00014 [root@localhost erst-inject]# ./erst-inject -n total error record count: 6 Signed-off-by: Liu Xinpeng Reviewed-by: Tony Luck Signed-off-by: Rafael J. Wysocki --- include/acpi/apei.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/acpi/apei.h b/include/acpi/apei.h index afaca3a075e8..dc60f7db5524 100644 --- a/include/acpi/apei.h +++ b/include/acpi/apei.h @@ -46,6 +46,8 @@ int erst_get_record_id_next(int *pos, u64 *record_id); void erst_get_record_id_end(void); ssize_t erst_read(u64 record_id, struct cper_record_header *record, size_t buflen); +ssize_t erst_read_record(u64 record_id, struct cper_record_header *record, + size_t buflen, size_t recordlen, const guid_t *creatorid); int erst_clear(u64 record_id); int arch_apei_enable_cmcff(struct acpi_hest_header *hest_hdr, void *data); -- cgit v1.2.3 From 4e140f59d285c1ca1e5c81b4c13e27366865bd09 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 10 Jan 2022 23:15:27 +0000 Subject: mm/usercopy: Check kmap addresses properly If you are copying to an address in the kmap region, you may not copy across a page boundary, no matter what the size of the underlying allocation. You can't kmap() a slab page because slab pages always come from low memory. Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220110231530.665970-2-willy@infradead.org --- include/linux/highmem-internal.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index a77be5630209..337bd9f32921 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -149,6 +149,11 @@ static inline void totalhigh_pages_add(long count) atomic_long_add(count, &_totalhigh_pages); } +static inline bool is_kmap_addr(const void *x) +{ + unsigned long addr = (unsigned long)x; + return addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP); +} #else /* CONFIG_HIGHMEM */ static inline struct page *kmap_to_page(void *addr) @@ -234,6 +239,11 @@ static inline void __kunmap_atomic(void *addr) static inline unsigned int nr_free_highpages(void) { return 0; } static inline unsigned long totalhigh_pages(void) { return 0UL; } +static inline bool is_kmap_addr(const void *x) +{ + return false; +} + #endif /* CONFIG_HIGHMEM */ /* -- cgit v1.2.3 From e6f3b3c9c109ed57230996cf4a4c1b8ae7e36a81 Mon Sep 17 00:00:00 2001 From: Sami Tolvanen Date: Tue, 5 Apr 2022 15:16:18 -0700 Subject: cfi: Use __builtin_function_start Clang 14 added support for the __builtin_function_start function, which allows us to implement the function_nocfi macro without architecture-specific inline assembly and in a way that also works with static initializers. Change CONFIG_CFI_CLANG to depend on Clang >= 14, define function_nocfi using __builtin_function_start, and remove the arm64 inline assembly implementation. Link: https://github.com/llvm/llvm-project/commit/ec2e26eaf63558934f5b73a6e530edc453cf9508 Link: https://github.com/ClangBuiltLinux/linux/issues/1353 Signed-off-by: Sami Tolvanen Reviewed-by: Nick Desaulniers Reviewed-by: Mark Rutland Tested-by: Mark Rutland Acked-by: Will Deacon # arm64 Reviewed-by: Nathan Chancellor Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220405221618.633743-1-samitolvanen@google.com --- include/linux/compiler-clang.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index babb1347148c..c84fec767445 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -69,6 +69,16 @@ #define __nocfi __attribute__((__no_sanitize__("cfi"))) #define __cficanonical __attribute__((__cfi_canonical_jump_table__)) +#if defined(CONFIG_CFI_CLANG) +/* + * With CONFIG_CFI_CLANG, the compiler replaces function address + * references with the address of the function's CFI jump table + * entry. The function_nocfi macro always returns the address of the + * actual function instead. + */ +#define function_nocfi(x) __builtin_function_start(x) +#endif + /* * Turn individual warnings and errors on and off locally, depending * on version. -- cgit v1.2.3 From 63cec1389e116ae0e2a15e612a5b49651e04be3f Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 4 Apr 2022 18:09:14 -0700 Subject: fscrypt: split up FS_CRYPTO_BLOCK_SIZE FS_CRYPTO_BLOCK_SIZE is neither the filesystem block size nor the granularity of encryption. Rather, it defines two logically separate constraints that both arise from the block size of the AES cipher: - The alignment required for the lengths of file contents blocks - The minimum input/output length for the filenames encryption modes Since there are way too many things called the "block size", and the connection with the AES block size is not easily understood, split FS_CRYPTO_BLOCK_SIZE into two constants FSCRYPT_CONTENTS_ALIGNMENT and FSCRYPT_FNAME_MIN_MSG_LEN that more clearly describe what they are. Signed-off-by: Eric Biggers Link: https://lore.kernel.org/r/20220405010914.18519-1-ebiggers@kernel.org --- include/linux/fscrypt.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 50d92d805bd8..efc7f96e5e26 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -18,7 +18,17 @@ #include #include -#define FS_CRYPTO_BLOCK_SIZE 16 +/* + * The lengths of all file contents blocks must be divisible by this value. + * This is needed to ensure that all contents encryption modes will work, as + * some of the supported modes don't support arbitrarily byte-aligned messages. + * + * Since the needed alignment is 16 bytes, most filesystems will meet this + * requirement naturally, as typical block sizes are powers of 2. However, if a + * filesystem can generate arbitrarily byte-aligned block lengths (e.g., via + * compression), then it will need to pad to this alignment before encryption. + */ +#define FSCRYPT_CONTENTS_ALIGNMENT 16 union fscrypt_policy; struct fscrypt_info; -- cgit v1.2.3 From 9554e908fb5d02e48a681d1eca180225bf109e83 Mon Sep 17 00:00:00 2001 From: Brian Gerst Date: Fri, 25 Mar 2022 11:39:51 -0400 Subject: ELF: Remove elf_core_copy_kernel_regs() x86-32 was the last architecture that implemented separate user and kernel registers. Signed-off-by: Brian Gerst Signed-off-by: Borislav Petkov Reviewed-by: Thomas Gleixner Acked-by: Andy Lutomirski Acked-by: Michael Ellerman Link: https://lore.kernel.org/r/20220325153953.162643-3-brgerst@gmail.com --- include/linux/elfcore.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include') diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index f8e206e82476..346a8b56cdc8 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -84,15 +84,6 @@ static inline void elf_core_copy_regs(elf_gregset_t *elfregs, struct pt_regs *re #endif } -static inline void elf_core_copy_kernel_regs(elf_gregset_t *elfregs, struct pt_regs *regs) -{ -#ifdef ELF_CORE_COPY_KERNEL_REGS - ELF_CORE_COPY_KERNEL_REGS((*elfregs), regs); -#else - elf_core_copy_regs(elfregs, regs); -#endif -} - static inline int elf_core_copy_task_regs(struct task_struct *t, elf_gregset_t* elfregs) { #if defined (ELF_CORE_COPY_TASK_REGS) -- cgit v1.2.3 From 64b97df995f0c943be469a019d6117c89e2131bc Mon Sep 17 00:00:00 2001 From: Lech Perczak Date: Wed, 13 Apr 2022 03:44:14 +0200 Subject: cdc_ether: export usbnet_cdc_zte_rx_fixup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit bfe9b9d2df66 ("cdc_ether: Improve ZTE MF823/831/910 handling") introduces a workaround for certain ZTE modems reporting invalid MAC addresses over CDC-ECM. The same issue was present on their RNDIS interface,which was fixed in commit a5a18bdf7453 ("rndis_host: Set valid random MAC on buggy devices"). However, internal modem of ZTE MF286R router, on its RNDIS interface, also exhibits a second issue fixed already in CDC-ECM, of the device not respecting configured random MAC address. In order to share the fixup for this with rndis_host driver, export the workaround function, which will be re-used in the following commit in rndis_host. Cc: Kristian Evensen Cc: Bjørn Mork Cc: Oliver Neukum Signed-off-by: Lech Perczak Signed-off-by: Paolo Abeni --- include/linux/usb/usbnet.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 8336e86ce606..1b4d72d5e891 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -214,6 +214,7 @@ extern int usbnet_ether_cdc_bind(struct usbnet *dev, struct usb_interface *intf) extern int usbnet_cdc_bind(struct usbnet *, struct usb_interface *); extern void usbnet_cdc_unbind(struct usbnet *, struct usb_interface *); extern void usbnet_cdc_status(struct usbnet *, struct urb *); +extern int usbnet_cdc_zte_rx_fixup(struct usbnet *dev, struct sk_buff *skb); /* CDC and RNDIS support the same host-chosen packet filters for IN transfers */ #define DEFAULT_FILTER (USB_CDC_PACKET_TYPE_BROADCAST \ -- cgit v1.2.3 From 36e747972d8b4c09e6e3275e31a3acba46e2c4d2 Mon Sep 17 00:00:00 2001 From: Lech Perczak Date: Wed, 13 Apr 2022 03:44:15 +0200 Subject: rndis_host: enable the bogus MAC fixup for ZTE devices from cdc_ether MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Certain ZTE modems, namely: MF823. MF831, MF910, built-in modem from MF286R, expose both CDC-ECM and RNDIS network interfaces. They have a trait of ignoring the locally-administered MAC address configured on the interface both in CDC-ECM and RNDIS part, and this leads to dropping of incoming traffic by the host. However, the workaround was only present in CDC-ECM, and MF286R explicitly requires it in RNDIS mode. Re-use the workaround in rndis_host as well, to fix operation of MF286R module, some versions of which expose only the RNDIS interface. Do so by introducing new flag, RNDIS_DRIVER_DATA_DST_MAC_FIXUP, and testing for it in rndis_rx_fixup. This is required, as RNDIS uses frame batching, and all of the packets inside the batch need the fixup. This might introduce a performance penalty, because test is done for every returned Ethernet frame. Apply the workaround to both "flavors" of RNDIS interfaces, as older ZTE modems, like MF823 found in the wild, report the USB_CLASS_COMM class interfaces, while MF286R reports USB_CLASS_WIRELESS_CONTROLLER. Suggested-by: Bjørn Mork Cc: Kristian Evensen Cc: Oliver Neukum Signed-off-by: Lech Perczak Signed-off-by: Paolo Abeni --- include/linux/usb/rndis_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/usb/rndis_host.h b/include/linux/usb/rndis_host.h index 809bccd08455..cc42db51bbba 100644 --- a/include/linux/usb/rndis_host.h +++ b/include/linux/usb/rndis_host.h @@ -197,6 +197,7 @@ struct rndis_keepalive_c { /* IN (optionally OUT) */ /* Flags for driver_info::data */ #define RNDIS_DRIVER_DATA_POLL_STATUS 1 /* poll status before control */ +#define RNDIS_DRIVER_DATA_DST_MAC_FIXUP 2 /* device ignores configured MAC address */ extern void rndis_status(struct usbnet *dev, struct urb *urb); extern int -- cgit v1.2.3 From fde33ca4cb2bae6472714123b451475fdfd9995c Mon Sep 17 00:00:00 2001 From: Anna-Maria Behnsen Date: Mon, 11 Apr 2022 16:01:15 +0200 Subject: tracing/timer: Add missing argument documentation of trace points Documentation of trace points timer_start, timer_expire_entry and hrtimer_start lack always the last argument. Add it to keep implementation and documentation in sync. Signed-off-by: Anna-Maria Behnsen Signed-off-by: Thomas Gleixner Acked-by: Steven Rostedt (Google) Link: https://lore.kernel.org/r/20220411140115.24185-1-anna-maria@linutronix.de --- include/trace/events/timer.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index 6ad031c71be7..2e713a7d9aa3 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -48,6 +48,7 @@ DEFINE_EVENT(timer_class, timer_init, * timer_start - called when the timer is started * @timer: pointer to struct timer_list * @expires: the timers expiry time + * @flags: the timers flags */ TRACE_EVENT(timer_start, @@ -84,6 +85,7 @@ TRACE_EVENT(timer_start, /** * timer_expire_entry - called immediately before the timer callback * @timer: pointer to struct timer_list + * @baseclk: value of timer_base::clk when timer expires * * Allows to determine the timer latency. */ @@ -190,7 +192,8 @@ TRACE_EVENT(hrtimer_init, /** * hrtimer_start - called when the hrtimer is started - * @hrtimer: pointer to struct hrtimer + * @hrtimer: pointer to struct hrtimer + * @mode: the hrtimers mode */ TRACE_EVENT(hrtimer_start, -- cgit v1.2.3 From 3dc6ffae2da201284cb24af66af77ee0bbb2efaa Mon Sep 17 00:00:00 2001 From: Kurt Kanzenbach Date: Thu, 14 Apr 2022 11:18:03 +0200 Subject: timekeeping: Introduce fast accessor to clock tai Introduce fast/NMI safe accessor to clock tai for tracing. The Linux kernel tracing infrastructure has support for using different clocks to generate timestamps for trace events. Especially in TSN networks it's useful to have TAI as trace clock, because the application scheduling is done in accordance to the network time, which is based on TAI. With a tai trace_clock in place, it becomes very convenient to correlate network activity with Linux kernel application traces. Use the same implementation as ktime_get_boot_fast_ns() does by reading the monotonic time and adding the TAI offset. The same limitations as for the fast boot implementation apply. The TAI offset may change at run time e.g., by setting the time or using adjtimex() with an offset. However, these kind of offset changes are rare events. Nevertheless, the user has to be aware and deal with it in post processing. An alternative approach would be to use the same implementation as ktime_get_real_fast_ns() does. However, this requires to add an additional u64 member to the tk_read_base struct. This struct together with a seqcount is designed to fit into a single cache line on 64 bit architectures. Adding a new member would violate this constraint. Signed-off-by: Kurt Kanzenbach Signed-off-by: Thomas Gleixner Cc: Steven Rostedt Link: https://lore.kernel.org/r/20220414091805.89667-2-kurt@linutronix.de --- include/linux/timekeeping.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 78a98bdff76d..fe1e467ba046 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -177,6 +177,7 @@ static inline u64 ktime_get_raw_ns(void) extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); extern u64 ktime_get_boot_fast_ns(void); +extern u64 ktime_get_tai_fast_ns(void); extern u64 ktime_get_real_fast_ns(void); /* -- cgit v1.2.3 From 19aed2d6cdb72a7c92909832b9480d9cadebeef9 Mon Sep 17 00:00:00 2001 From: Akihiko Odaki Date: Fri, 8 Apr 2022 13:11:14 +0900 Subject: ASoC: soc-card: Create jack kcontrol without pins snd_soc_card_jack_new() allowed to create jack kcontrol without pins, but did not create kcontrols. The jack would not have kcontrols if pins were not going to be added. This renames the old snd_soc_card_jack_new() to snd_soc_card_jack_new_pins() for use when pins are provided or will be added later. The new snd_soc_card_jack_new() appropriately creates a jack for use without pins and adds a kcontrol. Signed-off-by: Akihiko Odaki Link: https://lore.kernel.org/r/20220408041114.6024-1-akihiko.odaki@gmail.com Signed-off-by: Mark Brown --- include/sound/soc-card.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/sound/soc-card.h b/include/sound/soc-card.h index 4f2cc4fb56b7..df08573bd80c 100644 --- a/include/sound/soc-card.h +++ b/include/sound/soc-card.h @@ -16,8 +16,11 @@ enum snd_soc_card_subclass { struct snd_kcontrol *snd_soc_card_get_kcontrol(struct snd_soc_card *soc_card, const char *name); int snd_soc_card_jack_new(struct snd_soc_card *card, const char *id, int type, - struct snd_soc_jack *jack, - struct snd_soc_jack_pin *pins, unsigned int num_pins); + struct snd_soc_jack *jack); +int snd_soc_card_jack_new_pins(struct snd_soc_card *card, const char *id, + int type, struct snd_soc_jack *jack, + struct snd_soc_jack_pin *pins, + unsigned int num_pins); int snd_soc_card_suspend_pre(struct snd_soc_card *card); int snd_soc_card_suspend_post(struct snd_soc_card *card); -- cgit v1.2.3 From d8bb92e70a434584f5b8a882eb46930cc22fd45a Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Mon, 11 Apr 2022 16:25:39 +0300 Subject: drm/dp: Factor out a function to probe a DPCD address Factor out from drm_dp_dpcd_read() a function to probe a DPCD address with a 1-byte read access. This will be needed by the next patch doing a read from an LTTPR address, which must happen without the preceding wake-up read in drm_dp_dpcd_read(). While at it add tracing for the 1 byte read even if the read was successful. v2: Add a probe function instead of exporting drm_dp_dpcd_access(). (Jani) v3: Add tracing for the 1-byte read even if the read was successful. (Khaled) Cc: Jani Nikula Cc: Khaled Almahallawy Cc: dri-devel@lists.freedesktop.org Signed-off-by: Imre Deak Reviewed-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20220411132539.984647-1-imre.deak@intel.com --- include/drm/dp/drm_dp_helper.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/drm/dp/drm_dp_helper.h b/include/drm/dp/drm_dp_helper.h index 51e02cf75277..53d1e722f4de 100644 --- a/include/drm/dp/drm_dp_helper.h +++ b/include/drm/dp/drm_dp_helper.h @@ -2053,6 +2053,7 @@ struct drm_dp_aux { bool is_remote; }; +int drm_dp_dpcd_probe(struct drm_dp_aux *aux, unsigned int offset); ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset, void *buffer, size_t size); ssize_t drm_dp_dpcd_write(struct drm_dp_aux *aux, unsigned int offset, -- cgit v1.2.3 From af47d8033fc731f19600efd27ba4a7d0fdfcc77c Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 14 Apr 2022 21:42:48 +0300 Subject: gpiolib: Introduce a helper to get first GPIO controller node Introduce a helper to get first GPIO controller node which drivers may want to use. Signed-off-by: Andy Shevchenko Tested-by: Marek Szyprowski --- include/linux/gpio/driver.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 12de0b22b4ef..83e2d72e51bb 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -766,4 +766,14 @@ static inline unsigned int gpiochip_node_count(struct device *dev) return count; } +static inline struct fwnode_handle *gpiochip_node_get_first(struct device *dev) +{ + struct fwnode_handle *fwnode; + + for_each_gpiochip_node(dev, fwnode) + return fwnode; + + return NULL; +} + #endif /* __LINUX_GPIO_DRIVER_H */ -- cgit v1.2.3 From f1724d397c60d296c0805c95a46ae7fc7163b70c Mon Sep 17 00:00:00 2001 From: Kai Ye Date: Sat, 9 Apr 2022 16:03:18 +0800 Subject: crypto: hisilicon/qm - add register checking for ACC Add register detection function to accelerator. Provided a tool that user can checking differential register through Debugfs. e.g. cd /sys/kernel/debug/hisi_zip//zip_dfx cat diff_regs Signed-off-by: Longfang Liu Signed-off-by: Kai Ye Signed-off-by: Herbert Xu --- include/linux/hisi_acc_qm.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index 177f7b7cd414..39acc0316a60 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -168,6 +168,12 @@ enum qm_vf_state { QM_NOT_READY, }; +struct dfx_diff_registers { + u32 *regs; + u32 reg_offset; + u32 reg_len; +}; + struct qm_dfx { atomic64_t err_irq_cnt; atomic64_t aeq_irq_cnt; @@ -190,6 +196,8 @@ struct qm_debug { struct dentry *debug_root; struct dentry *qm_d; struct debugfs_file files[DEBUG_FILE_NUM]; + struct dfx_diff_registers *qm_diff_regs; + struct dfx_diff_registers *acc_diff_regs; }; struct qm_shaper_factor { @@ -448,6 +456,12 @@ int hisi_qm_sriov_disable(struct pci_dev *pdev, bool is_frozen); int hisi_qm_sriov_configure(struct pci_dev *pdev, int num_vfs); void hisi_qm_dev_err_init(struct hisi_qm *qm); void hisi_qm_dev_err_uninit(struct hisi_qm *qm); +int hisi_qm_diff_regs_init(struct hisi_qm *qm, + struct dfx_diff_registers *dregs, int reg_len); +void hisi_qm_diff_regs_uninit(struct hisi_qm *qm, int reg_len); +void hisi_qm_acc_diff_regs_dump(struct hisi_qm *qm, struct seq_file *s, + struct dfx_diff_registers *dregs, int regs_len); + pci_ers_result_t hisi_qm_dev_err_detected(struct pci_dev *pdev, pci_channel_state_t state); pci_ers_result_t hisi_qm_dev_slot_reset(struct pci_dev *pdev); -- cgit v1.2.3 From a888ccd6c66683a49977ba6a2b91fe52fbec9367 Mon Sep 17 00:00:00 2001 From: Kai Ye Date: Sat, 9 Apr 2022 16:03:25 +0800 Subject: crypto: hisilicon/qm - add last word dumping for ACC Add last word dumping function during acc engines controller reset. The last words are reported to the printed information during the reset. The dmesg information included qm debugging registers and engine debugging registers. It can help to improve debugging capability. Signed-off-by: Kai Ye Signed-off-by: Herbert Xu --- include/linux/hisi_acc_qm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index 39acc0316a60..e5522eaf88fd 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -196,6 +196,9 @@ struct qm_debug { struct dentry *debug_root; struct dentry *qm_d; struct debugfs_file files[DEBUG_FILE_NUM]; + unsigned int *qm_last_words; + /* ACC engines recoreding last regs */ + unsigned int *last_words; struct dfx_diff_registers *qm_diff_regs; struct dfx_diff_registers *acc_diff_regs; }; @@ -251,6 +254,7 @@ struct hisi_qm_err_ini { void (*open_sva_prefetch)(struct hisi_qm *qm); void (*close_sva_prefetch)(struct hisi_qm *qm); void (*log_dev_hw_err)(struct hisi_qm *qm, u32 err_sts); + void (*show_last_dfx_regs)(struct hisi_qm *qm); void (*err_info_init)(struct hisi_qm *qm); }; -- cgit v1.2.3 From f6f586102add59d57bcc6eea06fdeaae11bb17a1 Mon Sep 17 00:00:00 2001 From: Eric Tremblay Date: Wed, 30 Mar 2022 12:46:40 +0200 Subject: serial: 8250: Handle UART without interrupt on TEMT using em485 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce the UART_CAP_NOTEMT capability. The capability indicates that the UART doesn't have an interrupt available on TEMT. In the case where the device does not support it, we calculate the maximum time it could take for the transmitter to empty the shift register. When we get in the situation where we get the THRE interrupt, we check if the TEMT bit is set. If it's not, we start the a timer and recall __stop_tx() after the delay. The transmit sequence is a bit modified when the capability is set. The new timer is used between the last interrupt(THRE) and a potential stop_tx timer. Signed-off-by: Giulio Benetti [moved to use added UART_CAP_TEMT] Signed-off-by: Heiko Stuebner [moved to use added UART_CAP_NOTEMT, improve timeout] Signed-off-by: Eric Tremblay [rebased to v5.17, making use of tty_get_frame_size] Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20220330104642.229507-2-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index ff84a3ed10ea..de135852107c 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -79,7 +79,9 @@ struct uart_8250_ops { struct uart_8250_em485 { struct hrtimer start_tx_timer; /* "rs485 start tx" timer */ struct hrtimer stop_tx_timer; /* "rs485 stop tx" timer */ + struct hrtimer no_temt_timer; /* "rs485 no TEMT interrupt" timer */ struct hrtimer *active_timer; /* pointer to active timer */ + unsigned long no_temt_delay; /* Delay for no_temt_timer */ struct uart_8250_port *port; /* for hrtimer callbacks */ unsigned int tx_stopped:1; /* tx is currently stopped */ }; -- cgit v1.2.3 From f3c5264f452a5b0ac1de1f2f657efbabdea3c76a Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 12 Apr 2022 18:31:58 +0200 Subject: net: page_pool: introduce ethtool stats Introduce page_pool APIs to report stats through ethtool and reduce duplicated code in each driver. Signed-off-by: Lorenzo Bianconi Reviewed-by: Jakub Kicinski Reviewed-by: Ilias Apalodimas Signed-off-by: David S. Miller --- include/net/page_pool.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include') diff --git a/include/net/page_pool.h b/include/net/page_pool.h index ea5fb70e5101..813c93499f20 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -117,6 +117,10 @@ struct page_pool_stats { struct page_pool_recycle_stats recycle_stats; }; +int page_pool_ethtool_stats_get_count(void); +u8 *page_pool_ethtool_stats_get_strings(u8 *data); +u64 *page_pool_ethtool_stats_get(u64 *data, void *stats); + /* * Drivers that wish to harvest page pool stats and report them to users * (perhaps via ethtool, debugfs, or another mechanism) can allocate a @@ -124,6 +128,23 @@ struct page_pool_stats { */ bool page_pool_get_stats(struct page_pool *pool, struct page_pool_stats *stats); +#else + +static inline int page_pool_ethtool_stats_get_count(void) +{ + return 0; +} + +static inline u8 *page_pool_ethtool_stats_get_strings(u8 *data) +{ + return data; +} + +static inline u64 *page_pool_ethtool_stats_get(u64 *data, void *stats) +{ + return data; +} + #endif struct page_pool { -- cgit v1.2.3 From 462ac1cdf4d7acf100f9b21ad8bf72c88ceb902f Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Thu, 14 Apr 2022 12:22:27 -0700 Subject: drm/i915/doc: Convert drm_i915_query_topology_info comment to kerneldoc This structure has a great comment describing the fields, but it's not currently in kerneldoc form and does not show up in the generated documentation. Let's fix that and also clarify the description of what "subslice" refers to on gen12 platforms and beyond and that "slice" is no longer meaningful on Xe_HP and beyond. Signed-off-by: Matt Roper Reviewed-by: Francisco Jerez Link: https://patchwork.freedesktop.org/patch/msgid/20220414192230.749771-1-matthew.d.roper@intel.com --- include/uapi/drm/i915_drm.h | 110 +++++++++++++++++++++++++++++++------------- 1 file changed, 78 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 9ab021c4d632..73e1c6180ddb 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -2775,66 +2775,112 @@ struct drm_i915_query { __u64 items_ptr; }; -/* - * Data written by the kernel with query DRM_I915_QUERY_TOPOLOGY_INFO : - * - * data: contains the 3 pieces of information : - * - * - the slice mask with one bit per slice telling whether a slice is - * available. The availability of slice X can be queried with the following - * formula : - * - * (data[X / 8] >> (X % 8)) & 1 - * - * - the subslice mask for each slice with one bit per subslice telling - * whether a subslice is available. Gen12 has dual-subslices, which are - * similar to two gen11 subslices. For gen12, this array represents dual- - * subslices. The availability of subslice Y in slice X can be queried - * with the following formula : - * - * (data[subslice_offset + - * X * subslice_stride + - * Y / 8] >> (Y % 8)) & 1 - * - * - the EU mask for each subslice in each slice with one bit per EU telling - * whether an EU is available. The availability of EU Z in subslice Y in - * slice X can be queried with the following formula : +/** + * struct drm_i915_query_topology_info * - * (data[eu_offset + - * (X * max_subslices + Y) * eu_stride + - * Z / 8] >> (Z % 8)) & 1 + * Describes slice/subslice/EU information queried by + * %DRM_I915_QUERY_TOPOLOGY_INFO */ struct drm_i915_query_topology_info { - /* + /** + * @flags: + * * Unused for now. Must be cleared to zero. */ __u16 flags; + /** + * @max_slices: + * + * The number of bits used to express the slice mask. + */ __u16 max_slices; + + /** + * @max_subslices: + * + * The number of bits used to express the subslice mask. + */ __u16 max_subslices; + + /** + * @max_eus_per_subslice: + * + * The number of bits in the EU mask that correspond to a single + * subslice's EUs. + */ __u16 max_eus_per_subslice; - /* + /** + * @subslice_offset: + * * Offset in data[] at which the subslice masks are stored. */ __u16 subslice_offset; - /* + /** + * @subslice_stride: + * * Stride at which each of the subslice masks for each slice are * stored. */ __u16 subslice_stride; - /* + /** + * @eu_offset: + * * Offset in data[] at which the EU masks are stored. */ __u16 eu_offset; - /* + /** + * @eu_stride: + * * Stride at which each of the EU masks for each subslice are stored. */ __u16 eu_stride; + /** + * @data: + * + * Contains 3 pieces of information : + * + * - The slice mask with one bit per slice telling whether a slice is + * available. The availability of slice X can be queried with the + * following formula : + * + * .. code:: c + * + * (data[X / 8] >> (X % 8)) & 1 + * + * Starting with Xe_HP platforms, Intel hardware no longer has + * traditional slices so i915 will always report a single slice + * (hardcoded slicemask = 0x1) which contains all of the platform's + * subslices. I.e., the mask here does not reflect any of the newer + * hardware concepts such as "gslices" or "cslices" since userspace + * is capable of inferring those from the subslice mask. + * + * - The subslice mask for each slice with one bit per subslice telling + * whether a subslice is available. Starting with Gen12 we use the + * term "subslice" to refer to what the hardware documentation + * describes as a "dual-subslices." The availability of subslice Y + * in slice X can be queried with the following formula : + * + * .. code:: c + * + * (data[subslice_offset + X * subslice_stride + Y / 8] >> (Y % 8)) & 1 + * + * - The EU mask for each subslice in each slice, with one bit per EU + * telling whether an EU is available. The availability of EU Z in + * subslice Y in slice X can be queried with the following formula : + * + * .. code:: c + * + * (data[eu_offset + + * (X * max_subslices + Y) * eu_stride + + * Z / 8 + * ] >> (Z % 8)) & 1 + */ __u8 data[]; }; -- cgit v1.2.3 From a2e5402691e2326991704b1fb73646fa2efde1c3 Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Thu, 14 Apr 2022 12:22:28 -0700 Subject: drm/i915/doc: Convert perf UAPI comments to kerneldoc Convert the comments for drm_i915_query_perf_config and drm_i915_perf_oa_config to kerneldoc so that they will show up in the generated documentation. Also correct a couple places that referred to query_id when they actually meant to refer to query_item.flags. Signed-off-by: Matt Roper Reviewed-by: Francisco Jerez Link: https://patchwork.freedesktop.org/patch/msgid/20220414192230.749771-2-matthew.d.roper@intel.com --- include/uapi/drm/i915_drm.h | 116 ++++++++++++++++++++++++++++++++------------ 1 file changed, 86 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 73e1c6180ddb..787dab98f7b0 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -2657,24 +2657,65 @@ enum drm_i915_perf_record_type { DRM_I915_PERF_RECORD_MAX /* non-ABI */ }; -/* +/** + * struct drm_i915_perf_oa_config + * * Structure to upload perf dynamic configuration into the kernel. */ struct drm_i915_perf_oa_config { - /** String formatted like "%08x-%04x-%04x-%04x-%012x" */ + /** + * @uuid: + * + * String formatted like "%\08x-%\04x-%\04x-%\04x-%\012x" + */ char uuid[36]; + /** + * @n_mux_regs: + * + * Number of mux regs in &mux_regs_ptr. + */ __u32 n_mux_regs; + + /** + * @n_boolean_regs: + * + * Number of boolean regs in &boolean_regs_ptr. + */ __u32 n_boolean_regs; + + /** + * @n_flex_regs: + * + * Number of flex regs in &flex_regs_ptr. + */ __u32 n_flex_regs; - /* - * These fields are pointers to tuples of u32 values (register address, - * value). For example the expected length of the buffer pointed by - * mux_regs_ptr is (2 * sizeof(u32) * n_mux_regs). + /** + * @mux_regs_ptr: + * + * Pointer to tuples of u32 values (register address, value) for mux + * registers. Expected length of buffer is (2 * sizeof(u32) * + * &n_mux_regs). */ __u64 mux_regs_ptr; + + /** + * @boolean_regs_ptr: + * + * Pointer to tuples of u32 values (register address, value) for mux + * registers. Expected length of buffer is (2 * sizeof(u32) * + * &n_boolean_regs). + */ __u64 boolean_regs_ptr; + + /** + * @flex_regs_ptr: + * + * Pointer to tuples of u32 values (register address, value) for mux + * registers. Expected length of buffer is (2 * sizeof(u32) * + * &n_flex_regs). + */ __u64 flex_regs_ptr; }; @@ -3001,52 +3042,67 @@ struct drm_i915_query_engine_info { struct drm_i915_engine_info engines[]; }; -/* - * Data written by the kernel with query DRM_I915_QUERY_PERF_CONFIG. +/** + * struct drm_i915_query_perf_config + * + * Data written by the kernel with query %DRM_I915_QUERY_PERF_CONFIG. */ struct drm_i915_query_perf_config { union { - /* - * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_LIST, i915 sets - * this fields to the number of configurations available. + /** + * @n_configs: + * + * When &drm_i915_query_item.flags == + * %DRM_I915_QUERY_PERF_CONFIG_LIST, i915 sets this fields to + * the number of configurations available. */ __u64 n_configs; - /* - * When query_id == DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID, - * i915 will use the value in this field as configuration - * identifier to decide what data to write into config_ptr. + /** + * @config: + * + * When &drm_i915_query_item.flags == + * %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID, i915 will use the + * value in this field as configuration identifier to decide + * what data to write into config_ptr. */ __u64 config; - /* - * When query_id == DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID, - * i915 will use the value in this field as configuration - * identifier to decide what data to write into config_ptr. + /** + * @uuid: + * + * When &drm_i915_query_item.flags == + * %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID, i915 will use the + * value in this field as configuration identifier to decide + * what data to write into config_ptr. * * String formatted like "%08x-%04x-%04x-%04x-%012x" */ char uuid[36]; }; - /* + /** + * @flags: + * * Unused for now. Must be cleared to zero. */ __u32 flags; - /* - * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_LIST, i915 will - * write an array of __u64 of configuration identifiers. + /** + * @data: + * + * When &drm_i915_query_item.flags == %DRM_I915_QUERY_PERF_CONFIG_LIST, + * i915 will write an array of __u64 of configuration identifiers. * - * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_DATA, i915 will - * write a struct drm_i915_perf_oa_config. If the following fields of - * drm_i915_perf_oa_config are set not set to 0, i915 will write into - * the associated pointers the values of submitted when the + * When &drm_i915_query_item.flags == %DRM_I915_QUERY_PERF_CONFIG_DATA, + * i915 will write a struct drm_i915_perf_oa_config. If the following + * fields of struct drm_i915_perf_oa_config are not set to 0, i915 will + * write into the associated pointers the values of submitted when the * configuration was created : * - * - n_mux_regs - * - n_boolean_regs - * - n_flex_regs + * - &drm_i915_perf_oa_config.n_mux_regs + * - &drm_i915_perf_oa_config.n_boolean_regs + * - &drm_i915_perf_oa_config.n_flex_regs */ __u8 data[]; }; -- cgit v1.2.3 From 1c671ad753dbbf5f5da7b18175d05acc3cccf1a8 Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Thu, 14 Apr 2022 12:22:29 -0700 Subject: drm/i915/doc: Link query items to their uapi structs Document the possible options for drm_i915_query_item.query_id with links to the corresponding uapi structures. Signed-off-by: Matt Roper Reviewed-by: Francisco Jerez Link: https://patchwork.freedesktop.org/patch/msgid/20220414192230.749771-3-matthew.d.roper@intel.com --- include/uapi/drm/i915_drm.h | 34 ++++++++++++++++++++-------------- 1 file changed, 20 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 787dab98f7b0..097a7935a510 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -2724,18 +2724,24 @@ struct drm_i915_perf_oa_config { * * The behaviour is determined by the @query_id. Note that exactly what * @data_ptr is also depends on the specific @query_id. - * - * For specific queries see: - * * `GuC HWCONFIG blob uAPI`_ */ struct drm_i915_query_item { - /** @query_id: The id for this query */ + /** + * @query_id: + * + * The id for this query. Currently accepted query IDs are: + * - %DRM_I915_QUERY_TOPOLOGY_INFO (see struct drm_i915_query_topology_info) + * - %DRM_I915_QUERY_ENGINE_INFO (see struct drm_i915_engine_info) + * - %DRM_I915_QUERY_PERF_CONFIG (see struct drm_i915_query_perf_config) + * - %DRM_I915_QUERY_MEMORY_REGIONS (see struct drm_i915_query_memory_regions) + * - %DRM_I915_QUERY_HWCONFIG_BLOB (see `GuC HWCONFIG blob uAPI`) + */ __u64 query_id; -#define DRM_I915_QUERY_TOPOLOGY_INFO 1 -#define DRM_I915_QUERY_ENGINE_INFO 2 -#define DRM_I915_QUERY_PERF_CONFIG 3 -#define DRM_I915_QUERY_MEMORY_REGIONS 4 -#define DRM_I915_QUERY_HWCONFIG_BLOB 5 +#define DRM_I915_QUERY_TOPOLOGY_INFO 1 +#define DRM_I915_QUERY_ENGINE_INFO 2 +#define DRM_I915_QUERY_PERF_CONFIG 3 +#define DRM_I915_QUERY_MEMORY_REGIONS 4 +#define DRM_I915_QUERY_HWCONFIG_BLOB 5 /* Must be kept compact -- no holes and well documented */ /** @@ -2751,14 +2757,14 @@ struct drm_i915_query_item { /** * @flags: * - * When query_id == DRM_I915_QUERY_TOPOLOGY_INFO, must be 0. + * When &query_id == %DRM_I915_QUERY_TOPOLOGY_INFO, must be 0. * - * When query_id == DRM_I915_QUERY_PERF_CONFIG, must be one of the + * When &query_id == %DRM_I915_QUERY_PERF_CONFIG, must be one of the * following: * - * - DRM_I915_QUERY_PERF_CONFIG_LIST - * - DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID - * - DRM_I915_QUERY_PERF_CONFIG_FOR_UUID + * - %DRM_I915_QUERY_PERF_CONFIG_LIST + * - %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID + * - %DRM_I915_QUERY_PERF_CONFIG_FOR_UUID */ __u32 flags; #define DRM_I915_QUERY_PERF_CONFIG_LIST 1 -- cgit v1.2.3 From c94fde8f516610b0961b65a59bc8885e6df23cb9 Mon Sep 17 00:00:00 2001 From: Matt Atwood Date: Thu, 14 Apr 2022 12:22:30 -0700 Subject: drm/i915/uapi: Add DRM_I915_QUERY_GEOMETRY_SUBSLICES Newer platforms have DSS that aren't necessarily available for both geometry and compute, two queries will need to exist. This introduces the first, when passing a valid engine class and engine instance in the flags returns a topology describing geometry. Based on past discussion, we currently only support this new query item on Xe_HP and beyond; earlier platforms do not need to worry about geometry and compute pipelines having access to different topology and should continue to use the existing topology query. v2: fix white space errors v3: change flags from hosting 2 8 bit numbers to holding a i915_engine_class_instance struct v4: add error if non rcs engine passed. v5 (by MattR): - Improve kerneldoc and cross references to related structs/enums. (Daniel) - Clarify that geometry query is only supported on render engines (Francisco) - Clarify that the new query is only supported on Xe_HP+. - Fix checkpatch warnings. Cc: Ashutosh Dixit Cc: Matt Roper Cc: Joonas Lahtinen Cc: Francisco Jerez UMD (mesa): https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14143 Testcase: igt@i915_query@test-query-geometry-subslices Signed-off-by: Matt Atwood Signed-off-by: Matt Roper Reviewed-by: Francisco Jerez Link: https://patchwork.freedesktop.org/patch/msgid/20220414192230.749771-4-matthew.d.roper@intel.com --- include/uapi/drm/i915_drm.h | 27 +++++++++++++++++++++++---- 1 file changed, 23 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 097a7935a510..35ca528803fd 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -172,7 +172,9 @@ enum drm_i915_gem_engine_class { I915_ENGINE_CLASS_INVALID = -1 }; -/* +/** + * struct i915_engine_class_instance - Engine class/instance identifier + * * There may be more than one engine fulfilling any role within the system. * Each engine of a class is given a unique instance number and therefore * any engine can be specified by its class:instance tuplet. APIs that allow @@ -180,10 +182,21 @@ enum drm_i915_gem_engine_class { * for this identification. */ struct i915_engine_class_instance { - __u16 engine_class; /* see enum drm_i915_gem_engine_class */ - __u16 engine_instance; + /** + * @engine_class: + * + * Engine class from enum drm_i915_gem_engine_class + */ + __u16 engine_class; #define I915_ENGINE_CLASS_INVALID_NONE -1 #define I915_ENGINE_CLASS_INVALID_VIRTUAL -2 + + /** + * @engine_instance: + * + * Engine instance. + */ + __u16 engine_instance; }; /** @@ -2735,6 +2748,7 @@ struct drm_i915_query_item { * - %DRM_I915_QUERY_PERF_CONFIG (see struct drm_i915_query_perf_config) * - %DRM_I915_QUERY_MEMORY_REGIONS (see struct drm_i915_query_memory_regions) * - %DRM_I915_QUERY_HWCONFIG_BLOB (see `GuC HWCONFIG blob uAPI`) + * - %DRM_I915_QUERY_GEOMETRY_SUBSLICES (see struct drm_i915_query_topology_info) */ __u64 query_id; #define DRM_I915_QUERY_TOPOLOGY_INFO 1 @@ -2742,6 +2756,7 @@ struct drm_i915_query_item { #define DRM_I915_QUERY_PERF_CONFIG 3 #define DRM_I915_QUERY_MEMORY_REGIONS 4 #define DRM_I915_QUERY_HWCONFIG_BLOB 5 +#define DRM_I915_QUERY_GEOMETRY_SUBSLICES 6 /* Must be kept compact -- no holes and well documented */ /** @@ -2765,6 +2780,9 @@ struct drm_i915_query_item { * - %DRM_I915_QUERY_PERF_CONFIG_LIST * - %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID * - %DRM_I915_QUERY_PERF_CONFIG_FOR_UUID + * + * When &query_id == %DRM_I915_QUERY_GEOMETRY_SUBSLICES must contain + * a struct i915_engine_class_instance that references a render engine. */ __u32 flags; #define DRM_I915_QUERY_PERF_CONFIG_LIST 1 @@ -3051,7 +3069,8 @@ struct drm_i915_query_engine_info { /** * struct drm_i915_query_perf_config * - * Data written by the kernel with query %DRM_I915_QUERY_PERF_CONFIG. + * Data written by the kernel with query %DRM_I915_QUERY_PERF_CONFIG and + * %DRM_I915_QUERY_GEOMETRY_SUBSLICES. */ struct drm_i915_query_perf_config { union { -- cgit v1.2.3 From 4dc84c06a343fcb95fd5a0acb537aefa4ebdd1b0 Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Tue, 12 Apr 2022 10:01:19 +0800 Subject: net: ethtool: extend ringparam set/get APIs for tx_push Currently tx push is a standard driver feature which controls use of a fast path descriptor push. So this patch extends the ringparam APIs and data structures to support set/get tx push by ethtool -G/g. Signed-off-by: Jie Wang Signed-off-by: Guangbin Huang Signed-off-by: Jakub Kicinski --- include/linux/ethtool.h | 4 ++++ include/uapi/linux/ethtool_netlink.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 4af58459a1e7..99dc7bfbcd3c 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -71,11 +71,13 @@ enum { * struct kernel_ethtool_ringparam - RX/TX ring configuration * @rx_buf_len: Current length of buffers on the rx ring. * @tcp_data_split: Scatter packet headers and data to separate buffers + * @tx_push: The flag of tx push mode * @cqe_size: Size of TX/RX completion queue event */ struct kernel_ethtool_ringparam { u32 rx_buf_len; u8 tcp_data_split; + u8 tx_push; u32 cqe_size; }; @@ -83,10 +85,12 @@ struct kernel_ethtool_ringparam { * enum ethtool_supported_ring_param - indicator caps for setting ring params * @ETHTOOL_RING_USE_RX_BUF_LEN: capture for setting rx_buf_len * @ETHTOOL_RING_USE_CQE_SIZE: capture for setting cqe_size + * @ETHTOOL_RING_USE_TX_PUSH: capture for setting tx_push */ enum ethtool_supported_ring_param { ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0), ETHTOOL_RING_USE_CQE_SIZE = BIT(1), + ETHTOOL_RING_USE_TX_PUSH = BIT(2), }; #define __ETH_RSS_HASH_BIT(bit) ((u32)1 << (bit)) diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 979850221b8d..d2fb4f7be61b 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -338,6 +338,7 @@ enum { ETHTOOL_A_RINGS_RX_BUF_LEN, /* u32 */ ETHTOOL_A_RINGS_TCP_DATA_SPLIT, /* u8 */ ETHTOOL_A_RINGS_CQE_SIZE, /* u32 */ + ETHTOOL_A_RINGS_TX_PUSH, /* u8 */ /* add new constants above here */ __ETHTOOL_A_RINGS_CNT, -- cgit v1.2.3 From db53cd3d88dc328dea2e968c9c8d3b4294a8a674 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 13 Apr 2022 11:43:20 -0600 Subject: net: Handle l3mdev in ip_tunnel_init_flow Ido reported that the commit referenced in the Fixes tag broke a gre use case with dummy devices. Add a check to ip_tunnel_init_flow to see if the oif is an l3mdev port and if so set the oif to 0 to avoid the oif comparison in fib_lookup_good_nhc. Fixes: 40867d74c374 ("net: Add l3mdev index to flow struct and avoid oif reset for port devices") Reported-by: Ido Schimmel Signed-off-by: David Ahern Signed-off-by: Jakub Kicinski --- include/net/ip_tunnels.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 0219fe907b26..88dee57eac8a 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -243,11 +243,18 @@ static inline __be32 tunnel_id_to_key32(__be64 tun_id) static inline void ip_tunnel_init_flow(struct flowi4 *fl4, int proto, __be32 daddr, __be32 saddr, - __be32 key, __u8 tos, int oif, + __be32 key, __u8 tos, + struct net *net, int oif, __u32 mark, __u32 tun_inner_hash) { memset(fl4, 0, sizeof(*fl4)); - fl4->flowi4_oif = oif; + + if (oif) { + fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index_rcu(net, oif); + /* Legacy VRF/l3mdev use case */ + fl4->flowi4_oif = fl4->flowi4_l3mdev ? 0 : oif; + } + fl4->daddr = daddr; fl4->saddr = saddr; fl4->flowi4_tos = tos; -- cgit v1.2.3 From 9cb7c013420f98fa6fd12fc6a5dc055170c108db Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 13 Apr 2022 11:13:33 -0700 Subject: ipv6: make ip6_rt_gc_expire an atomic_t Reads and Writes to ip6_rt_gc_expire always have been racy, as syzbot reported lately [1] There is a possible risk of under-flow, leading to unexpected high value passed to fib6_run_gc(), although I have not observed this in the field. Hosts hitting ip6_dst_gc() very hard are under pretty bad state anyway. [1] BUG: KCSAN: data-race in ip6_dst_gc / ip6_dst_gc read-write to 0xffff888102110744 of 4 bytes by task 13165 on cpu 1: ip6_dst_gc+0x1f3/0x220 net/ipv6/route.c:3311 dst_alloc+0x9b/0x160 net/core/dst.c:86 ip6_dst_alloc net/ipv6/route.c:344 [inline] icmp6_dst_alloc+0xb2/0x360 net/ipv6/route.c:3261 mld_sendpack+0x2b9/0x580 net/ipv6/mcast.c:1807 mld_send_cr net/ipv6/mcast.c:2119 [inline] mld_ifc_work+0x576/0x800 net/ipv6/mcast.c:2651 process_one_work+0x3d3/0x720 kernel/workqueue.c:2289 worker_thread+0x618/0xa70 kernel/workqueue.c:2436 kthread+0x1a9/0x1e0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 read-write to 0xffff888102110744 of 4 bytes by task 11607 on cpu 0: ip6_dst_gc+0x1f3/0x220 net/ipv6/route.c:3311 dst_alloc+0x9b/0x160 net/core/dst.c:86 ip6_dst_alloc net/ipv6/route.c:344 [inline] icmp6_dst_alloc+0xb2/0x360 net/ipv6/route.c:3261 mld_sendpack+0x2b9/0x580 net/ipv6/mcast.c:1807 mld_send_cr net/ipv6/mcast.c:2119 [inline] mld_ifc_work+0x576/0x800 net/ipv6/mcast.c:2651 process_one_work+0x3d3/0x720 kernel/workqueue.c:2289 worker_thread+0x618/0xa70 kernel/workqueue.c:2436 kthread+0x1a9/0x1e0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 value changed: 0x00000bb3 -> 0x00000ba9 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 11607 Comm: kworker/0:21 Not tainted 5.18.0-rc1-syzkaller-00037-g42e7a03d3bad-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: mld mld_ifc_work Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Reported-by: syzbot Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20220413181333.649424-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/net/netns/ipv6.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 3d83b64471d3..b4af4837d80b 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -75,8 +75,8 @@ struct netns_ipv6 { struct list_head fib6_walkers; rwlock_t fib6_walker_lock; spinlock_t fib6_gc_lock; - unsigned int ip6_rt_gc_expire; - unsigned long ip6_rt_last_gc; + atomic_t ip6_rt_gc_expire; + unsigned long ip6_rt_last_gc; unsigned char flowlabel_has_excl; #ifdef CONFIG_IPV6_MULTIPLE_TABLES bool fib6_has_custom_rules; -- cgit v1.2.3 From 2dfe63e61cc31ee59ce951672b0850b5229cd5b0 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 14 Apr 2022 19:13:40 -0700 Subject: mm, kfence: support kmem_dump_obj() for KFENCE objects Calling kmem_obj_info() via kmem_dump_obj() on KFENCE objects has been producing garbage data due to the object not actually being maintained by SLAB or SLUB. Fix this by implementing __kfence_obj_info() that copies relevant information to struct kmem_obj_info when the object was allocated by KFENCE; this is called by a common kmem_obj_info(), which also calls the slab/slub/slob specific variant now called __kmem_obj_info(). For completeness, kmem_dump_obj() now displays if the object was allocated by KFENCE. Link: https://lore.kernel.org/all/20220323090520.GG16885@xsang-OptiPlex-9020/ Link: https://lkml.kernel.org/r/20220406131558.3558585-1-elver@google.com Fixes: b89fb5ef0ce6 ("mm, kfence: insert KFENCE hooks for SLUB") Fixes: d3fb45f370d9 ("mm, kfence: insert KFENCE hooks for SLAB") Signed-off-by: Marco Elver Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Reported-by: kernel test robot Acked-by: Vlastimil Babka [slab] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfence.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include') diff --git a/include/linux/kfence.h b/include/linux/kfence.h index f49e64222628..726857a4b680 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -204,6 +204,22 @@ static __always_inline __must_check bool kfence_free(void *addr) */ bool __must_check kfence_handle_page_fault(unsigned long addr, bool is_write, struct pt_regs *regs); +#ifdef CONFIG_PRINTK +struct kmem_obj_info; +/** + * __kfence_obj_info() - fill kmem_obj_info struct + * @kpp: kmem_obj_info to be filled + * @object: the object + * + * Return: + * * false - not a KFENCE object + * * true - a KFENCE object, filled @kpp + * + * Copies information to @kpp for KFENCE objects. + */ +bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab); +#endif + #else /* CONFIG_KFENCE */ static inline bool is_kfence_address(const void *addr) { return false; } @@ -221,6 +237,14 @@ static inline bool __must_check kfence_handle_page_fault(unsigned long addr, boo return false; } +#ifdef CONFIG_PRINTK +struct kmem_obj_info; +static inline bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) +{ + return false; +} +#endif + #endif #endif /* _LINUX_KFENCE_H */ -- cgit v1.2.3 From f9a2fb73318eb4dbf8cd84866b8b0dd012d8b116 Mon Sep 17 00:00:00 2001 From: Arun Ajith S Date: Fri, 15 Apr 2022 08:34:02 +0000 Subject: net/ipv6: Introduce accept_unsolicited_na knob to implement router-side changes for RFC9131 Add a new neighbour cache entry in STALE state for routers on receiving an unsolicited (gratuitous) neighbour advertisement with target link-layer-address option specified. This is similar to the arp_accept configuration for IPv4. A new sysctl endpoint is created to turn on this behaviour: /proc/sys/net/ipv6/conf/interface/accept_unsolicited_na. Signed-off-by: Arun Ajith S Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + include/uapi/linux/ipv6.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 16870f86c74d..918bfea4ef5f 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -61,6 +61,7 @@ struct ipv6_devconf { __s32 suppress_frag_ndisc; __s32 accept_ra_mtu; __s32 drop_unsolicited_na; + __s32 accept_unsolicited_na; struct ipv6_stable_secret { bool initialized; struct in6_addr secret; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index d4178dace0bf..549ddeaf788b 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -194,6 +194,7 @@ enum { DEVCONF_IOAM6_ID, DEVCONF_IOAM6_ID_WIDE, DEVCONF_NDISC_EVICT_NOCARRIER, + DEVCONF_ACCEPT_UNSOLICITED_NA, DEVCONF_MAX }; -- cgit v1.2.3 From da40b613f89c43c58986e6f30560ad6573a4d569 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Apr 2022 17:10:41 -0700 Subject: tcp: add drop reason support to tcp_validate_incoming() Creates four new drop reasons for the following cases: 1) packet being rejected by RFC 7323 PAWS check 2) packet being rejected by SEQUENCE check 3) Invalid RST packet 4) Invalid SYN packet Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ++++++ include/trace/events/skb.h | 5 +++++ 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0ef11df1bc67..a903da1fa0ed 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -381,6 +381,12 @@ enum skb_drop_reason { * the ofo queue, corresponding to * LINUX_MIB_TCPOFOMERGE */ + SKB_DROP_REASON_TCP_RFC7323_PAWS, /* PAWS check, corresponding to + * LINUX_MIB_PAWSESTABREJECTED + */ + SKB_DROP_REASON_TCP_INVALID_SEQUENCE, /* Not acceptable SEQ field */ + SKB_DROP_REASON_TCP_RESET, /* Invalid RST packet */ + SKB_DROP_REASON_TCP_INVALID_SYN, /* Incoming packet has unexpected SYN flag */ SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */ SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by * BPF_PROG_TYPE_CGROUP_SKB diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 2da72a9a5764..820dacd14bad 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -37,6 +37,11 @@ EM(SKB_DROP_REASON_TCP_OLD_DATA, TCP_OLD_DATA) \ EM(SKB_DROP_REASON_TCP_OVERWINDOW, TCP_OVERWINDOW) \ EM(SKB_DROP_REASON_TCP_OFOMERGE, TCP_OFOMERGE) \ + EM(SKB_DROP_REASON_TCP_RFC7323_PAWS, TCP_RFC7323_PAWS) \ + EM(SKB_DROP_REASON_TCP_INVALID_SEQUENCE, \ + TCP_INVALID_SEQUENCE) \ + EM(SKB_DROP_REASON_TCP_RESET, TCP_RESET) \ + EM(SKB_DROP_REASON_TCP_INVALID_SYN, TCP_INVALID_SYN) \ EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES) \ EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS, \ BPF_CGROUP_EGRESS) \ -- cgit v1.2.3 From 669da7a71890b2b2a31a7e9571c0fdf1123e26ef Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Apr 2022 17:10:43 -0700 Subject: tcp: add drop reasons to tcp_rcv_state_process() Add basic support for drop reasons in tcp_rcv_state_process() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +++ include/trace/events/skb.h | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a903da1fa0ed..6f1410b5ff13 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -387,6 +387,9 @@ enum skb_drop_reason { SKB_DROP_REASON_TCP_INVALID_SEQUENCE, /* Not acceptable SEQ field */ SKB_DROP_REASON_TCP_RESET, /* Invalid RST packet */ SKB_DROP_REASON_TCP_INVALID_SYN, /* Incoming packet has unexpected SYN flag */ + SKB_DROP_REASON_TCP_CLOSE, /* TCP socket in CLOSE state */ + SKB_DROP_REASON_TCP_FASTOPEN, /* dropped by FASTOPEN request socket */ + SKB_DROP_REASON_TCP_OLD_ACK, /* TCP ACK is old, but in window */ SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */ SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by * BPF_PROG_TYPE_CGROUP_SKB diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 820dacd14bad..fbe21ad038bc 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -42,6 +42,9 @@ TCP_INVALID_SEQUENCE) \ EM(SKB_DROP_REASON_TCP_RESET, TCP_RESET) \ EM(SKB_DROP_REASON_TCP_INVALID_SYN, TCP_INVALID_SYN) \ + EM(SKB_DROP_REASON_TCP_CLOSE, TCP_CLOSE) \ + EM(SKB_DROP_REASON_TCP_FASTOPEN, TCP_FASTOPEN) \ + EM(SKB_DROP_REASON_TCP_OLD_ACK, TCP_OLD_ACK) \ EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES) \ EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS, \ BPF_CGROUP_EGRESS) \ -- cgit v1.2.3 From 4b506af9c5b8de0da34097d50d9448dfb33d70c3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Apr 2022 17:10:44 -0700 Subject: tcp: add two drop reasons for tcp_ack() Add TCP_TOO_OLD_ACK and TCP_ACK_UNSENT_DATA drop reasons so that tcp_rcv_established() can report them. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 ++ include/trace/events/skb.h | 3 +++ 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6f1410b5ff13..9ff5557b1909 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -390,6 +390,8 @@ enum skb_drop_reason { SKB_DROP_REASON_TCP_CLOSE, /* TCP socket in CLOSE state */ SKB_DROP_REASON_TCP_FASTOPEN, /* dropped by FASTOPEN request socket */ SKB_DROP_REASON_TCP_OLD_ACK, /* TCP ACK is old, but in window */ + SKB_DROP_REASON_TCP_TOO_OLD_ACK, /* TCP ACK is too old */ + SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, /* TCP ACK for data we haven't sent yet */ SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */ SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by * BPF_PROG_TYPE_CGROUP_SKB diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index fbe21ad038bc..eab0b09223f3 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -45,6 +45,9 @@ EM(SKB_DROP_REASON_TCP_CLOSE, TCP_CLOSE) \ EM(SKB_DROP_REASON_TCP_FASTOPEN, TCP_FASTOPEN) \ EM(SKB_DROP_REASON_TCP_OLD_ACK, TCP_OLD_ACK) \ + EM(SKB_DROP_REASON_TCP_TOO_OLD_ACK, TCP_TOO_OLD_ACK) \ + EM(SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, \ + TCP_ACK_UNSENT_DATA) \ EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES) \ EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS, \ BPF_CGROUP_EGRESS) \ -- cgit v1.2.3 From e7c89ae4078eab24af71ba26b91642e819a4bd7f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Apr 2022 17:10:45 -0700 Subject: tcp: add drop reason support to tcp_prune_ofo_queue() Add one reason for packets dropped from OFO queue because of memory pressure. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + include/trace/events/skb.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9ff5557b1909..ad15ad208b56 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -392,6 +392,7 @@ enum skb_drop_reason { SKB_DROP_REASON_TCP_OLD_ACK, /* TCP ACK is old, but in window */ SKB_DROP_REASON_TCP_TOO_OLD_ACK, /* TCP ACK is too old */ SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, /* TCP ACK for data we haven't sent yet */ + SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, /* pruned from TCP OFO queue */ SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */ SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by * BPF_PROG_TYPE_CGROUP_SKB diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index eab0b09223f3..73d7a6e594cb 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -48,6 +48,8 @@ EM(SKB_DROP_REASON_TCP_TOO_OLD_ACK, TCP_TOO_OLD_ACK) \ EM(SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, \ TCP_ACK_UNSENT_DATA) \ + EM(SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, \ + TCP_OFO_QUEUE_PRUNE) \ EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES) \ EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS, \ BPF_CGROUP_EGRESS) \ -- cgit v1.2.3 From 8fbf195798b56e1e87f62d01be636a6425c304c2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 15 Apr 2022 17:10:48 -0700 Subject: tcp: add drop reason support to tcp_ofo_queue() packets in OFO queue might be redundant, and dropped. tcp_drop() is no longer needed. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + include/trace/events/skb.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ad15ad208b56..84d78df60453 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -393,6 +393,7 @@ enum skb_drop_reason { SKB_DROP_REASON_TCP_TOO_OLD_ACK, /* TCP ACK is too old */ SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, /* TCP ACK for data we haven't sent yet */ SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, /* pruned from TCP OFO queue */ + SKB_DROP_REASON_TCP_OFO_DROP, /* data already in receive queue */ SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */ SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by * BPF_PROG_TYPE_CGROUP_SKB diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 73d7a6e594cb..a477bf907498 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -37,6 +37,7 @@ EM(SKB_DROP_REASON_TCP_OLD_DATA, TCP_OLD_DATA) \ EM(SKB_DROP_REASON_TCP_OVERWINDOW, TCP_OVERWINDOW) \ EM(SKB_DROP_REASON_TCP_OFOMERGE, TCP_OFOMERGE) \ + EM(SKB_DROP_REASON_TCP_OFO_DROP, TCP_OFO_DROP) \ EM(SKB_DROP_REASON_TCP_RFC7323_PAWS, TCP_RFC7323_PAWS) \ EM(SKB_DROP_REASON_TCP_INVALID_SEQUENCE, \ TCP_INVALID_SEQUENCE) \ -- cgit v1.2.3 From 0df71650c051ab106c921de257f4b38e9e3dd251 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 24 Mar 2022 16:35:24 -0400 Subject: block: allow using the per-cpu bio cache from bio_alloc_bioset Replace the BIO_PERCPU_CACHE bio-internal flag with a REQ_ALLOC_CACHE one that can be passed to bio_alloc / bio_alloc_bioset, and implement the percpu cache allocation logic in a helper called from bio_alloc_bioset. This allows any bio_alloc_bioset user to use the percpu caches instead of having the functionality tied to struct kiocb. Signed-off-by: Mike Snitzer [hch: refactored a bit] Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220324203526.62306-2-snitzer@kernel.org Signed-off-by: Jens Axboe --- include/linux/bio.h | 2 -- include/linux/blk_types.h | 3 ++- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 278cc81cc1e7..0fe8a51a0778 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -405,8 +405,6 @@ extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src); struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, unsigned int opf, gfp_t gfp_mask, struct bio_set *bs); -struct bio *bio_alloc_kiocb(struct kiocb *kiocb, struct block_device *bdev, - unsigned short nr_vecs, unsigned int opf, struct bio_set *bs); struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs); extern void bio_put(struct bio *); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 1973ef9bd40f..4968cb17b13b 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -329,7 +329,6 @@ enum { BIO_QOS_MERGED, /* but went through rq_qos merge path */ BIO_REMAPPED, BIO_ZONE_WRITE_LOCKED, /* Owns a zoned device zone write lock */ - BIO_PERCPU_CACHE, /* can participate in per-cpu alloc cache */ BIO_FLAG_LAST }; @@ -414,6 +413,7 @@ enum req_flag_bits { __REQ_NOUNMAP, /* do not free blocks when zeroing */ __REQ_POLLED, /* caller polls for completion using bio_poll */ + __REQ_ALLOC_CACHE, /* allocate IO from cache if available */ /* for driver use */ __REQ_DRV, @@ -439,6 +439,7 @@ enum req_flag_bits { #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) #define REQ_POLLED (1ULL << __REQ_POLLED) +#define REQ_ALLOC_CACHE (1ULL << __REQ_ALLOC_CACHE) #define REQ_DRV (1ULL << __REQ_DRV) #define REQ_SWAP (1ULL << __REQ_SWAP) -- cgit v1.2.3 From b53f3dcd705e52a07bd0311870dbfb6842e88c91 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Thu, 24 Mar 2022 16:35:25 -0400 Subject: block: allow use of per-cpu bio alloc cache by block drivers Refine per-cpu bio alloc cache interfaces so that DM and other block drivers can properly create and use the cache: DM uses bioset_init_from_src() to do its final bioset initialization, so must update bioset_init_from_src() to set BIOSET_PERCPU_CACHE if %src bioset has a cache. Also move bio_clear_polled() to include/linux/bio.h to allow users outside of block core. Signed-off-by: Mike Snitzer Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220324203526.62306-3-snitzer@kernel.org Signed-off-by: Jens Axboe --- include/linux/bio.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 0fe8a51a0778..8e87f3065042 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -780,6 +780,12 @@ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb) bio->bi_opf |= REQ_NOWAIT; } +static inline void bio_clear_polled(struct bio *bio) +{ + /* can't support alloc cache if we turn off polling */ + bio->bi_opf &= ~(REQ_POLLED | REQ_ALLOC_CACHE); +} + struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev, unsigned int nr_pages, unsigned int opf, gfp_t gfp); -- cgit v1.2.3 From 066ff571011d8416e903d3d4f1f41e0b5eb91e1d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 6 Apr 2022 08:12:27 +0200 Subject: block: turn bio_kmalloc into a simple kmalloc wrapper Remove the magic autofree semantics and require the callers to explicitly call bio_init to initialize the bio. This allows bio_free to catch accidental bio_put calls on bio_init()ed bios as well. Signed-off-by: Christoph Hellwig Acked-by: Coly Li Acked-by: Mike Snitzer Link: https://lore.kernel.org/r/20220406061228.410163-5-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/bio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 8e87f3065042..49eff01fb829 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -405,7 +405,7 @@ extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src); struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, unsigned int opf, gfp_t gfp_mask, struct bio_set *bs); -struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs); +struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask); extern void bio_put(struct bio *); struct bio *bio_alloc_clone(struct block_device *bdev, struct bio *bio_src, -- cgit v1.2.3 From 817e8b51eb3d927ce6d56ecf9f48bc3c5b26168b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:33 +0200 Subject: target: pass a block_device to target_configure_unmap_from_queue The SCSI target drivers is a consumer of the block layer and shoul d generally work on struct block_device. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220415045258.199825-3-hch@lst.de Signed-off-by: Jens Axboe --- include/target/target_core_backend.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index 675f3a1fe613..773963a1e0b5 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -14,7 +14,7 @@ #define TRANSPORT_FLAG_PASSTHROUGH_ALUA 0x2 #define TRANSPORT_FLAG_PASSTHROUGH_PGR 0x4 -struct request_queue; +struct block_device; struct scatterlist; struct target_backend_ops { @@ -117,7 +117,7 @@ sense_reason_t passthrough_parse_cdb(struct se_cmd *cmd, bool target_sense_desc_format(struct se_device *dev); sector_t target_to_linux_sector(struct se_device *dev, sector_t lb); bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib, - struct request_queue *q); + struct block_device *bdev); static inline bool target_dev_configured(struct se_device *se_dev) { -- cgit v1.2.3 From 10f0d2a517796b8f6dc04fb0cc3e49003ae6b0bc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:42 +0200 Subject: block: add a bdev_nonrot helper Add a helper to check the nonrot flag based on the block_device instead of having to poke into the block layer internal request_queue. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Acked-by: David Sterba [btrfs] Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220415045258.199825-12-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 60d016138997..3a9578e14a6b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1326,6 +1326,11 @@ static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) return 0; } +static inline bool bdev_nonrot(struct block_device *bdev) +{ + return blk_queue_nonrot(bdev_get_queue(bdev)); +} + static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); -- cgit v1.2.3 From 08e688fdb8f7e862092ae64cee20bc8b463d1046 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:43 +0200 Subject: block: add a bdev_write_cache helper Add a helper to check the write cache flag based on the block_device instead of having to poke into the block layer internal request_queue. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Acked-by: David Sterba [btrfs] Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220415045258.199825-13-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 3a9578e14a6b..807a49aa5a27 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1331,6 +1331,11 @@ static inline bool bdev_nonrot(struct block_device *bdev) return blk_queue_nonrot(bdev_get_queue(bdev)); } +static inline bool bdev_write_cache(struct block_device *bdev) +{ + return test_bit(QUEUE_FLAG_WC, &bdev_get_queue(bdev)->queue_flags); +} + static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); -- cgit v1.2.3 From a557e82e5a01826f902bd94fc925c03f253cb712 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:44 +0200 Subject: block: add a bdev_fua helper Add a helper to check the FUA flag based on the block_device instead of having to poke into the block layer internal request_queue. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220415045258.199825-14-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 807a49aa5a27..075b16d4560e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -602,7 +602,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); REQ_FAILFAST_DRIVER)) #define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) #define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) -#define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags) #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) #define blk_queue_nowait(q) test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags) @@ -1336,6 +1335,11 @@ static inline bool bdev_write_cache(struct block_device *bdev) return test_bit(QUEUE_FLAG_WC, &bdev_get_queue(bdev)->queue_flags); } +static inline bool bdev_fua(struct block_device *bdev) +{ + return test_bit(QUEUE_FLAG_FUA, &bdev_get_queue(bdev)->queue_flags); +} + static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); -- cgit v1.2.3 From 36d254893aa6a6e204075c3cce94bb572ac32c04 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:45 +0200 Subject: block: add a bdev_stable_writes helper Add a helper to check the stable writes flag based on the block_device instead of having to poke into the block layer internal request_queue. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220415045258.199825-15-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 075b16d4560e..a433798c3343 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1330,6 +1330,12 @@ static inline bool bdev_nonrot(struct block_device *bdev) return blk_queue_nonrot(bdev_get_queue(bdev)); } +static inline bool bdev_stable_writes(struct block_device *bdev) +{ + return test_bit(QUEUE_FLAG_STABLE_WRITES, + &bdev_get_queue(bdev)->queue_flags); +} + static inline bool bdev_write_cache(struct block_device *bdev) { return test_bit(QUEUE_FLAG_WC, &bdev_get_queue(bdev)->queue_flags); -- cgit v1.2.3 From 2aba0d19f4d8c8929b4b3b94a9cfde2aa20e6ee2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:46 +0200 Subject: block: add a bdev_max_zone_append_sectors helper Add a helper to check the max supported sectors for zone append based on the block_device instead of having to poke into the block layer internal request_queue. Signed-off-by: Christoph Hellwig Acked-by: Damien Le Moal Reviewed-by: Martin K. Petersen Reviewed-by: Johannes Thumshirn Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220415045258.199825-16-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a433798c3343..f8c50b77543e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1188,6 +1188,12 @@ static inline unsigned int queue_max_zone_append_sectors(const struct request_qu return min(l->max_zone_append_sectors, l->max_sectors); } +static inline unsigned int +bdev_max_zone_append_sectors(struct block_device *bdev) +{ + return queue_max_zone_append_sectors(bdev_get_queue(bdev)); +} + static inline unsigned queue_logical_block_size(const struct request_queue *q) { int retval = 512; -- cgit v1.2.3 From 640f2a23911b8388989547f89d055afbb910b88e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:48 +0200 Subject: block: use bdev_alignment_offset in disk_alignment_offset_show This does the same as the open coded variant except for an extra branch, and allows to remove queue_alignment_offset entirely. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20220415045258.199825-18-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f8c50b77543e..d5346e72e364 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1251,14 +1251,6 @@ bdev_zone_write_granularity(struct block_device *bdev) return queue_zone_write_granularity(bdev_get_queue(bdev)); } -static inline int queue_alignment_offset(const struct request_queue *q) -{ - if (q->limits.misaligned) - return -1; - - return q->limits.alignment_offset; -} - static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector) { unsigned int granularity = max(lim->physical_block_size, lim->io_min); -- cgit v1.2.3 From 89098b075cb74a80083bc4ed6b71d0ee18b6898f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:49 +0200 Subject: block: move bdev_alignment_offset and queue_limit_alignment_offset out of line No need to inline these fairly larger helpers. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20220415045258.199825-19-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 21 +-------------------- 1 file changed, 1 insertion(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d5346e72e364..0a1795ac2627 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1251,26 +1251,7 @@ bdev_zone_write_granularity(struct block_device *bdev) return queue_zone_write_granularity(bdev_get_queue(bdev)); } -static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector) -{ - unsigned int granularity = max(lim->physical_block_size, lim->io_min); - unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT) - << SECTOR_SHIFT; - - return (granularity + lim->alignment_offset - alignment) % granularity; -} - -static inline int bdev_alignment_offset(struct block_device *bdev) -{ - struct request_queue *q = bdev_get_queue(bdev); - - if (q->limits.misaligned) - return -1; - if (bdev_is_partition(bdev)) - return queue_limit_alignment_offset(&q->limits, - bdev->bd_start_sect); - return q->limits.alignment_offset; -} +int bdev_alignment_offset(struct block_device *bdev); static inline int queue_discard_alignment(const struct request_queue *q) { -- cgit v1.2.3 From 4e1462ffe8998749884d61f91be251a7a8719677 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:50 +0200 Subject: block: remove queue_discard_alignment Just use bdev_alignment_offset in disk_discard_alignment_show instead. That helpers is the same except for an always false branch that doesn't matter in this slow path. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20220415045258.199825-20-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0a1795ac2627..5a9b7aeda010 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1253,14 +1253,6 @@ bdev_zone_write_granularity(struct block_device *bdev) int bdev_alignment_offset(struct block_device *bdev); -static inline int queue_discard_alignment(const struct request_queue *q) -{ - if (q->limits.discard_misaligned) - return -1; - - return q->limits.discard_alignment; -} - static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector) { unsigned int alignment, granularity, offset; -- cgit v1.2.3 From 5c4b4a5c6f11c869a57c6bd977143430bc9dc43d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:52 +0200 Subject: block: move {bdev,queue_limit}_discard_alignment out of line No need to inline these fairly larger helpers. Also fix the return value to be unsigned, just like the field in struct queue_limits. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20220415045258.199825-22-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 34 +--------------------------------- 1 file changed, 1 insertion(+), 33 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5a9b7aeda010..34b1cfd06742 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1252,39 +1252,7 @@ bdev_zone_write_granularity(struct block_device *bdev) } int bdev_alignment_offset(struct block_device *bdev); - -static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector) -{ - unsigned int alignment, granularity, offset; - - if (!lim->max_discard_sectors) - return 0; - - /* Why are these in bytes, not sectors? */ - alignment = lim->discard_alignment >> SECTOR_SHIFT; - granularity = lim->discard_granularity >> SECTOR_SHIFT; - if (!granularity) - return 0; - - /* Offset of the partition start in 'granularity' sectors */ - offset = sector_div(sector, granularity); - - /* And why do we do this modulus *again* in blkdev_issue_discard()? */ - offset = (granularity + alignment - offset) % granularity; - - /* Turn it back into bytes, gaah */ - return offset << SECTOR_SHIFT; -} - -static inline int bdev_discard_alignment(struct block_device *bdev) -{ - struct request_queue *q = bdev_get_queue(bdev); - - if (bdev_is_partition(bdev)) - return queue_limit_discard_alignment(&q->limits, - bdev->bd_start_sect); - return q->limits.discard_alignment; -} +unsigned int bdev_discard_alignment(struct block_device *bdev); static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { -- cgit v1.2.3 From cf0fbf894bb543f472f682c486be48298eccf199 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:54 +0200 Subject: block: add a bdev_max_discard_sectors helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a helper to query the number of sectors support per each discard bio based on the block device and use this helper to stop various places from poking into the request_queue to see if discard is supported and if so how much. This mirrors what is done e.g. for write zeroes as well. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Acked-by: Christoph Böhmwalder [drbd] Acked-by: Coly Li [bcache] Acked-by: David Sterba [btrfs] Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220415045258.199825-24-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 34b1cfd06742..ce16247d3afa 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1254,6 +1254,11 @@ bdev_zone_write_granularity(struct block_device *bdev) int bdev_alignment_offset(struct block_device *bdev); unsigned int bdev_discard_alignment(struct block_device *bdev); +static inline unsigned int bdev_max_discard_sectors(struct block_device *bdev) +{ + return bdev_get_queue(bdev)->limits.max_discard_sectors; +} + static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); -- cgit v1.2.3 From 70200574cc229f6ba038259e8142af2aa09e6976 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:55 +0200 Subject: block: remove QUEUE_FLAG_DISCARD MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Just use a non-zero max_discard_sectors as an indicator for discard support, similar to what is done for write zeroes. The only places where needs special attention is the RAID5 driver, which must clear discard support for security reasons by default, even if the default stacking rules would allow for it. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Acked-by: Christoph Böhmwalder [drbd] Acked-by: Jan Höppner [s390] Acked-by: Coly Li [bcache] Acked-by: David Sterba [btrfs] Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220415045258.199825-25-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ce16247d3afa..767ab22e1052 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -540,7 +540,6 @@ struct request_queue { #define QUEUE_FLAG_NONROT 6 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ #define QUEUE_FLAG_IO_STAT 7 /* do disk/partitions IO accounting */ -#define QUEUE_FLAG_DISCARD 8 /* supports DISCARD */ #define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ #define QUEUE_FLAG_SECERASE 11 /* supports secure erase */ @@ -582,7 +581,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags) #define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) #define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) -#define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) #define blk_queue_zone_resetall(q) \ test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags) #define blk_queue_secure_erase(q) \ -- cgit v1.2.3 From 7b47ef52d0a2025fd1408a8a0990933b8e1e510f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:56 +0200 Subject: block: add a bdev_discard_granularity helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Abstract away implementation details from file systems by providing a block_device based helper to retrieve the discard granularity. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Acked-by: Christoph Böhmwalder [drbd] Acked-by: Ryusuke Konishi Acked-by: David Sterba [btrfs] Link: https://lore.kernel.org/r/20220415045258.199825-26-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 767ab22e1052..f1cf557ea20e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1257,6 +1257,11 @@ static inline unsigned int bdev_max_discard_sectors(struct block_device *bdev) return bdev_get_queue(bdev)->limits.max_discard_sectors; } +static inline unsigned int bdev_discard_granularity(struct block_device *bdev) +{ + return bdev_get_queue(bdev)->limits.discard_granularity; +} + static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); -- cgit v1.2.3 From 44abff2c0b970ae3d310b97617525dc01f248d7c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 15 Apr 2022 06:52:57 +0200 Subject: block: decouple REQ_OP_SECURE_ERASE from REQ_OP_DISCARD MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Secure erase is a very different operation from discard in that it is a data integrity operation vs hint. Fully split the limits and helper infrastructure to make the separation more clear. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Acked-by: Christoph Böhmwalder [drbd] Acked-by: Ryusuke Konishi [nifs2] Acked-by: Jaegeuk Kim [f2fs] Acked-by: Coly Li [bcache] Acked-by: David Sterba [btrfs] Acked-by: Chao Yu Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220415045258.199825-27-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 27 ++++++++++++++++----------- 1 file changed, 16 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f1cf557ea20e..c9b5925af5a3 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -248,6 +248,7 @@ struct queue_limits { unsigned int io_opt; unsigned int max_discard_sectors; unsigned int max_hw_discard_sectors; + unsigned int max_secure_erase_sectors; unsigned int max_write_zeroes_sectors; unsigned int max_zone_append_sectors; unsigned int discard_granularity; @@ -542,7 +543,6 @@ struct request_queue { #define QUEUE_FLAG_IO_STAT 7 /* do disk/partitions IO accounting */ #define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ -#define QUEUE_FLAG_SECERASE 11 /* supports secure erase */ #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ #define QUEUE_FLAG_DEAD 13 /* queue tear-down finished */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ @@ -583,8 +583,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) #define blk_queue_zone_resetall(q) \ test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags) -#define blk_queue_secure_erase(q) \ - (test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags)) #define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) #define blk_queue_pci_p2pdma(q) \ test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags) @@ -947,6 +945,8 @@ extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_segments(struct request_queue *, unsigned short); extern void blk_queue_max_discard_segments(struct request_queue *, unsigned short); +void blk_queue_max_secure_erase_sectors(struct request_queue *q, + unsigned int max_sectors); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); @@ -1087,13 +1087,12 @@ static inline long nr_blockdev_pages(void) extern void blk_io_schedule(void); -#define BLKDEV_DISCARD_SECURE (1 << 0) /* issue a secure erase */ - -extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); -extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, int flags, - struct bio **biop); +int blkdev_issue_discard(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask); +int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, struct bio **biop); +int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp); #define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */ #define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */ @@ -1112,7 +1111,7 @@ static inline int sb_issue_discard(struct super_block *sb, sector_t block, SECTOR_SHIFT), nr_blocks << (sb->s_blocksize_bits - SECTOR_SHIFT), - gfp_mask, flags); + gfp_mask); } static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, sector_t nr_blocks, gfp_t gfp_mask) @@ -1262,6 +1261,12 @@ static inline unsigned int bdev_discard_granularity(struct block_device *bdev) return bdev_get_queue(bdev)->limits.discard_granularity; } +static inline unsigned int +bdev_max_secure_erase_sectors(struct block_device *bdev) +{ + return bdev_get_queue(bdev)->limits.max_secure_erase_sectors; +} + static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); -- cgit v1.2.3 From a2daa27c0c6137481226aee5b3136e453c642929 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 14 Feb 2022 11:44:42 +0100 Subject: swiotlb: simplify swiotlb_max_segment Remove the bogus Xen override that was usually larger than the actual size and just calculate the value on demand. Note that swiotlb_max_segment still doesn't make sense as an interface and should eventually be removed. Signed-off-by: Christoph Hellwig Reviewed-by: Anshuman Khandual Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Boris Ostrovsky --- include/linux/swiotlb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index f6c3638255d5..9fb3a568f0c5 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -164,7 +164,6 @@ static inline void swiotlb_adjust_size(unsigned long size) #endif /* CONFIG_SWIOTLB */ extern void swiotlb_print_info(void); -extern void swiotlb_set_max_segment(unsigned int); #ifdef CONFIG_DMA_RESTRICTED_POOL struct page *swiotlb_alloc(struct device *dev, size_t size); -- cgit v1.2.3 From 0d5ffd9a256d8995764f9d4a35a8c3917839d169 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 14 Feb 2022 11:07:28 +0100 Subject: swiotlb: rename swiotlb_late_init_with_default_size swiotlb_late_init_with_default_size is an overly verbose name that doesn't even catch what the function is doing, given that the size is not just a default but the actual requested size. Rename it to swiotlb_init_late. Signed-off-by: Christoph Hellwig Reviewed-by: Anshuman Khandual Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Boris Ostrovsky --- include/linux/swiotlb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 9fb3a568f0c5..b48b26bfa0ed 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -40,7 +40,7 @@ extern void swiotlb_init(int verbose); int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose); unsigned long swiotlb_size_or_default(void); extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); -extern int swiotlb_late_init_with_default_size(size_t default_size); +int swiotlb_init_late(size_t size); extern void __init swiotlb_update_mem_attributes(void); phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, -- cgit v1.2.3 From 78013eaadf696d2105982abb4018fbae394ca08f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 14 Feb 2022 14:11:44 +0100 Subject: x86: remove the IOMMU table infrastructure The IOMMU table tries to separate the different IOMMUs into different backends, but actually requires various cross calls. Rewrite the code to do the generic swiotlb/swiotlb-xen setup directly in pci-dma.c and then just call into the IOMMU drivers. Signed-off-by: Christoph Hellwig Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Boris Ostrovsky --- include/linux/dmar.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 45e903d84733..cbd714a198a0 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -121,7 +121,7 @@ extern int dmar_remove_dev_scope(struct dmar_pci_notify_info *info, u16 segment, struct dmar_dev_scope *devices, int count); /* Intel IOMMU detection */ -extern int detect_intel_iommu(void); +void detect_intel_iommu(void); extern int enable_drhd_fault_handling(void); extern int dmar_device_add(acpi_handle handle); extern int dmar_device_remove(acpi_handle handle); @@ -197,6 +197,10 @@ static inline bool dmar_platform_optin(void) return false; } +static inline void detect_intel_iommu(void) +{ +} + #endif /* CONFIG_DMAR_TABLE */ struct irte { -- cgit v1.2.3 From c6af2aa9ffc9763826607bc2664ef3ea4475ed18 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 29 Mar 2022 17:27:33 +0200 Subject: swiotlb: make the swiotlb_init interface more useful Pass a boolean flag to indicate if swiotlb needs to be enabled based on the addressing needs, and replace the verbose argument with a set of flags, including one to force enable bounce buffering. Note that this patch removes the possibility to force xen-swiotlb use with the swiotlb=force parameter on the command line on x86 (arm and arm64 never supported that), but this interface will be restored shortly. Signed-off-by: Christoph Hellwig Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Boris Ostrovsky --- include/linux/swiotlb.h | 15 +++++++-------- include/trace/events/swiotlb.h | 29 ++++++++++------------------- 2 files changed, 17 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index b48b26bfa0ed..ae0407173e84 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -13,11 +13,8 @@ struct device; struct page; struct scatterlist; -enum swiotlb_force { - SWIOTLB_NORMAL, /* Default - depending on HW DMA mask etc. */ - SWIOTLB_FORCE, /* swiotlb=force */ - SWIOTLB_NO_FORCE, /* swiotlb=noforce */ -}; +#define SWIOTLB_VERBOSE (1 << 0) /* verbose initialization */ +#define SWIOTLB_FORCE (1 << 1) /* force bounce buffering */ /* * Maximum allowable number of contiguous slabs to map, @@ -36,8 +33,7 @@ enum swiotlb_force { /* default to 64MB */ #define IO_TLB_DEFAULT_SIZE (64UL<<20) -extern void swiotlb_init(int verbose); -int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose); +int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, unsigned int flags); unsigned long swiotlb_size_or_default(void); extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); int swiotlb_init_late(size_t size); @@ -126,13 +122,16 @@ static inline bool is_swiotlb_force_bounce(struct device *dev) return mem && mem->force_bounce; } +void swiotlb_init(bool addressing_limited, unsigned int flags); void __init swiotlb_exit(void); unsigned int swiotlb_max_segment(void); size_t swiotlb_max_mapping_size(struct device *dev); bool is_swiotlb_active(struct device *dev); void __init swiotlb_adjust_size(unsigned long size); #else -#define swiotlb_force SWIOTLB_NO_FORCE +static inline void swiotlb_init(bool addressing_limited, unsigned int flags) +{ +} static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) { return false; diff --git a/include/trace/events/swiotlb.h b/include/trace/events/swiotlb.h index 705be43b71ab..da05c9ebd224 100644 --- a/include/trace/events/swiotlb.h +++ b/include/trace/events/swiotlb.h @@ -8,20 +8,15 @@ #include TRACE_EVENT(swiotlb_bounced, - - TP_PROTO(struct device *dev, - dma_addr_t dev_addr, - size_t size, - enum swiotlb_force swiotlb_force), - - TP_ARGS(dev, dev_addr, size, swiotlb_force), + TP_PROTO(struct device *dev, dma_addr_t dev_addr, size_t size), + TP_ARGS(dev, dev_addr, size), TP_STRUCT__entry( - __string( dev_name, dev_name(dev) ) - __field( u64, dma_mask ) - __field( dma_addr_t, dev_addr ) - __field( size_t, size ) - __field( enum swiotlb_force, swiotlb_force ) + __string(dev_name, dev_name(dev)) + __field(u64, dma_mask) + __field(dma_addr_t, dev_addr) + __field(size_t, size) + __field(bool, force) ), TP_fast_assign( @@ -29,19 +24,15 @@ TRACE_EVENT(swiotlb_bounced, __entry->dma_mask = (dev->dma_mask ? *dev->dma_mask : 0); __entry->dev_addr = dev_addr; __entry->size = size; - __entry->swiotlb_force = swiotlb_force; + __entry->force = is_swiotlb_force_bounce(dev); ), - TP_printk("dev_name: %s dma_mask=%llx dev_addr=%llx " - "size=%zu %s", + TP_printk("dev_name: %s dma_mask=%llx dev_addr=%llx size=%zu %s", __get_str(dev_name), __entry->dma_mask, (unsigned long long)__entry->dev_addr, __entry->size, - __print_symbolic(__entry->swiotlb_force, - { SWIOTLB_NORMAL, "NORMAL" }, - { SWIOTLB_FORCE, "FORCE" }, - { SWIOTLB_NO_FORCE, "NO_FORCE" })) + __entry->force ? "FORCE" : "NORMAL") ); #endif /* _TRACE_SWIOTLB_H */ -- cgit v1.2.3 From 8ba2ed1be90fc210126f68186564707478552c95 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 28 Feb 2022 13:36:57 +0200 Subject: swiotlb: add a SWIOTLB_ANY flag to lift the low memory restriction Power SVM wants to allocate a swiotlb buffer that is not restricted to low memory for the trusted hypervisor scheme. Consolidate the support for this into the swiotlb_init interface by adding a new flag. Signed-off-by: Christoph Hellwig Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Boris Ostrovsky --- include/linux/swiotlb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index ae0407173e84..eabdd8998702 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -15,6 +15,7 @@ struct scatterlist; #define SWIOTLB_VERBOSE (1 << 0) /* verbose initialization */ #define SWIOTLB_FORCE (1 << 1) /* force bounce buffering */ +#define SWIOTLB_ANY (1 << 2) /* allow any memory for the buffer */ /* * Maximum allowable number of contiguous slabs to map, -- cgit v1.2.3 From 742519538e6b07250c8085bbff4bd358bc03bf16 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 14 Feb 2022 11:12:59 +0100 Subject: swiotlb: pass a gfp_mask argument to swiotlb_init_late Let the caller chose a zone to allocate from. This will be used later on by the xen-swiotlb initialization on arm. Signed-off-by: Christoph Hellwig Reviewed-by: Anshuman Khandual Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Boris Ostrovsky --- include/linux/swiotlb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index eabdd8998702..ee655f2e4d28 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -37,7 +37,7 @@ struct scatterlist; int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, unsigned int flags); unsigned long swiotlb_size_or_default(void); extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); -int swiotlb_init_late(size_t size); +int swiotlb_init_late(size_t size, gfp_t gfp_mask); extern void __init swiotlb_update_mem_attributes(void); phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, -- cgit v1.2.3 From 7374153d294eb51de5a81ac38ff1c4fef8927bec Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 14 Mar 2022 08:02:57 +0100 Subject: swiotlb: provide swiotlb_init variants that remap the buffer To shared more code between swiotlb and xen-swiotlb, offer a swiotlb_init_remap interface and add a remap callback to swiotlb_init_late that will allow Xen to remap the buffer without duplicating much of the logic. Signed-off-by: Christoph Hellwig Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Boris Ostrovsky --- include/linux/swiotlb.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index ee655f2e4d28..7b50c82f84ce 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -36,8 +36,11 @@ struct scatterlist; int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, unsigned int flags); unsigned long swiotlb_size_or_default(void); +void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags, + int (*remap)(void *tlb, unsigned long nslabs)); +int swiotlb_init_late(size_t size, gfp_t gfp_mask, + int (*remap)(void *tlb, unsigned long nslabs)); extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); -int swiotlb_init_late(size_t size, gfp_t gfp_mask); extern void __init swiotlb_update_mem_attributes(void); phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, -- cgit v1.2.3 From 3f70356edf5611c28a68d8d5a9c2b442c9eb81e6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 14 Mar 2022 07:58:45 +0100 Subject: swiotlb: merge swiotlb-xen initialization into swiotlb Reuse the generic swiotlb initialization for xen-swiotlb. For ARM/ARM64 this works trivially, while for x86 xen_swiotlb_fixup needs to be passed as the remap argument to swiotlb_init_remap/swiotlb_init_late. Note that the lower bound of the swiotlb size is changed to the smaller IO_TLB_MIN_SLABS based value with this patch, but that is fine as the 2MB value used in Xen before was just an optimization and is not the hard lower bound. Signed-off-by: Christoph Hellwig Reviewed-by: Stefano Stabellini Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Boris Ostrovsky --- include/xen/arm/page.h | 1 - include/xen/swiotlb-xen.h | 8 ++++++-- 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/xen/arm/page.h b/include/xen/arm/page.h index ac1b65470563..7e199c6656b9 100644 --- a/include/xen/arm/page.h +++ b/include/xen/arm/page.h @@ -115,6 +115,5 @@ static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) bool xen_arch_need_swiotlb(struct device *dev, phys_addr_t phys, dma_addr_t dev_addr); -unsigned long xen_get_swiotlb_free_pages(unsigned int order); #endif /* _ASM_ARM_XEN_PAGE_H */ diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h index b3e647f86e3e..590ceb923f0c 100644 --- a/include/xen/swiotlb-xen.h +++ b/include/xen/swiotlb-xen.h @@ -10,8 +10,12 @@ void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle, void xen_dma_sync_for_device(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir); -int xen_swiotlb_init(void); -void __init xen_swiotlb_init_early(void); +#ifdef CONFIG_SWIOTLB_XEN +int xen_swiotlb_fixup(void *buf, unsigned long nslabs); +#else +#define xen_swiotlb_fixup NULL +#endif + extern const struct dma_map_ops xen_swiotlb_dma_ops; #endif /* __LINUX_SWIOTLB_XEN_H */ -- cgit v1.2.3 From 6424e31b1c050a25aea033206d5f626f3523448c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 15 Mar 2022 07:41:04 +0100 Subject: swiotlb: remove swiotlb_init_with_tbl and swiotlb_init_late_with_tbl No users left. Signed-off-by: Christoph Hellwig Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Boris Ostrovsky --- include/linux/swiotlb.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 7b50c82f84ce..7ed35dd3de6e 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -34,13 +34,11 @@ struct scatterlist; /* default to 64MB */ #define IO_TLB_DEFAULT_SIZE (64UL<<20) -int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, unsigned int flags); unsigned long swiotlb_size_or_default(void); void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags, int (*remap)(void *tlb, unsigned long nslabs)); int swiotlb_init_late(size_t size, gfp_t gfp_mask, int (*remap)(void *tlb, unsigned long nslabs)); -extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); extern void __init swiotlb_update_mem_attributes(void); phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, -- cgit v1.2.3 From 964320cb45eecdcd0bd322896593bf805d8b3711 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:13 +0200 Subject: media: dvb-usb-ids.h: sort entries The entries there are alphabetically sorted, but some are at the wrong place. Re-sort them. While here, replace spaces by tabs where needed. Link: https://lore.kernel.org/linux-media/0208dbba189b754b999759f06c2584242c879f4d.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 591 ++++++++++++++++++++++---------------------- 1 file changed, 297 insertions(+), 294 deletions(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index b0a535d6893a..dcf5772c84a0 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -11,80 +11,74 @@ #define _DVB_USB_IDS_H_ /* Vendor IDs */ -#define USB_VID_ADSTECH 0x06e1 -#define USB_VID_AFATECH 0x15a4 + +#define USB_VID_774 0x7a69 +#define USB_VID_ADSTECH 0x06e1 +#define USB_VID_AFATECH 0x15a4 #define USB_VID_ALCOR_MICRO 0x058f #define USB_VID_ALINK 0x05e3 #define USB_VID_AMT 0x1c73 #define USB_VID_ANCHOR 0x0547 -#define USB_VID_ANSONIC 0x10b9 +#define USB_VID_ANSONIC 0x10b9 #define USB_VID_ANUBIS_ELECTRONIC 0x10fd #define USB_VID_ASUS 0x0b05 #define USB_VID_AVERMEDIA 0x07ca +#define USB_VID_AZUREWAVE 0x13d3 #define USB_VID_COMPRO 0x185b #define USB_VID_COMPRO_UNK 0x145f #define USB_VID_CONEXANT 0x0572 -#define USB_VID_CYPRESS 0x04b4 -#define USB_VID_DEXATEK 0x1d19 +#define USB_VID_CYPRESS 0x04b4 +#define USB_VID_DEXATEK 0x1d19 #define USB_VID_DIBCOM 0x10b8 #define USB_VID_DPOSH 0x1498 #define USB_VID_DVICO 0x0fe9 #define USB_VID_E3C 0x18b4 #define USB_VID_ELGATO 0x0fd9 #define USB_VID_EMPIA 0xeb1a +#define USB_VID_EVOLUTEPC 0x1e59 #define USB_VID_GENPIX 0x09c0 +#define USB_VID_GIGABYTE 0x1044 #define USB_VID_GRANDTEC 0x5032 #define USB_VID_GTEK 0x1f4d -#define USB_VID_HANFTEK 0x15f4 +#define USB_VID_HAMA 0x147f +#define USB_VID_HANFTEK 0x15f4 #define USB_VID_HAUPPAUGE 0x2040 +#define USB_VID_HUMAX_COEX 0x10b9 #define USB_VID_HYPER_PALTEK 0x1025 #define USB_VID_INTEL 0x8086 -#define USB_VID_ITETECH 0x048d +#define USB_VID_ITETECH 0x048d #define USB_VID_KWORLD 0xeb2a #define USB_VID_KWORLD_2 0x1b80 #define USB_VID_KYE 0x0458 -#define USB_VID_LEADTEK 0x0413 +#define USB_VID_LEADTEK 0x0413 #define USB_VID_LITEON 0x04ca #define USB_VID_MEDION 0x1660 +#define USB_VID_MICROSOFT 0x045e #define USB_VID_MIGLIA 0x18f3 #define USB_VID_MSI 0x0db0 #define USB_VID_MSI_2 0x1462 #define USB_VID_OPERA1 0x695c -#define USB_VID_PINNACLE 0x2304 #define USB_VID_PCTV 0x2013 +#define USB_VID_PINNACLE 0x2304 #define USB_VID_PIXELVIEW 0x1554 -#define USB_VID_REALTEK 0x0bda +#define USB_VID_REALTEK 0x0bda +#define USB_VID_SONY 0x1415 +#define USB_VID_TECHNISAT 0x14f7 #define USB_VID_TECHNOTREND 0x0b48 +#define USB_VID_TELESTAR 0x10b9 #define USB_VID_TERRATEC 0x0ccd #define USB_VID_TERRATEC_2 0x153b -#define USB_VID_TELESTAR 0x10b9 -#define USB_VID_VISIONPLUS 0x13d3 -#define USB_VID_SONY 0x1415 -#define USB_PID_TEVII_S421 0xd421 -#define USB_PID_TEVII_S480_1 0xd481 -#define USB_PID_TEVII_S480_2 0xd482 -#define USB_PID_TEVII_S630 0xd630 -#define USB_PID_TEVII_S632 0xd632 -#define USB_PID_TEVII_S650 0xd650 -#define USB_PID_TEVII_S660 0xd660 -#define USB_PID_TEVII_S662 0xd662 -#define USB_VID_TWINHAN 0x1822 +#define USB_VID_TWINHAN 0x1822 #define USB_VID_ULTIMA_ELECTRONIC 0x05d8 -#define USB_VID_UNIWILL 0x1584 +#define USB_VID_UNIWILL 0x1584 +#define USB_VID_VISIONPLUS 0x13d3 #define USB_VID_WIDEVIEW 0x14aa -#define USB_VID_GIGABYTE 0x1044 -#define USB_VID_YUAN 0x1164 #define USB_VID_XTENSIONS 0x1ae7 +#define USB_VID_YUAN 0x1164 #define USB_VID_ZYDAS 0x0ace -#define USB_VID_HUMAX_COEX 0x10b9 -#define USB_VID_774 0x7a69 -#define USB_VID_EVOLUTEPC 0x1e59 -#define USB_VID_AZUREWAVE 0x13d3 -#define USB_VID_TECHNISAT 0x14f7 -#define USB_VID_HAMA 0x147f -#define USB_VID_MICROSOFT 0x045e /* Product IDs */ + #define USB_PID_ADSTECH_USB2_COLD 0xa333 #define USB_PID_ADSTECH_USB2_WARM 0xa334 #define USB_PID_AFATECH_AF9005 0x9020 @@ -95,341 +89,350 @@ #define USB_PID_AFATECH_AF9035_1002 0x1002 #define USB_PID_AFATECH_AF9035_1003 0x1003 #define USB_PID_AFATECH_AF9035_9035 0x9035 -#define USB_PID_TREKSTOR_DVBT 0x901b -#define USB_PID_TREKSTOR_TERRES_2_0 0xC803 #define USB_PID_ALINK_DTU 0xf170 #define USB_PID_ANSONIC_DVBT_USB 0x6000 #define USB_PID_ANYSEE 0x861f -#define USB_PID_AZUREWAVE_AD_TU700 0x3237 -#define USB_PID_AZUREWAVE_6007 0x0ccd -#define USB_PID_AVERMEDIA_DVBT_USB_COLD 0x0001 -#define USB_PID_AVERMEDIA_DVBT_USB_WARM 0x0002 +#define USB_PID_ARTEC_T14BR 0x810f +#define USB_PID_ARTEC_T14_COLD 0x810b +#define USB_PID_ARTEC_T14_WARM 0x810c +#define USB_PID_ASUS_U3000 0x171f +#define USB_PID_ASUS_U3000H 0x1736 +#define USB_PID_ASUS_U3100 0x173f +#define USB_PID_ASUS_U3100MINI_PLUS 0x1779 +#define USB_PID_AVERMEDIA_1867 0x1867 +#define USB_PID_AVERMEDIA_A309 0xa309 +#define USB_PID_AVERMEDIA_A310 0xa310 +#define USB_PID_AVERMEDIA_A805 0xa805 +#define USB_PID_AVERMEDIA_A815M 0x815a +#define USB_PID_AVERMEDIA_A835 0xa835 +#define USB_PID_AVERMEDIA_A835B_1835 0x1835 +#define USB_PID_AVERMEDIA_A835B_2835 0x2835 +#define USB_PID_AVERMEDIA_A835B_3835 0x3835 +#define USB_PID_AVERMEDIA_A835B_4835 0x4835 +#define USB_PID_AVERMEDIA_A850 0x850a +#define USB_PID_AVERMEDIA_A850T 0x850b +#define USB_PID_AVERMEDIA_A867 0xa867 +#define USB_PID_AVERMEDIA_B835 0xb835 #define USB_PID_AVERMEDIA_DVBT_USB2_COLD 0xa800 #define USB_PID_AVERMEDIA_DVBT_USB2_WARM 0xa801 +#define USB_PID_AVERMEDIA_DVBT_USB_COLD 0x0001 +#define USB_PID_AVERMEDIA_DVBT_USB_WARM 0x0002 +#define USB_PID_AVERMEDIA_EXPRESS 0xb568 +#define USB_PID_AVERMEDIA_H335 0x0335 +#define USB_PID_AVERMEDIA_HYBRID_ULTRA_USB_M039R 0x0039 +#define USB_PID_AVERMEDIA_HYBRID_ULTRA_USB_M039R_ATSC 0x1039 +#define USB_PID_AVERMEDIA_HYBRID_ULTRA_USB_M039R_DVBT 0x2039 +#define USB_PID_AVERMEDIA_MCE_USB_M038 0x1228 +#define USB_PID_AVERMEDIA_TD110 0xa110 +#define USB_PID_AVERMEDIA_TD310 0x1871 +#define USB_PID_AVERMEDIA_TWINSTAR 0x0825 +#define USB_PID_AVERMEDIA_VOLAR 0xa807 +#define USB_PID_AVERMEDIA_VOLAR_2 0xb808 +#define USB_PID_AVERMEDIA_VOLAR_A868R 0xa868 +#define USB_PID_AVERMEDIA_VOLAR_X 0xa815 +#define USB_PID_AVERMEDIA_VOLAR_X_2 0x8150 +#define USB_PID_AZUREWAVE_6007 0x0ccd +#define USB_PID_AZUREWAVE_AD_TU700 0x3237 +#define USB_PID_AZUREWAVE_AZ6027 0x3275 #define USB_PID_COMPRO_DVBU2000_COLD 0xd000 -#define USB_PID_COMPRO_DVBU2000_WARM 0xd001 #define USB_PID_COMPRO_DVBU2000_UNK_COLD 0x010c #define USB_PID_COMPRO_DVBU2000_UNK_WARM 0x010d +#define USB_PID_COMPRO_DVBU2000_WARM 0xd001 #define USB_PID_COMPRO_VIDEOMATE_U500 0x1e78 #define USB_PID_COMPRO_VIDEOMATE_U500_PC 0x1e80 #define USB_PID_CONCEPTRONIC_CTVDIGRCU 0xe397 #define USB_PID_CONEXANT_D680_DMB 0x86d6 -#define USB_PID_CREATIX_CTX1921 0x1921 +#define USB_PID_CPYTO_REDI_PC50A 0xa803 +#define USB_PID_CREATIX_CTX1921 0x1921 +#define USB_PID_CTVDIGDUAL_V2 0xe410 #define USB_PID_DELOCK_USB2_DVBT 0xb803 +#define USB_PID_DIBCOM_ANCHOR_2135_COLD 0x2131 #define USB_PID_DIBCOM_HOOK_DEFAULT 0x0064 #define USB_PID_DIBCOM_HOOK_DEFAULT_REENUM 0x0065 #define USB_PID_DIBCOM_MOD3000_COLD 0x0bb8 #define USB_PID_DIBCOM_MOD3000_WARM 0x0bb9 #define USB_PID_DIBCOM_MOD3001_COLD 0x0bc6 #define USB_PID_DIBCOM_MOD3001_WARM 0x0bc7 -#define USB_PID_DIBCOM_STK7700P 0x1e14 +#define USB_PID_DIBCOM_NIM7090 0x1bb2 +#define USB_PID_DIBCOM_NIM8096MD 0x1fa8 +#define USB_PID_DIBCOM_NIM9090M 0x2383 +#define USB_PID_DIBCOM_NIM9090MD 0x2384 +#define USB_PID_DIBCOM_STK7070P 0x1ebc +#define USB_PID_DIBCOM_STK7070PD 0x1ebe +#define USB_PID_DIBCOM_STK7700D 0x1ef0 +#define USB_PID_DIBCOM_STK7700P 0x1e14 #define USB_PID_DIBCOM_STK7700P_PC 0x1e78 -#define USB_PID_DIBCOM_STK7700D 0x1ef0 #define USB_PID_DIBCOM_STK7700_U7000 0x7001 -#define USB_PID_DIBCOM_STK7070P 0x1ebc -#define USB_PID_DIBCOM_STK7070PD 0x1ebe -#define USB_PID_DIBCOM_STK807XP 0x1f90 +#define USB_PID_DIBCOM_STK7770P 0x1e80 +#define USB_PID_DIBCOM_STK807XP 0x1f90 #define USB_PID_DIBCOM_STK807XPVR 0x1f98 -#define USB_PID_DIBCOM_STK8096GP 0x1fa0 -#define USB_PID_DIBCOM_STK8096PVR 0x1faa -#define USB_PID_DIBCOM_NIM8096MD 0x1fa8 -#define USB_PID_DIBCOM_TFE8096P 0x1f9C -#define USB_PID_DIBCOM_ANCHOR_2135_COLD 0x2131 -#define USB_PID_DIBCOM_STK7770P 0x1e80 -#define USB_PID_DIBCOM_NIM7090 0x1bb2 +#define USB_PID_DIBCOM_STK8096GP 0x1fa0 +#define USB_PID_DIBCOM_STK8096PVR 0x1faa #define USB_PID_DIBCOM_TFE7090PVR 0x1bb4 -#define USB_PID_DIBCOM_TFE7790P 0x1e6e -#define USB_PID_DIBCOM_NIM9090M 0x2383 -#define USB_PID_DIBCOM_NIM9090MD 0x2384 +#define USB_PID_DIBCOM_TFE7790P 0x1e6e +#define USB_PID_DIBCOM_TFE8096P 0x1f9C +#define USB_PID_DIGITALNOW_BLUEBIRD_DUAL_1_COLD 0xdb54 +#define USB_PID_DIGITALNOW_BLUEBIRD_DUAL_1_WARM 0xdb55 +#define USB_PID_DIGIVOX_MINI_SL_COLD 0xe360 +#define USB_PID_DIGIVOX_MINI_SL_WARM 0xe361 +#define USB_PID_DNTV_TINYUSB2_COLD 0x3223 +#define USB_PID_DNTV_TINYUSB2_WARM 0x3224 #define USB_PID_DPOSH_M9206_COLD 0x9206 #define USB_PID_DPOSH_M9206_WARM 0xa090 +#define USB_PID_DTT200U_COLD 0x0201 +#define USB_PID_DTT200U_WARM 0x0301 +#define USB_PID_DVB_T_USB_STICK_HIGH_SPEED_COLD 0x5000 +#define USB_PID_DVB_T_USB_STICK_HIGH_SPEED_WARM 0x5001 +#define USB_PID_DVICO_BLUEBIRD_DUAL_1_COLD 0xdb50 +#define USB_PID_DVICO_BLUEBIRD_DUAL_1_WARM 0xdb51 +#define USB_PID_DVICO_BLUEBIRD_DUAL_2_COLD 0xdb58 +#define USB_PID_DVICO_BLUEBIRD_DUAL_2_WARM 0xdb59 +#define USB_PID_DVICO_BLUEBIRD_DUAL_4 0xdb78 +#define USB_PID_DVICO_BLUEBIRD_DUAL_4_REV_2 0xdb98 +#define USB_PID_DVICO_BLUEBIRD_DVB_T_NANO_2 0xdb70 +#define USB_PID_DVICO_BLUEBIRD_DVB_T_NANO_2_NFW_WARM 0xdb71 +#define USB_PID_DVICO_BLUEBIRD_LG064F_COLD 0xd500 +#define USB_PID_DVICO_BLUEBIRD_LG064F_WARM 0xd501 +#define USB_PID_DVICO_BLUEBIRD_LGDT 0xd820 +#define USB_PID_DVICO_BLUEBIRD_LGZ201_COLD 0xdb00 +#define USB_PID_DVICO_BLUEBIRD_LGZ201_WARM 0xdb01 +#define USB_PID_DVICO_BLUEBIRD_TH7579_COLD 0xdb10 +#define USB_PID_DVICO_BLUEBIRD_TH7579_WARM 0xdb11 +#define USB_PID_DW2102 0x2102 +#define USB_PID_DW2104 0x2104 +#define USB_PID_DW3101 0x3101 #define USB_PID_E3C_EC168 0x1689 #define USB_PID_E3C_EC168_2 0xfffa #define USB_PID_E3C_EC168_3 0xfffb #define USB_PID_E3C_EC168_4 0x1001 #define USB_PID_E3C_EC168_5 0x1002 +#define USB_PID_ELGATO_EYETV_DIVERSITY 0x0011 +#define USB_PID_ELGATO_EYETV_DTT 0x0021 +#define USB_PID_ELGATO_EYETV_DTT_2 0x003f +#define USB_PID_ELGATO_EYETV_DTT_Dlx 0x0020 +#define USB_PID_ELGATO_EYETV_SAT 0x002a +#define USB_PID_ELGATO_EYETV_SAT_V2 0x0025 +#define USB_PID_ELGATO_EYETV_SAT_V3 0x0036 +#define USB_PID_EVOLVEO_XTRATV_STICK 0xa115 #define USB_PID_FREECOM_DVBT 0x0160 #define USB_PID_FREECOM_DVBT_2 0x0161 -#define USB_PID_UNIWILL_STK7700P 0x6003 +#define USB_PID_FRIIO_WHITE 0x0001 #define USB_PID_GENIUS_TVGO_DVB_T03 0x4012 +#define USB_PID_GENPIX_8PSK_REV_1_COLD 0x0200 +#define USB_PID_GENPIX_8PSK_REV_1_WARM 0x0201 +#define USB_PID_GENPIX_8PSK_REV_2 0x0202 +#define USB_PID_GENPIX_SKYWALKER_1 0x0203 +#define USB_PID_GENPIX_SKYWALKER_2 0x0206 +#define USB_PID_GENPIX_SKYWALKER_CW3K 0x0204 +#define USB_PID_GIGABYTE_U7000 0x7001 +#define USB_PID_GIGABYTE_U8000 0x7002 +#define USB_PID_GOTVIEW_SAT_HD 0x5456 +#define USB_PID_GRANDTEC_DVBT_USB2_COLD 0x0bc6 +#define USB_PID_GRANDTEC_DVBT_USB2_WARM 0x0bc7 #define USB_PID_GRANDTEC_DVBT_USB_COLD 0x0fa0 #define USB_PID_GRANDTEC_DVBT_USB_WARM 0x0fa1 -#define USB_PID_GOTVIEW_SAT_HD 0x5456 +#define USB_PID_HAMA_DVBT_HYBRID 0x2758 +#define USB_PID_HANFTEK_UMT_010_COLD 0x0001 +#define USB_PID_HANFTEK_UMT_010_WARM 0x0015 +#define USB_PID_HAUPPAUGE_MYTV_T 0x7080 +#define USB_PID_HAUPPAUGE_NOVA_TD_STICK 0x9580 +#define USB_PID_HAUPPAUGE_NOVA_TD_STICK_52009 0x5200 +#define USB_PID_HAUPPAUGE_NOVA_T_500 0x9941 +#define USB_PID_HAUPPAUGE_NOVA_T_500_2 0x9950 +#define USB_PID_HAUPPAUGE_NOVA_T_500_3 0x8400 +#define USB_PID_HAUPPAUGE_NOVA_T_STICK 0x7050 +#define USB_PID_HAUPPAUGE_NOVA_T_STICK_2 0x7060 +#define USB_PID_HAUPPAUGE_NOVA_T_STICK_3 0x7070 +#define USB_PID_HAUPPAUGE_TIGER_ATSC 0xb200 +#define USB_PID_HAUPPAUGE_TIGER_ATSC_B210 0xb210 #define USB_PID_INTEL_CE9500 0x9500 #define USB_PID_ITETECH_IT9135 0x9135 #define USB_PID_ITETECH_IT9135_9005 0x9005 #define USB_PID_ITETECH_IT9135_9006 0x9006 #define USB_PID_ITETECH_IT9303 0x9306 -#define USB_PID_KWORLD_399U 0xe399 -#define USB_PID_KWORLD_399U_2 0xe400 #define USB_PID_KWORLD_395U 0xe396 #define USB_PID_KWORLD_395U_2 0xe39b #define USB_PID_KWORLD_395U_3 0xe395 #define USB_PID_KWORLD_395U_4 0xe39a +#define USB_PID_KWORLD_399U 0xe399 +#define USB_PID_KWORLD_399U_2 0xe400 #define USB_PID_KWORLD_MC810 0xc810 -#define USB_PID_KWORLD_PC160_2T 0xc160 +#define USB_PID_KWORLD_PC160_2T 0xc160 #define USB_PID_KWORLD_PC160_T 0xc161 #define USB_PID_KWORLD_UB383_T 0xe383 #define USB_PID_KWORLD_UB499_2T_T09 0xe409 #define USB_PID_KWORLD_VSTREAM_COLD 0x17de #define USB_PID_KWORLD_VSTREAM_WARM 0x17df +#define USB_PID_KYE_DVB_T_COLD 0x701e +#define USB_PID_KYE_DVB_T_WARM 0x701f +#define USB_PID_LIFEVIEW_TV_WALKER_TWIN_COLD 0x0514 +#define USB_PID_LIFEVIEW_TV_WALKER_TWIN_WARM 0x0513 +#define USB_PID_LITEON_DVB_T_COLD 0xf000 +#define USB_PID_LITEON_DVB_T_WARM 0xf001 +#define USB_PID_MEDION_MD95700 0x0932 +#define USB_PID_MSI_DIGIVOX_DUO 0x8801 +#define USB_PID_MSI_DIGI_VOX_MINI_II 0x1513 +#define USB_PID_MSI_DIGI_VOX_MINI_III 0x8807 +#define USB_PID_MSI_MEGASKY580 0x5580 +#define USB_PID_MSI_MEGASKY580_55801 0x5581 +#define USB_PID_MYGICA_D689 0xd811 +#define USB_PID_MYGICA_T230 0xc688 +#define USB_PID_MYGICA_T230A 0x689a +#define USB_PID_MYGICA_T230C 0xc689 +#define USB_PID_MYGICA_T230C2 0xc68a +#define USB_PID_MYGICA_T230C2_LITE 0xc69a +#define USB_PID_MYGICA_T230C_LITE 0xc699 +#define USB_PID_NEBULA_DIGITV 0x0201 +#define USB_PID_NOXON_DAB_STICK 0x00b3 +#define USB_PID_NOXON_DAB_STICK_REV2 0x00e0 +#define USB_PID_NOXON_DAB_STICK_REV3 0x00b4 +#define USB_PID_OPERA1_COLD 0x2830 +#define USB_PID_OPERA1_WARM 0x3829 +#define USB_PID_PCTV_2002E 0x025c +#define USB_PID_PCTV_2002E_SE 0x025d +#define USB_PID_PCTV_200E 0x020e +#define USB_PID_PCTV_400E 0x020f +#define USB_PID_PCTV_450E 0x0222 +#define USB_PID_PCTV_452E 0x021f +#define USB_PID_PCTV_78E 0x025a +#define USB_PID_PCTV_79E 0x0262 +#define USB_PID_PINNACLE_EXPRESSCARD_320CX 0x022e +#define USB_PID_PINNACLE_PCTV2000E 0x022c +#define USB_PID_PINNACLE_PCTV282E 0x0248 +#define USB_PID_PINNACLE_PCTV310E 0x3211 +#define USB_PID_PINNACLE_PCTV340E 0x023d +#define USB_PID_PINNACLE_PCTV340E_SE 0x023e +#define USB_PID_PINNACLE_PCTV71E 0x022b +#define USB_PID_PINNACLE_PCTV72E 0x0236 +#define USB_PID_PINNACLE_PCTV73A 0x0243 +#define USB_PID_PINNACLE_PCTV73E 0x0237 +#define USB_PID_PINNACLE_PCTV73ESE 0x0245 +#define USB_PID_PINNACLE_PCTV74E 0x0246 +#define USB_PID_PINNACLE_PCTV801E 0x023a +#define USB_PID_PINNACLE_PCTV801E_SE 0x023b +#define USB_PID_PINNACLE_PCTV_DUAL_DIVERSITY_DVB_T 0x0229 +#define USB_PID_PINNACLE_PCTV_DVB_T_FLASH 0x0228 +#define USB_PID_PIXELVIEW_SBTVD 0x5010 #define USB_PID_PROF_1100 0xb012 +#define USB_PID_PROLECTRIX_DV107669 0xd803 +#define USB_PID_REALTEK_RTL2831U 0x2831 +#define USB_PID_REALTEK_RTL2832U 0x2832 +#define USB_PID_SIGMATEK_DVB_110 0x6610 +#define USB_PID_SONY_PLAYTV 0x0003 +#define USB_PID_SVEON_STV20 0xe39d +#define USB_PID_SVEON_STV20_RTL2832U 0xd39d +#define USB_PID_SVEON_STV21 0xd3b0 +#define USB_PID_SVEON_STV22 0xe401 +#define USB_PID_SVEON_STV22_IT9137 0xe411 +#define USB_PID_SVEON_STV27 0xd3af +#define USB_PID_TECHNISAT_AIRSTAR_TELESTICK_2 0x0004 +#define USB_PID_TECHNISAT_USB2_CABLESTAR_HDCI 0x0003 +#define USB_PID_TECHNISAT_USB2_DVB_S2 0x0500 +#define USB_PID_TECHNISAT_USB2_HDCI_V1 0x0001 +#define USB_PID_TECHNISAT_USB2_HDCI_V2 0x0002 +#define USB_PID_TECHNOTREND_CONNECT_CT2_4650_CI 0x3012 +#define USB_PID_TECHNOTREND_CONNECT_CT2_4650_CI_2 0x3015 +#define USB_PID_TECHNOTREND_CONNECT_CT3650 0x300d +#define USB_PID_TECHNOTREND_CONNECT_S2400 0x3006 +#define USB_PID_TECHNOTREND_CONNECT_S2400_8KEEPROM 0x3009 +#define USB_PID_TECHNOTREND_CONNECT_S2_3600 0x3007 +#define USB_PID_TECHNOTREND_CONNECT_S2_3650_CI 0x300a +#define USB_PID_TECHNOTREND_CONNECT_S2_4600 0x3011 +#define USB_PID_TECHNOTREND_CONNECT_S2_4650_CI 0x3017 +#define USB_PID_TECHNOTREND_TVSTICK_CT2_4400 0x3014 +#define USB_PID_TELESTAR_STARSTICK_2 0x8000 +#define USB_PID_TERRATEC_CINERGY_DT_XS_DIVERSITY 0x005a +#define USB_PID_TERRATEC_CINERGY_DT_XS_DIVERSITY_2 0x0081 +#define USB_PID_TERRATEC_CINERGY_HT_EXPRESS 0x0060 +#define USB_PID_TERRATEC_CINERGY_HT_USB_XE 0x0058 #define USB_PID_TERRATEC_CINERGY_S 0x0064 -#define USB_PID_TERRATEC_CINERGY_T_USB_XE 0x0055 -#define USB_PID_TERRATEC_CINERGY_T_USB_XE_REV2 0x0069 +#define USB_PID_TERRATEC_CINERGY_S2_1 0x1181 +#define USB_PID_TERRATEC_CINERGY_S2_2 0x1182 +#define USB_PID_TERRATEC_CINERGY_S2_R1 0x00a8 +#define USB_PID_TERRATEC_CINERGY_S2_R2 0x00b0 +#define USB_PID_TERRATEC_CINERGY_S2_R3 0x0102 +#define USB_PID_TERRATEC_CINERGY_S2_R4 0x0105 +#define USB_PID_TERRATEC_CINERGY_TC2_STICK 0x10b2 +#define USB_PID_TERRATEC_CINERGY_T_EXPRESS 0x0062 #define USB_PID_TERRATEC_CINERGY_T_STICK 0x0093 -#define USB_PID_TERRATEC_CINERGY_T_STICK_RC 0x0097 -#define USB_PID_TERRATEC_CINERGY_T_STICK_DUAL_RC 0x0099 #define USB_PID_TERRATEC_CINERGY_T_STICK_BLACK_REV1 0x00a9 -#define USB_PID_TERRATEC_CINERGY_TC2_STICK 0x10b2 -#define USB_PID_TWINHAN_VP7041_COLD 0x3201 -#define USB_PID_TWINHAN_VP7041_WARM 0x3202 +#define USB_PID_TERRATEC_CINERGY_T_STICK_DUAL_RC 0x0099 +#define USB_PID_TERRATEC_CINERGY_T_STICK_RC 0x0097 +#define USB_PID_TERRATEC_CINERGY_T_USB_XE 0x0055 +#define USB_PID_TERRATEC_CINERGY_T_USB_XE_REV2 0x0069 +#define USB_PID_TERRATEC_CINERGY_T_XXS 0x0078 +#define USB_PID_TERRATEC_CINERGY_T_XXS_2 0x00ab +#define USB_PID_TERRATEC_DVBS2CI_V1 0x10a4 +#define USB_PID_TERRATEC_DVBS2CI_V2 0x10ac +#define USB_PID_TERRATEC_H7 0x10b4 +#define USB_PID_TERRATEC_H7_2 0x10a3 +#define USB_PID_TERRATEC_H7_3 0x10a5 +#define USB_PID_TERRATEC_T1 0x10ae +#define USB_PID_TERRATEC_T3 0x10a0 +#define USB_PID_TERRATEC_T5 0x10a1 +#define USB_PID_TEVII_S421 0xd421 +#define USB_PID_TEVII_S480_1 0xd481 +#define USB_PID_TEVII_S480_2 0xd482 +#define USB_PID_TEVII_S630 0xd630 +#define USB_PID_TEVII_S632 0xd632 +#define USB_PID_TEVII_S650 0xd650 +#define USB_PID_TEVII_S660 0xd660 +#define USB_PID_TEVII_S662 0xd662 +#define USB_PID_TINYTWIN 0x3226 +#define USB_PID_TINYTWIN_2 0xe402 +#define USB_PID_TINYTWIN_3 0x9016 +#define USB_PID_TREKSTOR_DVBT 0x901b +#define USB_PID_TREKSTOR_TERRES_2_0 0xC803 +#define USB_PID_TURBOX_DTT_2000 0xd3a4 +#define USB_PID_TVWAY_PLUS 0x0002 #define USB_PID_TWINHAN_VP7020_COLD 0x3203 #define USB_PID_TWINHAN_VP7020_WARM 0x3204 -#define USB_PID_TWINHAN_VP7045_COLD 0x3205 -#define USB_PID_TWINHAN_VP7045_WARM 0x3206 #define USB_PID_TWINHAN_VP7021_COLD 0x3207 #define USB_PID_TWINHAN_VP7021_WARM 0x3208 +#define USB_PID_TWINHAN_VP7041_COLD 0x3201 +#define USB_PID_TWINHAN_VP7041_WARM 0x3202 +#define USB_PID_TWINHAN_VP7045_COLD 0x3205 +#define USB_PID_TWINHAN_VP7045_WARM 0x3206 #define USB_PID_TWINHAN_VP7049 0x3219 -#define USB_PID_TINYTWIN 0x3226 -#define USB_PID_TINYTWIN_2 0xe402 -#define USB_PID_TINYTWIN_3 0x9016 -#define USB_PID_DNTV_TINYUSB2_COLD 0x3223 -#define USB_PID_DNTV_TINYUSB2_WARM 0x3224 -#define USB_PID_ULTIMA_TVBOX_COLD 0x8105 -#define USB_PID_ULTIMA_TVBOX_WARM 0x8106 #define USB_PID_ULTIMA_TVBOX_AN2235_COLD 0x8107 #define USB_PID_ULTIMA_TVBOX_AN2235_WARM 0x8108 #define USB_PID_ULTIMA_TVBOX_ANCHOR_COLD 0x2235 +#define USB_PID_ULTIMA_TVBOX_COLD 0x8105 #define USB_PID_ULTIMA_TVBOX_USB2_COLD 0x8109 -#define USB_PID_ULTIMA_TVBOX_USB2_WARM 0x810a -#define USB_PID_ARTEC_T14_COLD 0x810b -#define USB_PID_ARTEC_T14_WARM 0x810c -#define USB_PID_ARTEC_T14BR 0x810f #define USB_PID_ULTIMA_TVBOX_USB2_FX_COLD 0x8613 #define USB_PID_ULTIMA_TVBOX_USB2_FX_WARM 0x1002 +#define USB_PID_ULTIMA_TVBOX_USB2_WARM 0x810a +#define USB_PID_ULTIMA_TVBOX_WARM 0x8106 +#define USB_PID_UNIWILL_STK7700P 0x6003 #define USB_PID_UNK_HYPER_PALTEK_COLD 0x005e #define USB_PID_UNK_HYPER_PALTEK_WARM 0x005f -#define USB_PID_HANFTEK_UMT_010_COLD 0x0001 -#define USB_PID_HANFTEK_UMT_010_WARM 0x0015 -#define USB_PID_DTT200U_COLD 0x0201 -#define USB_PID_DTT200U_WARM 0x0301 -#define USB_PID_WT220U_ZAP250_COLD 0x0220 +#define USB_PID_WINFAST_DTV2000DS 0x6a04 +#define USB_PID_WINFAST_DTV2000DS_PLUS 0x6f12 +#define USB_PID_WINFAST_DTV_DONGLE_COLD 0x6025 +#define USB_PID_WINFAST_DTV_DONGLE_GOLD 0x6029 +#define USB_PID_WINFAST_DTV_DONGLE_H 0x60f6 +#define USB_PID_WINFAST_DTV_DONGLE_MINID 0x6f0f +#define USB_PID_WINFAST_DTV_DONGLE_STK7700P 0x6f00 +#define USB_PID_WINFAST_DTV_DONGLE_STK7700P_2 0x6f01 +#define USB_PID_WINFAST_DTV_DONGLE_WARM 0x6026 +#define USB_PID_WINTV_NOVA_T_USB2_COLD 0x9300 +#define USB_PID_WINTV_NOVA_T_USB2_WARM 0x9301 +#define USB_PID_WINTV_SOLOHD 0x0264 +#define USB_PID_WINTV_SOLOHD_2 0x8268 #define USB_PID_WT220U_COLD 0x0222 -#define USB_PID_WT220U_WARM 0x0221 #define USB_PID_WT220U_FC_COLD 0x0225 #define USB_PID_WT220U_FC_WARM 0x0226 +#define USB_PID_WT220U_WARM 0x0221 +#define USB_PID_WT220U_ZAP250_COLD 0x0220 #define USB_PID_WT220U_ZL0353_COLD 0x022a #define USB_PID_WT220U_ZL0353_WARM 0x022b -#define USB_PID_WINTV_NOVA_T_USB2_COLD 0x9300 -#define USB_PID_WINTV_NOVA_T_USB2_WARM 0x9301 -#define USB_PID_HAUPPAUGE_NOVA_T_500 0x9941 -#define USB_PID_HAUPPAUGE_NOVA_T_500_2 0x9950 -#define USB_PID_HAUPPAUGE_NOVA_T_500_3 0x8400 -#define USB_PID_HAUPPAUGE_NOVA_T_STICK 0x7050 -#define USB_PID_HAUPPAUGE_NOVA_T_STICK_2 0x7060 -#define USB_PID_HAUPPAUGE_NOVA_T_STICK_3 0x7070 -#define USB_PID_HAUPPAUGE_MYTV_T 0x7080 -#define USB_PID_HAUPPAUGE_NOVA_TD_STICK 0x9580 -#define USB_PID_HAUPPAUGE_NOVA_TD_STICK_52009 0x5200 -#define USB_PID_HAUPPAUGE_TIGER_ATSC 0xb200 -#define USB_PID_HAUPPAUGE_TIGER_ATSC_B210 0xb210 -#define USB_PID_AVERMEDIA_EXPRESS 0xb568 -#define USB_PID_AVERMEDIA_VOLAR 0xa807 -#define USB_PID_AVERMEDIA_VOLAR_2 0xb808 -#define USB_PID_AVERMEDIA_VOLAR_A868R 0xa868 -#define USB_PID_AVERMEDIA_MCE_USB_M038 0x1228 -#define USB_PID_AVERMEDIA_HYBRID_ULTRA_USB_M039R 0x0039 -#define USB_PID_AVERMEDIA_HYBRID_ULTRA_USB_M039R_ATSC 0x1039 -#define USB_PID_AVERMEDIA_HYBRID_ULTRA_USB_M039R_DVBT 0x2039 -#define USB_PID_AVERMEDIA_VOLAR_X 0xa815 -#define USB_PID_AVERMEDIA_VOLAR_X_2 0x8150 -#define USB_PID_AVERMEDIA_A309 0xa309 -#define USB_PID_AVERMEDIA_A310 0xa310 -#define USB_PID_AVERMEDIA_A850 0x850a -#define USB_PID_AVERMEDIA_A850T 0x850b -#define USB_PID_AVERMEDIA_A805 0xa805 -#define USB_PID_AVERMEDIA_A815M 0x815a -#define USB_PID_AVERMEDIA_A835 0xa835 -#define USB_PID_AVERMEDIA_B835 0xb835 -#define USB_PID_AVERMEDIA_A835B_1835 0x1835 -#define USB_PID_AVERMEDIA_A835B_2835 0x2835 -#define USB_PID_AVERMEDIA_A835B_3835 0x3835 -#define USB_PID_AVERMEDIA_A835B_4835 0x4835 -#define USB_PID_AVERMEDIA_1867 0x1867 -#define USB_PID_AVERMEDIA_A867 0xa867 -#define USB_PID_AVERMEDIA_H335 0x0335 -#define USB_PID_AVERMEDIA_TD110 0xa110 -#define USB_PID_AVERMEDIA_TD310 0x1871 -#define USB_PID_AVERMEDIA_TWINSTAR 0x0825 -#define USB_PID_TECHNOTREND_CONNECT_S2400 0x3006 -#define USB_PID_TECHNOTREND_CONNECT_S2400_8KEEPROM 0x3009 -#define USB_PID_TECHNOTREND_CONNECT_CT3650 0x300d -#define USB_PID_TECHNOTREND_CONNECT_S2_4600 0x3011 -#define USB_PID_TECHNOTREND_CONNECT_CT2_4650_CI 0x3012 -#define USB_PID_TECHNOTREND_CONNECT_CT2_4650_CI_2 0x3015 -#define USB_PID_TECHNOTREND_TVSTICK_CT2_4400 0x3014 -#define USB_PID_TECHNOTREND_CONNECT_S2_4650_CI 0x3017 -#define USB_PID_TERRATEC_CINERGY_DT_XS_DIVERSITY 0x005a -#define USB_PID_TERRATEC_CINERGY_DT_XS_DIVERSITY_2 0x0081 -#define USB_PID_TERRATEC_CINERGY_HT_USB_XE 0x0058 -#define USB_PID_TERRATEC_CINERGY_HT_EXPRESS 0x0060 -#define USB_PID_TERRATEC_CINERGY_T_EXPRESS 0x0062 -#define USB_PID_TERRATEC_CINERGY_T_XXS 0x0078 -#define USB_PID_TERRATEC_CINERGY_T_XXS_2 0x00ab -#define USB_PID_TERRATEC_CINERGY_S2_R1 0x00a8 -#define USB_PID_TERRATEC_CINERGY_S2_R2 0x00b0 -#define USB_PID_TERRATEC_CINERGY_S2_R3 0x0102 -#define USB_PID_TERRATEC_CINERGY_S2_R4 0x0105 -#define USB_PID_TERRATEC_CINERGY_S2_1 0x1181 -#define USB_PID_TERRATEC_CINERGY_S2_2 0x1182 -#define USB_PID_TERRATEC_H7 0x10b4 -#define USB_PID_TERRATEC_H7_2 0x10a3 -#define USB_PID_TERRATEC_H7_3 0x10a5 -#define USB_PID_TERRATEC_T1 0x10ae -#define USB_PID_TERRATEC_T3 0x10a0 -#define USB_PID_TERRATEC_T5 0x10a1 -#define USB_PID_NOXON_DAB_STICK 0x00b3 -#define USB_PID_NOXON_DAB_STICK_REV2 0x00e0 -#define USB_PID_NOXON_DAB_STICK_REV3 0x00b4 -#define USB_PID_PINNACLE_EXPRESSCARD_320CX 0x022e -#define USB_PID_PINNACLE_PCTV2000E 0x022c -#define USB_PID_PINNACLE_PCTV_DVB_T_FLASH 0x0228 -#define USB_PID_PINNACLE_PCTV_DUAL_DIVERSITY_DVB_T 0x0229 -#define USB_PID_PINNACLE_PCTV71E 0x022b -#define USB_PID_PINNACLE_PCTV72E 0x0236 -#define USB_PID_PINNACLE_PCTV73E 0x0237 -#define USB_PID_PINNACLE_PCTV310E 0x3211 -#define USB_PID_PINNACLE_PCTV801E 0x023a -#define USB_PID_PINNACLE_PCTV801E_SE 0x023b -#define USB_PID_PINNACLE_PCTV340E 0x023d -#define USB_PID_PINNACLE_PCTV340E_SE 0x023e -#define USB_PID_PINNACLE_PCTV73A 0x0243 -#define USB_PID_PINNACLE_PCTV73ESE 0x0245 -#define USB_PID_PINNACLE_PCTV74E 0x0246 -#define USB_PID_PINNACLE_PCTV282E 0x0248 -#define USB_PID_PIXELVIEW_SBTVD 0x5010 -#define USB_PID_PCTV_200E 0x020e -#define USB_PID_PCTV_400E 0x020f -#define USB_PID_PCTV_450E 0x0222 -#define USB_PID_PCTV_452E 0x021f -#define USB_PID_PCTV_78E 0x025a -#define USB_PID_PCTV_79E 0x0262 -#define USB_PID_REALTEK_RTL2831U 0x2831 -#define USB_PID_REALTEK_RTL2832U 0x2832 -#define USB_PID_TECHNOTREND_CONNECT_S2_3600 0x3007 -#define USB_PID_TECHNOTREND_CONNECT_S2_3650_CI 0x300a -#define USB_PID_NEBULA_DIGITV 0x0201 -#define USB_PID_DVICO_BLUEBIRD_LGDT 0xd820 -#define USB_PID_DVICO_BLUEBIRD_LG064F_COLD 0xd500 -#define USB_PID_DVICO_BLUEBIRD_LG064F_WARM 0xd501 -#define USB_PID_DVICO_BLUEBIRD_LGZ201_COLD 0xdb00 -#define USB_PID_DVICO_BLUEBIRD_LGZ201_WARM 0xdb01 -#define USB_PID_DVICO_BLUEBIRD_TH7579_COLD 0xdb10 -#define USB_PID_DVICO_BLUEBIRD_TH7579_WARM 0xdb11 -#define USB_PID_DVICO_BLUEBIRD_DUAL_1_COLD 0xdb50 -#define USB_PID_DVICO_BLUEBIRD_DUAL_1_WARM 0xdb51 -#define USB_PID_DVICO_BLUEBIRD_DUAL_2_COLD 0xdb58 -#define USB_PID_DVICO_BLUEBIRD_DUAL_2_WARM 0xdb59 -#define USB_PID_DVICO_BLUEBIRD_DUAL_4 0xdb78 -#define USB_PID_DVICO_BLUEBIRD_DUAL_4_REV_2 0xdb98 -#define USB_PID_DVICO_BLUEBIRD_DVB_T_NANO_2 0xdb70 -#define USB_PID_DVICO_BLUEBIRD_DVB_T_NANO_2_NFW_WARM 0xdb71 -#define USB_PID_DIGITALNOW_BLUEBIRD_DUAL_1_COLD 0xdb54 -#define USB_PID_DIGITALNOW_BLUEBIRD_DUAL_1_WARM 0xdb55 -#define USB_PID_MEDION_MD95700 0x0932 -#define USB_PID_MSI_MEGASKY580 0x5580 -#define USB_PID_MSI_MEGASKY580_55801 0x5581 -#define USB_PID_KYE_DVB_T_COLD 0x701e -#define USB_PID_KYE_DVB_T_WARM 0x701f -#define USB_PID_LITEON_DVB_T_COLD 0xf000 -#define USB_PID_LITEON_DVB_T_WARM 0xf001 -#define USB_PID_DIGIVOX_MINI_SL_COLD 0xe360 -#define USB_PID_DIGIVOX_MINI_SL_WARM 0xe361 -#define USB_PID_GRANDTEC_DVBT_USB2_COLD 0x0bc6 -#define USB_PID_GRANDTEC_DVBT_USB2_WARM 0x0bc7 -#define USB_PID_WINFAST_DTV2000DS 0x6a04 -#define USB_PID_WINFAST_DTV2000DS_PLUS 0x6f12 -#define USB_PID_WINFAST_DTV_DONGLE_COLD 0x6025 -#define USB_PID_WINFAST_DTV_DONGLE_WARM 0x6026 -#define USB_PID_WINFAST_DTV_DONGLE_STK7700P 0x6f00 -#define USB_PID_WINFAST_DTV_DONGLE_H 0x60f6 -#define USB_PID_WINFAST_DTV_DONGLE_STK7700P_2 0x6f01 -#define USB_PID_WINFAST_DTV_DONGLE_GOLD 0x6029 -#define USB_PID_WINFAST_DTV_DONGLE_MINID 0x6f0f -#define USB_PID_GENPIX_8PSK_REV_1_COLD 0x0200 -#define USB_PID_GENPIX_8PSK_REV_1_WARM 0x0201 -#define USB_PID_GENPIX_8PSK_REV_2 0x0202 -#define USB_PID_GENPIX_SKYWALKER_1 0x0203 -#define USB_PID_GENPIX_SKYWALKER_CW3K 0x0204 -#define USB_PID_GENPIX_SKYWALKER_2 0x0206 -#define USB_PID_SIGMATEK_DVB_110 0x6610 -#define USB_PID_MSI_DIGI_VOX_MINI_II 0x1513 -#define USB_PID_MSI_DIGIVOX_DUO 0x8801 -#define USB_PID_OPERA1_COLD 0x2830 -#define USB_PID_OPERA1_WARM 0x3829 -#define USB_PID_LIFEVIEW_TV_WALKER_TWIN_COLD 0x0514 -#define USB_PID_LIFEVIEW_TV_WALKER_TWIN_WARM 0x0513 -#define USB_PID_GIGABYTE_U7000 0x7001 -#define USB_PID_GIGABYTE_U8000 0x7002 -#define USB_PID_ASUS_U3000 0x171f -#define USB_PID_ASUS_U3000H 0x1736 -#define USB_PID_ASUS_U3100 0x173f -#define USB_PID_ASUS_U3100MINI_PLUS 0x1779 +#define USB_PID_XBOX_ONE_TUNER 0x02d5 +#define USB_PID_XTENSIONS_XD_380 0x0381 #define USB_PID_YUAN_EC372S 0x1edc -#define USB_PID_YUAN_STK7700PH 0x1f08 -#define USB_PID_YUAN_PD378S 0x2edc #define USB_PID_YUAN_MC770 0x0871 +#define USB_PID_YUAN_PD378S 0x2edc #define USB_PID_YUAN_STK7700D 0x1efc -#define USB_PID_YUAN_STK7700D_2 0x1e8c -#define USB_PID_DW2102 0x2102 -#define USB_PID_DW2104 0x2104 -#define USB_PID_DW3101 0x3101 -#define USB_PID_XTENSIONS_XD_380 0x0381 -#define USB_PID_TELESTAR_STARSTICK_2 0x8000 -#define USB_PID_MSI_DIGI_VOX_MINI_III 0x8807 -#define USB_PID_SONY_PLAYTV 0x0003 -#define USB_PID_MYGICA_D689 0xd811 -#define USB_PID_MYGICA_T230 0xc688 -#define USB_PID_MYGICA_T230C 0xc689 -#define USB_PID_MYGICA_T230C2 0xc68a -#define USB_PID_MYGICA_T230C_LITE 0xc699 -#define USB_PID_MYGICA_T230C2_LITE 0xc69a -#define USB_PID_MYGICA_T230A 0x689a -#define USB_PID_ELGATO_EYETV_DIVERSITY 0x0011 -#define USB_PID_ELGATO_EYETV_DTT 0x0021 -#define USB_PID_ELGATO_EYETV_DTT_2 0x003f -#define USB_PID_ELGATO_EYETV_DTT_Dlx 0x0020 -#define USB_PID_ELGATO_EYETV_SAT 0x002a -#define USB_PID_ELGATO_EYETV_SAT_V2 0x0025 -#define USB_PID_ELGATO_EYETV_SAT_V3 0x0036 -#define USB_PID_DVB_T_USB_STICK_HIGH_SPEED_COLD 0x5000 -#define USB_PID_DVB_T_USB_STICK_HIGH_SPEED_WARM 0x5001 -#define USB_PID_FRIIO_WHITE 0x0001 -#define USB_PID_TVWAY_PLUS 0x0002 -#define USB_PID_SVEON_STV20 0xe39d -#define USB_PID_SVEON_STV20_RTL2832U 0xd39d -#define USB_PID_SVEON_STV21 0xd3b0 -#define USB_PID_SVEON_STV22 0xe401 -#define USB_PID_SVEON_STV22_IT9137 0xe411 -#define USB_PID_AZUREWAVE_AZ6027 0x3275 -#define USB_PID_TERRATEC_DVBS2CI_V1 0x10a4 -#define USB_PID_TERRATEC_DVBS2CI_V2 0x10ac -#define USB_PID_TECHNISAT_USB2_HDCI_V1 0x0001 -#define USB_PID_TECHNISAT_USB2_HDCI_V2 0x0002 -#define USB_PID_TECHNISAT_USB2_CABLESTAR_HDCI 0x0003 -#define USB_PID_TECHNISAT_AIRSTAR_TELESTICK_2 0x0004 -#define USB_PID_TECHNISAT_USB2_DVB_S2 0x0500 -#define USB_PID_CPYTO_REDI_PC50A 0xa803 -#define USB_PID_CTVDIGDUAL_V2 0xe410 -#define USB_PID_PCTV_2002E 0x025c -#define USB_PID_PCTV_2002E_SE 0x025d -#define USB_PID_SVEON_STV27 0xd3af -#define USB_PID_TURBOX_DTT_2000 0xd3a4 -#define USB_PID_WINTV_SOLOHD 0x0264 -#define USB_PID_WINTV_SOLOHD_2 0x8268 -#define USB_PID_EVOLVEO_XTRATV_STICK 0xa115 -#define USB_PID_HAMA_DVBT_HYBRID 0x2758 -#define USB_PID_XBOX_ONE_TUNER 0x02d5 -#define USB_PID_PROLECTRIX_DV107669 0xd803 +#define USB_PID_YUAN_STK7700D_2 0x1e8c +#define USB_PID_YUAN_STK7700PH 0x1f08 + #endif -- cgit v1.2.3 From 2f8bc51dd0c5b9376259ae03e2a145e5261e06a9 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:14 +0200 Subject: media: dvb-usb: move USB IDs to dvb-usb-ids.h Almost all drivers based on dvb-usb place their USB IDs at dvb-usb-ids.h. In order to make it more standard, place the remaining ones also there. Link: https://lore.kernel.org/linux-media/7b32d5383169d23082758a7b69edef2f099202f3.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index dcf5772c84a0..9577cae8c73b 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -17,6 +17,7 @@ #define USB_VID_AFATECH 0x15a4 #define USB_VID_ALCOR_MICRO 0x058f #define USB_VID_ALINK 0x05e3 +#define USB_VID_AME 0x06be #define USB_VID_AMT 0x1c73 #define USB_VID_ANCHOR 0x0547 #define USB_VID_ANSONIC 0x10b9 @@ -38,6 +39,7 @@ #define USB_VID_EVOLUTEPC 0x1e59 #define USB_VID_GENPIX 0x09c0 #define USB_VID_GIGABYTE 0x1044 +#define USB_VID_GOTVIEW 0x1fe1 #define USB_VID_GRANDTEC 0x5032 #define USB_VID_GTEK 0x1f4d #define USB_VID_HAMA 0x147f @@ -61,6 +63,8 @@ #define USB_VID_PCTV 0x2013 #define USB_VID_PINNACLE 0x2304 #define USB_VID_PIXELVIEW 0x1554 +#define USB_VID_PROF_1 0x3011 +#define USB_VID_PROF_2 0x3034 #define USB_VID_REALTEK 0x0bda #define USB_VID_SONY 0x1415 #define USB_VID_TECHNISAT 0x14f7 @@ -68,6 +72,7 @@ #define USB_VID_TELESTAR 0x10b9 #define USB_VID_TERRATEC 0x0ccd #define USB_VID_TERRATEC_2 0x153b +#define USB_VID_TEVII 0x9022 #define USB_VID_TWINHAN 0x1822 #define USB_VID_ULTIMA_ELECTRONIC 0x05d8 #define USB_VID_UNIWILL 0x1584 @@ -90,6 +95,7 @@ #define USB_PID_AFATECH_AF9035_1003 0x1003 #define USB_PID_AFATECH_AF9035_9035 0x9035 #define USB_PID_ALINK_DTU 0xf170 +#define USB_PID_AME_DTV5100 0xa232 #define USB_PID_ANSONIC_DVBT_USB 0x6000 #define USB_PID_ANYSEE 0x861f #define USB_PID_ARTEC_T14BR 0x810f @@ -198,6 +204,7 @@ #define USB_PID_DVICO_BLUEBIRD_LGZ201_WARM 0xdb01 #define USB_PID_DVICO_BLUEBIRD_TH7579_COLD 0xdb10 #define USB_PID_DVICO_BLUEBIRD_TH7579_WARM 0xdb11 +#define USB_PID_DW2101 0x2101 #define USB_PID_DW2102 0x2102 #define USB_PID_DW2104 0x2104 #define USB_PID_DW3101 0x3101 @@ -217,6 +224,9 @@ #define USB_PID_FREECOM_DVBT 0x0160 #define USB_PID_FREECOM_DVBT_2 0x0161 #define USB_PID_FRIIO_WHITE 0x0001 +#define USB_PID_GENIATECH_SU3000 0x3000 +#define USB_PID_GENIATECH_T220 0xd220 +#define USB_PID_GENIATECH_X3M_SPC1400HD 0x3100 #define USB_PID_GENIUS_TVGO_DVB_T03 0x4012 #define USB_PID_GENPIX_8PSK_REV_1_COLD 0x0200 #define USB_PID_GENPIX_8PSK_REV_1_WARM 0x0201 @@ -234,6 +244,7 @@ #define USB_PID_HAMA_DVBT_HYBRID 0x2758 #define USB_PID_HANFTEK_UMT_010_COLD 0x0001 #define USB_PID_HANFTEK_UMT_010_WARM 0x0015 +#define USB_PID_HAUPPAUGE_MAX_S2 0xd900 #define USB_PID_HAUPPAUGE_MYTV_T 0x7080 #define USB_PID_HAUPPAUGE_NOVA_TD_STICK 0x9580 #define USB_PID_HAUPPAUGE_NOVA_TD_STICK_52009 0x5200 @@ -314,6 +325,7 @@ #define USB_PID_PINNACLE_PCTV_DVB_T_FLASH 0x0228 #define USB_PID_PIXELVIEW_SBTVD 0x5010 #define USB_PID_PROF_1100 0xb012 +#define USB_PID_PROF_7500 0x7500 #define USB_PID_PROLECTRIX_DV107669 0xd803 #define USB_PID_REALTEK_RTL2831U 0x2831 #define USB_PID_REALTEK_RTL2832U 0x2832 @@ -348,10 +360,12 @@ #define USB_PID_TERRATEC_CINERGY_S 0x0064 #define USB_PID_TERRATEC_CINERGY_S2_1 0x1181 #define USB_PID_TERRATEC_CINERGY_S2_2 0x1182 +#define USB_PID_TERRATEC_CINERGY_S2_BOX 0x0105 #define USB_PID_TERRATEC_CINERGY_S2_R1 0x00a8 #define USB_PID_TERRATEC_CINERGY_S2_R2 0x00b0 #define USB_PID_TERRATEC_CINERGY_S2_R3 0x0102 #define USB_PID_TERRATEC_CINERGY_S2_R4 0x0105 +#define USB_PID_TERRATEC_CINERGY_T2 0x0038 #define USB_PID_TERRATEC_CINERGY_TC2_STICK 0x10b2 #define USB_PID_TERRATEC_CINERGY_T_EXPRESS 0x0062 #define USB_PID_TERRATEC_CINERGY_T_STICK 0x0093 @@ -383,6 +397,8 @@ #define USB_PID_TINYTWIN_3 0x9016 #define USB_PID_TREKSTOR_DVBT 0x901b #define USB_PID_TREKSTOR_TERRES_2_0 0xC803 +#define USB_PID_TTEVII_S482_1 0xd483 +#define USB_PID_TTEVII_S482_2 0xd484 #define USB_PID_TURBOX_DTT_2000 0xd3a4 #define USB_PID_TVWAY_PLUS 0x0002 #define USB_PID_TWINHAN_VP7020_COLD 0x3203 -- cgit v1.2.3 From 82a4a3ba3380bafc33f58c9b8057bb6577a7f113 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:16 +0200 Subject: media: dvb-usb: Add helper macros for using USB VID/PID In order to use designated initializers and to avoid avoid big lines at the USB ID tables, define some helper macros. Link: https://lore.kernel.org/linux-media/f82e376dea2e9b922f51a03d1e7730b03e49cc7d.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index 9577cae8c73b..5ae55c20912e 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -10,6 +10,14 @@ #ifndef _DVB_USB_IDS_H_ #define _DVB_USB_IDS_H_ +#include + +#define DVB_USB_DEV(pid, vid) \ + [vid] = { USB_DEVICE(USB_VID_ ## pid, USB_PID_ ## vid) } + +#define DVB_USB_DEV_VER(pid, vid, lo, hi) \ + [vid] = { USB_DEVICE_VER(USB_VID_ ## pid, USB_PID_ ## vid, lo, hi) } + /* Vendor IDs */ #define USB_VID_774 0x7a69 -- cgit v1.2.3 From b18869ba190dce7ac9802143253fa0a0a639d059 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:22 +0200 Subject: media: digitv: use the newer dvb-usb macros for USB device In order to make the drivers under dvb-usb more homogeneous, use the new macro. Link: https://lore.kernel.org/linux-media/68de8820a361e61c25bf7402acac71b3770ff906.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index 5ae55c20912e..c3bea2bf9dda 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -104,6 +104,7 @@ #define USB_PID_AFATECH_AF9035_9035 0x9035 #define USB_PID_ALINK_DTU 0xf170 #define USB_PID_AME_DTV5100 0xa232 +#define USB_PID_ANCHOR_NEBULA_DIGITV 0x0201 #define USB_PID_ANSONIC_DVBT_USB 0x6000 #define USB_PID_ANYSEE 0x861f #define USB_PID_ARTEC_T14BR 0x810f @@ -301,7 +302,6 @@ #define USB_PID_MYGICA_T230C2 0xc68a #define USB_PID_MYGICA_T230C2_LITE 0xc69a #define USB_PID_MYGICA_T230C_LITE 0xc699 -#define USB_PID_NEBULA_DIGITV 0x0201 #define USB_PID_NOXON_DAB_STICK 0x00b3 #define USB_PID_NOXON_DAB_STICK_REV2 0x00e0 #define USB_PID_NOXON_DAB_STICK_REV3 0x00b4 -- cgit v1.2.3 From 86fd1a41fc58108833358e3a5e238c548c98edd2 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:23 +0200 Subject: media: dvb-usb: dtt200u: use an enum for the device number The device number is currently a value that needs to be the same on two separate tables, but the code doesn't actually enforce it, leading to errors as boards get added or removed. Fix it by using an enum. Link: https://lore.kernel.org/linux-media/9fa3d1add4c58e1320dcc18578fda2d0106becda.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index c3bea2bf9dda..66a5b2045552 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -194,8 +194,6 @@ #define USB_PID_DNTV_TINYUSB2_WARM 0x3224 #define USB_PID_DPOSH_M9206_COLD 0x9206 #define USB_PID_DPOSH_M9206_WARM 0xa090 -#define USB_PID_DTT200U_COLD 0x0201 -#define USB_PID_DTT200U_WARM 0x0301 #define USB_PID_DVB_T_USB_STICK_HIGH_SPEED_COLD 0x5000 #define USB_PID_DVB_T_USB_STICK_HIGH_SPEED_WARM 0x5001 #define USB_PID_DVICO_BLUEBIRD_DUAL_1_COLD 0xdb50 @@ -290,6 +288,7 @@ #define USB_PID_LITEON_DVB_T_COLD 0xf000 #define USB_PID_LITEON_DVB_T_WARM 0xf001 #define USB_PID_MEDION_MD95700 0x0932 +#define USB_PID_MIGLIA_WT220U_ZAP250_COLD 0x0220 #define USB_PID_MSI_DIGIVOX_DUO 0x8801 #define USB_PID_MSI_DIGI_VOX_MINI_II 0x1513 #define USB_PID_MSI_DIGI_VOX_MINI_III 0x8807 @@ -430,6 +429,15 @@ #define USB_PID_UNIWILL_STK7700P 0x6003 #define USB_PID_UNK_HYPER_PALTEK_COLD 0x005e #define USB_PID_UNK_HYPER_PALTEK_WARM 0x005f +#define USB_PID_WIDEVIEW_DTT200U_COLD 0x0201 +#define USB_PID_WIDEVIEW_DTT200U_WARM 0x0301 +#define USB_PID_WIDEVIEW_WT220U_COLD 0x0222 +#define USB_PID_WIDEVIEW_WT220U_FC_COLD 0x0225 +#define USB_PID_WIDEVIEW_WT220U_FC_WARM 0x0226 +#define USB_PID_WIDEVIEW_WT220U_WARM 0x0221 +#define USB_PID_WIDEVIEW_WT220U_ZAP250_COLD 0x0220 +#define USB_PID_WIDEVIEW_WT220U_ZL0353_COLD 0x022a +#define USB_PID_WIDEVIEW_WT220U_ZL0353_WARM 0x022b #define USB_PID_WINFAST_DTV2000DS 0x6a04 #define USB_PID_WINFAST_DTV2000DS_PLUS 0x6f12 #define USB_PID_WINFAST_DTV_DONGLE_COLD 0x6025 @@ -443,13 +451,6 @@ #define USB_PID_WINTV_NOVA_T_USB2_WARM 0x9301 #define USB_PID_WINTV_SOLOHD 0x0264 #define USB_PID_WINTV_SOLOHD_2 0x8268 -#define USB_PID_WT220U_COLD 0x0222 -#define USB_PID_WT220U_FC_COLD 0x0225 -#define USB_PID_WT220U_FC_WARM 0x0226 -#define USB_PID_WT220U_WARM 0x0221 -#define USB_PID_WT220U_ZAP250_COLD 0x0220 -#define USB_PID_WT220U_ZL0353_COLD 0x022a -#define USB_PID_WT220U_ZL0353_WARM 0x022b #define USB_PID_XBOX_ONE_TUNER 0x02d5 #define USB_PID_XTENSIONS_XD_380 0x0381 #define USB_PID_YUAN_EC372S 0x1edc -- cgit v1.2.3 From 2fa2002f533e0ed847922cdf9479ea0875f4e49f Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:25 +0200 Subject: media: dw2102: use the newer dvb-usb macros for USB device In order to make the drivers under dvb-usb more homogeneous, use the new macro, and rename some PIDs. Link: https://lore.kernel.org/linux-media/828998ef3f0843bab4e84780e42f8f0802f57be7.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index 66a5b2045552..e41902d06ccc 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -160,6 +160,10 @@ #define USB_PID_CPYTO_REDI_PC50A 0xa803 #define USB_PID_CREATIX_CTX1921 0x1921 #define USB_PID_CTVDIGDUAL_V2 0xe410 +#define USB_PID_CYPRESS_DW2101 0x2101 +#define USB_PID_CYPRESS_DW2102 0x2102 +#define USB_PID_CYPRESS_DW2104 0x2104 +#define USB_PID_CYPRESS_DW3101 0x3101 #define USB_PID_DELOCK_USB2_DVBT 0xb803 #define USB_PID_DIBCOM_ANCHOR_2135_COLD 0x2131 #define USB_PID_DIBCOM_HOOK_DEFAULT 0x0064 @@ -211,10 +215,6 @@ #define USB_PID_DVICO_BLUEBIRD_LGZ201_WARM 0xdb01 #define USB_PID_DVICO_BLUEBIRD_TH7579_COLD 0xdb10 #define USB_PID_DVICO_BLUEBIRD_TH7579_WARM 0xdb11 -#define USB_PID_DW2101 0x2101 -#define USB_PID_DW2102 0x2102 -#define USB_PID_DW2104 0x2104 -#define USB_PID_DW3101 0x3101 #define USB_PID_E3C_EC168 0x1689 #define USB_PID_E3C_EC168_2 0xfffa #define USB_PID_E3C_EC168_3 0xfffb @@ -394,6 +394,8 @@ #define USB_PID_TEVII_S421 0xd421 #define USB_PID_TEVII_S480_1 0xd481 #define USB_PID_TEVII_S480_2 0xd482 +#define USB_PID_TEVII_S482_1 0xd483 +#define USB_PID_TEVII_S482_2 0xd484 #define USB_PID_TEVII_S630 0xd630 #define USB_PID_TEVII_S632 0xd632 #define USB_PID_TEVII_S650 0xd650 @@ -404,8 +406,6 @@ #define USB_PID_TINYTWIN_3 0x9016 #define USB_PID_TREKSTOR_DVBT 0x901b #define USB_PID_TREKSTOR_TERRES_2_0 0xC803 -#define USB_PID_TTEVII_S482_1 0xd483 -#define USB_PID_TTEVII_S482_2 0xd484 #define USB_PID_TURBOX_DTT_2000 0xd3a4 #define USB_PID_TVWAY_PLUS 0x0002 #define USB_PID_TWINHAN_VP7020_COLD 0x3203 -- cgit v1.2.3 From 3473fd1711527c24b3d37d6b13cfd341e2d5a3c7 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:27 +0200 Subject: media: dvb-usb: m920x: use an enum for the device number The device number is currently a value that needs to be the same on two separate tables, but the code doesn't actually enforce it, leading to errors as boards get added or removed. Fix it by using an enum. Link: https://lore.kernel.org/linux-media/c6f6bab97c39561add54f69a75980f4d453f7c17.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index e41902d06ccc..10d73c108149 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -106,6 +106,9 @@ #define USB_PID_AME_DTV5100 0xa232 #define USB_PID_ANCHOR_NEBULA_DIGITV 0x0201 #define USB_PID_ANSONIC_DVBT_USB 0x6000 +#define USB_PID_ANUBIS_LIFEVIEW_TV_WALKER_TWIN_COLD 0x0514 +#define USB_PID_ANUBIS_LIFEVIEW_TV_WALKER_TWIN_WARM 0x0513 +#define USB_PID_ANUBIS_MSI_DIGI_VOX_MINI_II 0x1513 #define USB_PID_ANYSEE 0x861f #define USB_PID_ARTEC_T14BR 0x810f #define USB_PID_ARTEC_T14_COLD 0x810b @@ -149,6 +152,7 @@ #define USB_PID_AZUREWAVE_6007 0x0ccd #define USB_PID_AZUREWAVE_AD_TU700 0x3237 #define USB_PID_AZUREWAVE_AZ6027 0x3275 +#define USB_PID_AZUREWAVE_TWINHAN_VP7049 0x3219 #define USB_PID_COMPRO_DVBU2000_COLD 0xd000 #define USB_PID_COMPRO_DVBU2000_UNK_COLD 0x010c #define USB_PID_COMPRO_DVBU2000_UNK_WARM 0x010d @@ -283,14 +287,11 @@ #define USB_PID_KWORLD_VSTREAM_WARM 0x17df #define USB_PID_KYE_DVB_T_COLD 0x701e #define USB_PID_KYE_DVB_T_WARM 0x701f -#define USB_PID_LIFEVIEW_TV_WALKER_TWIN_COLD 0x0514 -#define USB_PID_LIFEVIEW_TV_WALKER_TWIN_WARM 0x0513 #define USB_PID_LITEON_DVB_T_COLD 0xf000 #define USB_PID_LITEON_DVB_T_WARM 0xf001 #define USB_PID_MEDION_MD95700 0x0932 #define USB_PID_MIGLIA_WT220U_ZAP250_COLD 0x0220 #define USB_PID_MSI_DIGIVOX_DUO 0x8801 -#define USB_PID_MSI_DIGI_VOX_MINI_II 0x1513 #define USB_PID_MSI_DIGI_VOX_MINI_III 0x8807 #define USB_PID_MSI_MEGASKY580 0x5580 #define USB_PID_MSI_MEGASKY580_55801 0x5581 @@ -317,7 +318,6 @@ #define USB_PID_PINNACLE_EXPRESSCARD_320CX 0x022e #define USB_PID_PINNACLE_PCTV2000E 0x022c #define USB_PID_PINNACLE_PCTV282E 0x0248 -#define USB_PID_PINNACLE_PCTV310E 0x3211 #define USB_PID_PINNACLE_PCTV340E 0x023d #define USB_PID_PINNACLE_PCTV340E_SE 0x023e #define USB_PID_PINNACLE_PCTV71E 0x022b @@ -416,7 +416,6 @@ #define USB_PID_TWINHAN_VP7041_WARM 0x3202 #define USB_PID_TWINHAN_VP7045_COLD 0x3205 #define USB_PID_TWINHAN_VP7045_WARM 0x3206 -#define USB_PID_TWINHAN_VP7049 0x3219 #define USB_PID_ULTIMA_TVBOX_AN2235_COLD 0x8107 #define USB_PID_ULTIMA_TVBOX_AN2235_WARM 0x8108 #define USB_PID_ULTIMA_TVBOX_ANCHOR_COLD 0x2235 @@ -429,6 +428,7 @@ #define USB_PID_UNIWILL_STK7700P 0x6003 #define USB_PID_UNK_HYPER_PALTEK_COLD 0x005e #define USB_PID_UNK_HYPER_PALTEK_WARM 0x005f +#define USB_PID_VISIONPLUS_PINNACLE_PCTV310E 0x3211 #define USB_PID_WIDEVIEW_DTT200U_COLD 0x0201 #define USB_PID_WIDEVIEW_DTT200U_WARM 0x0301 #define USB_PID_WIDEVIEW_WT220U_COLD 0x0222 -- cgit v1.2.3 From cb794c2b7ae5b769fd46a3cce9508f7e04bf172b Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:28 +0200 Subject: media: dvb-usb: nova-t-usb2: use an enum for the device number The device number is currently a value that needs to be the same on two separate tables, but the code doesn't actually enforce it, leading to errors as boards get added or removed. Fix it by using an enum. Link: https://lore.kernel.org/linux-media/58f1a356b7b75bbefef3aa07cd99896c446df32f.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index 10d73c108149..cc1df632d08b 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -267,6 +267,8 @@ #define USB_PID_HAUPPAUGE_NOVA_T_STICK_3 0x7070 #define USB_PID_HAUPPAUGE_TIGER_ATSC 0xb200 #define USB_PID_HAUPPAUGE_TIGER_ATSC_B210 0xb210 +#define USB_PID_HAUPPAUGE_WINTV_NOVA_T_USB2_COLD 0x9300 +#define USB_PID_HAUPPAUGE_WINTV_NOVA_T_USB2_WARM 0x9301 #define USB_PID_INTEL_CE9500 0x9500 #define USB_PID_ITETECH_IT9135 0x9135 #define USB_PID_ITETECH_IT9135_9005 0x9005 @@ -447,8 +449,6 @@ #define USB_PID_WINFAST_DTV_DONGLE_STK7700P 0x6f00 #define USB_PID_WINFAST_DTV_DONGLE_STK7700P_2 0x6f01 #define USB_PID_WINFAST_DTV_DONGLE_WARM 0x6026 -#define USB_PID_WINTV_NOVA_T_USB2_COLD 0x9300 -#define USB_PID_WINTV_NOVA_T_USB2_WARM 0x9301 #define USB_PID_WINTV_SOLOHD 0x0264 #define USB_PID_WINTV_SOLOHD_2 0x8268 #define USB_PID_XBOX_ONE_TUNER 0x02d5 -- cgit v1.2.3 From 22127ac8eb8d919d7366b370c1451f3b61ebc1de Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:29 +0200 Subject: media: dvb-usb: opera1: use an enum for the device number The device number is currently a value that needs to be the same on two separate tables, but the code doesn't actually enforce it, leading to errors as boards get added or removed. Fix it by using an enum. Link: https://lore.kernel.org/linux-media/08861d80b6706ac1ed04a68959ebb78f27cb028d.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index cc1df632d08b..6aa15988b577 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -168,6 +168,7 @@ #define USB_PID_CYPRESS_DW2102 0x2102 #define USB_PID_CYPRESS_DW2104 0x2104 #define USB_PID_CYPRESS_DW3101 0x3101 +#define USB_PID_CYPRESS_OPERA1_COLD 0x2830 #define USB_PID_DELOCK_USB2_DVBT 0xb803 #define USB_PID_DIBCOM_ANCHOR_2135_COLD 0x2131 #define USB_PID_DIBCOM_HOOK_DEFAULT 0x0064 @@ -307,7 +308,6 @@ #define USB_PID_NOXON_DAB_STICK 0x00b3 #define USB_PID_NOXON_DAB_STICK_REV2 0x00e0 #define USB_PID_NOXON_DAB_STICK_REV3 0x00b4 -#define USB_PID_OPERA1_COLD 0x2830 #define USB_PID_OPERA1_WARM 0x3829 #define USB_PID_PCTV_2002E 0x025c #define USB_PID_PCTV_2002E_SE 0x025d -- cgit v1.2.3 From 710801c7ba81993d635a458cd9a0fc02f921c439 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:30 +0200 Subject: media: dvb-usb: pctv452e: use an enum for the device number The device number is currently a value that needs to be the same on two separate tables, but the code doesn't actually enforce it, leading to errors as boards get added or removed. Fix it by using an enum. Link: https://lore.kernel.org/linux-media/283a8c6bdf9778f832b4f6acc104c06688281668.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index 6aa15988b577..ed6e37f23cbc 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -314,7 +314,6 @@ #define USB_PID_PCTV_200E 0x020e #define USB_PID_PCTV_400E 0x020f #define USB_PID_PCTV_450E 0x0222 -#define USB_PID_PCTV_452E 0x021f #define USB_PID_PCTV_78E 0x025a #define USB_PID_PCTV_79E 0x0262 #define USB_PID_PINNACLE_EXPRESSCARD_320CX 0x022e @@ -330,6 +329,7 @@ #define USB_PID_PINNACLE_PCTV74E 0x0246 #define USB_PID_PINNACLE_PCTV801E 0x023a #define USB_PID_PINNACLE_PCTV801E_SE 0x023b +#define USB_PID_PINNACLE_PCTV_452E 0x021f #define USB_PID_PINNACLE_PCTV_DUAL_DIVERSITY_DVB_T 0x0229 #define USB_PID_PINNACLE_PCTV_DVB_T_FLASH 0x0228 #define USB_PID_PIXELVIEW_SBTVD 0x5010 -- cgit v1.2.3 From 5c1a56c9f0658d9b2d4be333fd896cd1b6cbaa82 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:32 +0200 Subject: media: dvb-usb: ttusb2: use an enum for the device number The device number is currently a value that needs to be the same on two separate tables, but the code doesn't actually enforce it, leading to errors as boards get added or removed. Fix it by using an enum. Link: https://lore.kernel.org/linux-media/b447d9fd3832da5eff6267e8fe742c431f1133f2.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index ed6e37f23cbc..0fad68bfe6f9 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -312,8 +312,6 @@ #define USB_PID_PCTV_2002E 0x025c #define USB_PID_PCTV_2002E_SE 0x025d #define USB_PID_PCTV_200E 0x020e -#define USB_PID_PCTV_400E 0x020f -#define USB_PID_PCTV_450E 0x0222 #define USB_PID_PCTV_78E 0x025a #define USB_PID_PCTV_79E 0x0262 #define USB_PID_PINNACLE_EXPRESSCARD_320CX 0x022e @@ -329,6 +327,8 @@ #define USB_PID_PINNACLE_PCTV74E 0x0246 #define USB_PID_PINNACLE_PCTV801E 0x023a #define USB_PID_PINNACLE_PCTV801E_SE 0x023b +#define USB_PID_PINNACLE_PCTV_400E 0x020f +#define USB_PID_PINNACLE_PCTV_450E 0x0222 #define USB_PID_PINNACLE_PCTV_452E 0x021f #define USB_PID_PINNACLE_PCTV_DUAL_DIVERSITY_DVB_T 0x0229 #define USB_PID_PINNACLE_PCTV_DVB_T_FLASH 0x0228 -- cgit v1.2.3 From 9c06331ca07f0e7288c949e7969ab108aa1c9807 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:34 +0200 Subject: media: dvb-usb: vp702x: use an enum for the device number The device number is currently a value that needs to be the same on two separate tables, but the code doesn't actually enforce it, leading to errors as boards get added or removed. Fix it by using an enum. Link: https://lore.kernel.org/linux-media/13bf6aab3909fae5da4c9a24c114b15e76abd146.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index 0fad68bfe6f9..e022e38b6f95 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -410,9 +410,6 @@ #define USB_PID_TREKSTOR_TERRES_2_0 0xC803 #define USB_PID_TURBOX_DTT_2000 0xd3a4 #define USB_PID_TVWAY_PLUS 0x0002 -#define USB_PID_TWINHAN_VP7020_COLD 0x3203 -#define USB_PID_TWINHAN_VP7020_WARM 0x3204 -#define USB_PID_TWINHAN_VP7021_COLD 0x3207 #define USB_PID_TWINHAN_VP7021_WARM 0x3208 #define USB_PID_TWINHAN_VP7041_COLD 0x3201 #define USB_PID_TWINHAN_VP7041_WARM 0x3202 @@ -431,6 +428,9 @@ #define USB_PID_UNK_HYPER_PALTEK_COLD 0x005e #define USB_PID_UNK_HYPER_PALTEK_WARM 0x005f #define USB_PID_VISIONPLUS_PINNACLE_PCTV310E 0x3211 +#define USB_PID_VISIONPLUS_VP7020_COLD 0x3203 +#define USB_PID_VISIONPLUS_VP7020_WARM 0x3204 +#define USB_PID_VISIONPLUS_VP7021_COLD 0x3207 #define USB_PID_WIDEVIEW_DTT200U_COLD 0x0201 #define USB_PID_WIDEVIEW_DTT200U_WARM 0x0301 #define USB_PID_WIDEVIEW_WT220U_COLD 0x0222 -- cgit v1.2.3 From 5710a24b34576a8873ee836953575fdb234b37e2 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:35 +0200 Subject: media: dvb-usb: vp7045: use an enum for the device number The device number is currently a value that needs to be the same on two separate tables, but the code doesn't actually enforce it, leading to errors as boards get added or removed. Fix it by using an enum. Link: https://lore.kernel.org/linux-media/0241bf842bf592dfa01b0ef4916afda396194f98.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index e022e38b6f95..9f53b3ce3e58 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -199,8 +199,6 @@ #define USB_PID_DIGITALNOW_BLUEBIRD_DUAL_1_WARM 0xdb55 #define USB_PID_DIGIVOX_MINI_SL_COLD 0xe360 #define USB_PID_DIGIVOX_MINI_SL_WARM 0xe361 -#define USB_PID_DNTV_TINYUSB2_COLD 0x3223 -#define USB_PID_DNTV_TINYUSB2_WARM 0x3224 #define USB_PID_DPOSH_M9206_COLD 0x9206 #define USB_PID_DPOSH_M9206_WARM 0xa090 #define USB_PID_DVB_T_USB_STICK_HIGH_SPEED_COLD 0x5000 @@ -413,8 +411,6 @@ #define USB_PID_TWINHAN_VP7021_WARM 0x3208 #define USB_PID_TWINHAN_VP7041_COLD 0x3201 #define USB_PID_TWINHAN_VP7041_WARM 0x3202 -#define USB_PID_TWINHAN_VP7045_COLD 0x3205 -#define USB_PID_TWINHAN_VP7045_WARM 0x3206 #define USB_PID_ULTIMA_TVBOX_AN2235_COLD 0x8107 #define USB_PID_ULTIMA_TVBOX_AN2235_WARM 0x8108 #define USB_PID_ULTIMA_TVBOX_ANCHOR_COLD 0x2235 @@ -428,9 +424,13 @@ #define USB_PID_UNK_HYPER_PALTEK_COLD 0x005e #define USB_PID_UNK_HYPER_PALTEK_WARM 0x005f #define USB_PID_VISIONPLUS_PINNACLE_PCTV310E 0x3211 +#define USB_PID_VISIONPLUS_TINYUSB2_COLD 0x3223 +#define USB_PID_VISIONPLUS_TINYUSB2_WARM 0x3224 #define USB_PID_VISIONPLUS_VP7020_COLD 0x3203 #define USB_PID_VISIONPLUS_VP7020_WARM 0x3204 #define USB_PID_VISIONPLUS_VP7021_COLD 0x3207 +#define USB_PID_VISIONPLUS_VP7045_COLD 0x3205 +#define USB_PID_VISIONPLUS_VP7045_WARM 0x3206 #define USB_PID_WIDEVIEW_DTT200U_COLD 0x0201 #define USB_PID_WIDEVIEW_DTT200U_WARM 0x0301 #define USB_PID_WIDEVIEW_WT220U_COLD 0x0222 -- cgit v1.2.3 From d763479abd67fc67a13aabe0ce19b4d775fbdcee Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:36 +0200 Subject: media: dvb-usb: dibusb-mb: use an enum for the device number The device number is currently a value that needs to be the same on two separate tables, but the code doesn't actually enforce it, leading to errors as boards get added or removed. Fix it by using an enum. Link: https://lore.kernel.org/linux-media/a300c26ad4e9bb913e86eeaf0ec7d72b9e7d5d3e.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index 9f53b3ce3e58..e4796464b0d7 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -133,8 +133,6 @@ #define USB_PID_AVERMEDIA_B835 0xb835 #define USB_PID_AVERMEDIA_DVBT_USB2_COLD 0xa800 #define USB_PID_AVERMEDIA_DVBT_USB2_WARM 0xa801 -#define USB_PID_AVERMEDIA_DVBT_USB_COLD 0x0001 -#define USB_PID_AVERMEDIA_DVBT_USB_WARM 0x0002 #define USB_PID_AVERMEDIA_EXPRESS 0xb568 #define USB_PID_AVERMEDIA_H335 0x0335 #define USB_PID_AVERMEDIA_HYBRID_ULTRA_USB_M039R 0x0039 @@ -230,6 +228,8 @@ #define USB_PID_ELGATO_EYETV_SAT 0x002a #define USB_PID_ELGATO_EYETV_SAT_V2 0x0025 #define USB_PID_ELGATO_EYETV_SAT_V3 0x0036 +#define USB_PID_EMPIA_VSTREAM_COLD 0x17de +#define USB_PID_EMPIA_VSTREAM_WARM 0x17df #define USB_PID_EVOLVEO_XTRATV_STICK 0xa115 #define USB_PID_FREECOM_DVBT 0x0160 #define USB_PID_FREECOM_DVBT_2 0x0161 @@ -251,6 +251,8 @@ #define USB_PID_GRANDTEC_DVBT_USB2_WARM 0x0bc7 #define USB_PID_GRANDTEC_DVBT_USB_COLD 0x0fa0 #define USB_PID_GRANDTEC_DVBT_USB_WARM 0x0fa1 +#define USB_PID_GRANDTEC_MOD3000_COLD 0x0bb8 +#define USB_PID_GRANDTEC_MOD3000_WARM 0x0bb9 #define USB_PID_HAMA_DVBT_HYBRID 0x2758 #define USB_PID_HANFTEK_UMT_010_COLD 0x0001 #define USB_PID_HANFTEK_UMT_010_WARM 0x0015 @@ -285,7 +287,6 @@ #define USB_PID_KWORLD_UB383_T 0xe383 #define USB_PID_KWORLD_UB499_2T_T09 0xe409 #define USB_PID_KWORLD_VSTREAM_COLD 0x17de -#define USB_PID_KWORLD_VSTREAM_WARM 0x17df #define USB_PID_KYE_DVB_T_COLD 0x701e #define USB_PID_KYE_DVB_T_WARM 0x701f #define USB_PID_LITEON_DVB_T_COLD 0xf000 @@ -429,10 +430,14 @@ #define USB_PID_VISIONPLUS_VP7020_COLD 0x3203 #define USB_PID_VISIONPLUS_VP7020_WARM 0x3204 #define USB_PID_VISIONPLUS_VP7021_COLD 0x3207 +#define USB_PID_VISIONPLUS_VP7041_COLD 0x3201 +#define USB_PID_VISIONPLUS_VP7041_WARM 0x3202 #define USB_PID_VISIONPLUS_VP7045_COLD 0x3205 #define USB_PID_VISIONPLUS_VP7045_WARM 0x3206 #define USB_PID_WIDEVIEW_DTT200U_COLD 0x0201 #define USB_PID_WIDEVIEW_DTT200U_WARM 0x0301 +#define USB_PID_WIDEVIEW_DVBT_USB_COLD 0x0001 +#define USB_PID_WIDEVIEW_DVBT_USB_WARM 0x0002 #define USB_PID_WIDEVIEW_WT220U_COLD 0x0222 #define USB_PID_WIDEVIEW_WT220U_FC_COLD 0x0225 #define USB_PID_WIDEVIEW_WT220U_FC_WARM 0x0226 -- cgit v1.2.3 From 281b21c56ed325ad5a23bf2dce45a8d7f751a577 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:37 +0200 Subject: media: dvb-usb: dibusb-mc: use an enum for the device number The device number is currently a value that needs to be the same on two separate tables, but the code doesn't actually enforce it, leading to errors as boards get added or removed. Fix it by using an enum. Link: https://lore.kernel.org/linux-media/f1d4fa4960b709152ae693800c830e19a4bc1f48.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index e4796464b0d7..4dba939760ed 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -111,8 +111,6 @@ #define USB_PID_ANUBIS_MSI_DIGI_VOX_MINI_II 0x1513 #define USB_PID_ANYSEE 0x861f #define USB_PID_ARTEC_T14BR 0x810f -#define USB_PID_ARTEC_T14_COLD 0x810b -#define USB_PID_ARTEC_T14_WARM 0x810c #define USB_PID_ASUS_U3000 0x171f #define USB_PID_ASUS_U3000H 0x1736 #define USB_PID_ASUS_U3100 0x173f @@ -195,12 +193,8 @@ #define USB_PID_DIBCOM_TFE8096P 0x1f9C #define USB_PID_DIGITALNOW_BLUEBIRD_DUAL_1_COLD 0xdb54 #define USB_PID_DIGITALNOW_BLUEBIRD_DUAL_1_WARM 0xdb55 -#define USB_PID_DIGIVOX_MINI_SL_COLD 0xe360 -#define USB_PID_DIGIVOX_MINI_SL_WARM 0xe361 #define USB_PID_DPOSH_M9206_COLD 0x9206 #define USB_PID_DPOSH_M9206_WARM 0xa090 -#define USB_PID_DVB_T_USB_STICK_HIGH_SPEED_COLD 0x5000 -#define USB_PID_DVB_T_USB_STICK_HIGH_SPEED_WARM 0x5001 #define USB_PID_DVICO_BLUEBIRD_DUAL_1_COLD 0xdb50 #define USB_PID_DVICO_BLUEBIRD_DUAL_1_WARM 0xdb51 #define USB_PID_DVICO_BLUEBIRD_DUAL_2_COLD 0xdb58 @@ -228,6 +222,8 @@ #define USB_PID_ELGATO_EYETV_SAT 0x002a #define USB_PID_ELGATO_EYETV_SAT_V2 0x0025 #define USB_PID_ELGATO_EYETV_SAT_V3 0x0036 +#define USB_PID_EMPIA_DIGIVOX_MINI_SL_COLD 0xe360 +#define USB_PID_EMPIA_DIGIVOX_MINI_SL_WARM 0xe361 #define USB_PID_EMPIA_VSTREAM_COLD 0x17de #define USB_PID_EMPIA_VSTREAM_WARM 0x17df #define USB_PID_EVOLVEO_XTRATV_STICK 0xa115 @@ -270,6 +266,8 @@ #define USB_PID_HAUPPAUGE_TIGER_ATSC_B210 0xb210 #define USB_PID_HAUPPAUGE_WINTV_NOVA_T_USB2_COLD 0x9300 #define USB_PID_HAUPPAUGE_WINTV_NOVA_T_USB2_WARM 0x9301 +#define USB_PID_HUMAX_DVB_T_STICK_HIGH_SPEED_COLD 0x5000 +#define USB_PID_HUMAX_DVB_T_STICK_HIGH_SPEED_WARM 0x5001 #define USB_PID_INTEL_CE9500 0x9500 #define USB_PID_ITETECH_IT9135 0x9135 #define USB_PID_ITETECH_IT9135_9005 0x9005 @@ -289,6 +287,8 @@ #define USB_PID_KWORLD_VSTREAM_COLD 0x17de #define USB_PID_KYE_DVB_T_COLD 0x701e #define USB_PID_KYE_DVB_T_WARM 0x701f +#define USB_PID_LEADTEK_WINFAST_DTV_DONGLE_COLD 0x6025 +#define USB_PID_LEADTEK_WINFAST_DTV_DONGLE_WARM 0x6026 #define USB_PID_LITEON_DVB_T_COLD 0xf000 #define USB_PID_LITEON_DVB_T_WARM 0xf001 #define USB_PID_MEDION_MD95700 0x0932 @@ -412,6 +412,8 @@ #define USB_PID_TWINHAN_VP7021_WARM 0x3208 #define USB_PID_TWINHAN_VP7041_COLD 0x3201 #define USB_PID_TWINHAN_VP7041_WARM 0x3202 +#define USB_PID_ULTIMA_ARTEC_T14_COLD 0x810b +#define USB_PID_ULTIMA_ARTEC_T14_WARM 0x810c #define USB_PID_ULTIMA_TVBOX_AN2235_COLD 0x8107 #define USB_PID_ULTIMA_TVBOX_AN2235_WARM 0x8108 #define USB_PID_ULTIMA_TVBOX_ANCHOR_COLD 0x2235 @@ -447,13 +449,11 @@ #define USB_PID_WIDEVIEW_WT220U_ZL0353_WARM 0x022b #define USB_PID_WINFAST_DTV2000DS 0x6a04 #define USB_PID_WINFAST_DTV2000DS_PLUS 0x6f12 -#define USB_PID_WINFAST_DTV_DONGLE_COLD 0x6025 #define USB_PID_WINFAST_DTV_DONGLE_GOLD 0x6029 #define USB_PID_WINFAST_DTV_DONGLE_H 0x60f6 #define USB_PID_WINFAST_DTV_DONGLE_MINID 0x6f0f #define USB_PID_WINFAST_DTV_DONGLE_STK7700P 0x6f00 #define USB_PID_WINFAST_DTV_DONGLE_STK7700P_2 0x6f01 -#define USB_PID_WINFAST_DTV_DONGLE_WARM 0x6026 #define USB_PID_WINTV_SOLOHD 0x0264 #define USB_PID_WINTV_SOLOHD_2 0x8268 #define USB_PID_XBOX_ONE_TUNER 0x02d5 -- cgit v1.2.3 From 3d59142ad94cf60b94b3dc94c19fdafa23aec8b1 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 28 Mar 2022 22:41:38 +0200 Subject: media: dvb-usb: dib0700_devices: use an enum for the device number The device number is currently a value that needs to be the same on two separate tables, but the code doesn't actually enforce it, leading to errors as boards get added or removed. Fix it by using an enum. Link: https://lore.kernel.org/linux-media/028699ec71158dbc49d710a4259eb8cdb7f673cb.1648499509.git.mchehab@kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/dvb-usb-ids.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h index 4dba939760ed..1b7d10f3d4aa 100644 --- a/include/media/dvb-usb-ids.h +++ b/include/media/dvb-usb-ids.h @@ -110,7 +110,6 @@ #define USB_PID_ANUBIS_LIFEVIEW_TV_WALKER_TWIN_WARM 0x0513 #define USB_PID_ANUBIS_MSI_DIGI_VOX_MINI_II 0x1513 #define USB_PID_ANYSEE 0x861f -#define USB_PID_ARTEC_T14BR 0x810f #define USB_PID_ASUS_U3000 0x171f #define USB_PID_ASUS_U3000H 0x1736 #define USB_PID_ASUS_U3100 0x173f @@ -158,7 +157,6 @@ #define USB_PID_CONCEPTRONIC_CTVDIGRCU 0xe397 #define USB_PID_CONEXANT_D680_DMB 0x86d6 #define USB_PID_CPYTO_REDI_PC50A 0xa803 -#define USB_PID_CREATIX_CTX1921 0x1921 #define USB_PID_CTVDIGDUAL_V2 0xe410 #define USB_PID_CYPRESS_DW2101 0x2101 #define USB_PID_CYPRESS_DW2102 0x2102 @@ -226,6 +224,7 @@ #define USB_PID_EMPIA_DIGIVOX_MINI_SL_WARM 0xe361 #define USB_PID_EMPIA_VSTREAM_COLD 0x17de #define USB_PID_EMPIA_VSTREAM_WARM 0x17df +#define USB_PID_EVOLUTEPC_TVWAY_PLUS 0x0002 #define USB_PID_EVOLVEO_XTRATV_STICK 0xa115 #define USB_PID_FREECOM_DVBT 0x0160 #define USB_PID_FREECOM_DVBT_2 0x0161 @@ -288,10 +287,15 @@ #define USB_PID_KYE_DVB_T_COLD 0x701e #define USB_PID_KYE_DVB_T_WARM 0x701f #define USB_PID_LEADTEK_WINFAST_DTV_DONGLE_COLD 0x6025 +#define USB_PID_LEADTEK_WINFAST_DTV_DONGLE_H 0x60f6 +#define USB_PID_LEADTEK_WINFAST_DTV_DONGLE_STK7700P 0x6f00 +#define USB_PID_LEADTEK_WINFAST_DTV_DONGLE_STK7700P_2 0x6f01 #define USB_PID_LEADTEK_WINFAST_DTV_DONGLE_WARM 0x6026 #define USB_PID_LITEON_DVB_T_COLD 0xf000 #define USB_PID_LITEON_DVB_T_WARM 0xf001 +#define USB_PID_MEDION_CREATIX_CTX1921 0x1921 #define USB_PID_MEDION_MD95700 0x0932 +#define USB_PID_MICROSOFT_XBOX_ONE_TUNER 0x02d5 #define USB_PID_MIGLIA_WT220U_ZAP250_COLD 0x0220 #define USB_PID_MSI_DIGIVOX_DUO 0x8801 #define USB_PID_MSI_DIGI_VOX_MINI_III 0x8807 @@ -313,6 +317,9 @@ #define USB_PID_PCTV_200E 0x020e #define USB_PID_PCTV_78E 0x025a #define USB_PID_PCTV_79E 0x0262 +#define USB_PID_PCTV_DIBCOM_STK8096PVR 0x1faa +#define USB_PID_PCTV_PINNACLE_PCTV282E 0x0248 +#define USB_PID_PCTV_PINNACLE_PCTV73ESE 0x0245 #define USB_PID_PINNACLE_EXPRESSCARD_320CX 0x022e #define USB_PID_PINNACLE_PCTV2000E 0x022c #define USB_PID_PINNACLE_PCTV282E 0x0248 @@ -408,10 +415,10 @@ #define USB_PID_TREKSTOR_DVBT 0x901b #define USB_PID_TREKSTOR_TERRES_2_0 0xC803 #define USB_PID_TURBOX_DTT_2000 0xd3a4 -#define USB_PID_TVWAY_PLUS 0x0002 #define USB_PID_TWINHAN_VP7021_WARM 0x3208 #define USB_PID_TWINHAN_VP7041_COLD 0x3201 #define USB_PID_TWINHAN_VP7041_WARM 0x3202 +#define USB_PID_ULTIMA_ARTEC_T14BR 0x810f #define USB_PID_ULTIMA_ARTEC_T14_COLD 0x810b #define USB_PID_ULTIMA_ARTEC_T14_WARM 0x810c #define USB_PID_ULTIMA_TVBOX_AN2235_COLD 0x8107 @@ -450,13 +457,9 @@ #define USB_PID_WINFAST_DTV2000DS 0x6a04 #define USB_PID_WINFAST_DTV2000DS_PLUS 0x6f12 #define USB_PID_WINFAST_DTV_DONGLE_GOLD 0x6029 -#define USB_PID_WINFAST_DTV_DONGLE_H 0x60f6 #define USB_PID_WINFAST_DTV_DONGLE_MINID 0x6f0f -#define USB_PID_WINFAST_DTV_DONGLE_STK7700P 0x6f00 -#define USB_PID_WINFAST_DTV_DONGLE_STK7700P_2 0x6f01 #define USB_PID_WINTV_SOLOHD 0x0264 #define USB_PID_WINTV_SOLOHD_2 0x8268 -#define USB_PID_XBOX_ONE_TUNER 0x02d5 #define USB_PID_XTENSIONS_XD_380 0x0381 #define USB_PID_YUAN_EC372S 0x1edc #define USB_PID_YUAN_MC770 0x0871 -- cgit v1.2.3 From f47a6113f4e87db7ca066635822e1b3ca3ed9514 Mon Sep 17 00:00:00 2001 From: Tzung-Bi Shih Date: Wed, 16 Feb 2022 16:03:03 +0800 Subject: platform/chrome: cros_ec: remove unused variable `was_wake_device` Reviewed-by: Prashant Malani Signed-off-by: Tzung-Bi Shih --- include/linux/platform_data/cros_ec_proto.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index df3c78c92ca2..c65971ec90ea 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -76,8 +76,6 @@ struct cros_ec_command { * struct cros_ec_device - Information about a ChromeOS EC device. * @phys_name: Name of physical comms layer (e.g. 'i2c-4'). * @dev: Device pointer for physical comms device - * @was_wake_device: True if this device was set to wake the system from - * sleep at the last suspend. * @cros_class: The class structure for this device. * @cmd_readmem: Direct read of the EC memory-mapped region, if supported. * @offset: Is within EC_LPC_ADDR_MEMMAP region. @@ -137,7 +135,6 @@ struct cros_ec_device { /* These are used by other drivers that want to talk to the EC */ const char *phys_name; struct device *dev; - bool was_wake_device; struct class *cros_class; int (*cmd_readmem)(struct cros_ec_device *ec, unsigned int offset, unsigned int bytes, void *dest); -- cgit v1.2.3 From 39772efd98adecbd5b8c6096d465d2fcbafbde6a Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sun, 13 Mar 2022 13:39:49 +0100 Subject: clk: imx8mp: Add DISP2 pixel clock Add pixel clock for second LCDIFv3 interface. Both LCDIFv3 interfaces use the same set of parent clock, so deduplicate imx8mp_media_disp1_pix_sels into common imx8mp_media_disp_pix_sels and use it for both. Signed-off-by: Marek Vasut Cc: Abel Vesa Cc: Fabio Estevam Cc: NXP Linux Team Cc: Peng Fan Cc: Shawn Guo Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20220313123949.207284-1-marex@denx.de Signed-off-by: Abel Vesa --- include/dt-bindings/clock/imx8mp-clock.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/clock/imx8mp-clock.h b/include/dt-bindings/clock/imx8mp-clock.h index 235c7a00d379..e05d21bf7813 100644 --- a/include/dt-bindings/clock/imx8mp-clock.h +++ b/include/dt-bindings/clock/imx8mp-clock.h @@ -318,7 +318,9 @@ #define IMX8MP_CLK_HSIO_AXI 311 #define IMX8MP_CLK_MEDIA_ISP 312 -#define IMX8MP_CLK_END 313 +#define IMX8MP_CLK_MEDIA_DISP2_PIX 313 + +#define IMX8MP_CLK_END 314 #define IMX8MP_CLK_AUDIOMIX_SAI1_IPG 0 #define IMX8MP_CLK_AUDIOMIX_SAI1_MCLK1 1 -- cgit v1.2.3 From c246f9b5fd617fe487f8b6f18851703f468501d6 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 18 Apr 2022 09:42:25 +0300 Subject: devlink: add support to create line card and expose to user Extend the devlink API so the driver is going to be able to create and destroy linecard instances. There can be multiple line cards per devlink device. Expose this new type of object over devlink netlink API to the userspace, with notifications. Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/devlink.h | 4 ++++ include/uapi/linux/devlink.h | 7 +++++++ 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index a30180c0988a..7aabdfb3bc6a 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -22,6 +22,7 @@ #include struct devlink; +struct devlink_linecard; struct devlink_port_phys_attrs { u32 port_number; /* Same value as "split group". @@ -1536,6 +1537,9 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, int devlink_rate_leaf_create(struct devlink_port *port, void *priv); void devlink_rate_leaf_destroy(struct devlink_port *devlink_port); void devlink_rate_nodes_destroy(struct devlink *devlink); +struct devlink_linecard *devlink_linecard_create(struct devlink *devlink, + unsigned int linecard_index); +void devlink_linecard_destroy(struct devlink_linecard *linecard); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index b897b80770f6..59c33ed2d3e7 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -131,6 +131,11 @@ enum devlink_command { DEVLINK_CMD_RATE_NEW, DEVLINK_CMD_RATE_DEL, + DEVLINK_CMD_LINECARD_GET, /* can dump */ + DEVLINK_CMD_LINECARD_SET, + DEVLINK_CMD_LINECARD_NEW, + DEVLINK_CMD_LINECARD_DEL, + /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 @@ -553,6 +558,8 @@ enum devlink_attr { DEVLINK_ATTR_REGION_MAX_SNAPSHOTS, /* u32 */ + DEVLINK_ATTR_LINECARD_INDEX, /* u32 */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, -- cgit v1.2.3 From fcdc8ce23a309c26a67fc613a741d9b21a248311 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 18 Apr 2022 09:42:26 +0300 Subject: devlink: implement line card provisioning In order to be able to configure all needed stuff on a port/netdevice of a line card without the line card being present, introduce line card provisioning. Basically by setting a type, provisioning process will start and driver is supposed to create a placeholder for instances (ports/netdevices) for a line card type. Allow the user to query the supported line card types over line card get command. Then implement two netlink command SET to allow user to set/unset the card type. On the driver API side, add provision/unprovision ops and supported types array to be advertised. Upon provision op call, the driver should take care of creating the instances for the particular line card type. Introduce provision_set/clear() functions to be called by the driver once the provisioning/unprovisioning is done on its side. These helpers are not to be called directly due to the async nature of provisioning. Example: $ devlink port # No ports are listed $ devlink lc pci/0000:01:00.0: lc 1 state unprovisioned supported_types: 16x100G lc 2 state unprovisioned supported_types: 16x100G lc 3 state unprovisioned supported_types: 16x100G lc 4 state unprovisioned supported_types: 16x100G lc 5 state unprovisioned supported_types: 16x100G lc 6 state unprovisioned supported_types: 16x100G lc 7 state unprovisioned supported_types: 16x100G lc 8 state unprovisioned supported_types: 16x100G $ devlink lc set pci/0000:01:00.0 lc 8 type 16x100G $ devlink lc show pci/0000:01:00.0 lc 8 pci/0000:01:00.0: lc 8 state active type 16x100G supported_types: 16x100G $ devlink port pci/0000:01:00.0/0: type notset flavour cpu port 0 splittable false pci/0000:01:00.0/53: type eth netdev enp1s0nl8p1 flavour physical lc 8 port 1 splittable true lanes 4 pci/0000:01:00.0/54: type eth netdev enp1s0nl8p2 flavour physical lc 8 port 2 splittable true lanes 4 pci/0000:01:00.0/55: type eth netdev enp1s0nl8p3 flavour physical lc 8 port 3 splittable true lanes 4 pci/0000:01:00.0/56: type eth netdev enp1s0nl8p4 flavour physical lc 8 port 4 splittable true lanes 4 pci/0000:01:00.0/57: type eth netdev enp1s0nl8p5 flavour physical lc 8 port 5 splittable true lanes 4 pci/0000:01:00.0/58: type eth netdev enp1s0nl8p6 flavour physical lc 8 port 6 splittable true lanes 4 pci/0000:01:00.0/59: type eth netdev enp1s0nl8p7 flavour physical lc 8 port 7 splittable true lanes 4 pci/0000:01:00.0/60: type eth netdev enp1s0nl8p8 flavour physical lc 8 port 8 splittable true lanes 4 pci/0000:01:00.0/61: type eth netdev enp1s0nl8p9 flavour physical lc 8 port 9 splittable true lanes 4 pci/0000:01:00.0/62: type eth netdev enp1s0nl8p10 flavour physical lc 8 port 10 splittable true lanes 4 pci/0000:01:00.0/63: type eth netdev enp1s0nl8p11 flavour physical lc 8 port 11 splittable true lanes 4 pci/0000:01:00.0/64: type eth netdev enp1s0nl8p12 flavour physical lc 8 port 12 splittable true lanes 4 pci/0000:01:00.0/125: type eth netdev enp1s0nl8p13 flavour physical lc 8 port 13 splittable true lanes 4 pci/0000:01:00.0/126: type eth netdev enp1s0nl8p14 flavour physical lc 8 port 14 splittable true lanes 4 pci/0000:01:00.0/127: type eth netdev enp1s0nl8p15 flavour physical lc 8 port 15 splittable true lanes 4 pci/0000:01:00.0/128: type eth netdev enp1s0nl8p16 flavour physical lc 8 port 16 splittable true lanes 4 $ devlink lc set pci/0000:01:00.0 lc 8 notype Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/devlink.h | 43 +++++++++++++++++++++++++++++++++++++++++-- include/uapi/linux/devlink.h | 15 +++++++++++++++ 2 files changed, 56 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 7aabdfb3bc6a..3e49d4ff498c 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -149,6 +149,40 @@ struct devlink_port_new_attrs { sfnum_valid:1; }; +/** + * struct devlink_linecard_ops - Linecard operations + * @provision: callback to provision the linecard slot with certain + * type of linecard. As a result of this operation, + * driver is expected to eventually (could be after + * the function call returns) call one of: + * devlink_linecard_provision_set() + * devlink_linecard_provision_fail() + * @unprovision: callback to unprovision the linecard slot. As a result + * of this operation, driver is expected to eventually + * (could be after the function call returns) call + * devlink_linecard_provision_clear() + * devlink_linecard_provision_fail() + * @same_provision: callback to ask the driver if linecard is already + * provisioned in the same way user asks this linecard to be + * provisioned. + * @types_count: callback to get number of supported types + * @types_get: callback to get next type in list + */ +struct devlink_linecard_ops { + int (*provision)(struct devlink_linecard *linecard, void *priv, + const char *type, const void *type_priv, + struct netlink_ext_ack *extack); + int (*unprovision)(struct devlink_linecard *linecard, void *priv, + struct netlink_ext_ack *extack); + bool (*same_provision)(struct devlink_linecard *linecard, void *priv, + const char *type, const void *type_priv); + unsigned int (*types_count)(struct devlink_linecard *linecard, + void *priv); + void (*types_get)(struct devlink_linecard *linecard, + void *priv, unsigned int index, const char **type, + const void **type_priv); +}; + struct devlink_sb_pool_info { enum devlink_sb_pool_type pool_type; u32 size; @@ -1537,9 +1571,14 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, int devlink_rate_leaf_create(struct devlink_port *port, void *priv); void devlink_rate_leaf_destroy(struct devlink_port *devlink_port); void devlink_rate_nodes_destroy(struct devlink *devlink); -struct devlink_linecard *devlink_linecard_create(struct devlink *devlink, - unsigned int linecard_index); +struct devlink_linecard * +devlink_linecard_create(struct devlink *devlink, unsigned int linecard_index, + const struct devlink_linecard_ops *ops, void *priv); void devlink_linecard_destroy(struct devlink_linecard *linecard); +void devlink_linecard_provision_set(struct devlink_linecard *linecard, + const char *type); +void devlink_linecard_provision_clear(struct devlink_linecard *linecard); +void devlink_linecard_provision_fail(struct devlink_linecard *linecard); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 59c33ed2d3e7..de91e4a0d476 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -343,6 +343,18 @@ enum devlink_reload_limit { #define DEVLINK_RELOAD_LIMITS_VALID_MASK (_BITUL(__DEVLINK_RELOAD_LIMIT_MAX) - 1) +enum devlink_linecard_state { + DEVLINK_LINECARD_STATE_UNSPEC, + DEVLINK_LINECARD_STATE_UNPROVISIONED, + DEVLINK_LINECARD_STATE_UNPROVISIONING, + DEVLINK_LINECARD_STATE_PROVISIONING, + DEVLINK_LINECARD_STATE_PROVISIONING_FAILED, + DEVLINK_LINECARD_STATE_PROVISIONED, + + __DEVLINK_LINECARD_STATE_MAX, + DEVLINK_LINECARD_STATE_MAX = __DEVLINK_LINECARD_STATE_MAX - 1 +}; + enum devlink_attr { /* don't change the order or add anything between, this is ABI! */ DEVLINK_ATTR_UNSPEC, @@ -559,6 +571,9 @@ enum devlink_attr { DEVLINK_ATTR_REGION_MAX_SNAPSHOTS, /* u32 */ DEVLINK_ATTR_LINECARD_INDEX, /* u32 */ + DEVLINK_ATTR_LINECARD_STATE, /* u8 */ + DEVLINK_ATTR_LINECARD_TYPE, /* string */ + DEVLINK_ATTR_LINECARD_SUPPORTED_TYPES, /* nested */ /* add new attributes above here, update the policy in devlink.c */ -- cgit v1.2.3 From fc9f50d5b366cd9f35bdee22fe3f8d77833cb1d8 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 18 Apr 2022 09:42:27 +0300 Subject: devlink: implement line card active state Allow driver to mark a line card as active. Expose this state to the userspace over devlink netlink interface with proper notifications. 'active' state means that line card was plugged in after being provisioned. Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/devlink.h | 2 ++ include/uapi/linux/devlink.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 3e49d4ff498c..d8061a11fee6 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1579,6 +1579,8 @@ void devlink_linecard_provision_set(struct devlink_linecard *linecard, const char *type); void devlink_linecard_provision_clear(struct devlink_linecard *linecard); void devlink_linecard_provision_fail(struct devlink_linecard *linecard); +void devlink_linecard_activate(struct devlink_linecard *linecard); +void devlink_linecard_deactivate(struct devlink_linecard *linecard); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index de91e4a0d476..b3d40a5d72ff 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -350,6 +350,7 @@ enum devlink_linecard_state { DEVLINK_LINECARD_STATE_PROVISIONING, DEVLINK_LINECARD_STATE_PROVISIONING_FAILED, DEVLINK_LINECARD_STATE_PROVISIONED, + DEVLINK_LINECARD_STATE_ACTIVE, __DEVLINK_LINECARD_STATE_MAX, DEVLINK_LINECARD_STATE_MAX = __DEVLINK_LINECARD_STATE_MAX - 1 -- cgit v1.2.3 From b837585985386e05478cb17868d23a6fa87c4f8d Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 18 Apr 2022 09:42:28 +0300 Subject: devlink: add port to line card relationship set In order to properly inform user about relationship between port and line card, introduce a driver API to set line card for a port. Use this information to extend port devlink netlink message by line card index and also include the line card index into phys_port_name and by that into a netdevice name. Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/devlink.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index d8061a11fee6..2a2a2a0c93f7 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -136,6 +136,7 @@ struct devlink_port { struct mutex reporters_lock; /* Protects reporter_list */ struct devlink_rate *devlink_rate; + struct devlink_linecard *linecard; }; struct devlink_port_new_attrs { @@ -1571,6 +1572,8 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, int devlink_rate_leaf_create(struct devlink_port *port, void *priv); void devlink_rate_leaf_destroy(struct devlink_port *devlink_port); void devlink_rate_nodes_destroy(struct devlink *devlink); +void devlink_port_linecard_set(struct devlink_port *devlink_port, + struct devlink_linecard *linecard); struct devlink_linecard * devlink_linecard_create(struct devlink *devlink, unsigned int linecard_index, const struct devlink_linecard_ops *ops, void *priv); -- cgit v1.2.3 From 5f0614a55ecebdf55f1a17db0b5f6b787ed009f1 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Sun, 17 Apr 2022 22:27:13 -0400 Subject: block: change exported IO accounting interface from gendisk to bdev Export IO accounting interfaces in terms of block_device now that gendisk has become more internal to block core. Rename __part_{start,end}_io_acct's first argument from part to bdev. Rename __part_{start,end}_io_acct to bdev_{start,end}_io_acct and export them. Remove disk_{start,end}_io_acct and update caller (zram) to use bdev_{start,end}_io_acct. DM can now be updated to use bdev_{start,end}_io_acct. Signed-off-by: Ming Lei Signed-off-by: Mike Snitzer Link: https://lore.kernel.org/r/20220418022733.56168-2-snitzer@kernel.org Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c9b5925af5a3..34724b15813b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1463,9 +1463,10 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } -unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, - unsigned int op); -void disk_end_io_acct(struct gendisk *disk, unsigned int op, +unsigned long bdev_start_io_acct(struct block_device *bdev, + unsigned int sectors, unsigned int op, + unsigned long start_time); +void bdev_end_io_acct(struct block_device *bdev, unsigned int op, unsigned long start_time); void bio_start_io_acct_time(struct bio *bio, unsigned long start_time); -- cgit v1.2.3 From dbdc1be32591af023db2812706f01e6cd2f42bfc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 30 Mar 2022 07:29:06 +0200 Subject: block: add a disk_openers helper Add a helper that returns the openers for a given gendisk to avoid having drivers poke into disk->part0 to get at this information in a somewhat cumbersome way. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20220330052917.2566582-5-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c9b5925af5a3..436645bde13f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -176,6 +176,21 @@ static inline bool disk_live(struct gendisk *disk) return !inode_unhashed(disk->part0->bd_inode); } +/** + * disk_openers - returns how many openers are there for a disk + * @disk: disk to check + * + * This returns the number of openers for a disk. Note that this value is only + * stable if disk->open_mutex is held. + * + * Note: Due to a quirk in the block layer open code, each open partition is + * only counted once even if there are multiple openers. + */ +static inline unsigned int disk_openers(struct gendisk *disk) +{ + return disk->part0->bd_openers; +} + /* * The gendisk is refcounted by the part0 block_device, and the bd_device * therein is also used for device model presentation in sysfs. -- cgit v1.2.3 From 9acf381f3e8f715175c29f4b6d722f6b6797d139 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 30 Mar 2022 07:29:07 +0200 Subject: block: turn bdev->bd_openers into an atomic_t All manipulation of bd_openers is under disk->open_mutex and will remain so for the foreseeable future. But at least one place reads it without the lock (blkdev_get) and there are more to be added. So make sure the compiler does not do turn the increments and decrements into non-atomic sequences by using an atomic_t. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20220330052917.2566582-6-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 2 +- include/linux/blkdev.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 4968cb17b13b..c62274466e72 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -44,7 +44,7 @@ struct block_device { unsigned long bd_stamp; bool bd_read_only; /* read-only policy */ dev_t bd_dev; - int bd_openers; + atomic_t bd_openers; struct inode * bd_inode; /* will die */ struct super_block * bd_super; void * bd_claiming; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 436645bde13f..afad3d1d0dac 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -188,7 +188,7 @@ static inline bool disk_live(struct gendisk *disk) */ static inline unsigned int disk_openers(struct gendisk *disk) { - return disk->part0->bd_openers; + return atomic_read(&disk->part0->bd_openers); } /* -- cgit v1.2.3 From 57b888ca2541785de2fcb90575b378921919b6c0 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Fri, 18 Mar 2022 09:54:22 -0700 Subject: platform/chrome: Re-introduce cros_ec_cmd_xfer and use it for ioctls Commit 413dda8f2c6f ("platform/chrome: cros_ec_chardev: Use cros_ec_cmd_xfer_status helper") inadvertendly changed the userspace ABI. Previously, cros_ec ioctls would only report errors if the EC communication failed, and otherwise return success and the result of the EC communication. An EC command execution failure was reported in the EC response field. The above mentioned commit changed this behavior, and the ioctl itself would fail. This breaks userspace commands trying to analyze the EC command execution error since the actual EC command response is no longer reported to userspace. Fix the problem by re-introducing the cros_ec_cmd_xfer() helper, and use it to handle ioctl messages. Fixes: 413dda8f2c6f ("platform/chrome: cros_ec_chardev: Use cros_ec_cmd_xfer_status helper") Cc: Daisuke Nojiri Cc: Rob Barnes Cc: Rajat Jain Cc: Brian Norris Cc: Parth Malkan Reviewed-by: Daisuke Nojiri Reviewed-by: Brian Norris Signed-off-by: Guenter Roeck Signed-off-by: Tzung-Bi Shih --- include/linux/platform_data/cros_ec_proto.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index c65971ec90ea..138fd912c808 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -213,6 +213,9 @@ int cros_ec_prepare_tx(struct cros_ec_device *ec_dev, int cros_ec_check_result(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); +int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, + struct cros_ec_command *msg); + int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); -- cgit v1.2.3 From 2f1e85b1aee459b7d0fd981839042c6a38ffaf0c Mon Sep 17 00:00:00 2001 From: Tonghao Zhang Date: Sat, 16 Apr 2022 00:40:45 +0800 Subject: net: sched: use queue_mapping to pick tx queue This patch fixes issue: * If we install tc filters with act_skbedit in clsact hook. It doesn't work, because netdev_core_pick_tx() overwrites queue_mapping. $ tc filter ... action skbedit queue_mapping 1 And this patch is useful: * We can use FQ + EDT to implement efficient policies. Tx queues are picked by xps, ndo_select_queue of netdev driver, or skb hash in netdev_core_pick_tx(). In fact, the netdev driver, and skb hash are _not_ under control. xps uses the CPUs map to select Tx queues, but we can't figure out which task_struct of pod/containter running on this cpu in most case. We can use clsact filters to classify one pod/container traffic to one Tx queue. Why ? In containter networking environment, there are two kinds of pod/ containter/net-namespace. One kind (e.g. P1, P2), the high throughput is key in these applications. But avoid running out of network resource, the outbound traffic of these pods is limited, using or sharing one dedicated Tx queues assigned HTB/TBF/FQ Qdisc. Other kind of pods (e.g. Pn), the low latency of data access is key. And the traffic is not limited. Pods use or share other dedicated Tx queues assigned FIFO Qdisc. This choice provides two benefits. First, contention on the HTB/FQ Qdisc lock is significantly reduced since fewer CPUs contend for the same queue. More importantly, Qdisc contention can be eliminated completely if each CPU has its own FIFO Qdisc for the second kind of pods. There must be a mechanism in place to support classifying traffic based on pods/container to different Tx queues. Note that clsact is outside of Qdisc while Qdisc can run a classifier to select a sub-queue under the lock. In general recording the decision in the skb seems a little heavy handed. This patch introduces a per-CPU variable, suggested by Eric. The xmit.skip_txqueue flag is firstly cleared in __dev_queue_xmit(). - Tx Qdisc may install that skbedit actions, then xmit.skip_txqueue flag is set in qdisc->enqueue() though tx queue has been selected in netdev_tx_queue_mapping() or netdev_core_pick_tx(). That flag is cleared firstly in __dev_queue_xmit(), is useful: - Avoid picking Tx queue with netdev_tx_queue_mapping() in next netdev in such case: eth0 macvlan - eth0.3 vlan - eth0 ixgbe-phy: For example, eth0, macvlan in pod, which root Qdisc install skbedit queue_mapping, send packets to eth0.3, vlan in host. In __dev_queue_xmit() of eth0.3, clear the flag, does not select tx queue according to skb->queue_mapping because there is no filters in clsact or tx Qdisc of this netdev. Same action taked in eth0, ixgbe in Host. - Avoid picking Tx queue for next packet. If we set xmit.skip_txqueue in tx Qdisc (qdisc->enqueue()), the proper way to clear it is clearing it in __dev_queue_xmit when processing next packets. For performance reasons, use the static key. If user does not config the NET_EGRESS, the patch will not be compiled. +----+ +----+ +----+ | P1 | | P2 | | Pn | +----+ +----+ +----+ | | | +-----------+-----------+ | | clsact/skbedit | MQ v +-----------+-----------+ | q0 | q1 | qn v v v HTB/FQ HTB/FQ ... FIFO Cc: Jamal Hadi Salim Cc: Cong Wang Cc: Jiri Pirko Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Jonathan Lemon Cc: Eric Dumazet Cc: Alexander Lobakin Cc: Paolo Abeni Cc: Talal Ahmad Cc: Kevin Hao Cc: Ilias Apalodimas Cc: Kees Cook Cc: Kumar Kartikeya Dwivedi Cc: Antoine Tenart Cc: Wei Wang Cc: Arnd Bergmann Suggested-by: Eric Dumazet Signed-off-by: Tonghao Zhang Acked-by: Jamal Hadi Salim Signed-off-by: Paolo Abeni --- include/linux/netdevice.h | 3 +++ include/linux/rtnetlink.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a602f29365b0..7dccbfd1bf56 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3061,6 +3061,9 @@ struct softnet_data { struct { u16 recursion; u8 more; +#ifdef CONFIG_NET_EGRESS + u8 skip_txqueue; +#endif } xmit; #ifdef CONFIG_RPS /* input_queue_head should be written by cpu owning this struct, diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 7f970b16da3a..ae2c6a3cec5d 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -100,6 +100,7 @@ void net_dec_ingress_queue(void); #ifdef CONFIG_NET_EGRESS void net_inc_egress_queue(void); void net_dec_egress_queue(void); +void netdev_xmit_skip_txqueue(bool skip); #endif void rtnetlink_init(void); -- cgit v1.2.3 From 38a6f0865796e26fc38fff4858f681d9ae76fa0f Mon Sep 17 00:00:00 2001 From: Tonghao Zhang Date: Sat, 16 Apr 2022 00:40:46 +0800 Subject: net: sched: support hash selecting tx queue This patch allows users to pick queue_mapping, range from A to B. Then we can load balance packets from A to B tx queue. The range is an unsigned 16bit value in decimal format. $ tc filter ... action skbedit queue_mapping skbhash A B "skbedit queue_mapping QUEUE_MAPPING" (from "man 8 tc-skbedit") is enhanced with flags: SKBEDIT_F_TXQ_SKBHASH +----+ +----+ +----+ | P1 | | P2 | | Pn | +----+ +----+ +----+ | | | +-----------+-----------+ | | clsact/skbedit | MQ v +-----------+-----------+ | q0 | qn | qm v v v HTB/FQ FIFO ... FIFO For example: If P1 sends out packets to different Pods on other host, and we want distribute flows from qn - qm. Then we can use skb->hash as hash. setup commands: $ NETDEV=eth0 $ ip netns add n1 $ ip link add ipv1 link $NETDEV type ipvlan mode l2 $ ip link set ipv1 netns n1 $ ip netns exec n1 ifconfig ipv1 2.2.2.100/24 up $ tc qdisc add dev $NETDEV clsact $ tc filter add dev $NETDEV egress protocol ip prio 1 \ flower skip_hw src_ip 2.2.2.100 action skbedit queue_mapping skbhash 2 6 $ tc qdisc add dev $NETDEV handle 1: root mq $ tc qdisc add dev $NETDEV parent 1:1 handle 2: htb $ tc class add dev $NETDEV parent 2: classid 2:1 htb rate 100kbit $ tc class add dev $NETDEV parent 2: classid 2:2 htb rate 200kbit $ tc qdisc add dev $NETDEV parent 1:2 tbf rate 100mbit burst 100mb latency 1 $ tc qdisc add dev $NETDEV parent 1:3 pfifo $ tc qdisc add dev $NETDEV parent 1:4 pfifo $ tc qdisc add dev $NETDEV parent 1:5 pfifo $ tc qdisc add dev $NETDEV parent 1:6 pfifo $ tc qdisc add dev $NETDEV parent 1:7 pfifo $ ip netns exec n1 iperf3 -c 2.2.2.1 -i 1 -t 10 -P 10 pick txqueue from 2 - 6: $ ethtool -S $NETDEV | grep -i tx_queue_[0-9]_bytes tx_queue_0_bytes: 42 tx_queue_1_bytes: 0 tx_queue_2_bytes: 11442586444 tx_queue_3_bytes: 7383615334 tx_queue_4_bytes: 3981365579 tx_queue_5_bytes: 3983235051 tx_queue_6_bytes: 6706236461 tx_queue_7_bytes: 42 tx_queue_8_bytes: 0 tx_queue_9_bytes: 0 txqueues 2 - 6 are mapped to classid 1:3 - 1:7 $ tc -s class show dev $NETDEV ... class mq 1:3 root leaf 8002: Sent 11949133672 bytes 7929798 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:4 root leaf 8003: Sent 7710449050 bytes 5117279 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:5 root leaf 8004: Sent 4157648675 bytes 2758990 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:6 root leaf 8005: Sent 4159632195 bytes 2759990 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:7 root leaf 8006: Sent 7003169603 bytes 4646912 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 ... Cc: Jamal Hadi Salim Cc: Cong Wang Cc: Jiri Pirko Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Jonathan Lemon Cc: Eric Dumazet Cc: Alexander Lobakin Cc: Paolo Abeni Cc: Talal Ahmad Cc: Kevin Hao Cc: Ilias Apalodimas Cc: Kees Cook Cc: Kumar Kartikeya Dwivedi Cc: Antoine Tenart Cc: Wei Wang Cc: Arnd Bergmann Signed-off-by: Tonghao Zhang Reviewed-by: Jamal Hadi Salim Signed-off-by: Paolo Abeni --- include/net/tc_act/tc_skbedit.h | 1 + include/uapi/linux/tc_act/tc_skbedit.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h index cab8229b9bed..dc1079f28e13 100644 --- a/include/net/tc_act/tc_skbedit.h +++ b/include/net/tc_act/tc_skbedit.h @@ -17,6 +17,7 @@ struct tcf_skbedit_params { u32 mark; u32 mask; u16 queue_mapping; + u16 mapping_mod; u16 ptype; struct rcu_head rcu; }; diff --git a/include/uapi/linux/tc_act/tc_skbedit.h b/include/uapi/linux/tc_act/tc_skbedit.h index 800e93377218..6cb6101208d0 100644 --- a/include/uapi/linux/tc_act/tc_skbedit.h +++ b/include/uapi/linux/tc_act/tc_skbedit.h @@ -29,6 +29,7 @@ #define SKBEDIT_F_PTYPE 0x8 #define SKBEDIT_F_MASK 0x10 #define SKBEDIT_F_INHERITDSFIELD 0x20 +#define SKBEDIT_F_TXQ_SKBHASH 0x40 struct tc_skbedit { tc_gen; @@ -45,6 +46,7 @@ enum { TCA_SKBEDIT_PTYPE, TCA_SKBEDIT_MASK, TCA_SKBEDIT_FLAGS, + TCA_SKBEDIT_QUEUE_MAPPING_MAX, __TCA_SKBEDIT_MAX }; #define TCA_SKBEDIT_MAX (__TCA_SKBEDIT_MAX - 1) -- cgit v1.2.3 From 15527fee767f592d894d954d78cf8af3685cda6d Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Thu, 14 Apr 2022 13:48:03 -0500 Subject: ASoC: SOF: add definitions for different IPC types MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add enum type to allow for different types of IPCs. The IPCv4 is intended for Intel only as a convergence path with firmware used in Windows. Follow-up patches will introduce different abstractions with .ops and different search paths for firmware and topology files. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Bard Liao Reviewed-by: Rander Wang Reviewed-by: Péter Ujfalusi Link: https://lore.kernel.org/r/20220414184817.362215-2-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/sound/sof.h b/include/sound/sof.h index 7cdfc954df12..2658a38be5bd 100644 --- a/include/sound/sof.h +++ b/include/sound/sof.h @@ -47,6 +47,13 @@ enum sof_dsp_power_states { SOF_DSP_PM_D3, }; +/* Definitions for multiple IPCs */ +enum sof_ipc_type { + SOF_IPC, + SOF_INTEL_IPC4, + SOF_IPC_TYPE_COUNT +}; + /* * SOF Platform data. */ @@ -83,6 +90,8 @@ struct snd_sof_pdata { const struct snd_soc_acpi_mach *machine; void *hw_pdata; + + enum sof_ipc_type ipc_type; }; /* -- cgit v1.2.3 From a375791512254c154fd0d3e4091c78f4b92a5c66 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Thu, 14 Apr 2022 13:48:04 -0500 Subject: ASoC: SOF: add path indirection to each IPC type MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With the addition of the IPCv4, we need the ability to select different paths for firmware and topologies. First add an indirection. Follow-up patches will add mechanisms to select a default IPC or override it. No functionality change in this patch. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Bard Liao Reviewed-by: Rander Wang Reviewed-by: Péter Ujfalusi Link: https://lore.kernel.org/r/20220414184817.362215-3-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/sound/sof.h b/include/sound/sof.h index 2658a38be5bd..69066fe064da 100644 --- a/include/sound/sof.h +++ b/include/sound/sof.h @@ -125,8 +125,8 @@ struct sof_dev_desc { const char *nocodec_tplg_filename; /* defaults paths for firmware and topology files */ - const char *default_fw_path; - const char *default_tplg_path; + const char *default_fw_path[SOF_IPC_TYPE_COUNT]; + const char *default_tplg_path[SOF_IPC_TYPE_COUNT]; /* default firmware name */ const char *default_fw_filename; -- cgit v1.2.3 From 0cf8ff05e5d2b94b3ccf8a1fbfc633ecb0be56b0 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Thu, 14 Apr 2022 13:48:05 -0500 Subject: ASoC: SOF: add default IPC capability and file paths MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds a default IPC type for each platform, along with file paths to be used for each IPC type. To make reviews simpler, we only modify platform descriptors in this table, the information will be used in the next patch. The Intel IPCv4 is only supported on Intel platforms after APL, and not by default. In follow-up patches, support for SKL and KBL will be added, and in those two cases the IPCv4 will be the default (and only supported mode). Signed-off-by: Pierre-Louis Bossart Reviewed-by: Bard Liao Reviewed-by: Rander Wang Reviewed-by: Péter Ujfalusi Link: https://lore.kernel.org/r/20220414184817.362215-4-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/sound/sof.h b/include/sound/sof.h index 69066fe064da..a65af85a4074 100644 --- a/include/sound/sof.h +++ b/include/sound/sof.h @@ -124,6 +124,10 @@ struct sof_dev_desc { /* defaults for no codec mode */ const char *nocodec_tplg_filename; + /* information on supported IPCs */ + unsigned int ipc_supported_mask; + enum sof_ipc_type ipc_default; + /* defaults paths for firmware and topology files */ const char *default_fw_path[SOF_IPC_TYPE_COUNT]; const char *default_tplg_path[SOF_IPC_TYPE_COUNT]; -- cgit v1.2.3 From a97abb3cae31b4e2420da96b95e54756333f2cc3 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Thu, 14 Apr 2022 13:48:06 -0500 Subject: ASoC: SOF: add IPC-dependent file names MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To avoid misleading file names, use different names for INTEL_IPC4 firmware files. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Bard Liao Reviewed-by: Rander Wang Reviewed-by: Péter Ujfalusi Reviewed-by: Chao Song Link: https://lore.kernel.org/r/20220414184817.362215-5-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/sof.h b/include/sound/sof.h index a65af85a4074..96997650be65 100644 --- a/include/sound/sof.h +++ b/include/sound/sof.h @@ -133,7 +133,7 @@ struct sof_dev_desc { const char *default_tplg_path[SOF_IPC_TYPE_COUNT]; /* default firmware name */ - const char *default_fw_filename; + const char *default_fw_filename[SOF_IPC_TYPE_COUNT]; const struct snd_sof_dsp_ops *ops; }; -- cgit v1.2.3 From 856601e5a7ebe69b1c07adef7be80f9a03884329 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Thu, 14 Apr 2022 13:48:10 -0500 Subject: ASoC: SOF: remove const qualifier for 'struct snd_sof_dsp_ops' MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now that we start having multiple platforms with minor variants, the use of the const qualifier for 'dsp_ops' is starting to be sub-optimal: the structures are copied across platforms, with only a couple of members that differ. This patch removes the const qualifier without any functionality changes, and adds an optional initialization callback. In follow-up patches, the dsp_ops will revisited for Intel HDaudio platforms, with the differences added programmatically over a common baseline. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Reviewed-by: Péter Ujfalusi Reviewed-by: Kai Vehmanen Reviewed-by: Rander Wang Reviewed-by: Bard Liao Link: https://lore.kernel.org/r/20220414184817.362215-9-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/sof.h b/include/sound/sof.h index 96997650be65..1a82a0db5e7f 100644 --- a/include/sound/sof.h +++ b/include/sound/sof.h @@ -16,6 +16,7 @@ #include struct snd_sof_dsp_ops; +struct snd_sof_dev; /** * enum sof_fw_state - DSP firmware state definitions @@ -135,7 +136,8 @@ struct sof_dev_desc { /* default firmware name */ const char *default_fw_filename[SOF_IPC_TYPE_COUNT]; - const struct snd_sof_dsp_ops *ops; + struct snd_sof_dsp_ops *ops; + int (*ops_init)(struct snd_sof_dev *sdev); }; int sof_dai_get_mclk(struct snd_soc_pcm_runtime *rtd); -- cgit v1.2.3 From 99a15348d5842b3c1f95220dc9b119ee0fe0d81b Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Thu, 31 Mar 2022 15:52:33 +0200 Subject: ASoC: Intel: avs: Declare vendor tokens MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Expose all vendor tokens that help shape AVS topology. Parsing helpers introduced in follow up patches make use of these to know which block they are currently dealing with and to verify their correctness. Signed-off-by: Amadeusz Sławiński Signed-off-by: Cezary Rojewski Link: https://lore.kernel.org/r/20220331135246.993089-2-cezary.rojewski@intel.com Signed-off-by: Mark Brown --- include/uapi/sound/intel/avs/tokens.h | 126 ++++++++++++++++++++++++++++++++++ 1 file changed, 126 insertions(+) create mode 100644 include/uapi/sound/intel/avs/tokens.h (limited to 'include') diff --git a/include/uapi/sound/intel/avs/tokens.h b/include/uapi/sound/intel/avs/tokens.h new file mode 100644 index 000000000000..754f02b2f444 --- /dev/null +++ b/include/uapi/sound/intel/avs/tokens.h @@ -0,0 +1,126 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright(c) 2021 Intel Corporation. All rights reserved. + * + * Authors: Cezary Rojewski + * Amadeusz Slawinski + */ + +#ifndef __UAPI_SOUND_INTEL_AVS_TOKENS_H +#define __UAPI_SOUND_INTEL_AVS_TOKENS_H + +enum avs_tplg_token { + /* struct avs_tplg */ + AVS_TKN_MANIFEST_NAME_STRING = 1, + AVS_TKN_MANIFEST_VERSION_U32 = 2, + AVS_TKN_MANIFEST_NUM_LIBRARIES_U32 = 3, + AVS_TKN_MANIFEST_NUM_AFMTS_U32 = 4, + AVS_TKN_MANIFEST_NUM_MODCFGS_BASE_U32 = 5, + AVS_TKN_MANIFEST_NUM_MODCFGS_EXT_U32 = 6, + AVS_TKN_MANIFEST_NUM_PPLCFGS_U32 = 7, + AVS_TKN_MANIFEST_NUM_BINDINGS_U32 = 8, + + /* struct avs_tplg_library */ + AVS_TKN_LIBRARY_ID_U32 = 101, + AVS_TKN_LIBRARY_NAME_STRING = 102, + + /* struct avs_audio_format */ + AVS_TKN_AFMT_ID_U32 = 201, + AVS_TKN_AFMT_SAMPLE_RATE_U32 = 202, + AVS_TKN_AFMT_BIT_DEPTH_U32 = 203, + AVS_TKN_AFMT_CHANNEL_MAP_U32 = 204, + AVS_TKN_AFMT_CHANNEL_CFG_U32 = 205, + AVS_TKN_AFMT_INTERLEAVING_U32 = 206, + AVS_TKN_AFMT_NUM_CHANNELS_U32 = 207, + AVS_TKN_AFMT_VALID_BIT_DEPTH_U32 = 208, + AVS_TKN_AFMT_SAMPLE_TYPE_U32 = 209, + + /* struct avs_tplg_modcfg_base */ + AVS_TKN_MODCFG_BASE_ID_U32 = 301, + AVS_TKN_MODCFG_BASE_CPC_U32 = 302, + AVS_TKN_MODCFG_BASE_IBS_U32 = 303, + AVS_TKN_MODCFG_BASE_OBS_U32 = 304, + AVS_TKN_MODCFG_BASE_PAGES_U32 = 305, + + /* struct avs_tplg_modcfg_ext */ + AVS_TKN_MODCFG_EXT_ID_U32 = 401, + AVS_TKN_MODCFG_EXT_TYPE_UUID = 402, + AVS_TKN_MODCFG_CPR_OUT_AFMT_ID_U32 = 403, + AVS_TKN_MODCFG_CPR_FEATURE_MASK_U32 = 404, + AVS_TKN_MODCFG_CPR_DMA_TYPE_U32 = 405, + AVS_TKN_MODCFG_CPR_DMABUFF_SIZE_U32 = 406, + AVS_TKN_MODCFG_CPR_VINDEX_U8 = 407, + AVS_TKN_MODCFG_CPR_BLOB_FMT_ID_U32 = 408, + AVS_TKN_MODCFG_MICSEL_OUT_AFMT_ID_U32 = 409, + AVS_TKN_MODCFG_INTELWOV_CPC_LP_MODE_U32 = 410, + AVS_TKN_MODCFG_SRC_OUT_FREQ_U32 = 411, + AVS_TKN_MODCFG_MUX_REF_AFMT_ID_U32 = 412, + AVS_TKN_MODCFG_MUX_OUT_AFMT_ID_U32 = 413, + AVS_TKN_MODCFG_AEC_REF_AFMT_ID_U32 = 414, + AVS_TKN_MODCFG_AEC_OUT_AFMT_ID_U32 = 415, + AVS_TKN_MODCFG_AEC_CPC_LP_MODE_U32 = 416, + AVS_TKN_MODCFG_ASRC_OUT_FREQ_U32 = 417, + AVS_TKN_MODCFG_ASRC_MODE_U8 = 418, + AVS_TKN_MODCFG_ASRC_DISABLE_JITTER_U8 = 419, + AVS_TKN_MODCFG_UPDOWN_MIX_OUT_CHAN_CFG_U32 = 420, + AVS_TKN_MODCFG_UPDOWN_MIX_COEFF_SELECT_U32 = 421, + AVS_TKN_MODCFG_UPDOWN_MIX_COEFF_0_S32 = 422, + AVS_TKN_MODCFG_UPDOWN_MIX_COEFF_1_S32 = 423, + AVS_TKN_MODCFG_UPDOWN_MIX_COEFF_2_S32 = 424, + AVS_TKN_MODCFG_UPDOWN_MIX_COEFF_3_S32 = 425, + AVS_TKN_MODCFG_UPDOWN_MIX_COEFF_4_S32 = 426, + AVS_TKN_MODCFG_UPDOWN_MIX_COEFF_5_S32 = 427, + AVS_TKN_MODCFG_UPDOWN_MIX_COEFF_6_S32 = 428, + AVS_TKN_MODCFG_UPDOWN_MIX_COEFF_7_S32 = 429, + AVS_TKN_MODCFG_UPDOWN_MIX_CHAN_MAP_U32 = 430, + AVS_TKN_MODCFG_EXT_NUM_INPUT_PINS_U16 = 431, + AVS_TKN_MODCFG_EXT_NUM_OUTPUT_PINS_U16 = 432, + + /* struct avs_tplg_pplcfg */ + AVS_TKN_PPLCFG_ID_U32 = 1401, + AVS_TKN_PPLCFG_REQ_SIZE_U16 = 1402, + AVS_TKN_PPLCFG_PRIORITY_U8 = 1403, + AVS_TKN_PPLCFG_LOW_POWER_BOOL = 1404, + AVS_TKN_PPLCFG_ATTRIBUTES_U16 = 1405, + AVS_TKN_PPLCFG_TRIGGER_U32 = 1406, + + /* struct avs_tplg_binding */ + AVS_TKN_BINDING_ID_U32 = 1501, + AVS_TKN_BINDING_TARGET_TPLG_NAME_STRING = 1502, + AVS_TKN_BINDING_TARGET_PATH_TMPL_ID_U32 = 1503, + AVS_TKN_BINDING_TARGET_PPL_ID_U32 = 1504, + AVS_TKN_BINDING_TARGET_MOD_ID_U32 = 1505, + AVS_TKN_BINDING_TARGET_MOD_PIN_U8 = 1506, + AVS_TKN_BINDING_MOD_ID_U32 = 1507, + AVS_TKN_BINDING_MOD_PIN_U8 = 1508, + AVS_TKN_BINDING_IS_SINK_U8 = 1509, + + /* struct avs_tplg_pipeline */ + AVS_TKN_PPL_ID_U32 = 1601, + AVS_TKN_PPL_PPLCFG_ID_U32 = 1602, + AVS_TKN_PPL_NUM_BINDING_IDS_U32 = 1603, + AVS_TKN_PPL_BINDING_ID_U32 = 1604, + + /* struct avs_tplg_module */ + AVS_TKN_MOD_ID_U32 = 1701, + AVS_TKN_MOD_MODCFG_BASE_ID_U32 = 1702, + AVS_TKN_MOD_IN_AFMT_ID_U32 = 1703, + AVS_TKN_MOD_CORE_ID_U8 = 1704, + AVS_TKN_MOD_PROC_DOMAIN_U8 = 1705, + AVS_TKN_MOD_MODCFG_EXT_ID_U32 = 1706, + + /* struct avs_tplg_path_template */ + AVS_TKN_PATH_TMPL_ID_U32 = 1801, + + /* struct avs_tplg_path */ + AVS_TKN_PATH_ID_U32 = 1901, + AVS_TKN_PATH_FE_FMT_ID_U32 = 1902, + AVS_TKN_PATH_BE_FMT_ID_U32 = 1903, + + /* struct avs_tplg_pin_format */ + AVS_TKN_PIN_FMT_INDEX_U32 = 2201, + AVS_TKN_PIN_FMT_IOBS_U32 = 2202, + AVS_TKN_PIN_FMT_AFMT_ID_U32 = 2203, +}; + +#endif -- cgit v1.2.3 From c6547c2ed0e1487c91983faccad841611ab6a783 Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Thu, 14 Apr 2022 18:22:37 +0200 Subject: dmaengine: imx: Move header to include/dma/ The i.MX DMA drivers are device tree only, nothing in include/linux/platform_data/dma-imx.h has platform_data in it, so move the file to include/linux/dma/imx-dma.h. Signed-off-by: Sascha Hauer Acked-By: Vinod Koul Link: https://lore.kernel.org/r/20220414162249.3934543-10-s.hauer@pengutronix.de Signed-off-by: Mark Brown --- include/linux/dma/imx-dma.h | 68 +++++++++++++++++++++++++++++++++++ include/linux/platform_data/dma-imx.h | 68 ----------------------------------- 2 files changed, 68 insertions(+), 68 deletions(-) create mode 100644 include/linux/dma/imx-dma.h delete mode 100644 include/linux/platform_data/dma-imx.h (limited to 'include') diff --git a/include/linux/dma/imx-dma.h b/include/linux/dma/imx-dma.h new file mode 100644 index 000000000000..b06cba85a6d4 --- /dev/null +++ b/include/linux/dma/imx-dma.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright 2004-2009 Freescale Semiconductor, Inc. All Rights Reserved. + */ + +#ifndef __LINUX_DMA_IMX_H +#define __LINUX_DMA_IMX_H + +#include +#include +#include + +/* + * This enumerates peripheral types. Used for SDMA. + */ +enum sdma_peripheral_type { + IMX_DMATYPE_SSI, /* MCU domain SSI */ + IMX_DMATYPE_SSI_SP, /* Shared SSI */ + IMX_DMATYPE_MMC, /* MMC */ + IMX_DMATYPE_SDHC, /* SDHC */ + IMX_DMATYPE_UART, /* MCU domain UART */ + IMX_DMATYPE_UART_SP, /* Shared UART */ + IMX_DMATYPE_FIRI, /* FIRI */ + IMX_DMATYPE_CSPI, /* MCU domain CSPI */ + IMX_DMATYPE_CSPI_SP, /* Shared CSPI */ + IMX_DMATYPE_SIM, /* SIM */ + IMX_DMATYPE_ATA, /* ATA */ + IMX_DMATYPE_CCM, /* CCM */ + IMX_DMATYPE_EXT, /* External peripheral */ + IMX_DMATYPE_MSHC, /* Memory Stick Host Controller */ + IMX_DMATYPE_MSHC_SP, /* Shared Memory Stick Host Controller */ + IMX_DMATYPE_DSP, /* DSP */ + IMX_DMATYPE_MEMORY, /* Memory */ + IMX_DMATYPE_FIFO_MEMORY,/* FIFO type Memory */ + IMX_DMATYPE_SPDIF, /* SPDIF */ + IMX_DMATYPE_IPU_MEMORY, /* IPU Memory */ + IMX_DMATYPE_ASRC, /* ASRC */ + IMX_DMATYPE_ESAI, /* ESAI */ + IMX_DMATYPE_SSI_DUAL, /* SSI Dual FIFO */ + IMX_DMATYPE_ASRC_SP, /* Shared ASRC */ + IMX_DMATYPE_SAI, /* SAI */ +}; + +enum imx_dma_prio { + DMA_PRIO_HIGH = 0, + DMA_PRIO_MEDIUM = 1, + DMA_PRIO_LOW = 2 +}; + +struct imx_dma_data { + int dma_request; /* DMA request line */ + int dma_request2; /* secondary DMA request line */ + enum sdma_peripheral_type peripheral_type; + int priority; +}; + +static inline int imx_dma_is_ipu(struct dma_chan *chan) +{ + return !strcmp(dev_name(chan->device->dev), "ipu-core"); +} + +static inline int imx_dma_is_general_purpose(struct dma_chan *chan) +{ + return !strcmp(chan->device->dev->driver->name, "imx-sdma") || + !strcmp(chan->device->dev->driver->name, "imx-dma"); +} + +#endif /* __LINUX_DMA_IMX_H */ diff --git a/include/linux/platform_data/dma-imx.h b/include/linux/platform_data/dma-imx.h deleted file mode 100644 index 281adbb26e6b..000000000000 --- a/include/linux/platform_data/dma-imx.h +++ /dev/null @@ -1,68 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright 2004-2009 Freescale Semiconductor, Inc. All Rights Reserved. - */ - -#ifndef __ASM_ARCH_MXC_DMA_H__ -#define __ASM_ARCH_MXC_DMA_H__ - -#include -#include -#include - -/* - * This enumerates peripheral types. Used for SDMA. - */ -enum sdma_peripheral_type { - IMX_DMATYPE_SSI, /* MCU domain SSI */ - IMX_DMATYPE_SSI_SP, /* Shared SSI */ - IMX_DMATYPE_MMC, /* MMC */ - IMX_DMATYPE_SDHC, /* SDHC */ - IMX_DMATYPE_UART, /* MCU domain UART */ - IMX_DMATYPE_UART_SP, /* Shared UART */ - IMX_DMATYPE_FIRI, /* FIRI */ - IMX_DMATYPE_CSPI, /* MCU domain CSPI */ - IMX_DMATYPE_CSPI_SP, /* Shared CSPI */ - IMX_DMATYPE_SIM, /* SIM */ - IMX_DMATYPE_ATA, /* ATA */ - IMX_DMATYPE_CCM, /* CCM */ - IMX_DMATYPE_EXT, /* External peripheral */ - IMX_DMATYPE_MSHC, /* Memory Stick Host Controller */ - IMX_DMATYPE_MSHC_SP, /* Shared Memory Stick Host Controller */ - IMX_DMATYPE_DSP, /* DSP */ - IMX_DMATYPE_MEMORY, /* Memory */ - IMX_DMATYPE_FIFO_MEMORY,/* FIFO type Memory */ - IMX_DMATYPE_SPDIF, /* SPDIF */ - IMX_DMATYPE_IPU_MEMORY, /* IPU Memory */ - IMX_DMATYPE_ASRC, /* ASRC */ - IMX_DMATYPE_ESAI, /* ESAI */ - IMX_DMATYPE_SSI_DUAL, /* SSI Dual FIFO */ - IMX_DMATYPE_ASRC_SP, /* Shared ASRC */ - IMX_DMATYPE_SAI, /* SAI */ -}; - -enum imx_dma_prio { - DMA_PRIO_HIGH = 0, - DMA_PRIO_MEDIUM = 1, - DMA_PRIO_LOW = 2 -}; - -struct imx_dma_data { - int dma_request; /* DMA request line */ - int dma_request2; /* secondary DMA request line */ - enum sdma_peripheral_type peripheral_type; - int priority; -}; - -static inline int imx_dma_is_ipu(struct dma_chan *chan) -{ - return !strcmp(dev_name(chan->device->dev), "ipu-core"); -} - -static inline int imx_dma_is_general_purpose(struct dma_chan *chan) -{ - return !strcmp(chan->device->dev->driver->name, "imx-sdma") || - !strcmp(chan->device->dev->driver->name, "imx-dma"); -} - -#endif -- cgit v1.2.3 From 824a0a02cd74776461aaa30d792b1ed9111c9aa5 Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Thu, 14 Apr 2022 18:22:39 +0200 Subject: dmaengine: imx-sdma: Add multi fifo support The i.MX SDMA engine can read from / write to multiple successive hardware FIFO registers, referred to as "Multi FIFO support". This is needed for the micfil driver and certain configurations of the SAI driver. This patch adds support for this feature. The number of FIFOs to read from / write to must be communicated from the client driver to the SDMA engine. For this the struct dma_slave_config::peripheral_config field is used. Signed-off-by: Sascha Hauer Acked-By: Vinod Koul Link: https://lore.kernel.org/r/20220414162249.3934543-12-s.hauer@pengutronix.de Signed-off-by: Mark Brown --- include/linux/dma/imx-dma.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/dma/imx-dma.h b/include/linux/dma/imx-dma.h index b06cba85a6d4..8887762360d4 100644 --- a/include/linux/dma/imx-dma.h +++ b/include/linux/dma/imx-dma.h @@ -39,6 +39,7 @@ enum sdma_peripheral_type { IMX_DMATYPE_SSI_DUAL, /* SSI Dual FIFO */ IMX_DMATYPE_ASRC_SP, /* Shared ASRC */ IMX_DMATYPE_SAI, /* SAI */ + IMX_DMATYPE_MULTI_SAI, /* MULTI FIFOs For Audio */ }; enum imx_dma_prio { @@ -65,4 +66,23 @@ static inline int imx_dma_is_general_purpose(struct dma_chan *chan) !strcmp(chan->device->dev->driver->name, "imx-dma"); } +/** + * struct sdma_peripheral_config - SDMA config for audio + * @n_fifos_src: Number of FIFOs for recording + * @n_fifos_dst: Number of FIFOs for playback + * @sw_done: Use software done. Needed for PDM (micfil) + * + * Some i.MX Audio devices (SAI, micfil) have multiple successive FIFO + * registers. For multichannel recording/playback the SAI/micfil have + * one FIFO register per channel and the SDMA engine has to read/write + * the next channel from/to the next register and wrap around to the + * first register when all channels are handled. The number of active + * channels must be communicated to the SDMA engine using this struct. + */ +struct sdma_peripheral_config { + int n_fifos_src; + int n_fifos_dst; + bool sw_done; +}; + #endif /* __LINUX_DMA_IMX_H */ -- cgit v1.2.3 From b617be33502d2bfefffef71924c7a7ba50264ff6 Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Mon, 11 Apr 2022 21:45:27 +0300 Subject: spi: add SPI_RX_CPHA_FLIP mode bit Some SPI devices latch MOSI bits on one clock phase, but produce valid MISO bits on the other phase. Add SPI_RX_CPHA_FLIP mode to instruct the controller driver to flip CPHA for Rx (MISO) only transfers. Signed-off-by: Baruch Siach Link: https://lore.kernel.org/r/a715ca92713ca02071f33dcca9960a66a03c949a.1649702729.git.baruch@tkos.co.il Signed-off-by: Mark Brown --- include/uapi/linux/spi/spi.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/spi/spi.h b/include/uapi/linux/spi/spi.h index 236a85f08ded..9d5f58059703 100644 --- a/include/uapi/linux/spi/spi.h +++ b/include/uapi/linux/spi/spi.h @@ -27,6 +27,7 @@ #define SPI_TX_OCTAL _BITUL(13) /* transmit with 8 wires */ #define SPI_RX_OCTAL _BITUL(14) /* receive with 8 wires */ #define SPI_3WIRE_HIZ _BITUL(15) /* high impedance turnaround */ +#define SPI_RX_CPHA_FLIP _BITUL(16) /* flip CPHA on Rx only xfer */ /* * All the bits defined above should be covered by SPI_MODE_USER_MASK. @@ -36,6 +37,6 @@ * These bits must not overlap. A static assert check should make sure of that. * If adding extra bits, make sure to increase the bit index below as well. */ -#define SPI_MODE_USER_MASK (_BITUL(16) - 1) +#define SPI_MODE_USER_MASK (_BITUL(17) - 1) #endif /* _UAPI_SPI_H */ -- cgit v1.2.3 From 6c846d026d490b2383d395bc8e7b06336219667b Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 19 Apr 2022 15:18:37 +0100 Subject: gpio: Don't fiddle with irqchips marked as immutable In order to move away from gpiolib messing with the internals of unsuspecting irqchips, add a flag by which irqchips advertise that they are not to be messed with, and do solemnly swear that they correctly call into the gpiolib helpers when required. Also nudge the users into converting their drivers to the new model. Reviewed-by: Andy Shevchenko Reviewed-by: Bartosz Golaszewski Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220419141846.598305-2-maz@kernel.org --- include/linux/irq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index f92788ccdba2..505308253d23 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -569,6 +569,7 @@ struct irq_chip { * IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND: Invokes __enable_irq()/__disable_irq() for wake irqs * in the suspend path if they are in disabled state * IRQCHIP_AFFINITY_PRE_STARTUP: Default affinity update before startup + * IRQCHIP_IMMUTABLE: Don't ever change anything in this chip */ enum { IRQCHIP_SET_TYPE_MASKED = (1 << 0), @@ -582,6 +583,7 @@ enum { IRQCHIP_SUPPORTS_NMI = (1 << 8), IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND = (1 << 9), IRQCHIP_AFFINITY_PRE_STARTUP = (1 << 10), + IRQCHIP_IMMUTABLE = (1 << 11), }; #include -- cgit v1.2.3 From 704f08753b6dcd0e08c1953af0b2c7f3fac87111 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 19 Apr 2022 15:18:38 +0100 Subject: gpio: Expose the gpiochip_irq_re[ql]res helpers The GPIO subsystem has a couple of internal helpers to manage resources on behalf of the irqchip. Expose them so that GPIO drivers can use them directly. Reviewed-by: Andy Shevchenko Reviewed-by: Bartosz Golaszewski Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220419141846.598305-3-maz@kernel.org --- include/linux/gpio/driver.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 98c93510640e..066bcfdf878d 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -579,6 +579,10 @@ void gpiochip_relres_irq(struct gpio_chip *gc, unsigned int offset); void gpiochip_disable_irq(struct gpio_chip *gc, unsigned int offset); void gpiochip_enable_irq(struct gpio_chip *gc, unsigned int offset); +/* irq_data versions of the above */ +int gpiochip_irq_reqres(struct irq_data *data); +void gpiochip_irq_relres(struct irq_data *data); + /* Line status inquiry for drivers */ bool gpiochip_line_is_open_drain(struct gpio_chip *gc, unsigned int offset); bool gpiochip_line_is_open_source(struct gpio_chip *gc, unsigned int offset); -- cgit v1.2.3 From 36b78aae4bfee749bbde73be570796bfd0f56bec Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 19 Apr 2022 15:18:39 +0100 Subject: gpio: Add helpers to ease the transition towards immutable irq_chip Add a couple of new helpers to make it slightly simpler to convert drivers to immutable irq_chip structures: - GPIOCHIP_IRQ_RESOURCE_HELPERS populates the irq_chip structure with the resource management callbacks - gpio_irq_chip_set_chip() populates the gpio_irq_chip.chip structure, avoiding the proliferation of ugly casts Reviewed-by: Andy Shevchenko Reviewed-by: Bartosz Golaszewski Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220419141846.598305-4-maz@kernel.org --- include/linux/gpio/driver.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 066bcfdf878d..832990099097 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -583,6 +583,18 @@ void gpiochip_enable_irq(struct gpio_chip *gc, unsigned int offset); int gpiochip_irq_reqres(struct irq_data *data); void gpiochip_irq_relres(struct irq_data *data); +/* Paste this in your irq_chip structure */ +#define GPIOCHIP_IRQ_RESOURCE_HELPERS \ + .irq_request_resources = gpiochip_irq_reqres, \ + .irq_release_resources = gpiochip_irq_relres + +static inline void gpio_irq_chip_set_chip(struct gpio_irq_chip *girq, + const struct irq_chip *chip) +{ + /* Yes, dropping const is ugly, but it isn't like we have a choice */ + girq->chip = (struct irq_chip *)chip; +} + /* Line status inquiry for drivers */ bool gpiochip_line_is_open_drain(struct gpio_chip *gc, unsigned int offset); bool gpiochip_line_is_open_source(struct gpio_chip *gc, unsigned int offset); -- cgit v1.2.3 From 08d3df8c81537089fc8f21006b56f2f6fb23c6f8 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sun, 1 Sep 2019 22:26:10 +0200 Subject: ARM: pxa: split up mach/hardware.h The mach/hardware.h is included in lots of places, and it provides three different things on pxa: - the cpu_is_pxa* macros - an indirect inclusion of mach/addr-map.h - the __REG() and io_pv2() helper macros Split it up into separate and mach/pxa-regs.h headers, then change all the files that use mach/hardware.h to include the exact set of those three headers that they actually need, allowing for further more targeted cleanup. linux/soc/pxa/cpu.h can remain permanently exported and is now in a global location along with similar headers. pxa-regs.h and addr-map.h are only used in a very small number of drivers now and can be moved to arch/arm/mach-pxa/ directly when those drivers are to pass the necessary data as resources. Cc: Michael Turquette Cc: Stephen Boyd Acked-by: Viresh Kumar Acked-by: Dmitry Torokhov Cc: Jacek Anaszewski Cc: Pavel Machek Acked-by: Ulf Hansson Cc: Dominik Brodowski Acked-by: Alexandre Belloni Cc: Greg Kroah-Hartman Cc: Guenter Roeck Acked-by: Mark Brown Cc: linux-clk@vger.kernel.org Cc: linux-pm@vger.kernel.org Cc: linux-input@vger.kernel.org Cc: linux-leds@vger.kernel.org Cc: linux-mmc@vger.kernel.org Cc: linux-mtd@lists.infradead.org Cc: linux-rtc@vger.kernel.org Cc: linux-usb@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Cc: linux-fbdev@vger.kernel.org Cc: linux-watchdog@vger.kernel.org Cc: alsa-devel@alsa-project.org Signed-off-by: Arnd Bergmann --- include/linux/soc/pxa/cpu.h | 252 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 252 insertions(+) create mode 100644 include/linux/soc/pxa/cpu.h (limited to 'include') diff --git a/include/linux/soc/pxa/cpu.h b/include/linux/soc/pxa/cpu.h new file mode 100644 index 000000000000..5782450ee45c --- /dev/null +++ b/include/linux/soc/pxa/cpu.h @@ -0,0 +1,252 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Author: Nicolas Pitre + * Created: Jun 15, 2001 + * Copyright: MontaVista Software Inc. + */ + +#ifndef __SOC_PXA_CPU_H +#define __SOC_PXA_CPU_H + +#ifdef CONFIG_ARM +#include +#endif + +/* + * CPU Stepping CPU_ID JTAG_ID + * + * PXA210 B0 0x69052922 0x2926C013 + * PXA210 B1 0x69052923 0x3926C013 + * PXA210 B2 0x69052924 0x4926C013 + * PXA210 C0 0x69052D25 0x5926C013 + * + * PXA250 A0 0x69052100 0x09264013 + * PXA250 A1 0x69052101 0x19264013 + * PXA250 B0 0x69052902 0x29264013 + * PXA250 B1 0x69052903 0x39264013 + * PXA250 B2 0x69052904 0x49264013 + * PXA250 C0 0x69052D05 0x59264013 + * + * PXA255 A0 0x69052D06 0x69264013 + * + * PXA26x A0 0x69052903 0x39264013 + * PXA26x B0 0x69052D05 0x59264013 + * + * PXA27x A0 0x69054110 0x09265013 + * PXA27x A1 0x69054111 0x19265013 + * PXA27x B0 0x69054112 0x29265013 + * PXA27x B1 0x69054113 0x39265013 + * PXA27x C0 0x69054114 0x49265013 + * PXA27x C5 0x69054117 0x79265013 + * + * PXA30x A0 0x69056880 0x0E648013 + * PXA30x A1 0x69056881 0x1E648013 + * PXA31x A0 0x69056890 0x0E649013 + * PXA31x A1 0x69056891 0x1E649013 + * PXA31x A2 0x69056892 0x2E649013 + * PXA32x B1 0x69056825 0x5E642013 + * PXA32x B2 0x69056826 0x6E642013 + * + * PXA930 B0 0x69056835 0x5E643013 + * PXA930 B1 0x69056837 0x7E643013 + * PXA930 B2 0x69056838 0x8E643013 + * + * PXA935 A0 0x56056931 0x1E653013 + * PXA935 B0 0x56056936 0x6E653013 + * PXA935 B1 0x56056938 0x8E653013 + */ +#ifdef CONFIG_PXA25x +#define __cpu_is_pxa210(id) \ + ({ \ + unsigned int _id = (id) & 0xf3f0; \ + _id == 0x2120; \ + }) + +#define __cpu_is_pxa250(id) \ + ({ \ + unsigned int _id = (id) & 0xf3ff; \ + _id <= 0x2105; \ + }) + +#define __cpu_is_pxa255(id) \ + ({ \ + unsigned int _id = (id) & 0xffff; \ + _id == 0x2d06; \ + }) + +#define __cpu_is_pxa25x(id) \ + ({ \ + unsigned int _id = (id) & 0xf300; \ + _id == 0x2100; \ + }) +#else +#define __cpu_is_pxa210(id) (0) +#define __cpu_is_pxa250(id) (0) +#define __cpu_is_pxa255(id) (0) +#define __cpu_is_pxa25x(id) (0) +#endif + +#ifdef CONFIG_PXA27x +#define __cpu_is_pxa27x(id) \ + ({ \ + unsigned int _id = (id) >> 4 & 0xfff; \ + _id == 0x411; \ + }) +#else +#define __cpu_is_pxa27x(id) (0) +#endif + +#ifdef CONFIG_CPU_PXA300 +#define __cpu_is_pxa300(id) \ + ({ \ + unsigned int _id = (id) >> 4 & 0xfff; \ + _id == 0x688; \ + }) +#else +#define __cpu_is_pxa300(id) (0) +#endif + +#ifdef CONFIG_CPU_PXA310 +#define __cpu_is_pxa310(id) \ + ({ \ + unsigned int _id = (id) >> 4 & 0xfff; \ + _id == 0x689; \ + }) +#else +#define __cpu_is_pxa310(id) (0) +#endif + +#ifdef CONFIG_CPU_PXA320 +#define __cpu_is_pxa320(id) \ + ({ \ + unsigned int _id = (id) >> 4 & 0xfff; \ + _id == 0x603 || _id == 0x682; \ + }) +#else +#define __cpu_is_pxa320(id) (0) +#endif + +#ifdef CONFIG_CPU_PXA930 +#define __cpu_is_pxa930(id) \ + ({ \ + unsigned int _id = (id) >> 4 & 0xfff; \ + _id == 0x683; \ + }) +#else +#define __cpu_is_pxa930(id) (0) +#endif + +#ifdef CONFIG_CPU_PXA935 +#define __cpu_is_pxa935(id) \ + ({ \ + unsigned int _id = (id) >> 4 & 0xfff; \ + _id == 0x693; \ + }) +#else +#define __cpu_is_pxa935(id) (0) +#endif + +#define cpu_is_pxa210() \ + ({ \ + __cpu_is_pxa210(read_cpuid_id()); \ + }) + +#define cpu_is_pxa250() \ + ({ \ + __cpu_is_pxa250(read_cpuid_id()); \ + }) + +#define cpu_is_pxa255() \ + ({ \ + __cpu_is_pxa255(read_cpuid_id()); \ + }) + +#define cpu_is_pxa25x() \ + ({ \ + __cpu_is_pxa25x(read_cpuid_id()); \ + }) + +#define cpu_is_pxa27x() \ + ({ \ + __cpu_is_pxa27x(read_cpuid_id()); \ + }) + +#define cpu_is_pxa300() \ + ({ \ + __cpu_is_pxa300(read_cpuid_id()); \ + }) + +#define cpu_is_pxa310() \ + ({ \ + __cpu_is_pxa310(read_cpuid_id()); \ + }) + +#define cpu_is_pxa320() \ + ({ \ + __cpu_is_pxa320(read_cpuid_id()); \ + }) + +#define cpu_is_pxa930() \ + ({ \ + __cpu_is_pxa930(read_cpuid_id()); \ + }) + +#define cpu_is_pxa935() \ + ({ \ + __cpu_is_pxa935(read_cpuid_id()); \ + }) + + + +/* + * CPUID Core Generation Bit + * <= 0x2 for pxa21x/pxa25x/pxa26x/pxa27x + */ +#if defined(CONFIG_PXA25x) || defined(CONFIG_PXA27x) +#define __cpu_is_pxa2xx(id) \ + ({ \ + unsigned int _id = (id) >> 13 & 0x7; \ + _id <= 0x2; \ + }) +#else +#define __cpu_is_pxa2xx(id) (0) +#endif + +#ifdef CONFIG_PXA3xx +#define __cpu_is_pxa3xx(id) \ + ({ \ + __cpu_is_pxa300(id) \ + || __cpu_is_pxa310(id) \ + || __cpu_is_pxa320(id) \ + || __cpu_is_pxa93x(id); \ + }) +#else +#define __cpu_is_pxa3xx(id) (0) +#endif + +#if defined(CONFIG_CPU_PXA930) || defined(CONFIG_CPU_PXA935) +#define __cpu_is_pxa93x(id) \ + ({ \ + __cpu_is_pxa930(id) \ + || __cpu_is_pxa935(id); \ + }) +#else +#define __cpu_is_pxa93x(id) (0) +#endif + +#define cpu_is_pxa2xx() \ + ({ \ + __cpu_is_pxa2xx(read_cpuid_id()); \ + }) + +#define cpu_is_pxa3xx() \ + ({ \ + __cpu_is_pxa3xx(read_cpuid_id()); \ + }) + +#define cpu_is_pxa93x() \ + ({ \ + __cpu_is_pxa93x(read_cpuid_id()); \ + }) + +#endif -- cgit v1.2.3 From 22f0866513c2e531ae65a9d5dfc82f24497ef3b3 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 2 Sep 2019 00:02:08 +0200 Subject: ARM: pxa: move mach/sound.h to linux/platform_data/ This is a basically a platform_data file, so move it out of the mach/* header directory. Cc: Marek Vasut Cc: Tomas Cech Cc: Sergey Lapin Acked-by: Mark Brown Acked-by: Robert Jarzmik Cc: alsa-devel@alsa-project.org Signed-off-by: Arnd Bergmann --- include/linux/platform_data/asoc-pxa.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) create mode 100644 include/linux/platform_data/asoc-pxa.h (limited to 'include') diff --git a/include/linux/platform_data/asoc-pxa.h b/include/linux/platform_data/asoc-pxa.h new file mode 100644 index 000000000000..327454cd8246 --- /dev/null +++ b/include/linux/platform_data/asoc-pxa.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __SOC_PXA_AUDIO_H__ +#define __SOC_PXA_AUDIO_H__ + +#include +#include +#include + +/* + * @reset_gpio: AC97 reset gpio (normally gpio113 or gpio95) + * a -1 value means no gpio will be used for reset + * @codec_pdata: AC97 codec platform_data + + * reset_gpio should only be specified for pxa27x CPUs where a silicon + * bug prevents correct operation of the reset line. If not specified, + * the default behaviour on these CPUs is to consider gpio 113 as the + * AC97 reset line, which is the default on most boards. + */ +typedef struct { + int (*startup)(struct snd_pcm_substream *, void *); + void (*shutdown)(struct snd_pcm_substream *, void *); + void (*suspend)(void *); + void (*resume)(void *); + void *priv; + int reset_gpio; + void *codec_pdata[AC97_BUS_MAX_DEVICES]; +} pxa2xx_audio_ops_t; + +extern void pxa_set_ac97_info(pxa2xx_audio_ops_t *ops); + +#endif -- cgit v1.2.3 From ee84cbd5df2beaf14e8af0955f1ab15ad3f81504 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 2 Sep 2019 00:15:44 +0200 Subject: ARM: pxa: move regs-lcd.h into driver Only the pxafb driver uses this header, so move it into the same directory. The SMART_* macros are required by some platform data definitions and can go into the linux/platform_data/video-pxafb.h header. Acked-by: Bartlomiej Zolnierkiewicz Acked-by: Robert Jarzmik Cc: dri-devel@lists.freedesktop.org Cc: linux-fbdev@vger.kernel.org Signed-off-by: Arnd Bergmann --- include/linux/platform_data/video-pxafb.h | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/platform_data/video-pxafb.h b/include/linux/platform_data/video-pxafb.h index b3d574778326..6333bac166a5 100644 --- a/include/linux/platform_data/video-pxafb.h +++ b/include/linux/platform_data/video-pxafb.h @@ -8,7 +8,6 @@ */ #include -#include /* * Supported LCD connections @@ -153,6 +152,27 @@ struct pxafb_mach_info { void pxa_set_fb_info(struct device *, struct pxafb_mach_info *); unsigned long pxafb_get_hsync_time(struct device *dev); +/* smartpanel related */ +#define SMART_CMD_A0 (0x1 << 8) +#define SMART_CMD_READ_STATUS_REG (0x0 << 9) +#define SMART_CMD_READ_FRAME_BUFFER ((0x0 << 9) | SMART_CMD_A0) +#define SMART_CMD_WRITE_COMMAND (0x1 << 9) +#define SMART_CMD_WRITE_DATA ((0x1 << 9) | SMART_CMD_A0) +#define SMART_CMD_WRITE_FRAME ((0x2 << 9) | SMART_CMD_A0) +#define SMART_CMD_WAIT_FOR_VSYNC (0x3 << 9) +#define SMART_CMD_NOOP (0x4 << 9) +#define SMART_CMD_INTERRUPT (0x5 << 9) + +#define SMART_CMD(x) (SMART_CMD_WRITE_COMMAND | ((x) & 0xff)) +#define SMART_DAT(x) (SMART_CMD_WRITE_DATA | ((x) & 0xff)) + +/* SMART_DELAY() is introduced for software controlled delay primitive which + * can be inserted between command sequences, unused command 0x6 is used here + * and delay ranges from 0ms ~ 255ms + */ +#define SMART_CMD_DELAY (0x6 << 9) +#define SMART_DELAY(ms) (SMART_CMD_DELAY | ((ms) & 0xff)) + #ifdef CONFIG_FB_PXA_SMARTPANEL extern int pxafb_smart_queue(struct fb_info *info, uint16_t *cmds, int); extern int pxafb_smart_flush(struct fb_info *info); -- cgit v1.2.3 From eb38c2053b67977844404cbbdee341dbf3a02d36 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 14 Mar 2022 23:09:10 +0100 Subject: can: rx-offload: rename can_rx_offload_queue_sorted() -> can_rx_offload_queue_timestamp() This patch renames the function can_rx_offload_queue_sorted() to can_rx_offload_queue_timestamp(). This better describes what the function does, it adds a newly RX'ed skb to the sorted queue by its timestamp. Link: https://lore.kernel.org/all/20220417194327.2699059-1-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/rx-offload.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index c11477620403..c205c51d79c9 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -42,8 +42,8 @@ int can_rx_offload_add_manual(struct net_device *dev, int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload, u64 reg); int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload); -int can_rx_offload_queue_sorted(struct can_rx_offload *offload, - struct sk_buff *skb, u32 timestamp); +int can_rx_offload_queue_timestamp(struct can_rx_offload *offload, + struct sk_buff *skb, u32 timestamp); unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, unsigned int idx, u32 timestamp, unsigned int *frame_len_ptr); -- cgit v1.2.3 From 9995c1d096c8ab1b5f1edc4141257719f6a53524 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 6 Apr 2022 14:00:55 -0500 Subject: ASoC: soc-pcm: improve BE transition for PAUSE_RELEASE MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 3aa1e96a2b95 ("ASoC: soc-pcm: fix BE handling of PAUSE_RELEASE") did not modify the existing logic and kept the same logic for the following transition play FE1 -> BE state is START pause FE1 -> BE state is PAUSED play FE2 -> BE state is START stop FE2 -> BE state is STOP <<< !! release FE1 -> BE state is START stop FE1 -> BE state is STOP At the time it was identified by reviewers that a better solution might consist in play FE1 -> BE state is START pause FE1 -> BE state is PAUSED play FE2 -> BE state is START stop FE2 -> BE state is PAUSE <<< !! release FE1 -> BE state is START stop FE1 -> BE state is STOP This patch suggest a transition to PAUSE when all the 'active' streams are paused. This would allow for a more consistent resource management for platforms where PAUSE and STOP are handled differently. To track the special case of an FE going from PAUSE_PUSH to STOP, we add a state variable for each FE context. This 'fe_pause' boolean is set on PAUSE_PUSH and cleared on either PAUSE_RELEASE and STOP triggers. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Reviewed-by: Ranjani Sridharan Reviewed-by: Péter Ujfalusi Reviewed-by: Bard Liao Link: https://lore.kernel.org/r/20220406190056.233481-2-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/sound/soc-dpcm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/sound/soc-dpcm.h b/include/sound/soc-dpcm.h index 75b92d883976..5b689c663290 100644 --- a/include/sound/soc-dpcm.h +++ b/include/sound/soc-dpcm.h @@ -103,6 +103,8 @@ struct snd_soc_dpcm_runtime { int trigger_pending; /* trigger cmd + 1 if pending, 0 if not */ int be_start; /* refcount protected by BE stream pcm lock */ + int be_pause; /* refcount protected by BE stream pcm lock */ + bool fe_pause; /* used to track STOP after PAUSE */ }; #define for_each_dpcm_fe(be, stream, _dpcm) \ -- cgit v1.2.3 From 8fb241e2d265de7c1711635f3f2048f33e02b57d Mon Sep 17 00:00:00 2001 From: Sandor Yu Date: Fri, 15 Apr 2022 10:42:49 +0800 Subject: drm: bridge: dw_hdmi: add reset function for PHY GEN1 PHY reset register(MC_PHYRSTZ) active high reset control for PHY GEN2, and active low reset control for PHY GEN1. Rename function dw_hdmi_phy_reset to dw_hdmi_phy_gen2_reset. Add dw_hdmi_phy_gen1_reset function for PHY GEN1. Signed-off-by: Sandor Yu Reviewed-by: Neil Armstrong Acked-by: Jernej Skrabec Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/e0b3be2d63fe3e95246fb8b8b0dcd57415b29e04.1649989179.git.Sandor.yu@nxp.com --- include/drm/bridge/dw_hdmi.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/bridge/dw_hdmi.h b/include/drm/bridge/dw_hdmi.h index 2a1f85f9a8a3..70082f80a8c8 100644 --- a/include/drm/bridge/dw_hdmi.h +++ b/include/drm/bridge/dw_hdmi.h @@ -187,9 +187,11 @@ void dw_hdmi_phy_i2c_set_addr(struct dw_hdmi *hdmi, u8 address); void dw_hdmi_phy_i2c_write(struct dw_hdmi *hdmi, unsigned short data, unsigned char addr); +void dw_hdmi_phy_gen1_reset(struct dw_hdmi *hdmi); + void dw_hdmi_phy_gen2_pddq(struct dw_hdmi *hdmi, u8 enable); void dw_hdmi_phy_gen2_txpwron(struct dw_hdmi *hdmi, u8 enable); -void dw_hdmi_phy_reset(struct dw_hdmi *hdmi); +void dw_hdmi_phy_gen2_reset(struct dw_hdmi *hdmi); enum drm_connector_status dw_hdmi_phy_read_hpd(struct dw_hdmi *hdmi, void *data); -- cgit v1.2.3 From d970ce303ff80ae57bbd3e784f2772dbf3056e0c Mon Sep 17 00:00:00 2001 From: Sandor Yu Date: Fri, 15 Apr 2022 10:42:50 +0800 Subject: drm: bridge: dw_hdmi: Audio: Add General Parallel Audio (GPA) driver General Parallel Audio (GPA) interface is one of the supported audio interface for synopsys HDMI module, which has verified for i.MX8MPlus platform. This is initial version for GPA. Signed-off-by: Shengjiu Wang Signed-off-by: Sandor Yu Reviewed-by: Neil Armstrong Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/f21ba3e8c4d9d028ac74c6f3c588ddbffe739399.1649989179.git.Sandor.yu@nxp.com --- include/drm/bridge/dw_hdmi.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/drm/bridge/dw_hdmi.h b/include/drm/bridge/dw_hdmi.h index 70082f80a8c8..f668e75fbabe 100644 --- a/include/drm/bridge/dw_hdmi.h +++ b/include/drm/bridge/dw_hdmi.h @@ -143,6 +143,11 @@ struct dw_hdmi_plat_data { const struct drm_display_info *info, const struct drm_display_mode *mode); + /* Platform-specific audio enable/disable (optional) */ + void (*enable_audio)(struct dw_hdmi *hdmi, int channel, + int width, int rate, int non_pcm); + void (*disable_audio)(struct dw_hdmi *hdmi); + /* Vendor PHY support */ const struct dw_hdmi_phy_ops *phy_ops; const char *phy_name; @@ -173,6 +178,8 @@ void dw_hdmi_setup_rx_sense(struct dw_hdmi *hdmi, bool hpd, bool rx_sense); int dw_hdmi_set_plugged_cb(struct dw_hdmi *hdmi, hdmi_codec_plugged_cb fn, struct device *codec_dev); +void dw_hdmi_set_sample_non_pcm(struct dw_hdmi *hdmi, unsigned int non_pcm); +void dw_hdmi_set_sample_width(struct dw_hdmi *hdmi, unsigned int width); void dw_hdmi_set_sample_rate(struct dw_hdmi *hdmi, unsigned int rate); void dw_hdmi_set_channel_count(struct dw_hdmi *hdmi, unsigned int cnt); void dw_hdmi_set_channel_status(struct dw_hdmi *hdmi, u8 *channel_status); -- cgit v1.2.3 From 055eb95533273bc334794dbc598400d10800528f Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Thu, 14 Apr 2022 09:12:33 -0700 Subject: bpf: Move rcu lock management out of BPF_PROG_RUN routines Commit 7d08c2c91171 ("bpf: Refactor BPF_PROG_RUN_ARRAY family of macros into functions") switched a bunch of BPF_PROG_RUN macros to inline routines. This changed the semantic a bit. Due to arguments expansion of macros, it used to be: rcu_read_lock(); array = rcu_dereference(cgrp->bpf.effective[atype]); ... Now, with with inline routines, we have: array_rcu = rcu_dereference(cgrp->bpf.effective[atype]); /* array_rcu can be kfree'd here */ rcu_read_lock(); array = rcu_dereference(array_rcu); I'm assuming in practice rcu subsystem isn't fast enough to trigger this but let's use rcu API properly. Also, rename to lower caps to not confuse with macros. Additionally, drop and expand BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY. See [1] for more context. [1] https://lore.kernel.org/bpf/CAKH8qBs60fOinFdxiiQikK_q0EcVxGvNTQoWvHLEUGbgcj1UYg@mail.gmail.com/T/#u v2 - keep rcu locks inside by passing cgroup_bpf Fixes: 7d08c2c91171 ("bpf: Refactor BPF_PROG_RUN_ARRAY family of macros into functions") Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20220414161233.170780-1-sdf@google.com --- include/linux/bpf.h | 115 ++++------------------------------------------------ 1 file changed, 7 insertions(+), 108 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bdb5298735ce..7bf441563ffc 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1221,7 +1221,7 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, /* an array of programs to be executed under rcu_lock. * * Typical usage: - * ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, bpf_prog_run); + * ret = bpf_prog_run_array(rcu_dereference(&bpf_prog_array), ctx, bpf_prog_run); * * the structure returned by bpf_prog_array_alloc() should be populated * with program pointers and the last pointer must be NULL. @@ -1315,83 +1315,22 @@ static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx) typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx); -static __always_inline int -BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, - const void *ctx, bpf_prog_run_fn run_prog, - int retval, u32 *ret_flags) -{ - const struct bpf_prog_array_item *item; - const struct bpf_prog *prog; - const struct bpf_prog_array *array; - struct bpf_run_ctx *old_run_ctx; - struct bpf_cg_run_ctx run_ctx; - u32 func_ret; - - run_ctx.retval = retval; - migrate_disable(); - rcu_read_lock(); - array = rcu_dereference(array_rcu); - item = &array->items[0]; - old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); - while ((prog = READ_ONCE(item->prog))) { - run_ctx.prog_item = item; - func_ret = run_prog(prog, ctx); - if (!(func_ret & 1) && !IS_ERR_VALUE((long)run_ctx.retval)) - run_ctx.retval = -EPERM; - *(ret_flags) |= (func_ret >> 1); - item++; - } - bpf_reset_run_ctx(old_run_ctx); - rcu_read_unlock(); - migrate_enable(); - return run_ctx.retval; -} - -static __always_inline int -BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, - const void *ctx, bpf_prog_run_fn run_prog, - int retval) -{ - const struct bpf_prog_array_item *item; - const struct bpf_prog *prog; - const struct bpf_prog_array *array; - struct bpf_run_ctx *old_run_ctx; - struct bpf_cg_run_ctx run_ctx; - - run_ctx.retval = retval; - migrate_disable(); - rcu_read_lock(); - array = rcu_dereference(array_rcu); - item = &array->items[0]; - old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); - while ((prog = READ_ONCE(item->prog))) { - run_ctx.prog_item = item; - if (!run_prog(prog, ctx) && !IS_ERR_VALUE((long)run_ctx.retval)) - run_ctx.retval = -EPERM; - item++; - } - bpf_reset_run_ctx(old_run_ctx); - rcu_read_unlock(); - migrate_enable(); - return run_ctx.retval; -} - static __always_inline u32 -BPF_PROG_RUN_ARRAY(const struct bpf_prog_array __rcu *array_rcu, +bpf_prog_run_array(const struct bpf_prog_array *array, const void *ctx, bpf_prog_run_fn run_prog) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; - const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_trace_run_ctx run_ctx; u32 ret = 1; - migrate_disable(); - rcu_read_lock(); - array = rcu_dereference(array_rcu); + RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "no rcu lock held"); + if (unlikely(!array)) - goto out; + return ret; + + migrate_disable(); old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { @@ -1400,50 +1339,10 @@ BPF_PROG_RUN_ARRAY(const struct bpf_prog_array __rcu *array_rcu, item++; } bpf_reset_run_ctx(old_run_ctx); -out: - rcu_read_unlock(); migrate_enable(); return ret; } -/* To be used by __cgroup_bpf_run_filter_skb for EGRESS BPF progs - * so BPF programs can request cwr for TCP packets. - * - * Current cgroup skb programs can only return 0 or 1 (0 to drop the - * packet. This macro changes the behavior so the low order bit - * indicates whether the packet should be dropped (0) or not (1) - * and the next bit is a congestion notification bit. This could be - * used by TCP to call tcp_enter_cwr() - * - * Hence, new allowed return values of CGROUP EGRESS BPF programs are: - * 0: drop packet - * 1: keep packet - * 2: drop packet and cn - * 3: keep packet and cn - * - * This macro then converts it to one of the NET_XMIT or an error - * code that is then interpreted as drop packet (and no cn): - * 0: NET_XMIT_SUCCESS skb should be transmitted - * 1: NET_XMIT_DROP skb should be dropped and cn - * 2: NET_XMIT_CN skb should be transmitted and cn - * 3: -err skb should be dropped - */ -#define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \ - ({ \ - u32 _flags = 0; \ - bool _cn; \ - u32 _ret; \ - _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, 0, &_flags); \ - _cn = _flags & BPF_RET_SET_CN; \ - if (_ret && !IS_ERR_VALUE((long)_ret)) \ - _ret = -EFAULT; \ - if (!_ret) \ - _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ - else \ - _ret = (_cn ? NET_XMIT_DROP : _ret); \ - _ret; \ - }) - #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); extern struct mutex bpf_stats_enabled_mutex; -- cgit v1.2.3 From 368cfcbaa3bf7a8c482f596a131dea4befeba10a Mon Sep 17 00:00:00 2001 From: Michael Srba Date: Mon, 11 Apr 2022 09:21:52 +0200 Subject: dt-bindings: clock: gcc-msm8998: Add definitions of SSC-related clocks Add definitions of four clocks which need to be manipulated in order to initialize the AHB bus which exposes the SCC block in the global address space. Signed-off-by: Michael Srba Acked-by: Rob Herring Reviewed-by: Stephen Boyd Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220411072156.24451-2-michael.srba@seznam.cz --- include/dt-bindings/clock/qcom,gcc-msm8998.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,gcc-msm8998.h b/include/dt-bindings/clock/qcom,gcc-msm8998.h index 72c99e486d86..1badb4f9c58f 100644 --- a/include/dt-bindings/clock/qcom,gcc-msm8998.h +++ b/include/dt-bindings/clock/qcom,gcc-msm8998.h @@ -186,6 +186,10 @@ #define UFS_UNIPRO_CORE_CLK_SRC 177 #define GCC_MMSS_GPLL0_CLK 178 #define HMSS_GPLL0_CLK_SRC 179 +#define GCC_IM_SLEEP 180 +#define AGGRE2_SNOC_NORTH_AXI 181 +#define SSC_XO 182 +#define SSC_CNOC_AHBS_CLK 183 #define PCIE_0_GDSC 0 #define UFS_GDSC 1 -- cgit v1.2.3 From 705191b03d507744c7e097f78d583621c14988ac Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 19 Apr 2022 15:14:23 +0200 Subject: fs: fix acl translation Last cycle we extended the idmapped mounts infrastructure to support idmapped mounts of idmapped filesystems (No such filesystem yet exist.). Since then, the meaning of an idmapped mount is a mount whose idmapping is different from the filesystems idmapping. While doing that work we missed to adapt the acl translation helpers. They still assume that checking for the identity mapping is enough. But they need to use the no_idmapping() helper instead. Note, POSIX ACLs are always translated right at the userspace-kernel boundary using the caller's current idmapping and the initial idmapping. The order depends on whether we're coming from or going to userspace. The filesystem's idmapping doesn't matter at the border. Consequently, if a non-idmapped mount is passed we need to make sure to always pass the initial idmapping as the mount's idmapping and not the filesystem idmapping. Since it's irrelevant here it would yield invalid ids and prevent setting acls for filesystems that are mountable in a userns and support posix acls (tmpfs and fuse). I verified the regression reported in [1] and verified that this patch fixes it. A regression test will be added to xfstests in parallel. Link: https://bugzilla.kernel.org/show_bug.cgi?id=215849 [1] Fixes: bd303368b776 ("fs: support mapped mounts of mapped filesystems") Cc: Seth Forshee Cc: Christoph Hellwig Cc: # 5.17 Cc: Signed-off-by: Christian Brauner (Microsoft) Signed-off-by: Linus Torvalds --- include/linux/posix_acl_xattr.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/posix_acl_xattr.h b/include/linux/posix_acl_xattr.h index 060e8d203181..1766e1de6956 100644 --- a/include/linux/posix_acl_xattr.h +++ b/include/linux/posix_acl_xattr.h @@ -34,15 +34,19 @@ posix_acl_xattr_count(size_t size) #ifdef CONFIG_FS_POSIX_ACL void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size); void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size); #else static inline void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size) { } static inline void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size) { } -- cgit v1.2.3 From 559089e0a93d44280ec3ab478830af319c56dbe3 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 15 Apr 2022 09:44:10 -0700 Subject: vmalloc: replace VM_NO_HUGE_VMAP with VM_ALLOW_HUGE_VMAP Huge page backed vmalloc memory could benefit performance in many cases. However, some users of vmalloc may not be ready to handle huge pages for various reasons: hardware constraints, potential pages split, etc. VM_NO_HUGE_VMAP was introduced to allow vmalloc users to opt-out huge pages. However, it is not easy to track down all the users that require the opt-out, as the allocation are passed different stacks and may cause issues in different layers. To address this issue, replace VM_NO_HUGE_VMAP with an opt-in flag, VM_ALLOW_HUGE_VMAP, so that users that benefit from huge pages could ask specificially. Also, remove vmalloc_no_huge() and add opt-in helper vmalloc_huge(). Fixes: fac54e2bfb5b ("x86/Kconfig: Select HAVE_ARCH_HUGE_VMALLOC with HAVE_ARCH_HUGE_VMAP") Link: https://lore.kernel.org/netdev/14444103-d51b-0fb3-ee63-c3f182f0b546@molgen.mpg.de/" Reviewed-by: Christoph Hellwig Signed-off-by: Song Liu Reviewed-by: Rik van Riel Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 3b1df7da402d..b159c2789961 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -26,7 +26,7 @@ struct notifier_block; /* in notifier.h */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ #define VM_FLUSH_RESET_PERMS 0x00000100 /* reset direct map and flush TLB on unmap, can't be freed in atomic context */ #define VM_MAP_PUT_PAGES 0x00000200 /* put pages and free array in vfree */ -#define VM_NO_HUGE_VMAP 0x00000400 /* force PAGE_SIZE pte mapping */ +#define VM_ALLOW_HUGE_VMAP 0x00000400 /* Allow for huge pages on archs with HAVE_ARCH_HUGE_VMALLOC */ #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ !defined(CONFIG_KASAN_VMALLOC) @@ -153,7 +153,7 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align, const void *caller) __alloc_size(1); void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) __alloc_size(1); -void *vmalloc_no_huge(unsigned long size) __alloc_size(1); +void *vmalloc_huge(unsigned long size, gfp_t gfp_mask) __alloc_size(1); extern void *__vmalloc_array(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); extern void *vmalloc_array(size_t n, size_t size) __alloc_size(1, 2); -- cgit v1.2.3 From b83deaa741558babf4b8d51d34f6637ccfff1b26 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 28 May 2020 22:57:40 +0200 Subject: ARM: pxa: move pcmcia board data into mach-pxa The drivers/pcmcia/pxa2xx_*.c are essentially part of the board files, but for historic reasons located in drivers/pcmcia. Move them into the same place as the actual board file to avoid lots of machine header inclusions. Cc: Marek Vasut Cc: Dominik Brodowski Cc: Jonathan Cameron Signed-off-by: Arnd Bergmann --- include/linux/platform_data/pcmcia-pxa2xx_viper.h | 12 --- include/pcmcia/soc_common.h | 125 ++++++++++++++++++++++ 2 files changed, 125 insertions(+), 12 deletions(-) delete mode 100644 include/linux/platform_data/pcmcia-pxa2xx_viper.h create mode 100644 include/pcmcia/soc_common.h (limited to 'include') diff --git a/include/linux/platform_data/pcmcia-pxa2xx_viper.h b/include/linux/platform_data/pcmcia-pxa2xx_viper.h deleted file mode 100644 index a23b58aff9e1..000000000000 --- a/include/linux/platform_data/pcmcia-pxa2xx_viper.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ARCOM_PCMCIA_H -#define __ARCOM_PCMCIA_H - -struct arcom_pcmcia_pdata { - int cd_gpio; - int rdy_gpio; - int pwr_gpio; - void (*reset)(int state); -}; - -#endif diff --git a/include/pcmcia/soc_common.h b/include/pcmcia/soc_common.h new file mode 100644 index 000000000000..26f1473a06c5 --- /dev/null +++ b/include/pcmcia/soc_common.h @@ -0,0 +1,125 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include + +struct module; +struct cpufreq_freqs; + +struct soc_pcmcia_regulator { + struct regulator *reg; + bool on; +}; + +struct pcmcia_state { + unsigned detect: 1, + ready: 1, + bvd1: 1, + bvd2: 1, + wrprot: 1, + vs_3v: 1, + vs_Xv: 1; +}; + +/* + * This structure encapsulates per-socket state which we might need to + * use when responding to a Card Services query of some kind. + */ +struct soc_pcmcia_socket { + struct pcmcia_socket socket; + + /* + * Info from low level handler + */ + unsigned int nr; + struct clk *clk; + + /* + * Core PCMCIA state + */ + const struct pcmcia_low_level *ops; + + unsigned int status; + socket_state_t cs_state; + + unsigned short spd_io[MAX_IO_WIN]; + unsigned short spd_mem[MAX_WIN]; + unsigned short spd_attr[MAX_WIN]; + + struct resource res_skt; + struct resource res_io; + struct resource res_mem; + struct resource res_attr; + void __iomem *virt_io; + + struct { + int gpio; + struct gpio_desc *desc; + unsigned int irq; + const char *name; + } stat[6]; +#define SOC_STAT_CD 0 /* Card detect */ +#define SOC_STAT_BVD1 1 /* BATDEAD / IOSTSCHG */ +#define SOC_STAT_BVD2 2 /* BATWARN / IOSPKR */ +#define SOC_STAT_RDY 3 /* Ready / Interrupt */ +#define SOC_STAT_VS1 4 /* Voltage sense 1 */ +#define SOC_STAT_VS2 5 /* Voltage sense 2 */ + + struct gpio_desc *gpio_reset; + struct gpio_desc *gpio_bus_enable; + struct soc_pcmcia_regulator vcc; + struct soc_pcmcia_regulator vpp; + + unsigned int irq_state; + +#ifdef CONFIG_CPU_FREQ + struct notifier_block cpufreq_nb; +#endif + struct timer_list poll_timer; + struct list_head node; + void *driver_data; +}; + + +struct pcmcia_low_level { + struct module *owner; + + /* first socket in system */ + int first; + /* nr of sockets */ + int nr; + + int (*hw_init)(struct soc_pcmcia_socket *); + void (*hw_shutdown)(struct soc_pcmcia_socket *); + + void (*socket_state)(struct soc_pcmcia_socket *, struct pcmcia_state *); + int (*configure_socket)(struct soc_pcmcia_socket *, const socket_state_t *); + + /* + * Enable card status IRQs on (re-)initialisation. This can + * be called at initialisation, power management event, or + * pcmcia event. + */ + void (*socket_init)(struct soc_pcmcia_socket *); + + /* + * Disable card status IRQs and PCMCIA bus on suspend. + */ + void (*socket_suspend)(struct soc_pcmcia_socket *); + + /* + * Hardware specific timing routines. + * If provided, the get_timing routine overrides the SOC default. + */ + unsigned int (*get_timing)(struct soc_pcmcia_socket *, unsigned int, unsigned int); + int (*set_timing)(struct soc_pcmcia_socket *); + int (*show_timing)(struct soc_pcmcia_socket *, char *); + +#ifdef CONFIG_CPU_FREQ + /* + * CPUFREQ support. + */ + int (*frequency_change)(struct soc_pcmcia_socket *, unsigned long, struct cpufreq_freqs *); +#endif +}; + + + -- cgit v1.2.3 From d4e5268a08b211b536fed29beb24271ecd85187e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 8 Apr 2022 11:45:55 +0200 Subject: x86,objtool: Mark cpu_startup_entry() __noreturn GCC-8 isn't clever enough to figure out that cpu_start_entry() is a noreturn while objtool is. This results in code after the call in start_secondary(). Give GCC a hand so that they all agree on things. vmlinux.o: warning: objtool: start_secondary()+0x10e: unreachable Reported-by: Rick Edgecombe Signed-off-by: Peter Zijlstra (Intel) Acked-by: Josh Poimboeuf Link: https://lore.kernel.org/r/20220408094718.383658532@infradead.org --- include/linux/cpu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 9cf51e41e697..54dc2f9a2d56 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -167,7 +167,7 @@ static inline int suspend_disable_secondary_cpus(void) { return 0; } static inline void suspend_enable_secondary_cpus(void) { } #endif /* !CONFIG_PM_SLEEP_SMP */ -void cpu_startup_entry(enum cpuhp_state state); +void __noreturn cpu_startup_entry(enum cpuhp_state state); void cpu_idle_poll_ctrl(bool enable); -- cgit v1.2.3 From 72c3c8d6e5275b19fd2d32ec787e8135a421c7ec Mon Sep 17 00:00:00 2001 From: Matt Atwood Date: Mon, 18 Apr 2022 11:51:57 +0530 Subject: drm/i915/rpl-p: Add PCI IDs Adding initial PCI ids for RPL-P. RPL-P behaves identically to ADL-P from i915's point of view. Changes since V1 : - SUBPLATFORM ADL_N and RPL_P clash as both are ADLP based - Matthew R Bspec: 55376 Signed-off-by: Matt Atwood Signed-off-by: Madhumitha Tolakanahalli Pradeep Signed-off-by: Tejas Upadhyay [mattrope: Corrected comment formatting to match coding style] Signed-off-by: Matt Roper Link: https://patchwork.freedesktop.org/patch/msgid/20220418062157.2974665-1-tejaskumarx.surendrakumar.upadhyay@intel.com --- include/drm/i915_pciids.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h index 0800dc8b98b3..a7b5eea7ffaa 100644 --- a/include/drm/i915_pciids.h +++ b/include/drm/i915_pciids.h @@ -683,4 +683,13 @@ INTEL_VGA_DEVICE(0xA78A, info), \ INTEL_VGA_DEVICE(0xA78B, info) +/* RPL-P */ +#define INTEL_RPLP_IDS(info) \ + INTEL_VGA_DEVICE(0xA720, info), \ + INTEL_VGA_DEVICE(0xA721, info), \ + INTEL_VGA_DEVICE(0xA7A0, info), \ + INTEL_VGA_DEVICE(0xA7A1, info), \ + INTEL_VGA_DEVICE(0xA7A8, info), \ + INTEL_VGA_DEVICE(0xA7A9, info) + #endif /* _I915_PCIIDS_H */ -- cgit v1.2.3 From dcf456c9a095a6e71f53d6f6f004133ee851ee70 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Mon, 18 Apr 2022 15:51:58 +0000 Subject: bpf: Fix usage of trace RCU in local storage. bpf_{sk,task,inode}_storage_free() do not need to use call_rcu_tasks_trace as no BPF program should be accessing the owner as it's being destroyed. The only other reader at this point is bpf_local_storage_map_free() which uses normal RCU. The only path that needs trace RCU are: * bpf_local_storage_{delete,update} helpers * map_{delete,update}_elem() syscalls Fixes: 0fe4b381a59e ("bpf: Allow bpf_local_storage to be used by sleepable programs") Signed-off-by: KP Singh Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20220418155158.2865678-1-kpsingh@kernel.org --- include/linux/bpf_local_storage.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 493e63258497..7ea18d4da84b 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -143,9 +143,9 @@ void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem, - bool uncharge_omem); + bool uncharge_omem, bool use_trace_rcu); -void bpf_selem_unlink(struct bpf_local_storage_elem *selem); +void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool use_trace_rcu); void bpf_selem_link_map(struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem); -- cgit v1.2.3 From 3abfaefb9a6dda5e0bfa6160f55abfd0e32d8b0a Mon Sep 17 00:00:00 2001 From: Liu Ying Date: Tue, 19 Apr 2022 09:08:49 +0800 Subject: phy: Add LVDS configuration options This patch allows LVDS PHYs to be configured through the generic functions and through a custom structure added to the generic union. The parameters added here are based on common LVDS PHY implementation practices. The set of parameters should cover all potential users. Cc: Kishon Vijay Abraham I Cc: Vinod Koul Cc: NXP Linux Team Signed-off-by: Liu Ying Link: https://lore.kernel.org/r/20220419010852.452169-3-victor.liu@nxp.com Signed-off-by: Vinod Koul --- include/linux/phy/phy-lvds.h | 32 ++++++++++++++++++++++++++++++++ include/linux/phy/phy.h | 4 ++++ 2 files changed, 36 insertions(+) create mode 100644 include/linux/phy/phy-lvds.h (limited to 'include') diff --git a/include/linux/phy/phy-lvds.h b/include/linux/phy/phy-lvds.h new file mode 100644 index 000000000000..09931d080a6d --- /dev/null +++ b/include/linux/phy/phy-lvds.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2020,2022 NXP + */ + +#ifndef __PHY_LVDS_H_ +#define __PHY_LVDS_H_ + +/** + * struct phy_configure_opts_lvds - LVDS configuration set + * @bits_per_lane_and_dclk_cycle: Number of bits per lane per differential + * clock cycle. + * @differential_clk_rate: Clock rate, in Hertz, of the LVDS + * differential clock. + * @lanes: Number of active, consecutive, + * data lanes, starting from lane 0, + * used for the transmissions. + * @is_slave: Boolean, true if the phy is a slave + * which works together with a master + * phy to support dual link transmission, + * otherwise a regular phy or a master phy. + * + * This structure is used to represent the configuration state of a LVDS phy. + */ +struct phy_configure_opts_lvds { + unsigned int bits_per_lane_and_dclk_cycle; + unsigned long differential_clk_rate; + unsigned int lanes; + bool is_slave; +}; + +#endif /* __PHY_LVDS_H_ */ diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index f3286f4cd306..b1413757fcc3 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -17,6 +17,7 @@ #include #include +#include #include struct phy; @@ -57,10 +58,13 @@ enum phy_media { * the MIPI_DPHY phy mode. * @dp: Configuration set applicable for phys supporting * the DisplayPort protocol. + * @lvds: Configuration set applicable for phys supporting + * the LVDS phy mode. */ union phy_configure_opts { struct phy_configure_opts_mipi_dphy mipi_dphy; struct phy_configure_opts_dp dp; + struct phy_configure_opts_lvds lvds; }; /** -- cgit v1.2.3 From 34951fcf26c59e78ae430fba1fce7c08b1871249 Mon Sep 17 00:00:00 2001 From: Boris Sukholitko Date: Tue, 19 Apr 2022 11:14:32 +0300 Subject: flow_dissector: Add number of vlan tags dissector Our customers in the fiber telecom world have network configurations where they would like to control their traffic according to the number of tags appearing in the packet. For example, TR247 GPON conformance test suite specification mostly talks about untagged, single, double tagged packets and gives lax guidelines on the vlan protocol vs. number of vlan tags. This is different from the common IT networks where 802.1Q and 802.1ad protocols are usually describe single and double tagged packet. GPON configurations that we work with have arbitrary mix the above protocols and number of vlan tags in the packet. The goal is to make the following TC commands possible: tc filter add dev eth1 ingress flower \ num_of_vlans 1 vlan_prio 5 action drop From our logs, we have redirect rules such that: tc filter add dev $GPON ingress flower num_of_vlans $N \ action mirred egress redirect dev $DEV where N can range from 0 to 3 and $DEV is the function of $N. Also there are rules setting skb mark based on the number of vlans: tc filter add dev $GPON ingress flower num_of_vlans $N vlan_prio \ $P action skbedit mark $M This new dissector allows extracting the number of vlan tags existing in the packet. Signed-off-by: Boris Sukholitko Signed-off-by: David S. Miller --- include/net/flow_dissector.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 9f65f1bfbd24..a4c6057c7097 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -253,6 +253,14 @@ struct flow_dissector_key_hash { u32 hash; }; +/** + * struct flow_dissector_key_num_of_vlans: + * @num_of_vlans: num_of_vlans value + */ +struct flow_dissector_key_num_of_vlans { + u8 num_of_vlans; +}; + enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */ FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */ @@ -282,6 +290,7 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_META, /* struct flow_dissector_key_meta */ FLOW_DISSECTOR_KEY_CT, /* struct flow_dissector_key_ct */ FLOW_DISSECTOR_KEY_HASH, /* struct flow_dissector_key_hash */ + FLOW_DISSECTOR_KEY_NUM_OF_VLANS, /* struct flow_dissector_key_num_of_vlans */ FLOW_DISSECTOR_KEY_MAX, }; -- cgit v1.2.3 From b4000312822615ba2222e368188029e9b725dbf4 Mon Sep 17 00:00:00 2001 From: Boris Sukholitko Date: Tue, 19 Apr 2022 11:14:33 +0300 Subject: net/sched: flower: Add number of vlan tags filter These are bookkeeping parts of the new num_of_vlans filter. Defines, dump, load and set are being done here. Signed-off-by: Boris Sukholitko Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 404f97fb239c..9a2ee1e39fad 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -587,6 +587,8 @@ enum { TCA_FLOWER_KEY_HASH, /* u32 */ TCA_FLOWER_KEY_HASH_MASK, /* u32 */ + TCA_FLOWER_KEY_NUM_OF_VLANS, /* u8 */ + __TCA_FLOWER_MAX, }; -- cgit v1.2.3 From fc44ff0ae9f2aa20b64c4e63ab4614156df80240 Mon Sep 17 00:00:00 2001 From: Ben Walker Date: Tue, 1 Mar 2022 11:25:48 -0700 Subject: dmaengine: Document dmaengine_prep_dma_memset Document this function to make clear the expected behavior of the 'value' parameter. It was intended to match the behavior of POSIX memset as laid out here: https://lore.kernel.org/dmaengine/YejrA5ZWZ3lTRO%2F1@matsya/ Signed-off-by: Ben Walker Link: https://lore.kernel.org/r/20220301182551.883474-2-benjamin.walker@intel.com Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 6db9e03afd0b..b46b88e6aa0d 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -1030,6 +1030,14 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_interleaved_dma( return chan->device->device_prep_interleaved_dma(chan, xt, flags); } +/** + * dmaengine_prep_dma_memset() - Prepare a DMA memset descriptor. + * @chan: The channel to be used for this descriptor + * @dest: Address of buffer to be set + * @value: Treated as a single byte value that fills the destination buffer + * @len: The total size of dest + * @flags: DMA engine flags + */ static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memset( struct dma_chan *chan, dma_addr_t dest, int value, size_t len, unsigned long flags) -- cgit v1.2.3 From 5252c1c5a08e583ab1363f809002cd8a59272b35 Mon Sep 17 00:00:00 2001 From: Chun-Kuang Hu Date: Sat, 16 Apr 2022 17:54:28 +0800 Subject: soc: mediatek: cmdq: Use mailbox rx_callback instead of cmdq_task_cb rx_callback is a standard mailbox callback mechanism and could cover the function of proprietary cmdq_task_cb, so use the standard one instead of the proprietary one. Client has changed to use the standard callback machanism and sync dma buffer in client driver, so remove the proprietary callback in cmdq helper. Signed-off-by: Chun-Kuang Hu Reviewed-by: jason-jh.lin Tested-by: jason-jh.lin Link: https://lore.kernel.org/r/1650102868-26219-1-git-send-email-chunkuang.hu@kernel.org Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/mtk-cmdq.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index ac6b5f3cba95..2b498f4f3946 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -268,8 +268,6 @@ int cmdq_pkt_finalize(struct cmdq_pkt *pkt); * cmdq_pkt_flush_async() - trigger CMDQ to asynchronously execute the CMDQ * packet and call back at the end of done packet * @pkt: the CMDQ packet - * @cb: called at the end of done packet - * @data: this data will pass back to cb * * Return: 0 for success; else the error code is returned * @@ -277,7 +275,6 @@ int cmdq_pkt_finalize(struct cmdq_pkt *pkt); * at the end of done packet. Note that this is an ASYNC function. When the * function returned, it may or may not be finished. */ -int cmdq_pkt_flush_async(struct cmdq_pkt *pkt, cmdq_async_flush_cb cb, - void *data); +int cmdq_pkt_flush_async(struct cmdq_pkt *pkt); #endif /* __MTK_CMDQ_H__ */ -- cgit v1.2.3 From b57de4ffd7c6d1247fdaef8437450ab7c1dd4ed0 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 19 Apr 2022 19:27:48 +0100 Subject: KVM: arm64: Simplify kvm_cpu_has_pending_timer() kvm_cpu_has_pending_timer() ends up checking all the possible timers for a wake-up cause. However, we already check for pending interrupts whenever we try to wake-up a vcpu, including the timer interrupts. Obviously, doing the same work twice is once too many. Reduce this helper to almost nothing, but keep it around, as we are going to make use of it soon. Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220419182755.601427-4-maz@kernel.org --- include/kvm/arm_arch_timer.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index 51c19381108c..cd6d8f260eab 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -76,8 +76,6 @@ int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_timer_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); -bool kvm_timer_is_pending(struct kvm_vcpu *vcpu); - u64 kvm_phys_timer_read(void); void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu); -- cgit v1.2.3 From 7a107b2c6b813c3c587d1e76cb405dc637dd2b36 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Wed, 20 Apr 2022 11:19:01 +0300 Subject: Revert "serial: 8250: Handle UART without interrupt on TEMT using em485" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This partially reverts commit f6f586102add. The code added by that commit containted math overflow for 32-bit archs. In addition, the approach used in it is unnecessarily complicated requiring a dedicated timer just for notemt. A simpler approach for providing UART_CAP_NOTEMT already exists (patches 1-2): https://lore.kernel.org/linux-serial/20220411083321.9131-3-ilpo.jarvinen@linux.intel.com/T/#u Thus, simply revert the UART_CAP_NOTEMT change for now. There were two driver changes within the patch series adding UART_CAP_NOTEMT taking advantage of the newly added flag. This does not revert the driver changes and therefore also UART_CAP_NOTEMT define has to remain. UART_CAP_NOTEMT remains no-op until support is again added. Fixes: f6f586102add ("serial: 8250: Handle UART without interrupt on TEMT using em485") Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/5f874142-fb1f-bff7-f33-fac823e65e2e@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index de135852107c..ff84a3ed10ea 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -79,9 +79,7 @@ struct uart_8250_ops { struct uart_8250_em485 { struct hrtimer start_tx_timer; /* "rs485 start tx" timer */ struct hrtimer stop_tx_timer; /* "rs485 stop tx" timer */ - struct hrtimer no_temt_timer; /* "rs485 no TEMT interrupt" timer */ struct hrtimer *active_timer; /* pointer to active timer */ - unsigned long no_temt_delay; /* Delay for no_temt_timer */ struct uart_8250_port *port; /* for hrtimer callbacks */ unsigned int tx_stopped:1; /* tx is currently stopped */ }; -- cgit v1.2.3 From 92ece28072f18f30099770c5d4b8e300ea6820fa Mon Sep 17 00:00:00 2001 From: Liu Jian Date: Sat, 16 Apr 2022 18:58:00 +0800 Subject: net: Change skb_ensure_writable()'s write_len param to unsigned int type Both pskb_may_pull() and skb_clone_writable()'s length parameters are of type unsigned int already. Therefore, change this function's write_len param to unsigned int type. Signed-off-by: Liu Jian Signed-off-by: Daniel Borkmann Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20220416105801.88708-3-liujian56@huawei.com --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2394441fa3dd..b37c829d08e1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3885,7 +3885,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features, unsigned int offset); struct sk_buff *skb_vlan_untag(struct sk_buff *skb); -int skb_ensure_writable(struct sk_buff *skb, int write_len); +int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); -- cgit v1.2.3 From 8cd9efd1b7fb329681d5a5fdf441c8fc8dc4f5ae Mon Sep 17 00:00:00 2001 From: Zack Rusin Date: Mon, 11 Apr 2022 23:35:22 -0400 Subject: drm/ttm: Add common debugfs code for resource managers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Drivers duplicate the code required to add debugfs entries for various ttm resource managers. To fix it add common TTM resource manager debugfs code that each driver can reuse. Specific resource managers can overwrite ttm_resource_manager_func::debug to get more information from those debugfs entries. Signed-off-by: Zack Rusin Cc: Huang Rui Cc: David Airlie Cc: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220412033526.369115-2-zack@kde.org Reviewed-by: Christian König --- include/drm/ttm/ttm_resource.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index f82fee18c07f..441653693970 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -381,4 +381,8 @@ ttm_kmap_iter_linear_io_init(struct ttm_kmap_iter_linear_io *iter_io, void ttm_kmap_iter_linear_io_fini(struct ttm_kmap_iter_linear_io *iter_io, struct ttm_device *bdev, struct ttm_resource *mem); + +void ttm_resource_manager_create_debugfs(struct ttm_resource_manager *man, + struct dentry * parent, + const char *name); #endif -- cgit v1.2.3 From 37c5f9e80e015d0df17d0c377c18523002986851 Mon Sep 17 00:00:00 2001 From: Oleksandr Ocheretnyi Date: Sun, 17 Apr 2022 11:46:47 -0700 Subject: mtd: fix 'part' field data corruption in mtd_info Commit 46b5889cc2c5 ("mtd: implement proper partition handling") started using "mtd_get_master_ofs()" in mtd callbacks to determine memory offsets by means of 'part' field from mtd_info, what previously was smashed accessing 'master' field in the mtd_set_dev_defaults() method. That provides wrong offset what causes hardware access errors. Just make 'part', 'master' as separate fields, rather than using union type to avoid 'part' data corruption when mtd_set_dev_defaults() is called. Fixes: 46b5889cc2c5 ("mtd: implement proper partition handling") Signed-off-by: Oleksandr Ocheretnyi Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20220417184649.449289-1-oocheret@cisco.com --- include/linux/mtd/mtd.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 151607e9d64a..955aee14b0f7 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -389,10 +389,8 @@ struct mtd_info { /* List of partitions attached to this MTD device */ struct list_head partitions; - union { - struct mtd_part part; - struct mtd_master master; - }; + struct mtd_part part; + struct mtd_master master; }; static inline struct mtd_info *mtd_get_master(struct mtd_info *mtd) -- cgit v1.2.3 From f4c5c7f9d2e5ab005d57826b740b694b042a737c Mon Sep 17 00:00:00 2001 From: Felix Matouschek Date: Mon, 18 Apr 2022 15:28:03 +0200 Subject: mtd: spinand: Add support for XTX XT26G0xA Add support for XTX Technology XT26G01AXXXXX, XTX26G02AXXXXX and XTX26G04AXXXXX SPI NAND. These are 3V, 1G/2G/4Gbit serial SLC NAND flash devices with on-die ECC (8bit strength per 512bytes). Tested on Teltonika RUTX10 flashed with OpenWrt. Links: - http://www.xtxtech.com/download/?AId=225 - https://datasheet.lcsc.com/szlcsc/2005251034_XTX-XT26G01AWSEGA_C558841.pdf Signed-off-by: Felix Matouschek Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20220418132803.664103-1-felix@matouschek.org --- include/linux/mtd/spinand.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 3aa28240a77f..5584d3bb6556 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -266,6 +266,7 @@ extern const struct spinand_manufacturer micron_spinand_manufacturer; extern const struct spinand_manufacturer paragon_spinand_manufacturer; extern const struct spinand_manufacturer toshiba_spinand_manufacturer; extern const struct spinand_manufacturer winbond_spinand_manufacturer; +extern const struct spinand_manufacturer xtx_spinand_manufacturer; /** * struct spinand_op_variants - SPI NAND operation variants -- cgit v1.2.3 From 0b0002315adfea3d9eb102665a4441727d4d2621 Mon Sep 17 00:00:00 2001 From: Weili Qian Date: Sat, 16 Apr 2022 18:45:56 +0800 Subject: crypto: hisilicon/qm - remove unused function declaration The 'hisi_qm_get_hw_version' function is unused, so remove the function declaration. Signed-off-by: Weili Qian Signed-off-by: Herbert Xu --- include/linux/hisi_acc_qm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index e5522eaf88fd..5177858aeea9 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -453,7 +453,6 @@ int hisi_qp_send(struct hisi_qp *qp, const void *msg); int hisi_qm_get_free_qp_num(struct hisi_qm *qm); int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number); void hisi_qm_debug_init(struct hisi_qm *qm); -enum qm_hw_ver hisi_qm_get_hw_version(struct pci_dev *pdev); void hisi_qm_debug_regs_clear(struct hisi_qm *qm); int hisi_qm_sriov_enable(struct pci_dev *pdev, int max_vfs); int hisi_qm_sriov_disable(struct pci_dev *pdev, bool is_frozen); -- cgit v1.2.3 From fb06eb9727d67eac16e6b6aff35362476389cb88 Mon Sep 17 00:00:00 2001 From: Weili Qian Date: Sat, 16 Apr 2022 18:45:57 +0800 Subject: crypto: hisilicon/qm - set function with static These functions 'hisi_qm_create_qp' and 'hisi_qm_set_vft' are not used outside qm.c, so they are marked as static. Signed-off-by: Weili Qian Signed-off-by: Herbert Xu --- include/linux/hisi_acc_qm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index 5177858aeea9..e99b286b50bc 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -445,13 +445,11 @@ int hisi_qm_init(struct hisi_qm *qm); void hisi_qm_uninit(struct hisi_qm *qm); int hisi_qm_start(struct hisi_qm *qm); int hisi_qm_stop(struct hisi_qm *qm, enum qm_stop_reason r); -struct hisi_qp *hisi_qm_create_qp(struct hisi_qm *qm, u8 alg_type); int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg); int hisi_qm_stop_qp(struct hisi_qp *qp); void hisi_qm_release_qp(struct hisi_qp *qp); int hisi_qp_send(struct hisi_qp *qp, const void *msg); int hisi_qm_get_free_qp_num(struct hisi_qm *qm); -int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number); void hisi_qm_debug_init(struct hisi_qm *qm); void hisi_qm_debug_regs_clear(struct hisi_qm *qm); int hisi_qm_sriov_enable(struct pci_dev *pdev, int max_vfs); -- cgit v1.2.3 From 7982996c5b0812cbf7846deff0e2f5dcbf290129 Mon Sep 17 00:00:00 2001 From: Weili Qian Date: Sat, 16 Apr 2022 18:45:58 +0800 Subject: crypto: hisilicon/qm - replace hisi_qm_release_qp() with hisi_qm_free_qps() hisi_qm_free_qps() can release multiple queues in one call, and it is already exported. So, replace hisi_qm_release_qp() with hisi_qm_free_qps() in zip_crypto.c, and do not export hisi_qm_release_qp() outside qm.c. Signed-off-by: Weili Qian Signed-off-by: Herbert Xu --- include/linux/hisi_acc_qm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index e99b286b50bc..d2ccb11071c5 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -447,7 +447,6 @@ int hisi_qm_start(struct hisi_qm *qm); int hisi_qm_stop(struct hisi_qm *qm, enum qm_stop_reason r); int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg); int hisi_qm_stop_qp(struct hisi_qp *qp); -void hisi_qm_release_qp(struct hisi_qp *qp); int hisi_qp_send(struct hisi_qp *qp, const void *msg); int hisi_qm_get_free_qp_num(struct hisi_qm *qm); void hisi_qm_debug_init(struct hisi_qm *qm); -- cgit v1.2.3 From b0c42232fce499ba96fbf2c5ebd2368efeb6597e Mon Sep 17 00:00:00 2001 From: Weili Qian Date: Sat, 16 Apr 2022 18:45:59 +0800 Subject: crypto: hisilicon/qm - remove hisi_qm_get_free_qp_num() hisi_qm_get_free_qp_num() is to get the free queue number on the function. It is a simple function and is only called by hisi_qm_get_available_instances(). This patch modifies to get the free queue directly in hisi_qm_get_available_instances(), and remove hisi_qm_get_free_qp_num(). Signed-off-by: Weili Qian Signed-off-by: Herbert Xu --- include/linux/hisi_acc_qm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h index d2ccb11071c5..6cabafffd0dd 100644 --- a/include/linux/hisi_acc_qm.h +++ b/include/linux/hisi_acc_qm.h @@ -448,7 +448,6 @@ int hisi_qm_stop(struct hisi_qm *qm, enum qm_stop_reason r); int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg); int hisi_qm_stop_qp(struct hisi_qp *qp); int hisi_qp_send(struct hisi_qp *qp, const void *msg); -int hisi_qm_get_free_qp_num(struct hisi_qm *qm); void hisi_qm_debug_init(struct hisi_qm *qm); void hisi_qm_debug_regs_clear(struct hisi_qm *qm); int hisi_qm_sriov_enable(struct pci_dev *pdev, int max_vfs); -- cgit v1.2.3 From 6c7f98b334a32df5cac8abac8983ac4ce17cab57 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 11 Apr 2022 16:13:59 +0200 Subject: vfio/mdev: Remove vfio_mdev.c Now that all mdev drivers directly create their own mdev_device driver and directly register with the vfio core's vfio_device_ops this is all dead code. Delete vfio_mdev.c and the mdev_parent_ops members that are connected to it. Signed-off-by: Jason Gunthorpe Signed-off-by: Christoph Hellwig Signed-off-by: Zhi Wang Link: http://patchwork.freedesktop.org/patch/msgid/20220411141403.86980-31-hch@lst.de Reviewed-by: Kirti Wankhede Reviewed-by: Zhi Wang --- include/linux/mdev.h | 48 +----------------------------------------------- 1 file changed, 1 insertion(+), 47 deletions(-) (limited to 'include') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 15d03f6532d0..192aed656116 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -40,40 +40,7 @@ struct device *mtype_get_parent_dev(struct mdev_type *mtype); * @mdev_attr_groups: Attributes of the mediated device. * @supported_type_groups: Attributes to define supported types. It is mandatory * to provide supported types. - * @create: Called to allocate basic resources in parent device's - * driver for a particular mediated device. It is - * mandatory to provide create ops. - * @mdev: mdev_device structure on of mediated device - * that is being created - * Returns integer: success (0) or error (< 0) - * @remove: Called to free resources in parent device's driver for - * a mediated device. It is mandatory to provide 'remove' - * ops. - * @mdev: mdev_device device structure which is being - * destroyed - * Returns integer: success (0) or error (< 0) - * @read: Read emulation callback - * @mdev: mediated device structure - * @buf: read buffer - * @count: number of bytes to read - * @ppos: address. - * Retuns number on bytes read on success or error. - * @write: Write emulation callback - * @mdev: mediated device structure - * @buf: write buffer - * @count: number of bytes to be written - * @ppos: address. - * Retuns number on bytes written on success or error. - * @ioctl: IOCTL callback - * @mdev: mediated device structure - * @cmd: ioctl command - * @arg: arguments to ioctl - * @mmap: mmap callback - * @mdev: mediated device structure - * @vma: vma structure - * @request: request callback to release device - * @mdev: mediated device structure - * @count: request sequence number + * * Parent device that support mediated device should be registered with mdev * module with mdev_parent_ops structure. **/ @@ -83,19 +50,6 @@ struct mdev_parent_ops { const struct attribute_group **dev_attr_groups; const struct attribute_group **mdev_attr_groups; struct attribute_group **supported_type_groups; - - int (*create)(struct mdev_device *mdev); - int (*remove)(struct mdev_device *mdev); - int (*open_device)(struct mdev_device *mdev); - void (*close_device)(struct mdev_device *mdev); - ssize_t (*read)(struct mdev_device *mdev, char __user *buf, - size_t count, loff_t *ppos); - ssize_t (*write)(struct mdev_device *mdev, const char __user *buf, - size_t count, loff_t *ppos); - long (*ioctl)(struct mdev_device *mdev, unsigned int cmd, - unsigned long arg); - int (*mmap)(struct mdev_device *mdev, struct vm_area_struct *vma); - void (*request)(struct mdev_device *mdev, unsigned int count); }; /* interface for exporting mdev supported type attributes */ -- cgit v1.2.3 From e6486939d8ea22569af942a1888aa3824f59cc5e Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 11 Apr 2022 16:14:00 +0200 Subject: vfio/mdev: Remove mdev_parent_ops dev_attr_groups This is only used by one sample to print a fixed string that is pointless. In general, having a device driver attach sysfs attributes to the parent is horrific. This should never happen, and always leads to some kind of liftime bug as it become very difficult for the sysfs attribute to go back to any data owned by the device driver. Remove the general mechanism to create this abuse. Signed-off-by: Jason Gunthorpe Signed-off-by: Christoph Hellwig Signed-off-by: Zhi Wang Link: http://patchwork.freedesktop.org/patch/msgid/20220411141403.86980-32-hch@lst.de Reviewed-by: Kirti Wankhede Reviewed-by: Zhi Wang --- include/linux/mdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 192aed656116..69df1fa2cb6f 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -36,7 +36,6 @@ struct device *mtype_get_parent_dev(struct mdev_type *mtype); * * @owner: The module owner. * @device_driver: Which device driver to probe() on newly created devices - * @dev_attr_groups: Attributes of the parent device. * @mdev_attr_groups: Attributes of the mediated device. * @supported_type_groups: Attributes to define supported types. It is mandatory * to provide supported types. @@ -47,7 +46,6 @@ struct device *mtype_get_parent_dev(struct mdev_type *mtype); struct mdev_parent_ops { struct module *owner; struct mdev_driver *device_driver; - const struct attribute_group **dev_attr_groups; const struct attribute_group **mdev_attr_groups; struct attribute_group **supported_type_groups; }; -- cgit v1.2.3 From 6b42f491e17ce13f5ff7f2d1f49c73a0f4c47b20 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 11 Apr 2022 16:14:01 +0200 Subject: vfio/mdev: Remove mdev_parent_ops The last useful member in this struct is the supported_type_groups, move it to the mdev_driver and delete mdev_parent_ops. Replace it with mdev_driver as an argument to mdev_register_device() Signed-off-by: Jason Gunthorpe Signed-off-by: Christoph Hellwig Signed-off-by: Zhi Wang Link: http://patchwork.freedesktop.org/patch/msgid/20220411141403.86980-33-hch@lst.de Reviewed-by: Kirti Wankhede Reviewed-by: Zhi Wang --- include/linux/mdev.h | 25 ++++--------------------- 1 file changed, 4 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 69df1fa2cb6f..1f6f57a3c316 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -30,26 +30,6 @@ unsigned int mdev_get_type_group_id(struct mdev_device *mdev); unsigned int mtype_get_type_group_id(struct mdev_type *mtype); struct device *mtype_get_parent_dev(struct mdev_type *mtype); -/** - * struct mdev_parent_ops - Structure to be registered for each parent device to - * register the device to mdev module. - * - * @owner: The module owner. - * @device_driver: Which device driver to probe() on newly created devices - * @mdev_attr_groups: Attributes of the mediated device. - * @supported_type_groups: Attributes to define supported types. It is mandatory - * to provide supported types. - * - * Parent device that support mediated device should be registered with mdev - * module with mdev_parent_ops structure. - **/ -struct mdev_parent_ops { - struct module *owner; - struct mdev_driver *device_driver; - const struct attribute_group **mdev_attr_groups; - struct attribute_group **supported_type_groups; -}; - /* interface for exporting mdev supported type attributes */ struct mdev_type_attribute { struct attribute attr; @@ -74,12 +54,15 @@ struct mdev_type_attribute mdev_type_attr_##_name = \ * struct mdev_driver - Mediated device driver * @probe: called when new device created * @remove: called when device removed + * @supported_type_groups: Attributes to define supported types. It is mandatory + * to provide supported types. * @driver: device driver structure * **/ struct mdev_driver { int (*probe)(struct mdev_device *dev); void (*remove)(struct mdev_device *dev); + struct attribute_group **supported_type_groups; struct device_driver driver; }; @@ -98,7 +81,7 @@ static inline const guid_t *mdev_uuid(struct mdev_device *mdev) extern struct bus_type mdev_bus_type; -int mdev_register_device(struct device *dev, const struct mdev_parent_ops *ops); +int mdev_register_device(struct device *dev, struct mdev_driver *mdev_driver); void mdev_unregister_device(struct device *dev); int mdev_register_driver(struct mdev_driver *drv); -- cgit v1.2.3 From 2917f53113be3b7a0f374e02cebe6d6b749366b5 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 11 Apr 2022 16:14:03 +0200 Subject: vfio/mdev: Remove mdev drvdata This is no longer used, remove it. All usages were moved over to either use container_of() from a vfio_device or to use dev_drvdata() directly on the mdev. Signed-off-by: Jason Gunthorpe Signed-off-by: Christoph Hellwig Signed-off-by: Zhi Wang Link: http://patchwork.freedesktop.org/patch/msgid/20220411141403.86980-35-hch@lst.de Reviewed-by: Kirti Wankhede Reviewed-by: Zhi Wang --- include/linux/mdev.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include') diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 1f6f57a3c316..bb539794f54a 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -15,7 +15,6 @@ struct mdev_type; struct mdev_device { struct device dev; guid_t uuid; - void *driver_data; struct list_head next; struct mdev_type *type; bool active; @@ -66,14 +65,6 @@ struct mdev_driver { struct device_driver driver; }; -static inline void *mdev_get_drvdata(struct mdev_device *mdev) -{ - return mdev->driver_data; -} -static inline void mdev_set_drvdata(struct mdev_device *mdev, void *data) -{ - mdev->driver_data = data; -} static inline const guid_t *mdev_uuid(struct mdev_device *mdev) { return &mdev->uuid; -- cgit v1.2.3 From 042c48848b7d8dab4f095bce2872c02f711bf5d0 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 5 Aug 2019 23:15:37 +0200 Subject: ARM: omap1: move lcd_dma code into omapfb driver The omapfb driver is split into platform specific code for omap1, and driver code that is also specific to omap1. Moving both parts into the driver directory simplifies the structure and avoids the dependency on certain omap machine header files. As mach/lcd_dma.h can not be included from include/linux/omap-dma.h any more now, move the omap_lcd_dma_running() declaration into the omap-dma header, which matches where it is defined. Acked-by: Bartlomiej Zolnierkiewicz Acked-by: Tony Lindgren Signed-off-by: Arnd Bergmann --- include/linux/omap-dma.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h index 5c5c93ad6b50..441f5f0919c6 100644 --- a/include/linux/omap-dma.h +++ b/include/linux/omap-dma.h @@ -328,8 +328,8 @@ extern dma_addr_t omap_get_dma_dst_pos(int lch); extern int omap_get_dma_active_status(int lch); extern int omap_dma_running(void); -#if defined(CONFIG_ARCH_OMAP1) && IS_ENABLED(CONFIG_FB_OMAP) -#include +#if IS_ENABLED(CONFIG_FB_OMAP) +extern int omap_lcd_dma_running(void); #else static inline int omap_lcd_dma_running(void) { -- cgit v1.2.3 From 0768fb6709343679e55f7135e2ed2c432e4500d8 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 9 Aug 2019 21:42:31 +0200 Subject: ARM: omap1: declare a dummy omap_set_dma_priority omapfb calls directly into the omap_set_dma_priority() function in the DMA driver. This prevents compile-testing omapfb on other architectures. Add an inline function next to the other ones for non-omap configurations. Acked-by: Bartlomiej Zolnierkiewicz Acked-by: Tony Lindgren Signed-off-by: Arnd Bergmann --- include/linux/omap-dma.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h index 441f5f0919c6..5e228428fda1 100644 --- a/include/linux/omap-dma.h +++ b/include/linux/omap-dma.h @@ -338,6 +338,9 @@ static inline int omap_lcd_dma_running(void) #endif #else /* CONFIG_ARCH_OMAP */ +static inline void omap_set_dma_priority(int lch, int dst_port, int priority) +{ +} static inline struct omap_system_dma_plat_info *omap_get_plat_info(void) { -- cgit v1.2.3 From e8e77e97507bf3ec5419b8067d242b538cf75cba Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 6 Aug 2019 14:34:31 +0200 Subject: ARM: omap1: move mach/usb.h to include/linux/soc The register definitions in this header are used in at least four different places, with little hope of completely cleaning that up. Split up the file into a portion that becomes a linux-wide header under include/linux/soc/ti/, and the parts that are actually only needed by board files. Acked-by: Felipe Balbi Acked-by: Tony Lindgren Signed-off-by: Arnd Bergmann --- include/linux/soc/ti/omap1-usb.h | 116 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 116 insertions(+) create mode 100644 include/linux/soc/ti/omap1-usb.h (limited to 'include') diff --git a/include/linux/soc/ti/omap1-usb.h b/include/linux/soc/ti/omap1-usb.h new file mode 100644 index 000000000000..67488698601a --- /dev/null +++ b/include/linux/soc/ti/omap1-usb.h @@ -0,0 +1,116 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __SOC_TI_OMAP1_USB +#define __SOC_TI_OMAP1_USB +/* + * Constants in this file are used all over the place, in platform + * code, as well as the udc, phy and ohci drivers. + * This is not a great design, but unlikely to get fixed after + * such a long time. Don't do this elsewhere. + */ + +#define OMAP1_OTG_BASE 0xfffb0400 +#define OMAP1_UDC_BASE 0xfffb4000 + +#define OMAP2_UDC_BASE 0x4805e200 +#define OMAP2_OTG_BASE 0x4805e300 +#define OTG_BASE OMAP1_OTG_BASE +#define UDC_BASE OMAP1_UDC_BASE + +/* + * OTG and transceiver registers, for OMAPs starting with ARM926 + */ +#define OTG_REV (OTG_BASE + 0x00) +#define OTG_SYSCON_1 (OTG_BASE + 0x04) +# define USB2_TRX_MODE(w) (((w)>>24)&0x07) +# define USB1_TRX_MODE(w) (((w)>>20)&0x07) +# define USB0_TRX_MODE(w) (((w)>>16)&0x07) +# define OTG_IDLE_EN (1 << 15) +# define HST_IDLE_EN (1 << 14) +# define DEV_IDLE_EN (1 << 13) +# define OTG_RESET_DONE (1 << 2) +# define OTG_SOFT_RESET (1 << 1) +#define OTG_SYSCON_2 (OTG_BASE + 0x08) +# define OTG_EN (1 << 31) +# define USBX_SYNCHRO (1 << 30) +# define OTG_MST16 (1 << 29) +# define SRP_GPDATA (1 << 28) +# define SRP_GPDVBUS (1 << 27) +# define SRP_GPUVBUS(w) (((w)>>24)&0x07) +# define A_WAIT_VRISE(w) (((w)>>20)&0x07) +# define B_ASE_BRST(w) (((w)>>16)&0x07) +# define SRP_DPW (1 << 14) +# define SRP_DATA (1 << 13) +# define SRP_VBUS (1 << 12) +# define OTG_PADEN (1 << 10) +# define HMC_PADEN (1 << 9) +# define UHOST_EN (1 << 8) +# define HMC_TLLSPEED (1 << 7) +# define HMC_TLLATTACH (1 << 6) +# define OTG_HMC(w) (((w)>>0)&0x3f) +#define OTG_CTRL (OTG_BASE + 0x0c) +# define OTG_USB2_EN (1 << 29) +# define OTG_USB2_DP (1 << 28) +# define OTG_USB2_DM (1 << 27) +# define OTG_USB1_EN (1 << 26) +# define OTG_USB1_DP (1 << 25) +# define OTG_USB1_DM (1 << 24) +# define OTG_USB0_EN (1 << 23) +# define OTG_USB0_DP (1 << 22) +# define OTG_USB0_DM (1 << 21) +# define OTG_ASESSVLD (1 << 20) +# define OTG_BSESSEND (1 << 19) +# define OTG_BSESSVLD (1 << 18) +# define OTG_VBUSVLD (1 << 17) +# define OTG_ID (1 << 16) +# define OTG_DRIVER_SEL (1 << 15) +# define OTG_A_SETB_HNPEN (1 << 12) +# define OTG_A_BUSREQ (1 << 11) +# define OTG_B_HNPEN (1 << 9) +# define OTG_B_BUSREQ (1 << 8) +# define OTG_BUSDROP (1 << 7) +# define OTG_PULLDOWN (1 << 5) +# define OTG_PULLUP (1 << 4) +# define OTG_DRV_VBUS (1 << 3) +# define OTG_PD_VBUS (1 << 2) +# define OTG_PU_VBUS (1 << 1) +# define OTG_PU_ID (1 << 0) +#define OTG_IRQ_EN (OTG_BASE + 0x10) /* 16-bit */ +# define DRIVER_SWITCH (1 << 15) +# define A_VBUS_ERR (1 << 13) +# define A_REQ_TMROUT (1 << 12) +# define A_SRP_DETECT (1 << 11) +# define B_HNP_FAIL (1 << 10) +# define B_SRP_TMROUT (1 << 9) +# define B_SRP_DONE (1 << 8) +# define B_SRP_STARTED (1 << 7) +# define OPRT_CHG (1 << 0) +#define OTG_IRQ_SRC (OTG_BASE + 0x14) /* 16-bit */ + // same bits as in IRQ_EN +#define OTG_OUTCTRL (OTG_BASE + 0x18) /* 16-bit */ +# define OTGVPD (1 << 14) +# define OTGVPU (1 << 13) +# define OTGPUID (1 << 12) +# define USB2VDR (1 << 10) +# define USB2PDEN (1 << 9) +# define USB2PUEN (1 << 8) +# define USB1VDR (1 << 6) +# define USB1PDEN (1 << 5) +# define USB1PUEN (1 << 4) +# define USB0VDR (1 << 2) +# define USB0PDEN (1 << 1) +# define USB0PUEN (1 << 0) +#define OTG_TEST (OTG_BASE + 0x20) /* 16-bit */ +#define OTG_VENDOR_CODE (OTG_BASE + 0xfc) /* 16-bit */ + +/*-------------------------------------------------------------------------*/ + +/* OMAP1 */ +#define USB_TRANSCEIVER_CTRL (0xfffe1000 + 0x0064) +# define CONF_USB2_UNI_R (1 << 8) +# define CONF_USB1_UNI_R (1 << 7) +# define CONF_USB_PORT0_R(x) (((x)>>4)&0x7) +# define CONF_USB0_ISOLATE_R (1 << 3) +# define CONF_USB_PWRDN_DM_R (1 << 2) +# define CONF_USB_PWRDN_DP_R (1 << 1) + +#endif -- cgit v1.2.3 From 1e9ca7c811f76b16c7822ad009b6b0c352227a15 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 6 Aug 2019 15:24:58 +0200 Subject: ARM: omap1: move some headers to include/linux/soc There are three remaining header files that are used by omap1 specific device drivers: - mach/soc.h provides cpu_is_omapXXX abstractions - mach/hardware.h provides omap_read/omap_write functions and physical addresses - mach/mux.h provides an omap specific pinctrl abstraction This is generally not how we do platform abstractions today, and it would be good to completely get rid of these in favor of passing information through platform devices and the pinctrl subsystem. However, given that nobody is working on that, just move it one step forward by splitting out the header files that are used by drivers today from the machine headers that are only used internally. Acked-by: Tony Lindgren Signed-off-by: Arnd Bergmann --- include/linux/soc/ti/omap1-io.h | 143 ++++++++++++++++++ include/linux/soc/ti/omap1-mux.h | 311 +++++++++++++++++++++++++++++++++++++++ include/linux/soc/ti/omap1-soc.h | 198 +++++++++++++++++++++++++ 3 files changed, 652 insertions(+) create mode 100644 include/linux/soc/ti/omap1-io.h create mode 100644 include/linux/soc/ti/omap1-mux.h create mode 100644 include/linux/soc/ti/omap1-soc.h (limited to 'include') diff --git a/include/linux/soc/ti/omap1-io.h b/include/linux/soc/ti/omap1-io.h new file mode 100644 index 000000000000..9332c92690f4 --- /dev/null +++ b/include/linux/soc/ti/omap1-io.h @@ -0,0 +1,143 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __ASM_ARCH_OMAP_IO_H +#define __ASM_ARCH_OMAP_IO_H + +#ifndef __ASSEMBLER__ +#include + +#if defined(CONFIG_ARCH_OMAP) && defined(CONFIG_ARCH_OMAP1) +/* + * NOTE: Please use ioremap + __raw_read/write where possible instead of these + */ +extern u8 omap_readb(u32 pa); +extern u16 omap_readw(u32 pa); +extern u32 omap_readl(u32 pa); +extern void omap_writeb(u8 v, u32 pa); +extern void omap_writew(u16 v, u32 pa); +extern void omap_writel(u32 v, u32 pa); +#elif defined(CONFIG_COMPILE_TEST) +static inline u8 omap_readb(u32 pa) { return 0; } +static inline u16 omap_readw(u32 pa) { return 0; } +static inline u32 omap_readl(u32 pa) { return 0; } +static inline void omap_writeb(u8 v, u32 pa) { } +static inline void omap_writew(u16 v, u32 pa) { } +static inline void omap_writel(u32 v, u32 pa) { } +#endif +#endif + +/* + * ---------------------------------------------------------------------------- + * System control registers + * ---------------------------------------------------------------------------- + */ +#define MOD_CONF_CTRL_0 0xfffe1080 +#define MOD_CONF_CTRL_1 0xfffe1110 + +/* + * --------------------------------------------------------------------------- + * UPLD + * --------------------------------------------------------------------------- + */ +#define ULPD_REG_BASE (0xfffe0800) +#define ULPD_IT_STATUS (ULPD_REG_BASE + 0x14) +#define ULPD_SETUP_ANALOG_CELL_3 (ULPD_REG_BASE + 0x24) +#define ULPD_CLOCK_CTRL (ULPD_REG_BASE + 0x30) +# define DIS_USB_PVCI_CLK (1 << 5) /* no USB/FAC synch */ +# define USB_MCLK_EN (1 << 4) /* enable W4_USB_CLKO */ +#define ULPD_SOFT_REQ (ULPD_REG_BASE + 0x34) +# define SOFT_UDC_REQ (1 << 4) +# define SOFT_USB_CLK_REQ (1 << 3) +# define SOFT_DPLL_REQ (1 << 0) +#define ULPD_DPLL_CTRL (ULPD_REG_BASE + 0x3c) +#define ULPD_STATUS_REQ (ULPD_REG_BASE + 0x40) +#define ULPD_APLL_CTRL (ULPD_REG_BASE + 0x4c) +#define ULPD_POWER_CTRL (ULPD_REG_BASE + 0x50) +#define ULPD_SOFT_DISABLE_REQ_REG (ULPD_REG_BASE + 0x68) +# define DIS_MMC2_DPLL_REQ (1 << 11) +# define DIS_MMC1_DPLL_REQ (1 << 10) +# define DIS_UART3_DPLL_REQ (1 << 9) +# define DIS_UART2_DPLL_REQ (1 << 8) +# define DIS_UART1_DPLL_REQ (1 << 7) +# define DIS_USB_HOST_DPLL_REQ (1 << 6) +#define ULPD_SDW_CLK_DIV_CTRL_SEL (ULPD_REG_BASE + 0x74) +#define ULPD_CAM_CLK_CTRL (ULPD_REG_BASE + 0x7c) + +/* + * ---------------------------------------------------------------------------- + * Clocks + * ---------------------------------------------------------------------------- + */ +#define CLKGEN_REG_BASE (0xfffece00) +#define ARM_CKCTL (CLKGEN_REG_BASE + 0x0) +#define ARM_IDLECT1 (CLKGEN_REG_BASE + 0x4) +#define ARM_IDLECT2 (CLKGEN_REG_BASE + 0x8) +#define ARM_EWUPCT (CLKGEN_REG_BASE + 0xC) +#define ARM_RSTCT1 (CLKGEN_REG_BASE + 0x10) +#define ARM_RSTCT2 (CLKGEN_REG_BASE + 0x14) +#define ARM_SYSST (CLKGEN_REG_BASE + 0x18) +#define ARM_IDLECT3 (CLKGEN_REG_BASE + 0x24) + +#define CK_RATEF 1 +#define CK_IDLEF 2 +#define CK_ENABLEF 4 +#define CK_SELECTF 8 +#define SETARM_IDLE_SHIFT + +/* DPLL control registers */ +#define DPLL_CTL (0xfffecf00) + +/* DSP clock control. Must use __raw_readw() and __raw_writew() with these */ +#define DSP_CONFIG_REG_BASE IOMEM(0xe1008000) +#define DSP_CKCTL (DSP_CONFIG_REG_BASE + 0x0) +#define DSP_IDLECT1 (DSP_CONFIG_REG_BASE + 0x4) +#define DSP_IDLECT2 (DSP_CONFIG_REG_BASE + 0x8) +#define DSP_RSTCT2 (DSP_CONFIG_REG_BASE + 0x14) + +/* + * ---------------------------------------------------------------------------- + * Pulse-Width Light + * ---------------------------------------------------------------------------- + */ +#define OMAP_PWL_BASE 0xfffb5800 +#define OMAP_PWL_ENABLE (OMAP_PWL_BASE + 0x00) +#define OMAP_PWL_CLK_ENABLE (OMAP_PWL_BASE + 0x04) + +/* + * ---------------------------------------------------------------------------- + * Pin multiplexing registers + * ---------------------------------------------------------------------------- + */ +#define FUNC_MUX_CTRL_0 0xfffe1000 +#define FUNC_MUX_CTRL_1 0xfffe1004 +#define FUNC_MUX_CTRL_2 0xfffe1008 +#define COMP_MODE_CTRL_0 0xfffe100c +#define FUNC_MUX_CTRL_3 0xfffe1010 +#define FUNC_MUX_CTRL_4 0xfffe1014 +#define FUNC_MUX_CTRL_5 0xfffe1018 +#define FUNC_MUX_CTRL_6 0xfffe101C +#define FUNC_MUX_CTRL_7 0xfffe1020 +#define FUNC_MUX_CTRL_8 0xfffe1024 +#define FUNC_MUX_CTRL_9 0xfffe1028 +#define FUNC_MUX_CTRL_A 0xfffe102C +#define FUNC_MUX_CTRL_B 0xfffe1030 +#define FUNC_MUX_CTRL_C 0xfffe1034 +#define FUNC_MUX_CTRL_D 0xfffe1038 +#define PULL_DWN_CTRL_0 0xfffe1040 +#define PULL_DWN_CTRL_1 0xfffe1044 +#define PULL_DWN_CTRL_2 0xfffe1048 +#define PULL_DWN_CTRL_3 0xfffe104c +#define PULL_DWN_CTRL_4 0xfffe10ac + +/* OMAP-1610 specific multiplexing registers */ +#define FUNC_MUX_CTRL_E 0xfffe1090 +#define FUNC_MUX_CTRL_F 0xfffe1094 +#define FUNC_MUX_CTRL_10 0xfffe1098 +#define FUNC_MUX_CTRL_11 0xfffe109c +#define FUNC_MUX_CTRL_12 0xfffe10a0 +#define PU_PD_SEL_0 0xfffe10b4 +#define PU_PD_SEL_1 0xfffe10b8 +#define PU_PD_SEL_2 0xfffe10bc +#define PU_PD_SEL_3 0xfffe10c0 +#define PU_PD_SEL_4 0xfffe10c4 + +#endif diff --git a/include/linux/soc/ti/omap1-mux.h b/include/linux/soc/ti/omap1-mux.h new file mode 100644 index 000000000000..59c239b5569c --- /dev/null +++ b/include/linux/soc/ti/omap1-mux.h @@ -0,0 +1,311 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef __SOC_TI_OMAP1_MUX_H +#define __SOC_TI_OMAP1_MUX_H +/* + * This should not really be a global header, it reflects the + * traditional way that omap1 does pin muxing without the + * pinctrl subsystem. + */ + +enum omap7xx_index { + /* OMAP 730 keyboard */ + E2_7XX_KBR0, + J7_7XX_KBR1, + E1_7XX_KBR2, + F3_7XX_KBR3, + D2_7XX_KBR4, + C2_7XX_KBC0, + D3_7XX_KBC1, + E4_7XX_KBC2, + F4_7XX_KBC3, + E3_7XX_KBC4, + + /* USB */ + AA17_7XX_USB_DM, + W16_7XX_USB_PU_EN, + W17_7XX_USB_VBUSI, + W18_7XX_USB_DMCK_OUT, + W19_7XX_USB_DCRST, + + /* MMC */ + MMC_7XX_CMD, + MMC_7XX_CLK, + MMC_7XX_DAT0, + + /* I2C */ + I2C_7XX_SCL, + I2C_7XX_SDA, + + /* SPI */ + SPI_7XX_1, + SPI_7XX_2, + SPI_7XX_3, + SPI_7XX_4, + SPI_7XX_5, + SPI_7XX_6, + + /* UART */ + UART_7XX_1, + UART_7XX_2, +}; + +enum omap1xxx_index { + /* UART1 (BT_UART_GATING)*/ + UART1_TX = 0, + UART1_RTS, + + /* UART2 (COM_UART_GATING)*/ + UART2_TX, + UART2_RX, + UART2_CTS, + UART2_RTS, + + /* UART3 (GIGA_UART_GATING) */ + UART3_TX, + UART3_RX, + UART3_CTS, + UART3_RTS, + UART3_CLKREQ, + UART3_BCLK, /* 12MHz clock out */ + Y15_1610_UART3_RTS, + + /* PWT & PWL */ + PWT, + PWL, + + /* USB master generic */ + R18_USB_VBUS, + R18_1510_USB_GPIO0, + W4_USB_PUEN, + W4_USB_CLKO, + W4_USB_HIGHZ, + W4_GPIO58, + + /* USB1 master */ + USB1_SUSP, + USB1_SEO, + W13_1610_USB1_SE0, + USB1_TXEN, + USB1_TXD, + USB1_VP, + USB1_VM, + USB1_RCV, + USB1_SPEED, + R13_1610_USB1_SPEED, + R13_1710_USB1_SE0, + + /* USB2 master */ + USB2_SUSP, + USB2_VP, + USB2_TXEN, + USB2_VM, + USB2_RCV, + USB2_SEO, + USB2_TXD, + + /* OMAP-1510 GPIO */ + R18_1510_GPIO0, + R19_1510_GPIO1, + M14_1510_GPIO2, + + /* OMAP1610 GPIO */ + P18_1610_GPIO3, + Y15_1610_GPIO17, + + /* OMAP-1710 GPIO */ + R18_1710_GPIO0, + V2_1710_GPIO10, + N21_1710_GPIO14, + W15_1710_GPIO40, + + /* MPUIO */ + MPUIO2, + N15_1610_MPUIO2, + MPUIO4, + MPUIO5, + T20_1610_MPUIO5, + W11_1610_MPUIO6, + V10_1610_MPUIO7, + W11_1610_MPUIO9, + V10_1610_MPUIO10, + W10_1610_MPUIO11, + E20_1610_MPUIO13, + U20_1610_MPUIO14, + E19_1610_MPUIO15, + + /* MCBSP2 */ + MCBSP2_CLKR, + MCBSP2_CLKX, + MCBSP2_DR, + MCBSP2_DX, + MCBSP2_FSR, + MCBSP2_FSX, + + /* MCBSP3 */ + MCBSP3_CLKX, + + /* Misc ballouts */ + BALLOUT_V8_ARMIO3, + N20_HDQ, + + /* OMAP-1610 MMC2 */ + W8_1610_MMC2_DAT0, + V8_1610_MMC2_DAT1, + W15_1610_MMC2_DAT2, + R10_1610_MMC2_DAT3, + Y10_1610_MMC2_CLK, + Y8_1610_MMC2_CMD, + V9_1610_MMC2_CMDDIR, + V5_1610_MMC2_DATDIR0, + W19_1610_MMC2_DATDIR1, + R18_1610_MMC2_CLKIN, + + /* OMAP-1610 External Trace Interface */ + M19_1610_ETM_PSTAT0, + L15_1610_ETM_PSTAT1, + L18_1610_ETM_PSTAT2, + L19_1610_ETM_D0, + J19_1610_ETM_D6, + J18_1610_ETM_D7, + + /* OMAP16XX GPIO */ + P20_1610_GPIO4, + V9_1610_GPIO7, + W8_1610_GPIO9, + N20_1610_GPIO11, + N19_1610_GPIO13, + P10_1610_GPIO22, + V5_1610_GPIO24, + AA20_1610_GPIO_41, + W19_1610_GPIO48, + M7_1610_GPIO62, + V14_16XX_GPIO37, + R9_16XX_GPIO18, + L14_16XX_GPIO49, + + /* OMAP-1610 uWire */ + V19_1610_UWIRE_SCLK, + U18_1610_UWIRE_SDI, + W21_1610_UWIRE_SDO, + N14_1610_UWIRE_CS0, + P15_1610_UWIRE_CS3, + N15_1610_UWIRE_CS1, + + /* OMAP-1610 SPI */ + U19_1610_SPIF_SCK, + U18_1610_SPIF_DIN, + P20_1610_SPIF_DIN, + W21_1610_SPIF_DOUT, + R18_1610_SPIF_DOUT, + N14_1610_SPIF_CS0, + N15_1610_SPIF_CS1, + T19_1610_SPIF_CS2, + P15_1610_SPIF_CS3, + + /* OMAP-1610 Flash */ + L3_1610_FLASH_CS2B_OE, + M8_1610_FLASH_CS2B_WE, + + /* First MMC */ + MMC_CMD, + MMC_DAT1, + MMC_DAT2, + MMC_DAT0, + MMC_CLK, + MMC_DAT3, + + /* OMAP-1710 MMC CMDDIR and DATDIR0 */ + M15_1710_MMC_CLKI, + P19_1710_MMC_CMDDIR, + P20_1710_MMC_DATDIR0, + + /* OMAP-1610 USB0 alternate pin configuration */ + W9_USB0_TXEN, + AA9_USB0_VP, + Y5_USB0_RCV, + R9_USB0_VM, + V6_USB0_TXD, + W5_USB0_SE0, + V9_USB0_SPEED, + V9_USB0_SUSP, + + /* USB2 */ + W9_USB2_TXEN, + AA9_USB2_VP, + Y5_USB2_RCV, + R9_USB2_VM, + V6_USB2_TXD, + W5_USB2_SE0, + + /* 16XX UART */ + R13_1610_UART1_TX, + V14_16XX_UART1_RX, + R14_1610_UART1_CTS, + AA15_1610_UART1_RTS, + R9_16XX_UART2_RX, + L14_16XX_UART3_RX, + + /* I2C OMAP-1610 */ + I2C_SCL, + I2C_SDA, + + /* Keypad */ + F18_1610_KBC0, + D20_1610_KBC1, + D19_1610_KBC2, + E18_1610_KBC3, + C21_1610_KBC4, + G18_1610_KBR0, + F19_1610_KBR1, + H14_1610_KBR2, + E20_1610_KBR3, + E19_1610_KBR4, + N19_1610_KBR5, + + /* Power management */ + T20_1610_LOW_PWR, + + /* MCLK Settings */ + V5_1710_MCLK_ON, + V5_1710_MCLK_OFF, + R10_1610_MCLK_ON, + R10_1610_MCLK_OFF, + + /* CompactFlash controller */ + P11_1610_CF_CD2, + R11_1610_CF_IOIS16, + V10_1610_CF_IREQ, + W10_1610_CF_RESET, + W11_1610_CF_CD1, + + /* parallel camera */ + J15_1610_CAM_LCLK, + J18_1610_CAM_D7, + J19_1610_CAM_D6, + J14_1610_CAM_D5, + K18_1610_CAM_D4, + K19_1610_CAM_D3, + K15_1610_CAM_D2, + K14_1610_CAM_D1, + L19_1610_CAM_D0, + L18_1610_CAM_VS, + L15_1610_CAM_HS, + M19_1610_CAM_RSTZ, + Y15_1610_CAM_OUTCLK, + + /* serial camera */ + H19_1610_CAM_EXCLK, + Y12_1610_CCP_CLKP, + W13_1610_CCP_CLKM, + W14_1610_CCP_DATAP, + Y14_1610_CCP_DATAM, + +}; + +#ifdef CONFIG_OMAP_MUX +extern int omap_cfg_reg(unsigned long reg_cfg); +#else +static inline int omap_cfg_reg(unsigned long reg_cfg) { return 0; } +#endif + +#endif diff --git a/include/linux/soc/ti/omap1-soc.h b/include/linux/soc/ti/omap1-soc.h new file mode 100644 index 000000000000..81008d400bb6 --- /dev/null +++ b/include/linux/soc/ti/omap1-soc.h @@ -0,0 +1,198 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * OMAP cpu type detection + * + * Copyright (C) 2004, 2008 Nokia Corporation + * + * Copyright (C) 2009-11 Texas Instruments. + * + * Written by Tony Lindgren + * + * Added OMAP4/5 specific defines - Santosh Shilimkar + */ + +#ifndef __ASM_ARCH_OMAP_CPU_H +#define __ASM_ARCH_OMAP_CPU_H + +/* + * Test if multicore OMAP support is needed + */ +#undef MULTI_OMAP1 +#undef OMAP_NAME + +#ifdef CONFIG_ARCH_OMAP730 +# ifdef OMAP_NAME +# undef MULTI_OMAP1 +# define MULTI_OMAP1 +# else +# define OMAP_NAME omap730 +# endif +#endif +#ifdef CONFIG_ARCH_OMAP850 +# ifdef OMAP_NAME +# undef MULTI_OMAP1 +# define MULTI_OMAP1 +# else +# define OMAP_NAME omap850 +# endif +#endif +#ifdef CONFIG_ARCH_OMAP15XX +# ifdef OMAP_NAME +# undef MULTI_OMAP1 +# define MULTI_OMAP1 +# else +# define OMAP_NAME omap1510 +# endif +#endif +#ifdef CONFIG_ARCH_OMAP16XX +# ifdef OMAP_NAME +# undef MULTI_OMAP1 +# define MULTI_OMAP1 +# else +# define OMAP_NAME omap16xx +# endif +#endif + +/* + * omap_rev bits: + * CPU id bits (0730, 1510, 1710, 2422...) [31:16] + * CPU revision (See _REV_ defined in cpu.h) [15:08] + * CPU class bits (15xx, 16xx, 24xx, 34xx...) [07:00] + */ +unsigned int omap_rev(void); + +/* + * Get the CPU revision for OMAP devices + */ +#define GET_OMAP_REVISION() ((omap_rev() >> 8) & 0xff) + +/* + * Macros to group OMAP into cpu classes. + * These can be used in most places. + * cpu_is_omap7xx(): True for OMAP730, OMAP850 + * cpu_is_omap15xx(): True for OMAP1510, OMAP5910 and OMAP310 + * cpu_is_omap16xx(): True for OMAP1610, OMAP5912 and OMAP1710 + */ +#define GET_OMAP_CLASS (omap_rev() & 0xff) + +#define IS_OMAP_CLASS(class, id) \ +static inline int is_omap ##class (void) \ +{ \ + return (GET_OMAP_CLASS == (id)) ? 1 : 0; \ +} + +#define GET_OMAP_SUBCLASS ((omap_rev() >> 20) & 0x0fff) + +#define IS_OMAP_SUBCLASS(subclass, id) \ +static inline int is_omap ##subclass (void) \ +{ \ + return (GET_OMAP_SUBCLASS == (id)) ? 1 : 0; \ +} + +IS_OMAP_CLASS(7xx, 0x07) +IS_OMAP_CLASS(15xx, 0x15) +IS_OMAP_CLASS(16xx, 0x16) + +#define cpu_is_omap7xx() 0 +#define cpu_is_omap15xx() 0 +#define cpu_is_omap16xx() 0 + +#if defined(MULTI_OMAP1) +# if defined(CONFIG_ARCH_OMAP730) +# undef cpu_is_omap7xx +# define cpu_is_omap7xx() is_omap7xx() +# endif +# if defined(CONFIG_ARCH_OMAP850) +# undef cpu_is_omap7xx +# define cpu_is_omap7xx() is_omap7xx() +# endif +# if defined(CONFIG_ARCH_OMAP15XX) +# undef cpu_is_omap15xx +# define cpu_is_omap15xx() is_omap15xx() +# endif +# if defined(CONFIG_ARCH_OMAP16XX) +# undef cpu_is_omap16xx +# define cpu_is_omap16xx() is_omap16xx() +# endif +#else +# if defined(CONFIG_ARCH_OMAP730) +# undef cpu_is_omap7xx +# define cpu_is_omap7xx() 1 +# endif +# if defined(CONFIG_ARCH_OMAP850) +# undef cpu_is_omap7xx +# define cpu_is_omap7xx() 1 +# endif +# if defined(CONFIG_ARCH_OMAP15XX) +# undef cpu_is_omap15xx +# define cpu_is_omap15xx() 1 +# endif +# if defined(CONFIG_ARCH_OMAP16XX) +# undef cpu_is_omap16xx +# define cpu_is_omap16xx() 1 +# endif +#endif + +/* + * Macros to detect individual cpu types. + * These are only rarely needed. + * cpu_is_omap310(): True for OMAP310 + * cpu_is_omap1510(): True for OMAP1510 + * cpu_is_omap1610(): True for OMAP1610 + * cpu_is_omap1611(): True for OMAP1611 + * cpu_is_omap5912(): True for OMAP5912 + * cpu_is_omap1621(): True for OMAP1621 + * cpu_is_omap1710(): True for OMAP1710 + */ +#define GET_OMAP_TYPE ((omap_rev() >> 16) & 0xffff) + +#define IS_OMAP_TYPE(type, id) \ +static inline int is_omap ##type (void) \ +{ \ + return (GET_OMAP_TYPE == (id)) ? 1 : 0; \ +} + +IS_OMAP_TYPE(310, 0x0310) +IS_OMAP_TYPE(1510, 0x1510) +IS_OMAP_TYPE(1610, 0x1610) +IS_OMAP_TYPE(1611, 0x1611) +IS_OMAP_TYPE(5912, 0x1611) +IS_OMAP_TYPE(1621, 0x1621) +IS_OMAP_TYPE(1710, 0x1710) + +#define cpu_is_omap310() 0 +#define cpu_is_omap1510() 0 +#define cpu_is_omap1610() 0 +#define cpu_is_omap5912() 0 +#define cpu_is_omap1611() 0 +#define cpu_is_omap1621() 0 +#define cpu_is_omap1710() 0 + +#define cpu_class_is_omap1() 1 + +/* + * Whether we have MULTI_OMAP1 or not, we still need to distinguish + * between 310 vs. 1510 and 1611B/5912 vs. 1710. + */ + +#if defined(CONFIG_ARCH_OMAP15XX) +# undef cpu_is_omap310 +# undef cpu_is_omap1510 +# define cpu_is_omap310() is_omap310() +# define cpu_is_omap1510() is_omap1510() +#endif + +#if defined(CONFIG_ARCH_OMAP16XX) +# undef cpu_is_omap1610 +# undef cpu_is_omap1611 +# undef cpu_is_omap5912 +# undef cpu_is_omap1621 +# undef cpu_is_omap1710 +# define cpu_is_omap1610() is_omap1610() +# define cpu_is_omap1611() is_omap1611() +# define cpu_is_omap5912() is_omap5912() +# define cpu_is_omap1621() is_omap1621() +# define cpu_is_omap1710() is_omap1710() +#endif + +#endif -- cgit v1.2.3 From 9fe15316563cbd46601c770a7214ccc5e1925bfb Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 6 Aug 2019 15:13:18 +0200 Subject: ARM: omap1: innovator: move ohci phy power handling to board file The innovator board needs a special case for its phy control. Move the corresponding code into the board file and out of the common code by adding another callback. Acked-by: Felipe Balbi Acked-by: Tony Lindgren Signed-off-by: Arnd Bergmann --- include/linux/platform_data/usb-omap1.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/platform_data/usb-omap1.h b/include/linux/platform_data/usb-omap1.h index 878e572a78bf..e7b8dc92a269 100644 --- a/include/linux/platform_data/usb-omap1.h +++ b/include/linux/platform_data/usb-omap1.h @@ -50,6 +50,8 @@ struct omap_usb_config { int (*ocpi_enable)(void); void (*lb_reset)(void); + + int (*transceiver_power)(int on); }; #endif /* __LINUX_USB_OMAP1_H */ -- cgit v1.2.3 From 17ea03b75e5665c9ce4945aa5afd097f3c845cdf Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 27 Nov 2020 15:46:47 +0100 Subject: ARM: omap: dma: make usb support optional Most of the plat-omap/dma.c code is specific to the USB driver. Hide that code when it is not in use, to make it clearer which parts are actually still required. Acked-by: Tony Lindgren Signed-off-by: Arnd Bergmann --- include/linux/omap-dma.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h index 5e228428fda1..07fa58ae9902 100644 --- a/include/linux/omap-dma.h +++ b/include/linux/omap-dma.h @@ -299,8 +299,9 @@ extern void omap_set_dma_priority(int lch, int dst_port, int priority); extern int omap_request_dma(int dev_id, const char *dev_name, void (*callback)(int lch, u16 ch_status, void *data), void *data, int *dma_ch); -extern void omap_disable_dma_irq(int ch, u16 irq_bits); extern void omap_free_dma(int ch); +#if IS_ENABLED(CONFIG_USB_OMAP) +extern void omap_disable_dma_irq(int ch, u16 irq_bits); extern void omap_start_dma(int lch); extern void omap_stop_dma(int lch); extern void omap_set_dma_transfer_params(int lch, int data_type, @@ -326,6 +327,8 @@ extern void omap_set_dma_dest_burst_mode(int lch, extern dma_addr_t omap_get_dma_src_pos(int lch); extern dma_addr_t omap_get_dma_dst_pos(int lch); extern int omap_get_dma_active_status(int lch); +#endif + extern int omap_dma_running(void); #if IS_ENABLED(CONFIG_FB_OMAP) -- cgit v1.2.3 From 3550bba25d5587a701e6edf20e20984d2ee72c78 Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Sat, 9 Apr 2022 11:51:28 +0200 Subject: gpiolib: of: Introduce hook for missing gpio-ranges Since commit 2ab73c6d8323 ("gpio: Support GPIO controllers without pin-ranges") the device tree nodes of GPIO controller need the gpio-ranges property to handle gpio-hogs. Unfortunately it's impossible to guarantee that every new kernel is shipped with an updated device tree binary. In order to provide backward compatibility with those older DTB, we need a callback within of_gpiochip_add_pin_range() so the relevant platform driver can handle this case. Fixes: 2ab73c6d8323 ("gpio: Support GPIO controllers without pin-ranges") Signed-off-by: Stefan Wahren Reviewed-by: Florian Fainelli Tested-by: Florian Fainelli Acked-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20220409095129.45786-2-stefan.wahren@i2se.com Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 98c93510640e..c2041bd01f90 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -492,6 +492,18 @@ struct gpio_chip { */ int (*of_xlate)(struct gpio_chip *gc, const struct of_phandle_args *gpiospec, u32 *flags); + + /** + * @of_gpio_ranges_fallback: + * + * Optional hook for the case that no gpio-ranges property is defined + * within the device tree node "np" (usually DT before introduction + * of gpio-ranges). So this callback is helpful to provide the + * necessary backward compatibility for the pin ranges. + */ + int (*of_gpio_ranges_fallback)(struct gpio_chip *gc, + struct device_node *np); + #endif /* CONFIG_OF_GPIO */ }; -- cgit v1.2.3 From 7e842d70fe599bc13594b650b2144c4b6e6d6bf1 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 20 Apr 2022 09:05:26 +0200 Subject: memory: renesas-rpc-if: Fix HF/OSPI data transfer in Manual Mode HyperFlash devices fail to probe: rpc-if-hyperflash rpc-if-hyperflash: probing of hyperbus device failed In HyperFlash or Octal-SPI Flash mode, the Transfer Data Enable bits (SPIDE) in the Manual Mode Enable Setting Register (SMENR) are derived from half of the transfer size, cfr. the rpcif_bits_set() helper function. However, rpcif_reg_{read,write}() does not take the bus size into account, and does not double all Manual Mode Data Register access sizes when communicating with a HyperFlash or Octal-SPI Flash device. Fix this, and avoid the back-and-forth conversion between transfer size and Transfer Data Enable bits, by explicitly storing the transfer size in struct rpcif, and using that value to determine access size in rpcif_reg_{read,write}(). Enforce that the "high" Manual Mode Read/Write Data Registers (SM[RW]DR1) are only used for 8-byte data accesses. While at it, forbid writing to the Manual Mode Read Data Registers, as they are read-only. Fixes: fff53a551db50f5e ("memory: renesas-rpc-if: Correct QSPI data transfer in Manual mode") Signed-off-by: Geert Uytterhoeven Signed-off-by: Krzysztof Kozlowski Tested-by: Lad Prabhakar Tested-by: Wolfram Sang Reviewed-by: Wolfram Sang Link: https://lore.kernel.org/r/cde9bfacf704c81865f57b15d1b48a4793da4286.1649681476.git.geert+renesas@glider.be Link: https://lore.kernel.org/r/20220420070526.9367-1-krzysztof.kozlowski@linaro.org' Signed-off-by: Arnd Bergmann --- include/memory/renesas-rpc-if.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/memory/renesas-rpc-if.h b/include/memory/renesas-rpc-if.h index 7c93f5177532..9c0ad64b8d29 100644 --- a/include/memory/renesas-rpc-if.h +++ b/include/memory/renesas-rpc-if.h @@ -72,6 +72,7 @@ struct rpcif { enum rpcif_type type; enum rpcif_data_dir dir; u8 bus_size; + u8 xfer_size; void *buffer; u32 xferlen; u32 smcr; -- cgit v1.2.3 From 8d084b2eae7fc5fcfc9f143cd7321a88e1cd76aa Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 5 Apr 2022 17:15:13 +0200 Subject: usb: typec: tcpm: Fix undefined behavior due to shift overflowing the constant MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix: drivers/usb/typec/tcpm/tcpm.c: In function ‘run_state_machine’: drivers/usb/typec/tcpm/tcpm.c:4724:3: error: case label does not reduce to an integer constant case BDO_MODE_TESTDATA: ^~~~ See https://lore.kernel.org/r/YkwQ6%2BtIH8GQpuct@zn.tnic for the gory details as to why it triggers with older gccs only. Signed-off-by: Borislav Petkov Cc: Greg Kroah-Hartman Cc: linux-usb@vger.kernel.org Link: https://lore.kernel.org/r/20220405151517.29753-8-bp@alien8.de Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/pd_bdo.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/usb/pd_bdo.h b/include/linux/usb/pd_bdo.h index 033fe3e17141..7c25b88d79f9 100644 --- a/include/linux/usb/pd_bdo.h +++ b/include/linux/usb/pd_bdo.h @@ -15,7 +15,7 @@ #define BDO_MODE_CARRIER2 (5 << 28) #define BDO_MODE_CARRIER3 (6 << 28) #define BDO_MODE_EYE (7 << 28) -#define BDO_MODE_TESTDATA (8 << 28) +#define BDO_MODE_TESTDATA (8U << 28) #define BDO_MODE_MASK(mode) ((mode) & 0xf0000000) -- cgit v1.2.3 From 2031f2876896d82aca7e82f84accd9181b9587fb Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 15 Apr 2022 00:43:43 +0000 Subject: KVM: Add helpers to wrap vcpu->srcu_idx and yell if it's abused Add wrappers to acquire/release KVM's SRCU lock when stashing the index in vcpu->src_idx, along with rudimentary detection of illegal usage, e.g. re-acquiring SRCU and thus overwriting vcpu->src_idx. Because the SRCU index is (currently) either 0 or 1, illegal nesting bugs can go unnoticed for quite some time and only cause problems when the nested lock happens to get a different index. Wrap the WARNs in PROVE_RCU=y, and make them ONCE, otherwise KVM will likely yell so loudly that it will bring the kernel to its knees. Signed-off-by: Sean Christopherson Tested-by: Fabiano Rosas Message-Id: <20220415004343.2203171-4-seanjc@google.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3f9b22c4983a..2dab4b696682 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -315,7 +315,10 @@ struct kvm_vcpu { int cpu; int vcpu_id; /* id given by userspace at creation */ int vcpu_idx; /* index in kvm->vcpus array */ - int srcu_idx; + int ____srcu_idx; /* Don't use this directly. You've been warned. */ +#ifdef CONFIG_PROVE_RCU + int srcu_depth; +#endif int mode; u64 requests; unsigned long guest_debug; @@ -840,6 +843,25 @@ static inline void kvm_vm_bugged(struct kvm *kvm) unlikely(__ret); \ }) +static inline void kvm_vcpu_srcu_read_lock(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_PROVE_RCU + WARN_ONCE(vcpu->srcu_depth++, + "KVM: Illegal vCPU srcu_idx LOCK, depth=%d", vcpu->srcu_depth - 1); +#endif + vcpu->____srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); +} + +static inline void kvm_vcpu_srcu_read_unlock(struct kvm_vcpu *vcpu) +{ + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->____srcu_idx); + +#ifdef CONFIG_PROVE_RCU + WARN_ONCE(--vcpu->srcu_depth, + "KVM: Illegal vCPU srcu_idx UNLOCK, depth=%d", vcpu->srcu_depth); +#endif +} + static inline bool kvm_dirty_log_manual_protect_and_init_set(struct kvm *kvm) { return !!(kvm->manual_dirty_log_protect & KVM_DIRTY_LOG_INITIALLY_SET); -- cgit v1.2.3 From 1e3dc1d8622b2699e6cf1cc06885105b13c9c514 Mon Sep 17 00:00:00 2001 From: Tomas Winkler Date: Tue, 19 Apr 2022 12:33:08 -0700 Subject: drm/i915/gsc: add gsc as a mei auxiliary device GSC is a graphics system controller, it provides a chassis controller for graphics discrete cards. There are two MEI interfaces in GSC: HECI1 and HECI2. Both interfaces are on the BAR0 at offsets 0x00258000 and 0x00259000. GSC is a GT Engine (class 4: instance 6). HECI1 interrupt is signaled via bit 15 and HECI2 via bit 14 in the interrupt register. This patch exports GSC as auxiliary device for mei driver to bind to for HECI2 interface and prepares for HECI1 interface as it will follow up soon. CC: Rodrigo Vivi Signed-off-by: Tomas Winkler Signed-off-by: Vitaly Lubart Signed-off-by: Alexander Usyskin Acked-by: Tvrtko Ursulin Reviewed-by: Daniele Ceraolo Spurio Signed-off-by: Daniele Ceraolo Spurio Link: https://patchwork.freedesktop.org/patch/msgid/20220419193314.526966-2-daniele.ceraolospurio@intel.com --- include/linux/mei_aux.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 include/linux/mei_aux.h (limited to 'include') diff --git a/include/linux/mei_aux.h b/include/linux/mei_aux.h new file mode 100644 index 000000000000..587f25128848 --- /dev/null +++ b/include/linux/mei_aux.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022, Intel Corporation. All rights reserved. + */ +#ifndef _LINUX_MEI_AUX_H +#define _LINUX_MEI_AUX_H + +#include + +struct mei_aux_device { + struct auxiliary_device aux_dev; + int irq; + struct resource bar; +}; + +#define auxiliary_dev_to_mei_aux_dev(auxiliary_dev) \ + container_of(auxiliary_dev, struct mei_aux_device, aux_dev) + +#endif /* _LINUX_MEI_AUX_H */ -- cgit v1.2.3 From 988f11e046401f8561c4afefa506a50f0203de40 Mon Sep 17 00:00:00 2001 From: liaohua Date: Thu, 7 Apr 2022 15:29:48 +0800 Subject: latencytop: move sysctl to its own file This moves latencytop sysctl to kernel/latencytop.c Signed-off-by: liaohua Signed-off-by: Luis Chamberlain --- include/linux/latencytop.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/latencytop.h b/include/linux/latencytop.h index abe3d95f795b..84f1053cf2a8 100644 --- a/include/linux/latencytop.h +++ b/include/linux/latencytop.h @@ -38,9 +38,6 @@ account_scheduler_latency(struct task_struct *task, int usecs, int inter) void clear_tsk_latency_tracing(struct task_struct *p); -int sysctl_latencytop(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos); - #else static inline void -- cgit v1.2.3 From 683412ccf61294d727ead4a73d97397396e69a6b Mon Sep 17 00:00:00 2001 From: Mingwei Zhang Date: Thu, 21 Apr 2022 03:14:07 +0000 Subject: KVM: SEV: add cache flush to solve SEV cache incoherency issues Flush the CPU caches when memory is reclaimed from an SEV guest (where reclaim also includes it being unmapped from KVM's memslots). Due to lack of coherency for SEV encrypted memory, failure to flush results in silent data corruption if userspace is malicious/broken and doesn't ensure SEV guest memory is properly pinned and unpinned. Cache coherency is not enforced across the VM boundary in SEV (AMD APM vol.2 Section 15.34.7). Confidential cachelines, generated by confidential VM guests have to be explicitly flushed on the host side. If a memory page containing dirty confidential cachelines was released by VM and reallocated to another user, the cachelines may corrupt the new user at a later time. KVM takes a shortcut by assuming all confidential memory remain pinned until the end of VM lifetime. Therefore, KVM does not flush cache at mmu_notifier invalidation events. Because of this incorrect assumption and the lack of cache flushing, malicous userspace can crash the host kernel: creating a malicious VM and continuously allocates/releases unpinned confidential memory pages when the VM is running. Add cache flush operations to mmu_notifier operations to ensure that any physical memory leaving the guest VM get flushed. In particular, hook mmu_notifier_invalidate_range_start and mmu_notifier_release events and flush cache accordingly. The hook after releasing the mmu lock to avoid contention with other vCPUs. Cc: stable@vger.kernel.org Suggested-by: Sean Christpherson Reported-by: Mingwei Zhang Signed-off-by: Mingwei Zhang Message-Id: <20220421031407.2516575-4-mizhang@google.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 2dab4b696682..34eed5f85ed6 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -2219,6 +2219,8 @@ static inline long kvm_arch_vcpu_async_ioctl(struct file *filp, void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, unsigned long start, unsigned long end); +void kvm_arch_guest_memory_reclaimed(struct kvm *kvm); + #ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu); #else -- cgit v1.2.3 From 651877176c0846616add00f50b719ea6d59dff8d Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Sat, 4 Sep 2021 10:06:03 -0700 Subject: drm/fourcc: Add QCOM tiled modifiers These are mainly used internally in mesa, although I believe the display should be able to scan out the TILED3 format. Currently we define this modifier internally in mesa for use with modifier based allocation. But we can get rid of that hack if we define the modfiers properly. Signed-off-by: Rob Clark Link: https://lore.kernel.org/r/20210904170603.1739137-1-robdclark@gmail.com Signed-off-by: Rob Clark --- include/uapi/drm/drm_fourcc.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index fc0c1454d275..4bdf8dded9e7 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -609,6 +609,28 @@ extern "C" { */ #define DRM_FORMAT_MOD_QCOM_COMPRESSED fourcc_mod_code(QCOM, 1) +/* + * Qualcomm Tiled Format + * + * Similar to DRM_FORMAT_MOD_QCOM_COMPRESSED but not compressed. + * Implementation may be platform and base-format specific. + * + * Each macrotile consists of m x n (mostly 4 x 4) tiles. + * Pixel data pitch/stride is aligned with macrotile width. + * Pixel data height is aligned with macrotile height. + * Entire pixel data buffer is aligned with 4k(bytes). + */ +#define DRM_FORMAT_MOD_QCOM_TILED3 fourcc_mod_code(QCOM, 3) + +/* + * Qualcomm Alternate Tiled Format + * + * Alternate tiled format typically only used within GMEM. + * Implementation may be platform and base-format specific. + */ +#define DRM_FORMAT_MOD_QCOM_TILED2 fourcc_mod_code(QCOM, 2) + + /* Vivante framebuffer modifiers */ /* -- cgit v1.2.3 From 4bfba71640f8578b3daadb551d6bce12a2d436d8 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Thu, 17 Mar 2022 09:51:38 -0700 Subject: drm/msm: Add support for pointer params The 64b value field is already suffient to hold a pointer instead of immediate, but we also need a length field. Signed-off-by: Rob Clark Link: https://lore.kernel.org/r/20220317165144.222101-2-robdclark@gmail.com Signed-off-by: Rob Clark --- include/uapi/drm/msm_drm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h index 07efc8033492..0aa1a8cb4e0d 100644 --- a/include/uapi/drm/msm_drm.h +++ b/include/uapi/drm/msm_drm.h @@ -95,6 +95,8 @@ struct drm_msm_param { __u32 pipe; /* in, MSM_PIPE_x */ __u32 param; /* in, MSM_PARAM_x */ __u64 value; /* out (get_param) or in (set_param) */ + __u32 len; /* zero for non-pointer params */ + __u32 pad; /* must be zero */ }; /* -- cgit v1.2.3 From d4726d7700688835f4784d3b94de6fff2cbe16c2 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Thu, 17 Mar 2022 09:51:40 -0700 Subject: drm/msm: Add a way to override processes comm/cmdline In the cause of using the GPU via virtgpu, the host side process is really a sort of proxy, and not terribly interesting from the PoV of crash/fault logging. Add a way to override these per process so that we can see the guest process's name. v2: Handle kmalloc failure, add comment to explain kstrdup returns NULL if passed NULL [Dan Carpenter] Signed-off-by: Rob Clark Link: https://lore.kernel.org/r/20220317165144.222101-4-robdclark@gmail.com Signed-off-by: Rob Clark --- include/uapi/drm/msm_drm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h index 0aa1a8cb4e0d..794ad1948497 100644 --- a/include/uapi/drm/msm_drm.h +++ b/include/uapi/drm/msm_drm.h @@ -82,6 +82,8 @@ struct drm_msm_timespec { #define MSM_PARAM_FAULTS 0x09 /* RO */ #define MSM_PARAM_SUSPENDS 0x0a /* RO */ #define MSM_PARAM_SYSPROF 0x0b /* WO: 1 preserves perfcntrs, 2 also disables suspend */ +#define MSM_PARAM_COMM 0x0c /* WO: override for task->comm */ +#define MSM_PARAM_CMDLINE 0x0d /* WO: override for task cmdline */ /* For backwards compat. The original support for preemption was based on * a single ring per priority level so # of priority levels equals the # -- cgit v1.2.3 From a636a0ff11483a4c158acc31ee7ca083d98a0d13 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Mon, 11 Apr 2022 14:58:39 -0700 Subject: drm/msm: Add a way for userspace to allocate GPU iova The motivation at this point is mainly native userspace mesa driver in a VM guest. The one remaining synchronous "hotpath" is buffer allocation, because guest needs to wait to know the bo's iova before it can start emitting cmdstream/state that references the new bo. By allocating the iova in the guest userspace, we no longer need to wait for a response from the host, but can just rely on the allocation request being processed before the cmdstream submission. Allocation failures (OoM, etc) would just be treated as context-lost (ie. GL_GUILTY_CONTEXT_RESET) or subsequent allocations (or readpix, etc) can raise GL_OUT_OF_MEMORY. v2: Fix inuse check v3: Change mismatched iova case to -EBUSY Signed-off-by: Rob Clark Reviewed-by: Dmitry Baryshkov Reviewed-by: Dmitry Osipenko Link: https://lore.kernel.org/r/20220411215849.297838-11-robdclark@gmail.com Signed-off-by: Rob Clark --- include/uapi/drm/msm_drm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h index 794ad1948497..3c7b097c4e3d 100644 --- a/include/uapi/drm/msm_drm.h +++ b/include/uapi/drm/msm_drm.h @@ -84,6 +84,8 @@ struct drm_msm_timespec { #define MSM_PARAM_SYSPROF 0x0b /* WO: 1 preserves perfcntrs, 2 also disables suspend */ #define MSM_PARAM_COMM 0x0c /* WO: override for task->comm */ #define MSM_PARAM_CMDLINE 0x0d /* WO: override for task cmdline */ +#define MSM_PARAM_VA_START 0x0e /* RO: start of valid GPU iova range */ +#define MSM_PARAM_VA_SIZE 0x0f /* RO: size of valid GPU iova range (bytes) */ /* For backwards compat. The original support for preemption was based on * a single ring per priority level so # of priority levels equals the # @@ -135,6 +137,7 @@ struct drm_msm_gem_new { #define MSM_INFO_GET_IOVA 0x01 /* get iova, returned by value */ #define MSM_INFO_SET_NAME 0x02 /* set the debug name (by pointer) */ #define MSM_INFO_GET_NAME 0x03 /* get debug name, returned by pointer */ +#define MSM_INFO_SET_IOVA 0x04 /* set the iova, passed by value */ struct drm_msm_gem_info { __u32 handle; /* in */ -- cgit v1.2.3 From 405ce051236cc65b30bbfe490b28ce60ae6aed85 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Thu, 21 Apr 2022 16:35:33 -0700 Subject: mm/hwpoison: fix race between hugetlb free/demotion and memory_failure_hugetlb() There is a race condition between memory_failure_hugetlb() and hugetlb free/demotion, which causes setting PageHWPoison flag on the wrong page. The one simple result is that wrong processes can be killed, but another (more serious) one is that the actual error is left unhandled, so no one prevents later access to it, and that might lead to more serious results like consuming corrupted data. Think about the below race window: CPU 1 CPU 2 memory_failure_hugetlb struct page *head = compound_head(p); hugetlb page might be freed to buddy, or even changed to another compound page. get_hwpoison_page -- page is not what we want now... The current code first does prechecks roughly and then reconfirms after taking refcount, but it's found that it makes code overly complicated, so move the prechecks in a single hugetlb_lock range. A newly introduced function, try_memory_failure_hugetlb(), always takes hugetlb_lock (even for non-hugetlb pages). That can be improved, but memory_failure() is rare in principle, so should not be a big problem. Link: https://lkml.kernel.org/r/20220408135323.1559401-2-naoya.horiguchi@linux.dev Fixes: 761ad8d7c7b5 ("mm: hwpoison: introduce memory_failure_hugetlb()") Signed-off-by: Naoya Horiguchi Reported-by: Mike Kravetz Reviewed-by: Miaohe Lin Reviewed-by: Mike Kravetz Cc: Yang Shi Cc: Dan Carpenter Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 6 ++++++ include/linux/mm.h | 8 ++++++++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 53c1b6082a4c..ac2a1d758a80 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -169,6 +169,7 @@ long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); bool isolate_huge_page(struct page *page, struct list_head *list); int get_hwpoison_huge_page(struct page *page, bool *hugetlb); +int get_huge_page_for_hwpoison(unsigned long pfn, int flags); void putback_active_hugepage(struct page *page); void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason); void free_huge_page(struct page *page); @@ -378,6 +379,11 @@ static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb) return 0; } +static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags) +{ + return 0; +} + static inline void putback_active_hugepage(struct page *page) { } diff --git a/include/linux/mm.h b/include/linux/mm.h index e34edb775334..9f44254af8ce 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3197,6 +3197,14 @@ extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); +#ifdef CONFIG_MEMORY_FAILURE +extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags); +#else +static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags) +{ + return 0; +} +#endif #ifndef arch_memory_failure static inline int arch_memory_failure(unsigned long pfn, int flags) -- cgit v1.2.3 From 9b3016154c913b2e7ec5ae5c9a42eb9e732d86aa Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Thu, 21 Apr 2022 16:35:40 -0700 Subject: memcg: sync flush only if periodic flush is delayed MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Daniel Dao has reported [1] a regression on workloads that may trigger a lot of refaults (anon and file). The underlying issue is that flushing rstat is expensive. Although rstat flush are batched with (nr_cpus * MEMCG_BATCH) stat updates, it seems like there are workloads which genuinely do stat updates larger than batch value within short amount of time. Since the rstat flush can happen in the performance critical codepaths like page faults, such workload can suffer greatly. This patch fixes this regression by making the rstat flushing conditional in the performance critical codepaths. More specifically, the kernel relies on the async periodic rstat flusher to flush the stats and only if the periodic flusher is delayed by more than twice the amount of its normal time window then the kernel allows rstat flushing from the performance critical codepaths. Now the question: what are the side-effects of this change? The worst that can happen is the refault codepath will see 4sec old lruvec stats and may cause false (or missed) activations of the refaulted page which may under-or-overestimate the workingset size. Though that is not very concerning as the kernel can already miss or do false activations. There are two more codepaths whose flushing behavior is not changed by this patch and we may need to come to them in future. One is the writeback stats used by dirty throttling and second is the deactivation heuristic in the reclaim. For now keeping an eye on them and if there is report of regression due to these codepaths, we will reevaluate then. Link: https://lore.kernel.org/all/CA+wXwBSyO87ZX5PVwdHm-=dBjZYECGmfnydUicUyrQqndgX2MQ@mail.gmail.com [1] Link: https://lkml.kernel.org/r/20220304184040.1304781-1-shakeelb@google.com Fixes: 1f828223b799 ("memcg: flush lruvec stats in the refault") Signed-off-by: Shakeel Butt Reported-by: Daniel Dao Tested-by: Ivan Babrou Cc: Michal Hocko Cc: Roman Gushchin Cc: Johannes Weiner Cc: Michal Koutný Cc: Frank Hofmann Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index a68dce3873fc..89b14729d59f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1012,6 +1012,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, } void mem_cgroup_flush_stats(void); +void mem_cgroup_flush_stats_delayed(void); void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); @@ -1455,6 +1456,10 @@ static inline void mem_cgroup_flush_stats(void) { } +static inline void mem_cgroup_flush_stats_delayed(void) +{ +} + static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { -- cgit v1.2.3 From 5f24d5a579d1eace79d505b148808a850b417d4c Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 21 Apr 2022 16:35:46 -0700 Subject: mm, hugetlb: allow for "high" userspace addresses This is a fix for commit f6795053dac8 ("mm: mmap: Allow for "high" userspace addresses") for hugetlb. This patch adds support for "high" userspace addresses that are optionally supported on the system and have to be requested via a hint mechanism ("high" addr parameter to mmap). Architectures such as powerpc and x86 achieve this by making changes to their architectural versions of hugetlb_get_unmapped_area() function. However, arm64 uses the generic version of that function. So take into account arch_get_mmap_base() and arch_get_mmap_end() in hugetlb_get_unmapped_area(). To allow that, move those two macros out of mm/mmap.c into include/linux/sched/mm.h If these macros are not defined in architectural code then they default to (TASK_SIZE) and (base) so should not introduce any behavioural changes to architectures that do not define them. For the time being, only ARM64 is affected by this change. Catalin (ARM64) said "We should have fixed hugetlb_get_unmapped_area() as well when we added support for 52-bit VA. The reason for commit f6795053dac8 was to prevent normal mmap() from returning addresses above 48-bit by default as some user-space had hard assumptions about this. It's a slight ABI change if you do this for hugetlb_get_unmapped_area() but I doubt anyone would notice. It's more likely that the current behaviour would cause issues, so I'd rather have them consistent. Basically when arm64 gained support for 52-bit addresses we did not want user-space calling mmap() to suddenly get such high addresses, otherwise we could have inadvertently broken some programs (similar behaviour to x86 here). Hence we added commit f6795053dac8. But we missed hugetlbfs which could still get such high mmap() addresses. So in theory that's a potential regression that should have bee addressed at the same time as commit f6795053dac8 (and before arm64 enabled 52-bit addresses)" Link: https://lkml.kernel.org/r/ab847b6edb197bffdfe189e70fb4ac76bfe79e0d.1650033747.git.christophe.leroy@csgroup.eu Fixes: f6795053dac8 ("mm: mmap: Allow for "high" userspace addresses") Signed-off-by: Christophe Leroy Reviewed-by: Catalin Marinas Cc: Steve Capper Cc: Will Deacon Cc: [5.0.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/mm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index a80356e9dc69..1ad1f4bfa025 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -136,6 +136,14 @@ static inline void mm_update_next_owner(struct mm_struct *mm) #endif /* CONFIG_MEMCG */ #ifdef CONFIG_MMU +#ifndef arch_get_mmap_end +#define arch_get_mmap_end(addr) (TASK_SIZE) +#endif + +#ifndef arch_get_mmap_base +#define arch_get_mmap_base(addr, base) (base) +#endif + extern void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack); extern unsigned long -- cgit v1.2.3 From e4a38402c36e42df28eb1a5394be87e6571fb48a Mon Sep 17 00:00:00 2001 From: Nico Pache Date: Thu, 21 Apr 2022 16:36:01 -0700 Subject: oom_kill.c: futex: delay the OOM reaper to allow time for proper futex cleanup The pthread struct is allocated on PRIVATE|ANONYMOUS memory [1] which can be targeted by the oom reaper. This mapping is used to store the futex robust list head; the kernel does not keep a copy of the robust list and instead references a userspace address to maintain the robustness during a process death. A race can occur between exit_mm and the oom reaper that allows the oom reaper to free the memory of the futex robust list before the exit path has handled the futex death: CPU1 CPU2 -------------------------------------------------------------------- page_fault do_exit "signal" wake_oom_reaper oom_reaper oom_reap_task_mm (invalidates mm) exit_mm exit_mm_release futex_exit_release futex_cleanup exit_robust_list get_user (EFAULT- can't access memory) If the get_user EFAULT's, the kernel will be unable to recover the waiters on the robust_list, leaving userspace mutexes hung indefinitely. Delay the OOM reaper, allowing more time for the exit path to perform the futex cleanup. Reproducer: https://gitlab.com/jsavitz/oom_futex_reproducer Based on a patch by Michal Hocko. Link: https://elixir.bootlin.com/glibc/glibc-2.35/source/nptl/allocatestack.c#L370 [1] Link: https://lkml.kernel.org/r/20220414144042.677008-1-npache@redhat.com Fixes: 212925802454 ("mm: oom: let oom_reap_task and exit_mmap run concurrently") Signed-off-by: Joel Savitz Signed-off-by: Nico Pache Co-developed-by: Joel Savitz Suggested-by: Thomas Gleixner Acked-by: Thomas Gleixner Acked-by: Michal Hocko Cc: Rafael Aquini Cc: Waiman Long Cc: Herton R. Krzesinski Cc: Juri Lelli Cc: Vincent Guittot Cc: Dietmar Eggemann Cc: Steven Rostedt Cc: Ben Segall Cc: Mel Gorman Cc: Daniel Bristot de Oliveira Cc: David Rientjes Cc: Andrea Arcangeli Cc: Davidlohr Bueso Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Joel Savitz Cc: Darren Hart Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index d5e3c00b74e1..a8911b1f35aa 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1443,6 +1443,7 @@ struct task_struct { int pagefault_disabled; #ifdef CONFIG_MMU struct task_struct *oom_reaper_list; + struct timer_list oom_reaper_timer; #endif #ifdef CONFIG_VMAP_STACK struct vm_struct *stack_vm_area; -- cgit v1.2.3 From ea3364db9068e37bd8e12b9a99c7c92385593ed7 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Fri, 8 Apr 2022 14:48:34 -0700 Subject: dt-bindings: interconnect: qcom: Add sc8280xp binding The Qualcomm SC8280XP platform has the usual set of busses, add a binding for these interconnect providers and port definitions to allow interconnect paths to be expressed in the sc8280xp DeviceTree. Reviewed-by: Krzysztof Kozlowski Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220408214835.624494-1-bjorn.andersson@linaro.org Signed-off-by: Georgi Djakov --- include/dt-bindings/interconnect/qcom,sc8280xp.h | 232 +++++++++++++++++++++++ 1 file changed, 232 insertions(+) create mode 100644 include/dt-bindings/interconnect/qcom,sc8280xp.h (limited to 'include') diff --git a/include/dt-bindings/interconnect/qcom,sc8280xp.h b/include/dt-bindings/interconnect/qcom,sc8280xp.h new file mode 100644 index 000000000000..a3e5fda7c127 --- /dev/null +++ b/include/dt-bindings/interconnect/qcom,sc8280xp.h @@ -0,0 +1,232 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2021, The Linux Foundation. All rights reserved. + * Copyright (c) 2022, Linaro Ltd. + */ + +#ifndef __DT_BINDINGS_INTERCONNECT_QCOM_SC8280XP_H +#define __DT_BINDINGS_INTERCONNECT_QCOM_SC8280XP_H + +/* aggre1_noc */ +#define MASTER_QSPI_0 0 +#define MASTER_QUP_1 1 +#define MASTER_QUP_2 2 +#define MASTER_A1NOC_CFG 3 +#define MASTER_IPA 4 +#define MASTER_EMAC_1 5 +#define MASTER_SDCC_4 6 +#define MASTER_UFS_MEM 7 +#define MASTER_USB3_0 8 +#define MASTER_USB3_1 9 +#define MASTER_USB3_MP 10 +#define MASTER_USB4_0 11 +#define MASTER_USB4_1 12 +#define SLAVE_A1NOC_SNOC 13 +#define SLAVE_USB_NOC_SNOC 14 +#define SLAVE_SERVICE_A1NOC 15 + +/* aggre2_noc */ +#define MASTER_QDSS_BAM 0 +#define MASTER_QUP_0 1 +#define MASTER_A2NOC_CFG 2 +#define MASTER_CRYPTO 3 +#define MASTER_SENSORS_PROC 4 +#define MASTER_SP 5 +#define MASTER_EMAC 6 +#define MASTER_PCIE_0 7 +#define MASTER_PCIE_1 8 +#define MASTER_PCIE_2A 9 +#define MASTER_PCIE_2B 10 +#define MASTER_PCIE_3A 11 +#define MASTER_PCIE_3B 12 +#define MASTER_PCIE_4 13 +#define MASTER_QDSS_ETR 14 +#define MASTER_SDCC_2 15 +#define MASTER_UFS_CARD 16 +#define SLAVE_A2NOC_SNOC 17 +#define SLAVE_ANOC_PCIE_GEM_NOC 18 +#define SLAVE_SERVICE_A2NOC 19 + +/* clk_virt */ +#define MASTER_IPA_CORE 0 +#define MASTER_QUP_CORE_0 1 +#define MASTER_QUP_CORE_1 2 +#define MASTER_QUP_CORE_2 3 +#define SLAVE_IPA_CORE 4 +#define SLAVE_QUP_CORE_0 5 +#define SLAVE_QUP_CORE_1 6 +#define SLAVE_QUP_CORE_2 7 + +/* config_noc */ +#define MASTER_GEM_NOC_CNOC 0 +#define MASTER_GEM_NOC_PCIE_SNOC 1 +#define SLAVE_AHB2PHY_0 2 +#define SLAVE_AHB2PHY_1 3 +#define SLAVE_AHB2PHY_2 4 +#define SLAVE_AOSS 5 +#define SLAVE_APPSS 6 +#define SLAVE_CAMERA_CFG 7 +#define SLAVE_CLK_CTL 8 +#define SLAVE_CDSP_CFG 9 +#define SLAVE_CDSP1_CFG 10 +#define SLAVE_RBCPR_CX_CFG 11 +#define SLAVE_RBCPR_MMCX_CFG 12 +#define SLAVE_RBCPR_MX_CFG 13 +#define SLAVE_CPR_NSPCX 14 +#define SLAVE_CRYPTO_0_CFG 15 +#define SLAVE_CX_RDPM 16 +#define SLAVE_DCC_CFG 17 +#define SLAVE_DISPLAY_CFG 18 +#define SLAVE_DISPLAY1_CFG 19 +#define SLAVE_EMAC_CFG 20 +#define SLAVE_EMAC1_CFG 21 +#define SLAVE_GFX3D_CFG 22 +#define SLAVE_HWKM 23 +#define SLAVE_IMEM_CFG 24 +#define SLAVE_IPA_CFG 25 +#define SLAVE_IPC_ROUTER_CFG 26 +#define SLAVE_LPASS 27 +#define SLAVE_MX_RDPM 28 +#define SLAVE_MXC_RDPM 29 +#define SLAVE_PCIE_0_CFG 30 +#define SLAVE_PCIE_1_CFG 31 +#define SLAVE_PCIE_2A_CFG 32 +#define SLAVE_PCIE_2B_CFG 33 +#define SLAVE_PCIE_3A_CFG 34 +#define SLAVE_PCIE_3B_CFG 35 +#define SLAVE_PCIE_4_CFG 36 +#define SLAVE_PCIE_RSC_CFG 37 +#define SLAVE_PDM 38 +#define SLAVE_PIMEM_CFG 39 +#define SLAVE_PKA_WRAPPER_CFG 40 +#define SLAVE_PMU_WRAPPER_CFG 41 +#define SLAVE_QDSS_CFG 42 +#define SLAVE_QSPI_0 43 +#define SLAVE_QUP_0 44 +#define SLAVE_QUP_1 45 +#define SLAVE_QUP_2 46 +#define SLAVE_SDCC_2 47 +#define SLAVE_SDCC_4 48 +#define SLAVE_SECURITY 49 +#define SLAVE_SMMUV3_CFG 50 +#define SLAVE_SMSS_CFG 51 +#define SLAVE_SPSS_CFG 52 +#define SLAVE_TCSR 53 +#define SLAVE_TLMM 54 +#define SLAVE_UFS_CARD_CFG 55 +#define SLAVE_UFS_MEM_CFG 56 +#define SLAVE_USB3_0 57 +#define SLAVE_USB3_1 58 +#define SLAVE_USB3_MP 59 +#define SLAVE_USB4_0 60 +#define SLAVE_USB4_1 61 +#define SLAVE_VENUS_CFG 62 +#define SLAVE_VSENSE_CTRL_CFG 63 +#define SLAVE_VSENSE_CTRL_R_CFG 64 +#define SLAVE_A1NOC_CFG 65 +#define SLAVE_A2NOC_CFG 66 +#define SLAVE_ANOC_PCIE_BRIDGE_CFG 67 +#define SLAVE_DDRSS_CFG 68 +#define SLAVE_CNOC_MNOC_CFG 69 +#define SLAVE_SNOC_CFG 70 +#define SLAVE_SNOC_SF_BRIDGE_CFG 71 +#define SLAVE_IMEM 72 +#define SLAVE_PIMEM 73 +#define SLAVE_SERVICE_CNOC 74 +#define SLAVE_PCIE_0 75 +#define SLAVE_PCIE_1 76 +#define SLAVE_PCIE_2A 77 +#define SLAVE_PCIE_2B 78 +#define SLAVE_PCIE_3A 79 +#define SLAVE_PCIE_3B 80 +#define SLAVE_PCIE_4 81 +#define SLAVE_QDSS_STM 82 +#define SLAVE_SMSS 83 +#define SLAVE_TCU 84 + +/* dc_noc */ +#define MASTER_CNOC_DC_NOC 0 +#define SLAVE_LLCC_CFG 1 +#define SLAVE_GEM_NOC_CFG 2 + +/* gem_noc */ +#define MASTER_GPU_TCU 0 +#define MASTER_PCIE_TCU 1 +#define MASTER_SYS_TCU 2 +#define MASTER_APPSS_PROC 3 +#define MASTER_COMPUTE_NOC 4 +#define MASTER_COMPUTE_NOC_1 5 +#define MASTER_GEM_NOC_CFG 6 +#define MASTER_GFX3D 7 +#define MASTER_MNOC_HF_MEM_NOC 8 +#define MASTER_MNOC_SF_MEM_NOC 9 +#define MASTER_ANOC_PCIE_GEM_NOC 10 +#define MASTER_SNOC_GC_MEM_NOC 11 +#define MASTER_SNOC_SF_MEM_NOC 12 +#define SLAVE_GEM_NOC_CNOC 13 +#define SLAVE_LLCC 14 +#define SLAVE_GEM_NOC_PCIE_CNOC 15 +#define SLAVE_SERVICE_GEM_NOC_1 16 +#define SLAVE_SERVICE_GEM_NOC_2 17 +#define SLAVE_SERVICE_GEM_NOC 18 + +/* lpass_ag_noc */ +#define MASTER_CNOC_LPASS_AG_NOC 0 +#define MASTER_LPASS_PROC 1 +#define SLAVE_LPASS_CORE_CFG 2 +#define SLAVE_LPASS_LPI_CFG 3 +#define SLAVE_LPASS_MPU_CFG 4 +#define SLAVE_LPASS_TOP_CFG 5 +#define SLAVE_LPASS_SNOC 6 +#define SLAVE_SERVICES_LPASS_AML_NOC 7 +#define SLAVE_SERVICE_LPASS_AG_NOC 8 + +/* mc_virt */ +#define MASTER_LLCC 0 +#define SLAVE_EBI1 1 + +/*mmss_noc */ +#define MASTER_CAMNOC_HF 0 +#define MASTER_MDP0 1 +#define MASTER_MDP1 2 +#define MASTER_MDP_CORE1_0 3 +#define MASTER_MDP_CORE1_1 4 +#define MASTER_CNOC_MNOC_CFG 5 +#define MASTER_ROTATOR 6 +#define MASTER_ROTATOR_1 7 +#define MASTER_VIDEO_P0 8 +#define MASTER_VIDEO_P1 9 +#define MASTER_VIDEO_PROC 10 +#define MASTER_CAMNOC_ICP 11 +#define MASTER_CAMNOC_SF 12 +#define SLAVE_MNOC_HF_MEM_NOC 13 +#define SLAVE_MNOC_SF_MEM_NOC 14 +#define SLAVE_SERVICE_MNOC 15 + +/* nspa_noc */ +#define MASTER_CDSP_NOC_CFG 0 +#define MASTER_CDSP_PROC 1 +#define SLAVE_CDSP_MEM_NOC 2 +#define SLAVE_NSP_XFR 3 +#define SLAVE_SERVICE_NSP_NOC 4 + +/* nspb_noc */ +#define MASTER_CDSPB_NOC_CFG 0 +#define MASTER_CDSP_PROC_B 1 +#define SLAVE_CDSPB_MEM_NOC 2 +#define SLAVE_NSPB_XFR 3 +#define SLAVE_SERVICE_NSPB_NOC 4 + +/* system_noc */ +#define MASTER_A1NOC_SNOC 0 +#define MASTER_A2NOC_SNOC 1 +#define MASTER_USB_NOC_SNOC 2 +#define MASTER_LPASS_ANOC 3 +#define MASTER_SNOC_CFG 4 +#define MASTER_PIMEM 5 +#define MASTER_GIC 6 +#define SLAVE_SNOC_GEM_NOC_GC 7 +#define SLAVE_SNOC_GEM_NOC_SF 8 +#define SLAVE_SERVICE_SNOC 9 + +#endif -- cgit v1.2.3 From 52ef8efcb75e8a8aab88e74c1376c2785d9a5452 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 2 Apr 2022 00:28:23 +0200 Subject: dma: omap: hide legacy interface The legacy interface for omap-dma is only used on OMAP1, and the same is true for the non-DT case. Make both of these conditional on CONFIG_ARCH_OMAP1 being set to simplify the dependency. The non-OMAP stub functions in include/linux/omap-dma.h are note needed any more either now, because they are only called on OMAP1. Acked-by: Tony Lindgren Acked-By: Vinod Koul Signed-off-by: Arnd Bergmann --- include/linux/omap-dma.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include') diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h index 07fa58ae9902..254b4e10511b 100644 --- a/include/linux/omap-dma.h +++ b/include/linux/omap-dma.h @@ -292,7 +292,6 @@ struct omap_system_dma_plat_info { #define dma_omap15xx() __dma_omap15xx(d) #define dma_omap16xx() __dma_omap16xx(d) -#if defined(CONFIG_ARCH_OMAP) extern struct omap_system_dma_plat_info *omap_get_plat_info(void); extern void omap_set_dma_priority(int lch, int dst_port, int priority); @@ -340,25 +339,4 @@ static inline int omap_lcd_dma_running(void) } #endif -#else /* CONFIG_ARCH_OMAP */ -static inline void omap_set_dma_priority(int lch, int dst_port, int priority) -{ -} - -static inline struct omap_system_dma_plat_info *omap_get_plat_info(void) -{ - return NULL; -} - -static inline int omap_request_dma(int dev_id, const char *dev_name, - void (*callback)(int lch, u16 ch_status, void *data), - void *data, int *dma_ch) -{ - return -ENODEV; -} - -static inline void omap_free_dma(int ch) { } - -#endif /* CONFIG_ARCH_OMAP */ - #endif /* __LINUX_OMAP_DMA_H */ -- cgit v1.2.3 From 615dce5bf7369334f8c4f19f7f8f2a5634b4f911 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 12 Sep 2019 10:11:24 +0200 Subject: ARM: omap1: fix build with no SoC selected In a multiplatform randconfig kernel, one can have CONFIG_ARCH_OMAP1 enabled, but none of the specific SoCs. This leads to some build issues as the code is not meant to deal with this configuration at the moment: arch/arm/mach-omap1/io.c:86:20: error: unused function 'omap1_map_common_io' [-Werror,-Wunused-function] arch/arm/mach-omap1/pm.h:113:2: error: "Power management for this processor not implemented yet" [-Werror,-W#warnings] Use the same trick as on OMAP2 and guard the actual compilation of platform code with another Makefile ifdef check based on an option that depends on having at least one SoC enabled. The io.c file still needs to get compiled to allow building device drivers with a dependency on CONFIG_ARCH_OMAP1. Acked-by: Tony Lindgren Signed-off-by: Arnd Bergmann --- include/linux/soc/ti/omap1-io.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/soc/ti/omap1-io.h b/include/linux/soc/ti/omap1-io.h index 9332c92690f4..f7f12728d4a6 100644 --- a/include/linux/soc/ti/omap1-io.h +++ b/include/linux/soc/ti/omap1-io.h @@ -5,7 +5,7 @@ #ifndef __ASSEMBLER__ #include -#if defined(CONFIG_ARCH_OMAP) && defined(CONFIG_ARCH_OMAP1) +#ifdef CONFIG_ARCH_OMAP1_ANY /* * NOTE: Please use ioremap + __raw_read/write where possible instead of these */ @@ -15,7 +15,7 @@ extern u32 omap_readl(u32 pa); extern void omap_writeb(u8 v, u32 pa); extern void omap_writew(u16 v, u32 pa); extern void omap_writel(u32 v, u32 pa); -#elif defined(CONFIG_COMPILE_TEST) +#else static inline u8 omap_readb(u32 pa) { return 0; } static inline u16 omap_readw(u32 pa) { return 0; } static inline u32 omap_readl(u32 pa) { return 0; } -- cgit v1.2.3 From 78ed93d72ded679e3caf0758357209887bda885f Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Mon, 4 Apr 2022 13:12:04 +0200 Subject: signal: Deliver SIGTRAP on perf event asynchronously if blocked With SIGTRAP on perf events, we have encountered termination of processes due to user space attempting to block delivery of SIGTRAP. Consider this case: ... sigset_t s; sigemptyset(&s); sigaddset(&s, SIGTRAP | ); sigprocmask(SIG_BLOCK, &s, ...); ... When the perf event triggers, while SIGTRAP is blocked, force_sig_perf() will force the signal, but revert back to the default handler, thus terminating the task. This makes sense for error conditions, but not so much for explicitly requested monitoring. However, the expectation is still that signals generated by perf events are synchronous, which will no longer be the case if the signal is blocked and delivered later. To give user space the ability to clearly distinguish synchronous from asynchronous signals, introduce siginfo_t::si_perf_flags and TRAP_PERF_FLAG_ASYNC (opted for flags in case more binary information is required in future). The resolution to the problem is then to (a) no longer force the signal (avoiding the terminations), but (b) tell user space via si_perf_flags if the signal was synchronous or not, so that such signals can be handled differently (e.g. let user space decide to ignore or consider the data imprecise). The alternative of making the kernel ignore SIGTRAP on perf events if the signal is blocked may work for some usecases, but likely causes issues in others that then have to revert back to interception of sigprocmask() (which we want to avoid). [ A concrete example: when using breakpoint perf events to track data-flow, in a region of code where signals are blocked, data-flow can no longer be tracked accurately. When a relevant asynchronous signal is received after unblocking the signal, the data-flow tracking logic needs to know its state is imprecise. ] Fixes: 97ba62b27867 ("perf: Add support for SIGTRAP on perf events") Reported-by: Dmitry Vyukov Signed-off-by: Marco Elver Signed-off-by: Peter Zijlstra (Intel) Acked-by: Geert Uytterhoeven Tested-by: Dmitry Vyukov Link: https://lore.kernel.org/r/20220404111204.935357-1-elver@google.com --- include/linux/compat.h | 1 + include/linux/sched/signal.h | 2 +- include/uapi/asm-generic/siginfo.h | 7 +++++++ 3 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/compat.h b/include/linux/compat.h index 1c758b0e0359..01fddf72a81f 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -235,6 +235,7 @@ typedef struct compat_siginfo { struct { compat_ulong_t _data; u32 _type; + u32 _flags; } _perf; }; } _sigfault; diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 3c8b34876744..bab7cc56b13a 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -320,7 +320,7 @@ int send_sig_mceerr(int code, void __user *, short, struct task_struct *); int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper); int force_sig_pkuerr(void __user *addr, u32 pkey); -int force_sig_perf(void __user *addr, u32 type, u64 sig_data); +int send_sig_perf(void __user *addr, u32 type, u64 sig_data); int force_sig_ptrace_errno_trap(int errno, void __user *addr); int force_sig_fault_trapno(int sig, int code, void __user *addr, int trapno); diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h index 3ba180f550d7..ffbe4cec9f32 100644 --- a/include/uapi/asm-generic/siginfo.h +++ b/include/uapi/asm-generic/siginfo.h @@ -99,6 +99,7 @@ union __sifields { struct { unsigned long _data; __u32 _type; + __u32 _flags; } _perf; }; } _sigfault; @@ -164,6 +165,7 @@ typedef struct siginfo { #define si_pkey _sifields._sigfault._addr_pkey._pkey #define si_perf_data _sifields._sigfault._perf._data #define si_perf_type _sifields._sigfault._perf._type +#define si_perf_flags _sifields._sigfault._perf._flags #define si_band _sifields._sigpoll._band #define si_fd _sifields._sigpoll._fd #define si_call_addr _sifields._sigsys._call_addr @@ -270,6 +272,11 @@ typedef struct siginfo { * that are of the form: ((PTRACE_EVENT_XXX << 8) | SIGTRAP) */ +/* + * Flags for si_perf_flags if SIGTRAP si_code is TRAP_PERF. + */ +#define TRAP_PERF_FLAG_ASYNC (1u << 0) + /* * SIGCHLD si_codes */ -- cgit v1.2.3 From 03f16cd020eb8bb2eb837e2090086f296a9fa91d Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 18 Apr 2022 09:50:36 -0700 Subject: objtool: Add CONFIG_OBJTOOL Now that stack validation is an optional feature of objtool, add CONFIG_OBJTOOL and replace most usages of CONFIG_STACK_VALIDATION with it. CONFIG_STACK_VALIDATION can now be considered to be frame-pointer specific. CONFIG_UNWINDER_ORC is already inherently valid for live patching, so no need to "validate" it. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Miroslav Benes Link: https://lkml.kernel.org/r/939bf3d85604b2a126412bf11af6e3bd3b872bcb.1650300597.git.jpoimboe@redhat.com --- include/linux/compiler.h | 6 +++--- include/linux/instrumentation.h | 6 +++--- include/linux/objtool.h | 6 +++--- 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 219aa5ddbc73..01ce94b58b42 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -109,7 +109,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #endif /* Unreachable code */ -#ifdef CONFIG_STACK_VALIDATION +#ifdef CONFIG_OBJTOOL /* * These macros help objtool understand GCC code flow for unreachable code. * The __COUNTER__ based labels are a hack to make each instance of the macros @@ -128,10 +128,10 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, /* Annotate a C jump table to allow objtool to follow the code flow */ #define __annotate_jump_table __section(".rodata..c_jump_table") -#else +#else /* !CONFIG_OBJTOOL */ #define annotate_unreachable() #define __annotate_jump_table -#endif +#endif /* CONFIG_OBJTOOL */ #ifndef unreachable # define unreachable() do { \ diff --git a/include/linux/instrumentation.h b/include/linux/instrumentation.h index 24359b4a9605..9111a3704072 100644 --- a/include/linux/instrumentation.h +++ b/include/linux/instrumentation.h @@ -2,7 +2,7 @@ #ifndef __LINUX_INSTRUMENTATION_H #define __LINUX_INSTRUMENTATION_H -#if defined(CONFIG_DEBUG_ENTRY) && defined(CONFIG_STACK_VALIDATION) +#ifdef CONFIG_VMLINUX_VALIDATION #include @@ -53,9 +53,9 @@ ".popsection\n\t" : : "i" (c)); \ }) #define instrumentation_end() __instrumentation_end(__COUNTER__) -#else +#else /* !CONFIG_VMLINUX_VALIDATION */ # define instrumentation_begin() do { } while(0) # define instrumentation_end() do { } while(0) -#endif +#endif /* CONFIG_VMLINUX_VALIDATION */ #endif /* __LINUX_INSTRUMENTATION_H */ diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 586d35720f13..977d90ba642d 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -38,7 +38,7 @@ struct unwind_hint { #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 #define UNWIND_HINT_TYPE_FUNC 3 -#ifdef CONFIG_STACK_VALIDATION +#ifdef CONFIG_OBJTOOL #ifndef __ASSEMBLY__ @@ -157,7 +157,7 @@ struct unwind_hint { #endif /* __ASSEMBLY__ */ -#else /* !CONFIG_STACK_VALIDATION */ +#else /* !CONFIG_OBJTOOL */ #ifndef __ASSEMBLY__ @@ -179,6 +179,6 @@ struct unwind_hint { .endm #endif -#endif /* CONFIG_STACK_VALIDATION */ +#endif /* CONFIG_OBJTOOL */ #endif /* _LINUX_OBJTOOL_H */ -- cgit v1.2.3 From 0f620cefd7753175b6258fed85f76c2014ec3799 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 18 Apr 2022 09:50:41 -0700 Subject: objtool: Rename "VMLINUX_VALIDATION" -> "NOINSTR_VALIDATION" CONFIG_VMLINUX_VALIDATION is just the validation of the "noinstr" rules. That name is a misnomer, because now objtool actually does vmlinux validation for other reasons. Rename CONFIG_VMLINUX_VALIDATION to CONFIG_NOINSTR_VALIDATION. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Miroslav Benes Link: https://lkml.kernel.org/r/173f07e2d6d1afc0874aed975a61783207c6a531.1650300597.git.jpoimboe@redhat.com --- include/linux/instrumentation.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/instrumentation.h b/include/linux/instrumentation.h index 9111a3704072..bc7babe91b2e 100644 --- a/include/linux/instrumentation.h +++ b/include/linux/instrumentation.h @@ -2,7 +2,7 @@ #ifndef __LINUX_INSTRUMENTATION_H #define __LINUX_INSTRUMENTATION_H -#ifdef CONFIG_VMLINUX_VALIDATION +#ifdef CONFIG_NOINSTR_VALIDATION #include @@ -53,9 +53,9 @@ ".popsection\n\t" : : "i" (c)); \ }) #define instrumentation_end() __instrumentation_end(__COUNTER__) -#else /* !CONFIG_VMLINUX_VALIDATION */ +#else /* !CONFIG_NOINSTR_VALIDATION */ # define instrumentation_begin() do { } while(0) # define instrumentation_end() do { } while(0) -#endif /* CONFIG_VMLINUX_VALIDATION */ +#endif /* CONFIG_NOINSTR_VALIDATION */ #endif /* __LINUX_INSTRUMENTATION_H */ -- cgit v1.2.3 From 89e9c7280075f6733b22dd0740daeddeb1256ebf Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 20 Apr 2022 10:58:50 +0900 Subject: ipv6: Remove __ipv6_only_sock(). Since commit 9fe516ba3fb2 ("inet: move ipv6only in sock_common"), ipv6_only_sock() and __ipv6_only_sock() are the same macro. Let's remove the one. Signed-off-by: Kuniyuki Iwashima Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/ipv6.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 918bfea4ef5f..ec5ca392eaa3 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -340,8 +340,7 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk) return (struct raw6_sock *)sk; } -#define __ipv6_only_sock(sk) (sk->sk_ipv6only) -#define ipv6_only_sock(sk) (__ipv6_only_sock(sk)) +#define ipv6_only_sock(sk) (sk->sk_ipv6only) #define ipv6_sk_rxinfo(sk) ((sk)->sk_family == PF_INET6 && \ inet6_sk(sk)->rxopt.bits.rxinfo) @@ -358,7 +357,6 @@ static inline int inet_v6_ipv6only(const struct sock *sk) return ipv6_only_sock(sk); } #else -#define __ipv6_only_sock(sk) 0 #define ipv6_only_sock(sk) 0 #define ipv6_sk_rxinfo(sk) 0 -- cgit v1.2.3 From 67e1e2f4854bb2c0dd2b8440cf090016a0e1a091 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Thu, 21 Apr 2022 01:21:33 +0200 Subject: ipv4: Avoid using RTO_ONLINK with ip_route_connect(). Now that ip_rt_fix_tos() doesn't reset ->flowi4_scope unconditionally, we don't have to rely on the RTO_ONLINK bit to properly set the scope of a flowi4 structure. We can just set ->flowi4_scope explicitly and avoid using RTO_ONLINK in ->flowi4_tos. This patch converts callers of ip_route_connect(). Instead of setting the tos parameter with RT_CONN_FLAGS(sk), as all callers do, we can: 1- Drop the tos parameter from ip_route_connect(): its value was entirely based on sk, which is also passed as parameter. 2- Set ->flowi4_scope depending on the SOCK_LOCALROUTE socket option instead of always initialising it with RT_SCOPE_UNIVERSE (let's define ip_sock_rt_scope() for this purpose). 3- Avoid overloading ->flowi4_tos with RTO_ONLINK: since the scope is now properly initialised, we don't need to tell ip_rt_fix_tos() to adjust ->flowi4_scope for us. So let's define ip_sock_rt_tos(), which is the same as RT_CONN_FLAGS() but without the RTO_ONLINK bit overload. Note: In the original ip_route_connect() code, __ip_route_output_key() might clear the RTO_ONLINK bit of fl4->flowi4_tos (because of ip_rt_fix_tos()). Therefore flowi4_update_output() had to reuse the original tos variable. Now that we don't set RTO_ONLINK any more, this is not a problem and we can use fl4->flowi4_tos in flowi4_update_output(). Signed-off-by: Guillaume Nault Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/route.h | 36 ++++++++++++++++++++++++------------ 1 file changed, 24 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/net/route.h b/include/net/route.h index 25404fc2b483..991a3985712d 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -43,6 +43,19 @@ #define RT_CONN_FLAGS(sk) (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE)) #define RT_CONN_FLAGS_TOS(sk,tos) (RT_TOS(tos) | sock_flag(sk, SOCK_LOCALROUTE)) +static inline __u8 ip_sock_rt_scope(const struct sock *sk) +{ + if (sock_flag(sk, SOCK_LOCALROUTE)) + return RT_SCOPE_LINK; + + return RT_SCOPE_UNIVERSE; +} + +static inline __u8 ip_sock_rt_tos(const struct sock *sk) +{ + return RT_TOS(inet_sk(sk)->tos); +} + struct ip_tunnel_info; struct fib_nh; struct fib_info; @@ -289,39 +302,38 @@ static inline char rt_tos2priority(u8 tos) * ip_route_newports() calls. */ -static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32 src, - u32 tos, int oif, u8 protocol, +static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, + __be32 src, int oif, u8 protocol, __be16 sport, __be16 dport, - struct sock *sk) + const struct sock *sk) { __u8 flow_flags = 0; if (inet_sk(sk)->transparent) flow_flags |= FLOWI_FLAG_ANYSRC; - flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, - protocol, flow_flags, dst, src, dport, sport, - sk->sk_uid); + flowi4_init_output(fl4, oif, sk->sk_mark, ip_sock_rt_tos(sk), + ip_sock_rt_scope(sk), protocol, flow_flags, dst, + src, dport, sport, sk->sk_uid); } -static inline struct rtable *ip_route_connect(struct flowi4 *fl4, - __be32 dst, __be32 src, u32 tos, - int oif, u8 protocol, +static inline struct rtable *ip_route_connect(struct flowi4 *fl4, __be32 dst, + __be32 src, int oif, u8 protocol, __be16 sport, __be16 dport, struct sock *sk) { struct net *net = sock_net(sk); struct rtable *rt; - ip_route_connect_init(fl4, dst, src, tos, oif, protocol, - sport, dport, sk); + ip_route_connect_init(fl4, dst, src, oif, protocol, sport, dport, sk); if (!dst || !src) { rt = __ip_route_output_key(net, fl4); if (IS_ERR(rt)) return rt; ip_rt_put(rt); - flowi4_update_output(fl4, oif, tos, fl4->daddr, fl4->saddr); + flowi4_update_output(fl4, oif, fl4->flowi4_tos, fl4->daddr, + fl4->saddr); } security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); return ip_route_output_flow(net, fl4, sk); -- cgit v1.2.3 From b804923b7ccb9c9629703364e927b48cd02a9254 Mon Sep 17 00:00:00 2001 From: "jason-jh.lin" Date: Tue, 19 Apr 2022 17:41:36 +0800 Subject: soc: mediatek: add mtk-mmsys support for mt8195 vdosys0 1. Add mt8195 mmsys compatible for 2 vdosys. 2. Add io_start into each driver data of mt8195 vdosys. 3. Add get match data function to identify mmsys by io_start. 4. Add mt8195 routing table settings of vdosys0. Signed-off-by: jason-jh.lin Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: Rex-BC Chen Reviewed-by: CK Hu Link: https://lore.kernel.org/r/20220419094143.9561-2-jason-jh.lin@mediatek.com Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/mtk-mmsys.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/soc/mediatek/mtk-mmsys.h b/include/linux/soc/mediatek/mtk-mmsys.h index 4bba275e235a..cff5c9adbf46 100644 --- a/include/linux/soc/mediatek/mtk-mmsys.h +++ b/include/linux/soc/mediatek/mtk-mmsys.h @@ -17,13 +17,24 @@ enum mtk_ddp_comp_id { DDP_COMPONENT_COLOR0, DDP_COMPONENT_COLOR1, DDP_COMPONENT_DITHER, + DDP_COMPONENT_DITHER1, + DDP_COMPONENT_DP_INTF0, + DDP_COMPONENT_DP_INTF1, DDP_COMPONENT_DPI0, DDP_COMPONENT_DPI1, + DDP_COMPONENT_DSC0, + DDP_COMPONENT_DSC1, DDP_COMPONENT_DSI0, DDP_COMPONENT_DSI1, DDP_COMPONENT_DSI2, DDP_COMPONENT_DSI3, DDP_COMPONENT_GAMMA, + DDP_COMPONENT_MERGE0, + DDP_COMPONENT_MERGE1, + DDP_COMPONENT_MERGE2, + DDP_COMPONENT_MERGE3, + DDP_COMPONENT_MERGE4, + DDP_COMPONENT_MERGE5, DDP_COMPONENT_OD0, DDP_COMPONENT_OD1, DDP_COMPONENT_OVL0, -- cgit v1.2.3 From 4e8988c634a1159e803bfdc0118578ded97e012c Mon Sep 17 00:00:00 2001 From: "jason-jh.lin" Date: Tue, 19 Apr 2022 17:41:41 +0800 Subject: soc: mediatek: add DDP_DOMPONENT_DITHER0 enum for mt8195 vdosys0 The mmsys routing table of mt8195 vdosys0 has 2 DITHER components, so mmsys need to add DDP_COMPONENT_DITHER1 and change all usages of DITHER enum form DDP_COMPONENT_DITHER to DDP_COMPONENT_DITHER0. But its header need to keep DDP_COMPONENT_DITHER enum until drm/mediatek also changed it. Signed-off-by: jason-jh.lin Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: Rex-BC Chen Link: https://lore.kernel.org/r/20220419094143.9561-7-jason-jh.lin@mediatek.com Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/mtk-mmsys.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/soc/mediatek/mtk-mmsys.h b/include/linux/soc/mediatek/mtk-mmsys.h index cff5c9adbf46..59117d970daf 100644 --- a/include/linux/soc/mediatek/mtk-mmsys.h +++ b/include/linux/soc/mediatek/mtk-mmsys.h @@ -17,6 +17,7 @@ enum mtk_ddp_comp_id { DDP_COMPONENT_COLOR0, DDP_COMPONENT_COLOR1, DDP_COMPONENT_DITHER, + DDP_COMPONENT_DITHER0 = DDP_COMPONENT_DITHER, DDP_COMPONENT_DITHER1, DDP_COMPONENT_DP_INTF0, DDP_COMPONENT_DP_INTF1, -- cgit v1.2.3 From bd40cbb0e3b37a4d2a2d9e2ac40122cdf619b1f3 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 19 Apr 2022 19:29:16 +0200 Subject: PM: domains: Move genpd's time-accounting to ktime_get_mono_fast_ns() To move towards a more consistent behaviour between genpd and the runtime PM core, let's start by converting genpd's time-accounting from ktime_get() into ktime_get_mono_fast_ns(). Signed-off-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 67017c9390c8..043d48e4420a 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -98,7 +98,7 @@ struct genpd_power_state { u64 usage; u64 rejected; struct fwnode_handle *fwnode; - ktime_t idle_time; + u64 idle_time; void *data; }; @@ -149,8 +149,8 @@ struct generic_pm_domain { unsigned int state_count); unsigned int state_count; /* number of states */ unsigned int state_idx; /* state that genpd will go to when off */ - ktime_t on_time; - ktime_t accounting_time; + u64 on_time; + u64 accounting_time; const struct genpd_lock_ops *lock_ops; union { struct mutex mlock; -- cgit v1.2.3 From 6c2f421174273de8f83cde4286d1c076d43a2d35 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 19 Apr 2022 13:34:24 +0200 Subject: driver: platform: Add helper for safer setting of driver_override Several core drivers and buses expect that driver_override is a dynamically allocated memory thus later they can kfree() it. However such assumption is not documented, there were in the past and there are already users setting it to a string literal. This leads to kfree() of static memory during device release (e.g. in error paths or during unbind): kernel BUG at ../mm/slub.c:3960! Internal error: Oops - BUG: 0 [#1] PREEMPT SMP ARM ... (kfree) from [] (platform_device_release+0x88/0xb4) (platform_device_release) from [] (device_release+0x2c/0x90) (device_release) from [] (kobject_put+0xec/0x20c) (kobject_put) from [] (exynos5_clk_probe+0x154/0x18c) (exynos5_clk_probe) from [] (platform_drv_probe+0x6c/0xa4) (platform_drv_probe) from [] (really_probe+0x280/0x414) (really_probe) from [] (driver_probe_device+0x78/0x1c4) (driver_probe_device) from [] (bus_for_each_drv+0x74/0xb8) (bus_for_each_drv) from [] (__device_attach+0xd4/0x16c) (__device_attach) from [] (bus_probe_device+0x88/0x90) (bus_probe_device) from [] (device_add+0x3dc/0x62c) (device_add) from [] (of_platform_device_create_pdata+0x94/0xbc) (of_platform_device_create_pdata) from [] (of_platform_bus_create+0x1a8/0x4fc) (of_platform_bus_create) from [] (of_platform_bus_create+0x20c/0x4fc) (of_platform_bus_create) from [] (of_platform_populate+0x84/0x118) (of_platform_populate) from [] (of_platform_default_populate_init+0xa0/0xb8) (of_platform_default_populate_init) from [] (do_one_initcall+0x8c/0x404) Provide a helper which clearly documents the usage of driver_override. This will allow later to reuse the helper and reduce the amount of duplicated code. Convert the platform driver to use a new helper and make the driver_override field const char (it is not modified by the core). Reviewed-by: Rafael J. Wysocki Acked-by: Rafael J. Wysocki Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220419113435.246203-2-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/driver.h | 2 ++ include/linux/platform_device.h | 6 +++++- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index 15e7c5e15d62..700453017e1c 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -151,6 +151,8 @@ extern int __must_check driver_create_file(struct device_driver *driver, extern void driver_remove_file(struct device_driver *driver, const struct driver_attribute *attr); +int driver_set_override(struct device *dev, const char **override, + const char *s, size_t len); extern int __must_check driver_for_each_device(struct device_driver *drv, struct device *start, void *data, diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 7c96f169d274..582d83ed9a91 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -31,7 +31,11 @@ struct platform_device { struct resource *resource; const struct platform_device_id *id_entry; - char *driver_override; /* Driver name to force a match */ + /* + * Driver name to force a match. Do not set directly, because core + * frees it. Use driver_set_override() to set or clear it. + */ + const char *driver_override; /* MFD cell pointer */ struct mfd_cell *mfd_cell; -- cgit v1.2.3 From 6e67955087e72f1a5f64dd8014c27e1d9317fbb4 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 19 Apr 2022 13:34:25 +0200 Subject: amba: Use driver_set_override() instead of open-coding Use a helper to set driver_override to reduce the amount of duplicated code. Make the driver_override field const char, because it is not modified by the core and it matches other subsystems. Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220419113435.246203-3-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/amba/bus.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 6562f543c3e0..93799a72ff82 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -70,7 +70,11 @@ struct amba_device { unsigned int cid; struct amba_cs_uci_id uci; unsigned int irq[AMBA_NR_IRQS]; - char *driver_override; + /* + * Driver name to force a match. Do not set directly, because core + * frees it. Use driver_set_override() to set or clear it. + */ + const char *driver_override; }; struct amba_driver { -- cgit v1.2.3 From 5688f212e98a2469583a067fa5da4312ddc4e357 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 19 Apr 2022 13:34:26 +0200 Subject: fsl-mc: Use driver_set_override() instead of open-coding Use a helper to set driver_override to reduce the amount of duplicated code. Make the driver_override field const char, because it is not modified by the core and it matches other subsystems. Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220419113435.246203-4-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/fsl/mc.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index 7b6c42bfb660..7a87ab9eba99 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -170,7 +170,9 @@ struct fsl_mc_obj_desc { * @regions: pointer to array of MMIO region entries * @irqs: pointer to array of pointers to interrupts allocated to this device * @resource: generic resource associated with this MC object device, if any. - * @driver_override: driver name to force a match + * @driver_override: driver name to force a match; do not set directly, + * because core frees it; use driver_set_override() to + * set or clear it. * * Generic device object for MC object devices that are "attached" to a * MC bus. @@ -204,7 +206,7 @@ struct fsl_mc_device { struct fsl_mc_device_irq **irqs; struct fsl_mc_resource *resource; struct device_link *consumer_link; - char *driver_override; + const char *driver_override; }; #define to_fsl_mc_device(_dev) \ -- cgit v1.2.3 From 01ed100276bdac259f1b418b998904a7486b0b68 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 19 Apr 2022 13:34:27 +0200 Subject: hv: Use driver_set_override() instead of open-coding Use a helper to set driver_override to the reduce amount of duplicated code. Make the driver_override field const char, because it is not modified by the core and it matches other subsystems. Reviewed-by: Michael Kelley Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220419113435.246203-5-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index fe2e0179ed51..12e2336b23b7 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1257,7 +1257,11 @@ struct hv_device { u16 device_id; struct device device; - char *driver_override; /* Driver name to force a match */ + /* + * Driver name to force a match. Do not set directly, because core + * frees it. Use driver_set_override() to set or clear it. + */ + const char *driver_override; struct vmbus_channel *channel; struct kset *channels_kset; -- cgit v1.2.3 From 23d99baf9d729ca30b2fb6798a7b403a37bfb800 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 19 Apr 2022 13:34:28 +0200 Subject: PCI: Use driver_set_override() instead of open-coding Use a helper to set driver_override to the reduce amount of duplicated code. Make the driver_override field const char, because it is not modified by the core and it matches other subsystems. Reviewed-by: Andy Shevchenko Acked-by: Bjorn Helgaas Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220419113435.246203-6-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/pci.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 60adf42460ab..844d38f589cf 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -516,7 +516,11 @@ struct pci_dev { u16 acs_cap; /* ACS Capability offset */ phys_addr_t rom; /* Physical address if not from BAR */ size_t romlen; /* Length if not from BAR */ - char *driver_override; /* Driver name to force a match */ + /* + * Driver name to force a match. Do not set directly, because core + * frees it. Use driver_set_override() to set or clear it. + */ + const char *driver_override; unsigned long priv_flags; /* Private flags for the PCI driver */ -- cgit v1.2.3 From 19368f0f23e80929691dd5b1354832c0e0494419 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 19 Apr 2022 13:34:30 +0200 Subject: spi: Use helper for safer setting of driver_override Use a helper to set driver_override to the reduce amount of duplicated code. Reviewed-by: Mark Brown Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220419113435.246203-8-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/spi/spi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 5f8c063ddff4..f0177f9b6e13 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -138,6 +138,8 @@ extern int spi_delay_exec(struct spi_delay *_delay, struct spi_transfer *xfer); * for driver coldplugging, and in uevents used for hotplugging * @driver_override: If the name of a driver is written to this attribute, then * the device will bind to the named driver and only the named driver. + * Do not set directly, because core frees it; use driver_set_override() to + * set or clear it. * @cs_gpiod: gpio descriptor of the chipselect line (optional, NULL when * not using a GPIO line) * @word_delay: delay to be inserted between consecutive -- cgit v1.2.3 From 240bf4e665741241983580812a2be1b033f120ee Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 19 Apr 2022 13:34:31 +0200 Subject: vdpa: Use helper for safer setting of driver_override Use a helper to set driver_override to the reduce amount of duplicated code. Acked-by: Michael S. Tsirkin Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220419113435.246203-9-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/vdpa.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 8943a209202e..c0a5083632ab 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -64,7 +64,9 @@ struct vdpa_mgmt_dev; * struct vdpa_device - representation of a vDPA device * @dev: underlying device * @dma_dev: the actual device that is performing DMA - * @driver_override: driver name to force a match + * @driver_override: driver name to force a match; do not set directly, + * because core frees it; use driver_set_override() to + * set or clear it. * @config: the configuration ops for this device. * @cf_mutex: Protects get and set access to configuration layout. * @index: device index -- cgit v1.2.3 From 42cd402b8fd4672b692400fe5f9eecd55d2794ac Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 19 Apr 2022 13:34:35 +0200 Subject: rpmsg: Fix kfree() of static memory on setting driver_override The driver_override field from platform driver should not be initialized from static memory (string literal) because the core later kfree() it, for example when driver_override is set via sysfs. Use dedicated helper to set driver_override properly. Fixes: 950a7388f02b ("rpmsg: Turn name service into a stand alone driver") Fixes: c0cdc19f84a4 ("rpmsg: Driver for user space endpoint interface") Reviewed-by: Bjorn Andersson Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220419113435.246203-13-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/rpmsg.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/rpmsg.h b/include/linux/rpmsg.h index 02fa9116cd60..20c8cd1cde21 100644 --- a/include/linux/rpmsg.h +++ b/include/linux/rpmsg.h @@ -41,7 +41,9 @@ struct rpmsg_channel_info { * rpmsg_device - device that belong to the rpmsg bus * @dev: the device struct * @id: device id (used to match between rpmsg drivers and devices) - * @driver_override: driver name to force a match + * @driver_override: driver name to force a match; do not set directly, + * because core frees it; use driver_set_override() to + * set or clear it. * @src: local address * @dst: destination address * @ept: the rpmsg endpoint of this channel @@ -51,7 +53,7 @@ struct rpmsg_channel_info { struct rpmsg_device { struct device dev; struct rpmsg_device_id id; - char *driver_override; + const char *driver_override; u32 src; u32 dst; struct rpmsg_endpoint *ept; -- cgit v1.2.3 From f918cfc08c1755b9e54cd6effc923fa809045cf4 Mon Sep 17 00:00:00 2001 From: Ronak Jain Date: Wed, 6 Apr 2022 03:55:23 -0700 Subject: firmware: xilinx: add support for IOCTL and QUERY ID feature check Add support to check if IOCTL ID or QUERY ID is supported in firmware or not. Signed-off-by: Ronak Jain Link: https://lore.kernel.org/r/1649242526-17493-2-git-send-email-ronak.jain@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-zynqmp.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 14f00a7672d1..1ec73d5352c3 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -29,6 +29,11 @@ /* SMC SIP service Call Function Identifier Prefix */ #define PM_SIP_SVC 0xC2000000 + +/* PM API versions */ +#define PM_API_VERSION_2 2 + +/* ATF only commands */ #define PM_GET_TRUSTZONE_VERSION 0xa03 #define PM_SET_SUSPEND_MODE 0xa02 #define GET_CALLBACK_DATA 0xa01 @@ -460,6 +465,7 @@ int zynqmp_pm_load_pdi(const u32 src, const u64 address); int zynqmp_pm_register_notifier(const u32 node, const u32 event, const u32 wake, const u32 enable); int zynqmp_pm_feature(const u32 api_id); +int zynqmp_pm_is_function_supported(const u32 api_id, const u32 id); int zynqmp_pm_set_feature_config(enum pm_feature_config_id id, u32 value); int zynqmp_pm_get_feature_config(enum pm_feature_config_id id, u32 *payload); #else @@ -678,6 +684,11 @@ static inline int zynqmp_pm_pinctrl_get_function(const u32 pin, u32 *id) return -ENODEV; } +static inline int zynqmp_pm_is_function_supported(const u32 api_id, const u32 id) +{ + return -ENODEV; +} + static inline int zynqmp_pm_pinctrl_set_function(const u32 pin, const u32 id) { return -ENODEV; -- cgit v1.2.3 From 10fa1b2cdc899ab471000968af56215bf3c90d8e Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 22 Apr 2022 17:13:48 +0200 Subject: ACPI: bus: Avoid non-ACPI device objects in walks over children When walking the children of an ACPI device, take extra care to avoid using to_acpi_device() on the ones that are not ACPI devices, because that may lead to out-of-bounds access and memory corruption. While at it, make the function passed to acpi_dev_for_each_child() take a struct acpi_device pointer argument (instead of a struct device one), so it is more straightforward to use. Fixes: b7dd6298db81 ("ACPI: PM: Introduce acpi_dev_power_up_children_with_adr()") Reported-by: kernel test robot BugLink: https://lore.kernel.org/lkml/20220420064725.GB16310@xsang-OptiPlex-9020/ Signed-off-by: Rafael J. Wysocki Reviewed-by: Mika Westerberg --- include/acpi/acpi_bus.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index b44aaffedb91..772590e2eddb 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -482,7 +482,7 @@ extern struct bus_type acpi_bus_type; int acpi_bus_for_each_dev(int (*fn)(struct device *, void *), void *data); int acpi_dev_for_each_child(struct acpi_device *adev, - int (*fn)(struct device *, void *), void *data); + int (*fn)(struct acpi_device *, void *), void *data); /* * Events -- cgit v1.2.3 From bc1ce713a0843ba14a1e00d5275ad42a8873a5ce Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Thu, 3 Mar 2022 17:35:43 -0500 Subject: pwm: Add support for Xilinx AXI Timer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This adds PWM support for Xilinx LogiCORE IP AXI soft timers commonly found on Xilinx FPGAs. At the moment clock control is very basic: we just enable the clock during probe and pin the frequency. In the future, someone could add support for disabling the clock when not in use. Some common code has been specially demarcated. While currently only used by the PWM driver, it is anticipated that it may be split off in the future to be used by the timer driver as well. This driver was written with reference to Xilinx DS764 for v1.03.a [1]. [1] https://www.xilinx.com/support/documentation/ip_documentation/axi_timer/v1_03_a/axi_timer_ds764.pdf Signed-off-by: Sean Anderson Acked-by: Michal Simek Reviewed-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- include/clocksource/timer-xilinx.h | 73 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 73 insertions(+) create mode 100644 include/clocksource/timer-xilinx.h (limited to 'include') diff --git a/include/clocksource/timer-xilinx.h b/include/clocksource/timer-xilinx.h new file mode 100644 index 000000000000..c0f56fe6d22a --- /dev/null +++ b/include/clocksource/timer-xilinx.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2021 Sean Anderson + */ + +#ifndef XILINX_TIMER_H +#define XILINX_TIMER_H + +#include + +#define TCSR0 0x00 +#define TLR0 0x04 +#define TCR0 0x08 +#define TCSR1 0x10 +#define TLR1 0x14 +#define TCR1 0x18 + +#define TCSR_MDT BIT(0) +#define TCSR_UDT BIT(1) +#define TCSR_GENT BIT(2) +#define TCSR_CAPT BIT(3) +#define TCSR_ARHT BIT(4) +#define TCSR_LOAD BIT(5) +#define TCSR_ENIT BIT(6) +#define TCSR_ENT BIT(7) +#define TCSR_TINT BIT(8) +#define TCSR_PWMA BIT(9) +#define TCSR_ENALL BIT(10) +#define TCSR_CASC BIT(11) + +struct clk; +struct device_node; +struct regmap; + +/** + * struct xilinx_timer_priv - Private data for Xilinx AXI timer drivers + * @map: Regmap of the device, possibly with an offset + * @clk: Parent clock + * @max: Maximum value of the counters + */ +struct xilinx_timer_priv { + struct regmap *map; + struct clk *clk; + u32 max; +}; + +/** + * xilinx_timer_tlr_cycles() - Calculate the TLR for a period specified + * in clock cycles + * @priv: The timer's private data + * @tcsr: The value of the TCSR register for this counter + * @cycles: The number of cycles in this period + * + * Callers of this function MUST ensure that @cycles is representable as + * a TLR. + * + * Return: The calculated value for TLR + */ +u32 xilinx_timer_tlr_cycles(struct xilinx_timer_priv *priv, u32 tcsr, + u64 cycles); + +/** + * xilinx_timer_get_period() - Get the current period of a counter + * @priv: The timer's private data + * @tlr: The value of TLR for this counter + * @tcsr: The value of TCSR for this counter + * + * Return: The period, in ns + */ +unsigned int xilinx_timer_get_period(struct xilinx_timer_priv *priv, + u32 tlr, u32 tcsr); + +#endif /* XILINX_TIMER_H */ -- cgit v1.2.3 From 9e4ab6c89109472082616f8d2f6ada7deaffe161 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 19 Apr 2022 12:22:19 +0100 Subject: arm64/sme: Implement vector length configuration prctl()s As for SVE provide a prctl() interface which allows processes to configure their SME vector length. Signed-off-by: Mark Brown Reviewed-by: Catalin Marinas Link: https://lore.kernel.org/r/20220419112247.711548-12-broonie@kernel.org Signed-off-by: Catalin Marinas --- include/uapi/linux/prctl.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index e998764f0262..a5e06dcbba13 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -272,6 +272,15 @@ struct prctl_mm_map { # define PR_SCHED_CORE_SCOPE_THREAD_GROUP 1 # define PR_SCHED_CORE_SCOPE_PROCESS_GROUP 2 +/* arm64 Scalable Matrix Extension controls */ +/* Flag values must be in sync with SVE versions */ +#define PR_SME_SET_VL 63 /* set task vector length */ +# define PR_SME_SET_VL_ONEXEC (1 << 18) /* defer effect until exec */ +#define PR_SME_GET_VL 64 /* get task vector length */ +/* Bits common to PR_SME_SET_VL and PR_SME_GET_VL */ +# define PR_SME_VL_LEN_MASK 0xffff +# define PR_SME_VL_INHERIT (1 << 17) /* inherit across exec */ + #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0 -- cgit v1.2.3 From e12310a0d30f260b26297bc8d7c95769489af038 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 19 Apr 2022 12:22:28 +0100 Subject: arm64/sme: Implement ptrace support for streaming mode SVE registers The streaming mode SVE registers are represented using the same data structures as for SVE but since the vector lengths supported and in use may not be the same as SVE we represent them with a new type NT_ARM_SSVE. Unfortunately we only have a single 16 bit reserved field available in the header so there is no space to fit the current and maximum vector length for both standard and streaming SVE mode without redefining the structure in a way the creates a complicatd and fragile ABI. Since FFR is not present in streaming mode it is read and written as zero. Setting NT_ARM_SSVE registers will put the task into streaming mode, similarly setting NT_ARM_SVE registers will exit it. Reads that do not correspond to the current mode of the task will return the header with no register data. For compatibility reasons on write setting no flag for the register type will be interpreted as setting SVE registers, though users can provide no register data as an alternative mechanism for doing so. Signed-off-by: Mark Brown Reviewed-by: Catalin Marinas Link: https://lore.kernel.org/r/20220419112247.711548-21-broonie@kernel.org Signed-off-by: Catalin Marinas --- include/uapi/linux/elf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 787c657bfae8..a8dc688e1826 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -431,6 +431,7 @@ typedef struct elf64_shdr { #define NT_ARM_PACG_KEYS 0x408 /* ARM pointer authentication generic key */ #define NT_ARM_TAGGED_ADDR_CTRL 0x409 /* arm64 tagged address control (prctl()) */ #define NT_ARM_PAC_ENABLED_KEYS 0x40a /* arm64 ptr auth enabled keys (prctl()) */ +#define NT_ARM_SSVE 0x40b /* ARM Streaming SVE registers */ #define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ #define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ -- cgit v1.2.3 From 776b4a1cf36411e96972455ca72906b722b80ea1 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 19 Apr 2022 12:22:29 +0100 Subject: arm64/sme: Add ptrace support for ZA The ZA array can be read and written with the NT_ARM_ZA. Similarly to our interface for the SVE vector registers the regset consists of a header with information on the current vector length followed by an optional register data payload, represented as for signals as a series of horizontal vectors from 0 to VL/8 in the endianness independent format used for vectors. On get if ZA is enabled then register data will be provided, otherwise it will be omitted. On set if register data is provided then ZA is enabled and initialized using the provided data, otherwise it is disabled. Signed-off-by: Mark Brown Reviewed-by: Catalin Marinas Link: https://lore.kernel.org/r/20220419112247.711548-22-broonie@kernel.org Signed-off-by: Catalin Marinas --- include/uapi/linux/elf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index a8dc688e1826..97808f958903 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -432,6 +432,7 @@ typedef struct elf64_shdr { #define NT_ARM_TAGGED_ADDR_CTRL 0x409 /* arm64 tagged address control (prctl()) */ #define NT_ARM_PAC_ENABLED_KEYS 0x40a /* arm64 ptr auth enabled keys (prctl()) */ #define NT_ARM_SSVE 0x40b /* ARM Streaming SVE registers */ +#define NT_ARM_ZA 0x40c /* ARM SME ZA registers */ #define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ #define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ -- cgit v1.2.3 From faebd693c59387b7b765fab64b543855e15a91b4 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Thu, 21 Apr 2022 23:28:36 +0206 Subject: printk: rename cpulock functions Since the printk cpulock is CPU-reentrant and since it is used in all contexts, its usage must be carefully considered and most likely will require programming locklessly. To avoid mistaking the printk cpulock as a typical lock, rename it to cpu_sync. The main functions then become: printk_cpu_sync_get_irqsave(flags); printk_cpu_sync_put_irqrestore(flags); Add extra notes of caution in the function description to help developers understand the requirements for correct usage. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220421212250.565456-2-john.ogness@linutronix.de --- include/linux/printk.h | 54 ++++++++++++++++++++++++++++++-------------------- 1 file changed, 33 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index 1522df223c0f..859323a52985 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -277,43 +277,55 @@ static inline void printk_trigger_flush(void) #endif #ifdef CONFIG_SMP -extern int __printk_cpu_trylock(void); -extern void __printk_wait_on_cpu_lock(void); -extern void __printk_cpu_unlock(void); +extern int __printk_cpu_sync_try_get(void); +extern void __printk_cpu_sync_wait(void); +extern void __printk_cpu_sync_put(void); /** - * printk_cpu_lock_irqsave() - Acquire the printk cpu-reentrant spinning - * lock and disable interrupts. + * printk_cpu_sync_get_irqsave() - Acquire the printk cpu-reentrant spinning + * lock and disable interrupts. * @flags: Stack-allocated storage for saving local interrupt state, - * to be passed to printk_cpu_unlock_irqrestore(). + * to be passed to printk_cpu_sync_put_irqrestore(). * * If the lock is owned by another CPU, spin until it becomes available. * Interrupts are restored while spinning. + * + * CAUTION: This function must be used carefully. It does not behave like a + * typical lock. Here are important things to watch out for... + * + * * This function is reentrant on the same CPU. Therefore the calling + * code must not assume exclusive access to data if code accessing the + * data can run reentrant or within NMI context on the same CPU. + * + * * If there exists usage of this function from NMI context, it becomes + * unsafe to perform any type of locking or spinning to wait for other + * CPUs after calling this function from any context. This includes + * using spinlocks or any other busy-waiting synchronization methods. */ -#define printk_cpu_lock_irqsave(flags) \ - for (;;) { \ - local_irq_save(flags); \ - if (__printk_cpu_trylock()) \ - break; \ - local_irq_restore(flags); \ - __printk_wait_on_cpu_lock(); \ +#define printk_cpu_sync_get_irqsave(flags) \ + for (;;) { \ + local_irq_save(flags); \ + if (__printk_cpu_sync_try_get()) \ + break; \ + local_irq_restore(flags); \ + __printk_cpu_sync_wait(); \ } /** - * printk_cpu_unlock_irqrestore() - Release the printk cpu-reentrant spinning - * lock and restore interrupts. - * @flags: Caller's saved interrupt state, from printk_cpu_lock_irqsave(). + * printk_cpu_sync_put_irqrestore() - Release the printk cpu-reentrant spinning + * lock and restore interrupts. + * @flags: Caller's saved interrupt state, from printk_cpu_sync_get_irqsave(). */ -#define printk_cpu_unlock_irqrestore(flags) \ +#define printk_cpu_sync_put_irqrestore(flags) \ do { \ - __printk_cpu_unlock(); \ + __printk_cpu_sync_put(); \ local_irq_restore(flags); \ - } while (0) \ + } while (0) #else -#define printk_cpu_lock_irqsave(flags) ((void)flags) -#define printk_cpu_unlock_irqrestore(flags) ((void)flags) +#define printk_cpu_sync_get_irqsave(flags) ((void)flags) +#define printk_cpu_sync_put_irqrestore(flags) ((void)flags) #endif /* CONFIG_SMP */ -- cgit v1.2.3 From f5343321b71ac0a1112adeab0ff90b239bad3a83 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Thu, 21 Apr 2022 23:28:37 +0206 Subject: printk: cpu sync always disable interrupts The CPU sync functions are a NOP for !CONFIG_SMP. But for !CONFIG_SMP they still need to disable interrupts in order to preserve context within the CPU sync sections. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Reviewed-by: Sergey Senozhatsky Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220421212250.565456-3-john.ogness@linutronix.de --- include/linux/printk.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index 859323a52985..b70a42f94031 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -281,9 +281,16 @@ extern int __printk_cpu_sync_try_get(void); extern void __printk_cpu_sync_wait(void); extern void __printk_cpu_sync_put(void); +#else + +#define __printk_cpu_sync_try_get() true +#define __printk_cpu_sync_wait() +#define __printk_cpu_sync_put() +#endif /* CONFIG_SMP */ + /** - * printk_cpu_sync_get_irqsave() - Acquire the printk cpu-reentrant spinning - * lock and disable interrupts. + * printk_cpu_sync_get_irqsave() - Disable interrupts and acquire the printk + * cpu-reentrant spinning lock. * @flags: Stack-allocated storage for saving local interrupt state, * to be passed to printk_cpu_sync_put_irqrestore(). * @@ -322,13 +329,6 @@ extern void __printk_cpu_sync_put(void); local_irq_restore(flags); \ } while (0) -#else - -#define printk_cpu_sync_get_irqsave(flags) ((void)flags) -#define printk_cpu_sync_put_irqrestore(flags) ((void)flags) - -#endif /* CONFIG_SMP */ - extern int kptr_restrict; /** -- cgit v1.2.3 From a699449bb13b70b8bd10dc03ad7327ea3993221e Mon Sep 17 00:00:00 2001 From: John Ogness Date: Thu, 21 Apr 2022 23:28:44 +0206 Subject: printk: refactor and rework printing logic Refactor/rework printing logic in order to prepare for moving to threaded console printing. - Move @console_seq into struct console so that the current "position" of each console can be tracked individually. - Move @console_dropped into struct console so that the current drop count of each console can be tracked individually. - Modify printing logic so that each console independently loads, prepares, and prints its next record. - Remove exclusive_console logic. Since console positions are handled independently, replaying past records occurs naturally. - Update the comments explaining why preemption is disabled while printing from printk() context. With these changes, there is a change in behavior: the console replaying the log (formerly exclusive console) will no longer block other consoles. New messages appear on the other consoles while the newly added console is still replaying. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220421212250.565456-10-john.ogness@linutronix.de --- include/linux/console.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/console.h b/include/linux/console.h index 7cd758a4f44e..8c1686e2c233 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -151,6 +151,8 @@ struct console { int cflag; uint ispeed; uint ospeed; + u64 seq; + unsigned long dropped; void *data; struct console *next; }; -- cgit v1.2.3 From 3b604ca81202eea2a917eb6491e90f610fba0ec7 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Thu, 21 Apr 2022 23:28:46 +0206 Subject: printk: add pr_flush() Provide a might-sleep function to allow waiting for console printers to catch up to the latest logged message. Use pr_flush() whenever it is desirable to get buffered messages printed before continuing: suspend_console(), resume_console(), console_stop(), console_start(), console_unblank(). Signed-off-by: John Ogness Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220421212250.565456-12-john.ogness@linutronix.de --- include/linux/printk.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index b70a42f94031..091fba7283e1 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -170,6 +170,8 @@ extern void __printk_safe_exit(void); #define printk_deferred_enter __printk_safe_enter #define printk_deferred_exit __printk_safe_exit +extern bool pr_flush(int timeout_ms, bool reset_on_progress); + /* * Please don't use printk_ratelimit(), because it shares ratelimiting state * with all other unrelated printk_ratelimit() callsites. Instead use @@ -220,6 +222,11 @@ static inline void printk_deferred_exit(void) { } +static inline bool pr_flush(int timeout_ms, bool reset_on_progress) +{ + return true; +} + static inline int printk_ratelimit(void) { return 0; -- cgit v1.2.3 From 2bb2b7b57f81255c13f4395ea911d6bdc70c9fe2 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Thu, 21 Apr 2022 23:28:47 +0206 Subject: printk: add functions to prefer direct printing Once kthread printing is available, console printing will no longer occur in the context of the printk caller. However, there are some special contexts where it is desirable for the printk caller to directly print out kernel messages. Using pr_flush() to wait for threaded printers is only possible if the caller is in a sleepable context and the kthreads are active. That is not always the case. Introduce printk_prefer_direct_enter() and printk_prefer_direct_exit() functions to explicitly (and globally) activate/deactivate preferred direct console printing. The term "direct console printing" refers to printing to all enabled consoles from the context of the printk caller. The term "prefer" is used because this type of printing is only best effort. If the console is currently locked or other printers are already actively printing, the printk caller will need to rely on the other contexts to handle the printing. This preferred direct printing is how all printing has been handled until now (unless it was explicitly deferred). When kthread printing is introduced, there may be some unanticipated problems due to kthreads being unable to flush important messages. In order to minimize such risks, preferred direct printing is activated for the primary important messages when the system experiences general types of major errors. These are: - emergency reboot/shutdown - cpu and rcu stalls - hard and soft lockups - hung tasks - warn - sysrq Note that since kthread printing does not yet exist, no behavior changes result from this commit. This is only implementing the counter and marking the various places where preferred direct printing is active. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Acked-by: Paul E. McKenney # for RCU Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220421212250.565456-13-john.ogness@linutronix.de --- include/linux/printk.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index 091fba7283e1..cd26aab0ab2a 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -170,6 +170,9 @@ extern void __printk_safe_exit(void); #define printk_deferred_enter __printk_safe_enter #define printk_deferred_exit __printk_safe_exit +extern void printk_prefer_direct_enter(void); +extern void printk_prefer_direct_exit(void); + extern bool pr_flush(int timeout_ms, bool reset_on_progress); /* @@ -222,6 +225,14 @@ static inline void printk_deferred_exit(void) { } +static inline void printk_prefer_direct_enter(void) +{ +} + +static inline void printk_prefer_direct_exit(void) +{ +} + static inline bool pr_flush(int timeout_ms, bool reset_on_progress) { return true; -- cgit v1.2.3 From 09c5ba0aa2fcfdadb17d045c3ee6f86d69270df7 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Thu, 21 Apr 2022 23:28:48 +0206 Subject: printk: add kthread console printers Create a kthread for each console to perform console printing. During normal operation (@system_state == SYSTEM_RUNNING), the kthread printers are responsible for all printing on their respective consoles. During non-normal operation, console printing is done as it has been: within the context of the printk caller or within irqwork triggered by the printk caller, referred to as direct printing. Since threaded console printers are responsible for all printing during normal operation, this also includes messages generated via deferred printk calls. If direct printing is in effect during a deferred printk call, the queued irqwork will perform the direct printing. To make it clear that this is the only time that the irqwork will perform direct printing, rename the flag PRINTK_PENDING_OUTPUT to PRINTK_PENDING_DIRECT_OUTPUT. Threaded console printers synchronize against each other and against console lockers by taking the console lock for each message that is printed. Note that the kthread printers do not care about direct printing. They will always try to print if new records are available. They can be blocked by direct printing, but will be woken again once direct printing is finished. Console unregistration is a bit tricky because the associated kthread printer cannot be stopped while the console lock is held. A policy is implemented that states: whichever task clears con->thread (under the console lock) is responsible for stopping the kthread. unregister_console() will clear con->thread while the console lock is held and then stop the kthread after releasing the console lock. For consoles that have implemented the exit() callback, the kthread is stopped before exit() is called. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220421212250.565456-14-john.ogness@linutronix.de --- include/linux/console.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/console.h b/include/linux/console.h index 8c1686e2c233..9a251e70c090 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -153,6 +153,8 @@ struct console { uint ospeed; u64 seq; unsigned long dropped; + struct task_struct *thread; + void *data; struct console *next; }; -- cgit v1.2.3 From 5e7260712b9a76de19c32f15d667f8f93e573978 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Thu, 21 Apr 2022 14:47:26 +0200 Subject: qed: Remove IP services API. qed_nvmetcp_ip_services.c and its corresponding header file were introduced in commit 806ee7f81a2b ("qed: Add IP services APIs support") but there's still no users for any of the functions they declare. Since these files are effectively unused, let's just drop them. Found by code inspection. Compile-tested only. Signed-off-by: Guillaume Nault Link: https://lore.kernel.org/r/351ac8c847980e22850eb390553f8cc0e1ccd0ce.1650545051.git.gnault@redhat.com Signed-off-by: Jakub Kicinski --- include/linux/qed/qed_nvmetcp_ip_services_if.h | 29 -------------------------- 1 file changed, 29 deletions(-) delete mode 100644 include/linux/qed/qed_nvmetcp_ip_services_if.h (limited to 'include') diff --git a/include/linux/qed/qed_nvmetcp_ip_services_if.h b/include/linux/qed/qed_nvmetcp_ip_services_if.h deleted file mode 100644 index 3604aee53796..000000000000 --- a/include/linux/qed/qed_nvmetcp_ip_services_if.h +++ /dev/null @@ -1,29 +0,0 @@ -/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ -/* - * Copyright 2021 Marvell. All rights reserved. - */ - -#ifndef _QED_IP_SERVICES_IF_H -#define _QED_IP_SERVICES_IF_H - -#include -#include -#include -#include - -int qed_route_ipv4(struct sockaddr_storage *local_addr, - struct sockaddr_storage *remote_addr, - struct sockaddr *hardware_address, - struct net_device **ndev); -int qed_route_ipv6(struct sockaddr_storage *local_addr, - struct sockaddr_storage *remote_addr, - struct sockaddr *hardware_address, - struct net_device **ndev); -void qed_vlan_get_ndev(struct net_device **ndev, u16 *vlan_id); -struct pci_dev *qed_validate_ndev(struct net_device *ndev); -void qed_return_tcp_port(struct socket *sock); -int qed_fetch_tcp_port(struct sockaddr_storage local_ip_addr, - struct socket **sock, u16 *port); -__be16 qed_get_in_port(struct sockaddr_storage *sa); - -#endif /* _QED_IP_SERVICES_IF_H */ -- cgit v1.2.3 From b253a0680ceadc5d7b4acca7aa2d870326cad8ad Mon Sep 17 00:00:00 2001 From: Pengcheng Yang Date: Wed, 20 Apr 2022 10:34:41 +0800 Subject: tcp: ensure to use the most recently sent skb when filling the rate sample If an ACK (s)acks multiple skbs, we favor the information from the most recently sent skb by choosing the skb with the highest prior_delivered count. But in the interval between receiving ACKs, we send multiple skbs with the same prior_delivered, because the tp->delivered only changes when we receive an ACK. We used RACK's solution, copying tcp_rack_sent_after() as tcp_skb_sent_after() helper to determine "which packet was sent last?". Later, we will use tcp_skb_sent_after() instead in RACK. Fixes: b9f64820fb22 ("tcp: track data delivery rate for a TCP connection") Signed-off-by: Pengcheng Yang Cc: Paolo Abeni Acked-by: Neal Cardwell Tested-by: Neal Cardwell Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/1650422081-22153-1-git-send-email-yangpc@wangsu.com Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 70ca4a5e330a..be712fb9ddd7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1042,6 +1042,7 @@ struct rate_sample { int losses; /* number of packets marked lost upon ACK */ u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */ u32 prior_in_flight; /* in flight before this ACK */ + u32 last_end_seq; /* end_seq of most recently ACKed packet */ bool is_app_limited; /* is sample from packet with bubble in pipe? */ bool is_retrans; /* is sample from retransmission? */ bool is_ack_delayed; /* is this (likely) a delayed ACK? */ @@ -1164,6 +1165,11 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, bool is_sack_reneg, struct rate_sample *rs); void tcp_rate_check_app_limited(struct sock *sk); +static inline bool tcp_skb_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) +{ + return t1 > t2 || (t1 == t2 && after(seq1, seq2)); +} + /* These functions determine how the current flow behaves in respect of SACK * handling. SACK is negotiated with the peer, and therefore it can vary * between different flows. -- cgit v1.2.3 From 9ea4dcf49878bb9546b8fa9319dcbdc9b7ee20f8 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 22 Apr 2022 15:58:11 -0700 Subject: PM: CXL: Disable suspend The CXL specification claims S3 support at a hardware level, but at a system software level there are some missing pieces. Section 9.4 (CXL 2.0) rightly claims that "CXL mem adapters may need aux power to retain memory context across S3", but there is no enumeration mechanism for the OS to determine if a given adapter has that support. Moreover the save state and resume image for the system may inadvertantly end up in a CXL device that needs to be restored before the save state is recoverable. I.e. a circular dependency that is not resolvable without a third party save-area. Arrange for the cxl_mem driver to fail S3 attempts. This still nominaly allows for suspend, but requires unbinding all CXL memory devices before the suspend to ensure the typical DRAM flow is taken. The cxl_mem unbind flow is intended to also tear down all CXL memory regions associated with a given cxl_memdev. It is reasonable to assume that any device participating in a System RAM range published in the EFI memory map is covered by aux power and save-area outside the device itself. So this restriction can be minimized in the future once pre-existing region enumeration support arrives, and perhaps a spec update to clarify if the EFI memory map is sufficent for determining the range of devices managed by platform-firmware for S3 support. Per Rafael, if the CXL configuration prevents suspend then it should fail early before tasks are frozen, and mem_sleep should stop showing 'mem' as an option [1]. Effectively CXL augments the platform suspend ->valid() op since, for example, the ACPI ops are not aware of the CXL / PCI dependencies. Given the split role of platform firmware vs OS provisioned CXL memory it is up to the cxl_mem driver to determine if the CXL configuration has elements that platform firmware may not be prepared to restore. Link: https://lore.kernel.org/r/CAJZ5v0hGVN_=3iU8OLpHY3Ak35T5+JcBM-qs8SbojKrpd0VXsA@mail.gmail.com [1] Cc: "Rafael J. Wysocki" Cc: Pavel Machek Cc: Len Brown Reviewed-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/165066828317.3907920.5690432272182042556.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/linux/pm.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/pm.h b/include/linux/pm.h index e65b3ab28377..7911c4c9a7be 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -36,6 +36,15 @@ static inline void pm_vt_switch_unregister(struct device *dev) } #endif /* CONFIG_VT_CONSOLE_SLEEP */ +#ifdef CONFIG_CXL_SUSPEND +bool cxl_mem_active(void); +#else +static inline bool cxl_mem_active(void) +{ + return false; +} +#endif + /* * Device power management */ -- cgit v1.2.3 From 26f89535a5bb17915a2e1062c3999a2ee797c7b0 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Wed, 13 Apr 2022 22:12:46 -0700 Subject: cxl/mbox: Use type __u32 for mailbox payload sizes Payload sizes for mailbox commands are expected to be positive values coming from userspace. The documentation correctly describes these as always unsigned values. The mailbox and send structures that support the mailbox commands however, use __s32 types for the payloads. Replace __s32 with __u32 in the mailbox and send command structures and update usages. Kernel users of the interface already block all negative values and there is no known ability for userspace to have grown a dependency on submitting negative values to the kernel. The known user of the IOCTL, the CXL command line interface (cxl-cli) already enforces positive size values. A Smatch warning of a signedness uncovered this issue. Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Alison Schofield Link: https://lore.kernel.org/r/20220414051246.1244575-1-alison.schofield@intel.com Signed-off-by: Dan Williams --- include/uapi/linux/cxl_mem.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index 8d206f27bb6d..c71021a2a9ed 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -68,8 +68,8 @@ static const struct { * struct cxl_command_info - Command information returned from a query. * @id: ID number for the command. * @flags: Flags that specify command behavior. - * @size_in: Expected input size, or -1 if variable length. - * @size_out: Expected output size, or -1 if variable length. + * @size_in: Expected input size, or ~0 if variable length. + * @size_out: Expected output size, or ~0 if variable length. * * Represents a single command that is supported by both the driver and the * hardware. This is returned as part of an array from the query ioctl. The @@ -78,7 +78,7 @@ static const struct { * * - @id = 10 * - @flags = 0 - * - @size_in = -1 + * - @size_in = ~0 * - @size_out = 0 * * See struct cxl_mem_query_commands. @@ -89,8 +89,8 @@ struct cxl_command_info { __u32 flags; #define CXL_MEM_COMMAND_FLAG_MASK GENMASK(0, 0) - __s32 size_in; - __s32 size_out; + __u32 size_in; + __u32 size_out; }; /** @@ -169,13 +169,13 @@ struct cxl_send_command { __u32 retval; struct { - __s32 size; + __u32 size; __u32 rsvd; __u64 payload; } in; struct { - __s32 size; + __u32 size; __u32 rsvd; __u64 payload; } out; -- cgit v1.2.3 From f226041424cf87245d39a1b2dfae304308b36b6b Mon Sep 17 00:00:00 2001 From: Dave Gerlach Date: Sat, 9 Apr 2022 14:12:15 -0700 Subject: soc: ti: wkup_m3_ipc: Add support for toggling VTT regulator Some boards like the AM335x EVM-SK and AM437x GP EVM provide software control via a GPIO pin to toggle the DDR VTT regulator to reduce power consumption in low power states. The VTT regulator should be disabled after enabling self-refresh on suspend, and should be enabled before disabling self-refresh on resume. This is to allow proper self-refresh entry/exit commands to be transmitted to the memory. The "ti,vtt-gpio-pin" device tree property in the wkup_m3_ipc node specifies which GPIO pin to use. This property is communicated to the Wakeup Cortex M3 co-processor where the actual toggling of the GPIO pin happens in CM3 firmware [1]. Please note that the GPIO pin must be on the GPIO0 module as that module is in the wakeup power domain. [1] https://git.ti.com/cgit/processor-firmware/ti-amx3-cm3-pm-firmware/tree/src/pm_services/ddr.c?h=08.02.00.006#n190 Signed-off-by: Dave Gerlach Signed-off-by: Keerthy [dfustini: remove the unnecessary "ti,needs-vtt-toggle" property] Signed-off-by: Drew Fustini Signed-off-by: Nishanth Menon Link: https://lore.kernel.org/r/20220409211215.2529387-3-dfustini@baylibre.com --- include/linux/wkup_m3_ipc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/wkup_m3_ipc.h b/include/linux/wkup_m3_ipc.h index 3f496967b538..2bc52c6381d5 100644 --- a/include/linux/wkup_m3_ipc.h +++ b/include/linux/wkup_m3_ipc.h @@ -33,6 +33,7 @@ struct wkup_m3_ipc { int mem_type; unsigned long resume_addr; + int vtt_conf; int state; struct completion sync_complete; -- cgit v1.2.3 From 8be99c7b8bb17f2b82af4a0a6798b795f4d74436 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Wed, 13 Apr 2022 08:58:32 +0100 Subject: dt-bindings: clk: mpfs: add defines for two new clocks The RTC reference and MSSPLL were previously not documented or defined, as they were unused. Add their defines to the PolarFire SoC header. Fixes: 2145bb687e3f ("dt-bindings: clk: microchip: Add Microchip PolarFire host binding") Reviewed-by: Daire McNamara Signed-off-by: Conor Dooley Link: https://lore.kernel.org/r/20220413075835.3354193-6-conor.dooley@microchip.com Acked-by: Krzysztof Kozlowski Acked-by: Palmer Dabbelt Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/microchip,mpfs-clock.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/clock/microchip,mpfs-clock.h b/include/dt-bindings/clock/microchip,mpfs-clock.h index 73f2a9324857..4048669bf756 100644 --- a/include/dt-bindings/clock/microchip,mpfs-clock.h +++ b/include/dt-bindings/clock/microchip,mpfs-clock.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ /* * Daire McNamara, - * Copyright (C) 2020 Microchip Technology Inc. All rights reserved. + * Copyright (C) 2020-2022 Microchip Technology Inc. All rights reserved. */ #ifndef _DT_BINDINGS_CLK_MICROCHIP_MPFS_H_ @@ -42,4 +42,7 @@ #define CLK_ATHENA 31 #define CLK_CFM 32 +#define CLK_RTCREF 33 +#define CLK_MSSPLL 34 + #endif /* _DT_BINDINGS_CLK_MICROCHIP_MPFS_H_ */ -- cgit v1.2.3 From 038010bb30684c0219fa4f93a13149038f28291a Mon Sep 17 00:00:00 2001 From: John Crispin Date: Mon, 14 Mar 2022 09:44:03 +0100 Subject: dt-bindings: Add en7523-scu device tree binding documentation Adds device tree binding documentation for clocks in the EN7523 SOC. Reviewed-by: Rob Herring Signed-off-by: John Crispin Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20220314084409.84394-2-nbd@nbd.name Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/en7523-clk.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 include/dt-bindings/clock/en7523-clk.h (limited to 'include') diff --git a/include/dt-bindings/clock/en7523-clk.h b/include/dt-bindings/clock/en7523-clk.h new file mode 100644 index 000000000000..717d23a5e5ae --- /dev/null +++ b/include/dt-bindings/clock/en7523-clk.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ + +#ifndef _DT_BINDINGS_CLOCK_AIROHA_EN7523_H_ +#define _DT_BINDINGS_CLOCK_AIROHA_EN7523_H_ + +#define EN7523_CLK_GSW 0 +#define EN7523_CLK_EMI 1 +#define EN7523_CLK_BUS 2 +#define EN7523_CLK_SLIC 3 +#define EN7523_CLK_SPI 4 +#define EN7523_CLK_NPU 5 +#define EN7523_CLK_CRYPTO 6 +#define EN7523_CLK_PCIE 7 + +#define EN7523_NUM_CLOCKS 8 + +#endif /* _DT_BINDINGS_CLOCK_AIROHA_EN7523_H_ */ -- cgit v1.2.3 From 0f08c2e7458e25c967d844170f8ad1aac3b57a02 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Thu, 17 Mar 2022 12:55:06 +0900 Subject: usb: deprecate the third argument of usb_maxpacket() This is a transitional patch with the ultimate goal of changing the prototype of usb_maxpacket() from: | static inline __u16 | usb_maxpacket(struct usb_device *udev, int pipe, int is_out) into: | static inline u16 usb_maxpacket(struct usb_device *udev, int pipe) The third argument of usb_maxpacket(): is_out gets removed because it can be derived from its second argument: pipe using usb_pipeout(pipe). Furthermore, in the current version, ubs_pipeout(pipe) is called regardless in order to sanitize the is_out parameter. In order to make a smooth change, we first deprecate the is_out parameter by simply ignoring it (using a variadic function) and will remove it later, once all the callers get updated. The body of the function is reworked accordingly and is_out is replaced by usb_pipeout(pipe). The WARN_ON() calls become unnecessary and get removed. Finally, the return type is changed from __u16 to u16 because this is not a UAPI function. Signed-off-by: Vincent Mailhol Link: https://lore.kernel.org/r/20220317035514.6378-2-mailhol.vincent@wanadoo.fr Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/usb.h b/include/linux/usb.h index 200b7b79acb5..572e136f6314 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1969,21 +1969,17 @@ usb_pipe_endpoint(struct usb_device *dev, unsigned int pipe) return eps[usb_pipeendpoint(pipe)]; } -/*-------------------------------------------------------------------------*/ - -static inline __u16 -usb_maxpacket(struct usb_device *udev, int pipe, int is_out) +static inline u16 usb_maxpacket(struct usb_device *udev, int pipe, + /* int is_out deprecated */ ...) { struct usb_host_endpoint *ep; unsigned epnum = usb_pipeendpoint(pipe); - if (is_out) { - WARN_ON(usb_pipein(pipe)); + if (usb_pipeout(pipe)) ep = udev->ep_out[epnum]; - } else { - WARN_ON(usb_pipeout(pipe)); + else ep = udev->ep_in[epnum]; - } + if (!ep) return 0; @@ -1991,8 +1987,6 @@ usb_maxpacket(struct usb_device *udev, int pipe, int is_out) return usb_endpoint_maxp(&ep->desc); } -/* ----------------------------------------------------------------------- */ - /* translate USB error codes to codes user space understands */ static inline int usb_translate_errors(int error_code) { -- cgit v1.2.3 From 2ddf7617d568fdcbd3cc454bb4849fa6d3398c86 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Thu, 17 Mar 2022 12:55:13 +0900 Subject: usb: remove third argument of usb_maxpacket() Now that all users of usb_maxpacket() have been migrated to only use two arguments, remove the third variadic argument which was introduced for the transition. Signed-off-by: Vincent Mailhol Link: https://lore.kernel.org/r/20220317035514.6378-9-mailhol.vincent@wanadoo.fr Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/usb.h b/include/linux/usb.h index 572e136f6314..8127782aa7a1 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1969,8 +1969,7 @@ usb_pipe_endpoint(struct usb_device *dev, unsigned int pipe) return eps[usb_pipeendpoint(pipe)]; } -static inline u16 usb_maxpacket(struct usb_device *udev, int pipe, - /* int is_out deprecated */ ...) +static inline u16 usb_maxpacket(struct usb_device *udev, int pipe) { struct usb_host_endpoint *ep; unsigned epnum = usb_pipeendpoint(pipe); -- cgit v1.2.3 From bdddc253b0938a0063798881d1f6a971ea1d8943 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Thu, 17 Mar 2022 12:55:14 +0900 Subject: usb: rework usb_maxpacket() using usb_pipe_endpoint() Rework the body of usb_maxpacket() and just rely on the usb_pipe_endpoint() helper function to retrieve the host endpoint instead of doing it by hand. Signed-off-by: Vincent Mailhol Link: https://lore.kernel.org/r/20220317035514.6378-10-mailhol.vincent@wanadoo.fr Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/usb.h b/include/linux/usb.h index 8127782aa7a1..60bee864d897 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1971,13 +1971,7 @@ usb_pipe_endpoint(struct usb_device *dev, unsigned int pipe) static inline u16 usb_maxpacket(struct usb_device *udev, int pipe) { - struct usb_host_endpoint *ep; - unsigned epnum = usb_pipeendpoint(pipe); - - if (usb_pipeout(pipe)) - ep = udev->ep_out[epnum]; - else - ep = udev->ep_in[epnum]; + struct usb_host_endpoint *ep = usb_pipe_endpoint(udev, pipe); if (!ep) return 0; -- cgit v1.2.3 From 1e39e5a32ad7fdd82d6e071aa14ecd511eedc1f7 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 22 Apr 2022 14:55:39 -0700 Subject: mptcp: infinite mapping sending This patch adds the infinite mapping sending logic. Add a new flag send_infinite_map in struct mptcp_subflow_context. Set it true when a single contiguous subflow is in use and the allow_infinite_fallback flag is true in mptcp_pm_mp_fail_received(). In mptcp_sendmsg_frag(), if this flag is true, call the new function mptcp_update_infinite_map() to set the infinite mapping. Add a new flag infinite_map in struct mptcp_ext, set it true in mptcp_update_infinite_map(), and check this flag in a new helper mptcp_check_infinite_map(). In mptcp_update_infinite_map(), set data_len to 0, and clear the send_infinite_map flag, then do fallback. In mptcp_established_options(), use the helper mptcp_check_infinite_map() to let the infinite mapping DSS can be sent out in the fallback mode. Suggested-by: Paolo Abeni Signed-off-by: Geliang Tang Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/net/mptcp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 0a3b0fb04a3b..8b1afd6f5cc4 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -35,7 +35,8 @@ struct mptcp_ext { frozen:1, reset_transient:1; u8 reset_reason:4, - csum_reqd:1; + csum_reqd:1, + infinite_map:1; }; #define MPTCP_RM_IDS_MAX 8 -- cgit v1.2.3 From d9fdd02d4265c4c4fd5264b32b46034239192b7e Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 22 Apr 2022 14:55:42 -0700 Subject: mptcp: dump infinite_map field in mptcp_dump_mpext In trace event class mptcp_dump_mpext, dump the newly added infinite_map field of struct mptcp_dump_mpext too. Signed-off-by: Geliang Tang Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/trace/events/mptcp.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/mptcp.h b/include/trace/events/mptcp.h index f8e28e686c65..563e48617374 100644 --- a/include/trace/events/mptcp.h +++ b/include/trace/events/mptcp.h @@ -84,6 +84,7 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext, __field(u8, reset_transient) __field(u8, reset_reason) __field(u8, csum_reqd) + __field(u8, infinite_map) ), TP_fast_assign( @@ -102,9 +103,10 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext, __entry->reset_transient = mpext->reset_transient; __entry->reset_reason = mpext->reset_reason; __entry->csum_reqd = mpext->csum_reqd; + __entry->infinite_map = mpext->infinite_map; ), - TP_printk("data_ack=%llu data_seq=%llu subflow_seq=%u data_len=%u csum=%x use_map=%u dsn64=%u data_fin=%u use_ack=%u ack64=%u mpc_map=%u frozen=%u reset_transient=%u reset_reason=%u csum_reqd=%u", + TP_printk("data_ack=%llu data_seq=%llu subflow_seq=%u data_len=%u csum=%x use_map=%u dsn64=%u data_fin=%u use_ack=%u ack64=%u mpc_map=%u frozen=%u reset_transient=%u reset_reason=%u csum_reqd=%u infinite_map=%u", __entry->data_ack, __entry->data_seq, __entry->subflow_seq, __entry->data_len, __entry->csum, __entry->use_map, @@ -112,7 +114,7 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext, __entry->use_ack, __entry->ack64, __entry->mpc_map, __entry->frozen, __entry->reset_transient, __entry->reset_reason, - __entry->csum_reqd) + __entry->csum_reqd, __entry->infinite_map) ); DEFINE_EVENT(mptcp_dump_mpext, mptcp_sendmsg_frag, -- cgit v1.2.3 From 3813c932ed970dd4f413498ccecb03c73c4f1784 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 3 Mar 2022 13:55:08 +0000 Subject: media: cec: call enable_adap on s_log_addrs Don't enable/disable the adapter if the first fh is opened or the last fh is closed, instead do this when the adapter is configured or unconfigured, and also when we enter Monitor All or Monitor Pin mode for the first time or we exit the Monitor All/Pin mode for the last time. However, if needs_hpd is true, then do this when the physical address is set or cleared: in that case the adapter typically is powered by the HPD, so it really is disabled when the HPD is low. This case (needs_hpd is true) was already handled in this way, so this wasn't changed. The problem with the old behavior was that if the HPD goes low when no fh is open, and a transmit was in progress, then the adapter would be disabled, typically stopping the transmit immediately which leaves a partial message on the bus, which isn't nice and can confuse some adapters. It makes much more sense to disable it only when the adapter is unconfigured and we're not monitoring the bus, since then you really won't be using it anymore. To keep track of this store a CEC activation count and call adap_enable only when it goes from 0 to 1 or back to 0. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/cec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/media/cec.h b/include/media/cec.h index 77346f757036..97c5f5bfcbd0 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -185,6 +185,7 @@ struct cec_adap_ops { * Drivers that need this can set this field to true after the * cec_allocate_adapter() call. * @last_initiator: the initiator of the last transmitted message. + * @activate_cnt: number of times that CEC is activated * @monitor_all_cnt: number of filehandles monitoring all msgs * @monitor_pin_cnt: number of filehandles monitoring pin changes * @follower_cnt: number of filehandles in follower mode @@ -236,6 +237,7 @@ struct cec_adapter { bool cec_pin_is_high; bool adap_controls_phys_addr; u8 last_initiator; + u32 activate_cnt; u32 monitor_all_cnt; u32 monitor_pin_cnt; u32 follower_cnt; -- cgit v1.2.3 From 590a8e564c6eff7e77a84e728612f1269e3c0685 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 3 Mar 2022 14:01:44 +0000 Subject: media: cec: abort if the current transmit was canceled If a transmit-in-progress was canceled, then, once the transmit is done, mark it as aborted and refrain from retrying the transmit. To signal this situation the new transmit_in_progress_aborted field is set to true. The old implementation would just set adap->transmitting to NULL and set adap->transmit_in_progress to false, but on the hardware level the transmit was still ongoing. However, the framework would think the transmit was aborted, and if a new transmit was issued, then it could overwrite the HW buffer containing the old transmit with the new transmit, leading to garbled data on the CEC bus. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/cec.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/media/cec.h b/include/media/cec.h index 97c5f5bfcbd0..31d704f36707 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -163,6 +163,11 @@ struct cec_adap_ops { * @wait_queue: queue of transmits waiting for a reply * @transmitting: CEC messages currently being transmitted * @transmit_in_progress: true if a transmit is in progress + * @transmit_in_progress_aborted: true if a transmit is in progress is to be + * aborted. This happens if the logical address is + * invalidated while the transmit is ongoing. In that + * case the transmit will finish, but will not retransmit + * and be marked as ABORTED. * @kthread_config: kthread used to configure a CEC adapter * @config_completion: used to signal completion of the config kthread * @kthread: main CEC processing thread @@ -218,6 +223,7 @@ struct cec_adapter { struct list_head wait_queue; struct cec_data *transmitting; bool transmit_in_progress; + bool transmit_in_progress_aborted; struct task_struct *kthread_config; struct completion config_completion; -- cgit v1.2.3 From 567f882a401346779d05a90beb8f21865ebdd398 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 9 Mar 2022 10:55:43 +0000 Subject: media: cec.h: add cec_msg_recv_is_rx/tx_result helpers These two helper functions return true if the received message contains the result of a previous non-blocking transmit. Either the tx_status result (cec_msg_recv_is_tx_result) of the transmit, or the rx_status result (cec_msg_recv_is_rx_result) of the reply to the original transmit. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/cec.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/cec.h b/include/uapi/linux/cec.h index de936f5e446d..1d48da926216 100644 --- a/include/uapi/linux/cec.h +++ b/include/uapi/linux/cec.h @@ -142,6 +142,26 @@ static inline void cec_msg_set_reply_to(struct cec_msg *msg, msg->reply = msg->timeout = 0; } +/** + * cec_msg_recv_is_tx_result - return true if this message contains the + * result of an earlier non-blocking transmit + * @msg: the message structure from CEC_RECEIVE + */ +static inline int cec_msg_recv_is_tx_result(const struct cec_msg *msg) +{ + return msg->sequence && msg->tx_status && !msg->rx_status; +} + +/** + * cec_msg_recv_is_rx_result - return true if this message contains the + * reply of an earlier non-blocking transmit + * @msg: the message structure from CEC_RECEIVE + */ +static inline int cec_msg_recv_is_rx_result(const struct cec_msg *msg) +{ + return msg->sequence && !msg->tx_status && msg->rx_status; +} + /* cec_msg flags field */ #define CEC_MSG_FL_REPLY_TO_FOLLOWERS (1 << 0) #define CEC_MSG_FL_RAW (1 << 1) -- cgit v1.2.3 From dad272bd03d541dc7c0ff8331756eccf659f6f02 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Sat, 13 Nov 2021 11:05:24 +0000 Subject: media: cec: add xfer_timeout_ms field Allow drivers to change the transmit timeout value, i.e. after how long should a transmit be considered 'lost', i.e. the corresponding cec_transmit_done_ts was never called. Some CEC devices have their own timeout, and so this timeout value must be longer than that hardware timeout value. If it is shorter then the framework would consider the transmit lost, even though it is effectively still in progress at the hardware level. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/cec.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/media/cec.h b/include/media/cec.h index 31d704f36707..80340c9eb0f2 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -168,6 +168,8 @@ struct cec_adap_ops { * invalidated while the transmit is ongoing. In that * case the transmit will finish, but will not retransmit * and be marked as ABORTED. + * @xfer_timeout_ms: the transfer timeout in ms. + * If 0, then timeout after 2.1 ms. * @kthread_config: kthread used to configure a CEC adapter * @config_completion: used to signal completion of the config kthread * @kthread: main CEC processing thread @@ -224,6 +226,7 @@ struct cec_adapter { struct cec_data *transmitting; bool transmit_in_progress; bool transmit_in_progress_aborted; + unsigned int xfer_timeout_ms; struct task_struct *kthread_config; struct completion config_completion; -- cgit v1.2.3 From f1b57164305d6342b9f77a4f4482cde492b56983 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 3 Feb 2022 12:11:15 +0000 Subject: media: cec: add optional adap_configured callback This new optional callback is called when the adapter is fully configured or fully unconfigured. Some drivers may have to take action when this happens. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/cec.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/media/cec.h b/include/media/cec.h index 80340c9eb0f2..6f13b0222aa3 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -118,6 +118,7 @@ struct cec_adap_ops { int (*adap_monitor_all_enable)(struct cec_adapter *adap, bool enable); int (*adap_monitor_pin_enable)(struct cec_adapter *adap, bool enable); int (*adap_log_addr)(struct cec_adapter *adap, u8 logical_addr); + void (*adap_configured)(struct cec_adapter *adap, bool configured); int (*adap_transmit)(struct cec_adapter *adap, u8 attempts, u32 signal_free_time, struct cec_msg *msg); void (*adap_status)(struct cec_adapter *adap, struct seq_file *file); -- cgit v1.2.3 From 4e4dab4bb6029dbee63f12a249ddc44b0124ea63 Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Wed, 2 Mar 2022 22:03:01 +0000 Subject: media: media.h: Add new media link type To describe in the kernel the connection between devices and their supporting peripherals (for example, a camera sensor and the vcm driving the focusing lens for it), add a new type of media link to introduce the concept of these ancillary links. Add some elements to the uAPI documentation to explain the new link type, their purpose and some aspects of their current implementation. Reviewed-by: Laurent Pinchart Signed-off-by: Daniel Scally Reviewed-by: Jean-Michel Hautbois Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/media.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index 200fa8462b90..afbae7213d35 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -226,6 +226,7 @@ struct media_pad_desc { #define MEDIA_LNK_FL_LINK_TYPE (0xf << 28) # define MEDIA_LNK_FL_DATA_LINK (0 << 28) # define MEDIA_LNK_FL_INTERFACE_LINK (1 << 28) +# define MEDIA_LNK_FL_ANCILLARY_LINK (2 << 28) struct media_link_desc { struct media_pad_desc source; -- cgit v1.2.3 From 012c87f7696f3191f340d9bd6b4476d8d3bb25ad Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Wed, 2 Mar 2022 22:03:03 +0000 Subject: media: entity: Add support for ancillary links Add functions to create ancillary links, so that they don't need to be manually created by users. Reviewed-by: Laurent Pinchart Signed-off-by: Daniel Scally Reviewed-by: Jean-Michel Hautbois Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/media-entity.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/media/media-entity.h b/include/media/media-entity.h index 742918962d46..1d13b8939a11 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -1121,4 +1121,23 @@ void media_remove_intf_links(struct media_interface *intf); (((entity)->ops && (entity)->ops->operation) ? \ (entity)->ops->operation((entity) , ##args) : -ENOIOCTLCMD) +/** + * media_create_ancillary_link() - create an ancillary link between two + * instances of &media_entity + * + * @primary: pointer to the primary &media_entity + * @ancillary: pointer to the ancillary &media_entity + * + * Create an ancillary link between two entities, indicating that they + * represent two connected pieces of hardware that form a single logical unit. + * A typical example is a camera lens controller being linked to the sensor that + * it is supporting. + * + * The function sets both MEDIA_LNK_FL_ENABLED and MEDIA_LNK_FL_IMMUTABLE for + * the new link. + */ +struct media_link * +media_create_ancillary_link(struct media_entity *primary, + struct media_entity *ancillary); + #endif -- cgit v1.2.3 From a8a2bd1001f3b5de1a9cd583467ab4559a7b3b01 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Thu, 27 Jan 2022 09:25:48 +0000 Subject: media: mc: Remove redundant documentation Remove redundant kerneldoc documentation in mc-device.c. The functions are already documented in media-device.h, where non-redundant documentation is also moved. Signed-off-by: Sakari Ailus Reviewed-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/media/media-device.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/media/media-device.h b/include/media/media-device.h index 1345e6da688a..7d5b212792a5 100644 --- a/include/media/media-device.h +++ b/include/media/media-device.h @@ -219,6 +219,12 @@ static inline __must_check int media_entity_enum_init( * So drivers need to first initialize the media device, register any entity * within the media device, create pad to pad links and then finally register * the media device by calling media_device_register() as a final step. + * + * The caller is responsible for initializing the media device before + * registration. The following fields must be set: + * + * - dev must point to the parent device + * - model must be filled with the device model name */ void media_device_init(struct media_device *mdev); -- cgit v1.2.3 From db1fa290a35b1652628ba7b921ac7ad53ce36410 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Wed, 9 Mar 2022 09:12:01 +0000 Subject: media: mc: media_device_init() initialises a media_device, not media_entity The documentation for media_device_init() had several references to (struct) media_entity where it should have referred to struct media_device instead. Fix this. Signed-off-by: Sakari Ailus Reviewed-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/media/media-device.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/media/media-device.h b/include/media/media-device.h index 7d5b212792a5..bc015d2cf541 100644 --- a/include/media/media-device.h +++ b/include/media/media-device.h @@ -249,28 +249,28 @@ void media_device_cleanup(struct media_device *mdev); * The caller is responsible for initializing the &media_device structure * before registration. The following fields of &media_device must be set: * - * - &media_entity.dev must point to the parent device (usually a &pci_dev, + * - &media_device.dev must point to the parent device (usually a &pci_dev, * &usb_interface or &platform_device instance). * - * - &media_entity.model must be filled with the device model name as a + * - &media_device.model must be filled with the device model name as a * NUL-terminated UTF-8 string. The device/model revision must not be * stored in this field. * * The following fields are optional: * - * - &media_entity.serial is a unique serial number stored as a + * - &media_device.serial is a unique serial number stored as a * NUL-terminated ASCII string. The field is big enough to store a GUID * in text form. If the hardware doesn't provide a unique serial number * this field must be left empty. * - * - &media_entity.bus_info represents the location of the device in the + * - &media_device.bus_info represents the location of the device in the * system as a NUL-terminated ASCII string. For PCI/PCIe devices - * &media_entity.bus_info must be set to "PCI:" (or "PCIe:") followed by + * &media_device.bus_info must be set to "PCI:" (or "PCIe:") followed by * the value of pci_name(). For USB devices,the usb_make_path() function * must be used. This field is used by applications to distinguish between * otherwise identical devices that don't provide a serial number. * - * - &media_entity.hw_revision is the hardware device revision in a + * - &media_device.hw_revision is the hardware device revision in a * driver-specific format. When possible the revision should be formatted * with the KERNEL_VERSION() macro. * -- cgit v1.2.3 From 78a171e58717685ea0eb082a24bc75bd9e20518f Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Sat, 22 Jan 2022 11:25:57 +0000 Subject: media: mc: Provide a helper for setting bus_info field The bus_info or a similar field exists in a lot of structs, yet drivers tend to set the value of that field by themselves in a determinable way. Thus provide a helper for doing this. To be used in subsequent patches. Signed-off-by: Sakari Ailus Reviewed-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/media/media-device.h | 29 ++++++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/media/media-device.h b/include/media/media-device.h index bc015d2cf541..f0baee6771ef 100644 --- a/include/media/media-device.h +++ b/include/media/media-device.h @@ -13,12 +13,13 @@ #include #include +#include +#include #include #include struct ida; -struct device; struct media_device; /** @@ -181,8 +182,7 @@ struct media_device { atomic_t request_id; }; -/* We don't need to include pci.h or usb.h here */ -struct pci_dev; +/* We don't need to include usb.h here */ struct usb_device; #ifdef CONFIG_MEDIA_CONTROLLER @@ -502,4 +502,27 @@ static inline void __media_device_usb_init(struct media_device *mdev, #define media_device_usb_init(mdev, udev, name) \ __media_device_usb_init(mdev, udev, name, KBUILD_MODNAME) +/** + * media_set_bus_info() - Set bus_info field + * + * @bus_info: Variable where to write the bus info (char array) + * @bus_info_size: Length of the bus_info + * @dev: Related struct device + * + * Sets bus information based on &dev. This is currently done for PCI and + * platform devices. dev is required to be non-NULL for this to happen. + * + * This function is not meant to be called from drivers. + */ +static inline void +media_set_bus_info(char *bus_info, size_t bus_info_size, struct device *dev) +{ + if (!dev) + strscpy(bus_info, "no bus info", bus_info_size); + else if (dev_is_platform(dev)) + snprintf(bus_info, bus_info_size, "platform:%s", dev_name(dev)); + else if (dev_is_pci(dev)) + snprintf(bus_info, bus_info_size, "PCI:%s", dev_name(dev)); +} + #endif -- cgit v1.2.3 From cef699749f3789add5ecaf0a2f73a659cae1c7ae Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Sat, 22 Jan 2022 11:31:37 +0000 Subject: media: mc: Set bus_info in media_device_init() Set bus_info field based on struct device in media_device_init() and remove corresponding code from drivers. Also update media_device_init() documentation: the dev field must be now initialised before calling it. Signed-off-by: Sakari Ailus Reviewed-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/media/media-device.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/media/media-device.h b/include/media/media-device.h index f0baee6771ef..a10b30507524 100644 --- a/include/media/media-device.h +++ b/include/media/media-device.h @@ -225,6 +225,9 @@ static inline __must_check int media_entity_enum_init( * * - dev must point to the parent device * - model must be filled with the device model name + * + * The bus_info field is set by media_device_init() for PCI and platform devices + * if the field begins with '\0'. */ void media_device_init(struct media_device *mdev); @@ -249,9 +252,6 @@ void media_device_cleanup(struct media_device *mdev); * The caller is responsible for initializing the &media_device structure * before registration. The following fields of &media_device must be set: * - * - &media_device.dev must point to the parent device (usually a &pci_dev, - * &usb_interface or &platform_device instance). - * * - &media_device.model must be filled with the device model name as a * NUL-terminated UTF-8 string. The device/model revision must not be * stored in this field. -- cgit v1.2.3 From dadd47d46818c7587f769287aa4acca152d48039 Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Tue, 12 Apr 2022 10:42:40 +0100 Subject: media: v4l2-subdev: fix #endif comments Add comments after #endifs to clarify their scope. Signed-off-by: Tomi Valkeinen Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index 6c153b33bb04..a986fdd652e6 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -1023,7 +1023,7 @@ v4l2_subdev_get_try_compose(struct v4l2_subdev *sd, return &state->pads[pad].try_compose; } -#endif +#endif /* CONFIG_VIDEO_V4L2_SUBDEV_API */ extern const struct v4l2_file_operations v4l2_subdev_fops; @@ -1204,4 +1204,4 @@ extern const struct v4l2_subdev_ops v4l2_subdev_call_wrappers; void v4l2_subdev_notify_event(struct v4l2_subdev *sd, const struct v4l2_event *ev); -#endif +#endif /* _V4L2_SUBDEV_H */ -- cgit v1.2.3 From 40aaab9d773b07e9b106eac4256bb50fb1ba8cff Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Tue, 12 Apr 2022 10:42:42 +0100 Subject: media: subdev: rename subdev-state alloc & free v4l2_subdev_alloc_state() and v4l2_subdev_free_state() are not supposed to be used by the drivers. However, we do have a few drivers that use those at the moment, so we need to expose these functions for the time being. Prefix the functions with __ to mark the functions as internal. At the same time, rename them to v4l2_subdev_state_alloc and v4l2_subdev_state_free to match the style used for other functions like video_device_alloc() and media_request_alloc(). Signed-off-by: Tomi Valkeinen Reviewed-by: Laurent Pinchart Reviewed-by: Hans Verkuil Reviewed-by: Jacopo Mondi Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index a986fdd652e6..ac3bcc54ea07 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -1122,20 +1122,24 @@ int v4l2_subdev_link_validate_default(struct v4l2_subdev *sd, int v4l2_subdev_link_validate(struct media_link *link); /** - * v4l2_subdev_alloc_state - allocate v4l2_subdev_state + * __v4l2_subdev_state_alloc - allocate v4l2_subdev_state * * @sd: pointer to &struct v4l2_subdev for which the state is being allocated. * - * Must call v4l2_subdev_free_state() when state is no longer needed. + * Must call __v4l2_subdev_state_free() when state is no longer needed. + * + * Not to be called directly by the drivers. */ -struct v4l2_subdev_state *v4l2_subdev_alloc_state(struct v4l2_subdev *sd); +struct v4l2_subdev_state *__v4l2_subdev_state_alloc(struct v4l2_subdev *sd); /** - * v4l2_subdev_free_state - free a v4l2_subdev_state + * __v4l2_subdev_state_free - free a v4l2_subdev_state * * @state: v4l2_subdev_state to be freed. + * + * Not to be called directly by the drivers. */ -void v4l2_subdev_free_state(struct v4l2_subdev_state *state); +void __v4l2_subdev_state_free(struct v4l2_subdev_state *state); #endif /* CONFIG_MEDIA_CONTROLLER */ -- cgit v1.2.3 From f69952a4dc1ef13b69497408fedbd12c7ceb294d Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Tue, 12 Apr 2022 10:42:43 +0100 Subject: media: subdev: add active state to struct v4l2_subdev Add a new 'active_state' field to struct v4l2_subdev to which we can store the active state of a subdev. This will place the subdev configuration into a known place, allowing us to use the state directly from the v4l2 framework, thus simplifying the drivers. Also add functions v4l2_subdev_init_finalize() and v4l2_subdev_cleanup(), which will allocate and free the active state. The functions are named in a generic way so that they can be also used for other subdev initialization work. Signed-off-by: Tomi Valkeinen Reviewed-by: Hans Verkuil Reviewed-by: Jacopo Mondi Reviewed-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 58 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 58 insertions(+) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index ac3bcc54ea07..d0d0e4caf893 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -645,6 +645,9 @@ struct v4l2_subdev_ir_ops { * This structure only needs to be passed to the pad op if the 'which' field * of the main argument is set to %V4L2_SUBDEV_FORMAT_TRY. For * %V4L2_SUBDEV_FORMAT_ACTIVE it is safe to pass %NULL. + * + * Note: This struct is also used in active state, and the 'try' prefix is + * historical and to be removed. */ struct v4l2_subdev_pad_config { struct v4l2_mbus_framefmt try_fmt; @@ -885,6 +888,9 @@ struct v4l2_subdev_platform_data { * @subdev_notifier: A sub-device notifier implicitly registered for the sub- * device using v4l2_async_register_subdev_sensor(). * @pdata: common part of subdevice platform data + * @active_state: Active state for the subdev (NULL for subdevs tracking the + * state internally). Initialized by calling + * v4l2_subdev_init_finalize(). * * Each instance of a subdev driver should create this struct, either * stand-alone or embedded in a larger struct. @@ -916,6 +922,19 @@ struct v4l2_subdev { struct v4l2_async_notifier *notifier; struct v4l2_async_notifier *subdev_notifier; struct v4l2_subdev_platform_data *pdata; + + /* + * The fields below are private, and should only be accessed via + * appropriate functions. + */ + + /* + * TODO: active_state should most likely be changed from a pointer to an + * embedded field. For the time being it's kept as a pointer to more + * easily catch uses of active_state in the cases where the driver + * doesn't support it. + */ + struct v4l2_subdev_state *active_state; }; @@ -1141,6 +1160,45 @@ struct v4l2_subdev_state *__v4l2_subdev_state_alloc(struct v4l2_subdev *sd); */ void __v4l2_subdev_state_free(struct v4l2_subdev_state *state); +/** + * v4l2_subdev_init_finalize() - Finalizes the initialization of the subdevice + * @sd: The subdev + * + * This function finalizes the initialization of the subdev, including + * allocation of the active state for the subdev. + * + * This function must be called by the subdev drivers that use the centralized + * active state, after the subdev struct has been initialized and + * media_entity_pads_init() has been called, but before registering the + * subdev. + * + * The user must call v4l2_subdev_cleanup() when the subdev is being removed. + */ +int v4l2_subdev_init_finalize(struct v4l2_subdev *sd); + +/** + * v4l2_subdev_cleanup() - Releases the resources allocated by the subdevice + * @sd: The subdevice + * + * This function will release the resources allocated in + * v4l2_subdev_init_finalize. + */ +void v4l2_subdev_cleanup(struct v4l2_subdev *sd); + +/** + * v4l2_subdev_get_active_state() - Returns the active subdev state for + * subdevice + * @sd: The subdevice + * + * Returns the active state for the subdevice, or NULL if the subdev does not + * support active state. + */ +static inline struct v4l2_subdev_state * +v4l2_subdev_get_active_state(struct v4l2_subdev *sd) +{ + return sd->active_state; +} + #endif /* CONFIG_MEDIA_CONTROLLER */ /** -- cgit v1.2.3 From 2f91838c3b717b4b0b5dab005a7e50d3933bbdcd Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Tue, 12 Apr 2022 10:42:44 +0100 Subject: media: subdev: rename v4l2_subdev_get_pad_* helpers The subdev state is now used for both try and active cases. Rename rename v4l2_subdev_get_try_* helpers to v4l2_subdev_get_pad_*. Temporary wapper helper macros are added to keep the drivers using v4l2_subdev_get_try_* compiling. The next step is to change the uses in th drivers, and then drop the helpers. Signed-off-by: Tomi Valkeinen Reviewed-by: Hans Verkuil Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index d0d0e4caf893..eab8e4342613 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -989,7 +989,7 @@ struct v4l2_subdev_fh { #if defined(CONFIG_VIDEO_V4L2_SUBDEV_API) /** - * v4l2_subdev_get_try_format - ancillary routine to call + * v4l2_subdev_get_pad_format - ancillary routine to call * &struct v4l2_subdev_pad_config->try_fmt * * @sd: pointer to &struct v4l2_subdev @@ -997,7 +997,7 @@ struct v4l2_subdev_fh { * @pad: index of the pad in the &struct v4l2_subdev_state->pads array */ static inline struct v4l2_mbus_framefmt * -v4l2_subdev_get_try_format(struct v4l2_subdev *sd, +v4l2_subdev_get_pad_format(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, unsigned int pad) { @@ -1007,7 +1007,7 @@ v4l2_subdev_get_try_format(struct v4l2_subdev *sd, } /** - * v4l2_subdev_get_try_crop - ancillary routine to call + * v4l2_subdev_get_pad_crop - ancillary routine to call * &struct v4l2_subdev_pad_config->try_crop * * @sd: pointer to &struct v4l2_subdev @@ -1015,7 +1015,7 @@ v4l2_subdev_get_try_format(struct v4l2_subdev *sd, * @pad: index of the pad in the &struct v4l2_subdev_state->pads array. */ static inline struct v4l2_rect * -v4l2_subdev_get_try_crop(struct v4l2_subdev *sd, +v4l2_subdev_get_pad_crop(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, unsigned int pad) { @@ -1025,7 +1025,7 @@ v4l2_subdev_get_try_crop(struct v4l2_subdev *sd, } /** - * v4l2_subdev_get_try_compose - ancillary routine to call + * v4l2_subdev_get_pad_compose - ancillary routine to call * &struct v4l2_subdev_pad_config->try_compose * * @sd: pointer to &struct v4l2_subdev @@ -1033,7 +1033,7 @@ v4l2_subdev_get_try_crop(struct v4l2_subdev *sd, * @pad: index of the pad in the &struct v4l2_subdev_state->pads array. */ static inline struct v4l2_rect * -v4l2_subdev_get_try_compose(struct v4l2_subdev *sd, +v4l2_subdev_get_pad_compose(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, unsigned int pad) { @@ -1042,6 +1042,19 @@ v4l2_subdev_get_try_compose(struct v4l2_subdev *sd, return &state->pads[pad].try_compose; } +/* + * Temprary helpers until uses of v4l2_subdev_get_try_* functions have been + * renamed + */ +#define v4l2_subdev_get_try_format(sd, state, pad) \ + v4l2_subdev_get_pad_format(sd, state, pad) + +#define v4l2_subdev_get_try_crop(sd, state, pad) \ + v4l2_subdev_get_pad_crop(sd, state, pad) + +#define v4l2_subdev_get_try_compose(sd, state, pad) \ + v4l2_subdev_get_pad_compose(sd, state, pad) + #endif /* CONFIG_VIDEO_V4L2_SUBDEV_API */ extern const struct v4l2_file_operations v4l2_subdev_fops; -- cgit v1.2.3 From ed647ea668fb27cd21408d5cb7cc7d4c30417332 Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Tue, 12 Apr 2022 10:42:46 +0100 Subject: media: subdev: add subdev state locking The V4L2 subdevs have managed without centralized locking for the state (previously pad_config), as the try-state is supposedly safe (although I believe two TRY ioctls for the same fd would race), and the active-state, and its locking, is managed by the drivers internally. We now have active-state in a centralized position, and need locking. Strictly speaking the locking is only needed for new drivers that use the new state, as the current drivers continue behaving as they used to. However, active-state locking is complicated by the fact that currently the real active-state of a subdev is split into multiple parts: the new v4l2_subdev_state, subdev control state, and subdev's internal state. In the future all these three states should be combined into one state (the v4l2_subdev_state), and then a single lock for the state should be sufficient. But to solve the current split-state situation we need to share locks between the three states. This is accomplished by using the same lock management as the control handler does: we use a pointer to a mutex, allowing the driver to override the default mutex. Thus the driver can do e.g.: sd->state_lock = sd->ctrl_handler->lock; before calling v4l2_subdev_init_finalize(), resulting in sharing the same lock between the states and the controls. The locking model for active-state is such that any subdev op that gets the state as a parameter expects the state to be already locked by the caller, and expects the caller to release the lock. Signed-off-by: Tomi Valkeinen Reviewed-by: Laurent Pinchart Reviewed-by: Hans Verkuil Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 133 ++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 127 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index eab8e4342613..f967c27e41c3 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -658,6 +658,8 @@ struct v4l2_subdev_pad_config { /** * struct v4l2_subdev_state - Used for storing subdev state information. * + * @_lock: default for 'lock' + * @lock: mutex for the state. May be replaced by the user. * @pads: &struct v4l2_subdev_pad_config array * * This structure only needs to be passed to the pad op if the 'which' field @@ -665,6 +667,9 @@ struct v4l2_subdev_pad_config { * %V4L2_SUBDEV_FORMAT_ACTIVE it is safe to pass %NULL. */ struct v4l2_subdev_state { + /* lock for the struct v4l2_subdev_state fields */ + struct mutex _lock; + struct mutex *lock; struct v4l2_subdev_pad_config *pads; }; @@ -888,6 +893,9 @@ struct v4l2_subdev_platform_data { * @subdev_notifier: A sub-device notifier implicitly registered for the sub- * device using v4l2_async_register_subdev_sensor(). * @pdata: common part of subdevice platform data + * @state_lock: A pointer to a lock used for all the subdev's states, set by the + * driver. This is optional. If NULL, each state instance will get + * a lock of its own. * @active_state: Active state for the subdev (NULL for subdevs tracking the * state internally). Initialized by calling * v4l2_subdev_init_finalize(). @@ -922,6 +930,7 @@ struct v4l2_subdev { struct v4l2_async_notifier *notifier; struct v4l2_async_notifier *subdev_notifier; struct v4l2_subdev_platform_data *pdata; + struct mutex *state_lock; /* * The fields below are private, and should only be accessed via @@ -1157,12 +1166,16 @@ int v4l2_subdev_link_validate(struct media_link *link); * __v4l2_subdev_state_alloc - allocate v4l2_subdev_state * * @sd: pointer to &struct v4l2_subdev for which the state is being allocated. + * @lock_name: name of the state lock + * @key: lock_class_key for the lock * * Must call __v4l2_subdev_state_free() when state is no longer needed. * * Not to be called directly by the drivers. */ -struct v4l2_subdev_state *__v4l2_subdev_state_alloc(struct v4l2_subdev *sd); +struct v4l2_subdev_state *__v4l2_subdev_state_alloc(struct v4l2_subdev *sd, + const char *lock_name, + struct lock_class_key *key); /** * __v4l2_subdev_state_free - free a v4l2_subdev_state @@ -1187,7 +1200,16 @@ void __v4l2_subdev_state_free(struct v4l2_subdev_state *state); * * The user must call v4l2_subdev_cleanup() when the subdev is being removed. */ -int v4l2_subdev_init_finalize(struct v4l2_subdev *sd); +#define v4l2_subdev_init_finalize(sd) \ + ({ \ + static struct lock_class_key __key; \ + const char *name = KBUILD_BASENAME \ + ":" __stringify(__LINE__) ":sd->active_state->lock"; \ + __v4l2_subdev_init_finalize(sd, name, &__key); \ + }) + +int __v4l2_subdev_init_finalize(struct v4l2_subdev *sd, const char *name, + struct lock_class_key *key); /** * v4l2_subdev_cleanup() - Releases the resources allocated by the subdevice @@ -1199,16 +1221,85 @@ int v4l2_subdev_init_finalize(struct v4l2_subdev *sd); void v4l2_subdev_cleanup(struct v4l2_subdev *sd); /** - * v4l2_subdev_get_active_state() - Returns the active subdev state for - * subdevice + * v4l2_subdev_lock_state() - Locks the subdev state + * @state: The subdevice state + * + * Locks the given subdev state. + * + * The state must be unlocked with v4l2_subdev_unlock_state() after use. + */ +static inline void v4l2_subdev_lock_state(struct v4l2_subdev_state *state) +{ + mutex_lock(state->lock); +} + +/** + * v4l2_subdev_unlock_state() - Unlocks the subdev state + * @state: The subdevice state + * + * Unlocks the given subdev state. + */ +static inline void v4l2_subdev_unlock_state(struct v4l2_subdev_state *state) +{ + mutex_unlock(state->lock); +} + +/** + * v4l2_subdev_get_unlocked_active_state() - Checks that the active subdev state + * is unlocked and returns it + * @sd: The subdevice + * + * Returns the active state for the subdevice, or NULL if the subdev does not + * support active state. If the state is not NULL, calls + * lockdep_assert_not_held() to issue a warning if the state is locked. + * + * This function is to be used e.g. when getting the active state for the sole + * purpose of passing it forward, without accessing the state fields. + */ +static inline struct v4l2_subdev_state * +v4l2_subdev_get_unlocked_active_state(struct v4l2_subdev *sd) +{ + if (sd->active_state) + lockdep_assert_not_held(sd->active_state->lock); + return sd->active_state; +} + +/** + * v4l2_subdev_get_locked_active_state() - Checks that the active subdev state + * is locked and returns it + * * @sd: The subdevice * * Returns the active state for the subdevice, or NULL if the subdev does not - * support active state. + * support active state. If the state is not NULL, calls lockdep_assert_held() + * to issue a warning if the state is not locked. + * + * This function is to be used when the caller knows that the active state is + * already locked. + */ +static inline struct v4l2_subdev_state * +v4l2_subdev_get_locked_active_state(struct v4l2_subdev *sd) +{ + if (sd->active_state) + lockdep_assert_held(sd->active_state->lock); + return sd->active_state; +} + +/** + * v4l2_subdev_lock_and_get_active_state() - Locks and returns the active subdev + * state for the subdevice + * @sd: The subdevice + * + * Returns the locked active state for the subdevice, or NULL if the subdev + * does not support active state. + * + * The state must be unlocked with v4l2_subdev_unlock_state() after use. */ static inline struct v4l2_subdev_state * -v4l2_subdev_get_active_state(struct v4l2_subdev *sd) +v4l2_subdev_lock_and_get_active_state(struct v4l2_subdev *sd) { + if (sd->active_state) + v4l2_subdev_lock_state(sd->active_state); return sd->active_state; } @@ -1255,6 +1346,36 @@ extern const struct v4l2_subdev_ops v4l2_subdev_call_wrappers; __result; \ }) +/** + * v4l2_subdev_call_state_active - call an operation of a v4l2_subdev which + * takes state as a parameter, passing the + * subdev its active state. + * + * @sd: pointer to the &struct v4l2_subdev + * @o: name of the element at &struct v4l2_subdev_ops that contains @f. + * Each element there groups a set of callbacks functions. + * @f: callback function to be called. + * The callback functions are defined in groups, according to + * each element at &struct v4l2_subdev_ops. + * @args: arguments for @f. + * + * This is similar to v4l2_subdev_call(), except that this version can only be + * used for ops that take a subdev state as a parameter. The macro will get the + * active state, lock it before calling the op and unlock it after the call. + */ +#define v4l2_subdev_call_state_active(sd, o, f, args...) \ + ({ \ + int __result; \ + struct v4l2_subdev_state *state; \ + state = v4l2_subdev_get_unlocked_active_state(sd); \ + if (state) \ + v4l2_subdev_lock_state(state); \ + __result = v4l2_subdev_call(sd, o, f, state, ##args); \ + if (state) \ + v4l2_subdev_unlock_state(state); \ + __result; \ + }) + /** * v4l2_subdev_has_op - Checks if a subdev defines a certain operation. * -- cgit v1.2.3 From 14a6fca77ad122208a6db10e2abda2d7369c48a4 Mon Sep 17 00:00:00 2001 From: Tomi Valkeinen Date: Tue, 12 Apr 2022 10:42:48 +0100 Subject: media: subdev: add v4l2_subdev_get_fmt() helper function Add v4l2_subdev_get_fmt() helper function which implements v4l2_subdev_pad_ops.get_fmt using active state. Subdev drivers that support active state and do not need to do anything special in their get_fmt op can use this helper directly for v4l2_subdev_pad_ops.get_fmt. Signed-off-by: Tomi Valkeinen Reviewed-by: Hans Verkuil Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index f967c27e41c3..33a7201edb61 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -1303,6 +1303,27 @@ v4l2_subdev_lock_and_get_active_state(struct v4l2_subdev *sd) return sd->active_state; } +#if defined(CONFIG_VIDEO_V4L2_SUBDEV_API) + +/** + * v4l2_subdev_get_fmt() - Fill format based on state + * @sd: subdevice + * @state: subdevice state + * @format: pointer to &struct v4l2_subdev_format + * + * Fill @format->format field based on the information in the @format struct. + * + * This function can be used by the subdev drivers which support active state to + * implement v4l2_subdev_pad_ops.get_fmt if the subdev driver does not need to + * do anything special in their get_fmt op. + * + * Returns 0 on success, error value otherwise. + */ +int v4l2_subdev_get_fmt(struct v4l2_subdev *sd, struct v4l2_subdev_state *state, + struct v4l2_subdev_format *format); + +#endif /* CONFIG_VIDEO_V4L2_SUBDEV_API */ + #endif /* CONFIG_MEDIA_CONTROLLER */ /** -- cgit v1.2.3 From 4d19e0662fcc9e2f3bdada2c4e45dab36bd64a71 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Sun, 13 Mar 2022 16:04:57 +0000 Subject: media: i2c: cleanup comments For spdx, remove leading space Replacements parametrize to parameterize Signed-off-by: Tom Rix Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/i2c/mt9t112.h | 2 +- include/media/i2c/wm8775.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/i2c/mt9t112.h b/include/media/i2c/mt9t112.h index e678b6ae8e2f..825b4a169da8 100644 --- a/include/media/i2c/mt9t112.h +++ b/include/media/i2c/mt9t112.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0 */ /* mt9t112 Camera * * Copyright (C) 2009 Renesas Solutions Corp. diff --git a/include/media/i2c/wm8775.h b/include/media/i2c/wm8775.h index 83675817639e..6ccdeb3817ab 100644 --- a/include/media/i2c/wm8775.h +++ b/include/media/i2c/wm8775.h @@ -23,7 +23,7 @@ struct wm8775_platform_data { /* - * FIXME: Instead, we should parametrize the params + * FIXME: Instead, we should parameterize the params * that need different settings between ivtv, pvrusb2, and Nova-S */ bool is_nova_s; -- cgit v1.2.3 From 3d22dd432889f2f538b53f36f9f6bcd54825fc22 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 28 Mar 2022 17:01:53 +0100 Subject: media: media.h: remove unneeded inclusion Commit b3b7a9f138b7 ("[media] media-device: Use u64 ints for pointers") added this #include , presumably in order to use uintptr_t. Now that it is gone, we can compile this for userspace without . Signed-off-by: Masahiro Yamada Reviewed-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/media.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index afbae7213d35..3ddadaea849f 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -20,9 +20,6 @@ #ifndef __LINUX_MEDIA_H #define __LINUX_MEDIA_H -#ifndef __KERNEL__ -#include -#endif #include #include -- cgit v1.2.3 From 3c9b04d9631ef49e8b3aad72607b09099c18e40d Mon Sep 17 00:00:00 2001 From: Ian Jamison Date: Fri, 8 Apr 2022 18:53:45 +0100 Subject: media: media-entity.h: Fix documentation for media_create_intf_link The documentation comment was inserted between the return type and the function name. Reunite the lines. Signed-off-by: Ian Jamison Fixes: db7ee32aa185 ("[media] media-device.h: Improve documentation and update it") Reviewed-by: Kieran Bingham Reviewed-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/media-entity.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/media-entity.h b/include/media/media-entity.h index 1d13b8939a11..a9a1c0ec5d1c 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -1030,7 +1030,6 @@ __must_check media_devnode_create(struct media_device *mdev, * removed. */ void media_devnode_remove(struct media_intf_devnode *devnode); -struct media_link * /** * media_create_intf_link() - creates a link between an entity and an interface @@ -1061,6 +1060,7 @@ struct media_link * * the interface and media_device_register_entity() should be called for the * interface that will be part of the link. */ +struct media_link * __must_check media_create_intf_link(struct media_entity *entity, struct media_interface *intf, u32 flags); -- cgit v1.2.3 From 2308d5aff8d083a44aa02197d2f5687b73d98f82 Mon Sep 17 00:00:00 2001 From: Stanimir Varbanov Date: Thu, 3 Mar 2022 15:06:31 +0000 Subject: media: v4l: Add Qualcomm custom compressed pixel formats Add custom Qualcomm raw compressed pixel formats. They are used in Qualcomm SoCs to optimize the interconnect bandwidth. Signed-off-by: Stanimir Varbanov Acked-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 3768a0a80830..6d465dc443b7 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -746,6 +746,8 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_INZI v4l2_fourcc('I', 'N', 'Z', 'I') /* Intel Planar Greyscale 10-bit and Depth 16-bit */ #define V4L2_PIX_FMT_CNF4 v4l2_fourcc('C', 'N', 'F', '4') /* Intel 4-bit packed depth confidence information */ #define V4L2_PIX_FMT_HI240 v4l2_fourcc('H', 'I', '2', '4') /* BTTV 8-bit dithered RGB */ +#define V4L2_PIX_FMT_QC08C v4l2_fourcc('Q', '0', '8', 'C') /* Qualcomm 8-bit compressed */ +#define V4L2_PIX_FMT_QC10C v4l2_fourcc('Q', '1', '0', 'C') /* Qualcomm 10-bit compressed */ /* 10bit raw bayer packed, 32 bytes for every 25 pixels, last LSB 6 bits unused */ #define V4L2_PIX_FMT_IPU3_SBGGR10 v4l2_fourcc('i', 'p', '3', 'b') /* IPU3 packed 10-bit BGGR bayer */ -- cgit v1.2.3 From fcbc4acf8b8dff5fc420a14026bd4ab1798cf465 Mon Sep 17 00:00:00 2001 From: Dikshita Agarwal Date: Tue, 19 Apr 2022 06:06:42 +0100 Subject: media: v4l2-ctrls: Add intra-refresh type control Add a control to set intra-refresh type. Signed-off-by: Dikshita Agarwal Reviewed-by: Nicolas Dufresne Acked-by: Hans Verkuil Signed-off-by: Stanimir Varbanov Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/v4l2-controls.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index bb40129446d4..dfff69ed88f7 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -449,6 +449,11 @@ enum v4l2_mpeg_video_multi_slice_mode { #define V4L2_CID_MPEG_VIDEO_USE_LTR_FRAMES (V4L2_CID_CODEC_BASE+234) #define V4L2_CID_MPEG_VIDEO_DEC_CONCEAL_COLOR (V4L2_CID_CODEC_BASE+235) #define V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD (V4L2_CID_CODEC_BASE+236) +#define V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD_TYPE (V4L2_CID_CODEC_BASE+237) +enum v4l2_mpeg_video_intra_refresh_period_type { + V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD_TYPE_RANDOM = 0, + V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD_TYPE_CYCLIC = 1, +}; /* CIDs for the MPEG-2 Part 2 (H.262) codec */ #define V4L2_CID_MPEG_VIDEO_MPEG2_LEVEL (V4L2_CID_CODEC_BASE+270) -- cgit v1.2.3 From 8e29da69feade64ec7fe9e1a2824b967c5183a21 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 18 Apr 2022 10:44:00 -0600 Subject: io_uring: add support for IORING_ASYNC_CANCEL_ALL The current cancelation will lookup and cancel the first request it finds based on the key passed in. Add a flag that allows to cancel any request that matches they key. It completes with the number of requests found and canceled, or res < 0 if an error occured. Signed-off-by: Jens Axboe Link: https://lore.kernel.org/r/20220418164402.75259-4-axboe@kernel.dk --- include/uapi/linux/io_uring.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 1845cf7c80ba..476e58a2837f 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -187,6 +187,13 @@ enum { #define IORING_POLL_UPDATE_EVENTS (1U << 1) #define IORING_POLL_UPDATE_USER_DATA (1U << 2) +/* + * ASYNC_CANCEL flags. + * + * IORING_ASYNC_CANCEL_ALL Cancel all requests that match the given key + */ +#define IORING_ASYNC_CANCEL_ALL (1U << 0) + /* * IO completion data structure (Completion Queue Entry) */ -- cgit v1.2.3 From 4bf94615b8886305199ed5755cb72fea88258d15 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 18 Apr 2022 10:44:01 -0600 Subject: io_uring: allow IORING_OP_ASYNC_CANCEL with 'fd' key Currently sqe->addr must contain the user_data of the request being canceled. Introduce the IORING_ASYNC_CANCEL_FD flag, which tells the kernel that we're keying off the file fd instead for cancelation. This allows canceling any request that a) uses a file, and b) was assigned the file based on the value being passed in. Signed-off-by: Jens Axboe Link: https://lore.kernel.org/r/20220418164402.75259-5-axboe@kernel.dk --- include/uapi/linux/io_uring.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 476e58a2837f..cc7fe82a1798 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -191,8 +191,11 @@ enum { * ASYNC_CANCEL flags. * * IORING_ASYNC_CANCEL_ALL Cancel all requests that match the given key + * IORING_ASYNC_CANCEL_FD Key off 'fd' for cancelation rather than the + * request 'user_data' */ #define IORING_ASYNC_CANCEL_ALL (1U << 0) +#define IORING_ASYNC_CANCEL_FD (1U << 1) /* * IO completion data structure (Completion Queue Entry) -- cgit v1.2.3 From 970f256edb8c1259c8ed48d52b38215135396126 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 18 Apr 2022 10:44:02 -0600 Subject: io_uring: add support for IORING_ASYNC_CANCEL_ANY Rather than match on a specific key, be it user_data or file, allow canceling any request that we can lookup. Works like IORING_ASYNC_CANCEL_ALL in that it cancels multiple requests, but it doesn't key off user_data or the file. Can't be set with IORING_ASYNC_CANCEL_FD, as that's a key selector. Only one may be used at the time. Signed-off-by: Jens Axboe Link: https://lore.kernel.org/r/20220418164402.75259-6-axboe@kernel.dk Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index cc7fe82a1798..980d82eb196e 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -193,9 +193,11 @@ enum { * IORING_ASYNC_CANCEL_ALL Cancel all requests that match the given key * IORING_ASYNC_CANCEL_FD Key off 'fd' for cancelation rather than the * request 'user_data' + * IORING_ASYNC_CANCEL_ANY Match any request */ #define IORING_ASYNC_CANCEL_ALL (1U << 0) #define IORING_ASYNC_CANCEL_FD (1U << 1) +#define IORING_ASYNC_CANCEL_ANY (1U << 2) /* * IO completion data structure (Completion Queue Entry) -- cgit v1.2.3 From 47894438e916ca3fe44db33c2d4a1670fd296d6f Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Thu, 21 Apr 2022 02:13:40 -0700 Subject: io_uring: add trace support for CQE overflow Add trace function for overflowing CQ ring. Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220421091345.2115755-2-dylany@fb.com Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 42 ++++++++++++++++++++++++++++++++++++++++- 1 file changed, 41 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index cddf5b6fbeb4..42534ec2ab9d 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -530,7 +530,7 @@ TRACE_EVENT(io_uring_req_failed, ), TP_printk("ring %p, req %p, user_data 0x%llx, " - "op %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, " + "op %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, " "len=%u, rw_flags=0x%x, buf_index=%d, " "personality=%d, file_index=%d, pad=0x%llx/%llx, error=%d", __entry->ctx, __entry->req, __entry->user_data, @@ -543,6 +543,46 @@ TRACE_EVENT(io_uring_req_failed, (unsigned long long) __entry->pad2, __entry->error) ); + +/* + * io_uring_cqe_overflow - a CQE overflowed + * + * @ctx: pointer to a ring context structure + * @user_data: user data associated with the request + * @res: CQE result + * @cflags: CQE flags + * @ocqe: pointer to the overflow cqe (if available) + * + */ +TRACE_EVENT(io_uring_cqe_overflow, + + TP_PROTO(void *ctx, unsigned long long user_data, s32 res, u32 cflags, + void *ocqe), + + TP_ARGS(ctx, user_data, res, cflags, ocqe), + + TP_STRUCT__entry ( + __field( void *, ctx ) + __field( unsigned long long, user_data ) + __field( s32, res ) + __field( u32, cflags ) + __field( void *, ocqe ) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->user_data = user_data; + __entry->res = res; + __entry->cflags = cflags; + __entry->ocqe = ocqe; + ), + + TP_printk("ring %p, user_data 0x%llx, res %d, flags %x, " + "overflow_cqe %p", + __entry->ctx, __entry->user_data, __entry->res, + __entry->cflags, __entry->ocqe) +); + #endif /* _TRACE_IO_URING_H */ /* This part must be outside protection */ -- cgit v1.2.3 From e9621e2bec80fe63f677a759066a5089b292f43a Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Wed, 23 Mar 2022 08:44:19 -0700 Subject: io_uring: add fsetxattr and setxattr support This adds support to io_uring for the fsetxattr and setxattr API. Signed-off-by: Stefan Roesch Acked-by: Christian Brauner Link: https://lore.kernel.org/r/20220323154420.3301504-4-shr@fb.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 980d82eb196e..864bd6a4d4ff 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -45,6 +45,7 @@ struct io_uring_sqe { __u32 rename_flags; __u32 unlink_flags; __u32 hardlink_flags; + __u32 xattr_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -60,7 +61,8 @@ struct io_uring_sqe { __s32 splice_fd_in; __u32 file_index; }; - __u64 __pad2[2]; + __u64 addr3; + __u64 __pad2[1]; }; enum { @@ -145,6 +147,8 @@ enum { IORING_OP_SYMLINKAT, IORING_OP_LINKAT, IORING_OP_MSG_RING, + IORING_OP_FSETXATTR, + IORING_OP_SETXATTR, /* this goes last, obviously */ IORING_OP_LAST, -- cgit v1.2.3 From a56834e0fafe0adf7f22a28a5dbec3e8c3031a0e Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Wed, 23 Mar 2022 08:44:20 -0700 Subject: io_uring: add fgetxattr and getxattr support This adds support to io_uring for the fgetxattr and getxattr API. Signed-off-by: Stefan Roesch Acked-by: Christian Brauner Link: https://lore.kernel.org/r/20220323154420.3301504-5-shr@fb.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 864bd6a4d4ff..8ca1d9ae56d6 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -149,6 +149,8 @@ enum { IORING_OP_MSG_RING, IORING_OP_FSETXATTR, IORING_OP_SETXATTR, + IORING_OP_FGETXATTR, + IORING_OP_GETXATTR, /* this goes last, obviously */ IORING_OP_LAST, -- cgit v1.2.3 From 0200ce6a57c5de802f4e438485c14cc9d63d5f4b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 24 Apr 2022 18:16:57 -0600 Subject: io_uring: fix trace for reduced sqe padding __pad2 is only 1 u64 now, the other one is addr3. Adjust the trace so that it matches up. Fixes: a56834e0fafe ("io_uring: add fgetxattr and getxattr support") Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 42534ec2ab9d..05b786f8b0bf 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -506,7 +506,7 @@ TRACE_EVENT(io_uring_req_failed, __field( u16, personality ) __field( u32, file_index ) __field( u64, pad1 ) - __field( u64, pad2 ) + __field( u64, addr3 ) __field( int, error ) ), @@ -525,14 +525,15 @@ TRACE_EVENT(io_uring_req_failed, __entry->personality = sqe->personality; __entry->file_index = sqe->file_index; __entry->pad1 = sqe->__pad2[0]; - __entry->pad2 = sqe->__pad2[1]; + __entry->addr3 = sqe->addr3; __entry->error = error; ), TP_printk("ring %p, req %p, user_data 0x%llx, " "op %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, " "len=%u, rw_flags=0x%x, buf_index=%d, " - "personality=%d, file_index=%d, pad=0x%llx/%llx, error=%d", + "personality=%d, file_index=%d, pad=0x%llx, addr3=%llx, " + "error=%d", __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, __entry->flags, __entry->ioprio, (unsigned long long)__entry->off, @@ -540,7 +541,7 @@ TRACE_EVENT(io_uring_req_failed, __entry->op_flags, __entry->buf_index, __entry->personality, __entry->file_index, (unsigned long long) __entry->pad1, - (unsigned long long) __entry->pad2, __entry->error) + (unsigned long long) __entry->addr3, __entry->error) ); -- cgit v1.2.3 From da214a475f8bd1d3e9e7a19ddfeb4d1617551bab Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 12 Apr 2022 14:22:39 -0600 Subject: net: add __sys_socket_file() This works like __sys_socket(), except instead of allocating and returning a socket fd, it just returns the file associated with the socket. No fd is installed into the process file table. This is similar to do_accept(), and allows io_uring to use this without instantiating a file descriptor in the process file table. Signed-off-by: Jens Axboe Acked-by: David S. Miller Link: https://lore.kernel.org/r/20220412202240.234207-2-axboe@kernel.dk --- include/linux/socket.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/socket.h b/include/linux/socket.h index 6f85f5d957ef..a1882e1e71d2 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -434,6 +434,7 @@ extern struct file *do_accept(struct file *file, unsigned file_flags, extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_socket(int family, int type, int protocol); +extern struct file *__sys_socket_file(int family, int type, int protocol); extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen); extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr, int addrlen, int file_flags); -- cgit v1.2.3 From 1374e08e2d44863c931910797852589803997668 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 12 Apr 2022 14:22:40 -0600 Subject: io_uring: add socket(2) support Supports both regular socket(2) where a normal file descriptor is instantiated when called, or direct descriptors. Link: https://lore.kernel.org/r/20220412202240.234207-3-axboe@kernel.dk Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 8ca1d9ae56d6..5fb52bf32435 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -151,6 +151,7 @@ enum { IORING_OP_SETXATTR, IORING_OP_FGETXATTR, IORING_OP_GETXATTR, + IORING_OP_SOCKET, /* this goes last, obviously */ IORING_OP_LAST, -- cgit v1.2.3 From 90715507cb899df6c726494c0225d30130ad0cc5 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Mon, 25 Apr 2022 15:41:55 +0900 Subject: dt-bindings: power: Add r8a779g0 SYSC power domain definitions Add power domain indices for R-Car V4H (r8a779g0). Signed-off-by: Yoshihiro Shimoda Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220425064201.459633-2-yoshihiro.shimoda.uh@renesas.com Signed-off-by: Geert Uytterhoeven --- include/dt-bindings/power/r8a779g0-sysc.h | 45 +++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) create mode 100644 include/dt-bindings/power/r8a779g0-sysc.h (limited to 'include') diff --git a/include/dt-bindings/power/r8a779g0-sysc.h b/include/dt-bindings/power/r8a779g0-sysc.h new file mode 100644 index 000000000000..7daa70f1814e --- /dev/null +++ b/include/dt-bindings/power/r8a779g0-sysc.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (C) 2022 Renesas Electronics Corp. + */ +#ifndef __DT_BINDINGS_POWER_R8A779G0_SYSC_H__ +#define __DT_BINDINGS_POWER_R8A779G0_SYSC_H__ + +/* + * These power domain indices match the Power Domain Register Numbers (PDR) + */ + +#define R8A779G0_PD_A1E0D0C0 0 +#define R8A779G0_PD_A1E0D0C1 1 +#define R8A779G0_PD_A1E0D1C0 2 +#define R8A779G0_PD_A1E0D1C1 3 +#define R8A779G0_PD_A2E0D0 16 +#define R8A779G0_PD_A2E0D1 17 +#define R8A779G0_PD_A3E0 20 +#define R8A779G0_PD_A33DGA 24 +#define R8A779G0_PD_A23DGB 25 +#define R8A779G0_PD_A1DSP0 33 +#define R8A779G0_PD_A2IMP01 34 +#define R8A779G0_PD_A2PSC 35 +#define R8A779G0_PD_A2CV0 36 +#define R8A779G0_PD_A2CV1 37 +#define R8A779G0_PD_A1CNN0 41 +#define R8A779G0_PD_A2CN0 42 +#define R8A779G0_PD_A3IR 43 +#define R8A779G0_PD_A1DSP1 45 +#define R8A779G0_PD_A2IMP23 46 +#define R8A779G0_PD_A2DMA 47 +#define R8A779G0_PD_A2CV2 48 +#define R8A779G0_PD_A2CV3 49 +#define R8A779G0_PD_A1DSP2 53 +#define R8A779G0_PD_A1DSP3 54 +#define R8A779G0_PD_A3VIP0 56 +#define R8A779G0_PD_A3VIP1 57 +#define R8A779G0_PD_A3VIP2 58 +#define R8A779G0_PD_A3ISP0 60 +#define R8A779G0_PD_A3ISP1 61 + +/* Always-on power area */ +#define R8A779G0_PD_ALWAYS_ON 64 + +#endif /* __DT_BINDINGS_POWER_R8A779G0_SYSC_H__*/ -- cgit v1.2.3 From f2afa78d5a0c0b0b2461a5c532d7a84214a1b633 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Mon, 25 Apr 2022 15:41:56 +0900 Subject: dt-bindings: clock: Add r8a779g0 CPG Core Clock Definitions Add all Clock Pulse Generator Core Clock Outputs for the Renesas R-Car V4H (R8A779G0) SoC. Signed-off-by: Yoshihiro Shimoda Link: https://lore.kernel.org/r/20220425064201.459633-3-yoshihiro.shimoda.uh@renesas.com Signed-off-by: Geert Uytterhoeven --- include/dt-bindings/clock/r8a779g0-cpg-mssr.h | 90 +++++++++++++++++++++++++++ 1 file changed, 90 insertions(+) create mode 100644 include/dt-bindings/clock/r8a779g0-cpg-mssr.h (limited to 'include') diff --git a/include/dt-bindings/clock/r8a779g0-cpg-mssr.h b/include/dt-bindings/clock/r8a779g0-cpg-mssr.h new file mode 100644 index 000000000000..754c54a6eb06 --- /dev/null +++ b/include/dt-bindings/clock/r8a779g0-cpg-mssr.h @@ -0,0 +1,90 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (C) 2022 Renesas Electronics Corp. + */ +#ifndef __DT_BINDINGS_CLOCK_R8A779G0_CPG_MSSR_H__ +#define __DT_BINDINGS_CLOCK_R8A779G0_CPG_MSSR_H__ + +#include + +/* r8a779g0 CPG Core Clocks */ + +#define R8A779G0_CLK_ZX 0 +#define R8A779G0_CLK_ZS 1 +#define R8A779G0_CLK_ZT 2 +#define R8A779G0_CLK_ZTR 3 +#define R8A779G0_CLK_S0D2 4 +#define R8A779G0_CLK_S0D3 5 +#define R8A779G0_CLK_S0D4 6 +#define R8A779G0_CLK_S0D1_VIO 7 +#define R8A779G0_CLK_S0D2_VIO 8 +#define R8A779G0_CLK_S0D4_VIO 9 +#define R8A779G0_CLK_S0D8_VIO 10 +#define R8A779G0_CLK_S0D1_VC 11 +#define R8A779G0_CLK_S0D2_VC 12 +#define R8A779G0_CLK_S0D4_VC 13 +#define R8A779G0_CLK_S0D2_MM 14 +#define R8A779G0_CLK_S0D4_MM 15 +#define R8A779G0_CLK_S0D2_U3DG 16 +#define R8A779G0_CLK_S0D4_U3DG 17 +#define R8A779G0_CLK_S0D2_RT 18 +#define R8A779G0_CLK_S0D3_RT 19 +#define R8A779G0_CLK_S0D4_RT 20 +#define R8A779G0_CLK_S0D6_RT 21 +#define R8A779G0_CLK_S0D24_RT 22 +#define R8A779G0_CLK_S0D2_PER 23 +#define R8A779G0_CLK_S0D3_PER 24 +#define R8A779G0_CLK_S0D4_PER 25 +#define R8A779G0_CLK_S0D6_PER 26 +#define R8A779G0_CLK_S0D12_PER 27 +#define R8A779G0_CLK_S0D24_PER 28 +#define R8A779G0_CLK_S0D1_HSC 29 +#define R8A779G0_CLK_S0D2_HSC 30 +#define R8A779G0_CLK_S0D4_HSC 31 +#define R8A779G0_CLK_S0D2_CC 32 +#define R8A779G0_CLK_SVD1_IR 33 +#define R8A779G0_CLK_SVD2_IR 34 +#define R8A779G0_CLK_SVD1_VIP 35 +#define R8A779G0_CLK_SVD2_VIP 36 +#define R8A779G0_CLK_CL 37 +#define R8A779G0_CLK_CL16M 38 +#define R8A779G0_CLK_CL16M_MM 39 +#define R8A779G0_CLK_CL16M_RT 40 +#define R8A779G0_CLK_CL16M_PER 41 +#define R8A779G0_CLK_CL16M_HSC 42 +#define R8A779G0_CLK_Z0 43 +#define R8A779G0_CLK_ZB3 44 +#define R8A779G0_CLK_ZB3D2 45 +#define R8A779G0_CLK_ZB3D4 46 +#define R8A779G0_CLK_ZG 47 +#define R8A779G0_CLK_SD0H 48 +#define R8A779G0_CLK_SD0 49 +#define R8A779G0_CLK_RPC 50 +#define R8A779G0_CLK_RPCD2 51 +#define R8A779G0_CLK_MSO 52 +#define R8A779G0_CLK_CANFD 53 +#define R8A779G0_CLK_CSI 54 +#define R8A779G0_CLK_FRAY 55 +#define R8A779G0_CLK_IPC 56 +#define R8A779G0_CLK_SASYNCRT 57 +#define R8A779G0_CLK_SASYNCPERD1 58 +#define R8A779G0_CLK_SASYNCPERD2 59 +#define R8A779G0_CLK_SASYNCPERD4 60 +#define R8A779G0_CLK_VIOBUS 61 +#define R8A779G0_CLK_VIOBUSD2 62 +#define R8A779G0_CLK_VCBUS 63 +#define R8A779G0_CLK_VCBUSD2 64 +#define R8A779G0_CLK_DSIEXT 65 +#define R8A779G0_CLK_DSIREF 66 +#define R8A779G0_CLK_ADGH 67 +#define R8A779G0_CLK_OSC 68 +#define R8A779G0_CLK_ZR0 69 +#define R8A779G0_CLK_ZR1 70 +#define R8A779G0_CLK_ZR2 71 +#define R8A779G0_CLK_IMPA 72 +#define R8A779G0_CLK_IMPAD4 73 +#define R8A779G0_CLK_CPEX 74 +#define R8A779G0_CLK_CBFUSA 75 +#define R8A779G0_CLK_R 76 + +#endif /* __DT_BINDINGS_CLOCK_R8A779G0_CPG_MSSR_H__ */ -- cgit v1.2.3 From da68386d9edb1f57abf886febe5c5169ebd4d2c9 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 21 Apr 2022 09:31:02 +0200 Subject: drm: Rename dp/ to display/ Rename dp/ to display/ to account for additional display-related helpers, such as HDMI. Update all related include statements. No functional changes. Various drivers, such as i915 and amdgpu, use similar naming scheme by putting code for video-output standards into a local display/ directory. The new directory's name is aligned with this convention. v2: * update commit message (Javier) Signed-off-by: Thomas Zimmermann Reviewed-by: Lyude Paul Reviewed-by: Javier Martinez Canillas Reviewed-by: Alex Deucher Link: https://patchwork.freedesktop.org/patch/msgid/20220421073108.19226-3-tzimmermann@suse.de --- include/drm/display/drm_dp_aux_bus.h | 57 + include/drm/display/drm_dp_dual_mode_helper.h | 121 ++ include/drm/display/drm_dp_helper.h | 2380 +++++++++++++++++++++++++ include/drm/display/drm_dp_mst_helper.h | 972 ++++++++++ include/drm/dp/drm_dp_aux_bus.h | 57 - include/drm/dp/drm_dp_dual_mode_helper.h | 121 -- include/drm/dp/drm_dp_helper.h | 2380 ------------------------- include/drm/dp/drm_dp_mst_helper.h | 972 ---------- include/drm/drm_dsc.h | 2 +- 9 files changed, 3531 insertions(+), 3531 deletions(-) create mode 100644 include/drm/display/drm_dp_aux_bus.h create mode 100644 include/drm/display/drm_dp_dual_mode_helper.h create mode 100644 include/drm/display/drm_dp_helper.h create mode 100644 include/drm/display/drm_dp_mst_helper.h delete mode 100644 include/drm/dp/drm_dp_aux_bus.h delete mode 100644 include/drm/dp/drm_dp_dual_mode_helper.h delete mode 100644 include/drm/dp/drm_dp_helper.h delete mode 100644 include/drm/dp/drm_dp_mst_helper.h (limited to 'include') diff --git a/include/drm/display/drm_dp_aux_bus.h b/include/drm/display/drm_dp_aux_bus.h new file mode 100644 index 000000000000..4f19b20b1dd6 --- /dev/null +++ b/include/drm/display/drm_dp_aux_bus.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2021 Google Inc. + * + * The DP AUX bus is used for devices that are connected over a DisplayPort + * AUX bus. The devices on the far side of the bus are referred to as + * endpoints in this code. + */ + +#ifndef _DP_AUX_BUS_H_ +#define _DP_AUX_BUS_H_ + +#include +#include + +/** + * struct dp_aux_ep_device - Main dev structure for DP AUX endpoints + * + * This is used to instantiate devices that are connected via a DP AUX + * bus. Usually the device is a panel, but conceivable other devices could + * be hooked up there. + */ +struct dp_aux_ep_device { + /** @dev: The normal dev pointer */ + struct device dev; + /** @aux: Pointer to the aux bus */ + struct drm_dp_aux *aux; +}; + +struct dp_aux_ep_driver { + int (*probe)(struct dp_aux_ep_device *aux_ep); + void (*remove)(struct dp_aux_ep_device *aux_ep); + void (*shutdown)(struct dp_aux_ep_device *aux_ep); + struct device_driver driver; +}; + +static inline struct dp_aux_ep_device *to_dp_aux_ep_dev(struct device *dev) +{ + return container_of(dev, struct dp_aux_ep_device, dev); +} + +static inline struct dp_aux_ep_driver *to_dp_aux_ep_drv(struct device_driver *drv) +{ + return container_of(drv, struct dp_aux_ep_driver, driver); +} + +int of_dp_aux_populate_ep_devices(struct drm_dp_aux *aux); +void of_dp_aux_depopulate_ep_devices(struct drm_dp_aux *aux); +int devm_of_dp_aux_populate_ep_devices(struct drm_dp_aux *aux); + +#define dp_aux_dp_driver_register(aux_ep_drv) \ + __dp_aux_dp_driver_register(aux_ep_drv, THIS_MODULE) +int __dp_aux_dp_driver_register(struct dp_aux_ep_driver *aux_ep_drv, + struct module *owner); +void dp_aux_dp_driver_unregister(struct dp_aux_ep_driver *aux_ep_drv); + +#endif /* _DP_AUX_BUS_H_ */ diff --git a/include/drm/display/drm_dp_dual_mode_helper.h b/include/drm/display/drm_dp_dual_mode_helper.h new file mode 100644 index 000000000000..7ee482265087 --- /dev/null +++ b/include/drm/display/drm_dp_dual_mode_helper.h @@ -0,0 +1,121 @@ +/* + * Copyright © 2016 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#ifndef DRM_DP_DUAL_MODE_HELPER_H +#define DRM_DP_DUAL_MODE_HELPER_H + +#include + +/* + * Optional for type 1 DVI adaptors + * Mandatory for type 1 HDMI and type 2 adaptors + */ +#define DP_DUAL_MODE_HDMI_ID 0x00 /* 00-0f */ +#define DP_DUAL_MODE_HDMI_ID_LEN 16 +/* + * Optional for type 1 adaptors + * Mandatory for type 2 adaptors + */ +#define DP_DUAL_MODE_ADAPTOR_ID 0x10 +#define DP_DUAL_MODE_REV_MASK 0x07 +#define DP_DUAL_MODE_REV_TYPE2 0x00 +#define DP_DUAL_MODE_TYPE_MASK 0xf0 +#define DP_DUAL_MODE_TYPE_TYPE2 0xa0 +/* This field is marked reserved in dual mode spec, used in LSPCON */ +#define DP_DUAL_MODE_TYPE_HAS_DPCD 0x08 +#define DP_DUAL_MODE_IEEE_OUI 0x11 /* 11-13*/ +#define DP_DUAL_IEEE_OUI_LEN 3 +#define DP_DUAL_DEVICE_ID 0x14 /* 14-19 */ +#define DP_DUAL_DEVICE_ID_LEN 6 +#define DP_DUAL_MODE_HARDWARE_REV 0x1a +#define DP_DUAL_MODE_FIRMWARE_MAJOR_REV 0x1b +#define DP_DUAL_MODE_FIRMWARE_MINOR_REV 0x1c +#define DP_DUAL_MODE_MAX_TMDS_CLOCK 0x1d +#define DP_DUAL_MODE_I2C_SPEED_CAP 0x1e +#define DP_DUAL_MODE_TMDS_OEN 0x20 +#define DP_DUAL_MODE_TMDS_DISABLE 0x01 +#define DP_DUAL_MODE_HDMI_PIN_CTRL 0x21 +#define DP_DUAL_MODE_CEC_ENABLE 0x01 +#define DP_DUAL_MODE_I2C_SPEED_CTRL 0x22 + +/* LSPCON specific registers, defined by MCA */ +#define DP_DUAL_MODE_LSPCON_MODE_CHANGE 0x40 +#define DP_DUAL_MODE_LSPCON_CURRENT_MODE 0x41 +#define DP_DUAL_MODE_LSPCON_MODE_PCON 0x1 + +struct drm_device; +struct i2c_adapter; + +ssize_t drm_dp_dual_mode_read(struct i2c_adapter *adapter, + u8 offset, void *buffer, size_t size); +ssize_t drm_dp_dual_mode_write(struct i2c_adapter *adapter, + u8 offset, const void *buffer, size_t size); + +/** + * enum drm_lspcon_mode + * @DRM_LSPCON_MODE_INVALID: No LSPCON. + * @DRM_LSPCON_MODE_LS: Level shifter mode of LSPCON + * which drives DP++ to HDMI 1.4 conversion. + * @DRM_LSPCON_MODE_PCON: Protocol converter mode of LSPCON + * which drives DP++ to HDMI 2.0 active conversion. + */ +enum drm_lspcon_mode { + DRM_LSPCON_MODE_INVALID, + DRM_LSPCON_MODE_LS, + DRM_LSPCON_MODE_PCON, +}; + +/** + * enum drm_dp_dual_mode_type - Type of the DP dual mode adaptor + * @DRM_DP_DUAL_MODE_NONE: No DP dual mode adaptor + * @DRM_DP_DUAL_MODE_UNKNOWN: Could be either none or type 1 DVI adaptor + * @DRM_DP_DUAL_MODE_TYPE1_DVI: Type 1 DVI adaptor + * @DRM_DP_DUAL_MODE_TYPE1_HDMI: Type 1 HDMI adaptor + * @DRM_DP_DUAL_MODE_TYPE2_DVI: Type 2 DVI adaptor + * @DRM_DP_DUAL_MODE_TYPE2_HDMI: Type 2 HDMI adaptor + * @DRM_DP_DUAL_MODE_LSPCON: Level shifter / protocol converter + */ +enum drm_dp_dual_mode_type { + DRM_DP_DUAL_MODE_NONE, + DRM_DP_DUAL_MODE_UNKNOWN, + DRM_DP_DUAL_MODE_TYPE1_DVI, + DRM_DP_DUAL_MODE_TYPE1_HDMI, + DRM_DP_DUAL_MODE_TYPE2_DVI, + DRM_DP_DUAL_MODE_TYPE2_HDMI, + DRM_DP_DUAL_MODE_LSPCON, +}; + +enum drm_dp_dual_mode_type +drm_dp_dual_mode_detect(const struct drm_device *dev, struct i2c_adapter *adapter); +int drm_dp_dual_mode_max_tmds_clock(const struct drm_device *dev, enum drm_dp_dual_mode_type type, + struct i2c_adapter *adapter); +int drm_dp_dual_mode_get_tmds_output(const struct drm_device *dev, enum drm_dp_dual_mode_type type, + struct i2c_adapter *adapter, bool *enabled); +int drm_dp_dual_mode_set_tmds_output(const struct drm_device *dev, enum drm_dp_dual_mode_type type, + struct i2c_adapter *adapter, bool enable); +const char *drm_dp_get_dual_mode_type_name(enum drm_dp_dual_mode_type type); + +int drm_lspcon_get_mode(const struct drm_device *dev, struct i2c_adapter *adapter, + enum drm_lspcon_mode *current_mode); +int drm_lspcon_set_mode(const struct drm_device *dev, struct i2c_adapter *adapter, + enum drm_lspcon_mode reqd_mode); +#endif diff --git a/include/drm/display/drm_dp_helper.h b/include/drm/display/drm_dp_helper.h new file mode 100644 index 000000000000..91af98e6617c --- /dev/null +++ b/include/drm/display/drm_dp_helper.h @@ -0,0 +1,2380 @@ +/* + * Copyright © 2008 Keith Packard + * + * Permission to use, copy, modify, distribute, and sell this software and its + * documentation for any purpose is hereby granted without fee, provided that + * the above copyright notice appear in all copies and that both that copyright + * notice and this permission notice appear in supporting documentation, and + * that the name of the copyright holders not be used in advertising or + * publicity pertaining to distribution of the software without specific, + * written prior permission. The copyright holders make no representations + * about the suitability of this software for any purpose. It is provided "as + * is" without express or implied warranty. + * + * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, + * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO + * EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT OR + * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, + * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER + * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE + * OF THIS SOFTWARE. + */ + +#ifndef _DRM_DP_HELPER_H_ +#define _DRM_DP_HELPER_H_ + +#include +#include +#include +#include + +struct drm_device; +struct drm_dp_aux; +struct drm_panel; + +/* + * Unless otherwise noted, all values are from the DP 1.1a spec. Note that + * DP and DPCD versions are independent. Differences from 1.0 are not noted, + * 1.0 devices basically don't exist in the wild. + * + * Abbreviations, in chronological order: + * + * eDP: Embedded DisplayPort version 1 + * DPI: DisplayPort Interoperability Guideline v1.1a + * 1.2: DisplayPort 1.2 + * MST: Multistream Transport - part of DP 1.2a + * + * 1.2 formally includes both eDP and DPI definitions. + */ + +/* MSA (Main Stream Attribute) MISC bits (as MISC1<<8|MISC0) */ +#define DP_MSA_MISC_SYNC_CLOCK (1 << 0) +#define DP_MSA_MISC_INTERLACE_VTOTAL_EVEN (1 << 8) +#define DP_MSA_MISC_STEREO_NO_3D (0 << 9) +#define DP_MSA_MISC_STEREO_PROG_RIGHT_EYE (1 << 9) +#define DP_MSA_MISC_STEREO_PROG_LEFT_EYE (3 << 9) +/* bits per component for non-RAW */ +#define DP_MSA_MISC_6_BPC (0 << 5) +#define DP_MSA_MISC_8_BPC (1 << 5) +#define DP_MSA_MISC_10_BPC (2 << 5) +#define DP_MSA_MISC_12_BPC (3 << 5) +#define DP_MSA_MISC_16_BPC (4 << 5) +/* bits per component for RAW */ +#define DP_MSA_MISC_RAW_6_BPC (1 << 5) +#define DP_MSA_MISC_RAW_7_BPC (2 << 5) +#define DP_MSA_MISC_RAW_8_BPC (3 << 5) +#define DP_MSA_MISC_RAW_10_BPC (4 << 5) +#define DP_MSA_MISC_RAW_12_BPC (5 << 5) +#define DP_MSA_MISC_RAW_14_BPC (6 << 5) +#define DP_MSA_MISC_RAW_16_BPC (7 << 5) +/* pixel encoding/colorimetry format */ +#define _DP_MSA_MISC_COLOR(misc1_7, misc0_21, misc0_3, misc0_4) \ + ((misc1_7) << 15 | (misc0_4) << 4 | (misc0_3) << 3 | ((misc0_21) << 1)) +#define DP_MSA_MISC_COLOR_RGB _DP_MSA_MISC_COLOR(0, 0, 0, 0) +#define DP_MSA_MISC_COLOR_CEA_RGB _DP_MSA_MISC_COLOR(0, 0, 1, 0) +#define DP_MSA_MISC_COLOR_RGB_WIDE_FIXED _DP_MSA_MISC_COLOR(0, 3, 0, 0) +#define DP_MSA_MISC_COLOR_RGB_WIDE_FLOAT _DP_MSA_MISC_COLOR(0, 3, 0, 1) +#define DP_MSA_MISC_COLOR_Y_ONLY _DP_MSA_MISC_COLOR(1, 0, 0, 0) +#define DP_MSA_MISC_COLOR_RAW _DP_MSA_MISC_COLOR(1, 1, 0, 0) +#define DP_MSA_MISC_COLOR_YCBCR_422_BT601 _DP_MSA_MISC_COLOR(0, 1, 1, 0) +#define DP_MSA_MISC_COLOR_YCBCR_422_BT709 _DP_MSA_MISC_COLOR(0, 1, 1, 1) +#define DP_MSA_MISC_COLOR_YCBCR_444_BT601 _DP_MSA_MISC_COLOR(0, 2, 1, 0) +#define DP_MSA_MISC_COLOR_YCBCR_444_BT709 _DP_MSA_MISC_COLOR(0, 2, 1, 1) +#define DP_MSA_MISC_COLOR_XVYCC_422_BT601 _DP_MSA_MISC_COLOR(0, 1, 0, 0) +#define DP_MSA_MISC_COLOR_XVYCC_422_BT709 _DP_MSA_MISC_COLOR(0, 1, 0, 1) +#define DP_MSA_MISC_COLOR_XVYCC_444_BT601 _DP_MSA_MISC_COLOR(0, 2, 0, 0) +#define DP_MSA_MISC_COLOR_XVYCC_444_BT709 _DP_MSA_MISC_COLOR(0, 2, 0, 1) +#define DP_MSA_MISC_COLOR_OPRGB _DP_MSA_MISC_COLOR(0, 0, 1, 1) +#define DP_MSA_MISC_COLOR_DCI_P3 _DP_MSA_MISC_COLOR(0, 3, 1, 0) +#define DP_MSA_MISC_COLOR_COLOR_PROFILE _DP_MSA_MISC_COLOR(0, 3, 1, 1) +#define DP_MSA_MISC_COLOR_VSC_SDP (1 << 14) + +#define DP_AUX_MAX_PAYLOAD_BYTES 16 + +#define DP_AUX_I2C_WRITE 0x0 +#define DP_AUX_I2C_READ 0x1 +#define DP_AUX_I2C_WRITE_STATUS_UPDATE 0x2 +#define DP_AUX_I2C_MOT 0x4 +#define DP_AUX_NATIVE_WRITE 0x8 +#define DP_AUX_NATIVE_READ 0x9 + +#define DP_AUX_NATIVE_REPLY_ACK (0x0 << 0) +#define DP_AUX_NATIVE_REPLY_NACK (0x1 << 0) +#define DP_AUX_NATIVE_REPLY_DEFER (0x2 << 0) +#define DP_AUX_NATIVE_REPLY_MASK (0x3 << 0) + +#define DP_AUX_I2C_REPLY_ACK (0x0 << 2) +#define DP_AUX_I2C_REPLY_NACK (0x1 << 2) +#define DP_AUX_I2C_REPLY_DEFER (0x2 << 2) +#define DP_AUX_I2C_REPLY_MASK (0x3 << 2) + +/* DPCD Field Address Mapping */ + +/* Receiver Capability */ +#define DP_DPCD_REV 0x000 +# define DP_DPCD_REV_10 0x10 +# define DP_DPCD_REV_11 0x11 +# define DP_DPCD_REV_12 0x12 +# define DP_DPCD_REV_13 0x13 +# define DP_DPCD_REV_14 0x14 + +#define DP_MAX_LINK_RATE 0x001 + +#define DP_MAX_LANE_COUNT 0x002 +# define DP_MAX_LANE_COUNT_MASK 0x1f +# define DP_TPS3_SUPPORTED (1 << 6) /* 1.2 */ +# define DP_ENHANCED_FRAME_CAP (1 << 7) + +#define DP_MAX_DOWNSPREAD 0x003 +# define DP_MAX_DOWNSPREAD_0_5 (1 << 0) +# define DP_STREAM_REGENERATION_STATUS_CAP (1 << 1) /* 2.0 */ +# define DP_NO_AUX_HANDSHAKE_LINK_TRAINING (1 << 6) +# define DP_TPS4_SUPPORTED (1 << 7) + +#define DP_NORP 0x004 + +#define DP_DOWNSTREAMPORT_PRESENT 0x005 +# define DP_DWN_STRM_PORT_PRESENT (1 << 0) +# define DP_DWN_STRM_PORT_TYPE_MASK 0x06 +# define DP_DWN_STRM_PORT_TYPE_DP (0 << 1) +# define DP_DWN_STRM_PORT_TYPE_ANALOG (1 << 1) +# define DP_DWN_STRM_PORT_TYPE_TMDS (2 << 1) +# define DP_DWN_STRM_PORT_TYPE_OTHER (3 << 1) +# define DP_FORMAT_CONVERSION (1 << 3) +# define DP_DETAILED_CAP_INFO_AVAILABLE (1 << 4) /* DPI */ + +#define DP_MAIN_LINK_CHANNEL_CODING 0x006 +# define DP_CAP_ANSI_8B10B (1 << 0) +# define DP_CAP_ANSI_128B132B (1 << 1) /* 2.0 */ + +#define DP_DOWN_STREAM_PORT_COUNT 0x007 +# define DP_PORT_COUNT_MASK 0x0f +# define DP_MSA_TIMING_PAR_IGNORED (1 << 6) /* eDP */ +# define DP_OUI_SUPPORT (1 << 7) + +#define DP_RECEIVE_PORT_0_CAP_0 0x008 +# define DP_LOCAL_EDID_PRESENT (1 << 1) +# define DP_ASSOCIATED_TO_PRECEDING_PORT (1 << 2) + +#define DP_RECEIVE_PORT_0_BUFFER_SIZE 0x009 + +#define DP_RECEIVE_PORT_1_CAP_0 0x00a +#define DP_RECEIVE_PORT_1_BUFFER_SIZE 0x00b + +#define DP_I2C_SPEED_CAP 0x00c /* DPI */ +# define DP_I2C_SPEED_1K 0x01 +# define DP_I2C_SPEED_5K 0x02 +# define DP_I2C_SPEED_10K 0x04 +# define DP_I2C_SPEED_100K 0x08 +# define DP_I2C_SPEED_400K 0x10 +# define DP_I2C_SPEED_1M 0x20 + +#define DP_EDP_CONFIGURATION_CAP 0x00d /* XXX 1.2? */ +# define DP_ALTERNATE_SCRAMBLER_RESET_CAP (1 << 0) +# define DP_FRAMING_CHANGE_CAP (1 << 1) +# define DP_DPCD_DISPLAY_CONTROL_CAPABLE (1 << 3) /* edp v1.2 or higher */ + +#define DP_TRAINING_AUX_RD_INTERVAL 0x00e /* XXX 1.2? */ +# define DP_TRAINING_AUX_RD_MASK 0x7F /* DP 1.3 */ +# define DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT (1 << 7) /* DP 1.3 */ + +#define DP_ADAPTER_CAP 0x00f /* 1.2 */ +# define DP_FORCE_LOAD_SENSE_CAP (1 << 0) +# define DP_ALTERNATE_I2C_PATTERN_CAP (1 << 1) + +#define DP_SUPPORTED_LINK_RATES 0x010 /* eDP 1.4 */ +# define DP_MAX_SUPPORTED_RATES 8 /* 16-bit little-endian */ + +/* Multiple stream transport */ +#define DP_FAUX_CAP 0x020 /* 1.2 */ +# define DP_FAUX_CAP_1 (1 << 0) + +#define DP_SINK_VIDEO_FALLBACK_FORMATS 0x020 /* 2.0 */ +# define DP_FALLBACK_1024x768_60HZ_24BPP (1 << 0) +# define DP_FALLBACK_1280x720_60HZ_24BPP (1 << 1) +# define DP_FALLBACK_1920x1080_60HZ_24BPP (1 << 2) + +#define DP_MSTM_CAP 0x021 /* 1.2 */ +# define DP_MST_CAP (1 << 0) +# define DP_SINGLE_STREAM_SIDEBAND_MSG (1 << 1) /* 2.0 */ + +#define DP_NUMBER_OF_AUDIO_ENDPOINTS 0x022 /* 1.2 */ + +/* AV_SYNC_DATA_BLOCK 1.2 */ +#define DP_AV_GRANULARITY 0x023 +# define DP_AG_FACTOR_MASK (0xf << 0) +# define DP_AG_FACTOR_3MS (0 << 0) +# define DP_AG_FACTOR_2MS (1 << 0) +# define DP_AG_FACTOR_1MS (2 << 0) +# define DP_AG_FACTOR_500US (3 << 0) +# define DP_AG_FACTOR_200US (4 << 0) +# define DP_AG_FACTOR_100US (5 << 0) +# define DP_AG_FACTOR_10US (6 << 0) +# define DP_AG_FACTOR_1US (7 << 0) +# define DP_VG_FACTOR_MASK (0xf << 4) +# define DP_VG_FACTOR_3MS (0 << 4) +# define DP_VG_FACTOR_2MS (1 << 4) +# define DP_VG_FACTOR_1MS (2 << 4) +# define DP_VG_FACTOR_500US (3 << 4) +# define DP_VG_FACTOR_200US (4 << 4) +# define DP_VG_FACTOR_100US (5 << 4) + +#define DP_AUD_DEC_LAT0 0x024 +#define DP_AUD_DEC_LAT1 0x025 + +#define DP_AUD_PP_LAT0 0x026 +#define DP_AUD_PP_LAT1 0x027 + +#define DP_VID_INTER_LAT 0x028 + +#define DP_VID_PROG_LAT 0x029 + +#define DP_REP_LAT 0x02a + +#define DP_AUD_DEL_INS0 0x02b +#define DP_AUD_DEL_INS1 0x02c +#define DP_AUD_DEL_INS2 0x02d +/* End of AV_SYNC_DATA_BLOCK */ + +#define DP_RECEIVER_ALPM_CAP 0x02e /* eDP 1.4 */ +# define DP_ALPM_CAP (1 << 0) + +#define DP_SINK_DEVICE_AUX_FRAME_SYNC_CAP 0x02f /* eDP 1.4 */ +# define DP_AUX_FRAME_SYNC_CAP (1 << 0) + +#define DP_GUID 0x030 /* 1.2 */ + +#define DP_DSC_SUPPORT 0x060 /* DP 1.4 */ +# define DP_DSC_DECOMPRESSION_IS_SUPPORTED (1 << 0) + +#define DP_DSC_REV 0x061 +# define DP_DSC_MAJOR_MASK (0xf << 0) +# define DP_DSC_MINOR_MASK (0xf << 4) +# define DP_DSC_MAJOR_SHIFT 0 +# define DP_DSC_MINOR_SHIFT 4 + +#define DP_DSC_RC_BUF_BLK_SIZE 0x062 +# define DP_DSC_RC_BUF_BLK_SIZE_1 0x0 +# define DP_DSC_RC_BUF_BLK_SIZE_4 0x1 +# define DP_DSC_RC_BUF_BLK_SIZE_16 0x2 +# define DP_DSC_RC_BUF_BLK_SIZE_64 0x3 + +#define DP_DSC_RC_BUF_SIZE 0x063 + +#define DP_DSC_SLICE_CAP_1 0x064 +# define DP_DSC_1_PER_DP_DSC_SINK (1 << 0) +# define DP_DSC_2_PER_DP_DSC_SINK (1 << 1) +# define DP_DSC_4_PER_DP_DSC_SINK (1 << 3) +# define DP_DSC_6_PER_DP_DSC_SINK (1 << 4) +# define DP_DSC_8_PER_DP_DSC_SINK (1 << 5) +# define DP_DSC_10_PER_DP_DSC_SINK (1 << 6) +# define DP_DSC_12_PER_DP_DSC_SINK (1 << 7) + +#define DP_DSC_LINE_BUF_BIT_DEPTH 0x065 +# define DP_DSC_LINE_BUF_BIT_DEPTH_MASK (0xf << 0) +# define DP_DSC_LINE_BUF_BIT_DEPTH_9 0x0 +# define DP_DSC_LINE_BUF_BIT_DEPTH_10 0x1 +# define DP_DSC_LINE_BUF_BIT_DEPTH_11 0x2 +# define DP_DSC_LINE_BUF_BIT_DEPTH_12 0x3 +# define DP_DSC_LINE_BUF_BIT_DEPTH_13 0x4 +# define DP_DSC_LINE_BUF_BIT_DEPTH_14 0x5 +# define DP_DSC_LINE_BUF_BIT_DEPTH_15 0x6 +# define DP_DSC_LINE_BUF_BIT_DEPTH_16 0x7 +# define DP_DSC_LINE_BUF_BIT_DEPTH_8 0x8 + +#define DP_DSC_BLK_PREDICTION_SUPPORT 0x066 +# define DP_DSC_BLK_PREDICTION_IS_SUPPORTED (1 << 0) + +#define DP_DSC_MAX_BITS_PER_PIXEL_LOW 0x067 /* eDP 1.4 */ + +#define DP_DSC_MAX_BITS_PER_PIXEL_HI 0x068 /* eDP 1.4 */ +# define DP_DSC_MAX_BITS_PER_PIXEL_HI_MASK (0x3 << 0) +# define DP_DSC_MAX_BITS_PER_PIXEL_HI_SHIFT 8 + +#define DP_DSC_DEC_COLOR_FORMAT_CAP 0x069 +# define DP_DSC_RGB (1 << 0) +# define DP_DSC_YCbCr444 (1 << 1) +# define DP_DSC_YCbCr422_Simple (1 << 2) +# define DP_DSC_YCbCr422_Native (1 << 3) +# define DP_DSC_YCbCr420_Native (1 << 4) + +#define DP_DSC_DEC_COLOR_DEPTH_CAP 0x06A +# define DP_DSC_8_BPC (1 << 1) +# define DP_DSC_10_BPC (1 << 2) +# define DP_DSC_12_BPC (1 << 3) + +#define DP_DSC_PEAK_THROUGHPUT 0x06B +# define DP_DSC_THROUGHPUT_MODE_0_MASK (0xf << 0) +# define DP_DSC_THROUGHPUT_MODE_0_SHIFT 0 +# define DP_DSC_THROUGHPUT_MODE_0_UNSUPPORTED 0 +# define DP_DSC_THROUGHPUT_MODE_0_340 (1 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_400 (2 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_450 (3 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_500 (4 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_550 (5 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_600 (6 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_650 (7 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_700 (8 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_750 (9 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_800 (10 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_850 (11 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_900 (12 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_950 (13 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_1000 (14 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_170 (15 << 0) /* 1.4a */ +# define DP_DSC_THROUGHPUT_MODE_1_MASK (0xf << 4) +# define DP_DSC_THROUGHPUT_MODE_1_SHIFT 4 +# define DP_DSC_THROUGHPUT_MODE_1_UNSUPPORTED 0 +# define DP_DSC_THROUGHPUT_MODE_1_340 (1 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_400 (2 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_450 (3 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_500 (4 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_550 (5 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_600 (6 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_650 (7 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_700 (8 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_750 (9 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_800 (10 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_850 (11 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_900 (12 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_950 (13 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_1000 (14 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_170 (15 << 4) + +#define DP_DSC_MAX_SLICE_WIDTH 0x06C +#define DP_DSC_MIN_SLICE_WIDTH_VALUE 2560 +#define DP_DSC_SLICE_WIDTH_MULTIPLIER 320 + +#define DP_DSC_SLICE_CAP_2 0x06D +# define DP_DSC_16_PER_DP_DSC_SINK (1 << 0) +# define DP_DSC_20_PER_DP_DSC_SINK (1 << 1) +# define DP_DSC_24_PER_DP_DSC_SINK (1 << 2) + +#define DP_DSC_BITS_PER_PIXEL_INC 0x06F +# define DP_DSC_BITS_PER_PIXEL_1_16 0x0 +# define DP_DSC_BITS_PER_PIXEL_1_8 0x1 +# define DP_DSC_BITS_PER_PIXEL_1_4 0x2 +# define DP_DSC_BITS_PER_PIXEL_1_2 0x3 +# define DP_DSC_BITS_PER_PIXEL_1 0x4 + +#define DP_PSR_SUPPORT 0x070 /* XXX 1.2? */ +# define DP_PSR_IS_SUPPORTED 1 +# define DP_PSR2_IS_SUPPORTED 2 /* eDP 1.4 */ +# define DP_PSR2_WITH_Y_COORD_IS_SUPPORTED 3 /* eDP 1.4a */ + +#define DP_PSR_CAPS 0x071 /* XXX 1.2? */ +# define DP_PSR_NO_TRAIN_ON_EXIT 1 +# define DP_PSR_SETUP_TIME_330 (0 << 1) +# define DP_PSR_SETUP_TIME_275 (1 << 1) +# define DP_PSR_SETUP_TIME_220 (2 << 1) +# define DP_PSR_SETUP_TIME_165 (3 << 1) +# define DP_PSR_SETUP_TIME_110 (4 << 1) +# define DP_PSR_SETUP_TIME_55 (5 << 1) +# define DP_PSR_SETUP_TIME_0 (6 << 1) +# define DP_PSR_SETUP_TIME_MASK (7 << 1) +# define DP_PSR_SETUP_TIME_SHIFT 1 +# define DP_PSR2_SU_Y_COORDINATE_REQUIRED (1 << 4) /* eDP 1.4a */ +# define DP_PSR2_SU_GRANULARITY_REQUIRED (1 << 5) /* eDP 1.4b */ + +#define DP_PSR2_SU_X_GRANULARITY 0x072 /* eDP 1.4b */ +#define DP_PSR2_SU_Y_GRANULARITY 0x074 /* eDP 1.4b */ + +/* + * 0x80-0x8f describe downstream port capabilities, but there are two layouts + * based on whether DP_DETAILED_CAP_INFO_AVAILABLE was set. If it was not, + * each port's descriptor is one byte wide. If it was set, each port's is + * four bytes wide, starting with the one byte from the base info. As of + * DP interop v1.1a only VGA defines additional detail. + */ + +/* offset 0 */ +#define DP_DOWNSTREAM_PORT_0 0x80 +# define DP_DS_PORT_TYPE_MASK (7 << 0) +# define DP_DS_PORT_TYPE_DP 0 +# define DP_DS_PORT_TYPE_VGA 1 +# define DP_DS_PORT_TYPE_DVI 2 +# define DP_DS_PORT_TYPE_HDMI 3 +# define DP_DS_PORT_TYPE_NON_EDID 4 +# define DP_DS_PORT_TYPE_DP_DUALMODE 5 +# define DP_DS_PORT_TYPE_WIRELESS 6 +# define DP_DS_PORT_HPD (1 << 3) +# define DP_DS_NON_EDID_MASK (0xf << 4) +# define DP_DS_NON_EDID_720x480i_60 (1 << 4) +# define DP_DS_NON_EDID_720x480i_50 (2 << 4) +# define DP_DS_NON_EDID_1920x1080i_60 (3 << 4) +# define DP_DS_NON_EDID_1920x1080i_50 (4 << 4) +# define DP_DS_NON_EDID_1280x720_60 (5 << 4) +# define DP_DS_NON_EDID_1280x720_50 (7 << 4) +/* offset 1 for VGA is maximum megapixels per second / 8 */ +/* offset 1 for DVI/HDMI is maximum TMDS clock in Mbps / 2.5 */ +/* offset 2 for VGA/DVI/HDMI */ +# define DP_DS_MAX_BPC_MASK (3 << 0) +# define DP_DS_8BPC 0 +# define DP_DS_10BPC 1 +# define DP_DS_12BPC 2 +# define DP_DS_16BPC 3 +/* HDMI2.1 PCON FRL CONFIGURATION */ +# define DP_PCON_MAX_FRL_BW (7 << 2) +# define DP_PCON_MAX_0GBPS (0 << 2) +# define DP_PCON_MAX_9GBPS (1 << 2) +# define DP_PCON_MAX_18GBPS (2 << 2) +# define DP_PCON_MAX_24GBPS (3 << 2) +# define DP_PCON_MAX_32GBPS (4 << 2) +# define DP_PCON_MAX_40GBPS (5 << 2) +# define DP_PCON_MAX_48GBPS (6 << 2) +# define DP_PCON_SOURCE_CTL_MODE (1 << 5) + +/* offset 3 for DVI */ +# define DP_DS_DVI_DUAL_LINK (1 << 1) +# define DP_DS_DVI_HIGH_COLOR_DEPTH (1 << 2) +/* offset 3 for HDMI */ +# define DP_DS_HDMI_FRAME_SEQ_TO_FRAME_PACK (1 << 0) +# define DP_DS_HDMI_YCBCR422_PASS_THROUGH (1 << 1) +# define DP_DS_HDMI_YCBCR420_PASS_THROUGH (1 << 2) +# define DP_DS_HDMI_YCBCR444_TO_422_CONV (1 << 3) +# define DP_DS_HDMI_YCBCR444_TO_420_CONV (1 << 4) + +/* + * VESA DP-to-HDMI PCON Specification adds caps for colorspace + * conversion in DFP cap DPCD 83h. Sec6.1 Table-3. + * Based on the available support the source can enable + * color conversion by writing into PROTOCOL_COVERTER_CONTROL_2 + * DPCD 3052h. + */ +# define DP_DS_HDMI_BT601_RGB_YCBCR_CONV (1 << 5) +# define DP_DS_HDMI_BT709_RGB_YCBCR_CONV (1 << 6) +# define DP_DS_HDMI_BT2020_RGB_YCBCR_CONV (1 << 7) + +#define DP_MAX_DOWNSTREAM_PORTS 0x10 + +/* DP Forward error Correction Registers */ +#define DP_FEC_CAPABILITY 0x090 /* 1.4 */ +# define DP_FEC_CAPABLE (1 << 0) +# define DP_FEC_UNCORR_BLK_ERROR_COUNT_CAP (1 << 1) +# define DP_FEC_CORR_BLK_ERROR_COUNT_CAP (1 << 2) +# define DP_FEC_BIT_ERROR_COUNT_CAP (1 << 3) +#define DP_FEC_CAPABILITY_1 0x091 /* 2.0 */ + +/* DP-HDMI2.1 PCON DSC ENCODER SUPPORT */ +#define DP_PCON_DSC_ENCODER_CAP_SIZE 0xD /* 0x92 through 0x9E */ +#define DP_PCON_DSC_ENCODER 0x092 +# define DP_PCON_DSC_ENCODER_SUPPORTED (1 << 0) +# define DP_PCON_DSC_PPS_ENC_OVERRIDE (1 << 1) + +/* DP-HDMI2.1 PCON DSC Version */ +#define DP_PCON_DSC_VERSION 0x093 +# define DP_PCON_DSC_MAJOR_MASK (0xF << 0) +# define DP_PCON_DSC_MINOR_MASK (0xF << 4) +# define DP_PCON_DSC_MAJOR_SHIFT 0 +# define DP_PCON_DSC_MINOR_SHIFT 4 + +/* DP-HDMI2.1 PCON DSC RC Buffer block size */ +#define DP_PCON_DSC_RC_BUF_BLK_INFO 0x094 +# define DP_PCON_DSC_RC_BUF_BLK_SIZE (0x3 << 0) +# define DP_PCON_DSC_RC_BUF_BLK_1KB 0 +# define DP_PCON_DSC_RC_BUF_BLK_4KB 1 +# define DP_PCON_DSC_RC_BUF_BLK_16KB 2 +# define DP_PCON_DSC_RC_BUF_BLK_64KB 3 + +/* DP-HDMI2.1 PCON DSC RC Buffer size */ +#define DP_PCON_DSC_RC_BUF_SIZE 0x095 + +/* DP-HDMI2.1 PCON DSC Slice capabilities-1 */ +#define DP_PCON_DSC_SLICE_CAP_1 0x096 +# define DP_PCON_DSC_1_PER_DSC_ENC (0x1 << 0) +# define DP_PCON_DSC_2_PER_DSC_ENC (0x1 << 1) +# define DP_PCON_DSC_4_PER_DSC_ENC (0x1 << 3) +# define DP_PCON_DSC_6_PER_DSC_ENC (0x1 << 4) +# define DP_PCON_DSC_8_PER_DSC_ENC (0x1 << 5) +# define DP_PCON_DSC_10_PER_DSC_ENC (0x1 << 6) +# define DP_PCON_DSC_12_PER_DSC_ENC (0x1 << 7) + +#define DP_PCON_DSC_BUF_BIT_DEPTH 0x097 +# define DP_PCON_DSC_BIT_DEPTH_MASK (0xF << 0) +# define DP_PCON_DSC_DEPTH_9_BITS 0 +# define DP_PCON_DSC_DEPTH_10_BITS 1 +# define DP_PCON_DSC_DEPTH_11_BITS 2 +# define DP_PCON_DSC_DEPTH_12_BITS 3 +# define DP_PCON_DSC_DEPTH_13_BITS 4 +# define DP_PCON_DSC_DEPTH_14_BITS 5 +# define DP_PCON_DSC_DEPTH_15_BITS 6 +# define DP_PCON_DSC_DEPTH_16_BITS 7 +# define DP_PCON_DSC_DEPTH_8_BITS 8 + +#define DP_PCON_DSC_BLOCK_PREDICTION 0x098 +# define DP_PCON_DSC_BLOCK_PRED_SUPPORT (0x1 << 0) + +#define DP_PCON_DSC_ENC_COLOR_FMT_CAP 0x099 +# define DP_PCON_DSC_ENC_RGB (0x1 << 0) +# define DP_PCON_DSC_ENC_YUV444 (0x1 << 1) +# define DP_PCON_DSC_ENC_YUV422_S (0x1 << 2) +# define DP_PCON_DSC_ENC_YUV422_N (0x1 << 3) +# define DP_PCON_DSC_ENC_YUV420_N (0x1 << 4) + +#define DP_PCON_DSC_ENC_COLOR_DEPTH_CAP 0x09A +# define DP_PCON_DSC_ENC_8BPC (0x1 << 1) +# define DP_PCON_DSC_ENC_10BPC (0x1 << 2) +# define DP_PCON_DSC_ENC_12BPC (0x1 << 3) + +#define DP_PCON_DSC_MAX_SLICE_WIDTH 0x09B + +/* DP-HDMI2.1 PCON DSC Slice capabilities-2 */ +#define DP_PCON_DSC_SLICE_CAP_2 0x09C +# define DP_PCON_DSC_16_PER_DSC_ENC (0x1 << 0) +# define DP_PCON_DSC_20_PER_DSC_ENC (0x1 << 1) +# define DP_PCON_DSC_24_PER_DSC_ENC (0x1 << 2) + +/* DP-HDMI2.1 PCON HDMI TX Encoder Bits/pixel increment */ +#define DP_PCON_DSC_BPP_INCR 0x09E +# define DP_PCON_DSC_BPP_INCR_MASK (0x7 << 0) +# define DP_PCON_DSC_ONE_16TH_BPP 0 +# define DP_PCON_DSC_ONE_8TH_BPP 1 +# define DP_PCON_DSC_ONE_4TH_BPP 2 +# define DP_PCON_DSC_ONE_HALF_BPP 3 +# define DP_PCON_DSC_ONE_BPP 4 + +/* DP Extended DSC Capabilities */ +#define DP_DSC_BRANCH_OVERALL_THROUGHPUT_0 0x0a0 /* DP 1.4a SCR */ +#define DP_DSC_BRANCH_OVERALL_THROUGHPUT_1 0x0a1 +#define DP_DSC_BRANCH_MAX_LINE_WIDTH 0x0a2 + +/* DFP Capability Extension */ +#define DP_DFP_CAPABILITY_EXTENSION_SUPPORT 0x0a3 /* 2.0 */ + +/* Link Configuration */ +#define DP_LINK_BW_SET 0x100 +# define DP_LINK_RATE_TABLE 0x00 /* eDP 1.4 */ +# define DP_LINK_BW_1_62 0x06 +# define DP_LINK_BW_2_7 0x0a +# define DP_LINK_BW_5_4 0x14 /* 1.2 */ +# define DP_LINK_BW_8_1 0x1e /* 1.4 */ +# define DP_LINK_BW_10 0x01 /* 2.0 128b/132b Link Layer */ +# define DP_LINK_BW_13_5 0x04 /* 2.0 128b/132b Link Layer */ +# define DP_LINK_BW_20 0x02 /* 2.0 128b/132b Link Layer */ + +#define DP_LANE_COUNT_SET 0x101 +# define DP_LANE_COUNT_MASK 0x0f +# define DP_LANE_COUNT_ENHANCED_FRAME_EN (1 << 7) + +#define DP_TRAINING_PATTERN_SET 0x102 +# define DP_TRAINING_PATTERN_DISABLE 0 +# define DP_TRAINING_PATTERN_1 1 +# define DP_TRAINING_PATTERN_2 2 +# define DP_TRAINING_PATTERN_2_CDS 3 /* 2.0 E11 */ +# define DP_TRAINING_PATTERN_3 3 /* 1.2 */ +# define DP_TRAINING_PATTERN_4 7 /* 1.4 */ +# define DP_TRAINING_PATTERN_MASK 0x3 +# define DP_TRAINING_PATTERN_MASK_1_4 0xf + +/* DPCD 1.1 only. For DPCD >= 1.2 see per-lane DP_LINK_QUAL_LANEn_SET */ +# define DP_LINK_QUAL_PATTERN_11_DISABLE (0 << 2) +# define DP_LINK_QUAL_PATTERN_11_D10_2 (1 << 2) +# define DP_LINK_QUAL_PATTERN_11_ERROR_RATE (2 << 2) +# define DP_LINK_QUAL_PATTERN_11_PRBS7 (3 << 2) +# define DP_LINK_QUAL_PATTERN_11_MASK (3 << 2) + +# define DP_RECOVERED_CLOCK_OUT_EN (1 << 4) +# define DP_LINK_SCRAMBLING_DISABLE (1 << 5) + +# define DP_SYMBOL_ERROR_COUNT_BOTH (0 << 6) +# define DP_SYMBOL_ERROR_COUNT_DISPARITY (1 << 6) +# define DP_SYMBOL_ERROR_COUNT_SYMBOL (2 << 6) +# define DP_SYMBOL_ERROR_COUNT_MASK (3 << 6) + +#define DP_TRAINING_LANE0_SET 0x103 +#define DP_TRAINING_LANE1_SET 0x104 +#define DP_TRAINING_LANE2_SET 0x105 +#define DP_TRAINING_LANE3_SET 0x106 + +# define DP_TRAIN_VOLTAGE_SWING_MASK 0x3 +# define DP_TRAIN_VOLTAGE_SWING_SHIFT 0 +# define DP_TRAIN_MAX_SWING_REACHED (1 << 2) +# define DP_TRAIN_VOLTAGE_SWING_LEVEL_0 (0 << 0) +# define DP_TRAIN_VOLTAGE_SWING_LEVEL_1 (1 << 0) +# define DP_TRAIN_VOLTAGE_SWING_LEVEL_2 (2 << 0) +# define DP_TRAIN_VOLTAGE_SWING_LEVEL_3 (3 << 0) + +# define DP_TRAIN_PRE_EMPHASIS_MASK (3 << 3) +# define DP_TRAIN_PRE_EMPH_LEVEL_0 (0 << 3) +# define DP_TRAIN_PRE_EMPH_LEVEL_1 (1 << 3) +# define DP_TRAIN_PRE_EMPH_LEVEL_2 (2 << 3) +# define DP_TRAIN_PRE_EMPH_LEVEL_3 (3 << 3) + +# define DP_TRAIN_PRE_EMPHASIS_SHIFT 3 +# define DP_TRAIN_MAX_PRE_EMPHASIS_REACHED (1 << 5) + +# define DP_TX_FFE_PRESET_VALUE_MASK (0xf << 0) /* 2.0 128b/132b Link Layer */ + +#define DP_DOWNSPREAD_CTRL 0x107 +# define DP_SPREAD_AMP_0_5 (1 << 4) +# define DP_MSA_TIMING_PAR_IGNORE_EN (1 << 7) /* eDP */ + +#define DP_MAIN_LINK_CHANNEL_CODING_SET 0x108 +# define DP_SET_ANSI_8B10B (1 << 0) +# define DP_SET_ANSI_128B132B (1 << 1) + +#define DP_I2C_SPEED_CONTROL_STATUS 0x109 /* DPI */ +/* bitmask as for DP_I2C_SPEED_CAP */ + +#define DP_EDP_CONFIGURATION_SET 0x10a /* XXX 1.2? */ +# define DP_ALTERNATE_SCRAMBLER_RESET_ENABLE (1 << 0) +# define DP_FRAMING_CHANGE_ENABLE (1 << 1) +# define DP_PANEL_SELF_TEST_ENABLE (1 << 7) + +#define DP_LINK_QUAL_LANE0_SET 0x10b /* DPCD >= 1.2 */ +#define DP_LINK_QUAL_LANE1_SET 0x10c +#define DP_LINK_QUAL_LANE2_SET 0x10d +#define DP_LINK_QUAL_LANE3_SET 0x10e +# define DP_LINK_QUAL_PATTERN_DISABLE 0 +# define DP_LINK_QUAL_PATTERN_D10_2 1 +# define DP_LINK_QUAL_PATTERN_ERROR_RATE 2 +# define DP_LINK_QUAL_PATTERN_PRBS7 3 +# define DP_LINK_QUAL_PATTERN_80BIT_CUSTOM 4 +# define DP_LINK_QUAL_PATTERN_CP2520_PAT_1 5 +# define DP_LINK_QUAL_PATTERN_CP2520_PAT_2 6 +# define DP_LINK_QUAL_PATTERN_CP2520_PAT_3 7 +/* DP 2.0 UHBR10, UHBR13.5, UHBR20 */ +# define DP_LINK_QUAL_PATTERN_128B132B_TPS1 0x08 +# define DP_LINK_QUAL_PATTERN_128B132B_TPS2 0x10 +# define DP_LINK_QUAL_PATTERN_PRSBS9 0x18 +# define DP_LINK_QUAL_PATTERN_PRSBS11 0x20 +# define DP_LINK_QUAL_PATTERN_PRSBS15 0x28 +# define DP_LINK_QUAL_PATTERN_PRSBS23 0x30 +# define DP_LINK_QUAL_PATTERN_PRSBS31 0x38 +# define DP_LINK_QUAL_PATTERN_CUSTOM 0x40 +# define DP_LINK_QUAL_PATTERN_SQUARE 0x48 + +#define DP_TRAINING_LANE0_1_SET2 0x10f +#define DP_TRAINING_LANE2_3_SET2 0x110 +# define DP_LANE02_POST_CURSOR2_SET_MASK (3 << 0) +# define DP_LANE02_MAX_POST_CURSOR2_REACHED (1 << 2) +# define DP_LANE13_POST_CURSOR2_SET_MASK (3 << 4) +# define DP_LANE13_MAX_POST_CURSOR2_REACHED (1 << 6) + +#define DP_MSTM_CTRL 0x111 /* 1.2 */ +# define DP_MST_EN (1 << 0) +# define DP_UP_REQ_EN (1 << 1) +# define DP_UPSTREAM_IS_SRC (1 << 2) + +#define DP_AUDIO_DELAY0 0x112 /* 1.2 */ +#define DP_AUDIO_DELAY1 0x113 +#define DP_AUDIO_DELAY2 0x114 + +#define DP_LINK_RATE_SET 0x115 /* eDP 1.4 */ +# define DP_LINK_RATE_SET_SHIFT 0 +# define DP_LINK_RATE_SET_MASK (7 << 0) + +#define DP_RECEIVER_ALPM_CONFIG 0x116 /* eDP 1.4 */ +# define DP_ALPM_ENABLE (1 << 0) +# define DP_ALPM_LOCK_ERROR_IRQ_HPD_ENABLE (1 << 1) + +#define DP_SINK_DEVICE_AUX_FRAME_SYNC_CONF 0x117 /* eDP 1.4 */ +# define DP_AUX_FRAME_SYNC_ENABLE (1 << 0) +# define DP_IRQ_HPD_ENABLE (1 << 1) + +#define DP_UPSTREAM_DEVICE_DP_PWR_NEED 0x118 /* 1.2 */ +# define DP_PWR_NOT_NEEDED (1 << 0) + +#define DP_FEC_CONFIGURATION 0x120 /* 1.4 */ +# define DP_FEC_READY (1 << 0) +# define DP_FEC_ERR_COUNT_SEL_MASK (7 << 1) +# define DP_FEC_ERR_COUNT_DIS (0 << 1) +# define DP_FEC_UNCORR_BLK_ERROR_COUNT (1 << 1) +# define DP_FEC_CORR_BLK_ERROR_COUNT (2 << 1) +# define DP_FEC_BIT_ERROR_COUNT (3 << 1) +# define DP_FEC_LANE_SELECT_MASK (3 << 4) +# define DP_FEC_LANE_0_SELECT (0 << 4) +# define DP_FEC_LANE_1_SELECT (1 << 4) +# define DP_FEC_LANE_2_SELECT (2 << 4) +# define DP_FEC_LANE_3_SELECT (3 << 4) + +#define DP_AUX_FRAME_SYNC_VALUE 0x15c /* eDP 1.4 */ +# define DP_AUX_FRAME_SYNC_VALID (1 << 0) + +#define DP_DSC_ENABLE 0x160 /* DP 1.4 */ +# define DP_DECOMPRESSION_EN (1 << 0) +#define DP_DSC_CONFIGURATION 0x161 /* DP 2.0 */ + +#define DP_PSR_EN_CFG 0x170 /* XXX 1.2? */ +# define DP_PSR_ENABLE BIT(0) +# define DP_PSR_MAIN_LINK_ACTIVE BIT(1) +# define DP_PSR_CRC_VERIFICATION BIT(2) +# define DP_PSR_FRAME_CAPTURE BIT(3) +# define DP_PSR_SU_REGION_SCANLINE_CAPTURE BIT(4) /* eDP 1.4a */ +# define DP_PSR_IRQ_HPD_WITH_CRC_ERRORS BIT(5) /* eDP 1.4a */ +# define DP_PSR_ENABLE_PSR2 BIT(6) /* eDP 1.4a */ + +#define DP_ADAPTER_CTRL 0x1a0 +# define DP_ADAPTER_CTRL_FORCE_LOAD_SENSE (1 << 0) + +#define DP_BRANCH_DEVICE_CTRL 0x1a1 +# define DP_BRANCH_DEVICE_IRQ_HPD (1 << 0) + +#define DP_PAYLOAD_ALLOCATE_SET 0x1c0 +#define DP_PAYLOAD_ALLOCATE_START_TIME_SLOT 0x1c1 +#define DP_PAYLOAD_ALLOCATE_TIME_SLOT_COUNT 0x1c2 + +/* Link/Sink Device Status */ +#define DP_SINK_COUNT 0x200 +/* prior to 1.2 bit 7 was reserved mbz */ +# define DP_GET_SINK_COUNT(x) ((((x) & 0x80) >> 1) | ((x) & 0x3f)) +# define DP_SINK_CP_READY (1 << 6) + +#define DP_DEVICE_SERVICE_IRQ_VECTOR 0x201 +# define DP_REMOTE_CONTROL_COMMAND_PENDING (1 << 0) +# define DP_AUTOMATED_TEST_REQUEST (1 << 1) +# define DP_CP_IRQ (1 << 2) +# define DP_MCCS_IRQ (1 << 3) +# define DP_DOWN_REP_MSG_RDY (1 << 4) /* 1.2 MST */ +# define DP_UP_REQ_MSG_RDY (1 << 5) /* 1.2 MST */ +# define DP_SINK_SPECIFIC_IRQ (1 << 6) + +#define DP_LANE0_1_STATUS 0x202 +#define DP_LANE2_3_STATUS 0x203 +# define DP_LANE_CR_DONE (1 << 0) +# define DP_LANE_CHANNEL_EQ_DONE (1 << 1) +# define DP_LANE_SYMBOL_LOCKED (1 << 2) + +#define DP_CHANNEL_EQ_BITS (DP_LANE_CR_DONE | \ + DP_LANE_CHANNEL_EQ_DONE | \ + DP_LANE_SYMBOL_LOCKED) + +#define DP_LANE_ALIGN_STATUS_UPDATED 0x204 +#define DP_INTERLANE_ALIGN_DONE (1 << 0) +#define DP_128B132B_DPRX_EQ_INTERLANE_ALIGN_DONE (1 << 2) /* 2.0 E11 */ +#define DP_128B132B_DPRX_CDS_INTERLANE_ALIGN_DONE (1 << 3) /* 2.0 E11 */ +#define DP_128B132B_LT_FAILED (1 << 4) /* 2.0 E11 */ +#define DP_DOWNSTREAM_PORT_STATUS_CHANGED (1 << 6) +#define DP_LINK_STATUS_UPDATED (1 << 7) + +#define DP_SINK_STATUS 0x205 +# define DP_RECEIVE_PORT_0_STATUS (1 << 0) +# define DP_RECEIVE_PORT_1_STATUS (1 << 1) +# define DP_STREAM_REGENERATION_STATUS (1 << 2) /* 2.0 */ +# define DP_INTRA_HOP_AUX_REPLY_INDICATION (1 << 3) /* 2.0 */ + +#define DP_ADJUST_REQUEST_LANE0_1 0x206 +#define DP_ADJUST_REQUEST_LANE2_3 0x207 +# define DP_ADJUST_VOLTAGE_SWING_LANE0_MASK 0x03 +# define DP_ADJUST_VOLTAGE_SWING_LANE0_SHIFT 0 +# define DP_ADJUST_PRE_EMPHASIS_LANE0_MASK 0x0c +# define DP_ADJUST_PRE_EMPHASIS_LANE0_SHIFT 2 +# define DP_ADJUST_VOLTAGE_SWING_LANE1_MASK 0x30 +# define DP_ADJUST_VOLTAGE_SWING_LANE1_SHIFT 4 +# define DP_ADJUST_PRE_EMPHASIS_LANE1_MASK 0xc0 +# define DP_ADJUST_PRE_EMPHASIS_LANE1_SHIFT 6 + +/* DP 2.0 128b/132b Link Layer */ +# define DP_ADJUST_TX_FFE_PRESET_LANE0_MASK (0xf << 0) +# define DP_ADJUST_TX_FFE_PRESET_LANE0_SHIFT 0 +# define DP_ADJUST_TX_FFE_PRESET_LANE1_MASK (0xf << 4) +# define DP_ADJUST_TX_FFE_PRESET_LANE1_SHIFT 4 + +#define DP_ADJUST_REQUEST_POST_CURSOR2 0x20c +# define DP_ADJUST_POST_CURSOR2_LANE0_MASK 0x03 +# define DP_ADJUST_POST_CURSOR2_LANE0_SHIFT 0 +# define DP_ADJUST_POST_CURSOR2_LANE1_MASK 0x0c +# define DP_ADJUST_POST_CURSOR2_LANE1_SHIFT 2 +# define DP_ADJUST_POST_CURSOR2_LANE2_MASK 0x30 +# define DP_ADJUST_POST_CURSOR2_LANE2_SHIFT 4 +# define DP_ADJUST_POST_CURSOR2_LANE3_MASK 0xc0 +# define DP_ADJUST_POST_CURSOR2_LANE3_SHIFT 6 + +#define DP_TEST_REQUEST 0x218 +# define DP_TEST_LINK_TRAINING (1 << 0) +# define DP_TEST_LINK_VIDEO_PATTERN (1 << 1) +# define DP_TEST_LINK_EDID_READ (1 << 2) +# define DP_TEST_LINK_PHY_TEST_PATTERN (1 << 3) /* DPCD >= 1.1 */ +# define DP_TEST_LINK_FAUX_PATTERN (1 << 4) /* DPCD >= 1.2 */ +# define DP_TEST_LINK_AUDIO_PATTERN (1 << 5) /* DPCD >= 1.2 */ +# define DP_TEST_LINK_AUDIO_DISABLED_VIDEO (1 << 6) /* DPCD >= 1.2 */ + +#define DP_TEST_LINK_RATE 0x219 +# define DP_LINK_RATE_162 (0x6) +# define DP_LINK_RATE_27 (0xa) + +#define DP_TEST_LANE_COUNT 0x220 + +#define DP_TEST_PATTERN 0x221 +# define DP_NO_TEST_PATTERN 0x0 +# define DP_COLOR_RAMP 0x1 +# define DP_BLACK_AND_WHITE_VERTICAL_LINES 0x2 +# define DP_COLOR_SQUARE 0x3 + +#define DP_TEST_H_TOTAL_HI 0x222 +#define DP_TEST_H_TOTAL_LO 0x223 + +#define DP_TEST_V_TOTAL_HI 0x224 +#define DP_TEST_V_TOTAL_LO 0x225 + +#define DP_TEST_H_START_HI 0x226 +#define DP_TEST_H_START_LO 0x227 + +#define DP_TEST_V_START_HI 0x228 +#define DP_TEST_V_START_LO 0x229 + +#define DP_TEST_HSYNC_HI 0x22A +# define DP_TEST_HSYNC_POLARITY (1 << 7) +# define DP_TEST_HSYNC_WIDTH_HI_MASK (127 << 0) +#define DP_TEST_HSYNC_WIDTH_LO 0x22B + +#define DP_TEST_VSYNC_HI 0x22C +# define DP_TEST_VSYNC_POLARITY (1 << 7) +# define DP_TEST_VSYNC_WIDTH_HI_MASK (127 << 0) +#define DP_TEST_VSYNC_WIDTH_LO 0x22D + +#define DP_TEST_H_WIDTH_HI 0x22E +#define DP_TEST_H_WIDTH_LO 0x22F + +#define DP_TEST_V_HEIGHT_HI 0x230 +#define DP_TEST_V_HEIGHT_LO 0x231 + +#define DP_TEST_MISC0 0x232 +# define DP_TEST_SYNC_CLOCK (1 << 0) +# define DP_TEST_COLOR_FORMAT_MASK (3 << 1) +# define DP_TEST_COLOR_FORMAT_SHIFT 1 +# define DP_COLOR_FORMAT_RGB (0 << 1) +# define DP_COLOR_FORMAT_YCbCr422 (1 << 1) +# define DP_COLOR_FORMAT_YCbCr444 (2 << 1) +# define DP_TEST_DYNAMIC_RANGE_VESA (0 << 3) +# define DP_TEST_DYNAMIC_RANGE_CEA (1 << 3) +# define DP_TEST_YCBCR_COEFFICIENTS (1 << 4) +# define DP_YCBCR_COEFFICIENTS_ITU601 (0 << 4) +# define DP_YCBCR_COEFFICIENTS_ITU709 (1 << 4) +# define DP_TEST_BIT_DEPTH_MASK (7 << 5) +# define DP_TEST_BIT_DEPTH_SHIFT 5 +# define DP_TEST_BIT_DEPTH_6 (0 << 5) +# define DP_TEST_BIT_DEPTH_8 (1 << 5) +# define DP_TEST_BIT_DEPTH_10 (2 << 5) +# define DP_TEST_BIT_DEPTH_12 (3 << 5) +# define DP_TEST_BIT_DEPTH_16 (4 << 5) + +#define DP_TEST_MISC1 0x233 +# define DP_TEST_REFRESH_DENOMINATOR (1 << 0) +# define DP_TEST_INTERLACED (1 << 1) + +#define DP_TEST_REFRESH_RATE_NUMERATOR 0x234 + +#define DP_TEST_MISC0 0x232 + +#define DP_TEST_CRC_R_CR 0x240 +#define DP_TEST_CRC_G_Y 0x242 +#define DP_TEST_CRC_B_CB 0x244 + +#define DP_TEST_SINK_MISC 0x246 +# define DP_TEST_CRC_SUPPORTED (1 << 5) +# define DP_TEST_COUNT_MASK 0xf + +#define DP_PHY_TEST_PATTERN 0x248 +# define DP_PHY_TEST_PATTERN_SEL_MASK 0x7 +# define DP_PHY_TEST_PATTERN_NONE 0x0 +# define DP_PHY_TEST_PATTERN_D10_2 0x1 +# define DP_PHY_TEST_PATTERN_ERROR_COUNT 0x2 +# define DP_PHY_TEST_PATTERN_PRBS7 0x3 +# define DP_PHY_TEST_PATTERN_80BIT_CUSTOM 0x4 +# define DP_PHY_TEST_PATTERN_CP2520 0x5 + +#define DP_PHY_SQUARE_PATTERN 0x249 + +#define DP_TEST_HBR2_SCRAMBLER_RESET 0x24A +#define DP_TEST_80BIT_CUSTOM_PATTERN_7_0 0x250 +#define DP_TEST_80BIT_CUSTOM_PATTERN_15_8 0x251 +#define DP_TEST_80BIT_CUSTOM_PATTERN_23_16 0x252 +#define DP_TEST_80BIT_CUSTOM_PATTERN_31_24 0x253 +#define DP_TEST_80BIT_CUSTOM_PATTERN_39_32 0x254 +#define DP_TEST_80BIT_CUSTOM_PATTERN_47_40 0x255 +#define DP_TEST_80BIT_CUSTOM_PATTERN_55_48 0x256 +#define DP_TEST_80BIT_CUSTOM_PATTERN_63_56 0x257 +#define DP_TEST_80BIT_CUSTOM_PATTERN_71_64 0x258 +#define DP_TEST_80BIT_CUSTOM_PATTERN_79_72 0x259 + +#define DP_TEST_RESPONSE 0x260 +# define DP_TEST_ACK (1 << 0) +# define DP_TEST_NAK (1 << 1) +# define DP_TEST_EDID_CHECKSUM_WRITE (1 << 2) + +#define DP_TEST_EDID_CHECKSUM 0x261 + +#define DP_TEST_SINK 0x270 +# define DP_TEST_SINK_START (1 << 0) +#define DP_TEST_AUDIO_MODE 0x271 +#define DP_TEST_AUDIO_PATTERN_TYPE 0x272 +#define DP_TEST_AUDIO_PERIOD_CH1 0x273 +#define DP_TEST_AUDIO_PERIOD_CH2 0x274 +#define DP_TEST_AUDIO_PERIOD_CH3 0x275 +#define DP_TEST_AUDIO_PERIOD_CH4 0x276 +#define DP_TEST_AUDIO_PERIOD_CH5 0x277 +#define DP_TEST_AUDIO_PERIOD_CH6 0x278 +#define DP_TEST_AUDIO_PERIOD_CH7 0x279 +#define DP_TEST_AUDIO_PERIOD_CH8 0x27A + +#define DP_FEC_STATUS 0x280 /* 1.4 */ +# define DP_FEC_DECODE_EN_DETECTED (1 << 0) +# define DP_FEC_DECODE_DIS_DETECTED (1 << 1) + +#define DP_FEC_ERROR_COUNT_LSB 0x0281 /* 1.4 */ + +#define DP_FEC_ERROR_COUNT_MSB 0x0282 /* 1.4 */ +# define DP_FEC_ERROR_COUNT_MASK 0x7F +# define DP_FEC_ERR_COUNT_VALID (1 << 7) + +#define DP_PAYLOAD_TABLE_UPDATE_STATUS 0x2c0 /* 1.2 MST */ +# define DP_PAYLOAD_TABLE_UPDATED (1 << 0) +# define DP_PAYLOAD_ACT_HANDLED (1 << 1) + +#define DP_VC_PAYLOAD_ID_SLOT_1 0x2c1 /* 1.2 MST */ +/* up to ID_SLOT_63 at 0x2ff */ + +/* Source Device-specific */ +#define DP_SOURCE_OUI 0x300 + +/* Sink Device-specific */ +#define DP_SINK_OUI 0x400 + +/* Branch Device-specific */ +#define DP_BRANCH_OUI 0x500 +#define DP_BRANCH_ID 0x503 +#define DP_BRANCH_REVISION_START 0x509 +#define DP_BRANCH_HW_REV 0x509 +#define DP_BRANCH_SW_REV 0x50A + +/* Link/Sink Device Power Control */ +#define DP_SET_POWER 0x600 +# define DP_SET_POWER_D0 0x1 +# define DP_SET_POWER_D3 0x2 +# define DP_SET_POWER_MASK 0x3 +# define DP_SET_POWER_D3_AUX_ON 0x5 + +/* eDP-specific */ +#define DP_EDP_DPCD_REV 0x700 /* eDP 1.2 */ +# define DP_EDP_11 0x00 +# define DP_EDP_12 0x01 +# define DP_EDP_13 0x02 +# define DP_EDP_14 0x03 +# define DP_EDP_14a 0x04 /* eDP 1.4a */ +# define DP_EDP_14b 0x05 /* eDP 1.4b */ + +#define DP_EDP_GENERAL_CAP_1 0x701 +# define DP_EDP_TCON_BACKLIGHT_ADJUSTMENT_CAP (1 << 0) +# define DP_EDP_BACKLIGHT_PIN_ENABLE_CAP (1 << 1) +# define DP_EDP_BACKLIGHT_AUX_ENABLE_CAP (1 << 2) +# define DP_EDP_PANEL_SELF_TEST_PIN_ENABLE_CAP (1 << 3) +# define DP_EDP_PANEL_SELF_TEST_AUX_ENABLE_CAP (1 << 4) +# define DP_EDP_FRC_ENABLE_CAP (1 << 5) +# define DP_EDP_COLOR_ENGINE_CAP (1 << 6) +# define DP_EDP_SET_POWER_CAP (1 << 7) + +#define DP_EDP_BACKLIGHT_ADJUSTMENT_CAP 0x702 +# define DP_EDP_BACKLIGHT_BRIGHTNESS_PWM_PIN_CAP (1 << 0) +# define DP_EDP_BACKLIGHT_BRIGHTNESS_AUX_SET_CAP (1 << 1) +# define DP_EDP_BACKLIGHT_BRIGHTNESS_BYTE_COUNT (1 << 2) +# define DP_EDP_BACKLIGHT_AUX_PWM_PRODUCT_CAP (1 << 3) +# define DP_EDP_BACKLIGHT_FREQ_PWM_PIN_PASSTHRU_CAP (1 << 4) +# define DP_EDP_BACKLIGHT_FREQ_AUX_SET_CAP (1 << 5) +# define DP_EDP_DYNAMIC_BACKLIGHT_CAP (1 << 6) +# define DP_EDP_VBLANK_BACKLIGHT_UPDATE_CAP (1 << 7) + +#define DP_EDP_GENERAL_CAP_2 0x703 +# define DP_EDP_OVERDRIVE_ENGINE_ENABLED (1 << 0) + +#define DP_EDP_GENERAL_CAP_3 0x704 /* eDP 1.4 */ +# define DP_EDP_X_REGION_CAP_MASK (0xf << 0) +# define DP_EDP_X_REGION_CAP_SHIFT 0 +# define DP_EDP_Y_REGION_CAP_MASK (0xf << 4) +# define DP_EDP_Y_REGION_CAP_SHIFT 4 + +#define DP_EDP_DISPLAY_CONTROL_REGISTER 0x720 +# define DP_EDP_BACKLIGHT_ENABLE (1 << 0) +# define DP_EDP_BLACK_VIDEO_ENABLE (1 << 1) +# define DP_EDP_FRC_ENABLE (1 << 2) +# define DP_EDP_COLOR_ENGINE_ENABLE (1 << 3) +# define DP_EDP_VBLANK_BACKLIGHT_UPDATE_ENABLE (1 << 7) + +#define DP_EDP_BACKLIGHT_MODE_SET_REGISTER 0x721 +# define DP_EDP_BACKLIGHT_CONTROL_MODE_MASK (3 << 0) +# define DP_EDP_BACKLIGHT_CONTROL_MODE_PWM (0 << 0) +# define DP_EDP_BACKLIGHT_CONTROL_MODE_PRESET (1 << 0) +# define DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD (2 << 0) +# define DP_EDP_BACKLIGHT_CONTROL_MODE_PRODUCT (3 << 0) +# define DP_EDP_BACKLIGHT_FREQ_PWM_PIN_PASSTHRU_ENABLE (1 << 2) +# define DP_EDP_BACKLIGHT_FREQ_AUX_SET_ENABLE (1 << 3) +# define DP_EDP_DYNAMIC_BACKLIGHT_ENABLE (1 << 4) +# define DP_EDP_REGIONAL_BACKLIGHT_ENABLE (1 << 5) +# define DP_EDP_UPDATE_REGION_BRIGHTNESS (1 << 6) /* eDP 1.4 */ + +#define DP_EDP_BACKLIGHT_BRIGHTNESS_MSB 0x722 +#define DP_EDP_BACKLIGHT_BRIGHTNESS_LSB 0x723 + +#define DP_EDP_PWMGEN_BIT_COUNT 0x724 +#define DP_EDP_PWMGEN_BIT_COUNT_CAP_MIN 0x725 +#define DP_EDP_PWMGEN_BIT_COUNT_CAP_MAX 0x726 +# define DP_EDP_PWMGEN_BIT_COUNT_MASK (0x1f << 0) + +#define DP_EDP_BACKLIGHT_CONTROL_STATUS 0x727 + +#define DP_EDP_BACKLIGHT_FREQ_SET 0x728 +# define DP_EDP_BACKLIGHT_FREQ_BASE_KHZ 27000 + +#define DP_EDP_BACKLIGHT_FREQ_CAP_MIN_MSB 0x72a +#define DP_EDP_BACKLIGHT_FREQ_CAP_MIN_MID 0x72b +#define DP_EDP_BACKLIGHT_FREQ_CAP_MIN_LSB 0x72c + +#define DP_EDP_BACKLIGHT_FREQ_CAP_MAX_MSB 0x72d +#define DP_EDP_BACKLIGHT_FREQ_CAP_MAX_MID 0x72e +#define DP_EDP_BACKLIGHT_FREQ_CAP_MAX_LSB 0x72f + +#define DP_EDP_DBC_MINIMUM_BRIGHTNESS_SET 0x732 +#define DP_EDP_DBC_MAXIMUM_BRIGHTNESS_SET 0x733 + +#define DP_EDP_REGIONAL_BACKLIGHT_BASE 0x740 /* eDP 1.4 */ +#define DP_EDP_REGIONAL_BACKLIGHT_0 0x741 /* eDP 1.4 */ + +#define DP_EDP_MSO_LINK_CAPABILITIES 0x7a4 /* eDP 1.4 */ +# define DP_EDP_MSO_NUMBER_OF_LINKS_MASK (7 << 0) +# define DP_EDP_MSO_NUMBER_OF_LINKS_SHIFT 0 +# define DP_EDP_MSO_INDEPENDENT_LINK_BIT (1 << 3) + +/* Sideband MSG Buffers */ +#define DP_SIDEBAND_MSG_DOWN_REQ_BASE 0x1000 /* 1.2 MST */ +#define DP_SIDEBAND_MSG_UP_REP_BASE 0x1200 /* 1.2 MST */ +#define DP_SIDEBAND_MSG_DOWN_REP_BASE 0x1400 /* 1.2 MST */ +#define DP_SIDEBAND_MSG_UP_REQ_BASE 0x1600 /* 1.2 MST */ + +/* DPRX Event Status Indicator */ +#define DP_SINK_COUNT_ESI 0x2002 /* same as 0x200 */ +#define DP_DEVICE_SERVICE_IRQ_VECTOR_ESI0 0x2003 /* same as 0x201 */ + +#define DP_DEVICE_SERVICE_IRQ_VECTOR_ESI1 0x2004 /* 1.2 */ +# define DP_RX_GTC_MSTR_REQ_STATUS_CHANGE (1 << 0) +# define DP_LOCK_ACQUISITION_REQUEST (1 << 1) +# define DP_CEC_IRQ (1 << 2) + +#define DP_LINK_SERVICE_IRQ_VECTOR_ESI0 0x2005 /* 1.2 */ +# define RX_CAP_CHANGED (1 << 0) +# define LINK_STATUS_CHANGED (1 << 1) +# define STREAM_STATUS_CHANGED (1 << 2) +# define HDMI_LINK_STATUS_CHANGED (1 << 3) +# define CONNECTED_OFF_ENTRY_REQUESTED (1 << 4) + +#define DP_PSR_ERROR_STATUS 0x2006 /* XXX 1.2? */ +# define DP_PSR_LINK_CRC_ERROR (1 << 0) +# define DP_PSR_RFB_STORAGE_ERROR (1 << 1) +# define DP_PSR_VSC_SDP_UNCORRECTABLE_ERROR (1 << 2) /* eDP 1.4 */ + +#define DP_PSR_ESI 0x2007 /* XXX 1.2? */ +# define DP_PSR_CAPS_CHANGE (1 << 0) + +#define DP_PSR_STATUS 0x2008 /* XXX 1.2? */ +# define DP_PSR_SINK_INACTIVE 0 +# define DP_PSR_SINK_ACTIVE_SRC_SYNCED 1 +# define DP_PSR_SINK_ACTIVE_RFB 2 +# define DP_PSR_SINK_ACTIVE_SINK_SYNCED 3 +# define DP_PSR_SINK_ACTIVE_RESYNC 4 +# define DP_PSR_SINK_INTERNAL_ERROR 7 +# define DP_PSR_SINK_STATE_MASK 0x07 + +#define DP_SYNCHRONIZATION_LATENCY_IN_SINK 0x2009 /* edp 1.4 */ +# define DP_MAX_RESYNC_FRAME_COUNT_MASK (0xf << 0) +# define DP_MAX_RESYNC_FRAME_COUNT_SHIFT 0 +# define DP_LAST_ACTUAL_SYNCHRONIZATION_LATENCY_MASK (0xf << 4) +# define DP_LAST_ACTUAL_SYNCHRONIZATION_LATENCY_SHIFT 4 + +#define DP_LAST_RECEIVED_PSR_SDP 0x200a /* eDP 1.2 */ +# define DP_PSR_STATE_BIT (1 << 0) /* eDP 1.2 */ +# define DP_UPDATE_RFB_BIT (1 << 1) /* eDP 1.2 */ +# define DP_CRC_VALID_BIT (1 << 2) /* eDP 1.2 */ +# define DP_SU_VALID (1 << 3) /* eDP 1.4 */ +# define DP_FIRST_SCAN_LINE_SU_REGION (1 << 4) /* eDP 1.4 */ +# define DP_LAST_SCAN_LINE_SU_REGION (1 << 5) /* eDP 1.4 */ +# define DP_Y_COORDINATE_VALID (1 << 6) /* eDP 1.4a */ + +#define DP_RECEIVER_ALPM_STATUS 0x200b /* eDP 1.4 */ +# define DP_ALPM_LOCK_TIMEOUT_ERROR (1 << 0) + +#define DP_LANE0_1_STATUS_ESI 0x200c /* status same as 0x202 */ +#define DP_LANE2_3_STATUS_ESI 0x200d /* status same as 0x203 */ +#define DP_LANE_ALIGN_STATUS_UPDATED_ESI 0x200e /* status same as 0x204 */ +#define DP_SINK_STATUS_ESI 0x200f /* status same as 0x205 */ + +/* Extended Receiver Capability: See DP_DPCD_REV for definitions */ +#define DP_DP13_DPCD_REV 0x2200 + +#define DP_DPRX_FEATURE_ENUMERATION_LIST 0x2210 /* DP 1.3 */ +# define DP_GTC_CAP (1 << 0) /* DP 1.3 */ +# define DP_SST_SPLIT_SDP_CAP (1 << 1) /* DP 1.4 */ +# define DP_AV_SYNC_CAP (1 << 2) /* DP 1.3 */ +# define DP_VSC_SDP_EXT_FOR_COLORIMETRY_SUPPORTED (1 << 3) /* DP 1.3 */ +# define DP_VSC_EXT_VESA_SDP_SUPPORTED (1 << 4) /* DP 1.4 */ +# define DP_VSC_EXT_VESA_SDP_CHAINING_SUPPORTED (1 << 5) /* DP 1.4 */ +# define DP_VSC_EXT_CEA_SDP_SUPPORTED (1 << 6) /* DP 1.4 */ +# define DP_VSC_EXT_CEA_SDP_CHAINING_SUPPORTED (1 << 7) /* DP 1.4 */ + +#define DP_128B132B_SUPPORTED_LINK_RATES 0x2215 /* 2.0 */ +# define DP_UHBR10 (1 << 0) +# define DP_UHBR20 (1 << 1) +# define DP_UHBR13_5 (1 << 2) + +#define DP_128B132B_TRAINING_AUX_RD_INTERVAL 0x2216 /* 2.0 */ +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_1MS_UNIT (1 << 7) +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_MASK 0x7f +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_400_US 0x00 +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_4_MS 0x01 +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_8_MS 0x02 +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_12_MS 0x03 +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_16_MS 0x04 +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_32_MS 0x05 +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_64_MS 0x06 + +#define DP_TEST_264BIT_CUSTOM_PATTERN_7_0 0x2230 +#define DP_TEST_264BIT_CUSTOM_PATTERN_263_256 0x2250 + +/* DSC Extended Capability Branch Total DSC Resources */ +#define DP_DSC_SUPPORT_AND_DSC_DECODER_COUNT 0x2260 /* 2.0 */ +# define DP_DSC_DECODER_COUNT_MASK (0b111 << 5) +# define DP_DSC_DECODER_COUNT_SHIFT 5 +#define DP_DSC_MAX_SLICE_COUNT_AND_AGGREGATION_0 0x2270 /* 2.0 */ +# define DP_DSC_DECODER_0_MAXIMUM_SLICE_COUNT_MASK (1 << 0) +# define DP_DSC_DECODER_0_AGGREGATION_SUPPORT_MASK (0b111 << 1) +# define DP_DSC_DECODER_0_AGGREGATION_SUPPORT_SHIFT 1 + +/* Protocol Converter Extension */ +/* HDMI CEC tunneling over AUX DP 1.3 section 5.3.3.3.1 DPCD 1.4+ */ +#define DP_CEC_TUNNELING_CAPABILITY 0x3000 +# define DP_CEC_TUNNELING_CAPABLE (1 << 0) +# define DP_CEC_SNOOPING_CAPABLE (1 << 1) +# define DP_CEC_MULTIPLE_LA_CAPABLE (1 << 2) + +#define DP_CEC_TUNNELING_CONTROL 0x3001 +# define DP_CEC_TUNNELING_ENABLE (1 << 0) +# define DP_CEC_SNOOPING_ENABLE (1 << 1) + +#define DP_CEC_RX_MESSAGE_INFO 0x3002 +# define DP_CEC_RX_MESSAGE_LEN_MASK (0xf << 0) +# define DP_CEC_RX_MESSAGE_LEN_SHIFT 0 +# define DP_CEC_RX_MESSAGE_HPD_STATE (1 << 4) +# define DP_CEC_RX_MESSAGE_HPD_LOST (1 << 5) +# define DP_CEC_RX_MESSAGE_ACKED (1 << 6) +# define DP_CEC_RX_MESSAGE_ENDED (1 << 7) + +#define DP_CEC_TX_MESSAGE_INFO 0x3003 +# define DP_CEC_TX_MESSAGE_LEN_MASK (0xf << 0) +# define DP_CEC_TX_MESSAGE_LEN_SHIFT 0 +# define DP_CEC_TX_RETRY_COUNT_MASK (0x7 << 4) +# define DP_CEC_TX_RETRY_COUNT_SHIFT 4 +# define DP_CEC_TX_MESSAGE_SEND (1 << 7) + +#define DP_CEC_TUNNELING_IRQ_FLAGS 0x3004 +# define DP_CEC_RX_MESSAGE_INFO_VALID (1 << 0) +# define DP_CEC_RX_MESSAGE_OVERFLOW (1 << 1) +# define DP_CEC_TX_MESSAGE_SENT (1 << 4) +# define DP_CEC_TX_LINE_ERROR (1 << 5) +# define DP_CEC_TX_ADDRESS_NACK_ERROR (1 << 6) +# define DP_CEC_TX_DATA_NACK_ERROR (1 << 7) + +#define DP_CEC_LOGICAL_ADDRESS_MASK 0x300E /* 0x300F word */ +# define DP_CEC_LOGICAL_ADDRESS_0 (1 << 0) +# define DP_CEC_LOGICAL_ADDRESS_1 (1 << 1) +# define DP_CEC_LOGICAL_ADDRESS_2 (1 << 2) +# define DP_CEC_LOGICAL_ADDRESS_3 (1 << 3) +# define DP_CEC_LOGICAL_ADDRESS_4 (1 << 4) +# define DP_CEC_LOGICAL_ADDRESS_5 (1 << 5) +# define DP_CEC_LOGICAL_ADDRESS_6 (1 << 6) +# define DP_CEC_LOGICAL_ADDRESS_7 (1 << 7) +#define DP_CEC_LOGICAL_ADDRESS_MASK_2 0x300F /* 0x300E word */ +# define DP_CEC_LOGICAL_ADDRESS_8 (1 << 0) +# define DP_CEC_LOGICAL_ADDRESS_9 (1 << 1) +# define DP_CEC_LOGICAL_ADDRESS_10 (1 << 2) +# define DP_CEC_LOGICAL_ADDRESS_11 (1 << 3) +# define DP_CEC_LOGICAL_ADDRESS_12 (1 << 4) +# define DP_CEC_LOGICAL_ADDRESS_13 (1 << 5) +# define DP_CEC_LOGICAL_ADDRESS_14 (1 << 6) +# define DP_CEC_LOGICAL_ADDRESS_15 (1 << 7) + +#define DP_CEC_RX_MESSAGE_BUFFER 0x3010 +#define DP_CEC_TX_MESSAGE_BUFFER 0x3020 +#define DP_CEC_MESSAGE_BUFFER_LENGTH 0x10 + +/* PCON CONFIGURE-1 FRL FOR HDMI SINK */ +#define DP_PCON_HDMI_LINK_CONFIG_1 0x305A +# define DP_PCON_ENABLE_MAX_FRL_BW (7 << 0) +# define DP_PCON_ENABLE_MAX_BW_0GBPS 0 +# define DP_PCON_ENABLE_MAX_BW_9GBPS 1 +# define DP_PCON_ENABLE_MAX_BW_18GBPS 2 +# define DP_PCON_ENABLE_MAX_BW_24GBPS 3 +# define DP_PCON_ENABLE_MAX_BW_32GBPS 4 +# define DP_PCON_ENABLE_MAX_BW_40GBPS 5 +# define DP_PCON_ENABLE_MAX_BW_48GBPS 6 +# define DP_PCON_ENABLE_SOURCE_CTL_MODE (1 << 3) +# define DP_PCON_ENABLE_CONCURRENT_LINK (1 << 4) +# define DP_PCON_ENABLE_SEQUENTIAL_LINK (0 << 4) +# define DP_PCON_ENABLE_LINK_FRL_MODE (1 << 5) +# define DP_PCON_ENABLE_HPD_READY (1 << 6) +# define DP_PCON_ENABLE_HDMI_LINK (1 << 7) + +/* PCON CONFIGURE-2 FRL FOR HDMI SINK */ +#define DP_PCON_HDMI_LINK_CONFIG_2 0x305B +# define DP_PCON_MAX_LINK_BW_MASK (0x3F << 0) +# define DP_PCON_FRL_BW_MASK_9GBPS (1 << 0) +# define DP_PCON_FRL_BW_MASK_18GBPS (1 << 1) +# define DP_PCON_FRL_BW_MASK_24GBPS (1 << 2) +# define DP_PCON_FRL_BW_MASK_32GBPS (1 << 3) +# define DP_PCON_FRL_BW_MASK_40GBPS (1 << 4) +# define DP_PCON_FRL_BW_MASK_48GBPS (1 << 5) +# define DP_PCON_FRL_LINK_TRAIN_EXTENDED (1 << 6) +# define DP_PCON_FRL_LINK_TRAIN_NORMAL (0 << 6) + +/* PCON HDMI LINK STATUS */ +#define DP_PCON_HDMI_TX_LINK_STATUS 0x303B +# define DP_PCON_HDMI_TX_LINK_ACTIVE (1 << 0) +# define DP_PCON_FRL_READY (1 << 1) + +/* PCON HDMI POST FRL STATUS */ +#define DP_PCON_HDMI_POST_FRL_STATUS 0x3036 +# define DP_PCON_HDMI_LINK_MODE (1 << 0) +# define DP_PCON_HDMI_MODE_TMDS 0 +# define DP_PCON_HDMI_MODE_FRL 1 +# define DP_PCON_HDMI_FRL_TRAINED_BW (0x3F << 1) +# define DP_PCON_FRL_TRAINED_BW_9GBPS (1 << 1) +# define DP_PCON_FRL_TRAINED_BW_18GBPS (1 << 2) +# define DP_PCON_FRL_TRAINED_BW_24GBPS (1 << 3) +# define DP_PCON_FRL_TRAINED_BW_32GBPS (1 << 4) +# define DP_PCON_FRL_TRAINED_BW_40GBPS (1 << 5) +# define DP_PCON_FRL_TRAINED_BW_48GBPS (1 << 6) + +#define DP_PROTOCOL_CONVERTER_CONTROL_0 0x3050 /* DP 1.3 */ +# define DP_HDMI_DVI_OUTPUT_CONFIG (1 << 0) /* DP 1.3 */ +#define DP_PROTOCOL_CONVERTER_CONTROL_1 0x3051 /* DP 1.3 */ +# define DP_CONVERSION_TO_YCBCR420_ENABLE (1 << 0) /* DP 1.3 */ +# define DP_HDMI_EDID_PROCESSING_DISABLE (1 << 1) /* DP 1.4 */ +# define DP_HDMI_AUTONOMOUS_SCRAMBLING_DISABLE (1 << 2) /* DP 1.4 */ +# define DP_HDMI_FORCE_SCRAMBLING (1 << 3) /* DP 1.4 */ +#define DP_PROTOCOL_CONVERTER_CONTROL_2 0x3052 /* DP 1.3 */ +# define DP_CONVERSION_TO_YCBCR422_ENABLE (1 << 0) /* DP 1.3 */ +# define DP_PCON_ENABLE_DSC_ENCODER (1 << 1) +# define DP_PCON_ENCODER_PPS_OVERRIDE_MASK (0x3 << 2) +# define DP_PCON_ENC_PPS_OVERRIDE_DISABLED 0 +# define DP_PCON_ENC_PPS_OVERRIDE_EN_PARAMS 1 +# define DP_PCON_ENC_PPS_OVERRIDE_EN_BUFFER 2 +# define DP_CONVERSION_RGB_YCBCR_MASK (7 << 4) +# define DP_CONVERSION_BT601_RGB_YCBCR_ENABLE (1 << 4) +# define DP_CONVERSION_BT709_RGB_YCBCR_ENABLE (1 << 5) +# define DP_CONVERSION_BT2020_RGB_YCBCR_ENABLE (1 << 6) + +/* PCON Downstream HDMI ERROR Status per Lane */ +#define DP_PCON_HDMI_ERROR_STATUS_LN0 0x3037 +#define DP_PCON_HDMI_ERROR_STATUS_LN1 0x3038 +#define DP_PCON_HDMI_ERROR_STATUS_LN2 0x3039 +#define DP_PCON_HDMI_ERROR_STATUS_LN3 0x303A +# define DP_PCON_HDMI_ERROR_COUNT_MASK (0x7 << 0) +# define DP_PCON_HDMI_ERROR_COUNT_THREE_PLUS (1 << 0) +# define DP_PCON_HDMI_ERROR_COUNT_TEN_PLUS (1 << 1) +# define DP_PCON_HDMI_ERROR_COUNT_HUNDRED_PLUS (1 << 2) + +/* PCON HDMI CONFIG PPS Override Buffer + * Valid Offsets to be added to Base : 0-127 + */ +#define DP_PCON_HDMI_PPS_OVERRIDE_BASE 0x3100 + +/* PCON HDMI CONFIG PPS Override Parameter: Slice height + * Offset-0 8LSBs of the Slice height. + * Offset-1 8MSBs of the Slice height. + */ +#define DP_PCON_HDMI_PPS_OVRD_SLICE_HEIGHT 0x3180 + +/* PCON HDMI CONFIG PPS Override Parameter: Slice width + * Offset-0 8LSBs of the Slice width. + * Offset-1 8MSBs of the Slice width. + */ +#define DP_PCON_HDMI_PPS_OVRD_SLICE_WIDTH 0x3182 + +/* PCON HDMI CONFIG PPS Override Parameter: bits_per_pixel + * Offset-0 8LSBs of the bits_per_pixel. + * Offset-1 2MSBs of the bits_per_pixel. + */ +#define DP_PCON_HDMI_PPS_OVRD_BPP 0x3184 + +/* HDCP 1.3 and HDCP 2.2 */ +#define DP_AUX_HDCP_BKSV 0x68000 +#define DP_AUX_HDCP_RI_PRIME 0x68005 +#define DP_AUX_HDCP_AKSV 0x68007 +#define DP_AUX_HDCP_AN 0x6800C +#define DP_AUX_HDCP_V_PRIME(h) (0x68014 + h * 4) +#define DP_AUX_HDCP_BCAPS 0x68028 +# define DP_BCAPS_REPEATER_PRESENT BIT(1) +# define DP_BCAPS_HDCP_CAPABLE BIT(0) +#define DP_AUX_HDCP_BSTATUS 0x68029 +# define DP_BSTATUS_REAUTH_REQ BIT(3) +# define DP_BSTATUS_LINK_FAILURE BIT(2) +# define DP_BSTATUS_R0_PRIME_READY BIT(1) +# define DP_BSTATUS_READY BIT(0) +#define DP_AUX_HDCP_BINFO 0x6802A +#define DP_AUX_HDCP_KSV_FIFO 0x6802C +#define DP_AUX_HDCP_AINFO 0x6803B + +/* DP HDCP2.2 parameter offsets in DPCD address space */ +#define DP_HDCP_2_2_REG_RTX_OFFSET 0x69000 +#define DP_HDCP_2_2_REG_TXCAPS_OFFSET 0x69008 +#define DP_HDCP_2_2_REG_CERT_RX_OFFSET 0x6900B +#define DP_HDCP_2_2_REG_RRX_OFFSET 0x69215 +#define DP_HDCP_2_2_REG_RX_CAPS_OFFSET 0x6921D +#define DP_HDCP_2_2_REG_EKPUB_KM_OFFSET 0x69220 +#define DP_HDCP_2_2_REG_EKH_KM_WR_OFFSET 0x692A0 +#define DP_HDCP_2_2_REG_M_OFFSET 0x692B0 +#define DP_HDCP_2_2_REG_HPRIME_OFFSET 0x692C0 +#define DP_HDCP_2_2_REG_EKH_KM_RD_OFFSET 0x692E0 +#define DP_HDCP_2_2_REG_RN_OFFSET 0x692F0 +#define DP_HDCP_2_2_REG_LPRIME_OFFSET 0x692F8 +#define DP_HDCP_2_2_REG_EDKEY_KS_OFFSET 0x69318 +#define DP_HDCP_2_2_REG_RIV_OFFSET 0x69328 +#define DP_HDCP_2_2_REG_RXINFO_OFFSET 0x69330 +#define DP_HDCP_2_2_REG_SEQ_NUM_V_OFFSET 0x69332 +#define DP_HDCP_2_2_REG_VPRIME_OFFSET 0x69335 +#define DP_HDCP_2_2_REG_RECV_ID_LIST_OFFSET 0x69345 +#define DP_HDCP_2_2_REG_V_OFFSET 0x693E0 +#define DP_HDCP_2_2_REG_SEQ_NUM_M_OFFSET 0x693F0 +#define DP_HDCP_2_2_REG_K_OFFSET 0x693F3 +#define DP_HDCP_2_2_REG_STREAM_ID_TYPE_OFFSET 0x693F5 +#define DP_HDCP_2_2_REG_MPRIME_OFFSET 0x69473 +#define DP_HDCP_2_2_REG_RXSTATUS_OFFSET 0x69493 +#define DP_HDCP_2_2_REG_STREAM_TYPE_OFFSET 0x69494 +#define DP_HDCP_2_2_REG_DBG_OFFSET 0x69518 + +/* LTTPR: Link Training (LT)-tunable PHY Repeaters */ +#define DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV 0xf0000 /* 1.3 */ +#define DP_MAX_LINK_RATE_PHY_REPEATER 0xf0001 /* 1.4a */ +#define DP_PHY_REPEATER_CNT 0xf0002 /* 1.3 */ +#define DP_PHY_REPEATER_MODE 0xf0003 /* 1.3 */ +#define DP_MAX_LANE_COUNT_PHY_REPEATER 0xf0004 /* 1.4a */ +#define DP_Repeater_FEC_CAPABILITY 0xf0004 /* 1.4 */ +#define DP_PHY_REPEATER_EXTENDED_WAIT_TIMEOUT 0xf0005 /* 1.4a */ +#define DP_MAIN_LINK_CHANNEL_CODING_PHY_REPEATER 0xf0006 /* 2.0 */ +# define DP_PHY_REPEATER_128B132B_SUPPORTED (1 << 0) +/* See DP_128B132B_SUPPORTED_LINK_RATES for values */ +#define DP_PHY_REPEATER_128B132B_RATES 0xf0007 /* 2.0 */ +#define DP_PHY_REPEATER_EQ_DONE 0xf0008 /* 2.0 E11 */ + +enum drm_dp_phy { + DP_PHY_DPRX, + + DP_PHY_LTTPR1, + DP_PHY_LTTPR2, + DP_PHY_LTTPR3, + DP_PHY_LTTPR4, + DP_PHY_LTTPR5, + DP_PHY_LTTPR6, + DP_PHY_LTTPR7, + DP_PHY_LTTPR8, + + DP_MAX_LTTPR_COUNT = DP_PHY_LTTPR8, +}; + +#define DP_PHY_LTTPR(i) (DP_PHY_LTTPR1 + (i)) + +#define __DP_LTTPR1_BASE 0xf0010 /* 1.3 */ +#define __DP_LTTPR2_BASE 0xf0060 /* 1.3 */ +#define DP_LTTPR_BASE(dp_phy) \ + (__DP_LTTPR1_BASE + (__DP_LTTPR2_BASE - __DP_LTTPR1_BASE) * \ + ((dp_phy) - DP_PHY_LTTPR1)) + +#define DP_LTTPR_REG(dp_phy, lttpr1_reg) \ + (DP_LTTPR_BASE(dp_phy) - DP_LTTPR_BASE(DP_PHY_LTTPR1) + (lttpr1_reg)) + +#define DP_TRAINING_PATTERN_SET_PHY_REPEATER1 0xf0010 /* 1.3 */ +#define DP_TRAINING_PATTERN_SET_PHY_REPEATER(dp_phy) \ + DP_LTTPR_REG(dp_phy, DP_TRAINING_PATTERN_SET_PHY_REPEATER1) + +#define DP_TRAINING_LANE0_SET_PHY_REPEATER1 0xf0011 /* 1.3 */ +#define DP_TRAINING_LANE0_SET_PHY_REPEATER(dp_phy) \ + DP_LTTPR_REG(dp_phy, DP_TRAINING_LANE0_SET_PHY_REPEATER1) + +#define DP_TRAINING_LANE1_SET_PHY_REPEATER1 0xf0012 /* 1.3 */ +#define DP_TRAINING_LANE2_SET_PHY_REPEATER1 0xf0013 /* 1.3 */ +#define DP_TRAINING_LANE3_SET_PHY_REPEATER1 0xf0014 /* 1.3 */ +#define DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1 0xf0020 /* 1.4a */ +#define DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER(dp_phy) \ + DP_LTTPR_REG(dp_phy, DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1) + +#define DP_TRANSMITTER_CAPABILITY_PHY_REPEATER1 0xf0021 /* 1.4a */ +# define DP_VOLTAGE_SWING_LEVEL_3_SUPPORTED BIT(0) +# define DP_PRE_EMPHASIS_LEVEL_3_SUPPORTED BIT(1) + +#define DP_128B132B_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1 0xf0022 /* 2.0 */ +#define DP_128B132B_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER(dp_phy) \ + DP_LTTPR_REG(dp_phy, DP_128B132B_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1) +/* see DP_128B132B_TRAINING_AUX_RD_INTERVAL for values */ + +#define DP_LANE0_1_STATUS_PHY_REPEATER1 0xf0030 /* 1.3 */ +#define DP_LANE0_1_STATUS_PHY_REPEATER(dp_phy) \ + DP_LTTPR_REG(dp_phy, DP_LANE0_1_STATUS_PHY_REPEATER1) + +#define DP_LANE2_3_STATUS_PHY_REPEATER1 0xf0031 /* 1.3 */ + +#define DP_LANE_ALIGN_STATUS_UPDATED_PHY_REPEATER1 0xf0032 /* 1.3 */ +#define DP_ADJUST_REQUEST_LANE0_1_PHY_REPEATER1 0xf0033 /* 1.3 */ +#define DP_ADJUST_REQUEST_LANE2_3_PHY_REPEATER1 0xf0034 /* 1.3 */ +#define DP_SYMBOL_ERROR_COUNT_LANE0_PHY_REPEATER1 0xf0035 /* 1.3 */ +#define DP_SYMBOL_ERROR_COUNT_LANE1_PHY_REPEATER1 0xf0037 /* 1.3 */ +#define DP_SYMBOL_ERROR_COUNT_LANE2_PHY_REPEATER1 0xf0039 /* 1.3 */ +#define DP_SYMBOL_ERROR_COUNT_LANE3_PHY_REPEATER1 0xf003b /* 1.3 */ + +#define __DP_FEC1_BASE 0xf0290 /* 1.4 */ +#define __DP_FEC2_BASE 0xf0298 /* 1.4 */ +#define DP_FEC_BASE(dp_phy) \ + (__DP_FEC1_BASE + ((__DP_FEC2_BASE - __DP_FEC1_BASE) * \ + ((dp_phy) - DP_PHY_LTTPR1))) + +#define DP_FEC_REG(dp_phy, fec1_reg) \ + (DP_FEC_BASE(dp_phy) - DP_FEC_BASE(DP_PHY_LTTPR1) + fec1_reg) + +#define DP_FEC_STATUS_PHY_REPEATER1 0xf0290 /* 1.4 */ +#define DP_FEC_STATUS_PHY_REPEATER(dp_phy) \ + DP_FEC_REG(dp_phy, DP_FEC_STATUS_PHY_REPEATER1) + +#define DP_FEC_ERROR_COUNT_PHY_REPEATER1 0xf0291 /* 1.4 */ +#define DP_FEC_CAPABILITY_PHY_REPEATER1 0xf0294 /* 1.4a */ + +#define DP_LTTPR_MAX_ADD 0xf02ff /* 1.4 */ + +#define DP_DPCD_MAX_ADD 0xfffff /* 1.4 */ + +/* Repeater modes */ +#define DP_PHY_REPEATER_MODE_TRANSPARENT 0x55 /* 1.3 */ +#define DP_PHY_REPEATER_MODE_NON_TRANSPARENT 0xaa /* 1.3 */ + +/* DP HDCP message start offsets in DPCD address space */ +#define DP_HDCP_2_2_AKE_INIT_OFFSET DP_HDCP_2_2_REG_RTX_OFFSET +#define DP_HDCP_2_2_AKE_SEND_CERT_OFFSET DP_HDCP_2_2_REG_CERT_RX_OFFSET +#define DP_HDCP_2_2_AKE_NO_STORED_KM_OFFSET DP_HDCP_2_2_REG_EKPUB_KM_OFFSET +#define DP_HDCP_2_2_AKE_STORED_KM_OFFSET DP_HDCP_2_2_REG_EKH_KM_WR_OFFSET +#define DP_HDCP_2_2_AKE_SEND_HPRIME_OFFSET DP_HDCP_2_2_REG_HPRIME_OFFSET +#define DP_HDCP_2_2_AKE_SEND_PAIRING_INFO_OFFSET \ + DP_HDCP_2_2_REG_EKH_KM_RD_OFFSET +#define DP_HDCP_2_2_LC_INIT_OFFSET DP_HDCP_2_2_REG_RN_OFFSET +#define DP_HDCP_2_2_LC_SEND_LPRIME_OFFSET DP_HDCP_2_2_REG_LPRIME_OFFSET +#define DP_HDCP_2_2_SKE_SEND_EKS_OFFSET DP_HDCP_2_2_REG_EDKEY_KS_OFFSET +#define DP_HDCP_2_2_REP_SEND_RECVID_LIST_OFFSET DP_HDCP_2_2_REG_RXINFO_OFFSET +#define DP_HDCP_2_2_REP_SEND_ACK_OFFSET DP_HDCP_2_2_REG_V_OFFSET +#define DP_HDCP_2_2_REP_STREAM_MANAGE_OFFSET DP_HDCP_2_2_REG_SEQ_NUM_M_OFFSET +#define DP_HDCP_2_2_REP_STREAM_READY_OFFSET DP_HDCP_2_2_REG_MPRIME_OFFSET + +#define HDCP_2_2_DP_RXSTATUS_LEN 1 +#define HDCP_2_2_DP_RXSTATUS_READY(x) ((x) & BIT(0)) +#define HDCP_2_2_DP_RXSTATUS_H_PRIME(x) ((x) & BIT(1)) +#define HDCP_2_2_DP_RXSTATUS_PAIRING(x) ((x) & BIT(2)) +#define HDCP_2_2_DP_RXSTATUS_REAUTH_REQ(x) ((x) & BIT(3)) +#define HDCP_2_2_DP_RXSTATUS_LINK_FAILED(x) ((x) & BIT(4)) + +/* DP 1.2 Sideband message defines */ +/* peer device type - DP 1.2a Table 2-92 */ +#define DP_PEER_DEVICE_NONE 0x0 +#define DP_PEER_DEVICE_SOURCE_OR_SST 0x1 +#define DP_PEER_DEVICE_MST_BRANCHING 0x2 +#define DP_PEER_DEVICE_SST_SINK 0x3 +#define DP_PEER_DEVICE_DP_LEGACY_CONV 0x4 + +/* DP 1.2 MST sideband request names DP 1.2a Table 2-80 */ +#define DP_GET_MSG_TRANSACTION_VERSION 0x00 /* DP 1.3 */ +#define DP_LINK_ADDRESS 0x01 +#define DP_CONNECTION_STATUS_NOTIFY 0x02 +#define DP_ENUM_PATH_RESOURCES 0x10 +#define DP_ALLOCATE_PAYLOAD 0x11 +#define DP_QUERY_PAYLOAD 0x12 +#define DP_RESOURCE_STATUS_NOTIFY 0x13 +#define DP_CLEAR_PAYLOAD_ID_TABLE 0x14 +#define DP_REMOTE_DPCD_READ 0x20 +#define DP_REMOTE_DPCD_WRITE 0x21 +#define DP_REMOTE_I2C_READ 0x22 +#define DP_REMOTE_I2C_WRITE 0x23 +#define DP_POWER_UP_PHY 0x24 +#define DP_POWER_DOWN_PHY 0x25 +#define DP_SINK_EVENT_NOTIFY 0x30 +#define DP_QUERY_STREAM_ENC_STATUS 0x38 +#define DP_QUERY_STREAM_ENC_STATUS_STATE_NO_EXIST 0 +#define DP_QUERY_STREAM_ENC_STATUS_STATE_INACTIVE 1 +#define DP_QUERY_STREAM_ENC_STATUS_STATE_ACTIVE 2 + +/* DP 1.2 MST sideband reply types */ +#define DP_SIDEBAND_REPLY_ACK 0x00 +#define DP_SIDEBAND_REPLY_NAK 0x01 + +/* DP 1.2 MST sideband nak reasons - table 2.84 */ +#define DP_NAK_WRITE_FAILURE 0x01 +#define DP_NAK_INVALID_READ 0x02 +#define DP_NAK_CRC_FAILURE 0x03 +#define DP_NAK_BAD_PARAM 0x04 +#define DP_NAK_DEFER 0x05 +#define DP_NAK_LINK_FAILURE 0x06 +#define DP_NAK_NO_RESOURCES 0x07 +#define DP_NAK_DPCD_FAIL 0x08 +#define DP_NAK_I2C_NAK 0x09 +#define DP_NAK_ALLOCATE_FAIL 0x0a + +#define MODE_I2C_START 1 +#define MODE_I2C_WRITE 2 +#define MODE_I2C_READ 4 +#define MODE_I2C_STOP 8 + +/* DP 1.2 MST PORTs - Section 2.5.1 v1.2a spec */ +#define DP_MST_PHYSICAL_PORT_0 0 +#define DP_MST_LOGICAL_PORT_0 8 + +#define DP_LINK_CONSTANT_N_VALUE 0x8000 +#define DP_LINK_STATUS_SIZE 6 +bool drm_dp_channel_eq_ok(const u8 link_status[DP_LINK_STATUS_SIZE], + int lane_count); +bool drm_dp_clock_recovery_ok(const u8 link_status[DP_LINK_STATUS_SIZE], + int lane_count); +u8 drm_dp_get_adjust_request_voltage(const u8 link_status[DP_LINK_STATUS_SIZE], + int lane); +u8 drm_dp_get_adjust_request_pre_emphasis(const u8 link_status[DP_LINK_STATUS_SIZE], + int lane); +u8 drm_dp_get_adjust_tx_ffe_preset(const u8 link_status[DP_LINK_STATUS_SIZE], + int lane); + +#define DP_BRANCH_OUI_HEADER_SIZE 0xc +#define DP_RECEIVER_CAP_SIZE 0xf +#define DP_DSC_RECEIVER_CAP_SIZE 0xf +#define EDP_PSR_RECEIVER_CAP_SIZE 2 +#define EDP_DISPLAY_CTL_CAP_SIZE 3 +#define DP_LTTPR_COMMON_CAP_SIZE 8 +#define DP_LTTPR_PHY_CAP_SIZE 3 + +int drm_dp_read_clock_recovery_delay(struct drm_dp_aux *aux, const u8 dpcd[DP_RECEIVER_CAP_SIZE], + enum drm_dp_phy dp_phy, bool uhbr); +int drm_dp_read_channel_eq_delay(struct drm_dp_aux *aux, const u8 dpcd[DP_RECEIVER_CAP_SIZE], + enum drm_dp_phy dp_phy, bool uhbr); + +void drm_dp_link_train_clock_recovery_delay(const struct drm_dp_aux *aux, + const u8 dpcd[DP_RECEIVER_CAP_SIZE]); +void drm_dp_lttpr_link_train_clock_recovery_delay(void); +void drm_dp_link_train_channel_eq_delay(const struct drm_dp_aux *aux, + const u8 dpcd[DP_RECEIVER_CAP_SIZE]); +void drm_dp_lttpr_link_train_channel_eq_delay(const struct drm_dp_aux *aux, + const u8 caps[DP_LTTPR_PHY_CAP_SIZE]); + +int drm_dp_128b132b_read_aux_rd_interval(struct drm_dp_aux *aux); +bool drm_dp_128b132b_lane_channel_eq_done(const u8 link_status[DP_LINK_STATUS_SIZE], + int lane_count); +bool drm_dp_128b132b_lane_symbol_locked(const u8 link_status[DP_LINK_STATUS_SIZE], + int lane_count); +bool drm_dp_128b132b_eq_interlane_align_done(const u8 link_status[DP_LINK_STATUS_SIZE]); +bool drm_dp_128b132b_cds_interlane_align_done(const u8 link_status[DP_LINK_STATUS_SIZE]); +bool drm_dp_128b132b_link_training_failed(const u8 link_status[DP_LINK_STATUS_SIZE]); + +u8 drm_dp_link_rate_to_bw_code(int link_rate); +int drm_dp_bw_code_to_link_rate(u8 link_bw); + +#define DP_SDP_AUDIO_TIMESTAMP 0x01 +#define DP_SDP_AUDIO_STREAM 0x02 +#define DP_SDP_EXTENSION 0x04 /* DP 1.1 */ +#define DP_SDP_AUDIO_COPYMANAGEMENT 0x05 /* DP 1.2 */ +#define DP_SDP_ISRC 0x06 /* DP 1.2 */ +#define DP_SDP_VSC 0x07 /* DP 1.2 */ +#define DP_SDP_CAMERA_GENERIC(i) (0x08 + (i)) /* 0-7, DP 1.3 */ +#define DP_SDP_PPS 0x10 /* DP 1.4 */ +#define DP_SDP_VSC_EXT_VESA 0x20 /* DP 1.4 */ +#define DP_SDP_VSC_EXT_CEA 0x21 /* DP 1.4 */ +/* 0x80+ CEA-861 infoframe types */ + +/** + * struct dp_sdp_header - DP secondary data packet header + * @HB0: Secondary Data Packet ID + * @HB1: Secondary Data Packet Type + * @HB2: Secondary Data Packet Specific header, Byte 0 + * @HB3: Secondary Data packet Specific header, Byte 1 + */ +struct dp_sdp_header { + u8 HB0; + u8 HB1; + u8 HB2; + u8 HB3; +} __packed; + +#define EDP_SDP_HEADER_REVISION_MASK 0x1F +#define EDP_SDP_HEADER_VALID_PAYLOAD_BYTES 0x1F +#define DP_SDP_PPS_HEADER_PAYLOAD_BYTES_MINUS_1 0x7F + +/** + * struct dp_sdp - DP secondary data packet + * @sdp_header: DP secondary data packet header + * @db: DP secondaray data packet data blocks + * VSC SDP Payload for PSR + * db[0]: Stereo Interface + * db[1]: 0 - PSR State; 1 - Update RFB; 2 - CRC Valid + * db[2]: CRC value bits 7:0 of the R or Cr component + * db[3]: CRC value bits 15:8 of the R or Cr component + * db[4]: CRC value bits 7:0 of the G or Y component + * db[5]: CRC value bits 15:8 of the G or Y component + * db[6]: CRC value bits 7:0 of the B or Cb component + * db[7]: CRC value bits 15:8 of the B or Cb component + * db[8] - db[31]: Reserved + * VSC SDP Payload for Pixel Encoding/Colorimetry Format + * db[0] - db[15]: Reserved + * db[16]: Pixel Encoding and Colorimetry Formats + * db[17]: Dynamic Range and Component Bit Depth + * db[18]: Content Type + * db[19] - db[31]: Reserved + */ +struct dp_sdp { + struct dp_sdp_header sdp_header; + u8 db[32]; +} __packed; + +#define EDP_VSC_PSR_STATE_ACTIVE (1<<0) +#define EDP_VSC_PSR_UPDATE_RFB (1<<1) +#define EDP_VSC_PSR_CRC_VALUES_VALID (1<<2) + +/** + * enum dp_pixelformat - drm DP Pixel encoding formats + * + * This enum is used to indicate DP VSC SDP Pixel encoding formats. + * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through + * DB18] + * + * @DP_PIXELFORMAT_RGB: RGB pixel encoding format + * @DP_PIXELFORMAT_YUV444: YCbCr 4:4:4 pixel encoding format + * @DP_PIXELFORMAT_YUV422: YCbCr 4:2:2 pixel encoding format + * @DP_PIXELFORMAT_YUV420: YCbCr 4:2:0 pixel encoding format + * @DP_PIXELFORMAT_Y_ONLY: Y Only pixel encoding format + * @DP_PIXELFORMAT_RAW: RAW pixel encoding format + * @DP_PIXELFORMAT_RESERVED: Reserved pixel encoding format + */ +enum dp_pixelformat { + DP_PIXELFORMAT_RGB = 0, + DP_PIXELFORMAT_YUV444 = 0x1, + DP_PIXELFORMAT_YUV422 = 0x2, + DP_PIXELFORMAT_YUV420 = 0x3, + DP_PIXELFORMAT_Y_ONLY = 0x4, + DP_PIXELFORMAT_RAW = 0x5, + DP_PIXELFORMAT_RESERVED = 0x6, +}; + +/** + * enum dp_colorimetry - drm DP Colorimetry formats + * + * This enum is used to indicate DP VSC SDP Colorimetry formats. + * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through + * DB18] and a name of enum member follows DRM_MODE_COLORIMETRY definition. + * + * @DP_COLORIMETRY_DEFAULT: sRGB (IEC 61966-2-1) or + * ITU-R BT.601 colorimetry format + * @DP_COLORIMETRY_RGB_WIDE_FIXED: RGB wide gamut fixed point colorimetry format + * @DP_COLORIMETRY_BT709_YCC: ITU-R BT.709 colorimetry format + * @DP_COLORIMETRY_RGB_WIDE_FLOAT: RGB wide gamut floating point + * (scRGB (IEC 61966-2-2)) colorimetry format + * @DP_COLORIMETRY_XVYCC_601: xvYCC601 colorimetry format + * @DP_COLORIMETRY_OPRGB: OpRGB colorimetry format + * @DP_COLORIMETRY_XVYCC_709: xvYCC709 colorimetry format + * @DP_COLORIMETRY_DCI_P3_RGB: DCI-P3 (SMPTE RP 431-2) colorimetry format + * @DP_COLORIMETRY_SYCC_601: sYCC601 colorimetry format + * @DP_COLORIMETRY_RGB_CUSTOM: RGB Custom Color Profile colorimetry format + * @DP_COLORIMETRY_OPYCC_601: opYCC601 colorimetry format + * @DP_COLORIMETRY_BT2020_RGB: ITU-R BT.2020 R' G' B' colorimetry format + * @DP_COLORIMETRY_BT2020_CYCC: ITU-R BT.2020 Y'c C'bc C'rc colorimetry format + * @DP_COLORIMETRY_BT2020_YCC: ITU-R BT.2020 Y' C'b C'r colorimetry format + */ +enum dp_colorimetry { + DP_COLORIMETRY_DEFAULT = 0, + DP_COLORIMETRY_RGB_WIDE_FIXED = 0x1, + DP_COLORIMETRY_BT709_YCC = 0x1, + DP_COLORIMETRY_RGB_WIDE_FLOAT = 0x2, + DP_COLORIMETRY_XVYCC_601 = 0x2, + DP_COLORIMETRY_OPRGB = 0x3, + DP_COLORIMETRY_XVYCC_709 = 0x3, + DP_COLORIMETRY_DCI_P3_RGB = 0x4, + DP_COLORIMETRY_SYCC_601 = 0x4, + DP_COLORIMETRY_RGB_CUSTOM = 0x5, + DP_COLORIMETRY_OPYCC_601 = 0x5, + DP_COLORIMETRY_BT2020_RGB = 0x6, + DP_COLORIMETRY_BT2020_CYCC = 0x6, + DP_COLORIMETRY_BT2020_YCC = 0x7, +}; + +/** + * enum dp_dynamic_range - drm DP Dynamic Range + * + * This enum is used to indicate DP VSC SDP Dynamic Range. + * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through + * DB18] + * + * @DP_DYNAMIC_RANGE_VESA: VESA range + * @DP_DYNAMIC_RANGE_CTA: CTA range + */ +enum dp_dynamic_range { + DP_DYNAMIC_RANGE_VESA = 0, + DP_DYNAMIC_RANGE_CTA = 1, +}; + +/** + * enum dp_content_type - drm DP Content Type + * + * This enum is used to indicate DP VSC SDP Content Types. + * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through + * DB18] + * CTA-861-G defines content types and expected processing by a sink device + * + * @DP_CONTENT_TYPE_NOT_DEFINED: Not defined type + * @DP_CONTENT_TYPE_GRAPHICS: Graphics type + * @DP_CONTENT_TYPE_PHOTO: Photo type + * @DP_CONTENT_TYPE_VIDEO: Video type + * @DP_CONTENT_TYPE_GAME: Game type + */ +enum dp_content_type { + DP_CONTENT_TYPE_NOT_DEFINED = 0x00, + DP_CONTENT_TYPE_GRAPHICS = 0x01, + DP_CONTENT_TYPE_PHOTO = 0x02, + DP_CONTENT_TYPE_VIDEO = 0x03, + DP_CONTENT_TYPE_GAME = 0x04, +}; + +/** + * struct drm_dp_vsc_sdp - drm DP VSC SDP + * + * This structure represents a DP VSC SDP of drm + * It is based on DP 1.4 spec [Table 2-116: VSC SDP Header Bytes] and + * [Table 2-117: VSC SDP Payload for DB16 through DB18] + * + * @sdp_type: secondary-data packet type + * @revision: revision number + * @length: number of valid data bytes + * @pixelformat: pixel encoding format + * @colorimetry: colorimetry format + * @bpc: bit per color + * @dynamic_range: dynamic range information + * @content_type: CTA-861-G defines content types and expected processing by a sink device + */ +struct drm_dp_vsc_sdp { + unsigned char sdp_type; + unsigned char revision; + unsigned char length; + enum dp_pixelformat pixelformat; + enum dp_colorimetry colorimetry; + int bpc; + enum dp_dynamic_range dynamic_range; + enum dp_content_type content_type; +}; + +void drm_dp_vsc_sdp_log(const char *level, struct device *dev, + const struct drm_dp_vsc_sdp *vsc); + +int drm_dp_psr_setup_time(const u8 psr_cap[EDP_PSR_RECEIVER_CAP_SIZE]); + +static inline int +drm_dp_max_link_rate(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return drm_dp_bw_code_to_link_rate(dpcd[DP_MAX_LINK_RATE]); +} + +static inline u8 +drm_dp_max_lane_count(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return dpcd[DP_MAX_LANE_COUNT] & DP_MAX_LANE_COUNT_MASK; +} + +static inline bool +drm_dp_enhanced_frame_cap(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return dpcd[DP_DPCD_REV] >= 0x11 && + (dpcd[DP_MAX_LANE_COUNT] & DP_ENHANCED_FRAME_CAP); +} + +static inline bool +drm_dp_fast_training_cap(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return dpcd[DP_DPCD_REV] >= 0x11 && + (dpcd[DP_MAX_DOWNSPREAD] & DP_NO_AUX_HANDSHAKE_LINK_TRAINING); +} + +static inline bool +drm_dp_tps3_supported(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return dpcd[DP_DPCD_REV] >= 0x12 && + dpcd[DP_MAX_LANE_COUNT] & DP_TPS3_SUPPORTED; +} + +static inline bool +drm_dp_max_downspread(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return dpcd[DP_DPCD_REV] >= 0x11 || + dpcd[DP_MAX_DOWNSPREAD] & DP_MAX_DOWNSPREAD_0_5; +} + +static inline bool +drm_dp_tps4_supported(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return dpcd[DP_DPCD_REV] >= 0x14 && + dpcd[DP_MAX_DOWNSPREAD] & DP_TPS4_SUPPORTED; +} + +static inline u8 +drm_dp_training_pattern_mask(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return (dpcd[DP_DPCD_REV] >= 0x14) ? DP_TRAINING_PATTERN_MASK_1_4 : + DP_TRAINING_PATTERN_MASK; +} + +static inline bool +drm_dp_is_branch(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_PRESENT; +} + +/* DP/eDP DSC support */ +u8 drm_dp_dsc_sink_max_slice_count(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE], + bool is_edp); +u8 drm_dp_dsc_sink_line_buf_depth(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]); +int drm_dp_dsc_sink_supported_input_bpcs(const u8 dsc_dpc[DP_DSC_RECEIVER_CAP_SIZE], + u8 dsc_bpc[3]); + +static inline bool +drm_dp_sink_supports_dsc(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]) +{ + return dsc_dpcd[DP_DSC_SUPPORT - DP_DSC_SUPPORT] & + DP_DSC_DECOMPRESSION_IS_SUPPORTED; +} + +static inline u16 +drm_edp_dsc_sink_output_bpp(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]) +{ + return dsc_dpcd[DP_DSC_MAX_BITS_PER_PIXEL_LOW - DP_DSC_SUPPORT] | + (dsc_dpcd[DP_DSC_MAX_BITS_PER_PIXEL_HI - DP_DSC_SUPPORT] & + DP_DSC_MAX_BITS_PER_PIXEL_HI_MASK << + DP_DSC_MAX_BITS_PER_PIXEL_HI_SHIFT); +} + +static inline u32 +drm_dp_dsc_sink_max_slice_width(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]) +{ + /* Max Slicewidth = Number of Pixels * 320 */ + return dsc_dpcd[DP_DSC_MAX_SLICE_WIDTH - DP_DSC_SUPPORT] * + DP_DSC_SLICE_WIDTH_MULTIPLIER; +} + +/* Forward Error Correction Support on DP 1.4 */ +static inline bool +drm_dp_sink_supports_fec(const u8 fec_capable) +{ + return fec_capable & DP_FEC_CAPABLE; +} + +static inline bool +drm_dp_channel_coding_supported(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return dpcd[DP_MAIN_LINK_CHANNEL_CODING] & DP_CAP_ANSI_8B10B; +} + +static inline bool +drm_dp_alternate_scrambler_reset_cap(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return dpcd[DP_EDP_CONFIGURATION_CAP] & + DP_ALTERNATE_SCRAMBLER_RESET_CAP; +} + +/* Ignore MSA timing for Adaptive Sync support on DP 1.4 */ +static inline bool +drm_dp_sink_can_do_video_without_timing_msa(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + return dpcd[DP_DOWN_STREAM_PORT_COUNT] & + DP_MSA_TIMING_PAR_IGNORED; +} + +/** + * drm_edp_backlight_supported() - Check an eDP DPCD for VESA backlight support + * @edp_dpcd: The DPCD to check + * + * Note that currently this function will return %false for panels which support various DPCD + * backlight features but which require the brightness be set through PWM, and don't support setting + * the brightness level via the DPCD. + * + * Returns: %True if @edp_dpcd indicates that VESA backlight controls are supported, %false + * otherwise + */ +static inline bool +drm_edp_backlight_supported(const u8 edp_dpcd[EDP_DISPLAY_CTL_CAP_SIZE]) +{ + return !!(edp_dpcd[1] & DP_EDP_TCON_BACKLIGHT_ADJUSTMENT_CAP); +} + +/* + * DisplayPort AUX channel + */ + +/** + * struct drm_dp_aux_msg - DisplayPort AUX channel transaction + * @address: address of the (first) register to access + * @request: contains the type of transaction (see DP_AUX_* macros) + * @reply: upon completion, contains the reply type of the transaction + * @buffer: pointer to a transmission or reception buffer + * @size: size of @buffer + */ +struct drm_dp_aux_msg { + unsigned int address; + u8 request; + u8 reply; + void *buffer; + size_t size; +}; + +struct cec_adapter; +struct edid; +struct drm_connector; + +/** + * struct drm_dp_aux_cec - DisplayPort CEC-Tunneling-over-AUX + * @lock: mutex protecting this struct + * @adap: the CEC adapter for CEC-Tunneling-over-AUX support. + * @connector: the connector this CEC adapter is associated with + * @unregister_work: unregister the CEC adapter + */ +struct drm_dp_aux_cec { + struct mutex lock; + struct cec_adapter *adap; + struct drm_connector *connector; + struct delayed_work unregister_work; +}; + +/** + * struct drm_dp_aux - DisplayPort AUX channel + * + * An AUX channel can also be used to transport I2C messages to a sink. A + * typical application of that is to access an EDID that's present in the sink + * device. The @transfer() function can also be used to execute such + * transactions. The drm_dp_aux_register() function registers an I2C adapter + * that can be passed to drm_probe_ddc(). Upon removal, drivers should call + * drm_dp_aux_unregister() to remove the I2C adapter. The I2C adapter uses long + * transfers by default; if a partial response is received, the adapter will + * drop down to the size given by the partial response for this transaction + * only. + */ +struct drm_dp_aux { + /** + * @name: user-visible name of this AUX channel and the + * I2C-over-AUX adapter. + * + * It's also used to specify the name of the I2C adapter. If set + * to %NULL, dev_name() of @dev will be used. + */ + const char *name; + + /** + * @ddc: I2C adapter that can be used for I2C-over-AUX + * communication + */ + struct i2c_adapter ddc; + + /** + * @dev: pointer to struct device that is the parent for this + * AUX channel. + */ + struct device *dev; + + /** + * @drm_dev: pointer to the &drm_device that owns this AUX channel. + * Beware, this may be %NULL before drm_dp_aux_register() has been + * called. + * + * It should be set to the &drm_device that will be using this AUX + * channel as early as possible. For many graphics drivers this should + * happen before drm_dp_aux_init(), however it's perfectly fine to set + * this field later so long as it's assigned before calling + * drm_dp_aux_register(). + */ + struct drm_device *drm_dev; + + /** + * @crtc: backpointer to the crtc that is currently using this + * AUX channel + */ + struct drm_crtc *crtc; + + /** + * @hw_mutex: internal mutex used for locking transfers. + * + * Note that if the underlying hardware is shared among multiple + * channels, the driver needs to do additional locking to + * prevent concurrent access. + */ + struct mutex hw_mutex; + + /** + * @crc_work: worker that captures CRCs for each frame + */ + struct work_struct crc_work; + + /** + * @crc_count: counter of captured frame CRCs + */ + u8 crc_count; + + /** + * @transfer: transfers a message representing a single AUX + * transaction. + * + * This is a hardware-specific implementation of how + * transactions are executed that the drivers must provide. + * + * A pointer to a &drm_dp_aux_msg structure describing the + * transaction is passed into this function. Upon success, the + * implementation should return the number of payload bytes that + * were transferred, or a negative error-code on failure. + * + * Helpers will propagate these errors, with the exception of + * the %-EBUSY error, which causes a transaction to be retried. + * On a short, helpers will return %-EPROTO to make it simpler + * to check for failure. + * + * The @transfer() function must only modify the reply field of + * the &drm_dp_aux_msg structure. The retry logic and i2c + * helpers assume this is the case. + * + * Also note that this callback can be called no matter the + * state @dev is in. Drivers that need that device to be powered + * to perform this operation will first need to make sure it's + * been properly enabled. + */ + ssize_t (*transfer)(struct drm_dp_aux *aux, + struct drm_dp_aux_msg *msg); + + /** + * @i2c_nack_count: Counts I2C NACKs, used for DP validation. + */ + unsigned i2c_nack_count; + /** + * @i2c_defer_count: Counts I2C DEFERs, used for DP validation. + */ + unsigned i2c_defer_count; + /** + * @cec: struct containing fields used for CEC-Tunneling-over-AUX. + */ + struct drm_dp_aux_cec cec; + /** + * @is_remote: Is this AUX CH actually using sideband messaging. + */ + bool is_remote; +}; + +int drm_dp_dpcd_probe(struct drm_dp_aux *aux, unsigned int offset); +ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset, + void *buffer, size_t size); +ssize_t drm_dp_dpcd_write(struct drm_dp_aux *aux, unsigned int offset, + void *buffer, size_t size); + +/** + * drm_dp_dpcd_readb() - read a single byte from the DPCD + * @aux: DisplayPort AUX channel + * @offset: address of the register to read + * @valuep: location where the value of the register will be stored + * + * Returns the number of bytes transferred (1) on success, or a negative + * error code on failure. + */ +static inline ssize_t drm_dp_dpcd_readb(struct drm_dp_aux *aux, + unsigned int offset, u8 *valuep) +{ + return drm_dp_dpcd_read(aux, offset, valuep, 1); +} + +/** + * drm_dp_dpcd_writeb() - write a single byte to the DPCD + * @aux: DisplayPort AUX channel + * @offset: address of the register to write + * @value: value to write to the register + * + * Returns the number of bytes transferred (1) on success, or a negative + * error code on failure. + */ +static inline ssize_t drm_dp_dpcd_writeb(struct drm_dp_aux *aux, + unsigned int offset, u8 value) +{ + return drm_dp_dpcd_write(aux, offset, &value, 1); +} + +int drm_dp_read_dpcd_caps(struct drm_dp_aux *aux, + u8 dpcd[DP_RECEIVER_CAP_SIZE]); + +int drm_dp_dpcd_read_link_status(struct drm_dp_aux *aux, + u8 status[DP_LINK_STATUS_SIZE]); + +int drm_dp_dpcd_read_phy_link_status(struct drm_dp_aux *aux, + enum drm_dp_phy dp_phy, + u8 link_status[DP_LINK_STATUS_SIZE]); + +bool drm_dp_send_real_edid_checksum(struct drm_dp_aux *aux, + u8 real_edid_checksum); + +int drm_dp_read_downstream_info(struct drm_dp_aux *aux, + const u8 dpcd[DP_RECEIVER_CAP_SIZE], + u8 downstream_ports[DP_MAX_DOWNSTREAM_PORTS]); +bool drm_dp_downstream_is_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], u8 type); +bool drm_dp_downstream_is_tmds(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], + const struct edid *edid); +int drm_dp_downstream_max_dotclock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]); +int drm_dp_downstream_max_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], + const struct edid *edid); +int drm_dp_downstream_min_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], + const struct edid *edid); +int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], + const struct edid *edid); +bool drm_dp_downstream_420_passthrough(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]); +bool drm_dp_downstream_444_to_420_conversion(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]); +struct drm_display_mode *drm_dp_downstream_mode(struct drm_device *dev, + const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]); +int drm_dp_downstream_id(struct drm_dp_aux *aux, char id[6]); +void drm_dp_downstream_debug(struct seq_file *m, + const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], + const struct edid *edid, + struct drm_dp_aux *aux); +enum drm_mode_subconnector +drm_dp_subconnector_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]); +void drm_dp_set_subconnector_property(struct drm_connector *connector, + enum drm_connector_status status, + const u8 *dpcd, + const u8 port_cap[4]); + +struct drm_dp_desc; +bool drm_dp_read_sink_count_cap(struct drm_connector *connector, + const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const struct drm_dp_desc *desc); +int drm_dp_read_sink_count(struct drm_dp_aux *aux); + +int drm_dp_read_lttpr_common_caps(struct drm_dp_aux *aux, + const u8 dpcd[DP_RECEIVER_CAP_SIZE], + u8 caps[DP_LTTPR_COMMON_CAP_SIZE]); +int drm_dp_read_lttpr_phy_caps(struct drm_dp_aux *aux, + const u8 dpcd[DP_RECEIVER_CAP_SIZE], + enum drm_dp_phy dp_phy, + u8 caps[DP_LTTPR_PHY_CAP_SIZE]); +int drm_dp_lttpr_count(const u8 cap[DP_LTTPR_COMMON_CAP_SIZE]); +int drm_dp_lttpr_max_link_rate(const u8 caps[DP_LTTPR_COMMON_CAP_SIZE]); +int drm_dp_lttpr_max_lane_count(const u8 caps[DP_LTTPR_COMMON_CAP_SIZE]); +bool drm_dp_lttpr_voltage_swing_level_3_supported(const u8 caps[DP_LTTPR_PHY_CAP_SIZE]); +bool drm_dp_lttpr_pre_emphasis_level_3_supported(const u8 caps[DP_LTTPR_PHY_CAP_SIZE]); + +void drm_dp_remote_aux_init(struct drm_dp_aux *aux); +void drm_dp_aux_init(struct drm_dp_aux *aux); +int drm_dp_aux_register(struct drm_dp_aux *aux); +void drm_dp_aux_unregister(struct drm_dp_aux *aux); + +int drm_dp_start_crc(struct drm_dp_aux *aux, struct drm_crtc *crtc); +int drm_dp_stop_crc(struct drm_dp_aux *aux); + +struct drm_dp_dpcd_ident { + u8 oui[3]; + u8 device_id[6]; + u8 hw_rev; + u8 sw_major_rev; + u8 sw_minor_rev; +} __packed; + +/** + * struct drm_dp_desc - DP branch/sink device descriptor + * @ident: DP device identification from DPCD 0x400 (sink) or 0x500 (branch). + * @quirks: Quirks; use drm_dp_has_quirk() to query for the quirks. + */ +struct drm_dp_desc { + struct drm_dp_dpcd_ident ident; + u32 quirks; +}; + +int drm_dp_read_desc(struct drm_dp_aux *aux, struct drm_dp_desc *desc, + bool is_branch); + +/** + * enum drm_dp_quirk - Display Port sink/branch device specific quirks + * + * Display Port sink and branch devices in the wild have a variety of bugs, try + * to collect them here. The quirks are shared, but it's up to the drivers to + * implement workarounds for them. + */ +enum drm_dp_quirk { + /** + * @DP_DPCD_QUIRK_CONSTANT_N: + * + * The device requires main link attributes Mvid and Nvid to be limited + * to 16 bits. So will give a constant value (0x8000) for compatability. + */ + DP_DPCD_QUIRK_CONSTANT_N, + /** + * @DP_DPCD_QUIRK_NO_PSR: + * + * The device does not support PSR even if reports that it supports or + * driver still need to implement proper handling for such device. + */ + DP_DPCD_QUIRK_NO_PSR, + /** + * @DP_DPCD_QUIRK_NO_SINK_COUNT: + * + * The device does not set SINK_COUNT to a non-zero value. + * The driver should ignore SINK_COUNT during detection. Note that + * drm_dp_read_sink_count_cap() automatically checks for this quirk. + */ + DP_DPCD_QUIRK_NO_SINK_COUNT, + /** + * @DP_DPCD_QUIRK_DSC_WITHOUT_VIRTUAL_DPCD: + * + * The device supports MST DSC despite not supporting Virtual DPCD. + * The DSC caps can be read from the physical aux instead. + */ + DP_DPCD_QUIRK_DSC_WITHOUT_VIRTUAL_DPCD, + /** + * @DP_DPCD_QUIRK_CAN_DO_MAX_LINK_RATE_3_24_GBPS: + * + * The device supports a link rate of 3.24 Gbps (multiplier 0xc) despite + * the DP_MAX_LINK_RATE register reporting a lower max multiplier. + */ + DP_DPCD_QUIRK_CAN_DO_MAX_LINK_RATE_3_24_GBPS, +}; + +/** + * drm_dp_has_quirk() - does the DP device have a specific quirk + * @desc: Device descriptor filled by drm_dp_read_desc() + * @quirk: Quirk to query for + * + * Return true if DP device identified by @desc has @quirk. + */ +static inline bool +drm_dp_has_quirk(const struct drm_dp_desc *desc, enum drm_dp_quirk quirk) +{ + return desc->quirks & BIT(quirk); +} + +/** + * struct drm_edp_backlight_info - Probed eDP backlight info struct + * @pwmgen_bit_count: The pwmgen bit count + * @pwm_freq_pre_divider: The PWM frequency pre-divider value being used for this backlight, if any + * @max: The maximum backlight level that may be set + * @lsb_reg_used: Do we also write values to the DP_EDP_BACKLIGHT_BRIGHTNESS_LSB register? + * @aux_enable: Does the panel support the AUX enable cap? + * @aux_set: Does the panel support setting the brightness through AUX? + * + * This structure contains various data about an eDP backlight, which can be populated by using + * drm_edp_backlight_init(). + */ +struct drm_edp_backlight_info { + u8 pwmgen_bit_count; + u8 pwm_freq_pre_divider; + u16 max; + + bool lsb_reg_used : 1; + bool aux_enable : 1; + bool aux_set : 1; +}; + +int +drm_edp_backlight_init(struct drm_dp_aux *aux, struct drm_edp_backlight_info *bl, + u16 driver_pwm_freq_hz, const u8 edp_dpcd[EDP_DISPLAY_CTL_CAP_SIZE], + u16 *current_level, u8 *current_mode); +int drm_edp_backlight_set_level(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl, + u16 level); +int drm_edp_backlight_enable(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl, + u16 level); +int drm_edp_backlight_disable(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl); + +#if IS_ENABLED(CONFIG_DRM_KMS_HELPER) && (IS_BUILTIN(CONFIG_BACKLIGHT_CLASS_DEVICE) || \ + (IS_MODULE(CONFIG_DRM_KMS_HELPER) && IS_MODULE(CONFIG_BACKLIGHT_CLASS_DEVICE))) + +int drm_panel_dp_aux_backlight(struct drm_panel *panel, struct drm_dp_aux *aux); + +#else + +static inline int drm_panel_dp_aux_backlight(struct drm_panel *panel, + struct drm_dp_aux *aux) +{ + return 0; +} + +#endif + +#ifdef CONFIG_DRM_DP_CEC +void drm_dp_cec_irq(struct drm_dp_aux *aux); +void drm_dp_cec_register_connector(struct drm_dp_aux *aux, + struct drm_connector *connector); +void drm_dp_cec_unregister_connector(struct drm_dp_aux *aux); +void drm_dp_cec_set_edid(struct drm_dp_aux *aux, const struct edid *edid); +void drm_dp_cec_unset_edid(struct drm_dp_aux *aux); +#else +static inline void drm_dp_cec_irq(struct drm_dp_aux *aux) +{ +} + +static inline void +drm_dp_cec_register_connector(struct drm_dp_aux *aux, + struct drm_connector *connector) +{ +} + +static inline void drm_dp_cec_unregister_connector(struct drm_dp_aux *aux) +{ +} + +static inline void drm_dp_cec_set_edid(struct drm_dp_aux *aux, + const struct edid *edid) +{ +} + +static inline void drm_dp_cec_unset_edid(struct drm_dp_aux *aux) +{ +} + +#endif + +/** + * struct drm_dp_phy_test_params - DP Phy Compliance parameters + * @link_rate: Requested Link rate from DPCD 0x219 + * @num_lanes: Number of lanes requested by sing through DPCD 0x220 + * @phy_pattern: DP Phy test pattern from DPCD 0x248 + * @hbr2_reset: DP HBR2_COMPLIANCE_SCRAMBLER_RESET from DCPD 0x24A and 0x24B + * @custom80: DP Test_80BIT_CUSTOM_PATTERN from DPCDs 0x250 through 0x259 + * @enhanced_frame_cap: flag for enhanced frame capability. + */ +struct drm_dp_phy_test_params { + int link_rate; + u8 num_lanes; + u8 phy_pattern; + u8 hbr2_reset[2]; + u8 custom80[10]; + bool enhanced_frame_cap; +}; + +int drm_dp_get_phy_test_pattern(struct drm_dp_aux *aux, + struct drm_dp_phy_test_params *data); +int drm_dp_set_phy_test_pattern(struct drm_dp_aux *aux, + struct drm_dp_phy_test_params *data, u8 dp_rev); +int drm_dp_get_pcon_max_frl_bw(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4]); +int drm_dp_pcon_frl_prepare(struct drm_dp_aux *aux, bool enable_frl_ready_hpd); +bool drm_dp_pcon_is_frl_ready(struct drm_dp_aux *aux); +int drm_dp_pcon_frl_configure_1(struct drm_dp_aux *aux, int max_frl_gbps, + u8 frl_mode); +int drm_dp_pcon_frl_configure_2(struct drm_dp_aux *aux, int max_frl_mask, + u8 frl_type); +int drm_dp_pcon_reset_frl_config(struct drm_dp_aux *aux); +int drm_dp_pcon_frl_enable(struct drm_dp_aux *aux); + +bool drm_dp_pcon_hdmi_link_active(struct drm_dp_aux *aux); +int drm_dp_pcon_hdmi_link_mode(struct drm_dp_aux *aux, u8 *frl_trained_mask); +void drm_dp_pcon_hdmi_frl_link_error_count(struct drm_dp_aux *aux, + struct drm_connector *connector); +bool drm_dp_pcon_enc_is_dsc_1_2(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]); +int drm_dp_pcon_dsc_max_slices(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]); +int drm_dp_pcon_dsc_max_slice_width(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]); +int drm_dp_pcon_dsc_bpp_incr(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]); +int drm_dp_pcon_pps_default(struct drm_dp_aux *aux); +int drm_dp_pcon_pps_override_buf(struct drm_dp_aux *aux, u8 pps_buf[128]); +int drm_dp_pcon_pps_override_param(struct drm_dp_aux *aux, u8 pps_param[6]); +bool drm_dp_downstream_rgb_to_ycbcr_conversion(const u8 dpcd[DP_RECEIVER_CAP_SIZE], + const u8 port_cap[4], u8 color_spc); +int drm_dp_pcon_convert_rgb_to_ycbcr(struct drm_dp_aux *aux, u8 color_spc); + +#endif /* _DRM_DP_HELPER_H_ */ diff --git a/include/drm/display/drm_dp_mst_helper.h b/include/drm/display/drm_dp_mst_helper.h new file mode 100644 index 000000000000..10adec068b7f --- /dev/null +++ b/include/drm/display/drm_dp_mst_helper.h @@ -0,0 +1,972 @@ +/* + * Copyright © 2014 Red Hat. + * + * Permission to use, copy, modify, distribute, and sell this software and its + * documentation for any purpose is hereby granted without fee, provided that + * the above copyright notice appear in all copies and that both that copyright + * notice and this permission notice appear in supporting documentation, and + * that the name of the copyright holders not be used in advertising or + * publicity pertaining to distribution of the software without specific, + * written prior permission. The copyright holders make no representations + * about the suitability of this software for any purpose. It is provided "as + * is" without express or implied warranty. + * + * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, + * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO + * EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT OR + * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, + * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER + * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE + * OF THIS SOFTWARE. + */ +#ifndef _DRM_DP_MST_HELPER_H_ +#define _DRM_DP_MST_HELPER_H_ + +#include +#include +#include + +#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) +#include +#include + +enum drm_dp_mst_topology_ref_type { + DRM_DP_MST_TOPOLOGY_REF_GET, + DRM_DP_MST_TOPOLOGY_REF_PUT, +}; + +struct drm_dp_mst_topology_ref_history { + struct drm_dp_mst_topology_ref_entry { + enum drm_dp_mst_topology_ref_type type; + int count; + ktime_t ts_nsec; + depot_stack_handle_t backtrace; + } *entries; + int len; +}; +#endif /* IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) */ + +struct drm_dp_mst_branch; + +/** + * struct drm_dp_vcpi - Virtual Channel Payload Identifier + * @vcpi: Virtual channel ID. + * @pbn: Payload Bandwidth Number for this channel + * @aligned_pbn: PBN aligned with slot size + * @num_slots: number of slots for this PBN + */ +struct drm_dp_vcpi { + int vcpi; + int pbn; + int aligned_pbn; + int num_slots; +}; + +/** + * struct drm_dp_mst_port - MST port + * @port_num: port number + * @input: if this port is an input port. Protected by + * &drm_dp_mst_topology_mgr.base.lock. + * @mcs: message capability status - DP 1.2 spec. Protected by + * &drm_dp_mst_topology_mgr.base.lock. + * @ddps: DisplayPort Device Plug Status - DP 1.2. Protected by + * &drm_dp_mst_topology_mgr.base.lock. + * @pdt: Peer Device Type. Protected by + * &drm_dp_mst_topology_mgr.base.lock. + * @ldps: Legacy Device Plug Status. Protected by + * &drm_dp_mst_topology_mgr.base.lock. + * @dpcd_rev: DPCD revision of device on this port. Protected by + * &drm_dp_mst_topology_mgr.base.lock. + * @num_sdp_streams: Number of simultaneous streams. Protected by + * &drm_dp_mst_topology_mgr.base.lock. + * @num_sdp_stream_sinks: Number of stream sinks. Protected by + * &drm_dp_mst_topology_mgr.base.lock. + * @full_pbn: Max possible bandwidth for this port. Protected by + * &drm_dp_mst_topology_mgr.base.lock. + * @next: link to next port on this branch device + * @aux: i2c aux transport to talk to device connected to this port, protected + * by &drm_dp_mst_topology_mgr.base.lock. + * @parent: branch device parent of this port + * @vcpi: Virtual Channel Payload info for this port. + * @connector: DRM connector this port is connected to. Protected by + * &drm_dp_mst_topology_mgr.base.lock. + * @mgr: topology manager this port lives under. + * + * This structure represents an MST port endpoint on a device somewhere + * in the MST topology. + */ +struct drm_dp_mst_port { + /** + * @topology_kref: refcount for this port's lifetime in the topology, + * only the DP MST helpers should need to touch this + */ + struct kref topology_kref; + + /** + * @malloc_kref: refcount for the memory allocation containing this + * structure. See drm_dp_mst_get_port_malloc() and + * drm_dp_mst_put_port_malloc(). + */ + struct kref malloc_kref; + +#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) + /** + * @topology_ref_history: A history of each topology + * reference/dereference. See CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS. + */ + struct drm_dp_mst_topology_ref_history topology_ref_history; +#endif + + u8 port_num; + bool input; + bool mcs; + bool ddps; + u8 pdt; + bool ldps; + u8 dpcd_rev; + u8 num_sdp_streams; + u8 num_sdp_stream_sinks; + uint16_t full_pbn; + struct list_head next; + /** + * @mstb: the branch device connected to this port, if there is one. + * This should be considered protected for reading by + * &drm_dp_mst_topology_mgr.lock. There are two exceptions to this: + * &drm_dp_mst_topology_mgr.up_req_work and + * &drm_dp_mst_topology_mgr.work, which do not grab + * &drm_dp_mst_topology_mgr.lock during reads but are the only + * updaters of this list and are protected from writing concurrently + * by &drm_dp_mst_topology_mgr.probe_lock. + */ + struct drm_dp_mst_branch *mstb; + struct drm_dp_aux aux; /* i2c bus for this port? */ + struct drm_dp_mst_branch *parent; + + struct drm_dp_vcpi vcpi; + struct drm_connector *connector; + struct drm_dp_mst_topology_mgr *mgr; + + /** + * @cached_edid: for DP logical ports - make tiling work by ensuring + * that the EDID for all connectors is read immediately. + */ + struct edid *cached_edid; + /** + * @has_audio: Tracks whether the sink connector to this port is + * audio-capable. + */ + bool has_audio; + + /** + * @fec_capable: bool indicating if FEC can be supported up to that + * point in the MST topology. + */ + bool fec_capable; +}; + +/* sideband msg header - not bit struct */ +struct drm_dp_sideband_msg_hdr { + u8 lct; + u8 lcr; + u8 rad[8]; + bool broadcast; + bool path_msg; + u8 msg_len; + bool somt; + bool eomt; + bool seqno; +}; + +struct drm_dp_sideband_msg_rx { + u8 chunk[48]; + u8 msg[256]; + u8 curchunk_len; + u8 curchunk_idx; /* chunk we are parsing now */ + u8 curchunk_hdrlen; + u8 curlen; /* total length of the msg */ + bool have_somt; + bool have_eomt; + struct drm_dp_sideband_msg_hdr initial_hdr; +}; + +/** + * struct drm_dp_mst_branch - MST branch device. + * @rad: Relative Address to talk to this branch device. + * @lct: Link count total to talk to this branch device. + * @num_ports: number of ports on the branch. + * @port_parent: pointer to the port parent, NULL if toplevel. + * @mgr: topology manager for this branch device. + * @link_address_sent: if a link address message has been sent to this device yet. + * @guid: guid for DP 1.2 branch device. port under this branch can be + * identified by port #. + * + * This structure represents an MST branch device, there is one + * primary branch device at the root, along with any other branches connected + * to downstream port of parent branches. + */ +struct drm_dp_mst_branch { + /** + * @topology_kref: refcount for this branch device's lifetime in the + * topology, only the DP MST helpers should need to touch this + */ + struct kref topology_kref; + + /** + * @malloc_kref: refcount for the memory allocation containing this + * structure. See drm_dp_mst_get_mstb_malloc() and + * drm_dp_mst_put_mstb_malloc(). + */ + struct kref malloc_kref; + +#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) + /** + * @topology_ref_history: A history of each topology + * reference/dereference. See CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS. + */ + struct drm_dp_mst_topology_ref_history topology_ref_history; +#endif + + /** + * @destroy_next: linked-list entry used by + * drm_dp_delayed_destroy_work() + */ + struct list_head destroy_next; + + u8 rad[8]; + u8 lct; + int num_ports; + + /** + * @ports: the list of ports on this branch device. This should be + * considered protected for reading by &drm_dp_mst_topology_mgr.lock. + * There are two exceptions to this: + * &drm_dp_mst_topology_mgr.up_req_work and + * &drm_dp_mst_topology_mgr.work, which do not grab + * &drm_dp_mst_topology_mgr.lock during reads but are the only + * updaters of this list and are protected from updating the list + * concurrently by @drm_dp_mst_topology_mgr.probe_lock + */ + struct list_head ports; + + struct drm_dp_mst_port *port_parent; + struct drm_dp_mst_topology_mgr *mgr; + + bool link_address_sent; + + /* global unique identifier to identify branch devices */ + u8 guid[16]; +}; + + +struct drm_dp_nak_reply { + u8 guid[16]; + u8 reason; + u8 nak_data; +}; + +struct drm_dp_link_address_ack_reply { + u8 guid[16]; + u8 nports; + struct drm_dp_link_addr_reply_port { + bool input_port; + u8 peer_device_type; + u8 port_number; + bool mcs; + bool ddps; + bool legacy_device_plug_status; + u8 dpcd_revision; + u8 peer_guid[16]; + u8 num_sdp_streams; + u8 num_sdp_stream_sinks; + } ports[16]; +}; + +struct drm_dp_remote_dpcd_read_ack_reply { + u8 port_number; + u8 num_bytes; + u8 bytes[255]; +}; + +struct drm_dp_remote_dpcd_write_ack_reply { + u8 port_number; +}; + +struct drm_dp_remote_dpcd_write_nak_reply { + u8 port_number; + u8 reason; + u8 bytes_written_before_failure; +}; + +struct drm_dp_remote_i2c_read_ack_reply { + u8 port_number; + u8 num_bytes; + u8 bytes[255]; +}; + +struct drm_dp_remote_i2c_read_nak_reply { + u8 port_number; + u8 nak_reason; + u8 i2c_nak_transaction; +}; + +struct drm_dp_remote_i2c_write_ack_reply { + u8 port_number; +}; + +struct drm_dp_query_stream_enc_status_ack_reply { + /* Bit[23:16]- Stream Id */ + u8 stream_id; + + /* Bit[15]- Signed */ + bool reply_signed; + + /* Bit[10:8]- Stream Output Sink Type */ + bool unauthorizable_device_present; + bool legacy_device_present; + bool query_capable_device_present; + + /* Bit[12:11]- Stream Output CP Type */ + bool hdcp_1x_device_present; + bool hdcp_2x_device_present; + + /* Bit[4]- Stream Authentication */ + bool auth_completed; + + /* Bit[3]- Stream Encryption */ + bool encryption_enabled; + + /* Bit[2]- Stream Repeater Function Present */ + bool repeater_present; + + /* Bit[1:0]- Stream State */ + u8 state; +}; + +#define DRM_DP_MAX_SDP_STREAMS 16 +struct drm_dp_allocate_payload { + u8 port_number; + u8 number_sdp_streams; + u8 vcpi; + u16 pbn; + u8 sdp_stream_sink[DRM_DP_MAX_SDP_STREAMS]; +}; + +struct drm_dp_allocate_payload_ack_reply { + u8 port_number; + u8 vcpi; + u16 allocated_pbn; +}; + +struct drm_dp_connection_status_notify { + u8 guid[16]; + u8 port_number; + bool legacy_device_plug_status; + bool displayport_device_plug_status; + bool message_capability_status; + bool input_port; + u8 peer_device_type; +}; + +struct drm_dp_remote_dpcd_read { + u8 port_number; + u32 dpcd_address; + u8 num_bytes; +}; + +struct drm_dp_remote_dpcd_write { + u8 port_number; + u32 dpcd_address; + u8 num_bytes; + u8 *bytes; +}; + +#define DP_REMOTE_I2C_READ_MAX_TRANSACTIONS 4 +struct drm_dp_remote_i2c_read { + u8 num_transactions; + u8 port_number; + struct drm_dp_remote_i2c_read_tx { + u8 i2c_dev_id; + u8 num_bytes; + u8 *bytes; + u8 no_stop_bit; + u8 i2c_transaction_delay; + } transactions[DP_REMOTE_I2C_READ_MAX_TRANSACTIONS]; + u8 read_i2c_device_id; + u8 num_bytes_read; +}; + +struct drm_dp_remote_i2c_write { + u8 port_number; + u8 write_i2c_device_id; + u8 num_bytes; + u8 *bytes; +}; + +struct drm_dp_query_stream_enc_status { + u8 stream_id; + u8 client_id[7]; /* 56-bit nonce */ + u8 stream_event; + bool valid_stream_event; + u8 stream_behavior; + u8 valid_stream_behavior; +}; + +/* this covers ENUM_RESOURCES, POWER_DOWN_PHY, POWER_UP_PHY */ +struct drm_dp_port_number_req { + u8 port_number; +}; + +struct drm_dp_enum_path_resources_ack_reply { + u8 port_number; + bool fec_capable; + u16 full_payload_bw_number; + u16 avail_payload_bw_number; +}; + +/* covers POWER_DOWN_PHY, POWER_UP_PHY */ +struct drm_dp_port_number_rep { + u8 port_number; +}; + +struct drm_dp_query_payload { + u8 port_number; + u8 vcpi; +}; + +struct drm_dp_resource_status_notify { + u8 port_number; + u8 guid[16]; + u16 available_pbn; +}; + +struct drm_dp_query_payload_ack_reply { + u8 port_number; + u16 allocated_pbn; +}; + +struct drm_dp_sideband_msg_req_body { + u8 req_type; + union ack_req { + struct drm_dp_connection_status_notify conn_stat; + struct drm_dp_port_number_req port_num; + struct drm_dp_resource_status_notify resource_stat; + + struct drm_dp_query_payload query_payload; + struct drm_dp_allocate_payload allocate_payload; + + struct drm_dp_remote_dpcd_read dpcd_read; + struct drm_dp_remote_dpcd_write dpcd_write; + + struct drm_dp_remote_i2c_read i2c_read; + struct drm_dp_remote_i2c_write i2c_write; + + struct drm_dp_query_stream_enc_status enc_status; + } u; +}; + +struct drm_dp_sideband_msg_reply_body { + u8 reply_type; + u8 req_type; + union ack_replies { + struct drm_dp_nak_reply nak; + struct drm_dp_link_address_ack_reply link_addr; + struct drm_dp_port_number_rep port_number; + + struct drm_dp_enum_path_resources_ack_reply path_resources; + struct drm_dp_allocate_payload_ack_reply allocate_payload; + struct drm_dp_query_payload_ack_reply query_payload; + + struct drm_dp_remote_dpcd_read_ack_reply remote_dpcd_read_ack; + struct drm_dp_remote_dpcd_write_ack_reply remote_dpcd_write_ack; + struct drm_dp_remote_dpcd_write_nak_reply remote_dpcd_write_nack; + + struct drm_dp_remote_i2c_read_ack_reply remote_i2c_read_ack; + struct drm_dp_remote_i2c_read_nak_reply remote_i2c_read_nack; + struct drm_dp_remote_i2c_write_ack_reply remote_i2c_write_ack; + + struct drm_dp_query_stream_enc_status_ack_reply enc_status; + } u; +}; + +/* msg is queued to be put into a slot */ +#define DRM_DP_SIDEBAND_TX_QUEUED 0 +/* msg has started transmitting on a slot - still on msgq */ +#define DRM_DP_SIDEBAND_TX_START_SEND 1 +/* msg has finished transmitting on a slot - removed from msgq only in slot */ +#define DRM_DP_SIDEBAND_TX_SENT 2 +/* msg has received a response - removed from slot */ +#define DRM_DP_SIDEBAND_TX_RX 3 +#define DRM_DP_SIDEBAND_TX_TIMEOUT 4 + +struct drm_dp_sideband_msg_tx { + u8 msg[256]; + u8 chunk[48]; + u8 cur_offset; + u8 cur_len; + struct drm_dp_mst_branch *dst; + struct list_head next; + int seqno; + int state; + bool path_msg; + struct drm_dp_sideband_msg_reply_body reply; +}; + +/* sideband msg handler */ +struct drm_dp_mst_topology_mgr; +struct drm_dp_mst_topology_cbs { + /* create a connector for a port */ + struct drm_connector *(*add_connector)(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port, const char *path); + /* + * Checks for any pending MST interrupts, passing them to MST core for + * processing, the same way an HPD IRQ pulse handler would do this. + * If provided MST core calls this callback from a poll-waiting loop + * when waiting for MST down message replies. The driver is expected + * to guard against a race between this callback and the driver's HPD + * IRQ pulse handler. + */ + void (*poll_hpd_irq)(struct drm_dp_mst_topology_mgr *mgr); +}; + +#define DP_MAX_PAYLOAD (sizeof(unsigned long) * 8) + +#define DP_PAYLOAD_LOCAL 1 +#define DP_PAYLOAD_REMOTE 2 +#define DP_PAYLOAD_DELETE_LOCAL 3 + +struct drm_dp_payload { + int payload_state; + int start_slot; + int num_slots; + int vcpi; +}; + +#define to_dp_mst_topology_state(x) container_of(x, struct drm_dp_mst_topology_state, base) + +struct drm_dp_vcpi_allocation { + struct drm_dp_mst_port *port; + int vcpi; + int pbn; + bool dsc_enabled; + struct list_head next; +}; + +struct drm_dp_mst_topology_state { + struct drm_private_state base; + struct list_head vcpis; + struct drm_dp_mst_topology_mgr *mgr; + u8 total_avail_slots; + u8 start_slot; +}; + +#define to_dp_mst_topology_mgr(x) container_of(x, struct drm_dp_mst_topology_mgr, base) + +/** + * struct drm_dp_mst_topology_mgr - DisplayPort MST manager + * + * This struct represents the toplevel displayport MST topology manager. + * There should be one instance of this for every MST capable DP connector + * on the GPU. + */ +struct drm_dp_mst_topology_mgr { + /** + * @base: Base private object for atomic + */ + struct drm_private_obj base; + + /** + * @dev: device pointer for adding i2c devices etc. + */ + struct drm_device *dev; + /** + * @cbs: callbacks for connector addition and destruction. + */ + const struct drm_dp_mst_topology_cbs *cbs; + /** + * @max_dpcd_transaction_bytes: maximum number of bytes to read/write + * in one go. + */ + int max_dpcd_transaction_bytes; + /** + * @aux: AUX channel for the DP MST connector this topolgy mgr is + * controlling. + */ + struct drm_dp_aux *aux; + /** + * @max_payloads: maximum number of payloads the GPU can generate. + */ + int max_payloads; + /** + * @max_lane_count: maximum number of lanes the GPU can drive. + */ + int max_lane_count; + /** + * @max_link_rate: maximum link rate per lane GPU can output, in kHz. + */ + int max_link_rate; + /** + * @conn_base_id: DRM connector ID this mgr is connected to. Only used + * to build the MST connector path value. + */ + int conn_base_id; + + /** + * @up_req_recv: Message receiver state for up requests. + */ + struct drm_dp_sideband_msg_rx up_req_recv; + + /** + * @down_rep_recv: Message receiver state for replies to down + * requests. + */ + struct drm_dp_sideband_msg_rx down_rep_recv; + + /** + * @lock: protects @mst_state, @mst_primary, @dpcd, and + * @payload_id_table_cleared. + */ + struct mutex lock; + + /** + * @probe_lock: Prevents @work and @up_req_work, the only writers of + * &drm_dp_mst_port.mstb and &drm_dp_mst_branch.ports, from racing + * while they update the topology. + */ + struct mutex probe_lock; + + /** + * @mst_state: If this manager is enabled for an MST capable port. False + * if no MST sink/branch devices is connected. + */ + bool mst_state : 1; + + /** + * @payload_id_table_cleared: Whether or not we've cleared the payload + * ID table for @mst_primary. Protected by @lock. + */ + bool payload_id_table_cleared : 1; + + /** + * @mst_primary: Pointer to the primary/first branch device. + */ + struct drm_dp_mst_branch *mst_primary; + + /** + * @dpcd: Cache of DPCD for primary port. + */ + u8 dpcd[DP_RECEIVER_CAP_SIZE]; + /** + * @sink_count: Sink count from DEVICE_SERVICE_IRQ_VECTOR_ESI0. + */ + u8 sink_count; + /** + * @pbn_div: PBN to slots divisor. + */ + int pbn_div; + + /** + * @funcs: Atomic helper callbacks + */ + const struct drm_private_state_funcs *funcs; + + /** + * @qlock: protects @tx_msg_downq and &drm_dp_sideband_msg_tx.state + */ + struct mutex qlock; + + /** + * @tx_msg_downq: List of pending down requests + */ + struct list_head tx_msg_downq; + + /** + * @payload_lock: Protect payload information. + */ + struct mutex payload_lock; + /** + * @proposed_vcpis: Array of pointers for the new VCPI allocation. The + * VCPI structure itself is &drm_dp_mst_port.vcpi, and the size of + * this array is determined by @max_payloads. + */ + struct drm_dp_vcpi **proposed_vcpis; + /** + * @payloads: Array of payloads. The size of this array is determined + * by @max_payloads. + */ + struct drm_dp_payload *payloads; + /** + * @payload_mask: Elements of @payloads actually in use. Since + * reallocation of active outputs isn't possible gaps can be created by + * disabling outputs out of order compared to how they've been enabled. + */ + unsigned long payload_mask; + /** + * @vcpi_mask: Similar to @payload_mask, but for @proposed_vcpis. + */ + unsigned long vcpi_mask; + + /** + * @tx_waitq: Wait to queue stall for the tx worker. + */ + wait_queue_head_t tx_waitq; + /** + * @work: Probe work. + */ + struct work_struct work; + /** + * @tx_work: Sideband transmit worker. This can nest within the main + * @work worker for each transaction @work launches. + */ + struct work_struct tx_work; + + /** + * @destroy_port_list: List of to be destroyed connectors. + */ + struct list_head destroy_port_list; + /** + * @destroy_branch_device_list: List of to be destroyed branch + * devices. + */ + struct list_head destroy_branch_device_list; + /** + * @delayed_destroy_lock: Protects @destroy_port_list and + * @destroy_branch_device_list. + */ + struct mutex delayed_destroy_lock; + + /** + * @delayed_destroy_wq: Workqueue used for delayed_destroy_work items. + * A dedicated WQ makes it possible to drain any requeued work items + * on it. + */ + struct workqueue_struct *delayed_destroy_wq; + + /** + * @delayed_destroy_work: Work item to destroy MST port and branch + * devices, needed to avoid locking inversion. + */ + struct work_struct delayed_destroy_work; + + /** + * @up_req_list: List of pending up requests from the topology that + * need to be processed, in chronological order. + */ + struct list_head up_req_list; + /** + * @up_req_lock: Protects @up_req_list + */ + struct mutex up_req_lock; + /** + * @up_req_work: Work item to process up requests received from the + * topology. Needed to avoid blocking hotplug handling and sideband + * transmissions. + */ + struct work_struct up_req_work; + +#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) + /** + * @topology_ref_history_lock: protects + * &drm_dp_mst_port.topology_ref_history and + * &drm_dp_mst_branch.topology_ref_history. + */ + struct mutex topology_ref_history_lock; +#endif +}; + +int drm_dp_mst_topology_mgr_init(struct drm_dp_mst_topology_mgr *mgr, + struct drm_device *dev, struct drm_dp_aux *aux, + int max_dpcd_transaction_bytes, + int max_payloads, + int max_lane_count, int max_link_rate, + int conn_base_id); + +void drm_dp_mst_topology_mgr_destroy(struct drm_dp_mst_topology_mgr *mgr); + +bool drm_dp_read_mst_cap(struct drm_dp_aux *aux, const u8 dpcd[DP_RECEIVER_CAP_SIZE]); +int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool mst_state); + +int drm_dp_mst_hpd_irq(struct drm_dp_mst_topology_mgr *mgr, u8 *esi, bool *handled); + + +int +drm_dp_mst_detect_port(struct drm_connector *connector, + struct drm_modeset_acquire_ctx *ctx, + struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_port *port); + +struct edid *drm_dp_mst_get_edid(struct drm_connector *connector, struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port); + +int drm_dp_get_vc_payload_bw(const struct drm_dp_mst_topology_mgr *mgr, + int link_rate, int link_lane_count); + +int drm_dp_calc_pbn_mode(int clock, int bpp, bool dsc); + +bool drm_dp_mst_allocate_vcpi(struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_port *port, int pbn, int slots); + +int drm_dp_mst_get_vcpi_slots(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port); + + +void drm_dp_mst_reset_vcpi_slots(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port); + +void drm_dp_mst_update_slots(struct drm_dp_mst_topology_state *mst_state, uint8_t link_encoding_cap); + +void drm_dp_mst_deallocate_vcpi(struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_port *port); + + +int drm_dp_find_vcpi_slots(struct drm_dp_mst_topology_mgr *mgr, + int pbn); + + +int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr, int start_slot); + + +int drm_dp_update_payload_part2(struct drm_dp_mst_topology_mgr *mgr); + +int drm_dp_check_act_status(struct drm_dp_mst_topology_mgr *mgr); + +void drm_dp_mst_dump_topology(struct seq_file *m, + struct drm_dp_mst_topology_mgr *mgr); + +void drm_dp_mst_topology_mgr_suspend(struct drm_dp_mst_topology_mgr *mgr); +int __must_check +drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr, + bool sync); + +ssize_t drm_dp_mst_dpcd_read(struct drm_dp_aux *aux, + unsigned int offset, void *buffer, size_t size); +ssize_t drm_dp_mst_dpcd_write(struct drm_dp_aux *aux, + unsigned int offset, void *buffer, size_t size); + +int drm_dp_mst_connector_late_register(struct drm_connector *connector, + struct drm_dp_mst_port *port); +void drm_dp_mst_connector_early_unregister(struct drm_connector *connector, + struct drm_dp_mst_port *port); + +struct drm_dp_mst_topology_state *drm_atomic_get_mst_topology_state(struct drm_atomic_state *state, + struct drm_dp_mst_topology_mgr *mgr); +int __must_check +drm_dp_atomic_find_vcpi_slots(struct drm_atomic_state *state, + struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_port *port, int pbn, + int pbn_div); +int drm_dp_mst_atomic_enable_dsc(struct drm_atomic_state *state, + struct drm_dp_mst_port *port, + int pbn, int pbn_div, + bool enable); +int __must_check +drm_dp_mst_add_affected_dsc_crtcs(struct drm_atomic_state *state, + struct drm_dp_mst_topology_mgr *mgr); +int __must_check +drm_dp_atomic_release_vcpi_slots(struct drm_atomic_state *state, + struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_port *port); +int drm_dp_send_power_updown_phy(struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_port *port, bool power_up); +int drm_dp_send_query_stream_enc_status(struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_port *port, + struct drm_dp_query_stream_enc_status_ack_reply *status); +int __must_check drm_dp_mst_atomic_check(struct drm_atomic_state *state); + +void drm_dp_mst_get_port_malloc(struct drm_dp_mst_port *port); +void drm_dp_mst_put_port_malloc(struct drm_dp_mst_port *port); + +struct drm_dp_aux *drm_dp_mst_dsc_aux_for_port(struct drm_dp_mst_port *port); + +extern const struct drm_private_state_funcs drm_dp_mst_topology_state_funcs; + +/** + * __drm_dp_mst_state_iter_get - private atomic state iterator function for + * macro-internal use + * @state: &struct drm_atomic_state pointer + * @mgr: pointer to the &struct drm_dp_mst_topology_mgr iteration cursor + * @old_state: optional pointer to the old &struct drm_dp_mst_topology_state + * iteration cursor + * @new_state: optional pointer to the new &struct drm_dp_mst_topology_state + * iteration cursor + * @i: int iteration cursor, for macro-internal use + * + * Used by for_each_oldnew_mst_mgr_in_state(), + * for_each_old_mst_mgr_in_state(), and for_each_new_mst_mgr_in_state(). Don't + * call this directly. + * + * Returns: + * True if the current &struct drm_private_obj is a &struct + * drm_dp_mst_topology_mgr, false otherwise. + */ +static inline bool +__drm_dp_mst_state_iter_get(struct drm_atomic_state *state, + struct drm_dp_mst_topology_mgr **mgr, + struct drm_dp_mst_topology_state **old_state, + struct drm_dp_mst_topology_state **new_state, + int i) +{ + struct __drm_private_objs_state *objs_state = &state->private_objs[i]; + + if (objs_state->ptr->funcs != &drm_dp_mst_topology_state_funcs) + return false; + + *mgr = to_dp_mst_topology_mgr(objs_state->ptr); + if (old_state) + *old_state = to_dp_mst_topology_state(objs_state->old_state); + if (new_state) + *new_state = to_dp_mst_topology_state(objs_state->new_state); + + return true; +} + +/** + * for_each_oldnew_mst_mgr_in_state - iterate over all DP MST topology + * managers in an atomic update + * @__state: &struct drm_atomic_state pointer + * @mgr: &struct drm_dp_mst_topology_mgr iteration cursor + * @old_state: &struct drm_dp_mst_topology_state iteration cursor for the old + * state + * @new_state: &struct drm_dp_mst_topology_state iteration cursor for the new + * state + * @__i: int iteration cursor, for macro-internal use + * + * This iterates over all DRM DP MST topology managers in an atomic update, + * tracking both old and new state. This is useful in places where the state + * delta needs to be considered, for example in atomic check functions. + */ +#define for_each_oldnew_mst_mgr_in_state(__state, mgr, old_state, new_state, __i) \ + for ((__i) = 0; (__i) < (__state)->num_private_objs; (__i)++) \ + for_each_if(__drm_dp_mst_state_iter_get((__state), &(mgr), &(old_state), &(new_state), (__i))) + +/** + * for_each_old_mst_mgr_in_state - iterate over all DP MST topology managers + * in an atomic update + * @__state: &struct drm_atomic_state pointer + * @mgr: &struct drm_dp_mst_topology_mgr iteration cursor + * @old_state: &struct drm_dp_mst_topology_state iteration cursor for the old + * state + * @__i: int iteration cursor, for macro-internal use + * + * This iterates over all DRM DP MST topology managers in an atomic update, + * tracking only the old state. This is useful in disable functions, where we + * need the old state the hardware is still in. + */ +#define for_each_old_mst_mgr_in_state(__state, mgr, old_state, __i) \ + for ((__i) = 0; (__i) < (__state)->num_private_objs; (__i)++) \ + for_each_if(__drm_dp_mst_state_iter_get((__state), &(mgr), &(old_state), NULL, (__i))) + +/** + * for_each_new_mst_mgr_in_state - iterate over all DP MST topology managers + * in an atomic update + * @__state: &struct drm_atomic_state pointer + * @mgr: &struct drm_dp_mst_topology_mgr iteration cursor + * @new_state: &struct drm_dp_mst_topology_state iteration cursor for the new + * state + * @__i: int iteration cursor, for macro-internal use + * + * This iterates over all DRM DP MST topology managers in an atomic update, + * tracking only the new state. This is useful in enable functions, where we + * need the new state the hardware should be in when the atomic commit + * operation has completed. + */ +#define for_each_new_mst_mgr_in_state(__state, mgr, new_state, __i) \ + for ((__i) = 0; (__i) < (__state)->num_private_objs; (__i)++) \ + for_each_if(__drm_dp_mst_state_iter_get((__state), &(mgr), NULL, &(new_state), (__i))) + +#endif diff --git a/include/drm/dp/drm_dp_aux_bus.h b/include/drm/dp/drm_dp_aux_bus.h deleted file mode 100644 index 4f19b20b1dd6..000000000000 --- a/include/drm/dp/drm_dp_aux_bus.h +++ /dev/null @@ -1,57 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright 2021 Google Inc. - * - * The DP AUX bus is used for devices that are connected over a DisplayPort - * AUX bus. The devices on the far side of the bus are referred to as - * endpoints in this code. - */ - -#ifndef _DP_AUX_BUS_H_ -#define _DP_AUX_BUS_H_ - -#include -#include - -/** - * struct dp_aux_ep_device - Main dev structure for DP AUX endpoints - * - * This is used to instantiate devices that are connected via a DP AUX - * bus. Usually the device is a panel, but conceivable other devices could - * be hooked up there. - */ -struct dp_aux_ep_device { - /** @dev: The normal dev pointer */ - struct device dev; - /** @aux: Pointer to the aux bus */ - struct drm_dp_aux *aux; -}; - -struct dp_aux_ep_driver { - int (*probe)(struct dp_aux_ep_device *aux_ep); - void (*remove)(struct dp_aux_ep_device *aux_ep); - void (*shutdown)(struct dp_aux_ep_device *aux_ep); - struct device_driver driver; -}; - -static inline struct dp_aux_ep_device *to_dp_aux_ep_dev(struct device *dev) -{ - return container_of(dev, struct dp_aux_ep_device, dev); -} - -static inline struct dp_aux_ep_driver *to_dp_aux_ep_drv(struct device_driver *drv) -{ - return container_of(drv, struct dp_aux_ep_driver, driver); -} - -int of_dp_aux_populate_ep_devices(struct drm_dp_aux *aux); -void of_dp_aux_depopulate_ep_devices(struct drm_dp_aux *aux); -int devm_of_dp_aux_populate_ep_devices(struct drm_dp_aux *aux); - -#define dp_aux_dp_driver_register(aux_ep_drv) \ - __dp_aux_dp_driver_register(aux_ep_drv, THIS_MODULE) -int __dp_aux_dp_driver_register(struct dp_aux_ep_driver *aux_ep_drv, - struct module *owner); -void dp_aux_dp_driver_unregister(struct dp_aux_ep_driver *aux_ep_drv); - -#endif /* _DP_AUX_BUS_H_ */ diff --git a/include/drm/dp/drm_dp_dual_mode_helper.h b/include/drm/dp/drm_dp_dual_mode_helper.h deleted file mode 100644 index 7ee482265087..000000000000 --- a/include/drm/dp/drm_dp_dual_mode_helper.h +++ /dev/null @@ -1,121 +0,0 @@ -/* - * Copyright © 2016 Intel Corporation - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - */ - -#ifndef DRM_DP_DUAL_MODE_HELPER_H -#define DRM_DP_DUAL_MODE_HELPER_H - -#include - -/* - * Optional for type 1 DVI adaptors - * Mandatory for type 1 HDMI and type 2 adaptors - */ -#define DP_DUAL_MODE_HDMI_ID 0x00 /* 00-0f */ -#define DP_DUAL_MODE_HDMI_ID_LEN 16 -/* - * Optional for type 1 adaptors - * Mandatory for type 2 adaptors - */ -#define DP_DUAL_MODE_ADAPTOR_ID 0x10 -#define DP_DUAL_MODE_REV_MASK 0x07 -#define DP_DUAL_MODE_REV_TYPE2 0x00 -#define DP_DUAL_MODE_TYPE_MASK 0xf0 -#define DP_DUAL_MODE_TYPE_TYPE2 0xa0 -/* This field is marked reserved in dual mode spec, used in LSPCON */ -#define DP_DUAL_MODE_TYPE_HAS_DPCD 0x08 -#define DP_DUAL_MODE_IEEE_OUI 0x11 /* 11-13*/ -#define DP_DUAL_IEEE_OUI_LEN 3 -#define DP_DUAL_DEVICE_ID 0x14 /* 14-19 */ -#define DP_DUAL_DEVICE_ID_LEN 6 -#define DP_DUAL_MODE_HARDWARE_REV 0x1a -#define DP_DUAL_MODE_FIRMWARE_MAJOR_REV 0x1b -#define DP_DUAL_MODE_FIRMWARE_MINOR_REV 0x1c -#define DP_DUAL_MODE_MAX_TMDS_CLOCK 0x1d -#define DP_DUAL_MODE_I2C_SPEED_CAP 0x1e -#define DP_DUAL_MODE_TMDS_OEN 0x20 -#define DP_DUAL_MODE_TMDS_DISABLE 0x01 -#define DP_DUAL_MODE_HDMI_PIN_CTRL 0x21 -#define DP_DUAL_MODE_CEC_ENABLE 0x01 -#define DP_DUAL_MODE_I2C_SPEED_CTRL 0x22 - -/* LSPCON specific registers, defined by MCA */ -#define DP_DUAL_MODE_LSPCON_MODE_CHANGE 0x40 -#define DP_DUAL_MODE_LSPCON_CURRENT_MODE 0x41 -#define DP_DUAL_MODE_LSPCON_MODE_PCON 0x1 - -struct drm_device; -struct i2c_adapter; - -ssize_t drm_dp_dual_mode_read(struct i2c_adapter *adapter, - u8 offset, void *buffer, size_t size); -ssize_t drm_dp_dual_mode_write(struct i2c_adapter *adapter, - u8 offset, const void *buffer, size_t size); - -/** - * enum drm_lspcon_mode - * @DRM_LSPCON_MODE_INVALID: No LSPCON. - * @DRM_LSPCON_MODE_LS: Level shifter mode of LSPCON - * which drives DP++ to HDMI 1.4 conversion. - * @DRM_LSPCON_MODE_PCON: Protocol converter mode of LSPCON - * which drives DP++ to HDMI 2.0 active conversion. - */ -enum drm_lspcon_mode { - DRM_LSPCON_MODE_INVALID, - DRM_LSPCON_MODE_LS, - DRM_LSPCON_MODE_PCON, -}; - -/** - * enum drm_dp_dual_mode_type - Type of the DP dual mode adaptor - * @DRM_DP_DUAL_MODE_NONE: No DP dual mode adaptor - * @DRM_DP_DUAL_MODE_UNKNOWN: Could be either none or type 1 DVI adaptor - * @DRM_DP_DUAL_MODE_TYPE1_DVI: Type 1 DVI adaptor - * @DRM_DP_DUAL_MODE_TYPE1_HDMI: Type 1 HDMI adaptor - * @DRM_DP_DUAL_MODE_TYPE2_DVI: Type 2 DVI adaptor - * @DRM_DP_DUAL_MODE_TYPE2_HDMI: Type 2 HDMI adaptor - * @DRM_DP_DUAL_MODE_LSPCON: Level shifter / protocol converter - */ -enum drm_dp_dual_mode_type { - DRM_DP_DUAL_MODE_NONE, - DRM_DP_DUAL_MODE_UNKNOWN, - DRM_DP_DUAL_MODE_TYPE1_DVI, - DRM_DP_DUAL_MODE_TYPE1_HDMI, - DRM_DP_DUAL_MODE_TYPE2_DVI, - DRM_DP_DUAL_MODE_TYPE2_HDMI, - DRM_DP_DUAL_MODE_LSPCON, -}; - -enum drm_dp_dual_mode_type -drm_dp_dual_mode_detect(const struct drm_device *dev, struct i2c_adapter *adapter); -int drm_dp_dual_mode_max_tmds_clock(const struct drm_device *dev, enum drm_dp_dual_mode_type type, - struct i2c_adapter *adapter); -int drm_dp_dual_mode_get_tmds_output(const struct drm_device *dev, enum drm_dp_dual_mode_type type, - struct i2c_adapter *adapter, bool *enabled); -int drm_dp_dual_mode_set_tmds_output(const struct drm_device *dev, enum drm_dp_dual_mode_type type, - struct i2c_adapter *adapter, bool enable); -const char *drm_dp_get_dual_mode_type_name(enum drm_dp_dual_mode_type type); - -int drm_lspcon_get_mode(const struct drm_device *dev, struct i2c_adapter *adapter, - enum drm_lspcon_mode *current_mode); -int drm_lspcon_set_mode(const struct drm_device *dev, struct i2c_adapter *adapter, - enum drm_lspcon_mode reqd_mode); -#endif diff --git a/include/drm/dp/drm_dp_helper.h b/include/drm/dp/drm_dp_helper.h deleted file mode 100644 index 91af98e6617c..000000000000 --- a/include/drm/dp/drm_dp_helper.h +++ /dev/null @@ -1,2380 +0,0 @@ -/* - * Copyright © 2008 Keith Packard - * - * Permission to use, copy, modify, distribute, and sell this software and its - * documentation for any purpose is hereby granted without fee, provided that - * the above copyright notice appear in all copies and that both that copyright - * notice and this permission notice appear in supporting documentation, and - * that the name of the copyright holders not be used in advertising or - * publicity pertaining to distribution of the software without specific, - * written prior permission. The copyright holders make no representations - * about the suitability of this software for any purpose. It is provided "as - * is" without express or implied warranty. - * - * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, - * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO - * EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT OR - * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, - * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER - * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE - * OF THIS SOFTWARE. - */ - -#ifndef _DRM_DP_HELPER_H_ -#define _DRM_DP_HELPER_H_ - -#include -#include -#include -#include - -struct drm_device; -struct drm_dp_aux; -struct drm_panel; - -/* - * Unless otherwise noted, all values are from the DP 1.1a spec. Note that - * DP and DPCD versions are independent. Differences from 1.0 are not noted, - * 1.0 devices basically don't exist in the wild. - * - * Abbreviations, in chronological order: - * - * eDP: Embedded DisplayPort version 1 - * DPI: DisplayPort Interoperability Guideline v1.1a - * 1.2: DisplayPort 1.2 - * MST: Multistream Transport - part of DP 1.2a - * - * 1.2 formally includes both eDP and DPI definitions. - */ - -/* MSA (Main Stream Attribute) MISC bits (as MISC1<<8|MISC0) */ -#define DP_MSA_MISC_SYNC_CLOCK (1 << 0) -#define DP_MSA_MISC_INTERLACE_VTOTAL_EVEN (1 << 8) -#define DP_MSA_MISC_STEREO_NO_3D (0 << 9) -#define DP_MSA_MISC_STEREO_PROG_RIGHT_EYE (1 << 9) -#define DP_MSA_MISC_STEREO_PROG_LEFT_EYE (3 << 9) -/* bits per component for non-RAW */ -#define DP_MSA_MISC_6_BPC (0 << 5) -#define DP_MSA_MISC_8_BPC (1 << 5) -#define DP_MSA_MISC_10_BPC (2 << 5) -#define DP_MSA_MISC_12_BPC (3 << 5) -#define DP_MSA_MISC_16_BPC (4 << 5) -/* bits per component for RAW */ -#define DP_MSA_MISC_RAW_6_BPC (1 << 5) -#define DP_MSA_MISC_RAW_7_BPC (2 << 5) -#define DP_MSA_MISC_RAW_8_BPC (3 << 5) -#define DP_MSA_MISC_RAW_10_BPC (4 << 5) -#define DP_MSA_MISC_RAW_12_BPC (5 << 5) -#define DP_MSA_MISC_RAW_14_BPC (6 << 5) -#define DP_MSA_MISC_RAW_16_BPC (7 << 5) -/* pixel encoding/colorimetry format */ -#define _DP_MSA_MISC_COLOR(misc1_7, misc0_21, misc0_3, misc0_4) \ - ((misc1_7) << 15 | (misc0_4) << 4 | (misc0_3) << 3 | ((misc0_21) << 1)) -#define DP_MSA_MISC_COLOR_RGB _DP_MSA_MISC_COLOR(0, 0, 0, 0) -#define DP_MSA_MISC_COLOR_CEA_RGB _DP_MSA_MISC_COLOR(0, 0, 1, 0) -#define DP_MSA_MISC_COLOR_RGB_WIDE_FIXED _DP_MSA_MISC_COLOR(0, 3, 0, 0) -#define DP_MSA_MISC_COLOR_RGB_WIDE_FLOAT _DP_MSA_MISC_COLOR(0, 3, 0, 1) -#define DP_MSA_MISC_COLOR_Y_ONLY _DP_MSA_MISC_COLOR(1, 0, 0, 0) -#define DP_MSA_MISC_COLOR_RAW _DP_MSA_MISC_COLOR(1, 1, 0, 0) -#define DP_MSA_MISC_COLOR_YCBCR_422_BT601 _DP_MSA_MISC_COLOR(0, 1, 1, 0) -#define DP_MSA_MISC_COLOR_YCBCR_422_BT709 _DP_MSA_MISC_COLOR(0, 1, 1, 1) -#define DP_MSA_MISC_COLOR_YCBCR_444_BT601 _DP_MSA_MISC_COLOR(0, 2, 1, 0) -#define DP_MSA_MISC_COLOR_YCBCR_444_BT709 _DP_MSA_MISC_COLOR(0, 2, 1, 1) -#define DP_MSA_MISC_COLOR_XVYCC_422_BT601 _DP_MSA_MISC_COLOR(0, 1, 0, 0) -#define DP_MSA_MISC_COLOR_XVYCC_422_BT709 _DP_MSA_MISC_COLOR(0, 1, 0, 1) -#define DP_MSA_MISC_COLOR_XVYCC_444_BT601 _DP_MSA_MISC_COLOR(0, 2, 0, 0) -#define DP_MSA_MISC_COLOR_XVYCC_444_BT709 _DP_MSA_MISC_COLOR(0, 2, 0, 1) -#define DP_MSA_MISC_COLOR_OPRGB _DP_MSA_MISC_COLOR(0, 0, 1, 1) -#define DP_MSA_MISC_COLOR_DCI_P3 _DP_MSA_MISC_COLOR(0, 3, 1, 0) -#define DP_MSA_MISC_COLOR_COLOR_PROFILE _DP_MSA_MISC_COLOR(0, 3, 1, 1) -#define DP_MSA_MISC_COLOR_VSC_SDP (1 << 14) - -#define DP_AUX_MAX_PAYLOAD_BYTES 16 - -#define DP_AUX_I2C_WRITE 0x0 -#define DP_AUX_I2C_READ 0x1 -#define DP_AUX_I2C_WRITE_STATUS_UPDATE 0x2 -#define DP_AUX_I2C_MOT 0x4 -#define DP_AUX_NATIVE_WRITE 0x8 -#define DP_AUX_NATIVE_READ 0x9 - -#define DP_AUX_NATIVE_REPLY_ACK (0x0 << 0) -#define DP_AUX_NATIVE_REPLY_NACK (0x1 << 0) -#define DP_AUX_NATIVE_REPLY_DEFER (0x2 << 0) -#define DP_AUX_NATIVE_REPLY_MASK (0x3 << 0) - -#define DP_AUX_I2C_REPLY_ACK (0x0 << 2) -#define DP_AUX_I2C_REPLY_NACK (0x1 << 2) -#define DP_AUX_I2C_REPLY_DEFER (0x2 << 2) -#define DP_AUX_I2C_REPLY_MASK (0x3 << 2) - -/* DPCD Field Address Mapping */ - -/* Receiver Capability */ -#define DP_DPCD_REV 0x000 -# define DP_DPCD_REV_10 0x10 -# define DP_DPCD_REV_11 0x11 -# define DP_DPCD_REV_12 0x12 -# define DP_DPCD_REV_13 0x13 -# define DP_DPCD_REV_14 0x14 - -#define DP_MAX_LINK_RATE 0x001 - -#define DP_MAX_LANE_COUNT 0x002 -# define DP_MAX_LANE_COUNT_MASK 0x1f -# define DP_TPS3_SUPPORTED (1 << 6) /* 1.2 */ -# define DP_ENHANCED_FRAME_CAP (1 << 7) - -#define DP_MAX_DOWNSPREAD 0x003 -# define DP_MAX_DOWNSPREAD_0_5 (1 << 0) -# define DP_STREAM_REGENERATION_STATUS_CAP (1 << 1) /* 2.0 */ -# define DP_NO_AUX_HANDSHAKE_LINK_TRAINING (1 << 6) -# define DP_TPS4_SUPPORTED (1 << 7) - -#define DP_NORP 0x004 - -#define DP_DOWNSTREAMPORT_PRESENT 0x005 -# define DP_DWN_STRM_PORT_PRESENT (1 << 0) -# define DP_DWN_STRM_PORT_TYPE_MASK 0x06 -# define DP_DWN_STRM_PORT_TYPE_DP (0 << 1) -# define DP_DWN_STRM_PORT_TYPE_ANALOG (1 << 1) -# define DP_DWN_STRM_PORT_TYPE_TMDS (2 << 1) -# define DP_DWN_STRM_PORT_TYPE_OTHER (3 << 1) -# define DP_FORMAT_CONVERSION (1 << 3) -# define DP_DETAILED_CAP_INFO_AVAILABLE (1 << 4) /* DPI */ - -#define DP_MAIN_LINK_CHANNEL_CODING 0x006 -# define DP_CAP_ANSI_8B10B (1 << 0) -# define DP_CAP_ANSI_128B132B (1 << 1) /* 2.0 */ - -#define DP_DOWN_STREAM_PORT_COUNT 0x007 -# define DP_PORT_COUNT_MASK 0x0f -# define DP_MSA_TIMING_PAR_IGNORED (1 << 6) /* eDP */ -# define DP_OUI_SUPPORT (1 << 7) - -#define DP_RECEIVE_PORT_0_CAP_0 0x008 -# define DP_LOCAL_EDID_PRESENT (1 << 1) -# define DP_ASSOCIATED_TO_PRECEDING_PORT (1 << 2) - -#define DP_RECEIVE_PORT_0_BUFFER_SIZE 0x009 - -#define DP_RECEIVE_PORT_1_CAP_0 0x00a -#define DP_RECEIVE_PORT_1_BUFFER_SIZE 0x00b - -#define DP_I2C_SPEED_CAP 0x00c /* DPI */ -# define DP_I2C_SPEED_1K 0x01 -# define DP_I2C_SPEED_5K 0x02 -# define DP_I2C_SPEED_10K 0x04 -# define DP_I2C_SPEED_100K 0x08 -# define DP_I2C_SPEED_400K 0x10 -# define DP_I2C_SPEED_1M 0x20 - -#define DP_EDP_CONFIGURATION_CAP 0x00d /* XXX 1.2? */ -# define DP_ALTERNATE_SCRAMBLER_RESET_CAP (1 << 0) -# define DP_FRAMING_CHANGE_CAP (1 << 1) -# define DP_DPCD_DISPLAY_CONTROL_CAPABLE (1 << 3) /* edp v1.2 or higher */ - -#define DP_TRAINING_AUX_RD_INTERVAL 0x00e /* XXX 1.2? */ -# define DP_TRAINING_AUX_RD_MASK 0x7F /* DP 1.3 */ -# define DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT (1 << 7) /* DP 1.3 */ - -#define DP_ADAPTER_CAP 0x00f /* 1.2 */ -# define DP_FORCE_LOAD_SENSE_CAP (1 << 0) -# define DP_ALTERNATE_I2C_PATTERN_CAP (1 << 1) - -#define DP_SUPPORTED_LINK_RATES 0x010 /* eDP 1.4 */ -# define DP_MAX_SUPPORTED_RATES 8 /* 16-bit little-endian */ - -/* Multiple stream transport */ -#define DP_FAUX_CAP 0x020 /* 1.2 */ -# define DP_FAUX_CAP_1 (1 << 0) - -#define DP_SINK_VIDEO_FALLBACK_FORMATS 0x020 /* 2.0 */ -# define DP_FALLBACK_1024x768_60HZ_24BPP (1 << 0) -# define DP_FALLBACK_1280x720_60HZ_24BPP (1 << 1) -# define DP_FALLBACK_1920x1080_60HZ_24BPP (1 << 2) - -#define DP_MSTM_CAP 0x021 /* 1.2 */ -# define DP_MST_CAP (1 << 0) -# define DP_SINGLE_STREAM_SIDEBAND_MSG (1 << 1) /* 2.0 */ - -#define DP_NUMBER_OF_AUDIO_ENDPOINTS 0x022 /* 1.2 */ - -/* AV_SYNC_DATA_BLOCK 1.2 */ -#define DP_AV_GRANULARITY 0x023 -# define DP_AG_FACTOR_MASK (0xf << 0) -# define DP_AG_FACTOR_3MS (0 << 0) -# define DP_AG_FACTOR_2MS (1 << 0) -# define DP_AG_FACTOR_1MS (2 << 0) -# define DP_AG_FACTOR_500US (3 << 0) -# define DP_AG_FACTOR_200US (4 << 0) -# define DP_AG_FACTOR_100US (5 << 0) -# define DP_AG_FACTOR_10US (6 << 0) -# define DP_AG_FACTOR_1US (7 << 0) -# define DP_VG_FACTOR_MASK (0xf << 4) -# define DP_VG_FACTOR_3MS (0 << 4) -# define DP_VG_FACTOR_2MS (1 << 4) -# define DP_VG_FACTOR_1MS (2 << 4) -# define DP_VG_FACTOR_500US (3 << 4) -# define DP_VG_FACTOR_200US (4 << 4) -# define DP_VG_FACTOR_100US (5 << 4) - -#define DP_AUD_DEC_LAT0 0x024 -#define DP_AUD_DEC_LAT1 0x025 - -#define DP_AUD_PP_LAT0 0x026 -#define DP_AUD_PP_LAT1 0x027 - -#define DP_VID_INTER_LAT 0x028 - -#define DP_VID_PROG_LAT 0x029 - -#define DP_REP_LAT 0x02a - -#define DP_AUD_DEL_INS0 0x02b -#define DP_AUD_DEL_INS1 0x02c -#define DP_AUD_DEL_INS2 0x02d -/* End of AV_SYNC_DATA_BLOCK */ - -#define DP_RECEIVER_ALPM_CAP 0x02e /* eDP 1.4 */ -# define DP_ALPM_CAP (1 << 0) - -#define DP_SINK_DEVICE_AUX_FRAME_SYNC_CAP 0x02f /* eDP 1.4 */ -# define DP_AUX_FRAME_SYNC_CAP (1 << 0) - -#define DP_GUID 0x030 /* 1.2 */ - -#define DP_DSC_SUPPORT 0x060 /* DP 1.4 */ -# define DP_DSC_DECOMPRESSION_IS_SUPPORTED (1 << 0) - -#define DP_DSC_REV 0x061 -# define DP_DSC_MAJOR_MASK (0xf << 0) -# define DP_DSC_MINOR_MASK (0xf << 4) -# define DP_DSC_MAJOR_SHIFT 0 -# define DP_DSC_MINOR_SHIFT 4 - -#define DP_DSC_RC_BUF_BLK_SIZE 0x062 -# define DP_DSC_RC_BUF_BLK_SIZE_1 0x0 -# define DP_DSC_RC_BUF_BLK_SIZE_4 0x1 -# define DP_DSC_RC_BUF_BLK_SIZE_16 0x2 -# define DP_DSC_RC_BUF_BLK_SIZE_64 0x3 - -#define DP_DSC_RC_BUF_SIZE 0x063 - -#define DP_DSC_SLICE_CAP_1 0x064 -# define DP_DSC_1_PER_DP_DSC_SINK (1 << 0) -# define DP_DSC_2_PER_DP_DSC_SINK (1 << 1) -# define DP_DSC_4_PER_DP_DSC_SINK (1 << 3) -# define DP_DSC_6_PER_DP_DSC_SINK (1 << 4) -# define DP_DSC_8_PER_DP_DSC_SINK (1 << 5) -# define DP_DSC_10_PER_DP_DSC_SINK (1 << 6) -# define DP_DSC_12_PER_DP_DSC_SINK (1 << 7) - -#define DP_DSC_LINE_BUF_BIT_DEPTH 0x065 -# define DP_DSC_LINE_BUF_BIT_DEPTH_MASK (0xf << 0) -# define DP_DSC_LINE_BUF_BIT_DEPTH_9 0x0 -# define DP_DSC_LINE_BUF_BIT_DEPTH_10 0x1 -# define DP_DSC_LINE_BUF_BIT_DEPTH_11 0x2 -# define DP_DSC_LINE_BUF_BIT_DEPTH_12 0x3 -# define DP_DSC_LINE_BUF_BIT_DEPTH_13 0x4 -# define DP_DSC_LINE_BUF_BIT_DEPTH_14 0x5 -# define DP_DSC_LINE_BUF_BIT_DEPTH_15 0x6 -# define DP_DSC_LINE_BUF_BIT_DEPTH_16 0x7 -# define DP_DSC_LINE_BUF_BIT_DEPTH_8 0x8 - -#define DP_DSC_BLK_PREDICTION_SUPPORT 0x066 -# define DP_DSC_BLK_PREDICTION_IS_SUPPORTED (1 << 0) - -#define DP_DSC_MAX_BITS_PER_PIXEL_LOW 0x067 /* eDP 1.4 */ - -#define DP_DSC_MAX_BITS_PER_PIXEL_HI 0x068 /* eDP 1.4 */ -# define DP_DSC_MAX_BITS_PER_PIXEL_HI_MASK (0x3 << 0) -# define DP_DSC_MAX_BITS_PER_PIXEL_HI_SHIFT 8 - -#define DP_DSC_DEC_COLOR_FORMAT_CAP 0x069 -# define DP_DSC_RGB (1 << 0) -# define DP_DSC_YCbCr444 (1 << 1) -# define DP_DSC_YCbCr422_Simple (1 << 2) -# define DP_DSC_YCbCr422_Native (1 << 3) -# define DP_DSC_YCbCr420_Native (1 << 4) - -#define DP_DSC_DEC_COLOR_DEPTH_CAP 0x06A -# define DP_DSC_8_BPC (1 << 1) -# define DP_DSC_10_BPC (1 << 2) -# define DP_DSC_12_BPC (1 << 3) - -#define DP_DSC_PEAK_THROUGHPUT 0x06B -# define DP_DSC_THROUGHPUT_MODE_0_MASK (0xf << 0) -# define DP_DSC_THROUGHPUT_MODE_0_SHIFT 0 -# define DP_DSC_THROUGHPUT_MODE_0_UNSUPPORTED 0 -# define DP_DSC_THROUGHPUT_MODE_0_340 (1 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_400 (2 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_450 (3 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_500 (4 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_550 (5 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_600 (6 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_650 (7 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_700 (8 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_750 (9 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_800 (10 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_850 (11 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_900 (12 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_950 (13 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_1000 (14 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_170 (15 << 0) /* 1.4a */ -# define DP_DSC_THROUGHPUT_MODE_1_MASK (0xf << 4) -# define DP_DSC_THROUGHPUT_MODE_1_SHIFT 4 -# define DP_DSC_THROUGHPUT_MODE_1_UNSUPPORTED 0 -# define DP_DSC_THROUGHPUT_MODE_1_340 (1 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_400 (2 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_450 (3 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_500 (4 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_550 (5 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_600 (6 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_650 (7 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_700 (8 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_750 (9 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_800 (10 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_850 (11 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_900 (12 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_950 (13 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_1000 (14 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_170 (15 << 4) - -#define DP_DSC_MAX_SLICE_WIDTH 0x06C -#define DP_DSC_MIN_SLICE_WIDTH_VALUE 2560 -#define DP_DSC_SLICE_WIDTH_MULTIPLIER 320 - -#define DP_DSC_SLICE_CAP_2 0x06D -# define DP_DSC_16_PER_DP_DSC_SINK (1 << 0) -# define DP_DSC_20_PER_DP_DSC_SINK (1 << 1) -# define DP_DSC_24_PER_DP_DSC_SINK (1 << 2) - -#define DP_DSC_BITS_PER_PIXEL_INC 0x06F -# define DP_DSC_BITS_PER_PIXEL_1_16 0x0 -# define DP_DSC_BITS_PER_PIXEL_1_8 0x1 -# define DP_DSC_BITS_PER_PIXEL_1_4 0x2 -# define DP_DSC_BITS_PER_PIXEL_1_2 0x3 -# define DP_DSC_BITS_PER_PIXEL_1 0x4 - -#define DP_PSR_SUPPORT 0x070 /* XXX 1.2? */ -# define DP_PSR_IS_SUPPORTED 1 -# define DP_PSR2_IS_SUPPORTED 2 /* eDP 1.4 */ -# define DP_PSR2_WITH_Y_COORD_IS_SUPPORTED 3 /* eDP 1.4a */ - -#define DP_PSR_CAPS 0x071 /* XXX 1.2? */ -# define DP_PSR_NO_TRAIN_ON_EXIT 1 -# define DP_PSR_SETUP_TIME_330 (0 << 1) -# define DP_PSR_SETUP_TIME_275 (1 << 1) -# define DP_PSR_SETUP_TIME_220 (2 << 1) -# define DP_PSR_SETUP_TIME_165 (3 << 1) -# define DP_PSR_SETUP_TIME_110 (4 << 1) -# define DP_PSR_SETUP_TIME_55 (5 << 1) -# define DP_PSR_SETUP_TIME_0 (6 << 1) -# define DP_PSR_SETUP_TIME_MASK (7 << 1) -# define DP_PSR_SETUP_TIME_SHIFT 1 -# define DP_PSR2_SU_Y_COORDINATE_REQUIRED (1 << 4) /* eDP 1.4a */ -# define DP_PSR2_SU_GRANULARITY_REQUIRED (1 << 5) /* eDP 1.4b */ - -#define DP_PSR2_SU_X_GRANULARITY 0x072 /* eDP 1.4b */ -#define DP_PSR2_SU_Y_GRANULARITY 0x074 /* eDP 1.4b */ - -/* - * 0x80-0x8f describe downstream port capabilities, but there are two layouts - * based on whether DP_DETAILED_CAP_INFO_AVAILABLE was set. If it was not, - * each port's descriptor is one byte wide. If it was set, each port's is - * four bytes wide, starting with the one byte from the base info. As of - * DP interop v1.1a only VGA defines additional detail. - */ - -/* offset 0 */ -#define DP_DOWNSTREAM_PORT_0 0x80 -# define DP_DS_PORT_TYPE_MASK (7 << 0) -# define DP_DS_PORT_TYPE_DP 0 -# define DP_DS_PORT_TYPE_VGA 1 -# define DP_DS_PORT_TYPE_DVI 2 -# define DP_DS_PORT_TYPE_HDMI 3 -# define DP_DS_PORT_TYPE_NON_EDID 4 -# define DP_DS_PORT_TYPE_DP_DUALMODE 5 -# define DP_DS_PORT_TYPE_WIRELESS 6 -# define DP_DS_PORT_HPD (1 << 3) -# define DP_DS_NON_EDID_MASK (0xf << 4) -# define DP_DS_NON_EDID_720x480i_60 (1 << 4) -# define DP_DS_NON_EDID_720x480i_50 (2 << 4) -# define DP_DS_NON_EDID_1920x1080i_60 (3 << 4) -# define DP_DS_NON_EDID_1920x1080i_50 (4 << 4) -# define DP_DS_NON_EDID_1280x720_60 (5 << 4) -# define DP_DS_NON_EDID_1280x720_50 (7 << 4) -/* offset 1 for VGA is maximum megapixels per second / 8 */ -/* offset 1 for DVI/HDMI is maximum TMDS clock in Mbps / 2.5 */ -/* offset 2 for VGA/DVI/HDMI */ -# define DP_DS_MAX_BPC_MASK (3 << 0) -# define DP_DS_8BPC 0 -# define DP_DS_10BPC 1 -# define DP_DS_12BPC 2 -# define DP_DS_16BPC 3 -/* HDMI2.1 PCON FRL CONFIGURATION */ -# define DP_PCON_MAX_FRL_BW (7 << 2) -# define DP_PCON_MAX_0GBPS (0 << 2) -# define DP_PCON_MAX_9GBPS (1 << 2) -# define DP_PCON_MAX_18GBPS (2 << 2) -# define DP_PCON_MAX_24GBPS (3 << 2) -# define DP_PCON_MAX_32GBPS (4 << 2) -# define DP_PCON_MAX_40GBPS (5 << 2) -# define DP_PCON_MAX_48GBPS (6 << 2) -# define DP_PCON_SOURCE_CTL_MODE (1 << 5) - -/* offset 3 for DVI */ -# define DP_DS_DVI_DUAL_LINK (1 << 1) -# define DP_DS_DVI_HIGH_COLOR_DEPTH (1 << 2) -/* offset 3 for HDMI */ -# define DP_DS_HDMI_FRAME_SEQ_TO_FRAME_PACK (1 << 0) -# define DP_DS_HDMI_YCBCR422_PASS_THROUGH (1 << 1) -# define DP_DS_HDMI_YCBCR420_PASS_THROUGH (1 << 2) -# define DP_DS_HDMI_YCBCR444_TO_422_CONV (1 << 3) -# define DP_DS_HDMI_YCBCR444_TO_420_CONV (1 << 4) - -/* - * VESA DP-to-HDMI PCON Specification adds caps for colorspace - * conversion in DFP cap DPCD 83h. Sec6.1 Table-3. - * Based on the available support the source can enable - * color conversion by writing into PROTOCOL_COVERTER_CONTROL_2 - * DPCD 3052h. - */ -# define DP_DS_HDMI_BT601_RGB_YCBCR_CONV (1 << 5) -# define DP_DS_HDMI_BT709_RGB_YCBCR_CONV (1 << 6) -# define DP_DS_HDMI_BT2020_RGB_YCBCR_CONV (1 << 7) - -#define DP_MAX_DOWNSTREAM_PORTS 0x10 - -/* DP Forward error Correction Registers */ -#define DP_FEC_CAPABILITY 0x090 /* 1.4 */ -# define DP_FEC_CAPABLE (1 << 0) -# define DP_FEC_UNCORR_BLK_ERROR_COUNT_CAP (1 << 1) -# define DP_FEC_CORR_BLK_ERROR_COUNT_CAP (1 << 2) -# define DP_FEC_BIT_ERROR_COUNT_CAP (1 << 3) -#define DP_FEC_CAPABILITY_1 0x091 /* 2.0 */ - -/* DP-HDMI2.1 PCON DSC ENCODER SUPPORT */ -#define DP_PCON_DSC_ENCODER_CAP_SIZE 0xD /* 0x92 through 0x9E */ -#define DP_PCON_DSC_ENCODER 0x092 -# define DP_PCON_DSC_ENCODER_SUPPORTED (1 << 0) -# define DP_PCON_DSC_PPS_ENC_OVERRIDE (1 << 1) - -/* DP-HDMI2.1 PCON DSC Version */ -#define DP_PCON_DSC_VERSION 0x093 -# define DP_PCON_DSC_MAJOR_MASK (0xF << 0) -# define DP_PCON_DSC_MINOR_MASK (0xF << 4) -# define DP_PCON_DSC_MAJOR_SHIFT 0 -# define DP_PCON_DSC_MINOR_SHIFT 4 - -/* DP-HDMI2.1 PCON DSC RC Buffer block size */ -#define DP_PCON_DSC_RC_BUF_BLK_INFO 0x094 -# define DP_PCON_DSC_RC_BUF_BLK_SIZE (0x3 << 0) -# define DP_PCON_DSC_RC_BUF_BLK_1KB 0 -# define DP_PCON_DSC_RC_BUF_BLK_4KB 1 -# define DP_PCON_DSC_RC_BUF_BLK_16KB 2 -# define DP_PCON_DSC_RC_BUF_BLK_64KB 3 - -/* DP-HDMI2.1 PCON DSC RC Buffer size */ -#define DP_PCON_DSC_RC_BUF_SIZE 0x095 - -/* DP-HDMI2.1 PCON DSC Slice capabilities-1 */ -#define DP_PCON_DSC_SLICE_CAP_1 0x096 -# define DP_PCON_DSC_1_PER_DSC_ENC (0x1 << 0) -# define DP_PCON_DSC_2_PER_DSC_ENC (0x1 << 1) -# define DP_PCON_DSC_4_PER_DSC_ENC (0x1 << 3) -# define DP_PCON_DSC_6_PER_DSC_ENC (0x1 << 4) -# define DP_PCON_DSC_8_PER_DSC_ENC (0x1 << 5) -# define DP_PCON_DSC_10_PER_DSC_ENC (0x1 << 6) -# define DP_PCON_DSC_12_PER_DSC_ENC (0x1 << 7) - -#define DP_PCON_DSC_BUF_BIT_DEPTH 0x097 -# define DP_PCON_DSC_BIT_DEPTH_MASK (0xF << 0) -# define DP_PCON_DSC_DEPTH_9_BITS 0 -# define DP_PCON_DSC_DEPTH_10_BITS 1 -# define DP_PCON_DSC_DEPTH_11_BITS 2 -# define DP_PCON_DSC_DEPTH_12_BITS 3 -# define DP_PCON_DSC_DEPTH_13_BITS 4 -# define DP_PCON_DSC_DEPTH_14_BITS 5 -# define DP_PCON_DSC_DEPTH_15_BITS 6 -# define DP_PCON_DSC_DEPTH_16_BITS 7 -# define DP_PCON_DSC_DEPTH_8_BITS 8 - -#define DP_PCON_DSC_BLOCK_PREDICTION 0x098 -# define DP_PCON_DSC_BLOCK_PRED_SUPPORT (0x1 << 0) - -#define DP_PCON_DSC_ENC_COLOR_FMT_CAP 0x099 -# define DP_PCON_DSC_ENC_RGB (0x1 << 0) -# define DP_PCON_DSC_ENC_YUV444 (0x1 << 1) -# define DP_PCON_DSC_ENC_YUV422_S (0x1 << 2) -# define DP_PCON_DSC_ENC_YUV422_N (0x1 << 3) -# define DP_PCON_DSC_ENC_YUV420_N (0x1 << 4) - -#define DP_PCON_DSC_ENC_COLOR_DEPTH_CAP 0x09A -# define DP_PCON_DSC_ENC_8BPC (0x1 << 1) -# define DP_PCON_DSC_ENC_10BPC (0x1 << 2) -# define DP_PCON_DSC_ENC_12BPC (0x1 << 3) - -#define DP_PCON_DSC_MAX_SLICE_WIDTH 0x09B - -/* DP-HDMI2.1 PCON DSC Slice capabilities-2 */ -#define DP_PCON_DSC_SLICE_CAP_2 0x09C -# define DP_PCON_DSC_16_PER_DSC_ENC (0x1 << 0) -# define DP_PCON_DSC_20_PER_DSC_ENC (0x1 << 1) -# define DP_PCON_DSC_24_PER_DSC_ENC (0x1 << 2) - -/* DP-HDMI2.1 PCON HDMI TX Encoder Bits/pixel increment */ -#define DP_PCON_DSC_BPP_INCR 0x09E -# define DP_PCON_DSC_BPP_INCR_MASK (0x7 << 0) -# define DP_PCON_DSC_ONE_16TH_BPP 0 -# define DP_PCON_DSC_ONE_8TH_BPP 1 -# define DP_PCON_DSC_ONE_4TH_BPP 2 -# define DP_PCON_DSC_ONE_HALF_BPP 3 -# define DP_PCON_DSC_ONE_BPP 4 - -/* DP Extended DSC Capabilities */ -#define DP_DSC_BRANCH_OVERALL_THROUGHPUT_0 0x0a0 /* DP 1.4a SCR */ -#define DP_DSC_BRANCH_OVERALL_THROUGHPUT_1 0x0a1 -#define DP_DSC_BRANCH_MAX_LINE_WIDTH 0x0a2 - -/* DFP Capability Extension */ -#define DP_DFP_CAPABILITY_EXTENSION_SUPPORT 0x0a3 /* 2.0 */ - -/* Link Configuration */ -#define DP_LINK_BW_SET 0x100 -# define DP_LINK_RATE_TABLE 0x00 /* eDP 1.4 */ -# define DP_LINK_BW_1_62 0x06 -# define DP_LINK_BW_2_7 0x0a -# define DP_LINK_BW_5_4 0x14 /* 1.2 */ -# define DP_LINK_BW_8_1 0x1e /* 1.4 */ -# define DP_LINK_BW_10 0x01 /* 2.0 128b/132b Link Layer */ -# define DP_LINK_BW_13_5 0x04 /* 2.0 128b/132b Link Layer */ -# define DP_LINK_BW_20 0x02 /* 2.0 128b/132b Link Layer */ - -#define DP_LANE_COUNT_SET 0x101 -# define DP_LANE_COUNT_MASK 0x0f -# define DP_LANE_COUNT_ENHANCED_FRAME_EN (1 << 7) - -#define DP_TRAINING_PATTERN_SET 0x102 -# define DP_TRAINING_PATTERN_DISABLE 0 -# define DP_TRAINING_PATTERN_1 1 -# define DP_TRAINING_PATTERN_2 2 -# define DP_TRAINING_PATTERN_2_CDS 3 /* 2.0 E11 */ -# define DP_TRAINING_PATTERN_3 3 /* 1.2 */ -# define DP_TRAINING_PATTERN_4 7 /* 1.4 */ -# define DP_TRAINING_PATTERN_MASK 0x3 -# define DP_TRAINING_PATTERN_MASK_1_4 0xf - -/* DPCD 1.1 only. For DPCD >= 1.2 see per-lane DP_LINK_QUAL_LANEn_SET */ -# define DP_LINK_QUAL_PATTERN_11_DISABLE (0 << 2) -# define DP_LINK_QUAL_PATTERN_11_D10_2 (1 << 2) -# define DP_LINK_QUAL_PATTERN_11_ERROR_RATE (2 << 2) -# define DP_LINK_QUAL_PATTERN_11_PRBS7 (3 << 2) -# define DP_LINK_QUAL_PATTERN_11_MASK (3 << 2) - -# define DP_RECOVERED_CLOCK_OUT_EN (1 << 4) -# define DP_LINK_SCRAMBLING_DISABLE (1 << 5) - -# define DP_SYMBOL_ERROR_COUNT_BOTH (0 << 6) -# define DP_SYMBOL_ERROR_COUNT_DISPARITY (1 << 6) -# define DP_SYMBOL_ERROR_COUNT_SYMBOL (2 << 6) -# define DP_SYMBOL_ERROR_COUNT_MASK (3 << 6) - -#define DP_TRAINING_LANE0_SET 0x103 -#define DP_TRAINING_LANE1_SET 0x104 -#define DP_TRAINING_LANE2_SET 0x105 -#define DP_TRAINING_LANE3_SET 0x106 - -# define DP_TRAIN_VOLTAGE_SWING_MASK 0x3 -# define DP_TRAIN_VOLTAGE_SWING_SHIFT 0 -# define DP_TRAIN_MAX_SWING_REACHED (1 << 2) -# define DP_TRAIN_VOLTAGE_SWING_LEVEL_0 (0 << 0) -# define DP_TRAIN_VOLTAGE_SWING_LEVEL_1 (1 << 0) -# define DP_TRAIN_VOLTAGE_SWING_LEVEL_2 (2 << 0) -# define DP_TRAIN_VOLTAGE_SWING_LEVEL_3 (3 << 0) - -# define DP_TRAIN_PRE_EMPHASIS_MASK (3 << 3) -# define DP_TRAIN_PRE_EMPH_LEVEL_0 (0 << 3) -# define DP_TRAIN_PRE_EMPH_LEVEL_1 (1 << 3) -# define DP_TRAIN_PRE_EMPH_LEVEL_2 (2 << 3) -# define DP_TRAIN_PRE_EMPH_LEVEL_3 (3 << 3) - -# define DP_TRAIN_PRE_EMPHASIS_SHIFT 3 -# define DP_TRAIN_MAX_PRE_EMPHASIS_REACHED (1 << 5) - -# define DP_TX_FFE_PRESET_VALUE_MASK (0xf << 0) /* 2.0 128b/132b Link Layer */ - -#define DP_DOWNSPREAD_CTRL 0x107 -# define DP_SPREAD_AMP_0_5 (1 << 4) -# define DP_MSA_TIMING_PAR_IGNORE_EN (1 << 7) /* eDP */ - -#define DP_MAIN_LINK_CHANNEL_CODING_SET 0x108 -# define DP_SET_ANSI_8B10B (1 << 0) -# define DP_SET_ANSI_128B132B (1 << 1) - -#define DP_I2C_SPEED_CONTROL_STATUS 0x109 /* DPI */ -/* bitmask as for DP_I2C_SPEED_CAP */ - -#define DP_EDP_CONFIGURATION_SET 0x10a /* XXX 1.2? */ -# define DP_ALTERNATE_SCRAMBLER_RESET_ENABLE (1 << 0) -# define DP_FRAMING_CHANGE_ENABLE (1 << 1) -# define DP_PANEL_SELF_TEST_ENABLE (1 << 7) - -#define DP_LINK_QUAL_LANE0_SET 0x10b /* DPCD >= 1.2 */ -#define DP_LINK_QUAL_LANE1_SET 0x10c -#define DP_LINK_QUAL_LANE2_SET 0x10d -#define DP_LINK_QUAL_LANE3_SET 0x10e -# define DP_LINK_QUAL_PATTERN_DISABLE 0 -# define DP_LINK_QUAL_PATTERN_D10_2 1 -# define DP_LINK_QUAL_PATTERN_ERROR_RATE 2 -# define DP_LINK_QUAL_PATTERN_PRBS7 3 -# define DP_LINK_QUAL_PATTERN_80BIT_CUSTOM 4 -# define DP_LINK_QUAL_PATTERN_CP2520_PAT_1 5 -# define DP_LINK_QUAL_PATTERN_CP2520_PAT_2 6 -# define DP_LINK_QUAL_PATTERN_CP2520_PAT_3 7 -/* DP 2.0 UHBR10, UHBR13.5, UHBR20 */ -# define DP_LINK_QUAL_PATTERN_128B132B_TPS1 0x08 -# define DP_LINK_QUAL_PATTERN_128B132B_TPS2 0x10 -# define DP_LINK_QUAL_PATTERN_PRSBS9 0x18 -# define DP_LINK_QUAL_PATTERN_PRSBS11 0x20 -# define DP_LINK_QUAL_PATTERN_PRSBS15 0x28 -# define DP_LINK_QUAL_PATTERN_PRSBS23 0x30 -# define DP_LINK_QUAL_PATTERN_PRSBS31 0x38 -# define DP_LINK_QUAL_PATTERN_CUSTOM 0x40 -# define DP_LINK_QUAL_PATTERN_SQUARE 0x48 - -#define DP_TRAINING_LANE0_1_SET2 0x10f -#define DP_TRAINING_LANE2_3_SET2 0x110 -# define DP_LANE02_POST_CURSOR2_SET_MASK (3 << 0) -# define DP_LANE02_MAX_POST_CURSOR2_REACHED (1 << 2) -# define DP_LANE13_POST_CURSOR2_SET_MASK (3 << 4) -# define DP_LANE13_MAX_POST_CURSOR2_REACHED (1 << 6) - -#define DP_MSTM_CTRL 0x111 /* 1.2 */ -# define DP_MST_EN (1 << 0) -# define DP_UP_REQ_EN (1 << 1) -# define DP_UPSTREAM_IS_SRC (1 << 2) - -#define DP_AUDIO_DELAY0 0x112 /* 1.2 */ -#define DP_AUDIO_DELAY1 0x113 -#define DP_AUDIO_DELAY2 0x114 - -#define DP_LINK_RATE_SET 0x115 /* eDP 1.4 */ -# define DP_LINK_RATE_SET_SHIFT 0 -# define DP_LINK_RATE_SET_MASK (7 << 0) - -#define DP_RECEIVER_ALPM_CONFIG 0x116 /* eDP 1.4 */ -# define DP_ALPM_ENABLE (1 << 0) -# define DP_ALPM_LOCK_ERROR_IRQ_HPD_ENABLE (1 << 1) - -#define DP_SINK_DEVICE_AUX_FRAME_SYNC_CONF 0x117 /* eDP 1.4 */ -# define DP_AUX_FRAME_SYNC_ENABLE (1 << 0) -# define DP_IRQ_HPD_ENABLE (1 << 1) - -#define DP_UPSTREAM_DEVICE_DP_PWR_NEED 0x118 /* 1.2 */ -# define DP_PWR_NOT_NEEDED (1 << 0) - -#define DP_FEC_CONFIGURATION 0x120 /* 1.4 */ -# define DP_FEC_READY (1 << 0) -# define DP_FEC_ERR_COUNT_SEL_MASK (7 << 1) -# define DP_FEC_ERR_COUNT_DIS (0 << 1) -# define DP_FEC_UNCORR_BLK_ERROR_COUNT (1 << 1) -# define DP_FEC_CORR_BLK_ERROR_COUNT (2 << 1) -# define DP_FEC_BIT_ERROR_COUNT (3 << 1) -# define DP_FEC_LANE_SELECT_MASK (3 << 4) -# define DP_FEC_LANE_0_SELECT (0 << 4) -# define DP_FEC_LANE_1_SELECT (1 << 4) -# define DP_FEC_LANE_2_SELECT (2 << 4) -# define DP_FEC_LANE_3_SELECT (3 << 4) - -#define DP_AUX_FRAME_SYNC_VALUE 0x15c /* eDP 1.4 */ -# define DP_AUX_FRAME_SYNC_VALID (1 << 0) - -#define DP_DSC_ENABLE 0x160 /* DP 1.4 */ -# define DP_DECOMPRESSION_EN (1 << 0) -#define DP_DSC_CONFIGURATION 0x161 /* DP 2.0 */ - -#define DP_PSR_EN_CFG 0x170 /* XXX 1.2? */ -# define DP_PSR_ENABLE BIT(0) -# define DP_PSR_MAIN_LINK_ACTIVE BIT(1) -# define DP_PSR_CRC_VERIFICATION BIT(2) -# define DP_PSR_FRAME_CAPTURE BIT(3) -# define DP_PSR_SU_REGION_SCANLINE_CAPTURE BIT(4) /* eDP 1.4a */ -# define DP_PSR_IRQ_HPD_WITH_CRC_ERRORS BIT(5) /* eDP 1.4a */ -# define DP_PSR_ENABLE_PSR2 BIT(6) /* eDP 1.4a */ - -#define DP_ADAPTER_CTRL 0x1a0 -# define DP_ADAPTER_CTRL_FORCE_LOAD_SENSE (1 << 0) - -#define DP_BRANCH_DEVICE_CTRL 0x1a1 -# define DP_BRANCH_DEVICE_IRQ_HPD (1 << 0) - -#define DP_PAYLOAD_ALLOCATE_SET 0x1c0 -#define DP_PAYLOAD_ALLOCATE_START_TIME_SLOT 0x1c1 -#define DP_PAYLOAD_ALLOCATE_TIME_SLOT_COUNT 0x1c2 - -/* Link/Sink Device Status */ -#define DP_SINK_COUNT 0x200 -/* prior to 1.2 bit 7 was reserved mbz */ -# define DP_GET_SINK_COUNT(x) ((((x) & 0x80) >> 1) | ((x) & 0x3f)) -# define DP_SINK_CP_READY (1 << 6) - -#define DP_DEVICE_SERVICE_IRQ_VECTOR 0x201 -# define DP_REMOTE_CONTROL_COMMAND_PENDING (1 << 0) -# define DP_AUTOMATED_TEST_REQUEST (1 << 1) -# define DP_CP_IRQ (1 << 2) -# define DP_MCCS_IRQ (1 << 3) -# define DP_DOWN_REP_MSG_RDY (1 << 4) /* 1.2 MST */ -# define DP_UP_REQ_MSG_RDY (1 << 5) /* 1.2 MST */ -# define DP_SINK_SPECIFIC_IRQ (1 << 6) - -#define DP_LANE0_1_STATUS 0x202 -#define DP_LANE2_3_STATUS 0x203 -# define DP_LANE_CR_DONE (1 << 0) -# define DP_LANE_CHANNEL_EQ_DONE (1 << 1) -# define DP_LANE_SYMBOL_LOCKED (1 << 2) - -#define DP_CHANNEL_EQ_BITS (DP_LANE_CR_DONE | \ - DP_LANE_CHANNEL_EQ_DONE | \ - DP_LANE_SYMBOL_LOCKED) - -#define DP_LANE_ALIGN_STATUS_UPDATED 0x204 -#define DP_INTERLANE_ALIGN_DONE (1 << 0) -#define DP_128B132B_DPRX_EQ_INTERLANE_ALIGN_DONE (1 << 2) /* 2.0 E11 */ -#define DP_128B132B_DPRX_CDS_INTERLANE_ALIGN_DONE (1 << 3) /* 2.0 E11 */ -#define DP_128B132B_LT_FAILED (1 << 4) /* 2.0 E11 */ -#define DP_DOWNSTREAM_PORT_STATUS_CHANGED (1 << 6) -#define DP_LINK_STATUS_UPDATED (1 << 7) - -#define DP_SINK_STATUS 0x205 -# define DP_RECEIVE_PORT_0_STATUS (1 << 0) -# define DP_RECEIVE_PORT_1_STATUS (1 << 1) -# define DP_STREAM_REGENERATION_STATUS (1 << 2) /* 2.0 */ -# define DP_INTRA_HOP_AUX_REPLY_INDICATION (1 << 3) /* 2.0 */ - -#define DP_ADJUST_REQUEST_LANE0_1 0x206 -#define DP_ADJUST_REQUEST_LANE2_3 0x207 -# define DP_ADJUST_VOLTAGE_SWING_LANE0_MASK 0x03 -# define DP_ADJUST_VOLTAGE_SWING_LANE0_SHIFT 0 -# define DP_ADJUST_PRE_EMPHASIS_LANE0_MASK 0x0c -# define DP_ADJUST_PRE_EMPHASIS_LANE0_SHIFT 2 -# define DP_ADJUST_VOLTAGE_SWING_LANE1_MASK 0x30 -# define DP_ADJUST_VOLTAGE_SWING_LANE1_SHIFT 4 -# define DP_ADJUST_PRE_EMPHASIS_LANE1_MASK 0xc0 -# define DP_ADJUST_PRE_EMPHASIS_LANE1_SHIFT 6 - -/* DP 2.0 128b/132b Link Layer */ -# define DP_ADJUST_TX_FFE_PRESET_LANE0_MASK (0xf << 0) -# define DP_ADJUST_TX_FFE_PRESET_LANE0_SHIFT 0 -# define DP_ADJUST_TX_FFE_PRESET_LANE1_MASK (0xf << 4) -# define DP_ADJUST_TX_FFE_PRESET_LANE1_SHIFT 4 - -#define DP_ADJUST_REQUEST_POST_CURSOR2 0x20c -# define DP_ADJUST_POST_CURSOR2_LANE0_MASK 0x03 -# define DP_ADJUST_POST_CURSOR2_LANE0_SHIFT 0 -# define DP_ADJUST_POST_CURSOR2_LANE1_MASK 0x0c -# define DP_ADJUST_POST_CURSOR2_LANE1_SHIFT 2 -# define DP_ADJUST_POST_CURSOR2_LANE2_MASK 0x30 -# define DP_ADJUST_POST_CURSOR2_LANE2_SHIFT 4 -# define DP_ADJUST_POST_CURSOR2_LANE3_MASK 0xc0 -# define DP_ADJUST_POST_CURSOR2_LANE3_SHIFT 6 - -#define DP_TEST_REQUEST 0x218 -# define DP_TEST_LINK_TRAINING (1 << 0) -# define DP_TEST_LINK_VIDEO_PATTERN (1 << 1) -# define DP_TEST_LINK_EDID_READ (1 << 2) -# define DP_TEST_LINK_PHY_TEST_PATTERN (1 << 3) /* DPCD >= 1.1 */ -# define DP_TEST_LINK_FAUX_PATTERN (1 << 4) /* DPCD >= 1.2 */ -# define DP_TEST_LINK_AUDIO_PATTERN (1 << 5) /* DPCD >= 1.2 */ -# define DP_TEST_LINK_AUDIO_DISABLED_VIDEO (1 << 6) /* DPCD >= 1.2 */ - -#define DP_TEST_LINK_RATE 0x219 -# define DP_LINK_RATE_162 (0x6) -# define DP_LINK_RATE_27 (0xa) - -#define DP_TEST_LANE_COUNT 0x220 - -#define DP_TEST_PATTERN 0x221 -# define DP_NO_TEST_PATTERN 0x0 -# define DP_COLOR_RAMP 0x1 -# define DP_BLACK_AND_WHITE_VERTICAL_LINES 0x2 -# define DP_COLOR_SQUARE 0x3 - -#define DP_TEST_H_TOTAL_HI 0x222 -#define DP_TEST_H_TOTAL_LO 0x223 - -#define DP_TEST_V_TOTAL_HI 0x224 -#define DP_TEST_V_TOTAL_LO 0x225 - -#define DP_TEST_H_START_HI 0x226 -#define DP_TEST_H_START_LO 0x227 - -#define DP_TEST_V_START_HI 0x228 -#define DP_TEST_V_START_LO 0x229 - -#define DP_TEST_HSYNC_HI 0x22A -# define DP_TEST_HSYNC_POLARITY (1 << 7) -# define DP_TEST_HSYNC_WIDTH_HI_MASK (127 << 0) -#define DP_TEST_HSYNC_WIDTH_LO 0x22B - -#define DP_TEST_VSYNC_HI 0x22C -# define DP_TEST_VSYNC_POLARITY (1 << 7) -# define DP_TEST_VSYNC_WIDTH_HI_MASK (127 << 0) -#define DP_TEST_VSYNC_WIDTH_LO 0x22D - -#define DP_TEST_H_WIDTH_HI 0x22E -#define DP_TEST_H_WIDTH_LO 0x22F - -#define DP_TEST_V_HEIGHT_HI 0x230 -#define DP_TEST_V_HEIGHT_LO 0x231 - -#define DP_TEST_MISC0 0x232 -# define DP_TEST_SYNC_CLOCK (1 << 0) -# define DP_TEST_COLOR_FORMAT_MASK (3 << 1) -# define DP_TEST_COLOR_FORMAT_SHIFT 1 -# define DP_COLOR_FORMAT_RGB (0 << 1) -# define DP_COLOR_FORMAT_YCbCr422 (1 << 1) -# define DP_COLOR_FORMAT_YCbCr444 (2 << 1) -# define DP_TEST_DYNAMIC_RANGE_VESA (0 << 3) -# define DP_TEST_DYNAMIC_RANGE_CEA (1 << 3) -# define DP_TEST_YCBCR_COEFFICIENTS (1 << 4) -# define DP_YCBCR_COEFFICIENTS_ITU601 (0 << 4) -# define DP_YCBCR_COEFFICIENTS_ITU709 (1 << 4) -# define DP_TEST_BIT_DEPTH_MASK (7 << 5) -# define DP_TEST_BIT_DEPTH_SHIFT 5 -# define DP_TEST_BIT_DEPTH_6 (0 << 5) -# define DP_TEST_BIT_DEPTH_8 (1 << 5) -# define DP_TEST_BIT_DEPTH_10 (2 << 5) -# define DP_TEST_BIT_DEPTH_12 (3 << 5) -# define DP_TEST_BIT_DEPTH_16 (4 << 5) - -#define DP_TEST_MISC1 0x233 -# define DP_TEST_REFRESH_DENOMINATOR (1 << 0) -# define DP_TEST_INTERLACED (1 << 1) - -#define DP_TEST_REFRESH_RATE_NUMERATOR 0x234 - -#define DP_TEST_MISC0 0x232 - -#define DP_TEST_CRC_R_CR 0x240 -#define DP_TEST_CRC_G_Y 0x242 -#define DP_TEST_CRC_B_CB 0x244 - -#define DP_TEST_SINK_MISC 0x246 -# define DP_TEST_CRC_SUPPORTED (1 << 5) -# define DP_TEST_COUNT_MASK 0xf - -#define DP_PHY_TEST_PATTERN 0x248 -# define DP_PHY_TEST_PATTERN_SEL_MASK 0x7 -# define DP_PHY_TEST_PATTERN_NONE 0x0 -# define DP_PHY_TEST_PATTERN_D10_2 0x1 -# define DP_PHY_TEST_PATTERN_ERROR_COUNT 0x2 -# define DP_PHY_TEST_PATTERN_PRBS7 0x3 -# define DP_PHY_TEST_PATTERN_80BIT_CUSTOM 0x4 -# define DP_PHY_TEST_PATTERN_CP2520 0x5 - -#define DP_PHY_SQUARE_PATTERN 0x249 - -#define DP_TEST_HBR2_SCRAMBLER_RESET 0x24A -#define DP_TEST_80BIT_CUSTOM_PATTERN_7_0 0x250 -#define DP_TEST_80BIT_CUSTOM_PATTERN_15_8 0x251 -#define DP_TEST_80BIT_CUSTOM_PATTERN_23_16 0x252 -#define DP_TEST_80BIT_CUSTOM_PATTERN_31_24 0x253 -#define DP_TEST_80BIT_CUSTOM_PATTERN_39_32 0x254 -#define DP_TEST_80BIT_CUSTOM_PATTERN_47_40 0x255 -#define DP_TEST_80BIT_CUSTOM_PATTERN_55_48 0x256 -#define DP_TEST_80BIT_CUSTOM_PATTERN_63_56 0x257 -#define DP_TEST_80BIT_CUSTOM_PATTERN_71_64 0x258 -#define DP_TEST_80BIT_CUSTOM_PATTERN_79_72 0x259 - -#define DP_TEST_RESPONSE 0x260 -# define DP_TEST_ACK (1 << 0) -# define DP_TEST_NAK (1 << 1) -# define DP_TEST_EDID_CHECKSUM_WRITE (1 << 2) - -#define DP_TEST_EDID_CHECKSUM 0x261 - -#define DP_TEST_SINK 0x270 -# define DP_TEST_SINK_START (1 << 0) -#define DP_TEST_AUDIO_MODE 0x271 -#define DP_TEST_AUDIO_PATTERN_TYPE 0x272 -#define DP_TEST_AUDIO_PERIOD_CH1 0x273 -#define DP_TEST_AUDIO_PERIOD_CH2 0x274 -#define DP_TEST_AUDIO_PERIOD_CH3 0x275 -#define DP_TEST_AUDIO_PERIOD_CH4 0x276 -#define DP_TEST_AUDIO_PERIOD_CH5 0x277 -#define DP_TEST_AUDIO_PERIOD_CH6 0x278 -#define DP_TEST_AUDIO_PERIOD_CH7 0x279 -#define DP_TEST_AUDIO_PERIOD_CH8 0x27A - -#define DP_FEC_STATUS 0x280 /* 1.4 */ -# define DP_FEC_DECODE_EN_DETECTED (1 << 0) -# define DP_FEC_DECODE_DIS_DETECTED (1 << 1) - -#define DP_FEC_ERROR_COUNT_LSB 0x0281 /* 1.4 */ - -#define DP_FEC_ERROR_COUNT_MSB 0x0282 /* 1.4 */ -# define DP_FEC_ERROR_COUNT_MASK 0x7F -# define DP_FEC_ERR_COUNT_VALID (1 << 7) - -#define DP_PAYLOAD_TABLE_UPDATE_STATUS 0x2c0 /* 1.2 MST */ -# define DP_PAYLOAD_TABLE_UPDATED (1 << 0) -# define DP_PAYLOAD_ACT_HANDLED (1 << 1) - -#define DP_VC_PAYLOAD_ID_SLOT_1 0x2c1 /* 1.2 MST */ -/* up to ID_SLOT_63 at 0x2ff */ - -/* Source Device-specific */ -#define DP_SOURCE_OUI 0x300 - -/* Sink Device-specific */ -#define DP_SINK_OUI 0x400 - -/* Branch Device-specific */ -#define DP_BRANCH_OUI 0x500 -#define DP_BRANCH_ID 0x503 -#define DP_BRANCH_REVISION_START 0x509 -#define DP_BRANCH_HW_REV 0x509 -#define DP_BRANCH_SW_REV 0x50A - -/* Link/Sink Device Power Control */ -#define DP_SET_POWER 0x600 -# define DP_SET_POWER_D0 0x1 -# define DP_SET_POWER_D3 0x2 -# define DP_SET_POWER_MASK 0x3 -# define DP_SET_POWER_D3_AUX_ON 0x5 - -/* eDP-specific */ -#define DP_EDP_DPCD_REV 0x700 /* eDP 1.2 */ -# define DP_EDP_11 0x00 -# define DP_EDP_12 0x01 -# define DP_EDP_13 0x02 -# define DP_EDP_14 0x03 -# define DP_EDP_14a 0x04 /* eDP 1.4a */ -# define DP_EDP_14b 0x05 /* eDP 1.4b */ - -#define DP_EDP_GENERAL_CAP_1 0x701 -# define DP_EDP_TCON_BACKLIGHT_ADJUSTMENT_CAP (1 << 0) -# define DP_EDP_BACKLIGHT_PIN_ENABLE_CAP (1 << 1) -# define DP_EDP_BACKLIGHT_AUX_ENABLE_CAP (1 << 2) -# define DP_EDP_PANEL_SELF_TEST_PIN_ENABLE_CAP (1 << 3) -# define DP_EDP_PANEL_SELF_TEST_AUX_ENABLE_CAP (1 << 4) -# define DP_EDP_FRC_ENABLE_CAP (1 << 5) -# define DP_EDP_COLOR_ENGINE_CAP (1 << 6) -# define DP_EDP_SET_POWER_CAP (1 << 7) - -#define DP_EDP_BACKLIGHT_ADJUSTMENT_CAP 0x702 -# define DP_EDP_BACKLIGHT_BRIGHTNESS_PWM_PIN_CAP (1 << 0) -# define DP_EDP_BACKLIGHT_BRIGHTNESS_AUX_SET_CAP (1 << 1) -# define DP_EDP_BACKLIGHT_BRIGHTNESS_BYTE_COUNT (1 << 2) -# define DP_EDP_BACKLIGHT_AUX_PWM_PRODUCT_CAP (1 << 3) -# define DP_EDP_BACKLIGHT_FREQ_PWM_PIN_PASSTHRU_CAP (1 << 4) -# define DP_EDP_BACKLIGHT_FREQ_AUX_SET_CAP (1 << 5) -# define DP_EDP_DYNAMIC_BACKLIGHT_CAP (1 << 6) -# define DP_EDP_VBLANK_BACKLIGHT_UPDATE_CAP (1 << 7) - -#define DP_EDP_GENERAL_CAP_2 0x703 -# define DP_EDP_OVERDRIVE_ENGINE_ENABLED (1 << 0) - -#define DP_EDP_GENERAL_CAP_3 0x704 /* eDP 1.4 */ -# define DP_EDP_X_REGION_CAP_MASK (0xf << 0) -# define DP_EDP_X_REGION_CAP_SHIFT 0 -# define DP_EDP_Y_REGION_CAP_MASK (0xf << 4) -# define DP_EDP_Y_REGION_CAP_SHIFT 4 - -#define DP_EDP_DISPLAY_CONTROL_REGISTER 0x720 -# define DP_EDP_BACKLIGHT_ENABLE (1 << 0) -# define DP_EDP_BLACK_VIDEO_ENABLE (1 << 1) -# define DP_EDP_FRC_ENABLE (1 << 2) -# define DP_EDP_COLOR_ENGINE_ENABLE (1 << 3) -# define DP_EDP_VBLANK_BACKLIGHT_UPDATE_ENABLE (1 << 7) - -#define DP_EDP_BACKLIGHT_MODE_SET_REGISTER 0x721 -# define DP_EDP_BACKLIGHT_CONTROL_MODE_MASK (3 << 0) -# define DP_EDP_BACKLIGHT_CONTROL_MODE_PWM (0 << 0) -# define DP_EDP_BACKLIGHT_CONTROL_MODE_PRESET (1 << 0) -# define DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD (2 << 0) -# define DP_EDP_BACKLIGHT_CONTROL_MODE_PRODUCT (3 << 0) -# define DP_EDP_BACKLIGHT_FREQ_PWM_PIN_PASSTHRU_ENABLE (1 << 2) -# define DP_EDP_BACKLIGHT_FREQ_AUX_SET_ENABLE (1 << 3) -# define DP_EDP_DYNAMIC_BACKLIGHT_ENABLE (1 << 4) -# define DP_EDP_REGIONAL_BACKLIGHT_ENABLE (1 << 5) -# define DP_EDP_UPDATE_REGION_BRIGHTNESS (1 << 6) /* eDP 1.4 */ - -#define DP_EDP_BACKLIGHT_BRIGHTNESS_MSB 0x722 -#define DP_EDP_BACKLIGHT_BRIGHTNESS_LSB 0x723 - -#define DP_EDP_PWMGEN_BIT_COUNT 0x724 -#define DP_EDP_PWMGEN_BIT_COUNT_CAP_MIN 0x725 -#define DP_EDP_PWMGEN_BIT_COUNT_CAP_MAX 0x726 -# define DP_EDP_PWMGEN_BIT_COUNT_MASK (0x1f << 0) - -#define DP_EDP_BACKLIGHT_CONTROL_STATUS 0x727 - -#define DP_EDP_BACKLIGHT_FREQ_SET 0x728 -# define DP_EDP_BACKLIGHT_FREQ_BASE_KHZ 27000 - -#define DP_EDP_BACKLIGHT_FREQ_CAP_MIN_MSB 0x72a -#define DP_EDP_BACKLIGHT_FREQ_CAP_MIN_MID 0x72b -#define DP_EDP_BACKLIGHT_FREQ_CAP_MIN_LSB 0x72c - -#define DP_EDP_BACKLIGHT_FREQ_CAP_MAX_MSB 0x72d -#define DP_EDP_BACKLIGHT_FREQ_CAP_MAX_MID 0x72e -#define DP_EDP_BACKLIGHT_FREQ_CAP_MAX_LSB 0x72f - -#define DP_EDP_DBC_MINIMUM_BRIGHTNESS_SET 0x732 -#define DP_EDP_DBC_MAXIMUM_BRIGHTNESS_SET 0x733 - -#define DP_EDP_REGIONAL_BACKLIGHT_BASE 0x740 /* eDP 1.4 */ -#define DP_EDP_REGIONAL_BACKLIGHT_0 0x741 /* eDP 1.4 */ - -#define DP_EDP_MSO_LINK_CAPABILITIES 0x7a4 /* eDP 1.4 */ -# define DP_EDP_MSO_NUMBER_OF_LINKS_MASK (7 << 0) -# define DP_EDP_MSO_NUMBER_OF_LINKS_SHIFT 0 -# define DP_EDP_MSO_INDEPENDENT_LINK_BIT (1 << 3) - -/* Sideband MSG Buffers */ -#define DP_SIDEBAND_MSG_DOWN_REQ_BASE 0x1000 /* 1.2 MST */ -#define DP_SIDEBAND_MSG_UP_REP_BASE 0x1200 /* 1.2 MST */ -#define DP_SIDEBAND_MSG_DOWN_REP_BASE 0x1400 /* 1.2 MST */ -#define DP_SIDEBAND_MSG_UP_REQ_BASE 0x1600 /* 1.2 MST */ - -/* DPRX Event Status Indicator */ -#define DP_SINK_COUNT_ESI 0x2002 /* same as 0x200 */ -#define DP_DEVICE_SERVICE_IRQ_VECTOR_ESI0 0x2003 /* same as 0x201 */ - -#define DP_DEVICE_SERVICE_IRQ_VECTOR_ESI1 0x2004 /* 1.2 */ -# define DP_RX_GTC_MSTR_REQ_STATUS_CHANGE (1 << 0) -# define DP_LOCK_ACQUISITION_REQUEST (1 << 1) -# define DP_CEC_IRQ (1 << 2) - -#define DP_LINK_SERVICE_IRQ_VECTOR_ESI0 0x2005 /* 1.2 */ -# define RX_CAP_CHANGED (1 << 0) -# define LINK_STATUS_CHANGED (1 << 1) -# define STREAM_STATUS_CHANGED (1 << 2) -# define HDMI_LINK_STATUS_CHANGED (1 << 3) -# define CONNECTED_OFF_ENTRY_REQUESTED (1 << 4) - -#define DP_PSR_ERROR_STATUS 0x2006 /* XXX 1.2? */ -# define DP_PSR_LINK_CRC_ERROR (1 << 0) -# define DP_PSR_RFB_STORAGE_ERROR (1 << 1) -# define DP_PSR_VSC_SDP_UNCORRECTABLE_ERROR (1 << 2) /* eDP 1.4 */ - -#define DP_PSR_ESI 0x2007 /* XXX 1.2? */ -# define DP_PSR_CAPS_CHANGE (1 << 0) - -#define DP_PSR_STATUS 0x2008 /* XXX 1.2? */ -# define DP_PSR_SINK_INACTIVE 0 -# define DP_PSR_SINK_ACTIVE_SRC_SYNCED 1 -# define DP_PSR_SINK_ACTIVE_RFB 2 -# define DP_PSR_SINK_ACTIVE_SINK_SYNCED 3 -# define DP_PSR_SINK_ACTIVE_RESYNC 4 -# define DP_PSR_SINK_INTERNAL_ERROR 7 -# define DP_PSR_SINK_STATE_MASK 0x07 - -#define DP_SYNCHRONIZATION_LATENCY_IN_SINK 0x2009 /* edp 1.4 */ -# define DP_MAX_RESYNC_FRAME_COUNT_MASK (0xf << 0) -# define DP_MAX_RESYNC_FRAME_COUNT_SHIFT 0 -# define DP_LAST_ACTUAL_SYNCHRONIZATION_LATENCY_MASK (0xf << 4) -# define DP_LAST_ACTUAL_SYNCHRONIZATION_LATENCY_SHIFT 4 - -#define DP_LAST_RECEIVED_PSR_SDP 0x200a /* eDP 1.2 */ -# define DP_PSR_STATE_BIT (1 << 0) /* eDP 1.2 */ -# define DP_UPDATE_RFB_BIT (1 << 1) /* eDP 1.2 */ -# define DP_CRC_VALID_BIT (1 << 2) /* eDP 1.2 */ -# define DP_SU_VALID (1 << 3) /* eDP 1.4 */ -# define DP_FIRST_SCAN_LINE_SU_REGION (1 << 4) /* eDP 1.4 */ -# define DP_LAST_SCAN_LINE_SU_REGION (1 << 5) /* eDP 1.4 */ -# define DP_Y_COORDINATE_VALID (1 << 6) /* eDP 1.4a */ - -#define DP_RECEIVER_ALPM_STATUS 0x200b /* eDP 1.4 */ -# define DP_ALPM_LOCK_TIMEOUT_ERROR (1 << 0) - -#define DP_LANE0_1_STATUS_ESI 0x200c /* status same as 0x202 */ -#define DP_LANE2_3_STATUS_ESI 0x200d /* status same as 0x203 */ -#define DP_LANE_ALIGN_STATUS_UPDATED_ESI 0x200e /* status same as 0x204 */ -#define DP_SINK_STATUS_ESI 0x200f /* status same as 0x205 */ - -/* Extended Receiver Capability: See DP_DPCD_REV for definitions */ -#define DP_DP13_DPCD_REV 0x2200 - -#define DP_DPRX_FEATURE_ENUMERATION_LIST 0x2210 /* DP 1.3 */ -# define DP_GTC_CAP (1 << 0) /* DP 1.3 */ -# define DP_SST_SPLIT_SDP_CAP (1 << 1) /* DP 1.4 */ -# define DP_AV_SYNC_CAP (1 << 2) /* DP 1.3 */ -# define DP_VSC_SDP_EXT_FOR_COLORIMETRY_SUPPORTED (1 << 3) /* DP 1.3 */ -# define DP_VSC_EXT_VESA_SDP_SUPPORTED (1 << 4) /* DP 1.4 */ -# define DP_VSC_EXT_VESA_SDP_CHAINING_SUPPORTED (1 << 5) /* DP 1.4 */ -# define DP_VSC_EXT_CEA_SDP_SUPPORTED (1 << 6) /* DP 1.4 */ -# define DP_VSC_EXT_CEA_SDP_CHAINING_SUPPORTED (1 << 7) /* DP 1.4 */ - -#define DP_128B132B_SUPPORTED_LINK_RATES 0x2215 /* 2.0 */ -# define DP_UHBR10 (1 << 0) -# define DP_UHBR20 (1 << 1) -# define DP_UHBR13_5 (1 << 2) - -#define DP_128B132B_TRAINING_AUX_RD_INTERVAL 0x2216 /* 2.0 */ -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_1MS_UNIT (1 << 7) -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_MASK 0x7f -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_400_US 0x00 -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_4_MS 0x01 -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_8_MS 0x02 -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_12_MS 0x03 -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_16_MS 0x04 -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_32_MS 0x05 -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_64_MS 0x06 - -#define DP_TEST_264BIT_CUSTOM_PATTERN_7_0 0x2230 -#define DP_TEST_264BIT_CUSTOM_PATTERN_263_256 0x2250 - -/* DSC Extended Capability Branch Total DSC Resources */ -#define DP_DSC_SUPPORT_AND_DSC_DECODER_COUNT 0x2260 /* 2.0 */ -# define DP_DSC_DECODER_COUNT_MASK (0b111 << 5) -# define DP_DSC_DECODER_COUNT_SHIFT 5 -#define DP_DSC_MAX_SLICE_COUNT_AND_AGGREGATION_0 0x2270 /* 2.0 */ -# define DP_DSC_DECODER_0_MAXIMUM_SLICE_COUNT_MASK (1 << 0) -# define DP_DSC_DECODER_0_AGGREGATION_SUPPORT_MASK (0b111 << 1) -# define DP_DSC_DECODER_0_AGGREGATION_SUPPORT_SHIFT 1 - -/* Protocol Converter Extension */ -/* HDMI CEC tunneling over AUX DP 1.3 section 5.3.3.3.1 DPCD 1.4+ */ -#define DP_CEC_TUNNELING_CAPABILITY 0x3000 -# define DP_CEC_TUNNELING_CAPABLE (1 << 0) -# define DP_CEC_SNOOPING_CAPABLE (1 << 1) -# define DP_CEC_MULTIPLE_LA_CAPABLE (1 << 2) - -#define DP_CEC_TUNNELING_CONTROL 0x3001 -# define DP_CEC_TUNNELING_ENABLE (1 << 0) -# define DP_CEC_SNOOPING_ENABLE (1 << 1) - -#define DP_CEC_RX_MESSAGE_INFO 0x3002 -# define DP_CEC_RX_MESSAGE_LEN_MASK (0xf << 0) -# define DP_CEC_RX_MESSAGE_LEN_SHIFT 0 -# define DP_CEC_RX_MESSAGE_HPD_STATE (1 << 4) -# define DP_CEC_RX_MESSAGE_HPD_LOST (1 << 5) -# define DP_CEC_RX_MESSAGE_ACKED (1 << 6) -# define DP_CEC_RX_MESSAGE_ENDED (1 << 7) - -#define DP_CEC_TX_MESSAGE_INFO 0x3003 -# define DP_CEC_TX_MESSAGE_LEN_MASK (0xf << 0) -# define DP_CEC_TX_MESSAGE_LEN_SHIFT 0 -# define DP_CEC_TX_RETRY_COUNT_MASK (0x7 << 4) -# define DP_CEC_TX_RETRY_COUNT_SHIFT 4 -# define DP_CEC_TX_MESSAGE_SEND (1 << 7) - -#define DP_CEC_TUNNELING_IRQ_FLAGS 0x3004 -# define DP_CEC_RX_MESSAGE_INFO_VALID (1 << 0) -# define DP_CEC_RX_MESSAGE_OVERFLOW (1 << 1) -# define DP_CEC_TX_MESSAGE_SENT (1 << 4) -# define DP_CEC_TX_LINE_ERROR (1 << 5) -# define DP_CEC_TX_ADDRESS_NACK_ERROR (1 << 6) -# define DP_CEC_TX_DATA_NACK_ERROR (1 << 7) - -#define DP_CEC_LOGICAL_ADDRESS_MASK 0x300E /* 0x300F word */ -# define DP_CEC_LOGICAL_ADDRESS_0 (1 << 0) -# define DP_CEC_LOGICAL_ADDRESS_1 (1 << 1) -# define DP_CEC_LOGICAL_ADDRESS_2 (1 << 2) -# define DP_CEC_LOGICAL_ADDRESS_3 (1 << 3) -# define DP_CEC_LOGICAL_ADDRESS_4 (1 << 4) -# define DP_CEC_LOGICAL_ADDRESS_5 (1 << 5) -# define DP_CEC_LOGICAL_ADDRESS_6 (1 << 6) -# define DP_CEC_LOGICAL_ADDRESS_7 (1 << 7) -#define DP_CEC_LOGICAL_ADDRESS_MASK_2 0x300F /* 0x300E word */ -# define DP_CEC_LOGICAL_ADDRESS_8 (1 << 0) -# define DP_CEC_LOGICAL_ADDRESS_9 (1 << 1) -# define DP_CEC_LOGICAL_ADDRESS_10 (1 << 2) -# define DP_CEC_LOGICAL_ADDRESS_11 (1 << 3) -# define DP_CEC_LOGICAL_ADDRESS_12 (1 << 4) -# define DP_CEC_LOGICAL_ADDRESS_13 (1 << 5) -# define DP_CEC_LOGICAL_ADDRESS_14 (1 << 6) -# define DP_CEC_LOGICAL_ADDRESS_15 (1 << 7) - -#define DP_CEC_RX_MESSAGE_BUFFER 0x3010 -#define DP_CEC_TX_MESSAGE_BUFFER 0x3020 -#define DP_CEC_MESSAGE_BUFFER_LENGTH 0x10 - -/* PCON CONFIGURE-1 FRL FOR HDMI SINK */ -#define DP_PCON_HDMI_LINK_CONFIG_1 0x305A -# define DP_PCON_ENABLE_MAX_FRL_BW (7 << 0) -# define DP_PCON_ENABLE_MAX_BW_0GBPS 0 -# define DP_PCON_ENABLE_MAX_BW_9GBPS 1 -# define DP_PCON_ENABLE_MAX_BW_18GBPS 2 -# define DP_PCON_ENABLE_MAX_BW_24GBPS 3 -# define DP_PCON_ENABLE_MAX_BW_32GBPS 4 -# define DP_PCON_ENABLE_MAX_BW_40GBPS 5 -# define DP_PCON_ENABLE_MAX_BW_48GBPS 6 -# define DP_PCON_ENABLE_SOURCE_CTL_MODE (1 << 3) -# define DP_PCON_ENABLE_CONCURRENT_LINK (1 << 4) -# define DP_PCON_ENABLE_SEQUENTIAL_LINK (0 << 4) -# define DP_PCON_ENABLE_LINK_FRL_MODE (1 << 5) -# define DP_PCON_ENABLE_HPD_READY (1 << 6) -# define DP_PCON_ENABLE_HDMI_LINK (1 << 7) - -/* PCON CONFIGURE-2 FRL FOR HDMI SINK */ -#define DP_PCON_HDMI_LINK_CONFIG_2 0x305B -# define DP_PCON_MAX_LINK_BW_MASK (0x3F << 0) -# define DP_PCON_FRL_BW_MASK_9GBPS (1 << 0) -# define DP_PCON_FRL_BW_MASK_18GBPS (1 << 1) -# define DP_PCON_FRL_BW_MASK_24GBPS (1 << 2) -# define DP_PCON_FRL_BW_MASK_32GBPS (1 << 3) -# define DP_PCON_FRL_BW_MASK_40GBPS (1 << 4) -# define DP_PCON_FRL_BW_MASK_48GBPS (1 << 5) -# define DP_PCON_FRL_LINK_TRAIN_EXTENDED (1 << 6) -# define DP_PCON_FRL_LINK_TRAIN_NORMAL (0 << 6) - -/* PCON HDMI LINK STATUS */ -#define DP_PCON_HDMI_TX_LINK_STATUS 0x303B -# define DP_PCON_HDMI_TX_LINK_ACTIVE (1 << 0) -# define DP_PCON_FRL_READY (1 << 1) - -/* PCON HDMI POST FRL STATUS */ -#define DP_PCON_HDMI_POST_FRL_STATUS 0x3036 -# define DP_PCON_HDMI_LINK_MODE (1 << 0) -# define DP_PCON_HDMI_MODE_TMDS 0 -# define DP_PCON_HDMI_MODE_FRL 1 -# define DP_PCON_HDMI_FRL_TRAINED_BW (0x3F << 1) -# define DP_PCON_FRL_TRAINED_BW_9GBPS (1 << 1) -# define DP_PCON_FRL_TRAINED_BW_18GBPS (1 << 2) -# define DP_PCON_FRL_TRAINED_BW_24GBPS (1 << 3) -# define DP_PCON_FRL_TRAINED_BW_32GBPS (1 << 4) -# define DP_PCON_FRL_TRAINED_BW_40GBPS (1 << 5) -# define DP_PCON_FRL_TRAINED_BW_48GBPS (1 << 6) - -#define DP_PROTOCOL_CONVERTER_CONTROL_0 0x3050 /* DP 1.3 */ -# define DP_HDMI_DVI_OUTPUT_CONFIG (1 << 0) /* DP 1.3 */ -#define DP_PROTOCOL_CONVERTER_CONTROL_1 0x3051 /* DP 1.3 */ -# define DP_CONVERSION_TO_YCBCR420_ENABLE (1 << 0) /* DP 1.3 */ -# define DP_HDMI_EDID_PROCESSING_DISABLE (1 << 1) /* DP 1.4 */ -# define DP_HDMI_AUTONOMOUS_SCRAMBLING_DISABLE (1 << 2) /* DP 1.4 */ -# define DP_HDMI_FORCE_SCRAMBLING (1 << 3) /* DP 1.4 */ -#define DP_PROTOCOL_CONVERTER_CONTROL_2 0x3052 /* DP 1.3 */ -# define DP_CONVERSION_TO_YCBCR422_ENABLE (1 << 0) /* DP 1.3 */ -# define DP_PCON_ENABLE_DSC_ENCODER (1 << 1) -# define DP_PCON_ENCODER_PPS_OVERRIDE_MASK (0x3 << 2) -# define DP_PCON_ENC_PPS_OVERRIDE_DISABLED 0 -# define DP_PCON_ENC_PPS_OVERRIDE_EN_PARAMS 1 -# define DP_PCON_ENC_PPS_OVERRIDE_EN_BUFFER 2 -# define DP_CONVERSION_RGB_YCBCR_MASK (7 << 4) -# define DP_CONVERSION_BT601_RGB_YCBCR_ENABLE (1 << 4) -# define DP_CONVERSION_BT709_RGB_YCBCR_ENABLE (1 << 5) -# define DP_CONVERSION_BT2020_RGB_YCBCR_ENABLE (1 << 6) - -/* PCON Downstream HDMI ERROR Status per Lane */ -#define DP_PCON_HDMI_ERROR_STATUS_LN0 0x3037 -#define DP_PCON_HDMI_ERROR_STATUS_LN1 0x3038 -#define DP_PCON_HDMI_ERROR_STATUS_LN2 0x3039 -#define DP_PCON_HDMI_ERROR_STATUS_LN3 0x303A -# define DP_PCON_HDMI_ERROR_COUNT_MASK (0x7 << 0) -# define DP_PCON_HDMI_ERROR_COUNT_THREE_PLUS (1 << 0) -# define DP_PCON_HDMI_ERROR_COUNT_TEN_PLUS (1 << 1) -# define DP_PCON_HDMI_ERROR_COUNT_HUNDRED_PLUS (1 << 2) - -/* PCON HDMI CONFIG PPS Override Buffer - * Valid Offsets to be added to Base : 0-127 - */ -#define DP_PCON_HDMI_PPS_OVERRIDE_BASE 0x3100 - -/* PCON HDMI CONFIG PPS Override Parameter: Slice height - * Offset-0 8LSBs of the Slice height. - * Offset-1 8MSBs of the Slice height. - */ -#define DP_PCON_HDMI_PPS_OVRD_SLICE_HEIGHT 0x3180 - -/* PCON HDMI CONFIG PPS Override Parameter: Slice width - * Offset-0 8LSBs of the Slice width. - * Offset-1 8MSBs of the Slice width. - */ -#define DP_PCON_HDMI_PPS_OVRD_SLICE_WIDTH 0x3182 - -/* PCON HDMI CONFIG PPS Override Parameter: bits_per_pixel - * Offset-0 8LSBs of the bits_per_pixel. - * Offset-1 2MSBs of the bits_per_pixel. - */ -#define DP_PCON_HDMI_PPS_OVRD_BPP 0x3184 - -/* HDCP 1.3 and HDCP 2.2 */ -#define DP_AUX_HDCP_BKSV 0x68000 -#define DP_AUX_HDCP_RI_PRIME 0x68005 -#define DP_AUX_HDCP_AKSV 0x68007 -#define DP_AUX_HDCP_AN 0x6800C -#define DP_AUX_HDCP_V_PRIME(h) (0x68014 + h * 4) -#define DP_AUX_HDCP_BCAPS 0x68028 -# define DP_BCAPS_REPEATER_PRESENT BIT(1) -# define DP_BCAPS_HDCP_CAPABLE BIT(0) -#define DP_AUX_HDCP_BSTATUS 0x68029 -# define DP_BSTATUS_REAUTH_REQ BIT(3) -# define DP_BSTATUS_LINK_FAILURE BIT(2) -# define DP_BSTATUS_R0_PRIME_READY BIT(1) -# define DP_BSTATUS_READY BIT(0) -#define DP_AUX_HDCP_BINFO 0x6802A -#define DP_AUX_HDCP_KSV_FIFO 0x6802C -#define DP_AUX_HDCP_AINFO 0x6803B - -/* DP HDCP2.2 parameter offsets in DPCD address space */ -#define DP_HDCP_2_2_REG_RTX_OFFSET 0x69000 -#define DP_HDCP_2_2_REG_TXCAPS_OFFSET 0x69008 -#define DP_HDCP_2_2_REG_CERT_RX_OFFSET 0x6900B -#define DP_HDCP_2_2_REG_RRX_OFFSET 0x69215 -#define DP_HDCP_2_2_REG_RX_CAPS_OFFSET 0x6921D -#define DP_HDCP_2_2_REG_EKPUB_KM_OFFSET 0x69220 -#define DP_HDCP_2_2_REG_EKH_KM_WR_OFFSET 0x692A0 -#define DP_HDCP_2_2_REG_M_OFFSET 0x692B0 -#define DP_HDCP_2_2_REG_HPRIME_OFFSET 0x692C0 -#define DP_HDCP_2_2_REG_EKH_KM_RD_OFFSET 0x692E0 -#define DP_HDCP_2_2_REG_RN_OFFSET 0x692F0 -#define DP_HDCP_2_2_REG_LPRIME_OFFSET 0x692F8 -#define DP_HDCP_2_2_REG_EDKEY_KS_OFFSET 0x69318 -#define DP_HDCP_2_2_REG_RIV_OFFSET 0x69328 -#define DP_HDCP_2_2_REG_RXINFO_OFFSET 0x69330 -#define DP_HDCP_2_2_REG_SEQ_NUM_V_OFFSET 0x69332 -#define DP_HDCP_2_2_REG_VPRIME_OFFSET 0x69335 -#define DP_HDCP_2_2_REG_RECV_ID_LIST_OFFSET 0x69345 -#define DP_HDCP_2_2_REG_V_OFFSET 0x693E0 -#define DP_HDCP_2_2_REG_SEQ_NUM_M_OFFSET 0x693F0 -#define DP_HDCP_2_2_REG_K_OFFSET 0x693F3 -#define DP_HDCP_2_2_REG_STREAM_ID_TYPE_OFFSET 0x693F5 -#define DP_HDCP_2_2_REG_MPRIME_OFFSET 0x69473 -#define DP_HDCP_2_2_REG_RXSTATUS_OFFSET 0x69493 -#define DP_HDCP_2_2_REG_STREAM_TYPE_OFFSET 0x69494 -#define DP_HDCP_2_2_REG_DBG_OFFSET 0x69518 - -/* LTTPR: Link Training (LT)-tunable PHY Repeaters */ -#define DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV 0xf0000 /* 1.3 */ -#define DP_MAX_LINK_RATE_PHY_REPEATER 0xf0001 /* 1.4a */ -#define DP_PHY_REPEATER_CNT 0xf0002 /* 1.3 */ -#define DP_PHY_REPEATER_MODE 0xf0003 /* 1.3 */ -#define DP_MAX_LANE_COUNT_PHY_REPEATER 0xf0004 /* 1.4a */ -#define DP_Repeater_FEC_CAPABILITY 0xf0004 /* 1.4 */ -#define DP_PHY_REPEATER_EXTENDED_WAIT_TIMEOUT 0xf0005 /* 1.4a */ -#define DP_MAIN_LINK_CHANNEL_CODING_PHY_REPEATER 0xf0006 /* 2.0 */ -# define DP_PHY_REPEATER_128B132B_SUPPORTED (1 << 0) -/* See DP_128B132B_SUPPORTED_LINK_RATES for values */ -#define DP_PHY_REPEATER_128B132B_RATES 0xf0007 /* 2.0 */ -#define DP_PHY_REPEATER_EQ_DONE 0xf0008 /* 2.0 E11 */ - -enum drm_dp_phy { - DP_PHY_DPRX, - - DP_PHY_LTTPR1, - DP_PHY_LTTPR2, - DP_PHY_LTTPR3, - DP_PHY_LTTPR4, - DP_PHY_LTTPR5, - DP_PHY_LTTPR6, - DP_PHY_LTTPR7, - DP_PHY_LTTPR8, - - DP_MAX_LTTPR_COUNT = DP_PHY_LTTPR8, -}; - -#define DP_PHY_LTTPR(i) (DP_PHY_LTTPR1 + (i)) - -#define __DP_LTTPR1_BASE 0xf0010 /* 1.3 */ -#define __DP_LTTPR2_BASE 0xf0060 /* 1.3 */ -#define DP_LTTPR_BASE(dp_phy) \ - (__DP_LTTPR1_BASE + (__DP_LTTPR2_BASE - __DP_LTTPR1_BASE) * \ - ((dp_phy) - DP_PHY_LTTPR1)) - -#define DP_LTTPR_REG(dp_phy, lttpr1_reg) \ - (DP_LTTPR_BASE(dp_phy) - DP_LTTPR_BASE(DP_PHY_LTTPR1) + (lttpr1_reg)) - -#define DP_TRAINING_PATTERN_SET_PHY_REPEATER1 0xf0010 /* 1.3 */ -#define DP_TRAINING_PATTERN_SET_PHY_REPEATER(dp_phy) \ - DP_LTTPR_REG(dp_phy, DP_TRAINING_PATTERN_SET_PHY_REPEATER1) - -#define DP_TRAINING_LANE0_SET_PHY_REPEATER1 0xf0011 /* 1.3 */ -#define DP_TRAINING_LANE0_SET_PHY_REPEATER(dp_phy) \ - DP_LTTPR_REG(dp_phy, DP_TRAINING_LANE0_SET_PHY_REPEATER1) - -#define DP_TRAINING_LANE1_SET_PHY_REPEATER1 0xf0012 /* 1.3 */ -#define DP_TRAINING_LANE2_SET_PHY_REPEATER1 0xf0013 /* 1.3 */ -#define DP_TRAINING_LANE3_SET_PHY_REPEATER1 0xf0014 /* 1.3 */ -#define DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1 0xf0020 /* 1.4a */ -#define DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER(dp_phy) \ - DP_LTTPR_REG(dp_phy, DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1) - -#define DP_TRANSMITTER_CAPABILITY_PHY_REPEATER1 0xf0021 /* 1.4a */ -# define DP_VOLTAGE_SWING_LEVEL_3_SUPPORTED BIT(0) -# define DP_PRE_EMPHASIS_LEVEL_3_SUPPORTED BIT(1) - -#define DP_128B132B_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1 0xf0022 /* 2.0 */ -#define DP_128B132B_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER(dp_phy) \ - DP_LTTPR_REG(dp_phy, DP_128B132B_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1) -/* see DP_128B132B_TRAINING_AUX_RD_INTERVAL for values */ - -#define DP_LANE0_1_STATUS_PHY_REPEATER1 0xf0030 /* 1.3 */ -#define DP_LANE0_1_STATUS_PHY_REPEATER(dp_phy) \ - DP_LTTPR_REG(dp_phy, DP_LANE0_1_STATUS_PHY_REPEATER1) - -#define DP_LANE2_3_STATUS_PHY_REPEATER1 0xf0031 /* 1.3 */ - -#define DP_LANE_ALIGN_STATUS_UPDATED_PHY_REPEATER1 0xf0032 /* 1.3 */ -#define DP_ADJUST_REQUEST_LANE0_1_PHY_REPEATER1 0xf0033 /* 1.3 */ -#define DP_ADJUST_REQUEST_LANE2_3_PHY_REPEATER1 0xf0034 /* 1.3 */ -#define DP_SYMBOL_ERROR_COUNT_LANE0_PHY_REPEATER1 0xf0035 /* 1.3 */ -#define DP_SYMBOL_ERROR_COUNT_LANE1_PHY_REPEATER1 0xf0037 /* 1.3 */ -#define DP_SYMBOL_ERROR_COUNT_LANE2_PHY_REPEATER1 0xf0039 /* 1.3 */ -#define DP_SYMBOL_ERROR_COUNT_LANE3_PHY_REPEATER1 0xf003b /* 1.3 */ - -#define __DP_FEC1_BASE 0xf0290 /* 1.4 */ -#define __DP_FEC2_BASE 0xf0298 /* 1.4 */ -#define DP_FEC_BASE(dp_phy) \ - (__DP_FEC1_BASE + ((__DP_FEC2_BASE - __DP_FEC1_BASE) * \ - ((dp_phy) - DP_PHY_LTTPR1))) - -#define DP_FEC_REG(dp_phy, fec1_reg) \ - (DP_FEC_BASE(dp_phy) - DP_FEC_BASE(DP_PHY_LTTPR1) + fec1_reg) - -#define DP_FEC_STATUS_PHY_REPEATER1 0xf0290 /* 1.4 */ -#define DP_FEC_STATUS_PHY_REPEATER(dp_phy) \ - DP_FEC_REG(dp_phy, DP_FEC_STATUS_PHY_REPEATER1) - -#define DP_FEC_ERROR_COUNT_PHY_REPEATER1 0xf0291 /* 1.4 */ -#define DP_FEC_CAPABILITY_PHY_REPEATER1 0xf0294 /* 1.4a */ - -#define DP_LTTPR_MAX_ADD 0xf02ff /* 1.4 */ - -#define DP_DPCD_MAX_ADD 0xfffff /* 1.4 */ - -/* Repeater modes */ -#define DP_PHY_REPEATER_MODE_TRANSPARENT 0x55 /* 1.3 */ -#define DP_PHY_REPEATER_MODE_NON_TRANSPARENT 0xaa /* 1.3 */ - -/* DP HDCP message start offsets in DPCD address space */ -#define DP_HDCP_2_2_AKE_INIT_OFFSET DP_HDCP_2_2_REG_RTX_OFFSET -#define DP_HDCP_2_2_AKE_SEND_CERT_OFFSET DP_HDCP_2_2_REG_CERT_RX_OFFSET -#define DP_HDCP_2_2_AKE_NO_STORED_KM_OFFSET DP_HDCP_2_2_REG_EKPUB_KM_OFFSET -#define DP_HDCP_2_2_AKE_STORED_KM_OFFSET DP_HDCP_2_2_REG_EKH_KM_WR_OFFSET -#define DP_HDCP_2_2_AKE_SEND_HPRIME_OFFSET DP_HDCP_2_2_REG_HPRIME_OFFSET -#define DP_HDCP_2_2_AKE_SEND_PAIRING_INFO_OFFSET \ - DP_HDCP_2_2_REG_EKH_KM_RD_OFFSET -#define DP_HDCP_2_2_LC_INIT_OFFSET DP_HDCP_2_2_REG_RN_OFFSET -#define DP_HDCP_2_2_LC_SEND_LPRIME_OFFSET DP_HDCP_2_2_REG_LPRIME_OFFSET -#define DP_HDCP_2_2_SKE_SEND_EKS_OFFSET DP_HDCP_2_2_REG_EDKEY_KS_OFFSET -#define DP_HDCP_2_2_REP_SEND_RECVID_LIST_OFFSET DP_HDCP_2_2_REG_RXINFO_OFFSET -#define DP_HDCP_2_2_REP_SEND_ACK_OFFSET DP_HDCP_2_2_REG_V_OFFSET -#define DP_HDCP_2_2_REP_STREAM_MANAGE_OFFSET DP_HDCP_2_2_REG_SEQ_NUM_M_OFFSET -#define DP_HDCP_2_2_REP_STREAM_READY_OFFSET DP_HDCP_2_2_REG_MPRIME_OFFSET - -#define HDCP_2_2_DP_RXSTATUS_LEN 1 -#define HDCP_2_2_DP_RXSTATUS_READY(x) ((x) & BIT(0)) -#define HDCP_2_2_DP_RXSTATUS_H_PRIME(x) ((x) & BIT(1)) -#define HDCP_2_2_DP_RXSTATUS_PAIRING(x) ((x) & BIT(2)) -#define HDCP_2_2_DP_RXSTATUS_REAUTH_REQ(x) ((x) & BIT(3)) -#define HDCP_2_2_DP_RXSTATUS_LINK_FAILED(x) ((x) & BIT(4)) - -/* DP 1.2 Sideband message defines */ -/* peer device type - DP 1.2a Table 2-92 */ -#define DP_PEER_DEVICE_NONE 0x0 -#define DP_PEER_DEVICE_SOURCE_OR_SST 0x1 -#define DP_PEER_DEVICE_MST_BRANCHING 0x2 -#define DP_PEER_DEVICE_SST_SINK 0x3 -#define DP_PEER_DEVICE_DP_LEGACY_CONV 0x4 - -/* DP 1.2 MST sideband request names DP 1.2a Table 2-80 */ -#define DP_GET_MSG_TRANSACTION_VERSION 0x00 /* DP 1.3 */ -#define DP_LINK_ADDRESS 0x01 -#define DP_CONNECTION_STATUS_NOTIFY 0x02 -#define DP_ENUM_PATH_RESOURCES 0x10 -#define DP_ALLOCATE_PAYLOAD 0x11 -#define DP_QUERY_PAYLOAD 0x12 -#define DP_RESOURCE_STATUS_NOTIFY 0x13 -#define DP_CLEAR_PAYLOAD_ID_TABLE 0x14 -#define DP_REMOTE_DPCD_READ 0x20 -#define DP_REMOTE_DPCD_WRITE 0x21 -#define DP_REMOTE_I2C_READ 0x22 -#define DP_REMOTE_I2C_WRITE 0x23 -#define DP_POWER_UP_PHY 0x24 -#define DP_POWER_DOWN_PHY 0x25 -#define DP_SINK_EVENT_NOTIFY 0x30 -#define DP_QUERY_STREAM_ENC_STATUS 0x38 -#define DP_QUERY_STREAM_ENC_STATUS_STATE_NO_EXIST 0 -#define DP_QUERY_STREAM_ENC_STATUS_STATE_INACTIVE 1 -#define DP_QUERY_STREAM_ENC_STATUS_STATE_ACTIVE 2 - -/* DP 1.2 MST sideband reply types */ -#define DP_SIDEBAND_REPLY_ACK 0x00 -#define DP_SIDEBAND_REPLY_NAK 0x01 - -/* DP 1.2 MST sideband nak reasons - table 2.84 */ -#define DP_NAK_WRITE_FAILURE 0x01 -#define DP_NAK_INVALID_READ 0x02 -#define DP_NAK_CRC_FAILURE 0x03 -#define DP_NAK_BAD_PARAM 0x04 -#define DP_NAK_DEFER 0x05 -#define DP_NAK_LINK_FAILURE 0x06 -#define DP_NAK_NO_RESOURCES 0x07 -#define DP_NAK_DPCD_FAIL 0x08 -#define DP_NAK_I2C_NAK 0x09 -#define DP_NAK_ALLOCATE_FAIL 0x0a - -#define MODE_I2C_START 1 -#define MODE_I2C_WRITE 2 -#define MODE_I2C_READ 4 -#define MODE_I2C_STOP 8 - -/* DP 1.2 MST PORTs - Section 2.5.1 v1.2a spec */ -#define DP_MST_PHYSICAL_PORT_0 0 -#define DP_MST_LOGICAL_PORT_0 8 - -#define DP_LINK_CONSTANT_N_VALUE 0x8000 -#define DP_LINK_STATUS_SIZE 6 -bool drm_dp_channel_eq_ok(const u8 link_status[DP_LINK_STATUS_SIZE], - int lane_count); -bool drm_dp_clock_recovery_ok(const u8 link_status[DP_LINK_STATUS_SIZE], - int lane_count); -u8 drm_dp_get_adjust_request_voltage(const u8 link_status[DP_LINK_STATUS_SIZE], - int lane); -u8 drm_dp_get_adjust_request_pre_emphasis(const u8 link_status[DP_LINK_STATUS_SIZE], - int lane); -u8 drm_dp_get_adjust_tx_ffe_preset(const u8 link_status[DP_LINK_STATUS_SIZE], - int lane); - -#define DP_BRANCH_OUI_HEADER_SIZE 0xc -#define DP_RECEIVER_CAP_SIZE 0xf -#define DP_DSC_RECEIVER_CAP_SIZE 0xf -#define EDP_PSR_RECEIVER_CAP_SIZE 2 -#define EDP_DISPLAY_CTL_CAP_SIZE 3 -#define DP_LTTPR_COMMON_CAP_SIZE 8 -#define DP_LTTPR_PHY_CAP_SIZE 3 - -int drm_dp_read_clock_recovery_delay(struct drm_dp_aux *aux, const u8 dpcd[DP_RECEIVER_CAP_SIZE], - enum drm_dp_phy dp_phy, bool uhbr); -int drm_dp_read_channel_eq_delay(struct drm_dp_aux *aux, const u8 dpcd[DP_RECEIVER_CAP_SIZE], - enum drm_dp_phy dp_phy, bool uhbr); - -void drm_dp_link_train_clock_recovery_delay(const struct drm_dp_aux *aux, - const u8 dpcd[DP_RECEIVER_CAP_SIZE]); -void drm_dp_lttpr_link_train_clock_recovery_delay(void); -void drm_dp_link_train_channel_eq_delay(const struct drm_dp_aux *aux, - const u8 dpcd[DP_RECEIVER_CAP_SIZE]); -void drm_dp_lttpr_link_train_channel_eq_delay(const struct drm_dp_aux *aux, - const u8 caps[DP_LTTPR_PHY_CAP_SIZE]); - -int drm_dp_128b132b_read_aux_rd_interval(struct drm_dp_aux *aux); -bool drm_dp_128b132b_lane_channel_eq_done(const u8 link_status[DP_LINK_STATUS_SIZE], - int lane_count); -bool drm_dp_128b132b_lane_symbol_locked(const u8 link_status[DP_LINK_STATUS_SIZE], - int lane_count); -bool drm_dp_128b132b_eq_interlane_align_done(const u8 link_status[DP_LINK_STATUS_SIZE]); -bool drm_dp_128b132b_cds_interlane_align_done(const u8 link_status[DP_LINK_STATUS_SIZE]); -bool drm_dp_128b132b_link_training_failed(const u8 link_status[DP_LINK_STATUS_SIZE]); - -u8 drm_dp_link_rate_to_bw_code(int link_rate); -int drm_dp_bw_code_to_link_rate(u8 link_bw); - -#define DP_SDP_AUDIO_TIMESTAMP 0x01 -#define DP_SDP_AUDIO_STREAM 0x02 -#define DP_SDP_EXTENSION 0x04 /* DP 1.1 */ -#define DP_SDP_AUDIO_COPYMANAGEMENT 0x05 /* DP 1.2 */ -#define DP_SDP_ISRC 0x06 /* DP 1.2 */ -#define DP_SDP_VSC 0x07 /* DP 1.2 */ -#define DP_SDP_CAMERA_GENERIC(i) (0x08 + (i)) /* 0-7, DP 1.3 */ -#define DP_SDP_PPS 0x10 /* DP 1.4 */ -#define DP_SDP_VSC_EXT_VESA 0x20 /* DP 1.4 */ -#define DP_SDP_VSC_EXT_CEA 0x21 /* DP 1.4 */ -/* 0x80+ CEA-861 infoframe types */ - -/** - * struct dp_sdp_header - DP secondary data packet header - * @HB0: Secondary Data Packet ID - * @HB1: Secondary Data Packet Type - * @HB2: Secondary Data Packet Specific header, Byte 0 - * @HB3: Secondary Data packet Specific header, Byte 1 - */ -struct dp_sdp_header { - u8 HB0; - u8 HB1; - u8 HB2; - u8 HB3; -} __packed; - -#define EDP_SDP_HEADER_REVISION_MASK 0x1F -#define EDP_SDP_HEADER_VALID_PAYLOAD_BYTES 0x1F -#define DP_SDP_PPS_HEADER_PAYLOAD_BYTES_MINUS_1 0x7F - -/** - * struct dp_sdp - DP secondary data packet - * @sdp_header: DP secondary data packet header - * @db: DP secondaray data packet data blocks - * VSC SDP Payload for PSR - * db[0]: Stereo Interface - * db[1]: 0 - PSR State; 1 - Update RFB; 2 - CRC Valid - * db[2]: CRC value bits 7:0 of the R or Cr component - * db[3]: CRC value bits 15:8 of the R or Cr component - * db[4]: CRC value bits 7:0 of the G or Y component - * db[5]: CRC value bits 15:8 of the G or Y component - * db[6]: CRC value bits 7:0 of the B or Cb component - * db[7]: CRC value bits 15:8 of the B or Cb component - * db[8] - db[31]: Reserved - * VSC SDP Payload for Pixel Encoding/Colorimetry Format - * db[0] - db[15]: Reserved - * db[16]: Pixel Encoding and Colorimetry Formats - * db[17]: Dynamic Range and Component Bit Depth - * db[18]: Content Type - * db[19] - db[31]: Reserved - */ -struct dp_sdp { - struct dp_sdp_header sdp_header; - u8 db[32]; -} __packed; - -#define EDP_VSC_PSR_STATE_ACTIVE (1<<0) -#define EDP_VSC_PSR_UPDATE_RFB (1<<1) -#define EDP_VSC_PSR_CRC_VALUES_VALID (1<<2) - -/** - * enum dp_pixelformat - drm DP Pixel encoding formats - * - * This enum is used to indicate DP VSC SDP Pixel encoding formats. - * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through - * DB18] - * - * @DP_PIXELFORMAT_RGB: RGB pixel encoding format - * @DP_PIXELFORMAT_YUV444: YCbCr 4:4:4 pixel encoding format - * @DP_PIXELFORMAT_YUV422: YCbCr 4:2:2 pixel encoding format - * @DP_PIXELFORMAT_YUV420: YCbCr 4:2:0 pixel encoding format - * @DP_PIXELFORMAT_Y_ONLY: Y Only pixel encoding format - * @DP_PIXELFORMAT_RAW: RAW pixel encoding format - * @DP_PIXELFORMAT_RESERVED: Reserved pixel encoding format - */ -enum dp_pixelformat { - DP_PIXELFORMAT_RGB = 0, - DP_PIXELFORMAT_YUV444 = 0x1, - DP_PIXELFORMAT_YUV422 = 0x2, - DP_PIXELFORMAT_YUV420 = 0x3, - DP_PIXELFORMAT_Y_ONLY = 0x4, - DP_PIXELFORMAT_RAW = 0x5, - DP_PIXELFORMAT_RESERVED = 0x6, -}; - -/** - * enum dp_colorimetry - drm DP Colorimetry formats - * - * This enum is used to indicate DP VSC SDP Colorimetry formats. - * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through - * DB18] and a name of enum member follows DRM_MODE_COLORIMETRY definition. - * - * @DP_COLORIMETRY_DEFAULT: sRGB (IEC 61966-2-1) or - * ITU-R BT.601 colorimetry format - * @DP_COLORIMETRY_RGB_WIDE_FIXED: RGB wide gamut fixed point colorimetry format - * @DP_COLORIMETRY_BT709_YCC: ITU-R BT.709 colorimetry format - * @DP_COLORIMETRY_RGB_WIDE_FLOAT: RGB wide gamut floating point - * (scRGB (IEC 61966-2-2)) colorimetry format - * @DP_COLORIMETRY_XVYCC_601: xvYCC601 colorimetry format - * @DP_COLORIMETRY_OPRGB: OpRGB colorimetry format - * @DP_COLORIMETRY_XVYCC_709: xvYCC709 colorimetry format - * @DP_COLORIMETRY_DCI_P3_RGB: DCI-P3 (SMPTE RP 431-2) colorimetry format - * @DP_COLORIMETRY_SYCC_601: sYCC601 colorimetry format - * @DP_COLORIMETRY_RGB_CUSTOM: RGB Custom Color Profile colorimetry format - * @DP_COLORIMETRY_OPYCC_601: opYCC601 colorimetry format - * @DP_COLORIMETRY_BT2020_RGB: ITU-R BT.2020 R' G' B' colorimetry format - * @DP_COLORIMETRY_BT2020_CYCC: ITU-R BT.2020 Y'c C'bc C'rc colorimetry format - * @DP_COLORIMETRY_BT2020_YCC: ITU-R BT.2020 Y' C'b C'r colorimetry format - */ -enum dp_colorimetry { - DP_COLORIMETRY_DEFAULT = 0, - DP_COLORIMETRY_RGB_WIDE_FIXED = 0x1, - DP_COLORIMETRY_BT709_YCC = 0x1, - DP_COLORIMETRY_RGB_WIDE_FLOAT = 0x2, - DP_COLORIMETRY_XVYCC_601 = 0x2, - DP_COLORIMETRY_OPRGB = 0x3, - DP_COLORIMETRY_XVYCC_709 = 0x3, - DP_COLORIMETRY_DCI_P3_RGB = 0x4, - DP_COLORIMETRY_SYCC_601 = 0x4, - DP_COLORIMETRY_RGB_CUSTOM = 0x5, - DP_COLORIMETRY_OPYCC_601 = 0x5, - DP_COLORIMETRY_BT2020_RGB = 0x6, - DP_COLORIMETRY_BT2020_CYCC = 0x6, - DP_COLORIMETRY_BT2020_YCC = 0x7, -}; - -/** - * enum dp_dynamic_range - drm DP Dynamic Range - * - * This enum is used to indicate DP VSC SDP Dynamic Range. - * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through - * DB18] - * - * @DP_DYNAMIC_RANGE_VESA: VESA range - * @DP_DYNAMIC_RANGE_CTA: CTA range - */ -enum dp_dynamic_range { - DP_DYNAMIC_RANGE_VESA = 0, - DP_DYNAMIC_RANGE_CTA = 1, -}; - -/** - * enum dp_content_type - drm DP Content Type - * - * This enum is used to indicate DP VSC SDP Content Types. - * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through - * DB18] - * CTA-861-G defines content types and expected processing by a sink device - * - * @DP_CONTENT_TYPE_NOT_DEFINED: Not defined type - * @DP_CONTENT_TYPE_GRAPHICS: Graphics type - * @DP_CONTENT_TYPE_PHOTO: Photo type - * @DP_CONTENT_TYPE_VIDEO: Video type - * @DP_CONTENT_TYPE_GAME: Game type - */ -enum dp_content_type { - DP_CONTENT_TYPE_NOT_DEFINED = 0x00, - DP_CONTENT_TYPE_GRAPHICS = 0x01, - DP_CONTENT_TYPE_PHOTO = 0x02, - DP_CONTENT_TYPE_VIDEO = 0x03, - DP_CONTENT_TYPE_GAME = 0x04, -}; - -/** - * struct drm_dp_vsc_sdp - drm DP VSC SDP - * - * This structure represents a DP VSC SDP of drm - * It is based on DP 1.4 spec [Table 2-116: VSC SDP Header Bytes] and - * [Table 2-117: VSC SDP Payload for DB16 through DB18] - * - * @sdp_type: secondary-data packet type - * @revision: revision number - * @length: number of valid data bytes - * @pixelformat: pixel encoding format - * @colorimetry: colorimetry format - * @bpc: bit per color - * @dynamic_range: dynamic range information - * @content_type: CTA-861-G defines content types and expected processing by a sink device - */ -struct drm_dp_vsc_sdp { - unsigned char sdp_type; - unsigned char revision; - unsigned char length; - enum dp_pixelformat pixelformat; - enum dp_colorimetry colorimetry; - int bpc; - enum dp_dynamic_range dynamic_range; - enum dp_content_type content_type; -}; - -void drm_dp_vsc_sdp_log(const char *level, struct device *dev, - const struct drm_dp_vsc_sdp *vsc); - -int drm_dp_psr_setup_time(const u8 psr_cap[EDP_PSR_RECEIVER_CAP_SIZE]); - -static inline int -drm_dp_max_link_rate(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return drm_dp_bw_code_to_link_rate(dpcd[DP_MAX_LINK_RATE]); -} - -static inline u8 -drm_dp_max_lane_count(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return dpcd[DP_MAX_LANE_COUNT] & DP_MAX_LANE_COUNT_MASK; -} - -static inline bool -drm_dp_enhanced_frame_cap(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return dpcd[DP_DPCD_REV] >= 0x11 && - (dpcd[DP_MAX_LANE_COUNT] & DP_ENHANCED_FRAME_CAP); -} - -static inline bool -drm_dp_fast_training_cap(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return dpcd[DP_DPCD_REV] >= 0x11 && - (dpcd[DP_MAX_DOWNSPREAD] & DP_NO_AUX_HANDSHAKE_LINK_TRAINING); -} - -static inline bool -drm_dp_tps3_supported(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return dpcd[DP_DPCD_REV] >= 0x12 && - dpcd[DP_MAX_LANE_COUNT] & DP_TPS3_SUPPORTED; -} - -static inline bool -drm_dp_max_downspread(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return dpcd[DP_DPCD_REV] >= 0x11 || - dpcd[DP_MAX_DOWNSPREAD] & DP_MAX_DOWNSPREAD_0_5; -} - -static inline bool -drm_dp_tps4_supported(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return dpcd[DP_DPCD_REV] >= 0x14 && - dpcd[DP_MAX_DOWNSPREAD] & DP_TPS4_SUPPORTED; -} - -static inline u8 -drm_dp_training_pattern_mask(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return (dpcd[DP_DPCD_REV] >= 0x14) ? DP_TRAINING_PATTERN_MASK_1_4 : - DP_TRAINING_PATTERN_MASK; -} - -static inline bool -drm_dp_is_branch(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_PRESENT; -} - -/* DP/eDP DSC support */ -u8 drm_dp_dsc_sink_max_slice_count(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE], - bool is_edp); -u8 drm_dp_dsc_sink_line_buf_depth(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]); -int drm_dp_dsc_sink_supported_input_bpcs(const u8 dsc_dpc[DP_DSC_RECEIVER_CAP_SIZE], - u8 dsc_bpc[3]); - -static inline bool -drm_dp_sink_supports_dsc(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]) -{ - return dsc_dpcd[DP_DSC_SUPPORT - DP_DSC_SUPPORT] & - DP_DSC_DECOMPRESSION_IS_SUPPORTED; -} - -static inline u16 -drm_edp_dsc_sink_output_bpp(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]) -{ - return dsc_dpcd[DP_DSC_MAX_BITS_PER_PIXEL_LOW - DP_DSC_SUPPORT] | - (dsc_dpcd[DP_DSC_MAX_BITS_PER_PIXEL_HI - DP_DSC_SUPPORT] & - DP_DSC_MAX_BITS_PER_PIXEL_HI_MASK << - DP_DSC_MAX_BITS_PER_PIXEL_HI_SHIFT); -} - -static inline u32 -drm_dp_dsc_sink_max_slice_width(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]) -{ - /* Max Slicewidth = Number of Pixels * 320 */ - return dsc_dpcd[DP_DSC_MAX_SLICE_WIDTH - DP_DSC_SUPPORT] * - DP_DSC_SLICE_WIDTH_MULTIPLIER; -} - -/* Forward Error Correction Support on DP 1.4 */ -static inline bool -drm_dp_sink_supports_fec(const u8 fec_capable) -{ - return fec_capable & DP_FEC_CAPABLE; -} - -static inline bool -drm_dp_channel_coding_supported(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return dpcd[DP_MAIN_LINK_CHANNEL_CODING] & DP_CAP_ANSI_8B10B; -} - -static inline bool -drm_dp_alternate_scrambler_reset_cap(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return dpcd[DP_EDP_CONFIGURATION_CAP] & - DP_ALTERNATE_SCRAMBLER_RESET_CAP; -} - -/* Ignore MSA timing for Adaptive Sync support on DP 1.4 */ -static inline bool -drm_dp_sink_can_do_video_without_timing_msa(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) -{ - return dpcd[DP_DOWN_STREAM_PORT_COUNT] & - DP_MSA_TIMING_PAR_IGNORED; -} - -/** - * drm_edp_backlight_supported() - Check an eDP DPCD for VESA backlight support - * @edp_dpcd: The DPCD to check - * - * Note that currently this function will return %false for panels which support various DPCD - * backlight features but which require the brightness be set through PWM, and don't support setting - * the brightness level via the DPCD. - * - * Returns: %True if @edp_dpcd indicates that VESA backlight controls are supported, %false - * otherwise - */ -static inline bool -drm_edp_backlight_supported(const u8 edp_dpcd[EDP_DISPLAY_CTL_CAP_SIZE]) -{ - return !!(edp_dpcd[1] & DP_EDP_TCON_BACKLIGHT_ADJUSTMENT_CAP); -} - -/* - * DisplayPort AUX channel - */ - -/** - * struct drm_dp_aux_msg - DisplayPort AUX channel transaction - * @address: address of the (first) register to access - * @request: contains the type of transaction (see DP_AUX_* macros) - * @reply: upon completion, contains the reply type of the transaction - * @buffer: pointer to a transmission or reception buffer - * @size: size of @buffer - */ -struct drm_dp_aux_msg { - unsigned int address; - u8 request; - u8 reply; - void *buffer; - size_t size; -}; - -struct cec_adapter; -struct edid; -struct drm_connector; - -/** - * struct drm_dp_aux_cec - DisplayPort CEC-Tunneling-over-AUX - * @lock: mutex protecting this struct - * @adap: the CEC adapter for CEC-Tunneling-over-AUX support. - * @connector: the connector this CEC adapter is associated with - * @unregister_work: unregister the CEC adapter - */ -struct drm_dp_aux_cec { - struct mutex lock; - struct cec_adapter *adap; - struct drm_connector *connector; - struct delayed_work unregister_work; -}; - -/** - * struct drm_dp_aux - DisplayPort AUX channel - * - * An AUX channel can also be used to transport I2C messages to a sink. A - * typical application of that is to access an EDID that's present in the sink - * device. The @transfer() function can also be used to execute such - * transactions. The drm_dp_aux_register() function registers an I2C adapter - * that can be passed to drm_probe_ddc(). Upon removal, drivers should call - * drm_dp_aux_unregister() to remove the I2C adapter. The I2C adapter uses long - * transfers by default; if a partial response is received, the adapter will - * drop down to the size given by the partial response for this transaction - * only. - */ -struct drm_dp_aux { - /** - * @name: user-visible name of this AUX channel and the - * I2C-over-AUX adapter. - * - * It's also used to specify the name of the I2C adapter. If set - * to %NULL, dev_name() of @dev will be used. - */ - const char *name; - - /** - * @ddc: I2C adapter that can be used for I2C-over-AUX - * communication - */ - struct i2c_adapter ddc; - - /** - * @dev: pointer to struct device that is the parent for this - * AUX channel. - */ - struct device *dev; - - /** - * @drm_dev: pointer to the &drm_device that owns this AUX channel. - * Beware, this may be %NULL before drm_dp_aux_register() has been - * called. - * - * It should be set to the &drm_device that will be using this AUX - * channel as early as possible. For many graphics drivers this should - * happen before drm_dp_aux_init(), however it's perfectly fine to set - * this field later so long as it's assigned before calling - * drm_dp_aux_register(). - */ - struct drm_device *drm_dev; - - /** - * @crtc: backpointer to the crtc that is currently using this - * AUX channel - */ - struct drm_crtc *crtc; - - /** - * @hw_mutex: internal mutex used for locking transfers. - * - * Note that if the underlying hardware is shared among multiple - * channels, the driver needs to do additional locking to - * prevent concurrent access. - */ - struct mutex hw_mutex; - - /** - * @crc_work: worker that captures CRCs for each frame - */ - struct work_struct crc_work; - - /** - * @crc_count: counter of captured frame CRCs - */ - u8 crc_count; - - /** - * @transfer: transfers a message representing a single AUX - * transaction. - * - * This is a hardware-specific implementation of how - * transactions are executed that the drivers must provide. - * - * A pointer to a &drm_dp_aux_msg structure describing the - * transaction is passed into this function. Upon success, the - * implementation should return the number of payload bytes that - * were transferred, or a negative error-code on failure. - * - * Helpers will propagate these errors, with the exception of - * the %-EBUSY error, which causes a transaction to be retried. - * On a short, helpers will return %-EPROTO to make it simpler - * to check for failure. - * - * The @transfer() function must only modify the reply field of - * the &drm_dp_aux_msg structure. The retry logic and i2c - * helpers assume this is the case. - * - * Also note that this callback can be called no matter the - * state @dev is in. Drivers that need that device to be powered - * to perform this operation will first need to make sure it's - * been properly enabled. - */ - ssize_t (*transfer)(struct drm_dp_aux *aux, - struct drm_dp_aux_msg *msg); - - /** - * @i2c_nack_count: Counts I2C NACKs, used for DP validation. - */ - unsigned i2c_nack_count; - /** - * @i2c_defer_count: Counts I2C DEFERs, used for DP validation. - */ - unsigned i2c_defer_count; - /** - * @cec: struct containing fields used for CEC-Tunneling-over-AUX. - */ - struct drm_dp_aux_cec cec; - /** - * @is_remote: Is this AUX CH actually using sideband messaging. - */ - bool is_remote; -}; - -int drm_dp_dpcd_probe(struct drm_dp_aux *aux, unsigned int offset); -ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset, - void *buffer, size_t size); -ssize_t drm_dp_dpcd_write(struct drm_dp_aux *aux, unsigned int offset, - void *buffer, size_t size); - -/** - * drm_dp_dpcd_readb() - read a single byte from the DPCD - * @aux: DisplayPort AUX channel - * @offset: address of the register to read - * @valuep: location where the value of the register will be stored - * - * Returns the number of bytes transferred (1) on success, or a negative - * error code on failure. - */ -static inline ssize_t drm_dp_dpcd_readb(struct drm_dp_aux *aux, - unsigned int offset, u8 *valuep) -{ - return drm_dp_dpcd_read(aux, offset, valuep, 1); -} - -/** - * drm_dp_dpcd_writeb() - write a single byte to the DPCD - * @aux: DisplayPort AUX channel - * @offset: address of the register to write - * @value: value to write to the register - * - * Returns the number of bytes transferred (1) on success, or a negative - * error code on failure. - */ -static inline ssize_t drm_dp_dpcd_writeb(struct drm_dp_aux *aux, - unsigned int offset, u8 value) -{ - return drm_dp_dpcd_write(aux, offset, &value, 1); -} - -int drm_dp_read_dpcd_caps(struct drm_dp_aux *aux, - u8 dpcd[DP_RECEIVER_CAP_SIZE]); - -int drm_dp_dpcd_read_link_status(struct drm_dp_aux *aux, - u8 status[DP_LINK_STATUS_SIZE]); - -int drm_dp_dpcd_read_phy_link_status(struct drm_dp_aux *aux, - enum drm_dp_phy dp_phy, - u8 link_status[DP_LINK_STATUS_SIZE]); - -bool drm_dp_send_real_edid_checksum(struct drm_dp_aux *aux, - u8 real_edid_checksum); - -int drm_dp_read_downstream_info(struct drm_dp_aux *aux, - const u8 dpcd[DP_RECEIVER_CAP_SIZE], - u8 downstream_ports[DP_MAX_DOWNSTREAM_PORTS]); -bool drm_dp_downstream_is_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4], u8 type); -bool drm_dp_downstream_is_tmds(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4], - const struct edid *edid); -int drm_dp_downstream_max_dotclock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4]); -int drm_dp_downstream_max_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4], - const struct edid *edid); -int drm_dp_downstream_min_tmds_clock(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4], - const struct edid *edid); -int drm_dp_downstream_max_bpc(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4], - const struct edid *edid); -bool drm_dp_downstream_420_passthrough(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4]); -bool drm_dp_downstream_444_to_420_conversion(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4]); -struct drm_display_mode *drm_dp_downstream_mode(struct drm_device *dev, - const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4]); -int drm_dp_downstream_id(struct drm_dp_aux *aux, char id[6]); -void drm_dp_downstream_debug(struct seq_file *m, - const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4], - const struct edid *edid, - struct drm_dp_aux *aux); -enum drm_mode_subconnector -drm_dp_subconnector_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4]); -void drm_dp_set_subconnector_property(struct drm_connector *connector, - enum drm_connector_status status, - const u8 *dpcd, - const u8 port_cap[4]); - -struct drm_dp_desc; -bool drm_dp_read_sink_count_cap(struct drm_connector *connector, - const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const struct drm_dp_desc *desc); -int drm_dp_read_sink_count(struct drm_dp_aux *aux); - -int drm_dp_read_lttpr_common_caps(struct drm_dp_aux *aux, - const u8 dpcd[DP_RECEIVER_CAP_SIZE], - u8 caps[DP_LTTPR_COMMON_CAP_SIZE]); -int drm_dp_read_lttpr_phy_caps(struct drm_dp_aux *aux, - const u8 dpcd[DP_RECEIVER_CAP_SIZE], - enum drm_dp_phy dp_phy, - u8 caps[DP_LTTPR_PHY_CAP_SIZE]); -int drm_dp_lttpr_count(const u8 cap[DP_LTTPR_COMMON_CAP_SIZE]); -int drm_dp_lttpr_max_link_rate(const u8 caps[DP_LTTPR_COMMON_CAP_SIZE]); -int drm_dp_lttpr_max_lane_count(const u8 caps[DP_LTTPR_COMMON_CAP_SIZE]); -bool drm_dp_lttpr_voltage_swing_level_3_supported(const u8 caps[DP_LTTPR_PHY_CAP_SIZE]); -bool drm_dp_lttpr_pre_emphasis_level_3_supported(const u8 caps[DP_LTTPR_PHY_CAP_SIZE]); - -void drm_dp_remote_aux_init(struct drm_dp_aux *aux); -void drm_dp_aux_init(struct drm_dp_aux *aux); -int drm_dp_aux_register(struct drm_dp_aux *aux); -void drm_dp_aux_unregister(struct drm_dp_aux *aux); - -int drm_dp_start_crc(struct drm_dp_aux *aux, struct drm_crtc *crtc); -int drm_dp_stop_crc(struct drm_dp_aux *aux); - -struct drm_dp_dpcd_ident { - u8 oui[3]; - u8 device_id[6]; - u8 hw_rev; - u8 sw_major_rev; - u8 sw_minor_rev; -} __packed; - -/** - * struct drm_dp_desc - DP branch/sink device descriptor - * @ident: DP device identification from DPCD 0x400 (sink) or 0x500 (branch). - * @quirks: Quirks; use drm_dp_has_quirk() to query for the quirks. - */ -struct drm_dp_desc { - struct drm_dp_dpcd_ident ident; - u32 quirks; -}; - -int drm_dp_read_desc(struct drm_dp_aux *aux, struct drm_dp_desc *desc, - bool is_branch); - -/** - * enum drm_dp_quirk - Display Port sink/branch device specific quirks - * - * Display Port sink and branch devices in the wild have a variety of bugs, try - * to collect them here. The quirks are shared, but it's up to the drivers to - * implement workarounds for them. - */ -enum drm_dp_quirk { - /** - * @DP_DPCD_QUIRK_CONSTANT_N: - * - * The device requires main link attributes Mvid and Nvid to be limited - * to 16 bits. So will give a constant value (0x8000) for compatability. - */ - DP_DPCD_QUIRK_CONSTANT_N, - /** - * @DP_DPCD_QUIRK_NO_PSR: - * - * The device does not support PSR even if reports that it supports or - * driver still need to implement proper handling for such device. - */ - DP_DPCD_QUIRK_NO_PSR, - /** - * @DP_DPCD_QUIRK_NO_SINK_COUNT: - * - * The device does not set SINK_COUNT to a non-zero value. - * The driver should ignore SINK_COUNT during detection. Note that - * drm_dp_read_sink_count_cap() automatically checks for this quirk. - */ - DP_DPCD_QUIRK_NO_SINK_COUNT, - /** - * @DP_DPCD_QUIRK_DSC_WITHOUT_VIRTUAL_DPCD: - * - * The device supports MST DSC despite not supporting Virtual DPCD. - * The DSC caps can be read from the physical aux instead. - */ - DP_DPCD_QUIRK_DSC_WITHOUT_VIRTUAL_DPCD, - /** - * @DP_DPCD_QUIRK_CAN_DO_MAX_LINK_RATE_3_24_GBPS: - * - * The device supports a link rate of 3.24 Gbps (multiplier 0xc) despite - * the DP_MAX_LINK_RATE register reporting a lower max multiplier. - */ - DP_DPCD_QUIRK_CAN_DO_MAX_LINK_RATE_3_24_GBPS, -}; - -/** - * drm_dp_has_quirk() - does the DP device have a specific quirk - * @desc: Device descriptor filled by drm_dp_read_desc() - * @quirk: Quirk to query for - * - * Return true if DP device identified by @desc has @quirk. - */ -static inline bool -drm_dp_has_quirk(const struct drm_dp_desc *desc, enum drm_dp_quirk quirk) -{ - return desc->quirks & BIT(quirk); -} - -/** - * struct drm_edp_backlight_info - Probed eDP backlight info struct - * @pwmgen_bit_count: The pwmgen bit count - * @pwm_freq_pre_divider: The PWM frequency pre-divider value being used for this backlight, if any - * @max: The maximum backlight level that may be set - * @lsb_reg_used: Do we also write values to the DP_EDP_BACKLIGHT_BRIGHTNESS_LSB register? - * @aux_enable: Does the panel support the AUX enable cap? - * @aux_set: Does the panel support setting the brightness through AUX? - * - * This structure contains various data about an eDP backlight, which can be populated by using - * drm_edp_backlight_init(). - */ -struct drm_edp_backlight_info { - u8 pwmgen_bit_count; - u8 pwm_freq_pre_divider; - u16 max; - - bool lsb_reg_used : 1; - bool aux_enable : 1; - bool aux_set : 1; -}; - -int -drm_edp_backlight_init(struct drm_dp_aux *aux, struct drm_edp_backlight_info *bl, - u16 driver_pwm_freq_hz, const u8 edp_dpcd[EDP_DISPLAY_CTL_CAP_SIZE], - u16 *current_level, u8 *current_mode); -int drm_edp_backlight_set_level(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl, - u16 level); -int drm_edp_backlight_enable(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl, - u16 level); -int drm_edp_backlight_disable(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl); - -#if IS_ENABLED(CONFIG_DRM_KMS_HELPER) && (IS_BUILTIN(CONFIG_BACKLIGHT_CLASS_DEVICE) || \ - (IS_MODULE(CONFIG_DRM_KMS_HELPER) && IS_MODULE(CONFIG_BACKLIGHT_CLASS_DEVICE))) - -int drm_panel_dp_aux_backlight(struct drm_panel *panel, struct drm_dp_aux *aux); - -#else - -static inline int drm_panel_dp_aux_backlight(struct drm_panel *panel, - struct drm_dp_aux *aux) -{ - return 0; -} - -#endif - -#ifdef CONFIG_DRM_DP_CEC -void drm_dp_cec_irq(struct drm_dp_aux *aux); -void drm_dp_cec_register_connector(struct drm_dp_aux *aux, - struct drm_connector *connector); -void drm_dp_cec_unregister_connector(struct drm_dp_aux *aux); -void drm_dp_cec_set_edid(struct drm_dp_aux *aux, const struct edid *edid); -void drm_dp_cec_unset_edid(struct drm_dp_aux *aux); -#else -static inline void drm_dp_cec_irq(struct drm_dp_aux *aux) -{ -} - -static inline void -drm_dp_cec_register_connector(struct drm_dp_aux *aux, - struct drm_connector *connector) -{ -} - -static inline void drm_dp_cec_unregister_connector(struct drm_dp_aux *aux) -{ -} - -static inline void drm_dp_cec_set_edid(struct drm_dp_aux *aux, - const struct edid *edid) -{ -} - -static inline void drm_dp_cec_unset_edid(struct drm_dp_aux *aux) -{ -} - -#endif - -/** - * struct drm_dp_phy_test_params - DP Phy Compliance parameters - * @link_rate: Requested Link rate from DPCD 0x219 - * @num_lanes: Number of lanes requested by sing through DPCD 0x220 - * @phy_pattern: DP Phy test pattern from DPCD 0x248 - * @hbr2_reset: DP HBR2_COMPLIANCE_SCRAMBLER_RESET from DCPD 0x24A and 0x24B - * @custom80: DP Test_80BIT_CUSTOM_PATTERN from DPCDs 0x250 through 0x259 - * @enhanced_frame_cap: flag for enhanced frame capability. - */ -struct drm_dp_phy_test_params { - int link_rate; - u8 num_lanes; - u8 phy_pattern; - u8 hbr2_reset[2]; - u8 custom80[10]; - bool enhanced_frame_cap; -}; - -int drm_dp_get_phy_test_pattern(struct drm_dp_aux *aux, - struct drm_dp_phy_test_params *data); -int drm_dp_set_phy_test_pattern(struct drm_dp_aux *aux, - struct drm_dp_phy_test_params *data, u8 dp_rev); -int drm_dp_get_pcon_max_frl_bw(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4]); -int drm_dp_pcon_frl_prepare(struct drm_dp_aux *aux, bool enable_frl_ready_hpd); -bool drm_dp_pcon_is_frl_ready(struct drm_dp_aux *aux); -int drm_dp_pcon_frl_configure_1(struct drm_dp_aux *aux, int max_frl_gbps, - u8 frl_mode); -int drm_dp_pcon_frl_configure_2(struct drm_dp_aux *aux, int max_frl_mask, - u8 frl_type); -int drm_dp_pcon_reset_frl_config(struct drm_dp_aux *aux); -int drm_dp_pcon_frl_enable(struct drm_dp_aux *aux); - -bool drm_dp_pcon_hdmi_link_active(struct drm_dp_aux *aux); -int drm_dp_pcon_hdmi_link_mode(struct drm_dp_aux *aux, u8 *frl_trained_mask); -void drm_dp_pcon_hdmi_frl_link_error_count(struct drm_dp_aux *aux, - struct drm_connector *connector); -bool drm_dp_pcon_enc_is_dsc_1_2(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]); -int drm_dp_pcon_dsc_max_slices(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]); -int drm_dp_pcon_dsc_max_slice_width(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]); -int drm_dp_pcon_dsc_bpp_incr(const u8 pcon_dsc_dpcd[DP_PCON_DSC_ENCODER_CAP_SIZE]); -int drm_dp_pcon_pps_default(struct drm_dp_aux *aux); -int drm_dp_pcon_pps_override_buf(struct drm_dp_aux *aux, u8 pps_buf[128]); -int drm_dp_pcon_pps_override_param(struct drm_dp_aux *aux, u8 pps_param[6]); -bool drm_dp_downstream_rgb_to_ycbcr_conversion(const u8 dpcd[DP_RECEIVER_CAP_SIZE], - const u8 port_cap[4], u8 color_spc); -int drm_dp_pcon_convert_rgb_to_ycbcr(struct drm_dp_aux *aux, u8 color_spc); - -#endif /* _DRM_DP_HELPER_H_ */ diff --git a/include/drm/dp/drm_dp_mst_helper.h b/include/drm/dp/drm_dp_mst_helper.h deleted file mode 100644 index 08276eb8c187..000000000000 --- a/include/drm/dp/drm_dp_mst_helper.h +++ /dev/null @@ -1,972 +0,0 @@ -/* - * Copyright © 2014 Red Hat. - * - * Permission to use, copy, modify, distribute, and sell this software and its - * documentation for any purpose is hereby granted without fee, provided that - * the above copyright notice appear in all copies and that both that copyright - * notice and this permission notice appear in supporting documentation, and - * that the name of the copyright holders not be used in advertising or - * publicity pertaining to distribution of the software without specific, - * written prior permission. The copyright holders make no representations - * about the suitability of this software for any purpose. It is provided "as - * is" without express or implied warranty. - * - * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, - * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO - * EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT OR - * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, - * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER - * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE - * OF THIS SOFTWARE. - */ -#ifndef _DRM_DP_MST_HELPER_H_ -#define _DRM_DP_MST_HELPER_H_ - -#include -#include -#include - -#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) -#include -#include - -enum drm_dp_mst_topology_ref_type { - DRM_DP_MST_TOPOLOGY_REF_GET, - DRM_DP_MST_TOPOLOGY_REF_PUT, -}; - -struct drm_dp_mst_topology_ref_history { - struct drm_dp_mst_topology_ref_entry { - enum drm_dp_mst_topology_ref_type type; - int count; - ktime_t ts_nsec; - depot_stack_handle_t backtrace; - } *entries; - int len; -}; -#endif /* IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) */ - -struct drm_dp_mst_branch; - -/** - * struct drm_dp_vcpi - Virtual Channel Payload Identifier - * @vcpi: Virtual channel ID. - * @pbn: Payload Bandwidth Number for this channel - * @aligned_pbn: PBN aligned with slot size - * @num_slots: number of slots for this PBN - */ -struct drm_dp_vcpi { - int vcpi; - int pbn; - int aligned_pbn; - int num_slots; -}; - -/** - * struct drm_dp_mst_port - MST port - * @port_num: port number - * @input: if this port is an input port. Protected by - * &drm_dp_mst_topology_mgr.base.lock. - * @mcs: message capability status - DP 1.2 spec. Protected by - * &drm_dp_mst_topology_mgr.base.lock. - * @ddps: DisplayPort Device Plug Status - DP 1.2. Protected by - * &drm_dp_mst_topology_mgr.base.lock. - * @pdt: Peer Device Type. Protected by - * &drm_dp_mst_topology_mgr.base.lock. - * @ldps: Legacy Device Plug Status. Protected by - * &drm_dp_mst_topology_mgr.base.lock. - * @dpcd_rev: DPCD revision of device on this port. Protected by - * &drm_dp_mst_topology_mgr.base.lock. - * @num_sdp_streams: Number of simultaneous streams. Protected by - * &drm_dp_mst_topology_mgr.base.lock. - * @num_sdp_stream_sinks: Number of stream sinks. Protected by - * &drm_dp_mst_topology_mgr.base.lock. - * @full_pbn: Max possible bandwidth for this port. Protected by - * &drm_dp_mst_topology_mgr.base.lock. - * @next: link to next port on this branch device - * @aux: i2c aux transport to talk to device connected to this port, protected - * by &drm_dp_mst_topology_mgr.base.lock. - * @parent: branch device parent of this port - * @vcpi: Virtual Channel Payload info for this port. - * @connector: DRM connector this port is connected to. Protected by - * &drm_dp_mst_topology_mgr.base.lock. - * @mgr: topology manager this port lives under. - * - * This structure represents an MST port endpoint on a device somewhere - * in the MST topology. - */ -struct drm_dp_mst_port { - /** - * @topology_kref: refcount for this port's lifetime in the topology, - * only the DP MST helpers should need to touch this - */ - struct kref topology_kref; - - /** - * @malloc_kref: refcount for the memory allocation containing this - * structure. See drm_dp_mst_get_port_malloc() and - * drm_dp_mst_put_port_malloc(). - */ - struct kref malloc_kref; - -#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) - /** - * @topology_ref_history: A history of each topology - * reference/dereference. See CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS. - */ - struct drm_dp_mst_topology_ref_history topology_ref_history; -#endif - - u8 port_num; - bool input; - bool mcs; - bool ddps; - u8 pdt; - bool ldps; - u8 dpcd_rev; - u8 num_sdp_streams; - u8 num_sdp_stream_sinks; - uint16_t full_pbn; - struct list_head next; - /** - * @mstb: the branch device connected to this port, if there is one. - * This should be considered protected for reading by - * &drm_dp_mst_topology_mgr.lock. There are two exceptions to this: - * &drm_dp_mst_topology_mgr.up_req_work and - * &drm_dp_mst_topology_mgr.work, which do not grab - * &drm_dp_mst_topology_mgr.lock during reads but are the only - * updaters of this list and are protected from writing concurrently - * by &drm_dp_mst_topology_mgr.probe_lock. - */ - struct drm_dp_mst_branch *mstb; - struct drm_dp_aux aux; /* i2c bus for this port? */ - struct drm_dp_mst_branch *parent; - - struct drm_dp_vcpi vcpi; - struct drm_connector *connector; - struct drm_dp_mst_topology_mgr *mgr; - - /** - * @cached_edid: for DP logical ports - make tiling work by ensuring - * that the EDID for all connectors is read immediately. - */ - struct edid *cached_edid; - /** - * @has_audio: Tracks whether the sink connector to this port is - * audio-capable. - */ - bool has_audio; - - /** - * @fec_capable: bool indicating if FEC can be supported up to that - * point in the MST topology. - */ - bool fec_capable; -}; - -/* sideband msg header - not bit struct */ -struct drm_dp_sideband_msg_hdr { - u8 lct; - u8 lcr; - u8 rad[8]; - bool broadcast; - bool path_msg; - u8 msg_len; - bool somt; - bool eomt; - bool seqno; -}; - -struct drm_dp_sideband_msg_rx { - u8 chunk[48]; - u8 msg[256]; - u8 curchunk_len; - u8 curchunk_idx; /* chunk we are parsing now */ - u8 curchunk_hdrlen; - u8 curlen; /* total length of the msg */ - bool have_somt; - bool have_eomt; - struct drm_dp_sideband_msg_hdr initial_hdr; -}; - -/** - * struct drm_dp_mst_branch - MST branch device. - * @rad: Relative Address to talk to this branch device. - * @lct: Link count total to talk to this branch device. - * @num_ports: number of ports on the branch. - * @port_parent: pointer to the port parent, NULL if toplevel. - * @mgr: topology manager for this branch device. - * @link_address_sent: if a link address message has been sent to this device yet. - * @guid: guid for DP 1.2 branch device. port under this branch can be - * identified by port #. - * - * This structure represents an MST branch device, there is one - * primary branch device at the root, along with any other branches connected - * to downstream port of parent branches. - */ -struct drm_dp_mst_branch { - /** - * @topology_kref: refcount for this branch device's lifetime in the - * topology, only the DP MST helpers should need to touch this - */ - struct kref topology_kref; - - /** - * @malloc_kref: refcount for the memory allocation containing this - * structure. See drm_dp_mst_get_mstb_malloc() and - * drm_dp_mst_put_mstb_malloc(). - */ - struct kref malloc_kref; - -#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) - /** - * @topology_ref_history: A history of each topology - * reference/dereference. See CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS. - */ - struct drm_dp_mst_topology_ref_history topology_ref_history; -#endif - - /** - * @destroy_next: linked-list entry used by - * drm_dp_delayed_destroy_work() - */ - struct list_head destroy_next; - - u8 rad[8]; - u8 lct; - int num_ports; - - /** - * @ports: the list of ports on this branch device. This should be - * considered protected for reading by &drm_dp_mst_topology_mgr.lock. - * There are two exceptions to this: - * &drm_dp_mst_topology_mgr.up_req_work and - * &drm_dp_mst_topology_mgr.work, which do not grab - * &drm_dp_mst_topology_mgr.lock during reads but are the only - * updaters of this list and are protected from updating the list - * concurrently by @drm_dp_mst_topology_mgr.probe_lock - */ - struct list_head ports; - - struct drm_dp_mst_port *port_parent; - struct drm_dp_mst_topology_mgr *mgr; - - bool link_address_sent; - - /* global unique identifier to identify branch devices */ - u8 guid[16]; -}; - - -struct drm_dp_nak_reply { - u8 guid[16]; - u8 reason; - u8 nak_data; -}; - -struct drm_dp_link_address_ack_reply { - u8 guid[16]; - u8 nports; - struct drm_dp_link_addr_reply_port { - bool input_port; - u8 peer_device_type; - u8 port_number; - bool mcs; - bool ddps; - bool legacy_device_plug_status; - u8 dpcd_revision; - u8 peer_guid[16]; - u8 num_sdp_streams; - u8 num_sdp_stream_sinks; - } ports[16]; -}; - -struct drm_dp_remote_dpcd_read_ack_reply { - u8 port_number; - u8 num_bytes; - u8 bytes[255]; -}; - -struct drm_dp_remote_dpcd_write_ack_reply { - u8 port_number; -}; - -struct drm_dp_remote_dpcd_write_nak_reply { - u8 port_number; - u8 reason; - u8 bytes_written_before_failure; -}; - -struct drm_dp_remote_i2c_read_ack_reply { - u8 port_number; - u8 num_bytes; - u8 bytes[255]; -}; - -struct drm_dp_remote_i2c_read_nak_reply { - u8 port_number; - u8 nak_reason; - u8 i2c_nak_transaction; -}; - -struct drm_dp_remote_i2c_write_ack_reply { - u8 port_number; -}; - -struct drm_dp_query_stream_enc_status_ack_reply { - /* Bit[23:16]- Stream Id */ - u8 stream_id; - - /* Bit[15]- Signed */ - bool reply_signed; - - /* Bit[10:8]- Stream Output Sink Type */ - bool unauthorizable_device_present; - bool legacy_device_present; - bool query_capable_device_present; - - /* Bit[12:11]- Stream Output CP Type */ - bool hdcp_1x_device_present; - bool hdcp_2x_device_present; - - /* Bit[4]- Stream Authentication */ - bool auth_completed; - - /* Bit[3]- Stream Encryption */ - bool encryption_enabled; - - /* Bit[2]- Stream Repeater Function Present */ - bool repeater_present; - - /* Bit[1:0]- Stream State */ - u8 state; -}; - -#define DRM_DP_MAX_SDP_STREAMS 16 -struct drm_dp_allocate_payload { - u8 port_number; - u8 number_sdp_streams; - u8 vcpi; - u16 pbn; - u8 sdp_stream_sink[DRM_DP_MAX_SDP_STREAMS]; -}; - -struct drm_dp_allocate_payload_ack_reply { - u8 port_number; - u8 vcpi; - u16 allocated_pbn; -}; - -struct drm_dp_connection_status_notify { - u8 guid[16]; - u8 port_number; - bool legacy_device_plug_status; - bool displayport_device_plug_status; - bool message_capability_status; - bool input_port; - u8 peer_device_type; -}; - -struct drm_dp_remote_dpcd_read { - u8 port_number; - u32 dpcd_address; - u8 num_bytes; -}; - -struct drm_dp_remote_dpcd_write { - u8 port_number; - u32 dpcd_address; - u8 num_bytes; - u8 *bytes; -}; - -#define DP_REMOTE_I2C_READ_MAX_TRANSACTIONS 4 -struct drm_dp_remote_i2c_read { - u8 num_transactions; - u8 port_number; - struct drm_dp_remote_i2c_read_tx { - u8 i2c_dev_id; - u8 num_bytes; - u8 *bytes; - u8 no_stop_bit; - u8 i2c_transaction_delay; - } transactions[DP_REMOTE_I2C_READ_MAX_TRANSACTIONS]; - u8 read_i2c_device_id; - u8 num_bytes_read; -}; - -struct drm_dp_remote_i2c_write { - u8 port_number; - u8 write_i2c_device_id; - u8 num_bytes; - u8 *bytes; -}; - -struct drm_dp_query_stream_enc_status { - u8 stream_id; - u8 client_id[7]; /* 56-bit nonce */ - u8 stream_event; - bool valid_stream_event; - u8 stream_behavior; - u8 valid_stream_behavior; -}; - -/* this covers ENUM_RESOURCES, POWER_DOWN_PHY, POWER_UP_PHY */ -struct drm_dp_port_number_req { - u8 port_number; -}; - -struct drm_dp_enum_path_resources_ack_reply { - u8 port_number; - bool fec_capable; - u16 full_payload_bw_number; - u16 avail_payload_bw_number; -}; - -/* covers POWER_DOWN_PHY, POWER_UP_PHY */ -struct drm_dp_port_number_rep { - u8 port_number; -}; - -struct drm_dp_query_payload { - u8 port_number; - u8 vcpi; -}; - -struct drm_dp_resource_status_notify { - u8 port_number; - u8 guid[16]; - u16 available_pbn; -}; - -struct drm_dp_query_payload_ack_reply { - u8 port_number; - u16 allocated_pbn; -}; - -struct drm_dp_sideband_msg_req_body { - u8 req_type; - union ack_req { - struct drm_dp_connection_status_notify conn_stat; - struct drm_dp_port_number_req port_num; - struct drm_dp_resource_status_notify resource_stat; - - struct drm_dp_query_payload query_payload; - struct drm_dp_allocate_payload allocate_payload; - - struct drm_dp_remote_dpcd_read dpcd_read; - struct drm_dp_remote_dpcd_write dpcd_write; - - struct drm_dp_remote_i2c_read i2c_read; - struct drm_dp_remote_i2c_write i2c_write; - - struct drm_dp_query_stream_enc_status enc_status; - } u; -}; - -struct drm_dp_sideband_msg_reply_body { - u8 reply_type; - u8 req_type; - union ack_replies { - struct drm_dp_nak_reply nak; - struct drm_dp_link_address_ack_reply link_addr; - struct drm_dp_port_number_rep port_number; - - struct drm_dp_enum_path_resources_ack_reply path_resources; - struct drm_dp_allocate_payload_ack_reply allocate_payload; - struct drm_dp_query_payload_ack_reply query_payload; - - struct drm_dp_remote_dpcd_read_ack_reply remote_dpcd_read_ack; - struct drm_dp_remote_dpcd_write_ack_reply remote_dpcd_write_ack; - struct drm_dp_remote_dpcd_write_nak_reply remote_dpcd_write_nack; - - struct drm_dp_remote_i2c_read_ack_reply remote_i2c_read_ack; - struct drm_dp_remote_i2c_read_nak_reply remote_i2c_read_nack; - struct drm_dp_remote_i2c_write_ack_reply remote_i2c_write_ack; - - struct drm_dp_query_stream_enc_status_ack_reply enc_status; - } u; -}; - -/* msg is queued to be put into a slot */ -#define DRM_DP_SIDEBAND_TX_QUEUED 0 -/* msg has started transmitting on a slot - still on msgq */ -#define DRM_DP_SIDEBAND_TX_START_SEND 1 -/* msg has finished transmitting on a slot - removed from msgq only in slot */ -#define DRM_DP_SIDEBAND_TX_SENT 2 -/* msg has received a response - removed from slot */ -#define DRM_DP_SIDEBAND_TX_RX 3 -#define DRM_DP_SIDEBAND_TX_TIMEOUT 4 - -struct drm_dp_sideband_msg_tx { - u8 msg[256]; - u8 chunk[48]; - u8 cur_offset; - u8 cur_len; - struct drm_dp_mst_branch *dst; - struct list_head next; - int seqno; - int state; - bool path_msg; - struct drm_dp_sideband_msg_reply_body reply; -}; - -/* sideband msg handler */ -struct drm_dp_mst_topology_mgr; -struct drm_dp_mst_topology_cbs { - /* create a connector for a port */ - struct drm_connector *(*add_connector)(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port, const char *path); - /* - * Checks for any pending MST interrupts, passing them to MST core for - * processing, the same way an HPD IRQ pulse handler would do this. - * If provided MST core calls this callback from a poll-waiting loop - * when waiting for MST down message replies. The driver is expected - * to guard against a race between this callback and the driver's HPD - * IRQ pulse handler. - */ - void (*poll_hpd_irq)(struct drm_dp_mst_topology_mgr *mgr); -}; - -#define DP_MAX_PAYLOAD (sizeof(unsigned long) * 8) - -#define DP_PAYLOAD_LOCAL 1 -#define DP_PAYLOAD_REMOTE 2 -#define DP_PAYLOAD_DELETE_LOCAL 3 - -struct drm_dp_payload { - int payload_state; - int start_slot; - int num_slots; - int vcpi; -}; - -#define to_dp_mst_topology_state(x) container_of(x, struct drm_dp_mst_topology_state, base) - -struct drm_dp_vcpi_allocation { - struct drm_dp_mst_port *port; - int vcpi; - int pbn; - bool dsc_enabled; - struct list_head next; -}; - -struct drm_dp_mst_topology_state { - struct drm_private_state base; - struct list_head vcpis; - struct drm_dp_mst_topology_mgr *mgr; - u8 total_avail_slots; - u8 start_slot; -}; - -#define to_dp_mst_topology_mgr(x) container_of(x, struct drm_dp_mst_topology_mgr, base) - -/** - * struct drm_dp_mst_topology_mgr - DisplayPort MST manager - * - * This struct represents the toplevel displayport MST topology manager. - * There should be one instance of this for every MST capable DP connector - * on the GPU. - */ -struct drm_dp_mst_topology_mgr { - /** - * @base: Base private object for atomic - */ - struct drm_private_obj base; - - /** - * @dev: device pointer for adding i2c devices etc. - */ - struct drm_device *dev; - /** - * @cbs: callbacks for connector addition and destruction. - */ - const struct drm_dp_mst_topology_cbs *cbs; - /** - * @max_dpcd_transaction_bytes: maximum number of bytes to read/write - * in one go. - */ - int max_dpcd_transaction_bytes; - /** - * @aux: AUX channel for the DP MST connector this topolgy mgr is - * controlling. - */ - struct drm_dp_aux *aux; - /** - * @max_payloads: maximum number of payloads the GPU can generate. - */ - int max_payloads; - /** - * @max_lane_count: maximum number of lanes the GPU can drive. - */ - int max_lane_count; - /** - * @max_link_rate: maximum link rate per lane GPU can output, in kHz. - */ - int max_link_rate; - /** - * @conn_base_id: DRM connector ID this mgr is connected to. Only used - * to build the MST connector path value. - */ - int conn_base_id; - - /** - * @up_req_recv: Message receiver state for up requests. - */ - struct drm_dp_sideband_msg_rx up_req_recv; - - /** - * @down_rep_recv: Message receiver state for replies to down - * requests. - */ - struct drm_dp_sideband_msg_rx down_rep_recv; - - /** - * @lock: protects @mst_state, @mst_primary, @dpcd, and - * @payload_id_table_cleared. - */ - struct mutex lock; - - /** - * @probe_lock: Prevents @work and @up_req_work, the only writers of - * &drm_dp_mst_port.mstb and &drm_dp_mst_branch.ports, from racing - * while they update the topology. - */ - struct mutex probe_lock; - - /** - * @mst_state: If this manager is enabled for an MST capable port. False - * if no MST sink/branch devices is connected. - */ - bool mst_state : 1; - - /** - * @payload_id_table_cleared: Whether or not we've cleared the payload - * ID table for @mst_primary. Protected by @lock. - */ - bool payload_id_table_cleared : 1; - - /** - * @mst_primary: Pointer to the primary/first branch device. - */ - struct drm_dp_mst_branch *mst_primary; - - /** - * @dpcd: Cache of DPCD for primary port. - */ - u8 dpcd[DP_RECEIVER_CAP_SIZE]; - /** - * @sink_count: Sink count from DEVICE_SERVICE_IRQ_VECTOR_ESI0. - */ - u8 sink_count; - /** - * @pbn_div: PBN to slots divisor. - */ - int pbn_div; - - /** - * @funcs: Atomic helper callbacks - */ - const struct drm_private_state_funcs *funcs; - - /** - * @qlock: protects @tx_msg_downq and &drm_dp_sideband_msg_tx.state - */ - struct mutex qlock; - - /** - * @tx_msg_downq: List of pending down requests - */ - struct list_head tx_msg_downq; - - /** - * @payload_lock: Protect payload information. - */ - struct mutex payload_lock; - /** - * @proposed_vcpis: Array of pointers for the new VCPI allocation. The - * VCPI structure itself is &drm_dp_mst_port.vcpi, and the size of - * this array is determined by @max_payloads. - */ - struct drm_dp_vcpi **proposed_vcpis; - /** - * @payloads: Array of payloads. The size of this array is determined - * by @max_payloads. - */ - struct drm_dp_payload *payloads; - /** - * @payload_mask: Elements of @payloads actually in use. Since - * reallocation of active outputs isn't possible gaps can be created by - * disabling outputs out of order compared to how they've been enabled. - */ - unsigned long payload_mask; - /** - * @vcpi_mask: Similar to @payload_mask, but for @proposed_vcpis. - */ - unsigned long vcpi_mask; - - /** - * @tx_waitq: Wait to queue stall for the tx worker. - */ - wait_queue_head_t tx_waitq; - /** - * @work: Probe work. - */ - struct work_struct work; - /** - * @tx_work: Sideband transmit worker. This can nest within the main - * @work worker for each transaction @work launches. - */ - struct work_struct tx_work; - - /** - * @destroy_port_list: List of to be destroyed connectors. - */ - struct list_head destroy_port_list; - /** - * @destroy_branch_device_list: List of to be destroyed branch - * devices. - */ - struct list_head destroy_branch_device_list; - /** - * @delayed_destroy_lock: Protects @destroy_port_list and - * @destroy_branch_device_list. - */ - struct mutex delayed_destroy_lock; - - /** - * @delayed_destroy_wq: Workqueue used for delayed_destroy_work items. - * A dedicated WQ makes it possible to drain any requeued work items - * on it. - */ - struct workqueue_struct *delayed_destroy_wq; - - /** - * @delayed_destroy_work: Work item to destroy MST port and branch - * devices, needed to avoid locking inversion. - */ - struct work_struct delayed_destroy_work; - - /** - * @up_req_list: List of pending up requests from the topology that - * need to be processed, in chronological order. - */ - struct list_head up_req_list; - /** - * @up_req_lock: Protects @up_req_list - */ - struct mutex up_req_lock; - /** - * @up_req_work: Work item to process up requests received from the - * topology. Needed to avoid blocking hotplug handling and sideband - * transmissions. - */ - struct work_struct up_req_work; - -#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) - /** - * @topology_ref_history_lock: protects - * &drm_dp_mst_port.topology_ref_history and - * &drm_dp_mst_branch.topology_ref_history. - */ - struct mutex topology_ref_history_lock; -#endif -}; - -int drm_dp_mst_topology_mgr_init(struct drm_dp_mst_topology_mgr *mgr, - struct drm_device *dev, struct drm_dp_aux *aux, - int max_dpcd_transaction_bytes, - int max_payloads, - int max_lane_count, int max_link_rate, - int conn_base_id); - -void drm_dp_mst_topology_mgr_destroy(struct drm_dp_mst_topology_mgr *mgr); - -bool drm_dp_read_mst_cap(struct drm_dp_aux *aux, const u8 dpcd[DP_RECEIVER_CAP_SIZE]); -int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool mst_state); - -int drm_dp_mst_hpd_irq(struct drm_dp_mst_topology_mgr *mgr, u8 *esi, bool *handled); - - -int -drm_dp_mst_detect_port(struct drm_connector *connector, - struct drm_modeset_acquire_ctx *ctx, - struct drm_dp_mst_topology_mgr *mgr, - struct drm_dp_mst_port *port); - -struct edid *drm_dp_mst_get_edid(struct drm_connector *connector, struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port); - -int drm_dp_get_vc_payload_bw(const struct drm_dp_mst_topology_mgr *mgr, - int link_rate, int link_lane_count); - -int drm_dp_calc_pbn_mode(int clock, int bpp, bool dsc); - -bool drm_dp_mst_allocate_vcpi(struct drm_dp_mst_topology_mgr *mgr, - struct drm_dp_mst_port *port, int pbn, int slots); - -int drm_dp_mst_get_vcpi_slots(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port); - - -void drm_dp_mst_reset_vcpi_slots(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port); - -void drm_dp_mst_update_slots(struct drm_dp_mst_topology_state *mst_state, uint8_t link_encoding_cap); - -void drm_dp_mst_deallocate_vcpi(struct drm_dp_mst_topology_mgr *mgr, - struct drm_dp_mst_port *port); - - -int drm_dp_find_vcpi_slots(struct drm_dp_mst_topology_mgr *mgr, - int pbn); - - -int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr, int start_slot); - - -int drm_dp_update_payload_part2(struct drm_dp_mst_topology_mgr *mgr); - -int drm_dp_check_act_status(struct drm_dp_mst_topology_mgr *mgr); - -void drm_dp_mst_dump_topology(struct seq_file *m, - struct drm_dp_mst_topology_mgr *mgr); - -void drm_dp_mst_topology_mgr_suspend(struct drm_dp_mst_topology_mgr *mgr); -int __must_check -drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr, - bool sync); - -ssize_t drm_dp_mst_dpcd_read(struct drm_dp_aux *aux, - unsigned int offset, void *buffer, size_t size); -ssize_t drm_dp_mst_dpcd_write(struct drm_dp_aux *aux, - unsigned int offset, void *buffer, size_t size); - -int drm_dp_mst_connector_late_register(struct drm_connector *connector, - struct drm_dp_mst_port *port); -void drm_dp_mst_connector_early_unregister(struct drm_connector *connector, - struct drm_dp_mst_port *port); - -struct drm_dp_mst_topology_state *drm_atomic_get_mst_topology_state(struct drm_atomic_state *state, - struct drm_dp_mst_topology_mgr *mgr); -int __must_check -drm_dp_atomic_find_vcpi_slots(struct drm_atomic_state *state, - struct drm_dp_mst_topology_mgr *mgr, - struct drm_dp_mst_port *port, int pbn, - int pbn_div); -int drm_dp_mst_atomic_enable_dsc(struct drm_atomic_state *state, - struct drm_dp_mst_port *port, - int pbn, int pbn_div, - bool enable); -int __must_check -drm_dp_mst_add_affected_dsc_crtcs(struct drm_atomic_state *state, - struct drm_dp_mst_topology_mgr *mgr); -int __must_check -drm_dp_atomic_release_vcpi_slots(struct drm_atomic_state *state, - struct drm_dp_mst_topology_mgr *mgr, - struct drm_dp_mst_port *port); -int drm_dp_send_power_updown_phy(struct drm_dp_mst_topology_mgr *mgr, - struct drm_dp_mst_port *port, bool power_up); -int drm_dp_send_query_stream_enc_status(struct drm_dp_mst_topology_mgr *mgr, - struct drm_dp_mst_port *port, - struct drm_dp_query_stream_enc_status_ack_reply *status); -int __must_check drm_dp_mst_atomic_check(struct drm_atomic_state *state); - -void drm_dp_mst_get_port_malloc(struct drm_dp_mst_port *port); -void drm_dp_mst_put_port_malloc(struct drm_dp_mst_port *port); - -struct drm_dp_aux *drm_dp_mst_dsc_aux_for_port(struct drm_dp_mst_port *port); - -extern const struct drm_private_state_funcs drm_dp_mst_topology_state_funcs; - -/** - * __drm_dp_mst_state_iter_get - private atomic state iterator function for - * macro-internal use - * @state: &struct drm_atomic_state pointer - * @mgr: pointer to the &struct drm_dp_mst_topology_mgr iteration cursor - * @old_state: optional pointer to the old &struct drm_dp_mst_topology_state - * iteration cursor - * @new_state: optional pointer to the new &struct drm_dp_mst_topology_state - * iteration cursor - * @i: int iteration cursor, for macro-internal use - * - * Used by for_each_oldnew_mst_mgr_in_state(), - * for_each_old_mst_mgr_in_state(), and for_each_new_mst_mgr_in_state(). Don't - * call this directly. - * - * Returns: - * True if the current &struct drm_private_obj is a &struct - * drm_dp_mst_topology_mgr, false otherwise. - */ -static inline bool -__drm_dp_mst_state_iter_get(struct drm_atomic_state *state, - struct drm_dp_mst_topology_mgr **mgr, - struct drm_dp_mst_topology_state **old_state, - struct drm_dp_mst_topology_state **new_state, - int i) -{ - struct __drm_private_objs_state *objs_state = &state->private_objs[i]; - - if (objs_state->ptr->funcs != &drm_dp_mst_topology_state_funcs) - return false; - - *mgr = to_dp_mst_topology_mgr(objs_state->ptr); - if (old_state) - *old_state = to_dp_mst_topology_state(objs_state->old_state); - if (new_state) - *new_state = to_dp_mst_topology_state(objs_state->new_state); - - return true; -} - -/** - * for_each_oldnew_mst_mgr_in_state - iterate over all DP MST topology - * managers in an atomic update - * @__state: &struct drm_atomic_state pointer - * @mgr: &struct drm_dp_mst_topology_mgr iteration cursor - * @old_state: &struct drm_dp_mst_topology_state iteration cursor for the old - * state - * @new_state: &struct drm_dp_mst_topology_state iteration cursor for the new - * state - * @__i: int iteration cursor, for macro-internal use - * - * This iterates over all DRM DP MST topology managers in an atomic update, - * tracking both old and new state. This is useful in places where the state - * delta needs to be considered, for example in atomic check functions. - */ -#define for_each_oldnew_mst_mgr_in_state(__state, mgr, old_state, new_state, __i) \ - for ((__i) = 0; (__i) < (__state)->num_private_objs; (__i)++) \ - for_each_if(__drm_dp_mst_state_iter_get((__state), &(mgr), &(old_state), &(new_state), (__i))) - -/** - * for_each_old_mst_mgr_in_state - iterate over all DP MST topology managers - * in an atomic update - * @__state: &struct drm_atomic_state pointer - * @mgr: &struct drm_dp_mst_topology_mgr iteration cursor - * @old_state: &struct drm_dp_mst_topology_state iteration cursor for the old - * state - * @__i: int iteration cursor, for macro-internal use - * - * This iterates over all DRM DP MST topology managers in an atomic update, - * tracking only the old state. This is useful in disable functions, where we - * need the old state the hardware is still in. - */ -#define for_each_old_mst_mgr_in_state(__state, mgr, old_state, __i) \ - for ((__i) = 0; (__i) < (__state)->num_private_objs; (__i)++) \ - for_each_if(__drm_dp_mst_state_iter_get((__state), &(mgr), &(old_state), NULL, (__i))) - -/** - * for_each_new_mst_mgr_in_state - iterate over all DP MST topology managers - * in an atomic update - * @__state: &struct drm_atomic_state pointer - * @mgr: &struct drm_dp_mst_topology_mgr iteration cursor - * @new_state: &struct drm_dp_mst_topology_state iteration cursor for the new - * state - * @__i: int iteration cursor, for macro-internal use - * - * This iterates over all DRM DP MST topology managers in an atomic update, - * tracking only the new state. This is useful in enable functions, where we - * need the new state the hardware should be in when the atomic commit - * operation has completed. - */ -#define for_each_new_mst_mgr_in_state(__state, mgr, new_state, __i) \ - for ((__i) = 0; (__i) < (__state)->num_private_objs; (__i)++) \ - for_each_if(__drm_dp_mst_state_iter_get((__state), &(mgr), NULL, &(new_state), (__i))) - -#endif diff --git a/include/drm/drm_dsc.h b/include/drm/drm_dsc.h index ca022e960dcc..84e3d11cc1bb 100644 --- a/include/drm/drm_dsc.h +++ b/include/drm/drm_dsc.h @@ -8,7 +8,7 @@ #ifndef DRM_DSC_H_ #define DRM_DSC_H_ -#include +#include /* VESA Display Stream Compression DSC 1.2 constants */ #define DSC_NUM_BUF_RANGES 15 -- cgit v1.2.3 From 5d1b8b4a14f798c1bc627fb788112067ee26d1da Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 21 Apr 2022 09:31:04 +0200 Subject: drm/display: Split DisplayPort header into core and helper Move DisplayPort protocol constants and structures into the new header drm_dp.h, which can be used by DRM core components. The existing header drm_dp_helper.h now only contains helper code for graphics drivers. No functional changes. Signed-off-by: Thomas Zimmermann Reviewed-by: Lyude Paul Reviewed-by: Javier Martinez Canillas Link: https://patchwork.freedesktop.org/patch/msgid/20220421073108.19226-5-tzimmermann@suse.de --- include/drm/display/drm_dp.h | 1688 +++++++++++++++++++++++++++++++++++ include/drm/display/drm_dp_helper.h | 1662 +--------------------------------- 2 files changed, 1690 insertions(+), 1660 deletions(-) create mode 100644 include/drm/display/drm_dp.h (limited to 'include') diff --git a/include/drm/display/drm_dp.h b/include/drm/display/drm_dp.h new file mode 100644 index 000000000000..3c937f8bdb42 --- /dev/null +++ b/include/drm/display/drm_dp.h @@ -0,0 +1,1688 @@ +/* + * Copyright © 2008 Keith Packard + * + * Permission to use, copy, modify, distribute, and sell this software and its + * documentation for any purpose is hereby granted without fee, provided that + * the above copyright notice appear in all copies and that both that copyright + * notice and this permission notice appear in supporting documentation, and + * that the name of the copyright holders not be used in advertising or + * publicity pertaining to distribution of the software without specific, + * written prior permission. The copyright holders make no representations + * about the suitability of this software for any purpose. It is provided "as + * is" without express or implied warranty. + * + * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, + * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO + * EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT OR + * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, + * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER + * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE + * OF THIS SOFTWARE. + */ + +#ifndef _DRM_DP_H_ +#define _DRM_DP_H_ + +#include + +/* + * Unless otherwise noted, all values are from the DP 1.1a spec. Note that + * DP and DPCD versions are independent. Differences from 1.0 are not noted, + * 1.0 devices basically don't exist in the wild. + * + * Abbreviations, in chronological order: + * + * eDP: Embedded DisplayPort version 1 + * DPI: DisplayPort Interoperability Guideline v1.1a + * 1.2: DisplayPort 1.2 + * MST: Multistream Transport - part of DP 1.2a + * + * 1.2 formally includes both eDP and DPI definitions. + */ + +/* MSA (Main Stream Attribute) MISC bits (as MISC1<<8|MISC0) */ +#define DP_MSA_MISC_SYNC_CLOCK (1 << 0) +#define DP_MSA_MISC_INTERLACE_VTOTAL_EVEN (1 << 8) +#define DP_MSA_MISC_STEREO_NO_3D (0 << 9) +#define DP_MSA_MISC_STEREO_PROG_RIGHT_EYE (1 << 9) +#define DP_MSA_MISC_STEREO_PROG_LEFT_EYE (3 << 9) +/* bits per component for non-RAW */ +#define DP_MSA_MISC_6_BPC (0 << 5) +#define DP_MSA_MISC_8_BPC (1 << 5) +#define DP_MSA_MISC_10_BPC (2 << 5) +#define DP_MSA_MISC_12_BPC (3 << 5) +#define DP_MSA_MISC_16_BPC (4 << 5) +/* bits per component for RAW */ +#define DP_MSA_MISC_RAW_6_BPC (1 << 5) +#define DP_MSA_MISC_RAW_7_BPC (2 << 5) +#define DP_MSA_MISC_RAW_8_BPC (3 << 5) +#define DP_MSA_MISC_RAW_10_BPC (4 << 5) +#define DP_MSA_MISC_RAW_12_BPC (5 << 5) +#define DP_MSA_MISC_RAW_14_BPC (6 << 5) +#define DP_MSA_MISC_RAW_16_BPC (7 << 5) +/* pixel encoding/colorimetry format */ +#define _DP_MSA_MISC_COLOR(misc1_7, misc0_21, misc0_3, misc0_4) \ + ((misc1_7) << 15 | (misc0_4) << 4 | (misc0_3) << 3 | ((misc0_21) << 1)) +#define DP_MSA_MISC_COLOR_RGB _DP_MSA_MISC_COLOR(0, 0, 0, 0) +#define DP_MSA_MISC_COLOR_CEA_RGB _DP_MSA_MISC_COLOR(0, 0, 1, 0) +#define DP_MSA_MISC_COLOR_RGB_WIDE_FIXED _DP_MSA_MISC_COLOR(0, 3, 0, 0) +#define DP_MSA_MISC_COLOR_RGB_WIDE_FLOAT _DP_MSA_MISC_COLOR(0, 3, 0, 1) +#define DP_MSA_MISC_COLOR_Y_ONLY _DP_MSA_MISC_COLOR(1, 0, 0, 0) +#define DP_MSA_MISC_COLOR_RAW _DP_MSA_MISC_COLOR(1, 1, 0, 0) +#define DP_MSA_MISC_COLOR_YCBCR_422_BT601 _DP_MSA_MISC_COLOR(0, 1, 1, 0) +#define DP_MSA_MISC_COLOR_YCBCR_422_BT709 _DP_MSA_MISC_COLOR(0, 1, 1, 1) +#define DP_MSA_MISC_COLOR_YCBCR_444_BT601 _DP_MSA_MISC_COLOR(0, 2, 1, 0) +#define DP_MSA_MISC_COLOR_YCBCR_444_BT709 _DP_MSA_MISC_COLOR(0, 2, 1, 1) +#define DP_MSA_MISC_COLOR_XVYCC_422_BT601 _DP_MSA_MISC_COLOR(0, 1, 0, 0) +#define DP_MSA_MISC_COLOR_XVYCC_422_BT709 _DP_MSA_MISC_COLOR(0, 1, 0, 1) +#define DP_MSA_MISC_COLOR_XVYCC_444_BT601 _DP_MSA_MISC_COLOR(0, 2, 0, 0) +#define DP_MSA_MISC_COLOR_XVYCC_444_BT709 _DP_MSA_MISC_COLOR(0, 2, 0, 1) +#define DP_MSA_MISC_COLOR_OPRGB _DP_MSA_MISC_COLOR(0, 0, 1, 1) +#define DP_MSA_MISC_COLOR_DCI_P3 _DP_MSA_MISC_COLOR(0, 3, 1, 0) +#define DP_MSA_MISC_COLOR_COLOR_PROFILE _DP_MSA_MISC_COLOR(0, 3, 1, 1) +#define DP_MSA_MISC_COLOR_VSC_SDP (1 << 14) + +#define DP_AUX_MAX_PAYLOAD_BYTES 16 + +#define DP_AUX_I2C_WRITE 0x0 +#define DP_AUX_I2C_READ 0x1 +#define DP_AUX_I2C_WRITE_STATUS_UPDATE 0x2 +#define DP_AUX_I2C_MOT 0x4 +#define DP_AUX_NATIVE_WRITE 0x8 +#define DP_AUX_NATIVE_READ 0x9 + +#define DP_AUX_NATIVE_REPLY_ACK (0x0 << 0) +#define DP_AUX_NATIVE_REPLY_NACK (0x1 << 0) +#define DP_AUX_NATIVE_REPLY_DEFER (0x2 << 0) +#define DP_AUX_NATIVE_REPLY_MASK (0x3 << 0) + +#define DP_AUX_I2C_REPLY_ACK (0x0 << 2) +#define DP_AUX_I2C_REPLY_NACK (0x1 << 2) +#define DP_AUX_I2C_REPLY_DEFER (0x2 << 2) +#define DP_AUX_I2C_REPLY_MASK (0x3 << 2) + +/* DPCD Field Address Mapping */ + +/* Receiver Capability */ +#define DP_DPCD_REV 0x000 +# define DP_DPCD_REV_10 0x10 +# define DP_DPCD_REV_11 0x11 +# define DP_DPCD_REV_12 0x12 +# define DP_DPCD_REV_13 0x13 +# define DP_DPCD_REV_14 0x14 + +#define DP_MAX_LINK_RATE 0x001 + +#define DP_MAX_LANE_COUNT 0x002 +# define DP_MAX_LANE_COUNT_MASK 0x1f +# define DP_TPS3_SUPPORTED (1 << 6) /* 1.2 */ +# define DP_ENHANCED_FRAME_CAP (1 << 7) + +#define DP_MAX_DOWNSPREAD 0x003 +# define DP_MAX_DOWNSPREAD_0_5 (1 << 0) +# define DP_STREAM_REGENERATION_STATUS_CAP (1 << 1) /* 2.0 */ +# define DP_NO_AUX_HANDSHAKE_LINK_TRAINING (1 << 6) +# define DP_TPS4_SUPPORTED (1 << 7) + +#define DP_NORP 0x004 + +#define DP_DOWNSTREAMPORT_PRESENT 0x005 +# define DP_DWN_STRM_PORT_PRESENT (1 << 0) +# define DP_DWN_STRM_PORT_TYPE_MASK 0x06 +# define DP_DWN_STRM_PORT_TYPE_DP (0 << 1) +# define DP_DWN_STRM_PORT_TYPE_ANALOG (1 << 1) +# define DP_DWN_STRM_PORT_TYPE_TMDS (2 << 1) +# define DP_DWN_STRM_PORT_TYPE_OTHER (3 << 1) +# define DP_FORMAT_CONVERSION (1 << 3) +# define DP_DETAILED_CAP_INFO_AVAILABLE (1 << 4) /* DPI */ + +#define DP_MAIN_LINK_CHANNEL_CODING 0x006 +# define DP_CAP_ANSI_8B10B (1 << 0) +# define DP_CAP_ANSI_128B132B (1 << 1) /* 2.0 */ + +#define DP_DOWN_STREAM_PORT_COUNT 0x007 +# define DP_PORT_COUNT_MASK 0x0f +# define DP_MSA_TIMING_PAR_IGNORED (1 << 6) /* eDP */ +# define DP_OUI_SUPPORT (1 << 7) + +#define DP_RECEIVE_PORT_0_CAP_0 0x008 +# define DP_LOCAL_EDID_PRESENT (1 << 1) +# define DP_ASSOCIATED_TO_PRECEDING_PORT (1 << 2) + +#define DP_RECEIVE_PORT_0_BUFFER_SIZE 0x009 + +#define DP_RECEIVE_PORT_1_CAP_0 0x00a +#define DP_RECEIVE_PORT_1_BUFFER_SIZE 0x00b + +#define DP_I2C_SPEED_CAP 0x00c /* DPI */ +# define DP_I2C_SPEED_1K 0x01 +# define DP_I2C_SPEED_5K 0x02 +# define DP_I2C_SPEED_10K 0x04 +# define DP_I2C_SPEED_100K 0x08 +# define DP_I2C_SPEED_400K 0x10 +# define DP_I2C_SPEED_1M 0x20 + +#define DP_EDP_CONFIGURATION_CAP 0x00d /* XXX 1.2? */ +# define DP_ALTERNATE_SCRAMBLER_RESET_CAP (1 << 0) +# define DP_FRAMING_CHANGE_CAP (1 << 1) +# define DP_DPCD_DISPLAY_CONTROL_CAPABLE (1 << 3) /* edp v1.2 or higher */ + +#define DP_TRAINING_AUX_RD_INTERVAL 0x00e /* XXX 1.2? */ +# define DP_TRAINING_AUX_RD_MASK 0x7F /* DP 1.3 */ +# define DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT (1 << 7) /* DP 1.3 */ + +#define DP_ADAPTER_CAP 0x00f /* 1.2 */ +# define DP_FORCE_LOAD_SENSE_CAP (1 << 0) +# define DP_ALTERNATE_I2C_PATTERN_CAP (1 << 1) + +#define DP_SUPPORTED_LINK_RATES 0x010 /* eDP 1.4 */ +# define DP_MAX_SUPPORTED_RATES 8 /* 16-bit little-endian */ + +/* Multiple stream transport */ +#define DP_FAUX_CAP 0x020 /* 1.2 */ +# define DP_FAUX_CAP_1 (1 << 0) + +#define DP_SINK_VIDEO_FALLBACK_FORMATS 0x020 /* 2.0 */ +# define DP_FALLBACK_1024x768_60HZ_24BPP (1 << 0) +# define DP_FALLBACK_1280x720_60HZ_24BPP (1 << 1) +# define DP_FALLBACK_1920x1080_60HZ_24BPP (1 << 2) + +#define DP_MSTM_CAP 0x021 /* 1.2 */ +# define DP_MST_CAP (1 << 0) +# define DP_SINGLE_STREAM_SIDEBAND_MSG (1 << 1) /* 2.0 */ + +#define DP_NUMBER_OF_AUDIO_ENDPOINTS 0x022 /* 1.2 */ + +/* AV_SYNC_DATA_BLOCK 1.2 */ +#define DP_AV_GRANULARITY 0x023 +# define DP_AG_FACTOR_MASK (0xf << 0) +# define DP_AG_FACTOR_3MS (0 << 0) +# define DP_AG_FACTOR_2MS (1 << 0) +# define DP_AG_FACTOR_1MS (2 << 0) +# define DP_AG_FACTOR_500US (3 << 0) +# define DP_AG_FACTOR_200US (4 << 0) +# define DP_AG_FACTOR_100US (5 << 0) +# define DP_AG_FACTOR_10US (6 << 0) +# define DP_AG_FACTOR_1US (7 << 0) +# define DP_VG_FACTOR_MASK (0xf << 4) +# define DP_VG_FACTOR_3MS (0 << 4) +# define DP_VG_FACTOR_2MS (1 << 4) +# define DP_VG_FACTOR_1MS (2 << 4) +# define DP_VG_FACTOR_500US (3 << 4) +# define DP_VG_FACTOR_200US (4 << 4) +# define DP_VG_FACTOR_100US (5 << 4) + +#define DP_AUD_DEC_LAT0 0x024 +#define DP_AUD_DEC_LAT1 0x025 + +#define DP_AUD_PP_LAT0 0x026 +#define DP_AUD_PP_LAT1 0x027 + +#define DP_VID_INTER_LAT 0x028 + +#define DP_VID_PROG_LAT 0x029 + +#define DP_REP_LAT 0x02a + +#define DP_AUD_DEL_INS0 0x02b +#define DP_AUD_DEL_INS1 0x02c +#define DP_AUD_DEL_INS2 0x02d +/* End of AV_SYNC_DATA_BLOCK */ + +#define DP_RECEIVER_ALPM_CAP 0x02e /* eDP 1.4 */ +# define DP_ALPM_CAP (1 << 0) + +#define DP_SINK_DEVICE_AUX_FRAME_SYNC_CAP 0x02f /* eDP 1.4 */ +# define DP_AUX_FRAME_SYNC_CAP (1 << 0) + +#define DP_GUID 0x030 /* 1.2 */ + +#define DP_DSC_SUPPORT 0x060 /* DP 1.4 */ +# define DP_DSC_DECOMPRESSION_IS_SUPPORTED (1 << 0) + +#define DP_DSC_REV 0x061 +# define DP_DSC_MAJOR_MASK (0xf << 0) +# define DP_DSC_MINOR_MASK (0xf << 4) +# define DP_DSC_MAJOR_SHIFT 0 +# define DP_DSC_MINOR_SHIFT 4 + +#define DP_DSC_RC_BUF_BLK_SIZE 0x062 +# define DP_DSC_RC_BUF_BLK_SIZE_1 0x0 +# define DP_DSC_RC_BUF_BLK_SIZE_4 0x1 +# define DP_DSC_RC_BUF_BLK_SIZE_16 0x2 +# define DP_DSC_RC_BUF_BLK_SIZE_64 0x3 + +#define DP_DSC_RC_BUF_SIZE 0x063 + +#define DP_DSC_SLICE_CAP_1 0x064 +# define DP_DSC_1_PER_DP_DSC_SINK (1 << 0) +# define DP_DSC_2_PER_DP_DSC_SINK (1 << 1) +# define DP_DSC_4_PER_DP_DSC_SINK (1 << 3) +# define DP_DSC_6_PER_DP_DSC_SINK (1 << 4) +# define DP_DSC_8_PER_DP_DSC_SINK (1 << 5) +# define DP_DSC_10_PER_DP_DSC_SINK (1 << 6) +# define DP_DSC_12_PER_DP_DSC_SINK (1 << 7) + +#define DP_DSC_LINE_BUF_BIT_DEPTH 0x065 +# define DP_DSC_LINE_BUF_BIT_DEPTH_MASK (0xf << 0) +# define DP_DSC_LINE_BUF_BIT_DEPTH_9 0x0 +# define DP_DSC_LINE_BUF_BIT_DEPTH_10 0x1 +# define DP_DSC_LINE_BUF_BIT_DEPTH_11 0x2 +# define DP_DSC_LINE_BUF_BIT_DEPTH_12 0x3 +# define DP_DSC_LINE_BUF_BIT_DEPTH_13 0x4 +# define DP_DSC_LINE_BUF_BIT_DEPTH_14 0x5 +# define DP_DSC_LINE_BUF_BIT_DEPTH_15 0x6 +# define DP_DSC_LINE_BUF_BIT_DEPTH_16 0x7 +# define DP_DSC_LINE_BUF_BIT_DEPTH_8 0x8 + +#define DP_DSC_BLK_PREDICTION_SUPPORT 0x066 +# define DP_DSC_BLK_PREDICTION_IS_SUPPORTED (1 << 0) + +#define DP_DSC_MAX_BITS_PER_PIXEL_LOW 0x067 /* eDP 1.4 */ + +#define DP_DSC_MAX_BITS_PER_PIXEL_HI 0x068 /* eDP 1.4 */ +# define DP_DSC_MAX_BITS_PER_PIXEL_HI_MASK (0x3 << 0) +# define DP_DSC_MAX_BITS_PER_PIXEL_HI_SHIFT 8 + +#define DP_DSC_DEC_COLOR_FORMAT_CAP 0x069 +# define DP_DSC_RGB (1 << 0) +# define DP_DSC_YCbCr444 (1 << 1) +# define DP_DSC_YCbCr422_Simple (1 << 2) +# define DP_DSC_YCbCr422_Native (1 << 3) +# define DP_DSC_YCbCr420_Native (1 << 4) + +#define DP_DSC_DEC_COLOR_DEPTH_CAP 0x06A +# define DP_DSC_8_BPC (1 << 1) +# define DP_DSC_10_BPC (1 << 2) +# define DP_DSC_12_BPC (1 << 3) + +#define DP_DSC_PEAK_THROUGHPUT 0x06B +# define DP_DSC_THROUGHPUT_MODE_0_MASK (0xf << 0) +# define DP_DSC_THROUGHPUT_MODE_0_SHIFT 0 +# define DP_DSC_THROUGHPUT_MODE_0_UNSUPPORTED 0 +# define DP_DSC_THROUGHPUT_MODE_0_340 (1 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_400 (2 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_450 (3 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_500 (4 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_550 (5 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_600 (6 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_650 (7 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_700 (8 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_750 (9 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_800 (10 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_850 (11 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_900 (12 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_950 (13 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_1000 (14 << 0) +# define DP_DSC_THROUGHPUT_MODE_0_170 (15 << 0) /* 1.4a */ +# define DP_DSC_THROUGHPUT_MODE_1_MASK (0xf << 4) +# define DP_DSC_THROUGHPUT_MODE_1_SHIFT 4 +# define DP_DSC_THROUGHPUT_MODE_1_UNSUPPORTED 0 +# define DP_DSC_THROUGHPUT_MODE_1_340 (1 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_400 (2 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_450 (3 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_500 (4 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_550 (5 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_600 (6 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_650 (7 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_700 (8 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_750 (9 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_800 (10 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_850 (11 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_900 (12 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_950 (13 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_1000 (14 << 4) +# define DP_DSC_THROUGHPUT_MODE_1_170 (15 << 4) + +#define DP_DSC_MAX_SLICE_WIDTH 0x06C +#define DP_DSC_MIN_SLICE_WIDTH_VALUE 2560 +#define DP_DSC_SLICE_WIDTH_MULTIPLIER 320 + +#define DP_DSC_SLICE_CAP_2 0x06D +# define DP_DSC_16_PER_DP_DSC_SINK (1 << 0) +# define DP_DSC_20_PER_DP_DSC_SINK (1 << 1) +# define DP_DSC_24_PER_DP_DSC_SINK (1 << 2) + +#define DP_DSC_BITS_PER_PIXEL_INC 0x06F +# define DP_DSC_BITS_PER_PIXEL_1_16 0x0 +# define DP_DSC_BITS_PER_PIXEL_1_8 0x1 +# define DP_DSC_BITS_PER_PIXEL_1_4 0x2 +# define DP_DSC_BITS_PER_PIXEL_1_2 0x3 +# define DP_DSC_BITS_PER_PIXEL_1 0x4 + +#define DP_PSR_SUPPORT 0x070 /* XXX 1.2? */ +# define DP_PSR_IS_SUPPORTED 1 +# define DP_PSR2_IS_SUPPORTED 2 /* eDP 1.4 */ +# define DP_PSR2_WITH_Y_COORD_IS_SUPPORTED 3 /* eDP 1.4a */ + +#define DP_PSR_CAPS 0x071 /* XXX 1.2? */ +# define DP_PSR_NO_TRAIN_ON_EXIT 1 +# define DP_PSR_SETUP_TIME_330 (0 << 1) +# define DP_PSR_SETUP_TIME_275 (1 << 1) +# define DP_PSR_SETUP_TIME_220 (2 << 1) +# define DP_PSR_SETUP_TIME_165 (3 << 1) +# define DP_PSR_SETUP_TIME_110 (4 << 1) +# define DP_PSR_SETUP_TIME_55 (5 << 1) +# define DP_PSR_SETUP_TIME_0 (6 << 1) +# define DP_PSR_SETUP_TIME_MASK (7 << 1) +# define DP_PSR_SETUP_TIME_SHIFT 1 +# define DP_PSR2_SU_Y_COORDINATE_REQUIRED (1 << 4) /* eDP 1.4a */ +# define DP_PSR2_SU_GRANULARITY_REQUIRED (1 << 5) /* eDP 1.4b */ + +#define DP_PSR2_SU_X_GRANULARITY 0x072 /* eDP 1.4b */ +#define DP_PSR2_SU_Y_GRANULARITY 0x074 /* eDP 1.4b */ + +/* + * 0x80-0x8f describe downstream port capabilities, but there are two layouts + * based on whether DP_DETAILED_CAP_INFO_AVAILABLE was set. If it was not, + * each port's descriptor is one byte wide. If it was set, each port's is + * four bytes wide, starting with the one byte from the base info. As of + * DP interop v1.1a only VGA defines additional detail. + */ + +/* offset 0 */ +#define DP_DOWNSTREAM_PORT_0 0x80 +# define DP_DS_PORT_TYPE_MASK (7 << 0) +# define DP_DS_PORT_TYPE_DP 0 +# define DP_DS_PORT_TYPE_VGA 1 +# define DP_DS_PORT_TYPE_DVI 2 +# define DP_DS_PORT_TYPE_HDMI 3 +# define DP_DS_PORT_TYPE_NON_EDID 4 +# define DP_DS_PORT_TYPE_DP_DUALMODE 5 +# define DP_DS_PORT_TYPE_WIRELESS 6 +# define DP_DS_PORT_HPD (1 << 3) +# define DP_DS_NON_EDID_MASK (0xf << 4) +# define DP_DS_NON_EDID_720x480i_60 (1 << 4) +# define DP_DS_NON_EDID_720x480i_50 (2 << 4) +# define DP_DS_NON_EDID_1920x1080i_60 (3 << 4) +# define DP_DS_NON_EDID_1920x1080i_50 (4 << 4) +# define DP_DS_NON_EDID_1280x720_60 (5 << 4) +# define DP_DS_NON_EDID_1280x720_50 (7 << 4) +/* offset 1 for VGA is maximum megapixels per second / 8 */ +/* offset 1 for DVI/HDMI is maximum TMDS clock in Mbps / 2.5 */ +/* offset 2 for VGA/DVI/HDMI */ +# define DP_DS_MAX_BPC_MASK (3 << 0) +# define DP_DS_8BPC 0 +# define DP_DS_10BPC 1 +# define DP_DS_12BPC 2 +# define DP_DS_16BPC 3 +/* HDMI2.1 PCON FRL CONFIGURATION */ +# define DP_PCON_MAX_FRL_BW (7 << 2) +# define DP_PCON_MAX_0GBPS (0 << 2) +# define DP_PCON_MAX_9GBPS (1 << 2) +# define DP_PCON_MAX_18GBPS (2 << 2) +# define DP_PCON_MAX_24GBPS (3 << 2) +# define DP_PCON_MAX_32GBPS (4 << 2) +# define DP_PCON_MAX_40GBPS (5 << 2) +# define DP_PCON_MAX_48GBPS (6 << 2) +# define DP_PCON_SOURCE_CTL_MODE (1 << 5) + +/* offset 3 for DVI */ +# define DP_DS_DVI_DUAL_LINK (1 << 1) +# define DP_DS_DVI_HIGH_COLOR_DEPTH (1 << 2) +/* offset 3 for HDMI */ +# define DP_DS_HDMI_FRAME_SEQ_TO_FRAME_PACK (1 << 0) +# define DP_DS_HDMI_YCBCR422_PASS_THROUGH (1 << 1) +# define DP_DS_HDMI_YCBCR420_PASS_THROUGH (1 << 2) +# define DP_DS_HDMI_YCBCR444_TO_422_CONV (1 << 3) +# define DP_DS_HDMI_YCBCR444_TO_420_CONV (1 << 4) + +/* + * VESA DP-to-HDMI PCON Specification adds caps for colorspace + * conversion in DFP cap DPCD 83h. Sec6.1 Table-3. + * Based on the available support the source can enable + * color conversion by writing into PROTOCOL_COVERTER_CONTROL_2 + * DPCD 3052h. + */ +# define DP_DS_HDMI_BT601_RGB_YCBCR_CONV (1 << 5) +# define DP_DS_HDMI_BT709_RGB_YCBCR_CONV (1 << 6) +# define DP_DS_HDMI_BT2020_RGB_YCBCR_CONV (1 << 7) + +#define DP_MAX_DOWNSTREAM_PORTS 0x10 + +/* DP Forward error Correction Registers */ +#define DP_FEC_CAPABILITY 0x090 /* 1.4 */ +# define DP_FEC_CAPABLE (1 << 0) +# define DP_FEC_UNCORR_BLK_ERROR_COUNT_CAP (1 << 1) +# define DP_FEC_CORR_BLK_ERROR_COUNT_CAP (1 << 2) +# define DP_FEC_BIT_ERROR_COUNT_CAP (1 << 3) +#define DP_FEC_CAPABILITY_1 0x091 /* 2.0 */ + +/* DP-HDMI2.1 PCON DSC ENCODER SUPPORT */ +#define DP_PCON_DSC_ENCODER_CAP_SIZE 0xD /* 0x92 through 0x9E */ +#define DP_PCON_DSC_ENCODER 0x092 +# define DP_PCON_DSC_ENCODER_SUPPORTED (1 << 0) +# define DP_PCON_DSC_PPS_ENC_OVERRIDE (1 << 1) + +/* DP-HDMI2.1 PCON DSC Version */ +#define DP_PCON_DSC_VERSION 0x093 +# define DP_PCON_DSC_MAJOR_MASK (0xF << 0) +# define DP_PCON_DSC_MINOR_MASK (0xF << 4) +# define DP_PCON_DSC_MAJOR_SHIFT 0 +# define DP_PCON_DSC_MINOR_SHIFT 4 + +/* DP-HDMI2.1 PCON DSC RC Buffer block size */ +#define DP_PCON_DSC_RC_BUF_BLK_INFO 0x094 +# define DP_PCON_DSC_RC_BUF_BLK_SIZE (0x3 << 0) +# define DP_PCON_DSC_RC_BUF_BLK_1KB 0 +# define DP_PCON_DSC_RC_BUF_BLK_4KB 1 +# define DP_PCON_DSC_RC_BUF_BLK_16KB 2 +# define DP_PCON_DSC_RC_BUF_BLK_64KB 3 + +/* DP-HDMI2.1 PCON DSC RC Buffer size */ +#define DP_PCON_DSC_RC_BUF_SIZE 0x095 + +/* DP-HDMI2.1 PCON DSC Slice capabilities-1 */ +#define DP_PCON_DSC_SLICE_CAP_1 0x096 +# define DP_PCON_DSC_1_PER_DSC_ENC (0x1 << 0) +# define DP_PCON_DSC_2_PER_DSC_ENC (0x1 << 1) +# define DP_PCON_DSC_4_PER_DSC_ENC (0x1 << 3) +# define DP_PCON_DSC_6_PER_DSC_ENC (0x1 << 4) +# define DP_PCON_DSC_8_PER_DSC_ENC (0x1 << 5) +# define DP_PCON_DSC_10_PER_DSC_ENC (0x1 << 6) +# define DP_PCON_DSC_12_PER_DSC_ENC (0x1 << 7) + +#define DP_PCON_DSC_BUF_BIT_DEPTH 0x097 +# define DP_PCON_DSC_BIT_DEPTH_MASK (0xF << 0) +# define DP_PCON_DSC_DEPTH_9_BITS 0 +# define DP_PCON_DSC_DEPTH_10_BITS 1 +# define DP_PCON_DSC_DEPTH_11_BITS 2 +# define DP_PCON_DSC_DEPTH_12_BITS 3 +# define DP_PCON_DSC_DEPTH_13_BITS 4 +# define DP_PCON_DSC_DEPTH_14_BITS 5 +# define DP_PCON_DSC_DEPTH_15_BITS 6 +# define DP_PCON_DSC_DEPTH_16_BITS 7 +# define DP_PCON_DSC_DEPTH_8_BITS 8 + +#define DP_PCON_DSC_BLOCK_PREDICTION 0x098 +# define DP_PCON_DSC_BLOCK_PRED_SUPPORT (0x1 << 0) + +#define DP_PCON_DSC_ENC_COLOR_FMT_CAP 0x099 +# define DP_PCON_DSC_ENC_RGB (0x1 << 0) +# define DP_PCON_DSC_ENC_YUV444 (0x1 << 1) +# define DP_PCON_DSC_ENC_YUV422_S (0x1 << 2) +# define DP_PCON_DSC_ENC_YUV422_N (0x1 << 3) +# define DP_PCON_DSC_ENC_YUV420_N (0x1 << 4) + +#define DP_PCON_DSC_ENC_COLOR_DEPTH_CAP 0x09A +# define DP_PCON_DSC_ENC_8BPC (0x1 << 1) +# define DP_PCON_DSC_ENC_10BPC (0x1 << 2) +# define DP_PCON_DSC_ENC_12BPC (0x1 << 3) + +#define DP_PCON_DSC_MAX_SLICE_WIDTH 0x09B + +/* DP-HDMI2.1 PCON DSC Slice capabilities-2 */ +#define DP_PCON_DSC_SLICE_CAP_2 0x09C +# define DP_PCON_DSC_16_PER_DSC_ENC (0x1 << 0) +# define DP_PCON_DSC_20_PER_DSC_ENC (0x1 << 1) +# define DP_PCON_DSC_24_PER_DSC_ENC (0x1 << 2) + +/* DP-HDMI2.1 PCON HDMI TX Encoder Bits/pixel increment */ +#define DP_PCON_DSC_BPP_INCR 0x09E +# define DP_PCON_DSC_BPP_INCR_MASK (0x7 << 0) +# define DP_PCON_DSC_ONE_16TH_BPP 0 +# define DP_PCON_DSC_ONE_8TH_BPP 1 +# define DP_PCON_DSC_ONE_4TH_BPP 2 +# define DP_PCON_DSC_ONE_HALF_BPP 3 +# define DP_PCON_DSC_ONE_BPP 4 + +/* DP Extended DSC Capabilities */ +#define DP_DSC_BRANCH_OVERALL_THROUGHPUT_0 0x0a0 /* DP 1.4a SCR */ +#define DP_DSC_BRANCH_OVERALL_THROUGHPUT_1 0x0a1 +#define DP_DSC_BRANCH_MAX_LINE_WIDTH 0x0a2 + +/* DFP Capability Extension */ +#define DP_DFP_CAPABILITY_EXTENSION_SUPPORT 0x0a3 /* 2.0 */ + +/* Link Configuration */ +#define DP_LINK_BW_SET 0x100 +# define DP_LINK_RATE_TABLE 0x00 /* eDP 1.4 */ +# define DP_LINK_BW_1_62 0x06 +# define DP_LINK_BW_2_7 0x0a +# define DP_LINK_BW_5_4 0x14 /* 1.2 */ +# define DP_LINK_BW_8_1 0x1e /* 1.4 */ +# define DP_LINK_BW_10 0x01 /* 2.0 128b/132b Link Layer */ +# define DP_LINK_BW_13_5 0x04 /* 2.0 128b/132b Link Layer */ +# define DP_LINK_BW_20 0x02 /* 2.0 128b/132b Link Layer */ + +#define DP_LANE_COUNT_SET 0x101 +# define DP_LANE_COUNT_MASK 0x0f +# define DP_LANE_COUNT_ENHANCED_FRAME_EN (1 << 7) + +#define DP_TRAINING_PATTERN_SET 0x102 +# define DP_TRAINING_PATTERN_DISABLE 0 +# define DP_TRAINING_PATTERN_1 1 +# define DP_TRAINING_PATTERN_2 2 +# define DP_TRAINING_PATTERN_2_CDS 3 /* 2.0 E11 */ +# define DP_TRAINING_PATTERN_3 3 /* 1.2 */ +# define DP_TRAINING_PATTERN_4 7 /* 1.4 */ +# define DP_TRAINING_PATTERN_MASK 0x3 +# define DP_TRAINING_PATTERN_MASK_1_4 0xf + +/* DPCD 1.1 only. For DPCD >= 1.2 see per-lane DP_LINK_QUAL_LANEn_SET */ +# define DP_LINK_QUAL_PATTERN_11_DISABLE (0 << 2) +# define DP_LINK_QUAL_PATTERN_11_D10_2 (1 << 2) +# define DP_LINK_QUAL_PATTERN_11_ERROR_RATE (2 << 2) +# define DP_LINK_QUAL_PATTERN_11_PRBS7 (3 << 2) +# define DP_LINK_QUAL_PATTERN_11_MASK (3 << 2) + +# define DP_RECOVERED_CLOCK_OUT_EN (1 << 4) +# define DP_LINK_SCRAMBLING_DISABLE (1 << 5) + +# define DP_SYMBOL_ERROR_COUNT_BOTH (0 << 6) +# define DP_SYMBOL_ERROR_COUNT_DISPARITY (1 << 6) +# define DP_SYMBOL_ERROR_COUNT_SYMBOL (2 << 6) +# define DP_SYMBOL_ERROR_COUNT_MASK (3 << 6) + +#define DP_TRAINING_LANE0_SET 0x103 +#define DP_TRAINING_LANE1_SET 0x104 +#define DP_TRAINING_LANE2_SET 0x105 +#define DP_TRAINING_LANE3_SET 0x106 + +# define DP_TRAIN_VOLTAGE_SWING_MASK 0x3 +# define DP_TRAIN_VOLTAGE_SWING_SHIFT 0 +# define DP_TRAIN_MAX_SWING_REACHED (1 << 2) +# define DP_TRAIN_VOLTAGE_SWING_LEVEL_0 (0 << 0) +# define DP_TRAIN_VOLTAGE_SWING_LEVEL_1 (1 << 0) +# define DP_TRAIN_VOLTAGE_SWING_LEVEL_2 (2 << 0) +# define DP_TRAIN_VOLTAGE_SWING_LEVEL_3 (3 << 0) + +# define DP_TRAIN_PRE_EMPHASIS_MASK (3 << 3) +# define DP_TRAIN_PRE_EMPH_LEVEL_0 (0 << 3) +# define DP_TRAIN_PRE_EMPH_LEVEL_1 (1 << 3) +# define DP_TRAIN_PRE_EMPH_LEVEL_2 (2 << 3) +# define DP_TRAIN_PRE_EMPH_LEVEL_3 (3 << 3) + +# define DP_TRAIN_PRE_EMPHASIS_SHIFT 3 +# define DP_TRAIN_MAX_PRE_EMPHASIS_REACHED (1 << 5) + +# define DP_TX_FFE_PRESET_VALUE_MASK (0xf << 0) /* 2.0 128b/132b Link Layer */ + +#define DP_DOWNSPREAD_CTRL 0x107 +# define DP_SPREAD_AMP_0_5 (1 << 4) +# define DP_MSA_TIMING_PAR_IGNORE_EN (1 << 7) /* eDP */ + +#define DP_MAIN_LINK_CHANNEL_CODING_SET 0x108 +# define DP_SET_ANSI_8B10B (1 << 0) +# define DP_SET_ANSI_128B132B (1 << 1) + +#define DP_I2C_SPEED_CONTROL_STATUS 0x109 /* DPI */ +/* bitmask as for DP_I2C_SPEED_CAP */ + +#define DP_EDP_CONFIGURATION_SET 0x10a /* XXX 1.2? */ +# define DP_ALTERNATE_SCRAMBLER_RESET_ENABLE (1 << 0) +# define DP_FRAMING_CHANGE_ENABLE (1 << 1) +# define DP_PANEL_SELF_TEST_ENABLE (1 << 7) + +#define DP_LINK_QUAL_LANE0_SET 0x10b /* DPCD >= 1.2 */ +#define DP_LINK_QUAL_LANE1_SET 0x10c +#define DP_LINK_QUAL_LANE2_SET 0x10d +#define DP_LINK_QUAL_LANE3_SET 0x10e +# define DP_LINK_QUAL_PATTERN_DISABLE 0 +# define DP_LINK_QUAL_PATTERN_D10_2 1 +# define DP_LINK_QUAL_PATTERN_ERROR_RATE 2 +# define DP_LINK_QUAL_PATTERN_PRBS7 3 +# define DP_LINK_QUAL_PATTERN_80BIT_CUSTOM 4 +# define DP_LINK_QUAL_PATTERN_CP2520_PAT_1 5 +# define DP_LINK_QUAL_PATTERN_CP2520_PAT_2 6 +# define DP_LINK_QUAL_PATTERN_CP2520_PAT_3 7 +/* DP 2.0 UHBR10, UHBR13.5, UHBR20 */ +# define DP_LINK_QUAL_PATTERN_128B132B_TPS1 0x08 +# define DP_LINK_QUAL_PATTERN_128B132B_TPS2 0x10 +# define DP_LINK_QUAL_PATTERN_PRSBS9 0x18 +# define DP_LINK_QUAL_PATTERN_PRSBS11 0x20 +# define DP_LINK_QUAL_PATTERN_PRSBS15 0x28 +# define DP_LINK_QUAL_PATTERN_PRSBS23 0x30 +# define DP_LINK_QUAL_PATTERN_PRSBS31 0x38 +# define DP_LINK_QUAL_PATTERN_CUSTOM 0x40 +# define DP_LINK_QUAL_PATTERN_SQUARE 0x48 + +#define DP_TRAINING_LANE0_1_SET2 0x10f +#define DP_TRAINING_LANE2_3_SET2 0x110 +# define DP_LANE02_POST_CURSOR2_SET_MASK (3 << 0) +# define DP_LANE02_MAX_POST_CURSOR2_REACHED (1 << 2) +# define DP_LANE13_POST_CURSOR2_SET_MASK (3 << 4) +# define DP_LANE13_MAX_POST_CURSOR2_REACHED (1 << 6) + +#define DP_MSTM_CTRL 0x111 /* 1.2 */ +# define DP_MST_EN (1 << 0) +# define DP_UP_REQ_EN (1 << 1) +# define DP_UPSTREAM_IS_SRC (1 << 2) + +#define DP_AUDIO_DELAY0 0x112 /* 1.2 */ +#define DP_AUDIO_DELAY1 0x113 +#define DP_AUDIO_DELAY2 0x114 + +#define DP_LINK_RATE_SET 0x115 /* eDP 1.4 */ +# define DP_LINK_RATE_SET_SHIFT 0 +# define DP_LINK_RATE_SET_MASK (7 << 0) + +#define DP_RECEIVER_ALPM_CONFIG 0x116 /* eDP 1.4 */ +# define DP_ALPM_ENABLE (1 << 0) +# define DP_ALPM_LOCK_ERROR_IRQ_HPD_ENABLE (1 << 1) + +#define DP_SINK_DEVICE_AUX_FRAME_SYNC_CONF 0x117 /* eDP 1.4 */ +# define DP_AUX_FRAME_SYNC_ENABLE (1 << 0) +# define DP_IRQ_HPD_ENABLE (1 << 1) + +#define DP_UPSTREAM_DEVICE_DP_PWR_NEED 0x118 /* 1.2 */ +# define DP_PWR_NOT_NEEDED (1 << 0) + +#define DP_FEC_CONFIGURATION 0x120 /* 1.4 */ +# define DP_FEC_READY (1 << 0) +# define DP_FEC_ERR_COUNT_SEL_MASK (7 << 1) +# define DP_FEC_ERR_COUNT_DIS (0 << 1) +# define DP_FEC_UNCORR_BLK_ERROR_COUNT (1 << 1) +# define DP_FEC_CORR_BLK_ERROR_COUNT (2 << 1) +# define DP_FEC_BIT_ERROR_COUNT (3 << 1) +# define DP_FEC_LANE_SELECT_MASK (3 << 4) +# define DP_FEC_LANE_0_SELECT (0 << 4) +# define DP_FEC_LANE_1_SELECT (1 << 4) +# define DP_FEC_LANE_2_SELECT (2 << 4) +# define DP_FEC_LANE_3_SELECT (3 << 4) + +#define DP_AUX_FRAME_SYNC_VALUE 0x15c /* eDP 1.4 */ +# define DP_AUX_FRAME_SYNC_VALID (1 << 0) + +#define DP_DSC_ENABLE 0x160 /* DP 1.4 */ +# define DP_DECOMPRESSION_EN (1 << 0) +#define DP_DSC_CONFIGURATION 0x161 /* DP 2.0 */ + +#define DP_PSR_EN_CFG 0x170 /* XXX 1.2? */ +# define DP_PSR_ENABLE BIT(0) +# define DP_PSR_MAIN_LINK_ACTIVE BIT(1) +# define DP_PSR_CRC_VERIFICATION BIT(2) +# define DP_PSR_FRAME_CAPTURE BIT(3) +# define DP_PSR_SU_REGION_SCANLINE_CAPTURE BIT(4) /* eDP 1.4a */ +# define DP_PSR_IRQ_HPD_WITH_CRC_ERRORS BIT(5) /* eDP 1.4a */ +# define DP_PSR_ENABLE_PSR2 BIT(6) /* eDP 1.4a */ + +#define DP_ADAPTER_CTRL 0x1a0 +# define DP_ADAPTER_CTRL_FORCE_LOAD_SENSE (1 << 0) + +#define DP_BRANCH_DEVICE_CTRL 0x1a1 +# define DP_BRANCH_DEVICE_IRQ_HPD (1 << 0) + +#define DP_PAYLOAD_ALLOCATE_SET 0x1c0 +#define DP_PAYLOAD_ALLOCATE_START_TIME_SLOT 0x1c1 +#define DP_PAYLOAD_ALLOCATE_TIME_SLOT_COUNT 0x1c2 + +/* Link/Sink Device Status */ +#define DP_SINK_COUNT 0x200 +/* prior to 1.2 bit 7 was reserved mbz */ +# define DP_GET_SINK_COUNT(x) ((((x) & 0x80) >> 1) | ((x) & 0x3f)) +# define DP_SINK_CP_READY (1 << 6) + +#define DP_DEVICE_SERVICE_IRQ_VECTOR 0x201 +# define DP_REMOTE_CONTROL_COMMAND_PENDING (1 << 0) +# define DP_AUTOMATED_TEST_REQUEST (1 << 1) +# define DP_CP_IRQ (1 << 2) +# define DP_MCCS_IRQ (1 << 3) +# define DP_DOWN_REP_MSG_RDY (1 << 4) /* 1.2 MST */ +# define DP_UP_REQ_MSG_RDY (1 << 5) /* 1.2 MST */ +# define DP_SINK_SPECIFIC_IRQ (1 << 6) + +#define DP_LANE0_1_STATUS 0x202 +#define DP_LANE2_3_STATUS 0x203 +# define DP_LANE_CR_DONE (1 << 0) +# define DP_LANE_CHANNEL_EQ_DONE (1 << 1) +# define DP_LANE_SYMBOL_LOCKED (1 << 2) + +#define DP_CHANNEL_EQ_BITS (DP_LANE_CR_DONE | \ + DP_LANE_CHANNEL_EQ_DONE | \ + DP_LANE_SYMBOL_LOCKED) + +#define DP_LANE_ALIGN_STATUS_UPDATED 0x204 +#define DP_INTERLANE_ALIGN_DONE (1 << 0) +#define DP_128B132B_DPRX_EQ_INTERLANE_ALIGN_DONE (1 << 2) /* 2.0 E11 */ +#define DP_128B132B_DPRX_CDS_INTERLANE_ALIGN_DONE (1 << 3) /* 2.0 E11 */ +#define DP_128B132B_LT_FAILED (1 << 4) /* 2.0 E11 */ +#define DP_DOWNSTREAM_PORT_STATUS_CHANGED (1 << 6) +#define DP_LINK_STATUS_UPDATED (1 << 7) + +#define DP_SINK_STATUS 0x205 +# define DP_RECEIVE_PORT_0_STATUS (1 << 0) +# define DP_RECEIVE_PORT_1_STATUS (1 << 1) +# define DP_STREAM_REGENERATION_STATUS (1 << 2) /* 2.0 */ +# define DP_INTRA_HOP_AUX_REPLY_INDICATION (1 << 3) /* 2.0 */ + +#define DP_ADJUST_REQUEST_LANE0_1 0x206 +#define DP_ADJUST_REQUEST_LANE2_3 0x207 +# define DP_ADJUST_VOLTAGE_SWING_LANE0_MASK 0x03 +# define DP_ADJUST_VOLTAGE_SWING_LANE0_SHIFT 0 +# define DP_ADJUST_PRE_EMPHASIS_LANE0_MASK 0x0c +# define DP_ADJUST_PRE_EMPHASIS_LANE0_SHIFT 2 +# define DP_ADJUST_VOLTAGE_SWING_LANE1_MASK 0x30 +# define DP_ADJUST_VOLTAGE_SWING_LANE1_SHIFT 4 +# define DP_ADJUST_PRE_EMPHASIS_LANE1_MASK 0xc0 +# define DP_ADJUST_PRE_EMPHASIS_LANE1_SHIFT 6 + +/* DP 2.0 128b/132b Link Layer */ +# define DP_ADJUST_TX_FFE_PRESET_LANE0_MASK (0xf << 0) +# define DP_ADJUST_TX_FFE_PRESET_LANE0_SHIFT 0 +# define DP_ADJUST_TX_FFE_PRESET_LANE1_MASK (0xf << 4) +# define DP_ADJUST_TX_FFE_PRESET_LANE1_SHIFT 4 + +#define DP_ADJUST_REQUEST_POST_CURSOR2 0x20c +# define DP_ADJUST_POST_CURSOR2_LANE0_MASK 0x03 +# define DP_ADJUST_POST_CURSOR2_LANE0_SHIFT 0 +# define DP_ADJUST_POST_CURSOR2_LANE1_MASK 0x0c +# define DP_ADJUST_POST_CURSOR2_LANE1_SHIFT 2 +# define DP_ADJUST_POST_CURSOR2_LANE2_MASK 0x30 +# define DP_ADJUST_POST_CURSOR2_LANE2_SHIFT 4 +# define DP_ADJUST_POST_CURSOR2_LANE3_MASK 0xc0 +# define DP_ADJUST_POST_CURSOR2_LANE3_SHIFT 6 + +#define DP_TEST_REQUEST 0x218 +# define DP_TEST_LINK_TRAINING (1 << 0) +# define DP_TEST_LINK_VIDEO_PATTERN (1 << 1) +# define DP_TEST_LINK_EDID_READ (1 << 2) +# define DP_TEST_LINK_PHY_TEST_PATTERN (1 << 3) /* DPCD >= 1.1 */ +# define DP_TEST_LINK_FAUX_PATTERN (1 << 4) /* DPCD >= 1.2 */ +# define DP_TEST_LINK_AUDIO_PATTERN (1 << 5) /* DPCD >= 1.2 */ +# define DP_TEST_LINK_AUDIO_DISABLED_VIDEO (1 << 6) /* DPCD >= 1.2 */ + +#define DP_TEST_LINK_RATE 0x219 +# define DP_LINK_RATE_162 (0x6) +# define DP_LINK_RATE_27 (0xa) + +#define DP_TEST_LANE_COUNT 0x220 + +#define DP_TEST_PATTERN 0x221 +# define DP_NO_TEST_PATTERN 0x0 +# define DP_COLOR_RAMP 0x1 +# define DP_BLACK_AND_WHITE_VERTICAL_LINES 0x2 +# define DP_COLOR_SQUARE 0x3 + +#define DP_TEST_H_TOTAL_HI 0x222 +#define DP_TEST_H_TOTAL_LO 0x223 + +#define DP_TEST_V_TOTAL_HI 0x224 +#define DP_TEST_V_TOTAL_LO 0x225 + +#define DP_TEST_H_START_HI 0x226 +#define DP_TEST_H_START_LO 0x227 + +#define DP_TEST_V_START_HI 0x228 +#define DP_TEST_V_START_LO 0x229 + +#define DP_TEST_HSYNC_HI 0x22A +# define DP_TEST_HSYNC_POLARITY (1 << 7) +# define DP_TEST_HSYNC_WIDTH_HI_MASK (127 << 0) +#define DP_TEST_HSYNC_WIDTH_LO 0x22B + +#define DP_TEST_VSYNC_HI 0x22C +# define DP_TEST_VSYNC_POLARITY (1 << 7) +# define DP_TEST_VSYNC_WIDTH_HI_MASK (127 << 0) +#define DP_TEST_VSYNC_WIDTH_LO 0x22D + +#define DP_TEST_H_WIDTH_HI 0x22E +#define DP_TEST_H_WIDTH_LO 0x22F + +#define DP_TEST_V_HEIGHT_HI 0x230 +#define DP_TEST_V_HEIGHT_LO 0x231 + +#define DP_TEST_MISC0 0x232 +# define DP_TEST_SYNC_CLOCK (1 << 0) +# define DP_TEST_COLOR_FORMAT_MASK (3 << 1) +# define DP_TEST_COLOR_FORMAT_SHIFT 1 +# define DP_COLOR_FORMAT_RGB (0 << 1) +# define DP_COLOR_FORMAT_YCbCr422 (1 << 1) +# define DP_COLOR_FORMAT_YCbCr444 (2 << 1) +# define DP_TEST_DYNAMIC_RANGE_VESA (0 << 3) +# define DP_TEST_DYNAMIC_RANGE_CEA (1 << 3) +# define DP_TEST_YCBCR_COEFFICIENTS (1 << 4) +# define DP_YCBCR_COEFFICIENTS_ITU601 (0 << 4) +# define DP_YCBCR_COEFFICIENTS_ITU709 (1 << 4) +# define DP_TEST_BIT_DEPTH_MASK (7 << 5) +# define DP_TEST_BIT_DEPTH_SHIFT 5 +# define DP_TEST_BIT_DEPTH_6 (0 << 5) +# define DP_TEST_BIT_DEPTH_8 (1 << 5) +# define DP_TEST_BIT_DEPTH_10 (2 << 5) +# define DP_TEST_BIT_DEPTH_12 (3 << 5) +# define DP_TEST_BIT_DEPTH_16 (4 << 5) + +#define DP_TEST_MISC1 0x233 +# define DP_TEST_REFRESH_DENOMINATOR (1 << 0) +# define DP_TEST_INTERLACED (1 << 1) + +#define DP_TEST_REFRESH_RATE_NUMERATOR 0x234 + +#define DP_TEST_MISC0 0x232 + +#define DP_TEST_CRC_R_CR 0x240 +#define DP_TEST_CRC_G_Y 0x242 +#define DP_TEST_CRC_B_CB 0x244 + +#define DP_TEST_SINK_MISC 0x246 +# define DP_TEST_CRC_SUPPORTED (1 << 5) +# define DP_TEST_COUNT_MASK 0xf + +#define DP_PHY_TEST_PATTERN 0x248 +# define DP_PHY_TEST_PATTERN_SEL_MASK 0x7 +# define DP_PHY_TEST_PATTERN_NONE 0x0 +# define DP_PHY_TEST_PATTERN_D10_2 0x1 +# define DP_PHY_TEST_PATTERN_ERROR_COUNT 0x2 +# define DP_PHY_TEST_PATTERN_PRBS7 0x3 +# define DP_PHY_TEST_PATTERN_80BIT_CUSTOM 0x4 +# define DP_PHY_TEST_PATTERN_CP2520 0x5 + +#define DP_PHY_SQUARE_PATTERN 0x249 + +#define DP_TEST_HBR2_SCRAMBLER_RESET 0x24A +#define DP_TEST_80BIT_CUSTOM_PATTERN_7_0 0x250 +#define DP_TEST_80BIT_CUSTOM_PATTERN_15_8 0x251 +#define DP_TEST_80BIT_CUSTOM_PATTERN_23_16 0x252 +#define DP_TEST_80BIT_CUSTOM_PATTERN_31_24 0x253 +#define DP_TEST_80BIT_CUSTOM_PATTERN_39_32 0x254 +#define DP_TEST_80BIT_CUSTOM_PATTERN_47_40 0x255 +#define DP_TEST_80BIT_CUSTOM_PATTERN_55_48 0x256 +#define DP_TEST_80BIT_CUSTOM_PATTERN_63_56 0x257 +#define DP_TEST_80BIT_CUSTOM_PATTERN_71_64 0x258 +#define DP_TEST_80BIT_CUSTOM_PATTERN_79_72 0x259 + +#define DP_TEST_RESPONSE 0x260 +# define DP_TEST_ACK (1 << 0) +# define DP_TEST_NAK (1 << 1) +# define DP_TEST_EDID_CHECKSUM_WRITE (1 << 2) + +#define DP_TEST_EDID_CHECKSUM 0x261 + +#define DP_TEST_SINK 0x270 +# define DP_TEST_SINK_START (1 << 0) +#define DP_TEST_AUDIO_MODE 0x271 +#define DP_TEST_AUDIO_PATTERN_TYPE 0x272 +#define DP_TEST_AUDIO_PERIOD_CH1 0x273 +#define DP_TEST_AUDIO_PERIOD_CH2 0x274 +#define DP_TEST_AUDIO_PERIOD_CH3 0x275 +#define DP_TEST_AUDIO_PERIOD_CH4 0x276 +#define DP_TEST_AUDIO_PERIOD_CH5 0x277 +#define DP_TEST_AUDIO_PERIOD_CH6 0x278 +#define DP_TEST_AUDIO_PERIOD_CH7 0x279 +#define DP_TEST_AUDIO_PERIOD_CH8 0x27A + +#define DP_FEC_STATUS 0x280 /* 1.4 */ +# define DP_FEC_DECODE_EN_DETECTED (1 << 0) +# define DP_FEC_DECODE_DIS_DETECTED (1 << 1) + +#define DP_FEC_ERROR_COUNT_LSB 0x0281 /* 1.4 */ + +#define DP_FEC_ERROR_COUNT_MSB 0x0282 /* 1.4 */ +# define DP_FEC_ERROR_COUNT_MASK 0x7F +# define DP_FEC_ERR_COUNT_VALID (1 << 7) + +#define DP_PAYLOAD_TABLE_UPDATE_STATUS 0x2c0 /* 1.2 MST */ +# define DP_PAYLOAD_TABLE_UPDATED (1 << 0) +# define DP_PAYLOAD_ACT_HANDLED (1 << 1) + +#define DP_VC_PAYLOAD_ID_SLOT_1 0x2c1 /* 1.2 MST */ +/* up to ID_SLOT_63 at 0x2ff */ + +/* Source Device-specific */ +#define DP_SOURCE_OUI 0x300 + +/* Sink Device-specific */ +#define DP_SINK_OUI 0x400 + +/* Branch Device-specific */ +#define DP_BRANCH_OUI 0x500 +#define DP_BRANCH_ID 0x503 +#define DP_BRANCH_REVISION_START 0x509 +#define DP_BRANCH_HW_REV 0x509 +#define DP_BRANCH_SW_REV 0x50A + +/* Link/Sink Device Power Control */ +#define DP_SET_POWER 0x600 +# define DP_SET_POWER_D0 0x1 +# define DP_SET_POWER_D3 0x2 +# define DP_SET_POWER_MASK 0x3 +# define DP_SET_POWER_D3_AUX_ON 0x5 + +/* eDP-specific */ +#define DP_EDP_DPCD_REV 0x700 /* eDP 1.2 */ +# define DP_EDP_11 0x00 +# define DP_EDP_12 0x01 +# define DP_EDP_13 0x02 +# define DP_EDP_14 0x03 +# define DP_EDP_14a 0x04 /* eDP 1.4a */ +# define DP_EDP_14b 0x05 /* eDP 1.4b */ + +#define DP_EDP_GENERAL_CAP_1 0x701 +# define DP_EDP_TCON_BACKLIGHT_ADJUSTMENT_CAP (1 << 0) +# define DP_EDP_BACKLIGHT_PIN_ENABLE_CAP (1 << 1) +# define DP_EDP_BACKLIGHT_AUX_ENABLE_CAP (1 << 2) +# define DP_EDP_PANEL_SELF_TEST_PIN_ENABLE_CAP (1 << 3) +# define DP_EDP_PANEL_SELF_TEST_AUX_ENABLE_CAP (1 << 4) +# define DP_EDP_FRC_ENABLE_CAP (1 << 5) +# define DP_EDP_COLOR_ENGINE_CAP (1 << 6) +# define DP_EDP_SET_POWER_CAP (1 << 7) + +#define DP_EDP_BACKLIGHT_ADJUSTMENT_CAP 0x702 +# define DP_EDP_BACKLIGHT_BRIGHTNESS_PWM_PIN_CAP (1 << 0) +# define DP_EDP_BACKLIGHT_BRIGHTNESS_AUX_SET_CAP (1 << 1) +# define DP_EDP_BACKLIGHT_BRIGHTNESS_BYTE_COUNT (1 << 2) +# define DP_EDP_BACKLIGHT_AUX_PWM_PRODUCT_CAP (1 << 3) +# define DP_EDP_BACKLIGHT_FREQ_PWM_PIN_PASSTHRU_CAP (1 << 4) +# define DP_EDP_BACKLIGHT_FREQ_AUX_SET_CAP (1 << 5) +# define DP_EDP_DYNAMIC_BACKLIGHT_CAP (1 << 6) +# define DP_EDP_VBLANK_BACKLIGHT_UPDATE_CAP (1 << 7) + +#define DP_EDP_GENERAL_CAP_2 0x703 +# define DP_EDP_OVERDRIVE_ENGINE_ENABLED (1 << 0) + +#define DP_EDP_GENERAL_CAP_3 0x704 /* eDP 1.4 */ +# define DP_EDP_X_REGION_CAP_MASK (0xf << 0) +# define DP_EDP_X_REGION_CAP_SHIFT 0 +# define DP_EDP_Y_REGION_CAP_MASK (0xf << 4) +# define DP_EDP_Y_REGION_CAP_SHIFT 4 + +#define DP_EDP_DISPLAY_CONTROL_REGISTER 0x720 +# define DP_EDP_BACKLIGHT_ENABLE (1 << 0) +# define DP_EDP_BLACK_VIDEO_ENABLE (1 << 1) +# define DP_EDP_FRC_ENABLE (1 << 2) +# define DP_EDP_COLOR_ENGINE_ENABLE (1 << 3) +# define DP_EDP_VBLANK_BACKLIGHT_UPDATE_ENABLE (1 << 7) + +#define DP_EDP_BACKLIGHT_MODE_SET_REGISTER 0x721 +# define DP_EDP_BACKLIGHT_CONTROL_MODE_MASK (3 << 0) +# define DP_EDP_BACKLIGHT_CONTROL_MODE_PWM (0 << 0) +# define DP_EDP_BACKLIGHT_CONTROL_MODE_PRESET (1 << 0) +# define DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD (2 << 0) +# define DP_EDP_BACKLIGHT_CONTROL_MODE_PRODUCT (3 << 0) +# define DP_EDP_BACKLIGHT_FREQ_PWM_PIN_PASSTHRU_ENABLE (1 << 2) +# define DP_EDP_BACKLIGHT_FREQ_AUX_SET_ENABLE (1 << 3) +# define DP_EDP_DYNAMIC_BACKLIGHT_ENABLE (1 << 4) +# define DP_EDP_REGIONAL_BACKLIGHT_ENABLE (1 << 5) +# define DP_EDP_UPDATE_REGION_BRIGHTNESS (1 << 6) /* eDP 1.4 */ + +#define DP_EDP_BACKLIGHT_BRIGHTNESS_MSB 0x722 +#define DP_EDP_BACKLIGHT_BRIGHTNESS_LSB 0x723 + +#define DP_EDP_PWMGEN_BIT_COUNT 0x724 +#define DP_EDP_PWMGEN_BIT_COUNT_CAP_MIN 0x725 +#define DP_EDP_PWMGEN_BIT_COUNT_CAP_MAX 0x726 +# define DP_EDP_PWMGEN_BIT_COUNT_MASK (0x1f << 0) + +#define DP_EDP_BACKLIGHT_CONTROL_STATUS 0x727 + +#define DP_EDP_BACKLIGHT_FREQ_SET 0x728 +# define DP_EDP_BACKLIGHT_FREQ_BASE_KHZ 27000 + +#define DP_EDP_BACKLIGHT_FREQ_CAP_MIN_MSB 0x72a +#define DP_EDP_BACKLIGHT_FREQ_CAP_MIN_MID 0x72b +#define DP_EDP_BACKLIGHT_FREQ_CAP_MIN_LSB 0x72c + +#define DP_EDP_BACKLIGHT_FREQ_CAP_MAX_MSB 0x72d +#define DP_EDP_BACKLIGHT_FREQ_CAP_MAX_MID 0x72e +#define DP_EDP_BACKLIGHT_FREQ_CAP_MAX_LSB 0x72f + +#define DP_EDP_DBC_MINIMUM_BRIGHTNESS_SET 0x732 +#define DP_EDP_DBC_MAXIMUM_BRIGHTNESS_SET 0x733 + +#define DP_EDP_REGIONAL_BACKLIGHT_BASE 0x740 /* eDP 1.4 */ +#define DP_EDP_REGIONAL_BACKLIGHT_0 0x741 /* eDP 1.4 */ + +#define DP_EDP_MSO_LINK_CAPABILITIES 0x7a4 /* eDP 1.4 */ +# define DP_EDP_MSO_NUMBER_OF_LINKS_MASK (7 << 0) +# define DP_EDP_MSO_NUMBER_OF_LINKS_SHIFT 0 +# define DP_EDP_MSO_INDEPENDENT_LINK_BIT (1 << 3) + +/* Sideband MSG Buffers */ +#define DP_SIDEBAND_MSG_DOWN_REQ_BASE 0x1000 /* 1.2 MST */ +#define DP_SIDEBAND_MSG_UP_REP_BASE 0x1200 /* 1.2 MST */ +#define DP_SIDEBAND_MSG_DOWN_REP_BASE 0x1400 /* 1.2 MST */ +#define DP_SIDEBAND_MSG_UP_REQ_BASE 0x1600 /* 1.2 MST */ + +/* DPRX Event Status Indicator */ +#define DP_SINK_COUNT_ESI 0x2002 /* same as 0x200 */ +#define DP_DEVICE_SERVICE_IRQ_VECTOR_ESI0 0x2003 /* same as 0x201 */ + +#define DP_DEVICE_SERVICE_IRQ_VECTOR_ESI1 0x2004 /* 1.2 */ +# define DP_RX_GTC_MSTR_REQ_STATUS_CHANGE (1 << 0) +# define DP_LOCK_ACQUISITION_REQUEST (1 << 1) +# define DP_CEC_IRQ (1 << 2) + +#define DP_LINK_SERVICE_IRQ_VECTOR_ESI0 0x2005 /* 1.2 */ +# define RX_CAP_CHANGED (1 << 0) +# define LINK_STATUS_CHANGED (1 << 1) +# define STREAM_STATUS_CHANGED (1 << 2) +# define HDMI_LINK_STATUS_CHANGED (1 << 3) +# define CONNECTED_OFF_ENTRY_REQUESTED (1 << 4) + +#define DP_PSR_ERROR_STATUS 0x2006 /* XXX 1.2? */ +# define DP_PSR_LINK_CRC_ERROR (1 << 0) +# define DP_PSR_RFB_STORAGE_ERROR (1 << 1) +# define DP_PSR_VSC_SDP_UNCORRECTABLE_ERROR (1 << 2) /* eDP 1.4 */ + +#define DP_PSR_ESI 0x2007 /* XXX 1.2? */ +# define DP_PSR_CAPS_CHANGE (1 << 0) + +#define DP_PSR_STATUS 0x2008 /* XXX 1.2? */ +# define DP_PSR_SINK_INACTIVE 0 +# define DP_PSR_SINK_ACTIVE_SRC_SYNCED 1 +# define DP_PSR_SINK_ACTIVE_RFB 2 +# define DP_PSR_SINK_ACTIVE_SINK_SYNCED 3 +# define DP_PSR_SINK_ACTIVE_RESYNC 4 +# define DP_PSR_SINK_INTERNAL_ERROR 7 +# define DP_PSR_SINK_STATE_MASK 0x07 + +#define DP_SYNCHRONIZATION_LATENCY_IN_SINK 0x2009 /* edp 1.4 */ +# define DP_MAX_RESYNC_FRAME_COUNT_MASK (0xf << 0) +# define DP_MAX_RESYNC_FRAME_COUNT_SHIFT 0 +# define DP_LAST_ACTUAL_SYNCHRONIZATION_LATENCY_MASK (0xf << 4) +# define DP_LAST_ACTUAL_SYNCHRONIZATION_LATENCY_SHIFT 4 + +#define DP_LAST_RECEIVED_PSR_SDP 0x200a /* eDP 1.2 */ +# define DP_PSR_STATE_BIT (1 << 0) /* eDP 1.2 */ +# define DP_UPDATE_RFB_BIT (1 << 1) /* eDP 1.2 */ +# define DP_CRC_VALID_BIT (1 << 2) /* eDP 1.2 */ +# define DP_SU_VALID (1 << 3) /* eDP 1.4 */ +# define DP_FIRST_SCAN_LINE_SU_REGION (1 << 4) /* eDP 1.4 */ +# define DP_LAST_SCAN_LINE_SU_REGION (1 << 5) /* eDP 1.4 */ +# define DP_Y_COORDINATE_VALID (1 << 6) /* eDP 1.4a */ + +#define DP_RECEIVER_ALPM_STATUS 0x200b /* eDP 1.4 */ +# define DP_ALPM_LOCK_TIMEOUT_ERROR (1 << 0) + +#define DP_LANE0_1_STATUS_ESI 0x200c /* status same as 0x202 */ +#define DP_LANE2_3_STATUS_ESI 0x200d /* status same as 0x203 */ +#define DP_LANE_ALIGN_STATUS_UPDATED_ESI 0x200e /* status same as 0x204 */ +#define DP_SINK_STATUS_ESI 0x200f /* status same as 0x205 */ + +/* Extended Receiver Capability: See DP_DPCD_REV for definitions */ +#define DP_DP13_DPCD_REV 0x2200 + +#define DP_DPRX_FEATURE_ENUMERATION_LIST 0x2210 /* DP 1.3 */ +# define DP_GTC_CAP (1 << 0) /* DP 1.3 */ +# define DP_SST_SPLIT_SDP_CAP (1 << 1) /* DP 1.4 */ +# define DP_AV_SYNC_CAP (1 << 2) /* DP 1.3 */ +# define DP_VSC_SDP_EXT_FOR_COLORIMETRY_SUPPORTED (1 << 3) /* DP 1.3 */ +# define DP_VSC_EXT_VESA_SDP_SUPPORTED (1 << 4) /* DP 1.4 */ +# define DP_VSC_EXT_VESA_SDP_CHAINING_SUPPORTED (1 << 5) /* DP 1.4 */ +# define DP_VSC_EXT_CEA_SDP_SUPPORTED (1 << 6) /* DP 1.4 */ +# define DP_VSC_EXT_CEA_SDP_CHAINING_SUPPORTED (1 << 7) /* DP 1.4 */ + +#define DP_128B132B_SUPPORTED_LINK_RATES 0x2215 /* 2.0 */ +# define DP_UHBR10 (1 << 0) +# define DP_UHBR20 (1 << 1) +# define DP_UHBR13_5 (1 << 2) + +#define DP_128B132B_TRAINING_AUX_RD_INTERVAL 0x2216 /* 2.0 */ +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_1MS_UNIT (1 << 7) +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_MASK 0x7f +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_400_US 0x00 +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_4_MS 0x01 +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_8_MS 0x02 +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_12_MS 0x03 +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_16_MS 0x04 +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_32_MS 0x05 +# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_64_MS 0x06 + +#define DP_TEST_264BIT_CUSTOM_PATTERN_7_0 0x2230 +#define DP_TEST_264BIT_CUSTOM_PATTERN_263_256 0x2250 + +/* DSC Extended Capability Branch Total DSC Resources */ +#define DP_DSC_SUPPORT_AND_DSC_DECODER_COUNT 0x2260 /* 2.0 */ +# define DP_DSC_DECODER_COUNT_MASK (0b111 << 5) +# define DP_DSC_DECODER_COUNT_SHIFT 5 +#define DP_DSC_MAX_SLICE_COUNT_AND_AGGREGATION_0 0x2270 /* 2.0 */ +# define DP_DSC_DECODER_0_MAXIMUM_SLICE_COUNT_MASK (1 << 0) +# define DP_DSC_DECODER_0_AGGREGATION_SUPPORT_MASK (0b111 << 1) +# define DP_DSC_DECODER_0_AGGREGATION_SUPPORT_SHIFT 1 + +/* Protocol Converter Extension */ +/* HDMI CEC tunneling over AUX DP 1.3 section 5.3.3.3.1 DPCD 1.4+ */ +#define DP_CEC_TUNNELING_CAPABILITY 0x3000 +# define DP_CEC_TUNNELING_CAPABLE (1 << 0) +# define DP_CEC_SNOOPING_CAPABLE (1 << 1) +# define DP_CEC_MULTIPLE_LA_CAPABLE (1 << 2) + +#define DP_CEC_TUNNELING_CONTROL 0x3001 +# define DP_CEC_TUNNELING_ENABLE (1 << 0) +# define DP_CEC_SNOOPING_ENABLE (1 << 1) + +#define DP_CEC_RX_MESSAGE_INFO 0x3002 +# define DP_CEC_RX_MESSAGE_LEN_MASK (0xf << 0) +# define DP_CEC_RX_MESSAGE_LEN_SHIFT 0 +# define DP_CEC_RX_MESSAGE_HPD_STATE (1 << 4) +# define DP_CEC_RX_MESSAGE_HPD_LOST (1 << 5) +# define DP_CEC_RX_MESSAGE_ACKED (1 << 6) +# define DP_CEC_RX_MESSAGE_ENDED (1 << 7) + +#define DP_CEC_TX_MESSAGE_INFO 0x3003 +# define DP_CEC_TX_MESSAGE_LEN_MASK (0xf << 0) +# define DP_CEC_TX_MESSAGE_LEN_SHIFT 0 +# define DP_CEC_TX_RETRY_COUNT_MASK (0x7 << 4) +# define DP_CEC_TX_RETRY_COUNT_SHIFT 4 +# define DP_CEC_TX_MESSAGE_SEND (1 << 7) + +#define DP_CEC_TUNNELING_IRQ_FLAGS 0x3004 +# define DP_CEC_RX_MESSAGE_INFO_VALID (1 << 0) +# define DP_CEC_RX_MESSAGE_OVERFLOW (1 << 1) +# define DP_CEC_TX_MESSAGE_SENT (1 << 4) +# define DP_CEC_TX_LINE_ERROR (1 << 5) +# define DP_CEC_TX_ADDRESS_NACK_ERROR (1 << 6) +# define DP_CEC_TX_DATA_NACK_ERROR (1 << 7) + +#define DP_CEC_LOGICAL_ADDRESS_MASK 0x300E /* 0x300F word */ +# define DP_CEC_LOGICAL_ADDRESS_0 (1 << 0) +# define DP_CEC_LOGICAL_ADDRESS_1 (1 << 1) +# define DP_CEC_LOGICAL_ADDRESS_2 (1 << 2) +# define DP_CEC_LOGICAL_ADDRESS_3 (1 << 3) +# define DP_CEC_LOGICAL_ADDRESS_4 (1 << 4) +# define DP_CEC_LOGICAL_ADDRESS_5 (1 << 5) +# define DP_CEC_LOGICAL_ADDRESS_6 (1 << 6) +# define DP_CEC_LOGICAL_ADDRESS_7 (1 << 7) +#define DP_CEC_LOGICAL_ADDRESS_MASK_2 0x300F /* 0x300E word */ +# define DP_CEC_LOGICAL_ADDRESS_8 (1 << 0) +# define DP_CEC_LOGICAL_ADDRESS_9 (1 << 1) +# define DP_CEC_LOGICAL_ADDRESS_10 (1 << 2) +# define DP_CEC_LOGICAL_ADDRESS_11 (1 << 3) +# define DP_CEC_LOGICAL_ADDRESS_12 (1 << 4) +# define DP_CEC_LOGICAL_ADDRESS_13 (1 << 5) +# define DP_CEC_LOGICAL_ADDRESS_14 (1 << 6) +# define DP_CEC_LOGICAL_ADDRESS_15 (1 << 7) + +#define DP_CEC_RX_MESSAGE_BUFFER 0x3010 +#define DP_CEC_TX_MESSAGE_BUFFER 0x3020 +#define DP_CEC_MESSAGE_BUFFER_LENGTH 0x10 + +/* PCON CONFIGURE-1 FRL FOR HDMI SINK */ +#define DP_PCON_HDMI_LINK_CONFIG_1 0x305A +# define DP_PCON_ENABLE_MAX_FRL_BW (7 << 0) +# define DP_PCON_ENABLE_MAX_BW_0GBPS 0 +# define DP_PCON_ENABLE_MAX_BW_9GBPS 1 +# define DP_PCON_ENABLE_MAX_BW_18GBPS 2 +# define DP_PCON_ENABLE_MAX_BW_24GBPS 3 +# define DP_PCON_ENABLE_MAX_BW_32GBPS 4 +# define DP_PCON_ENABLE_MAX_BW_40GBPS 5 +# define DP_PCON_ENABLE_MAX_BW_48GBPS 6 +# define DP_PCON_ENABLE_SOURCE_CTL_MODE (1 << 3) +# define DP_PCON_ENABLE_CONCURRENT_LINK (1 << 4) +# define DP_PCON_ENABLE_SEQUENTIAL_LINK (0 << 4) +# define DP_PCON_ENABLE_LINK_FRL_MODE (1 << 5) +# define DP_PCON_ENABLE_HPD_READY (1 << 6) +# define DP_PCON_ENABLE_HDMI_LINK (1 << 7) + +/* PCON CONFIGURE-2 FRL FOR HDMI SINK */ +#define DP_PCON_HDMI_LINK_CONFIG_2 0x305B +# define DP_PCON_MAX_LINK_BW_MASK (0x3F << 0) +# define DP_PCON_FRL_BW_MASK_9GBPS (1 << 0) +# define DP_PCON_FRL_BW_MASK_18GBPS (1 << 1) +# define DP_PCON_FRL_BW_MASK_24GBPS (1 << 2) +# define DP_PCON_FRL_BW_MASK_32GBPS (1 << 3) +# define DP_PCON_FRL_BW_MASK_40GBPS (1 << 4) +# define DP_PCON_FRL_BW_MASK_48GBPS (1 << 5) +# define DP_PCON_FRL_LINK_TRAIN_EXTENDED (1 << 6) +# define DP_PCON_FRL_LINK_TRAIN_NORMAL (0 << 6) + +/* PCON HDMI LINK STATUS */ +#define DP_PCON_HDMI_TX_LINK_STATUS 0x303B +# define DP_PCON_HDMI_TX_LINK_ACTIVE (1 << 0) +# define DP_PCON_FRL_READY (1 << 1) + +/* PCON HDMI POST FRL STATUS */ +#define DP_PCON_HDMI_POST_FRL_STATUS 0x3036 +# define DP_PCON_HDMI_LINK_MODE (1 << 0) +# define DP_PCON_HDMI_MODE_TMDS 0 +# define DP_PCON_HDMI_MODE_FRL 1 +# define DP_PCON_HDMI_FRL_TRAINED_BW (0x3F << 1) +# define DP_PCON_FRL_TRAINED_BW_9GBPS (1 << 1) +# define DP_PCON_FRL_TRAINED_BW_18GBPS (1 << 2) +# define DP_PCON_FRL_TRAINED_BW_24GBPS (1 << 3) +# define DP_PCON_FRL_TRAINED_BW_32GBPS (1 << 4) +# define DP_PCON_FRL_TRAINED_BW_40GBPS (1 << 5) +# define DP_PCON_FRL_TRAINED_BW_48GBPS (1 << 6) + +#define DP_PROTOCOL_CONVERTER_CONTROL_0 0x3050 /* DP 1.3 */ +# define DP_HDMI_DVI_OUTPUT_CONFIG (1 << 0) /* DP 1.3 */ +#define DP_PROTOCOL_CONVERTER_CONTROL_1 0x3051 /* DP 1.3 */ +# define DP_CONVERSION_TO_YCBCR420_ENABLE (1 << 0) /* DP 1.3 */ +# define DP_HDMI_EDID_PROCESSING_DISABLE (1 << 1) /* DP 1.4 */ +# define DP_HDMI_AUTONOMOUS_SCRAMBLING_DISABLE (1 << 2) /* DP 1.4 */ +# define DP_HDMI_FORCE_SCRAMBLING (1 << 3) /* DP 1.4 */ +#define DP_PROTOCOL_CONVERTER_CONTROL_2 0x3052 /* DP 1.3 */ +# define DP_CONVERSION_TO_YCBCR422_ENABLE (1 << 0) /* DP 1.3 */ +# define DP_PCON_ENABLE_DSC_ENCODER (1 << 1) +# define DP_PCON_ENCODER_PPS_OVERRIDE_MASK (0x3 << 2) +# define DP_PCON_ENC_PPS_OVERRIDE_DISABLED 0 +# define DP_PCON_ENC_PPS_OVERRIDE_EN_PARAMS 1 +# define DP_PCON_ENC_PPS_OVERRIDE_EN_BUFFER 2 +# define DP_CONVERSION_RGB_YCBCR_MASK (7 << 4) +# define DP_CONVERSION_BT601_RGB_YCBCR_ENABLE (1 << 4) +# define DP_CONVERSION_BT709_RGB_YCBCR_ENABLE (1 << 5) +# define DP_CONVERSION_BT2020_RGB_YCBCR_ENABLE (1 << 6) + +/* PCON Downstream HDMI ERROR Status per Lane */ +#define DP_PCON_HDMI_ERROR_STATUS_LN0 0x3037 +#define DP_PCON_HDMI_ERROR_STATUS_LN1 0x3038 +#define DP_PCON_HDMI_ERROR_STATUS_LN2 0x3039 +#define DP_PCON_HDMI_ERROR_STATUS_LN3 0x303A +# define DP_PCON_HDMI_ERROR_COUNT_MASK (0x7 << 0) +# define DP_PCON_HDMI_ERROR_COUNT_THREE_PLUS (1 << 0) +# define DP_PCON_HDMI_ERROR_COUNT_TEN_PLUS (1 << 1) +# define DP_PCON_HDMI_ERROR_COUNT_HUNDRED_PLUS (1 << 2) + +/* PCON HDMI CONFIG PPS Override Buffer + * Valid Offsets to be added to Base : 0-127 + */ +#define DP_PCON_HDMI_PPS_OVERRIDE_BASE 0x3100 + +/* PCON HDMI CONFIG PPS Override Parameter: Slice height + * Offset-0 8LSBs of the Slice height. + * Offset-1 8MSBs of the Slice height. + */ +#define DP_PCON_HDMI_PPS_OVRD_SLICE_HEIGHT 0x3180 + +/* PCON HDMI CONFIG PPS Override Parameter: Slice width + * Offset-0 8LSBs of the Slice width. + * Offset-1 8MSBs of the Slice width. + */ +#define DP_PCON_HDMI_PPS_OVRD_SLICE_WIDTH 0x3182 + +/* PCON HDMI CONFIG PPS Override Parameter: bits_per_pixel + * Offset-0 8LSBs of the bits_per_pixel. + * Offset-1 2MSBs of the bits_per_pixel. + */ +#define DP_PCON_HDMI_PPS_OVRD_BPP 0x3184 + +/* HDCP 1.3 and HDCP 2.2 */ +#define DP_AUX_HDCP_BKSV 0x68000 +#define DP_AUX_HDCP_RI_PRIME 0x68005 +#define DP_AUX_HDCP_AKSV 0x68007 +#define DP_AUX_HDCP_AN 0x6800C +#define DP_AUX_HDCP_V_PRIME(h) (0x68014 + h * 4) +#define DP_AUX_HDCP_BCAPS 0x68028 +# define DP_BCAPS_REPEATER_PRESENT BIT(1) +# define DP_BCAPS_HDCP_CAPABLE BIT(0) +#define DP_AUX_HDCP_BSTATUS 0x68029 +# define DP_BSTATUS_REAUTH_REQ BIT(3) +# define DP_BSTATUS_LINK_FAILURE BIT(2) +# define DP_BSTATUS_R0_PRIME_READY BIT(1) +# define DP_BSTATUS_READY BIT(0) +#define DP_AUX_HDCP_BINFO 0x6802A +#define DP_AUX_HDCP_KSV_FIFO 0x6802C +#define DP_AUX_HDCP_AINFO 0x6803B + +/* DP HDCP2.2 parameter offsets in DPCD address space */ +#define DP_HDCP_2_2_REG_RTX_OFFSET 0x69000 +#define DP_HDCP_2_2_REG_TXCAPS_OFFSET 0x69008 +#define DP_HDCP_2_2_REG_CERT_RX_OFFSET 0x6900B +#define DP_HDCP_2_2_REG_RRX_OFFSET 0x69215 +#define DP_HDCP_2_2_REG_RX_CAPS_OFFSET 0x6921D +#define DP_HDCP_2_2_REG_EKPUB_KM_OFFSET 0x69220 +#define DP_HDCP_2_2_REG_EKH_KM_WR_OFFSET 0x692A0 +#define DP_HDCP_2_2_REG_M_OFFSET 0x692B0 +#define DP_HDCP_2_2_REG_HPRIME_OFFSET 0x692C0 +#define DP_HDCP_2_2_REG_EKH_KM_RD_OFFSET 0x692E0 +#define DP_HDCP_2_2_REG_RN_OFFSET 0x692F0 +#define DP_HDCP_2_2_REG_LPRIME_OFFSET 0x692F8 +#define DP_HDCP_2_2_REG_EDKEY_KS_OFFSET 0x69318 +#define DP_HDCP_2_2_REG_RIV_OFFSET 0x69328 +#define DP_HDCP_2_2_REG_RXINFO_OFFSET 0x69330 +#define DP_HDCP_2_2_REG_SEQ_NUM_V_OFFSET 0x69332 +#define DP_HDCP_2_2_REG_VPRIME_OFFSET 0x69335 +#define DP_HDCP_2_2_REG_RECV_ID_LIST_OFFSET 0x69345 +#define DP_HDCP_2_2_REG_V_OFFSET 0x693E0 +#define DP_HDCP_2_2_REG_SEQ_NUM_M_OFFSET 0x693F0 +#define DP_HDCP_2_2_REG_K_OFFSET 0x693F3 +#define DP_HDCP_2_2_REG_STREAM_ID_TYPE_OFFSET 0x693F5 +#define DP_HDCP_2_2_REG_MPRIME_OFFSET 0x69473 +#define DP_HDCP_2_2_REG_RXSTATUS_OFFSET 0x69493 +#define DP_HDCP_2_2_REG_STREAM_TYPE_OFFSET 0x69494 +#define DP_HDCP_2_2_REG_DBG_OFFSET 0x69518 + +/* LTTPR: Link Training (LT)-tunable PHY Repeaters */ +#define DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV 0xf0000 /* 1.3 */ +#define DP_MAX_LINK_RATE_PHY_REPEATER 0xf0001 /* 1.4a */ +#define DP_PHY_REPEATER_CNT 0xf0002 /* 1.3 */ +#define DP_PHY_REPEATER_MODE 0xf0003 /* 1.3 */ +#define DP_MAX_LANE_COUNT_PHY_REPEATER 0xf0004 /* 1.4a */ +#define DP_Repeater_FEC_CAPABILITY 0xf0004 /* 1.4 */ +#define DP_PHY_REPEATER_EXTENDED_WAIT_TIMEOUT 0xf0005 /* 1.4a */ +#define DP_MAIN_LINK_CHANNEL_CODING_PHY_REPEATER 0xf0006 /* 2.0 */ +# define DP_PHY_REPEATER_128B132B_SUPPORTED (1 << 0) +/* See DP_128B132B_SUPPORTED_LINK_RATES for values */ +#define DP_PHY_REPEATER_128B132B_RATES 0xf0007 /* 2.0 */ +#define DP_PHY_REPEATER_EQ_DONE 0xf0008 /* 2.0 E11 */ + +enum drm_dp_phy { + DP_PHY_DPRX, + + DP_PHY_LTTPR1, + DP_PHY_LTTPR2, + DP_PHY_LTTPR3, + DP_PHY_LTTPR4, + DP_PHY_LTTPR5, + DP_PHY_LTTPR6, + DP_PHY_LTTPR7, + DP_PHY_LTTPR8, + + DP_MAX_LTTPR_COUNT = DP_PHY_LTTPR8, +}; + +#define DP_PHY_LTTPR(i) (DP_PHY_LTTPR1 + (i)) + +#define __DP_LTTPR1_BASE 0xf0010 /* 1.3 */ +#define __DP_LTTPR2_BASE 0xf0060 /* 1.3 */ +#define DP_LTTPR_BASE(dp_phy) \ + (__DP_LTTPR1_BASE + (__DP_LTTPR2_BASE - __DP_LTTPR1_BASE) * \ + ((dp_phy) - DP_PHY_LTTPR1)) + +#define DP_LTTPR_REG(dp_phy, lttpr1_reg) \ + (DP_LTTPR_BASE(dp_phy) - DP_LTTPR_BASE(DP_PHY_LTTPR1) + (lttpr1_reg)) + +#define DP_TRAINING_PATTERN_SET_PHY_REPEATER1 0xf0010 /* 1.3 */ +#define DP_TRAINING_PATTERN_SET_PHY_REPEATER(dp_phy) \ + DP_LTTPR_REG(dp_phy, DP_TRAINING_PATTERN_SET_PHY_REPEATER1) + +#define DP_TRAINING_LANE0_SET_PHY_REPEATER1 0xf0011 /* 1.3 */ +#define DP_TRAINING_LANE0_SET_PHY_REPEATER(dp_phy) \ + DP_LTTPR_REG(dp_phy, DP_TRAINING_LANE0_SET_PHY_REPEATER1) + +#define DP_TRAINING_LANE1_SET_PHY_REPEATER1 0xf0012 /* 1.3 */ +#define DP_TRAINING_LANE2_SET_PHY_REPEATER1 0xf0013 /* 1.3 */ +#define DP_TRAINING_LANE3_SET_PHY_REPEATER1 0xf0014 /* 1.3 */ +#define DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1 0xf0020 /* 1.4a */ +#define DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER(dp_phy) \ + DP_LTTPR_REG(dp_phy, DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1) + +#define DP_TRANSMITTER_CAPABILITY_PHY_REPEATER1 0xf0021 /* 1.4a */ +# define DP_VOLTAGE_SWING_LEVEL_3_SUPPORTED BIT(0) +# define DP_PRE_EMPHASIS_LEVEL_3_SUPPORTED BIT(1) + +#define DP_128B132B_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1 0xf0022 /* 2.0 */ +#define DP_128B132B_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER(dp_phy) \ + DP_LTTPR_REG(dp_phy, DP_128B132B_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1) +/* see DP_128B132B_TRAINING_AUX_RD_INTERVAL for values */ + +#define DP_LANE0_1_STATUS_PHY_REPEATER1 0xf0030 /* 1.3 */ +#define DP_LANE0_1_STATUS_PHY_REPEATER(dp_phy) \ + DP_LTTPR_REG(dp_phy, DP_LANE0_1_STATUS_PHY_REPEATER1) + +#define DP_LANE2_3_STATUS_PHY_REPEATER1 0xf0031 /* 1.3 */ + +#define DP_LANE_ALIGN_STATUS_UPDATED_PHY_REPEATER1 0xf0032 /* 1.3 */ +#define DP_ADJUST_REQUEST_LANE0_1_PHY_REPEATER1 0xf0033 /* 1.3 */ +#define DP_ADJUST_REQUEST_LANE2_3_PHY_REPEATER1 0xf0034 /* 1.3 */ +#define DP_SYMBOL_ERROR_COUNT_LANE0_PHY_REPEATER1 0xf0035 /* 1.3 */ +#define DP_SYMBOL_ERROR_COUNT_LANE1_PHY_REPEATER1 0xf0037 /* 1.3 */ +#define DP_SYMBOL_ERROR_COUNT_LANE2_PHY_REPEATER1 0xf0039 /* 1.3 */ +#define DP_SYMBOL_ERROR_COUNT_LANE3_PHY_REPEATER1 0xf003b /* 1.3 */ + +#define __DP_FEC1_BASE 0xf0290 /* 1.4 */ +#define __DP_FEC2_BASE 0xf0298 /* 1.4 */ +#define DP_FEC_BASE(dp_phy) \ + (__DP_FEC1_BASE + ((__DP_FEC2_BASE - __DP_FEC1_BASE) * \ + ((dp_phy) - DP_PHY_LTTPR1))) + +#define DP_FEC_REG(dp_phy, fec1_reg) \ + (DP_FEC_BASE(dp_phy) - DP_FEC_BASE(DP_PHY_LTTPR1) + fec1_reg) + +#define DP_FEC_STATUS_PHY_REPEATER1 0xf0290 /* 1.4 */ +#define DP_FEC_STATUS_PHY_REPEATER(dp_phy) \ + DP_FEC_REG(dp_phy, DP_FEC_STATUS_PHY_REPEATER1) + +#define DP_FEC_ERROR_COUNT_PHY_REPEATER1 0xf0291 /* 1.4 */ +#define DP_FEC_CAPABILITY_PHY_REPEATER1 0xf0294 /* 1.4a */ + +#define DP_LTTPR_MAX_ADD 0xf02ff /* 1.4 */ + +#define DP_DPCD_MAX_ADD 0xfffff /* 1.4 */ + +/* Repeater modes */ +#define DP_PHY_REPEATER_MODE_TRANSPARENT 0x55 /* 1.3 */ +#define DP_PHY_REPEATER_MODE_NON_TRANSPARENT 0xaa /* 1.3 */ + +/* DP HDCP message start offsets in DPCD address space */ +#define DP_HDCP_2_2_AKE_INIT_OFFSET DP_HDCP_2_2_REG_RTX_OFFSET +#define DP_HDCP_2_2_AKE_SEND_CERT_OFFSET DP_HDCP_2_2_REG_CERT_RX_OFFSET +#define DP_HDCP_2_2_AKE_NO_STORED_KM_OFFSET DP_HDCP_2_2_REG_EKPUB_KM_OFFSET +#define DP_HDCP_2_2_AKE_STORED_KM_OFFSET DP_HDCP_2_2_REG_EKH_KM_WR_OFFSET +#define DP_HDCP_2_2_AKE_SEND_HPRIME_OFFSET DP_HDCP_2_2_REG_HPRIME_OFFSET +#define DP_HDCP_2_2_AKE_SEND_PAIRING_INFO_OFFSET \ + DP_HDCP_2_2_REG_EKH_KM_RD_OFFSET +#define DP_HDCP_2_2_LC_INIT_OFFSET DP_HDCP_2_2_REG_RN_OFFSET +#define DP_HDCP_2_2_LC_SEND_LPRIME_OFFSET DP_HDCP_2_2_REG_LPRIME_OFFSET +#define DP_HDCP_2_2_SKE_SEND_EKS_OFFSET DP_HDCP_2_2_REG_EDKEY_KS_OFFSET +#define DP_HDCP_2_2_REP_SEND_RECVID_LIST_OFFSET DP_HDCP_2_2_REG_RXINFO_OFFSET +#define DP_HDCP_2_2_REP_SEND_ACK_OFFSET DP_HDCP_2_2_REG_V_OFFSET +#define DP_HDCP_2_2_REP_STREAM_MANAGE_OFFSET DP_HDCP_2_2_REG_SEQ_NUM_M_OFFSET +#define DP_HDCP_2_2_REP_STREAM_READY_OFFSET DP_HDCP_2_2_REG_MPRIME_OFFSET + +#define HDCP_2_2_DP_RXSTATUS_LEN 1 +#define HDCP_2_2_DP_RXSTATUS_READY(x) ((x) & BIT(0)) +#define HDCP_2_2_DP_RXSTATUS_H_PRIME(x) ((x) & BIT(1)) +#define HDCP_2_2_DP_RXSTATUS_PAIRING(x) ((x) & BIT(2)) +#define HDCP_2_2_DP_RXSTATUS_REAUTH_REQ(x) ((x) & BIT(3)) +#define HDCP_2_2_DP_RXSTATUS_LINK_FAILED(x) ((x) & BIT(4)) + +/* DP 1.2 Sideband message defines */ +/* peer device type - DP 1.2a Table 2-92 */ +#define DP_PEER_DEVICE_NONE 0x0 +#define DP_PEER_DEVICE_SOURCE_OR_SST 0x1 +#define DP_PEER_DEVICE_MST_BRANCHING 0x2 +#define DP_PEER_DEVICE_SST_SINK 0x3 +#define DP_PEER_DEVICE_DP_LEGACY_CONV 0x4 + +/* DP 1.2 MST sideband request names DP 1.2a Table 2-80 */ +#define DP_GET_MSG_TRANSACTION_VERSION 0x00 /* DP 1.3 */ +#define DP_LINK_ADDRESS 0x01 +#define DP_CONNECTION_STATUS_NOTIFY 0x02 +#define DP_ENUM_PATH_RESOURCES 0x10 +#define DP_ALLOCATE_PAYLOAD 0x11 +#define DP_QUERY_PAYLOAD 0x12 +#define DP_RESOURCE_STATUS_NOTIFY 0x13 +#define DP_CLEAR_PAYLOAD_ID_TABLE 0x14 +#define DP_REMOTE_DPCD_READ 0x20 +#define DP_REMOTE_DPCD_WRITE 0x21 +#define DP_REMOTE_I2C_READ 0x22 +#define DP_REMOTE_I2C_WRITE 0x23 +#define DP_POWER_UP_PHY 0x24 +#define DP_POWER_DOWN_PHY 0x25 +#define DP_SINK_EVENT_NOTIFY 0x30 +#define DP_QUERY_STREAM_ENC_STATUS 0x38 +#define DP_QUERY_STREAM_ENC_STATUS_STATE_NO_EXIST 0 +#define DP_QUERY_STREAM_ENC_STATUS_STATE_INACTIVE 1 +#define DP_QUERY_STREAM_ENC_STATUS_STATE_ACTIVE 2 + +/* DP 1.2 MST sideband reply types */ +#define DP_SIDEBAND_REPLY_ACK 0x00 +#define DP_SIDEBAND_REPLY_NAK 0x01 + +/* DP 1.2 MST sideband nak reasons - table 2.84 */ +#define DP_NAK_WRITE_FAILURE 0x01 +#define DP_NAK_INVALID_READ 0x02 +#define DP_NAK_CRC_FAILURE 0x03 +#define DP_NAK_BAD_PARAM 0x04 +#define DP_NAK_DEFER 0x05 +#define DP_NAK_LINK_FAILURE 0x06 +#define DP_NAK_NO_RESOURCES 0x07 +#define DP_NAK_DPCD_FAIL 0x08 +#define DP_NAK_I2C_NAK 0x09 +#define DP_NAK_ALLOCATE_FAIL 0x0a + +#define MODE_I2C_START 1 +#define MODE_I2C_WRITE 2 +#define MODE_I2C_READ 4 +#define MODE_I2C_STOP 8 + +/* DP 1.2 MST PORTs - Section 2.5.1 v1.2a spec */ +#define DP_MST_PHYSICAL_PORT_0 0 +#define DP_MST_LOGICAL_PORT_0 8 + +#define DP_LINK_CONSTANT_N_VALUE 0x8000 +#define DP_LINK_STATUS_SIZE 6 + +#define DP_BRANCH_OUI_HEADER_SIZE 0xc +#define DP_RECEIVER_CAP_SIZE 0xf +#define DP_DSC_RECEIVER_CAP_SIZE 0xf +#define EDP_PSR_RECEIVER_CAP_SIZE 2 +#define EDP_DISPLAY_CTL_CAP_SIZE 3 +#define DP_LTTPR_COMMON_CAP_SIZE 8 +#define DP_LTTPR_PHY_CAP_SIZE 3 + +#define DP_SDP_AUDIO_TIMESTAMP 0x01 +#define DP_SDP_AUDIO_STREAM 0x02 +#define DP_SDP_EXTENSION 0x04 /* DP 1.1 */ +#define DP_SDP_AUDIO_COPYMANAGEMENT 0x05 /* DP 1.2 */ +#define DP_SDP_ISRC 0x06 /* DP 1.2 */ +#define DP_SDP_VSC 0x07 /* DP 1.2 */ +#define DP_SDP_CAMERA_GENERIC(i) (0x08 + (i)) /* 0-7, DP 1.3 */ +#define DP_SDP_PPS 0x10 /* DP 1.4 */ +#define DP_SDP_VSC_EXT_VESA 0x20 /* DP 1.4 */ +#define DP_SDP_VSC_EXT_CEA 0x21 /* DP 1.4 */ +/* 0x80+ CEA-861 infoframe types */ + +/** + * struct dp_sdp_header - DP secondary data packet header + * @HB0: Secondary Data Packet ID + * @HB1: Secondary Data Packet Type + * @HB2: Secondary Data Packet Specific header, Byte 0 + * @HB3: Secondary Data packet Specific header, Byte 1 + */ +struct dp_sdp_header { + u8 HB0; + u8 HB1; + u8 HB2; + u8 HB3; +} __packed; + +#define EDP_SDP_HEADER_REVISION_MASK 0x1F +#define EDP_SDP_HEADER_VALID_PAYLOAD_BYTES 0x1F +#define DP_SDP_PPS_HEADER_PAYLOAD_BYTES_MINUS_1 0x7F + +/** + * struct dp_sdp - DP secondary data packet + * @sdp_header: DP secondary data packet header + * @db: DP secondaray data packet data blocks + * VSC SDP Payload for PSR + * db[0]: Stereo Interface + * db[1]: 0 - PSR State; 1 - Update RFB; 2 - CRC Valid + * db[2]: CRC value bits 7:0 of the R or Cr component + * db[3]: CRC value bits 15:8 of the R or Cr component + * db[4]: CRC value bits 7:0 of the G or Y component + * db[5]: CRC value bits 15:8 of the G or Y component + * db[6]: CRC value bits 7:0 of the B or Cb component + * db[7]: CRC value bits 15:8 of the B or Cb component + * db[8] - db[31]: Reserved + * VSC SDP Payload for Pixel Encoding/Colorimetry Format + * db[0] - db[15]: Reserved + * db[16]: Pixel Encoding and Colorimetry Formats + * db[17]: Dynamic Range and Component Bit Depth + * db[18]: Content Type + * db[19] - db[31]: Reserved + */ +struct dp_sdp { + struct dp_sdp_header sdp_header; + u8 db[32]; +} __packed; + +#define EDP_VSC_PSR_STATE_ACTIVE (1<<0) +#define EDP_VSC_PSR_UPDATE_RFB (1<<1) +#define EDP_VSC_PSR_CRC_VALUES_VALID (1<<2) + +/** + * enum dp_pixelformat - drm DP Pixel encoding formats + * + * This enum is used to indicate DP VSC SDP Pixel encoding formats. + * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through + * DB18] + * + * @DP_PIXELFORMAT_RGB: RGB pixel encoding format + * @DP_PIXELFORMAT_YUV444: YCbCr 4:4:4 pixel encoding format + * @DP_PIXELFORMAT_YUV422: YCbCr 4:2:2 pixel encoding format + * @DP_PIXELFORMAT_YUV420: YCbCr 4:2:0 pixel encoding format + * @DP_PIXELFORMAT_Y_ONLY: Y Only pixel encoding format + * @DP_PIXELFORMAT_RAW: RAW pixel encoding format + * @DP_PIXELFORMAT_RESERVED: Reserved pixel encoding format + */ +enum dp_pixelformat { + DP_PIXELFORMAT_RGB = 0, + DP_PIXELFORMAT_YUV444 = 0x1, + DP_PIXELFORMAT_YUV422 = 0x2, + DP_PIXELFORMAT_YUV420 = 0x3, + DP_PIXELFORMAT_Y_ONLY = 0x4, + DP_PIXELFORMAT_RAW = 0x5, + DP_PIXELFORMAT_RESERVED = 0x6, +}; + +/** + * enum dp_colorimetry - drm DP Colorimetry formats + * + * This enum is used to indicate DP VSC SDP Colorimetry formats. + * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through + * DB18] and a name of enum member follows DRM_MODE_COLORIMETRY definition. + * + * @DP_COLORIMETRY_DEFAULT: sRGB (IEC 61966-2-1) or + * ITU-R BT.601 colorimetry format + * @DP_COLORIMETRY_RGB_WIDE_FIXED: RGB wide gamut fixed point colorimetry format + * @DP_COLORIMETRY_BT709_YCC: ITU-R BT.709 colorimetry format + * @DP_COLORIMETRY_RGB_WIDE_FLOAT: RGB wide gamut floating point + * (scRGB (IEC 61966-2-2)) colorimetry format + * @DP_COLORIMETRY_XVYCC_601: xvYCC601 colorimetry format + * @DP_COLORIMETRY_OPRGB: OpRGB colorimetry format + * @DP_COLORIMETRY_XVYCC_709: xvYCC709 colorimetry format + * @DP_COLORIMETRY_DCI_P3_RGB: DCI-P3 (SMPTE RP 431-2) colorimetry format + * @DP_COLORIMETRY_SYCC_601: sYCC601 colorimetry format + * @DP_COLORIMETRY_RGB_CUSTOM: RGB Custom Color Profile colorimetry format + * @DP_COLORIMETRY_OPYCC_601: opYCC601 colorimetry format + * @DP_COLORIMETRY_BT2020_RGB: ITU-R BT.2020 R' G' B' colorimetry format + * @DP_COLORIMETRY_BT2020_CYCC: ITU-R BT.2020 Y'c C'bc C'rc colorimetry format + * @DP_COLORIMETRY_BT2020_YCC: ITU-R BT.2020 Y' C'b C'r colorimetry format + */ +enum dp_colorimetry { + DP_COLORIMETRY_DEFAULT = 0, + DP_COLORIMETRY_RGB_WIDE_FIXED = 0x1, + DP_COLORIMETRY_BT709_YCC = 0x1, + DP_COLORIMETRY_RGB_WIDE_FLOAT = 0x2, + DP_COLORIMETRY_XVYCC_601 = 0x2, + DP_COLORIMETRY_OPRGB = 0x3, + DP_COLORIMETRY_XVYCC_709 = 0x3, + DP_COLORIMETRY_DCI_P3_RGB = 0x4, + DP_COLORIMETRY_SYCC_601 = 0x4, + DP_COLORIMETRY_RGB_CUSTOM = 0x5, + DP_COLORIMETRY_OPYCC_601 = 0x5, + DP_COLORIMETRY_BT2020_RGB = 0x6, + DP_COLORIMETRY_BT2020_CYCC = 0x6, + DP_COLORIMETRY_BT2020_YCC = 0x7, +}; + +/** + * enum dp_dynamic_range - drm DP Dynamic Range + * + * This enum is used to indicate DP VSC SDP Dynamic Range. + * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through + * DB18] + * + * @DP_DYNAMIC_RANGE_VESA: VESA range + * @DP_DYNAMIC_RANGE_CTA: CTA range + */ +enum dp_dynamic_range { + DP_DYNAMIC_RANGE_VESA = 0, + DP_DYNAMIC_RANGE_CTA = 1, +}; + +/** + * enum dp_content_type - drm DP Content Type + * + * This enum is used to indicate DP VSC SDP Content Types. + * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through + * DB18] + * CTA-861-G defines content types and expected processing by a sink device + * + * @DP_CONTENT_TYPE_NOT_DEFINED: Not defined type + * @DP_CONTENT_TYPE_GRAPHICS: Graphics type + * @DP_CONTENT_TYPE_PHOTO: Photo type + * @DP_CONTENT_TYPE_VIDEO: Video type + * @DP_CONTENT_TYPE_GAME: Game type + */ +enum dp_content_type { + DP_CONTENT_TYPE_NOT_DEFINED = 0x00, + DP_CONTENT_TYPE_GRAPHICS = 0x01, + DP_CONTENT_TYPE_PHOTO = 0x02, + DP_CONTENT_TYPE_VIDEO = 0x03, + DP_CONTENT_TYPE_GAME = 0x04, +}; + +#endif /* _DRM_DP_H_ */ diff --git a/include/drm/display/drm_dp_helper.h b/include/drm/display/drm_dp_helper.h index 91af98e6617c..dca40a045dd6 100644 --- a/include/drm/display/drm_dp_helper.h +++ b/include/drm/display/drm_dp_helper.h @@ -25,1501 +25,14 @@ #include #include -#include + +#include #include struct drm_device; struct drm_dp_aux; struct drm_panel; -/* - * Unless otherwise noted, all values are from the DP 1.1a spec. Note that - * DP and DPCD versions are independent. Differences from 1.0 are not noted, - * 1.0 devices basically don't exist in the wild. - * - * Abbreviations, in chronological order: - * - * eDP: Embedded DisplayPort version 1 - * DPI: DisplayPort Interoperability Guideline v1.1a - * 1.2: DisplayPort 1.2 - * MST: Multistream Transport - part of DP 1.2a - * - * 1.2 formally includes both eDP and DPI definitions. - */ - -/* MSA (Main Stream Attribute) MISC bits (as MISC1<<8|MISC0) */ -#define DP_MSA_MISC_SYNC_CLOCK (1 << 0) -#define DP_MSA_MISC_INTERLACE_VTOTAL_EVEN (1 << 8) -#define DP_MSA_MISC_STEREO_NO_3D (0 << 9) -#define DP_MSA_MISC_STEREO_PROG_RIGHT_EYE (1 << 9) -#define DP_MSA_MISC_STEREO_PROG_LEFT_EYE (3 << 9) -/* bits per component for non-RAW */ -#define DP_MSA_MISC_6_BPC (0 << 5) -#define DP_MSA_MISC_8_BPC (1 << 5) -#define DP_MSA_MISC_10_BPC (2 << 5) -#define DP_MSA_MISC_12_BPC (3 << 5) -#define DP_MSA_MISC_16_BPC (4 << 5) -/* bits per component for RAW */ -#define DP_MSA_MISC_RAW_6_BPC (1 << 5) -#define DP_MSA_MISC_RAW_7_BPC (2 << 5) -#define DP_MSA_MISC_RAW_8_BPC (3 << 5) -#define DP_MSA_MISC_RAW_10_BPC (4 << 5) -#define DP_MSA_MISC_RAW_12_BPC (5 << 5) -#define DP_MSA_MISC_RAW_14_BPC (6 << 5) -#define DP_MSA_MISC_RAW_16_BPC (7 << 5) -/* pixel encoding/colorimetry format */ -#define _DP_MSA_MISC_COLOR(misc1_7, misc0_21, misc0_3, misc0_4) \ - ((misc1_7) << 15 | (misc0_4) << 4 | (misc0_3) << 3 | ((misc0_21) << 1)) -#define DP_MSA_MISC_COLOR_RGB _DP_MSA_MISC_COLOR(0, 0, 0, 0) -#define DP_MSA_MISC_COLOR_CEA_RGB _DP_MSA_MISC_COLOR(0, 0, 1, 0) -#define DP_MSA_MISC_COLOR_RGB_WIDE_FIXED _DP_MSA_MISC_COLOR(0, 3, 0, 0) -#define DP_MSA_MISC_COLOR_RGB_WIDE_FLOAT _DP_MSA_MISC_COLOR(0, 3, 0, 1) -#define DP_MSA_MISC_COLOR_Y_ONLY _DP_MSA_MISC_COLOR(1, 0, 0, 0) -#define DP_MSA_MISC_COLOR_RAW _DP_MSA_MISC_COLOR(1, 1, 0, 0) -#define DP_MSA_MISC_COLOR_YCBCR_422_BT601 _DP_MSA_MISC_COLOR(0, 1, 1, 0) -#define DP_MSA_MISC_COLOR_YCBCR_422_BT709 _DP_MSA_MISC_COLOR(0, 1, 1, 1) -#define DP_MSA_MISC_COLOR_YCBCR_444_BT601 _DP_MSA_MISC_COLOR(0, 2, 1, 0) -#define DP_MSA_MISC_COLOR_YCBCR_444_BT709 _DP_MSA_MISC_COLOR(0, 2, 1, 1) -#define DP_MSA_MISC_COLOR_XVYCC_422_BT601 _DP_MSA_MISC_COLOR(0, 1, 0, 0) -#define DP_MSA_MISC_COLOR_XVYCC_422_BT709 _DP_MSA_MISC_COLOR(0, 1, 0, 1) -#define DP_MSA_MISC_COLOR_XVYCC_444_BT601 _DP_MSA_MISC_COLOR(0, 2, 0, 0) -#define DP_MSA_MISC_COLOR_XVYCC_444_BT709 _DP_MSA_MISC_COLOR(0, 2, 0, 1) -#define DP_MSA_MISC_COLOR_OPRGB _DP_MSA_MISC_COLOR(0, 0, 1, 1) -#define DP_MSA_MISC_COLOR_DCI_P3 _DP_MSA_MISC_COLOR(0, 3, 1, 0) -#define DP_MSA_MISC_COLOR_COLOR_PROFILE _DP_MSA_MISC_COLOR(0, 3, 1, 1) -#define DP_MSA_MISC_COLOR_VSC_SDP (1 << 14) - -#define DP_AUX_MAX_PAYLOAD_BYTES 16 - -#define DP_AUX_I2C_WRITE 0x0 -#define DP_AUX_I2C_READ 0x1 -#define DP_AUX_I2C_WRITE_STATUS_UPDATE 0x2 -#define DP_AUX_I2C_MOT 0x4 -#define DP_AUX_NATIVE_WRITE 0x8 -#define DP_AUX_NATIVE_READ 0x9 - -#define DP_AUX_NATIVE_REPLY_ACK (0x0 << 0) -#define DP_AUX_NATIVE_REPLY_NACK (0x1 << 0) -#define DP_AUX_NATIVE_REPLY_DEFER (0x2 << 0) -#define DP_AUX_NATIVE_REPLY_MASK (0x3 << 0) - -#define DP_AUX_I2C_REPLY_ACK (0x0 << 2) -#define DP_AUX_I2C_REPLY_NACK (0x1 << 2) -#define DP_AUX_I2C_REPLY_DEFER (0x2 << 2) -#define DP_AUX_I2C_REPLY_MASK (0x3 << 2) - -/* DPCD Field Address Mapping */ - -/* Receiver Capability */ -#define DP_DPCD_REV 0x000 -# define DP_DPCD_REV_10 0x10 -# define DP_DPCD_REV_11 0x11 -# define DP_DPCD_REV_12 0x12 -# define DP_DPCD_REV_13 0x13 -# define DP_DPCD_REV_14 0x14 - -#define DP_MAX_LINK_RATE 0x001 - -#define DP_MAX_LANE_COUNT 0x002 -# define DP_MAX_LANE_COUNT_MASK 0x1f -# define DP_TPS3_SUPPORTED (1 << 6) /* 1.2 */ -# define DP_ENHANCED_FRAME_CAP (1 << 7) - -#define DP_MAX_DOWNSPREAD 0x003 -# define DP_MAX_DOWNSPREAD_0_5 (1 << 0) -# define DP_STREAM_REGENERATION_STATUS_CAP (1 << 1) /* 2.0 */ -# define DP_NO_AUX_HANDSHAKE_LINK_TRAINING (1 << 6) -# define DP_TPS4_SUPPORTED (1 << 7) - -#define DP_NORP 0x004 - -#define DP_DOWNSTREAMPORT_PRESENT 0x005 -# define DP_DWN_STRM_PORT_PRESENT (1 << 0) -# define DP_DWN_STRM_PORT_TYPE_MASK 0x06 -# define DP_DWN_STRM_PORT_TYPE_DP (0 << 1) -# define DP_DWN_STRM_PORT_TYPE_ANALOG (1 << 1) -# define DP_DWN_STRM_PORT_TYPE_TMDS (2 << 1) -# define DP_DWN_STRM_PORT_TYPE_OTHER (3 << 1) -# define DP_FORMAT_CONVERSION (1 << 3) -# define DP_DETAILED_CAP_INFO_AVAILABLE (1 << 4) /* DPI */ - -#define DP_MAIN_LINK_CHANNEL_CODING 0x006 -# define DP_CAP_ANSI_8B10B (1 << 0) -# define DP_CAP_ANSI_128B132B (1 << 1) /* 2.0 */ - -#define DP_DOWN_STREAM_PORT_COUNT 0x007 -# define DP_PORT_COUNT_MASK 0x0f -# define DP_MSA_TIMING_PAR_IGNORED (1 << 6) /* eDP */ -# define DP_OUI_SUPPORT (1 << 7) - -#define DP_RECEIVE_PORT_0_CAP_0 0x008 -# define DP_LOCAL_EDID_PRESENT (1 << 1) -# define DP_ASSOCIATED_TO_PRECEDING_PORT (1 << 2) - -#define DP_RECEIVE_PORT_0_BUFFER_SIZE 0x009 - -#define DP_RECEIVE_PORT_1_CAP_0 0x00a -#define DP_RECEIVE_PORT_1_BUFFER_SIZE 0x00b - -#define DP_I2C_SPEED_CAP 0x00c /* DPI */ -# define DP_I2C_SPEED_1K 0x01 -# define DP_I2C_SPEED_5K 0x02 -# define DP_I2C_SPEED_10K 0x04 -# define DP_I2C_SPEED_100K 0x08 -# define DP_I2C_SPEED_400K 0x10 -# define DP_I2C_SPEED_1M 0x20 - -#define DP_EDP_CONFIGURATION_CAP 0x00d /* XXX 1.2? */ -# define DP_ALTERNATE_SCRAMBLER_RESET_CAP (1 << 0) -# define DP_FRAMING_CHANGE_CAP (1 << 1) -# define DP_DPCD_DISPLAY_CONTROL_CAPABLE (1 << 3) /* edp v1.2 or higher */ - -#define DP_TRAINING_AUX_RD_INTERVAL 0x00e /* XXX 1.2? */ -# define DP_TRAINING_AUX_RD_MASK 0x7F /* DP 1.3 */ -# define DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT (1 << 7) /* DP 1.3 */ - -#define DP_ADAPTER_CAP 0x00f /* 1.2 */ -# define DP_FORCE_LOAD_SENSE_CAP (1 << 0) -# define DP_ALTERNATE_I2C_PATTERN_CAP (1 << 1) - -#define DP_SUPPORTED_LINK_RATES 0x010 /* eDP 1.4 */ -# define DP_MAX_SUPPORTED_RATES 8 /* 16-bit little-endian */ - -/* Multiple stream transport */ -#define DP_FAUX_CAP 0x020 /* 1.2 */ -# define DP_FAUX_CAP_1 (1 << 0) - -#define DP_SINK_VIDEO_FALLBACK_FORMATS 0x020 /* 2.0 */ -# define DP_FALLBACK_1024x768_60HZ_24BPP (1 << 0) -# define DP_FALLBACK_1280x720_60HZ_24BPP (1 << 1) -# define DP_FALLBACK_1920x1080_60HZ_24BPP (1 << 2) - -#define DP_MSTM_CAP 0x021 /* 1.2 */ -# define DP_MST_CAP (1 << 0) -# define DP_SINGLE_STREAM_SIDEBAND_MSG (1 << 1) /* 2.0 */ - -#define DP_NUMBER_OF_AUDIO_ENDPOINTS 0x022 /* 1.2 */ - -/* AV_SYNC_DATA_BLOCK 1.2 */ -#define DP_AV_GRANULARITY 0x023 -# define DP_AG_FACTOR_MASK (0xf << 0) -# define DP_AG_FACTOR_3MS (0 << 0) -# define DP_AG_FACTOR_2MS (1 << 0) -# define DP_AG_FACTOR_1MS (2 << 0) -# define DP_AG_FACTOR_500US (3 << 0) -# define DP_AG_FACTOR_200US (4 << 0) -# define DP_AG_FACTOR_100US (5 << 0) -# define DP_AG_FACTOR_10US (6 << 0) -# define DP_AG_FACTOR_1US (7 << 0) -# define DP_VG_FACTOR_MASK (0xf << 4) -# define DP_VG_FACTOR_3MS (0 << 4) -# define DP_VG_FACTOR_2MS (1 << 4) -# define DP_VG_FACTOR_1MS (2 << 4) -# define DP_VG_FACTOR_500US (3 << 4) -# define DP_VG_FACTOR_200US (4 << 4) -# define DP_VG_FACTOR_100US (5 << 4) - -#define DP_AUD_DEC_LAT0 0x024 -#define DP_AUD_DEC_LAT1 0x025 - -#define DP_AUD_PP_LAT0 0x026 -#define DP_AUD_PP_LAT1 0x027 - -#define DP_VID_INTER_LAT 0x028 - -#define DP_VID_PROG_LAT 0x029 - -#define DP_REP_LAT 0x02a - -#define DP_AUD_DEL_INS0 0x02b -#define DP_AUD_DEL_INS1 0x02c -#define DP_AUD_DEL_INS2 0x02d -/* End of AV_SYNC_DATA_BLOCK */ - -#define DP_RECEIVER_ALPM_CAP 0x02e /* eDP 1.4 */ -# define DP_ALPM_CAP (1 << 0) - -#define DP_SINK_DEVICE_AUX_FRAME_SYNC_CAP 0x02f /* eDP 1.4 */ -# define DP_AUX_FRAME_SYNC_CAP (1 << 0) - -#define DP_GUID 0x030 /* 1.2 */ - -#define DP_DSC_SUPPORT 0x060 /* DP 1.4 */ -# define DP_DSC_DECOMPRESSION_IS_SUPPORTED (1 << 0) - -#define DP_DSC_REV 0x061 -# define DP_DSC_MAJOR_MASK (0xf << 0) -# define DP_DSC_MINOR_MASK (0xf << 4) -# define DP_DSC_MAJOR_SHIFT 0 -# define DP_DSC_MINOR_SHIFT 4 - -#define DP_DSC_RC_BUF_BLK_SIZE 0x062 -# define DP_DSC_RC_BUF_BLK_SIZE_1 0x0 -# define DP_DSC_RC_BUF_BLK_SIZE_4 0x1 -# define DP_DSC_RC_BUF_BLK_SIZE_16 0x2 -# define DP_DSC_RC_BUF_BLK_SIZE_64 0x3 - -#define DP_DSC_RC_BUF_SIZE 0x063 - -#define DP_DSC_SLICE_CAP_1 0x064 -# define DP_DSC_1_PER_DP_DSC_SINK (1 << 0) -# define DP_DSC_2_PER_DP_DSC_SINK (1 << 1) -# define DP_DSC_4_PER_DP_DSC_SINK (1 << 3) -# define DP_DSC_6_PER_DP_DSC_SINK (1 << 4) -# define DP_DSC_8_PER_DP_DSC_SINK (1 << 5) -# define DP_DSC_10_PER_DP_DSC_SINK (1 << 6) -# define DP_DSC_12_PER_DP_DSC_SINK (1 << 7) - -#define DP_DSC_LINE_BUF_BIT_DEPTH 0x065 -# define DP_DSC_LINE_BUF_BIT_DEPTH_MASK (0xf << 0) -# define DP_DSC_LINE_BUF_BIT_DEPTH_9 0x0 -# define DP_DSC_LINE_BUF_BIT_DEPTH_10 0x1 -# define DP_DSC_LINE_BUF_BIT_DEPTH_11 0x2 -# define DP_DSC_LINE_BUF_BIT_DEPTH_12 0x3 -# define DP_DSC_LINE_BUF_BIT_DEPTH_13 0x4 -# define DP_DSC_LINE_BUF_BIT_DEPTH_14 0x5 -# define DP_DSC_LINE_BUF_BIT_DEPTH_15 0x6 -# define DP_DSC_LINE_BUF_BIT_DEPTH_16 0x7 -# define DP_DSC_LINE_BUF_BIT_DEPTH_8 0x8 - -#define DP_DSC_BLK_PREDICTION_SUPPORT 0x066 -# define DP_DSC_BLK_PREDICTION_IS_SUPPORTED (1 << 0) - -#define DP_DSC_MAX_BITS_PER_PIXEL_LOW 0x067 /* eDP 1.4 */ - -#define DP_DSC_MAX_BITS_PER_PIXEL_HI 0x068 /* eDP 1.4 */ -# define DP_DSC_MAX_BITS_PER_PIXEL_HI_MASK (0x3 << 0) -# define DP_DSC_MAX_BITS_PER_PIXEL_HI_SHIFT 8 - -#define DP_DSC_DEC_COLOR_FORMAT_CAP 0x069 -# define DP_DSC_RGB (1 << 0) -# define DP_DSC_YCbCr444 (1 << 1) -# define DP_DSC_YCbCr422_Simple (1 << 2) -# define DP_DSC_YCbCr422_Native (1 << 3) -# define DP_DSC_YCbCr420_Native (1 << 4) - -#define DP_DSC_DEC_COLOR_DEPTH_CAP 0x06A -# define DP_DSC_8_BPC (1 << 1) -# define DP_DSC_10_BPC (1 << 2) -# define DP_DSC_12_BPC (1 << 3) - -#define DP_DSC_PEAK_THROUGHPUT 0x06B -# define DP_DSC_THROUGHPUT_MODE_0_MASK (0xf << 0) -# define DP_DSC_THROUGHPUT_MODE_0_SHIFT 0 -# define DP_DSC_THROUGHPUT_MODE_0_UNSUPPORTED 0 -# define DP_DSC_THROUGHPUT_MODE_0_340 (1 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_400 (2 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_450 (3 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_500 (4 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_550 (5 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_600 (6 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_650 (7 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_700 (8 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_750 (9 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_800 (10 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_850 (11 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_900 (12 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_950 (13 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_1000 (14 << 0) -# define DP_DSC_THROUGHPUT_MODE_0_170 (15 << 0) /* 1.4a */ -# define DP_DSC_THROUGHPUT_MODE_1_MASK (0xf << 4) -# define DP_DSC_THROUGHPUT_MODE_1_SHIFT 4 -# define DP_DSC_THROUGHPUT_MODE_1_UNSUPPORTED 0 -# define DP_DSC_THROUGHPUT_MODE_1_340 (1 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_400 (2 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_450 (3 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_500 (4 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_550 (5 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_600 (6 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_650 (7 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_700 (8 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_750 (9 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_800 (10 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_850 (11 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_900 (12 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_950 (13 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_1000 (14 << 4) -# define DP_DSC_THROUGHPUT_MODE_1_170 (15 << 4) - -#define DP_DSC_MAX_SLICE_WIDTH 0x06C -#define DP_DSC_MIN_SLICE_WIDTH_VALUE 2560 -#define DP_DSC_SLICE_WIDTH_MULTIPLIER 320 - -#define DP_DSC_SLICE_CAP_2 0x06D -# define DP_DSC_16_PER_DP_DSC_SINK (1 << 0) -# define DP_DSC_20_PER_DP_DSC_SINK (1 << 1) -# define DP_DSC_24_PER_DP_DSC_SINK (1 << 2) - -#define DP_DSC_BITS_PER_PIXEL_INC 0x06F -# define DP_DSC_BITS_PER_PIXEL_1_16 0x0 -# define DP_DSC_BITS_PER_PIXEL_1_8 0x1 -# define DP_DSC_BITS_PER_PIXEL_1_4 0x2 -# define DP_DSC_BITS_PER_PIXEL_1_2 0x3 -# define DP_DSC_BITS_PER_PIXEL_1 0x4 - -#define DP_PSR_SUPPORT 0x070 /* XXX 1.2? */ -# define DP_PSR_IS_SUPPORTED 1 -# define DP_PSR2_IS_SUPPORTED 2 /* eDP 1.4 */ -# define DP_PSR2_WITH_Y_COORD_IS_SUPPORTED 3 /* eDP 1.4a */ - -#define DP_PSR_CAPS 0x071 /* XXX 1.2? */ -# define DP_PSR_NO_TRAIN_ON_EXIT 1 -# define DP_PSR_SETUP_TIME_330 (0 << 1) -# define DP_PSR_SETUP_TIME_275 (1 << 1) -# define DP_PSR_SETUP_TIME_220 (2 << 1) -# define DP_PSR_SETUP_TIME_165 (3 << 1) -# define DP_PSR_SETUP_TIME_110 (4 << 1) -# define DP_PSR_SETUP_TIME_55 (5 << 1) -# define DP_PSR_SETUP_TIME_0 (6 << 1) -# define DP_PSR_SETUP_TIME_MASK (7 << 1) -# define DP_PSR_SETUP_TIME_SHIFT 1 -# define DP_PSR2_SU_Y_COORDINATE_REQUIRED (1 << 4) /* eDP 1.4a */ -# define DP_PSR2_SU_GRANULARITY_REQUIRED (1 << 5) /* eDP 1.4b */ - -#define DP_PSR2_SU_X_GRANULARITY 0x072 /* eDP 1.4b */ -#define DP_PSR2_SU_Y_GRANULARITY 0x074 /* eDP 1.4b */ - -/* - * 0x80-0x8f describe downstream port capabilities, but there are two layouts - * based on whether DP_DETAILED_CAP_INFO_AVAILABLE was set. If it was not, - * each port's descriptor is one byte wide. If it was set, each port's is - * four bytes wide, starting with the one byte from the base info. As of - * DP interop v1.1a only VGA defines additional detail. - */ - -/* offset 0 */ -#define DP_DOWNSTREAM_PORT_0 0x80 -# define DP_DS_PORT_TYPE_MASK (7 << 0) -# define DP_DS_PORT_TYPE_DP 0 -# define DP_DS_PORT_TYPE_VGA 1 -# define DP_DS_PORT_TYPE_DVI 2 -# define DP_DS_PORT_TYPE_HDMI 3 -# define DP_DS_PORT_TYPE_NON_EDID 4 -# define DP_DS_PORT_TYPE_DP_DUALMODE 5 -# define DP_DS_PORT_TYPE_WIRELESS 6 -# define DP_DS_PORT_HPD (1 << 3) -# define DP_DS_NON_EDID_MASK (0xf << 4) -# define DP_DS_NON_EDID_720x480i_60 (1 << 4) -# define DP_DS_NON_EDID_720x480i_50 (2 << 4) -# define DP_DS_NON_EDID_1920x1080i_60 (3 << 4) -# define DP_DS_NON_EDID_1920x1080i_50 (4 << 4) -# define DP_DS_NON_EDID_1280x720_60 (5 << 4) -# define DP_DS_NON_EDID_1280x720_50 (7 << 4) -/* offset 1 for VGA is maximum megapixels per second / 8 */ -/* offset 1 for DVI/HDMI is maximum TMDS clock in Mbps / 2.5 */ -/* offset 2 for VGA/DVI/HDMI */ -# define DP_DS_MAX_BPC_MASK (3 << 0) -# define DP_DS_8BPC 0 -# define DP_DS_10BPC 1 -# define DP_DS_12BPC 2 -# define DP_DS_16BPC 3 -/* HDMI2.1 PCON FRL CONFIGURATION */ -# define DP_PCON_MAX_FRL_BW (7 << 2) -# define DP_PCON_MAX_0GBPS (0 << 2) -# define DP_PCON_MAX_9GBPS (1 << 2) -# define DP_PCON_MAX_18GBPS (2 << 2) -# define DP_PCON_MAX_24GBPS (3 << 2) -# define DP_PCON_MAX_32GBPS (4 << 2) -# define DP_PCON_MAX_40GBPS (5 << 2) -# define DP_PCON_MAX_48GBPS (6 << 2) -# define DP_PCON_SOURCE_CTL_MODE (1 << 5) - -/* offset 3 for DVI */ -# define DP_DS_DVI_DUAL_LINK (1 << 1) -# define DP_DS_DVI_HIGH_COLOR_DEPTH (1 << 2) -/* offset 3 for HDMI */ -# define DP_DS_HDMI_FRAME_SEQ_TO_FRAME_PACK (1 << 0) -# define DP_DS_HDMI_YCBCR422_PASS_THROUGH (1 << 1) -# define DP_DS_HDMI_YCBCR420_PASS_THROUGH (1 << 2) -# define DP_DS_HDMI_YCBCR444_TO_422_CONV (1 << 3) -# define DP_DS_HDMI_YCBCR444_TO_420_CONV (1 << 4) - -/* - * VESA DP-to-HDMI PCON Specification adds caps for colorspace - * conversion in DFP cap DPCD 83h. Sec6.1 Table-3. - * Based on the available support the source can enable - * color conversion by writing into PROTOCOL_COVERTER_CONTROL_2 - * DPCD 3052h. - */ -# define DP_DS_HDMI_BT601_RGB_YCBCR_CONV (1 << 5) -# define DP_DS_HDMI_BT709_RGB_YCBCR_CONV (1 << 6) -# define DP_DS_HDMI_BT2020_RGB_YCBCR_CONV (1 << 7) - -#define DP_MAX_DOWNSTREAM_PORTS 0x10 - -/* DP Forward error Correction Registers */ -#define DP_FEC_CAPABILITY 0x090 /* 1.4 */ -# define DP_FEC_CAPABLE (1 << 0) -# define DP_FEC_UNCORR_BLK_ERROR_COUNT_CAP (1 << 1) -# define DP_FEC_CORR_BLK_ERROR_COUNT_CAP (1 << 2) -# define DP_FEC_BIT_ERROR_COUNT_CAP (1 << 3) -#define DP_FEC_CAPABILITY_1 0x091 /* 2.0 */ - -/* DP-HDMI2.1 PCON DSC ENCODER SUPPORT */ -#define DP_PCON_DSC_ENCODER_CAP_SIZE 0xD /* 0x92 through 0x9E */ -#define DP_PCON_DSC_ENCODER 0x092 -# define DP_PCON_DSC_ENCODER_SUPPORTED (1 << 0) -# define DP_PCON_DSC_PPS_ENC_OVERRIDE (1 << 1) - -/* DP-HDMI2.1 PCON DSC Version */ -#define DP_PCON_DSC_VERSION 0x093 -# define DP_PCON_DSC_MAJOR_MASK (0xF << 0) -# define DP_PCON_DSC_MINOR_MASK (0xF << 4) -# define DP_PCON_DSC_MAJOR_SHIFT 0 -# define DP_PCON_DSC_MINOR_SHIFT 4 - -/* DP-HDMI2.1 PCON DSC RC Buffer block size */ -#define DP_PCON_DSC_RC_BUF_BLK_INFO 0x094 -# define DP_PCON_DSC_RC_BUF_BLK_SIZE (0x3 << 0) -# define DP_PCON_DSC_RC_BUF_BLK_1KB 0 -# define DP_PCON_DSC_RC_BUF_BLK_4KB 1 -# define DP_PCON_DSC_RC_BUF_BLK_16KB 2 -# define DP_PCON_DSC_RC_BUF_BLK_64KB 3 - -/* DP-HDMI2.1 PCON DSC RC Buffer size */ -#define DP_PCON_DSC_RC_BUF_SIZE 0x095 - -/* DP-HDMI2.1 PCON DSC Slice capabilities-1 */ -#define DP_PCON_DSC_SLICE_CAP_1 0x096 -# define DP_PCON_DSC_1_PER_DSC_ENC (0x1 << 0) -# define DP_PCON_DSC_2_PER_DSC_ENC (0x1 << 1) -# define DP_PCON_DSC_4_PER_DSC_ENC (0x1 << 3) -# define DP_PCON_DSC_6_PER_DSC_ENC (0x1 << 4) -# define DP_PCON_DSC_8_PER_DSC_ENC (0x1 << 5) -# define DP_PCON_DSC_10_PER_DSC_ENC (0x1 << 6) -# define DP_PCON_DSC_12_PER_DSC_ENC (0x1 << 7) - -#define DP_PCON_DSC_BUF_BIT_DEPTH 0x097 -# define DP_PCON_DSC_BIT_DEPTH_MASK (0xF << 0) -# define DP_PCON_DSC_DEPTH_9_BITS 0 -# define DP_PCON_DSC_DEPTH_10_BITS 1 -# define DP_PCON_DSC_DEPTH_11_BITS 2 -# define DP_PCON_DSC_DEPTH_12_BITS 3 -# define DP_PCON_DSC_DEPTH_13_BITS 4 -# define DP_PCON_DSC_DEPTH_14_BITS 5 -# define DP_PCON_DSC_DEPTH_15_BITS 6 -# define DP_PCON_DSC_DEPTH_16_BITS 7 -# define DP_PCON_DSC_DEPTH_8_BITS 8 - -#define DP_PCON_DSC_BLOCK_PREDICTION 0x098 -# define DP_PCON_DSC_BLOCK_PRED_SUPPORT (0x1 << 0) - -#define DP_PCON_DSC_ENC_COLOR_FMT_CAP 0x099 -# define DP_PCON_DSC_ENC_RGB (0x1 << 0) -# define DP_PCON_DSC_ENC_YUV444 (0x1 << 1) -# define DP_PCON_DSC_ENC_YUV422_S (0x1 << 2) -# define DP_PCON_DSC_ENC_YUV422_N (0x1 << 3) -# define DP_PCON_DSC_ENC_YUV420_N (0x1 << 4) - -#define DP_PCON_DSC_ENC_COLOR_DEPTH_CAP 0x09A -# define DP_PCON_DSC_ENC_8BPC (0x1 << 1) -# define DP_PCON_DSC_ENC_10BPC (0x1 << 2) -# define DP_PCON_DSC_ENC_12BPC (0x1 << 3) - -#define DP_PCON_DSC_MAX_SLICE_WIDTH 0x09B - -/* DP-HDMI2.1 PCON DSC Slice capabilities-2 */ -#define DP_PCON_DSC_SLICE_CAP_2 0x09C -# define DP_PCON_DSC_16_PER_DSC_ENC (0x1 << 0) -# define DP_PCON_DSC_20_PER_DSC_ENC (0x1 << 1) -# define DP_PCON_DSC_24_PER_DSC_ENC (0x1 << 2) - -/* DP-HDMI2.1 PCON HDMI TX Encoder Bits/pixel increment */ -#define DP_PCON_DSC_BPP_INCR 0x09E -# define DP_PCON_DSC_BPP_INCR_MASK (0x7 << 0) -# define DP_PCON_DSC_ONE_16TH_BPP 0 -# define DP_PCON_DSC_ONE_8TH_BPP 1 -# define DP_PCON_DSC_ONE_4TH_BPP 2 -# define DP_PCON_DSC_ONE_HALF_BPP 3 -# define DP_PCON_DSC_ONE_BPP 4 - -/* DP Extended DSC Capabilities */ -#define DP_DSC_BRANCH_OVERALL_THROUGHPUT_0 0x0a0 /* DP 1.4a SCR */ -#define DP_DSC_BRANCH_OVERALL_THROUGHPUT_1 0x0a1 -#define DP_DSC_BRANCH_MAX_LINE_WIDTH 0x0a2 - -/* DFP Capability Extension */ -#define DP_DFP_CAPABILITY_EXTENSION_SUPPORT 0x0a3 /* 2.0 */ - -/* Link Configuration */ -#define DP_LINK_BW_SET 0x100 -# define DP_LINK_RATE_TABLE 0x00 /* eDP 1.4 */ -# define DP_LINK_BW_1_62 0x06 -# define DP_LINK_BW_2_7 0x0a -# define DP_LINK_BW_5_4 0x14 /* 1.2 */ -# define DP_LINK_BW_8_1 0x1e /* 1.4 */ -# define DP_LINK_BW_10 0x01 /* 2.0 128b/132b Link Layer */ -# define DP_LINK_BW_13_5 0x04 /* 2.0 128b/132b Link Layer */ -# define DP_LINK_BW_20 0x02 /* 2.0 128b/132b Link Layer */ - -#define DP_LANE_COUNT_SET 0x101 -# define DP_LANE_COUNT_MASK 0x0f -# define DP_LANE_COUNT_ENHANCED_FRAME_EN (1 << 7) - -#define DP_TRAINING_PATTERN_SET 0x102 -# define DP_TRAINING_PATTERN_DISABLE 0 -# define DP_TRAINING_PATTERN_1 1 -# define DP_TRAINING_PATTERN_2 2 -# define DP_TRAINING_PATTERN_2_CDS 3 /* 2.0 E11 */ -# define DP_TRAINING_PATTERN_3 3 /* 1.2 */ -# define DP_TRAINING_PATTERN_4 7 /* 1.4 */ -# define DP_TRAINING_PATTERN_MASK 0x3 -# define DP_TRAINING_PATTERN_MASK_1_4 0xf - -/* DPCD 1.1 only. For DPCD >= 1.2 see per-lane DP_LINK_QUAL_LANEn_SET */ -# define DP_LINK_QUAL_PATTERN_11_DISABLE (0 << 2) -# define DP_LINK_QUAL_PATTERN_11_D10_2 (1 << 2) -# define DP_LINK_QUAL_PATTERN_11_ERROR_RATE (2 << 2) -# define DP_LINK_QUAL_PATTERN_11_PRBS7 (3 << 2) -# define DP_LINK_QUAL_PATTERN_11_MASK (3 << 2) - -# define DP_RECOVERED_CLOCK_OUT_EN (1 << 4) -# define DP_LINK_SCRAMBLING_DISABLE (1 << 5) - -# define DP_SYMBOL_ERROR_COUNT_BOTH (0 << 6) -# define DP_SYMBOL_ERROR_COUNT_DISPARITY (1 << 6) -# define DP_SYMBOL_ERROR_COUNT_SYMBOL (2 << 6) -# define DP_SYMBOL_ERROR_COUNT_MASK (3 << 6) - -#define DP_TRAINING_LANE0_SET 0x103 -#define DP_TRAINING_LANE1_SET 0x104 -#define DP_TRAINING_LANE2_SET 0x105 -#define DP_TRAINING_LANE3_SET 0x106 - -# define DP_TRAIN_VOLTAGE_SWING_MASK 0x3 -# define DP_TRAIN_VOLTAGE_SWING_SHIFT 0 -# define DP_TRAIN_MAX_SWING_REACHED (1 << 2) -# define DP_TRAIN_VOLTAGE_SWING_LEVEL_0 (0 << 0) -# define DP_TRAIN_VOLTAGE_SWING_LEVEL_1 (1 << 0) -# define DP_TRAIN_VOLTAGE_SWING_LEVEL_2 (2 << 0) -# define DP_TRAIN_VOLTAGE_SWING_LEVEL_3 (3 << 0) - -# define DP_TRAIN_PRE_EMPHASIS_MASK (3 << 3) -# define DP_TRAIN_PRE_EMPH_LEVEL_0 (0 << 3) -# define DP_TRAIN_PRE_EMPH_LEVEL_1 (1 << 3) -# define DP_TRAIN_PRE_EMPH_LEVEL_2 (2 << 3) -# define DP_TRAIN_PRE_EMPH_LEVEL_3 (3 << 3) - -# define DP_TRAIN_PRE_EMPHASIS_SHIFT 3 -# define DP_TRAIN_MAX_PRE_EMPHASIS_REACHED (1 << 5) - -# define DP_TX_FFE_PRESET_VALUE_MASK (0xf << 0) /* 2.0 128b/132b Link Layer */ - -#define DP_DOWNSPREAD_CTRL 0x107 -# define DP_SPREAD_AMP_0_5 (1 << 4) -# define DP_MSA_TIMING_PAR_IGNORE_EN (1 << 7) /* eDP */ - -#define DP_MAIN_LINK_CHANNEL_CODING_SET 0x108 -# define DP_SET_ANSI_8B10B (1 << 0) -# define DP_SET_ANSI_128B132B (1 << 1) - -#define DP_I2C_SPEED_CONTROL_STATUS 0x109 /* DPI */ -/* bitmask as for DP_I2C_SPEED_CAP */ - -#define DP_EDP_CONFIGURATION_SET 0x10a /* XXX 1.2? */ -# define DP_ALTERNATE_SCRAMBLER_RESET_ENABLE (1 << 0) -# define DP_FRAMING_CHANGE_ENABLE (1 << 1) -# define DP_PANEL_SELF_TEST_ENABLE (1 << 7) - -#define DP_LINK_QUAL_LANE0_SET 0x10b /* DPCD >= 1.2 */ -#define DP_LINK_QUAL_LANE1_SET 0x10c -#define DP_LINK_QUAL_LANE2_SET 0x10d -#define DP_LINK_QUAL_LANE3_SET 0x10e -# define DP_LINK_QUAL_PATTERN_DISABLE 0 -# define DP_LINK_QUAL_PATTERN_D10_2 1 -# define DP_LINK_QUAL_PATTERN_ERROR_RATE 2 -# define DP_LINK_QUAL_PATTERN_PRBS7 3 -# define DP_LINK_QUAL_PATTERN_80BIT_CUSTOM 4 -# define DP_LINK_QUAL_PATTERN_CP2520_PAT_1 5 -# define DP_LINK_QUAL_PATTERN_CP2520_PAT_2 6 -# define DP_LINK_QUAL_PATTERN_CP2520_PAT_3 7 -/* DP 2.0 UHBR10, UHBR13.5, UHBR20 */ -# define DP_LINK_QUAL_PATTERN_128B132B_TPS1 0x08 -# define DP_LINK_QUAL_PATTERN_128B132B_TPS2 0x10 -# define DP_LINK_QUAL_PATTERN_PRSBS9 0x18 -# define DP_LINK_QUAL_PATTERN_PRSBS11 0x20 -# define DP_LINK_QUAL_PATTERN_PRSBS15 0x28 -# define DP_LINK_QUAL_PATTERN_PRSBS23 0x30 -# define DP_LINK_QUAL_PATTERN_PRSBS31 0x38 -# define DP_LINK_QUAL_PATTERN_CUSTOM 0x40 -# define DP_LINK_QUAL_PATTERN_SQUARE 0x48 - -#define DP_TRAINING_LANE0_1_SET2 0x10f -#define DP_TRAINING_LANE2_3_SET2 0x110 -# define DP_LANE02_POST_CURSOR2_SET_MASK (3 << 0) -# define DP_LANE02_MAX_POST_CURSOR2_REACHED (1 << 2) -# define DP_LANE13_POST_CURSOR2_SET_MASK (3 << 4) -# define DP_LANE13_MAX_POST_CURSOR2_REACHED (1 << 6) - -#define DP_MSTM_CTRL 0x111 /* 1.2 */ -# define DP_MST_EN (1 << 0) -# define DP_UP_REQ_EN (1 << 1) -# define DP_UPSTREAM_IS_SRC (1 << 2) - -#define DP_AUDIO_DELAY0 0x112 /* 1.2 */ -#define DP_AUDIO_DELAY1 0x113 -#define DP_AUDIO_DELAY2 0x114 - -#define DP_LINK_RATE_SET 0x115 /* eDP 1.4 */ -# define DP_LINK_RATE_SET_SHIFT 0 -# define DP_LINK_RATE_SET_MASK (7 << 0) - -#define DP_RECEIVER_ALPM_CONFIG 0x116 /* eDP 1.4 */ -# define DP_ALPM_ENABLE (1 << 0) -# define DP_ALPM_LOCK_ERROR_IRQ_HPD_ENABLE (1 << 1) - -#define DP_SINK_DEVICE_AUX_FRAME_SYNC_CONF 0x117 /* eDP 1.4 */ -# define DP_AUX_FRAME_SYNC_ENABLE (1 << 0) -# define DP_IRQ_HPD_ENABLE (1 << 1) - -#define DP_UPSTREAM_DEVICE_DP_PWR_NEED 0x118 /* 1.2 */ -# define DP_PWR_NOT_NEEDED (1 << 0) - -#define DP_FEC_CONFIGURATION 0x120 /* 1.4 */ -# define DP_FEC_READY (1 << 0) -# define DP_FEC_ERR_COUNT_SEL_MASK (7 << 1) -# define DP_FEC_ERR_COUNT_DIS (0 << 1) -# define DP_FEC_UNCORR_BLK_ERROR_COUNT (1 << 1) -# define DP_FEC_CORR_BLK_ERROR_COUNT (2 << 1) -# define DP_FEC_BIT_ERROR_COUNT (3 << 1) -# define DP_FEC_LANE_SELECT_MASK (3 << 4) -# define DP_FEC_LANE_0_SELECT (0 << 4) -# define DP_FEC_LANE_1_SELECT (1 << 4) -# define DP_FEC_LANE_2_SELECT (2 << 4) -# define DP_FEC_LANE_3_SELECT (3 << 4) - -#define DP_AUX_FRAME_SYNC_VALUE 0x15c /* eDP 1.4 */ -# define DP_AUX_FRAME_SYNC_VALID (1 << 0) - -#define DP_DSC_ENABLE 0x160 /* DP 1.4 */ -# define DP_DECOMPRESSION_EN (1 << 0) -#define DP_DSC_CONFIGURATION 0x161 /* DP 2.0 */ - -#define DP_PSR_EN_CFG 0x170 /* XXX 1.2? */ -# define DP_PSR_ENABLE BIT(0) -# define DP_PSR_MAIN_LINK_ACTIVE BIT(1) -# define DP_PSR_CRC_VERIFICATION BIT(2) -# define DP_PSR_FRAME_CAPTURE BIT(3) -# define DP_PSR_SU_REGION_SCANLINE_CAPTURE BIT(4) /* eDP 1.4a */ -# define DP_PSR_IRQ_HPD_WITH_CRC_ERRORS BIT(5) /* eDP 1.4a */ -# define DP_PSR_ENABLE_PSR2 BIT(6) /* eDP 1.4a */ - -#define DP_ADAPTER_CTRL 0x1a0 -# define DP_ADAPTER_CTRL_FORCE_LOAD_SENSE (1 << 0) - -#define DP_BRANCH_DEVICE_CTRL 0x1a1 -# define DP_BRANCH_DEVICE_IRQ_HPD (1 << 0) - -#define DP_PAYLOAD_ALLOCATE_SET 0x1c0 -#define DP_PAYLOAD_ALLOCATE_START_TIME_SLOT 0x1c1 -#define DP_PAYLOAD_ALLOCATE_TIME_SLOT_COUNT 0x1c2 - -/* Link/Sink Device Status */ -#define DP_SINK_COUNT 0x200 -/* prior to 1.2 bit 7 was reserved mbz */ -# define DP_GET_SINK_COUNT(x) ((((x) & 0x80) >> 1) | ((x) & 0x3f)) -# define DP_SINK_CP_READY (1 << 6) - -#define DP_DEVICE_SERVICE_IRQ_VECTOR 0x201 -# define DP_REMOTE_CONTROL_COMMAND_PENDING (1 << 0) -# define DP_AUTOMATED_TEST_REQUEST (1 << 1) -# define DP_CP_IRQ (1 << 2) -# define DP_MCCS_IRQ (1 << 3) -# define DP_DOWN_REP_MSG_RDY (1 << 4) /* 1.2 MST */ -# define DP_UP_REQ_MSG_RDY (1 << 5) /* 1.2 MST */ -# define DP_SINK_SPECIFIC_IRQ (1 << 6) - -#define DP_LANE0_1_STATUS 0x202 -#define DP_LANE2_3_STATUS 0x203 -# define DP_LANE_CR_DONE (1 << 0) -# define DP_LANE_CHANNEL_EQ_DONE (1 << 1) -# define DP_LANE_SYMBOL_LOCKED (1 << 2) - -#define DP_CHANNEL_EQ_BITS (DP_LANE_CR_DONE | \ - DP_LANE_CHANNEL_EQ_DONE | \ - DP_LANE_SYMBOL_LOCKED) - -#define DP_LANE_ALIGN_STATUS_UPDATED 0x204 -#define DP_INTERLANE_ALIGN_DONE (1 << 0) -#define DP_128B132B_DPRX_EQ_INTERLANE_ALIGN_DONE (1 << 2) /* 2.0 E11 */ -#define DP_128B132B_DPRX_CDS_INTERLANE_ALIGN_DONE (1 << 3) /* 2.0 E11 */ -#define DP_128B132B_LT_FAILED (1 << 4) /* 2.0 E11 */ -#define DP_DOWNSTREAM_PORT_STATUS_CHANGED (1 << 6) -#define DP_LINK_STATUS_UPDATED (1 << 7) - -#define DP_SINK_STATUS 0x205 -# define DP_RECEIVE_PORT_0_STATUS (1 << 0) -# define DP_RECEIVE_PORT_1_STATUS (1 << 1) -# define DP_STREAM_REGENERATION_STATUS (1 << 2) /* 2.0 */ -# define DP_INTRA_HOP_AUX_REPLY_INDICATION (1 << 3) /* 2.0 */ - -#define DP_ADJUST_REQUEST_LANE0_1 0x206 -#define DP_ADJUST_REQUEST_LANE2_3 0x207 -# define DP_ADJUST_VOLTAGE_SWING_LANE0_MASK 0x03 -# define DP_ADJUST_VOLTAGE_SWING_LANE0_SHIFT 0 -# define DP_ADJUST_PRE_EMPHASIS_LANE0_MASK 0x0c -# define DP_ADJUST_PRE_EMPHASIS_LANE0_SHIFT 2 -# define DP_ADJUST_VOLTAGE_SWING_LANE1_MASK 0x30 -# define DP_ADJUST_VOLTAGE_SWING_LANE1_SHIFT 4 -# define DP_ADJUST_PRE_EMPHASIS_LANE1_MASK 0xc0 -# define DP_ADJUST_PRE_EMPHASIS_LANE1_SHIFT 6 - -/* DP 2.0 128b/132b Link Layer */ -# define DP_ADJUST_TX_FFE_PRESET_LANE0_MASK (0xf << 0) -# define DP_ADJUST_TX_FFE_PRESET_LANE0_SHIFT 0 -# define DP_ADJUST_TX_FFE_PRESET_LANE1_MASK (0xf << 4) -# define DP_ADJUST_TX_FFE_PRESET_LANE1_SHIFT 4 - -#define DP_ADJUST_REQUEST_POST_CURSOR2 0x20c -# define DP_ADJUST_POST_CURSOR2_LANE0_MASK 0x03 -# define DP_ADJUST_POST_CURSOR2_LANE0_SHIFT 0 -# define DP_ADJUST_POST_CURSOR2_LANE1_MASK 0x0c -# define DP_ADJUST_POST_CURSOR2_LANE1_SHIFT 2 -# define DP_ADJUST_POST_CURSOR2_LANE2_MASK 0x30 -# define DP_ADJUST_POST_CURSOR2_LANE2_SHIFT 4 -# define DP_ADJUST_POST_CURSOR2_LANE3_MASK 0xc0 -# define DP_ADJUST_POST_CURSOR2_LANE3_SHIFT 6 - -#define DP_TEST_REQUEST 0x218 -# define DP_TEST_LINK_TRAINING (1 << 0) -# define DP_TEST_LINK_VIDEO_PATTERN (1 << 1) -# define DP_TEST_LINK_EDID_READ (1 << 2) -# define DP_TEST_LINK_PHY_TEST_PATTERN (1 << 3) /* DPCD >= 1.1 */ -# define DP_TEST_LINK_FAUX_PATTERN (1 << 4) /* DPCD >= 1.2 */ -# define DP_TEST_LINK_AUDIO_PATTERN (1 << 5) /* DPCD >= 1.2 */ -# define DP_TEST_LINK_AUDIO_DISABLED_VIDEO (1 << 6) /* DPCD >= 1.2 */ - -#define DP_TEST_LINK_RATE 0x219 -# define DP_LINK_RATE_162 (0x6) -# define DP_LINK_RATE_27 (0xa) - -#define DP_TEST_LANE_COUNT 0x220 - -#define DP_TEST_PATTERN 0x221 -# define DP_NO_TEST_PATTERN 0x0 -# define DP_COLOR_RAMP 0x1 -# define DP_BLACK_AND_WHITE_VERTICAL_LINES 0x2 -# define DP_COLOR_SQUARE 0x3 - -#define DP_TEST_H_TOTAL_HI 0x222 -#define DP_TEST_H_TOTAL_LO 0x223 - -#define DP_TEST_V_TOTAL_HI 0x224 -#define DP_TEST_V_TOTAL_LO 0x225 - -#define DP_TEST_H_START_HI 0x226 -#define DP_TEST_H_START_LO 0x227 - -#define DP_TEST_V_START_HI 0x228 -#define DP_TEST_V_START_LO 0x229 - -#define DP_TEST_HSYNC_HI 0x22A -# define DP_TEST_HSYNC_POLARITY (1 << 7) -# define DP_TEST_HSYNC_WIDTH_HI_MASK (127 << 0) -#define DP_TEST_HSYNC_WIDTH_LO 0x22B - -#define DP_TEST_VSYNC_HI 0x22C -# define DP_TEST_VSYNC_POLARITY (1 << 7) -# define DP_TEST_VSYNC_WIDTH_HI_MASK (127 << 0) -#define DP_TEST_VSYNC_WIDTH_LO 0x22D - -#define DP_TEST_H_WIDTH_HI 0x22E -#define DP_TEST_H_WIDTH_LO 0x22F - -#define DP_TEST_V_HEIGHT_HI 0x230 -#define DP_TEST_V_HEIGHT_LO 0x231 - -#define DP_TEST_MISC0 0x232 -# define DP_TEST_SYNC_CLOCK (1 << 0) -# define DP_TEST_COLOR_FORMAT_MASK (3 << 1) -# define DP_TEST_COLOR_FORMAT_SHIFT 1 -# define DP_COLOR_FORMAT_RGB (0 << 1) -# define DP_COLOR_FORMAT_YCbCr422 (1 << 1) -# define DP_COLOR_FORMAT_YCbCr444 (2 << 1) -# define DP_TEST_DYNAMIC_RANGE_VESA (0 << 3) -# define DP_TEST_DYNAMIC_RANGE_CEA (1 << 3) -# define DP_TEST_YCBCR_COEFFICIENTS (1 << 4) -# define DP_YCBCR_COEFFICIENTS_ITU601 (0 << 4) -# define DP_YCBCR_COEFFICIENTS_ITU709 (1 << 4) -# define DP_TEST_BIT_DEPTH_MASK (7 << 5) -# define DP_TEST_BIT_DEPTH_SHIFT 5 -# define DP_TEST_BIT_DEPTH_6 (0 << 5) -# define DP_TEST_BIT_DEPTH_8 (1 << 5) -# define DP_TEST_BIT_DEPTH_10 (2 << 5) -# define DP_TEST_BIT_DEPTH_12 (3 << 5) -# define DP_TEST_BIT_DEPTH_16 (4 << 5) - -#define DP_TEST_MISC1 0x233 -# define DP_TEST_REFRESH_DENOMINATOR (1 << 0) -# define DP_TEST_INTERLACED (1 << 1) - -#define DP_TEST_REFRESH_RATE_NUMERATOR 0x234 - -#define DP_TEST_MISC0 0x232 - -#define DP_TEST_CRC_R_CR 0x240 -#define DP_TEST_CRC_G_Y 0x242 -#define DP_TEST_CRC_B_CB 0x244 - -#define DP_TEST_SINK_MISC 0x246 -# define DP_TEST_CRC_SUPPORTED (1 << 5) -# define DP_TEST_COUNT_MASK 0xf - -#define DP_PHY_TEST_PATTERN 0x248 -# define DP_PHY_TEST_PATTERN_SEL_MASK 0x7 -# define DP_PHY_TEST_PATTERN_NONE 0x0 -# define DP_PHY_TEST_PATTERN_D10_2 0x1 -# define DP_PHY_TEST_PATTERN_ERROR_COUNT 0x2 -# define DP_PHY_TEST_PATTERN_PRBS7 0x3 -# define DP_PHY_TEST_PATTERN_80BIT_CUSTOM 0x4 -# define DP_PHY_TEST_PATTERN_CP2520 0x5 - -#define DP_PHY_SQUARE_PATTERN 0x249 - -#define DP_TEST_HBR2_SCRAMBLER_RESET 0x24A -#define DP_TEST_80BIT_CUSTOM_PATTERN_7_0 0x250 -#define DP_TEST_80BIT_CUSTOM_PATTERN_15_8 0x251 -#define DP_TEST_80BIT_CUSTOM_PATTERN_23_16 0x252 -#define DP_TEST_80BIT_CUSTOM_PATTERN_31_24 0x253 -#define DP_TEST_80BIT_CUSTOM_PATTERN_39_32 0x254 -#define DP_TEST_80BIT_CUSTOM_PATTERN_47_40 0x255 -#define DP_TEST_80BIT_CUSTOM_PATTERN_55_48 0x256 -#define DP_TEST_80BIT_CUSTOM_PATTERN_63_56 0x257 -#define DP_TEST_80BIT_CUSTOM_PATTERN_71_64 0x258 -#define DP_TEST_80BIT_CUSTOM_PATTERN_79_72 0x259 - -#define DP_TEST_RESPONSE 0x260 -# define DP_TEST_ACK (1 << 0) -# define DP_TEST_NAK (1 << 1) -# define DP_TEST_EDID_CHECKSUM_WRITE (1 << 2) - -#define DP_TEST_EDID_CHECKSUM 0x261 - -#define DP_TEST_SINK 0x270 -# define DP_TEST_SINK_START (1 << 0) -#define DP_TEST_AUDIO_MODE 0x271 -#define DP_TEST_AUDIO_PATTERN_TYPE 0x272 -#define DP_TEST_AUDIO_PERIOD_CH1 0x273 -#define DP_TEST_AUDIO_PERIOD_CH2 0x274 -#define DP_TEST_AUDIO_PERIOD_CH3 0x275 -#define DP_TEST_AUDIO_PERIOD_CH4 0x276 -#define DP_TEST_AUDIO_PERIOD_CH5 0x277 -#define DP_TEST_AUDIO_PERIOD_CH6 0x278 -#define DP_TEST_AUDIO_PERIOD_CH7 0x279 -#define DP_TEST_AUDIO_PERIOD_CH8 0x27A - -#define DP_FEC_STATUS 0x280 /* 1.4 */ -# define DP_FEC_DECODE_EN_DETECTED (1 << 0) -# define DP_FEC_DECODE_DIS_DETECTED (1 << 1) - -#define DP_FEC_ERROR_COUNT_LSB 0x0281 /* 1.4 */ - -#define DP_FEC_ERROR_COUNT_MSB 0x0282 /* 1.4 */ -# define DP_FEC_ERROR_COUNT_MASK 0x7F -# define DP_FEC_ERR_COUNT_VALID (1 << 7) - -#define DP_PAYLOAD_TABLE_UPDATE_STATUS 0x2c0 /* 1.2 MST */ -# define DP_PAYLOAD_TABLE_UPDATED (1 << 0) -# define DP_PAYLOAD_ACT_HANDLED (1 << 1) - -#define DP_VC_PAYLOAD_ID_SLOT_1 0x2c1 /* 1.2 MST */ -/* up to ID_SLOT_63 at 0x2ff */ - -/* Source Device-specific */ -#define DP_SOURCE_OUI 0x300 - -/* Sink Device-specific */ -#define DP_SINK_OUI 0x400 - -/* Branch Device-specific */ -#define DP_BRANCH_OUI 0x500 -#define DP_BRANCH_ID 0x503 -#define DP_BRANCH_REVISION_START 0x509 -#define DP_BRANCH_HW_REV 0x509 -#define DP_BRANCH_SW_REV 0x50A - -/* Link/Sink Device Power Control */ -#define DP_SET_POWER 0x600 -# define DP_SET_POWER_D0 0x1 -# define DP_SET_POWER_D3 0x2 -# define DP_SET_POWER_MASK 0x3 -# define DP_SET_POWER_D3_AUX_ON 0x5 - -/* eDP-specific */ -#define DP_EDP_DPCD_REV 0x700 /* eDP 1.2 */ -# define DP_EDP_11 0x00 -# define DP_EDP_12 0x01 -# define DP_EDP_13 0x02 -# define DP_EDP_14 0x03 -# define DP_EDP_14a 0x04 /* eDP 1.4a */ -# define DP_EDP_14b 0x05 /* eDP 1.4b */ - -#define DP_EDP_GENERAL_CAP_1 0x701 -# define DP_EDP_TCON_BACKLIGHT_ADJUSTMENT_CAP (1 << 0) -# define DP_EDP_BACKLIGHT_PIN_ENABLE_CAP (1 << 1) -# define DP_EDP_BACKLIGHT_AUX_ENABLE_CAP (1 << 2) -# define DP_EDP_PANEL_SELF_TEST_PIN_ENABLE_CAP (1 << 3) -# define DP_EDP_PANEL_SELF_TEST_AUX_ENABLE_CAP (1 << 4) -# define DP_EDP_FRC_ENABLE_CAP (1 << 5) -# define DP_EDP_COLOR_ENGINE_CAP (1 << 6) -# define DP_EDP_SET_POWER_CAP (1 << 7) - -#define DP_EDP_BACKLIGHT_ADJUSTMENT_CAP 0x702 -# define DP_EDP_BACKLIGHT_BRIGHTNESS_PWM_PIN_CAP (1 << 0) -# define DP_EDP_BACKLIGHT_BRIGHTNESS_AUX_SET_CAP (1 << 1) -# define DP_EDP_BACKLIGHT_BRIGHTNESS_BYTE_COUNT (1 << 2) -# define DP_EDP_BACKLIGHT_AUX_PWM_PRODUCT_CAP (1 << 3) -# define DP_EDP_BACKLIGHT_FREQ_PWM_PIN_PASSTHRU_CAP (1 << 4) -# define DP_EDP_BACKLIGHT_FREQ_AUX_SET_CAP (1 << 5) -# define DP_EDP_DYNAMIC_BACKLIGHT_CAP (1 << 6) -# define DP_EDP_VBLANK_BACKLIGHT_UPDATE_CAP (1 << 7) - -#define DP_EDP_GENERAL_CAP_2 0x703 -# define DP_EDP_OVERDRIVE_ENGINE_ENABLED (1 << 0) - -#define DP_EDP_GENERAL_CAP_3 0x704 /* eDP 1.4 */ -# define DP_EDP_X_REGION_CAP_MASK (0xf << 0) -# define DP_EDP_X_REGION_CAP_SHIFT 0 -# define DP_EDP_Y_REGION_CAP_MASK (0xf << 4) -# define DP_EDP_Y_REGION_CAP_SHIFT 4 - -#define DP_EDP_DISPLAY_CONTROL_REGISTER 0x720 -# define DP_EDP_BACKLIGHT_ENABLE (1 << 0) -# define DP_EDP_BLACK_VIDEO_ENABLE (1 << 1) -# define DP_EDP_FRC_ENABLE (1 << 2) -# define DP_EDP_COLOR_ENGINE_ENABLE (1 << 3) -# define DP_EDP_VBLANK_BACKLIGHT_UPDATE_ENABLE (1 << 7) - -#define DP_EDP_BACKLIGHT_MODE_SET_REGISTER 0x721 -# define DP_EDP_BACKLIGHT_CONTROL_MODE_MASK (3 << 0) -# define DP_EDP_BACKLIGHT_CONTROL_MODE_PWM (0 << 0) -# define DP_EDP_BACKLIGHT_CONTROL_MODE_PRESET (1 << 0) -# define DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD (2 << 0) -# define DP_EDP_BACKLIGHT_CONTROL_MODE_PRODUCT (3 << 0) -# define DP_EDP_BACKLIGHT_FREQ_PWM_PIN_PASSTHRU_ENABLE (1 << 2) -# define DP_EDP_BACKLIGHT_FREQ_AUX_SET_ENABLE (1 << 3) -# define DP_EDP_DYNAMIC_BACKLIGHT_ENABLE (1 << 4) -# define DP_EDP_REGIONAL_BACKLIGHT_ENABLE (1 << 5) -# define DP_EDP_UPDATE_REGION_BRIGHTNESS (1 << 6) /* eDP 1.4 */ - -#define DP_EDP_BACKLIGHT_BRIGHTNESS_MSB 0x722 -#define DP_EDP_BACKLIGHT_BRIGHTNESS_LSB 0x723 - -#define DP_EDP_PWMGEN_BIT_COUNT 0x724 -#define DP_EDP_PWMGEN_BIT_COUNT_CAP_MIN 0x725 -#define DP_EDP_PWMGEN_BIT_COUNT_CAP_MAX 0x726 -# define DP_EDP_PWMGEN_BIT_COUNT_MASK (0x1f << 0) - -#define DP_EDP_BACKLIGHT_CONTROL_STATUS 0x727 - -#define DP_EDP_BACKLIGHT_FREQ_SET 0x728 -# define DP_EDP_BACKLIGHT_FREQ_BASE_KHZ 27000 - -#define DP_EDP_BACKLIGHT_FREQ_CAP_MIN_MSB 0x72a -#define DP_EDP_BACKLIGHT_FREQ_CAP_MIN_MID 0x72b -#define DP_EDP_BACKLIGHT_FREQ_CAP_MIN_LSB 0x72c - -#define DP_EDP_BACKLIGHT_FREQ_CAP_MAX_MSB 0x72d -#define DP_EDP_BACKLIGHT_FREQ_CAP_MAX_MID 0x72e -#define DP_EDP_BACKLIGHT_FREQ_CAP_MAX_LSB 0x72f - -#define DP_EDP_DBC_MINIMUM_BRIGHTNESS_SET 0x732 -#define DP_EDP_DBC_MAXIMUM_BRIGHTNESS_SET 0x733 - -#define DP_EDP_REGIONAL_BACKLIGHT_BASE 0x740 /* eDP 1.4 */ -#define DP_EDP_REGIONAL_BACKLIGHT_0 0x741 /* eDP 1.4 */ - -#define DP_EDP_MSO_LINK_CAPABILITIES 0x7a4 /* eDP 1.4 */ -# define DP_EDP_MSO_NUMBER_OF_LINKS_MASK (7 << 0) -# define DP_EDP_MSO_NUMBER_OF_LINKS_SHIFT 0 -# define DP_EDP_MSO_INDEPENDENT_LINK_BIT (1 << 3) - -/* Sideband MSG Buffers */ -#define DP_SIDEBAND_MSG_DOWN_REQ_BASE 0x1000 /* 1.2 MST */ -#define DP_SIDEBAND_MSG_UP_REP_BASE 0x1200 /* 1.2 MST */ -#define DP_SIDEBAND_MSG_DOWN_REP_BASE 0x1400 /* 1.2 MST */ -#define DP_SIDEBAND_MSG_UP_REQ_BASE 0x1600 /* 1.2 MST */ - -/* DPRX Event Status Indicator */ -#define DP_SINK_COUNT_ESI 0x2002 /* same as 0x200 */ -#define DP_DEVICE_SERVICE_IRQ_VECTOR_ESI0 0x2003 /* same as 0x201 */ - -#define DP_DEVICE_SERVICE_IRQ_VECTOR_ESI1 0x2004 /* 1.2 */ -# define DP_RX_GTC_MSTR_REQ_STATUS_CHANGE (1 << 0) -# define DP_LOCK_ACQUISITION_REQUEST (1 << 1) -# define DP_CEC_IRQ (1 << 2) - -#define DP_LINK_SERVICE_IRQ_VECTOR_ESI0 0x2005 /* 1.2 */ -# define RX_CAP_CHANGED (1 << 0) -# define LINK_STATUS_CHANGED (1 << 1) -# define STREAM_STATUS_CHANGED (1 << 2) -# define HDMI_LINK_STATUS_CHANGED (1 << 3) -# define CONNECTED_OFF_ENTRY_REQUESTED (1 << 4) - -#define DP_PSR_ERROR_STATUS 0x2006 /* XXX 1.2? */ -# define DP_PSR_LINK_CRC_ERROR (1 << 0) -# define DP_PSR_RFB_STORAGE_ERROR (1 << 1) -# define DP_PSR_VSC_SDP_UNCORRECTABLE_ERROR (1 << 2) /* eDP 1.4 */ - -#define DP_PSR_ESI 0x2007 /* XXX 1.2? */ -# define DP_PSR_CAPS_CHANGE (1 << 0) - -#define DP_PSR_STATUS 0x2008 /* XXX 1.2? */ -# define DP_PSR_SINK_INACTIVE 0 -# define DP_PSR_SINK_ACTIVE_SRC_SYNCED 1 -# define DP_PSR_SINK_ACTIVE_RFB 2 -# define DP_PSR_SINK_ACTIVE_SINK_SYNCED 3 -# define DP_PSR_SINK_ACTIVE_RESYNC 4 -# define DP_PSR_SINK_INTERNAL_ERROR 7 -# define DP_PSR_SINK_STATE_MASK 0x07 - -#define DP_SYNCHRONIZATION_LATENCY_IN_SINK 0x2009 /* edp 1.4 */ -# define DP_MAX_RESYNC_FRAME_COUNT_MASK (0xf << 0) -# define DP_MAX_RESYNC_FRAME_COUNT_SHIFT 0 -# define DP_LAST_ACTUAL_SYNCHRONIZATION_LATENCY_MASK (0xf << 4) -# define DP_LAST_ACTUAL_SYNCHRONIZATION_LATENCY_SHIFT 4 - -#define DP_LAST_RECEIVED_PSR_SDP 0x200a /* eDP 1.2 */ -# define DP_PSR_STATE_BIT (1 << 0) /* eDP 1.2 */ -# define DP_UPDATE_RFB_BIT (1 << 1) /* eDP 1.2 */ -# define DP_CRC_VALID_BIT (1 << 2) /* eDP 1.2 */ -# define DP_SU_VALID (1 << 3) /* eDP 1.4 */ -# define DP_FIRST_SCAN_LINE_SU_REGION (1 << 4) /* eDP 1.4 */ -# define DP_LAST_SCAN_LINE_SU_REGION (1 << 5) /* eDP 1.4 */ -# define DP_Y_COORDINATE_VALID (1 << 6) /* eDP 1.4a */ - -#define DP_RECEIVER_ALPM_STATUS 0x200b /* eDP 1.4 */ -# define DP_ALPM_LOCK_TIMEOUT_ERROR (1 << 0) - -#define DP_LANE0_1_STATUS_ESI 0x200c /* status same as 0x202 */ -#define DP_LANE2_3_STATUS_ESI 0x200d /* status same as 0x203 */ -#define DP_LANE_ALIGN_STATUS_UPDATED_ESI 0x200e /* status same as 0x204 */ -#define DP_SINK_STATUS_ESI 0x200f /* status same as 0x205 */ - -/* Extended Receiver Capability: See DP_DPCD_REV for definitions */ -#define DP_DP13_DPCD_REV 0x2200 - -#define DP_DPRX_FEATURE_ENUMERATION_LIST 0x2210 /* DP 1.3 */ -# define DP_GTC_CAP (1 << 0) /* DP 1.3 */ -# define DP_SST_SPLIT_SDP_CAP (1 << 1) /* DP 1.4 */ -# define DP_AV_SYNC_CAP (1 << 2) /* DP 1.3 */ -# define DP_VSC_SDP_EXT_FOR_COLORIMETRY_SUPPORTED (1 << 3) /* DP 1.3 */ -# define DP_VSC_EXT_VESA_SDP_SUPPORTED (1 << 4) /* DP 1.4 */ -# define DP_VSC_EXT_VESA_SDP_CHAINING_SUPPORTED (1 << 5) /* DP 1.4 */ -# define DP_VSC_EXT_CEA_SDP_SUPPORTED (1 << 6) /* DP 1.4 */ -# define DP_VSC_EXT_CEA_SDP_CHAINING_SUPPORTED (1 << 7) /* DP 1.4 */ - -#define DP_128B132B_SUPPORTED_LINK_RATES 0x2215 /* 2.0 */ -# define DP_UHBR10 (1 << 0) -# define DP_UHBR20 (1 << 1) -# define DP_UHBR13_5 (1 << 2) - -#define DP_128B132B_TRAINING_AUX_RD_INTERVAL 0x2216 /* 2.0 */ -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_1MS_UNIT (1 << 7) -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_MASK 0x7f -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_400_US 0x00 -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_4_MS 0x01 -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_8_MS 0x02 -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_12_MS 0x03 -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_16_MS 0x04 -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_32_MS 0x05 -# define DP_128B132B_TRAINING_AUX_RD_INTERVAL_64_MS 0x06 - -#define DP_TEST_264BIT_CUSTOM_PATTERN_7_0 0x2230 -#define DP_TEST_264BIT_CUSTOM_PATTERN_263_256 0x2250 - -/* DSC Extended Capability Branch Total DSC Resources */ -#define DP_DSC_SUPPORT_AND_DSC_DECODER_COUNT 0x2260 /* 2.0 */ -# define DP_DSC_DECODER_COUNT_MASK (0b111 << 5) -# define DP_DSC_DECODER_COUNT_SHIFT 5 -#define DP_DSC_MAX_SLICE_COUNT_AND_AGGREGATION_0 0x2270 /* 2.0 */ -# define DP_DSC_DECODER_0_MAXIMUM_SLICE_COUNT_MASK (1 << 0) -# define DP_DSC_DECODER_0_AGGREGATION_SUPPORT_MASK (0b111 << 1) -# define DP_DSC_DECODER_0_AGGREGATION_SUPPORT_SHIFT 1 - -/* Protocol Converter Extension */ -/* HDMI CEC tunneling over AUX DP 1.3 section 5.3.3.3.1 DPCD 1.4+ */ -#define DP_CEC_TUNNELING_CAPABILITY 0x3000 -# define DP_CEC_TUNNELING_CAPABLE (1 << 0) -# define DP_CEC_SNOOPING_CAPABLE (1 << 1) -# define DP_CEC_MULTIPLE_LA_CAPABLE (1 << 2) - -#define DP_CEC_TUNNELING_CONTROL 0x3001 -# define DP_CEC_TUNNELING_ENABLE (1 << 0) -# define DP_CEC_SNOOPING_ENABLE (1 << 1) - -#define DP_CEC_RX_MESSAGE_INFO 0x3002 -# define DP_CEC_RX_MESSAGE_LEN_MASK (0xf << 0) -# define DP_CEC_RX_MESSAGE_LEN_SHIFT 0 -# define DP_CEC_RX_MESSAGE_HPD_STATE (1 << 4) -# define DP_CEC_RX_MESSAGE_HPD_LOST (1 << 5) -# define DP_CEC_RX_MESSAGE_ACKED (1 << 6) -# define DP_CEC_RX_MESSAGE_ENDED (1 << 7) - -#define DP_CEC_TX_MESSAGE_INFO 0x3003 -# define DP_CEC_TX_MESSAGE_LEN_MASK (0xf << 0) -# define DP_CEC_TX_MESSAGE_LEN_SHIFT 0 -# define DP_CEC_TX_RETRY_COUNT_MASK (0x7 << 4) -# define DP_CEC_TX_RETRY_COUNT_SHIFT 4 -# define DP_CEC_TX_MESSAGE_SEND (1 << 7) - -#define DP_CEC_TUNNELING_IRQ_FLAGS 0x3004 -# define DP_CEC_RX_MESSAGE_INFO_VALID (1 << 0) -# define DP_CEC_RX_MESSAGE_OVERFLOW (1 << 1) -# define DP_CEC_TX_MESSAGE_SENT (1 << 4) -# define DP_CEC_TX_LINE_ERROR (1 << 5) -# define DP_CEC_TX_ADDRESS_NACK_ERROR (1 << 6) -# define DP_CEC_TX_DATA_NACK_ERROR (1 << 7) - -#define DP_CEC_LOGICAL_ADDRESS_MASK 0x300E /* 0x300F word */ -# define DP_CEC_LOGICAL_ADDRESS_0 (1 << 0) -# define DP_CEC_LOGICAL_ADDRESS_1 (1 << 1) -# define DP_CEC_LOGICAL_ADDRESS_2 (1 << 2) -# define DP_CEC_LOGICAL_ADDRESS_3 (1 << 3) -# define DP_CEC_LOGICAL_ADDRESS_4 (1 << 4) -# define DP_CEC_LOGICAL_ADDRESS_5 (1 << 5) -# define DP_CEC_LOGICAL_ADDRESS_6 (1 << 6) -# define DP_CEC_LOGICAL_ADDRESS_7 (1 << 7) -#define DP_CEC_LOGICAL_ADDRESS_MASK_2 0x300F /* 0x300E word */ -# define DP_CEC_LOGICAL_ADDRESS_8 (1 << 0) -# define DP_CEC_LOGICAL_ADDRESS_9 (1 << 1) -# define DP_CEC_LOGICAL_ADDRESS_10 (1 << 2) -# define DP_CEC_LOGICAL_ADDRESS_11 (1 << 3) -# define DP_CEC_LOGICAL_ADDRESS_12 (1 << 4) -# define DP_CEC_LOGICAL_ADDRESS_13 (1 << 5) -# define DP_CEC_LOGICAL_ADDRESS_14 (1 << 6) -# define DP_CEC_LOGICAL_ADDRESS_15 (1 << 7) - -#define DP_CEC_RX_MESSAGE_BUFFER 0x3010 -#define DP_CEC_TX_MESSAGE_BUFFER 0x3020 -#define DP_CEC_MESSAGE_BUFFER_LENGTH 0x10 - -/* PCON CONFIGURE-1 FRL FOR HDMI SINK */ -#define DP_PCON_HDMI_LINK_CONFIG_1 0x305A -# define DP_PCON_ENABLE_MAX_FRL_BW (7 << 0) -# define DP_PCON_ENABLE_MAX_BW_0GBPS 0 -# define DP_PCON_ENABLE_MAX_BW_9GBPS 1 -# define DP_PCON_ENABLE_MAX_BW_18GBPS 2 -# define DP_PCON_ENABLE_MAX_BW_24GBPS 3 -# define DP_PCON_ENABLE_MAX_BW_32GBPS 4 -# define DP_PCON_ENABLE_MAX_BW_40GBPS 5 -# define DP_PCON_ENABLE_MAX_BW_48GBPS 6 -# define DP_PCON_ENABLE_SOURCE_CTL_MODE (1 << 3) -# define DP_PCON_ENABLE_CONCURRENT_LINK (1 << 4) -# define DP_PCON_ENABLE_SEQUENTIAL_LINK (0 << 4) -# define DP_PCON_ENABLE_LINK_FRL_MODE (1 << 5) -# define DP_PCON_ENABLE_HPD_READY (1 << 6) -# define DP_PCON_ENABLE_HDMI_LINK (1 << 7) - -/* PCON CONFIGURE-2 FRL FOR HDMI SINK */ -#define DP_PCON_HDMI_LINK_CONFIG_2 0x305B -# define DP_PCON_MAX_LINK_BW_MASK (0x3F << 0) -# define DP_PCON_FRL_BW_MASK_9GBPS (1 << 0) -# define DP_PCON_FRL_BW_MASK_18GBPS (1 << 1) -# define DP_PCON_FRL_BW_MASK_24GBPS (1 << 2) -# define DP_PCON_FRL_BW_MASK_32GBPS (1 << 3) -# define DP_PCON_FRL_BW_MASK_40GBPS (1 << 4) -# define DP_PCON_FRL_BW_MASK_48GBPS (1 << 5) -# define DP_PCON_FRL_LINK_TRAIN_EXTENDED (1 << 6) -# define DP_PCON_FRL_LINK_TRAIN_NORMAL (0 << 6) - -/* PCON HDMI LINK STATUS */ -#define DP_PCON_HDMI_TX_LINK_STATUS 0x303B -# define DP_PCON_HDMI_TX_LINK_ACTIVE (1 << 0) -# define DP_PCON_FRL_READY (1 << 1) - -/* PCON HDMI POST FRL STATUS */ -#define DP_PCON_HDMI_POST_FRL_STATUS 0x3036 -# define DP_PCON_HDMI_LINK_MODE (1 << 0) -# define DP_PCON_HDMI_MODE_TMDS 0 -# define DP_PCON_HDMI_MODE_FRL 1 -# define DP_PCON_HDMI_FRL_TRAINED_BW (0x3F << 1) -# define DP_PCON_FRL_TRAINED_BW_9GBPS (1 << 1) -# define DP_PCON_FRL_TRAINED_BW_18GBPS (1 << 2) -# define DP_PCON_FRL_TRAINED_BW_24GBPS (1 << 3) -# define DP_PCON_FRL_TRAINED_BW_32GBPS (1 << 4) -# define DP_PCON_FRL_TRAINED_BW_40GBPS (1 << 5) -# define DP_PCON_FRL_TRAINED_BW_48GBPS (1 << 6) - -#define DP_PROTOCOL_CONVERTER_CONTROL_0 0x3050 /* DP 1.3 */ -# define DP_HDMI_DVI_OUTPUT_CONFIG (1 << 0) /* DP 1.3 */ -#define DP_PROTOCOL_CONVERTER_CONTROL_1 0x3051 /* DP 1.3 */ -# define DP_CONVERSION_TO_YCBCR420_ENABLE (1 << 0) /* DP 1.3 */ -# define DP_HDMI_EDID_PROCESSING_DISABLE (1 << 1) /* DP 1.4 */ -# define DP_HDMI_AUTONOMOUS_SCRAMBLING_DISABLE (1 << 2) /* DP 1.4 */ -# define DP_HDMI_FORCE_SCRAMBLING (1 << 3) /* DP 1.4 */ -#define DP_PROTOCOL_CONVERTER_CONTROL_2 0x3052 /* DP 1.3 */ -# define DP_CONVERSION_TO_YCBCR422_ENABLE (1 << 0) /* DP 1.3 */ -# define DP_PCON_ENABLE_DSC_ENCODER (1 << 1) -# define DP_PCON_ENCODER_PPS_OVERRIDE_MASK (0x3 << 2) -# define DP_PCON_ENC_PPS_OVERRIDE_DISABLED 0 -# define DP_PCON_ENC_PPS_OVERRIDE_EN_PARAMS 1 -# define DP_PCON_ENC_PPS_OVERRIDE_EN_BUFFER 2 -# define DP_CONVERSION_RGB_YCBCR_MASK (7 << 4) -# define DP_CONVERSION_BT601_RGB_YCBCR_ENABLE (1 << 4) -# define DP_CONVERSION_BT709_RGB_YCBCR_ENABLE (1 << 5) -# define DP_CONVERSION_BT2020_RGB_YCBCR_ENABLE (1 << 6) - -/* PCON Downstream HDMI ERROR Status per Lane */ -#define DP_PCON_HDMI_ERROR_STATUS_LN0 0x3037 -#define DP_PCON_HDMI_ERROR_STATUS_LN1 0x3038 -#define DP_PCON_HDMI_ERROR_STATUS_LN2 0x3039 -#define DP_PCON_HDMI_ERROR_STATUS_LN3 0x303A -# define DP_PCON_HDMI_ERROR_COUNT_MASK (0x7 << 0) -# define DP_PCON_HDMI_ERROR_COUNT_THREE_PLUS (1 << 0) -# define DP_PCON_HDMI_ERROR_COUNT_TEN_PLUS (1 << 1) -# define DP_PCON_HDMI_ERROR_COUNT_HUNDRED_PLUS (1 << 2) - -/* PCON HDMI CONFIG PPS Override Buffer - * Valid Offsets to be added to Base : 0-127 - */ -#define DP_PCON_HDMI_PPS_OVERRIDE_BASE 0x3100 - -/* PCON HDMI CONFIG PPS Override Parameter: Slice height - * Offset-0 8LSBs of the Slice height. - * Offset-1 8MSBs of the Slice height. - */ -#define DP_PCON_HDMI_PPS_OVRD_SLICE_HEIGHT 0x3180 - -/* PCON HDMI CONFIG PPS Override Parameter: Slice width - * Offset-0 8LSBs of the Slice width. - * Offset-1 8MSBs of the Slice width. - */ -#define DP_PCON_HDMI_PPS_OVRD_SLICE_WIDTH 0x3182 - -/* PCON HDMI CONFIG PPS Override Parameter: bits_per_pixel - * Offset-0 8LSBs of the bits_per_pixel. - * Offset-1 2MSBs of the bits_per_pixel. - */ -#define DP_PCON_HDMI_PPS_OVRD_BPP 0x3184 - -/* HDCP 1.3 and HDCP 2.2 */ -#define DP_AUX_HDCP_BKSV 0x68000 -#define DP_AUX_HDCP_RI_PRIME 0x68005 -#define DP_AUX_HDCP_AKSV 0x68007 -#define DP_AUX_HDCP_AN 0x6800C -#define DP_AUX_HDCP_V_PRIME(h) (0x68014 + h * 4) -#define DP_AUX_HDCP_BCAPS 0x68028 -# define DP_BCAPS_REPEATER_PRESENT BIT(1) -# define DP_BCAPS_HDCP_CAPABLE BIT(0) -#define DP_AUX_HDCP_BSTATUS 0x68029 -# define DP_BSTATUS_REAUTH_REQ BIT(3) -# define DP_BSTATUS_LINK_FAILURE BIT(2) -# define DP_BSTATUS_R0_PRIME_READY BIT(1) -# define DP_BSTATUS_READY BIT(0) -#define DP_AUX_HDCP_BINFO 0x6802A -#define DP_AUX_HDCP_KSV_FIFO 0x6802C -#define DP_AUX_HDCP_AINFO 0x6803B - -/* DP HDCP2.2 parameter offsets in DPCD address space */ -#define DP_HDCP_2_2_REG_RTX_OFFSET 0x69000 -#define DP_HDCP_2_2_REG_TXCAPS_OFFSET 0x69008 -#define DP_HDCP_2_2_REG_CERT_RX_OFFSET 0x6900B -#define DP_HDCP_2_2_REG_RRX_OFFSET 0x69215 -#define DP_HDCP_2_2_REG_RX_CAPS_OFFSET 0x6921D -#define DP_HDCP_2_2_REG_EKPUB_KM_OFFSET 0x69220 -#define DP_HDCP_2_2_REG_EKH_KM_WR_OFFSET 0x692A0 -#define DP_HDCP_2_2_REG_M_OFFSET 0x692B0 -#define DP_HDCP_2_2_REG_HPRIME_OFFSET 0x692C0 -#define DP_HDCP_2_2_REG_EKH_KM_RD_OFFSET 0x692E0 -#define DP_HDCP_2_2_REG_RN_OFFSET 0x692F0 -#define DP_HDCP_2_2_REG_LPRIME_OFFSET 0x692F8 -#define DP_HDCP_2_2_REG_EDKEY_KS_OFFSET 0x69318 -#define DP_HDCP_2_2_REG_RIV_OFFSET 0x69328 -#define DP_HDCP_2_2_REG_RXINFO_OFFSET 0x69330 -#define DP_HDCP_2_2_REG_SEQ_NUM_V_OFFSET 0x69332 -#define DP_HDCP_2_2_REG_VPRIME_OFFSET 0x69335 -#define DP_HDCP_2_2_REG_RECV_ID_LIST_OFFSET 0x69345 -#define DP_HDCP_2_2_REG_V_OFFSET 0x693E0 -#define DP_HDCP_2_2_REG_SEQ_NUM_M_OFFSET 0x693F0 -#define DP_HDCP_2_2_REG_K_OFFSET 0x693F3 -#define DP_HDCP_2_2_REG_STREAM_ID_TYPE_OFFSET 0x693F5 -#define DP_HDCP_2_2_REG_MPRIME_OFFSET 0x69473 -#define DP_HDCP_2_2_REG_RXSTATUS_OFFSET 0x69493 -#define DP_HDCP_2_2_REG_STREAM_TYPE_OFFSET 0x69494 -#define DP_HDCP_2_2_REG_DBG_OFFSET 0x69518 - -/* LTTPR: Link Training (LT)-tunable PHY Repeaters */ -#define DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV 0xf0000 /* 1.3 */ -#define DP_MAX_LINK_RATE_PHY_REPEATER 0xf0001 /* 1.4a */ -#define DP_PHY_REPEATER_CNT 0xf0002 /* 1.3 */ -#define DP_PHY_REPEATER_MODE 0xf0003 /* 1.3 */ -#define DP_MAX_LANE_COUNT_PHY_REPEATER 0xf0004 /* 1.4a */ -#define DP_Repeater_FEC_CAPABILITY 0xf0004 /* 1.4 */ -#define DP_PHY_REPEATER_EXTENDED_WAIT_TIMEOUT 0xf0005 /* 1.4a */ -#define DP_MAIN_LINK_CHANNEL_CODING_PHY_REPEATER 0xf0006 /* 2.0 */ -# define DP_PHY_REPEATER_128B132B_SUPPORTED (1 << 0) -/* See DP_128B132B_SUPPORTED_LINK_RATES for values */ -#define DP_PHY_REPEATER_128B132B_RATES 0xf0007 /* 2.0 */ -#define DP_PHY_REPEATER_EQ_DONE 0xf0008 /* 2.0 E11 */ - -enum drm_dp_phy { - DP_PHY_DPRX, - - DP_PHY_LTTPR1, - DP_PHY_LTTPR2, - DP_PHY_LTTPR3, - DP_PHY_LTTPR4, - DP_PHY_LTTPR5, - DP_PHY_LTTPR6, - DP_PHY_LTTPR7, - DP_PHY_LTTPR8, - - DP_MAX_LTTPR_COUNT = DP_PHY_LTTPR8, -}; - -#define DP_PHY_LTTPR(i) (DP_PHY_LTTPR1 + (i)) - -#define __DP_LTTPR1_BASE 0xf0010 /* 1.3 */ -#define __DP_LTTPR2_BASE 0xf0060 /* 1.3 */ -#define DP_LTTPR_BASE(dp_phy) \ - (__DP_LTTPR1_BASE + (__DP_LTTPR2_BASE - __DP_LTTPR1_BASE) * \ - ((dp_phy) - DP_PHY_LTTPR1)) - -#define DP_LTTPR_REG(dp_phy, lttpr1_reg) \ - (DP_LTTPR_BASE(dp_phy) - DP_LTTPR_BASE(DP_PHY_LTTPR1) + (lttpr1_reg)) - -#define DP_TRAINING_PATTERN_SET_PHY_REPEATER1 0xf0010 /* 1.3 */ -#define DP_TRAINING_PATTERN_SET_PHY_REPEATER(dp_phy) \ - DP_LTTPR_REG(dp_phy, DP_TRAINING_PATTERN_SET_PHY_REPEATER1) - -#define DP_TRAINING_LANE0_SET_PHY_REPEATER1 0xf0011 /* 1.3 */ -#define DP_TRAINING_LANE0_SET_PHY_REPEATER(dp_phy) \ - DP_LTTPR_REG(dp_phy, DP_TRAINING_LANE0_SET_PHY_REPEATER1) - -#define DP_TRAINING_LANE1_SET_PHY_REPEATER1 0xf0012 /* 1.3 */ -#define DP_TRAINING_LANE2_SET_PHY_REPEATER1 0xf0013 /* 1.3 */ -#define DP_TRAINING_LANE3_SET_PHY_REPEATER1 0xf0014 /* 1.3 */ -#define DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1 0xf0020 /* 1.4a */ -#define DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER(dp_phy) \ - DP_LTTPR_REG(dp_phy, DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1) - -#define DP_TRANSMITTER_CAPABILITY_PHY_REPEATER1 0xf0021 /* 1.4a */ -# define DP_VOLTAGE_SWING_LEVEL_3_SUPPORTED BIT(0) -# define DP_PRE_EMPHASIS_LEVEL_3_SUPPORTED BIT(1) - -#define DP_128B132B_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1 0xf0022 /* 2.0 */ -#define DP_128B132B_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER(dp_phy) \ - DP_LTTPR_REG(dp_phy, DP_128B132B_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1) -/* see DP_128B132B_TRAINING_AUX_RD_INTERVAL for values */ - -#define DP_LANE0_1_STATUS_PHY_REPEATER1 0xf0030 /* 1.3 */ -#define DP_LANE0_1_STATUS_PHY_REPEATER(dp_phy) \ - DP_LTTPR_REG(dp_phy, DP_LANE0_1_STATUS_PHY_REPEATER1) - -#define DP_LANE2_3_STATUS_PHY_REPEATER1 0xf0031 /* 1.3 */ - -#define DP_LANE_ALIGN_STATUS_UPDATED_PHY_REPEATER1 0xf0032 /* 1.3 */ -#define DP_ADJUST_REQUEST_LANE0_1_PHY_REPEATER1 0xf0033 /* 1.3 */ -#define DP_ADJUST_REQUEST_LANE2_3_PHY_REPEATER1 0xf0034 /* 1.3 */ -#define DP_SYMBOL_ERROR_COUNT_LANE0_PHY_REPEATER1 0xf0035 /* 1.3 */ -#define DP_SYMBOL_ERROR_COUNT_LANE1_PHY_REPEATER1 0xf0037 /* 1.3 */ -#define DP_SYMBOL_ERROR_COUNT_LANE2_PHY_REPEATER1 0xf0039 /* 1.3 */ -#define DP_SYMBOL_ERROR_COUNT_LANE3_PHY_REPEATER1 0xf003b /* 1.3 */ - -#define __DP_FEC1_BASE 0xf0290 /* 1.4 */ -#define __DP_FEC2_BASE 0xf0298 /* 1.4 */ -#define DP_FEC_BASE(dp_phy) \ - (__DP_FEC1_BASE + ((__DP_FEC2_BASE - __DP_FEC1_BASE) * \ - ((dp_phy) - DP_PHY_LTTPR1))) - -#define DP_FEC_REG(dp_phy, fec1_reg) \ - (DP_FEC_BASE(dp_phy) - DP_FEC_BASE(DP_PHY_LTTPR1) + fec1_reg) - -#define DP_FEC_STATUS_PHY_REPEATER1 0xf0290 /* 1.4 */ -#define DP_FEC_STATUS_PHY_REPEATER(dp_phy) \ - DP_FEC_REG(dp_phy, DP_FEC_STATUS_PHY_REPEATER1) - -#define DP_FEC_ERROR_COUNT_PHY_REPEATER1 0xf0291 /* 1.4 */ -#define DP_FEC_CAPABILITY_PHY_REPEATER1 0xf0294 /* 1.4a */ - -#define DP_LTTPR_MAX_ADD 0xf02ff /* 1.4 */ - -#define DP_DPCD_MAX_ADD 0xfffff /* 1.4 */ - -/* Repeater modes */ -#define DP_PHY_REPEATER_MODE_TRANSPARENT 0x55 /* 1.3 */ -#define DP_PHY_REPEATER_MODE_NON_TRANSPARENT 0xaa /* 1.3 */ - -/* DP HDCP message start offsets in DPCD address space */ -#define DP_HDCP_2_2_AKE_INIT_OFFSET DP_HDCP_2_2_REG_RTX_OFFSET -#define DP_HDCP_2_2_AKE_SEND_CERT_OFFSET DP_HDCP_2_2_REG_CERT_RX_OFFSET -#define DP_HDCP_2_2_AKE_NO_STORED_KM_OFFSET DP_HDCP_2_2_REG_EKPUB_KM_OFFSET -#define DP_HDCP_2_2_AKE_STORED_KM_OFFSET DP_HDCP_2_2_REG_EKH_KM_WR_OFFSET -#define DP_HDCP_2_2_AKE_SEND_HPRIME_OFFSET DP_HDCP_2_2_REG_HPRIME_OFFSET -#define DP_HDCP_2_2_AKE_SEND_PAIRING_INFO_OFFSET \ - DP_HDCP_2_2_REG_EKH_KM_RD_OFFSET -#define DP_HDCP_2_2_LC_INIT_OFFSET DP_HDCP_2_2_REG_RN_OFFSET -#define DP_HDCP_2_2_LC_SEND_LPRIME_OFFSET DP_HDCP_2_2_REG_LPRIME_OFFSET -#define DP_HDCP_2_2_SKE_SEND_EKS_OFFSET DP_HDCP_2_2_REG_EDKEY_KS_OFFSET -#define DP_HDCP_2_2_REP_SEND_RECVID_LIST_OFFSET DP_HDCP_2_2_REG_RXINFO_OFFSET -#define DP_HDCP_2_2_REP_SEND_ACK_OFFSET DP_HDCP_2_2_REG_V_OFFSET -#define DP_HDCP_2_2_REP_STREAM_MANAGE_OFFSET DP_HDCP_2_2_REG_SEQ_NUM_M_OFFSET -#define DP_HDCP_2_2_REP_STREAM_READY_OFFSET DP_HDCP_2_2_REG_MPRIME_OFFSET - -#define HDCP_2_2_DP_RXSTATUS_LEN 1 -#define HDCP_2_2_DP_RXSTATUS_READY(x) ((x) & BIT(0)) -#define HDCP_2_2_DP_RXSTATUS_H_PRIME(x) ((x) & BIT(1)) -#define HDCP_2_2_DP_RXSTATUS_PAIRING(x) ((x) & BIT(2)) -#define HDCP_2_2_DP_RXSTATUS_REAUTH_REQ(x) ((x) & BIT(3)) -#define HDCP_2_2_DP_RXSTATUS_LINK_FAILED(x) ((x) & BIT(4)) - -/* DP 1.2 Sideband message defines */ -/* peer device type - DP 1.2a Table 2-92 */ -#define DP_PEER_DEVICE_NONE 0x0 -#define DP_PEER_DEVICE_SOURCE_OR_SST 0x1 -#define DP_PEER_DEVICE_MST_BRANCHING 0x2 -#define DP_PEER_DEVICE_SST_SINK 0x3 -#define DP_PEER_DEVICE_DP_LEGACY_CONV 0x4 - -/* DP 1.2 MST sideband request names DP 1.2a Table 2-80 */ -#define DP_GET_MSG_TRANSACTION_VERSION 0x00 /* DP 1.3 */ -#define DP_LINK_ADDRESS 0x01 -#define DP_CONNECTION_STATUS_NOTIFY 0x02 -#define DP_ENUM_PATH_RESOURCES 0x10 -#define DP_ALLOCATE_PAYLOAD 0x11 -#define DP_QUERY_PAYLOAD 0x12 -#define DP_RESOURCE_STATUS_NOTIFY 0x13 -#define DP_CLEAR_PAYLOAD_ID_TABLE 0x14 -#define DP_REMOTE_DPCD_READ 0x20 -#define DP_REMOTE_DPCD_WRITE 0x21 -#define DP_REMOTE_I2C_READ 0x22 -#define DP_REMOTE_I2C_WRITE 0x23 -#define DP_POWER_UP_PHY 0x24 -#define DP_POWER_DOWN_PHY 0x25 -#define DP_SINK_EVENT_NOTIFY 0x30 -#define DP_QUERY_STREAM_ENC_STATUS 0x38 -#define DP_QUERY_STREAM_ENC_STATUS_STATE_NO_EXIST 0 -#define DP_QUERY_STREAM_ENC_STATUS_STATE_INACTIVE 1 -#define DP_QUERY_STREAM_ENC_STATUS_STATE_ACTIVE 2 - -/* DP 1.2 MST sideband reply types */ -#define DP_SIDEBAND_REPLY_ACK 0x00 -#define DP_SIDEBAND_REPLY_NAK 0x01 - -/* DP 1.2 MST sideband nak reasons - table 2.84 */ -#define DP_NAK_WRITE_FAILURE 0x01 -#define DP_NAK_INVALID_READ 0x02 -#define DP_NAK_CRC_FAILURE 0x03 -#define DP_NAK_BAD_PARAM 0x04 -#define DP_NAK_DEFER 0x05 -#define DP_NAK_LINK_FAILURE 0x06 -#define DP_NAK_NO_RESOURCES 0x07 -#define DP_NAK_DPCD_FAIL 0x08 -#define DP_NAK_I2C_NAK 0x09 -#define DP_NAK_ALLOCATE_FAIL 0x0a - -#define MODE_I2C_START 1 -#define MODE_I2C_WRITE 2 -#define MODE_I2C_READ 4 -#define MODE_I2C_STOP 8 - -/* DP 1.2 MST PORTs - Section 2.5.1 v1.2a spec */ -#define DP_MST_PHYSICAL_PORT_0 0 -#define DP_MST_LOGICAL_PORT_0 8 - -#define DP_LINK_CONSTANT_N_VALUE 0x8000 -#define DP_LINK_STATUS_SIZE 6 bool drm_dp_channel_eq_ok(const u8 link_status[DP_LINK_STATUS_SIZE], int lane_count); bool drm_dp_clock_recovery_ok(const u8 link_status[DP_LINK_STATUS_SIZE], @@ -1531,14 +44,6 @@ u8 drm_dp_get_adjust_request_pre_emphasis(const u8 link_status[DP_LINK_STATUS_SI u8 drm_dp_get_adjust_tx_ffe_preset(const u8 link_status[DP_LINK_STATUS_SIZE], int lane); -#define DP_BRANCH_OUI_HEADER_SIZE 0xc -#define DP_RECEIVER_CAP_SIZE 0xf -#define DP_DSC_RECEIVER_CAP_SIZE 0xf -#define EDP_PSR_RECEIVER_CAP_SIZE 2 -#define EDP_DISPLAY_CTL_CAP_SIZE 3 -#define DP_LTTPR_COMMON_CAP_SIZE 8 -#define DP_LTTPR_PHY_CAP_SIZE 3 - int drm_dp_read_clock_recovery_delay(struct drm_dp_aux *aux, const u8 dpcd[DP_RECEIVER_CAP_SIZE], enum drm_dp_phy dp_phy, bool uhbr); int drm_dp_read_channel_eq_delay(struct drm_dp_aux *aux, const u8 dpcd[DP_RECEIVER_CAP_SIZE], @@ -1564,169 +69,6 @@ bool drm_dp_128b132b_link_training_failed(const u8 link_status[DP_LINK_STATUS_SI u8 drm_dp_link_rate_to_bw_code(int link_rate); int drm_dp_bw_code_to_link_rate(u8 link_bw); -#define DP_SDP_AUDIO_TIMESTAMP 0x01 -#define DP_SDP_AUDIO_STREAM 0x02 -#define DP_SDP_EXTENSION 0x04 /* DP 1.1 */ -#define DP_SDP_AUDIO_COPYMANAGEMENT 0x05 /* DP 1.2 */ -#define DP_SDP_ISRC 0x06 /* DP 1.2 */ -#define DP_SDP_VSC 0x07 /* DP 1.2 */ -#define DP_SDP_CAMERA_GENERIC(i) (0x08 + (i)) /* 0-7, DP 1.3 */ -#define DP_SDP_PPS 0x10 /* DP 1.4 */ -#define DP_SDP_VSC_EXT_VESA 0x20 /* DP 1.4 */ -#define DP_SDP_VSC_EXT_CEA 0x21 /* DP 1.4 */ -/* 0x80+ CEA-861 infoframe types */ - -/** - * struct dp_sdp_header - DP secondary data packet header - * @HB0: Secondary Data Packet ID - * @HB1: Secondary Data Packet Type - * @HB2: Secondary Data Packet Specific header, Byte 0 - * @HB3: Secondary Data packet Specific header, Byte 1 - */ -struct dp_sdp_header { - u8 HB0; - u8 HB1; - u8 HB2; - u8 HB3; -} __packed; - -#define EDP_SDP_HEADER_REVISION_MASK 0x1F -#define EDP_SDP_HEADER_VALID_PAYLOAD_BYTES 0x1F -#define DP_SDP_PPS_HEADER_PAYLOAD_BYTES_MINUS_1 0x7F - -/** - * struct dp_sdp - DP secondary data packet - * @sdp_header: DP secondary data packet header - * @db: DP secondaray data packet data blocks - * VSC SDP Payload for PSR - * db[0]: Stereo Interface - * db[1]: 0 - PSR State; 1 - Update RFB; 2 - CRC Valid - * db[2]: CRC value bits 7:0 of the R or Cr component - * db[3]: CRC value bits 15:8 of the R or Cr component - * db[4]: CRC value bits 7:0 of the G or Y component - * db[5]: CRC value bits 15:8 of the G or Y component - * db[6]: CRC value bits 7:0 of the B or Cb component - * db[7]: CRC value bits 15:8 of the B or Cb component - * db[8] - db[31]: Reserved - * VSC SDP Payload for Pixel Encoding/Colorimetry Format - * db[0] - db[15]: Reserved - * db[16]: Pixel Encoding and Colorimetry Formats - * db[17]: Dynamic Range and Component Bit Depth - * db[18]: Content Type - * db[19] - db[31]: Reserved - */ -struct dp_sdp { - struct dp_sdp_header sdp_header; - u8 db[32]; -} __packed; - -#define EDP_VSC_PSR_STATE_ACTIVE (1<<0) -#define EDP_VSC_PSR_UPDATE_RFB (1<<1) -#define EDP_VSC_PSR_CRC_VALUES_VALID (1<<2) - -/** - * enum dp_pixelformat - drm DP Pixel encoding formats - * - * This enum is used to indicate DP VSC SDP Pixel encoding formats. - * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through - * DB18] - * - * @DP_PIXELFORMAT_RGB: RGB pixel encoding format - * @DP_PIXELFORMAT_YUV444: YCbCr 4:4:4 pixel encoding format - * @DP_PIXELFORMAT_YUV422: YCbCr 4:2:2 pixel encoding format - * @DP_PIXELFORMAT_YUV420: YCbCr 4:2:0 pixel encoding format - * @DP_PIXELFORMAT_Y_ONLY: Y Only pixel encoding format - * @DP_PIXELFORMAT_RAW: RAW pixel encoding format - * @DP_PIXELFORMAT_RESERVED: Reserved pixel encoding format - */ -enum dp_pixelformat { - DP_PIXELFORMAT_RGB = 0, - DP_PIXELFORMAT_YUV444 = 0x1, - DP_PIXELFORMAT_YUV422 = 0x2, - DP_PIXELFORMAT_YUV420 = 0x3, - DP_PIXELFORMAT_Y_ONLY = 0x4, - DP_PIXELFORMAT_RAW = 0x5, - DP_PIXELFORMAT_RESERVED = 0x6, -}; - -/** - * enum dp_colorimetry - drm DP Colorimetry formats - * - * This enum is used to indicate DP VSC SDP Colorimetry formats. - * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through - * DB18] and a name of enum member follows DRM_MODE_COLORIMETRY definition. - * - * @DP_COLORIMETRY_DEFAULT: sRGB (IEC 61966-2-1) or - * ITU-R BT.601 colorimetry format - * @DP_COLORIMETRY_RGB_WIDE_FIXED: RGB wide gamut fixed point colorimetry format - * @DP_COLORIMETRY_BT709_YCC: ITU-R BT.709 colorimetry format - * @DP_COLORIMETRY_RGB_WIDE_FLOAT: RGB wide gamut floating point - * (scRGB (IEC 61966-2-2)) colorimetry format - * @DP_COLORIMETRY_XVYCC_601: xvYCC601 colorimetry format - * @DP_COLORIMETRY_OPRGB: OpRGB colorimetry format - * @DP_COLORIMETRY_XVYCC_709: xvYCC709 colorimetry format - * @DP_COLORIMETRY_DCI_P3_RGB: DCI-P3 (SMPTE RP 431-2) colorimetry format - * @DP_COLORIMETRY_SYCC_601: sYCC601 colorimetry format - * @DP_COLORIMETRY_RGB_CUSTOM: RGB Custom Color Profile colorimetry format - * @DP_COLORIMETRY_OPYCC_601: opYCC601 colorimetry format - * @DP_COLORIMETRY_BT2020_RGB: ITU-R BT.2020 R' G' B' colorimetry format - * @DP_COLORIMETRY_BT2020_CYCC: ITU-R BT.2020 Y'c C'bc C'rc colorimetry format - * @DP_COLORIMETRY_BT2020_YCC: ITU-R BT.2020 Y' C'b C'r colorimetry format - */ -enum dp_colorimetry { - DP_COLORIMETRY_DEFAULT = 0, - DP_COLORIMETRY_RGB_WIDE_FIXED = 0x1, - DP_COLORIMETRY_BT709_YCC = 0x1, - DP_COLORIMETRY_RGB_WIDE_FLOAT = 0x2, - DP_COLORIMETRY_XVYCC_601 = 0x2, - DP_COLORIMETRY_OPRGB = 0x3, - DP_COLORIMETRY_XVYCC_709 = 0x3, - DP_COLORIMETRY_DCI_P3_RGB = 0x4, - DP_COLORIMETRY_SYCC_601 = 0x4, - DP_COLORIMETRY_RGB_CUSTOM = 0x5, - DP_COLORIMETRY_OPYCC_601 = 0x5, - DP_COLORIMETRY_BT2020_RGB = 0x6, - DP_COLORIMETRY_BT2020_CYCC = 0x6, - DP_COLORIMETRY_BT2020_YCC = 0x7, -}; - -/** - * enum dp_dynamic_range - drm DP Dynamic Range - * - * This enum is used to indicate DP VSC SDP Dynamic Range. - * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through - * DB18] - * - * @DP_DYNAMIC_RANGE_VESA: VESA range - * @DP_DYNAMIC_RANGE_CTA: CTA range - */ -enum dp_dynamic_range { - DP_DYNAMIC_RANGE_VESA = 0, - DP_DYNAMIC_RANGE_CTA = 1, -}; - -/** - * enum dp_content_type - drm DP Content Type - * - * This enum is used to indicate DP VSC SDP Content Types. - * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through - * DB18] - * CTA-861-G defines content types and expected processing by a sink device - * - * @DP_CONTENT_TYPE_NOT_DEFINED: Not defined type - * @DP_CONTENT_TYPE_GRAPHICS: Graphics type - * @DP_CONTENT_TYPE_PHOTO: Photo type - * @DP_CONTENT_TYPE_VIDEO: Video type - * @DP_CONTENT_TYPE_GAME: Game type - */ -enum dp_content_type { - DP_CONTENT_TYPE_NOT_DEFINED = 0x00, - DP_CONTENT_TYPE_GRAPHICS = 0x01, - DP_CONTENT_TYPE_PHOTO = 0x02, - DP_CONTENT_TYPE_VIDEO = 0x03, - DP_CONTENT_TYPE_GAME = 0x04, -}; - /** * struct drm_dp_vsc_sdp - drm DP VSC SDP * -- cgit v1.2.3 From 2a64b147350f5b28f6b41873fcb453aaebea01c3 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 21 Apr 2022 09:31:05 +0200 Subject: drm/display: Move DSC header and helpers into display-helper module DSC is the Display Stream Compression standard for DisplayPort. Move the DSC code into display/ and split the header into files for protocol core and DRM helpers. Adapt all users of the code. No functional changes. To avoid the proliferation of Kconfig options, DSC is part of DRM's support for DisplayPort. If necessary, a new option could make DSC an independent feature. Signed-off-by: Thomas Zimmermann Reviewed-by: Javier Martinez Canillas Link: https://patchwork.freedesktop.org/patch/msgid/20220421073108.19226-6-tzimmermann@suse.de --- include/drm/display/drm_dsc.h | 605 ++++++++++++++++++++++++++++++++++ include/drm/display/drm_dsc_helper.h | 20 ++ include/drm/drm_dsc.h | 611 ----------------------------------- 3 files changed, 625 insertions(+), 611 deletions(-) create mode 100644 include/drm/display/drm_dsc.h create mode 100644 include/drm/display/drm_dsc_helper.h delete mode 100644 include/drm/drm_dsc.h (limited to 'include') diff --git a/include/drm/display/drm_dsc.h b/include/drm/display/drm_dsc.h new file mode 100644 index 000000000000..bc90273d06a6 --- /dev/null +++ b/include/drm/display/drm_dsc.h @@ -0,0 +1,605 @@ +/* SPDX-License-Identifier: MIT + * Copyright (C) 2018 Intel Corp. + * + * Authors: + * Manasi Navare + */ + +#ifndef DRM_DSC_H_ +#define DRM_DSC_H_ + +#include + +/* VESA Display Stream Compression DSC 1.2 constants */ +#define DSC_NUM_BUF_RANGES 15 +#define DSC_MUX_WORD_SIZE_8_10_BPC 48 +#define DSC_MUX_WORD_SIZE_12_BPC 64 +#define DSC_RC_PIXELS_PER_GROUP 3 +#define DSC_SCALE_DECREMENT_INTERVAL_MAX 4095 +#define DSC_RANGE_BPG_OFFSET_MASK 0x3f + +/* DSC Rate Control Constants */ +#define DSC_RC_MODEL_SIZE_CONST 8192 +#define DSC_RC_EDGE_FACTOR_CONST 6 +#define DSC_RC_TGT_OFFSET_HI_CONST 3 +#define DSC_RC_TGT_OFFSET_LO_CONST 3 + +/* DSC PPS constants and macros */ +#define DSC_PPS_VERSION_MAJOR_SHIFT 4 +#define DSC_PPS_BPC_SHIFT 4 +#define DSC_PPS_MSB_SHIFT 8 +#define DSC_PPS_LSB_MASK (0xFF << 0) +#define DSC_PPS_BPP_HIGH_MASK (0x3 << 8) +#define DSC_PPS_VBR_EN_SHIFT 2 +#define DSC_PPS_SIMPLE422_SHIFT 3 +#define DSC_PPS_CONVERT_RGB_SHIFT 4 +#define DSC_PPS_BLOCK_PRED_EN_SHIFT 5 +#define DSC_PPS_INIT_XMIT_DELAY_HIGH_MASK (0x3 << 8) +#define DSC_PPS_SCALE_DEC_INT_HIGH_MASK (0xF << 8) +#define DSC_PPS_RC_TGT_OFFSET_HI_SHIFT 4 +#define DSC_PPS_RC_RANGE_MINQP_SHIFT 11 +#define DSC_PPS_RC_RANGE_MAXQP_SHIFT 6 +#define DSC_PPS_NATIVE_420_SHIFT 1 +#define DSC_1_2_MAX_LINEBUF_DEPTH_BITS 16 +#define DSC_1_2_MAX_LINEBUF_DEPTH_VAL 0 +#define DSC_1_1_MAX_LINEBUF_DEPTH_BITS 13 + +/** + * struct drm_dsc_rc_range_parameters - DSC Rate Control range parameters + * + * This defines different rate control parameters used by the DSC engine + * to compress the frame. + */ +struct drm_dsc_rc_range_parameters { + /** + * @range_min_qp: Min Quantization Parameters allowed for this range + */ + u8 range_min_qp; + /** + * @range_max_qp: Max Quantization Parameters allowed for this range + */ + u8 range_max_qp; + /** + * @range_bpg_offset: + * Bits/group offset to apply to target for this group + */ + u8 range_bpg_offset; +}; + +/** + * struct drm_dsc_config - Parameters required to configure DSC + * + * Driver populates this structure with all the parameters required + * to configure the display stream compression on the source. + */ +struct drm_dsc_config { + /** + * @line_buf_depth: + * Bits per component for previous reconstructed line buffer + */ + u8 line_buf_depth; + /** + * @bits_per_component: Bits per component to code (8/10/12) + */ + u8 bits_per_component; + /** + * @convert_rgb: + * Flag to indicate if RGB - YCoCg conversion is needed + * True if RGB input, False if YCoCg input + */ + bool convert_rgb; + /** + * @slice_count: Number fo slices per line used by the DSC encoder + */ + u8 slice_count; + /** + * @slice_width: Width of each slice in pixels + */ + u16 slice_width; + /** + * @slice_height: Slice height in pixels + */ + u16 slice_height; + /** + * @simple_422: True if simple 4_2_2 mode is enabled else False + */ + bool simple_422; + /** + * @pic_width: Width of the input display frame in pixels + */ + u16 pic_width; + /** + * @pic_height: Vertical height of the input display frame + */ + u16 pic_height; + /** + * @rc_tgt_offset_high: + * Offset to bits/group used by RC to determine QP adjustment + */ + u8 rc_tgt_offset_high; + /** + * @rc_tgt_offset_low: + * Offset to bits/group used by RC to determine QP adjustment + */ + u8 rc_tgt_offset_low; + /** + * @bits_per_pixel: + * Target bits per pixel with 4 fractional bits, bits_per_pixel << 4 + */ + u16 bits_per_pixel; + /** + * @rc_edge_factor: + * Factor to determine if an edge is present based on the bits produced + */ + u8 rc_edge_factor; + /** + * @rc_quant_incr_limit1: + * Slow down incrementing once the range reaches this value + */ + u8 rc_quant_incr_limit1; + /** + * @rc_quant_incr_limit0: + * Slow down incrementing once the range reaches this value + */ + u8 rc_quant_incr_limit0; + /** + * @initial_xmit_delay: + * Number of pixels to delay the initial transmission + */ + u16 initial_xmit_delay; + /** + * @initial_dec_delay: + * Initial decoder delay, number of pixel times that the decoder + * accumulates data in its rate buffer before starting to decode + * and output pixels. + */ + u16 initial_dec_delay; + /** + * @block_pred_enable: + * True if block prediction is used to code any groups within the + * picture. False if BP not used + */ + bool block_pred_enable; + /** + * @first_line_bpg_offset: + * Number of additional bits allocated for each group on the first + * line of slice. + */ + u8 first_line_bpg_offset; + /** + * @initial_offset: Value to use for RC model offset at slice start + */ + u16 initial_offset; + /** + * @rc_buf_thresh: Thresholds defining each of the buffer ranges + */ + u16 rc_buf_thresh[DSC_NUM_BUF_RANGES - 1]; + /** + * @rc_range_params: + * Parameters for each of the RC ranges defined in + * &struct drm_dsc_rc_range_parameters + */ + struct drm_dsc_rc_range_parameters rc_range_params[DSC_NUM_BUF_RANGES]; + /** + * @rc_model_size: Total size of RC model + */ + u16 rc_model_size; + /** + * @flatness_min_qp: Minimum QP where flatness information is sent + */ + u8 flatness_min_qp; + /** + * @flatness_max_qp: Maximum QP where flatness information is sent + */ + u8 flatness_max_qp; + /** + * @initial_scale_value: Initial value for the scale factor + */ + u8 initial_scale_value; + /** + * @scale_decrement_interval: + * Specifies number of group times between decrementing the scale factor + * at beginning of a slice. + */ + u16 scale_decrement_interval; + /** + * @scale_increment_interval: + * Number of group times between incrementing the scale factor value + * used at the beginning of a slice. + */ + u16 scale_increment_interval; + /** + * @nfl_bpg_offset: Non first line BPG offset to be used + */ + u16 nfl_bpg_offset; + /** + * @slice_bpg_offset: BPG offset used to enforce slice bit + */ + u16 slice_bpg_offset; + /** + * @final_offset: Final RC linear transformation offset value + */ + u16 final_offset; + /** + * @vbr_enable: True if VBR mode is enabled, false if disabled + */ + bool vbr_enable; + /** + * @mux_word_size: Mux word size (in bits) for SSM mode + */ + u8 mux_word_size; + /** + * @slice_chunk_size: + * The (max) size in bytes of the "chunks" that are used in slice + * multiplexing. + */ + u16 slice_chunk_size; + /** + * @rc_bits: Rate control buffer size in bits + */ + u16 rc_bits; + /** + * @dsc_version_minor: DSC minor version + */ + u8 dsc_version_minor; + /** + * @dsc_version_major: DSC major version + */ + u8 dsc_version_major; + /** + * @native_422: True if Native 4:2:2 supported, else false + */ + bool native_422; + /** + * @native_420: True if Native 4:2:0 supported else false. + */ + bool native_420; + /** + * @second_line_bpg_offset: + * Additional bits/grp for seconnd line of slice for native 4:2:0 + */ + u8 second_line_bpg_offset; + /** + * @nsl_bpg_offset: + * Num of bits deallocated for each grp that is not in second line of + * slice + */ + u16 nsl_bpg_offset; + /** + * @second_line_offset_adj: + * Offset adjustment for second line in Native 4:2:0 mode + */ + u16 second_line_offset_adj; +}; + +/** + * struct drm_dsc_picture_parameter_set - Represents 128 bytes of + * Picture Parameter Set + * + * The VESA DSC standard defines picture parameter set (PPS) which display + * stream compression encoders must communicate to decoders. + * The PPS is encapsulated in 128 bytes (PPS 0 through PPS 127). The fields in + * this structure are as per Table 4.1 in Vesa DSC specification v1.1/v1.2. + * The PPS fields that span over more than a byte should be stored in Big Endian + * format. + */ +struct drm_dsc_picture_parameter_set { + /** + * @dsc_version: + * PPS0[3:0] - dsc_version_minor: Contains Minor version of DSC + * PPS0[7:4] - dsc_version_major: Contains major version of DSC + */ + u8 dsc_version; + /** + * @pps_identifier: + * PPS1[7:0] - Application specific identifier that can be + * used to differentiate between different PPS tables. + */ + u8 pps_identifier; + /** + * @pps_reserved: + * PPS2[7:0]- RESERVED Byte + */ + u8 pps_reserved; + /** + * @pps_3: + * PPS3[3:0] - linebuf_depth: Contains linebuffer bit depth used to + * generate the bitstream. (0x0 - 16 bits for DSC 1.2, 0x8 - 8 bits, + * 0xA - 10 bits, 0xB - 11 bits, 0xC - 12 bits, 0xD - 13 bits, + * 0xE - 14 bits for DSC1.2, 0xF - 14 bits for DSC 1.2. + * PPS3[7:4] - bits_per_component: Bits per component for the original + * pixels of the encoded picture. + * 0x0 = 16bpc (allowed only when dsc_version_minor = 0x2) + * 0x8 = 8bpc, 0xA = 10bpc, 0xC = 12bpc, 0xE = 14bpc (also + * allowed only when dsc_minor_version = 0x2) + */ + u8 pps_3; + /** + * @pps_4: + * PPS4[1:0] -These are the most significant 2 bits of + * compressed BPP bits_per_pixel[9:0] syntax element. + * PPS4[2] - vbr_enable: 0 = VBR disabled, 1 = VBR enabled + * PPS4[3] - simple_422: Indicates if decoder drops samples to + * reconstruct the 4:2:2 picture. + * PPS4[4] - Convert_rgb: Indicates if DSC color space conversion is + * active. + * PPS4[5] - blobk_pred_enable: Indicates if BP is used to code any + * groups in picture + * PPS4[7:6] - Reseved bits + */ + u8 pps_4; + /** + * @bits_per_pixel_low: + * PPS5[7:0] - This indicates the lower significant 8 bits of + * the compressed BPP bits_per_pixel[9:0] element. + */ + u8 bits_per_pixel_low; + /** + * @pic_height: + * PPS6[7:0], PPS7[7:0] -pic_height: Specifies the number of pixel rows + * within the raster. + */ + __be16 pic_height; + /** + * @pic_width: + * PPS8[7:0], PPS9[7:0] - pic_width: Number of pixel columns within + * the raster. + */ + __be16 pic_width; + /** + * @slice_height: + * PPS10[7:0], PPS11[7:0] - Slice height in units of pixels. + */ + __be16 slice_height; + /** + * @slice_width: + * PPS12[7:0], PPS13[7:0] - Slice width in terms of pixels. + */ + __be16 slice_width; + /** + * @chunk_size: + * PPS14[7:0], PPS15[7:0] - Size in units of bytes of the chunks + * that are used for slice multiplexing. + */ + __be16 chunk_size; + /** + * @initial_xmit_delay_high: + * PPS16[1:0] - Most Significant two bits of initial transmission delay. + * It specifies the number of pixel times that the encoder waits before + * transmitting data from its rate buffer. + * PPS16[7:2] - Reserved + */ + u8 initial_xmit_delay_high; + /** + * @initial_xmit_delay_low: + * PPS17[7:0] - Least significant 8 bits of initial transmission delay. + */ + u8 initial_xmit_delay_low; + /** + * @initial_dec_delay: + * + * PPS18[7:0], PPS19[7:0] - Initial decoding delay which is the number + * of pixel times that the decoder accumulates data in its rate buffer + * before starting to decode and output pixels. + */ + __be16 initial_dec_delay; + /** + * @pps20_reserved: + * + * PPS20[7:0] - Reserved + */ + u8 pps20_reserved; + /** + * @initial_scale_value: + * PPS21[5:0] - Initial rcXformScale factor used at beginning + * of a slice. + * PPS21[7:6] - Reserved + */ + u8 initial_scale_value; + /** + * @scale_increment_interval: + * PPS22[7:0], PPS23[7:0] - Number of group times between incrementing + * the rcXformScale factor at end of a slice. + */ + __be16 scale_increment_interval; + /** + * @scale_decrement_interval_high: + * PPS24[3:0] - Higher 4 bits indicating number of group times between + * decrementing the rcXformScale factor at beginning of a slice. + * PPS24[7:4] - Reserved + */ + u8 scale_decrement_interval_high; + /** + * @scale_decrement_interval_low: + * PPS25[7:0] - Lower 8 bits of scale decrement interval + */ + u8 scale_decrement_interval_low; + /** + * @pps26_reserved: + * PPS26[7:0] + */ + u8 pps26_reserved; + /** + * @first_line_bpg_offset: + * PPS27[4:0] - Number of additional bits that are allocated + * for each group on first line of a slice. + * PPS27[7:5] - Reserved + */ + u8 first_line_bpg_offset; + /** + * @nfl_bpg_offset: + * PPS28[7:0], PPS29[7:0] - Number of bits including frac bits + * deallocated for each group for groups after the first line of slice. + */ + __be16 nfl_bpg_offset; + /** + * @slice_bpg_offset: + * PPS30, PPS31[7:0] - Number of bits that are deallocated for each + * group to enforce the slice constraint. + */ + __be16 slice_bpg_offset; + /** + * @initial_offset: + * PPS32,33[7:0] - Initial value for rcXformOffset + */ + __be16 initial_offset; + /** + * @final_offset: + * PPS34,35[7:0] - Maximum end-of-slice value for rcXformOffset + */ + __be16 final_offset; + /** + * @flatness_min_qp: + * PPS36[4:0] - Minimum QP at which flatness is signaled and + * flatness QP adjustment is made. + * PPS36[7:5] - Reserved + */ + u8 flatness_min_qp; + /** + * @flatness_max_qp: + * PPS37[4:0] - Max QP at which flatness is signalled and + * the flatness adjustment is made. + * PPS37[7:5] - Reserved + */ + u8 flatness_max_qp; + /** + * @rc_model_size: + * PPS38,39[7:0] - Number of bits within RC Model. + */ + __be16 rc_model_size; + /** + * @rc_edge_factor: + * PPS40[3:0] - Ratio of current activity vs, previous + * activity to determine presence of edge. + * PPS40[7:4] - Reserved + */ + u8 rc_edge_factor; + /** + * @rc_quant_incr_limit0: + * PPS41[4:0] - QP threshold used in short term RC + * PPS41[7:5] - Reserved + */ + u8 rc_quant_incr_limit0; + /** + * @rc_quant_incr_limit1: + * PPS42[4:0] - QP threshold used in short term RC + * PPS42[7:5] - Reserved + */ + u8 rc_quant_incr_limit1; + /** + * @rc_tgt_offset: + * PPS43[3:0] - Lower end of the variability range around the target + * bits per group that is allowed by short term RC. + * PPS43[7:4]- Upper end of the variability range around the target + * bits per group that i allowed by short term rc. + */ + u8 rc_tgt_offset; + /** + * @rc_buf_thresh: + * PPS44[7:0] - PPS57[7:0] - Specifies the thresholds in RC model for + * the 15 ranges defined by 14 thresholds. + */ + u8 rc_buf_thresh[DSC_NUM_BUF_RANGES - 1]; + /** + * @rc_range_parameters: + * PPS58[7:0] - PPS87[7:0] + * Parameters that correspond to each of the 15 ranges. + */ + __be16 rc_range_parameters[DSC_NUM_BUF_RANGES]; + /** + * @native_422_420: + * PPS88[0] - 0 = Native 4:2:2 not used + * 1 = Native 4:2:2 used + * PPS88[1] - 0 = Native 4:2:0 not use + * 1 = Native 4:2:0 used + * PPS88[7:2] - Reserved 6 bits + */ + u8 native_422_420; + /** + * @second_line_bpg_offset: + * PPS89[4:0] - Additional bits/group budget for the + * second line of a slice in Native 4:2:0 mode. + * Set to 0 if DSC minor version is 1 or native420 is 0. + * PPS89[7:5] - Reserved + */ + u8 second_line_bpg_offset; + /** + * @nsl_bpg_offset: + * PPS90[7:0], PPS91[7:0] - Number of bits that are deallocated + * for each group that is not in the second line of a slice. + */ + __be16 nsl_bpg_offset; + /** + * @second_line_offset_adj: + * PPS92[7:0], PPS93[7:0] - Used as offset adjustment for the second + * line in Native 4:2:0 mode. + */ + __be16 second_line_offset_adj; + /** + * @pps_long_94_reserved: + * PPS 94, 95, 96, 97 - Reserved + */ + u32 pps_long_94_reserved; + /** + * @pps_long_98_reserved: + * PPS 98, 99, 100, 101 - Reserved + */ + u32 pps_long_98_reserved; + /** + * @pps_long_102_reserved: + * PPS 102, 103, 104, 105 - Reserved + */ + u32 pps_long_102_reserved; + /** + * @pps_long_106_reserved: + * PPS 106, 107, 108, 109 - reserved + */ + u32 pps_long_106_reserved; + /** + * @pps_long_110_reserved: + * PPS 110, 111, 112, 113 - reserved + */ + u32 pps_long_110_reserved; + /** + * @pps_long_114_reserved: + * PPS 114 - 117 - reserved + */ + u32 pps_long_114_reserved; + /** + * @pps_long_118_reserved: + * PPS 118 - 121 - reserved + */ + u32 pps_long_118_reserved; + /** + * @pps_long_122_reserved: + * PPS 122- 125 - reserved + */ + u32 pps_long_122_reserved; + /** + * @pps_short_126_reserved: + * PPS 126, 127 - reserved + */ + __be16 pps_short_126_reserved; +} __packed; + +/** + * struct drm_dsc_pps_infoframe - DSC infoframe carrying the Picture Parameter + * Set Metadata + * + * This structure represents the DSC PPS infoframe required to send the Picture + * Parameter Set metadata required before enabling VESA Display Stream + * Compression. This is based on the DP Secondary Data Packet structure and + * comprises of SDP Header as defined &struct dp_sdp_header in drm_dp_helper.h + * and PPS payload defined in &struct drm_dsc_picture_parameter_set. + * + * @pps_header: Header for PPS as per DP SDP header format of type + * &struct dp_sdp_header + * @pps_payload: PPS payload fields as per DSC specification Table 4-1 + * as represented in &struct drm_dsc_picture_parameter_set + */ +struct drm_dsc_pps_infoframe { + struct dp_sdp_header pps_header; + struct drm_dsc_picture_parameter_set pps_payload; +} __packed; + +#endif /* _DRM_DSC_H_ */ diff --git a/include/drm/display/drm_dsc_helper.h b/include/drm/display/drm_dsc_helper.h new file mode 100644 index 000000000000..8b41edbbabab --- /dev/null +++ b/include/drm/display/drm_dsc_helper.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: MIT + * Copyright (C) 2018 Intel Corp. + * + * Authors: + * Manasi Navare + */ + +#ifndef DRM_DSC_HELPER_H_ +#define DRM_DSC_HELPER_H_ + +#include + +void drm_dsc_dp_pps_header_init(struct dp_sdp_header *pps_header); +int drm_dsc_dp_rc_buffer_size(u8 rc_buffer_block_size, u8 rc_buffer_size); +void drm_dsc_pps_payload_pack(struct drm_dsc_picture_parameter_set *pps_sdp, + const struct drm_dsc_config *dsc_cfg); +int drm_dsc_compute_rc_parameters(struct drm_dsc_config *vdsc_cfg); + +#endif /* _DRM_DSC_HELPER_H_ */ + diff --git a/include/drm/drm_dsc.h b/include/drm/drm_dsc.h deleted file mode 100644 index 84e3d11cc1bb..000000000000 --- a/include/drm/drm_dsc.h +++ /dev/null @@ -1,611 +0,0 @@ -/* SPDX-License-Identifier: MIT - * Copyright (C) 2018 Intel Corp. - * - * Authors: - * Manasi Navare - */ - -#ifndef DRM_DSC_H_ -#define DRM_DSC_H_ - -#include - -/* VESA Display Stream Compression DSC 1.2 constants */ -#define DSC_NUM_BUF_RANGES 15 -#define DSC_MUX_WORD_SIZE_8_10_BPC 48 -#define DSC_MUX_WORD_SIZE_12_BPC 64 -#define DSC_RC_PIXELS_PER_GROUP 3 -#define DSC_SCALE_DECREMENT_INTERVAL_MAX 4095 -#define DSC_RANGE_BPG_OFFSET_MASK 0x3f - -/* DSC Rate Control Constants */ -#define DSC_RC_MODEL_SIZE_CONST 8192 -#define DSC_RC_EDGE_FACTOR_CONST 6 -#define DSC_RC_TGT_OFFSET_HI_CONST 3 -#define DSC_RC_TGT_OFFSET_LO_CONST 3 - -/* DSC PPS constants and macros */ -#define DSC_PPS_VERSION_MAJOR_SHIFT 4 -#define DSC_PPS_BPC_SHIFT 4 -#define DSC_PPS_MSB_SHIFT 8 -#define DSC_PPS_LSB_MASK (0xFF << 0) -#define DSC_PPS_BPP_HIGH_MASK (0x3 << 8) -#define DSC_PPS_VBR_EN_SHIFT 2 -#define DSC_PPS_SIMPLE422_SHIFT 3 -#define DSC_PPS_CONVERT_RGB_SHIFT 4 -#define DSC_PPS_BLOCK_PRED_EN_SHIFT 5 -#define DSC_PPS_INIT_XMIT_DELAY_HIGH_MASK (0x3 << 8) -#define DSC_PPS_SCALE_DEC_INT_HIGH_MASK (0xF << 8) -#define DSC_PPS_RC_TGT_OFFSET_HI_SHIFT 4 -#define DSC_PPS_RC_RANGE_MINQP_SHIFT 11 -#define DSC_PPS_RC_RANGE_MAXQP_SHIFT 6 -#define DSC_PPS_NATIVE_420_SHIFT 1 -#define DSC_1_2_MAX_LINEBUF_DEPTH_BITS 16 -#define DSC_1_2_MAX_LINEBUF_DEPTH_VAL 0 -#define DSC_1_1_MAX_LINEBUF_DEPTH_BITS 13 - -/** - * struct drm_dsc_rc_range_parameters - DSC Rate Control range parameters - * - * This defines different rate control parameters used by the DSC engine - * to compress the frame. - */ -struct drm_dsc_rc_range_parameters { - /** - * @range_min_qp: Min Quantization Parameters allowed for this range - */ - u8 range_min_qp; - /** - * @range_max_qp: Max Quantization Parameters allowed for this range - */ - u8 range_max_qp; - /** - * @range_bpg_offset: - * Bits/group offset to apply to target for this group - */ - u8 range_bpg_offset; -}; - -/** - * struct drm_dsc_config - Parameters required to configure DSC - * - * Driver populates this structure with all the parameters required - * to configure the display stream compression on the source. - */ -struct drm_dsc_config { - /** - * @line_buf_depth: - * Bits per component for previous reconstructed line buffer - */ - u8 line_buf_depth; - /** - * @bits_per_component: Bits per component to code (8/10/12) - */ - u8 bits_per_component; - /** - * @convert_rgb: - * Flag to indicate if RGB - YCoCg conversion is needed - * True if RGB input, False if YCoCg input - */ - bool convert_rgb; - /** - * @slice_count: Number fo slices per line used by the DSC encoder - */ - u8 slice_count; - /** - * @slice_width: Width of each slice in pixels - */ - u16 slice_width; - /** - * @slice_height: Slice height in pixels - */ - u16 slice_height; - /** - * @simple_422: True if simple 4_2_2 mode is enabled else False - */ - bool simple_422; - /** - * @pic_width: Width of the input display frame in pixels - */ - u16 pic_width; - /** - * @pic_height: Vertical height of the input display frame - */ - u16 pic_height; - /** - * @rc_tgt_offset_high: - * Offset to bits/group used by RC to determine QP adjustment - */ - u8 rc_tgt_offset_high; - /** - * @rc_tgt_offset_low: - * Offset to bits/group used by RC to determine QP adjustment - */ - u8 rc_tgt_offset_low; - /** - * @bits_per_pixel: - * Target bits per pixel with 4 fractional bits, bits_per_pixel << 4 - */ - u16 bits_per_pixel; - /** - * @rc_edge_factor: - * Factor to determine if an edge is present based on the bits produced - */ - u8 rc_edge_factor; - /** - * @rc_quant_incr_limit1: - * Slow down incrementing once the range reaches this value - */ - u8 rc_quant_incr_limit1; - /** - * @rc_quant_incr_limit0: - * Slow down incrementing once the range reaches this value - */ - u8 rc_quant_incr_limit0; - /** - * @initial_xmit_delay: - * Number of pixels to delay the initial transmission - */ - u16 initial_xmit_delay; - /** - * @initial_dec_delay: - * Initial decoder delay, number of pixel times that the decoder - * accumulates data in its rate buffer before starting to decode - * and output pixels. - */ - u16 initial_dec_delay; - /** - * @block_pred_enable: - * True if block prediction is used to code any groups within the - * picture. False if BP not used - */ - bool block_pred_enable; - /** - * @first_line_bpg_offset: - * Number of additional bits allocated for each group on the first - * line of slice. - */ - u8 first_line_bpg_offset; - /** - * @initial_offset: Value to use for RC model offset at slice start - */ - u16 initial_offset; - /** - * @rc_buf_thresh: Thresholds defining each of the buffer ranges - */ - u16 rc_buf_thresh[DSC_NUM_BUF_RANGES - 1]; - /** - * @rc_range_params: - * Parameters for each of the RC ranges defined in - * &struct drm_dsc_rc_range_parameters - */ - struct drm_dsc_rc_range_parameters rc_range_params[DSC_NUM_BUF_RANGES]; - /** - * @rc_model_size: Total size of RC model - */ - u16 rc_model_size; - /** - * @flatness_min_qp: Minimum QP where flatness information is sent - */ - u8 flatness_min_qp; - /** - * @flatness_max_qp: Maximum QP where flatness information is sent - */ - u8 flatness_max_qp; - /** - * @initial_scale_value: Initial value for the scale factor - */ - u8 initial_scale_value; - /** - * @scale_decrement_interval: - * Specifies number of group times between decrementing the scale factor - * at beginning of a slice. - */ - u16 scale_decrement_interval; - /** - * @scale_increment_interval: - * Number of group times between incrementing the scale factor value - * used at the beginning of a slice. - */ - u16 scale_increment_interval; - /** - * @nfl_bpg_offset: Non first line BPG offset to be used - */ - u16 nfl_bpg_offset; - /** - * @slice_bpg_offset: BPG offset used to enforce slice bit - */ - u16 slice_bpg_offset; - /** - * @final_offset: Final RC linear transformation offset value - */ - u16 final_offset; - /** - * @vbr_enable: True if VBR mode is enabled, false if disabled - */ - bool vbr_enable; - /** - * @mux_word_size: Mux word size (in bits) for SSM mode - */ - u8 mux_word_size; - /** - * @slice_chunk_size: - * The (max) size in bytes of the "chunks" that are used in slice - * multiplexing. - */ - u16 slice_chunk_size; - /** - * @rc_bits: Rate control buffer size in bits - */ - u16 rc_bits; - /** - * @dsc_version_minor: DSC minor version - */ - u8 dsc_version_minor; - /** - * @dsc_version_major: DSC major version - */ - u8 dsc_version_major; - /** - * @native_422: True if Native 4:2:2 supported, else false - */ - bool native_422; - /** - * @native_420: True if Native 4:2:0 supported else false. - */ - bool native_420; - /** - * @second_line_bpg_offset: - * Additional bits/grp for seconnd line of slice for native 4:2:0 - */ - u8 second_line_bpg_offset; - /** - * @nsl_bpg_offset: - * Num of bits deallocated for each grp that is not in second line of - * slice - */ - u16 nsl_bpg_offset; - /** - * @second_line_offset_adj: - * Offset adjustment for second line in Native 4:2:0 mode - */ - u16 second_line_offset_adj; -}; - -/** - * struct drm_dsc_picture_parameter_set - Represents 128 bytes of - * Picture Parameter Set - * - * The VESA DSC standard defines picture parameter set (PPS) which display - * stream compression encoders must communicate to decoders. - * The PPS is encapsulated in 128 bytes (PPS 0 through PPS 127). The fields in - * this structure are as per Table 4.1 in Vesa DSC specification v1.1/v1.2. - * The PPS fields that span over more than a byte should be stored in Big Endian - * format. - */ -struct drm_dsc_picture_parameter_set { - /** - * @dsc_version: - * PPS0[3:0] - dsc_version_minor: Contains Minor version of DSC - * PPS0[7:4] - dsc_version_major: Contains major version of DSC - */ - u8 dsc_version; - /** - * @pps_identifier: - * PPS1[7:0] - Application specific identifier that can be - * used to differentiate between different PPS tables. - */ - u8 pps_identifier; - /** - * @pps_reserved: - * PPS2[7:0]- RESERVED Byte - */ - u8 pps_reserved; - /** - * @pps_3: - * PPS3[3:0] - linebuf_depth: Contains linebuffer bit depth used to - * generate the bitstream. (0x0 - 16 bits for DSC 1.2, 0x8 - 8 bits, - * 0xA - 10 bits, 0xB - 11 bits, 0xC - 12 bits, 0xD - 13 bits, - * 0xE - 14 bits for DSC1.2, 0xF - 14 bits for DSC 1.2. - * PPS3[7:4] - bits_per_component: Bits per component for the original - * pixels of the encoded picture. - * 0x0 = 16bpc (allowed only when dsc_version_minor = 0x2) - * 0x8 = 8bpc, 0xA = 10bpc, 0xC = 12bpc, 0xE = 14bpc (also - * allowed only when dsc_minor_version = 0x2) - */ - u8 pps_3; - /** - * @pps_4: - * PPS4[1:0] -These are the most significant 2 bits of - * compressed BPP bits_per_pixel[9:0] syntax element. - * PPS4[2] - vbr_enable: 0 = VBR disabled, 1 = VBR enabled - * PPS4[3] - simple_422: Indicates if decoder drops samples to - * reconstruct the 4:2:2 picture. - * PPS4[4] - Convert_rgb: Indicates if DSC color space conversion is - * active. - * PPS4[5] - blobk_pred_enable: Indicates if BP is used to code any - * groups in picture - * PPS4[7:6] - Reseved bits - */ - u8 pps_4; - /** - * @bits_per_pixel_low: - * PPS5[7:0] - This indicates the lower significant 8 bits of - * the compressed BPP bits_per_pixel[9:0] element. - */ - u8 bits_per_pixel_low; - /** - * @pic_height: - * PPS6[7:0], PPS7[7:0] -pic_height: Specifies the number of pixel rows - * within the raster. - */ - __be16 pic_height; - /** - * @pic_width: - * PPS8[7:0], PPS9[7:0] - pic_width: Number of pixel columns within - * the raster. - */ - __be16 pic_width; - /** - * @slice_height: - * PPS10[7:0], PPS11[7:0] - Slice height in units of pixels. - */ - __be16 slice_height; - /** - * @slice_width: - * PPS12[7:0], PPS13[7:0] - Slice width in terms of pixels. - */ - __be16 slice_width; - /** - * @chunk_size: - * PPS14[7:0], PPS15[7:0] - Size in units of bytes of the chunks - * that are used for slice multiplexing. - */ - __be16 chunk_size; - /** - * @initial_xmit_delay_high: - * PPS16[1:0] - Most Significant two bits of initial transmission delay. - * It specifies the number of pixel times that the encoder waits before - * transmitting data from its rate buffer. - * PPS16[7:2] - Reserved - */ - u8 initial_xmit_delay_high; - /** - * @initial_xmit_delay_low: - * PPS17[7:0] - Least significant 8 bits of initial transmission delay. - */ - u8 initial_xmit_delay_low; - /** - * @initial_dec_delay: - * - * PPS18[7:0], PPS19[7:0] - Initial decoding delay which is the number - * of pixel times that the decoder accumulates data in its rate buffer - * before starting to decode and output pixels. - */ - __be16 initial_dec_delay; - /** - * @pps20_reserved: - * - * PPS20[7:0] - Reserved - */ - u8 pps20_reserved; - /** - * @initial_scale_value: - * PPS21[5:0] - Initial rcXformScale factor used at beginning - * of a slice. - * PPS21[7:6] - Reserved - */ - u8 initial_scale_value; - /** - * @scale_increment_interval: - * PPS22[7:0], PPS23[7:0] - Number of group times between incrementing - * the rcXformScale factor at end of a slice. - */ - __be16 scale_increment_interval; - /** - * @scale_decrement_interval_high: - * PPS24[3:0] - Higher 4 bits indicating number of group times between - * decrementing the rcXformScale factor at beginning of a slice. - * PPS24[7:4] - Reserved - */ - u8 scale_decrement_interval_high; - /** - * @scale_decrement_interval_low: - * PPS25[7:0] - Lower 8 bits of scale decrement interval - */ - u8 scale_decrement_interval_low; - /** - * @pps26_reserved: - * PPS26[7:0] - */ - u8 pps26_reserved; - /** - * @first_line_bpg_offset: - * PPS27[4:0] - Number of additional bits that are allocated - * for each group on first line of a slice. - * PPS27[7:5] - Reserved - */ - u8 first_line_bpg_offset; - /** - * @nfl_bpg_offset: - * PPS28[7:0], PPS29[7:0] - Number of bits including frac bits - * deallocated for each group for groups after the first line of slice. - */ - __be16 nfl_bpg_offset; - /** - * @slice_bpg_offset: - * PPS30, PPS31[7:0] - Number of bits that are deallocated for each - * group to enforce the slice constraint. - */ - __be16 slice_bpg_offset; - /** - * @initial_offset: - * PPS32,33[7:0] - Initial value for rcXformOffset - */ - __be16 initial_offset; - /** - * @final_offset: - * PPS34,35[7:0] - Maximum end-of-slice value for rcXformOffset - */ - __be16 final_offset; - /** - * @flatness_min_qp: - * PPS36[4:0] - Minimum QP at which flatness is signaled and - * flatness QP adjustment is made. - * PPS36[7:5] - Reserved - */ - u8 flatness_min_qp; - /** - * @flatness_max_qp: - * PPS37[4:0] - Max QP at which flatness is signalled and - * the flatness adjustment is made. - * PPS37[7:5] - Reserved - */ - u8 flatness_max_qp; - /** - * @rc_model_size: - * PPS38,39[7:0] - Number of bits within RC Model. - */ - __be16 rc_model_size; - /** - * @rc_edge_factor: - * PPS40[3:0] - Ratio of current activity vs, previous - * activity to determine presence of edge. - * PPS40[7:4] - Reserved - */ - u8 rc_edge_factor; - /** - * @rc_quant_incr_limit0: - * PPS41[4:0] - QP threshold used in short term RC - * PPS41[7:5] - Reserved - */ - u8 rc_quant_incr_limit0; - /** - * @rc_quant_incr_limit1: - * PPS42[4:0] - QP threshold used in short term RC - * PPS42[7:5] - Reserved - */ - u8 rc_quant_incr_limit1; - /** - * @rc_tgt_offset: - * PPS43[3:0] - Lower end of the variability range around the target - * bits per group that is allowed by short term RC. - * PPS43[7:4]- Upper end of the variability range around the target - * bits per group that i allowed by short term rc. - */ - u8 rc_tgt_offset; - /** - * @rc_buf_thresh: - * PPS44[7:0] - PPS57[7:0] - Specifies the thresholds in RC model for - * the 15 ranges defined by 14 thresholds. - */ - u8 rc_buf_thresh[DSC_NUM_BUF_RANGES - 1]; - /** - * @rc_range_parameters: - * PPS58[7:0] - PPS87[7:0] - * Parameters that correspond to each of the 15 ranges. - */ - __be16 rc_range_parameters[DSC_NUM_BUF_RANGES]; - /** - * @native_422_420: - * PPS88[0] - 0 = Native 4:2:2 not used - * 1 = Native 4:2:2 used - * PPS88[1] - 0 = Native 4:2:0 not use - * 1 = Native 4:2:0 used - * PPS88[7:2] - Reserved 6 bits - */ - u8 native_422_420; - /** - * @second_line_bpg_offset: - * PPS89[4:0] - Additional bits/group budget for the - * second line of a slice in Native 4:2:0 mode. - * Set to 0 if DSC minor version is 1 or native420 is 0. - * PPS89[7:5] - Reserved - */ - u8 second_line_bpg_offset; - /** - * @nsl_bpg_offset: - * PPS90[7:0], PPS91[7:0] - Number of bits that are deallocated - * for each group that is not in the second line of a slice. - */ - __be16 nsl_bpg_offset; - /** - * @second_line_offset_adj: - * PPS92[7:0], PPS93[7:0] - Used as offset adjustment for the second - * line in Native 4:2:0 mode. - */ - __be16 second_line_offset_adj; - /** - * @pps_long_94_reserved: - * PPS 94, 95, 96, 97 - Reserved - */ - u32 pps_long_94_reserved; - /** - * @pps_long_98_reserved: - * PPS 98, 99, 100, 101 - Reserved - */ - u32 pps_long_98_reserved; - /** - * @pps_long_102_reserved: - * PPS 102, 103, 104, 105 - Reserved - */ - u32 pps_long_102_reserved; - /** - * @pps_long_106_reserved: - * PPS 106, 107, 108, 109 - reserved - */ - u32 pps_long_106_reserved; - /** - * @pps_long_110_reserved: - * PPS 110, 111, 112, 113 - reserved - */ - u32 pps_long_110_reserved; - /** - * @pps_long_114_reserved: - * PPS 114 - 117 - reserved - */ - u32 pps_long_114_reserved; - /** - * @pps_long_118_reserved: - * PPS 118 - 121 - reserved - */ - u32 pps_long_118_reserved; - /** - * @pps_long_122_reserved: - * PPS 122- 125 - reserved - */ - u32 pps_long_122_reserved; - /** - * @pps_short_126_reserved: - * PPS 126, 127 - reserved - */ - __be16 pps_short_126_reserved; -} __packed; - -/** - * struct drm_dsc_pps_infoframe - DSC infoframe carrying the Picture Parameter - * Set Metadata - * - * This structure represents the DSC PPS infoframe required to send the Picture - * Parameter Set metadata required before enabling VESA Display Stream - * Compression. This is based on the DP Secondary Data Packet structure and - * comprises of SDP Header as defined &struct dp_sdp_header in drm_dp_helper.h - * and PPS payload defined in &struct drm_dsc_picture_parameter_set. - * - * @pps_header: Header for PPS as per DP SDP header format of type - * &struct dp_sdp_header - * @pps_payload: PPS payload fields as per DSC specification Table 4-1 - * as represented in &struct drm_dsc_picture_parameter_set - */ -struct drm_dsc_pps_infoframe { - struct dp_sdp_header pps_header; - struct drm_dsc_picture_parameter_set pps_payload; -} __packed; - -void drm_dsc_dp_pps_header_init(struct dp_sdp_header *pps_header); -int drm_dsc_dp_rc_buffer_size(u8 rc_buffer_block_size, u8 rc_buffer_size); -void drm_dsc_pps_payload_pack(struct drm_dsc_picture_parameter_set *pps_sdp, - const struct drm_dsc_config *dsc_cfg); -int drm_dsc_compute_rc_parameters(struct drm_dsc_config *vdsc_cfg); - -#endif /* _DRM_DSC_H_ */ -- cgit v1.2.3 From 6a99099fe1d6c46cbcd74298eeb386c4b9048f77 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 21 Apr 2022 09:31:06 +0200 Subject: drm/display: Move HDCP helpers into display-helper module Move DRM's HDCP helper library into the display/ subdirectory and add it to DRM's display helpers. Split the header file into core and helpers. Update all affected drivers. No functional changes. v3: * fix Kconfig dependencies v2: * fix include statements (Jani, Javier) * update Kconfig symbols Signed-off-by: Thomas Zimmermann Reviewed-by: Javier Martinez Canillas Link: https://patchwork.freedesktop.org/patch/msgid/20220421073108.19226-7-tzimmermann@suse.de --- include/drm/display/drm_hdcp.h | 298 ++++++++++++++++++++++++++++++++ include/drm/display/drm_hdcp_helper.h | 22 +++ include/drm/drm_hdcp.h | 308 ---------------------------------- include/drm/i915_mei_hdcp_interface.h | 2 +- 4 files changed, 321 insertions(+), 309 deletions(-) create mode 100644 include/drm/display/drm_hdcp.h create mode 100644 include/drm/display/drm_hdcp_helper.h delete mode 100644 include/drm/drm_hdcp.h (limited to 'include') diff --git a/include/drm/display/drm_hdcp.h b/include/drm/display/drm_hdcp.h new file mode 100644 index 000000000000..96a99b1377c0 --- /dev/null +++ b/include/drm/display/drm_hdcp.h @@ -0,0 +1,298 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright (C) 2017 Google, Inc. + * + * Authors: + * Sean Paul + */ + +#ifndef _DRM_HDCP_H_ +#define _DRM_HDCP_H_ + +#include + +/* Period of hdcp checks (to ensure we're still authenticated) */ +#define DRM_HDCP_CHECK_PERIOD_MS (128 * 16) +#define DRM_HDCP2_CHECK_PERIOD_MS 500 + +/* Shared lengths/masks between HDMI/DVI/DisplayPort */ +#define DRM_HDCP_AN_LEN 8 +#define DRM_HDCP_BSTATUS_LEN 2 +#define DRM_HDCP_KSV_LEN 5 +#define DRM_HDCP_RI_LEN 2 +#define DRM_HDCP_V_PRIME_PART_LEN 4 +#define DRM_HDCP_V_PRIME_NUM_PARTS 5 +#define DRM_HDCP_NUM_DOWNSTREAM(x) (x & 0x7f) +#define DRM_HDCP_MAX_CASCADE_EXCEEDED(x) (x & BIT(3)) +#define DRM_HDCP_MAX_DEVICE_EXCEEDED(x) (x & BIT(7)) + +/* Slave address for the HDCP registers in the receiver */ +#define DRM_HDCP_DDC_ADDR 0x3A + +/* Value to use at the end of the SHA-1 bytestream used for repeaters */ +#define DRM_HDCP_SHA1_TERMINATOR 0x80 + +/* HDCP register offsets for HDMI/DVI devices */ +#define DRM_HDCP_DDC_BKSV 0x00 +#define DRM_HDCP_DDC_RI_PRIME 0x08 +#define DRM_HDCP_DDC_AKSV 0x10 +#define DRM_HDCP_DDC_AN 0x18 +#define DRM_HDCP_DDC_V_PRIME(h) (0x20 + h * 4) +#define DRM_HDCP_DDC_BCAPS 0x40 +#define DRM_HDCP_DDC_BCAPS_REPEATER_PRESENT BIT(6) +#define DRM_HDCP_DDC_BCAPS_KSV_FIFO_READY BIT(5) +#define DRM_HDCP_DDC_BSTATUS 0x41 +#define DRM_HDCP_DDC_KSV_FIFO 0x43 + +#define DRM_HDCP_1_4_SRM_ID 0x8 +#define DRM_HDCP_1_4_VRL_LENGTH_SIZE 3 +#define DRM_HDCP_1_4_DCP_SIG_SIZE 40 + +/* Protocol message definition for HDCP2.2 specification */ +/* + * Protected content streams are classified into 2 types: + * - Type0: Can be transmitted with HDCP 1.4+ + * - Type1: Can be transmitted with HDCP 2.2+ + */ +#define HDCP_STREAM_TYPE0 0x00 +#define HDCP_STREAM_TYPE1 0x01 + +/* HDCP2.2 Msg IDs */ +#define HDCP_2_2_NULL_MSG 1 +#define HDCP_2_2_AKE_INIT 2 +#define HDCP_2_2_AKE_SEND_CERT 3 +#define HDCP_2_2_AKE_NO_STORED_KM 4 +#define HDCP_2_2_AKE_STORED_KM 5 +#define HDCP_2_2_AKE_SEND_HPRIME 7 +#define HDCP_2_2_AKE_SEND_PAIRING_INFO 8 +#define HDCP_2_2_LC_INIT 9 +#define HDCP_2_2_LC_SEND_LPRIME 10 +#define HDCP_2_2_SKE_SEND_EKS 11 +#define HDCP_2_2_REP_SEND_RECVID_LIST 12 +#define HDCP_2_2_REP_SEND_ACK 15 +#define HDCP_2_2_REP_STREAM_MANAGE 16 +#define HDCP_2_2_REP_STREAM_READY 17 + +#define HDCP_2_2_RTX_LEN 8 +#define HDCP_2_2_RRX_LEN 8 + +#define HDCP_2_2_K_PUB_RX_MOD_N_LEN 128 +#define HDCP_2_2_K_PUB_RX_EXP_E_LEN 3 +#define HDCP_2_2_K_PUB_RX_LEN (HDCP_2_2_K_PUB_RX_MOD_N_LEN + \ + HDCP_2_2_K_PUB_RX_EXP_E_LEN) + +#define HDCP_2_2_DCP_LLC_SIG_LEN 384 + +#define HDCP_2_2_E_KPUB_KM_LEN 128 +#define HDCP_2_2_E_KH_KM_M_LEN (16 + 16) +#define HDCP_2_2_H_PRIME_LEN 32 +#define HDCP_2_2_E_KH_KM_LEN 16 +#define HDCP_2_2_RN_LEN 8 +#define HDCP_2_2_L_PRIME_LEN 32 +#define HDCP_2_2_E_DKEY_KS_LEN 16 +#define HDCP_2_2_RIV_LEN 8 +#define HDCP_2_2_SEQ_NUM_LEN 3 +#define HDCP_2_2_V_PRIME_HALF_LEN (HDCP_2_2_L_PRIME_LEN / 2) +#define HDCP_2_2_RECEIVER_ID_LEN DRM_HDCP_KSV_LEN +#define HDCP_2_2_MAX_DEVICE_COUNT 31 +#define HDCP_2_2_RECEIVER_IDS_MAX_LEN (HDCP_2_2_RECEIVER_ID_LEN * \ + HDCP_2_2_MAX_DEVICE_COUNT) +#define HDCP_2_2_MPRIME_LEN 32 + +/* Following Macros take a byte at a time for bit(s) masking */ +/* + * TODO: HDCP_2_2_MAX_CONTENT_STREAMS_CNT is based upon actual + * H/W MST streams capacity. + * This required to be moved out to platform specific header. + */ +#define HDCP_2_2_MAX_CONTENT_STREAMS_CNT 4 +#define HDCP_2_2_TXCAP_MASK_LEN 2 +#define HDCP_2_2_RXCAPS_LEN 3 +#define HDCP_2_2_RX_REPEATER(x) ((x) & BIT(0)) +#define HDCP_2_2_DP_HDCP_CAPABLE(x) ((x) & BIT(1)) +#define HDCP_2_2_RXINFO_LEN 2 + +/* HDCP1.x compliant device in downstream */ +#define HDCP_2_2_HDCP1_DEVICE_CONNECTED(x) ((x) & BIT(0)) + +/* HDCP2.0 Compliant repeater in downstream */ +#define HDCP_2_2_HDCP_2_0_REP_CONNECTED(x) ((x) & BIT(1)) +#define HDCP_2_2_MAX_CASCADE_EXCEEDED(x) ((x) & BIT(2)) +#define HDCP_2_2_MAX_DEVS_EXCEEDED(x) ((x) & BIT(3)) +#define HDCP_2_2_DEV_COUNT_LO(x) (((x) & (0xF << 4)) >> 4) +#define HDCP_2_2_DEV_COUNT_HI(x) ((x) & BIT(0)) +#define HDCP_2_2_DEPTH(x) (((x) & (0x7 << 1)) >> 1) + +struct hdcp2_cert_rx { + u8 receiver_id[HDCP_2_2_RECEIVER_ID_LEN]; + u8 kpub_rx[HDCP_2_2_K_PUB_RX_LEN]; + u8 reserved[2]; + u8 dcp_signature[HDCP_2_2_DCP_LLC_SIG_LEN]; +} __packed; + +struct hdcp2_streamid_type { + u8 stream_id; + u8 stream_type; +} __packed; + +/* + * The TxCaps field specified in the HDCP HDMI, DP specs + * This field is big endian as specified in the errata. + */ +struct hdcp2_tx_caps { + /* Transmitter must set this to 0x2 */ + u8 version; + + /* Reserved for HDCP and DP Spec. Read as Zero */ + u8 tx_cap_mask[HDCP_2_2_TXCAP_MASK_LEN]; +} __packed; + +/* Main structures for HDCP2.2 protocol communication */ +struct hdcp2_ake_init { + u8 msg_id; + u8 r_tx[HDCP_2_2_RTX_LEN]; + struct hdcp2_tx_caps tx_caps; +} __packed; + +struct hdcp2_ake_send_cert { + u8 msg_id; + struct hdcp2_cert_rx cert_rx; + u8 r_rx[HDCP_2_2_RRX_LEN]; + u8 rx_caps[HDCP_2_2_RXCAPS_LEN]; +} __packed; + +struct hdcp2_ake_no_stored_km { + u8 msg_id; + u8 e_kpub_km[HDCP_2_2_E_KPUB_KM_LEN]; +} __packed; + +struct hdcp2_ake_stored_km { + u8 msg_id; + u8 e_kh_km_m[HDCP_2_2_E_KH_KM_M_LEN]; +} __packed; + +struct hdcp2_ake_send_hprime { + u8 msg_id; + u8 h_prime[HDCP_2_2_H_PRIME_LEN]; +} __packed; + +struct hdcp2_ake_send_pairing_info { + u8 msg_id; + u8 e_kh_km[HDCP_2_2_E_KH_KM_LEN]; +} __packed; + +struct hdcp2_lc_init { + u8 msg_id; + u8 r_n[HDCP_2_2_RN_LEN]; +} __packed; + +struct hdcp2_lc_send_lprime { + u8 msg_id; + u8 l_prime[HDCP_2_2_L_PRIME_LEN]; +} __packed; + +struct hdcp2_ske_send_eks { + u8 msg_id; + u8 e_dkey_ks[HDCP_2_2_E_DKEY_KS_LEN]; + u8 riv[HDCP_2_2_RIV_LEN]; +} __packed; + +struct hdcp2_rep_send_receiverid_list { + u8 msg_id; + u8 rx_info[HDCP_2_2_RXINFO_LEN]; + u8 seq_num_v[HDCP_2_2_SEQ_NUM_LEN]; + u8 v_prime[HDCP_2_2_V_PRIME_HALF_LEN]; + u8 receiver_ids[HDCP_2_2_RECEIVER_IDS_MAX_LEN]; +} __packed; + +struct hdcp2_rep_send_ack { + u8 msg_id; + u8 v[HDCP_2_2_V_PRIME_HALF_LEN]; +} __packed; + +struct hdcp2_rep_stream_manage { + u8 msg_id; + u8 seq_num_m[HDCP_2_2_SEQ_NUM_LEN]; + __be16 k; + struct hdcp2_streamid_type streams[HDCP_2_2_MAX_CONTENT_STREAMS_CNT]; +} __packed; + +struct hdcp2_rep_stream_ready { + u8 msg_id; + u8 m_prime[HDCP_2_2_MPRIME_LEN]; +} __packed; + +/* HDCP2.2 TIMEOUTs in mSec */ +#define HDCP_2_2_CERT_TIMEOUT_MS 100 +#define HDCP_2_2_DP_CERT_READ_TIMEOUT_MS 110 +#define HDCP_2_2_HPRIME_NO_PAIRED_TIMEOUT_MS 1000 +#define HDCP_2_2_HPRIME_PAIRED_TIMEOUT_MS 200 +#define HDCP_2_2_DP_HPRIME_READ_TIMEOUT_MS 7 +#define HDCP_2_2_PAIRING_TIMEOUT_MS 200 +#define HDCP_2_2_DP_PAIRING_READ_TIMEOUT_MS 5 +#define HDCP_2_2_HDMI_LPRIME_TIMEOUT_MS 20 +#define HDCP_2_2_DP_LPRIME_TIMEOUT_MS 16 +#define HDCP_2_2_RECVID_LIST_TIMEOUT_MS 3000 +#define HDCP_2_2_STREAM_READY_TIMEOUT_MS 100 + +/* HDMI HDCP2.2 Register Offsets */ +#define HDCP_2_2_HDMI_REG_VER_OFFSET 0x50 +#define HDCP_2_2_HDMI_REG_WR_MSG_OFFSET 0x60 +#define HDCP_2_2_HDMI_REG_RXSTATUS_OFFSET 0x70 +#define HDCP_2_2_HDMI_REG_RD_MSG_OFFSET 0x80 +#define HDCP_2_2_HDMI_REG_DBG_OFFSET 0xC0 + +#define HDCP_2_2_HDMI_SUPPORT_MASK BIT(2) +#define HDCP_2_2_RX_CAPS_VERSION_VAL 0x02 +#define HDCP_2_2_SEQ_NUM_MAX 0xFFFFFF +#define HDCP_2_2_DELAY_BEFORE_ENCRYPTION_EN 200 + +/* Below macros take a byte at a time and mask the bit(s) */ +#define HDCP_2_2_HDMI_RXSTATUS_LEN 2 +#define HDCP_2_2_HDMI_RXSTATUS_MSG_SZ_HI(x) ((x) & 0x3) +#define HDCP_2_2_HDMI_RXSTATUS_READY(x) ((x) & BIT(2)) +#define HDCP_2_2_HDMI_RXSTATUS_REAUTH_REQ(x) ((x) & BIT(3)) + +/* + * Helper functions to convert 24bit big endian hdcp sequence number to + * host format and back + */ +static inline +u32 drm_hdcp_be24_to_cpu(const u8 seq_num[HDCP_2_2_SEQ_NUM_LEN]) +{ + return (u32)(seq_num[2] | seq_num[1] << 8 | seq_num[0] << 16); +} + +static inline +void drm_hdcp_cpu_to_be24(u8 seq_num[HDCP_2_2_SEQ_NUM_LEN], u32 val) +{ + seq_num[0] = val >> 16; + seq_num[1] = val >> 8; + seq_num[2] = val; +} + +#define DRM_HDCP_SRM_GEN1_MAX_BYTES (5 * 1024) +#define DRM_HDCP_1_4_SRM_ID 0x8 +#define DRM_HDCP_SRM_ID_MASK (0xF << 4) +#define DRM_HDCP_1_4_VRL_LENGTH_SIZE 3 +#define DRM_HDCP_1_4_DCP_SIG_SIZE 40 +#define DRM_HDCP_2_SRM_ID 0x9 +#define DRM_HDCP_2_INDICATOR 0x1 +#define DRM_HDCP_2_INDICATOR_MASK 0xF +#define DRM_HDCP_2_VRL_LENGTH_SIZE 3 +#define DRM_HDCP_2_DCP_SIG_SIZE 384 +#define DRM_HDCP_2_NO_OF_DEV_PLUS_RESERVED_SZ 4 +#define DRM_HDCP_2_KSV_COUNT_2_LSBITS(byte) (((byte) & 0xC0) >> 6) + +struct hdcp_srm_header { + u8 srm_id; + u8 reserved; + __be16 srm_version; + u8 srm_gen_no; +} __packed; + +/* Content Type classification for HDCP2.2 vs others */ +#define DRM_MODE_HDCP_CONTENT_TYPE0 0 +#define DRM_MODE_HDCP_CONTENT_TYPE1 1 + +#endif diff --git a/include/drm/display/drm_hdcp_helper.h b/include/drm/display/drm_hdcp_helper.h new file mode 100644 index 000000000000..8aaf87bf2735 --- /dev/null +++ b/include/drm/display/drm_hdcp_helper.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright (C) 2017 Google, Inc. + * + * Authors: + * Sean Paul + */ + +#ifndef _DRM_HDCP_HELPER_H_INCLUDED_ +#define _DRM_HDCP_HELPER_H_INCLUDED_ + +#include + +struct drm_device; +struct drm_connector; + +int drm_hdcp_check_ksvs_revoked(struct drm_device *dev, u8 *ksvs, u32 ksv_count); +int drm_connector_attach_content_protection_property(struct drm_connector *connector, + bool hdcp_content_type); +void drm_hdcp_update_content_protection(struct drm_connector *connector, u64 val); + +#endif diff --git a/include/drm/drm_hdcp.h b/include/drm/drm_hdcp.h deleted file mode 100644 index 0b1111e3228e..000000000000 --- a/include/drm/drm_hdcp.h +++ /dev/null @@ -1,308 +0,0 @@ -/* SPDX-License-Identifier: MIT */ -/* - * Copyright (C) 2017 Google, Inc. - * - * Authors: - * Sean Paul - */ - -#ifndef _DRM_HDCP_H_INCLUDED_ -#define _DRM_HDCP_H_INCLUDED_ - -#include - -/* Period of hdcp checks (to ensure we're still authenticated) */ -#define DRM_HDCP_CHECK_PERIOD_MS (128 * 16) -#define DRM_HDCP2_CHECK_PERIOD_MS 500 - -/* Shared lengths/masks between HDMI/DVI/DisplayPort */ -#define DRM_HDCP_AN_LEN 8 -#define DRM_HDCP_BSTATUS_LEN 2 -#define DRM_HDCP_KSV_LEN 5 -#define DRM_HDCP_RI_LEN 2 -#define DRM_HDCP_V_PRIME_PART_LEN 4 -#define DRM_HDCP_V_PRIME_NUM_PARTS 5 -#define DRM_HDCP_NUM_DOWNSTREAM(x) (x & 0x7f) -#define DRM_HDCP_MAX_CASCADE_EXCEEDED(x) (x & BIT(3)) -#define DRM_HDCP_MAX_DEVICE_EXCEEDED(x) (x & BIT(7)) - -/* Slave address for the HDCP registers in the receiver */ -#define DRM_HDCP_DDC_ADDR 0x3A - -/* Value to use at the end of the SHA-1 bytestream used for repeaters */ -#define DRM_HDCP_SHA1_TERMINATOR 0x80 - -/* HDCP register offsets for HDMI/DVI devices */ -#define DRM_HDCP_DDC_BKSV 0x00 -#define DRM_HDCP_DDC_RI_PRIME 0x08 -#define DRM_HDCP_DDC_AKSV 0x10 -#define DRM_HDCP_DDC_AN 0x18 -#define DRM_HDCP_DDC_V_PRIME(h) (0x20 + h * 4) -#define DRM_HDCP_DDC_BCAPS 0x40 -#define DRM_HDCP_DDC_BCAPS_REPEATER_PRESENT BIT(6) -#define DRM_HDCP_DDC_BCAPS_KSV_FIFO_READY BIT(5) -#define DRM_HDCP_DDC_BSTATUS 0x41 -#define DRM_HDCP_DDC_KSV_FIFO 0x43 - -#define DRM_HDCP_1_4_SRM_ID 0x8 -#define DRM_HDCP_1_4_VRL_LENGTH_SIZE 3 -#define DRM_HDCP_1_4_DCP_SIG_SIZE 40 - -/* Protocol message definition for HDCP2.2 specification */ -/* - * Protected content streams are classified into 2 types: - * - Type0: Can be transmitted with HDCP 1.4+ - * - Type1: Can be transmitted with HDCP 2.2+ - */ -#define HDCP_STREAM_TYPE0 0x00 -#define HDCP_STREAM_TYPE1 0x01 - -/* HDCP2.2 Msg IDs */ -#define HDCP_2_2_NULL_MSG 1 -#define HDCP_2_2_AKE_INIT 2 -#define HDCP_2_2_AKE_SEND_CERT 3 -#define HDCP_2_2_AKE_NO_STORED_KM 4 -#define HDCP_2_2_AKE_STORED_KM 5 -#define HDCP_2_2_AKE_SEND_HPRIME 7 -#define HDCP_2_2_AKE_SEND_PAIRING_INFO 8 -#define HDCP_2_2_LC_INIT 9 -#define HDCP_2_2_LC_SEND_LPRIME 10 -#define HDCP_2_2_SKE_SEND_EKS 11 -#define HDCP_2_2_REP_SEND_RECVID_LIST 12 -#define HDCP_2_2_REP_SEND_ACK 15 -#define HDCP_2_2_REP_STREAM_MANAGE 16 -#define HDCP_2_2_REP_STREAM_READY 17 - -#define HDCP_2_2_RTX_LEN 8 -#define HDCP_2_2_RRX_LEN 8 - -#define HDCP_2_2_K_PUB_RX_MOD_N_LEN 128 -#define HDCP_2_2_K_PUB_RX_EXP_E_LEN 3 -#define HDCP_2_2_K_PUB_RX_LEN (HDCP_2_2_K_PUB_RX_MOD_N_LEN + \ - HDCP_2_2_K_PUB_RX_EXP_E_LEN) - -#define HDCP_2_2_DCP_LLC_SIG_LEN 384 - -#define HDCP_2_2_E_KPUB_KM_LEN 128 -#define HDCP_2_2_E_KH_KM_M_LEN (16 + 16) -#define HDCP_2_2_H_PRIME_LEN 32 -#define HDCP_2_2_E_KH_KM_LEN 16 -#define HDCP_2_2_RN_LEN 8 -#define HDCP_2_2_L_PRIME_LEN 32 -#define HDCP_2_2_E_DKEY_KS_LEN 16 -#define HDCP_2_2_RIV_LEN 8 -#define HDCP_2_2_SEQ_NUM_LEN 3 -#define HDCP_2_2_V_PRIME_HALF_LEN (HDCP_2_2_L_PRIME_LEN / 2) -#define HDCP_2_2_RECEIVER_ID_LEN DRM_HDCP_KSV_LEN -#define HDCP_2_2_MAX_DEVICE_COUNT 31 -#define HDCP_2_2_RECEIVER_IDS_MAX_LEN (HDCP_2_2_RECEIVER_ID_LEN * \ - HDCP_2_2_MAX_DEVICE_COUNT) -#define HDCP_2_2_MPRIME_LEN 32 - -/* Following Macros take a byte at a time for bit(s) masking */ -/* - * TODO: HDCP_2_2_MAX_CONTENT_STREAMS_CNT is based upon actual - * H/W MST streams capacity. - * This required to be moved out to platform specific header. - */ -#define HDCP_2_2_MAX_CONTENT_STREAMS_CNT 4 -#define HDCP_2_2_TXCAP_MASK_LEN 2 -#define HDCP_2_2_RXCAPS_LEN 3 -#define HDCP_2_2_RX_REPEATER(x) ((x) & BIT(0)) -#define HDCP_2_2_DP_HDCP_CAPABLE(x) ((x) & BIT(1)) -#define HDCP_2_2_RXINFO_LEN 2 - -/* HDCP1.x compliant device in downstream */ -#define HDCP_2_2_HDCP1_DEVICE_CONNECTED(x) ((x) & BIT(0)) - -/* HDCP2.0 Compliant repeater in downstream */ -#define HDCP_2_2_HDCP_2_0_REP_CONNECTED(x) ((x) & BIT(1)) -#define HDCP_2_2_MAX_CASCADE_EXCEEDED(x) ((x) & BIT(2)) -#define HDCP_2_2_MAX_DEVS_EXCEEDED(x) ((x) & BIT(3)) -#define HDCP_2_2_DEV_COUNT_LO(x) (((x) & (0xF << 4)) >> 4) -#define HDCP_2_2_DEV_COUNT_HI(x) ((x) & BIT(0)) -#define HDCP_2_2_DEPTH(x) (((x) & (0x7 << 1)) >> 1) - -struct hdcp2_cert_rx { - u8 receiver_id[HDCP_2_2_RECEIVER_ID_LEN]; - u8 kpub_rx[HDCP_2_2_K_PUB_RX_LEN]; - u8 reserved[2]; - u8 dcp_signature[HDCP_2_2_DCP_LLC_SIG_LEN]; -} __packed; - -struct hdcp2_streamid_type { - u8 stream_id; - u8 stream_type; -} __packed; - -/* - * The TxCaps field specified in the HDCP HDMI, DP specs - * This field is big endian as specified in the errata. - */ -struct hdcp2_tx_caps { - /* Transmitter must set this to 0x2 */ - u8 version; - - /* Reserved for HDCP and DP Spec. Read as Zero */ - u8 tx_cap_mask[HDCP_2_2_TXCAP_MASK_LEN]; -} __packed; - -/* Main structures for HDCP2.2 protocol communication */ -struct hdcp2_ake_init { - u8 msg_id; - u8 r_tx[HDCP_2_2_RTX_LEN]; - struct hdcp2_tx_caps tx_caps; -} __packed; - -struct hdcp2_ake_send_cert { - u8 msg_id; - struct hdcp2_cert_rx cert_rx; - u8 r_rx[HDCP_2_2_RRX_LEN]; - u8 rx_caps[HDCP_2_2_RXCAPS_LEN]; -} __packed; - -struct hdcp2_ake_no_stored_km { - u8 msg_id; - u8 e_kpub_km[HDCP_2_2_E_KPUB_KM_LEN]; -} __packed; - -struct hdcp2_ake_stored_km { - u8 msg_id; - u8 e_kh_km_m[HDCP_2_2_E_KH_KM_M_LEN]; -} __packed; - -struct hdcp2_ake_send_hprime { - u8 msg_id; - u8 h_prime[HDCP_2_2_H_PRIME_LEN]; -} __packed; - -struct hdcp2_ake_send_pairing_info { - u8 msg_id; - u8 e_kh_km[HDCP_2_2_E_KH_KM_LEN]; -} __packed; - -struct hdcp2_lc_init { - u8 msg_id; - u8 r_n[HDCP_2_2_RN_LEN]; -} __packed; - -struct hdcp2_lc_send_lprime { - u8 msg_id; - u8 l_prime[HDCP_2_2_L_PRIME_LEN]; -} __packed; - -struct hdcp2_ske_send_eks { - u8 msg_id; - u8 e_dkey_ks[HDCP_2_2_E_DKEY_KS_LEN]; - u8 riv[HDCP_2_2_RIV_LEN]; -} __packed; - -struct hdcp2_rep_send_receiverid_list { - u8 msg_id; - u8 rx_info[HDCP_2_2_RXINFO_LEN]; - u8 seq_num_v[HDCP_2_2_SEQ_NUM_LEN]; - u8 v_prime[HDCP_2_2_V_PRIME_HALF_LEN]; - u8 receiver_ids[HDCP_2_2_RECEIVER_IDS_MAX_LEN]; -} __packed; - -struct hdcp2_rep_send_ack { - u8 msg_id; - u8 v[HDCP_2_2_V_PRIME_HALF_LEN]; -} __packed; - -struct hdcp2_rep_stream_manage { - u8 msg_id; - u8 seq_num_m[HDCP_2_2_SEQ_NUM_LEN]; - __be16 k; - struct hdcp2_streamid_type streams[HDCP_2_2_MAX_CONTENT_STREAMS_CNT]; -} __packed; - -struct hdcp2_rep_stream_ready { - u8 msg_id; - u8 m_prime[HDCP_2_2_MPRIME_LEN]; -} __packed; - -/* HDCP2.2 TIMEOUTs in mSec */ -#define HDCP_2_2_CERT_TIMEOUT_MS 100 -#define HDCP_2_2_DP_CERT_READ_TIMEOUT_MS 110 -#define HDCP_2_2_HPRIME_NO_PAIRED_TIMEOUT_MS 1000 -#define HDCP_2_2_HPRIME_PAIRED_TIMEOUT_MS 200 -#define HDCP_2_2_DP_HPRIME_READ_TIMEOUT_MS 7 -#define HDCP_2_2_PAIRING_TIMEOUT_MS 200 -#define HDCP_2_2_DP_PAIRING_READ_TIMEOUT_MS 5 -#define HDCP_2_2_HDMI_LPRIME_TIMEOUT_MS 20 -#define HDCP_2_2_DP_LPRIME_TIMEOUT_MS 16 -#define HDCP_2_2_RECVID_LIST_TIMEOUT_MS 3000 -#define HDCP_2_2_STREAM_READY_TIMEOUT_MS 100 - -/* HDMI HDCP2.2 Register Offsets */ -#define HDCP_2_2_HDMI_REG_VER_OFFSET 0x50 -#define HDCP_2_2_HDMI_REG_WR_MSG_OFFSET 0x60 -#define HDCP_2_2_HDMI_REG_RXSTATUS_OFFSET 0x70 -#define HDCP_2_2_HDMI_REG_RD_MSG_OFFSET 0x80 -#define HDCP_2_2_HDMI_REG_DBG_OFFSET 0xC0 - -#define HDCP_2_2_HDMI_SUPPORT_MASK BIT(2) -#define HDCP_2_2_RX_CAPS_VERSION_VAL 0x02 -#define HDCP_2_2_SEQ_NUM_MAX 0xFFFFFF -#define HDCP_2_2_DELAY_BEFORE_ENCRYPTION_EN 200 - -/* Below macros take a byte at a time and mask the bit(s) */ -#define HDCP_2_2_HDMI_RXSTATUS_LEN 2 -#define HDCP_2_2_HDMI_RXSTATUS_MSG_SZ_HI(x) ((x) & 0x3) -#define HDCP_2_2_HDMI_RXSTATUS_READY(x) ((x) & BIT(2)) -#define HDCP_2_2_HDMI_RXSTATUS_REAUTH_REQ(x) ((x) & BIT(3)) - -/* - * Helper functions to convert 24bit big endian hdcp sequence number to - * host format and back - */ -static inline -u32 drm_hdcp_be24_to_cpu(const u8 seq_num[HDCP_2_2_SEQ_NUM_LEN]) -{ - return (u32)(seq_num[2] | seq_num[1] << 8 | seq_num[0] << 16); -} - -static inline -void drm_hdcp_cpu_to_be24(u8 seq_num[HDCP_2_2_SEQ_NUM_LEN], u32 val) -{ - seq_num[0] = val >> 16; - seq_num[1] = val >> 8; - seq_num[2] = val; -} - -#define DRM_HDCP_SRM_GEN1_MAX_BYTES (5 * 1024) -#define DRM_HDCP_1_4_SRM_ID 0x8 -#define DRM_HDCP_SRM_ID_MASK (0xF << 4) -#define DRM_HDCP_1_4_VRL_LENGTH_SIZE 3 -#define DRM_HDCP_1_4_DCP_SIG_SIZE 40 -#define DRM_HDCP_2_SRM_ID 0x9 -#define DRM_HDCP_2_INDICATOR 0x1 -#define DRM_HDCP_2_INDICATOR_MASK 0xF -#define DRM_HDCP_2_VRL_LENGTH_SIZE 3 -#define DRM_HDCP_2_DCP_SIG_SIZE 384 -#define DRM_HDCP_2_NO_OF_DEV_PLUS_RESERVED_SZ 4 -#define DRM_HDCP_2_KSV_COUNT_2_LSBITS(byte) (((byte) & 0xC0) >> 6) - -struct hdcp_srm_header { - u8 srm_id; - u8 reserved; - __be16 srm_version; - u8 srm_gen_no; -} __packed; - -struct drm_device; -struct drm_connector; - -int drm_hdcp_check_ksvs_revoked(struct drm_device *dev, - u8 *ksvs, u32 ksv_count); -int drm_connector_attach_content_protection_property( - struct drm_connector *connector, bool hdcp_content_type); -void drm_hdcp_update_content_protection(struct drm_connector *connector, - u64 val); - -/* Content Type classification for HDCP2.2 vs others */ -#define DRM_MODE_HDCP_CONTENT_TYPE0 0 -#define DRM_MODE_HDCP_CONTENT_TYPE1 1 - -#endif diff --git a/include/drm/i915_mei_hdcp_interface.h b/include/drm/i915_mei_hdcp_interface.h index 702f613243bb..f441cbcd95a4 100644 --- a/include/drm/i915_mei_hdcp_interface.h +++ b/include/drm/i915_mei_hdcp_interface.h @@ -11,7 +11,7 @@ #include #include -#include +#include /** * enum hdcp_port_type - HDCP port implementation type defined by ME FW -- cgit v1.2.3 From 4fc8cb47fcfdc93e274a1291757e478df4f9c39b Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 21 Apr 2022 09:31:07 +0200 Subject: drm/display: Move HDMI helpers into display-helper module Move DRM's HMDI helpers into the display/ subdirectoy and add it to DRM's display helpers. Update all affected drivers. No functional changes. The HDMI helpers were implemented in the EDID and connector code, but are actually unrelated. With the move to the display-helper library, we can remove the dependency on drm_edid.{c,h} in some driver's HDMI source files. Several of the HDMI helpers remain in EDID code because both share parts of their implementation internally. With better refractoring of the EDID code, those HDMI helpers could be moved into the display-helper library as well. v3: * fix Kconfig dependencies (Javier) v2: * reduce HDMI helpers to avoid exporting functions (Jani) * fix include statements (Jani, Javier) * update Kconfig symbols Signed-off-by: Thomas Zimmermann Reviewed-by: Javier Martinez Canillas Link: https://patchwork.freedesktop.org/patch/msgid/20220421073108.19226-8-tzimmermann@suse.de --- include/drm/display/drm_hdmi_helper.h | 27 +++++++++++++++++++++++++++ include/drm/drm_connector.h | 3 --- include/drm/drm_edid.h | 12 ------------ 3 files changed, 27 insertions(+), 15 deletions(-) create mode 100644 include/drm/display/drm_hdmi_helper.h (limited to 'include') diff --git a/include/drm/display/drm_hdmi_helper.h b/include/drm/display/drm_hdmi_helper.h new file mode 100644 index 000000000000..76d234826e22 --- /dev/null +++ b/include/drm/display/drm_hdmi_helper.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: MIT */ + +#ifndef DRM_HDMI_HELPER +#define DRM_HDMI_HELPER + +#include + +struct drm_connector; +struct drm_connector_state; +struct drm_display_mode; + +void +drm_hdmi_avi_infoframe_colorimetry(struct hdmi_avi_infoframe *frame, + const struct drm_connector_state *conn_state); + +void +drm_hdmi_avi_infoframe_bars(struct hdmi_avi_infoframe *frame, + const struct drm_connector_state *conn_state); + +int +drm_hdmi_infoframe_set_hdr_metadata(struct hdmi_drm_infoframe *frame, + const struct drm_connector_state *conn_state); + +void drm_hdmi_avi_infoframe_content_type(struct hdmi_avi_infoframe *frame, + const struct drm_connector_state *conn_state); + +#endif diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index 5166186146f4..3ac4bf87f257 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -1784,9 +1784,6 @@ int drm_mode_create_aspect_ratio_property(struct drm_device *dev); int drm_mode_create_hdmi_colorspace_property(struct drm_connector *connector); int drm_mode_create_dp_colorspace_property(struct drm_connector *connector); int drm_mode_create_content_type_property(struct drm_device *dev); -void drm_hdmi_avi_infoframe_content_type(struct hdmi_avi_infoframe *frame, - const struct drm_connector_state *conn_state); - int drm_mode_create_suggested_offset_properties(struct drm_device *dev); int drm_connector_set_path_property(struct drm_connector *connector, diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h index b7e170584000..c3204a58fb09 100644 --- a/include/drm/drm_edid.h +++ b/include/drm/drm_edid.h @@ -400,24 +400,12 @@ drm_hdmi_vendor_infoframe_from_display_mode(struct hdmi_vendor_infoframe *frame, const struct drm_connector *connector, const struct drm_display_mode *mode); -void -drm_hdmi_avi_infoframe_colorimetry(struct hdmi_avi_infoframe *frame, - const struct drm_connector_state *conn_state); - -void -drm_hdmi_avi_infoframe_bars(struct hdmi_avi_infoframe *frame, - const struct drm_connector_state *conn_state); - void drm_hdmi_avi_infoframe_quant_range(struct hdmi_avi_infoframe *frame, const struct drm_connector *connector, const struct drm_display_mode *mode, enum hdmi_quantization_range rgb_quant_range); -int -drm_hdmi_infoframe_set_hdr_metadata(struct hdmi_drm_infoframe *frame, - const struct drm_connector_state *conn_state); - /** * drm_eld_mnl - Get ELD monitor name length in bytes. * @eld: pointer to an eld memory structure with mnl set -- cgit v1.2.3 From 644edf52b6305506ba7fd552323c1dfaa9cf6d8d Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 21 Apr 2022 09:31:08 +0200 Subject: drm/display: Move SCDC helpers into display-helper library SCDC is the Status and Control Data Channel for HDMI. Move the SCDC helpers into display/ and split the header into files for core and helpers. Update all affected drivers. No functional changes. To avoid the proliferation of Kconfig options, SCDC is part of DRM's support for HDMI. If necessary, a new option could make SCDC an independent feature. Signed-off-by: Thomas Zimmermann Reviewed-by: Javier Martinez Canillas Link: https://patchwork.freedesktop.org/patch/msgid/20220421073108.19226-9-tzimmermann@suse.de --- include/drm/display/drm_scdc.h | 88 ++++++++++++++++++++++ include/drm/display/drm_scdc_helper.h | 79 ++++++++++++++++++++ include/drm/drm_scdc_helper.h | 136 ---------------------------------- 3 files changed, 167 insertions(+), 136 deletions(-) create mode 100644 include/drm/display/drm_scdc.h create mode 100644 include/drm/display/drm_scdc_helper.h delete mode 100644 include/drm/drm_scdc_helper.h (limited to 'include') diff --git a/include/drm/display/drm_scdc.h b/include/drm/display/drm_scdc.h new file mode 100644 index 000000000000..3d58f37e8ed8 --- /dev/null +++ b/include/drm/display/drm_scdc.h @@ -0,0 +1,88 @@ +/* + * Copyright (c) 2015 NVIDIA Corporation. All rights reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sub license, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + */ + +#ifndef DRM_SCDC_H +#define DRM_SCDC_H + +#define SCDC_SINK_VERSION 0x01 + +#define SCDC_SOURCE_VERSION 0x02 + +#define SCDC_UPDATE_0 0x10 +#define SCDC_READ_REQUEST_TEST (1 << 2) +#define SCDC_CED_UPDATE (1 << 1) +#define SCDC_STATUS_UPDATE (1 << 0) + +#define SCDC_UPDATE_1 0x11 + +#define SCDC_TMDS_CONFIG 0x20 +#define SCDC_TMDS_BIT_CLOCK_RATIO_BY_40 (1 << 1) +#define SCDC_TMDS_BIT_CLOCK_RATIO_BY_10 (0 << 1) +#define SCDC_SCRAMBLING_ENABLE (1 << 0) + +#define SCDC_SCRAMBLER_STATUS 0x21 +#define SCDC_SCRAMBLING_STATUS (1 << 0) + +#define SCDC_CONFIG_0 0x30 +#define SCDC_READ_REQUEST_ENABLE (1 << 0) + +#define SCDC_STATUS_FLAGS_0 0x40 +#define SCDC_CH2_LOCK (1 << 3) +#define SCDC_CH1_LOCK (1 << 2) +#define SCDC_CH0_LOCK (1 << 1) +#define SCDC_CH_LOCK_MASK (SCDC_CH2_LOCK | SCDC_CH1_LOCK | SCDC_CH0_LOCK) +#define SCDC_CLOCK_DETECT (1 << 0) + +#define SCDC_STATUS_FLAGS_1 0x41 + +#define SCDC_ERR_DET_0_L 0x50 +#define SCDC_ERR_DET_0_H 0x51 +#define SCDC_ERR_DET_1_L 0x52 +#define SCDC_ERR_DET_1_H 0x53 +#define SCDC_ERR_DET_2_L 0x54 +#define SCDC_ERR_DET_2_H 0x55 +#define SCDC_CHANNEL_VALID (1 << 7) + +#define SCDC_ERR_DET_CHECKSUM 0x56 + +#define SCDC_TEST_CONFIG_0 0xc0 +#define SCDC_TEST_READ_REQUEST (1 << 7) +#define SCDC_TEST_READ_REQUEST_DELAY(x) ((x) & 0x7f) + +#define SCDC_MANUFACTURER_IEEE_OUI 0xd0 +#define SCDC_MANUFACTURER_IEEE_OUI_SIZE 3 + +#define SCDC_DEVICE_ID 0xd3 +#define SCDC_DEVICE_ID_SIZE 8 + +#define SCDC_DEVICE_HARDWARE_REVISION 0xdb +#define SCDC_GET_DEVICE_HARDWARE_REVISION_MAJOR(x) (((x) >> 4) & 0xf) +#define SCDC_GET_DEVICE_HARDWARE_REVISION_MINOR(x) (((x) >> 0) & 0xf) + +#define SCDC_DEVICE_SOFTWARE_MAJOR_REVISION 0xdc +#define SCDC_DEVICE_SOFTWARE_MINOR_REVISION 0xdd + +#define SCDC_MANUFACTURER_SPECIFIC 0xde +#define SCDC_MANUFACTURER_SPECIFIC_SIZE 34 + +#endif diff --git a/include/drm/display/drm_scdc_helper.h b/include/drm/display/drm_scdc_helper.h new file mode 100644 index 000000000000..ded01fd948b4 --- /dev/null +++ b/include/drm/display/drm_scdc_helper.h @@ -0,0 +1,79 @@ +/* + * Copyright (c) 2015 NVIDIA Corporation. All rights reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sub license, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + */ + +#ifndef DRM_SCDC_HELPER_H +#define DRM_SCDC_HELPER_H + +#include + +#include + +struct i2c_adapter; + +ssize_t drm_scdc_read(struct i2c_adapter *adapter, u8 offset, void *buffer, + size_t size); +ssize_t drm_scdc_write(struct i2c_adapter *adapter, u8 offset, + const void *buffer, size_t size); + +/** + * drm_scdc_readb - read a single byte from SCDC + * @adapter: I2C adapter + * @offset: offset of register to read + * @value: return location for the register value + * + * Reads a single byte from SCDC. This is a convenience wrapper around the + * drm_scdc_read() function. + * + * Returns: + * 0 on success or a negative error code on failure. + */ +static inline int drm_scdc_readb(struct i2c_adapter *adapter, u8 offset, + u8 *value) +{ + return drm_scdc_read(adapter, offset, value, sizeof(*value)); +} + +/** + * drm_scdc_writeb - write a single byte to SCDC + * @adapter: I2C adapter + * @offset: offset of register to read + * @value: return location for the register value + * + * Writes a single byte to SCDC. This is a convenience wrapper around the + * drm_scdc_write() function. + * + * Returns: + * 0 on success or a negative error code on failure. + */ +static inline int drm_scdc_writeb(struct i2c_adapter *adapter, u8 offset, + u8 value) +{ + return drm_scdc_write(adapter, offset, &value, sizeof(value)); +} + +bool drm_scdc_get_scrambling_status(struct i2c_adapter *adapter); + +bool drm_scdc_set_scrambling(struct i2c_adapter *adapter, bool enable); +bool drm_scdc_set_high_tmds_clock_ratio(struct i2c_adapter *adapter, bool set); + +#endif diff --git a/include/drm/drm_scdc_helper.h b/include/drm/drm_scdc_helper.h deleted file mode 100644 index 6a483533aae4..000000000000 --- a/include/drm/drm_scdc_helper.h +++ /dev/null @@ -1,136 +0,0 @@ -/* - * Copyright (c) 2015 NVIDIA Corporation. All rights reserved. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sub license, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice (including the - * next paragraph) shall be included in all copies or substantial portions - * of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - */ - -#ifndef DRM_SCDC_HELPER_H -#define DRM_SCDC_HELPER_H - -#include -#include - -#define SCDC_SINK_VERSION 0x01 - -#define SCDC_SOURCE_VERSION 0x02 - -#define SCDC_UPDATE_0 0x10 -#define SCDC_READ_REQUEST_TEST (1 << 2) -#define SCDC_CED_UPDATE (1 << 1) -#define SCDC_STATUS_UPDATE (1 << 0) - -#define SCDC_UPDATE_1 0x11 - -#define SCDC_TMDS_CONFIG 0x20 -#define SCDC_TMDS_BIT_CLOCK_RATIO_BY_40 (1 << 1) -#define SCDC_TMDS_BIT_CLOCK_RATIO_BY_10 (0 << 1) -#define SCDC_SCRAMBLING_ENABLE (1 << 0) - -#define SCDC_SCRAMBLER_STATUS 0x21 -#define SCDC_SCRAMBLING_STATUS (1 << 0) - -#define SCDC_CONFIG_0 0x30 -#define SCDC_READ_REQUEST_ENABLE (1 << 0) - -#define SCDC_STATUS_FLAGS_0 0x40 -#define SCDC_CH2_LOCK (1 << 3) -#define SCDC_CH1_LOCK (1 << 2) -#define SCDC_CH0_LOCK (1 << 1) -#define SCDC_CH_LOCK_MASK (SCDC_CH2_LOCK | SCDC_CH1_LOCK | SCDC_CH0_LOCK) -#define SCDC_CLOCK_DETECT (1 << 0) - -#define SCDC_STATUS_FLAGS_1 0x41 - -#define SCDC_ERR_DET_0_L 0x50 -#define SCDC_ERR_DET_0_H 0x51 -#define SCDC_ERR_DET_1_L 0x52 -#define SCDC_ERR_DET_1_H 0x53 -#define SCDC_ERR_DET_2_L 0x54 -#define SCDC_ERR_DET_2_H 0x55 -#define SCDC_CHANNEL_VALID (1 << 7) - -#define SCDC_ERR_DET_CHECKSUM 0x56 - -#define SCDC_TEST_CONFIG_0 0xc0 -#define SCDC_TEST_READ_REQUEST (1 << 7) -#define SCDC_TEST_READ_REQUEST_DELAY(x) ((x) & 0x7f) - -#define SCDC_MANUFACTURER_IEEE_OUI 0xd0 -#define SCDC_MANUFACTURER_IEEE_OUI_SIZE 3 - -#define SCDC_DEVICE_ID 0xd3 -#define SCDC_DEVICE_ID_SIZE 8 - -#define SCDC_DEVICE_HARDWARE_REVISION 0xdb -#define SCDC_GET_DEVICE_HARDWARE_REVISION_MAJOR(x) (((x) >> 4) & 0xf) -#define SCDC_GET_DEVICE_HARDWARE_REVISION_MINOR(x) (((x) >> 0) & 0xf) - -#define SCDC_DEVICE_SOFTWARE_MAJOR_REVISION 0xdc -#define SCDC_DEVICE_SOFTWARE_MINOR_REVISION 0xdd - -#define SCDC_MANUFACTURER_SPECIFIC 0xde -#define SCDC_MANUFACTURER_SPECIFIC_SIZE 34 - -ssize_t drm_scdc_read(struct i2c_adapter *adapter, u8 offset, void *buffer, - size_t size); -ssize_t drm_scdc_write(struct i2c_adapter *adapter, u8 offset, - const void *buffer, size_t size); - -/** - * drm_scdc_readb - read a single byte from SCDC - * @adapter: I2C adapter - * @offset: offset of register to read - * @value: return location for the register value - * - * Reads a single byte from SCDC. This is a convenience wrapper around the - * drm_scdc_read() function. - * - * Returns: - * 0 on success or a negative error code on failure. - */ -static inline int drm_scdc_readb(struct i2c_adapter *adapter, u8 offset, - u8 *value) -{ - return drm_scdc_read(adapter, offset, value, sizeof(*value)); -} - -/** - * drm_scdc_writeb - write a single byte to SCDC - * @adapter: I2C adapter - * @offset: offset of register to read - * @value: return location for the register value - * - * Writes a single byte to SCDC. This is a convenience wrapper around the - * drm_scdc_write() function. - * - * Returns: - * 0 on success or a negative error code on failure. - */ -static inline int drm_scdc_writeb(struct i2c_adapter *adapter, u8 offset, - u8 value) -{ - return drm_scdc_write(adapter, offset, &value, sizeof(value)); -} - -bool drm_scdc_get_scrambling_status(struct i2c_adapter *adapter); - -bool drm_scdc_set_scrambling(struct i2c_adapter *adapter, bool enable); -bool drm_scdc_set_high_tmds_clock_ratio(struct i2c_adapter *adapter, bool set); -#endif -- cgit v1.2.3 From da32b5817253697671af961715517bfbb308a592 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Sat, 23 Apr 2022 11:07:49 +0100 Subject: mm: Add fault_in_subpage_writeable() to probe at sub-page granularity On hardware with features like arm64 MTE or SPARC ADI, an access fault can be triggered at sub-page granularity. Depending on how the fault_in_writeable() function is used, the caller can get into a live-lock by continuously retrying the fault-in on an address different from the one where the uaccess failed. In the majority of cases progress is ensured by the following conditions: 1. copy_to_user_nofault() guarantees at least one byte access if the user address is not faulting. 2. The fault_in_writeable() loop is resumed from the first address that could not be accessed by copy_to_user_nofault(). If the loop iteration is restarted from an earlier (initial) point, the loop is repeated with the same conditions and it would live-lock. Introduce an arch-specific probe_subpage_writeable() and call it from the newly added fault_in_subpage_writeable() function. The arch code with sub-page faults will have to implement the specific probing functionality. Note that no other fault_in_subpage_*() functions are added since they have no callers currently susceptible to a live-lock. Signed-off-by: Catalin Marinas Cc: Andrew Morton Link: https://lore.kernel.org/r/20220423100751.1870771-2-catalin.marinas@arm.com Signed-off-by: Catalin Marinas --- include/linux/pagemap.h | 1 + include/linux/uaccess.h | 22 ++++++++++++++++++++++ 2 files changed, 23 insertions(+) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 993994cd943a..6165283bdb6f 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1046,6 +1046,7 @@ void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter); * Fault in userspace address range. */ size_t fault_in_writeable(char __user *uaddr, size_t size); +size_t fault_in_subpage_writeable(char __user *uaddr, size_t size); size_t fault_in_safe_writeable(const char __user *uaddr, size_t size); size_t fault_in_readable(const char __user *uaddr, size_t size); diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 546179418ffa..5a328cf02b75 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -231,6 +231,28 @@ static inline bool pagefault_disabled(void) */ #define faulthandler_disabled() (pagefault_disabled() || in_atomic()) +#ifndef CONFIG_ARCH_HAS_SUBPAGE_FAULTS + +/** + * probe_subpage_writeable: probe the user range for write faults at sub-page + * granularity (e.g. arm64 MTE) + * @uaddr: start of address range + * @size: size of address range + * + * Returns 0 on success, the number of bytes not probed on fault. + * + * It is expected that the caller checked for the write permission of each + * page in the range either by put_user() or GUP. The architecture port can + * implement a more efficient get_user() probing if the same sub-page faults + * are triggered by either a read or a write. + */ +static inline size_t probe_subpage_writeable(char __user *uaddr, size_t size) +{ + return 0; +} + +#endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */ + #ifndef ARCH_HAS_NOCACHE_UACCESS static inline __must_check unsigned long -- cgit v1.2.3 From 8d92e4fbcf0fb7ecb24223b7b1ce95b9beb4dfa2 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 25 Apr 2022 06:44:21 +0300 Subject: devlink: introduce line card devices support Line card can contain one or more devices that makes sense to make visible to the user. For example, this can be a gearbox with flash memory, which could be updated. Provide the driver possibility to attach such devices to a line card and expose those to user. Example: $ devlink lc show pci/0000:01:00.0 lc 8 pci/0000:01:00.0: lc 8 state active type 16x100G supported_types: 16x100G devices: device 0 device 1 device 2 device 3 Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/devlink.h | 7 +++++++ include/uapi/linux/devlink.h | 3 +++ 2 files changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 2a2a2a0c93f7..c84b52fb9ff0 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1578,6 +1578,13 @@ struct devlink_linecard * devlink_linecard_create(struct devlink *devlink, unsigned int linecard_index, const struct devlink_linecard_ops *ops, void *priv); void devlink_linecard_destroy(struct devlink_linecard *linecard); +struct devlink_linecard_device; +struct devlink_linecard_device * +devlink_linecard_device_create(struct devlink_linecard *linecard, + unsigned int device_index); +void +devlink_linecard_device_destroy(struct devlink_linecard *linecard, + struct devlink_linecard_device *linecard_device); void devlink_linecard_provision_set(struct devlink_linecard *linecard, const char *type); void devlink_linecard_provision_clear(struct devlink_linecard *linecard); diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index b3d40a5d72ff..cd578645f94f 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -575,6 +575,9 @@ enum devlink_attr { DEVLINK_ATTR_LINECARD_STATE, /* u8 */ DEVLINK_ATTR_LINECARD_TYPE, /* string */ DEVLINK_ATTR_LINECARD_SUPPORTED_TYPES, /* nested */ + DEVLINK_ATTR_LINECARD_DEVICE_LIST, /* nested */ + DEVLINK_ATTR_LINECARD_DEVICE, /* nested */ + DEVLINK_ATTR_LINECARD_DEVICE_INDEX, /* u32 */ /* add new attributes above here, update the policy in devlink.c */ -- cgit v1.2.3 From 276910aecc6a4076f5fbfd8160ff70695d6c1eb5 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 25 Apr 2022 06:44:22 +0300 Subject: devlink: introduce line card info get message Allow the driver to provide per line card info get op to fill-up info, similar to the "devlink dev info". Example: $ devlink lc info pci/0000:01:00.0 lc 8 pci/0000:01:00.0: lc 8 versions: fixed: hw.revision 0 running: ini.version 4 Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/devlink.h | 7 ++++++- include/uapi/linux/devlink.h | 2 ++ 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index c84b52fb9ff0..f96dcb376630 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -150,6 +150,8 @@ struct devlink_port_new_attrs { sfnum_valid:1; }; +struct devlink_info_req; + /** * struct devlink_linecard_ops - Linecard operations * @provision: callback to provision the linecard slot with certain @@ -168,6 +170,7 @@ struct devlink_port_new_attrs { * provisioned. * @types_count: callback to get number of supported types * @types_get: callback to get next type in list + * @info_get: callback to get linecard info */ struct devlink_linecard_ops { int (*provision)(struct devlink_linecard *linecard, void *priv, @@ -182,6 +185,9 @@ struct devlink_linecard_ops { void (*types_get)(struct devlink_linecard *linecard, void *priv, unsigned int index, const char **type, const void **type_priv); + int (*info_get)(struct devlink_linecard *linecard, void *priv, + struct devlink_info_req *req, + struct netlink_ext_ack *extack); }; struct devlink_sb_pool_info { @@ -628,7 +634,6 @@ struct devlink_flash_update_params { #define DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK BIT(1) struct devlink_region; -struct devlink_info_req; /** * struct devlink_region_ops - Region operations diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index cd578645f94f..fb8c3864457f 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -136,6 +136,8 @@ enum devlink_command { DEVLINK_CMD_LINECARD_NEW, DEVLINK_CMD_LINECARD_DEL, + DEVLINK_CMD_LINECARD_INFO_GET, /* can dump */ + /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 -- cgit v1.2.3 From 28b2d1f1ac41dda0b239830765d85c7ae4434182 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 25 Apr 2022 06:44:23 +0300 Subject: devlink: introduce line card device info infrastructure Extend the line card info message with information (e.g., FW version) about devices found on the line card. Example: $ devlink lc info pci/0000:01:00.0 lc 8 pci/0000:01:00.0: lc 8 versions: fixed: hw.revision 0 running: ini.version 4 devices: device 0 versions: running: fw 19.2010.1310 device 1 versions: running: fw 19.2010.1310 device 2 versions: running: fw 19.2010.1310 device 3 versions: running: fw 19.2010.1310 Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/devlink.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index f96dcb376630..062895973656 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -151,6 +151,7 @@ struct devlink_port_new_attrs { }; struct devlink_info_req; +struct devlink_linecard_device; /** * struct devlink_linecard_ops - Linecard operations @@ -171,6 +172,7 @@ struct devlink_info_req; * @types_count: callback to get number of supported types * @types_get: callback to get next type in list * @info_get: callback to get linecard info + * @device_info_get: callback to get linecard device info */ struct devlink_linecard_ops { int (*provision)(struct devlink_linecard *linecard, void *priv, @@ -188,6 +190,9 @@ struct devlink_linecard_ops { int (*info_get)(struct devlink_linecard *linecard, void *priv, struct devlink_info_req *req, struct netlink_ext_ack *extack); + int (*device_info_get)(struct devlink_linecard_device *device, + void *priv, struct devlink_info_req *req, + struct netlink_ext_ack *extack); }; struct devlink_sb_pool_info { @@ -1583,10 +1588,9 @@ struct devlink_linecard * devlink_linecard_create(struct devlink *devlink, unsigned int linecard_index, const struct devlink_linecard_ops *ops, void *priv); void devlink_linecard_destroy(struct devlink_linecard *linecard); -struct devlink_linecard_device; struct devlink_linecard_device * devlink_linecard_device_create(struct devlink_linecard *linecard, - unsigned int device_index); + unsigned int device_index, void *priv); void devlink_linecard_device_destroy(struct devlink_linecard *linecard, struct devlink_linecard_device *linecard_device); -- cgit v1.2.3 From e8e7fbb6a39cd6761c843d97851eb40c5885e922 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Tue, 12 Apr 2022 11:49:43 +0200 Subject: PCI: Add PCI_EXP_SLTCTL_ASPL_DISABLE macro MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add macro defining Auto Slot Power Limit Disable bit in Slot Control Register. Link: https://lore.kernel.org/r/20220412094946.27069-2-pali@kernel.org Signed-off-by: Pali Rohár Signed-off-by: Marek Behún Signed-off-by: Lorenzo Pieralisi Acked-by: Bjorn Helgaas --- include/uapi/linux/pci_regs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index bee1a9ed6e66..108f8523fa04 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -616,6 +616,7 @@ #define PCI_EXP_SLTCTL_PWR_OFF 0x0400 /* Power Off */ #define PCI_EXP_SLTCTL_EIC 0x0800 /* Electromechanical Interlock Control */ #define PCI_EXP_SLTCTL_DLLSCE 0x1000 /* Data Link Layer State Changed Enable */ +#define PCI_EXP_SLTCTL_ASPL_DISABLE 0x2000 /* Auto Slot Power Limit Disable */ #define PCI_EXP_SLTCTL_IBPD_DISABLE 0x4000 /* In-band PD disable */ #define PCI_EXP_SLTSTA 0x1a /* Slot Status */ #define PCI_EXP_SLTSTA_ABP 0x0001 /* Attention Button Pressed */ -- cgit v1.2.3 From 3c938cc5cebcbd2291fe97f523c0705a2c24c77d Mon Sep 17 00:00:00 2001 From: Schspa Shi Date: Tue, 19 Apr 2022 09:28:10 +0800 Subject: gpio: use raw spinlock for gpio chip shadowed data In case of PREEMPT_RT, there is a raw_spinlock -> spinlock dependency as the lockdep report shows. __irq_set_handler irq_get_desc_buslock __irq_get_desc_lock raw_spin_lock_irqsave(&desc->lock, *flags); // raw spinlock get here __irq_do_set_handler mask_ack_irq dwapb_irq_ack spin_lock_irqsave(&gc->bgpio_lock, flags); // sleep able spinlock irq_put_desc_busunlock Replace with a raw lock to avoid BUGs. This lock is only used to access registers, and It's safe to replace with the raw lock without bad influence. [ 15.090359][ T1] ============================= [ 15.090365][ T1] [ BUG: Invalid wait context ] [ 15.090373][ T1] 5.10.59-rt52-00983-g186a6841c682-dirty #3 Not tainted [ 15.090386][ T1] ----------------------------- [ 15.090392][ T1] swapper/0/1 is trying to lock: [ 15.090402][ T1] 70ff00018507c188 (&gc->bgpio_lock){....}-{3:3}, at: _raw_spin_lock_irqsave+0x1c/0x28 [ 15.090470][ T1] other info that might help us debug this: [ 15.090477][ T1] context-{5:5} [ 15.090485][ T1] 3 locks held by swapper/0/1: [ 15.090497][ T1] #0: c2ff0001816de1a0 (&dev->mutex){....}-{4:4}, at: __device_driver_lock+0x98/0x104 [ 15.090553][ T1] #1: ffff90001485b4b8 (irq_domain_mutex){+.+.}-{4:4}, at: irq_domain_associate+0xbc/0x6d4 [ 15.090606][ T1] #2: 4bff000185d7a8e0 (lock_class){....}-{2:2}, at: _raw_spin_lock_irqsave+0x1c/0x28 [ 15.090654][ T1] stack backtrace: [ 15.090661][ T1] CPU: 4 PID: 1 Comm: swapper/0 Not tainted 5.10.59-rt52-00983-g186a6841c682-dirty #3 [ 15.090682][ T1] Hardware name: Horizon Robotics Journey 5 DVB (DT) [ 15.090692][ T1] Call trace: ...... [ 15.090811][ T1] _raw_spin_lock_irqsave+0x1c/0x28 [ 15.090828][ T1] dwapb_irq_ack+0xb4/0x300 [ 15.090846][ T1] __irq_do_set_handler+0x494/0xb2c [ 15.090864][ T1] __irq_set_handler+0x74/0x114 [ 15.090881][ T1] irq_set_chip_and_handler_name+0x44/0x58 [ 15.090900][ T1] gpiochip_irq_map+0x210/0x644 Signed-off-by: Schspa Shi Reviewed-by: Andy Shevchenko Acked-by: Linus Walleij Acked-by: Doug Berger Acked-by: Serge Semin Signed-off-by: Bartosz Golaszewski --- include/linux/gpio/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 98c93510640e..991d374dcf71 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -436,7 +436,7 @@ struct gpio_chip { void __iomem *reg_dir_in; bool bgpio_dir_unreadable; int bgpio_bits; - spinlock_t bgpio_lock; + raw_spinlock_t bgpio_lock; unsigned long bgpio_data; unsigned long bgpio_dir; #endif /* CONFIG_GPIO_GENERIC */ -- cgit v1.2.3 From 31c417c948d7f6909cb63f0ac3298f3c38f8ce20 Mon Sep 17 00:00:00 2001 From: Peilin Ye Date: Thu, 21 Apr 2022 15:09:02 -0700 Subject: ip_gre, ip6_gre: Fix race condition on o_seqno in collect_md mode As pointed out by Jakub Kicinski, currently using TUNNEL_SEQ in collect_md mode is racy for [IP6]GRE[TAP] devices. Consider the following sequence of events: 1. An [IP6]GRE[TAP] device is created in collect_md mode using "ip link add ... external". "ip" ignores "[o]seq" if "external" is specified, so TUNNEL_SEQ is off, and the device is marked as NETIF_F_LLTX (i.e. it uses lockless TX); 2. Someone sets TUNNEL_SEQ on outgoing skb's, using e.g. bpf_skb_set_tunnel_key() in an eBPF program attached to this device; 3. gre_fb_xmit() or __gre6_xmit() processes these skb's: gre_build_header(skb, tun_hlen, flags, protocol, tunnel_id_to_key32(tun_info->key.tun_id), (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0); ^^^^^^^^^^^^^^^^^ Since we are not using the TX lock (&txq->_xmit_lock), multiple CPUs may try to do this tunnel->o_seqno++ in parallel, which is racy. Fix it by making o_seqno atomic_t. As mentioned by Eric Dumazet in commit b790e01aee74 ("ip_gre: lockless xmit"), making o_seqno atomic_t increases "chance for packets being out of order at receiver" when NETIF_F_LLTX is on. Maybe a better fix would be: 1. Do not ignore "oseq" in external mode. Users MUST specify "oseq" if they want the kernel to allow sequencing of outgoing packets; 2. Reject all outgoing TUNNEL_SEQ packets if the device was not created with "oseq". Unfortunately, that would break userspace. We could now make [IP6]GRE[TAP] devices always NETIF_F_LLTX, but let us do it in separate patches to keep this fix minimal. Suggested-by: Jakub Kicinski Fixes: 77a5196a804e ("gre: add sequence number for collect md mode.") Signed-off-by: Peilin Ye Acked-by: William Tu Signed-off-by: David S. Miller --- include/net/ip6_tunnel.h | 2 +- include/net/ip_tunnels.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index a38c4f1e4e5c..74b369bddf49 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -58,7 +58,7 @@ struct ip6_tnl { /* These fields used only by GRE */ __u32 i_seqno; /* The last seen seqno */ - __u32 o_seqno; /* The last output seqno */ + atomic_t o_seqno; /* The last output seqno */ int hlen; /* tun_hlen + encap_hlen */ int tun_hlen; /* Precalculated header length */ int encap_hlen; /* Encap header length (FOU,GUE) */ diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 88dee57eac8a..c24fa934221d 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -116,7 +116,7 @@ struct ip_tunnel { /* These four fields used only by GRE */ u32 i_seqno; /* The last seen seqno */ - u32 o_seqno; /* The last output seqno */ + atomic_t o_seqno; /* The last output seqno */ int tun_hlen; /* Precalculated header length */ /* These four fields used only by ERSPAN */ -- cgit v1.2.3 From 4bfe744ff1644fbc0a991a2677dc874475dd6776 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 24 Apr 2022 17:34:07 -0700 Subject: tcp: fix potential xmit stalls caused by TCP_NOTSENT_LOWAT I had this bug sitting for too long in my pile, it is time to fix it. Thanks to Doug Porter for reminding me of it! We had various attempts in the past, including commit 0cbe6a8f089e ("tcp: remove SOCK_QUEUE_SHRUNK"), but the issue is that TCP stack currently only generates EPOLLOUT from input path, when tp->snd_una has advanced and skb(s) cleaned from rtx queue. If a flow has a big RTT, and/or receives SACKs, it is possible that the notsent part (tp->write_seq - tp->snd_nxt) reaches 0 and no more data can be sent until tp->snd_una finally advances. What is needed is to also check if POLLOUT needs to be generated whenever tp->snd_nxt is advanced, from output path. This bug triggers more often after an idle period, as we do not receive ACK for at least one RTT. tcp_notsent_lowat could be a fraction of what CWND and pacing rate would allow to send during this RTT. In a followup patch, I will remove the bogus call to tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED) from tcp_check_space(). Fact that we have decided to generate an EPOLLOUT does not mean the application has immediately refilled the transmit queue. This optimistic call might have been the reason the bug seemed not too serious. Tested: 200 ms rtt, 1% packet loss, 32 MB tcp_rmem[2] and tcp_wmem[2] $ echo 500000 >/proc/sys/net/ipv4/tcp_notsent_lowat $ cat bench_rr.sh SUM=0 for i in {1..10} do V=`netperf -H remote_host -l30 -t TCP_RR -- -r 10000000,10000 -o LOCAL_BYTES_SENT | egrep -v "MIGRATED|Bytes"` echo $V SUM=$(($SUM + $V)) done echo SUM=$SUM Before patch: $ bench_rr.sh 130000000 80000000 140000000 140000000 140000000 140000000 130000000 40000000 90000000 110000000 SUM=1140000000 After patch: $ bench_rr.sh 430000000 590000000 530000000 450000000 450000000 350000000 450000000 490000000 480000000 460000000 SUM=4680000000 # This is 410 % of the value before patch. Fixes: c9bee3b7fdec ("tcp: TCP_NOTSENT_LOWAT socket option") Signed-off-by: Eric Dumazet Reported-by: Doug Porter Cc: Soheil Hassas Yeganeh Cc: Neal Cardwell Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/net/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index be712fb9ddd7..b99d9d9cbd99 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -620,6 +620,7 @@ void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); void tcp_reset(struct sock *sk, struct sk_buff *skb); void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb); void tcp_fin(struct sock *sk); +void tcp_check_space(struct sock *sk); /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); -- cgit v1.2.3 From ba5a4fdd63ae0c575707030db0b634b160baddd7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 24 Apr 2022 13:35:09 -0700 Subject: tcp: make sure treq->af_specific is initialized syzbot complained about a recent change in TCP stack, hitting a NULL pointer [1] tcp request sockets have an af_specific pointer, which was used before the blamed change only for SYNACK generation in non SYNCOOKIE mode. tcp requests sockets momentarily created when third packet coming from client in SYNCOOKIE mode were not using treq->af_specific. Make sure this field is populated, in the same way normal TCP requests sockets do in tcp_conn_request(). [1] TCP: request_sock_TCPv6: Possible SYN flooding on port 20002. Sending cookies. Check SNMP counters. general protection fault, probably for non-canonical address 0xdffffc0000000001: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000008-0x000000000000000f] CPU: 1 PID: 3695 Comm: syz-executor864 Not tainted 5.18.0-rc3-syzkaller-00224-g5fd1fe4807f9 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:tcp_create_openreq_child+0xe16/0x16b0 net/ipv4/tcp_minisocks.c:534 Code: 48 c1 ea 03 80 3c 02 00 0f 85 e5 07 00 00 4c 8b b3 28 01 00 00 48 b8 00 00 00 00 00 fc ff df 49 8d 7e 08 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 c9 07 00 00 48 8b 3c 24 48 89 de 41 ff 56 08 48 RSP: 0018:ffffc90000de0588 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffff888076490330 RCX: 0000000000000100 RDX: 0000000000000001 RSI: ffffffff87d67ff0 RDI: 0000000000000008 RBP: ffff88806ee1c7f8 R08: 0000000000000000 R09: 0000000000000000 R10: ffffffff87d67f00 R11: 0000000000000000 R12: ffff88806ee1bfc0 R13: ffff88801b0e0368 R14: 0000000000000000 R15: 0000000000000000 FS: 00007f517fe58700(0000) GS:ffff8880b9d00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffcead76960 CR3: 000000006f97b000 CR4: 00000000003506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: tcp_v6_syn_recv_sock+0x199/0x23b0 net/ipv6/tcp_ipv6.c:1267 tcp_get_cookie_sock+0xc9/0x850 net/ipv4/syncookies.c:207 cookie_v6_check+0x15c3/0x2340 net/ipv6/syncookies.c:258 tcp_v6_cookie_check net/ipv6/tcp_ipv6.c:1131 [inline] tcp_v6_do_rcv+0x1148/0x13b0 net/ipv6/tcp_ipv6.c:1486 tcp_v6_rcv+0x3305/0x3840 net/ipv6/tcp_ipv6.c:1725 ip6_protocol_deliver_rcu+0x2e9/0x1900 net/ipv6/ip6_input.c:422 ip6_input_finish+0x14c/0x2c0 net/ipv6/ip6_input.c:464 NF_HOOK include/linux/netfilter.h:307 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] ip6_input+0x9c/0xd0 net/ipv6/ip6_input.c:473 dst_input include/net/dst.h:461 [inline] ip6_rcv_finish net/ipv6/ip6_input.c:76 [inline] NF_HOOK include/linux/netfilter.h:307 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] ipv6_rcv+0x27f/0x3b0 net/ipv6/ip6_input.c:297 __netif_receive_skb_one_core+0x114/0x180 net/core/dev.c:5405 __netif_receive_skb+0x24/0x1b0 net/core/dev.c:5519 process_backlog+0x3a0/0x7c0 net/core/dev.c:5847 __napi_poll+0xb3/0x6e0 net/core/dev.c:6413 napi_poll net/core/dev.c:6480 [inline] net_rx_action+0x8ec/0xc60 net/core/dev.c:6567 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558 invoke_softirq kernel/softirq.c:432 [inline] __irq_exit_rcu+0x123/0x180 kernel/softirq.c:637 irq_exit_rcu+0x5/0x20 kernel/softirq.c:649 sysvec_apic_timer_interrupt+0x93/0xc0 arch/x86/kernel/apic/apic.c:1097 Fixes: 5b0b9e4c2c89 ("tcp: md5: incorrect tcp_header_len for incoming connections") Signed-off-by: Eric Dumazet Cc: Francesco Ruggeri Signed-off-by: David S. Miller --- include/net/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index b99d9d9cbd99..cc1295037533 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -480,6 +480,7 @@ int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, u32 cookie); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, + const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb); #ifdef CONFIG_SYN_COOKIES -- cgit v1.2.3 From 38035c04f5865c4ef9597d6beed6a7178f90f64a Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 22 Apr 2022 15:03:13 +0300 Subject: inotify: move control flags from mask to mark flags The inotify control flags in the mark mask (e.g. FS_IN_ONE_SHOT) are not relevant to object interest mask, so move them to the mark flags. This frees up some bits in the object interest mask. Link: https://lore.kernel.org/r/20220422120327.3459282-3-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 0805b74cae44..b1c72edd9784 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -55,7 +55,6 @@ #define FS_ACCESS_PERM 0x00020000 /* access event in a permissions hook */ #define FS_OPEN_EXEC_PERM 0x00040000 /* open/exec event in a permission hook */ -#define FS_EXCL_UNLINK 0x04000000 /* do not send events if object is unlinked */ /* * Set on inode mark that cares about things that happen to its children. * Always set for dnotify and inotify. @@ -66,7 +65,6 @@ #define FS_RENAME 0x10000000 /* File was renamed */ #define FS_DN_MULTISHOT 0x20000000 /* dnotify multishot */ #define FS_ISDIR 0x40000000 /* event occurred against dir */ -#define FS_IN_ONESHOT 0x80000000 /* only send event once */ #define FS_MOVE (FS_MOVED_FROM | FS_MOVED_TO) @@ -106,8 +104,7 @@ FS_ERROR) /* Extra flags that may be reported with event or control handling of events */ -#define ALL_FSNOTIFY_FLAGS (FS_EXCL_UNLINK | FS_ISDIR | FS_IN_ONESHOT | \ - FS_DN_MULTISHOT | FS_EVENT_ON_CHILD) +#define ALL_FSNOTIFY_FLAGS (FS_ISDIR | FS_EVENT_ON_CHILD | FS_DN_MULTISHOT) #define ALL_FSNOTIFY_BITS (ALL_FSNOTIFY_EVENTS | ALL_FSNOTIFY_FLAGS) @@ -473,9 +470,14 @@ struct fsnotify_mark { struct fsnotify_mark_connector *connector; /* Events types to ignore [mark->lock, group->mark_mutex] */ __u32 ignored_mask; -#define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x01 -#define FSNOTIFY_MARK_FLAG_ALIVE 0x02 -#define FSNOTIFY_MARK_FLAG_ATTACHED 0x04 + /* General fsnotify mark flags */ +#define FSNOTIFY_MARK_FLAG_ALIVE 0x0001 +#define FSNOTIFY_MARK_FLAG_ATTACHED 0x0002 + /* inotify mark flags */ +#define FSNOTIFY_MARK_FLAG_EXCL_UNLINK 0x0010 +#define FSNOTIFY_MARK_FLAG_IN_ONESHOT 0x0020 + /* fanotify mark flags */ +#define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x0100 unsigned int flags; /* flags [mark->lock] */ }; -- cgit v1.2.3 From 867a448d587e7fa845bceaf4ee1c632448f2a9fa Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 22 Apr 2022 15:03:15 +0300 Subject: fsnotify: pass flags argument to fsnotify_alloc_group() Add flags argument to fsnotify_alloc_group(), define and use the flag FSNOTIFY_GROUP_USER in inotify and fanotify instead of the helper fsnotify_alloc_user_group() to indicate user allocation. Although the flag FSNOTIFY_GROUP_USER is currently not used after group allocation, we store the flags argument in the group struct for future use of other group flags. Link: https://lore.kernel.org/r/20220422120327.3459282-5-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index b1c72edd9784..f0bf557af009 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -210,6 +210,9 @@ struct fsnotify_group { unsigned int priority; bool shutdown; /* group is being shut down, don't queue more events */ +#define FSNOTIFY_GROUP_USER 0x01 /* user allocated group */ + int flags; + /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */ struct mutex mark_mutex; /* protect marks_list */ atomic_t user_waits; /* Number of tasks waiting for user @@ -543,8 +546,9 @@ static inline void fsnotify_update_flags(struct dentry *dentry) /* called from fsnotify listeners, such as fanotify or dnotify */ /* create a new group */ -extern struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops); -extern struct fsnotify_group *fsnotify_alloc_user_group(const struct fsnotify_ops *ops); +extern struct fsnotify_group *fsnotify_alloc_group( + const struct fsnotify_ops *ops, + int flags); /* get reference to a group */ extern void fsnotify_get_group(struct fsnotify_group *group); /* drop reference on a group from fsnotify_alloc_group */ -- cgit v1.2.3 From f3010343d9e119da35ee864b3a28993bb5c78ed7 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 22 Apr 2022 15:03:16 +0300 Subject: fsnotify: make allow_dups a property of the group Instead of passing the allow_dups argument to fsnotify_add_mark() as an argument, define the group flag FSNOTIFY_GROUP_DUPS to express the allow_dups behavior and set this behavior at group creation time for all calls of fsnotify_add_mark(). Rename the allow_dups argument to generic add_flags argument for future use. Link: https://lore.kernel.org/r/20220422120327.3459282-6-amir73il@gmail.com Suggested-by: Jan Kara Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index f0bf557af009..dd440e6ff528 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -211,6 +211,7 @@ struct fsnotify_group { bool shutdown; /* group is being shut down, don't queue more events */ #define FSNOTIFY_GROUP_USER 0x01 /* user allocated group */ +#define FSNOTIFY_GROUP_DUPS 0x02 /* allow multiple marks per object */ int flags; /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */ @@ -641,26 +642,26 @@ extern int fsnotify_get_conn_fsid(const struct fsnotify_mark_connector *conn, /* attach the mark to the object */ extern int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int obj_type, - int allow_dups, __kernel_fsid_t *fsid); + int add_flags, __kernel_fsid_t *fsid); extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark, fsnotify_connp_t *connp, - unsigned int obj_type, int allow_dups, + unsigned int obj_type, int add_flags, __kernel_fsid_t *fsid); /* attach the mark to the inode */ static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark, struct inode *inode, - int allow_dups) + int add_flags) { return fsnotify_add_mark(mark, &inode->i_fsnotify_marks, - FSNOTIFY_OBJ_TYPE_INODE, allow_dups, NULL); + FSNOTIFY_OBJ_TYPE_INODE, add_flags, NULL); } static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark, struct inode *inode, - int allow_dups) + int add_flags) { return fsnotify_add_mark_locked(mark, &inode->i_fsnotify_marks, - FSNOTIFY_OBJ_TYPE_INODE, allow_dups, + FSNOTIFY_OBJ_TYPE_INODE, add_flags, NULL); } -- cgit v1.2.3 From 43b245a788e2d8f1bb742668a9bdace02fcb3e96 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 22 Apr 2022 15:03:17 +0300 Subject: fsnotify: create helpers for group mark_mutex lock Create helpers to take and release the group mark_mutex lock. Define a flag FSNOTIFY_GROUP_NOFS in fsnotify_group that determines if the mark_mutex lock is fs reclaim safe or not. If not safe, the lock helpers take the lock and disable direct fs reclaim. In that case we annotate the mutex with a different lockdep class to express to lockdep that an allocation of mark of an fs reclaim safe group may take the group lock of another "NOFS" group to evict inodes. For now, converted only the callers in common code and no backend defines the NOFS flag. It is intended to be set by fanotify for evictable marks support. Link: https://lore.kernel.org/r/20220422120327.3459282-7-amir73il@gmail.com Suggested-by: Jan Kara Link: https://lore.kernel.org/r/20220321112310.vpr7oxro2xkz5llh@quack3.lan/ Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index dd440e6ff528..d62111e83244 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -20,6 +20,7 @@ #include #include #include +#include /* * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily @@ -212,7 +213,9 @@ struct fsnotify_group { #define FSNOTIFY_GROUP_USER 0x01 /* user allocated group */ #define FSNOTIFY_GROUP_DUPS 0x02 /* allow multiple marks per object */ +#define FSNOTIFY_GROUP_NOFS 0x04 /* group lock is not direct reclaim safe */ int flags; + unsigned int owner_flags; /* stored flags of mark_mutex owner */ /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */ struct mutex mark_mutex; /* protect marks_list */ @@ -254,6 +257,31 @@ struct fsnotify_group { }; }; +/* + * These helpers are used to prevent deadlock when reclaiming inodes with + * evictable marks of the same group that is allocating a new mark. + */ +static inline void fsnotify_group_lock(struct fsnotify_group *group) +{ + mutex_lock(&group->mark_mutex); + if (group->flags & FSNOTIFY_GROUP_NOFS) + group->owner_flags = memalloc_nofs_save(); +} + +static inline void fsnotify_group_unlock(struct fsnotify_group *group) +{ + if (group->flags & FSNOTIFY_GROUP_NOFS) + memalloc_nofs_restore(group->owner_flags); + mutex_unlock(&group->mark_mutex); +} + +static inline void fsnotify_group_assert_locked(struct fsnotify_group *group) +{ + WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex)); + if (group->flags & FSNOTIFY_GROUP_NOFS) + WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); +} + /* When calling fsnotify tell it if the data is a path or inode */ enum fsnotify_data_type { FSNOTIFY_EVENT_NONE, -- cgit v1.2.3 From c3638b5b13740fa31762d414bbce8b7a694e582a Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 22 Apr 2022 15:03:22 +0300 Subject: fsnotify: allow adding an inode mark without pinning inode fsnotify_add_mark() and variants implicitly take a reference on inode when attaching a mark to an inode. Make that behavior opt-out with the mark flag FSNOTIFY_MARK_FLAG_NO_IREF. Instead of taking the inode reference when attaching connector to inode and dropping the inode reference when detaching connector from inode, take the inode reference on attach of the first mark that wants to hold an inode reference and drop the inode reference on detach of the last mark that wants to hold an inode reference. Backends can "upgrade" an existing mark to take an inode reference, but cannot "downgrade" a mark with inode reference to release the refernce. This leaves the choice to the backend whether or not to pin the inode when adding an inode mark. This is intended to be used when adding a mark with ignored mask that is used for optimization in cases where group can afford getting unneeded events and reinstate the mark with ignored mask when inode is accessed again after being evicted. Link: https://lore.kernel.org/r/20220422120327.3459282-12-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index d62111e83244..9a1a9e78f69f 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -456,6 +456,7 @@ struct fsnotify_mark_connector { spinlock_t lock; unsigned short type; /* Type of object [lock] */ #define FSNOTIFY_CONN_FLAG_HAS_FSID 0x01 +#define FSNOTIFY_CONN_FLAG_HAS_IREF 0x02 unsigned short flags; /* flags [lock] */ __kernel_fsid_t fsid; /* fsid of filesystem containing object */ union { @@ -510,6 +511,7 @@ struct fsnotify_mark { #define FSNOTIFY_MARK_FLAG_IN_ONESHOT 0x0020 /* fanotify mark flags */ #define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x0100 +#define FSNOTIFY_MARK_FLAG_NO_IREF 0x0200 unsigned int flags; /* flags [mark->lock] */ }; -- cgit v1.2.3 From 7d5e005d982527e4029b0139823d179986e34cdc Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 22 Apr 2022 15:03:25 +0300 Subject: fanotify: implement "evictable" inode marks When an inode mark is created with flag FAN_MARK_EVICTABLE, it will not pin the marked inode to inode cache, so when inode is evicted from cache due to memory pressure, the mark will be lost. When an inode mark with flag FAN_MARK_EVICATBLE is updated without using this flag, the marked inode is pinned to inode cache. When an inode mark is updated with flag FAN_MARK_EVICTABLE but an existing mark already has the inode pinned, the mark update fails with error EEXIST. Evictable inode marks can be used to setup inode marks with ignored mask to suppress events from uninteresting files or directories in a lazy manner, upon receiving the first event, without having to iterate all the uninteresting files or directories before hand. The evictbale inode mark feature allows performing this lazy marks setup without exhausting the system memory with pinned inodes. This change does not enable the feature yet. Link: https://lore.kernel.org/linux-fsdevel/CAOQ4uxiRDpuS=2uA6+ZUM7yG9vVU-u212tkunBmSnP_u=mkv=Q@mail.gmail.com/ Link: https://lore.kernel.org/r/20220422120327.3459282-15-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/uapi/linux/fanotify.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index e8ac38cc2fd6..f1f89132d60e 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -82,6 +82,7 @@ #define FAN_MARK_IGNORED_SURV_MODIFY 0x00000040 #define FAN_MARK_FLUSH 0x00000080 /* FAN_MARK_FILESYSTEM is 0x00000100 */ +#define FAN_MARK_EVICTABLE 0x00000200 /* These are NOT bitwise flags. Both bits can be used togther. */ #define FAN_MARK_INODE 0x00000000 -- cgit v1.2.3 From 5f9d3bd520261fd7a850818c71809fd580e0f30c Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 22 Apr 2022 15:03:27 +0300 Subject: fanotify: enable "evictable" inode marks Now that the direct reclaim path is handled we can enable evictable inode marks. Link: https://lore.kernel.org/r/20220422120327.3459282-17-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fanotify.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 419cadcd7ff5..edc28555814c 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -66,6 +66,7 @@ FAN_MARK_ONLYDIR | \ FAN_MARK_IGNORED_MASK | \ FAN_MARK_IGNORED_SURV_MODIFY | \ + FAN_MARK_EVICTABLE | \ FAN_MARK_FLUSH) /* -- cgit v1.2.3 From cf51406ccb083941102fc101718d4c0a25b17917 Mon Sep 17 00:00:00 2001 From: Simon Trimmer Date: Mon, 25 Apr 2022 13:50:11 +0100 Subject: ASoC: soc.h: Introduce SOC_DOUBLE_R_S_EXT_TLV() macro A straightforward extension of the SOC_DOUBLE_R_S_TLV() macro that allows the get and put functions to be customised. Signed-off-by: Simon Trimmer Signed-off-by: Richard Fitzgerald Link: https://lore.kernel.org/r/20220425125012.3044919-2-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- include/sound/soc.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index 2d3261799d2c..8368b69dfef8 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -282,6 +282,17 @@ .get = xhandler_get, .put = xhandler_put, \ .private_value = SOC_DOUBLE_R_VALUE(reg_left, reg_right, xshift, \ xmax, xinvert) } +#define SOC_DOUBLE_R_S_EXT_TLV(xname, reg_left, reg_right, xshift, xmin, xmax, \ + xsign_bit, xinvert, xhandler_get, xhandler_put, \ + tlv_array) \ +{ .iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = (xname), \ + .access = SNDRV_CTL_ELEM_ACCESS_TLV_READ | \ + SNDRV_CTL_ELEM_ACCESS_READWRITE, \ + .tlv.p = (tlv_array), \ + .info = snd_soc_info_volsw, \ + .get = xhandler_get, .put = xhandler_put, \ + .private_value = SOC_DOUBLE_R_S_VALUE(reg_left, reg_right, xshift, \ + xmin, xmax, xsign_bit, xinvert) } #define SOC_SINGLE_BOOL_EXT(xname, xdata, xhandler_get, xhandler_put) \ { .iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = xname, \ .info = snd_soc_info_bool_ext, \ -- cgit v1.2.3 From 5349c0c93d15dff27d99fec12fc82040fab340bd Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Mon, 25 Apr 2022 13:50:12 +0100 Subject: ASoC: soc.h: Add SOC_SINGLE_S_EXT_TLV macro Add a SOC_SINGLE_S_EXT_TLV macro as a convenience wrapper around SOC_DOUBLE_R_S_EXT_TLV for mono volume controls. Signed-off-by: Richard Fitzgerald Link: https://lore.kernel.org/r/20220425125012.3044919-3-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- include/sound/soc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index 8368b69dfef8..f906e5a70830 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -293,6 +293,12 @@ .get = xhandler_get, .put = xhandler_put, \ .private_value = SOC_DOUBLE_R_S_VALUE(reg_left, reg_right, xshift, \ xmin, xmax, xsign_bit, xinvert) } +#define SOC_SINGLE_S_EXT_TLV(xname, xreg, xshift, xmin, xmax, \ + xsign_bit, xinvert, xhandler_get, xhandler_put, \ + tlv_array) \ + SOC_DOUBLE_R_S_EXT_TLV(xname, xreg, xreg, xshift, xmin, xmax, \ + xsign_bit, xinvert, xhandler_get, xhandler_put, \ + tlv_array) #define SOC_SINGLE_BOOL_EXT(xname, xdata, xhandler_get, xhandler_put) \ { .iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = xname, \ .info = snd_soc_info_bool_ext, \ -- cgit v1.2.3 From 430c3500995484962bdbccf358201afef8055535 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Mon, 25 Apr 2022 10:51:59 +0100 Subject: firmware: cirrus: cs_dsp: Avoid padding bytes in cs_dsp_coeff_ctl Change the order of members in struct cs_dsp_coeff_ctl to avoid the compiler having to insert alignment padding bytes. On a x86_64 build this saves 16 bytes per control. - Pointers are collected to the top of the struct (with the exception of priv, as noted below), so that they are inherently aligned. - The set and enable bitflags are placed together so they can be merged. - priv is placed at the end of the struct - it is for use by the client so it is helpful to make it stand out, and since the compiler will always pad the struct size to an alignment multiple putting a pointer last won't introduce any more padding. - struct cs_dsp_alg_region is placed at the end, right before priv, for the same reasoning as priv. Signed-off-by: Richard Fitzgerald Reviewed-by: Charles Keepax Link: https://lore.kernel.org/r/20220425095159.3044527-1-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- include/linux/firmware/cirrus/cs_dsp.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/firmware/cirrus/cs_dsp.h b/include/linux/firmware/cirrus/cs_dsp.h index 38b4da3ddfe4..30055706cce2 100644 --- a/include/linux/firmware/cirrus/cs_dsp.h +++ b/include/linux/firmware/cirrus/cs_dsp.h @@ -68,36 +68,36 @@ struct cs_dsp_alg_region { /** * struct cs_dsp_coeff_ctl - Describes a coefficient control + * @list: List node for internal use + * @dsp: DSP instance associated with this control + * @cache: Cached value of the control * @fw_name: Name of the firmware * @subname: Name of the control parsed from the WMFW * @subname_len: Length of subname - * @alg_region: Logical region associated with this control - * @dsp: DSP instance associated with this control - * @enabled: Flag indicating whether control is enabled - * @list: List node for internal use - * @cache: Cached value of the control * @offset: Offset of control within alg_region in words * @len: Length of the cached value in bytes - * @set: Flag indicating the value has been written by the user - * @flags: Bitfield of WMFW_CTL_FLAG_ control flags defined in wmfw.h * @type: One of the WMFW_CTL_TYPE_ control types defined in wmfw.h + * @flags: Bitfield of WMFW_CTL_FLAG_ control flags defined in wmfw.h + * @set: Flag indicating the value has been written by the user + * @enabled: Flag indicating whether control is enabled + * @alg_region: Logical region associated with this control * @priv: For use by the client */ struct cs_dsp_coeff_ctl { + struct list_head list; + struct cs_dsp *dsp; + void *cache; const char *fw_name; /* Subname is needed to match with firmware */ const char *subname; unsigned int subname_len; - struct cs_dsp_alg_region alg_region; - struct cs_dsp *dsp; - unsigned int enabled:1; - struct list_head list; - void *cache; unsigned int offset; size_t len; - unsigned int set:1; - unsigned int flags; unsigned int type; + unsigned int flags; + unsigned int set:1; + unsigned int enabled:1; + struct cs_dsp_alg_region alg_region; void *priv; }; -- cgit v1.2.3 From 66200bbcde697dea7f48071d325ea4dec6f66b11 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Tue, 12 Apr 2022 19:49:00 -0700 Subject: Drivers: hv: vmbus: Add VMbus IMC device to unsupported list Hyper-V may offer an Initial Machine Configuration (IMC) synthetic device to guest VMs. The device may be used by Windows guests to get specialization information, such as the hostname. But the device is not used in Linux and there is no Linux driver, so it is unsupported. Currently, the IMC device GUID is not recognized by the VMbus driver, which results in an "Unknown GUID" error message during boot. Add the GUID to the list of known but unsupported devices so that the error message is not generated. Other than avoiding the error message, there is no change in guest behavior. Signed-off-by: Michael Kelley Link: https://lore.kernel.org/r/1649818140-100953-1-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index fe2e0179ed51..2d085d951ee4 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1451,12 +1451,14 @@ void vmbus_free_mmio(resource_size_t start, resource_size_t size); 0x80, 0x2e, 0x27, 0xed, 0xe1, 0x9f) /* - * Linux doesn't support the 3 devices: the first two are for - * Automatic Virtual Machine Activation, and the third is for - * Remote Desktop Virtualization. + * Linux doesn't support these 4 devices: the first two are for + * Automatic Virtual Machine Activation, the third is for + * Remote Desktop Virtualization, and the fourth is Initial + * Machine Configuration (IMC) used only by Windows guests. * {f8e65716-3cb3-4a06-9a60-1889c5cccab5} * {3375baf4-9e15-4b30-b765-67acb10d607b} * {276aacf4-ac15-426c-98dd-7521ad3f01fe} + * {c376c1c3-d276-48d2-90a9-c04748072c60} */ #define HV_AVMA1_GUID \ @@ -1471,6 +1473,10 @@ void vmbus_free_mmio(resource_size_t start, resource_size_t size); .guid = GUID_INIT(0x276aacf4, 0xac15, 0x426c, 0x98, 0xdd, \ 0x75, 0x21, 0xad, 0x3f, 0x01, 0xfe) +#define HV_IMC_GUID \ + .guid = GUID_INIT(0xc376c1c3, 0xd276, 0x48d2, 0x90, 0xa9, \ + 0xc0, 0x47, 0x48, 0x07, 0x2c, 0x60) + /* * Common header for Hyper-V ICs */ -- cgit v1.2.3 From b03afa57c65e1e045e02df49777e953742745f4c Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Tue, 19 Apr 2022 14:23:22 +0200 Subject: Drivers: hv: vmbus: Introduce vmbus_sendpacket_getid() The function can be used to send a VMbus packet and retrieve the corresponding transaction ID. It will be used by hv_pci. No functional change. Suggested-by: Michael Kelley Signed-off-by: Andrea Parri (Microsoft) Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20220419122325.10078-4-parri.andrea@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 2d085d951ee4..7cb8718825ee 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1161,6 +1161,13 @@ extern int vmbus_open(struct vmbus_channel *channel, extern void vmbus_close(struct vmbus_channel *channel); +extern int vmbus_sendpacket_getid(struct vmbus_channel *channel, + void *buffer, + u32 bufferLen, + u64 requestid, + u64 *trans_id, + enum vmbus_packet_type type, + u32 flags); extern int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer, u32 bufferLen, -- cgit v1.2.3 From 0aadb6a7bb811554cf39318b5d18e8ec50dd9f02 Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Tue, 19 Apr 2022 14:23:23 +0200 Subject: Drivers: hv: vmbus: Introduce vmbus_request_addr_match() The function can be used to retrieve and clear/remove a transation ID from a channel requestor, provided the memory address corresponding to the ID equals a specified address. The function, and its 'lockless' variant __vmbus_request_addr_match(), will be used by hv_pci. Refactor vmbus_request_addr() to reuse the 'newly' introduced code. No functional change. Suggested-by: Michael Kelley Signed-off-by: Andrea Parri (Microsoft) Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20220419122325.10078-5-parri.andrea@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 7cb8718825ee..2e4962a2fbec 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -788,6 +788,7 @@ struct vmbus_requestor { #define VMBUS_NO_RQSTOR U64_MAX #define VMBUS_RQST_ERROR (U64_MAX - 1) +#define VMBUS_RQST_ADDR_ANY U64_MAX /* NetVSC-specific */ #define VMBUS_RQST_ID_NO_RESPONSE (U64_MAX - 2) /* StorVSC-specific */ @@ -1042,6 +1043,10 @@ struct vmbus_channel { }; u64 vmbus_next_request_id(struct vmbus_channel *channel, u64 rqst_addr); +u64 __vmbus_request_addr_match(struct vmbus_channel *channel, u64 trans_id, + u64 rqst_addr); +u64 vmbus_request_addr_match(struct vmbus_channel *channel, u64 trans_id, + u64 rqst_addr); u64 vmbus_request_addr(struct vmbus_channel *channel, u64 trans_id); static inline bool is_hvsock_channel(const struct vmbus_channel *c) -- cgit v1.2.3 From b91eaf7267cf7aec0a4e087decf7770dfb694d78 Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Tue, 19 Apr 2022 14:23:24 +0200 Subject: Drivers: hv: vmbus: Introduce {lock,unlock}_requestor() To abtract the lock and unlock operations on the requestor spin lock. The helpers will come in handy in hv_pci. No functional change. Suggested-by: Michael Kelley Signed-off-by: Andrea Parri (Microsoft) Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20220419122325.10078-6-parri.andrea@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 2e4962a2fbec..460a716f4748 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1042,6 +1042,21 @@ struct vmbus_channel { u32 max_pkt_size; }; +#define lock_requestor(channel, flags) \ +do { \ + struct vmbus_requestor *rqstor = &(channel)->requestor; \ + \ + spin_lock_irqsave(&rqstor->req_lock, flags); \ +} while (0) + +static __always_inline void unlock_requestor(struct vmbus_channel *channel, + unsigned long flags) +{ + struct vmbus_requestor *rqstor = &channel->requestor; + + spin_unlock_irqrestore(&rqstor->req_lock, flags); +} + u64 vmbus_next_request_id(struct vmbus_channel *channel, u64 rqst_addr); u64 __vmbus_request_addr_match(struct vmbus_channel *channel, u64 trans_id, u64 rqst_addr); -- cgit v1.2.3 From 067c098766c6af667a9002d4e33cf1f3c998abbe Mon Sep 17 00:00:00 2001 From: Frank Rowand Date: Wed, 20 Apr 2022 17:25:05 -0500 Subject: of: overlay: rework overlay apply and remove kfree()s Fix various kfree() issues related to of_overlay_apply(). - Double kfree() of fdt and tree when init_overlay_changeset() returns an error. - free_overlay_changeset() free the root of the unflattened overlay (variable tree) instead of the memory that contains the unflattened overlay. - For the case of a failure during applying an overlay, move kfree() of new_fdt and overlay_mem into free_overlay_changeset(), which is called by the function that allocated them. - For the case of removing an overlay, the kfree() of new_fdt and overlay_mem remains in free_overlay_changeset(). - Check return value of of_fdt_unflatten_tree() for error instead of checking the returned value of overlay_root. - When storing pointers to allocated objects in ovcs, do so as near to the allocation as possible instead of in deeply layered function. More clearly document policy related to lifetime of pointers into overlay memory. Double kfree() Reported-by: Slawomir Stepien Signed-off-by: Frank Rowand Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20220420222505.928492-3-frowand.list@gmail.com --- include/linux/of.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/of.h b/include/linux/of.h index 04971e85fbc9..17741eee0ca4 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -1543,7 +1543,8 @@ static inline bool of_device_is_system_power_controller(const struct device_node */ enum of_overlay_notify_action { - OF_OVERLAY_PRE_APPLY = 0, + OF_OVERLAY_INIT = 0, /* kzalloc() of ovcs sets this value */ + OF_OVERLAY_PRE_APPLY, OF_OVERLAY_POST_APPLY, OF_OVERLAY_PRE_REMOVE, OF_OVERLAY_POST_REMOVE, -- cgit v1.2.3 From 5b0e58542acb3672f42e08cb1cd57784f5e08d6b Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 7 Apr 2022 12:08:54 +0200 Subject: net: ieee802154: Enhance/fix the names of the MLME return codes Let's keep these definitions as close to the specification as possible while they are not yet in use. The names get slightly longer, but we gain the minor cost of being able to search the spec more easily. Signed-off-by: Miquel Raynal Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20220407100903.1695973-2-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt --- include/linux/ieee802154.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h index 95c831162212..01d945c8b2e1 100644 --- a/include/linux/ieee802154.h +++ b/include/linux/ieee802154.h @@ -136,16 +136,16 @@ enum { IEEE802154_SUCCESS = 0x0, /* The beacon was lost following a synchronization request. */ - IEEE802154_BEACON_LOSS = 0xe0, + IEEE802154_BEACON_LOST = 0xe0, /* * A transmission could not take place due to activity on the * channel, i.e., the CSMA-CA mechanism has failed. */ - IEEE802154_CHNL_ACCESS_FAIL = 0xe1, + IEEE802154_CHANNEL_ACCESS_FAILURE = 0xe1, /* The GTS request has been denied by the PAN coordinator. */ - IEEE802154_DENINED = 0xe2, + IEEE802154_DENIED = 0xe2, /* The attempt to disable the transceiver has failed. */ - IEEE802154_DISABLE_TRX_FAIL = 0xe3, + IEEE802154_DISABLE_TRX_FAILURE = 0xe3, /* * The received frame induces a failed security check according to * the security suite. @@ -185,9 +185,9 @@ enum { * A PAN identifier conflict has been detected and communicated to the * PAN coordinator. */ - IEEE802154_PANID_CONFLICT = 0xee, + IEEE802154_PAN_ID_CONFLICT = 0xee, /* A coordinator realignment command has been received. */ - IEEE802154_REALIGMENT = 0xef, + IEEE802154_REALIGNMENT = 0xef, /* The transaction has expired and its information discarded. */ IEEE802154_TRANSACTION_EXPIRED = 0xf0, /* There is no capacity to store the transaction. */ @@ -203,7 +203,7 @@ enum { * A SET/GET request was issued with the identifier of a PIB attribute * that is not supported. */ - IEEE802154_UNSUPPORTED_ATTR = 0xf4, + IEEE802154_UNSUPPORTED_ATTRIBUTE = 0xf4, /* * A request to perform a scan operation failed because the MLME was * in the process of performing a previously initiated scan operation. -- cgit v1.2.3 From f06cfc233ac67e26ed137f4e098c047939cf1530 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 7 Apr 2022 12:08:55 +0200 Subject: net: ieee802154: Fill the list of MLME return codes There are more codes than already listed, let's be a bit more exhaustive. This will allow to drop device drivers local definitions of these codes. Signed-off-by: Miquel Raynal Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20220407100903.1695973-3-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt --- include/linux/ieee802154.h | 67 +++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 66 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h index 01d945c8b2e1..f1f9412b6ac6 100644 --- a/include/linux/ieee802154.h +++ b/include/linux/ieee802154.h @@ -134,7 +134,35 @@ enum { * a successful transmission. */ IEEE802154_SUCCESS = 0x0, - + /* The requested operation failed. */ + IEEE802154_MAC_ERROR = 0x1, + /* The requested operation has been cancelled. */ + IEEE802154_CANCELLED = 0x2, + /* + * Device is ready to poll the coordinator for data in a non beacon + * enabled PAN. + */ + IEEE802154_READY_FOR_POLL = 0x3, + /* Wrong frame counter. */ + IEEE802154_COUNTER_ERROR = 0xdb, + /* + * The frame does not conforms to the incoming key usage policy checking + * procedure. + */ + IEEE802154_IMPROPER_KEY_TYPE = 0xdc, + /* + * The frame does not conforms to the incoming security level usage + * policy checking procedure. + */ + IEEE802154_IMPROPER_SECURITY_LEVEL = 0xdd, + /* Secured frame received with an empty Frame Version field. */ + IEEE802154_UNSUPPORTED_LEGACY = 0xde, + /* + * A secured frame is received or must be sent but security is not + * enabled in the device. Or, the Auxiliary Security Header has security + * level of zero in it. + */ + IEEE802154_UNSUPPORTED_SECURITY = 0xdf, /* The beacon was lost following a synchronization request. */ IEEE802154_BEACON_LOST = 0xe0, /* @@ -204,11 +232,48 @@ enum { * that is not supported. */ IEEE802154_UNSUPPORTED_ATTRIBUTE = 0xf4, + /* Missing source or destination address or address mode. */ + IEEE802154_INVALID_ADDRESS = 0xf5, + /* + * MLME asked to turn the receiver on, but the on time duration is too + * big compared to the macBeaconOrder. + */ + IEEE802154_ON_TIME_TOO_LONG = 0xf6, + /* + * MLME asaked to turn the receiver on, but the request was delayed for + * too long before getting processed. + */ + IEEE802154_PAST_TIME = 0xf7, + /* + * The StartTime parameter is nonzero, and the MLME is not currently + * tracking the beacon of the coordinator through which it is + * associated. + */ + IEEE802154_TRACKING_OFF = 0xf8, + /* + * The index inside the hierarchical values in PIBAttribute is out of + * range. + */ + IEEE802154_INVALID_INDEX = 0xf9, + /* + * The number of PAN descriptors discovered during a scan has been + * reached. + */ + IEEE802154_LIMIT_REACHED = 0xfa, + /* + * The PIBAttribute parameter specifies an attribute that is a read-only + * attribute. + */ + IEEE802154_READ_ONLY = 0xfb, /* * A request to perform a scan operation failed because the MLME was * in the process of performing a previously initiated scan operation. */ IEEE802154_SCAN_IN_PROGRESS = 0xfc, + /* The outgoing superframe overlaps the incoming superframe. */ + IEEE802154_SUPERFRAME_OVERLAP = 0xfd, + /* Any other error situation. */ + IEEE802154_SYSTEM_ERROR = 0xff, }; /* frame control handling */ -- cgit v1.2.3 From 30ca44eb2480ede838c7c8c131a7d25589a98f0a Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 7 Apr 2022 12:08:57 +0200 Subject: net: mac802154: Create an offloaded transmission error helper So far there is only a helper for successful transmissions, which led device drivers to implement their own handling in case of error. Unfortunately, we really need all the drivers to give the hand back to the core once they are done in order to be able to build a proper synchronous API. So let's create a _xmit_error() helper and take this opportunity to fill the new device-global field storing Tx statuses. Suggested-by: Alexander Aring Signed-off-by: Miquel Raynal Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20220407100903.1695973-5-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt --- include/net/mac802154.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/mac802154.h b/include/net/mac802154.h index 2c3bbc6645ba..29f289d58720 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -498,4 +498,14 @@ void ieee802154_stop_queue(struct ieee802154_hw *hw); void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb, bool ifs_handling); +/** + * ieee802154_xmit_error - offloaded frame transmission failed + * + * @hw: pointer as obtained from ieee802154_alloc_hw(). + * @skb: buffer for transmission + * @reason: error code + */ +void ieee802154_xmit_error(struct ieee802154_hw *hw, struct sk_buff *skb, + int reason); + #endif /* NET_MAC802154_H */ -- cgit v1.2.3 From 5a1b57c0dde9b93ba8261fa1c81f9aae2bac284a Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 7 Apr 2022 12:08:58 +0200 Subject: net: mac802154: Create an error helper for asynchronous offloading errors A few drivers do the full transmit operation asynchronously, which means that a bus error that happens when forwarding the packet to the transmitter or a timeout happening when offloading the request to the transmitter will not be reported immediately. The solution in this case is to call this new helper to free the necessary resources, restart the queue and always return the same generic TRAC error code: IEEE802154_SYSTEM_ERROR. Suggested-by: Alexander Aring Signed-off-by: Miquel Raynal Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20220407100903.1695973-6-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt --- include/net/mac802154.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/mac802154.h b/include/net/mac802154.h index 29f289d58720..bdac0ddbdcdb 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -508,4 +508,13 @@ void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb, void ieee802154_xmit_error(struct ieee802154_hw *hw, struct sk_buff *skb, int reason); +/** + * ieee802154_xmit_hw_error - frame could not be offloaded to the transmitter + * because of a hardware error (bus error, timeout, etc) + * + * @hw: pointer as obtained from ieee802154_alloc_hw(). + * @skb: buffer for transmission + */ +void ieee802154_xmit_hw_error(struct ieee802154_hw *hw, struct sk_buff *skb); + #endif /* NET_MAC802154_H */ -- cgit v1.2.3 From c83227a5d05ed77b634ce4c2fc5f143ae2a4d6f5 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 21 Apr 2022 22:06:54 +0200 Subject: irq/gpio: ixp4xx: Drop boardfile probe path The boardfiles for IXP4xx have been deleted. Delete all the quirks and code dealing with that boot path and rely solely on device tree boot. Fix some missing static keywords that the kernel test robot was complaining about while we're at it. Cc: Bartosz Golaszewski Acked-by: Marc Zyngier Signed-off-by: Linus Walleij Signed-off-by: Bartosz Golaszewski --- include/linux/irqchip/irq-ixp4xx.h | 12 ------------ 1 file changed, 12 deletions(-) delete mode 100644 include/linux/irqchip/irq-ixp4xx.h (limited to 'include') diff --git a/include/linux/irqchip/irq-ixp4xx.h b/include/linux/irqchip/irq-ixp4xx.h deleted file mode 100644 index 9395917d6936..000000000000 --- a/include/linux/irqchip/irq-ixp4xx.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __IRQ_IXP4XX_H -#define __IRQ_IXP4XX_H - -#include -struct irq_domain; - -void ixp4xx_irq_init(resource_size_t irqbase, - bool is_356); -struct irq_domain *ixp4xx_get_irq_domain(void); - -#endif /* __IRQ_IXP4XX_H */ -- cgit v1.2.3 From fae74fb5d525f979085b6e70b883d7a7049bf15f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 25 Apr 2022 19:32:55 +0200 Subject: gpio: pcf857x: Make teardown callback return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All teardown functions return 0. Also there is little sense in returning a negative error code from an i2c remove function as this only results in emitting an error message but the device is removed nevertheless. This patch is a preparation for making i2c remove callbacks return void. Signed-off-by: Uwe Kleine-König Signed-off-by: Bartosz Golaszewski --- include/linux/platform_data/pcf857x.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/platform_data/pcf857x.h b/include/linux/platform_data/pcf857x.h index 11d4ed78c7f4..01d0a3ea3aef 100644 --- a/include/linux/platform_data/pcf857x.h +++ b/include/linux/platform_data/pcf857x.h @@ -36,7 +36,7 @@ struct pcf857x_platform_data { int (*setup)(struct i2c_client *client, int gpio, unsigned ngpio, void *context); - int (*teardown)(struct i2c_client *client, + void (*teardown)(struct i2c_client *client, int gpio, unsigned ngpio, void *context); void *context; -- cgit v1.2.3 From 0f40ba48de3b8a4c5793013768cd62805033869c Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Wed, 6 Apr 2022 15:10:19 +0530 Subject: drm/msm/dsi: Pass DSC params to drm_panel When DSC is enabled, we need to get the DSC parameters from the panel driver, so add a dsc parameter in panel to fetch and pass DSC configuration for DSI panels to DPU encoder, which will enable and then configure DSC hardware blocks accordingly. Signed-off-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Signed-off-by: Vinod Koul Patchwork: https://patchwork.freedesktop.org/patch/480910/ Link: https://lore.kernel.org/r/20220406094031.1027376-3-vkoul@kernel.org Signed-off-by: Dmitry Baryshkov --- include/drm/drm_panel.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/drm/drm_panel.h b/include/drm/drm_panel.h index 1ba2d424a53f..d279ee455f01 100644 --- a/include/drm/drm_panel.h +++ b/include/drm/drm_panel.h @@ -179,6 +179,13 @@ struct drm_panel { * Panel entry in registry. */ struct list_head list; + + /** + * @dsc: + * + * Panel DSC pps payload to be sent + */ + struct drm_dsc_config *dsc; }; void drm_panel_init(struct drm_panel *panel, struct device *dev, -- cgit v1.2.3 From c277f1411d7bc2831d48bde5c18d3b7f87c61646 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Mon, 21 Mar 2022 15:13:06 -0700 Subject: f2fs: introduce data read/write showing path info This was used in Android for a long time. Let's upstream it. Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 94 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 94 insertions(+) (limited to 'include') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 1779e133cea0..4d1ad64d4cab 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -2067,6 +2067,100 @@ TRACE_EVENT(f2fs_fiemap, __entry->ret) ); +DECLARE_EVENT_CLASS(f2fs__rw_start, + + TP_PROTO(struct inode *inode, loff_t offset, int bytes, + pid_t pid, char *pathname, char *command), + + TP_ARGS(inode, offset, bytes, pid, pathname, command), + + TP_STRUCT__entry( + __string(pathbuf, pathname) + __field(loff_t, offset) + __field(int, bytes) + __field(loff_t, i_size) + __string(cmdline, command) + __field(pid_t, pid) + __field(ino_t, ino) + ), + + TP_fast_assign( + /* + * Replace the spaces in filenames and cmdlines + * because this screws up the tooling that parses + * the traces. + */ + __assign_str(pathbuf, pathname); + (void)strreplace(__get_str(pathbuf), ' ', '_'); + __entry->offset = offset; + __entry->bytes = bytes; + __entry->i_size = i_size_read(inode); + __assign_str(cmdline, command); + (void)strreplace(__get_str(cmdline), ' ', '_'); + __entry->pid = pid; + __entry->ino = inode->i_ino; + ), + + TP_printk("entry_name %s, offset %llu, bytes %d, cmdline %s," + " pid %d, i_size %llu, ino %lu", + __get_str(pathbuf), __entry->offset, __entry->bytes, + __get_str(cmdline), __entry->pid, __entry->i_size, + (unsigned long) __entry->ino) +); + +DECLARE_EVENT_CLASS(f2fs__rw_end, + + TP_PROTO(struct inode *inode, loff_t offset, int bytes), + + TP_ARGS(inode, offset, bytes), + + TP_STRUCT__entry( + __field(ino_t, ino) + __field(loff_t, offset) + __field(int, bytes) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->offset = offset; + __entry->bytes = bytes; + ), + + TP_printk("ino %lu, offset %llu, bytes %d", + (unsigned long) __entry->ino, + __entry->offset, __entry->bytes) +); + +DEFINE_EVENT(f2fs__rw_start, f2fs_dataread_start, + + TP_PROTO(struct inode *inode, loff_t offset, int bytes, + pid_t pid, char *pathname, char *command), + + TP_ARGS(inode, offset, bytes, pid, pathname, command) +); + +DEFINE_EVENT(f2fs__rw_end, f2fs_dataread_end, + + TP_PROTO(struct inode *inode, loff_t offset, int bytes), + + TP_ARGS(inode, offset, bytes) +); + +DEFINE_EVENT(f2fs__rw_start, f2fs_datawrite_start, + + TP_PROTO(struct inode *inode, loff_t offset, int bytes, + pid_t pid, char *pathname, char *command), + + TP_ARGS(inode, offset, bytes, pid, pathname, command) +); + +DEFINE_EVENT(f2fs__rw_end, f2fs_datawrite_end, + + TP_PROTO(struct inode *inode, loff_t offset, int bytes), + + TP_ARGS(inode, offset, bytes) +); + #endif /* _TRACE_F2FS_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 7335631fcd5eecfa84555bd57433e6446d06ad21 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 15 Apr 2022 00:17:47 +0200 Subject: dt-bindings: clock: u8500: Add clkout clock bindings This adds device tree bindings for the externally routed clocks CLKOUT1 and CLKOUT2 clocks found in the DB8500. Cc: devicetree@vger.kernel.org Reviewed-by: Ulf Hansson Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20220414221751.323525-2-linus.walleij@linaro.org Reviewed-by: Rob Herring Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/ste-db8500-clkout.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 include/dt-bindings/clock/ste-db8500-clkout.h (limited to 'include') diff --git a/include/dt-bindings/clock/ste-db8500-clkout.h b/include/dt-bindings/clock/ste-db8500-clkout.h new file mode 100644 index 000000000000..ca07cb2bd1bc --- /dev/null +++ b/include/dt-bindings/clock/ste-db8500-clkout.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __STE_CLK_DB8500_CLKOUT_H__ +#define __STE_CLK_DB8500_CLKOUT_H__ + +#define DB8500_CLKOUT_1 0 +#define DB8500_CLKOUT_2 1 + +#define DB8500_CLKOUT_SRC_CLK38M 0 +#define DB8500_CLKOUT_SRC_ACLK 1 +#define DB8500_CLKOUT_SRC_SYSCLK 2 +#define DB8500_CLKOUT_SRC_LCDCLK 3 +#define DB8500_CLKOUT_SRC_SDMMCCLK 4 +#define DB8500_CLKOUT_SRC_TVCLK 5 +#define DB8500_CLKOUT_SRC_TIMCLK 6 +#define DB8500_CLKOUT_SRC_CLK009 7 + +#endif -- cgit v1.2.3 From f113a51aa2cfbd22c376d8722b5c9fef469be162 Mon Sep 17 00:00:00 2001 From: Chun-Jie Chen Date: Sat, 9 Apr 2022 21:22:37 +0800 Subject: dt-bindings: ARM: MediaTek: Add new document bindings of MT8186 clock This patch adds the new binding documentation for system clock and functional clock on MediaTek MT8186. Signed-off-by: Chun-Jie Chen Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20220409132251.31725-2-chun-jie.chen@mediatek.com Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/mt8186-clk.h | 445 +++++++++++++++++++++++++++++++++ 1 file changed, 445 insertions(+) create mode 100644 include/dt-bindings/clock/mt8186-clk.h (limited to 'include') diff --git a/include/dt-bindings/clock/mt8186-clk.h b/include/dt-bindings/clock/mt8186-clk.h new file mode 100644 index 000000000000..a70bf67af47d --- /dev/null +++ b/include/dt-bindings/clock/mt8186-clk.h @@ -0,0 +1,445 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Chun-Jie Chen + */ + +#ifndef _DT_BINDINGS_CLK_MT8186_H +#define _DT_BINDINGS_CLK_MT8186_H + +/* MCUSYS */ + +#define CLK_MCU_ARMPLL_LL_SEL 0 +#define CLK_MCU_ARMPLL_BL_SEL 1 +#define CLK_MCU_ARMPLL_BUS_SEL 2 +#define CLK_MCU_NR_CLK 3 + +/* TOPCKGEN */ + +#define CLK_TOP_AXI 0 +#define CLK_TOP_SCP 1 +#define CLK_TOP_MFG 2 +#define CLK_TOP_CAMTG 3 +#define CLK_TOP_CAMTG1 4 +#define CLK_TOP_CAMTG2 5 +#define CLK_TOP_CAMTG3 6 +#define CLK_TOP_CAMTG4 7 +#define CLK_TOP_CAMTG5 8 +#define CLK_TOP_CAMTG6 9 +#define CLK_TOP_UART 10 +#define CLK_TOP_SPI 11 +#define CLK_TOP_MSDC50_0_HCLK 12 +#define CLK_TOP_MSDC50_0 13 +#define CLK_TOP_MSDC30_1 14 +#define CLK_TOP_AUDIO 15 +#define CLK_TOP_AUD_INTBUS 16 +#define CLK_TOP_AUD_1 17 +#define CLK_TOP_AUD_2 18 +#define CLK_TOP_AUD_ENGEN1 19 +#define CLK_TOP_AUD_ENGEN2 20 +#define CLK_TOP_DISP_PWM 21 +#define CLK_TOP_SSPM 22 +#define CLK_TOP_DXCC 23 +#define CLK_TOP_USB_TOP 24 +#define CLK_TOP_SRCK 25 +#define CLK_TOP_SPM 26 +#define CLK_TOP_I2C 27 +#define CLK_TOP_PWM 28 +#define CLK_TOP_SENINF 29 +#define CLK_TOP_SENINF1 30 +#define CLK_TOP_SENINF2 31 +#define CLK_TOP_SENINF3 32 +#define CLK_TOP_AES_MSDCFDE 33 +#define CLK_TOP_PWRAP_ULPOSC 34 +#define CLK_TOP_CAMTM 35 +#define CLK_TOP_VENC 36 +#define CLK_TOP_CAM 37 +#define CLK_TOP_IMG1 38 +#define CLK_TOP_IPE 39 +#define CLK_TOP_DPMAIF 40 +#define CLK_TOP_VDEC 41 +#define CLK_TOP_DISP 42 +#define CLK_TOP_MDP 43 +#define CLK_TOP_AUDIO_H 44 +#define CLK_TOP_UFS 45 +#define CLK_TOP_AES_FDE 46 +#define CLK_TOP_AUDIODSP 47 +#define CLK_TOP_DVFSRC 48 +#define CLK_TOP_DSI_OCC 49 +#define CLK_TOP_SPMI_MST 50 +#define CLK_TOP_SPINOR 51 +#define CLK_TOP_NNA 52 +#define CLK_TOP_NNA1 53 +#define CLK_TOP_NNA2 54 +#define CLK_TOP_SSUSB_XHCI 55 +#define CLK_TOP_SSUSB_TOP_1P 56 +#define CLK_TOP_SSUSB_XHCI_1P 57 +#define CLK_TOP_WPE 58 +#define CLK_TOP_DPI 59 +#define CLK_TOP_U3_OCC_250M 60 +#define CLK_TOP_U3_OCC_500M 61 +#define CLK_TOP_ADSP_BUS 62 +#define CLK_TOP_APLL_I2S0_MCK_SEL 63 +#define CLK_TOP_APLL_I2S1_MCK_SEL 64 +#define CLK_TOP_APLL_I2S2_MCK_SEL 65 +#define CLK_TOP_APLL_I2S4_MCK_SEL 66 +#define CLK_TOP_APLL_TDMOUT_MCK_SEL 67 +#define CLK_TOP_MAINPLL_D2 68 +#define CLK_TOP_MAINPLL_D2_D2 69 +#define CLK_TOP_MAINPLL_D2_D4 70 +#define CLK_TOP_MAINPLL_D2_D16 71 +#define CLK_TOP_MAINPLL_D3 72 +#define CLK_TOP_MAINPLL_D3_D2 73 +#define CLK_TOP_MAINPLL_D3_D4 74 +#define CLK_TOP_MAINPLL_D5 75 +#define CLK_TOP_MAINPLL_D5_D2 76 +#define CLK_TOP_MAINPLL_D5_D4 77 +#define CLK_TOP_MAINPLL_D7 78 +#define CLK_TOP_MAINPLL_D7_D2 79 +#define CLK_TOP_MAINPLL_D7_D4 80 +#define CLK_TOP_UNIVPLL 81 +#define CLK_TOP_UNIVPLL_D2 82 +#define CLK_TOP_UNIVPLL_D2_D2 83 +#define CLK_TOP_UNIVPLL_D2_D4 84 +#define CLK_TOP_UNIVPLL_D3 85 +#define CLK_TOP_UNIVPLL_D3_D2 86 +#define CLK_TOP_UNIVPLL_D3_D4 87 +#define CLK_TOP_UNIVPLL_D3_D8 88 +#define CLK_TOP_UNIVPLL_D3_D32 89 +#define CLK_TOP_UNIVPLL_D5 90 +#define CLK_TOP_UNIVPLL_D5_D2 91 +#define CLK_TOP_UNIVPLL_D5_D4 92 +#define CLK_TOP_UNIVPLL_D7 93 +#define CLK_TOP_UNIVPLL_192M 94 +#define CLK_TOP_UNIVPLL_192M_D4 95 +#define CLK_TOP_UNIVPLL_192M_D8 96 +#define CLK_TOP_UNIVPLL_192M_D16 97 +#define CLK_TOP_UNIVPLL_192M_D32 98 +#define CLK_TOP_APLL1_D2 99 +#define CLK_TOP_APLL1_D4 100 +#define CLK_TOP_APLL1_D8 101 +#define CLK_TOP_APLL2_D2 102 +#define CLK_TOP_APLL2_D4 103 +#define CLK_TOP_APLL2_D8 104 +#define CLK_TOP_MMPLL_D2 105 +#define CLK_TOP_TVDPLL_D2 106 +#define CLK_TOP_TVDPLL_D4 107 +#define CLK_TOP_TVDPLL_D8 108 +#define CLK_TOP_TVDPLL_D16 109 +#define CLK_TOP_TVDPLL_D32 110 +#define CLK_TOP_MSDCPLL_D2 111 +#define CLK_TOP_ULPOSC1 112 +#define CLK_TOP_ULPOSC1_D2 113 +#define CLK_TOP_ULPOSC1_D4 114 +#define CLK_TOP_ULPOSC1_D8 115 +#define CLK_TOP_ULPOSC1_D10 116 +#define CLK_TOP_ULPOSC1_D16 117 +#define CLK_TOP_ULPOSC1_D32 118 +#define CLK_TOP_ADSPPLL_D2 119 +#define CLK_TOP_ADSPPLL_D4 120 +#define CLK_TOP_ADSPPLL_D8 121 +#define CLK_TOP_NNAPLL_D2 122 +#define CLK_TOP_NNAPLL_D4 123 +#define CLK_TOP_NNAPLL_D8 124 +#define CLK_TOP_NNA2PLL_D2 125 +#define CLK_TOP_NNA2PLL_D4 126 +#define CLK_TOP_NNA2PLL_D8 127 +#define CLK_TOP_F_BIST2FPC 128 +#define CLK_TOP_466M_FMEM 129 +#define CLK_TOP_MPLL 130 +#define CLK_TOP_APLL12_CK_DIV0 131 +#define CLK_TOP_APLL12_CK_DIV1 132 +#define CLK_TOP_APLL12_CK_DIV2 133 +#define CLK_TOP_APLL12_CK_DIV4 134 +#define CLK_TOP_APLL12_CK_DIV_TDMOUT_M 135 +#define CLK_TOP_NR_CLK 136 + +/* INFRACFG_AO */ + +#define CLK_INFRA_AO_PMIC_TMR 0 +#define CLK_INFRA_AO_PMIC_AP 1 +#define CLK_INFRA_AO_PMIC_MD 2 +#define CLK_INFRA_AO_PMIC_CONN 3 +#define CLK_INFRA_AO_SCP_CORE 4 +#define CLK_INFRA_AO_SEJ 5 +#define CLK_INFRA_AO_APXGPT 6 +#define CLK_INFRA_AO_ICUSB 7 +#define CLK_INFRA_AO_GCE 8 +#define CLK_INFRA_AO_THERM 9 +#define CLK_INFRA_AO_I2C_AP 10 +#define CLK_INFRA_AO_I2C_CCU 11 +#define CLK_INFRA_AO_I2C_SSPM 12 +#define CLK_INFRA_AO_I2C_RSV 13 +#define CLK_INFRA_AO_PWM_HCLK 14 +#define CLK_INFRA_AO_PWM1 15 +#define CLK_INFRA_AO_PWM2 16 +#define CLK_INFRA_AO_PWM3 17 +#define CLK_INFRA_AO_PWM4 18 +#define CLK_INFRA_AO_PWM5 19 +#define CLK_INFRA_AO_PWM 20 +#define CLK_INFRA_AO_UART0 21 +#define CLK_INFRA_AO_UART1 22 +#define CLK_INFRA_AO_UART2 23 +#define CLK_INFRA_AO_GCE_26M 24 +#define CLK_INFRA_AO_CQ_DMA_FPC 25 +#define CLK_INFRA_AO_BTIF 26 +#define CLK_INFRA_AO_SPI0 27 +#define CLK_INFRA_AO_MSDC0 28 +#define CLK_INFRA_AO_MSDCFDE 29 +#define CLK_INFRA_AO_MSDC1 30 +#define CLK_INFRA_AO_DVFSRC 31 +#define CLK_INFRA_AO_GCPU 32 +#define CLK_INFRA_AO_TRNG 33 +#define CLK_INFRA_AO_AUXADC 34 +#define CLK_INFRA_AO_CPUM 35 +#define CLK_INFRA_AO_CCIF1_AP 36 +#define CLK_INFRA_AO_CCIF1_MD 37 +#define CLK_INFRA_AO_AUXADC_MD 38 +#define CLK_INFRA_AO_AP_DMA 39 +#define CLK_INFRA_AO_XIU 40 +#define CLK_INFRA_AO_DEVICE_APC 41 +#define CLK_INFRA_AO_CCIF_AP 42 +#define CLK_INFRA_AO_DEBUGTOP 43 +#define CLK_INFRA_AO_AUDIO 44 +#define CLK_INFRA_AO_CCIF_MD 45 +#define CLK_INFRA_AO_DXCC_SEC_CORE 46 +#define CLK_INFRA_AO_DXCC_AO 47 +#define CLK_INFRA_AO_IMP_IIC 48 +#define CLK_INFRA_AO_DRAMC_F26M 49 +#define CLK_INFRA_AO_RG_PWM_FBCLK6 50 +#define CLK_INFRA_AO_SSUSB_TOP_HCLK 51 +#define CLK_INFRA_AO_DISP_PWM 52 +#define CLK_INFRA_AO_CLDMA_BCLK 53 +#define CLK_INFRA_AO_AUDIO_26M_BCLK 54 +#define CLK_INFRA_AO_SSUSB_TOP_P1_HCLK 55 +#define CLK_INFRA_AO_SPI1 56 +#define CLK_INFRA_AO_I2C4 57 +#define CLK_INFRA_AO_MODEM_TEMP_SHARE 58 +#define CLK_INFRA_AO_SPI2 59 +#define CLK_INFRA_AO_SPI3 60 +#define CLK_INFRA_AO_SSUSB_TOP_REF 61 +#define CLK_INFRA_AO_SSUSB_TOP_XHCI 62 +#define CLK_INFRA_AO_SSUSB_TOP_P1_REF 63 +#define CLK_INFRA_AO_SSUSB_TOP_P1_XHCI 64 +#define CLK_INFRA_AO_SSPM 65 +#define CLK_INFRA_AO_SSUSB_TOP_P1_SYS 66 +#define CLK_INFRA_AO_I2C5 67 +#define CLK_INFRA_AO_I2C5_ARBITER 68 +#define CLK_INFRA_AO_I2C5_IMM 69 +#define CLK_INFRA_AO_I2C1_ARBITER 70 +#define CLK_INFRA_AO_I2C1_IMM 71 +#define CLK_INFRA_AO_I2C2_ARBITER 72 +#define CLK_INFRA_AO_I2C2_IMM 73 +#define CLK_INFRA_AO_SPI4 74 +#define CLK_INFRA_AO_SPI5 75 +#define CLK_INFRA_AO_CQ_DMA 76 +#define CLK_INFRA_AO_BIST2FPC 77 +#define CLK_INFRA_AO_MSDC0_SELF 78 +#define CLK_INFRA_AO_SPINOR 79 +#define CLK_INFRA_AO_SSPM_26M_SELF 80 +#define CLK_INFRA_AO_SSPM_32K_SELF 81 +#define CLK_INFRA_AO_I2C6 82 +#define CLK_INFRA_AO_AP_MSDC0 83 +#define CLK_INFRA_AO_MD_MSDC0 84 +#define CLK_INFRA_AO_MSDC0_SRC 85 +#define CLK_INFRA_AO_MSDC1_SRC 86 +#define CLK_INFRA_AO_SEJ_F13M 87 +#define CLK_INFRA_AO_AES_TOP0_BCLK 88 +#define CLK_INFRA_AO_MCU_PM_BCLK 89 +#define CLK_INFRA_AO_CCIF2_AP 90 +#define CLK_INFRA_AO_CCIF2_MD 91 +#define CLK_INFRA_AO_CCIF3_AP 92 +#define CLK_INFRA_AO_CCIF3_MD 93 +#define CLK_INFRA_AO_FADSP_26M 94 +#define CLK_INFRA_AO_FADSP_32K 95 +#define CLK_INFRA_AO_CCIF4_AP 96 +#define CLK_INFRA_AO_CCIF4_MD 97 +#define CLK_INFRA_AO_FADSP 98 +#define CLK_INFRA_AO_FLASHIF_133M 99 +#define CLK_INFRA_AO_FLASHIF_66M 100 +#define CLK_INFRA_AO_NR_CLK 101 + +/* APMIXEDSYS */ + +#define CLK_APMIXED_ARMPLL_LL 0 +#define CLK_APMIXED_ARMPLL_BL 1 +#define CLK_APMIXED_CCIPLL 2 +#define CLK_APMIXED_MAINPLL 3 +#define CLK_APMIXED_UNIV2PLL 4 +#define CLK_APMIXED_MSDCPLL 5 +#define CLK_APMIXED_MMPLL 6 +#define CLK_APMIXED_NNAPLL 7 +#define CLK_APMIXED_NNA2PLL 8 +#define CLK_APMIXED_ADSPPLL 9 +#define CLK_APMIXED_MFGPLL 10 +#define CLK_APMIXED_TVDPLL 11 +#define CLK_APMIXED_APLL1 12 +#define CLK_APMIXED_APLL2 13 +#define CLK_APMIXED_NR_CLK 14 + +/* IMP_IIC_WRAP */ + +#define CLK_IMP_IIC_WRAP_AP_CLOCK_I2C0 0 +#define CLK_IMP_IIC_WRAP_AP_CLOCK_I2C1 1 +#define CLK_IMP_IIC_WRAP_AP_CLOCK_I2C2 2 +#define CLK_IMP_IIC_WRAP_AP_CLOCK_I2C3 3 +#define CLK_IMP_IIC_WRAP_AP_CLOCK_I2C4 4 +#define CLK_IMP_IIC_WRAP_AP_CLOCK_I2C5 5 +#define CLK_IMP_IIC_WRAP_AP_CLOCK_I2C6 6 +#define CLK_IMP_IIC_WRAP_AP_CLOCK_I2C7 7 +#define CLK_IMP_IIC_WRAP_AP_CLOCK_I2C8 8 +#define CLK_IMP_IIC_WRAP_AP_CLOCK_I2C9 9 +#define CLK_IMP_IIC_WRAP_NR_CLK 10 + +/* MFGCFG */ + +#define CLK_MFG_BG3D 0 +#define CLK_MFG_NR_CLK 1 + +/* MMSYS */ + +#define CLK_MM_DISP_MUTEX0 0 +#define CLK_MM_APB_MM_BUS 1 +#define CLK_MM_DISP_OVL0 2 +#define CLK_MM_DISP_RDMA0 3 +#define CLK_MM_DISP_OVL0_2L 4 +#define CLK_MM_DISP_WDMA0 5 +#define CLK_MM_DISP_RSZ0 6 +#define CLK_MM_DISP_AAL0 7 +#define CLK_MM_DISP_CCORR0 8 +#define CLK_MM_DISP_COLOR0 9 +#define CLK_MM_SMI_INFRA 10 +#define CLK_MM_DISP_DSC_WRAP0 11 +#define CLK_MM_DISP_GAMMA0 12 +#define CLK_MM_DISP_POSTMASK0 13 +#define CLK_MM_DISP_DITHER0 14 +#define CLK_MM_SMI_COMMON 15 +#define CLK_MM_DSI0 16 +#define CLK_MM_DISP_FAKE_ENG0 17 +#define CLK_MM_DISP_FAKE_ENG1 18 +#define CLK_MM_SMI_GALS 19 +#define CLK_MM_SMI_IOMMU 20 +#define CLK_MM_DISP_RDMA1 21 +#define CLK_MM_DISP_DPI 22 +#define CLK_MM_DSI0_DSI_CK_DOMAIN 23 +#define CLK_MM_DISP_26M 24 +#define CLK_MM_NR_CLK 25 + +/* WPESYS */ + +#define CLK_WPE_CK_EN 0 +#define CLK_WPE_SMI_LARB8_CK_EN 1 +#define CLK_WPE_SYS_EVENT_TX_CK_EN 2 +#define CLK_WPE_SMI_LARB8_PCLK_EN 3 +#define CLK_WPE_NR_CLK 4 + +/* IMGSYS1 */ + +#define CLK_IMG1_LARB9_IMG1 0 +#define CLK_IMG1_LARB10_IMG1 1 +#define CLK_IMG1_DIP 2 +#define CLK_IMG1_GALS_IMG1 3 +#define CLK_IMG1_NR_CLK 4 + +/* IMGSYS2 */ + +#define CLK_IMG2_LARB9_IMG2 0 +#define CLK_IMG2_LARB10_IMG2 1 +#define CLK_IMG2_MFB 2 +#define CLK_IMG2_WPE 3 +#define CLK_IMG2_MSS 4 +#define CLK_IMG2_GALS_IMG2 5 +#define CLK_IMG2_NR_CLK 6 + +/* VDECSYS */ + +#define CLK_VDEC_LARB1_CKEN 0 +#define CLK_VDEC_LAT_CKEN 1 +#define CLK_VDEC_LAT_ACTIVE 2 +#define CLK_VDEC_LAT_CKEN_ENG 3 +#define CLK_VDEC_MINI_MDP_CKEN_CFG_RG 4 +#define CLK_VDEC_CKEN 5 +#define CLK_VDEC_ACTIVE 6 +#define CLK_VDEC_CKEN_ENG 7 +#define CLK_VDEC_NR_CLK 8 + +/* VENCSYS */ + +#define CLK_VENC_CKE0_LARB 0 +#define CLK_VENC_CKE1_VENC 1 +#define CLK_VENC_CKE2_JPGENC 2 +#define CLK_VENC_CKE5_GALS 3 +#define CLK_VENC_NR_CLK 4 + +/* CAMSYS */ + +#define CLK_CAM_LARB13 0 +#define CLK_CAM_DFP_VAD 1 +#define CLK_CAM_LARB14 2 +#define CLK_CAM 3 +#define CLK_CAMTG 4 +#define CLK_CAM_SENINF 5 +#define CLK_CAMSV1 6 +#define CLK_CAMSV2 7 +#define CLK_CAMSV3 8 +#define CLK_CAM_CCU0 9 +#define CLK_CAM_CCU1 10 +#define CLK_CAM_MRAW0 11 +#define CLK_CAM_FAKE_ENG 12 +#define CLK_CAM_CCU_GALS 13 +#define CLK_CAM2MM_GALS 14 +#define CLK_CAM_NR_CLK 15 + +/* CAMSYS_RAWA */ + +#define CLK_CAM_RAWA_LARBX_RAWA 0 +#define CLK_CAM_RAWA 1 +#define CLK_CAM_RAWA_CAMTG_RAWA 2 +#define CLK_CAM_RAWA_NR_CLK 3 + +/* CAMSYS_RAWB */ + +#define CLK_CAM_RAWB_LARBX_RAWB 0 +#define CLK_CAM_RAWB 1 +#define CLK_CAM_RAWB_CAMTG_RAWB 2 +#define CLK_CAM_RAWB_NR_CLK 3 + +/* MDPSYS */ + +#define CLK_MDP_RDMA0 0 +#define CLK_MDP_TDSHP0 1 +#define CLK_MDP_IMG_DL_ASYNC0 2 +#define CLK_MDP_IMG_DL_ASYNC1 3 +#define CLK_MDP_DISP_RDMA 4 +#define CLK_MDP_HMS 5 +#define CLK_MDP_SMI0 6 +#define CLK_MDP_APB_BUS 7 +#define CLK_MDP_WROT0 8 +#define CLK_MDP_RSZ0 9 +#define CLK_MDP_HDR0 10 +#define CLK_MDP_MUTEX0 11 +#define CLK_MDP_WROT1 12 +#define CLK_MDP_RSZ1 13 +#define CLK_MDP_FAKE_ENG0 14 +#define CLK_MDP_AAL0 15 +#define CLK_MDP_DISP_WDMA 16 +#define CLK_MDP_COLOR 17 +#define CLK_MDP_IMG_DL_ASYNC2 18 +#define CLK_MDP_IMG_DL_RELAY0_ASYNC0 19 +#define CLK_MDP_IMG_DL_RELAY1_ASYNC1 20 +#define CLK_MDP_IMG_DL_RELAY2_ASYNC2 21 +#define CLK_MDP_NR_CLK 22 + +/* IPESYS */ + +#define CLK_IPE_LARB19 0 +#define CLK_IPE_LARB20 1 +#define CLK_IPE_SMI_SUBCOM 2 +#define CLK_IPE_FD 3 +#define CLK_IPE_FE 4 +#define CLK_IPE_RSC 5 +#define CLK_IPE_DPE 6 +#define CLK_IPE_GALS_IPE 7 +#define CLK_IPE_NR_CLK 8 + +#endif /* _DT_BINDINGS_CLK_MT8186_H */ -- cgit v1.2.3 From d9d31cf88702ae071bec033e5c8714048aa71285 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 25 Apr 2022 15:04:48 -0700 Subject: bpf: Use bpf_prog_run_array_cg_flags everywhere Rename bpf_prog_run_array_cg_flags to bpf_prog_run_array_cg and use it everywhere. check_return_code already enforces sane return ranges for all cgroup types. (only egress and bind hooks have uncanonical return ranges, the rest is using [0, 1]) No functional changes. v2: - 'func_ret & 1' under explicit test (Andrii & Martin) Suggested-by: Alexei Starovoitov Signed-off-by: Stanislav Fomichev Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220425220448.3669032-1-sdf@google.com --- include/linux/bpf-cgroup.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 88a51b242adc..669d96d074ad 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -225,24 +225,20 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, #define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, atype) \ ({ \ - u32 __unused_flags; \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ - NULL, \ - &__unused_flags); \ + NULL, NULL); \ __ret; \ }) #define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx) \ ({ \ - u32 __unused_flags; \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) { \ lock_sock(sk); \ __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ - t_ctx, \ - &__unused_flags); \ + t_ctx, NULL); \ release_sock(sk); \ } \ __ret; \ -- cgit v1.2.3 From 61df10c7799e27807ad5e459eec9d77cddf8bf45 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 25 Apr 2022 03:18:49 +0530 Subject: bpf: Allow storing unreferenced kptr in map This commit introduces a new pointer type 'kptr' which can be embedded in a map value to hold a PTR_TO_BTF_ID stored by a BPF program during its invocation. When storing such a kptr, BPF program's PTR_TO_BTF_ID register must have the same type as in the map value's BTF, and loading a kptr marks the destination register as PTR_TO_BTF_ID with the correct kernel BTF and BTF ID. Such kptr are unreferenced, i.e. by the time another invocation of the BPF program loads this pointer, the object which the pointer points to may not longer exist. Since PTR_TO_BTF_ID loads (using BPF_LDX) are patched to PROBE_MEM loads by the verifier, it would safe to allow user to still access such invalid pointer, but passing such pointers into BPF helpers and kfuncs should not be permitted. A future patch in this series will close this gap. The flexibility offered by allowing programs to dereference such invalid pointers while being safe at runtime frees the verifier from doing complex lifetime tracking. As long as the user may ensure that the object remains valid, it can ensure data read by it from the kernel object is valid. The user indicates that a certain pointer must be treated as kptr capable of accepting stores of PTR_TO_BTF_ID of a certain type, by using a BTF type tag 'kptr' on the pointed to type of the pointer. Then, this information is recorded in the object BTF which will be passed into the kernel by way of map's BTF information. The name and kind from the map value BTF is used to look up the in-kernel type, and the actual BTF and BTF ID is recorded in the map struct in a new kptr_off_tab member. For now, only storing pointers to structs is permitted. An example of this specification is shown below: #define __kptr __attribute__((btf_type_tag("kptr"))) struct map_value { ... struct task_struct __kptr *task; ... }; Then, in a BPF program, user may store PTR_TO_BTF_ID with the type task_struct into the map, and then load it later. Note that the destination register is marked PTR_TO_BTF_ID_OR_NULL, as the verifier cannot know whether the value is NULL or not statically, it must treat all potential loads at that map value offset as loading a possibly NULL pointer. Only BPF_LDX, BPF_STX, and BPF_ST (with insn->imm = 0 to denote NULL) are allowed instructions that can access such a pointer. On BPF_LDX, the destination register is updated to be a PTR_TO_BTF_ID, and on BPF_STX, it is checked whether the source register type is a PTR_TO_BTF_ID with same BTF type as specified in the map BTF. The access size must always be BPF_DW. For the map in map support, the kptr_off_tab for outer map is copied from the inner map's kptr_off_tab. It was chosen to do a deep copy instead of introducing a refcount to kptr_off_tab, because the copy only needs to be done when paramterizing using inner_map_fd in the map in map case, hence would be unnecessary for all other users. It is not permitted to use MAP_FREEZE command and mmap for BPF map having kptrs, similar to the bpf_timer case. A kptr also requires that BPF program has both read and write access to the map (hence both BPF_F_RDONLY_PROG and BPF_F_WRONLY_PROG are disallowed). Note that check_map_access must be called from both check_helper_mem_access and for the BPF instructions, hence the kptr check must distinguish between ACCESS_DIRECT and ACCESS_HELPER, and reject ACCESS_HELPER cases. We rename stack_access_src to bpf_access_src and reuse it for this purpose. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220424214901.2743946-2-memxor@gmail.com --- include/linux/bpf.h | 31 ++++++++++++++++++++++++++++++- include/linux/btf.h | 2 ++ 2 files changed, 32 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7bf441563ffc..ce12124048c0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -155,6 +155,24 @@ struct bpf_map_ops { const struct bpf_iter_seq_info *iter_seq_info; }; +enum { + /* Support at most 8 pointers in a BPF map value */ + BPF_MAP_VALUE_OFF_MAX = 8, +}; + +struct bpf_map_value_off_desc { + u32 offset; + struct { + struct btf *btf; + u32 btf_id; + } kptr; +}; + +struct bpf_map_value_off { + u32 nr_off; + struct bpf_map_value_off_desc off[]; +}; + struct bpf_map { /* The first two cachelines with read-mostly members of which some * are also accessed in fast-path (e.g. ops, max_entries). @@ -171,6 +189,7 @@ struct bpf_map { u64 map_extra; /* any per-map-type extra fields */ u32 map_flags; int spin_lock_off; /* >=0 valid offset, <0 error */ + struct bpf_map_value_off *kptr_off_tab; int timer_off; /* >=0 valid offset, <0 error */ u32 id; int numa_node; @@ -184,7 +203,7 @@ struct bpf_map { char name[BPF_OBJ_NAME_LEN]; bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ - /* 14 bytes hole */ + /* 6 bytes hole */ /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. @@ -217,6 +236,11 @@ static inline bool map_value_has_timer(const struct bpf_map *map) return map->timer_off >= 0; } +static inline bool map_value_has_kptrs(const struct bpf_map *map) +{ + return !IS_ERR_OR_NULL(map->kptr_off_tab); +} + static inline void check_and_init_map_value(struct bpf_map *map, void *dst) { if (unlikely(map_value_has_spin_lock(map))) @@ -1396,6 +1420,11 @@ void bpf_prog_put(struct bpf_prog *prog); void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock); void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); +struct bpf_map_value_off_desc *bpf_map_kptr_off_contains(struct bpf_map *map, u32 offset); +void bpf_map_free_kptr_off_tab(struct bpf_map *map); +struct bpf_map_value_off *bpf_map_copy_kptr_off_tab(const struct bpf_map *map); +bool bpf_map_equal_kptr_off_tab(const struct bpf_map *map_a, const struct bpf_map *map_b); + struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); diff --git a/include/linux/btf.h b/include/linux/btf.h index 36bc09b8e890..19c297f9a52f 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -123,6 +123,8 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, u32 expected_offset, u32 expected_size); int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); int btf_find_timer(const struct btf *btf, const struct btf_type *t); +struct bpf_map_value_off *btf_parse_kptrs(const struct btf *btf, + const struct btf_type *t); bool btf_type_is_void(const struct btf_type *t); s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind); const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, -- cgit v1.2.3 From 8f14852e89113d738c99c375b4c8b8b7e1073df1 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 25 Apr 2022 03:18:50 +0530 Subject: bpf: Tag argument to be released in bpf_func_proto Add a new type flag for bpf_arg_type that when set tells verifier that for a release function, that argument's register will be the one for which meta.ref_obj_id will be set, and which will then be released using release_reference. To capture the regno, introduce a new field release_regno in bpf_call_arg_meta. This would be required in the next patch, where we may either pass NULL or a refcounted pointer as an argument to the release function bpf_kptr_xchg. Just releasing only when meta.ref_obj_id is set is not enough, as there is a case where the type of argument needed matches, but the ref_obj_id is set to 0. Hence, we must enforce that whenever meta.ref_obj_id is zero, the register that is to be released can only be NULL for a release function. Since we now indicate whether an argument is to be released in bpf_func_proto itself, is_release_function helper has lost its utitlity, hence refactor code to work without it, and just rely on meta.release_regno to know when to release state for a ref_obj_id. Still, the restriction of one release argument and only one ref_obj_id passed to BPF helper or kfunc remains. This may be lifted in the future. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220424214901.2743946-3-memxor@gmail.com --- include/linux/bpf.h | 5 ++++- include/linux/bpf_verifier.h | 3 +-- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ce12124048c0..492edd2c5713 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -366,7 +366,10 @@ enum bpf_type_flag { */ MEM_PERCPU = BIT(4 + BPF_BASE_TYPE_BITS), - __BPF_TYPE_LAST_FLAG = MEM_PERCPU, + /* Indicates that the argument will be released. */ + OBJ_RELEASE = BIT(5 + BPF_BASE_TYPE_BITS), + + __BPF_TYPE_LAST_FLAG = OBJ_RELEASE, }; /* Max number of base types. */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 3a9d2d7cc6b7..1f1e7f2ea967 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -523,8 +523,7 @@ int check_ptr_off_reg(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno); int check_func_arg_reg_off(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, - enum bpf_arg_type arg_type, - bool is_release_func); + enum bpf_arg_type arg_type); int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno); int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, -- cgit v1.2.3 From 565138ac5f8a5330669a20e5f94759764e9165ec Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 21 Apr 2022 18:03:52 +0300 Subject: scsi: iscsi: Fix harmless double shift bug These flags are supposed to be bit numbers. Right now they cause a double shift bug where we use BIT(BIT(2)) instead of BIT(2). Fortunately, the bit numbers are small and it's done consistently so it does not cause an issue at run time. Link: https://lore.kernel.org/r/YmFyWHf8nrrx+SHa@kili Fixes: 5bd856256f8c ("scsi: iscsi: Merge suspend fields") Reviewed-by: Mike Christie Reviewed-by: Lee Duncan Signed-off-by: Dan Carpenter Signed-off-by: Martin K. Petersen --- include/scsi/libiscsi.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index d0a24779c52d..c0703cd20a99 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -54,9 +54,9 @@ enum { #define ISID_SIZE 6 /* Connection flags */ -#define ISCSI_CONN_FLAG_SUSPEND_TX BIT(0) -#define ISCSI_CONN_FLAG_SUSPEND_RX BIT(1) -#define ISCSI_CONN_FLAG_BOUND BIT(2) +#define ISCSI_CONN_FLAG_SUSPEND_TX 0 +#define ISCSI_CONN_FLAG_SUSPEND_RX 1 +#define ISCSI_CONN_FLAG_BOUND 2 #define ISCSI_ITT_MASK 0x1fff #define ISCSI_TOTAL_CMDS_MAX 4096 -- cgit v1.2.3 From c976e588b34e4ff2fdd2922edab4b983244a17e6 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 21 Apr 2022 11:30:20 -0700 Subject: scsi: sd: sd_zbc: Hide gap zones ZBC-2 allows host-managed disks to report gap zones. This allow zoned disks to report an offset between data zone starts that is a power of two even if the number of logical blocks with data per zone is not a power of two. Another new feature in ZBC-2 is support for constant zone starting LBA offsets. For zoned disks that report a constant zone starting LBA offset, hide the gap zones from the block layer. Report the offset between data zone starts as zone size and report the number of logical blocks with data per zone as the zone capacity. Link: https://lore.kernel.org/r/20220421183023.3462291-7-bvanassche@acm.org Acked-by: Douglas Gilbert Signed-off-by: Damien Le Moal [ bvanassche: Reworked this patch ] Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- include/scsi/scsi_proto.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/scsi/scsi_proto.h b/include/scsi/scsi_proto.h index f017843a8124..c03e35fc382c 100644 --- a/include/scsi/scsi_proto.h +++ b/include/scsi/scsi_proto.h @@ -307,7 +307,9 @@ enum zbc_zone_type { ZBC_ZONE_TYPE_CONV = 0x1, ZBC_ZONE_TYPE_SEQWRITE_REQ = 0x2, ZBC_ZONE_TYPE_SEQWRITE_PREF = 0x3, - /* 0x4 to 0xf are reserved */ + ZBC_ZONE_TYPE_SEQ_OR_BEFORE_REQ = 0x4, + ZBC_ZONE_TYPE_GAP = 0x5, + /* 0x6 to 0xf are reserved */ }; /* Zone conditions of REPORT ZONES zone descriptors */ @@ -323,6 +325,11 @@ enum zbc_zone_cond { ZBC_ZONE_COND_OFFLINE = 0xf, }; +enum zbc_zone_alignment_method { + ZBC_CONSTANT_ZONE_LENGTH = 0x1, + ZBC_CONSTANT_ZONE_START_OFFSET = 0x8, +}; + /* Version descriptor values for INQUIRY */ enum scsi_version_descriptor { SCSI_VERSION_DESCRIPTOR_FCP4 = 0x0a40, -- cgit v1.2.3 From c0a5a21c25f37c9fd7b36072f9968cdff1e4aa13 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 25 Apr 2022 03:18:51 +0530 Subject: bpf: Allow storing referenced kptr in map Extending the code in previous commits, introduce referenced kptr support, which needs to be tagged using 'kptr_ref' tag instead. Unlike unreferenced kptr, referenced kptr have a lot more restrictions. In addition to the type matching, only a newly introduced bpf_kptr_xchg helper is allowed to modify the map value at that offset. This transfers the referenced pointer being stored into the map, releasing the references state for the program, and returning the old value and creating new reference state for the returned pointer. Similar to unreferenced pointer case, return value for this case will also be PTR_TO_BTF_ID_OR_NULL. The reference for the returned pointer must either be eventually released by calling the corresponding release function, otherwise it must be transferred into another map. It is also allowed to call bpf_kptr_xchg with a NULL pointer, to clear the value, and obtain the old value if any. BPF_LDX, BPF_STX, and BPF_ST cannot access referenced kptr. A future commit will permit using BPF_LDX for such pointers, but attempt at making it safe, since the lifetime of object won't be guaranteed. There are valid reasons to enforce the restriction of permitting only bpf_kptr_xchg to operate on referenced kptr. The pointer value must be consistent in face of concurrent modification, and any prior values contained in the map must also be released before a new one is moved into the map. To ensure proper transfer of this ownership, bpf_kptr_xchg returns the old value, which the verifier would require the user to either free or move into another map, and releases the reference held for the pointer being moved in. In the future, direct BPF_XCHG instruction may also be permitted to work like bpf_kptr_xchg helper. Note that process_kptr_func doesn't have to call check_helper_mem_access, since we already disallow rdonly/wronly flags for map, which is what check_map_access_type checks, and we already ensure the PTR_TO_MAP_VALUE refers to kptr by obtaining its off_desc, so check_map_access is also not required. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220424214901.2743946-4-memxor@gmail.com --- include/linux/bpf.h | 8 ++++++++ include/uapi/linux/bpf.h | 12 ++++++++++++ 2 files changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 492edd2c5713..24310837bafc 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -160,8 +160,14 @@ enum { BPF_MAP_VALUE_OFF_MAX = 8, }; +enum bpf_kptr_type { + BPF_KPTR_UNREF, + BPF_KPTR_REF, +}; + struct bpf_map_value_off_desc { u32 offset; + enum bpf_kptr_type type; struct { struct btf *btf; u32 btf_id; @@ -418,6 +424,7 @@ enum bpf_arg_type { ARG_PTR_TO_STACK, /* pointer to stack */ ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */ ARG_PTR_TO_TIMER, /* pointer to bpf_timer */ + ARG_PTR_TO_KPTR, /* pointer to referenced kptr */ __BPF_ARG_TYPE_MAX, /* Extended arg_types. */ @@ -427,6 +434,7 @@ enum bpf_arg_type { ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET, ARG_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_ALLOC_MEM, ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK, + ARG_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d14b10b85e51..444fe6f1cf35 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5143,6 +5143,17 @@ union bpf_attr { * The **hash_algo** is returned on success, * **-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if * invalid arguments are passed. + * + * void *bpf_kptr_xchg(void *map_value, void *ptr) + * Description + * Exchange kptr at pointer *map_value* with *ptr*, and return the + * old value. *ptr* can be NULL, otherwise it must be a referenced + * pointer which will be released when this helper is called. + * Return + * The old value of kptr (which can be NULL). The returned pointer + * if not NULL, is a reference which must be released using its + * corresponding release function, or moved into a BPF map before + * program exit. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5339,6 +5350,7 @@ union bpf_attr { FN(copy_from_user_task), \ FN(skb_set_tstamp), \ FN(ima_file_hash), \ + FN(kptr_xchg), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 6efe152d4061a83a2c5db6a0e5b58f9345c9742f Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 25 Apr 2022 03:18:52 +0530 Subject: bpf: Prevent escaping of kptr loaded from maps While we can guarantee that even for unreferenced kptr, the object pointer points to being freed etc. can be handled by the verifier's exception handling (normal load patching to PROBE_MEM loads), we still cannot allow the user to pass these pointers to BPF helpers and kfunc, because the same exception handling won't be done for accesses inside the kernel. The same is true if a referenced pointer is loaded using normal load instruction. Since the reference is not guaranteed to be held while the pointer is used, it must be marked as untrusted. Hence introduce a new type flag, PTR_UNTRUSTED, which is used to mark all registers loading unreferenced and referenced kptr from BPF maps, and ensure they can never escape the BPF program and into the kernel by way of calling stable/unstable helpers. In check_ptr_to_btf_access, the !type_may_be_null check to reject type flags is still correct, as apart from PTR_MAYBE_NULL, only MEM_USER, MEM_PERCPU, and PTR_UNTRUSTED may be set for PTR_TO_BTF_ID. The first two are checked inside the function and rejected using a proper error message, but we still want to allow dereference of untrusted case. Also, we make sure to inherit PTR_UNTRUSTED when chain of pointers are walked, so that this flag is never dropped once it has been set on a PTR_TO_BTF_ID (i.e. trusted to untrusted transition can only be in one direction). In convert_ctx_accesses, extend the switch case to consider untrusted PTR_TO_BTF_ID in addition to normal PTR_TO_BTF_ID for PROBE_MEM conversion for BPF_LDX. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220424214901.2743946-5-memxor@gmail.com --- include/linux/bpf.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 24310837bafc..e13a5cbd4ebb 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -375,7 +375,15 @@ enum bpf_type_flag { /* Indicates that the argument will be released. */ OBJ_RELEASE = BIT(5 + BPF_BASE_TYPE_BITS), - __BPF_TYPE_LAST_FLAG = OBJ_RELEASE, + /* PTR is not trusted. This is only used with PTR_TO_BTF_ID, to mark + * unreferenced and referenced kptr loaded from map value using a load + * instruction, so that they can only be dereferenced but not escape the + * BPF program into the kernel (i.e. cannot be passed as arguments to + * kfunc or bpf helpers). + */ + PTR_UNTRUSTED = BIT(6 + BPF_BASE_TYPE_BITS), + + __BPF_TYPE_LAST_FLAG = PTR_UNTRUSTED, }; /* Max number of base types. */ -- cgit v1.2.3 From 4d7d7f69f4b104b2ddeec6a1e7fcfd2d044ed8c4 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 25 Apr 2022 03:18:53 +0530 Subject: bpf: Adapt copy_map_value for multiple offset case Since now there might be at most 10 offsets that need handling in copy_map_value, the manual shuffling and special case is no longer going to work. Hence, let's generalise the copy_map_value function by using a sorted array of offsets to skip regions that must be avoided while copying into and out of a map value. When the map is created, we populate the offset array in struct map, Then, copy_map_value uses this sorted offset array is used to memcpy while skipping timer, spin lock, and kptr. The array is allocated as in most cases none of these special fields would be present in map value, hence we can save on space for the common case by not embedding the entire object inside bpf_map struct. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220424214901.2743946-6-memxor@gmail.com --- include/linux/bpf.h | 56 ++++++++++++++++++++++++++++------------------------- 1 file changed, 30 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e13a5cbd4ebb..4e12b27a5de6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -158,6 +158,9 @@ struct bpf_map_ops { enum { /* Support at most 8 pointers in a BPF map value */ BPF_MAP_VALUE_OFF_MAX = 8, + BPF_MAP_OFF_ARR_MAX = BPF_MAP_VALUE_OFF_MAX + + 1 + /* for bpf_spin_lock */ + 1, /* for bpf_timer */ }; enum bpf_kptr_type { @@ -179,6 +182,12 @@ struct bpf_map_value_off { struct bpf_map_value_off_desc off[]; }; +struct bpf_map_off_arr { + u32 cnt; + u32 field_off[BPF_MAP_OFF_ARR_MAX]; + u8 field_sz[BPF_MAP_OFF_ARR_MAX]; +}; + struct bpf_map { /* The first two cachelines with read-mostly members of which some * are also accessed in fast-path (e.g. ops, max_entries). @@ -207,10 +216,7 @@ struct bpf_map { struct mem_cgroup *memcg; #endif char name[BPF_OBJ_NAME_LEN]; - bool bypass_spec_v1; - bool frozen; /* write-once; write-protected by freeze_mutex */ - /* 6 bytes hole */ - + struct bpf_map_off_arr *off_arr; /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. */ @@ -230,6 +236,8 @@ struct bpf_map { bool jited; bool xdp_has_frags; } owner; + bool bypass_spec_v1; + bool frozen; /* write-once; write-protected by freeze_mutex */ }; static inline bool map_value_has_spin_lock(const struct bpf_map *map) @@ -253,37 +261,33 @@ static inline void check_and_init_map_value(struct bpf_map *map, void *dst) memset(dst + map->spin_lock_off, 0, sizeof(struct bpf_spin_lock)); if (unlikely(map_value_has_timer(map))) memset(dst + map->timer_off, 0, sizeof(struct bpf_timer)); + if (unlikely(map_value_has_kptrs(map))) { + struct bpf_map_value_off *tab = map->kptr_off_tab; + int i; + + for (i = 0; i < tab->nr_off; i++) + *(u64 *)(dst + tab->off[i].offset) = 0; + } } /* copy everything but bpf_spin_lock and bpf_timer. There could be one of each. */ static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) { - u32 s_off = 0, s_sz = 0, t_off = 0, t_sz = 0; + u32 curr_off = 0; + int i; - if (unlikely(map_value_has_spin_lock(map))) { - s_off = map->spin_lock_off; - s_sz = sizeof(struct bpf_spin_lock); - } - if (unlikely(map_value_has_timer(map))) { - t_off = map->timer_off; - t_sz = sizeof(struct bpf_timer); + if (likely(!map->off_arr)) { + memcpy(dst, src, map->value_size); + return; } - if (unlikely(s_sz || t_sz)) { - if (s_off < t_off || !s_sz) { - swap(s_off, t_off); - swap(s_sz, t_sz); - } - memcpy(dst, src, t_off); - memcpy(dst + t_off + t_sz, - src + t_off + t_sz, - s_off - t_off - t_sz); - memcpy(dst + s_off + s_sz, - src + s_off + s_sz, - map->value_size - s_off - s_sz); - } else { - memcpy(dst, src, map->value_size); + for (i = 0; i < map->off_arr->cnt; i++) { + u32 next_off = map->off_arr->field_off[i]; + + memcpy(dst + curr_off, src + curr_off, next_off - curr_off); + curr_off += map->off_arr->field_sz[i]; } + memcpy(dst + curr_off, src + curr_off, map->value_size - curr_off); } void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); -- cgit v1.2.3 From 5ce937d613a423ca3102f53d9f3daf4210c1b6e2 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 25 Apr 2022 03:18:54 +0530 Subject: bpf: Populate pairs of btf_id and destructor kfunc in btf To support storing referenced PTR_TO_BTF_ID in maps, we require associating a specific BTF ID with a 'destructor' kfunc. This is because we need to release a live referenced pointer at a certain offset in map value from the map destruction path, otherwise we end up leaking resources. Hence, introduce support for passing an array of btf_id, kfunc_btf_id pairs that denote a BTF ID and its associated release function. Then, add an accessor 'btf_find_dtor_kfunc' which can be used to look up the destructor kfunc of a certain BTF ID. If found, we can use it to free the object from the map free path. The registration of these pairs also serve as a whitelist of structures which are allowed as referenced PTR_TO_BTF_ID in a BPF map, because without finding the destructor kfunc, we will bail and return an error. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220424214901.2743946-7-memxor@gmail.com --- include/linux/btf.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/linux/btf.h b/include/linux/btf.h index 19c297f9a52f..fea424681d66 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -40,6 +40,11 @@ struct btf_kfunc_id_set { }; }; +struct btf_id_dtor_kfunc { + u32 btf_id; + u32 kfunc_btf_id; +}; + extern const struct file_operations btf_fops; void btf_get(struct btf *btf); @@ -346,6 +351,9 @@ bool btf_kfunc_id_set_contains(const struct btf *btf, enum btf_kfunc_type type, u32 kfunc_btf_id); int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, const struct btf_kfunc_id_set *s); +s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id); +int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt, + struct module *owner); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) @@ -369,6 +377,15 @@ static inline int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, { return 0; } +static inline s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id) +{ + return -ENOENT; +} +static inline int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, + u32 add_cnt, struct module *owner) +{ + return 0; +} #endif #endif -- cgit v1.2.3 From 14a324f6a67ef6a53e04362a70160a47eb8afffa Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 25 Apr 2022 03:18:55 +0530 Subject: bpf: Wire up freeing of referenced kptr A destructor kfunc can be defined as void func(type *), where type may be void or any other pointer type as per convenience. In this patch, we ensure that the type is sane and capture the function pointer into off_desc of ptr_off_tab for the specific pointer offset, with the invariant that the dtor pointer is always set when 'kptr_ref' tag is applied to the pointer's pointee type, which is indicated by the flag BPF_MAP_VALUE_OFF_F_REF. Note that only BTF IDs whose destructor kfunc is registered, thus become the allowed BTF IDs for embedding as referenced kptr. Hence it serves the purpose of finding dtor kfunc BTF ID, as well acting as a check against the whitelist of allowed BTF IDs for this purpose. Finally, wire up the actual freeing of the referenced pointer if any at all available offsets, so that no references are leaked after the BPF map goes away and the BPF program previously moved the ownership a referenced pointer into it. The behavior is similar to BPF timers, where bpf_map_{update,delete}_elem will free any existing referenced kptr. The same case is with LRU map's bpf_lru_push_free/htab_lru_push_free functions, which are extended to reset unreferenced and free referenced kptr. Note that unlike BPF timers, kptr is not reset or freed when map uref drops to zero. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220424214901.2743946-8-memxor@gmail.com --- include/linux/bpf.h | 4 ++++ include/linux/btf.h | 2 ++ 2 files changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4e12b27a5de6..6141564c76c8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -23,6 +23,7 @@ #include #include #include +#include struct bpf_verifier_env; struct bpf_verifier_log; @@ -173,6 +174,8 @@ struct bpf_map_value_off_desc { enum bpf_kptr_type type; struct { struct btf *btf; + struct module *module; + btf_dtor_kfunc_t dtor; u32 btf_id; } kptr; }; @@ -1447,6 +1450,7 @@ struct bpf_map_value_off_desc *bpf_map_kptr_off_contains(struct bpf_map *map, u3 void bpf_map_free_kptr_off_tab(struct bpf_map *map); struct bpf_map_value_off *bpf_map_copy_kptr_off_tab(const struct bpf_map *map); bool bpf_map_equal_kptr_off_tab(const struct bpf_map *map_a, const struct bpf_map *map_b); +void bpf_map_free_kptrs(struct bpf_map *map, void *map_value); struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *bpf_map_get_with_uref(u32 ufd); diff --git a/include/linux/btf.h b/include/linux/btf.h index fea424681d66..f70625dd5bb4 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -45,6 +45,8 @@ struct btf_id_dtor_kfunc { u32 kfunc_btf_id; }; +typedef void (*btf_dtor_kfunc_t)(void *); + extern const struct file_operations btf_fops; void btf_get(struct btf *btf); -- cgit v1.2.3 From a1ef195996526da45bbc9710849254023df75aea Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 25 Apr 2022 03:18:56 +0530 Subject: bpf: Teach verifier about kptr_get kfunc helpers We introduce a new style of kfunc helpers, namely *_kptr_get, where they take pointer to the map value which points to a referenced kernel pointer contained in the map. Since this is referenced, only bpf_kptr_xchg from BPF side and xchg from kernel side is allowed to change the current value, and each pointer that resides in that location would be referenced, and RCU protected (this must be kept in mind while adding kernel types embeddable as reference kptr in BPF maps). This means that if do the load of the pointer value in an RCU read section, and find a live pointer, then as long as we hold RCU read lock, it won't be freed by a parallel xchg + release operation. This allows us to implement a safe refcount increment scheme. Hence, enforce that first argument of all such kfunc is a proper PTR_TO_MAP_VALUE pointing at the right offset to referenced pointer. For the rest of the arguments, they are subjected to typical kfunc argument checks, hence allowing some flexibility in passing more intent into how the reference should be taken. For instance, in case of struct nf_conn, it is not freed until RCU grace period ends, but can still be reused for another tuple once refcount has dropped to zero. Hence, a bpf_ct_kptr_get helper not only needs to call refcount_inc_not_zero, but also do a tuple match after incrementing the reference, and when it fails to match it, put the reference again and return NULL. This can be implemented easily if we allow passing additional parameters to the bpf_ct_kptr_get kfunc, like a struct bpf_sock_tuple * and a tuple__sz pair. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220424214901.2743946-9-memxor@gmail.com --- include/linux/btf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/btf.h b/include/linux/btf.h index f70625dd5bb4..2611cea2c2b6 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -17,6 +17,7 @@ enum btf_kfunc_type { BTF_KFUNC_TYPE_ACQUIRE, BTF_KFUNC_TYPE_RELEASE, BTF_KFUNC_TYPE_RET_NULL, + BTF_KFUNC_TYPE_KPTR_ACQUIRE, BTF_KFUNC_TYPE_MAX, }; @@ -35,6 +36,7 @@ struct btf_kfunc_id_set { struct btf_id_set *acquire_set; struct btf_id_set *release_set; struct btf_id_set *ret_null_set; + struct btf_id_set *kptr_acquire_set; }; struct btf_id_set *sets[BTF_KFUNC_TYPE_MAX]; }; -- cgit v1.2.3 From 2ab3b3808eb17f729edfd69e061667ca0a427195 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 25 Apr 2022 03:18:57 +0530 Subject: bpf: Make BTF type match stricter for release arguments The current of behavior of btf_struct_ids_match for release arguments is that when type match fails, it retries with first member type again (recursively). Since the offset is already 0, this is akin to just casting the pointer in normal C, since if type matches it was just embedded inside parent sturct as an object. However, we want to reject cases for release function type matching, be it kfunc or BPF helpers. An example is the following: struct foo { struct bar b; }; struct foo *v = acq_foo(); rel_bar(&v->b); // btf_struct_ids_match fails btf_types_are_same, then // retries with first member type and succeeds, while // it should fail. Hence, don't walk the struct and only rely on btf_types_are_same for strict mode. All users of strict mode must be dealing with zero offset anyway, since otherwise they would want the struct to be walked. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220424214901.2743946-10-memxor@gmail.com --- include/linux/bpf.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6141564c76c8..0af5793ba417 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1748,7 +1748,8 @@ int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf, u32 *next_btf_id, enum bpf_type_flag *flag); bool btf_struct_ids_match(struct bpf_verifier_log *log, const struct btf *btf, u32 id, int off, - const struct btf *need_btf, u32 need_type_id); + const struct btf *need_btf, u32 need_type_id, + bool strict); int btf_distill_func_proto(struct bpf_verifier_log *log, struct btf *btf, -- cgit v1.2.3 From 66eb6df79aefd6b3f7d2e749da7104e90cedc0ff Mon Sep 17 00:00:00 2001 From: Andrew Davis Date: Mon, 25 Apr 2022 09:16:16 -0500 Subject: tee: remove tee_shm_va2pa() and tee_shm_pa2va() We should not need to index into SHMs based on absolute VA/PA. These functions are not used and this kind of usage should not be encouraged anyway. Remove these functions. Signed-off-by: Andrew Davis Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'include') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 911cad324acc..17eb1c5205d3 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -298,24 +298,6 @@ void tee_shm_free(struct tee_shm *shm); */ void tee_shm_put(struct tee_shm *shm); -/** - * tee_shm_va2pa() - Get physical address of a virtual address - * @shm: Shared memory handle - * @va: Virtual address to tranlsate - * @pa: Returned physical address - * @returns 0 on success and < 0 on failure - */ -int tee_shm_va2pa(struct tee_shm *shm, void *va, phys_addr_t *pa); - -/** - * tee_shm_pa2va() - Get virtual address of a physical address - * @shm: Shared memory handle - * @pa: Physical address to tranlsate - * @va: Returned virtual address - * @returns 0 on success and < 0 on failure - */ -int tee_shm_pa2va(struct tee_shm *shm, phys_addr_t pa, void **va); - /** * tee_shm_get_va() - Get virtual address of a shared memory plus an offset * @shm: Shared memory handle -- cgit v1.2.3 From d8fc1c7c4c9b705ce5f5bba772ad66a0137c685d Mon Sep 17 00:00:00 2001 From: Andrew Davis Date: Mon, 25 Apr 2022 09:16:17 -0500 Subject: tee: remove flags TEE_IOCTL_SHM_MAPPED and TEE_IOCTL_SHM_DMA_BUF These look to be leftover from an early edition of this driver. Userspace does not need this information. Checking all users of this that I have access to I have verified no one is using them. They leak internal use flags out to userspace. Even more they are not correct anymore after a45ea4efa358. Lets drop these flags before someone does try to use them for something and they become ABI. Signed-off-by: Andrew Davis Acked-by: Sumit Garg Signed-off-by: Jens Wiklander --- include/uapi/linux/tee.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/tee.h b/include/uapi/linux/tee.h index 25a6c534beb1..23e57164693c 100644 --- a/include/uapi/linux/tee.h +++ b/include/uapi/linux/tee.h @@ -42,10 +42,6 @@ #define TEE_IOC_MAGIC 0xa4 #define TEE_IOC_BASE 0 -/* Flags relating to shared memory */ -#define TEE_IOCTL_SHM_MAPPED 0x1 /* memory mapped in normal world */ -#define TEE_IOCTL_SHM_DMA_BUF 0x2 /* dma-buf handle on shared memory */ - #define TEE_MAX_ARG_SIZE 1024 #define TEE_GEN_CAP_GP (1 << 0)/* GlobalPlatform compliant TEE */ -- cgit v1.2.3 From 1fa568e26f001e951b634d62ef3accdc80a87c7b Mon Sep 17 00:00:00 2001 From: Shida Zhang Date: Tue, 26 Apr 2022 11:20:07 +0800 Subject: bug: Have __warn() prototype defined unconditionally MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The __warn() prototype is declared in CONFIG_BUG scope but the function definition in panic.c is unconditional. The IBT enablement started using it unconditionally but a CONFIG_X86_KERNEL_IBT=y, CONFIG_BUG=n .config will trigger a arch/x86/kernel/traps.c: In function ‘__exc_control_protection’: arch/x86/kernel/traps.c:249:17: error: implicit declaration of function \ ‘__warn’; did you mean ‘pr_warn’? [-Werror=implicit-function-declaration] Pull up the declarations so that they're unconditionally visible too. [ bp: Rewrite commit message. ] Fixes: 991625f3dd2c ("x86/ibt: Add IBT feature, MSR and #CP handling") Suggested-by: Peter Zijlstra (Intel) Signed-off-by: Shida Zhang Signed-off-by: Borislav Petkov Link: https://lore.kernel.org/r/20220426032007.510245-1-starzhangzsd@gmail.com --- include/asm-generic/bug.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index edb0e2a602a8..ba1f860af38b 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -21,6 +21,12 @@ #include #include +struct warn_args; +struct pt_regs; + +void __warn(const char *file, int line, void *caller, unsigned taint, + struct pt_regs *regs, struct warn_args *args); + #ifdef CONFIG_BUG #ifdef CONFIG_GENERIC_BUG @@ -110,11 +116,6 @@ extern __printf(1, 2) void __warn_printk(const char *fmt, ...); #endif /* used internally by panic.c */ -struct warn_args; -struct pt_regs; - -void __warn(const char *file, int line, void *caller, unsigned taint, - struct pt_regs *regs, struct warn_args *args); #ifndef WARN_ON #define WARN_ON(condition) ({ \ -- cgit v1.2.3 From 97730bbb242cde22b7140acd202ffd88823886c9 Mon Sep 17 00:00:00 2001 From: Russ Weight Date: Thu, 21 Apr 2022 14:22:00 -0700 Subject: firmware_loader: Add firmware-upload support Extend the firmware subsystem to support a persistent sysfs interface that userspace may use to initiate a firmware update. For example, FPGA based PCIe cards load firmware and FPGA images from local FLASH when the card boots. The images in FLASH may be updated with new images provided by the user at his/her convenience. A device driver may call firmware_upload_register() to expose persistent "loading" and "data" sysfs files. These files are used in the same way as the fallback sysfs "loading" and "data" files. When 0 is written to "loading" to complete the write of firmware data, the data is transferred to the lower-level driver using pre-registered call-back functions. The data transfer is done in the context of a kernel worker thread. Reviewed-by: Luis Chamberlain Reviewed-by: Tianfei zhang Tested-by: Matthew Gerlach Signed-off-by: Russ Weight Link: https://lore.kernel.org/r/20220421212204.36052-5-russell.h.weight@intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware.h | 82 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 82 insertions(+) (limited to 'include') diff --git a/include/linux/firmware.h b/include/linux/firmware.h index ec2ccfebef65..de7fea3bca51 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -17,6 +17,64 @@ struct firmware { void *priv; }; +/** + * enum fw_upload_err - firmware upload error codes + * @FW_UPLOAD_ERR_NONE: returned to indicate success + * @FW_UPLOAD_ERR_HW_ERROR: error signalled by hardware, see kernel log + * @FW_UPLOAD_ERR_TIMEOUT: SW timed out on handshake with HW/firmware + * @FW_UPLOAD_ERR_CANCELED: upload was cancelled by the user + * @FW_UPLOAD_ERR_BUSY: there is an upload operation already in progress + * @FW_UPLOAD_ERR_INVALID_SIZE: invalid firmware image size + * @FW_UPLOAD_ERR_RW_ERROR: read or write to HW failed, see kernel log + * @FW_UPLOAD_ERR_WEAROUT: FLASH device is approaching wear-out, wait & retry + * @FW_UPLOAD_ERR_MAX: Maximum error code marker + */ +enum fw_upload_err { + FW_UPLOAD_ERR_NONE, + FW_UPLOAD_ERR_HW_ERROR, + FW_UPLOAD_ERR_TIMEOUT, + FW_UPLOAD_ERR_CANCELED, + FW_UPLOAD_ERR_BUSY, + FW_UPLOAD_ERR_INVALID_SIZE, + FW_UPLOAD_ERR_RW_ERROR, + FW_UPLOAD_ERR_WEAROUT, + FW_UPLOAD_ERR_MAX +}; + +struct fw_upload { + void *dd_handle; /* reference to parent driver */ + void *priv; /* firmware loader private fields */ +}; + +/** + * struct fw_upload_ops - device specific operations to support firmware upload + * @prepare: Required: Prepare secure update + * @write: Required: The write() op receives the remaining + * size to be written and must return the actual + * size written or a negative error code. The write() + * op will be called repeatedly until all data is + * written. + * @poll_complete: Required: Check for the completion of the + * HW authentication/programming process. + * @cancel: Required: Request cancellation of update. This op + * is called from the context of a different kernel + * thread, so race conditions need to be considered. + * @cleanup: Optional: Complements the prepare() + * function and is called at the completion + * of the update, on success or failure, if the + * prepare function succeeded. + */ +struct fw_upload_ops { + enum fw_upload_err (*prepare)(struct fw_upload *fw_upload, + const u8 *data, u32 size); + enum fw_upload_err (*write)(struct fw_upload *fw_upload, + const u8 *data, u32 offset, + u32 size, u32 *written); + enum fw_upload_err (*poll_complete)(struct fw_upload *fw_upload); + void (*cancel)(struct fw_upload *fw_upload); + void (*cleanup)(struct fw_upload *fw_upload); +}; + struct module; struct device; @@ -112,6 +170,30 @@ static inline int request_partial_firmware_into_buf #endif +#ifdef CONFIG_FW_UPLOAD + +struct fw_upload * +firmware_upload_register(struct module *module, struct device *parent, + const char *name, const struct fw_upload_ops *ops, + void *dd_handle); +void firmware_upload_unregister(struct fw_upload *fw_upload); + +#else + +static inline struct fw_upload * +firmware_upload_register(struct module *module, struct device *parent, + const char *name, const struct fw_upload_ops *ops, + void *dd_handle) +{ + return ERR_PTR(-EINVAL); +} + +static inline void firmware_upload_unregister(struct fw_upload *fw_upload) +{ +} + +#endif + int firmware_request_cache(struct device *device, const char *name); #endif -- cgit v1.2.3 From d405ac52ab19301622bddabf4bf925d199937823 Mon Sep 17 00:00:00 2001 From: Rohit Agarwal Date: Wed, 13 Apr 2022 18:23:34 +0530 Subject: dt-bindings: interconnect: Add Qualcomm SDX65 DT bindings Add interconnect IDs for Qualcomm SDX65 platform. Signed-off-by: Rohit Agarwal Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/1649854415-11174-2-git-send-email-quic_rohiagar@quicinc.com Signed-off-by: Georgi Djakov --- include/dt-bindings/interconnect/qcom,sdx65.h | 67 +++++++++++++++++++++++++++ 1 file changed, 67 insertions(+) create mode 100644 include/dt-bindings/interconnect/qcom,sdx65.h (limited to 'include') diff --git a/include/dt-bindings/interconnect/qcom,sdx65.h b/include/dt-bindings/interconnect/qcom,sdx65.h new file mode 100644 index 000000000000..b25288aa7d74 --- /dev/null +++ b/include/dt-bindings/interconnect/qcom,sdx65.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) */ +/* + * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#ifndef __DT_BINDINGS_INTERCONNECT_QCOM_SDX65_H +#define __DT_BINDINGS_INTERCONNECT_QCOM_SDX65_H + +#define MASTER_LLCC 0 +#define SLAVE_EBI1 1 + +#define MASTER_TCU_0 0 +#define MASTER_SNOC_GC_MEM_NOC 1 +#define MASTER_APPSS_PROC 2 +#define SLAVE_LLCC 3 +#define SLAVE_MEM_NOC_SNOC 4 +#define SLAVE_MEM_NOC_PCIE_SNOC 5 + +#define MASTER_AUDIO 0 +#define MASTER_BLSP_1 1 +#define MASTER_QDSS_BAM 2 +#define MASTER_QPIC 3 +#define MASTER_SNOC_CFG 4 +#define MASTER_SPMI_FETCHER 5 +#define MASTER_ANOC_SNOC 6 +#define MASTER_IPA 7 +#define MASTER_MEM_NOC_SNOC 8 +#define MASTER_MEM_NOC_PCIE_SNOC 9 +#define MASTER_CRYPTO 10 +#define MASTER_IPA_PCIE 11 +#define MASTER_PCIE_0 12 +#define MASTER_QDSS_ETR 13 +#define MASTER_SDCC_1 14 +#define MASTER_USB3 15 +#define SLAVE_AOSS 16 +#define SLAVE_APPSS 17 +#define SLAVE_AUDIO 18 +#define SLAVE_BLSP_1 19 +#define SLAVE_CLK_CTL 20 +#define SLAVE_CRYPTO_0_CFG 21 +#define SLAVE_CNOC_DDRSS 22 +#define SLAVE_ECC_CFG 23 +#define SLAVE_IMEM_CFG 24 +#define SLAVE_IPA_CFG 25 +#define SLAVE_CNOC_MSS 26 +#define SLAVE_PCIE_PARF 27 +#define SLAVE_PDM 28 +#define SLAVE_PRNG 29 +#define SLAVE_QDSS_CFG 30 +#define SLAVE_QPIC 31 +#define SLAVE_SDCC_1 32 +#define SLAVE_SNOC_CFG 33 +#define SLAVE_SPMI_FETCHER 34 +#define SLAVE_SPMI_VGI_COEX 35 +#define SLAVE_TCSR 36 +#define SLAVE_TLMM 37 +#define SLAVE_USB3 38 +#define SLAVE_USB3_PHY_CFG 39 +#define SLAVE_ANOC_SNOC 40 +#define SLAVE_SNOC_MEM_NOC_GC 41 +#define SLAVE_IMEM 42 +#define SLAVE_SERVICE_SNOC 43 +#define SLAVE_PCIE_0 44 +#define SLAVE_QDSS_STM 45 +#define SLAVE_TCU 46 + +#endif -- cgit v1.2.3 From d434743e5cac3558381b767f343eef5af246a4dc Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:37 +0530 Subject: bus: mhi: ep: Add support for registering MHI endpoint controllers This commit adds support for registering MHI endpoint controller drivers with the MHI endpoint stack. MHI endpoint controller drivers manage the interaction with the host machines (such as x86). They are also the MHI endpoint bus master in charge of managing the physical link between the host and endpoint device. Eventhough the MHI spec is bus agnostic, the current implementation is entirely based on PCIe bus. The endpoint controller driver encloses all information about the underlying physical bus like PCIe. The registration process involves parsing the channel configuration and allocating an MHI EP device. Channels used in the endpoint stack follows the perspective of the MHI host stack. i.e., UL - From host to endpoint DL - From endpoint to host Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-2-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 136 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 136 insertions(+) create mode 100644 include/linux/mhi_ep.h (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h new file mode 100644 index 000000000000..891b199a9703 --- /dev/null +++ b/include/linux/mhi_ep.h @@ -0,0 +1,136 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022, Linaro Ltd. + * + */ +#ifndef _MHI_EP_H_ +#define _MHI_EP_H_ + +#include +#include + +#define MHI_EP_DEFAULT_MTU 0x8000 + +/** + * struct mhi_ep_channel_config - Channel configuration structure for controller + * @name: The name of this channel + * @num: The number assigned to this channel + * @num_elements: The number of elements that can be queued to this channel + * @dir: Direction that data may flow on this channel + */ +struct mhi_ep_channel_config { + char *name; + u32 num; + u32 num_elements; + enum dma_data_direction dir; +}; + +/** + * struct mhi_ep_cntrl_config - MHI Endpoint controller configuration + * @mhi_version: MHI spec version supported by the controller + * @max_channels: Maximum number of channels supported + * @num_channels: Number of channels defined in @ch_cfg + * @ch_cfg: Array of defined channels + */ +struct mhi_ep_cntrl_config { + u32 mhi_version; + u32 max_channels; + u32 num_channels; + const struct mhi_ep_channel_config *ch_cfg; +}; + +/** + * struct mhi_ep_db_info - MHI Endpoint doorbell info + * @mask: Mask of the doorbell interrupt + * @status: Status of the doorbell interrupt + */ +struct mhi_ep_db_info { + u32 mask; + u32 status; +}; + +/** + * struct mhi_ep_cntrl - MHI Endpoint controller structure + * @cntrl_dev: Pointer to the struct device of physical bus acting as the MHI + * Endpoint controller + * @mhi_dev: MHI Endpoint device instance for the controller + * @mmio: MMIO region containing the MHI registers + * @mhi_chan: Points to the channel configuration table + * @mhi_event: Points to the event ring configurations table + * @mhi_cmd: Points to the command ring configurations table + * @sm: MHI Endpoint state machine + * @raise_irq: CB function for raising IRQ to the host + * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it + * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context + * @read_from_host: CB function for reading from host memory from endpoint + * @write_to_host: CB function for writing to host memory from endpoint + * @mhi_state: MHI Endpoint state + * @max_chan: Maximum channels supported by the endpoint controller + * @mru: MRU (Maximum Receive Unit) value of the endpoint controller + * @index: MHI Endpoint controller index + */ +struct mhi_ep_cntrl { + struct device *cntrl_dev; + struct mhi_ep_device *mhi_dev; + void __iomem *mmio; + + struct mhi_ep_chan *mhi_chan; + struct mhi_ep_event *mhi_event; + struct mhi_ep_cmd *mhi_cmd; + struct mhi_ep_sm *sm; + + void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector); + int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr, + void __iomem **virt, size_t size); + void (*unmap_free)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t phys, + void __iomem *virt, size_t size); + int (*read_from_host)(struct mhi_ep_cntrl *mhi_cntrl, u64 from, void *to, size_t size); + int (*write_to_host)(struct mhi_ep_cntrl *mhi_cntrl, void *from, u64 to, size_t size); + + enum mhi_state mhi_state; + + u32 max_chan; + u32 mru; + u32 index; +}; + +/** + * struct mhi_ep_device - Structure representing an MHI Endpoint device that binds + * to channels or is associated with controllers + * @dev: Driver model device node for the MHI Endpoint device + * @mhi_cntrl: Controller the device belongs to + * @id: Pointer to MHI Endpoint device ID struct + * @name: Name of the associated MHI Endpoint device + * @ul_chan: UL channel for the device + * @dl_chan: DL channel for the device + * @dev_type: MHI device type + */ +struct mhi_ep_device { + struct device dev; + struct mhi_ep_cntrl *mhi_cntrl; + const struct mhi_device_id *id; + const char *name; + struct mhi_ep_chan *ul_chan; + struct mhi_ep_chan *dl_chan; + enum mhi_device_type dev_type; +}; + +#define to_mhi_ep_device(dev) container_of(dev, struct mhi_ep_device, dev) + +/** + * mhi_ep_register_controller - Register MHI Endpoint controller + * @mhi_cntrl: MHI Endpoint controller to register + * @config: Configuration to use for the controller + * + * Return: 0 if controller registrations succeeds, a negative error code otherwise. + */ +int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl, + const struct mhi_ep_cntrl_config *config); + +/** + * mhi_ep_unregister_controller - Unregister MHI Endpoint controller + * @mhi_cntrl: MHI Endpoint controller to unregister + */ +void mhi_ep_unregister_controller(struct mhi_ep_cntrl *mhi_cntrl); + +#endif -- cgit v1.2.3 From ee0360b20b3fa08e2eee300eacb45e812ae44578 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:38 +0530 Subject: bus: mhi: ep: Add support for registering MHI endpoint client drivers This commit adds support for registering MHI endpoint client drivers with the MHI endpoint stack. MHI endpoint client drivers bind to one or more MHI endpoint devices inorder to send and receive the upper-layer protocol packets like IP packets, modem control messages, and diagnostics messages over MHI bus. Reviewed-by: Hemant Kumar Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-3-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 57 ++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 55 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index 891b199a9703..e2b94f9eb846 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -101,8 +101,8 @@ struct mhi_ep_cntrl { * @mhi_cntrl: Controller the device belongs to * @id: Pointer to MHI Endpoint device ID struct * @name: Name of the associated MHI Endpoint device - * @ul_chan: UL channel for the device - * @dl_chan: DL channel for the device + * @ul_chan: UL (from host to endpoint) channel for the device + * @dl_chan: DL (from endpoint to host) channel for the device * @dev_type: MHI device type */ struct mhi_ep_device { @@ -115,7 +115,60 @@ struct mhi_ep_device { enum mhi_device_type dev_type; }; +/** + * struct mhi_ep_driver - Structure representing a MHI Endpoint client driver + * @id_table: Pointer to MHI Endpoint device ID table + * @driver: Device driver model driver + * @probe: CB function for client driver probe function + * @remove: CB function for client driver remove function + * @ul_xfer_cb: CB function for UL (from host to endpoint) data transfer + * @dl_xfer_cb: CB function for DL (from endpoint to host) data transfer + */ +struct mhi_ep_driver { + const struct mhi_device_id *id_table; + struct device_driver driver; + int (*probe)(struct mhi_ep_device *mhi_ep, + const struct mhi_device_id *id); + void (*remove)(struct mhi_ep_device *mhi_ep); + void (*ul_xfer_cb)(struct mhi_ep_device *mhi_dev, + struct mhi_result *result); + void (*dl_xfer_cb)(struct mhi_ep_device *mhi_dev, + struct mhi_result *result); +}; + #define to_mhi_ep_device(dev) container_of(dev, struct mhi_ep_device, dev) +#define to_mhi_ep_driver(drv) container_of(drv, struct mhi_ep_driver, driver) + +/* + * module_mhi_ep_driver() - Helper macro for drivers that don't do + * anything special other than using default mhi_ep_driver_register() and + * mhi_ep_driver_unregister(). This eliminates a lot of boilerplate. + * Each module may only use this macro once. + */ +#define module_mhi_ep_driver(mhi_drv) \ + module_driver(mhi_drv, mhi_ep_driver_register, \ + mhi_ep_driver_unregister) + +/* + * Macro to avoid include chaining to get THIS_MODULE + */ +#define mhi_ep_driver_register(mhi_drv) \ + __mhi_ep_driver_register(mhi_drv, THIS_MODULE) + +/** + * __mhi_ep_driver_register - Register a driver with MHI Endpoint bus + * @mhi_drv: Driver to be associated with the device + * @owner: The module owner + * + * Return: 0 if driver registrations succeeds, a negative error code otherwise. + */ +int __mhi_ep_driver_register(struct mhi_ep_driver *mhi_drv, struct module *owner); + +/** + * mhi_ep_driver_unregister - Unregister a driver from MHI Endpoint bus + * @mhi_drv: Driver associated with the device + */ +void mhi_ep_driver_unregister(struct mhi_ep_driver *mhi_drv); /** * mhi_ep_register_controller - Register MHI Endpoint controller -- cgit v1.2.3 From e9e4da23cd65ea76ba658346f5c182791bd1cea9 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:40 +0530 Subject: bus: mhi: ep: Add support for managing MMIO registers Add support for managing the Memory Mapped Input Output (MMIO) registers of the MHI bus. All MHI operations are carried out using the MMIO registers by both host and the endpoint device. The MMIO registers reside inside the endpoint device memory (fixed location based on the platform) and the address is passed by the MHI EP controller driver during its registration. Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-5-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index e2b94f9eb846..5db048e258e4 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -59,6 +59,10 @@ struct mhi_ep_db_info { * @mhi_event: Points to the event ring configurations table * @mhi_cmd: Points to the command ring configurations table * @sm: MHI Endpoint state machine + * @ch_ctx_host_pa: Physical address of host channel context data structure + * @ev_ctx_host_pa: Physical address of host event context data structure + * @cmd_ctx_host_pa: Physical address of host command context data structure + * @chdb: Array of channel doorbell interrupt info * @raise_irq: CB function for raising IRQ to the host * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context @@ -67,6 +71,10 @@ struct mhi_ep_db_info { * @mhi_state: MHI Endpoint state * @max_chan: Maximum channels supported by the endpoint controller * @mru: MRU (Maximum Receive Unit) value of the endpoint controller + * @event_rings: Number of event rings supported by the endpoint controller + * @hw_event_rings: Number of hardware event rings supported by the endpoint controller + * @chdb_offset: Channel doorbell offset set by the host + * @erdb_offset: Event ring doorbell offset set by the host * @index: MHI Endpoint controller index */ struct mhi_ep_cntrl { @@ -79,6 +87,12 @@ struct mhi_ep_cntrl { struct mhi_ep_cmd *mhi_cmd; struct mhi_ep_sm *sm; + u64 ch_ctx_host_pa; + u64 ev_ctx_host_pa; + u64 cmd_ctx_host_pa; + + struct mhi_ep_db_info chdb[4]; + void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector); int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr, void __iomem **virt, size_t size); @@ -91,6 +105,10 @@ struct mhi_ep_cntrl { u32 max_chan; u32 mru; + u32 event_rings; + u32 hw_event_rings; + u32 chdb_offset; + u32 erdb_offset; u32 index; }; -- cgit v1.2.3 From 961aeb6892242e0a667f5b8eb62b9b0a6041752c Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:42 +0530 Subject: bus: mhi: ep: Add support for sending events to the host Add support for sending the events to the host over MHI bus from the endpoint. Following events are supported: 1. Transfer completion event 2. Command completion event 3. State change event 4. Execution Environment (EE) change event An event is sent whenever an operation has been completed in the MHI EP device. Event is sent using the MHI event ring and additionally the host is notified using an IRQ if required. Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-7-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index 5db048e258e4..46236ffb528a 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -59,10 +59,14 @@ struct mhi_ep_db_info { * @mhi_event: Points to the event ring configurations table * @mhi_cmd: Points to the command ring configurations table * @sm: MHI Endpoint state machine + * @ch_ctx_cache: Cache of host channel context data structure + * @ev_ctx_cache: Cache of host event context data structure + * @cmd_ctx_cache: Cache of host command context data structure * @ch_ctx_host_pa: Physical address of host channel context data structure * @ev_ctx_host_pa: Physical address of host event context data structure * @cmd_ctx_host_pa: Physical address of host command context data structure * @chdb: Array of channel doorbell interrupt info + * @event_lock: Lock for protecting event rings * @raise_irq: CB function for raising IRQ to the host * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context @@ -87,11 +91,15 @@ struct mhi_ep_cntrl { struct mhi_ep_cmd *mhi_cmd; struct mhi_ep_sm *sm; + struct mhi_chan_ctxt *ch_ctx_cache; + struct mhi_event_ctxt *ev_ctx_cache; + struct mhi_cmd_ctxt *cmd_ctx_cache; u64 ch_ctx_host_pa; u64 ev_ctx_host_pa; u64 cmd_ctx_host_pa; struct mhi_ep_db_info chdb[4]; + struct mutex event_lock; void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector); int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr, -- cgit v1.2.3 From f9baa4f737950523ca648866dfa345ac378e4487 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:43 +0530 Subject: bus: mhi: ep: Add support for managing MHI state machine Add support for managing the MHI state machine by controlling the state transitions. Only the following MHI state transitions are supported: 1. Ready state 2. M0 state 3. M3 state 4. SYS_ERR state Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-8-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index 46236ffb528a..2880d2aa88b8 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -67,6 +67,11 @@ struct mhi_ep_db_info { * @cmd_ctx_host_pa: Physical address of host command context data structure * @chdb: Array of channel doorbell interrupt info * @event_lock: Lock for protecting event rings + * @list_lock: Lock for protecting state transition and channel doorbell lists + * @state_lock: Lock for protecting state transitions + * @st_transition_list: List of state transitions + * @wq: Dedicated workqueue for handling rings and state changes + * @state_work: State transition worker * @raise_irq: CB function for raising IRQ to the host * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context @@ -100,6 +105,13 @@ struct mhi_ep_cntrl { struct mhi_ep_db_info chdb[4]; struct mutex event_lock; + spinlock_t list_lock; + spinlock_t state_lock; + + struct list_head st_transition_list; + + struct workqueue_struct *wq; + struct work_struct state_work; void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector); int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr, -- cgit v1.2.3 From 4799e71b082615445dc40ba0bbb86cbb76c24724 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:44 +0530 Subject: bus: mhi: ep: Add support for processing MHI endpoint interrupts Add support for processing MHI endpoint interrupts such as control interrupt, command interrupt and channel interrupt from the host. The interrupts will be generated in the endpoint device whenever host writes to the corresponding doorbell registers. The doorbell logic is handled inside the hardware internally. Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-9-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index 2880d2aa88b8..137bd3ee2e43 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -70,6 +70,7 @@ struct mhi_ep_db_info { * @list_lock: Lock for protecting state transition and channel doorbell lists * @state_lock: Lock for protecting state transitions * @st_transition_list: List of state transitions + * @ch_db_list: List of queued channel doorbells * @wq: Dedicated workqueue for handling rings and state changes * @state_work: State transition worker * @raise_irq: CB function for raising IRQ to the host @@ -85,6 +86,7 @@ struct mhi_ep_db_info { * @chdb_offset: Channel doorbell offset set by the host * @erdb_offset: Event ring doorbell offset set by the host * @index: MHI Endpoint controller index + * @irq: IRQ used by the endpoint controller */ struct mhi_ep_cntrl { struct device *cntrl_dev; @@ -109,6 +111,7 @@ struct mhi_ep_cntrl { spinlock_t state_lock; struct list_head st_transition_list; + struct list_head ch_db_list; struct workqueue_struct *wq; struct work_struct state_work; @@ -130,6 +133,7 @@ struct mhi_ep_cntrl { u32 chdb_offset; u32 erdb_offset; u32 index; + int irq; }; /** -- cgit v1.2.3 From fb3a26b7e8aff11e44d582604f61c38f63bd507c Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:45 +0530 Subject: bus: mhi: ep: Add support for powering up the MHI endpoint stack Add support for MHI endpoint power_up that includes initializing the MMIO and rings, caching the host MHI registers, and setting the MHI state to M0. After registering the MHI EP controller, the stack has to be powered up for usage. Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-10-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index 137bd3ee2e43..3b065f82fbeb 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -65,6 +65,9 @@ struct mhi_ep_db_info { * @ch_ctx_host_pa: Physical address of host channel context data structure * @ev_ctx_host_pa: Physical address of host event context data structure * @cmd_ctx_host_pa: Physical address of host command context data structure + * @ch_ctx_cache_phys: Physical address of the host channel context cache + * @ev_ctx_cache_phys: Physical address of the host event context cache + * @cmd_ctx_cache_phys: Physical address of the host command context cache * @chdb: Array of channel doorbell interrupt info * @event_lock: Lock for protecting event rings * @list_lock: Lock for protecting state transition and channel doorbell lists @@ -87,6 +90,7 @@ struct mhi_ep_db_info { * @erdb_offset: Event ring doorbell offset set by the host * @index: MHI Endpoint controller index * @irq: IRQ used by the endpoint controller + * @enabled: Check if the endpoint controller is enabled or not */ struct mhi_ep_cntrl { struct device *cntrl_dev; @@ -104,6 +108,9 @@ struct mhi_ep_cntrl { u64 ch_ctx_host_pa; u64 ev_ctx_host_pa; u64 cmd_ctx_host_pa; + phys_addr_t ch_ctx_cache_phys; + phys_addr_t ev_ctx_cache_phys; + phys_addr_t cmd_ctx_cache_phys; struct mhi_ep_db_info chdb[4]; struct mutex event_lock; @@ -134,6 +141,7 @@ struct mhi_ep_cntrl { u32 erdb_offset; u32 index; int irq; + bool enabled; }; /** @@ -228,4 +236,12 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl, */ void mhi_ep_unregister_controller(struct mhi_ep_cntrl *mhi_cntrl); +/** + * mhi_ep_power_up - Power up the MHI endpoint stack + * @mhi_cntrl: MHI Endpoint controller + * + * Return: 0 if power up succeeds, a negative error code otherwise. + */ +int mhi_ep_power_up(struct mhi_ep_cntrl *mhi_cntrl); + #endif -- cgit v1.2.3 From 5d507ee04894e166f8c5a29f05c6b06ce91d5833 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:46 +0530 Subject: bus: mhi: ep: Add support for powering down the MHI endpoint stack Add support for MHI endpoint power_down that includes stopping all available channels, destroying the channels, resetting the event and transfer rings and freeing the host cache. The stack will be powered down whenever the physical bus link goes down. Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-11-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index 3b065f82fbeb..9da683e8302c 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -244,4 +244,10 @@ void mhi_ep_unregister_controller(struct mhi_ep_cntrl *mhi_cntrl); */ int mhi_ep_power_up(struct mhi_ep_cntrl *mhi_cntrl); +/** + * mhi_ep_power_down - Power down the MHI endpoint stack + * @mhi_cntrl: MHI controller + */ +void mhi_ep_power_down(struct mhi_ep_cntrl *mhi_cntrl); + #endif -- cgit v1.2.3 From 7a97b6b47353c60dd1b53ada6180741437e377f2 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:47 +0530 Subject: bus: mhi: ep: Add support for handling MHI_RESET Add support for handling MHI_RESET in MHI endpoint stack. MHI_RESET will be issued by the host during shutdown and during error scenario so that it can recover the endpoint device without restarting the whole device. MHI_RESET handling involves resetting the internal MHI registers, data structures, state machines, resetting all channels/rings and setting MHICTRL.RESET bit to 0. Additionally the device will also move to READY state if the reset was due to SYS_ERR. Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-12-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index 9da683e8302c..2f31a54c205f 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -76,6 +76,7 @@ struct mhi_ep_db_info { * @ch_db_list: List of queued channel doorbells * @wq: Dedicated workqueue for handling rings and state changes * @state_work: State transition worker + * @reset_work: Worker for MHI Endpoint reset * @raise_irq: CB function for raising IRQ to the host * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context @@ -122,6 +123,7 @@ struct mhi_ep_cntrl { struct workqueue_struct *wq; struct work_struct state_work; + struct work_struct reset_work; void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector); int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr, -- cgit v1.2.3 From e827569062a804c67b51930ce83a4cb886113cb7 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:49 +0530 Subject: bus: mhi: ep: Add support for processing command rings Add support for processing the command rings. Command ring is used by the host to issue channel specific commands to the ep device. Following commands are supported: 1. Start channel 2. Stop channel 3. Reset channel Once the device receives the command doorbell interrupt from host, it executes the command and generates a command completion event to the host in the primary event ring. Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-14-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index 2f31a54c205f..8c6406d9c51f 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -77,6 +77,7 @@ struct mhi_ep_db_info { * @wq: Dedicated workqueue for handling rings and state changes * @state_work: State transition worker * @reset_work: Worker for MHI Endpoint reset + * @cmd_ring_work: Worker for processing command rings * @raise_irq: CB function for raising IRQ to the host * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context @@ -124,6 +125,7 @@ struct mhi_ep_cntrl { struct workqueue_struct *wq; struct work_struct state_work; struct work_struct reset_work; + struct work_struct cmd_ring_work; void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector); int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr, -- cgit v1.2.3 From 530125889977365cb6db32d7d0bd84c9f54c8aab Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:50 +0530 Subject: bus: mhi: ep: Add support for reading from the host Data transfer between host and the ep device happens over the transfer ring associated with each bi-directional channel pair. Host defines the transfer ring by allocating memory for it. The read and write pointer addresses of the transfer ring are stored in the channel context. Once host places the elements in the transfer ring, it increments the write pointer and rings the channel doorbell. Device will receive the doorbell interrupt and will process the transfer ring elements. This commit adds support for reading the transfer ring elements from the transfer ring till write pointer, incrementing the read pointer and finally sending the completion event to the host through corresponding event ring. Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-15-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index 8c6406d9c51f..fc7d197413eb 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -254,4 +254,13 @@ int mhi_ep_power_up(struct mhi_ep_cntrl *mhi_cntrl); */ void mhi_ep_power_down(struct mhi_ep_cntrl *mhi_cntrl); +/** + * mhi_ep_queue_is_empty - Determine whether the transfer queue is empty + * @mhi_dev: Device associated with the channels + * @dir: DMA direction for the channel + * + * Return: true if the queue is empty, false otherwise. + */ +bool mhi_ep_queue_is_empty(struct mhi_ep_device *mhi_dev, enum dma_data_direction dir); + #endif -- cgit v1.2.3 From 03c0bb8ec983f993a704417d73cc0a3511453d3e Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:51 +0530 Subject: bus: mhi: ep: Add support for processing channel rings Add support for processing the channel rings from host. For the channel ring associated with DL channel, the xfer callback will simply invoked. For the case of UL channel, the ring elements will be read in a buffer till the write pointer and later passed to the client driver using the xfer callback. The client drivers should provide the callbacks for both UL and DL channels during registration. Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-16-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index fc7d197413eb..eecc8f35d630 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -78,6 +78,7 @@ struct mhi_ep_db_info { * @state_work: State transition worker * @reset_work: Worker for MHI Endpoint reset * @cmd_ring_work: Worker for processing command rings + * @ch_ring_work: Worker for processing channel rings * @raise_irq: CB function for raising IRQ to the host * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context @@ -126,6 +127,7 @@ struct mhi_ep_cntrl { struct work_struct state_work; struct work_struct reset_work; struct work_struct cmd_ring_work; + struct work_struct ch_ring_work; void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector); int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr, -- cgit v1.2.3 From 2d945a394d9c1c59d88397cb383b11216d018a6b Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:52 +0530 Subject: bus: mhi: ep: Add support for queueing SKBs to the host Add support for queueing SKBs to the host over the transfer ring of the relevant channel. The mhi_ep_queue_skb() API will be used by the client networking drivers to queue the SKBs to the host over MHI bus. The host will add ring elements to the transfer ring periodically for the device and the device will write SKBs to the ring elements. If a single SKB doesn't fit in a ring element (TRE), it will be placed in multiple ring elements and the overflow event will be sent for all ring elements except the last one. For the last ring element, the EOT event will be sent indicating the packet boundary. Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-17-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mhi_ep.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index eecc8f35d630..478aece17046 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -265,4 +265,13 @@ void mhi_ep_power_down(struct mhi_ep_cntrl *mhi_cntrl); */ bool mhi_ep_queue_is_empty(struct mhi_ep_device *mhi_dev, enum dma_data_direction dir); +/** + * mhi_ep_queue_skb - Send SKBs to host over MHI Endpoint + * @mhi_dev: Device associated with the DL channel + * @skb: SKBs to be queued + * + * Return: 0 if the SKBs has been sent successfully, a negative error code otherwise. + */ +int mhi_ep_queue_skb(struct mhi_ep_device *mhi_dev, struct sk_buff *skb); + #endif -- cgit v1.2.3 From c268c0a8a33047cd957fecc1349d09a68eb6ad9e Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 5 Apr 2022 19:27:54 +0530 Subject: bus: mhi: ep: Add uevent support for module autoloading Add uevent support to MHI endpoint bus so that the client drivers can be autoloaded by udev when the MHI endpoint devices gets created. The client drivers are expected to provide MODULE_DEVICE_TABLE with the MHI id_table struct so that the alias can be exported. The MHI endpoint reused the mhi_device_id structure of the MHI bus. Reviewed-by: Alex Elder Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20220405135754.6622-19-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/mod_devicetable.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 5da5d990ff58..549590e9c644 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -835,6 +835,8 @@ struct wmi_device_id { #define MHI_DEVICE_MODALIAS_FMT "mhi:%s" #define MHI_NAME_SIZE 32 +#define MHI_EP_DEVICE_MODALIAS_FMT "mhi_ep:%s" + /** * struct mhi_device_id - MHI device identification * @chan: MHI channel name -- cgit v1.2.3 From 31f6bd7fad3b149a1eb6f67fc2e742e4df369b3d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 25 Apr 2022 17:33:58 +0300 Subject: serial: Store character timing information to uart_port MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Struct uart_port currently stores FIFO timeout. Having character timing information readily available is useful. Even serial core itself determines char_time from port->timeout using inverse calculation. Store frame_time directly into uart_port. Character time is stored in nanoseconds to have reasonable precision with high rates. To avoid overflow, 64-bit math is necessary. It might be possible to determine timeout from frame_time by multiplying it with fifosize as needed but only part of the users seem to be protected by a lock. Thus, this patch does not pursue storing only frame_time in uart_port. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20220425143410.12703-2-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index d4828e69087a..cbd5070bc87f 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -232,6 +232,7 @@ struct uart_port { int hw_stopped; /* sw-assisted CTS flow state */ unsigned int mctrl; /* current modem ctrl settings */ unsigned int timeout; /* character-based timeout */ + unsigned int frame_time; /* frame timing in ns */ unsigned int type; /* port type */ const struct uart_ops *ops; unsigned int custom_divisor; -- cgit v1.2.3 From 7a20917d30fb627bebff6bacbe860ad4eb3a04d6 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Fri, 22 Apr 2022 15:23:45 -0700 Subject: device property: Add helper to match multiple connections In some cases multiple connections with the same connection id needs to be resolved from a fwnode graph. One such example is when separate hardware is used for performing muxing and/or orientation switching of the SuperSpeed and SBU lines in a USB Type-C connector. In this case the connector needs to belong to a graph with multiple matching remote endpoints, and the Type-C controller needs to be able to resolve them both. Add a new API that allows this kind of lookup. Reviewed-by: Andy Shevchenko Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220422222351.1297276-2-bjorn.andersson@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/property.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/property.h b/include/linux/property.h index 4cd4b326941f..de7ff336d2c8 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -447,6 +447,11 @@ static inline void *device_connection_find_match(struct device *dev, return fwnode_connection_find_match(dev_fwnode(dev), con_id, data, match); } +int fwnode_connection_find_matches(struct fwnode_handle *fwnode, + const char *con_id, void *data, + devcon_match_fn_t match, + void **matches, unsigned int matches_len); + /* -------------------------------------------------------------------------- */ /* Software fwnode support - when HW description is incomplete or missing */ -- cgit v1.2.3 From 713fd49b430c37263c6cae2c82954f4e1cbcd90d Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Fri, 22 Apr 2022 15:23:48 -0700 Subject: usb: typec: mux: Introduce indirection Rather than directly exposing the implementation's representation of the typec muxes to the controller/clients, introduce an indirection object. This enables the introduction of turning this relationship into a one-to-many in the following patch. Acked-by: Heikki Krogerus Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220422222351.1297276-5-bjorn.andersson@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec_mux.h | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/usb/typec_mux.h b/include/linux/usb/typec_mux.h index a9d9957933dc..ee57781dcf28 100644 --- a/include/linux/usb/typec_mux.h +++ b/include/linux/usb/typec_mux.h @@ -8,11 +8,13 @@ struct device; struct typec_mux; +struct typec_mux_dev; struct typec_switch; +struct typec_switch_dev; struct typec_altmode; struct fwnode_handle; -typedef int (*typec_switch_set_fn_t)(struct typec_switch *sw, +typedef int (*typec_switch_set_fn_t)(struct typec_switch_dev *sw, enum typec_orientation orientation); struct typec_switch_desc { @@ -32,13 +34,13 @@ static inline struct typec_switch *typec_switch_get(struct device *dev) return fwnode_typec_switch_get(dev_fwnode(dev)); } -struct typec_switch * +struct typec_switch_dev * typec_switch_register(struct device *parent, const struct typec_switch_desc *desc); -void typec_switch_unregister(struct typec_switch *sw); +void typec_switch_unregister(struct typec_switch_dev *sw); -void typec_switch_set_drvdata(struct typec_switch *sw, void *data); -void *typec_switch_get_drvdata(struct typec_switch *sw); +void typec_switch_set_drvdata(struct typec_switch_dev *sw, void *data); +void *typec_switch_get_drvdata(struct typec_switch_dev *sw); struct typec_mux_state { struct typec_altmode *alt; @@ -46,7 +48,7 @@ struct typec_mux_state { void *data; }; -typedef int (*typec_mux_set_fn_t)(struct typec_mux *mux, +typedef int (*typec_mux_set_fn_t)(struct typec_mux_dev *mux, struct typec_mux_state *state); struct typec_mux_desc { @@ -67,11 +69,11 @@ typec_mux_get(struct device *dev, const struct typec_altmode_desc *desc) return fwnode_typec_mux_get(dev_fwnode(dev), desc); } -struct typec_mux * +struct typec_mux_dev * typec_mux_register(struct device *parent, const struct typec_mux_desc *desc); -void typec_mux_unregister(struct typec_mux *mux); +void typec_mux_unregister(struct typec_mux_dev *mux); -void typec_mux_set_drvdata(struct typec_mux *mux, void *data); -void *typec_mux_get_drvdata(struct typec_mux *mux); +void typec_mux_set_drvdata(struct typec_mux_dev *mux, void *data); +void *typec_mux_get_drvdata(struct typec_mux_dev *mux); #endif /* __USB_TYPEC_MUX */ -- cgit v1.2.3 From af1969a2d734d6272c0640b50c3ed31e59e203a9 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Sat, 23 Apr 2022 20:42:03 -0400 Subject: USB: gadget: Rename usb_gadget_probe_driver() In preparation for adding a "gadget" bus, this patch renames usb_gadget_probe_driver() to usb_gadget_register_driver(). The new name will be more accurate, since gadget drivers will be registered on the gadget bus and the probing will be done by the driver core, not the UDC core. Signed-off-by: Alan Stern Link: https://lore.kernel.org/r/YmSc29YZvxgT5fEJ@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/gadget.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 10fe57cf40be..5830b8a903da 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -745,7 +745,7 @@ struct usb_gadget_driver { */ /** - * usb_gadget_probe_driver - probe a gadget driver + * usb_gadget_register_driver - register a gadget driver * @driver: the driver being registered * Context: can sleep * @@ -755,7 +755,7 @@ struct usb_gadget_driver { * registration call returns. It's expected that the @bind() function will * be in init sections. */ -int usb_gadget_probe_driver(struct usb_gadget_driver *driver); +int usb_gadget_register_driver(struct usb_gadget_driver *driver); /** * usb_gadget_unregister_driver - unregister a gadget driver -- cgit v1.2.3 From fc274c1e997314bf47f6a62c79b5d7e554ed59c4 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Sat, 23 Apr 2022 21:35:51 -0400 Subject: USB: gadget: Add a new bus for gadgets This patch adds a "gadget" bus and uses it for registering gadgets and their drivers. From now on, bindings will be managed by the driver core rather than through ad-hoc manipulations in the UDC core. As part of this change, the driver_pending_list is removed. The UDC core won't need to keep track of unbound drivers for later binding, because the driver core handles all of that for us. However, we do need one new feature: a way to prevent gadget drivers from being bound to more than one gadget at a time. The existing code does this automatically, but the driver core doesn't -- it's perfectly happy to bind a single driver to all the matching devices on the bus. The patch adds a new bitflag to the usb_gadget_driver structure for this purpose. A nice side effect of this change is a reduction in the total lines of code, since now the driver core will do part of the work that the UDC used to do. A possible future patch could add udc devices to the gadget bus, say as a separate device type. Signed-off-by: Alan Stern Link: https://lore.kernel.org/r/YmSpdxaDNeC2BBOf@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/gadget.h | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 5830b8a903da..cf7af8a0a6e9 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -664,9 +664,9 @@ static inline int usb_gadget_check_config(struct usb_gadget *gadget) * @driver: Driver model state for this driver. * @udc_name: A name of UDC this driver should be bound to. If udc_name is NULL, * this driver will be bound to any available UDC. - * @pending: UDC core private data used for deferred probe of this driver. - * @match_existing_only: If udc is not found, return an error and don't add this - * gadget driver to list of pending driver + * @match_existing_only: If udc is not found, return an error and fail + * the driver registration + * @is_bound: Allow a driver to be bound to only one gadget * * Devices are disabled till a gadget driver successfully bind()s, which * means the driver will handle setup() requests needed to enumerate (and @@ -729,8 +729,8 @@ struct usb_gadget_driver { struct device_driver driver; char *udc_name; - struct list_head pending; unsigned match_existing_only:1; + bool is_bound:1; }; @@ -740,22 +740,30 @@ struct usb_gadget_driver { /* driver modules register and unregister, as usual. * these calls must be made in a context that can sleep. * - * these will usually be implemented directly by the hardware-dependent - * usb bus interface driver, which will only support a single driver. + * A gadget driver can be bound to only one gadget at a time. */ /** - * usb_gadget_register_driver - register a gadget driver + * usb_gadget_register_driver_owner - register a gadget driver * @driver: the driver being registered + * @owner: the driver module + * @mod_name: the driver module's build name * Context: can sleep * * Call this in your gadget driver's module initialization function, - * to tell the underlying usb controller driver about your driver. + * to tell the underlying UDC controller driver about your driver. * The @bind() function will be called to bind it to a gadget before this * registration call returns. It's expected that the @bind() function will * be in init sections. + * + * Use the macro defined below instead of calling this directly. */ -int usb_gadget_register_driver(struct usb_gadget_driver *driver); +int usb_gadget_register_driver_owner(struct usb_gadget_driver *driver, + struct module *owner, const char *mod_name); + +/* use a define to avoid include chaining to get THIS_MODULE & friends */ +#define usb_gadget_register_driver(driver) \ + usb_gadget_register_driver_owner(driver, THIS_MODULE, KBUILD_MODNAME) /** * usb_gadget_unregister_driver - unregister a gadget driver -- cgit v1.2.3 From 8e8b11956486e3fe8cacf54a1d492ebdd8cc1fb2 Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Thu, 17 Feb 2022 10:42:52 -0800 Subject: of/platform: Add stubs for of_platform_device_create/destroy() Code for platform_device_create() and of_platform_device_destroy() is only generated if CONFIG_OF_ADDRESS=y. Add stubs to avoid unresolved symbols when CONFIG_OF_ADDRESS is not set. Reviewed-by: Stephen Boyd Reviewed-by: Douglas Anderson Acked-by: Rob Herring Signed-off-by: Matthias Kaehlcke Link: https://lore.kernel.org/r/20220217104219.v21.1.I08fd2e1c775af04f663730e9fb4d00e6bbb38541@changeid Signed-off-by: Greg Kroah-Hartman --- include/linux/of_platform.h | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index 84a966623e78..d15b6cd5e1c3 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -61,16 +61,18 @@ static inline struct platform_device *of_find_device_by_node(struct device_node } #endif +extern int of_platform_bus_probe(struct device_node *root, + const struct of_device_id *matches, + struct device *parent); + +#ifdef CONFIG_OF_ADDRESS /* Platform devices and busses creation */ extern struct platform_device *of_platform_device_create(struct device_node *np, const char *bus_id, struct device *parent); extern int of_platform_device_destroy(struct device *dev, void *data); -extern int of_platform_bus_probe(struct device_node *root, - const struct of_device_id *matches, - struct device *parent); -#ifdef CONFIG_OF_ADDRESS + extern int of_platform_populate(struct device_node *root, const struct of_device_id *matches, const struct of_dev_auxdata *lookup, @@ -84,6 +86,18 @@ extern int devm_of_platform_populate(struct device *dev); extern void devm_of_platform_depopulate(struct device *dev); #else +/* Platform devices and busses creation */ +static inline struct platform_device *of_platform_device_create(struct device_node *np, + const char *bus_id, + struct device *parent) +{ + return NULL; +} +static inline int of_platform_device_destroy(struct device *dev, void *data) +{ + return -ENODEV; +} + static inline int of_platform_populate(struct device_node *root, const struct of_device_id *matches, const struct of_dev_auxdata *lookup, -- cgit v1.2.3 From 0298b4b95cb373c21e6323c905589f8dac42c5b4 Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Thu, 17 Feb 2022 10:42:53 -0800 Subject: usb: misc: Add onboard_usb_hub driver The main issue this driver addresses is that a USB hub needs to be powered before it can be discovered. For discrete onboard hubs (an example for such a hub is the Realtek RTS5411) this is often solved by supplying the hub with an 'always-on' regulator, which is kind of a hack. Some onboard hubs may require further initialization steps, like changing the state of a GPIO or enabling a clock, which requires even more hacks. This driver creates a platform device representing the hub which performs the necessary initialization. Currently it only supports switching on a single regulator, support for multiple regulators or other actions can be added as needed. Different initialization sequences can be supported based on the compatible string. Besides performing the initialization the driver can be configured to power the hub off during system suspend. This can help to extend battery life on battery powered devices which have no requirements to keep the hub powered during suspend. The driver can also be configured to leave the hub powered when a wakeup capable USB device is connected when suspending, and power it off otherwise. Technically the driver consists of two drivers, the platform driver described above and a very thin USB driver that subclasses the generic driver. The purpose of this driver is to provide the platform driver with the USB devices corresponding to the hub(s) (a hub controller may provide multiple 'logical' hubs, e.g. one to support USB 2.0 and another for USB 3.x). Note: the current series only supports hubs connected directly to a root hub, support for other configurations could be added if needed. Co-developed-by: Ravi Chandra Sadineni Reviewed-by: Douglas Anderson Acked-by: Alan Stern Signed-off-by: Ravi Chandra Sadineni Signed-off-by: Matthias Kaehlcke Link: https://lore.kernel.org/r/20220217104219.v21.2.I7c9a1f1d6ced41dd8310e8a03da666a32364e790@changeid Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/onboard_hub.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 include/linux/usb/onboard_hub.h (limited to 'include') diff --git a/include/linux/usb/onboard_hub.h b/include/linux/usb/onboard_hub.h new file mode 100644 index 000000000000..d9373230556e --- /dev/null +++ b/include/linux/usb/onboard_hub.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __LINUX_USB_ONBOARD_HUB_H +#define __LINUX_USB_ONBOARD_HUB_H + +struct usb_device; +struct list_head; + +#if IS_ENABLED(CONFIG_USB_ONBOARD_HUB) +void onboard_hub_create_pdevs(struct usb_device *parent_hub, struct list_head *pdev_list); +void onboard_hub_destroy_pdevs(struct list_head *pdev_list); +#else +static inline void onboard_hub_create_pdevs(struct usb_device *parent_hub, + struct list_head *pdev_list) {} +static inline void onboard_hub_destroy_pdevs(struct list_head *pdev_list) {} +#endif + +#endif /* __LINUX_USB_ONBOARD_HUB_H */ -- cgit v1.2.3 From c40b62216c1aecc0dc00faf33d71bd71cb440337 Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Thu, 17 Feb 2022 10:42:54 -0800 Subject: usb: core: hcd: Create platform devices for onboard hubs in probe() Call onboard_hub_create/destroy_pdevs() from usb_add/remove_hcd() for primary HCDs to create/destroy platform devices for onboard USB hubs that may be connected to the root hub of the controller. These functions are a NOP unless CONFIG_USB_ONBOARD_HUB=y/m. Also add a field to struct usb_hcd to keep track of the onboard hub platform devices that are owned by the HCD. Reviewed-by: Douglas Anderson Reviewed-by: Stephen Boyd Signed-off-by: Matthias Kaehlcke Link: https://lore.kernel.org/r/20220217104219.v21.3.I7a3a7d9d2126c34079b1cab87aa0b2ec3030f9b7@changeid Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 548a028f2dab..4ebc91c09182 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -198,6 +198,7 @@ struct usb_hcd { struct usb_hcd *shared_hcd; struct usb_hcd *primary_hcd; + struct list_head onboard_hub_devs; #define HCD_BUFFER_POOLS 4 struct dma_pool *pool[HCD_BUFFER_POOLS]; -- cgit v1.2.3 From 9723f69d1de37ca25474372ad1753ea39bb0dce1 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Fri, 8 Apr 2022 10:00:43 +0200 Subject: mmc: core: improve API to make clear that mmc_sw_reset is for cards To make it unambiguous that mmc_sw_reset() is for cards and not for controllers, we make the function argument mmc_card instead of mmc_host. There are no users to convert currently. Suggested-by: Ulf Hansson Signed-off-by: Wolfram Sang Link: https://lore.kernel.org/r/20220408080045.6497-3-wsa+renesas@sang-engineering.com Signed-off-by: Ulf Hansson --- include/linux/mmc/core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index de5c64bbdb72..6efec0b9820c 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -176,7 +176,7 @@ int mmc_wait_for_cmd(struct mmc_host *host, struct mmc_command *cmd, int retries); int mmc_hw_reset(struct mmc_card *card); -int mmc_sw_reset(struct mmc_host *host); +int mmc_sw_reset(struct mmc_card *card); void mmc_set_data_timeout(struct mmc_data *data, const struct mmc_card *card); #endif /* LINUX_MMC_CORE_H */ -- cgit v1.2.3 From 32f18e596141f40dbc5d8700b2730371ffd3055f Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Fri, 8 Apr 2022 10:00:44 +0200 Subject: mmc: improve API to make clear hw_reset callback is for cards To make it unambiguous that the hw_reset callback is for cards and not for controllers, we add 'card' to the callback name and convert all users in one go. We keep the argument as mmc_host, though, because the callback is used very early when mmc_card is not yet populated. Signed-off-by: Wolfram Sang Link: https://lore.kernel.org/r/20220408080045.6497-4-wsa+renesas@sang-engineering.com Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 7afb57cab00b..c193c50ccd78 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -181,7 +181,7 @@ struct mmc_host_ops { unsigned int max_dtr, int host_drv, int card_drv, int *drv_type); /* Reset the eMMC card via RST_n */ - void (*hw_reset)(struct mmc_host *host); + void (*card_hw_reset)(struct mmc_host *host); void (*card_event)(struct mmc_host *host); /* -- cgit v1.2.3 From 13acb62ce1ee7377ef03034fbbad6f5499464b86 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 12 Apr 2022 11:31:02 +0200 Subject: mmc: sh_mmcif: move platform_data header to proper location We have a dedicated directory for platform_data meanwhile, don't spoil the MMC directory with it. Reviewed-by: Geert Uytterhoeven Signed-off-by: Wolfram Sang Link: https://lore.kernel.org/r/20220412093102.3428-1-wsa+renesas@sang-engineering.com Signed-off-by: Ulf Hansson --- include/linux/mmc/sh_mmcif.h | 209 --------------------------------- include/linux/platform_data/sh_mmcif.h | 207 ++++++++++++++++++++++++++++++++ 2 files changed, 207 insertions(+), 209 deletions(-) delete mode 100644 include/linux/mmc/sh_mmcif.h create mode 100644 include/linux/platform_data/sh_mmcif.h (limited to 'include') diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/mmc/sh_mmcif.h deleted file mode 100644 index e25533b95d9f..000000000000 --- a/include/linux/mmc/sh_mmcif.h +++ /dev/null @@ -1,209 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * include/linux/mmc/sh_mmcif.h - * - * platform data for eMMC driver - * - * Copyright (C) 2010 Renesas Solutions Corp. - */ - -#ifndef LINUX_MMC_SH_MMCIF_H -#define LINUX_MMC_SH_MMCIF_H - -#include -#include - -/* - * MMCIF : CE_CLK_CTRL [19:16] - * 1000 : Peripheral clock / 512 - * 0111 : Peripheral clock / 256 - * 0110 : Peripheral clock / 128 - * 0101 : Peripheral clock / 64 - * 0100 : Peripheral clock / 32 - * 0011 : Peripheral clock / 16 - * 0010 : Peripheral clock / 8 - * 0001 : Peripheral clock / 4 - * 0000 : Peripheral clock / 2 - * 1111 : Peripheral clock (sup_pclk set '1') - */ - -struct sh_mmcif_plat_data { - unsigned int slave_id_tx; /* embedded slave_id_[tr]x */ - unsigned int slave_id_rx; - u8 sup_pclk; /* 1 :SH7757, 0: SH7724/SH7372 */ - unsigned long caps; - u32 ocr; -}; - -#define MMCIF_CE_CMD_SET 0x00000000 -#define MMCIF_CE_ARG 0x00000008 -#define MMCIF_CE_ARG_CMD12 0x0000000C -#define MMCIF_CE_CMD_CTRL 0x00000010 -#define MMCIF_CE_BLOCK_SET 0x00000014 -#define MMCIF_CE_CLK_CTRL 0x00000018 -#define MMCIF_CE_BUF_ACC 0x0000001C -#define MMCIF_CE_RESP3 0x00000020 -#define MMCIF_CE_RESP2 0x00000024 -#define MMCIF_CE_RESP1 0x00000028 -#define MMCIF_CE_RESP0 0x0000002C -#define MMCIF_CE_RESP_CMD12 0x00000030 -#define MMCIF_CE_DATA 0x00000034 -#define MMCIF_CE_INT 0x00000040 -#define MMCIF_CE_INT_MASK 0x00000044 -#define MMCIF_CE_HOST_STS1 0x00000048 -#define MMCIF_CE_HOST_STS2 0x0000004C -#define MMCIF_CE_CLK_CTRL2 0x00000070 -#define MMCIF_CE_VERSION 0x0000007C - -/* CE_BUF_ACC */ -#define BUF_ACC_DMAWEN (1 << 25) -#define BUF_ACC_DMAREN (1 << 24) -#define BUF_ACC_BUSW_32 (0 << 17) -#define BUF_ACC_BUSW_16 (1 << 17) -#define BUF_ACC_ATYP (1 << 16) - -/* CE_CLK_CTRL */ -#define CLK_ENABLE (1 << 24) /* 1: output mmc clock */ -#define CLK_CLEAR (0xf << 16) -#define CLK_SUP_PCLK (0xf << 16) -#define CLKDIV_4 (1 << 16) /* mmc clock frequency. - * n: bus clock/(2^(n+1)) */ -#define CLKDIV_256 (7 << 16) /* mmc clock frequency. (see above) */ -#define SRSPTO_256 (2 << 12) /* resp timeout */ -#define SRBSYTO_29 (0xf << 8) /* resp busy timeout */ -#define SRWDTO_29 (0xf << 4) /* read/write timeout */ -#define SCCSTO_29 (0xf << 0) /* ccs timeout */ - -/* CE_VERSION */ -#define SOFT_RST_ON (1 << 31) -#define SOFT_RST_OFF 0 - -static inline u32 sh_mmcif_readl(void __iomem *addr, int reg) -{ - return __raw_readl(addr + reg); -} - -static inline void sh_mmcif_writel(void __iomem *addr, int reg, u32 val) -{ - __raw_writel(val, addr + reg); -} - -#define SH_MMCIF_BBS 512 /* boot block size */ - -static inline void sh_mmcif_boot_cmd_send(void __iomem *base, - unsigned long cmd, unsigned long arg) -{ - sh_mmcif_writel(base, MMCIF_CE_INT, 0); - sh_mmcif_writel(base, MMCIF_CE_ARG, arg); - sh_mmcif_writel(base, MMCIF_CE_CMD_SET, cmd); -} - -static inline int sh_mmcif_boot_cmd_poll(void __iomem *base, unsigned long mask) -{ - unsigned long tmp; - int cnt; - - for (cnt = 0; cnt < 1000000; cnt++) { - tmp = sh_mmcif_readl(base, MMCIF_CE_INT); - if (tmp & mask) { - sh_mmcif_writel(base, MMCIF_CE_INT, tmp & ~mask); - return 0; - } - } - - return -1; -} - -static inline int sh_mmcif_boot_cmd(void __iomem *base, - unsigned long cmd, unsigned long arg) -{ - sh_mmcif_boot_cmd_send(base, cmd, arg); - return sh_mmcif_boot_cmd_poll(base, 0x00010000); -} - -static inline int sh_mmcif_boot_do_read_single(void __iomem *base, - unsigned int block_nr, - unsigned long *buf) -{ - int k; - - /* CMD13 - Status */ - sh_mmcif_boot_cmd(base, 0x0d400000, 0x00010000); - - if (sh_mmcif_readl(base, MMCIF_CE_RESP0) != 0x0900) - return -1; - - /* CMD17 - Read */ - sh_mmcif_boot_cmd(base, 0x11480000, block_nr * SH_MMCIF_BBS); - if (sh_mmcif_boot_cmd_poll(base, 0x00100000) < 0) - return -1; - - for (k = 0; k < (SH_MMCIF_BBS / 4); k++) - buf[k] = sh_mmcif_readl(base, MMCIF_CE_DATA); - - return 0; -} - -static inline int sh_mmcif_boot_do_read(void __iomem *base, - unsigned long first_block, - unsigned long nr_blocks, - void *buf) -{ - unsigned long k; - int ret = 0; - - /* In data transfer mode: Set clock to Bus clock/4 (about 20Mhz) */ - sh_mmcif_writel(base, MMCIF_CE_CLK_CTRL, - CLK_ENABLE | CLKDIV_4 | SRSPTO_256 | - SRBSYTO_29 | SRWDTO_29 | SCCSTO_29); - - /* CMD9 - Get CSD */ - sh_mmcif_boot_cmd(base, 0x09806000, 0x00010000); - - /* CMD7 - Select the card */ - sh_mmcif_boot_cmd(base, 0x07400000, 0x00010000); - - /* CMD16 - Set the block size */ - sh_mmcif_boot_cmd(base, 0x10400000, SH_MMCIF_BBS); - - for (k = 0; !ret && k < nr_blocks; k++) - ret = sh_mmcif_boot_do_read_single(base, first_block + k, - buf + (k * SH_MMCIF_BBS)); - - return ret; -} - -static inline void sh_mmcif_boot_init(void __iomem *base) -{ - /* reset */ - sh_mmcif_writel(base, MMCIF_CE_VERSION, SOFT_RST_ON); - sh_mmcif_writel(base, MMCIF_CE_VERSION, SOFT_RST_OFF); - - /* byte swap */ - sh_mmcif_writel(base, MMCIF_CE_BUF_ACC, BUF_ACC_ATYP); - - /* Set block size in MMCIF hardware */ - sh_mmcif_writel(base, MMCIF_CE_BLOCK_SET, SH_MMCIF_BBS); - - /* Enable the clock, set it to Bus clock/256 (about 325Khz). */ - sh_mmcif_writel(base, MMCIF_CE_CLK_CTRL, - CLK_ENABLE | CLKDIV_256 | SRSPTO_256 | - SRBSYTO_29 | SRWDTO_29 | SCCSTO_29); - - /* CMD0 */ - sh_mmcif_boot_cmd(base, 0x00000040, 0); - - /* CMD1 - Get OCR */ - do { - sh_mmcif_boot_cmd(base, 0x01405040, 0x40300000); /* CMD1 */ - } while ((sh_mmcif_readl(base, MMCIF_CE_RESP0) & 0x80000000) - != 0x80000000); - - /* CMD2 - Get CID */ - sh_mmcif_boot_cmd(base, 0x02806040, 0); - - /* CMD3 - Set card relative address */ - sh_mmcif_boot_cmd(base, 0x03400040, 0x00010000); -} - -#endif /* LINUX_MMC_SH_MMCIF_H */ diff --git a/include/linux/platform_data/sh_mmcif.h b/include/linux/platform_data/sh_mmcif.h new file mode 100644 index 000000000000..6eb914f958f9 --- /dev/null +++ b/include/linux/platform_data/sh_mmcif.h @@ -0,0 +1,207 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * platform data for eMMC driver + * + * Copyright (C) 2010 Renesas Solutions Corp. + */ + +#ifndef LINUX_MMC_SH_MMCIF_H +#define LINUX_MMC_SH_MMCIF_H + +#include +#include + +/* + * MMCIF : CE_CLK_CTRL [19:16] + * 1000 : Peripheral clock / 512 + * 0111 : Peripheral clock / 256 + * 0110 : Peripheral clock / 128 + * 0101 : Peripheral clock / 64 + * 0100 : Peripheral clock / 32 + * 0011 : Peripheral clock / 16 + * 0010 : Peripheral clock / 8 + * 0001 : Peripheral clock / 4 + * 0000 : Peripheral clock / 2 + * 1111 : Peripheral clock (sup_pclk set '1') + */ + +struct sh_mmcif_plat_data { + unsigned int slave_id_tx; /* embedded slave_id_[tr]x */ + unsigned int slave_id_rx; + u8 sup_pclk; /* 1 :SH7757, 0: SH7724/SH7372 */ + unsigned long caps; + u32 ocr; +}; + +#define MMCIF_CE_CMD_SET 0x00000000 +#define MMCIF_CE_ARG 0x00000008 +#define MMCIF_CE_ARG_CMD12 0x0000000C +#define MMCIF_CE_CMD_CTRL 0x00000010 +#define MMCIF_CE_BLOCK_SET 0x00000014 +#define MMCIF_CE_CLK_CTRL 0x00000018 +#define MMCIF_CE_BUF_ACC 0x0000001C +#define MMCIF_CE_RESP3 0x00000020 +#define MMCIF_CE_RESP2 0x00000024 +#define MMCIF_CE_RESP1 0x00000028 +#define MMCIF_CE_RESP0 0x0000002C +#define MMCIF_CE_RESP_CMD12 0x00000030 +#define MMCIF_CE_DATA 0x00000034 +#define MMCIF_CE_INT 0x00000040 +#define MMCIF_CE_INT_MASK 0x00000044 +#define MMCIF_CE_HOST_STS1 0x00000048 +#define MMCIF_CE_HOST_STS2 0x0000004C +#define MMCIF_CE_CLK_CTRL2 0x00000070 +#define MMCIF_CE_VERSION 0x0000007C + +/* CE_BUF_ACC */ +#define BUF_ACC_DMAWEN (1 << 25) +#define BUF_ACC_DMAREN (1 << 24) +#define BUF_ACC_BUSW_32 (0 << 17) +#define BUF_ACC_BUSW_16 (1 << 17) +#define BUF_ACC_ATYP (1 << 16) + +/* CE_CLK_CTRL */ +#define CLK_ENABLE (1 << 24) /* 1: output mmc clock */ +#define CLK_CLEAR (0xf << 16) +#define CLK_SUP_PCLK (0xf << 16) +#define CLKDIV_4 (1 << 16) /* mmc clock frequency. + * n: bus clock/(2^(n+1)) */ +#define CLKDIV_256 (7 << 16) /* mmc clock frequency. (see above) */ +#define SRSPTO_256 (2 << 12) /* resp timeout */ +#define SRBSYTO_29 (0xf << 8) /* resp busy timeout */ +#define SRWDTO_29 (0xf << 4) /* read/write timeout */ +#define SCCSTO_29 (0xf << 0) /* ccs timeout */ + +/* CE_VERSION */ +#define SOFT_RST_ON (1 << 31) +#define SOFT_RST_OFF 0 + +static inline u32 sh_mmcif_readl(void __iomem *addr, int reg) +{ + return __raw_readl(addr + reg); +} + +static inline void sh_mmcif_writel(void __iomem *addr, int reg, u32 val) +{ + __raw_writel(val, addr + reg); +} + +#define SH_MMCIF_BBS 512 /* boot block size */ + +static inline void sh_mmcif_boot_cmd_send(void __iomem *base, + unsigned long cmd, unsigned long arg) +{ + sh_mmcif_writel(base, MMCIF_CE_INT, 0); + sh_mmcif_writel(base, MMCIF_CE_ARG, arg); + sh_mmcif_writel(base, MMCIF_CE_CMD_SET, cmd); +} + +static inline int sh_mmcif_boot_cmd_poll(void __iomem *base, unsigned long mask) +{ + unsigned long tmp; + int cnt; + + for (cnt = 0; cnt < 1000000; cnt++) { + tmp = sh_mmcif_readl(base, MMCIF_CE_INT); + if (tmp & mask) { + sh_mmcif_writel(base, MMCIF_CE_INT, tmp & ~mask); + return 0; + } + } + + return -1; +} + +static inline int sh_mmcif_boot_cmd(void __iomem *base, + unsigned long cmd, unsigned long arg) +{ + sh_mmcif_boot_cmd_send(base, cmd, arg); + return sh_mmcif_boot_cmd_poll(base, 0x00010000); +} + +static inline int sh_mmcif_boot_do_read_single(void __iomem *base, + unsigned int block_nr, + unsigned long *buf) +{ + int k; + + /* CMD13 - Status */ + sh_mmcif_boot_cmd(base, 0x0d400000, 0x00010000); + + if (sh_mmcif_readl(base, MMCIF_CE_RESP0) != 0x0900) + return -1; + + /* CMD17 - Read */ + sh_mmcif_boot_cmd(base, 0x11480000, block_nr * SH_MMCIF_BBS); + if (sh_mmcif_boot_cmd_poll(base, 0x00100000) < 0) + return -1; + + for (k = 0; k < (SH_MMCIF_BBS / 4); k++) + buf[k] = sh_mmcif_readl(base, MMCIF_CE_DATA); + + return 0; +} + +static inline int sh_mmcif_boot_do_read(void __iomem *base, + unsigned long first_block, + unsigned long nr_blocks, + void *buf) +{ + unsigned long k; + int ret = 0; + + /* In data transfer mode: Set clock to Bus clock/4 (about 20Mhz) */ + sh_mmcif_writel(base, MMCIF_CE_CLK_CTRL, + CLK_ENABLE | CLKDIV_4 | SRSPTO_256 | + SRBSYTO_29 | SRWDTO_29 | SCCSTO_29); + + /* CMD9 - Get CSD */ + sh_mmcif_boot_cmd(base, 0x09806000, 0x00010000); + + /* CMD7 - Select the card */ + sh_mmcif_boot_cmd(base, 0x07400000, 0x00010000); + + /* CMD16 - Set the block size */ + sh_mmcif_boot_cmd(base, 0x10400000, SH_MMCIF_BBS); + + for (k = 0; !ret && k < nr_blocks; k++) + ret = sh_mmcif_boot_do_read_single(base, first_block + k, + buf + (k * SH_MMCIF_BBS)); + + return ret; +} + +static inline void sh_mmcif_boot_init(void __iomem *base) +{ + /* reset */ + sh_mmcif_writel(base, MMCIF_CE_VERSION, SOFT_RST_ON); + sh_mmcif_writel(base, MMCIF_CE_VERSION, SOFT_RST_OFF); + + /* byte swap */ + sh_mmcif_writel(base, MMCIF_CE_BUF_ACC, BUF_ACC_ATYP); + + /* Set block size in MMCIF hardware */ + sh_mmcif_writel(base, MMCIF_CE_BLOCK_SET, SH_MMCIF_BBS); + + /* Enable the clock, set it to Bus clock/256 (about 325Khz). */ + sh_mmcif_writel(base, MMCIF_CE_CLK_CTRL, + CLK_ENABLE | CLKDIV_256 | SRSPTO_256 | + SRBSYTO_29 | SRWDTO_29 | SCCSTO_29); + + /* CMD0 */ + sh_mmcif_boot_cmd(base, 0x00000040, 0); + + /* CMD1 - Get OCR */ + do { + sh_mmcif_boot_cmd(base, 0x01405040, 0x40300000); /* CMD1 */ + } while ((sh_mmcif_readl(base, MMCIF_CE_RESP0) & 0x80000000) + != 0x80000000); + + /* CMD2 - Get CID */ + sh_mmcif_boot_cmd(base, 0x02806040, 0); + + /* CMD3 - Set card relative address */ + sh_mmcif_boot_cmd(base, 0x03400040, 0x00010000); +} + +#endif /* LINUX_MMC_SH_MMCIF_H */ -- cgit v1.2.3 From 8e274732115f63c1d09136284431b3555bd5cc56 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Mon, 25 Apr 2022 23:04:28 +0206 Subject: printk: extend console_lock for per-console locking Currently threaded console printers synchronize against each other using console_lock(). However, different console drivers are unrelated and do not require any synchronization between each other. Removing the synchronization between the threaded console printers will allow each console to print at its own speed. But the threaded consoles printers do still need to synchronize against console_lock() callers. Introduce a per-console mutex and a new console boolean field @blocked to provide this synchronization. console_lock() is modified so that it must acquire the mutex of each console in order to set the @blocked field. Console printing threads will acquire their mutex while printing a record. If @blocked was set, the thread will go back to sleep instead of printing. The reason for the @blocked boolean field is so that console_lock() callers do not need to acquire multiple console mutexes simultaneously, which would introduce unnecessary complexity due to nested mutex locking. Also, a new field was chosen instead of adding a new @flags value so that the blocked status could be checked without concern of reading inconsistent values due to @flags updates from other contexts. Threaded console printers also need to synchronize against console_trylock() callers. Since console_trylock() may be called from any context, the per-console mutex cannot be used for this synchronization. (mutex_trylock() cannot be called from atomic contexts.) Introduce a global atomic counter to identify if any threaded printers are active. The threaded printers will also check the atomic counter to identify if the console has been locked by another task via console_trylock(). Note that @console_sem is still used to provide synchronization between console_lock() and console_trylock() callers. A locking overview for console_lock(), console_trylock(), and the threaded printers is as follows (pseudo code): console_lock() { down(&console_sem); for_each_console(con) { mutex_lock(&con->lock); con->blocked = true; mutex_unlock(&con->lock); } /* console_lock acquired */ } console_trylock() { if (down_trylock(&console_sem) == 0) { if (atomic_cmpxchg(&console_kthreads_active, 0, -1) == 0) { /* console_lock acquired */ } } } threaded_printer() { mutex_lock(&con->lock); if (!con->blocked) { /* console_lock() callers blocked */ if (atomic_inc_unless_negative(&console_kthreads_active)) { /* console_trylock() callers blocked */ con->write(); atomic_dec(&console_lock_count); } } mutex_unlock(&con->lock); } The console owner and waiter logic now only applies between contexts that have taken the console_lock via console_trylock(). Threaded printers never take the console_lock, so they do not have a console_lock to handover. Tasks that have used console_lock() will block the threaded printers using a mutex and if the console_lock is handed over to an atomic context, it would be unable to unblock the threaded printers. However, the console_trylock() case is really the only scenario that is interesting for handovers anyway. @panic_console_dropped must change to atomic_t since it is no longer protected exclusively by the console_lock. Since threaded printers remain asleep if they see that the console is locked, they now must be explicitly woken in __console_unlock(). This means wake_up_klogd() calls following a console_unlock() are no longer necessary and are removed. Also note that threaded printers no longer need to check @console_suspended. The check for the @blocked field implicitly covers the suspended console case. Signed-off-by: John Ogness Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/878rrs6ft7.fsf@jogness.linutronix.de --- include/linux/console.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/console.h b/include/linux/console.h index 9a251e70c090..143653090c48 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -16,6 +16,7 @@ #include #include +#include struct vc_data; struct console_font_op; @@ -154,6 +155,20 @@ struct console { u64 seq; unsigned long dropped; struct task_struct *thread; + bool blocked; + + /* + * The per-console lock is used by printing kthreads to synchronize + * this console with callers of console_lock(). This is necessary in + * order to allow printing kthreads to run in parallel to each other, + * while each safely accessing the @blocked field and synchronizing + * against direct printing via console_lock/console_unlock. + * + * Note: For synchronizing against direct printing via + * console_trylock/console_unlock, see the static global + * variable @console_kthreads_active. + */ + struct mutex lock; void *data; struct console *next; -- cgit v1.2.3 From cc51eaa8b530bf070e76847a717adcbf603469b7 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Tue, 26 Apr 2022 01:29:04 -0700 Subject: io_uring: add type to op enum It is useful to have a type enum for opcodes, to allow the compiler to assert that every value is used in a switch statement. Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220426082907.3600028-2-dylany@fb.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 5fb52bf32435..49d1f3994f8d 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -105,7 +105,7 @@ enum { #define IORING_SETUP_R_DISABLED (1U << 6) /* start with ring disabled */ #define IORING_SETUP_SUBMIT_ALL (1U << 7) /* continue submit on error */ -enum { +enum io_uring_op { IORING_OP_NOP, IORING_OP_READV, IORING_OP_WRITEV, -- cgit v1.2.3 From 33337d03f04f9ea3a50ac2d3490a5d7a3ba9be82 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Tue, 26 Apr 2022 01:29:05 -0700 Subject: io_uring: add io_uring_get_opcode In some debug scenarios it is useful to have the text representation of the opcode. Add this function in preparation. Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220426082907.3600028-3-dylany@fb.com Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 1814e698d861..24651c229ed2 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -10,6 +10,7 @@ struct sock *io_uring_get_socket(struct file *file); void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); void io_uring_unreg_ringfd(void); +const char *io_uring_get_opcode(u8 opcode); static inline void io_uring_files_cancel(void) { @@ -42,6 +43,10 @@ static inline void io_uring_files_cancel(void) static inline void io_uring_free(struct task_struct *tsk) { } +static inline const char *io_uring_get_opcode(u8 opcode) +{ + return ""; +} #endif #endif -- cgit v1.2.3 From 1460af7de6ab33da82b8a1f03ce0f8e831a9e29e Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Tue, 26 Apr 2022 01:29:06 -0700 Subject: io_uring: rename op -> opcode do this for consistency with the other trace messages Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220426082907.3600028-4-dylany@fb.com Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 05b786f8b0bf..42c7e1a3c6ae 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -530,7 +530,7 @@ TRACE_EVENT(io_uring_req_failed, ), TP_printk("ring %p, req %p, user_data 0x%llx, " - "op %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, " + "opcode %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, " "len=%u, rw_flags=0x%x, buf_index=%d, " "personality=%d, file_index=%d, pad=0x%llx, addr3=%llx, " "error=%d", -- cgit v1.2.3 From 54c861f930180e096483a6e1744c9c4b76e20da5 Mon Sep 17 00:00:00 2001 From: Daniel Ammann Date: Tue, 5 Apr 2022 14:54:25 +0200 Subject: mfd: tps65218: Fix trivial typo in comment The driver is for TPS65218, not TPS65219. Signed-off-by: Daniel Ammann Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20220405125426.28016-1-daniel.ammann@bytesatwork.ch --- include/linux/mfd/tps65218.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mfd/tps65218.h b/include/linux/mfd/tps65218.h index f4ca367e3473..122e24ddbd4b 100644 --- a/include/linux/mfd/tps65218.h +++ b/include/linux/mfd/tps65218.h @@ -1,7 +1,7 @@ /* * linux/mfd/tps65218.h * - * Functions to access TPS65219 power management chip. + * Functions to access TPS65218 power management chip. * * Copyright (C) 2014 Texas Instruments Incorporated - https://www.ti.com/ * -- cgit v1.2.3 From 7f5aaa4a0ae6948eace6cf30f40a3ec27ece8441 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ma=C3=ADra=20Canal?= Date: Wed, 6 Apr 2022 11:40:41 -0300 Subject: mfd: hi655x-pmic: Replace legacy gpio interface for gpiod interface MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Considering the current transition of the GPIO subsystem, remove all dependencies of the legacy GPIO interface (linux/gpio.h and linux /of_gpio.h) and replace it with the descriptor-based GPIO approach. Signed-off-by: Maíra Canal Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/Yk2maZuf+5FGL+eg@fedora --- include/linux/mfd/hi655x-pmic.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mfd/hi655x-pmic.h b/include/linux/mfd/hi655x-pmic.h index af5d97239c0d..6a012784dd1b 100644 --- a/include/linux/mfd/hi655x-pmic.h +++ b/include/linux/mfd/hi655x-pmic.h @@ -12,6 +12,8 @@ #ifndef __HI655X_PMIC_H #define __HI655X_PMIC_H +#include + /* Hi655x registers are mapped to memory bus in 4 bytes stride */ #define HI655X_STRIDE 4 #define HI655X_BUS_ADDR(x) ((x) << 2) @@ -53,7 +55,7 @@ struct hi655x_pmic { struct resource *res; struct device *dev; struct regmap *regmap; - int gpio; + struct gpio_desc *gpio; unsigned int ver; struct regmap_irq_chip_data *irq_data; }; -- cgit v1.2.3 From ba3beec2ec1d3b4fd8672ca6e781dac4b3267f6e Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Mon, 25 Apr 2022 17:37:45 +0200 Subject: xsk: Fix possible crash when multiple sockets are created Fix a crash that happens if an Rx only socket is created first, then a second socket is created that is Tx only and bound to the same umem as the first socket and also the same netdev and queue_id together with the XDP_SHARED_UMEM flag. In this specific case, the tx_descs array page pool was not created by the first socket as it was an Rx only socket. When the second socket is bound it needs this tx_descs array of this shared page pool as it has a Tx component, but unfortunately it was never allocated, leading to a crash. Note that this array is only used for zero-copy drivers using the batched Tx APIs, currently only ice and i40e. [ 5511.150360] BUG: kernel NULL pointer dereference, address: 0000000000000008 [ 5511.158419] #PF: supervisor write access in kernel mode [ 5511.164472] #PF: error_code(0x0002) - not-present page [ 5511.170416] PGD 0 P4D 0 [ 5511.173347] Oops: 0002 [#1] PREEMPT SMP PTI [ 5511.178186] CPU: 0 PID: 0 Comm: swapper/0 Tainted: G E 5.18.0-rc1+ #97 [ 5511.187245] Hardware name: Intel Corp. GRANTLEY/GRANTLEY, BIOS GRRFCRB1.86B.0276.D07.1605190235 05/19/2016 [ 5511.198418] RIP: 0010:xsk_tx_peek_release_desc_batch+0x198/0x310 [ 5511.205375] Code: c0 83 c6 01 84 c2 74 6d 8d 46 ff 23 07 44 89 e1 48 83 c0 14 48 c1 e1 04 48 c1 e0 04 48 03 47 10 4c 01 c1 48 8b 50 08 48 8b 00 <48> 89 51 08 48 89 01 41 80 bd d7 00 00 00 00 75 82 48 8b 19 49 8b [ 5511.227091] RSP: 0018:ffffc90000003dd0 EFLAGS: 00010246 [ 5511.233135] RAX: 0000000000000000 RBX: ffff88810c8da600 RCX: 0000000000000000 [ 5511.241384] RDX: 000000000000003c RSI: 0000000000000001 RDI: ffff888115f555c0 [ 5511.249634] RBP: ffffc90000003e08 R08: 0000000000000000 R09: ffff889092296b48 [ 5511.257886] R10: 0000ffffffffffff R11: ffff889092296800 R12: 0000000000000000 [ 5511.266138] R13: ffff88810c8db500 R14: 0000000000000040 R15: 0000000000000100 [ 5511.274387] FS: 0000000000000000(0000) GS:ffff88903f800000(0000) knlGS:0000000000000000 [ 5511.283746] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 5511.290389] CR2: 0000000000000008 CR3: 00000001046e2001 CR4: 00000000003706f0 [ 5511.298640] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 5511.306892] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 5511.315142] Call Trace: [ 5511.317972] [ 5511.320301] ice_xmit_zc+0x68/0x2f0 [ice] [ 5511.324977] ? ktime_get+0x38/0xa0 [ 5511.328913] ice_napi_poll+0x7a/0x6a0 [ice] [ 5511.333784] __napi_poll+0x2c/0x160 [ 5511.337821] net_rx_action+0xdd/0x200 [ 5511.342058] __do_softirq+0xe6/0x2dd [ 5511.346198] irq_exit_rcu+0xb5/0x100 [ 5511.350339] common_interrupt+0xa4/0xc0 [ 5511.354777] [ 5511.357201] [ 5511.359625] asm_common_interrupt+0x1e/0x40 [ 5511.364466] RIP: 0010:cpuidle_enter_state+0xd2/0x360 [ 5511.370211] Code: 49 89 c5 0f 1f 44 00 00 31 ff e8 e9 00 7b ff 45 84 ff 74 12 9c 58 f6 c4 02 0f 85 72 02 00 00 31 ff e8 02 0c 80 ff fb 45 85 f6 <0f> 88 11 01 00 00 49 63 c6 4c 2b 2c 24 48 8d 14 40 48 8d 14 90 49 [ 5511.391921] RSP: 0018:ffffffff82a03e60 EFLAGS: 00000202 [ 5511.397962] RAX: ffff88903f800000 RBX: 0000000000000001 RCX: 000000000000001f [ 5511.406214] RDX: 0000000000000000 RSI: ffffffff823400b9 RDI: ffffffff8234c046 [ 5511.424646] RBP: ffff88810a384800 R08: 000005032a28c046 R09: 0000000000000008 [ 5511.443233] R10: 000000000000000b R11: 0000000000000006 R12: ffffffff82bcf700 [ 5511.461922] R13: 000005032a28c046 R14: 0000000000000001 R15: 0000000000000000 [ 5511.480300] cpuidle_enter+0x29/0x40 [ 5511.494329] do_idle+0x1c7/0x250 [ 5511.507610] cpu_startup_entry+0x19/0x20 [ 5511.521394] start_kernel+0x649/0x66e [ 5511.534626] secondary_startup_64_no_verify+0xc3/0xcb [ 5511.549230] Detect such case during bind() and allocate this memory region via newly introduced xp_alloc_tx_descs(). Also, use kvcalloc instead of kcalloc as for other buffer pool allocations, so that it matches the kvfree() from xp_destroy(). Fixes: d1bc532e99be ("i40e: xsk: Move tmp desc array from driver to pool") Signed-off-by: Maciej Fijalkowski Signed-off-by: Daniel Borkmann Acked-by: Magnus Karlsson Link: https://lore.kernel.org/bpf/20220425153745.481322-1-maciej.fijalkowski@intel.com --- include/net/xsk_buff_pool.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 5554ee75e7da..647722e847b4 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -97,6 +97,7 @@ int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev, u16 queue_id, u16 flags); int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem, struct net_device *dev, u16 queue_id); +int xp_alloc_tx_descs(struct xsk_buff_pool *pool, struct xdp_sock *xs); void xp_destroy(struct xsk_buff_pool *pool); void xp_get_pool(struct xsk_buff_pool *pool); bool xp_put_pool(struct xsk_buff_pool *pool); -- cgit v1.2.3 From 54db804d5d7d36709d1ce70bde3b9a6c61b290b6 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 3 Mar 2022 17:55:21 -0600 Subject: scsi: fcoe: Fix Wstringop-overflow warnings in fcoe_wwn_from_mac() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the following Wstringop-overflow warnings when building with GCC-11: drivers/scsi/fcoe/fcoe.c: In function ‘fcoe_netdev_config’: drivers/scsi/fcoe/fcoe.c:744:32: warning: ‘fcoe_wwn_from_mac’ accessing 32 bytes in a region of size 6 [-Wstringop-overflow=] 744 | wwnn = fcoe_wwn_from_mac(ctlr->ctl_src_addr, 1, 0); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/scsi/fcoe/fcoe.c:744:32: note: referencing argument 1 of type ‘unsigned char *’ In file included from drivers/scsi/fcoe/fcoe.c:36: ./include/scsi/libfcoe.h:252:5: note: in a call to function ‘fcoe_wwn_from_mac’ 252 | u64 fcoe_wwn_from_mac(unsigned char mac[MAX_ADDR_LEN], unsigned int, unsigned int); | ^~~~~~~~~~~~~~~~~ drivers/scsi/fcoe/fcoe.c:747:32: warning: ‘fcoe_wwn_from_mac’ accessing 32 bytes in a region of size 6 [-Wstringop-overflow=] 747 | wwpn = fcoe_wwn_from_mac(ctlr->ctl_src_addr, | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 748 | 2, 0); | ~~~~~ drivers/scsi/fcoe/fcoe.c:747:32: note: referencing argument 1 of type ‘unsigned char *’ In file included from drivers/scsi/fcoe/fcoe.c:36: ./include/scsi/libfcoe.h:252:5: note: in a call to function ‘fcoe_wwn_from_mac’ 252 | u64 fcoe_wwn_from_mac(unsigned char mac[MAX_ADDR_LEN], unsigned int, unsigned int); | ^~~~~~~~~~~~~~~~~ CC drivers/scsi/bnx2fc/bnx2fc_io.o In function ‘bnx2fc_net_config’, inlined from ‘bnx2fc_if_create’ at drivers/scsi/bnx2fc/bnx2fc_fcoe.c:1543:7: drivers/scsi/bnx2fc/bnx2fc_fcoe.c:833:32: warning: ‘fcoe_wwn_from_mac’ accessing 32 bytes in a region of size 6 [-Wstringop-overflow=] 833 | wwnn = fcoe_wwn_from_mac(ctlr->ctl_src_addr, | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 834 | 1, 0); | ~~~~~ drivers/scsi/bnx2fc/bnx2fc_fcoe.c: In function ‘bnx2fc_if_create’: drivers/scsi/bnx2fc/bnx2fc_fcoe.c:833:32: note: referencing argument 1 of type ‘unsigned char *’ In file included from drivers/scsi/bnx2fc/bnx2fc.h:53, from drivers/scsi/bnx2fc/bnx2fc_fcoe.c:17: ./include/scsi/libfcoe.h:252:5: note: in a call to function ‘fcoe_wwn_from_mac’ 252 | u64 fcoe_wwn_from_mac(unsigned char mac[MAX_ADDR_LEN], unsigned int, unsigned int); | ^~~~~~~~~~~~~~~~~ In function ‘bnx2fc_net_config’, inlined from ‘bnx2fc_if_create’ at drivers/scsi/bnx2fc/bnx2fc_fcoe.c:1543:7: drivers/scsi/bnx2fc/bnx2fc_fcoe.c:839:32: warning: ‘fcoe_wwn_from_mac’ accessing 32 bytes in a region of size 6 [-Wstringop-overflow=] 839 | wwpn = fcoe_wwn_from_mac(ctlr->ctl_src_addr, | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 840 | 2, 0); | ~~~~~ drivers/scsi/bnx2fc/bnx2fc_fcoe.c: In function ‘bnx2fc_if_create’: drivers/scsi/bnx2fc/bnx2fc_fcoe.c:839:32: note: referencing argument 1 of type ‘unsigned char *’ In file included from drivers/scsi/bnx2fc/bnx2fc.h:53, from drivers/scsi/bnx2fc/bnx2fc_fcoe.c:17: ./include/scsi/libfcoe.h:252:5: note: in a call to function ‘fcoe_wwn_from_mac’ 252 | u64 fcoe_wwn_from_mac(unsigned char mac[MAX_ADDR_LEN], unsigned int, unsigned int); | ^~~~~~~~~~~~~~~~~ drivers/scsi/qedf/qedf_main.c: In function ‘__qedf_probe’: drivers/scsi/qedf/qedf_main.c:3520:30: warning: ‘fcoe_wwn_from_mac’ accessing 32 bytes in a region of size 6 [-Wstringop-overflow=] 3520 | qedf->wwnn = fcoe_wwn_from_mac(qedf->mac, 1, 0); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/scsi/qedf/qedf_main.c:3520:30: note: referencing argument 1 of type ‘unsigned char *’ In file included from drivers/scsi/qedf/qedf.h:9, from drivers/scsi/qedf/qedf_main.c:23: ./include/scsi/libfcoe.h:252:5: note: in a call to function ‘fcoe_wwn_from_mac’ 252 | u64 fcoe_wwn_from_mac(unsigned char mac[MAX_ADDR_LEN], unsigned int, unsigned int); | ^~~~~~~~~~~~~~~~~ drivers/scsi/qedf/qedf_main.c:3521:30: warning: ‘fcoe_wwn_from_mac’ accessing 32 bytes in a region of size 6 [-Wstringop-overflow=] 3521 | qedf->wwpn = fcoe_wwn_from_mac(qedf->mac, 2, 0); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/scsi/qedf/qedf_main.c:3521:30: note: referencing argument 1 of type ‘unsigned char *’ In file included from drivers/scsi/qedf/qedf.h:9, from drivers/scsi/qedf/qedf_main.c:23: ./include/scsi/libfcoe.h:252:5: note: in a call to function ‘fcoe_wwn_from_mac’ 252 | u64 fcoe_wwn_from_mac(unsigned char mac[MAX_ADDR_LEN], unsigned int, unsigned int); | ^~~~~~~~~~~~~~~~~ by changing the array size to the correct value of ETH_ALEN in the argument declaration. Also, fix a couple of checkpatch warnings: WARNING: function definition argument 'unsigned int' should also have an identifier name This helps with the ongoing efforts to globally enable -Wstringop-overflow. Link: https://github.com/KSPP/linux/issues/181 Fixes: 85b4aa4926a5 ("[SCSI] fcoe: Fibre Channel over Ethernet") Signed-off-by: Gustavo A. R. Silva --- include/scsi/libfcoe.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/scsi/libfcoe.h b/include/scsi/libfcoe.h index fac8e89aed81..310e0dbffda9 100644 --- a/include/scsi/libfcoe.h +++ b/include/scsi/libfcoe.h @@ -249,7 +249,8 @@ int fcoe_ctlr_recv_flogi(struct fcoe_ctlr *, struct fc_lport *, struct fc_frame *); /* libfcoe funcs */ -u64 fcoe_wwn_from_mac(unsigned char mac[MAX_ADDR_LEN], unsigned int, unsigned int); +u64 fcoe_wwn_from_mac(unsigned char mac[ETH_ALEN], unsigned int scheme, + unsigned int port); int fcoe_libfc_config(struct fc_lport *, struct fcoe_ctlr *, const struct libfc_function_template *, int init_fcp); u32 fcoe_fc_crc(struct fc_frame *fp); -- cgit v1.2.3 From c86cc5a3ec70f5644f1fa21610b943d0441bc1f7 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Fri, 22 Apr 2022 12:58:16 -0700 Subject: Bluetooth: hci_event: Fix checking for invalid handle on error status Commit d5ebaa7c5f6f6 introduces checks for handle range (e.g HCI_CONN_HANDLE_MAX) but controllers like Intel AX200 don't seem to respect the valid range int case of error status: > HCI Event: Connect Complete (0x03) plen 11 Status: Page Timeout (0x04) Handle: 65535 Address: 94:DB:56:XX:XX:XX (Sony Home Entertainment& Sound Products Inc) Link type: ACL (0x01) Encryption: Disabled (0x00) [1644965.827560] Bluetooth: hci0: Ignoring HCI_Connection_Complete for invalid handle Because of it is impossible to cleanup the connections properly since the stack would attempt to cancel the connection which is no longer in progress causing the following trace: < HCI Command: Create Connection Cancel (0x01|0x0008) plen 6 Address: 94:DB:56:XX:XX:XX (Sony Home Entertainment& Sound Products Inc) = bluetoothd: src/profile.c:record_cb() Unable to get Hands-Free Voice gateway SDP record: Connection timed out > HCI Event: Command Complete (0x0e) plen 10 Create Connection Cancel (0x01|0x0008) ncmd 1 Status: Unknown Connection Identifier (0x02) Address: 94:DB:56:XX:XX:XX (Sony Home Entertainment& Sound Products Inc) < HCI Command: Create Connection Cancel (0x01|0x0008) plen 6 Address: 94:DB:56:XX:XX:XX (Sony Home Entertainment& Sound Products Inc) Fixes: d5ebaa7c5f6f6 ("Bluetooth: hci_event: Ignore multiple conn complete events") Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 5cb095b09a94..69ef31cea582 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -578,6 +578,7 @@ enum { #define HCI_ERROR_CONNECTION_TIMEOUT 0x08 #define HCI_ERROR_REJ_LIMITED_RESOURCES 0x0d #define HCI_ERROR_REJ_BAD_ADDR 0x0f +#define HCI_ERROR_INVALID_PARAMETERS 0x12 #define HCI_ERROR_REMOTE_USER_TERM 0x13 #define HCI_ERROR_REMOTE_LOW_RESOURCES 0x14 #define HCI_ERROR_REMOTE_POWER_OFF 0x15 -- cgit v1.2.3 From 9b3628d79b46f06157affc56fdb218fdd4988321 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Fri, 22 Apr 2022 12:58:18 -0700 Subject: Bluetooth: hci_sync: Cleanup hci_conn if it cannot be aborted This attempts to cleanup the hci_conn if it cannot be aborted as otherwise it would likely result in having the controller and host stack out of sync with respect to connection handle. Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index d5377740e99c..8abd08245326 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1156,7 +1156,7 @@ int hci_conn_switch_role(struct hci_conn *conn, __u8 role); void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active); -void hci_le_conn_failed(struct hci_conn *conn, u8 status); +void hci_conn_failed(struct hci_conn *conn, u8 status); /* * hci_conn_get() and hci_conn_put() are used to control the life-time of an -- cgit v1.2.3 From 82028ba4d590c4e9eb3c93326019db7c26d02e35 Mon Sep 17 00:00:00 2001 From: Fabien Parent Date: Fri, 15 Apr 2022 17:36:24 +0200 Subject: mfd: mt6359: Add missing defines necessary for mtk-pmic-keys support Add 2 missing MT6359 registers that are needed to implement the keyboard driver. Signed-off-by: Fabien Parent Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20220415153629.1817202-3-fparent@baylibre.com --- include/linux/mfd/mt6359/registers.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/mt6359/registers.h b/include/linux/mfd/mt6359/registers.h index 2135c9695918..2a4394a27b1c 100644 --- a/include/linux/mfd/mt6359/registers.h +++ b/include/linux/mfd/mt6359/registers.h @@ -8,6 +8,8 @@ /* PMIC Registers */ #define MT6359_SWCID 0xa +#define MT6359_TOPSTATUS 0x2a +#define MT6359_TOP_RST_MISC 0x14c #define MT6359_MISC_TOP_INT_CON0 0x188 #define MT6359_MISC_TOP_INT_STATUS0 0x194 #define MT6359_TOP_INT_STATUS0 0x19e -- cgit v1.2.3 From c317ab71facc2cd0a94145973318a4c914e11acc Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Mon, 25 Apr 2022 21:32:47 +0800 Subject: bpf: Compute map_btf_id during build time For now, the field 'map_btf_id' in 'struct bpf_map_ops' for all map types are computed during vmlinux-btf init: btf_parse_vmlinux() -> btf_vmlinux_map_ids_init() It will lookup the btf_type according to the 'map_btf_name' field in 'struct bpf_map_ops'. This process can be done during build time, thanks to Jiri's resolve_btfids. selftest of map_ptr has passed: $96 map_ptr:OK Summary: 1/0 PASSED, 0 SKIPPED, 0 FAILED Reported-by: kernel test robot Signed-off-by: Menglong Dong Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0af5793ba417..be94833d390a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -148,8 +148,7 @@ struct bpf_map_ops { bpf_callback_t callback_fn, void *callback_ctx, u64 flags); - /* BTF name and id of struct allocated by map_alloc */ - const char * const map_btf_name; + /* BTF id of struct allocated by map_alloc */ int *map_btf_id; /* bpf_iter info used to open a seq_file */ -- cgit v1.2.3 From 9f79b8b7233942e9c4b071f1f331f17e7282bbfa Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 5 Apr 2022 15:12:55 +0800 Subject: uapi: simplify __ARCH_FLOCK{,64}_PAD a little Don't bother to define the symbols empty, just don't use them. That makes the intent a little more clear. Remove the unused HAVE_ARCH_STRUCT_FLOCK64 define and merge the 32-bit mips struct flock into the generic one. Add a new __ARCH_FLOCK_EXTRA_SYSID macro following the style of __ARCH_FLOCK_PAD to avoid having a separate definition just for one architecture. Signed-off-by: Christoph Hellwig Signed-off-by: Guo Ren Reviewed-by: Arnd Bergmann Tested-by: Heiko Stuebner Link: https://lore.kernel.org/r/20220405071314.3225832-2-guoren@kernel.org Signed-off-by: Palmer Dabbelt --- include/uapi/asm-generic/fcntl.h | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h index ecd0f5bdfc1d..77aa9f2ff98d 100644 --- a/include/uapi/asm-generic/fcntl.h +++ b/include/uapi/asm-generic/fcntl.h @@ -192,25 +192,19 @@ struct f_owner_ex { #define F_LINUX_SPECIFIC_BASE 1024 -#ifndef HAVE_ARCH_STRUCT_FLOCK -#ifndef __ARCH_FLOCK_PAD -#define __ARCH_FLOCK_PAD -#endif - struct flock { short l_type; short l_whence; __kernel_off_t l_start; __kernel_off_t l_len; __kernel_pid_t l_pid; - __ARCH_FLOCK_PAD -}; +#ifdef __ARCH_FLOCK_EXTRA_SYSID + __ARCH_FLOCK_EXTRA_SYSID #endif - -#ifndef HAVE_ARCH_STRUCT_FLOCK64 -#ifndef __ARCH_FLOCK64_PAD -#define __ARCH_FLOCK64_PAD +#ifdef __ARCH_FLOCK_PAD + __ARCH_FLOCK_PAD #endif +}; struct flock64 { short l_type; @@ -218,8 +212,9 @@ struct flock64 { __kernel_loff_t l_start; __kernel_loff_t l_len; __kernel_pid_t l_pid; +#ifdef __ARCH_FLOCK64_PAD __ARCH_FLOCK64_PAD -}; #endif +}; #endif /* _ASM_GENERIC_FCNTL_H */ -- cgit v1.2.3 From 306f7cc1e9061313c46d19e9bdffc819880794c1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 5 Apr 2022 15:12:56 +0800 Subject: uapi: always define F_GETLK64/F_SETLK64/F_SETLKW64 in fcntl.h The F_GETLK64/F_SETLK64/F_SETLKW64 fcntl opcodes are only implemented for the 32-bit syscall APIs, but are also needed for compat handling on 64-bit kernels. Consolidate them in unistd.h instead of definining the internal compat definitions in compat.h, which is rather error prone (e.g. parisc gets the values wrong currently). Note that before this change they were never visible to userspace due to the fact that CONFIG_64BIT is only set for kernel builds. Signed-off-by: Christoph Hellwig Signed-off-by: Guo Ren Reviewed-by: Arnd Bergmann Tested-by: Heiko Stuebner Link: https://lore.kernel.org/r/20220405071314.3225832-3-guoren@kernel.org Signed-off-by: Palmer Dabbelt --- include/uapi/asm-generic/fcntl.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h index 77aa9f2ff98d..f13d37b60775 100644 --- a/include/uapi/asm-generic/fcntl.h +++ b/include/uapi/asm-generic/fcntl.h @@ -116,13 +116,13 @@ #define F_GETSIG 11 /* for sockets. */ #endif -#ifndef CONFIG_64BIT +#if __BITS_PER_LONG == 32 || defined(__KERNEL__) #ifndef F_GETLK64 #define F_GETLK64 12 /* using 'struct flock64' */ #define F_SETLK64 13 #define F_SETLKW64 14 #endif -#endif +#endif /* __BITS_PER_LONG == 32 || defined(__KERNEL__) */ #ifndef F_SETOWN_EX #define F_SETOWN_EX 15 -- cgit v1.2.3 From 3ce0f2373f7073f04715b1ffd7b1812d3183f79a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 5 Apr 2022 15:12:57 +0800 Subject: compat: consolidate the compat_flock{,64} definition Provide a single common definition for the compat_flock and compat_flock64 structures using the same tricks as for the native variants. Another extra define is added for the packing required on x86. Signed-off-by: Christoph Hellwig Signed-off-by: Guo Ren Reviewed-by: Arnd Bergmann Tested-by: Heiko Stuebner Acked-by: Helge Deller # parisc Link: https://lore.kernel.org/r/20220405071314.3225832-4-guoren@kernel.org Signed-off-by: Palmer Dabbelt --- include/linux/compat.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include') diff --git a/include/linux/compat.h b/include/linux/compat.h index 1c758b0e0359..a0481fe6c5d5 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -258,6 +258,37 @@ struct compat_rlimit { compat_ulong_t rlim_max; }; +#ifdef __ARCH_NEED_COMPAT_FLOCK64_PACKED +#define __ARCH_COMPAT_FLOCK64_PACK __attribute__((packed)) +#else +#define __ARCH_COMPAT_FLOCK64_PACK +#endif + +struct compat_flock { + short l_type; + short l_whence; + compat_off_t l_start; + compat_off_t l_len; +#ifdef __ARCH_COMPAT_FLOCK_EXTRA_SYSID + __ARCH_COMPAT_FLOCK_EXTRA_SYSID +#endif + compat_pid_t l_pid; +#ifdef __ARCH_COMPAT_FLOCK_PAD + __ARCH_COMPAT_FLOCK_PAD +#endif +}; + +struct compat_flock64 { + short l_type; + short l_whence; + compat_loff_t l_start; + compat_loff_t l_len; + compat_pid_t l_pid; +#ifdef __ARCH_COMPAT_FLOCK64_PAD + __ARCH_COMPAT_FLOCK64_PAD +#endif +} __ARCH_COMPAT_FLOCK64_PACK; + struct compat_rusage { struct old_timeval32 ru_utime; struct old_timeval32 ru_stime; -- cgit v1.2.3 From 84a0c977ab9821a4b57f69d9a6108f64188d1e71 Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Tue, 5 Apr 2022 15:13:00 +0800 Subject: asm-generic: compat: Cleanup duplicate definitions There are 7 64bit architectures that support Linux COMPAT mode to run 32bit applications. A lot of definitions are duplicate: - COMPAT_USER_HZ - COMPAT_RLIM_INFINITY - COMPAT_OFF_T_MAX - __compat_uid_t, __compat_uid_t - compat_dev_t - compat_ipc_pid_t - struct compat_flock - struct compat_flock64 - struct compat_statfs - struct compat_ipc64_perm, compat_semid64_ds, compat_msqid64_ds, compat_shmid64_ds Cleanup duplicate definitions and merge them into asm-generic. Signed-off-by: Guo Ren Signed-off-by: Guo Ren Reviewed-by: Arnd Bergmann Reviewed-by: Christoph Hellwig Tested-by: Heiko Stuebner Acked-by: Helge Deller # parisc Link: https://lore.kernel.org/r/20220405071314.3225832-7-guoren@kernel.org Signed-off-by: Palmer Dabbelt --- include/asm-generic/compat.h | 106 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 106 insertions(+) (limited to 'include') diff --git a/include/asm-generic/compat.h b/include/asm-generic/compat.h index d46c0201cc34..11653d6846cc 100644 --- a/include/asm-generic/compat.h +++ b/include/asm-generic/compat.h @@ -2,6 +2,18 @@ #ifndef __ASM_GENERIC_COMPAT_H #define __ASM_GENERIC_COMPAT_H +#ifndef COMPAT_USER_HZ +#define COMPAT_USER_HZ 100 +#endif + +#ifndef COMPAT_RLIM_INFINITY +#define COMPAT_RLIM_INFINITY 0xffffffff +#endif + +#ifndef COMPAT_OFF_T_MAX +#define COMPAT_OFF_T_MAX 0x7fffffff +#endif + /* These types are common across all compat ABIs */ typedef u32 compat_size_t; typedef s32 compat_ssize_t; @@ -24,6 +36,11 @@ typedef u32 compat_caddr_t; typedef u32 compat_aio_context_t; typedef u32 compat_old_sigset_t; +#ifndef __compat_uid_t +typedef u32 __compat_uid_t; +typedef u32 __compat_gid_t; +#endif + #ifndef __compat_uid32_t typedef u32 __compat_uid32_t; typedef u32 __compat_gid32_t; @@ -47,4 +64,93 @@ typedef u32 compat_sigset_word; #define _COMPAT_NSIG_BPW 32 #endif +#ifndef compat_dev_t +typedef u32 compat_dev_t; +#endif + +#ifndef compat_ipc_pid_t +typedef s32 compat_ipc_pid_t; +#endif + +#ifndef compat_fsid_t +typedef __kernel_fsid_t compat_fsid_t; +#endif + +#ifndef compat_statfs +struct compat_statfs { + compat_int_t f_type; + compat_int_t f_bsize; + compat_int_t f_blocks; + compat_int_t f_bfree; + compat_int_t f_bavail; + compat_int_t f_files; + compat_int_t f_ffree; + compat_fsid_t f_fsid; + compat_int_t f_namelen; + compat_int_t f_frsize; + compat_int_t f_flags; + compat_int_t f_spare[4]; +}; +#endif + +#ifndef compat_ipc64_perm +struct compat_ipc64_perm { + compat_key_t key; + __compat_uid32_t uid; + __compat_gid32_t gid; + __compat_uid32_t cuid; + __compat_gid32_t cgid; + compat_mode_t mode; + unsigned char __pad1[4 - sizeof(compat_mode_t)]; + compat_ushort_t seq; + compat_ushort_t __pad2; + compat_ulong_t unused1; + compat_ulong_t unused2; +}; + +struct compat_semid64_ds { + struct compat_ipc64_perm sem_perm; + compat_ulong_t sem_otime; + compat_ulong_t sem_otime_high; + compat_ulong_t sem_ctime; + compat_ulong_t sem_ctime_high; + compat_ulong_t sem_nsems; + compat_ulong_t __unused3; + compat_ulong_t __unused4; +}; + +struct compat_msqid64_ds { + struct compat_ipc64_perm msg_perm; + compat_ulong_t msg_stime; + compat_ulong_t msg_stime_high; + compat_ulong_t msg_rtime; + compat_ulong_t msg_rtime_high; + compat_ulong_t msg_ctime; + compat_ulong_t msg_ctime_high; + compat_ulong_t msg_cbytes; + compat_ulong_t msg_qnum; + compat_ulong_t msg_qbytes; + compat_pid_t msg_lspid; + compat_pid_t msg_lrpid; + compat_ulong_t __unused4; + compat_ulong_t __unused5; +}; + +struct compat_shmid64_ds { + struct compat_ipc64_perm shm_perm; + compat_size_t shm_segsz; + compat_ulong_t shm_atime; + compat_ulong_t shm_atime_high; + compat_ulong_t shm_dtime; + compat_ulong_t shm_dtime_high; + compat_ulong_t shm_ctime; + compat_ulong_t shm_ctime_high; + compat_pid_t shm_cpid; + compat_pid_t shm_lpid; + compat_ulong_t shm_nattch; + compat_ulong_t __unused4; + compat_ulong_t __unused5; +}; +#endif + #endif -- cgit v1.2.3 From c86d2cad193a5c7f9b92467955bb7fb6642b9e80 Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Tue, 5 Apr 2022 15:13:01 +0800 Subject: syscalls: compat: Fix the missing part for __SYSCALL_COMPAT Make "uapi asm unistd.h" could be used for architectures' COMPAT mode. The __SYSCALL_COMPAT is first used in riscv. Signed-off-by: Guo Ren Signed-off-by: Guo Ren Reviewed-by: Arnd Bergmann Reviewed-by: Christoph Hellwig Tested-by: Heiko Stuebner Link: https://lore.kernel.org/r/20220405071314.3225832-8-guoren@kernel.org Signed-off-by: Palmer Dabbelt --- include/uapi/asm-generic/unistd.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 1c48b0ae3ba3..45fa180cc56a 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -383,7 +383,7 @@ __SYSCALL(__NR_syslog, sys_syslog) /* kernel/ptrace.c */ #define __NR_ptrace 117 -__SYSCALL(__NR_ptrace, sys_ptrace) +__SC_COMP(__NR_ptrace, sys_ptrace, compat_sys_ptrace) /* kernel/sched/core.c */ #define __NR_sched_setparam 118 @@ -779,7 +779,7 @@ __SYSCALL(__NR_rseq, sys_rseq) #define __NR_kexec_file_load 294 __SYSCALL(__NR_kexec_file_load, sys_kexec_file_load) /* 295 through 402 are unassigned to sync up with generic numbers, don't use */ -#if __BITS_PER_LONG == 32 +#if defined(__SYSCALL_COMPAT) || __BITS_PER_LONG == 32 #define __NR_clock_gettime64 403 __SYSCALL(__NR_clock_gettime64, sys_clock_gettime) #define __NR_clock_settime64 404 -- cgit v1.2.3 From 59c10c52f573faca862cda5ebcdd43831608eb5a Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Tue, 5 Apr 2022 15:13:05 +0800 Subject: riscv: compat: syscall: Add compat_sys_call_table implementation Implement compat sys_call_table and some system call functions: truncate64, ftruncate64, fallocate, pread64, pwrite64, sync_file_range, readahead, fadvise64_64 which need argument translation. Signed-off-by: Guo Ren Signed-off-by: Guo Ren Reviewed-by: Arnd Bergmann Tested-by: Heiko Stuebner Link: https://lore.kernel.org/r/20220405071314.3225832-12-guoren@kernel.org Signed-off-by: Palmer Dabbelt --- include/asm-generic/compat.h | 7 +++++++ include/linux/compat.h | 37 +++++++++++++++++++++++++++++++++++++ 2 files changed, 44 insertions(+) (limited to 'include') diff --git a/include/asm-generic/compat.h b/include/asm-generic/compat.h index 11653d6846cc..d06308a2a7a8 100644 --- a/include/asm-generic/compat.h +++ b/include/asm-generic/compat.h @@ -14,6 +14,13 @@ #define COMPAT_OFF_T_MAX 0x7fffffff #endif +#if !defined(compat_arg_u64) && !defined(CONFIG_CPU_BIG_ENDIAN) +#define compat_arg_u64(name) u32 name##_lo, u32 name##_hi +#define compat_arg_u64_dual(name) u32, name##_lo, u32, name##_hi +#define compat_arg_u64_glue(name) (((u64)name##_lo & 0xffffffffUL) | \ + ((u64)name##_hi << 32)) +#endif + /* These types are common across all compat ABIs */ typedef u32 compat_size_t; typedef s32 compat_ssize_t; diff --git a/include/linux/compat.h b/include/linux/compat.h index a0481fe6c5d5..ce6cd9b30d27 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -926,6 +926,43 @@ asmlinkage long compat_sys_sigaction(int sig, /* obsolete: net/socket.c */ asmlinkage long compat_sys_socketcall(int call, u32 __user *args); +#ifdef __ARCH_WANT_COMPAT_TRUNCATE64 +asmlinkage long compat_sys_truncate64(const char __user *pathname, compat_arg_u64(len)); +#endif + +#ifdef __ARCH_WANT_COMPAT_FTRUNCATE64 +asmlinkage long compat_sys_ftruncate64(unsigned int fd, compat_arg_u64(len)); +#endif + +#ifdef __ARCH_WANT_COMPAT_FALLOCATE +asmlinkage long compat_sys_fallocate(int fd, int mode, compat_arg_u64(offset), + compat_arg_u64(len)); +#endif + +#ifdef __ARCH_WANT_COMPAT_PREAD64 +asmlinkage long compat_sys_pread64(unsigned int fd, char __user *buf, size_t count, + compat_arg_u64(pos)); +#endif + +#ifdef __ARCH_WANT_COMPAT_PWRITE64 +asmlinkage long compat_sys_pwrite64(unsigned int fd, const char __user *buf, size_t count, + compat_arg_u64(pos)); +#endif + +#ifdef __ARCH_WANT_COMPAT_SYNC_FILE_RANGE +asmlinkage long compat_sys_sync_file_range(int fd, compat_arg_u64(pos), + compat_arg_u64(nbytes), unsigned int flags); +#endif + +#ifdef __ARCH_WANT_COMPAT_FADVISE64_64 +asmlinkage long compat_sys_fadvise64_64(int fd, compat_arg_u64(pos), + compat_arg_u64(len), int advice); +#endif + +#ifdef __ARCH_WANT_COMPAT_READAHEAD +asmlinkage long compat_sys_readahead(int fd, compat_arg_u64(offset), size_t count); +#endif + #endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ /** -- cgit v1.2.3 From a2a9d67a26ec94a99ed29efbd61cf5be0a575678 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 6 Apr 2022 11:31:19 +0900 Subject: bootconfig: Support embedding a bootconfig file in kernel This allows kernel developer to embed a default bootconfig file in the kernel instead of embedding it in the initrd. This will be good for who are using the kernel without initrd, or who needs a default bootconfigs. This needs to set two kconfigs: CONFIG_BOOT_CONFIG_EMBED=y and set the file path to CONFIG_BOOT_CONFIG_EMBED_FILE. Note that you still need 'bootconfig' command line option to load the embedded bootconfig. Also if you boot using an initrd with a different bootconfig, the kernel will use the bootconfig in the initrd, instead of the default bootconfig. Link: https://lkml.kernel.org/r/164921227943.1090670.14035119557571329218.stgit@devnote2 Cc: Padmanabha Srinivasaiah Cc: Jonathan Corbet Cc: Randy Dunlap Cc: Nick Desaulniers Cc: Sami Tolvanen Cc: Nathan Chancellor Cc: Masahiro Yamada Cc: Linux Kbuild mailing list Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (Google) --- include/linux/bootconfig.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index a4665c7ab07c..1611f9db878e 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -289,4 +289,14 @@ int __init xbc_get_info(int *node_size, size_t *data_size); /* XBC cleanup data structures */ void __init xbc_exit(void); +/* XBC embedded bootconfig data in kernel */ +#ifdef CONFIG_BOOT_CONFIG_EMBED +const char * __init xbc_get_embedded_bootconfig(size_t *size); +#else +static inline const char *xbc_get_embedded_bootconfig(size_t *size) +{ + return NULL; +} +#endif + #endif -- cgit v1.2.3 From 68822bdf76f10c3dc80609d4e2cdc1e847429086 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 22 Apr 2022 13:12:37 -0700 Subject: net: generalize skb freeing deferral to per-cpu lists Logic added in commit f35f821935d8 ("tcp: defer skb freeing after socket lock is released") helped bulk TCP flows to move the cost of skbs frees outside of critical section where socket lock was held. But for RPC traffic, or hosts with RFS enabled, the solution is far from being ideal. For RPC traffic, recvmsg() has to return to user space right after skb payload has been consumed, meaning that BH handler has no chance to pick the skb before recvmsg() thread. This issue is more visible with BIG TCP, as more RPC fit one skb. For RFS, even if BH handler picks the skbs, they are still picked from the cpu on which user thread is running. Ideally, it is better to free the skbs (and associated page frags) on the cpu that originally allocated them. This patch removes the per socket anchor (sk->defer_list) and instead uses a per-cpu list, which will hold more skbs per round. This new per-cpu list is drained at the end of net_action_rx(), after incoming packets have been processed, to lower latencies. In normal conditions, skbs are added to the per-cpu list with no further action. In the (unlikely) cases where the cpu does not run net_action_rx() handler fast enough, we use an IPI to raise NET_RX_SOFTIRQ on the remote cpu. Also, we do not bother draining the per-cpu list from dev_cpu_dead() This is because skbs in this list have no requirement on how fast they should be freed. Note that we can add in the future a small per-cpu cache if we see any contention on sd->defer_lock. Tested on a pair of hosts with 100Gbit NIC, RFS enabled, and /proc/sys/net/ipv4/tcp_rmem[2] tuned to 16MB to work around page recycling strategy used by NIC driver (its page pool capacity being too small compared to number of skbs/pages held in sockets receive queues) Note that this tuning was only done to demonstrate worse conditions for skb freeing for this particular test. These conditions can happen in more general production workload. 10 runs of one TCP_STREAM flow Before: Average throughput: 49685 Mbit. Kernel profiles on cpu running user thread recvmsg() show high cost for skb freeing related functions (*) 57.81% [kernel] [k] copy_user_enhanced_fast_string (*) 12.87% [kernel] [k] skb_release_data (*) 4.25% [kernel] [k] __free_one_page (*) 3.57% [kernel] [k] __list_del_entry_valid 1.85% [kernel] [k] __netif_receive_skb_core 1.60% [kernel] [k] __skb_datagram_iter (*) 1.59% [kernel] [k] free_unref_page_commit (*) 1.16% [kernel] [k] __slab_free 1.16% [kernel] [k] _copy_to_iter (*) 1.01% [kernel] [k] kfree (*) 0.88% [kernel] [k] free_unref_page 0.57% [kernel] [k] ip6_rcv_core 0.55% [kernel] [k] ip6t_do_table 0.54% [kernel] [k] flush_smp_call_function_queue (*) 0.54% [kernel] [k] free_pcppages_bulk 0.51% [kernel] [k] llist_reverse_order 0.38% [kernel] [k] process_backlog (*) 0.38% [kernel] [k] free_pcp_prepare 0.37% [kernel] [k] tcp_recvmsg_locked (*) 0.37% [kernel] [k] __list_add_valid 0.34% [kernel] [k] sock_rfree 0.34% [kernel] [k] _raw_spin_lock_irq (*) 0.33% [kernel] [k] __page_cache_release 0.33% [kernel] [k] tcp_v6_rcv (*) 0.33% [kernel] [k] __put_page (*) 0.29% [kernel] [k] __mod_zone_page_state 0.27% [kernel] [k] _raw_spin_lock After patch: Average throughput: 73076 Mbit. Kernel profiles on cpu running user thread recvmsg() looks better: 81.35% [kernel] [k] copy_user_enhanced_fast_string 1.95% [kernel] [k] _copy_to_iter 1.95% [kernel] [k] __skb_datagram_iter 1.27% [kernel] [k] __netif_receive_skb_core 1.03% [kernel] [k] ip6t_do_table 0.60% [kernel] [k] sock_rfree 0.50% [kernel] [k] tcp_v6_rcv 0.47% [kernel] [k] ip6_rcv_core 0.45% [kernel] [k] read_tsc 0.44% [kernel] [k] _raw_spin_lock_irqsave 0.37% [kernel] [k] _raw_spin_lock 0.37% [kernel] [k] native_irq_return_iret 0.33% [kernel] [k] __inet6_lookup_established 0.31% [kernel] [k] ip6_protocol_deliver_rcu 0.29% [kernel] [k] tcp_rcv_established 0.29% [kernel] [k] llist_reverse_order v2: kdoc issue (kernel bots) do not defer if (alloc_cpu == smp_processor_id()) (Paolo) replace the sk_buff_head with a single-linked list (Jakub) add a READ_ONCE()/WRITE_ONCE() for the lockless read of sd->defer_list Signed-off-by: Eric Dumazet Acked-by: Paolo Abeni Link: https://lore.kernel.org/r/20220422201237.416238-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 5 +++++ include/linux/skbuff.h | 3 +++ include/net/sock.h | 2 -- include/net/tcp.h | 12 ------------ 4 files changed, 8 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7dccbfd1bf56..ac8a5f71220a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3081,6 +3081,11 @@ struct softnet_data { struct sk_buff_head input_pkt_queue; struct napi_struct backlog; + /* Another possibly contended cache line */ + spinlock_t defer_lock ____cacheline_aligned_in_smp; + int defer_count; + struct sk_buff *defer_list; + call_single_data_t defer_csd; }; static inline void input_queue_head_incr(struct softnet_data *sd) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 84d78df60453..5cbc184ca685 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -888,6 +888,7 @@ typedef unsigned char *sk_buff_data_t; * delivery_time at egress. * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS + * @alloc_cpu: CPU which did the skb allocation. * @secmark: security marking * @mark: Generic packet mark * @reserved_tailroom: (aka @mark) number of bytes of free space available @@ -1080,6 +1081,7 @@ struct sk_buff { unsigned int sender_cpu; }; #endif + u16 alloc_cpu; #ifdef CONFIG_NETWORK_SECMARK __u32 secmark; #endif @@ -1321,6 +1323,7 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size); +void skb_attempt_defer_free(struct sk_buff *skb); struct sk_buff *napi_build_skb(void *data, unsigned int frag_size); diff --git a/include/net/sock.h b/include/net/sock.h index a01d6c421aa2..f9f8ecae0f8d 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -292,7 +292,6 @@ struct sk_filter; * @sk_pacing_shift: scaling factor for TCP Small Queues * @sk_lingertime: %SO_LINGER l_linger setting * @sk_backlog: always used with the per-socket spinlock held - * @defer_list: head of llist storing skbs to be freed * @sk_callback_lock: used with the callbacks in the end of this struct * @sk_error_queue: rarely used * @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt, @@ -417,7 +416,6 @@ struct sock { struct sk_buff *head; struct sk_buff *tail; } sk_backlog; - struct llist_head defer_list; #define sk_rmem_alloc sk_backlog.rmem_alloc diff --git a/include/net/tcp.h b/include/net/tcp.h index 679b1964d494..94a52ad1101c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1375,18 +1375,6 @@ static inline bool tcp_checksum_complete(struct sk_buff *skb) bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason); -#ifdef CONFIG_INET -void __sk_defer_free_flush(struct sock *sk); - -static inline void sk_defer_free_flush(struct sock *sk) -{ - if (llist_empty(&sk->defer_list)) - return; - __sk_defer_free_flush(sk); -} -#else -static inline void sk_defer_free_flush(struct sock *sk) {} -#endif int tcp_filter(struct sock *sk, struct sk_buff *skb); void tcp_set_state(struct sock *sk, int state); -- cgit v1.2.3 From 9bf2eed995f9f8136f00110214c120f2d7912ad8 Mon Sep 17 00:00:00 2001 From: Brendan Higgins Date: Mon, 18 Apr 2022 21:05:15 -0700 Subject: kunit: add support for kunit_suites that reference init code Add support for a new kind of kunit_suite registration macro called kunit_test_init_section_suite(); this new registration macro allows the registration of kunit_suites that reference functions marked __init and data marked __initdata. Signed-off-by: Brendan Higgins Tested-by: Martin Fernandez Reviewed-by: Kees Cook Reviewed-by: David Gow Signed-off-by: Shuah Khan --- include/kunit/test.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index 97cd76461886..17749b4467ad 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -308,6 +308,34 @@ static inline int kunit_run_all_tests(void) #define kunit_test_suite(suite) kunit_test_suites(&suite) +/** + * kunit_test_init_section_suites() - used to register one or more &struct + * kunit_suite containing init functions or + * init data. + * + * @__suites: a statically allocated list of &struct kunit_suite. + * + * This functions identically as &kunit_test_suites() except that it suppresses + * modpost warnings for referencing functions marked __init or data marked + * __initdata; this is OK because currently KUnit only runs tests upon boot + * during the init phase or upon loading a module during the init phase. + * + * NOTE TO KUNIT DEVS: If we ever allow KUnit tests to be run after boot, these + * tests must be excluded. + * + * The only thing this macro does that's different from kunit_test_suites is + * that it suffixes the array and suite declarations it makes with _probe; + * modpost suppresses warnings about referencing init data for symbols named in + * this manner. + */ +#define kunit_test_init_section_suites(__suites...) \ + __kunit_test_suites(CONCATENATE(__UNIQUE_ID(array), _probe), \ + CONCATENATE(__UNIQUE_ID(suites), _probe), \ + ##__suites) + +#define kunit_test_init_section_suite(suite) \ + kunit_test_init_section_suites(&suite) + #define kunit_suite_for_each_test_case(suite, test_case) \ for (test_case = suite->test_cases; test_case->run_case; test_case++) -- cgit v1.2.3 From 6510ea973d8d9d4a0cb2fb557b36bd1ab3eb49f6 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 25 Apr 2022 18:39:46 +0200 Subject: net: Use this_cpu_inc() to increment net->core_stats The macro dev_core_stats_##FIELD##_inc() disables preemption and invokes netdev_core_stats_alloc() to return a per-CPU pointer. netdev_core_stats_alloc() will allocate memory on its first invocation which breaks on PREEMPT_RT because it requires non-atomic context for memory allocation. This can be avoided by enabling preemption in netdev_core_stats_alloc() assuming the caller always disables preemption. It might be better to replace local_inc() with this_cpu_inc() now that dev_core_stats_##FIELD##_inc() gained a preempt-disable section and does not rely on already disabled preemption. This results in less instructions on x86-64: local_inc: | incl %gs:__preempt_count(%rip) # __preempt_count | movq 488(%rdi), %rax # _1->core_stats, _22 | testq %rax, %rax # _22 | je .L585 #, | add %gs:this_cpu_off(%rip), %rax # this_cpu_off, tcp_ptr__ | .L586: | testq %rax, %rax # _27 | je .L587 #, | incq (%rax) # _6->a.counter | .L587: | decl %gs:__preempt_count(%rip) # __preempt_count this_cpu_inc(), this patch: | movq 488(%rdi), %rax # _1->core_stats, _5 | testq %rax, %rax # _5 | je .L591 #, | .L585: | incq %gs:(%rax) # _18->rx_dropped Use unsigned long as type for the counter. Use this_cpu_inc() to increment the counter. Use a plain read of the counter. Signed-off-by: Sebastian Andrzej Siewior Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/YmbO0pxgtKpCw4SY@linutronix.de Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 59e27a2b7bf0..b1fbe21650bb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -199,10 +199,10 @@ struct net_device_stats { * Try to fit them in a single cache line, for dev_get_stats() sake. */ struct net_device_core_stats { - local_t rx_dropped; - local_t tx_dropped; - local_t rx_nohandler; -} __aligned(4 * sizeof(local_t)); + unsigned long rx_dropped; + unsigned long tx_dropped; + unsigned long rx_nohandler; +} __aligned(4 * sizeof(unsigned long)); #include #include @@ -3843,15 +3843,15 @@ static __always_inline bool __is_skb_forwardable(const struct net_device *dev, return false; } -struct net_device_core_stats *netdev_core_stats_alloc(struct net_device *dev); +struct net_device_core_stats __percpu *netdev_core_stats_alloc(struct net_device *dev); -static inline struct net_device_core_stats *dev_core_stats(struct net_device *dev) +static inline struct net_device_core_stats __percpu *dev_core_stats(struct net_device *dev) { /* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */ struct net_device_core_stats __percpu *p = READ_ONCE(dev->core_stats); if (likely(p)) - return this_cpu_ptr(p); + return p; return netdev_core_stats_alloc(dev); } @@ -3859,14 +3859,11 @@ static inline struct net_device_core_stats *dev_core_stats(struct net_device *de #define DEV_CORE_STATS_INC(FIELD) \ static inline void dev_core_stats_##FIELD##_inc(struct net_device *dev) \ { \ - struct net_device_core_stats *p; \ + struct net_device_core_stats __percpu *p; \ \ - preempt_disable(); \ p = dev_core_stats(dev); \ - \ if (p) \ - local_inc(&p->FIELD); \ - preempt_enable(); \ + this_cpu_inc(p->FIELD); \ } DEV_CORE_STATS_INC(rx_dropped) DEV_CORE_STATS_INC(tx_dropped) -- cgit v1.2.3 From 6423d2951087231706246f81851067f7f0593d4a Mon Sep 17 00:00:00 2001 From: Won Chung Date: Mon, 14 Mar 2022 19:54:58 +0000 Subject: driver core: Add sysfs support for physical location of a device When ACPI table includes _PLD fields for a device, create a new directory (physical_location) in sysfs to share _PLD fields. Currently without PLD information, when there are multiple of same devices, it is hard to distinguish which device corresponds to which physical device at which location. For example, when there are two Type C connectors, it is hard to find out which connector corresponds to the Type C port on the left panel versus the Type C port on the right panel. With PLD information provided, we can determine which specific device at which location is doing what. _PLD output includes much more fields, but only generic fields are added and exposed to sysfs, so that non-ACPI devices can also support it in the future. The minimal generic fields needed for locating a device are the following. - panel - vertical_position - horizontal_position - dock - lid Signed-off-by: Won Chung Link: https://lore.kernel.org/r/20220314195458.271430-1-wonchung@google.com Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 73 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 73 insertions(+) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index 93459724dcde..766fbea6ca83 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -386,6 +386,75 @@ struct dev_msi_info { #endif }; +/** + * enum device_physical_location_panel - Describes which panel surface of the + * system's housing the device connection point resides on. + * @DEVICE_PANEL_TOP: Device connection point is on the top panel. + * @DEVICE_PANEL_BOTTOM: Device connection point is on the bottom panel. + * @DEVICE_PANEL_LEFT: Device connection point is on the left panel. + * @DEVICE_PANEL_RIGHT: Device connection point is on the right panel. + * @DEVICE_PANEL_FRONT: Device connection point is on the front panel. + * @DEVICE_PANEL_BACK: Device connection point is on the back panel. + * @DEVICE_PANEL_UNKNOWN: The panel with device connection point is unknown. + */ +enum device_physical_location_panel { + DEVICE_PANEL_TOP, + DEVICE_PANEL_BOTTOM, + DEVICE_PANEL_LEFT, + DEVICE_PANEL_RIGHT, + DEVICE_PANEL_FRONT, + DEVICE_PANEL_BACK, + DEVICE_PANEL_UNKNOWN, +}; + +/** + * enum device_physical_location_vertical_position - Describes vertical + * position of the device connection point on the panel surface. + * @DEVICE_VERT_POS_UPPER: Device connection point is at upper part of panel. + * @DEVICE_VERT_POS_CENTER: Device connection point is at center part of panel. + * @DEVICE_VERT_POS_LOWER: Device connection point is at lower part of panel. + */ +enum device_physical_location_vertical_position { + DEVICE_VERT_POS_UPPER, + DEVICE_VERT_POS_CENTER, + DEVICE_VERT_POS_LOWER, +}; + +/** + * enum device_physical_location_horizontal_position - Describes horizontal + * position of the device connection point on the panel surface. + * @DEVICE_HORI_POS_LEFT: Device connection point is at left part of panel. + * @DEVICE_HORI_POS_CENTER: Device connection point is at center part of panel. + * @DEVICE_HORI_POS_RIGHT: Device connection point is at right part of panel. + */ +enum device_physical_location_horizontal_position { + DEVICE_HORI_POS_LEFT, + DEVICE_HORI_POS_CENTER, + DEVICE_HORI_POS_RIGHT, +}; + +/** + * struct device_physical_location - Device data related to physical location + * of the device connection point. + * @panel: Panel surface of the system's housing that the device connection + * point resides on. + * @vertical_position: Vertical position of the device connection point within + * the panel. + * @horizontal_position: Horizontal position of the device connection point + * within the panel. + * @dock: Set if the device connection point resides in a docking station or + * port replicator. + * @lid: Set if this device connection point resides on the lid of laptop + * system. + */ +struct device_physical_location { + enum device_physical_location_panel panel; + enum device_physical_location_vertical_position vertical_position; + enum device_physical_location_horizontal_position horizontal_position; + bool dock; + bool lid; +}; + /** * struct device - The basic device structure * @parent: The device's "parent" device, the device to which it is attached. @@ -453,6 +522,8 @@ struct dev_msi_info { * device (i.e. the bus driver that discovered the device). * @iommu_group: IOMMU group the device belongs to. * @iommu: Per device generic IOMMU runtime data + * @physical_location: Describes physical location of the device connection + * point in the system housing. * @removable: Whether the device can be removed from the system. This * should be set by the subsystem / bus driver that discovered * the device. @@ -567,6 +638,8 @@ struct device { struct iommu_group *iommu_group; struct dev_iommu *iommu; + struct device_physical_location *physical_location; + enum device_removable removable; bool offline_disabled:1; -- cgit v1.2.3 From 052e1f01bfae8be6f31b61ed3a2356edfca855dc Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 26 Apr 2022 10:54:33 -0700 Subject: net: atm: remove support for ZeitNet ZN122x ATM devices This driver received nothing but automated fixes in the last 15 years. Since it's using virt_to_bus it's unlikely to be used on any modern platform. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/uapi/linux/atm_zatm.h | 47 ------------------------------------------- 1 file changed, 47 deletions(-) delete mode 100644 include/uapi/linux/atm_zatm.h (limited to 'include') diff --git a/include/uapi/linux/atm_zatm.h b/include/uapi/linux/atm_zatm.h deleted file mode 100644 index 5135027b93c1..000000000000 --- a/include/uapi/linux/atm_zatm.h +++ /dev/null @@ -1,47 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* atm_zatm.h - Driver-specific declarations of the ZATM driver (for use by - driver-specific utilities) */ - -/* Written 1995-1999 by Werner Almesberger, EPFL LRC/ICA */ - - -#ifndef LINUX_ATM_ZATM_H -#define LINUX_ATM_ZATM_H - -/* - * Note: non-kernel programs including this file must also include - * sys/types.h for struct timeval - */ - -#include -#include - -#define ZATM_GETPOOL _IOW('a',ATMIOC_SARPRV+1,struct atmif_sioc) - /* get pool statistics */ -#define ZATM_GETPOOLZ _IOW('a',ATMIOC_SARPRV+2,struct atmif_sioc) - /* get statistics and zero */ -#define ZATM_SETPOOL _IOW('a',ATMIOC_SARPRV+3,struct atmif_sioc) - /* set pool parameters */ - -struct zatm_pool_info { - int ref_count; /* free buffer pool usage counters */ - int low_water,high_water; /* refill parameters */ - int rqa_count,rqu_count; /* queue condition counters */ - int offset,next_off; /* alignment optimizations: offset */ - int next_cnt,next_thres; /* repetition counter and threshold */ -}; - -struct zatm_pool_req { - int pool_num; /* pool number */ - struct zatm_pool_info info; /* actual information */ -}; - -#define ZATM_OAM_POOL 0 /* free buffer pool for OAM cells */ -#define ZATM_AAL0_POOL 1 /* free buffer pool for AAL0 cells */ -#define ZATM_AAL5_POOL_BASE 2 /* first AAL5 free buffer pool */ -#define ZATM_LAST_POOL ZATM_AAL5_POOL_BASE+10 /* max. 64 kB */ - -#define ZATM_TIMER_HISTORY_SIZE 16 /* number of timer adjustments to - record; must be 2^n */ - -#endif -- cgit v1.2.3 From afe57ecab58b976c54fcbc31d718f936a0cc98cc Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 26 Apr 2022 13:36:31 -0500 Subject: ASoC: SOF: bump SOF_ABI_MINOR Commit a0f84dfb3f6d9 ("ASoC: SOF: IPC: dai: Expand DAI_CONFIG IPC flags") did not update the SOF_ABI_MINOR, bump to version 20 before new changes are added. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Daniel Baluta Reviewed-by: Kai Vehmanen Link: https://lore.kernel.org/r/20220426183631.102356-1-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/uapi/sound/sof/abi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/sound/sof/abi.h b/include/uapi/sound/sof/abi.h index e052653a6e4c..b87e46684623 100644 --- a/include/uapi/sound/sof/abi.h +++ b/include/uapi/sound/sof/abi.h @@ -26,8 +26,8 @@ /* SOF ABI version major, minor and patch numbers */ #define SOF_ABI_MAJOR 3 -#define SOF_ABI_MINOR 19 -#define SOF_ABI_PATCH 1 +#define SOF_ABI_MINOR 20 +#define SOF_ABI_PATCH 0 /* SOF ABI version number. Format within 32bit word is MMmmmppp */ #define SOF_ABI_MAJOR_SHIFT 24 -- cgit v1.2.3 From 2d3694fdeef599ef5a1352b699bdd493a51ab8cb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Amadeusz=20S=C5=82awi=C5=84ski?= Date: Tue, 26 Apr 2022 22:05:38 +0200 Subject: ALSA: hda: intel-nhlt: Move structs out of #define block MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As functions prototypes regerdless of CONFIG options as well as some code depend on structures defined in sound/intel-nhlt.h header, move them out of #define block. This allows to compile code depending on mentioned header with "depends on ACPI || COMPILE_TEST" in Kconfig. Fixes: 47a1886a610a ("ASoC: Intel: avs: Enable AVS driver only on x86 platforms") Reported-by: kernel test robot Suggested-by: Pierre-Louis Bossart Reviewed-by: Cezary Rojewski Signed-off-by: Amadeusz Sławiński Link: https://lore.kernel.org/r/20220426200539.894010-1-amadeuszx.slawinski@linux.intel.com Signed-off-by: Mark Brown --- include/sound/intel-nhlt.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/sound/intel-nhlt.h b/include/sound/intel-nhlt.h index 6fb2d5e378fd..3d5cf201cd80 100644 --- a/include/sound/intel-nhlt.h +++ b/include/sound/intel-nhlt.h @@ -25,8 +25,6 @@ enum nhlt_device_type { NHLT_DEVICE_INVALID }; -#if IS_ENABLED(CONFIG_ACPI) && IS_ENABLED(CONFIG_SND_INTEL_NHLT) - struct wav_fmt { u16 fmt_tag; u16 channels; @@ -126,6 +124,8 @@ enum { NHLT_MIC_ARRAY_VENDOR_DEFINED = 0xf, }; +#if IS_ENABLED(CONFIG_ACPI) && IS_ENABLED(CONFIG_SND_INTEL_NHLT) + struct nhlt_acpi_table *intel_nhlt_init(struct device *dev); void intel_nhlt_free(struct nhlt_acpi_table *addr); @@ -143,8 +143,6 @@ intel_nhlt_get_endpoint_blob(struct device *dev, struct nhlt_acpi_table *nhlt, #else -struct nhlt_acpi_table; - static inline struct nhlt_acpi_table *intel_nhlt_init(struct device *dev) { return NULL; -- cgit v1.2.3 From b041b525dab95352fbd666b14dc73ab898df465f Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Thu, 10 Mar 2022 12:48:53 -0800 Subject: x86/split_lock: Make life miserable for split lockers In https://lore.kernel.org/all/87y22uujkm.ffs@tglx/ Thomas said: Its's simply wishful thinking that stuff gets fixed because of a WARN_ONCE(). This has never worked. The only thing which works is to make stuff fail hard or slow it down in a way which makes it annoying enough to users to complain. He was talking about WBINVD. But it made me think about how we use the split lock detection feature in Linux. Existing code has three options for applications: 1) Don't enable split lock detection (allow arbitrary split locks) 2) Warn once when a process uses split lock, but let the process keep running with split lock detection disabled 3) Kill process that use split locks Option 2 falls into the "wishful thinking" territory that Thomas warns does nothing. But option 3 might not be viable in a situation with legacy applications that need to run. Hence make option 2 much stricter to "slow it down in a way which makes it annoying". Primary reason for this change is to provide better quality of service to the rest of the applications running on the system. Internal testing shows that even with many processes splitting locks, performance for the rest of the system is much more responsive. The new "warn" mode operates like this. When an application tries to execute a bus lock the #AC handler. 1) Delays (interruptibly) 10 ms before moving to next step. 2) Blocks (interruptibly) until it can get the semaphore If interrupted, just return. Assume the signal will either kill the task, or direct execution away from the instruction that is trying to get the bus lock. 3) Disables split lock detection for the current core 4) Schedules a work queue to re-enable split lock detect in 2 jiffies 5) Returns The work queue that re-enables split lock detection also releases the semaphore. There is a corner case where a CPU may be taken offline while split lock detection is disabled. A CPU hotplug handler handles this case. Old behaviour was to only print the split lock warning on the first occurrence of a split lock from a task. Preserve that by adding a flag to the task structure that suppresses subsequent split lock messages from that task. Signed-off-by: Tony Luck Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20220310204854.31752-2-tony.luck@intel.com --- include/linux/sched.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index a8911b1f35aa..23e03c7824c4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -941,6 +941,9 @@ struct task_struct { #ifdef CONFIG_IOMMU_SVA unsigned pasid_activated:1; #endif +#ifdef CONFIG_CPU_SUP_INTEL + unsigned reported_split_lock:1; +#endif unsigned long atomic_flags; /* Flags requiring atomic access. */ -- cgit v1.2.3 From 4fd62f15afa0d0da4823f429a2fb4c3492a84edf Mon Sep 17 00:00:00 2001 From: Chuanhong Guo Date: Sun, 24 Apr 2022 11:25:23 +0800 Subject: mtd: nand: make mtk_ecc.c a separated module this code will be used in mediatek snfi spi-mem controller with pipelined ECC engine. Signed-off-by: Chuanhong Guo Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20220424032527.673605-2-gch981213@gmail.com --- include/linux/mtd/nand-ecc-mtk.h | 47 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) create mode 100644 include/linux/mtd/nand-ecc-mtk.h (limited to 'include') diff --git a/include/linux/mtd/nand-ecc-mtk.h b/include/linux/mtd/nand-ecc-mtk.h new file mode 100644 index 000000000000..0e48c36e6ca0 --- /dev/null +++ b/include/linux/mtd/nand-ecc-mtk.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* + * MTK SDG1 ECC controller + * + * Copyright (c) 2016 Mediatek + * Authors: Xiaolei Li + * Jorge Ramirez-Ortiz + */ + +#ifndef __DRIVERS_MTD_NAND_MTK_ECC_H__ +#define __DRIVERS_MTD_NAND_MTK_ECC_H__ + +#include + +enum mtk_ecc_mode {ECC_DMA_MODE = 0, ECC_NFI_MODE = 1}; +enum mtk_ecc_operation {ECC_ENCODE, ECC_DECODE}; + +struct device_node; +struct mtk_ecc; + +struct mtk_ecc_stats { + u32 corrected; + u32 bitflips; + u32 failed; +}; + +struct mtk_ecc_config { + enum mtk_ecc_operation op; + enum mtk_ecc_mode mode; + dma_addr_t addr; + u32 strength; + u32 sectors; + u32 len; +}; + +int mtk_ecc_encode(struct mtk_ecc *, struct mtk_ecc_config *, u8 *, u32); +void mtk_ecc_get_stats(struct mtk_ecc *, struct mtk_ecc_stats *, int); +int mtk_ecc_wait_done(struct mtk_ecc *, enum mtk_ecc_operation); +int mtk_ecc_enable(struct mtk_ecc *, struct mtk_ecc_config *); +void mtk_ecc_disable(struct mtk_ecc *); +void mtk_ecc_adjust_strength(struct mtk_ecc *ecc, u32 *p); +unsigned int mtk_ecc_get_parity_bits(struct mtk_ecc *ecc); + +struct mtk_ecc *of_mtk_ecc_get(struct device_node *); +void mtk_ecc_release(struct mtk_ecc *); + +#endif -- cgit v1.2.3 From e5be15767e7e284351853cbaba80cde8620341fb Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Mon, 25 Apr 2022 08:07:48 -0400 Subject: hex2bin: make the function hex_to_bin constant-time The function hex2bin is used to load cryptographic keys into device mapper targets dm-crypt and dm-integrity. It should take constant time independent on the processed data, so that concurrently running unprivileged code can't infer any information about the keys via microarchitectural convert channels. This patch changes the function hex_to_bin so that it contains no branches and no memory accesses. Note that this shouldn't cause performance degradation because the size of the new function is the same as the size of the old function (on x86-64) - and the new function causes no branch misprediction penalties. I compile-tested this function with gcc on aarch64 alpha arm hppa hppa64 i386 ia64 m68k mips32 mips64 powerpc powerpc64 riscv sh4 s390x sparc32 sparc64 x86_64 and with clang on aarch64 arm hexagon i386 mips32 mips64 powerpc powerpc64 s390x sparc32 sparc64 x86_64 to verify that there are no branches in the generated code. Signed-off-by: Mikulas Patocka Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index a890428bcc1a..fe6efb24d151 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -285,7 +285,7 @@ static inline char *hex_byte_pack_upper(char *buf, u8 byte) return buf; } -extern int hex_to_bin(char ch); +extern int hex_to_bin(unsigned char ch); extern int __must_check hex2bin(u8 *dst, const char *src, size_t count); extern char *bin2hex(char *dst, const void *src, size_t count); -- cgit v1.2.3 From 7d84c1ebf9ddafca27b481e6da7d24a023dacaa2 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 15 Apr 2022 21:20:02 +0200 Subject: x86/aperfmperf: Replace aperfmperf_get_khz() The frequency invariance infrastructure provides the APERF/MPERF samples already. Utilize them for the cpu frequency display in /proc/cpuinfo. The sample is considered valid for 20ms. So for idle or isolated NOHZ full CPUs the function returns 0, which is matching the previous behaviour. This gets rid of the mass IPIs and a delay of 20ms for stabilizing observed by Eric when reading /proc/cpuinfo. Reported-by: Eric Dumazet Signed-off-by: Thomas Gleixner Tested-by: Eric Dumazet Reviewed-by: Rafael J. Wysocki Acked-by: Peter Zijlstra (Intel) Acked-by: Paul E. McKenney Link: https://lore.kernel.org/r/20220415161206.875029458@linutronix.de --- include/linux/cpufreq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 35c7d6db4139..d5595d57f4e5 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -1199,7 +1199,6 @@ static inline void sched_cpufreq_governor_change(struct cpufreq_policy *policy, struct cpufreq_governor *old_gov) { } #endif -extern void arch_freq_prepare_all(void); extern unsigned int arch_freq_get_on_cpu(int cpu); #ifndef arch_set_freq_scale -- cgit v1.2.3 From b941820ec938d175fd6e4e7ba5b4a6ca9d092afd Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 25 Apr 2022 14:45:44 +0300 Subject: ACPI: OSL: Remove the helper for deactivating memory region There are no more users for acpi_release_memory(). Signed-off-by: Heikki Krogerus Reviewed-by: Greg Kroah-Hartman Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index d7136d13aa44..fadda404bcc9 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -520,9 +520,6 @@ int acpi_check_resource_conflict(const struct resource *res); int acpi_check_region(resource_size_t start, resource_size_t n, const char *name); -acpi_status acpi_release_memory(acpi_handle handle, struct resource *res, - u32 level); - int acpi_resources_are_enforced(void); #ifdef CONFIG_HIBERNATION -- cgit v1.2.3 From 1bc4ae0ccbc661b58d3e8f7b633c7786eaf7929f Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Mon, 25 Apr 2022 14:12:50 -0700 Subject: drm/i915: Add first set of DG2 PCI IDs The IDs added here are the subset reserved for 'motherboard down' designs of DG2. We have all the necessary support upstream to enable these now (although they'll continue to require force_probe until the usual requirements are met). The remaining DG2 IDs for add-in cards will come in a future patch once some additional required functionality has fully landed. Bspec: 44477 Cc: Lucas De Marchi Cc: Daniel Vetter Cc: Dave Airlie Cc: Rodrigo Vivi Cc: Joonas Lahtinen Cc: Jani Nikula Cc: Tvrtko Ursulin Signed-off-by: Matt Roper Reviewed-by: Lucas De Marchi Link: https://patchwork.freedesktop.org/patch/msgid/20220425211251.77154-3-matthew.d.roper@intel.com --- include/drm/i915_pciids.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include') diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h index a7b5eea7ffaa..283dadfbb4db 100644 --- a/include/drm/i915_pciids.h +++ b/include/drm/i915_pciids.h @@ -692,4 +692,26 @@ INTEL_VGA_DEVICE(0xA7A8, info), \ INTEL_VGA_DEVICE(0xA7A9, info) +/* DG2 */ +#define INTEL_DG2_G10_IDS(info) \ + INTEL_VGA_DEVICE(0x5690, info), \ + INTEL_VGA_DEVICE(0x5691, info), \ + INTEL_VGA_DEVICE(0x5692, info) + +#define INTEL_DG2_G11_IDS(info) \ + INTEL_VGA_DEVICE(0x5693, info), \ + INTEL_VGA_DEVICE(0x5694, info), \ + INTEL_VGA_DEVICE(0x5695, info), \ + INTEL_VGA_DEVICE(0x56B0, info) + +#define INTEL_DG2_G12_IDS(info) \ + INTEL_VGA_DEVICE(0x5696, info), \ + INTEL_VGA_DEVICE(0x5697, info), \ + INTEL_VGA_DEVICE(0x56B2, info) + +#define INTEL_DG2_IDS(info) \ + INTEL_DG2_G10_IDS(info), \ + INTEL_DG2_G11_IDS(info), \ + INTEL_DG2_G12_IDS(info) + #endif /* _I915_PCIIDS_H */ -- cgit v1.2.3 From 0a8e98305f63deaf0a799d5cf5532cc83af035d1 Mon Sep 17 00:00:00 2001 From: Tokunori Ikegami Date: Thu, 24 Mar 2022 02:04:56 +0900 Subject: mtd: cfi_cmdset_0002: Use chip_ready() for write on S29GL064N Since commit dfeae1073583("mtd: cfi_cmdset_0002: Change write buffer to check correct value") buffered writes fail on S29GL064N. This is because, on S29GL064N, reads return 0xFF at the end of DQ polling for write completion, where as, chip_good() check expects actual data written to the last location to be returned post DQ polling completion. Fix is to revert to using chip_good() for S29GL064N which only checks for DQ lines to settle down to determine write completion. Link: https://lore.kernel.org/r/b687c259-6413-26c9-d4c9-b3afa69ea124@pengutronix.de/ Fixes: dfeae1073583("mtd: cfi_cmdset_0002: Change write buffer to check correct value") Cc: stable@vger.kernel.org Signed-off-by: Tokunori Ikegami Acked-by: Vignesh Raghavendra Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20220323170458.5608-3-ikegami.t@gmail.com --- include/linux/mtd/cfi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h index fd1ecb821106..d88bb56c18e2 100644 --- a/include/linux/mtd/cfi.h +++ b/include/linux/mtd/cfi.h @@ -286,6 +286,7 @@ struct cfi_private { map_word sector_erase_cmd; unsigned long chipshift; /* Because they're of the same type */ const char *im_name; /* inter_module name for cmdset_setup */ + unsigned long quirks; struct flchip chips[]; /* per-chip data structure for each chip */ }; -- cgit v1.2.3 From ed36d04e8f8d7b00db451b0fa56a54e8e02ec43e Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 25 Apr 2022 13:42:02 +0100 Subject: iommu: Introduce device_iommu_capable() iommu_capable() only really works for systems where all IOMMU instances are completely homogeneous, and all devices are IOMMU-mapped. Implement the new variant which will be able to give a more accurate answer for whichever device the caller is actually interested in, and even more so once all the external users have been converted and we can reliably pass the device pointer through the internal driver interface too. Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/8407eb9586677995b7a9fd70d0fd82d85929a9bb.1650878781.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 9208eca4b0d1..e26cf84e5d82 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -417,6 +417,7 @@ static inline const struct iommu_ops *dev_iommu_ops(struct device *dev) extern int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops); extern int bus_iommu_probe(struct bus_type *bus); extern bool iommu_present(struct bus_type *bus); +extern bool device_iommu_capable(struct device *dev, enum iommu_cap cap); extern bool iommu_capable(struct bus_type *bus, enum iommu_cap cap); extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus); extern struct iommu_group *iommu_group_get_by_id(int id); @@ -689,6 +690,11 @@ static inline bool iommu_present(struct bus_type *bus) return false; } +static inline bool device_iommu_capable(struct device *dev, enum iommu_cap cap) +{ + return false; +} + static inline bool iommu_capable(struct bus_type *bus, enum iommu_cap cap) { return false; -- cgit v1.2.3 From d0be55fbeb6ac694d15af5d1aad19cdec8cd64e5 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 25 Apr 2022 13:42:03 +0100 Subject: iommu: Add capability for pre-boot DMA protection VT-d's dmar_platform_optin() actually represents a combination of properties fairly well standardised by Microsoft as "Pre-boot DMA Protection" and "Kernel DMA Protection"[1]. As such, we can provide interested consumers with an abstracted capability rather than driver-specific interfaces that won't scale. We name it for the former aspect since that's what external callers are most likely to be interested in; the latter is for the IOMMU layer to handle itself. [1] https://docs.microsoft.com/en-us/windows-hardware/design/device-experiences/oem-kernel-dma-protection Suggested-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Reviewed-by: Lu Baolu Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/d6218dff2702472da80db6aec2c9589010684551.1650878781.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index e26cf84e5d82..4123693ae319 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -107,6 +107,8 @@ enum iommu_cap { transactions */ IOMMU_CAP_INTR_REMAP, /* IOMMU supports interrupt isolation */ IOMMU_CAP_NOEXEC, /* IOMMU_NOEXEC flag */ + IOMMU_CAP_PRE_BOOT_PROTECTION, /* Firmware says it used the IOMMU for + DMA protection and we should too */ }; /* These are the possible reserved region types */ -- cgit v1.2.3 From 86eaf4a5b4312bea8676fb79399d9e08b53d8e71 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 25 Apr 2022 13:42:04 +0100 Subject: thunderbolt: Make iommu_dma_protection more accurate Between me trying to get rid of iommu_present() and Mario wanting to support the AMD equivalent of DMAR_PLATFORM_OPT_IN, scrutiny has shown that the iommu_dma_protection attribute is being far too optimistic. Even if an IOMMU might be present for some PCI segment in the system, that doesn't necessarily mean it provides translation for the device(s) we care about. Furthermore, all that DMAR_PLATFORM_OPT_IN really does is tell us that memory was protected before the kernel was loaded, and prevent the user from disabling the intel-iommu driver entirely. While that lets us assume kernel integrity, what matters for actual runtime DMA protection is whether we trust individual devices, based on the "external facing" property that we expect firmware to describe for Thunderbolt ports. It's proven challenging to determine the appropriate ports accurately given the variety of possible topologies, so while still not getting a perfect answer, by putting enough faith in firmware we can at least get a good bit closer. If we can see that any device near a Thunderbolt NHI has all the requisites for Kernel DMA Protection, chances are that it *is* a relevant port, but moreover that implies that firmware is playing the game overall, so we'll use that to assume that all Thunderbolt ports should be correctly marked and thus will end up fully protected. CC: Mario Limonciello Reviewed-by: Christoph Hellwig Acked-by: Mika Westerberg Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/b153f208bc9eafab5105bad0358b77366509d2d4.1650878781.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- include/linux/thunderbolt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index 124e13cb1469..7a8ad984e651 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -465,6 +465,7 @@ static inline struct tb_xdomain *tb_service_parent(struct tb_service *svc) * @msix_ida: Used to allocate MSI-X vectors for rings * @going_away: The host controller device is about to disappear so when * this flag is set, avoid touching the hardware anymore. + * @iommu_dma_protection: An IOMMU will isolate external-facing ports. * @interrupt_work: Work scheduled to handle ring interrupt when no * MSI-X is used. * @hop_count: Number of rings (end point hops) supported by NHI. @@ -479,6 +480,7 @@ struct tb_nhi { struct tb_ring **rx_rings; struct ida msix_ida; bool going_away; + bool iommu_dma_protection; struct work_struct interrupt_work; u32 hop_count; unsigned long quirks; -- cgit v1.2.3 From 2147c438fde135d6c145a96e373d9348e7076f7f Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 25 Apr 2022 16:40:02 -0700 Subject: x86/speculation: Add missing prototype for unpriv_ebpf_notify() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the following warnings seen with "make W=1": kernel/sysctl.c:183:13: warning: no previous prototype for ‘unpriv_ebpf_notify’ [-Wmissing-prototypes] 183 | void __weak unpriv_ebpf_notify(int new_state) | ^~~~~~~~~~~~~~~~~~ arch/x86/kernel/cpu/bugs.c:659:6: warning: no previous prototype for ‘unpriv_ebpf_notify’ [-Wmissing-prototypes] 659 | void unpriv_ebpf_notify(int new_state) | ^~~~~~~~~~~~~~~~~~ Fixes: 44a3918c8245 ("x86/speculation: Include unprivileged eBPF status in Spectre v2 mitigation reporting") Reported-by: kernel test robot Signed-off-by: Josh Poimboeuf Signed-off-by: Borislav Petkov Link: https://lore.kernel.org/r/5689d065f739602ececaee1e05e68b8644009608.1650930000.git.jpoimboe@redhat.com --- include/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bdb5298735ce..ecc3d3ec41cf 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2085,6 +2085,8 @@ void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, struct net_device *netdev); bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev); +void unpriv_ebpf_notify(int new_state); + #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); -- cgit v1.2.3 From c35fe2a68f29a0bda15ae994154cacaae5f69791 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Mon, 25 Apr 2022 16:18:33 +0100 Subject: elf: Fix the arm64 MTE ELF segment name and value Unfortunately, the name/value choice for the MTE ELF segment type (PT_ARM_MEMTAG_MTE) was pretty poor: LOPROC+1 is already in use by PT_AARCH64_UNWIND, as defined in the AArch64 ELF ABI (https://github.com/ARM-software/abi-aa/blob/main/aaelf64/aaelf64.rst). Update the ELF segment type value to LOPROC+2 and also change the define to PT_AARCH64_MEMTAG_MTE to match the AArch64 ELF ABI namespace. The AArch64 ELF ABI document is updating accordingly (segment type not previously mentioned in the document). Signed-off-by: Catalin Marinas Fixes: 761b9b366cec ("elf: Introduce the ARM MTE ELF segment type") Cc: Will Deacon Cc: Jonathan Corbet Cc: Eric Biederman Cc: Kees Cook Cc: Luis Machado Cc: Richard Earnshaw Link: https://lore.kernel.org/r/20220425151833.2603830-1-catalin.marinas@arm.com Signed-off-by: Will Deacon --- include/uapi/linux/elf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 787c657bfae8..7ce993e6786c 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -42,7 +42,7 @@ typedef __s64 Elf64_Sxword; /* ARM MTE memory tag segment type */ -#define PT_ARM_MEMTAG_MTE (PT_LOPROC + 0x1) +#define PT_AARCH64_MEMTAG_MTE (PT_LOPROC + 0x2) /* * Extended Numbering -- cgit v1.2.3 From 1ea2a07a532b0e22aabe7e8483f935c672b9e7ed Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 18 Apr 2022 08:49:50 +0800 Subject: iommu: Add DMA ownership management interfaces Multiple devices may be placed in the same IOMMU group because they cannot be isolated from each other. These devices must either be entirely under kernel control or userspace control, never a mixture. This adds dma ownership management in iommu core and exposes several interfaces for the device drivers and the device userspace assignment framework (i.e. VFIO), so that any conflict between user and kernel controlled dma could be detected at the beginning. The device driver oriented interfaces are, int iommu_device_use_default_domain(struct device *dev); void iommu_device_unuse_default_domain(struct device *dev); By calling iommu_device_use_default_domain(), the device driver tells the iommu layer that the device dma is handled through the kernel DMA APIs. The iommu layer will manage the IOVA and use the default domain for DMA address translation. The device user-space assignment framework oriented interfaces are, int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner); void iommu_group_release_dma_owner(struct iommu_group *group); bool iommu_group_dma_owner_claimed(struct iommu_group *group); The device userspace assignment must be disallowed if the DMA owner claiming interface returns failure. Signed-off-by: Jason Gunthorpe Signed-off-by: Kevin Tian Signed-off-by: Lu Baolu Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20220418005000.897664-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 9208eca4b0d1..77972ef978b5 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -675,6 +675,13 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, void iommu_sva_unbind_device(struct iommu_sva *handle); u32 iommu_sva_get_pasid(struct iommu_sva *handle); +int iommu_device_use_default_domain(struct device *dev); +void iommu_device_unuse_default_domain(struct device *dev); + +int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner); +void iommu_group_release_dma_owner(struct iommu_group *group); +bool iommu_group_dma_owner_claimed(struct iommu_group *group); + #else /* CONFIG_IOMMU_API */ struct iommu_ops {}; @@ -1031,6 +1038,30 @@ static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev) { return NULL; } + +static inline int iommu_device_use_default_domain(struct device *dev) +{ + return 0; +} + +static inline void iommu_device_unuse_default_domain(struct device *dev) +{ +} + +static inline int +iommu_group_claim_dma_owner(struct iommu_group *group, void *owner) +{ + return -ENODEV; +} + +static inline void iommu_group_release_dma_owner(struct iommu_group *group) +{ +} + +static inline bool iommu_group_dma_owner_claimed(struct iommu_group *group) +{ + return false; +} #endif /* CONFIG_IOMMU_API */ /** -- cgit v1.2.3 From 25f3bcfc54bcf7b0e45d140ec8bfbbf10ba11869 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 18 Apr 2022 08:49:51 +0800 Subject: driver core: Add dma_cleanup callback in bus_type The bus_type structure defines dma_configure() callback for bus drivers to configure DMA on the devices. This adds the paired dma_cleanup() callback and calls it during driver unbinding so that bus drivers can do some cleanup work. One use case for this paired DMA callbacks is for the bus driver to check for DMA ownership conflicts during driver binding, where multiple devices belonging to a same IOMMU group (the minimum granularity of isolation and protection) may be assigned to kernel drivers or user space respectively. Without this change, for example, the vfio driver has to listen to a bus BOUND_DRIVER event and then BUG_ON() in case of dma ownership conflict. This leads to bad user experience since careless driver binding operation may crash the system if the admin overlooks the group restriction. Aside from bad design, this leads to a security problem as a root user, even with lockdown=integrity, can force the kernel to BUG. With this change, the bus driver could check and set the DMA ownership in driver binding process and fail on ownership conflicts. The DMA ownership should be released during driver unbinding. Signed-off-by: Lu Baolu Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20220418005000.897664-3-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/device/bus.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index a039ab809753..d8b29ccd07e5 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -59,6 +59,8 @@ struct fwnode_handle; * bus supports. * @dma_configure: Called to setup DMA configuration on a device on * this bus. + * @dma_cleanup: Called to cleanup DMA configuration on a device on + * this bus. * @pm: Power management operations of this bus, callback the specific * device driver's pm-ops. * @iommu_ops: IOMMU specific operations for this bus, used to attach IOMMU @@ -103,6 +105,7 @@ struct bus_type { int (*num_vf)(struct device *dev); int (*dma_configure)(struct device *dev); + void (*dma_cleanup)(struct device *dev); const struct dev_pm_ops *pm; -- cgit v1.2.3 From 4a6d9dd564d0e7339fc15ecc5ce66db4ad842be2 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 18 Apr 2022 08:49:52 +0800 Subject: amba: Stop sharing platform_dma_configure() Stop sharing platform_dma_configure() helper as they are about to have their own bus dma_configure callbacks. Signed-off-by: Lu Baolu Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20220418005000.897664-4-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/platform_device.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 7c96f169d274..17fde717df68 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -328,8 +328,6 @@ extern int platform_pm_restore(struct device *dev); #define platform_pm_restore NULL #endif -extern int platform_dma_configure(struct device *dev); - #ifdef CONFIG_PM_SLEEP #define USE_PLATFORM_PM_SLEEP_OPS \ .suspend = platform_pm_suspend, \ -- cgit v1.2.3 From 512881eacfa72c2136b27b9934b7b27504a9efc2 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 18 Apr 2022 08:49:53 +0800 Subject: bus: platform,amba,fsl-mc,PCI: Add device DMA ownership management The devices on platform/amba/fsl-mc/PCI buses could be bound to drivers with the device DMA managed by kernel drivers or user-space applications. Unfortunately, multiple devices may be placed in the same IOMMU group because they cannot be isolated from each other. The DMA on these devices must either be entirely under kernel control or userspace control, never a mixture. Otherwise the driver integrity is not guaranteed because they could access each other through the peer-to-peer accesses which by-pass the IOMMU protection. This checks and sets the default DMA mode during driver binding, and cleanups during driver unbinding. In the default mode, the device DMA is managed by the device driver which handles DMA operations through the kernel DMA APIs (see Documentation/core-api/dma-api.rst). For cases where the devices are assigned for userspace control through the userspace driver framework(i.e. VFIO), the drivers(for example, vfio_pci/ vfio_platfrom etc.) may set a new flag (driver_managed_dma) to skip this default setting in the assumption that the drivers know what they are doing with the device DMA. Calling iommu_device_use_default_domain() before {of,acpi}_dma_configure is currently a problem. As things stand, the IOMMU driver ignored the initial iommu_probe_device() call when the device was added, since at that point it had no fwspec yet. In this situation, {of,acpi}_iommu_configure() are retriggering iommu_probe_device() after the IOMMU driver has seen the firmware data via .of_xlate to learn that it actually responsible for the given device. As the result, before that gets fixed, iommu_use_default_domain() goes at the end, and calls arch_teardown_dma_ops() if it fails. Cc: Greg Kroah-Hartman Cc: Bjorn Helgaas Cc: Stuart Yoder Cc: Laurentiu Tudor Signed-off-by: Lu Baolu Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Reviewed-by: Robin Murphy Tested-by: Eric Auger Link: https://lore.kernel.org/r/20220418005000.897664-5-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/amba/bus.h | 8 ++++++++ include/linux/fsl/mc.h | 8 ++++++++ include/linux/pci.h | 8 ++++++++ include/linux/platform_device.h | 8 ++++++++ 4 files changed, 32 insertions(+) (limited to 'include') diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 6562f543c3e0..2ddce9bcd00e 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -79,6 +79,14 @@ struct amba_driver { void (*remove)(struct amba_device *); void (*shutdown)(struct amba_device *); const struct amba_id *id_table; + /* + * For most device drivers, no need to care about this flag as long as + * all DMAs are handled through the kernel DMA API. For some special + * ones, for example VFIO drivers, they know how to manage the DMA + * themselves and set this flag so that the IOMMU layer will allow them + * to setup and manage their own I/O address space. + */ + bool driver_managed_dma; }; /* diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index 7b6c42bfb660..27efef8affb1 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -32,6 +32,13 @@ struct fsl_mc_io; * @shutdown: Function called at shutdown time to quiesce the device * @suspend: Function called when a device is stopped * @resume: Function called when a device is resumed + * @driver_managed_dma: Device driver doesn't use kernel DMA API for DMA. + * For most device drivers, no need to care about this flag + * as long as all DMAs are handled through the kernel DMA API. + * For some special ones, for example VFIO drivers, they know + * how to manage the DMA themselves and set this flag so that + * the IOMMU layer will allow them to setup and manage their + * own I/O address space. * * Generic DPAA device driver object for device drivers that are registered * with a DPRC bus. This structure is to be embedded in each device-specific @@ -45,6 +52,7 @@ struct fsl_mc_driver { void (*shutdown)(struct fsl_mc_device *dev); int (*suspend)(struct fsl_mc_device *dev, pm_message_t state); int (*resume)(struct fsl_mc_device *dev); + bool driver_managed_dma; }; #define to_fsl_mc_driver(_drv) \ diff --git a/include/linux/pci.h b/include/linux/pci.h index 60adf42460ab..b933d2b08d4d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -895,6 +895,13 @@ struct module; * created once it is bound to the driver. * @driver: Driver model structure. * @dynids: List of dynamically added device IDs. + * @driver_managed_dma: Device driver doesn't use kernel DMA API for DMA. + * For most device drivers, no need to care about this flag + * as long as all DMAs are handled through the kernel DMA API. + * For some special ones, for example VFIO drivers, they know + * how to manage the DMA themselves and set this flag so that + * the IOMMU layer will allow them to setup and manage their + * own I/O address space. */ struct pci_driver { struct list_head node; @@ -913,6 +920,7 @@ struct pci_driver { const struct attribute_group **dev_groups; struct device_driver driver; struct pci_dynids dynids; + bool driver_managed_dma; }; static inline struct pci_driver *to_pci_driver(struct device_driver *drv) diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 17fde717df68..b3d9c744f1e5 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -210,6 +210,14 @@ struct platform_driver { struct device_driver driver; const struct platform_device_id *id_table; bool prevent_deferred_probe; + /* + * For most device drivers, no need to care about this flag as long as + * all DMAs are handled through the kernel DMA API. For some special + * ones, for example VFIO drivers, they know how to manage the DMA + * themselves and set this flag so that the IOMMU layer will allow them + * to setup and manage their own I/O address space. + */ + bool driver_managed_dma; }; #define to_platform_driver(drv) (container_of((drv), struct platform_driver, \ -- cgit v1.2.3 From a5f1bd1afacd7b1e088f93f66af5453df0d8be9a Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 18 Apr 2022 08:50:00 +0800 Subject: iommu: Remove iommu group changes notifier The iommu group changes notifer is not referenced in the tree. Remove it to avoid dead code. Suggested-by: Christoph Hellwig Signed-off-by: Lu Baolu Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20220418005000.897664-12-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 23 ----------------------- 1 file changed, 23 deletions(-) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 77972ef978b5..6ef2df258673 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -407,13 +407,6 @@ static inline const struct iommu_ops *dev_iommu_ops(struct device *dev) return dev->iommu->iommu_dev->ops; } -#define IOMMU_GROUP_NOTIFY_ADD_DEVICE 1 /* Device added */ -#define IOMMU_GROUP_NOTIFY_DEL_DEVICE 2 /* Pre Device removed */ -#define IOMMU_GROUP_NOTIFY_BIND_DRIVER 3 /* Pre Driver bind */ -#define IOMMU_GROUP_NOTIFY_BOUND_DRIVER 4 /* Post Driver bind */ -#define IOMMU_GROUP_NOTIFY_UNBIND_DRIVER 5 /* Pre Driver unbind */ -#define IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER 6 /* Post Driver unbind */ - extern int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops); extern int bus_iommu_probe(struct bus_type *bus); extern bool iommu_present(struct bus_type *bus); @@ -478,10 +471,6 @@ extern int iommu_group_for_each_dev(struct iommu_group *group, void *data, extern struct iommu_group *iommu_group_get(struct device *dev); extern struct iommu_group *iommu_group_ref_get(struct iommu_group *group); extern void iommu_group_put(struct iommu_group *group); -extern int iommu_group_register_notifier(struct iommu_group *group, - struct notifier_block *nb); -extern int iommu_group_unregister_notifier(struct iommu_group *group, - struct notifier_block *nb); extern int iommu_register_device_fault_handler(struct device *dev, iommu_dev_fault_handler_t handler, void *data); @@ -878,18 +867,6 @@ static inline void iommu_group_put(struct iommu_group *group) { } -static inline int iommu_group_register_notifier(struct iommu_group *group, - struct notifier_block *nb) -{ - return -ENODEV; -} - -static inline int iommu_group_unregister_notifier(struct iommu_group *group, - struct notifier_block *nb) -{ - return 0; -} - static inline int iommu_register_device_fault_handler(struct device *dev, iommu_dev_fault_handler_t handler, -- cgit v1.2.3 From 00675017e0aeba5305665c52ded4ddce6a4c0231 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 4 Apr 2022 12:51:40 +0200 Subject: fs: add two trivial lookup helpers Similar to the addition of lookup_one() add a version of lookup_one_unlocked() and lookup_one_positive_unlocked() that take idmapped mounts into account. This is required to port overlay to support idmapped base layers. Cc: Tested-by: Giuseppe Scrivano Reviewed-by: Amir Goldstein Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner (Microsoft) Signed-off-by: Miklos Szeredi --- include/linux/namei.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/namei.h b/include/linux/namei.h index e89329bb3134..caeb08a98536 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -69,6 +69,12 @@ extern struct dentry *lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int); extern struct dentry *lookup_positive_unlocked(const char *, struct dentry *, int); struct dentry *lookup_one(struct user_namespace *, const char *, struct dentry *, int); +struct dentry *lookup_one_unlocked(struct user_namespace *mnt_userns, + const char *name, struct dentry *base, + int len); +struct dentry *lookup_one_positive_unlocked(struct user_namespace *mnt_userns, + const char *name, + struct dentry *base, int len); extern int follow_down_one(struct path *); extern int follow_down(struct path *); -- cgit v1.2.3 From dbde6d0c7a5a462a1767a07c28eadd2c3dd08fb2 Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Thu, 28 Apr 2022 16:51:05 +0200 Subject: hv_sock: Add validation for untrusted Hyper-V values For additional robustness in the face of Hyper-V errors or malicious behavior, validate all values that originate from packets that Hyper-V has sent to the guest in the host-to-guest ring buffer. Ensure that invalid values cannot cause data being copied out of the bounds of the source buffer in hvs_stream_dequeue(). Signed-off-by: Andrea Parri (Microsoft) Reviewed-by: Michael Kelley Reviewed-by: Stefano Garzarella Link: https://lore.kernel.org/r/20220428145107.7878-4-parri.andrea@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 460a716f4748..a01c9fd0a334 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1696,6 +1696,11 @@ static inline u32 hv_pkt_datalen(const struct vmpacket_descriptor *desc) return (desc->len8 << 3) - (desc->offset8 << 3); } +/* Get packet length associated with descriptor */ +static inline u32 hv_pkt_len(const struct vmpacket_descriptor *desc) +{ + return desc->len8 << 3; +} struct vmpacket_descriptor * hv_pkt_iter_first_raw(struct vmbus_channel *channel); -- cgit v1.2.3 From da795eb239d9e9496812e22cb582d38a71e0789a Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Thu, 28 Apr 2022 16:51:06 +0200 Subject: Drivers: hv: vmbus: Accept hv_sock offers in isolated guests So that isolated guests can communicate with the host via hv_sock channels. Signed-off-by: Andrea Parri (Microsoft) Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20220428145107.7878-5-parri.andrea@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index a01c9fd0a334..b028905d8334 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1064,10 +1064,14 @@ u64 vmbus_request_addr_match(struct vmbus_channel *channel, u64 trans_id, u64 rqst_addr); u64 vmbus_request_addr(struct vmbus_channel *channel, u64 trans_id); +static inline bool is_hvsock_offer(const struct vmbus_channel_offer_channel *o) +{ + return !!(o->offer.chn_flags & VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER); +} + static inline bool is_hvsock_channel(const struct vmbus_channel *c) { - return !!(c->offermsg.offer.chn_flags & - VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER); + return is_hvsock_offer(&c->offermsg); } static inline bool is_sub_channel(const struct vmbus_channel *c) -- cgit v1.2.3 From 1c9de08f7f952b4101f092802581344033d84429 Mon Sep 17 00:00:00 2001 From: "Andrea Parri (Microsoft)" Date: Thu, 28 Apr 2022 16:51:07 +0200 Subject: Drivers: hv: vmbus: Refactor the ring-buffer iterator functions With no users of hv_pkt_iter_next_raw() and no "external" users of hv_pkt_iter_first_raw(), the iterator functions can be refactored and simplified to remove some indirection/code. Signed-off-by: Andrea Parri (Microsoft) Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20220428145107.7878-6-parri.andrea@gmail.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 35 ++++------------------------------- 1 file changed, 4 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index b028905d8334..c440c45887c2 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1706,55 +1706,28 @@ static inline u32 hv_pkt_len(const struct vmpacket_descriptor *desc) return desc->len8 << 3; } -struct vmpacket_descriptor * -hv_pkt_iter_first_raw(struct vmbus_channel *channel); - struct vmpacket_descriptor * hv_pkt_iter_first(struct vmbus_channel *channel); struct vmpacket_descriptor * __hv_pkt_iter_next(struct vmbus_channel *channel, - const struct vmpacket_descriptor *pkt, - bool copy); + const struct vmpacket_descriptor *pkt); void hv_pkt_iter_close(struct vmbus_channel *channel); static inline struct vmpacket_descriptor * -hv_pkt_iter_next_pkt(struct vmbus_channel *channel, - const struct vmpacket_descriptor *pkt, - bool copy) +hv_pkt_iter_next(struct vmbus_channel *channel, + const struct vmpacket_descriptor *pkt) { struct vmpacket_descriptor *nxt; - nxt = __hv_pkt_iter_next(channel, pkt, copy); + nxt = __hv_pkt_iter_next(channel, pkt); if (!nxt) hv_pkt_iter_close(channel); return nxt; } -/* - * Get next packet descriptor without copying it out of the ring buffer - * If at end of list, return NULL and update host. - */ -static inline struct vmpacket_descriptor * -hv_pkt_iter_next_raw(struct vmbus_channel *channel, - const struct vmpacket_descriptor *pkt) -{ - return hv_pkt_iter_next_pkt(channel, pkt, false); -} - -/* - * Get next packet descriptor from iterator - * If at end of list, return NULL and update host. - */ -static inline struct vmpacket_descriptor * -hv_pkt_iter_next(struct vmbus_channel *channel, - const struct vmpacket_descriptor *pkt) -{ - return hv_pkt_iter_next_pkt(channel, pkt, true); -} - #define foreach_vmbus_pkt(pkt, channel) \ for (pkt = hv_pkt_iter_first(channel); pkt; \ pkt = hv_pkt_iter_next(channel, pkt)) -- cgit v1.2.3 From 6043257b1de069fbb5a2a52d7211c0275bc8c0e0 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 11 Apr 2022 12:16:05 -0300 Subject: iommu: Introduce the domain op enforce_cache_coherency() This new mechanism will replace using IOMMU_CAP_CACHE_COHERENCY and IOMMU_CACHE to control the no-snoop blocking behavior of the IOMMU. Currently only Intel and AMD IOMMUs are known to support this feature. They both implement it as an IOPTE bit, that when set, will cause PCIe TLPs to that IOVA with the no-snoop bit set to be treated as though the no-snoop bit was clear. The new API is triggered by calling enforce_cache_coherency() before mapping any IOVA to the domain which globally switches on no-snoop blocking. This allows other implementations that might block no-snoop globally and outside the IOPTE - AMD also documents such a HW capability. Leave AMD out of sync with Intel and have it block no-snoop even for in-kernel users. This can be trivially resolved in a follow up patch. Only VFIO needs to call this API because it does not have detailed control over the device to avoid requesting no-snoop behavior at the device level. Other places using domains with real kernel drivers should simply avoid asking their devices to set the no-snoop bit. Reviewed-by: Lu Baolu Reviewed-by: Kevin Tian Acked-by: Robin Murphy Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/1-v3-2cf356649677+a32-intel_no_snoop_jgg@nvidia.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 + include/linux/iommu.h | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 2f9891cb3d00..4c2baf2446c2 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -540,6 +540,7 @@ struct dmar_domain { u8 has_iotlb_device: 1; u8 iommu_coherency: 1; /* indicate coherency of iommu access */ u8 iommu_snooping: 1; /* indicate snooping control feature */ + u8 force_snooping : 1; /* Create IOPTEs with snoop control */ struct list_head devices; /* all devices' list */ struct iova_domain iovad; /* iova's that belong to this domain */ diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 4123693ae319..c7ad6b10e261 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -274,6 +274,9 @@ struct iommu_ops { * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush * queue * @iova_to_phys: translate iova to physical address + * @enforce_cache_coherency: Prevent any kind of DMA from bypassing IOMMU_CACHE, + * including no-snoop TLPs on PCIe or other platform + * specific mechanisms. * @enable_nesting: Enable nesting * @set_pgtable_quirks: Set io page table quirks (IO_PGTABLE_QUIRK_*) * @free: Release the domain after use. @@ -302,6 +305,7 @@ struct iommu_domain_ops { phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova); + bool (*enforce_cache_coherency)(struct iommu_domain *domain); int (*enable_nesting)(struct iommu_domain *domain); int (*set_pgtable_quirks)(struct iommu_domain *domain, unsigned long quirks); -- cgit v1.2.3 From 71cfafda9c9bd9812cdb62ddb94daf65a1af12c1 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 11 Apr 2022 12:16:06 -0300 Subject: vfio: Move the Intel no-snoop control off of IOMMU_CACHE IOMMU_CACHE means "normal DMA to this iommu_domain's IOVA should be cache coherent" and is used by the DMA API. The definition allows for special non-coherent DMA to exist - ie processing of the no-snoop flag in PCIe TLPs - so long as this behavior is opt-in by the device driver. The flag is mainly used by the DMA API to synchronize the IOMMU setting with the expected cache behavior of the DMA master. eg based on dev_is_dma_coherent() in some case. For Intel IOMMU IOMMU_CACHE was redefined to mean 'force all DMA to be cache coherent' which has the practical effect of causing the IOMMU to ignore the no-snoop bit in a PCIe TLP. x86 platforms are always IOMMU_CACHE, so Intel should ignore this flag. Instead use the new domain op enforce_cache_coherency() which causes every IOPTE created in the domain to have the no-snoop blocking behavior. Reconfigure VFIO to always use IOMMU_CACHE and call enforce_cache_coherency() to operate the special Intel behavior. Remove the IOMMU_CACHE test from Intel IOMMU. Ultimately VFIO plumbs the result of enforce_cache_coherency() back into the x86 platform code through kvm_arch_register_noncoherent_dma() which controls if the WBINVD instruction is available in the guest. No other archs implement kvm_arch_register_noncoherent_dma() nor are there any other known consumers of VFIO_DMA_CC_IOMMU that might be affected by the user visible result change on non-x86 archs. Reviewed-by: Kevin Tian Reviewed-by: Lu Baolu Acked-by: Alex Williamson Acked-by: Robin Murphy Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/2-v3-2cf356649677+a32-intel_no_snoop_jgg@nvidia.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 4c2baf2446c2..72e5d7900e71 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -539,7 +539,6 @@ struct dmar_domain { u8 has_iotlb_device: 1; u8 iommu_coherency: 1; /* indicate coherency of iommu access */ - u8 iommu_snooping: 1; /* indicate snooping control feature */ u8 force_snooping : 1; /* Create IOPTEs with snoop control */ struct list_head devices; /* all devices' list */ -- cgit v1.2.3 From f78dc1dad829e505d83e33dc0879887f074c52e1 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 11 Apr 2022 12:16:07 -0300 Subject: iommu: Redefine IOMMU_CAP_CACHE_COHERENCY as the cap flag for IOMMU_CACHE While the comment was correct that this flag was intended to convey the block no-snoop support in the IOMMU, it has become widely implemented and used to mean the IOMMU supports IOMMU_CACHE as a map flag. Only the Intel driver was different. Now that the Intel driver is using enforce_cache_coherency() update the comment to make it clear that IOMMU_CAP_CACHE_COHERENCY is only about IOMMU_CACHE. Fix the Intel driver to return true since IOMMU_CACHE always works. The two places that test this flag, usnic and vdpa, are both assigning userspace pages to a driver controlled iommu_domain and require IOMMU_CACHE behavior as they offer no way for userspace to synchronize caches. Reviewed-by: Kevin Tian Reviewed-by: Lu Baolu Acked-by: Robin Murphy Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/3-v3-2cf356649677+a32-intel_no_snoop_jgg@nvidia.com Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index c7ad6b10e261..575ab27ede5b 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -103,8 +103,7 @@ static inline bool iommu_is_dma_domain(struct iommu_domain *domain) } enum iommu_cap { - IOMMU_CAP_CACHE_COHERENCY, /* IOMMU can enforce cache coherent DMA - transactions */ + IOMMU_CAP_CACHE_COHERENCY, /* IOMMU_CACHE is supported */ IOMMU_CAP_INTR_REMAP, /* IOMMU supports interrupt isolation */ IOMMU_CAP_NOEXEC, /* IOMMU_NOEXEC flag */ IOMMU_CAP_PRE_BOOT_PROTECTION, /* Firmware says it used the IOMMU for -- cgit v1.2.3 From 992be5d3c818fcc277db246cb409659ca82abdbe Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Wed, 30 Mar 2022 16:05:35 +0100 Subject: firmware: arm_scmi: Make name_get operations return a const A few protocol operations are available that returns a pointer to an internal character array representing resource name. Make those functions return a const pointer to such array. Link: https://lore.kernel.org/r/20220330150551.2573938-7-cristian.marussi@arm.com Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index b87551f41f9f..ced37d1de1fe 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -146,7 +146,8 @@ struct scmi_perf_proto_ops { */ struct scmi_power_proto_ops { int (*num_domains_get)(const struct scmi_protocol_handle *ph); - char *(*name_get)(const struct scmi_protocol_handle *ph, u32 domain); + const char *(*name_get)(const struct scmi_protocol_handle *ph, + u32 domain); #define SCMI_POWER_STATE_TYPE_SHIFT 30 #define SCMI_POWER_STATE_ID_MASK (BIT(28) - 1) #define SCMI_POWER_STATE_PARAM(type, id) \ @@ -484,7 +485,8 @@ struct scmi_sensor_proto_ops { */ struct scmi_reset_proto_ops { int (*num_domains_get)(const struct scmi_protocol_handle *ph); - char *(*name_get)(const struct scmi_protocol_handle *ph, u32 domain); + const char *(*name_get)(const struct scmi_protocol_handle *ph, + u32 domain); int (*latency_get)(const struct scmi_protocol_handle *ph, u32 domain); int (*reset)(const struct scmi_protocol_handle *ph, u32 domain); int (*assert)(const struct scmi_protocol_handle *ph, u32 domain); -- cgit v1.2.3 From b260fccaebdc2c838e62aaef24fedf497f181d10 Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Wed, 30 Mar 2022 16:05:40 +0100 Subject: firmware: arm_scmi: Add SCMI v3.1 protocol extended names support Using the common protocol helper implementation add support for all new SCMIv3.1 extended names commands related to all protocols with the exception of SENSOR_AXIS_GET_NAME. Link: https://lore.kernel.org/r/20220330150551.2573938-12-cristian.marussi@arm.com Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index ced37d1de1fe..56e6f13355b8 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -13,7 +13,7 @@ #include #include -#define SCMI_MAX_STR_SIZE 16 +#define SCMI_MAX_STR_SIZE 64 #define SCMI_MAX_NUM_RATES 16 /** -- cgit v1.2.3 From 7aa75496ea1f38dfd99b93c66f8d9bc525d11efc Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Wed, 30 Mar 2022 16:05:48 +0100 Subject: firmware: arm_scmi: Add SCMI v3.1 clock notifications Add SCMI v3.1 clock pre and post notifications. Link: https://lore.kernel.org/r/20220330150551.2573938-20-cristian.marussi@arm.com Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 56e6f13355b8..0e20acc80d50 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -44,6 +44,8 @@ struct scmi_clock_info { char name[SCMI_MAX_STR_SIZE]; unsigned int enable_latency; bool rate_discrete; + bool rate_changed_notifications; + bool rate_change_requested_notifications; union { struct { int num_rates; @@ -744,6 +746,8 @@ void scmi_protocol_unregister(const struct scmi_protocol *proto); /* SCMI Notification API - Custom Event Reports */ enum scmi_notification_events { SCMI_EVENT_POWER_STATE_CHANGED = 0x0, + SCMI_EVENT_CLOCK_RATE_CHANGED = 0x0, + SCMI_EVENT_CLOCK_RATE_CHANGE_REQUESTED = 0x1, SCMI_EVENT_PERFORMANCE_LIMITS_CHANGED = 0x0, SCMI_EVENT_PERFORMANCE_LEVEL_CHANGED = 0x1, SCMI_EVENT_SENSOR_TRIP_POINT_EVENT = 0x0, @@ -760,6 +764,13 @@ struct scmi_power_state_changed_report { unsigned int power_state; }; +struct scmi_clock_rate_notif_report { + ktime_t timestamp; + unsigned int agent_id; + unsigned int clock_id; + unsigned long long rate; +}; + struct scmi_system_power_state_notifier_report { ktime_t timestamp; unsigned int agent_id; -- cgit v1.2.3 From 4c74701b1eb7636eb0cdd66b488b42920105122a Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Wed, 30 Mar 2022 16:05:49 +0100 Subject: firmware: arm_scmi: Add SCMI v3.1 VOLTAGE_LEVEL_SET_COMPLETE Add SCMI v3.1 voltage protocol support for asynchronous VOLTAGE_LEVEL_SET command. Note that, if a voltage domain is advertised to support the asynchronous version of VOLTAGE_LEVEL_SET, the command will be issued asynchronously unless explicitly requested to use the synchronous version by setting the mode to SCMI_VOLTAGE_LEVEL_SET_SYNC when calling voltage_ops->level_set. The SCMI regulator driver level_set invocation has been left unchanged so that it will transparently use the asynchronous version if available. Link: https://lore.kernel.org/r/20220330150551.2573938-21-cristian.marussi@arm.com Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 0e20acc80d50..1c58646ba381 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -495,6 +495,11 @@ struct scmi_reset_proto_ops { int (*deassert)(const struct scmi_protocol_handle *ph, u32 domain); }; +enum scmi_voltage_level_mode { + SCMI_VOLTAGE_LEVEL_SET_AUTO, + SCMI_VOLTAGE_LEVEL_SET_SYNC, +}; + /** * struct scmi_voltage_info - describe one available SCMI Voltage Domain * @@ -507,7 +512,8 @@ struct scmi_reset_proto_ops { * supported voltage level * @negative_volts_allowed: True if any of the entries of @levels_uv represent * a negative voltage. - * @attributes: represents Voltage Domain advertised attributes + * @async_level_set: True when the voltage domain supports asynchronous level + * set commands. * @name: name assigned to the Voltage Domain by platform * @num_levels: number of total entries in @levels_uv. * @levels_uv: array of entries describing the available voltage levels for @@ -517,7 +523,7 @@ struct scmi_voltage_info { unsigned int id; bool segmented; bool negative_volts_allowed; - unsigned int attributes; + bool async_level_set; char name[SCMI_MAX_STR_SIZE]; unsigned int num_levels; #define SCMI_VOLTAGE_SEGMENT_LOW 0 @@ -548,7 +554,7 @@ struct scmi_voltage_proto_ops { int (*config_get)(const struct scmi_protocol_handle *ph, u32 domain_id, u32 *config); int (*level_set)(const struct scmi_protocol_handle *ph, u32 domain_id, - u32 flags, s32 volt_uV); + enum scmi_voltage_level_mode mode, s32 volt_uV); int (*level_get)(const struct scmi_protocol_handle *ph, u32 domain_id, s32 *volt_uV); }; -- cgit v1.2.3 From ac3e62f51b3fbda78a44fff62ece8f11d8f08a25 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Mon, 7 Feb 2022 15:38:40 +0100 Subject: iio: core: Clarify the modes As part of a previous discussion with Jonathan Cameron [1], it appeared necessary to clarify the meaning of each mode so that new developers could understand better what they should use or not use and when. The idea of renaming these modes as been let aside because naming is a big deal and requires a lot of thinking. So for now let's focus on correctly explaining what each mode implies. [1] https://lore.kernel.org/linux-iio/20210930165510.2295e6c4@jic23-huawei/ Suggested-by: Jonathan Cameron Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/r/20220207143840.707510-14-miquel.raynal@bootlin.com Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 49 ++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 48 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 85cb924debd9..233d2e6b7721 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -315,7 +315,54 @@ static inline bool iio_channel_has_available(const struct iio_chan_spec *chan, s64 iio_get_time_ns(const struct iio_dev *indio_dev); unsigned int iio_get_time_res(const struct iio_dev *indio_dev); -/* Device operating modes */ +/* + * Device operating modes + * @INDIO_DIRECT_MODE: There is an access to either: + * a) The last single value available for devices that do not provide + * on-demand reads. + * b) A new value after performing an on-demand read otherwise. + * On most devices, this is a single-shot read. On some devices with data + * streams without an 'on-demand' function, this might also be the 'last value' + * feature. Above all, this mode internally means that we are not in any of the + * other modes, and sysfs reads should work. + * Device drivers should inform the core if they support this mode. + * @INDIO_BUFFER_TRIGGERED: Common mode when dealing with kfifo buffers. + * It indicates that an explicit trigger is required. This requests the core to + * attach a poll function when enabling the buffer, which is indicated by the + * _TRIGGERED suffix. + * The core will ensure this mode is set when registering a triggered buffer + * with iio_triggered_buffer_setup(). + * @INDIO_BUFFER_SOFTWARE: Another kfifo buffer mode, but not event triggered. + * No poll function can be attached because there is no triggered infrastructure + * we can use to cause capture. There is a kfifo that the driver will fill, but + * not "only one scan at a time". Typically, hardware will have a buffer that + * can hold multiple scans. Software may read one or more scans at a single time + * and push the available data to a Kfifo. This means the core will not attach + * any poll function when enabling the buffer. + * The core will ensure this mode is set when registering a simple kfifo buffer + * with devm_iio_kfifo_buffer_setup(). + * @INDIO_BUFFER_HARDWARE: For specific hardware, if unsure do not use this mode. + * Same as above but this time the buffer is not a kfifo where we have direct + * access to the data. Instead, the consumer driver must access the data through + * non software visible channels (or DMA when there is no demux possible in + * software) + * The core will ensure this mode is set when registering a dmaengine buffer + * with devm_iio_dmaengine_buffer_setup(). + * @INDIO_EVENT_TRIGGERED: Very unusual mode. + * Triggers usually refer to an external event which will start data capture. + * Here it is kind of the opposite as, a particular state of the data might + * produce an event which can be considered as an event. We don't necessarily + * have access to the data itself, but to the event produced. For example, this + * can be a threshold detector. The internal path of this mode is very close to + * the INDIO_BUFFER_TRIGGERED mode. + * The core will ensure this mode is set when registering a triggered event. + * @INDIO_HARDWARE_TRIGGERED: Very unusual mode. + * Here, triggers can result in data capture and can be routed to multiple + * hardware components, which make them close to regular triggers in the way + * they must be managed by the core, but without the entire interrupts/poll + * functions burden. Interrupts are irrelevant as the data flow is hardware + * mediated and distributed. + */ #define INDIO_DIRECT_MODE 0x01 #define INDIO_BUFFER_TRIGGERED 0x02 #define INDIO_BUFFER_SOFTWARE 0x04 -- cgit v1.2.3 From dbfb5f94e084287f0a3f23d14ef6692c43c98855 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 26 Apr 2022 16:35:06 -0700 Subject: dt-bindings: power: rpmpd: Add sc8280xp RPMh power-domains The sc8280xp has 13 power-domains controlled through the RPMh, document the compatible and provide definitions for the power-domains - and their active-only variants where applicable. The SA8540p differs slightly in the power domains exposed, so add a separate compatible for this, but reuse the constants to allow sharing the DeviceTree source. Signed-off-by: Bjorn Andersson Acked-by: Krzysztof Kozlowski Reviewed-by: Johan Hovold Link: https://lore.kernel.org/r/20220426233508.1762345-2-bjorn.andersson@linaro.org --- include/dt-bindings/power/qcom-rpmpd.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/power/qcom-rpmpd.h b/include/dt-bindings/power/qcom-rpmpd.h index 0a8978d0c78c..6cce5b7aa940 100644 --- a/include/dt-bindings/power/qcom-rpmpd.h +++ b/include/dt-bindings/power/qcom-rpmpd.h @@ -125,6 +125,24 @@ #define SC8180X_MX 9 #define SC8180X_MX_AO 10 +/* SC8280XP Power Domain Indexes */ +#define SC8280XP_CX 0 +#define SC8280XP_CX_AO 1 +#define SC8280XP_DDR 2 +#define SC8280XP_EBI 3 +#define SC8280XP_GFX 4 +#define SC8280XP_LCX 5 +#define SC8280XP_LMX 6 +#define SC8280XP_MMCX 7 +#define SC8280XP_MMCX_AO 8 +#define SC8280XP_MSS 9 +#define SC8280XP_MX 10 +#define SC8280XP_MXC 12 +#define SC8280XP_MX_AO 11 +#define SC8280XP_NSP 13 +#define SC8280XP_QPHY 14 +#define SC8280XP_XO 15 + /* SDM845 Power Domain performance levels */ #define RPMH_REGULATOR_LEVEL_RETENTION 16 #define RPMH_REGULATOR_LEVEL_MIN_SVS 48 -- cgit v1.2.3 From 6fd1d51cfa253b5ee7dae18d7cf1df830e9b6137 Mon Sep 17 00:00:00 2001 From: Erin MacNeil Date: Wed, 27 Apr 2022 16:02:37 -0400 Subject: net: SO_RCVMARK socket option for SO_MARK with recvmsg() Adding a new socket option, SO_RCVMARK, to indicate that SO_MARK should be included in the ancillary data returned by recvmsg(). Renamed the sock_recv_ts_and_drops() function to sock_recv_cmsgs(). Signed-off-by: Erin MacNeil Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Acked-by: Marc Kleine-Budde Link: https://lore.kernel.org/r/20220427200259.2564-1-lnx.erin@gmail.com Signed-off-by: Jakub Kicinski --- include/net/sock.h | 18 ++++++++++-------- include/uapi/asm-generic/socket.h | 2 ++ 2 files changed, 12 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index f9f8ecae0f8d..663041b92c21 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -893,6 +893,7 @@ enum sock_flags { SOCK_TXTIME, SOCK_XDP, /* XDP is attached */ SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */ + SOCK_RCVMARK, /* Receive SO_MARK ancillary data with packet */ }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) @@ -2647,20 +2648,21 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) __sock_recv_wifi_status(msg, sk, skb); } -void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, - struct sk_buff *skb); +void __sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb); #define SK_DEFAULT_STAMP (-1L * NSEC_PER_SEC) -static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, - struct sk_buff *skb) +static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb) { -#define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL) | \ - (1UL << SOCK_RCVTSTAMP)) +#define FLAGS_RECV_CMSGS ((1UL << SOCK_RXQ_OVFL) | \ + (1UL << SOCK_RCVTSTAMP) | \ + (1UL << SOCK_RCVMARK)) #define TSFLAGS_ANY (SOF_TIMESTAMPING_SOFTWARE | \ SOF_TIMESTAMPING_RAW_HARDWARE) - if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY) - __sock_recv_ts_and_drops(msg, sk, skb); + if (sk->sk_flags & FLAGS_RECV_CMSGS || sk->sk_tsflags & TSFLAGS_ANY) + __sock_recv_cmsgs(msg, sk, skb); else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP))) sock_write_timestamp(sk, skb->tstamp); else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP)) diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 467ca2f28760..638230899e98 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -130,6 +130,8 @@ #define SO_TXREHASH 74 +#define SO_RCVMARK 75 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) -- cgit v1.2.3 From cc10eee95204579fcd66fd5965073fdcbf629676 Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Wed, 13 Apr 2022 01:36:16 -0600 Subject: PCI/ACPI: add a helper for retrieving _OSC Control DWORDs During _OSC negotiation, when the 'Control' DWORD is needed from the result buffer after running _OSC, a couple of places performed manual pointer arithmetic to offset into the right spot in the raw buffer. Add a acpi_osc_ctx_get_pci_control() helper to use the #define'd DWORD offsets to fetch the DWORDs needed from @acpi_osc_context, and replace the above instances of the open-coded arithmetic. Cc: "Rafael J. Wysocki" Suggested-by: Davidlohr Bueso Acked-by: Rafael J. Wysocki Reviewed-by: Rafael J. Wysocki Reviewed-by: Davidlohr Bueso Reviewed by: Adam Manzanares Signed-off-by: Vishal Verma Link: https://lore.kernel.org/r/20220413073618.291335-2-vishal.l.verma@intel.com Signed-off-by: Dan Williams --- include/linux/acpi.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index d7136d13aa44..04e5a038dd57 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -608,6 +608,13 @@ extern u32 osc_sb_native_usb4_control; #define OSC_PCI_EXPRESS_LTR_CONTROL 0x00000020 #define OSC_PCI_EXPRESS_DPC_CONTROL 0x00000080 +static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context) +{ + u32 *ret = context->ret.pointer; + + return ret[OSC_CONTROL_DWORD]; +} + #define ACPI_GSB_ACCESS_ATTRIB_QUICK 0x00000002 #define ACPI_GSB_ACCESS_ATTRIB_SEND_RCV 0x00000004 #define ACPI_GSB_ACCESS_ATTRIB_BYTE 0x00000006 @@ -1004,6 +1011,12 @@ static inline int acpi_register_wakeup_handler(int wake_irq, static inline void acpi_unregister_wakeup_handler( bool (*wakeup)(void *context), void *context) { } +struct acpi_osc_context; +static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context) +{ + return 0; +} + #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC -- cgit v1.2.3 From 241d26bc26add2e2867c546f7474902406d37c60 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 13 Apr 2022 01:36:17 -0600 Subject: PCI/ACPI: Prefer CXL _OSC instead of PCIe _OSC for CXL host bridges OB In preparation for negotiating OS control of CXL _OSC features, do the minimal enabling to use CXL _OSC to handle the base PCIe feature negotiation. Recall that CXL _OSC is a super-set of PCIe _OSC and the CXL 2.0 specification mandates: "If a CXL Host Bridge device exposes CXL _OSC, CXL aware OSPM shall evaluate CXL _OSC and not evaluate PCIe _OSC." Rather than pass a boolean flag alongside @root to all the helper functions that need to consider PCIe specifics, add is_pcie() and is_cxl() helper functions to check the flavor of @root. This also allows for dynamic fallback to PCIe _OSC in cases where an attempt to use CXL _OXC fails. This can happen on CXL 1.1 platforms that publish ACPI0016 devices to indicate CXL host bridges, but do not publish the optional CXL _OSC method. CXL _OSC is mandatory for CXL 2.0 hosts. Cc: Bjorn Helgaas Cc: "Rafael J. Wysocki" Cc: Robert Moore Reviewed-by: Jonathan Cameron Reviewed-by: Rafael J. Wysocki Reviewed-by: Davidlohr Bueso Signed-off-by: Vishal Verma Link: https://lore.kernel.org/r/20220413073618.291335-3-vishal.l.verma@intel.com Signed-off-by: Dan Williams --- include/acpi/acpi_bus.h | 6 ++++++ include/linux/acpi.h | 4 ++++ 2 files changed, 10 insertions(+) (limited to 'include') diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index c4b78c21d793..305ebf2a3fa7 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -582,10 +582,16 @@ int unregister_acpi_bus_type(struct acpi_bus_type *); int acpi_bind_one(struct device *dev, struct acpi_device *adev); int acpi_unbind_one(struct device *dev); +enum acpi_bridge_type { + ACPI_BRIDGE_TYPE_PCIE = 1, + ACPI_BRIDGE_TYPE_CXL, +}; + struct acpi_pci_root { struct acpi_device * device; struct pci_bus *bus; u16 segment; + int bridge_type; struct resource secondary; /* downstream bus range */ u32 osc_support_set; /* _OSC state of support bits */ diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 04e5a038dd57..82d91d9ccce5 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -550,6 +550,10 @@ struct acpi_osc_context { acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); +/* Number of _OSC capability DWORDS depends on bridge type */ +#define OSC_PCI_CAPABILITY_DWORDS 3 +#define OSC_CXL_CAPABILITY_DWORDS 5 + /* Indexes into _OSC Capabilities Buffer (DWORDs 2 & 3 are device-specific) */ #define OSC_QUERY_DWORD 0 /* DWORD 1 */ #define OSC_SUPPORT_DWORD 1 /* DWORD 2 */ -- cgit v1.2.3 From 56368029d93bbb3246ee2e03268fa6dd9754be05 Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Wed, 13 Apr 2022 01:36:18 -0600 Subject: PCI/ACPI: negotiate CXL _OSC Add full support for negotiating _OSC as defined in the CXL 2.0 spec, as applicable to CXL-enabled platforms. Advertise support for the CXL features we support - 'CXL 2.0 port/device register access', 'Protocol Error Reporting', and 'CXL Native Hot Plug'. Request control for 'CXL Memory Error Reporting'. The requests are dependent on CONFIG_* based prerequisites, and prior PCI enabling, similar to how the standard PCI _OSC bits are determined. The CXL specification does not define any additional constraints on the hotplug flow beyond PCIe native hotplug, so a kernel that supports native PCIe hotplug, supports CXL hotplug. For error handling protocol and link errors just use PCIe AER. There is nascent support for amending AER events with CXL specific status [1], but there's otherwise no additional OS responsibility for CXL errors beyond PCIe AER. CXL Memory Errors behave the same as typical memory errors so CONFIG_MEMORY_FAILURE is sufficient to indicate support to platform firmware. [1]: https://lore.kernel.org/linux-cxl/164740402242.3912056.8303625392871313860.stgit@dwillia2-desk3.amr.corp.intel.com/ Cc: Bjorn Helgaas Cc: "Rafael J. Wysocki" Cc: Robert Moore Cc: Dan Williams Reviewed-by: Rafael J. Wysocki Reviewed-by: Davidlohr Bueso Signed-off-by: Vishal Verma Link: https://lore.kernel.org/r/20220413073618.291335-4-vishal.l.verma@intel.com Signed-off-by: Dan Williams --- include/acpi/acpi_bus.h | 6 ++++-- include/linux/acpi.h | 25 ++++++++++++++++++++++++- 2 files changed, 28 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 305ebf2a3fa7..4c463ae2777b 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -594,8 +594,10 @@ struct acpi_pci_root { int bridge_type; struct resource secondary; /* downstream bus range */ - u32 osc_support_set; /* _OSC state of support bits */ - u32 osc_control_set; /* _OSC state of control bits */ + u32 osc_support_set; /* _OSC state of support bits */ + u32 osc_control_set; /* _OSC state of control bits */ + u32 osc_ext_support_set; /* _OSC state of extended support bits */ + u32 osc_ext_control_set; /* _OSC state of extended control bits */ phys_addr_t mcfg_addr; }; diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 82d91d9ccce5..378a431666b3 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -554,10 +554,12 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); #define OSC_PCI_CAPABILITY_DWORDS 3 #define OSC_CXL_CAPABILITY_DWORDS 5 -/* Indexes into _OSC Capabilities Buffer (DWORDs 2 & 3 are device-specific) */ +/* Indexes into _OSC Capabilities Buffer (DWORDs 2 to 5 are device-specific) */ #define OSC_QUERY_DWORD 0 /* DWORD 1 */ #define OSC_SUPPORT_DWORD 1 /* DWORD 2 */ #define OSC_CONTROL_DWORD 2 /* DWORD 3 */ +#define OSC_EXT_SUPPORT_DWORD 3 /* DWORD 4 */ +#define OSC_EXT_CONTROL_DWORD 4 /* DWORD 5 */ /* _OSC Capabilities DWORD 1: Query/Control and Error Returns (generic) */ #define OSC_QUERY_ENABLE 0x00000001 /* input */ @@ -612,6 +614,15 @@ extern u32 osc_sb_native_usb4_control; #define OSC_PCI_EXPRESS_LTR_CONTROL 0x00000020 #define OSC_PCI_EXPRESS_DPC_CONTROL 0x00000080 +/* CXL _OSC: Capabilities DWORD 4: Support Field */ +#define OSC_CXL_1_1_PORT_REG_ACCESS_SUPPORT 0x00000001 +#define OSC_CXL_2_0_PORT_DEV_REG_ACCESS_SUPPORT 0x00000002 +#define OSC_CXL_PROTOCOL_ERR_REPORTING_SUPPORT 0x00000004 +#define OSC_CXL_NATIVE_HP_SUPPORT 0x00000008 + +/* CXL _OSC: Capabilities DWORD 5: Control Field */ +#define OSC_CXL_ERROR_REPORTING_CONTROL 0x00000001 + static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context) { u32 *ret = context->ret.pointer; @@ -619,6 +630,13 @@ static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context) return ret[OSC_CONTROL_DWORD]; } +static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context) +{ + u32 *ret = context->ret.pointer; + + return ret[OSC_EXT_CONTROL_DWORD]; +} + #define ACPI_GSB_ACCESS_ATTRIB_QUICK 0x00000002 #define ACPI_GSB_ACCESS_ATTRIB_SEND_RCV 0x00000004 #define ACPI_GSB_ACCESS_ATTRIB_BYTE 0x00000006 @@ -1021,6 +1039,11 @@ static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context) return 0; } +static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context) +{ + return 0; +} + #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC -- cgit v1.2.3 From d864b8ea6468cf1dce614a58eec92a23d8e07fec Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 26 Apr 2022 12:22:44 -0700 Subject: cxl/acpi: Add root device lockdep validation The CXL "root" device, ACPI0017, is an attach point for coordinating platform level CXL resources and is the parent device for a CXL port topology tree. As such it has distinct locking rules relative to other CXL subsystem objects, but because it is an ACPI device the lock class is established well before it is given to the cxl_acpi driver. However, the lockdep API does support changing the lock class "live" for situations like this. Add a device_lock_set_class() helper that a driver can use in ->probe() to set a custom lock class, and device_lock_reset_class() to return to the default "no validate" class before the custom lock class key goes out of scope after ->remove(). Note the helpers are all macros to support dead code elimination in the CONFIG_PROVE_LOCKING=n case, however device_set_lock_class() still needs #ifdef CONFIG_PROVE_LOCKING since lockdep_match_class() explicitly does not have a helper in the CONFIG_PROVE_LOCKING=n case (see comment in lockdep.h). The lockdep API needs 2 small tweaks to prevent "unused" warnings for the @key argument to lock_set_class(), and a new lock_set_novalidate_class() is added to supplement lockdep_set_novalidate_class() in the cases where the lock class is converted while the lock is held. Suggested-by: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Ingo Molnar Cc: Will Deacon Cc: Waiman Long Cc: Boqun Feng Cc: Alison Schofield Cc: Vishal Verma Cc: Ben Widawsky Cc: Jonathan Cameron Reviewed-by: Greg Kroah-Hartman Reviewed-by: Ira Weiny Link: https://lore.kernel.org/r/165100081305.1528964.11138612430659737238.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/linux/device.h | 43 +++++++++++++++++++++++++++++++++++++++++++ include/linux/lockdep.h | 6 +++++- 2 files changed, 48 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index 93459724dcde..833b0b3b0193 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -850,6 +850,49 @@ static inline bool device_supports_offline(struct device *dev) return dev->bus && dev->bus->offline && dev->bus->online; } +#define __device_lock_set_class(dev, name, key) \ +do { \ + struct device *__d2 __maybe_unused = dev; \ + lock_set_class(&__d2->mutex.dep_map, name, key, 0, _THIS_IP_); \ +} while (0) + +/** + * device_lock_set_class - Specify a temporary lock class while a device + * is attached to a driver + * @dev: device to modify + * @key: lock class key data + * + * This must be called with the device_lock() already held, for example + * from driver ->probe(). Take care to only override the default + * lockdep_no_validate class. + */ +#ifdef CONFIG_LOCKDEP +#define device_lock_set_class(dev, key) \ +do { \ + struct device *__d = dev; \ + dev_WARN_ONCE(__d, !lockdep_match_class(&__d->mutex, \ + &__lockdep_no_validate__), \ + "overriding existing custom lock class\n"); \ + __device_lock_set_class(__d, #key, key); \ +} while (0) +#else +#define device_lock_set_class(dev, key) __device_lock_set_class(dev, #key, key) +#endif + +/** + * device_lock_reset_class - Return a device to the default lockdep novalidate state + * @dev: device to modify + * + * This must be called with the device_lock() already held, for example + * from driver ->remove(). + */ +#define device_lock_reset_class(dev) \ +do { \ + struct device *__d __maybe_unused = dev; \ + lock_set_novalidate_class(&__d->mutex.dep_map, "&dev->mutex", \ + _THIS_IP_); \ +} while (0) + void lock_device_hotplug(void); void unlock_device_hotplug(void); int lock_device_hotplug_sysfs(void); diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 467b94257105..43b0dc6a0b21 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -290,6 +290,9 @@ extern void lock_set_class(struct lockdep_map *lock, const char *name, struct lock_class_key *key, unsigned int subclass, unsigned long ip); +#define lock_set_novalidate_class(l, n, i) \ + lock_set_class(l, n, &__lockdep_no_validate__, 0, i) + static inline void lock_set_subclass(struct lockdep_map *lock, unsigned int subclass, unsigned long ip) { @@ -357,7 +360,8 @@ static inline void lockdep_set_selftest_task(struct task_struct *task) # define lock_acquire(l, s, t, r, c, n, i) do { } while (0) # define lock_release(l, i) do { } while (0) # define lock_downgrade(l, i) do { } while (0) -# define lock_set_class(l, n, k, s, i) do { } while (0) +# define lock_set_class(l, n, key, s, i) do { (void)(key); } while (0) +# define lock_set_novalidate_class(l, n, i) do { } while (0) # define lock_set_subclass(l, s, i) do { } while (0) # define lockdep_init() do { } while (0) # define lockdep_init_map_type(lock, name, key, sub, inner, outer, type) \ -- cgit v1.2.3 From fd3abd2cafa46955846d731b9a6ded2c19ab73d8 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 21 Apr 2022 08:33:45 -0700 Subject: device-core: Kill the lockdep_mutex Per Peter [1], the lockdep API has native support for all the use cases lockdep_mutex was attempting to enable. Now that all lockdep_mutex users have been converted to those APIs, drop this lock. Link: https://lore.kernel.org/r/Ylf0dewci8myLvoW@hirez.programming.kicks-ass.net [1] Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Suggested-by: Peter Zijlstra Reviewed-by: Ira Weiny Acked-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/165055522548.3745911.14298368286915484086.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/linux/device.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index 833b0b3b0193..073f1b0126ac 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -400,8 +400,6 @@ struct dev_msi_info { * This identifies the device type and carries type-specific * information. * @mutex: Mutex to synchronize calls to its driver. - * @lockdep_mutex: An optional debug lock that a subsystem can use as a - * peer lock to gain localized lockdep coverage of the device_lock. * @bus: Type of bus device is on. * @driver: Which driver has allocated this * @platform_data: Platform data specific to the device. @@ -499,9 +497,6 @@ struct device { core doesn't touch it */ void *driver_data; /* Driver data, set and get with dev_set_drvdata/dev_get_drvdata */ -#ifdef CONFIG_PROVE_LOCKING - struct mutex lockdep_mutex; -#endif struct mutex mutex; /* mutex to synchronize calls to * its driver. */ -- cgit v1.2.3 From 033b87d24f7257c45506bd043ad85ed24a9925e2 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Tue, 26 Apr 2022 01:29:07 -0700 Subject: io_uring: use the text representation of ops in trace It is annoying to translate opcodes to textwhen tracing io_uring. Use the io_uring_get_opcode function instead to use the text representation. A downside here might have been that if the opcode is invalid it will not be obvious, however the opcode is already overridden in these cases to 0 (NOP) in io_init_req(). Therefore this is a non issue. Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220426082907.3600028-5-dylany@fb.com [axboe: don't include register, those are not req opcodes] Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 36 +++++++++++++++++++++--------------- 1 file changed, 21 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 42c7e1a3c6ae..3f2961baebcc 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -7,6 +7,7 @@ #include #include +#include struct io_wq_work; @@ -169,8 +170,9 @@ TRACE_EVENT(io_uring_queue_async_work, __entry->rw = rw; ), - TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d, flags 0x%x, %s queue, work %p", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, + TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, flags 0x%x, %s queue, work %p", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->flags, __entry->rw ? "hashed" : "normal", __entry->work) ); @@ -205,8 +207,9 @@ TRACE_EVENT(io_uring_defer, __entry->opcode = opcode; ), - TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d", - __entry->ctx, __entry->req, __entry->data, __entry->opcode) + TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s", + __entry->ctx, __entry->req, __entry->data, + io_uring_get_opcode(__entry->opcode)) ); /** @@ -305,9 +308,9 @@ TRACE_EVENT(io_uring_fail_link, __entry->link = link; ), - TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d, link %p", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, - __entry->link) + TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, link %p", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->link) ); /** @@ -389,9 +392,9 @@ TRACE_EVENT(io_uring_submit_sqe, __entry->sq_thread = sq_thread; ), - TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, flags 0x%x, " + TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, flags 0x%x, " "non block %d, sq_thread %d", __entry->ctx, __entry->req, - __entry->user_data, __entry->opcode, + __entry->user_data, io_uring_get_opcode(__entry->opcode), __entry->flags, __entry->force_nonblock, __entry->sq_thread) ); @@ -433,8 +436,9 @@ TRACE_EVENT(io_uring_poll_arm, __entry->events = events; ), - TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, mask 0x%x, events 0x%x", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, + TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, mask 0x%x, events 0x%x", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->mask, __entry->events) ); @@ -470,8 +474,9 @@ TRACE_EVENT(io_uring_task_add, __entry->mask = mask; ), - TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, mask %x", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, + TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, mask %x", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->mask) ); @@ -530,12 +535,13 @@ TRACE_EVENT(io_uring_req_failed, ), TP_printk("ring %p, req %p, user_data 0x%llx, " - "opcode %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, " + "opcode %s, flags 0x%x, prio=%d, off=%llu, addr=%llu, " "len=%u, rw_flags=0x%x, buf_index=%d, " "personality=%d, file_index=%d, pad=0x%llx, addr3=%llx, " "error=%d", __entry->ctx, __entry->req, __entry->user_data, - __entry->opcode, __entry->flags, __entry->ioprio, + io_uring_get_opcode(__entry->opcode), + __entry->flags, __entry->ioprio, (unsigned long long)__entry->off, (unsigned long long) __entry->addr, __entry->len, __entry->op_flags, -- cgit v1.2.3 From 9096bbe951ddd3f9dc813e73b5bde6d5715d1cdb Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 28 Apr 2022 23:15:58 -0700 Subject: mm: shmem: make shmem_init return void The return value of shmem_init is never used. So we can make it return void now. [akpm@linux-foundation.org: remove `return;' from void-returning function, per Muchun Song] Link: https://lkml.kernel.org/r/20220328112707.22217-1-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Cc: Muchun Song Cc: Hugh Dickins Signed-off-by: Andrew Morton --- include/linux/shmem_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index ab51d3cd39bd..3e915cc550bc 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -56,7 +56,7 @@ static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) * Functions in mm/shmem.c called directly from elsewhere: */ extern const struct fs_parameter_spec shmem_fs_parameters[]; -extern int shmem_init(void); +extern void shmem_init(void); extern int shmem_init_fs_context(struct fs_context *fc); extern struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags); -- cgit v1.2.3 From ef7a4ffc4c7f969d61e297c53cb2de1d6f012a11 Mon Sep 17 00:00:00 2001 From: Lu Jialin Date: Thu, 28 Apr 2022 23:16:00 -0700 Subject: mm/memcontrol.c: make cgroup_memory_noswap static cgroup_memory_noswap is only used in mm/memcontrol.c, therefore just make it static, and remove export in include/linux/memcontrol.h Link: https://lkml.kernel.org/r/20220421124736.62180-1-lujialin4@huawei.com Signed-off-by: Lu Jialin Acked-by: Johannes Weiner Acked-by: Shakeel Butt Acked-by: Roman Gushchin Reviewed-by: Muchun Song Cc: Michal Hocko Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 89b14729d59f..fe580cb96683 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -937,10 +937,6 @@ struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, struct mem_cgroup *oom_domain); void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); -#ifdef CONFIG_MEMCG_SWAP -extern bool cgroup_memory_noswap; -#endif - void folio_memcg_lock(struct folio *folio); void folio_memcg_unlock(struct folio *folio); void lock_page_memcg(struct page *page); -- cgit v1.2.3 From 2ba2b008a8bf5fd268a43d03ba79e0ad464d6836 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Thu, 28 Apr 2022 23:16:02 -0700 Subject: Revert "mm/memory-failure.c: fix race with changing page compound again" Reverts commit 888af2701db7 ("mm/memory-failure.c: fix race with changing page compound again") because now we fetch the page refcount under hugetlb_lock in try_memory_failure_hugetlb() so that the race check is no longer necessary. Link: https://lkml.kernel.org/r/20220408135323.1559401-4-naoya.horiguchi@linux.dev Signed-off-by: Naoya Horiguchi Suggested-by: Miaohe Lin Reviewed-by: Miaohe Lin Reviewed-by: Mike Kravetz Cc: Miaohe Lin Cc: Yang Shi Cc: Dan Carpenter Signed-off-by: Andrew Morton --- include/linux/mm.h | 1 - include/ras/ras_event.h | 1 - 2 files changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9f44254af8ce..d446e834a3e5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3251,7 +3251,6 @@ enum mf_action_page_type { MF_MSG_BUDDY, MF_MSG_DAX, MF_MSG_UNSPLIT_THP, - MF_MSG_DIFFERENT_PAGE_SIZE, MF_MSG_UNKNOWN, }; diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h index 1e694fd239b9..d0337a41141c 100644 --- a/include/ras/ras_event.h +++ b/include/ras/ras_event.h @@ -374,7 +374,6 @@ TRACE_EVENT(aer_event, EM ( MF_MSG_BUDDY, "free buddy page" ) \ EM ( MF_MSG_DAX, "dax page" ) \ EM ( MF_MSG_UNSPLIT_THP, "unsplit thp" ) \ - EM ( MF_MSG_DIFFERENT_PAGE_SIZE, "different page size" ) \ EMe ( MF_MSG_UNKNOWN, "unknown page" ) /* -- cgit v1.2.3 From 7d6e2d96384556a4f30547803be1f606eb805a62 Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Thu, 28 Apr 2022 23:16:09 -0700 Subject: mm: untangle config dependencies for demote-on-reclaim At the time demote-on-reclaim was introduced, it was tied to CONFIG_HOTPLUG_CPU + CONFIG_MIGRATE, but that is not really accurate. The only two things we need to depend on are CONFIG_NUMA + CONFIG_MIGRATE, so clean this up. Furthermore, we only register the hotplug memory notifier when the system has CONFIG_MEMORY_HOTPLUG. Link: https://lkml.kernel.org/r/20220322224016.4574-1-osalvador@suse.de Signed-off-by: Oscar Salvador Suggested-by: "Huang, Ying" Reviewed-by: "Huang, Ying" Cc: Dave Hansen Cc: Abhishek Goel Cc: Baolin Wang Signed-off-by: Andrew Morton --- include/linux/migrate.h | 34 +++++++++++++++------------------- 1 file changed, 15 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 90e75d5a54d6..2707bfd43a0d 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -47,17 +47,8 @@ void folio_migrate_copy(struct folio *newfolio, struct folio *folio); int folio_migrate_mapping(struct address_space *mapping, struct folio *newfolio, struct folio *folio, int extra_count); -extern bool numa_demotion_enabled; -extern void migrate_on_reclaim_init(void); -#ifdef CONFIG_HOTPLUG_CPU -extern void set_migration_target_nodes(void); -#else -static inline void set_migration_target_nodes(void) {} -#endif #else -static inline void set_migration_target_nodes(void) {} - static inline void putback_movable_pages(struct list_head *l) {} static inline int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, unsigned long private, enum migrate_mode mode, @@ -82,9 +73,23 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, return -ENOSYS; } -#define numa_demotion_enabled false #endif /* CONFIG_MIGRATION */ +#if defined(CONFIG_MIGRATION) && defined(CONFIG_NUMA) +extern void set_migration_target_nodes(void); +extern void migrate_on_reclaim_init(void); +extern bool numa_demotion_enabled; +extern int next_demotion_node(int node); +#else +static inline void set_migration_target_nodes(void) {} +static inline void migrate_on_reclaim_init(void) {} +static inline int next_demotion_node(int node) +{ + return NUMA_NO_NODE; +} +#define numa_demotion_enabled false +#endif + #ifdef CONFIG_COMPACTION extern int PageMovable(struct page *page); extern void __SetPageMovable(struct page *page, struct address_space *mapping); @@ -172,15 +177,6 @@ struct migrate_vma { int migrate_vma_setup(struct migrate_vma *args); void migrate_vma_pages(struct migrate_vma *migrate); void migrate_vma_finalize(struct migrate_vma *migrate); -int next_demotion_node(int node); - -#else /* CONFIG_MIGRATION disabled: */ - -static inline int next_demotion_node(int node) -{ - return NUMA_NO_NODE; -} - #endif /* CONFIG_MIGRATION */ #endif /* _LINUX_MIGRATE_H */ -- cgit v1.2.3 From 6a8e0596f00469c15ec556b9f3624acd2e9a04f9 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Thu, 28 Apr 2022 23:16:10 -0700 Subject: mm: rmap: introduce pfn_mkclean_range() to cleans PTEs The page_mkclean_one() is supposed to be used with the pfn that has a associated struct page, but not all the pfns (e.g. DAX) have a struct page. Introduce a new function pfn_mkclean_range() to cleans the PTEs (including PMDs) mapped with range of pfns which has no struct page associated with them. This helper will be used by DAX device in the next patch to make pfns clean. Link: https://lkml.kernel.org/r/20220403053957.10770-4-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Alistair Popple Cc: Al Viro Cc: Christoph Hellwig Cc: Dan Williams Cc: Hugh Dickins Cc: Jan Kara Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Ralph Campbell Cc: Ross Zwisler Cc: Xiongchun Duan Cc: Xiyu Yang Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/rmap.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 17230c458341..8573aae50d96 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -261,6 +261,9 @@ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *); */ int folio_mkclean(struct folio *); +int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, + struct vm_area_struct *vma); + void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked); /* -- cgit v1.2.3 From 0e5e64c0b0d7bb33a5e971ad17e771cf6e0a1127 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Thu, 28 Apr 2022 23:16:10 -0700 Subject: mm: simplify follow_invalidate_pte() The only user (DAX) of range and pmdpp parameters of follow_invalidate_pte() is gone, it is safe to remove them and make it static to simlify the code. This is revertant of the following commits: 097963959594 ("mm: add follow_pte_pmd()") a4d1a8852513 ("dax: update to new mmu_notifier semantic") There is only one caller of the follow_invalidate_pte(). So just fold it into follow_pte() and remove it. Link: https://lkml.kernel.org/r/20220403053957.10770-7-songmuchun@bytedance.com Signed-off-by: Muchun Song Reviewed-by: Christoph Hellwig Cc: Alistair Popple Cc: Al Viro Cc: Dan Williams Cc: Hugh Dickins Cc: Jan Kara Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Ralph Campbell Cc: Ross Zwisler Cc: Xiongchun Duan Cc: Xiyu Yang Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/mm.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index d446e834a3e5..16d6b46d2d3e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1845,9 +1845,6 @@ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); -int follow_invalidate_pte(struct mm_struct *mm, unsigned long address, - struct mmu_notifier_range *range, pte_t **ptepp, - pmd_t **pmdpp, spinlock_t **ptlp); int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp, spinlock_t **ptlp); int follow_pfn(struct vm_area_struct *vma, unsigned long address, -- cgit v1.2.3 From 3afa793082e624f7bd83533010ff4a676451d4ee Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 28 Apr 2022 23:16:14 -0700 Subject: mm/mmap: drop arch_vm_get_page_pgprot() There are no platforms left which use arch_vm_get_page_prot(). Just drop generic arch_vm_get_page_prot(). Link: https://lkml.kernel.org/r/20220414062125.609297-8-anshuman.khandual@arm.com Cc: Andrew Morton Cc: linux-mm@kvack.org Cc: linux-kernel@vger.kernel.org Reviewed-by: Christophe Leroy Reviewed-by: Catalin Marinas Signed-off-by: Anshuman Khandual Cc: Christoph Hellwig Cc: David S. Miller Cc: Ingo Molnar Cc: Khalid Aziz Cc: Michael Ellerman Cc: Paul Mackerras Cc: Thomas Gleixner Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/mman.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/mman.h b/include/linux/mman.h index b66e91b8176c..58b3abd457a3 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -93,10 +93,6 @@ static inline void vm_unacct_memory(long pages) #define arch_calc_vm_flag_bits(flags) 0 #endif -#ifndef arch_vm_get_page_prot -#define arch_vm_get_page_prot(vm_flags) __pgprot(0) -#endif - #ifndef arch_validate_prot /* * This is called from mprotect(). PROT_GROWSDOWN and PROT_GROWSUP have -- cgit v1.2.3 From 5981611d0a006472d367d7a8e6ead8afaecf17c7 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Thu, 28 Apr 2022 23:16:14 -0700 Subject: mm: hugetlb_vmemmap: cleanup hugetlb_vmemmap related functions Patch series "cleanup hugetlb_vmemmap". The word of "free" is not expressive enough to express the feature of optimizing vmemmap pages associated with each HugeTLB, rename this keywork to "optimize" is more clear. In this series, cheanup related codes to make it more clear and expressive. This is suggested by David. This patch (of 3): The word of "free" is not expressive enough to express the feature of optimizing vmemmap pages associated with each HugeTLB, rename this keywork to "optimize". And some function names are prefixed with "huge_page" instead of "hugetlb", it is easily to be confused with THP. In this patch, cheanup related functions to make code more clear and expressive. Link: https://lkml.kernel.org/r/20220404074652.68024-1-songmuchun@bytedance.com Link: https://lkml.kernel.org/r/20220404074652.68024-2-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: David Hildenbrand Cc: Mike Kravetz Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ac2a1d758a80..189bddb8eca4 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -624,7 +624,7 @@ struct hstate { unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP - unsigned int nr_free_vmemmap_pages; + unsigned int optimize_vmemmap_pages; #endif #ifdef CONFIG_CGROUP_HUGETLB /* cgroup control files */ -- cgit v1.2.3 From f10f1442c309ccef7a80ba3dc4abde0978e86fb4 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Thu, 28 Apr 2022 23:16:15 -0700 Subject: mm: hugetlb_vmemmap: cleanup hugetlb_free_vmemmap_enabled* The word of "free" is not expressive enough to express the feature of optimizing vmemmap pages associated with each HugeTLB, rename this keywork to "optimize". In this patch , cheanup the static key and hugetlb_free_vmemmap_enabled() to make code more expressive. Link: https://lkml.kernel.org/r/20220404074652.68024-3-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: David Hildenbrand Cc: Mike Kravetz Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 9d8eeaa67d05..573f499d5a2d 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -192,16 +192,16 @@ enum pageflags { #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP DECLARE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON, - hugetlb_free_vmemmap_enabled_key); + hugetlb_optimize_vmemmap_key); -static __always_inline bool hugetlb_free_vmemmap_enabled(void) +static __always_inline bool hugetlb_optimize_vmemmap_enabled(void) { return static_branch_maybe(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON, - &hugetlb_free_vmemmap_enabled_key); + &hugetlb_optimize_vmemmap_key); } /* - * If the feature of freeing some vmemmap pages associated with each HugeTLB + * If the feature of optimizing vmemmap pages associated with each HugeTLB * page is enabled, the head vmemmap page frame is reused and all of the tail * vmemmap addresses map to the head vmemmap page frame (furture details can * refer to the figure at the head of the mm/hugetlb_vmemmap.c). In other @@ -218,7 +218,7 @@ static __always_inline bool hugetlb_free_vmemmap_enabled(void) */ static __always_inline const struct page *page_fixed_fake_head(const struct page *page) { - if (!hugetlb_free_vmemmap_enabled()) + if (!hugetlb_optimize_vmemmap_enabled()) return page; /* @@ -247,7 +247,7 @@ static inline const struct page *page_fixed_fake_head(const struct page *page) return page; } -static inline bool hugetlb_free_vmemmap_enabled(void) +static inline bool hugetlb_optimize_vmemmap_enabled(void) { return false; } -- cgit v1.2.3 From 47010c040dec8af6347ec6259104fc13f7e7e30a Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Thu, 28 Apr 2022 23:16:15 -0700 Subject: mm: hugetlb_vmemmap: cleanup CONFIG_HUGETLB_PAGE_FREE_VMEMMAP* The word of "free" is not expressive enough to express the feature of optimizing vmemmap pages associated with each HugeTLB, rename this keywork to "optimize". In this patch , cheanup configs to make code more expressive. Link: https://lkml.kernel.org/r/20220404074652.68024-4-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Mike Kravetz Cc: David Hildenbrand Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 2 +- include/linux/mm.h | 2 +- include/linux/page-flags.h | 6 +++--- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 189bddb8eca4..ac2ece9e9c79 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -623,7 +623,7 @@ struct hstate { unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; -#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP +#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP unsigned int optimize_vmemmap_pages; #endif #ifdef CONFIG_CGROUP_HUGETLB diff --git a/include/linux/mm.h b/include/linux/mm.h index 16d6b46d2d3e..a8f4c7e96ad5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3145,7 +3145,7 @@ static inline void print_vma_addr(char *prefix, unsigned long rip) } #endif -#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP +#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP int vmemmap_remap_free(unsigned long start, unsigned long end, unsigned long reuse); int vmemmap_remap_alloc(unsigned long start, unsigned long end, diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 573f499d5a2d..1ea896887ee4 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -190,13 +190,13 @@ enum pageflags { #ifndef __GENERATING_BOUNDS_H -#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP -DECLARE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON, +#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP +DECLARE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON, hugetlb_optimize_vmemmap_key); static __always_inline bool hugetlb_optimize_vmemmap_enabled(void) { - return static_branch_maybe(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON, + return static_branch_maybe(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON, &hugetlb_optimize_vmemmap_key); } -- cgit v1.2.3 From e3246d8f52173a798710314a42fea83223036fc8 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Thu, 28 Apr 2022 23:16:15 -0700 Subject: mm/sparse-vmemmap: add a pgmap argument to section activation Patch series "sparse-vmemmap: memory savings for compound devmaps (device-dax)", v9. This series minimizes 'struct page' overhead by pursuing a similar approach as Muchun Song series "Free some vmemmap pages of hugetlb page" (now merged since v5.14), but applied to devmap with @vmemmap_shift (device-dax). The vmemmap dedpulication original idea (already used in HugeTLB) is to reuse/deduplicate tail page vmemmap areas, particular the area which only describes tail pages. So a vmemmap page describes 64 struct pages, and the first page for a given ZONE_DEVICE vmemmap would contain the head page and 63 tail pages. The second vmemmap page would contain only tail pages, and that's what gets reused across the rest of the subsection/section. The bigger the page size, the bigger the savings (2M hpage -> save 6 vmemmap pages; 1G hpage -> save 4094 vmemmap pages). This is done for PMEM /specifically only/ on device-dax configured namespaces, not fsdax. In other words, a devmap with a @vmemmap_shift. In terms of savings, per 1Tb of memory, the struct page cost would go down with compound devmap: * with 2M pages we lose 4G instead of 16G (0.39% instead of 1.5% of total memory) * with 1G pages we lose 40MB instead of 16G (0.0014% instead of 1.5% of total memory) The series is mostly summed up by patch 4, and to summarize what the series does: Patches 1 - 3: Minor cleanups in preparation for patch 4. Move the very nice docs of hugetlb_vmemmap.c into a Documentation/vm/ entry. Patch 4: Patch 4 is the one that takes care of the struct page savings (also referred to here as tail-page/vmemmap deduplication). Much like Muchun series, we reuse the second PTE tail page vmemmap areas across a given @vmemmap_shift On important difference though, is that contrary to the hugetlbfs series, there's no vmemmap for the area because we are late-populating it as opposed to remapping a system-ram range. IOW no freeing of pages of already initialized vmemmap like the case for hugetlbfs, which greatly simplifies the logic (besides not being arch-specific). altmap case unchanged and still goes via the vmemmap_populate(). Also adjust the newly added docs to the device-dax case. [Note that device-dax is still a little behind HugeTLB in terms of savings. I have an additional simple patch that reuses the head vmemmap page too, as a follow-up. That will double the savings and namespaces initialization.] Patch 5: Initialize fewer struct pages depending on the page size with DRAM backed struct pages -- because fewer pages are unique and most tail pages (with bigger vmemmap_shift). NVDIMM namespace bootstrap improves from ~268-358 ms to ~80-110/<1ms on 128G NVDIMMs with 2M and 1G respectivally. And struct page needed capacity will be 3.8x / 1071x smaller for 2M and 1G respectivelly. Tested on x86 with 1.5Tb of pmem (including pinning, and RDMA registration/deregistration scalability with 2M MRs) This patch (of 5): In support of using compound pages for devmap mappings, plumb the pgmap down to the vmemmap_populate implementation. Note that while altmap is retrievable from pgmap the memory hotplug code passes altmap without pgmap[*], so both need to be independently plumbed. So in addition to @altmap, pass @pgmap to sparse section populate functions namely: sparse_add_section section_activate populate_section_memmap __populate_section_memmap Passing @pgmap allows __populate_section_memmap() to both fetch the vmemmap_shift in which memmap metadata is created for and also to let sparse-vmemmap fetch pgmap ranges to co-relate to a given section and pick whether to just reuse tail pages from past onlined sections. While at it, fix the kdoc for @altmap for sparse_add_section(). [*] https://lore.kernel.org/linux-mm/20210319092635.6214-1-osalvador@suse.de/ Link: https://lkml.kernel.org/r/20220420155310.9712-1-joao.m.martins@oracle.com Link: https://lkml.kernel.org/r/20220420155310.9712-2-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Dan Williams Reviewed-by: Muchun Song Cc: Vishal Verma Cc: Matthew Wilcox Cc: Jason Gunthorpe Cc: Jane Chu Cc: Mike Kravetz Cc: Jonathan Corbet Cc: Christoph Hellwig Signed-off-by: Andrew Morton --- include/linux/memory_hotplug.h | 5 ++++- include/linux/mm.h | 3 ++- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 1ce6f8044f1e..e0b2209ab71c 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -15,6 +15,7 @@ struct memory_block; struct memory_group; struct resource; struct vmem_altmap; +struct dev_pagemap; #ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION /* @@ -122,6 +123,7 @@ typedef int __bitwise mhp_t; struct mhp_params { struct vmem_altmap *altmap; pgprot_t pgprot; + struct dev_pagemap *pgmap; }; bool mhp_range_allowed(u64 start, u64 size, bool need_mapping); @@ -333,7 +335,8 @@ extern void remove_pfn_range_from_zone(struct zone *zone, unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); extern int sparse_add_section(int nid, unsigned long pfn, - unsigned long nr_pages, struct vmem_altmap *altmap); + unsigned long nr_pages, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap); extern void sparse_remove_section(struct mem_section *ms, unsigned long pfn, unsigned long nr_pages, unsigned long map_offset, struct vmem_altmap *altmap); diff --git a/include/linux/mm.h b/include/linux/mm.h index a8f4c7e96ad5..80bba49387e9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3154,7 +3154,8 @@ int vmemmap_remap_alloc(unsigned long start, unsigned long end, void *sparse_buffer_alloc(unsigned long size); struct page * __populate_section_memmap(unsigned long pfn, - unsigned long nr_pages, int nid, struct vmem_altmap *altmap); + unsigned long nr_pages, int nid, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); -- cgit v1.2.3 From 4917f55b4ef963e2d2288fe4eb651728be8db406 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Thu, 28 Apr 2022 23:16:16 -0700 Subject: mm/sparse-vmemmap: improve memory savings for compound devmaps A compound devmap is a dev_pagemap with @vmemmap_shift > 0 and it means that pages are mapped at a given huge page alignment and utilize uses compound pages as opposed to order-0 pages. Take advantage of the fact that most tail pages look the same (except the first two) to minimize struct page overhead. Allocate a separate page for the vmemmap area which contains the head page and separate for the next 64 pages. The rest of the subsections then reuse this tail vmemmap page to initialize the rest of the tail pages. Sections are arch-dependent (e.g. on x86 it's 64M, 128M or 512M) and when initializing compound devmap with big enough @vmemmap_shift (e.g. 1G PUD) it may cross multiple sections. The vmemmap code needs to consult @pgmap so that multiple sections that all map the same tail data can refer back to the first copy of that data for a given gigantic page. On compound devmaps with 2M align, this mechanism lets 6 pages be saved out of the 8 necessary PFNs necessary to set the subsection's 512 struct pages being mapped. On a 1G compound devmap it saves 4094 pages. Altmap isn't supported yet, given various restrictions in altmap pfn allocator, thus fallback to the already in use vmemmap_populate(). It is worth noting that altmap for devmap mappings was there to relieve the pressure of inordinate amounts of memmap space to map terabytes of pmem. With compound pages the motivation for altmaps for pmem gets reduced. Link: https://lkml.kernel.org/r/20220420155310.9712-5-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Muchun Song Cc: Christoph Hellwig Cc: Dan Williams Cc: Jane Chu Cc: Jason Gunthorpe Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Vishal Verma Signed-off-by: Andrew Morton --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 80bba49387e9..b9316b2c11ce 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3161,7 +3161,7 @@ p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, - struct vmem_altmap *altmap); + struct vmem_altmap *altmap, struct page *reuse); void *vmemmap_alloc_block(unsigned long size, int node); struct vmem_altmap; void *vmemmap_alloc_block_buf(unsigned long size, int node, -- cgit v1.2.3 From ba91fb7dd03c4f463453f28af24851097a6547fb Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 28 Apr 2022 23:16:16 -0700 Subject: include/linux/swapops.h: remove stub for non_swap_entry() The stub for non_swap_entry() may not help much, because MAX_SWAPFILES has already contained all the information to decide whether a swap entry is real swap entry or pesudo ones (migrations, ...). There can be some performance influences on non_swap_entry() with below conditions all met: !CONFIG_MIGRATION && !CONFIG_MEMORY_FAILURE && !CONFIG_DEVICE_PRIVATE But that's definitely not the major config most machines will use, at the meantime it's already in a slow path of swap entry (being parsed from a swap pte), so IMHO it shouldn't be a major issue. Also according to the analysis from Alistair, somehow the stub didn't do the job right [1]. To make the code cleaner, let's drop the stub. [1] https://lore.kernel.org/lkml/8735ihbw6g.fsf@nvdebian.thelocal/ Note: the uffd-wp shmem & hugetlbfs series will need this patch to make sure swap entries work as expected with below config as spotted by Alistair: !CONFIG_MIGRATION && !CONFIG_MEMORY_FAILURE && !CONFIG_DEVICE_PRIVATE && CONFIG_PTE_MARKER (PS: this config should mostly never gonna happen, though, afaict..) Link: https://lkml.kernel.org/r/20220413191147.66645-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Alistair Popple Cc: Hugh Dickins Signed-off-by: Andrew Morton --- include/linux/swapops.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index d356ab4047f7..5af852b68805 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -387,18 +387,10 @@ static inline void num_poisoned_pages_inc(void) } #endif -#if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION) || \ - defined(CONFIG_DEVICE_PRIVATE) static inline int non_swap_entry(swp_entry_t entry) { return swp_type(entry) >= MAX_SWAPFILES; } -#else -static inline int non_swap_entry(swp_entry_t entry) -{ - return 0; -} -#endif #endif /* CONFIG_MMU */ #endif /* _LINUX_SWAPOPS_H */ -- cgit v1.2.3 From 7609385337a4feb6236e42dcd0df2185683ce839 Mon Sep 17 00:00:00 2001 From: xu xin Date: Thu, 28 Apr 2022 23:16:16 -0700 Subject: ksm: count ksm merging pages for each process Some applications or containers want to use KSM by calling madvise() to advise areas of address space to be MERGEABLE. But they may not know which applications are more likely to cause real merges in the deployment. If this patch is applied, it helps them know their corresponding number of merged pages, and then optimize their app code. As current KSM only counts the number of KSM merging pages(e.g. ksm_pages_sharing and ksm_pages_shared) of the whole system, we cannot see the more fine-grained KSM merging, for the upper application optimization, the merging area cannot be set easily according to the KSM page merging probability of each process. Therefore, it is necessary to add extra statistical means so that the upper level users can know the detailed KSM merging information of each process. We add a new proc file named as ksm_merging_pages under /proc// to indicate the involved ksm merging pages of this process. [akpm@linux-foundation.org: fix comment typo, remove BUG_ON()s] Link: https://lkml.kernel.org/r/20220325082318.2352853-1-xu.xin16@zte.com.cn Signed-off-by: xu xin Reported-by: kernel test robot Reviewed-by: Yang Yang Reviewed-by: Ran Xiaokai Reported-by: Zeal Robot Cc: Kees Cook Cc: Alexey Dobriyan Cc: Stephen Rothwell Cc: Ohhoon Kwon Cc: Matthew Wilcox (Oracle) Cc: Stephen Brennan Cc: Vlastimil Babka Cc: Feng Tang Cc: Yang Yang Cc: Ran Xiaokai Cc: Zeal Robot Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 8834e38c06a4..87eddd509de2 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -654,6 +654,13 @@ struct mm_struct { #ifdef CONFIG_IOMMU_SVA u32 pasid; +#endif +#ifdef CONFIG_KSM + /* + * Represent how many pages of this process are involved in KSM + * merging. + */ + unsigned long ksm_merging_pages; #endif } __randomize_layout; -- cgit v1.2.3 From 94bfe85bde18a99612bb5d0ce348643c2d352836 Mon Sep 17 00:00:00 2001 From: Yang Yang Date: Thu, 28 Apr 2022 23:16:16 -0700 Subject: mm/vmstat: add events for ksm cow Users may use ksm by calling madvise(, , MADV_MERGEABLE) when they want to save memory, it's a tradeoff by suffering delay on ksm cow. Users can get to know how much memory ksm saved by reading /sys/kernel/mm/ksm/pages_sharing, but they don't know what's the costs of ksm cow, and this is important of some delay sensitive tasks. So add ksm cow events to help users evaluate whether or how to use ksm. Also update Documentation/admin-guide/mm/ksm.rst with new added events. Link: https://lkml.kernel.org/r/20220331035616.2390805-1-yang.yang29@zte.com.cn Signed-off-by: Yang Yang Reviewed-by: David Hildenbrand Reviewed-by: xu xin Reviewed-by: Ran Xiaokai Cc: Matthew Wilcox (Oracle) Cc: Jonathan Corbet Cc: Dave Hansen Cc: Saravanan D Cc: Minchan Kim Cc: John Hubbard Signed-off-by: Andrew Morton --- include/linux/vm_event_item.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 16a0a4fd000b..e83967e4c20e 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -133,6 +133,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, KSM_SWPIN_COPY, #endif #endif +#ifdef CONFIG_KSM + COW_KSM, +#endif #ifdef CONFIG_X86 DIRECT_MAP_LEVEL2_SPLIT, DIRECT_MAP_LEVEL3_SPLIT, -- cgit v1.2.3 From 024c61eaff17f6a8c73cb8b25137251f0c3ef039 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 28 Apr 2022 23:16:17 -0700 Subject: mm: compaction: remove unneeded return value of kcompactd_run Patch series "A few cleanup and fixup patches for compaction". This series contains a few patches to clean up some obsolete comment, remove unneeded return value and so on. Also we fix the possible NULL pointer dereference. More details can be found in the respective changelogs. This patch (of 12): The return value of kcompactd_run() is unused now. Clean it up. Link: https://lkml.kernel.org/r/20220418141253.24298-1-linmiaohe@huawei.com Link: https://lkml.kernel.org/r/20220418141253.24298-2-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Cc; Mel Gorman Cc: David Hildenbrand Cc: Vlastimil Babka Cc: Pintu Kumar Cc: Charan Teja Kalla Signed-off-by: Andrew Morton --- include/linux/compaction.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 34bce35c808d..52a9ff65faee 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -177,7 +177,7 @@ static inline bool compaction_withdrawn(enum compact_result result) bool compaction_zonelist_suitable(struct alloc_context *ac, int order, int alloc_flags); -extern int kcompactd_run(int nid); +extern void kcompactd_run(int nid); extern void kcompactd_stop(int nid); extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx); @@ -212,9 +212,8 @@ static inline bool compaction_withdrawn(enum compact_result result) return true; } -static inline int kcompactd_run(int nid) +static inline void kcompactd_run(int nid) { - return 0; } static inline void kcompactd_stop(int nid) { -- cgit v1.2.3 From 766475cb526b2fc5ca21374b5810d6d8557870fc Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 28 Apr 2022 12:28:59 +0200 Subject: ARM: omap1: add back omap_set_dma_priority() stub One of my multiplatform patches went a little too far and removed a declaration that is needed for compile-testing the omapfb driver on non-OMAP1 platforms: arm-linux-gnueabi-ld: drivers/video/fbdev/omap/omapfb_main.o: in function `omapfb_do_probe': omapfb_main.c:(.text+0x41ec): undefined reference to `omap_set_dma_priority' Add back the inline stub, and in turn hide the definition when omapfb is disabled, like we do for the usb specific bits. Reported-by: kernel test robot Reviewed-by: Tony Lindgren Fixes: 52ef8efcb75e ("dma: omap: hide legacy interface") Signed-off-by: Arnd Bergmann --- include/linux/omap-dma.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h index 254b4e10511b..6f6c31e3fb93 100644 --- a/include/linux/omap-dma.h +++ b/include/linux/omap-dma.h @@ -294,7 +294,14 @@ struct omap_system_dma_plat_info { extern struct omap_system_dma_plat_info *omap_get_plat_info(void); +#if defined(CONFIG_ARCH_OMAP1) extern void omap_set_dma_priority(int lch, int dst_port, int priority); +#else +static inline void omap_set_dma_priority(int lch, int dst_port, int priority) +{ +} +#endif + extern int omap_request_dma(int dev_id, const char *dev_name, void (*callback)(int lch, u16 ch_status, void *data), void *data, int *dma_ch); -- cgit v1.2.3 From 50e7b416d2ab10b9771bd00a4d85df90ad2e4b37 Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Thu, 28 Apr 2022 15:43:37 +0100 Subject: sched/fair: Remove sched_trace_*() helper functions We no longer need them as we can use DWARF debug info or BTF + pahole to re-generate the required structs to compile against them for a given kernel. This moves the burden of maintaining these helper functions to the module. https://github.com/qais-yousef/sched_tp Note that pahole v1.15 is required at least for using DWARF. And for BTF v1.23 which is not yet released will be required. There's alignment problem that will lead to crashes in earlier versions when used with BTF. We should have enough infrastructure to make these helper functions now obsolete, so remove them. [Rewrote commit message to reflect the new alternative] Signed-off-by: Dietmar Eggemann Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220428144338.479094-2-qais.yousef@arm.com --- include/linux/sched.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 67f06f72c50e..fc74ea2578b7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2378,20 +2378,6 @@ static inline void rseq_syscall(struct pt_regs *regs) #endif -const struct sched_avg *sched_trace_cfs_rq_avg(struct cfs_rq *cfs_rq); -char *sched_trace_cfs_rq_path(struct cfs_rq *cfs_rq, char *str, int len); -int sched_trace_cfs_rq_cpu(struct cfs_rq *cfs_rq); - -const struct sched_avg *sched_trace_rq_avg_rt(struct rq *rq); -const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq); -const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq); - -int sched_trace_rq_cpu(struct rq *rq); -int sched_trace_rq_cpu_capacity(struct rq *rq); -int sched_trace_rq_nr_running(struct rq *rq); - -const struct cpumask *sched_trace_rd_span(struct root_domain *rd); - #ifdef CONFIG_SCHED_CORE extern void sched_core_free(struct task_struct *tsk); extern void sched_core_fork(struct task_struct *p); -- cgit v1.2.3 From 498af8d1678ae2351218337b47bbf3cb0fc16821 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Fri, 29 Apr 2022 12:39:45 +0100 Subject: firmware: arm_ffa: Add ffa_dev_get_drvdata helper function Add a helper function to fetch ffa_dev's driver_data using dev_get_drvdata. At the same time move existing ffa_dev_set_drvdata to use dev_set_drvdata. Link: https://lore.kernel.org/r/20220429113946.2087145-3-sudeep.holla@arm.com Suggested-by: Arunachalam Ganapathy Signed-off-by: Sudeep Holla --- include/linux/arm_ffa.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index 85651e41ded8..e5c76c1ef9ed 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -38,7 +38,12 @@ struct ffa_driver { static inline void ffa_dev_set_drvdata(struct ffa_device *fdev, void *data) { - fdev->dev.driver_data = data; + dev_set_drvdata(&fdev->dev, data); +} + +static inline void *ffa_dev_get_drvdata(struct ffa_device *fdev) +{ + return dev_get_drvdata(&fdev->dev); } #if IS_REACHABLE(CONFIG_ARM_FFA_TRANSPORT) -- cgit v1.2.3 From 892de36fd4a98fab3298d417c051d9099af5448d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 29 Apr 2022 12:22:10 -0400 Subject: SUNRPC: Ensure gss-proxy connects on setup For reasons best known to the author, gss-proxy does not implement a NULL procedure, and returns RPC_PROC_UNAVAIL. However we still want to ensure that we connect to the service at setup time. So add a quirk-flag specially for this case. Fixes: 1d658336b05f ("SUNRPC: Add RPC based upcall mechanism for RPCGSS auth") Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 267b7aeaf1a6..db5149567305 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -160,6 +160,7 @@ struct rpc_add_xprt_test { #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT (1UL << 9) #define RPC_CLNT_CREATE_SOFTERR (1UL << 10) #define RPC_CLNT_CREATE_REUSEPORT (1UL << 11) +#define RPC_CLNT_CREATE_IGNORE_NULL_UNAVAIL (1UL << 12) struct rpc_clnt *rpc_create(struct rpc_create_args *args); struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, -- cgit v1.2.3 From d495f942f40aa412f8d4d65951152648cfa09903 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Fri, 22 Apr 2022 12:30:13 +0200 Subject: KVM: fix bad user ABI for KVM_EXIT_SYSTEM_EVENT When KVM_EXIT_SYSTEM_EVENT was introduced, it included a flags member that at the time was unused. Unfortunately this extensibility mechanism has several issues: - x86 is not writing the member, so it would not be possible to use it on x86 except for new events - the member is not aligned to 64 bits, so the definition of the uAPI struct is incorrect for 32- on 64-bit userspace. This is a problem for RISC-V, which supports CONFIG_KVM_COMPAT, but fortunately usage of flags was only introduced in 5.18. Since padding has to be introduced, place a new field in there that tells if the flags field is valid. To allow further extensibility, in fact, change flags to an array of 16 values, and store how many of the values are valid. The availability of the new ndata field is tied to a system capability; all architectures are changed to fill in the field. To avoid breaking compilation of userspace that was using the flags field, provide a userspace-only union to overlap flags with data[0]. The new field is placed at the same offset for both 32- and 64-bit userspace. Cc: Will Deacon Cc: Marc Zyngier Cc: Peter Gonda Cc: Sean Christopherson Signed-off-by: Paolo Bonzini Reported-by: kernel test robot Message-Id: <20220422103013.34832-1-pbonzini@redhat.com> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 91a6fe4e02c0..6a184d260c7f 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -445,7 +445,13 @@ struct kvm_run { #define KVM_SYSTEM_EVENT_RESET 2 #define KVM_SYSTEM_EVENT_CRASH 3 __u32 type; - __u64 flags; + __u32 ndata; + union { +#ifndef __KERNEL__ + __u64 flags; +#endif + __u64 data[16]; + }; } system_event; /* KVM_EXIT_S390_STSI */ struct { @@ -1144,6 +1150,8 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_MEM_OP_EXTENSION 211 #define KVM_CAP_PMU_CAPABILITY 212 #define KVM_CAP_DISABLE_QUIRKS2 213 +/* #define KVM_CAP_VM_TSC_CONTROL 214 */ +#define KVM_CAP_SYSTEM_EVENT_DATA 215 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 991b4de3275728fd746ce15e00087fdbd51c29a1 Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Wed, 27 Apr 2022 21:19:23 -0700 Subject: drm/i915/uapi: Add kerneldoc for engine class enum We'll be adding a new type of engine soon. Let's document the existing engine classes first to help make it clear what each type of engine is used for. Cc: Andi Shyti Signed-off-by: Matt Roper Reviewed-by: Andi Shyti Reviewed-by: Jordan Justen Link: https://patchwork.freedesktop.org/patch/msgid/20220428041926.1483683-2-matthew.d.roper@intel.com --- include/uapi/drm/i915_drm.h | 53 ++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 47 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 35ca528803fd..ec000fc6c879 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -154,21 +154,62 @@ enum i915_mocs_table_index { I915_MOCS_CACHED, }; -/* +/** + * enum drm_i915_gem_engine_class - uapi engine type enumeration + * * Different engines serve different roles, and there may be more than one - * engine serving each role. enum drm_i915_gem_engine_class provides a - * classification of the role of the engine, which may be used when requesting - * operations to be performed on a certain subset of engines, or for providing - * information about that group. + * engine serving each role. This enum provides a classification of the role + * of the engine, which may be used when requesting operations to be performed + * on a certain subset of engines, or for providing information about that + * group. */ enum drm_i915_gem_engine_class { + /** + * @I915_ENGINE_CLASS_RENDER: + * + * Render engines support instructions used for 3D, Compute (GPGPU), + * and programmable media workloads. These instructions fetch data and + * dispatch individual work items to threads that operate in parallel. + * The threads run small programs (called "kernels" or "shaders") on + * the GPU's execution units (EUs). + */ I915_ENGINE_CLASS_RENDER = 0, + + /** + * @I915_ENGINE_CLASS_COPY: + * + * Copy engines (also referred to as "blitters") support instructions + * that move blocks of data from one location in memory to another, + * or that fill a specified location of memory with fixed data. + * Copy engines can perform pre-defined logical or bitwise operations + * on the source, destination, or pattern data. + */ I915_ENGINE_CLASS_COPY = 1, + + /** + * @I915_ENGINE_CLASS_VIDEO: + * + * Video engines (also referred to as "bit stream decode" (BSD) or + * "vdbox") support instructions that perform fixed-function media + * decode and encode. + */ I915_ENGINE_CLASS_VIDEO = 2, + + /** + * @I915_ENGINE_CLASS_VIDEO_ENHANCE: + * + * Video enhancement engines (also referred to as "vebox") support + * instructions related to image enhancement. + */ I915_ENGINE_CLASS_VIDEO_ENHANCE = 3, - /* should be kept compact */ + /* Values in this enum should be kept compact. */ + /** + * @I915_ENGINE_CLASS_INVALID: + * + * Placeholder value to represent an invalid engine class assignment. + */ I915_ENGINE_CLASS_INVALID = -1 }; -- cgit v1.2.3 From ecf8eca51f33dbfddcc23902bdee65c17587247c Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Wed, 27 Apr 2022 21:19:25 -0700 Subject: drm/i915/xehp: Add compute engine ABI We're now ready to start exposing compute engines to userspace. v2: - Move kerneldoc for other engine classes to a separate patch. (Andi) Cc: Daniele Ceraolo Spurio Cc: Tvrtko Ursulin Cc: Vinay Belgaumkar Cc: Jordan Justen Cc: Szymon Morek UMD (mesa): https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14395 Signed-off-by: Matt Roper Acked-by: Tvrtko Ursulin Reviewed-by: Andi Shyti Reviewed-by: Jordan Justen Tested-by: Jordan Justen # mesa anvil & iris Link: https://patchwork.freedesktop.org/patch/msgid/20220428041926.1483683-4-matthew.d.roper@intel.com --- include/uapi/drm/i915_drm.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index ec000fc6c879..a2def7b27009 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -203,6 +203,15 @@ enum drm_i915_gem_engine_class { */ I915_ENGINE_CLASS_VIDEO_ENHANCE = 3, + /** + * @I915_ENGINE_CLASS_COMPUTE: + * + * Compute engines support a subset of the instructions available + * on render engines: compute engines support Compute (GPGPU) and + * programmable media workloads, but do not support the 3D pipeline. + */ + I915_ENGINE_CLASS_COMPUTE = 4, + /* Values in this enum should be kept compact. */ /** -- cgit v1.2.3 From ec2a0f9c8b50865a11720651c9c536f20c578def Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Fri, 29 Apr 2022 14:36:58 -0700 Subject: kasan: mark KASAN_VMALLOC flags as kasan_vmalloc_flags_t Fix sparse warning: mm/kasan/shadow.c:496:15: warning: restricted kasan_vmalloc_flags_t degrades to integer Link: https://lkml.kernel.org/r/52d8fccdd3a48d4bdfd0ff522553bac2a13f1579.1649351254.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reported-by: kernel test robot Cc: Andrey Konovalov Cc: Marco Elver Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Andrey Ryabinin Signed-off-by: Andrew Morton --- include/linux/kasan.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index ceebcb9de7bf..b092277bf48d 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -23,10 +23,10 @@ struct task_struct; typedef unsigned int __bitwise kasan_vmalloc_flags_t; -#define KASAN_VMALLOC_NONE 0x00u -#define KASAN_VMALLOC_INIT 0x01u -#define KASAN_VMALLOC_VM_ALLOC 0x02u -#define KASAN_VMALLOC_PROT_NORMAL 0x04u +#define KASAN_VMALLOC_NONE ((__force kasan_vmalloc_flags_t)0x00u) +#define KASAN_VMALLOC_INIT ((__force kasan_vmalloc_flags_t)0x01u) +#define KASAN_VMALLOC_VM_ALLOC ((__force kasan_vmalloc_flags_t)0x02u) +#define KASAN_VMALLOC_PROT_NORMAL ((__force kasan_vmalloc_flags_t)0x04u) #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) -- cgit v1.2.3 From 5d8de293c224896a4da99763fce4f9794308caf4 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Apr 2022 14:37:59 -0700 Subject: vmcore: convert copy_oldmem_page() to take an iov_iter Patch series "Convert vmcore to use an iov_iter", v5. For some reason several people have been sending bad patches to fix compiler warnings in vmcore recently. Here's how it should be done. Compile-tested only on x86. As noted in the first patch, s390 should take this conversion a bit further, but I'm not inclined to do that work myself. This patch (of 3): Instead of passing in a 'buf' and 'userbuf' argument, pass in an iov_iter. s390 needs more work to pass the iov_iter down further, or refactor, but I'd be more comfortable if someone who can test on s390 did that work. It's more convenient to convert the whole of read_from_oldmem() to take an iov_iter at the same time, so rename it to read_from_oldmem_iter() and add a temporary read_from_oldmem() wrapper that creates an iov_iter. Link: https://lkml.kernel.org/r/20220408090636.560886-1-bhe@redhat.com Link: https://lkml.kernel.org/r/20220408090636.560886-2-bhe@redhat.com Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Baoquan He Reviewed-by: Christoph Hellwig Cc: Heiko Carstens Signed-off-by: Andrew Morton --- include/linux/crash_dump.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 620821549b23..a1cf7d5c03c7 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -24,11 +24,10 @@ extern int remap_oldmem_pfn_range(struct vm_area_struct *vma, unsigned long from, unsigned long pfn, unsigned long size, pgprot_t prot); -extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, - unsigned long, int); -extern ssize_t copy_oldmem_page_encrypted(unsigned long pfn, char *buf, - size_t csize, unsigned long offset, - int userbuf); +ssize_t copy_oldmem_page(struct iov_iter *i, unsigned long pfn, size_t csize, + unsigned long offset); +ssize_t copy_oldmem_page_encrypted(struct iov_iter *iter, unsigned long pfn, + size_t csize, unsigned long offset); void vmcore_cleanup(void); -- cgit v1.2.3 From e0690479917cbce740eef51fa3de92c69647a5ad Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Apr 2022 14:37:59 -0700 Subject: vmcore: convert read_from_oldmem() to take an iov_iter Remove the read_from_oldmem() wrapper introduced earlier and convert all the remaining callers to pass an iov_iter. Link: https://lkml.kernel.org/r/20220408090636.560886-4-bhe@redhat.com Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Baoquan He Reviewed-by: Christoph Hellwig Cc: Tiezhu Yang Cc: Amit Daniel Kachhap Cc: Al Viro Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- include/linux/crash_dump.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index a1cf7d5c03c7..0f3a656293b0 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -134,13 +134,11 @@ static inline int vmcore_add_device_dump(struct vmcoredd_data *data) #endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */ #ifdef CONFIG_PROC_VMCORE -ssize_t read_from_oldmem(char *buf, size_t count, - u64 *ppos, int userbuf, - bool encrypted); +ssize_t read_from_oldmem(struct iov_iter *iter, size_t count, + u64 *ppos, bool encrypted); #else -static inline ssize_t read_from_oldmem(char *buf, size_t count, - u64 *ppos, int userbuf, - bool encrypted) +static inline ssize_t read_from_oldmem(struct iov_iter *iter, size_t count, + u64 *ppos, bool encrypted) { return -EOPNOTSUPP; } -- cgit v1.2.3 From f485922d8fe4e44f6d52a5bb95a603b7c65554bb Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 29 Apr 2022 14:38:01 -0700 Subject: pipe: make poll_usage boolean and annotate its access Patch series "Fix data-races around epoll reported by KCSAN." This series suppresses a false positive KCSAN's message and fixes a real data-race. This patch (of 2): pipe_poll() runs locklessly and assigns 1 to poll_usage. Once poll_usage is set to 1, it never changes in other places. However, concurrent writes of a value trigger KCSAN, so let's make KCSAN happy. BUG: KCSAN: data-race in pipe_poll / pipe_poll write to 0xffff8880042f6678 of 4 bytes by task 174 on cpu 3: pipe_poll (fs/pipe.c:656) ep_item_poll.isra.0 (./include/linux/poll.h:88 fs/eventpoll.c:853) do_epoll_wait (fs/eventpoll.c:1692 fs/eventpoll.c:1806 fs/eventpoll.c:2234) __x64_sys_epoll_wait (fs/eventpoll.c:2246 fs/eventpoll.c:2241 fs/eventpoll.c:2241) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:113) write to 0xffff8880042f6678 of 4 bytes by task 177 on cpu 1: pipe_poll (fs/pipe.c:656) ep_item_poll.isra.0 (./include/linux/poll.h:88 fs/eventpoll.c:853) do_epoll_wait (fs/eventpoll.c:1692 fs/eventpoll.c:1806 fs/eventpoll.c:2234) __x64_sys_epoll_wait (fs/eventpoll.c:2246 fs/eventpoll.c:2241 fs/eventpoll.c:2241) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:113) Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 177 Comm: epoll_race Not tainted 5.17.0-58927-gf443e374ae13 #6 Hardware name: Red Hat KVM, BIOS 1.11.0-2.amzn2 04/01/2014 Link: https://lkml.kernel.org/r/20220322002653.33865-1-kuniyu@amazon.co.jp Link: https://lkml.kernel.org/r/20220322002653.33865-2-kuniyu@amazon.co.jp Fixes: 3b844826b6c6 ("pipe: avoid unnecessary EPOLLET wakeups under normal loads") Signed-off-by: Kuniyuki Iwashima Cc: Alexander Duyck Cc: Al Viro Cc: Davidlohr Bueso Cc: Kuniyuki Iwashima Cc: "Soheil Hassas Yeganeh" Cc: "Sridhar Samudrala" Signed-off-by: Andrew Morton --- include/linux/pipe_fs_i.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index c00c618ef290..cb0fd633a610 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -71,7 +71,7 @@ struct pipe_inode_info { unsigned int files; unsigned int r_counter; unsigned int w_counter; - unsigned int poll_usage; + bool poll_usage; struct page *tmp_page; struct fasync_struct *fasync_readers; struct fasync_struct *fasync_writers; -- cgit v1.2.3 From d679ae94fdd5d3ab00c35078f5af5f37e068b03d Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 29 Apr 2022 14:38:01 -0700 Subject: list: fix a data-race around ep->rdllist ep_poll() first calls ep_events_available() with no lock held and checks if ep->rdllist is empty by list_empty_careful(), which reads rdllist->prev. Thus all accesses to it need some protection to avoid store/load-tearing. Note INIT_LIST_HEAD_RCU() already has the annotation for both prev and next. Commit bf3b9f6372c4 ("epoll: Add busy poll support to epoll with socket fds.") added the first lockless ep_events_available(), and commit c5a282e9635e ("fs/epoll: reduce the scope of wq lock in epoll_wait()") made some ep_events_available() calls lockless and added single call under a lock, finally commit e59d3c64cba6 ("epoll: eliminate unnecessary lock for zero timeout") made the last ep_events_available() lockless. BUG: KCSAN: data-race in do_epoll_wait / do_epoll_wait write to 0xffff88810480c7d8 of 8 bytes by task 1802 on cpu 0: INIT_LIST_HEAD include/linux/list.h:38 [inline] list_splice_init include/linux/list.h:492 [inline] ep_start_scan fs/eventpoll.c:622 [inline] ep_send_events fs/eventpoll.c:1656 [inline] ep_poll fs/eventpoll.c:1806 [inline] do_epoll_wait+0x4eb/0xf40 fs/eventpoll.c:2234 do_epoll_pwait fs/eventpoll.c:2268 [inline] __do_sys_epoll_pwait fs/eventpoll.c:2281 [inline] __se_sys_epoll_pwait+0x12b/0x240 fs/eventpoll.c:2275 __x64_sys_epoll_pwait+0x74/0x80 fs/eventpoll.c:2275 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff88810480c7d8 of 8 bytes by task 1799 on cpu 1: list_empty_careful include/linux/list.h:329 [inline] ep_events_available fs/eventpoll.c:381 [inline] ep_poll fs/eventpoll.c:1797 [inline] do_epoll_wait+0x279/0xf40 fs/eventpoll.c:2234 do_epoll_pwait fs/eventpoll.c:2268 [inline] __do_sys_epoll_pwait fs/eventpoll.c:2281 [inline] __se_sys_epoll_pwait+0x12b/0x240 fs/eventpoll.c:2275 __x64_sys_epoll_pwait+0x74/0x80 fs/eventpoll.c:2275 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0xffff88810480c7d0 -> 0xffff888103c15098 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 1799 Comm: syz-fuzzer Tainted: G W 5.17.0-rc7-syzkaller-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Link: https://lkml.kernel.org/r/20220322002653.33865-3-kuniyu@amazon.co.jp Fixes: e59d3c64cba6 ("epoll: eliminate unnecessary lock for zero timeout") Fixes: c5a282e9635e ("fs/epoll: reduce the scope of wq lock in epoll_wait()") Fixes: bf3b9f6372c4 ("epoll: Add busy poll support to epoll with socket fds.") Signed-off-by: Kuniyuki Iwashima Reported-by: syzbot+bdd6e38a1ed5ee58d8bd@syzkaller.appspotmail.com Cc: Al Viro , Andrew Morton Cc: Kuniyuki Iwashima Cc: Kuniyuki Iwashima Cc: "Soheil Hassas Yeganeh" Cc: Davidlohr Bueso Cc: "Sridhar Samudrala" Cc: Alexander Duyck Signed-off-by: Andrew Morton --- include/linux/list.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/list.h b/include/linux/list.h index dd6c2041d09c..d7d2bfa1a365 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -35,7 +35,7 @@ static inline void INIT_LIST_HEAD(struct list_head *list) { WRITE_ONCE(list->next, list); - list->prev = list; + WRITE_ONCE(list->prev, list); } #ifdef CONFIG_DEBUG_LIST @@ -306,7 +306,7 @@ static inline int list_empty(const struct list_head *head) static inline void list_del_init_careful(struct list_head *entry) { __list_del_entry(entry); - entry->prev = entry; + WRITE_ONCE(entry->prev, entry); smp_store_release(&entry->next, entry); } @@ -326,7 +326,7 @@ static inline void list_del_init_careful(struct list_head *entry) static inline int list_empty_careful(const struct list_head *head) { struct list_head *next = smp_load_acquire(&head->next); - return list_is_head(next, head) && (next == head->prev); + return list_is_head(next, head) && (next == READ_ONCE(head->prev)); } /** -- cgit v1.2.3 From a9866bef5171c859cfabc1155c594d28f194aa23 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Fri, 29 Apr 2022 14:38:02 -0700 Subject: ptrace: fix wrong comment of PT_DTRACE PT_DTRACE is only used on um now, fix the wrong comment. Link: https://lkml.kernel.org/r/1649240981-11024-3-git-send-email-yangtiezhu@loongson.cn Signed-off-by: Tiezhu Yang Cc: Oleg Nesterov Signed-off-by: Andrew Morton --- include/linux/ptrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 15b3d176b6b4..db4509587d2c 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -30,7 +30,7 @@ extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, #define PT_SEIZED 0x00010000 /* SEIZE used, enable new behavior */ #define PT_PTRACED 0x00000001 -#define PT_DTRACE 0x00000002 /* delayed trace (used on m68k, i386) */ +#define PT_DTRACE 0x00000002 /* delayed trace (used on um) */ #define PT_OPT_FLAG_SHIFT 3 /* PT_TRACE_* event enable flags */ -- cgit v1.2.3 From 0e0af57e0e91b304f36b7d1dba859e3c04094273 Mon Sep 17 00:00:00 2001 From: "Dr. Thomas Orgis" Date: Fri, 29 Apr 2022 14:38:03 -0700 Subject: taskstats: version 12 with thread group and exe info The task exit struct needs some crucial information to be able to provide an enhanced version of process and thread accounting. This change provides: 1. ac_tgid in additon to ac_pid 2. thread group execution walltime in ac_tgetime 3. flag AGROUP in ac_flag to indicate the last task in a thread group / process 4. device ID and inode of task's /proc/self/exe in ac_exe_dev and ac_exe_inode 5. tools/accounting/procacct as demonstrator When a task exits, taskstats are reported to userspace including the task's pid and ppid, but without the id of the thread group this task is part of. Without the tgid, the stats of single tasks cannot be correlated to each other as a thread group (process). The taskstats documentation suggests that on process exit a data set consisting of accumulated stats for the whole group is produced. But such an additional set of stats is only produced for actually multithreaded processes, not groups that had only one thread, and also those stats only contain data about delay accounting and not the more basic information about CPU and memory resource usage. Adding the AGROUP flag to be set when the last task of a group exited enables determination of process end also for single-threaded processes. My applicaton basically does enhanced process accounting with summed cputime, biggest maxrss, tasks per process. The data is not available with the traditional BSD process accounting (which is not designed to be extensible) and the taskstats interface allows more efficient on-the-fly grouping and summing of the stats, anyway, without intermediate disk writes. Furthermore, I do carry statistics on which exact program binary is used how often with associated resources, getting a picture on how important which parts of a collection of installed scientific software in different versions are, and how well they put load on the machine. This is enabled by providing information on /proc/self/exe for each task. I assume the two 64-bit fields for device ID and inode are more appropriate than the possibly large resolved path to keep the data volume down. Add the tgid to the stats to complete task identification, the flag AGROUP to mark the last task of a group, the group wallclock time, and inode-based identification of the associated executable file. Add tools/accounting/procacct.c as a simplified fork of getdelays.c to demonstrate process and thread accounting. [thomas.orgis@uni-hamburg.de: fix version number in comment] Link: https://lkml.kernel.org/r/20220405003601.7a5f6008@plasteblaster Link: https://lkml.kernel.org/r/20220331004106.64e5616b@plasteblaster Signed-off-by: Dr. Thomas Orgis Reviewed-by: Ismael Luceno Cc: Balbir Singh Cc: Eric W. Biederman Cc: xu xin Cc: Yang Yang Signed-off-by: Andrew Morton --- include/uapi/linux/acct.h | 3 ++- include/uapi/linux/taskstats.h | 24 +++++++++++++++++++++--- 2 files changed, 23 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/acct.h b/include/uapi/linux/acct.h index 985b89068591..0e591152aa8a 100644 --- a/include/uapi/linux/acct.h +++ b/include/uapi/linux/acct.h @@ -103,12 +103,13 @@ struct acct_v3 /* * accounting flags */ - /* bit set when the process ... */ + /* bit set when the process/task ... */ #define AFORK 0x01 /* ... executed fork, but did not exec */ #define ASU 0x02 /* ... used super-user privileges */ #define ACOMPAT 0x04 /* ... used compatibility mode (VAX only not used) */ #define ACORE 0x08 /* ... dumped core */ #define AXSIG 0x10 /* ... was killed by a signal */ +#define AGROUP 0x20 /* ... was the last task of the process (task group) */ #if defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN) #define ACCT_BYTEORDER 0x80 /* accounting file is big endian */ diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index 12327d32378f..736154171489 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 11 +#define TASKSTATS_VERSION 12 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -48,7 +48,8 @@ struct taskstats { __u32 ac_exitcode; /* Exit status */ /* The accounting flags of a task as defined in - * Defined values are AFORK, ASU, ACOMPAT, ACORE, and AXSIG. + * Defined values are AFORK, ASU, ACOMPAT, ACORE, AXSIG, and AGROUP. + * (AGROUP since version 12). */ __u8 ac_flag; /* Record flags */ __u8 ac_nice; /* task_nice */ @@ -173,9 +174,26 @@ struct taskstats { /* v10: 64-bit btime to avoid overflow */ __u64 ac_btime64; /* 64-bit begin time */ - /* Delay waiting for memory compact */ + /* v11: Delay waiting for memory compact */ __u64 compact_count; __u64 compact_delay_total; + + /* v12 begin */ + __u32 ac_tgid; /* thread group ID */ + /* Thread group walltime up to now. This is total process walltime if + * AGROUP flag is set. + */ + __u64 ac_tgetime __attribute__((aligned(8))); + /* Lightweight information to identify process binary files. + * This leaves userspace to match this to a file system path, using + * MAJOR() and MINOR() macros to identify a device and mount point, + * the inode to identify the executable file. This is /proc/self/exe + * at the end, so matching the most recent exec(). Values are zero + * for kernel threads. + */ + __u64 ac_exe_dev; /* program binary device ID */ + __u64 ac_exe_inode; /* program binary inode number */ + /* v12 end */ }; -- cgit v1.2.3 From f94fd25cb0aaf77fd7453f31c5d394a1a68ecf60 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 28 Apr 2022 18:45:06 -0600 Subject: tcp: pass back data left in socket after receive This is currently done for CMSG_INQ, add an ability to do so via struct msghdr as well and have CMSG_INQ use that too. If the caller sets msghdr->msg_get_inq, then we'll pass back the hint in msghdr->msg_inq. Rearrange struct msghdr a bit so we can add this member while shrinking it at the same time. On a 64-bit build, it was 96 bytes before this change and 88 bytes afterwards. Reviewed-by: Eric Dumazet Signed-off-by: Jens Axboe Link: https://lore.kernel.org/r/650c22ca-cffc-0255-9a05-2413a1e20826@kernel.dk Signed-off-by: Jakub Kicinski --- include/linux/socket.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/socket.h b/include/linux/socket.h index 6f85f5d957ef..12085c9a8544 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -50,6 +50,9 @@ struct linger { struct msghdr { void *msg_name; /* ptr to socket address structure */ int msg_namelen; /* size of socket address structure */ + + int msg_inq; /* output, data left in socket */ + struct iov_iter msg_iter; /* data */ /* @@ -62,8 +65,9 @@ struct msghdr { void __user *msg_control_user; }; bool msg_control_is_user : 1; - __kernel_size_t msg_controllen; /* ancillary data buffer length */ + bool msg_get_inq : 1;/* return INQ after receive */ unsigned int msg_flags; /* flags on received message */ + __kernel_size_t msg_controllen; /* ancillary data buffer length */ struct kiocb *msg_iocb; /* ptr to iocb for async requests */ }; -- cgit v1.2.3 From f548a12efd5ab97e6b1fb332e5634ce44b3d9328 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 26 Apr 2022 17:39:50 -0600 Subject: io_uring: return hint on whether more data is available after receive For now just use a CQE flag for this, with big CQE support we could return the actual number of bytes left. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 49d1f3994f8d..92d1799892b2 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -220,9 +220,11 @@ struct io_uring_cqe { * * IORING_CQE_F_BUFFER If set, the upper 16 bits are the buffer ID * IORING_CQE_F_MORE If set, parent SQE will generate more CQE entries + * IORING_CQE_F_SOCK_NONEMPTY If set, more data to read after socket recv */ #define IORING_CQE_F_BUFFER (1U << 0) #define IORING_CQE_F_MORE (1U << 1) +#define IORING_CQE_F_SOCK_NONEMPTY (1U << 2) enum { IORING_CQE_BUFFER_SHIFT = 16, -- cgit v1.2.3 From de32bc6aad09131a30b4a9a738e2bf2ba5a9a5aa Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 28 Apr 2022 11:58:44 +0100 Subject: net: inline sock_alloc_send_skb sock_alloc_send_skb() is simple and just proxying to another function, so we can inline it and cut associated overhead. Signed-off-by: Pavel Begunkov Signed-off-by: David S. Miller --- include/net/sock.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 663041b92c21..73063c88a249 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1823,11 +1823,17 @@ int sock_getsockopt(struct socket *sock, int level, int op, char __user *optval, int __user *optlen); int sock_gettstamp(struct socket *sock, void __user *userstamp, bool timeval, bool time32); -struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, - int noblock, int *errcode); struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, unsigned long data_len, int noblock, int *errcode, int max_page_order); + +static inline struct sk_buff *sock_alloc_send_skb(struct sock *sk, + unsigned long size, + int noblock, int *errcode) +{ + return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0); +} + void *sock_kmalloc(struct sock *sk, int size, gfp_t priority); void sock_kfree_s(struct sock *sk, void *mem, int size); void sock_kzfree_s(struct sock *sk, void *mem, int size); -- cgit v1.2.3 From 657dd5f97b2ed16cdaa6339f42f9130240af1c04 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 28 Apr 2022 11:58:45 +0100 Subject: net: inline skb_zerocopy_iter_dgram skb_zerocopy_iter_dgram() is a small proxy function, inline it. For that, move __zerocopy_sg_from_iter into linux/skbuff.h Signed-off-by: Pavel Begunkov Signed-off-by: David S. Miller --- include/linux/skbuff.h | 36 ++++++++++++++++++++++-------------- 1 file changed, 22 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index dc4b3e1cf21b..3270cb72e4d8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -684,20 +684,6 @@ struct ubuf_info { int mm_account_pinned_pages(struct mmpin *mmp, size_t size); void mm_unaccount_pinned_pages(struct mmpin *mmp); -struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size); -struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, - struct ubuf_info *uarg); - -void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); - -void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, - bool success); - -int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len); -int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, - struct msghdr *msg, int len, - struct ubuf_info *uarg); - /* This data is invariant across clones and lives at * the end of the header data, ie. at skb->end. */ @@ -1679,6 +1665,28 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) } #endif +struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size); +struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, + struct ubuf_info *uarg); + +void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); + +void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, + bool success); + +int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, + struct iov_iter *from, size_t length); + +static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb, + struct msghdr *msg, int len) +{ + return __zerocopy_sg_from_iter(skb->sk, skb, &msg->msg_iter, len); +} + +int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, + struct msghdr *msg, int len, + struct ubuf_info *uarg); + /* Internal */ #define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB))) -- cgit v1.2.3 From c526fd8f9f4f21cb83c0b1c9a1ee9c0ac9be9e2e Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 28 Apr 2022 11:58:46 +0100 Subject: net: inline dev_queue_xmit() Inline dev_queue_xmit() and dev_queue_xmit_accel(), they both are small proxy functions doing nothing but redirecting the control flow to __dev_queue_xmit(). Signed-off-by: Pavel Begunkov Signed-off-by: David S. Miller --- include/linux/netdevice.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b75ca2d095ae..4aba92a4042a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2940,10 +2940,20 @@ u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); -int dev_queue_xmit(struct sk_buff *skb); -int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev); +int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev); int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id); +static inline int dev_queue_xmit(struct sk_buff *skb) +{ + return __dev_queue_xmit(skb, NULL); +} + +static inline int dev_queue_xmit_accel(struct sk_buff *skb, + struct net_device *sb_dev) +{ + return __dev_queue_xmit(skb, sb_dev); +} + static inline int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) { int ret; -- cgit v1.2.3 From 2f187bfa6f35cc8bf1626bfc09449a09a6063ea1 Mon Sep 17 00:00:00 2001 From: Colin Foster Date: Fri, 29 Apr 2022 14:30:36 -0700 Subject: net: ethernet: ocelot: remove the need for num_stats initializer There is a desire to share the oclot_stats_layout struct outside of the current vsc7514 driver. In order to do so, the length of the array needs to be known at compile time, and defined in the struct ocelot and struct felix_info. Since the array is defined in a .c file and would be declared in the header file via: extern struct ocelot_stat_layout[]; the size of the array will not be known at compile time to outside modules. To fix this, remove the need for defining the number of stats at compile time and allow this number to be determined at initialization. Signed-off-by: Colin Foster Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 9b4e6c78d0f4..5c4f57cfa785 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -105,6 +105,13 @@ #define REG_RESERVED_ADDR 0xffffffff #define REG_RESERVED(reg) REG(reg, REG_RESERVED_ADDR) +#define OCELOT_STAT_FLAG_END BIT(0) + +#define for_each_stat(ocelot, stat) \ + for ((stat) = ocelot->stats_layout; \ + !((stat)->flags & OCELOT_STAT_FLAG_END); \ + (stat)++) + enum ocelot_target { ANA = 1, QS, @@ -535,9 +542,12 @@ enum ocelot_ptp_pins { struct ocelot_stat_layout { u32 offset; + u32 flags; char name[ETH_GSTRING_LEN]; }; +#define OCELOT_STAT_END { .flags = OCELOT_STAT_FLAG_END } + struct ocelot_stats_region { struct list_head node; u32 offset; -- cgit v1.2.3 From 48cec73a891cca087fbc7791c4753784180991a9 Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Fri, 29 Apr 2022 09:19:53 +0200 Subject: net: lan966x: Fix compilation error MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Starting from the blamed commit, the lan966x build fails with the following compilation error: drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c:342:9: error: implicit declaration of function ‘ptp_find_pin_unlocked’ [-Werror=implicit-function-declaration] 342 | pin = ptp_find_pin_unlocked(phc->clock, PTP_PF_EXTTS, 0); The issue is that there is no stub function for ptp_find_pin_unlocked in case CONFIG_PTP_1588_CLOCK is not selected. Therefore add one. Reported-by: kernel test robot Fixes: f3d8e0a9c28ba0 ("net: lan966x: Add support for PTP_PF_EXTTS") Signed-off-by: Horatiu Vultur Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 554454cb8693..e8cc8b6bbf50 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -321,6 +321,10 @@ static inline int ptp_clock_index(struct ptp_clock *ptp) static inline int ptp_find_pin(struct ptp_clock *ptp, enum ptp_pin_function func, unsigned int chan) { return -1; } +static inline int ptp_find_pin_unlocked(struct ptp_clock *ptp, + enum ptp_pin_function func, + unsigned int chan) +{ return -1; } static inline int ptp_schedule_worker(struct ptp_clock *ptp, unsigned long delay) { return -EOPNOTSUPP; } -- cgit v1.2.3 From e788be95a57a9bebe446878ce9bf2750f6fe4974 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 28 Apr 2022 17:25:16 -0600 Subject: task_work: allow TWA_SIGNAL without a rescheduling IPI Some use cases don't always need an IPI when sending a TWA_SIGNAL notification. Add TWA_SIGNAL_NO_IPI, which is just like TWA_SIGNAL, except it doesn't send an IPI to the target task. It merely sets TIF_NOTIFY_SIGNAL and wakes up the task. This can be useful in avoiding a forceful transition to the kernel if the task is running in userspace. Depending on the task_work in question, it may be quite fine waiting for the next reschedule or kernel enter anyway, or the use case may even have other mechanisms for hinting to the task that a transition may be useful. This can drive more cooperative scheduling of task_work. Reviewed-by: Pavel Begunkov Link: https://lore.kernel.org/r/821f42b6-7d91-8074-8212-d34998097de4@kernel.dk Signed-off-by: Jens Axboe --- include/linux/sched/signal.h | 13 +++++++++++-- include/linux/task_work.h | 1 + 2 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 3c8b34876744..66b689f6cfcb 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -355,14 +355,23 @@ static inline void clear_notify_signal(void) smp_mb__after_atomic(); } +/* + * Returns 'true' if kick_process() is needed to force a transition from + * user -> kernel to guarantee expedient run of TWA_SIGNAL based task_work. + */ +static inline bool __set_notify_signal(struct task_struct *task) +{ + return !test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && + !wake_up_state(task, TASK_INTERRUPTIBLE); +} + /* * Called to break out of interruptible wait loops, and enter the * exit_to_user_mode_loop(). */ static inline void set_notify_signal(struct task_struct *task) { - if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && - !wake_up_state(task, TASK_INTERRUPTIBLE)) + if (__set_notify_signal(task)) kick_process(task); } diff --git a/include/linux/task_work.h b/include/linux/task_work.h index 897494b597ba..795ef5a68429 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -17,6 +17,7 @@ enum task_work_notify_mode { TWA_NONE, TWA_RESUME, TWA_SIGNAL, + TWA_SIGNAL_NO_IPI, }; static inline bool task_work_pending(struct task_struct *task) -- cgit v1.2.3 From e1169f06d5bbdbc2b22ae4e3083a4bf75ae5ecee Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 25 Apr 2022 19:49:03 -0600 Subject: io_uring: use TWA_SIGNAL_NO_IPI if IORING_SETUP_COOP_TASKRUN is used If this is set, io_uring will never use an IPI to deliver a task_work notification. This can be used in the common case where a single task or thread communicates with the ring, and doesn't rely on io_uring_cqe_peek(). This provides a noticeable win in performance, both from eliminating the IPI itself, but also from avoiding interrupting the submitting task unnecessarily. Reviewed-by: Pavel Begunkov Link: https://lore.kernel.org/r/20220426014904.60384-6-axboe@kernel.dk Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 980d82eb196e..a84f29d657c3 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -102,6 +102,14 @@ enum { #define IORING_SETUP_ATTACH_WQ (1U << 5) /* attach to existing wq */ #define IORING_SETUP_R_DISABLED (1U << 6) /* start with ring disabled */ #define IORING_SETUP_SUBMIT_ALL (1U << 7) /* continue submit on error */ +/* + * Cooperative task running. When requests complete, they often require + * forcing the submitter to transition to the kernel to complete. If this + * flag is set, work will be done when the task transitions anyway, rather + * than force an inter-processor interrupt reschedule. This avoids interrupting + * a task running in userspace, and saves an IPI. + */ +#define IORING_SETUP_COOP_TASKRUN (1U << 8) enum { IORING_OP_NOP, -- cgit v1.2.3 From ef060ea9e4fd3b763e7060a3af0a258d2d5d7c0d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 25 Apr 2022 19:49:04 -0600 Subject: io_uring: add IORING_SETUP_TASKRUN_FLAG If IORING_SETUP_COOP_TASKRUN is set to use cooperative scheduling for running task_work, then IORING_SETUP_TASKRUN_FLAG can be set so the application can tell if task_work is pending in the kernel for this ring. This allows use cases like io_uring_peek_cqe() to still function appropriately, or for the task to know when it would be useful to call io_uring_wait_cqe() to run pending events. Reviewed-by: Pavel Begunkov Link: https://lore.kernel.org/r/20220426014904.60384-7-axboe@kernel.dk Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index a84f29d657c3..fad63564678a 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -110,6 +110,12 @@ enum { * a task running in userspace, and saves an IPI. */ #define IORING_SETUP_COOP_TASKRUN (1U << 8) +/* + * If COOP_TASKRUN is set, get notified if task work is available for + * running and a kernel transition would be needed to run it. This sets + * IORING_SQ_TASKRUN in the sq ring flags. Not valid with COOP_TASKRUN. + */ +#define IORING_SETUP_TASKRUN_FLAG (1U << 9) enum { IORING_OP_NOP, @@ -256,6 +262,7 @@ struct io_sqring_offsets { */ #define IORING_SQ_NEED_WAKEUP (1U << 0) /* needs io_uring_enter wakeup */ #define IORING_SQ_CQ_OVERFLOW (1U << 1) /* CQ ring is overflown */ +#define IORING_SQ_TASKRUN (1U << 2) /* task should enter the kernel */ struct io_cqring_offsets { __u32 head; -- cgit v1.2.3 From d664e399128bd78b905ff480917e2c2d4949e101 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Apr 2022 15:31:02 +0200 Subject: sched: Fix missing prototype warnings A W=1 build emits more than a dozen missing prototype warnings related to scheduler and scheduler specific includes. Reported-by: kernel test robot Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220413133024.249118058@linutronix.de --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index fc74ea2578b7..a27316f5f737 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2388,4 +2388,6 @@ static inline void sched_core_free(struct task_struct *tsk) { } static inline void sched_core_fork(struct task_struct *p) { } #endif +extern void sched_set_stop_task(int cpu, struct task_struct *stop); + #endif -- cgit v1.2.3 From 1a90bfd220201fbe050dfc15deaac20ca5f15638 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 13 Apr 2022 15:31:05 +0200 Subject: smp: Make softirq handling RT safe in flush_smp_call_function_queue() flush_smp_call_function_queue() invokes do_softirq() which is not available on PREEMPT_RT. flush_smp_call_function_queue() is invoked from the idle task and the migration task with preemption or interrupts disabled. So RT kernels cannot process soft interrupts in that context as that has to acquire 'sleeping spinlocks' which is not possible with preemption or interrupts disabled and forbidden from the idle task anyway. The currently known SMP function call which raises a soft interrupt is in the block layer, but this functionality is not enabled on RT kernels due to latency and performance reasons. RT could wake up ksoftirqd unconditionally, but this wants to be avoided if there were soft interrupts pending already when this is invoked in the context of the migration task. The migration task might have preempted a threaded interrupt handler which raised a soft interrupt, but did not reach the local_bh_enable() to process it. The "running" ksoftirqd might prevent the handling in the interrupt thread context which is causing latency issues. Add a new function which handles this case explicitely for RT and falls back to do_softirq() on !RT kernels. In the RT case this warns when one of the flushed SMP function calls raised a soft interrupt so this can be investigated. [ tglx: Moved the RT part out of SMP code ] Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/YgKgL6aPj8aBES6G@linutronix.de Link: https://lore.kernel.org/r/20220413133024.356509586@linutronix.de --- include/linux/interrupt.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index f40754caaefa..a49fe8d88676 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -607,6 +607,15 @@ struct softirq_action asmlinkage void do_softirq(void); asmlinkage void __do_softirq(void); +#ifdef CONFIG_PREEMPT_RT +extern void do_softirq_post_smp_call_flush(unsigned int was_pending); +#else +static inline void do_softirq_post_smp_call_flush(unsigned int unused) +{ + do_softirq(); +} +#endif + extern void open_softirq(int nr, void (*action)(struct softirq_action *)); extern void softirq_init(void); extern void __raise_softirq_irqoff(unsigned int nr); -- cgit v1.2.3 From 47f753c1108e287edb3e27fad8a7511a9d55578e Mon Sep 17 00:00:00 2001 From: Tan Tee Min Date: Fri, 29 Apr 2022 19:58:07 +0800 Subject: net: stmmac: disable Split Header (SPH) for Intel platforms Based on DesignWare Ethernet QoS datasheet, we are seeing the limitation of Split Header (SPH) feature is not supported for Ipv4 fragmented packet. This SPH limitation will cause ping failure when the packets size exceed the MTU size. For example, the issue happens once the basic ping packet size is larger than the configured MTU size and the data is lost inside the fragmented packet, replaced by zeros/corrupted values, and leads to ping fail. So, disable the Split Header for Intel platforms. v2: Add fixes tag in commit message. Fixes: 67afd6d1cfdf("net: stmmac: Add Split Header support and enable it in XGMAC cores") Cc: # 5.10.x Suggested-by: Ong, Boon Leong Signed-off-by: Mohammad Athari Bin Ismail Signed-off-by: Wong Vee Khee Signed-off-by: Tan Tee Min Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 24eea1b05ca2..29917850f079 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -270,5 +270,6 @@ struct plat_stmmacenet_data { int msi_rx_base_vec; int msi_tx_base_vec; bool use_phy_wol; + bool sph_disable; }; #endif -- cgit v1.2.3 From 9bd1d9a0d8bb1a549831fd98fcc3105960f7068b Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Sun, 1 May 2022 16:55:06 +0200 Subject: soc: apple: Add RTKit IPC library Apple SoCs such as the M1 come with multiple embedded co-processors running proprietary firmware. Communication with those is established over a simple mailbox using the RTKit IPC protocol. This cannot be implemented inside the mailbox subsystem since on top of communication over channels we also need support for starting, hibernating and resetting these co-processors. We also need to handle shared memory allocations differently depending on the co-processor and don't want to split that across multiple drivers. Reviewed-by: Arnd Bergmann Signed-off-by: Sven Peter --- include/linux/soc/apple/rtkit.h | 155 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 155 insertions(+) create mode 100644 include/linux/soc/apple/rtkit.h (limited to 'include') diff --git a/include/linux/soc/apple/rtkit.h b/include/linux/soc/apple/rtkit.h new file mode 100644 index 000000000000..88eb832eac7b --- /dev/null +++ b/include/linux/soc/apple/rtkit.h @@ -0,0 +1,155 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR MIT */ +/* + * Apple RTKit IPC Library + * Copyright (C) The Asahi Linux Contributors + * + * Apple's SoCs come with various co-processors running their RTKit operating + * system. This protocol library is used by client drivers to use the + * features provided by them. + */ +#ifndef _LINUX_APPLE_RTKIT_H_ +#define _LINUX_APPLE_RTKIT_H_ + +#include +#include +#include + +/* + * Struct to represent implementation-specific RTKit operations. + * + * @buffer: Shared memory buffer allocated inside normal RAM. + * @iomem: Shared memory buffer controlled by the co-processors. + * @size: Size of the shared memory buffer. + * @iova: Device VA of shared memory buffer. + * @is_mapped: Shared memory buffer is managed by the co-processor. + */ + +struct apple_rtkit_shmem { + void *buffer; + void __iomem *iomem; + size_t size; + dma_addr_t iova; + bool is_mapped; +}; + +/* + * Struct to represent implementation-specific RTKit operations. + * + * @crashed: Called when the co-processor has crashed. Runs in process + * context. + * @recv_message: Function called when a message from RTKit is received + * on a non-system endpoint. Called from a worker thread. + * @recv_message_early: + * Like recv_message, but called from atomic context. It + * should return true if it handled the message. If it + * returns false, the message will be passed on to the + * worker thread. + * @shmem_setup: Setup shared memory buffer. If bfr.is_iomem is true the + * buffer is managed by the co-processor and needs to be mapped. + * Otherwise the buffer is managed by Linux and needs to be + * allocated. If not specified dma_alloc_coherent is used. + * Called in process context. + * @shmem_destroy: Undo the shared memory buffer setup in shmem_setup. If not + * specified dma_free_coherent is used. Called in process + * context. + */ +struct apple_rtkit_ops { + void (*crashed)(void *cookie); + void (*recv_message)(void *cookie, u8 endpoint, u64 message); + bool (*recv_message_early)(void *cookie, u8 endpoint, u64 message); + int (*shmem_setup)(void *cookie, struct apple_rtkit_shmem *bfr); + void (*shmem_destroy)(void *cookie, struct apple_rtkit_shmem *bfr); +}; + +struct apple_rtkit; + +/* + * Initializes the internal state required to handle RTKit. This + * should usually be called within _probe. + * + * @dev: Pointer to the device node this coprocessor is assocated with + * @cookie: opaque cookie passed to all functions defined in rtkit_ops + * @mbox_name: mailbox name used to communicate with the co-processor + * @mbox_idx: mailbox index to be used if mbox_name is NULL + * @ops: pointer to rtkit_ops to be used for this co-processor + */ +struct apple_rtkit *devm_apple_rtkit_init(struct device *dev, void *cookie, + const char *mbox_name, int mbox_idx, + const struct apple_rtkit_ops *ops); + +/* + * Reinitialize internal structures. Must only be called with the co-processor + * is held in reset. + */ +int apple_rtkit_reinit(struct apple_rtkit *rtk); + +/* + * Handle RTKit's boot process. Should be called after the CPU of the + * co-processor has been started. + */ +int apple_rtkit_boot(struct apple_rtkit *rtk); + +/* + * Quiesce the co-processor. + */ +int apple_rtkit_quiesce(struct apple_rtkit *rtk); + +/* + * Wake the co-processor up from hibernation mode. + */ +int apple_rtkit_wake(struct apple_rtkit *rtk); + +/* + * Shutdown the co-processor + */ +int apple_rtkit_shutdown(struct apple_rtkit *rtk); + +/* + * Checks if RTKit is running and ready to handle messages. + */ +bool apple_rtkit_is_running(struct apple_rtkit *rtk); + +/* + * Checks if RTKit has crashed. + */ +bool apple_rtkit_is_crashed(struct apple_rtkit *rtk); + +/* + * Starts an endpoint. Must be called after boot but before any messages can be + * sent or received from that endpoint. + */ +int apple_rtkit_start_ep(struct apple_rtkit *rtk, u8 endpoint); + +/* + * Send a message to the given endpoint. + * + * @rtk: RTKit reference + * @ep: target endpoint + * @message: message to be sent + * @completeion: will be completed once the message has been submitted + * to the hardware FIFO. Can be NULL. + * @atomic: if set to true this function can be called from atomic + * context. + */ +int apple_rtkit_send_message(struct apple_rtkit *rtk, u8 ep, u64 message, + struct completion *completion, bool atomic); + +/* + * Send a message to the given endpoint and wait until it has been submitted + * to the hardware FIFO. + * Will return zero on success and a negative error code on failure + * (e.g. -ETIME when the message couldn't be written within the given + * timeout) + * + * @rtk: RTKit reference + * @ep: target endpoint + * @message: message to be sent + * @timeout: timeout in milliseconds to allow the message transmission + * to be completed + * @atomic: if set to true this function can be called from atomic + * context. + */ +int apple_rtkit_send_message_wait(struct apple_rtkit *rtk, u8 ep, u64 message, + unsigned long timeout, bool atomic); + +#endif /* _LINUX_APPLE_RTKIT_H_ */ -- cgit v1.2.3 From 3254e0b9eb5649ffaa48717ebc9c593adc4ee6a9 Mon Sep 17 00:00:00 2001 From: Alexandru Tachici Date: Fri, 29 Apr 2022 18:34:31 +0300 Subject: ethtool: Add 10base-T1L link mode entry Add entry for the 10base-T1L full duplex mode. Reviewed-by: Andrew Lunn Reviewed-by: Oleksij Rempel Signed-off-by: Alexandru Tachici Signed-off-by: David S. Miller --- include/linux/phy.h | 2 +- include/uapi/linux/ethtool.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index 36ca2b5c2253..b12af9e2f389 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -65,7 +65,7 @@ extern const int phy_basic_ports_array[3]; extern const int phy_fibre_port_array[1]; extern const int phy_all_ports_features_array[7]; extern const int phy_10_100_features_array[4]; -extern const int phy_basic_t1_features_array[2]; +extern const int phy_basic_t1_features_array[3]; extern const int phy_gbit_features_array[2]; extern const int phy_10gbit_features_array[1]; diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 7bc4b8def12c..e0f0ee9bc89e 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1691,6 +1691,7 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_400000baseCR4_Full_BIT = 89, ETHTOOL_LINK_MODE_100baseFX_Half_BIT = 90, ETHTOOL_LINK_MODE_100baseFX_Full_BIT = 91, + ETHTOOL_LINK_MODE_10baseT1L_Full_BIT = 92, /* must be last entry */ __ETHTOOL_LINK_MODE_MASK_NBITS }; -- cgit v1.2.3 From 909b4f2bf764a903e9183111368f1509f9b40e6d Mon Sep 17 00:00:00 2001 From: Alexandru Tachici Date: Fri, 29 Apr 2022 18:34:32 +0300 Subject: net: phy: Add 10-BaseT1L registers The 802.3gc specification defines the 10-BaseT1L link mode for ethernet trafic on twisted wire pair. PMA status register can be used to detect if the phy supports 2.4 V TX level and PCS control register can be used to enable/disable PCS level loopback. Reviewed-by: Andrew Lunn Signed-off-by: Alexandru Tachici Signed-off-by: David S. Miller --- include/uapi/linux/mdio.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index c54e6eae5366..0b2eba36dd7c 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -67,6 +67,9 @@ #define MDIO_PCS_10GBRT_STAT2 33 /* 10GBASE-R/-T PCS status 2 */ #define MDIO_AN_10GBT_CTRL 32 /* 10GBASE-T auto-negotiation control */ #define MDIO_AN_10GBT_STAT 33 /* 10GBASE-T auto-negotiation status */ +#define MDIO_B10L_PMA_CTRL 2294 /* 10BASE-T1L PMA control */ +#define MDIO_PMA_10T1L_STAT 2295 /* 10BASE-T1L PMA status */ +#define MDIO_PCS_10T1L_CTRL 2278 /* 10BASE-T1L PCS control */ /* LASI (Link Alarm Status Interrupt) registers, defined by XENPAK MSA. */ #define MDIO_PMA_LASI_RXCTRL 0x9000 /* RX_ALARM control */ @@ -268,6 +271,28 @@ #define MDIO_AN_10GBT_STAT_MS 0x4000 /* Master/slave config */ #define MDIO_AN_10GBT_STAT_MSFLT 0x8000 /* Master/slave config fault */ +/* 10BASE-T1L PMA control */ +#define MDIO_PMA_10T1L_CTRL_LB_EN 0x0001 /* Enable loopback mode */ +#define MDIO_PMA_10T1L_CTRL_EEE_EN 0x0400 /* Enable EEE mode */ +#define MDIO_PMA_10T1L_CTRL_LOW_POWER 0x0800 /* Low-power mode */ +#define MDIO_PMA_10T1L_CTRL_2V4_EN 0x1000 /* Enable 2.4 Vpp operating mode */ +#define MDIO_PMA_10T1L_CTRL_TX_DIS 0x4000 /* Transmit disable */ +#define MDIO_PMA_10T1L_CTRL_PMA_RST 0x8000 /* MA reset */ + +/* 10BASE-T1L PMA status register. */ +#define MDIO_PMA_10T1L_STAT_LINK 0x0001 /* PMA receive link up */ +#define MDIO_PMA_10T1L_STAT_FAULT 0x0002 /* Fault condition detected */ +#define MDIO_PMA_10T1L_STAT_POLARITY 0x0004 /* Receive polarity is reversed */ +#define MDIO_PMA_10T1L_STAT_RECV_FAULT 0x0200 /* Able to detect fault on receive path */ +#define MDIO_PMA_10T1L_STAT_EEE 0x0400 /* PHY has EEE ability */ +#define MDIO_PMA_10T1L_STAT_LOW_POWER 0x0800 /* PMA has low-power ability */ +#define MDIO_PMA_10T1L_STAT_2V4_ABLE 0x1000 /* PHY has 2.4 Vpp operating mode ability */ +#define MDIO_PMA_10T1L_STAT_LB_ABLE 0x2000 /* PHY has loopback ability */ + +/* 10BASE-T1L PCS control register. */ +#define MDIO_PCS_10T1L_CTRL_LB 0x4000 /* Enable PCS level loopback mode */ +#define MDIO_PCS_10T1L_CTRL_RESET 0x8000 /* PCS reset */ + /* EEE Supported/Advertisement/LP Advertisement registers. * * EEE capability Register (3.20), Advertisement (7.60) and -- cgit v1.2.3 From 1b020e448e0fb67bcb04ee0f778d413045f965d3 Mon Sep 17 00:00:00 2001 From: Alexandru Tachici Date: Fri, 29 Apr 2022 18:34:33 +0300 Subject: net: phy: Add BaseT1 auto-negotiation registers Added BASE-T1 AN advertisement register (Registers 7.514, 7.515, and 7.516) and BASE-T1 AN LP Base Page ability register (Registers 7.517, 7.518, and 7.519). Reviewed-by: Andrew Lunn Signed-off-by: Alexandru Tachici Signed-off-by: David S. Miller --- include/uapi/linux/mdio.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index 0b2eba36dd7c..fa3515257f54 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -70,6 +70,14 @@ #define MDIO_B10L_PMA_CTRL 2294 /* 10BASE-T1L PMA control */ #define MDIO_PMA_10T1L_STAT 2295 /* 10BASE-T1L PMA status */ #define MDIO_PCS_10T1L_CTRL 2278 /* 10BASE-T1L PCS control */ +#define MDIO_AN_T1_CTRL 512 /* BASE-T1 AN control */ +#define MDIO_AN_T1_STAT 513 /* BASE-T1 AN status */ +#define MDIO_AN_T1_ADV_L 514 /* BASE-T1 AN advertisement register [15:0] */ +#define MDIO_AN_T1_ADV_M 515 /* BASE-T1 AN advertisement register [31:16] */ +#define MDIO_AN_T1_ADV_H 516 /* BASE-T1 AN advertisement register [47:32] */ +#define MDIO_AN_T1_LP_L 517 /* BASE-T1 AN LP Base Page ability register [15:0] */ +#define MDIO_AN_T1_LP_M 518 /* BASE-T1 AN LP Base Page ability register [31:16] */ +#define MDIO_AN_T1_LP_H 519 /* BASE-T1 AN LP Base Page ability register [47:32] */ /* LASI (Link Alarm Status Interrupt) registers, defined by XENPAK MSA. */ #define MDIO_PMA_LASI_RXCTRL 0x9000 /* RX_ALARM control */ @@ -293,6 +301,38 @@ #define MDIO_PCS_10T1L_CTRL_LB 0x4000 /* Enable PCS level loopback mode */ #define MDIO_PCS_10T1L_CTRL_RESET 0x8000 /* PCS reset */ +/* BASE-T1 auto-negotiation advertisement register [15:0] */ +#define MDIO_AN_T1_ADV_L_PAUSE_CAP ADVERTISE_PAUSE_CAP +#define MDIO_AN_T1_ADV_L_PAUSE_ASYM ADVERTISE_PAUSE_ASYM +#define MDIO_AN_T1_ADV_L_FORCE_MS 0x1000 /* Force Master/slave Configuration */ +#define MDIO_AN_T1_ADV_L_REMOTE_FAULT ADVERTISE_RFAULT +#define MDIO_AN_T1_ADV_L_ACK ADVERTISE_LPACK +#define MDIO_AN_T1_ADV_L_NEXT_PAGE_REQ ADVERTISE_NPAGE + +/* BASE-T1 auto-negotiation advertisement register [31:16] */ +#define MDIO_AN_T1_ADV_M_B10L 0x4000 /* device is compatible with 10BASE-T1L */ +#define MDIO_AN_T1_ADV_M_MST 0x0010 /* advertise master preference */ + +/* BASE-T1 auto-negotiation advertisement register [47:32] */ +#define MDIO_AN_T1_ADV_H_10L_TX_HI_REQ 0x1000 /* 10BASE-T1L High Level Transmit Request */ +#define MDIO_AN_T1_ADV_H_10L_TX_HI 0x2000 /* 10BASE-T1L High Level Transmit Ability */ + +/* BASE-T1 AN LP Base Page ability register [15:0] */ +#define MDIO_AN_T1_LP_L_PAUSE_CAP LPA_PAUSE_CAP +#define MDIO_AN_T1_LP_L_PAUSE_ASYM LPA_PAUSE_ASYM +#define MDIO_AN_T1_LP_L_FORCE_MS 0x1000 /* LP Force Master/slave Configuration */ +#define MDIO_AN_T1_LP_L_REMOTE_FAULT LPA_RFAULT +#define MDIO_AN_T1_LP_L_ACK LPA_LPACK +#define MDIO_AN_T1_LP_L_NEXT_PAGE_REQ LPA_NPAGE + +/* BASE-T1 AN LP Base Page ability register [31:16] */ +#define MDIO_AN_T1_LP_M_MST 0x0010 /* LP master preference */ +#define MDIO_AN_T1_LP_M_B10L 0x4000 /* LP is compatible with 10BASE-T1L */ + +/* BASE-T1 AN LP Base Page ability register [47:32] */ +#define MDIO_AN_T1_LP_H_10L_TX_HI_REQ 0x1000 /* 10BASE-T1L High Level LP Transmit Request */ +#define MDIO_AN_T1_LP_H_10L_TX_HI 0x2000 /* 10BASE-T1L High Level LP Transmit Ability */ + /* EEE Supported/Advertisement/LP Advertisement registers. * * EEE capability Register (3.20), Advertisement (7.60) and -- cgit v1.2.3 From 3da8ffd8545f62fec85a48a3c637b2f427974f11 Mon Sep 17 00:00:00 2001 From: Alexandru Tachici Date: Fri, 29 Apr 2022 18:34:34 +0300 Subject: net: phy: Add 10BASE-T1L support in phy-c45 This patch is needed because the BASE-T1 uses different registers for status, control and advertisement to those already employed in the existing phy-c45 functions. Where required, genphy_c45 functions will now check whether the device supports BASE-T1 and use the specific registers instead: 45.2.7.19 BASE-T1 AN control register, 45.2.7.20 BASE-T1 AN status, 45.2.7.21 BASE-T1 AN advertisement register, 45.2.7.22 BASE-T1 AN LP Base Page ability register, 45.2.1.185 BASE-T1 PMA/PMD control register. Tested-by: Oleksij Rempel Signed-off-by: Alexandru Tachici Signed-off-by: David S. Miller --- include/linux/mdio.h | 70 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/phy.h | 3 ++ include/uapi/linux/mdio.h | 10 +++++++ 3 files changed, 83 insertions(+) (limited to 'include') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index ecac96d52e01..00177567cfef 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -340,6 +340,76 @@ static inline void mii_10gbt_stat_mod_linkmode_lpa_t(unsigned long *advertising, advertising, lpa & MDIO_AN_10GBT_STAT_LP10G); } +/** + * mii_t1_adv_l_mod_linkmode_t + * @advertising: target the linkmode advertisement settings + * @lpa: value of the BASE-T1 Autonegotiation Advertisement [15:0] Register + * + * A small helper function that translates BASE-T1 Autonegotiation + * Advertisement [15:0] Register bits to linkmode advertisement settings. + * Other bits in advertising aren't changed. + */ +static inline void mii_t1_adv_l_mod_linkmode_t(unsigned long *advertising, u32 lpa) +{ + linkmode_mod_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising, + lpa & MDIO_AN_T1_ADV_L_PAUSE_CAP); + linkmode_mod_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising, + lpa & MDIO_AN_T1_ADV_L_PAUSE_ASYM); +} + +/** + * mii_t1_adv_m_mod_linkmode_t + * @advertising: target the linkmode advertisement settings + * @lpa: value of the BASE-T1 Autonegotiation Advertisement [31:16] Register + * + * A small helper function that translates BASE-T1 Autonegotiation + * Advertisement [31:16] Register bits to linkmode advertisement settings. + * Other bits in advertising aren't changed. + */ +static inline void mii_t1_adv_m_mod_linkmode_t(unsigned long *advertising, u32 lpa) +{ + linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, + advertising, lpa & MDIO_AN_T1_ADV_M_B10L); +} + +/** + * linkmode_adv_to_mii_t1_adv_l_t + * @advertising: the linkmode advertisement settings + * + * A small helper function that translates linkmode advertisement + * settings to phy autonegotiation advertisements for the + * BASE-T1 Autonegotiation Advertisement [15:0] Register. + */ +static inline u32 linkmode_adv_to_mii_t1_adv_l_t(unsigned long *advertising) +{ + u32 result = 0; + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising)) + result |= MDIO_AN_T1_ADV_L_PAUSE_CAP; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising)) + result |= MDIO_AN_T1_ADV_L_PAUSE_ASYM; + + return result; +} + +/** + * linkmode_adv_to_mii_t1_adv_m_t + * @advertising: the linkmode advertisement settings + * + * A small helper function that translates linkmode advertisement + * settings to phy autonegotiation advertisements for the + * BASE-T1 Autonegotiation Advertisement [31:16] Register. + */ +static inline u32 linkmode_adv_to_mii_t1_adv_m_t(unsigned long *advertising) +{ + u32 result = 0; + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, advertising)) + result |= MDIO_AN_T1_ADV_M_B10L; + + return result; +} + int __mdiobus_read(struct mii_bus *bus, int addr, u32 regnum); int __mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val); int __mdiobus_modify_changed(struct mii_bus *bus, int addr, u32 regnum, diff --git a/include/linux/phy.h b/include/linux/phy.h index b12af9e2f389..2d12054932ba 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -570,6 +570,7 @@ struct macsec_ops; * @autoneg_complete: Flag auto negotiation of the link has completed * @mdix: Current crossover * @mdix_ctrl: User setting of crossover + * @pma_extable: Cached value of PMA/PMD Extended Abilities Register * @interrupts: Flag interrupts have been enabled * @interface: enum phy_interface_t value * @skb: Netlink message for cable diagnostics @@ -698,6 +699,8 @@ struct phy_device { u8 mdix; u8 mdix_ctrl; + int pma_extable; + void (*phy_link_change)(struct phy_device *phydev, bool up); void (*adjust_link)(struct net_device *dev); diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index fa3515257f54..75b7257a51e1 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -70,6 +70,7 @@ #define MDIO_B10L_PMA_CTRL 2294 /* 10BASE-T1L PMA control */ #define MDIO_PMA_10T1L_STAT 2295 /* 10BASE-T1L PMA status */ #define MDIO_PCS_10T1L_CTRL 2278 /* 10BASE-T1L PCS control */ +#define MDIO_PMA_PMD_BT1 18 /* BASE-T1 PMA/PMD extended ability */ #define MDIO_AN_T1_CTRL 512 /* BASE-T1 AN control */ #define MDIO_AN_T1_STAT 513 /* BASE-T1 AN status */ #define MDIO_AN_T1_ADV_L 514 /* BASE-T1 AN advertisement register [15:0] */ @@ -78,6 +79,7 @@ #define MDIO_AN_T1_LP_L 517 /* BASE-T1 AN LP Base Page ability register [15:0] */ #define MDIO_AN_T1_LP_M 518 /* BASE-T1 AN LP Base Page ability register [31:16] */ #define MDIO_AN_T1_LP_H 519 /* BASE-T1 AN LP Base Page ability register [47:32] */ +#define MDIO_PMA_PMD_BT1_CTRL 2100 /* BASE-T1 PMA/PMD control register */ /* LASI (Link Alarm Status Interrupt) registers, defined by XENPAK MSA. */ #define MDIO_PMA_LASI_RXCTRL 0x9000 /* RX_ALARM control */ @@ -170,6 +172,7 @@ #define MDIO_PMA_CTRL2_10BT 0x000f /* 10BASE-T type */ #define MDIO_PMA_CTRL2_2_5GBT 0x0030 /* 2.5GBaseT type */ #define MDIO_PMA_CTRL2_5GBT 0x0031 /* 5GBaseT type */ +#define MDIO_PMA_CTRL2_BASET1 0x003D /* BASE-T1 type */ #define MDIO_PCS_CTRL2_TYPE 0x0003 /* PCS type selection */ #define MDIO_PCS_CTRL2_10GBR 0x0000 /* 10GBASE-R type */ #define MDIO_PCS_CTRL2_10GBX 0x0001 /* 10GBASE-X type */ @@ -223,6 +226,7 @@ #define MDIO_PMA_EXTABLE_1000BKX 0x0040 /* 1000BASE-KX ability */ #define MDIO_PMA_EXTABLE_100BTX 0x0080 /* 100BASE-TX ability */ #define MDIO_PMA_EXTABLE_10BT 0x0100 /* 10BASE-T ability */ +#define MDIO_PMA_EXTABLE_BT1 0x0800 /* BASE-T1 ability */ #define MDIO_PMA_EXTABLE_NBT 0x4000 /* 2.5/5GBASE-T ability */ /* PHY XGXS lane state register. */ @@ -301,6 +305,9 @@ #define MDIO_PCS_10T1L_CTRL_LB 0x4000 /* Enable PCS level loopback mode */ #define MDIO_PCS_10T1L_CTRL_RESET 0x8000 /* PCS reset */ +/* BASE-T1 PMA/PMD extended ability register. */ +#define MDIO_PMA_PMD_BT1_B10L_ABLE 0x0004 /* 10BASE-T1L Ability */ + /* BASE-T1 auto-negotiation advertisement register [15:0] */ #define MDIO_AN_T1_ADV_L_PAUSE_CAP ADVERTISE_PAUSE_CAP #define MDIO_AN_T1_ADV_L_PAUSE_ASYM ADVERTISE_PAUSE_ASYM @@ -333,6 +340,9 @@ #define MDIO_AN_T1_LP_H_10L_TX_HI_REQ 0x1000 /* 10BASE-T1L High Level LP Transmit Request */ #define MDIO_AN_T1_LP_H_10L_TX_HI 0x2000 /* 10BASE-T1L High Level LP Transmit Ability */ +/* BASE-T1 PMA/PMD control register */ +#define MDIO_PMA_PMD_BT1_CTRL_CFG_MST 0x4000 /* MASTER-SLAVE config value */ + /* EEE Supported/Advertisement/LP Advertisement registers. * * EEE capability Register (3.20), Advertisement (7.60) and -- cgit v1.2.3 From 246d921646c071b878480997c294db6c83215b06 Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Tue, 23 Nov 2021 13:37:52 -0500 Subject: fs-verity: define a function to return the integrity protected file digest Define a function named fsverity_get_digest() to return the verity file digest and the associated hash algorithm (enum hash_algo). This assumes that before calling fsverity_get_digest() the file must have been opened, which is even true for the IMA measure/appraise on file open policy rule use case (func=FILE_CHECK). do_open() calls vfs_open() immediately prior to ima_file_check(). Acked-by: Eric Biggers Signed-off-by: Mimi Zohar --- include/linux/fsverity.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index a7afc800bd8d..7af030fa3c36 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -12,8 +12,16 @@ #define _LINUX_FSVERITY_H #include +#include +#include #include +/* + * Largest digest size among all hash algorithms supported by fs-verity. + * Currently assumed to be <= size of fsverity_descriptor::root_hash. + */ +#define FS_VERITY_MAX_DIGEST_SIZE SHA512_DIGEST_SIZE + /* Verity operations for filesystems */ struct fsverity_operations { @@ -131,6 +139,9 @@ int fsverity_ioctl_enable(struct file *filp, const void __user *arg); /* measure.c */ int fsverity_ioctl_measure(struct file *filp, void __user *arg); +int fsverity_get_digest(struct inode *inode, + u8 digest[FS_VERITY_MAX_DIGEST_SIZE], + enum hash_algo *alg); /* open.c */ @@ -170,6 +181,13 @@ static inline int fsverity_ioctl_measure(struct file *filp, void __user *arg) return -EOPNOTSUPP; } +static inline int fsverity_get_digest(struct inode *inode, + u8 digest[FS_VERITY_MAX_DIGEST_SIZE], + enum hash_algo *alg) +{ + return -EOPNOTSUPP; +} + /* open.c */ static inline int fsverity_file_open(struct inode *inode, struct file *filp) -- cgit v1.2.3 From 57b8280a0a4163545b532ae516c2dd5c9b295ea3 Mon Sep 17 00:00:00 2001 From: Abhinav Kumar Date: Tue, 26 Apr 2022 07:41:18 -0700 Subject: drm: allow passing possible_crtcs to drm_writeback_connector_init() Clients of drm_writeback_connector_init() initialize the possible_crtcs and then invoke the call to this API. To simplify things, allow passing possible_crtcs as a parameter to drm_writeback_connector_init() and make changes to the other drm drivers to make them compatible with this change. changes in v2: - split the changes according to their functionality changes in v3: - allow passing possible_crtcs for existing users of drm_writeback_connector_init() - squash the vendor changes into the same commit so that each patch in the series can compile individually changes in v4: - keep only changes related to possible_crtcs - add line breaks after ARRAY_SIZE - stop using temporary variables for possible_crtcs changes in v5: - None changes in v6: - None changes in v7: - wrap long lines to match the coding style of existing drivers - Fix indentation and remove parenthesis where not needed - use u32 instead of uint32_t for possible_crtcs Signed-off-by: Abhinav Kumar Acked-by: Liviu Dudau Reviewed-by: Dmitry Baryshkov Reviewed-by: Laurent Pinchart Patchwork: https://patchwork.freedesktop.org/patch/483501/ Link: https://lore.kernel.org/r/1650984096-9964-2-git-send-email-quic_abhinavk@quicinc.com Signed-off-by: Dmitry Baryshkov --- include/drm/drm_writeback.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_writeback.h b/include/drm/drm_writeback.h index 9697d2714d2a..5d9263fdbd84 100644 --- a/include/drm/drm_writeback.h +++ b/include/drm/drm_writeback.h @@ -150,7 +150,8 @@ int drm_writeback_connector_init(struct drm_device *dev, struct drm_writeback_connector *wb_connector, const struct drm_connector_funcs *con_funcs, const struct drm_encoder_helper_funcs *enc_helper_funcs, - const u32 *formats, int n_formats); + const u32 *formats, int n_formats, + u32 possible_crtcs); int drm_writeback_set_fb(struct drm_connector_state *conn_state, struct drm_framebuffer *fb); -- cgit v1.2.3 From 7933aecffa28a1746997436426b5df767b2df925 Mon Sep 17 00:00:00 2001 From: Abhinav Kumar Date: Tue, 26 Apr 2022 07:41:19 -0700 Subject: drm: introduce drm_writeback_connector_init_with_encoder() API For vendors drivers which pass an already allocated and initialized encoder especially for cases where the encoder hardware is shared OR the writeback encoder shares the resources with the rest of the display pipeline introduce a new API, drm_writeback_connector_init_with_encoder() which expects an initialized encoder as a parameter and only sets up the writeback connector. changes in v5: - fix the encoder doc to indicate that its not valid for users of drm_writeback_connector_init_with_encoder() Reviewed-by: Liviu Dudau Signed-off-by: Abhinav Kumar Reviewed-by: Dmitry Baryshkov Reviewed-by: Laurent Pinchart Patchwork: https://patchwork.freedesktop.org/patch/483500/ Link: https://lore.kernel.org/r/1650984096-9964-3-git-send-email-quic_abhinavk@quicinc.com Signed-off-by: Dmitry Baryshkov --- include/drm/drm_writeback.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/drm/drm_writeback.h b/include/drm/drm_writeback.h index 5d9263fdbd84..17e576c80169 100644 --- a/include/drm/drm_writeback.h +++ b/include/drm/drm_writeback.h @@ -30,6 +30,8 @@ struct drm_writeback_connector { * @drm_writeback_connector control the behaviour of the @encoder * by passing the @enc_funcs parameter to drm_writeback_connector_init() * function. + * For users of drm_writeback_connector_init_with_encoder(), this field + * is not valid as the encoder is managed within their drivers. */ struct drm_encoder encoder; @@ -153,6 +155,12 @@ int drm_writeback_connector_init(struct drm_device *dev, const u32 *formats, int n_formats, u32 possible_crtcs); +int drm_writeback_connector_init_with_encoder(struct drm_device *dev, + struct drm_writeback_connector *wb_connector, + struct drm_encoder *enc, + const struct drm_connector_funcs *con_funcs, const u32 *formats, + int n_formats); + int drm_writeback_set_fb(struct drm_connector_state *conn_state, struct drm_framebuffer *fb); -- cgit v1.2.3 From 1ea28bc5542d607ff7c806e409a72862c5af8f5e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Thu, 21 Apr 2022 20:20:49 +0200 Subject: drm: handle kernel fences in drm_gem_plane_helper_prepare_fb v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit drm_gem_plane_helper_prepare_fb() was using drm_atomic_set_fence_for_plane() which ignores all implicit fences when an explicit fence is already set. That's rather unfortunate when the fb still has a kernel fence we need to wait for to avoid presenting garbage on the screen. So instead update the fence in the plane state directly. While at it also take care of all potential GEM objects and not just the first one. Also remove the now unused drm_atomic_set_fence_for_plane() function, new drivers should probably use the atomic helpers directly. v2: improve kerneldoc, use local variable and num_planes, WARN_ON_ONCE on missing planes. Signed-off-by: Christian König Reviewed-by: Daniel Vetter (v1) Acked-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20220429134230.24334-1-christian.koenig@amd.com --- include/drm/drm_atomic_uapi.h | 2 -- include/drm/drm_plane.h | 4 +--- 2 files changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/drm/drm_atomic_uapi.h b/include/drm/drm_atomic_uapi.h index 8cec52ad1277..4c6d39d7bdb2 100644 --- a/include/drm/drm_atomic_uapi.h +++ b/include/drm/drm_atomic_uapi.h @@ -49,8 +49,6 @@ drm_atomic_set_crtc_for_plane(struct drm_plane_state *plane_state, struct drm_crtc *crtc); void drm_atomic_set_fb_for_plane(struct drm_plane_state *plane_state, struct drm_framebuffer *fb); -void drm_atomic_set_fence_for_plane(struct drm_plane_state *plane_state, - struct dma_fence *fence); int __must_check drm_atomic_set_crtc_for_connector(struct drm_connector_state *conn_state, struct drm_crtc *crtc); diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h index 2628c7cde2da..89ea54652e87 100644 --- a/include/drm/drm_plane.h +++ b/include/drm/drm_plane.h @@ -74,9 +74,7 @@ struct drm_plane_state { * * Optional fence to wait for before scanning out @fb. The core atomic * code will set this when userspace is using explicit fencing. Do not - * write this field directly for a driver's implicit fence, use - * drm_atomic_set_fence_for_plane() to ensure that an explicit fence is - * preserved. + * write this field directly for a driver's implicit fence. * * Drivers should store any implicit fence in this from their * &drm_plane_helper_funcs.prepare_fb callback. See drm_gem_plane_helper_prepare_fb() -- cgit v1.2.3 From 8cf9e1210adf49cd83d11e2b1984540cf0e0be71 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 28 Apr 2022 17:59:39 +0200 Subject: mm: slab: fix comment for ARCH_KMALLOC_MINALIGN The comment next to the ARCH_KMALLOC_MINALIGN definition says that ARCH_KMALLOC_MINALIGN can be defined in arch headers. This is incorrect: it's actually ARCH_DMA_MINALIGN that can be defined there. Fix the comment. Signed-off-by: Andrey Konovalov Acked-by: David Rientjes Signed-off-by: Vlastimil Babka Link: https://lore.kernel.org/r/fe1ca7a25a054b61d1038686d07569416e287e7b.1651161548.git.andreyknvl@google.com --- include/linux/slab.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/slab.h b/include/linux/slab.h index 11ceddcae9f4..8c090599fc21 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -197,7 +197,7 @@ void kmem_dump_obj(void *object); /* * Some archs want to perform DMA into kmalloc caches and need a guaranteed * alignment larger than the alignment of a 64-bit integer. - * Setting ARCH_KMALLOC_MINALIGN in arch headers allows that. + * Setting ARCH_DMA_MINALIGN in arch headers allows that. */ #if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8 #define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN -- cgit v1.2.3 From 154036a3b3f39cb17fc65511011f4c4024846e91 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Thu, 28 Apr 2022 17:59:40 +0200 Subject: mm: slab: fix comment for __assume_kmalloc_alignment The comment next to the __assume_kmalloc_alignment definition is not precise: kmalloc relies on kmem_cache_alloc, so kmalloc technically returns pointers aligned to both ARCH_KMALLOC_MINALIGN and ARCH_SLAB_MINALIGN, not only to ARCH_KMALLOC_MINALIGN. (See create_kmalloc_cache()->create_boot_cache()->calculate_alignment() for SLAB and SLUB and __do_kmalloc_node() for SLOB.) Clarify the comment. The assumption specified by __assume_kmalloc_alignment is still correct, although it can be made stronger. I'll leave this to a separate patch. Signed-off-by: Andrey Konovalov Acked-by: David Rientjes Signed-off-by: Vlastimil Babka Link: https://lore.kernel.org/r/84d8142747230f2015eaf9705ee7c2e1a9f56596.1651161548.git.andreyknvl@google.com --- include/linux/slab.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/slab.h b/include/linux/slab.h index 8c090599fc21..58bb9392775d 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -217,9 +217,9 @@ void kmem_dump_obj(void *object); #endif /* - * kmalloc and friends return ARCH_KMALLOC_MINALIGN aligned - * pointers. kmem_cache_alloc and friends return ARCH_SLAB_MINALIGN - * aligned pointers. + * kmem_cache_alloc and friends return pointers aligned to ARCH_SLAB_MINALIGN. + * kmalloc and friends return pointers aligned to both ARCH_KMALLOC_MINALIGN + * and ARCH_SLAB_MINALIGN, but here we only assume the former alignment. */ #define __assume_kmalloc_alignment __assume_aligned(ARCH_KMALLOC_MINALIGN) #define __assume_slab_alignment __assume_aligned(ARCH_SLAB_MINALIGN) -- cgit v1.2.3 From 23587f7c5daa936524ede26201253a089666b5d9 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Fri, 29 Apr 2022 17:05:45 +0800 Subject: mm/slub: remove unused kmem_cache_order_objects max max field holds the largest slab order that was ever used for a slab cache. But it's unused now. Remove it. Signed-off-by: Miaohe Lin Reviewed-by: Muchun Song Acked-by: David Rientjes Signed-off-by: Vlastimil Babka Link: https://lore.kernel.org/r/20220429090545.33413-1-linmiaohe@huawei.com --- include/linux/slub_def.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 33c5c0e3bd8d..f9c68a9dac04 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -105,7 +105,6 @@ struct kmem_cache { struct kmem_cache_order_objects oo; /* Allocation and freeing of slabs */ - struct kmem_cache_order_objects max; struct kmem_cache_order_objects min; gfp_t allocflags; /* gfp flags to use on each alloc */ int refcount; /* Refcount for slab cache destroy */ -- cgit v1.2.3 From 94f697c5384bd7f9632acca483ba1ef9dd99ea97 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Fri, 29 Apr 2022 12:01:53 +0200 Subject: mtd: spi-nor: move spi_nor_write_ear() to winbond module The "Extended Address Register" is winbond specific. If the flash is larger than 16MiB and is used in 3 byte address mode, it is used to set the remaining address bits. Move the write_ear() function, the opcode macros and the spimem op template into the winbond module and rename them accordingly. Signed-off-by: Michael Walle Signed-off-by: Pratyush Yadav Reviewed-by: Pratyush Yadav Link: https://lore.kernel.org/r/20220429100153.2338501-1-michael@walle.cc --- include/linux/mtd/spi-nor.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 5e25a7b75ae2..e505c4a5c530 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -47,8 +47,6 @@ #define SPINOR_OP_RDID 0x9f /* Read JEDEC ID */ #define SPINOR_OP_RDSFDP 0x5a /* Read SFDP */ #define SPINOR_OP_RDCR 0x35 /* Read configuration register */ -#define SPINOR_OP_RDEAR 0xc8 /* Read Extended Address Register */ -#define SPINOR_OP_WREAR 0xc5 /* Write Extended Address Register */ #define SPINOR_OP_SRSTEN 0x66 /* Software Reset Enable */ #define SPINOR_OP_SRST 0x99 /* Software Reset */ #define SPINOR_OP_GBULK 0x98 /* Global Block Unlock */ -- cgit v1.2.3 From 43896f56b59eeaf08687fa976257ae7083d01b41 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Wed, 27 Apr 2022 18:21:31 +0200 Subject: clk: imx8mp: add clkout1/2 support clkout1 and clkout2 allow to supply clocks from the SoC to the board, which is used by some board designs to provide reference clocks. Signed-off-by: Lucas Stach Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20220427162131.3127303-1-l.stach@pengutronix.de Signed-off-by: Abel Vesa --- include/dt-bindings/clock/imx8mp-clock.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/clock/imx8mp-clock.h b/include/dt-bindings/clock/imx8mp-clock.h index e05d21bf7813..9d5cc2ddde89 100644 --- a/include/dt-bindings/clock/imx8mp-clock.h +++ b/include/dt-bindings/clock/imx8mp-clock.h @@ -317,10 +317,15 @@ #define IMX8MP_CLK_AUDIO_AXI 310 #define IMX8MP_CLK_HSIO_AXI 311 #define IMX8MP_CLK_MEDIA_ISP 312 - #define IMX8MP_CLK_MEDIA_DISP2_PIX 313 +#define IMX8MP_CLK_CLKOUT1_SEL 314 +#define IMX8MP_CLK_CLKOUT1_DIV 315 +#define IMX8MP_CLK_CLKOUT1 316 +#define IMX8MP_CLK_CLKOUT2_SEL 317 +#define IMX8MP_CLK_CLKOUT2_DIV 318 +#define IMX8MP_CLK_CLKOUT2 319 -#define IMX8MP_CLK_END 314 +#define IMX8MP_CLK_END 320 #define IMX8MP_CLK_AUDIOMIX_SAI1_IPG 0 #define IMX8MP_CLK_AUDIOMIX_SAI1_MCLK1 1 -- cgit v1.2.3 From b170143ae1113882731666aec9b9105356f1fc17 Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Sun, 1 May 2022 16:55:08 +0200 Subject: soc: apple: Add SART driver The NVMe co-processor on the Apple M1 uses a DMA address filter called SART for some DMA transactions. This adds a simple driver used to configure the memory regions from which DMA transactions are allowed. Unlike a real IOMMU, SART does not support any pagetables and can't be implemented inside the IOMMU subsystem using iommu_ops. It also can't be implemented using dma_map_ops since not all DMA transactions of the NVMe controller are filtered by SART. Instead, most buffers have to be registered using the integrated NVMe IOMMU and we can't have two separate dma_map_ops implementations for a single device. Co-developed-by: Hector Martin Reviewed-by: Arnd Bergmann Signed-off-by: Hector Martin Signed-off-by: Sven Peter --- include/linux/soc/apple/sart.h | 53 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 53 insertions(+) create mode 100644 include/linux/soc/apple/sart.h (limited to 'include') diff --git a/include/linux/soc/apple/sart.h b/include/linux/soc/apple/sart.h new file mode 100644 index 000000000000..2249bf6cde09 --- /dev/null +++ b/include/linux/soc/apple/sart.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR MIT */ +/* + * Apple SART device driver + * Copyright (C) The Asahi Linux Contributors + * + * Apple SART is a simple address filter for DMA transactions. + * Regions of physical memory must be added to the SART's allow + * list before any DMA can target these. Unlike a proper + * IOMMU no remapping can be done. + */ + +#ifndef _LINUX_SOC_APPLE_SART_H_ +#define _LINUX_SOC_APPLE_SART_H_ + +#include +#include +#include + +struct apple_sart; + +/* + * Get a reference to the SART attached to dev. + * + * Looks for the phandle reference in apple,sart and returns a pointer + * to the corresponding apple_sart struct to be used with + * apple_sart_add_allowed_region and apple_sart_remove_allowed_region. + */ +struct apple_sart *devm_apple_sart_get(struct device *dev); + +/* + * Adds the region [paddr, paddr+size] to the DMA allow list. + * + * @sart: SART reference + * @paddr: Start address of the region to be used for DMA + * @size: Size of the region to be used for DMA. + */ +int apple_sart_add_allowed_region(struct apple_sart *sart, phys_addr_t paddr, + size_t size); + +/* + * Removes the region [paddr, paddr+size] from the DMA allow list. + * + * Note that exact same paddr and size used for apple_sart_add_allowed_region + * have to be passed. + * + * @sart: SART reference + * @paddr: Start address of the region no longer used for DMA + * @size: Size of the region no longer used for DMA. + */ +int apple_sart_remove_allowed_region(struct apple_sart *sart, phys_addr_t paddr, + size_t size); + +#endif /* _LINUX_SOC_APPLE_SART_H_ */ -- cgit v1.2.3 From f502cc568de95e5ed9cc9e6133fa454fbe0c5c01 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 4 Mar 2022 11:48:38 -0800 Subject: KVM: Add max_vcpus field in common 'struct kvm' For TDX guests, the maximum number of vcpus needs to be specified when the TDX guest VM is initialized (creating the TDX data corresponding to TDX guest) before creating vcpu. It needs to record the maximum number of vcpus on VM creation (KVM_CREATE_VM) and return error if the number of vcpus exceeds it Because there is already max_vcpu member in arm64 struct kvm_arch, move it to common struct kvm and initialize it to KVM_MAX_VCPUS before kvm_arch_init_vm() instead of adding it to x86 struct kvm_arch. Signed-off-by: Sean Christopherson Signed-off-by: Isaku Yamahata Message-Id: Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 252ee4a61b58..f94f72bbd2d3 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -725,6 +725,7 @@ struct kvm { * and is accessed atomically. */ atomic_t online_vcpus; + int max_vcpus; int created_vcpus; int last_boosted_vcpu; struct list_head vm_list; -- cgit v1.2.3 From 1cdba21db2ca31514c60b9732fc3963ae24c59e0 Mon Sep 17 00:00:00 2001 From: Daniel Latypov Date: Fri, 29 Apr 2022 11:12:57 -0700 Subject: kunit: add ability to specify suite-level init and exit functions KUnit has support for setup/cleanup logic for each test case in a suite. But it lacks the ability to specify setup/cleanup for the entire suite itself. This can be used to do setup that is too expensive or cumbersome to do for each test. Or it can be used to do simpler things like log debug information after the suite completes. It's a fairly common feature, so the lack of it is noticeable. Some examples in other frameworks and languages: * https://docs.python.org/3/library/unittest.html#setupclass-and-teardownclass * https://google.github.io/googletest/reference/testing.html#Test::SetUpTestSuite Meta: This is very similar to this patch here: https://lore.kernel.org/linux-kselftest/20210805043503.20252-3-bvanassche@acm.org/ The changes from that patch: * pass in `struct kunit *` so users can do stuff like `kunit_info(suite, "debug message")` * makes sure the init failure is bubbled up as a failure * updates kunit-example-test.c to use a suite init * Updates kunit/usage.rst to mention the new support * some minor cosmetic things * use `suite_{init,exit}` instead of `{init/exit}_suite` * make suite init error message more consistent w/ test init * etc. Signed-off-by: Daniel Latypov Reviewed-by: David Gow Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- include/kunit/test.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index 17749b4467ad..607e02b8e167 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -153,6 +153,8 @@ static inline char *kunit_status_to_ok_not_ok(enum kunit_status status) * struct kunit_suite - describes a related collection of &struct kunit_case * * @name: the name of the test. Purely informational. + * @suite_init: called once per test suite before the test cases. + * @suite_exit: called once per test suite after all test cases. * @init: called before every test case. * @exit: called after every test case. * @test_cases: a null terminated array of test cases. @@ -167,6 +169,8 @@ static inline char *kunit_status_to_ok_not_ok(enum kunit_status status) */ struct kunit_suite { const char name[256]; + int (*suite_init)(struct kunit_suite *suite); + void (*suite_exit)(struct kunit_suite *suite); int (*init)(struct kunit *test); void (*exit)(struct kunit *test); struct kunit_case *test_cases; @@ -175,6 +179,7 @@ struct kunit_suite { char status_comment[KUNIT_STATUS_COMMENT_SIZE]; struct dentry *debugfs; char *log; + int suite_init_err; }; /** -- cgit v1.2.3 From db05628435aa761d30b4eae481a82befe7a8492a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 Apr 2022 06:27:12 +0200 Subject: blk-cgroup: move blkcg_{get,set}_fc_appid out of line No need to have these helpers inline. Also remove the stubs and just use an IS_ENABLED for the get side (the set side already is only built conditionlly). Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20220420042723.1010598-5-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 58 ++-------------------------------------------- 1 file changed, 2 insertions(+), 56 deletions(-) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 652cd05b0924..7a2f7de30173 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -218,61 +218,7 @@ static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } #endif /* CONFIG_BLK_CGROUP */ -#ifdef CONFIG_BLK_CGROUP_FC_APPID -/* - * Sets the fc_app_id field associted to blkcg - * @app_id: application identifier - * @cgrp_id: cgroup id - * @app_id_len: size of application identifier - */ -static inline int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len) -{ - struct cgroup *cgrp; - struct cgroup_subsys_state *css; - struct blkcg *blkcg; - int ret = 0; - - if (app_id_len > FC_APPID_LEN) - return -EINVAL; - - cgrp = cgroup_get_from_id(cgrp_id); - if (!cgrp) - return -ENOENT; - css = cgroup_get_e_css(cgrp, &io_cgrp_subsys); - if (!css) { - ret = -ENOENT; - goto out_cgrp_put; - } - blkcg = css_to_blkcg(css); - /* - * There is a slight race condition on setting the appid. - * Worst case an I/O may not find the right id. - * This is no different from the I/O we let pass while obtaining - * the vmid from the fabric. - * Adding the overhead of a lock is not necessary. - */ - strlcpy(blkcg->fc_app_id, app_id, app_id_len); - css_put(css); -out_cgrp_put: - cgroup_put(cgrp); - return ret; -} +int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len); +char *blkcg_get_fc_appid(struct bio *bio); -/** - * blkcg_get_fc_appid - get the fc app identifier associated with a bio - * @bio: target bio - * - * On success return the fc_app_id, on failure return NULL - */ -static inline char *blkcg_get_fc_appid(struct bio *bio) -{ - if (bio && bio->bi_blkg && - (bio->bi_blkg->blkcg->fc_app_id[0] != '\0')) - return bio->bi_blkg->blkcg->fc_app_id; - return NULL; -} -#else -static inline int blkcg_set_fc_appid(char *buf, u64 id, size_t len) { return -EINVAL; } -static inline char *blkcg_get_fc_appid(struct bio *bio) { return NULL; } -#endif /*CONFIG_BLK_CGROUP_FC_APPID*/ #endif /* _BLK_CGROUP_H */ -- cgit v1.2.3 From 216889aad362b5b7e998a5371348b5e95d485dd1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 Apr 2022 06:27:13 +0200 Subject: blk-cgroup: move blk_cgroup_congested out line There is no urgent need to inline this function, so move it out of line. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20220420042723.1010598-6-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 20 +------------------- 1 file changed, 1 insertion(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 7a2f7de30173..988965c1c27b 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -135,25 +135,7 @@ static inline struct blkcg *bio_blkcg(struct bio *bio) return NULL; } -static inline bool blk_cgroup_congested(void) -{ - struct cgroup_subsys_state *css; - bool ret = false; - - rcu_read_lock(); - css = kthread_blkcg(); - if (!css) - css = task_css(current, io_cgrp_id); - while (css) { - if (atomic_read(&css->cgroup->congestion_count)) { - ret = true; - break; - } - css = css->parent; - } - rcu_read_unlock(); - return ret; -} +bool blk_cgroup_congested(void); /** * blkcg_parent - get the parent of a blkcg -- cgit v1.2.3 From 397c9f46ee4d99024c64954b007c1b5762d01cb4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 Apr 2022 06:27:14 +0200 Subject: blk-cgroup: move blkcg_{pin,unpin}_online out of line Move these two functions out of line as there is no good reason to inline them. Also switch to passing a cgroup_subsys_state instead of doing the conversion in the caller to prepare for making the blkcg structure private to blk-cgroup. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20220420042723.1010598-7-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 46 ++-------------------------------------------- 1 file changed, 2 insertions(+), 44 deletions(-) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 988965c1c27b..0fb7459096e9 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -111,7 +111,6 @@ struct blkcg_gq { extern struct cgroup_subsys_state * const blkcg_root_css; -void blkcg_destroy_blkgs(struct blkcg *blkcg); void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); void blkcg_maybe_throttle_current(void); @@ -136,49 +135,8 @@ static inline struct blkcg *bio_blkcg(struct bio *bio) } bool blk_cgroup_congested(void); - -/** - * blkcg_parent - get the parent of a blkcg - * @blkcg: blkcg of interest - * - * Return the parent blkcg of @blkcg. Can be called anytime. - */ -static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) -{ - return css_to_blkcg(blkcg->css.parent); -} - -/** - * blkcg_pin_online - pin online state - * @blkcg: blkcg of interest - * - * While pinned, a blkcg is kept online. This is primarily used to - * impedance-match blkg and cgwb lifetimes so that blkg doesn't go offline - * while an associated cgwb is still active. - */ -static inline void blkcg_pin_online(struct blkcg *blkcg) -{ - refcount_inc(&blkcg->online_pin); -} - -/** - * blkcg_unpin_online - unpin online state - * @blkcg: blkcg of interest - * - * This is primarily used to impedance-match blkg and cgwb lifetimes so - * that blkg doesn't go offline while an associated cgwb is still active. - * When this count goes to zero, all active cgwbs have finished so the - * blkcg can continue destruction by calling blkcg_destroy_blkgs(). - */ -static inline void blkcg_unpin_online(struct blkcg *blkcg) -{ - do { - if (!refcount_dec_and_test(&blkcg->online_pin)) - break; - blkcg_destroy_blkgs(blkcg); - blkcg = blkcg_parent(blkcg); - } while (blkcg); -} +void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css); +void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css); #else /* CONFIG_BLK_CGROUP */ -- cgit v1.2.3 From dec223c92a4688f6c9642d640cfe15a99d289dd4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 Apr 2022 06:27:15 +0200 Subject: blk-cgroup: move struct blkcg to block/blk-cgroup.h There is no real need to expose the blkcg structure to the whole kernel. Move it to the private header an expose a helper to let the writeback code access the cgwb_list member. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20220420042723.1010598-8-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 6 ++---- include/linux/blk-cgroup.h | 32 +------------------------------- 2 files changed, 3 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 87ce24d238f3..2bd073fa6bb5 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -17,8 +17,6 @@ #include #include -struct blkcg; - static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi) { kref_get(&bdi->refcnt); @@ -154,7 +152,7 @@ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp); void wb_memcg_offline(struct mem_cgroup *memcg); -void wb_blkcg_offline(struct blkcg *blkcg); +void wb_blkcg_offline(struct cgroup_subsys_state *css); /** * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode @@ -378,7 +376,7 @@ static inline void wb_memcg_offline(struct mem_cgroup *memcg) { } -static inline void wb_blkcg_offline(struct blkcg *blkcg) +static inline void wb_blkcg_offline(struct cgroup_subsys_state *css) { } diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 0fb7459096e9..d7b188095040 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -37,29 +37,6 @@ enum blkg_iostat_type { BLKG_IOSTAT_NR, }; -struct blkcg_gq; -struct blkg_policy_data; - -struct blkcg { - struct cgroup_subsys_state css; - spinlock_t lock; - refcount_t online_pin; - - struct radix_tree_root blkg_tree; - struct blkcg_gq __rcu *blkg_hint; - struct hlist_head blkg_list; - - struct blkcg_policy_data *cpd[BLKCG_MAX_POLS]; - - struct list_head all_blkcgs_node; -#ifdef CONFIG_BLK_CGROUP_FC_APPID - char fc_app_id[FC_APPID_LEN]; -#endif -#ifdef CONFIG_CGROUP_WRITEBACK - struct list_head cgwb_list; -#endif -}; - struct blkg_iostat { u64 bytes[BLKG_IOSTAT_NR]; u64 ios[BLKG_IOSTAT_NR]; @@ -114,11 +91,6 @@ extern struct cgroup_subsys_state * const blkcg_root_css; void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); void blkcg_maybe_throttle_current(void); -static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) -{ - return css ? container_of(css, struct blkcg, css) : NULL; -} - /** * bio_blkcg - grab the blkcg associated with a bio * @bio: target bio @@ -137,12 +109,10 @@ static inline struct blkcg *bio_blkcg(struct bio *bio) bool blk_cgroup_congested(void); void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css); void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css); +struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css); #else /* CONFIG_BLK_CGROUP */ -struct blkcg { -}; - struct blkcg_gq { }; -- cgit v1.2.3 From f4a6a61cb6d40d9ae63e47743d33200f3efe3fe7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 Apr 2022 06:27:16 +0200 Subject: blktrace: cleanup the __trace_note_message interface Pass the cgroup_subsys_state instead of a the blkg so that blktrace doesn't need to poke into blk-cgroup internals, and give the name a blk prefix as the current name is way too generic for a public interface. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20220420042723.1010598-9-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 22501a293fa5..623e22492afa 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -27,12 +27,10 @@ struct blk_trace { atomic_t dropped; }; -struct blkcg; - extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *); extern void blk_trace_shutdown(struct request_queue *); -extern __printf(3, 4) -void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *fmt, ...); +__printf(3, 4) void __blk_trace_note_message(struct blk_trace *bt, + struct cgroup_subsys_state *css, const char *fmt, ...); /** * blk_add_trace_msg - Add a (simple) message to the blktrace stream @@ -47,14 +45,14 @@ void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *f * NOTE: Can not use 'static inline' due to presence of var args... * **/ -#define blk_add_cgroup_trace_msg(q, cg, fmt, ...) \ +#define blk_add_cgroup_trace_msg(q, css, fmt, ...) \ do { \ struct blk_trace *bt; \ \ rcu_read_lock(); \ bt = rcu_dereference((q)->blk_trace); \ if (unlikely(bt)) \ - __trace_note_message(bt, cg, fmt, ##__VA_ARGS__);\ + __blk_trace_note_message(bt, css, fmt, ##__VA_ARGS__);\ rcu_read_unlock(); \ } while (0) #define blk_add_trace_msg(q, fmt, ...) \ -- cgit v1.2.3 From bbb1ebe7a909db4de49777fb7676d5bf293f34c9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 Apr 2022 06:27:17 +0200 Subject: blk-cgroup: replace bio_blkcg with bio_blkcg_css All callers of bio_blkcg actually want the CSS, so replace it with an interface that does return the CSS. This now allows to move struct blkcg_gq to block/blk-cgroup.h instead of exposing it in a public header. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20220420042723.1010598-10-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 83 +++------------------------------------------- 1 file changed, 5 insertions(+), 78 deletions(-) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index d7b188095040..97c7968e3204 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -28,94 +28,18 @@ #define FC_APPID_LEN 129 #ifdef CONFIG_BLK_CGROUP - -enum blkg_iostat_type { - BLKG_IOSTAT_READ, - BLKG_IOSTAT_WRITE, - BLKG_IOSTAT_DISCARD, - - BLKG_IOSTAT_NR, -}; - -struct blkg_iostat { - u64 bytes[BLKG_IOSTAT_NR]; - u64 ios[BLKG_IOSTAT_NR]; -}; - -struct blkg_iostat_set { - struct u64_stats_sync sync; - struct blkg_iostat cur; - struct blkg_iostat last; -}; - -/* association between a blk cgroup and a request queue */ -struct blkcg_gq { - /* Pointer to the associated request_queue */ - struct request_queue *q; - struct list_head q_node; - struct hlist_node blkcg_node; - struct blkcg *blkcg; - - /* all non-root blkcg_gq's are guaranteed to have access to parent */ - struct blkcg_gq *parent; - - /* reference count */ - struct percpu_ref refcnt; - - /* is this blkg online? protected by both blkcg and q locks */ - bool online; - - struct blkg_iostat_set __percpu *iostat_cpu; - struct blkg_iostat_set iostat; - - struct blkg_policy_data *pd[BLKCG_MAX_POLS]; - - spinlock_t async_bio_lock; - struct bio_list async_bios; - union { - struct work_struct async_bio_work; - struct work_struct free_work; - }; - - atomic_t use_delay; - atomic64_t delay_nsec; - atomic64_t delay_start; - u64 last_delay; - int last_use; - - struct rcu_head rcu_head; -}; - extern struct cgroup_subsys_state * const blkcg_root_css; void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); void blkcg_maybe_throttle_current(void); - -/** - * bio_blkcg - grab the blkcg associated with a bio - * @bio: target bio - * - * This returns the blkcg associated with a bio, %NULL if not associated. - * Callers are expected to either handle %NULL or know association has been - * done prior to calling this. - */ -static inline struct blkcg *bio_blkcg(struct bio *bio) -{ - if (bio && bio->bi_blkg) - return bio->bi_blkg->blkcg; - return NULL; -} - bool blk_cgroup_congested(void); void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css); void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css); struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css); +struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio); #else /* CONFIG_BLK_CGROUP */ -struct blkcg_gq { -}; - #define blkcg_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL)) static inline void blkcg_maybe_throttle_current(void) { } @@ -123,7 +47,10 @@ static inline bool blk_cgroup_congested(void) { return false; } #ifdef CONFIG_BLOCK static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { } -static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } +static inline struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio) +{ + return NULL; +} #endif /* CONFIG_BLOCK */ #endif /* CONFIG_BLK_CGROUP */ -- cgit v1.2.3 From 7f20ba7c42fd899557cef7d001f48711c3066ba5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 Apr 2022 06:27:18 +0200 Subject: blk-cgroup: remove pointless CONFIG_BLOCK ifdefs No need to make BLK_CGROUP stubs conditional on CONFIG_BLOCK as they can't be used without that. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20220420042723.1010598-11-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 97c7968e3204..abbfa97d6d46 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -44,15 +44,11 @@ struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio); static inline void blkcg_maybe_throttle_current(void) { } static inline bool blk_cgroup_congested(void) { return false; } - -#ifdef CONFIG_BLOCK static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { } static inline struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio) { return NULL; } -#endif /* CONFIG_BLOCK */ - #endif /* CONFIG_BLK_CGROUP */ int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len); -- cgit v1.2.3 From c97ab271576dec2170e7b804cb05f7617b30fed9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 Apr 2022 06:27:19 +0200 Subject: blk-cgroup: remove unneeded includes from Remove all the includes that aren't actually needed from and push them to the actual source files where needed. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20220420042723.1010598-12-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index abbfa97d6d46..9f40dbc65f82 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -14,16 +14,11 @@ * Nauman Rafique */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include +#include + +struct bio; +struct cgroup_subsys_state; +struct request_queue; #define FC_APPID_LEN 129 -- cgit v1.2.3 From f624506f98b198e65b44da303f44974590fb16c0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 Apr 2022 06:27:23 +0200 Subject: kthread: unexport kthread_blkcg kthread_blkcg is only used by the built-in blk-cgroup code. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20220420042723.1010598-16-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/kthread.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index de5d75bafd66..30e5bec81d2b 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -222,9 +222,5 @@ void kthread_associate_blkcg(struct cgroup_subsys_state *css); struct cgroup_subsys_state *kthread_blkcg(void); #else static inline void kthread_associate_blkcg(struct cgroup_subsys_state *css) { } -static inline struct cgroup_subsys_state *kthread_blkcg(void) -{ - return NULL; -} #endif #endif /* _LINUX_KTHREAD_H */ -- cgit v1.2.3 From c92a6b5d63359dd6d2ce6ea88ecd8e31dd769f6b Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Wed, 2 Mar 2022 00:35:47 -0500 Subject: scsi: core: Query VPD size before getting full page We currently default to 255 bytes when fetching VPD pages during discovery. However, we have had a few devices that are known to wedge if the requested buffer exceeds a certain size. See commit af73623f5f10 ("[SCSI] sd: Reduce buffer size for vpd request") which works around one example of this problem in the SCSI disk driver. With commit d188b0675b21 ("scsi: core: Add sysfs attributes for VPD pages 0h and 89h") we now risk triggering the same issue in the generic midlayer code. The problem with the ATA VPD page in particular is that the SCSI portion of the page is trailed by 512 bytes of verbatim ATA Identify Device information. However, not all controllers actually provide the additional 512 bytes and will lock up if one asks for more than the 64 bytes containing the SCSI protocol fields. Instead of picking a new, somewhat arbitrary, number of bytes for the VPD buffer size, start fetching the 4-byte header for each page. The header contains the size of the page as far as the device is concerned. We can use the reported size to specify the correct allocation length when subsequently fetching the full page. The header validation is done by a new helper function scsi_get_vpd_size() and both scsi_get_vpd_page() and scsi_get_vpd_buf() now rely on this to query the page size. In addition, scsi_get_vpd_page() is simplified to mirror the logic in scsi_get_vpd_page(). This involves removing the Supported VPD Pages lookup prior to attempting to query a page. There does not appear any evidence, even in the oldest SCSI specs, that this step is required. We already rely on scsi_get_vpd_page() throughout the stack and this function never consulted the Supported VPD Pages. Since this has not caused any problems it should be safe to remove the precondition from scsi_get_vpd_page(). Instrumented runs also revealed that the Supported VPD Pages lookup had little effect since the device page index often was larger than the supplied buffer size. As a result, inquiries frequently bypassed the index check and went through the "If we ran off the end of the buffer, give us the benefit of the doubt" code path which assumed the page was present despite not being listed. The revised code takes both the page size reported by the device as well as the size of the buffer provided by the scsi_get_vpd_page() caller into account. Link: https://lore.kernel.org/r/20220302053559.32147-3-martin.petersen@oracle.com Fixes: d188b0675b21 ("scsi: core: Add sysfs attributes for VPD pages 0h and 89h") Reported-by: Maciej W. Rozycki Tested-by: Maciej W. Rozycki Reviewed-by: Christoph Hellwig Signed-off-by: Martin K. Petersen --- include/scsi/scsi_device.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 57e3e239a1fc..c37cc5b3ebeb 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -100,6 +100,10 @@ struct scsi_vpd { unsigned char data[]; }; +enum scsi_vpd_parameters { + SCSI_VPD_HEADER_SIZE = 4, +}; + struct scsi_device { struct Scsi_Host *host; struct request_queue *request_queue; @@ -141,7 +145,6 @@ struct scsi_device { const char * model; /* ... after scan; point to static string */ const char * rev; /* ... "nullnullnullnull" before scan */ -#define SCSI_VPD_PG_LEN 255 struct scsi_vpd __rcu *vpd_pg0; struct scsi_vpd __rcu *vpd_pg83; struct scsi_vpd __rcu *vpd_pg80; -- cgit v1.2.3 From e60ac0b9e445822e60230c00e68d8cdb7748701b Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Wed, 2 Mar 2022 00:35:50 -0500 Subject: scsi: core: Cache VPD pages b0, b1, b2 The SCSI disk driver consults VPD pages b0 (Block Limits), b1 (Block Device Characteristics), and b2 (Logical Block Provisioning). Instead of having sd.c request these pages every revalidate cycle, cache them along with the other commonly used VPDs. Link: https://lore.kernel.org/r/20220302053559.32147-6-martin.petersen@oracle.com Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- include/scsi/scsi_device.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index c37cc5b3ebeb..7cf5f3b7589f 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -149,6 +149,10 @@ struct scsi_device { struct scsi_vpd __rcu *vpd_pg83; struct scsi_vpd __rcu *vpd_pg80; struct scsi_vpd __rcu *vpd_pg89; + struct scsi_vpd __rcu *vpd_pgb0; + struct scsi_vpd __rcu *vpd_pgb1; + struct scsi_vpd __rcu *vpd_pgb2; + struct scsi_target *sdev_target; blist_flags_t sdev_bflags; /* black/white flags as also found in -- cgit v1.2.3 From f5e6d5a343761081317c89d23489c93fbafc69ff Mon Sep 17 00:00:00 2001 From: Sumit Saxena Date: Fri, 29 Apr 2022 17:16:35 -0400 Subject: scsi: mpi3mr: Add support for driver commands There are certain bsg commands which need to be completed by the driver without involving firmware. These requests are termed driver commands. Add support for these. Link: https://lore.kernel.org/r/20220429211641.642010-3-sumit.saxena@broadcom.com Reported by: Stephen Rothwell Reported-by: kernel test robot Reviewed-by: Himanshu Madhani Signed-off-by: Sumit Saxena Signed-off-by: Martin K. Petersen --- include/uapi/scsi/scsi_bsg_mpi3mr.h | 457 ++++++++++++++++++++++++++++++++++++ 1 file changed, 457 insertions(+) create mode 100644 include/uapi/scsi/scsi_bsg_mpi3mr.h (limited to 'include') diff --git a/include/uapi/scsi/scsi_bsg_mpi3mr.h b/include/uapi/scsi/scsi_bsg_mpi3mr.h new file mode 100644 index 000000000000..66697d963f64 --- /dev/null +++ b/include/uapi/scsi/scsi_bsg_mpi3mr.h @@ -0,0 +1,457 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later WITH Linux-syscall-note */ +/* + * Driver for Broadcom MPI3 Storage Controllers + * + * Copyright (C) 2017-2022 Broadcom Inc. + * (mailto: mpi3mr-linuxdrv.pdl@broadcom.com) + * + */ + +#ifndef SCSI_BSG_MPI3MR_H_INCLUDED +#define SCSI_BSG_MPI3MR_H_INCLUDED + +#include + +/* Definitions for BSG commands */ +#define MPI3MR_IOCTL_VERSION 0x06 + +#define MPI3MR_APP_DEFAULT_TIMEOUT (60) /*seconds*/ + +#define MPI3MR_BSG_ADPTYPE_UNKNOWN 0 +#define MPI3MR_BSG_ADPTYPE_AVGFAMILY 1 + +#define MPI3MR_BSG_ADPSTATE_UNKNOWN 0 +#define MPI3MR_BSG_ADPSTATE_OPERATIONAL 1 +#define MPI3MR_BSG_ADPSTATE_FAULT 2 +#define MPI3MR_BSG_ADPSTATE_IN_RESET 3 +#define MPI3MR_BSG_ADPSTATE_UNRECOVERABLE 4 + +#define MPI3MR_BSG_ADPRESET_UNKNOWN 0 +#define MPI3MR_BSG_ADPRESET_SOFT 1 +#define MPI3MR_BSG_ADPRESET_DIAG_FAULT 2 + +#define MPI3MR_BSG_LOGDATA_MAX_ENTRIES 400 +#define MPI3MR_BSG_LOGDATA_ENTRY_HEADER_SZ 4 + +#define MPI3MR_DRVBSG_OPCODE_UNKNOWN 0 +#define MPI3MR_DRVBSG_OPCODE_ADPINFO 1 +#define MPI3MR_DRVBSG_OPCODE_ADPRESET 2 +#define MPI3MR_DRVBSG_OPCODE_ALLTGTDEVINFO 4 +#define MPI3MR_DRVBSG_OPCODE_GETCHGCNT 5 +#define MPI3MR_DRVBSG_OPCODE_LOGDATAENABLE 6 +#define MPI3MR_DRVBSG_OPCODE_PELENABLE 7 +#define MPI3MR_DRVBSG_OPCODE_GETLOGDATA 8 +#define MPI3MR_DRVBSG_OPCODE_QUERY_HDB 9 +#define MPI3MR_DRVBSG_OPCODE_REPOST_HDB 10 +#define MPI3MR_DRVBSG_OPCODE_UPLOAD_HDB 11 +#define MPI3MR_DRVBSG_OPCODE_REFRESH_HDB_TRIGGERS 12 + + +#define MPI3MR_BSG_BUFTYPE_UNKNOWN 0 +#define MPI3MR_BSG_BUFTYPE_RAIDMGMT_CMD 1 +#define MPI3MR_BSG_BUFTYPE_RAIDMGMT_RESP 2 +#define MPI3MR_BSG_BUFTYPE_DATA_IN 3 +#define MPI3MR_BSG_BUFTYPE_DATA_OUT 4 +#define MPI3MR_BSG_BUFTYPE_MPI_REPLY 5 +#define MPI3MR_BSG_BUFTYPE_ERR_RESPONSE 6 +#define MPI3MR_BSG_BUFTYPE_MPI_REQUEST 0xFE + +#define MPI3MR_BSG_MPI_REPLY_BUFTYPE_UNKNOWN 0 +#define MPI3MR_BSG_MPI_REPLY_BUFTYPE_STATUS 1 +#define MPI3MR_BSG_MPI_REPLY_BUFTYPE_ADDRESS 2 + +#define MPI3MR_HDB_BUFTYPE_UNKNOWN 0 +#define MPI3MR_HDB_BUFTYPE_TRACE 1 +#define MPI3MR_HDB_BUFTYPE_FIRMWARE 2 +#define MPI3MR_HDB_BUFTYPE_RESERVED 3 + +#define MPI3MR_HDB_BUFSTATUS_UNKNOWN 0 +#define MPI3MR_HDB_BUFSTATUS_NOT_ALLOCATED 1 +#define MPI3MR_HDB_BUFSTATUS_POSTED_UNPAUSED 2 +#define MPI3MR_HDB_BUFSTATUS_POSTED_PAUSED 3 +#define MPI3MR_HDB_BUFSTATUS_RELEASED 4 + +#define MPI3MR_HDB_TRIGGER_TYPE_UNKNOWN 0 +#define MPI3MR_HDB_TRIGGER_TYPE_DIAGFAULT 1 +#define MPI3MR_HDB_TRIGGER_TYPE_ELEMENT 2 +#define MPI3MR_HDB_TRIGGER_TYPE_MASTER 3 + + +/* Supported BSG commands */ +enum command { + MPI3MR_DRV_CMD = 1, + MPI3MR_MPT_CMD = 2, +}; + +/** + * struct mpi3_driver_info_layout - Information about driver + * + * @information_length: Length of this structure in bytes + * @driver_signature: Driver Vendor name + * @os_name: Operating System Name + * @driver_name: Driver name + * @driver_version: Driver version + * @driver_release_date: Driver release date + * @driver_capabilities: Driver capabilities + */ +struct mpi3_driver_info_layout { + __le32 information_length; + __u8 driver_signature[12]; + __u8 os_name[16]; + __u8 os_version[12]; + __u8 driver_name[20]; + __u8 driver_version[32]; + __u8 driver_release_date[20]; + __le32 driver_capabilities; +}; + +/** + * struct mpi3mr_bsg_in_adpinfo - Adapter information request + * data returned by the driver. + * + * @adp_type: Adapter type + * @rsvd1: Reserved + * @pci_dev_id: PCI device ID of the adapter + * @pci_dev_hw_rev: PCI revision of the adapter + * @pci_subsys_dev_id: PCI subsystem device ID of the adapter + * @pci_subsys_ven_id: PCI subsystem vendor ID of the adapter + * @pci_dev: PCI device + * @pci_func: PCI function + * @pci_bus: PCI bus + * @rsvd2: Reserved + * @pci_seg_id: PCI segment ID + * @app_intfc_ver: version of the application interface definition + * @rsvd3: Reserved + * @rsvd4: Reserved + * @rsvd5: Reserved + * @driver_info: Driver Information (Version/Name) + */ +struct mpi3mr_bsg_in_adpinfo { + __u32 adp_type; + __u32 rsvd1; + __u32 pci_dev_id; + __u32 pci_dev_hw_rev; + __u32 pci_subsys_dev_id; + __u32 pci_subsys_ven_id; + __u32 pci_dev:5; + __u32 pci_func:3; + __u32 pci_bus:8; + __u16 rsvd2; + __u32 pci_seg_id; + __u32 app_intfc_ver; + __u8 adp_state; + __u8 rsvd3; + __u16 rsvd4; + __u32 rsvd5[2]; + struct mpi3_driver_info_layout driver_info; +}; + +/** + * struct mpi3mr_bsg_adp_reset - Adapter reset request + * payload data to the driver. + * + * @reset_type: Reset type + * @rsvd1: Reserved + * @rsvd2: Reserved + */ +struct mpi3mr_bsg_adp_reset { + __u8 reset_type; + __u8 rsvd1; + __u16 rsvd2; +}; + +/** + * struct mpi3mr_change_count - Topology change count + * returned by the driver. + * + * @change_count: Topology change count + * @rsvd: Reserved + */ +struct mpi3mr_change_count { + __u16 change_count; + __u16 rsvd; +}; + +/** + * struct mpi3mr_device_map_info - Target device mapping + * information + * + * @handle: Firmware device handle + * @perst_id: Persistent ID assigned by the firmware + * @target_id: Target ID assigned by the driver + * @bus_id: Bus ID assigned by the driver + * @rsvd1: Reserved + * @rsvd2: Reserved + */ +struct mpi3mr_device_map_info { + __u16 handle; + __u16 perst_id; + __u32 target_id; + __u8 bus_id; + __u8 rsvd1; + __u16 rsvd2; +}; + +/** + * struct mpi3mr_all_tgt_info - Target device mapping + * information returned by the driver + * + * @num_devices: The number of devices in driver's inventory + * @rsvd1: Reserved + * @rsvd2: Reserved + * @dmi: Variable length array of mapping information of targets + */ +struct mpi3mr_all_tgt_info { + __u16 num_devices; + __u16 rsvd1; + __u32 rsvd2; + struct mpi3mr_device_map_info dmi[1]; +}; + +/** + * struct mpi3mr_logdata_enable - Number of log data + * entries saved by the driver returned as payload data for + * enable logdata BSG request by the driver. + * + * @max_entries: Number of log data entries cached by the driver + * @rsvd: Reserved + */ +struct mpi3mr_logdata_enable { + __u16 max_entries; + __u16 rsvd; +}; + +/** + * struct mpi3mr_bsg_out_pel_enable - PEL enable request payload + * data to the driver. + * + * @pel_locale: PEL locale to the firmware + * @pel_class: PEL class to the firmware + * @rsvd: Reserved + */ +struct mpi3mr_bsg_out_pel_enable { + __u16 pel_locale; + __u8 pel_class; + __u8 rsvd; +}; + +/** + * struct mpi3mr_logdata_entry - Log data entry cached by the + * driver. + * + * @valid_entry: Is the entry valid + * @rsvd1: Reserved + * @rsvd2: Reserved + * @data: Variable length Log entry data + */ +struct mpi3mr_logdata_entry { + __u8 valid_entry; + __u8 rsvd1; + __u16 rsvd2; + __u8 data[1]; /* Variable length Array */ +}; + +/** + * struct mpi3mr_bsg_in_log_data - Log data entries saved by + * the driver returned as payload data for Get logdata request + * by the driver. + * + * @entry: Variable length Log data entry array + */ +struct mpi3mr_bsg_in_log_data { + struct mpi3mr_logdata_entry entry[1]; +}; + +/** + * struct mpi3mr_hdb_entry - host diag buffer entry. + * + * @buf_type: Buffer type + * @status: Buffer status + * @trigger_type: Trigger type + * @rsvd1: Reserved + * @size: Buffer size + * @rsvd2: Reserved + * @trigger_data: Trigger specific data + * @rsvd3: Reserved + * @rsvd4: Reserved + */ +struct mpi3mr_hdb_entry { + __u8 buf_type; + __u8 status; + __u8 trigger_type; + __u8 rsvd1; + __u16 size; + __u16 rsvd2; + __u64 trigger_data; + __u32 rsvd3; + __u32 rsvd4; +}; + + +/** + * struct mpi3mr_bsg_in_hdb_status - This structure contains + * return data for the BSG request to retrieve the number of host + * diagnostic buffers supported by the driver and their current + * status and additional status specific data if any in forms of + * multiple hdb entries. + * + * @num_hdb_types: Number of host diag buffer types supported + * @rsvd1: Reserved + * @rsvd2: Reserved + * @rsvd3: Reserved + * @entry: Variable length Diag buffer status entry array + */ +struct mpi3mr_bsg_in_hdb_status { + __u8 num_hdb_types; + __u8 rsvd1; + __u16 rsvd2; + __u32 rsvd3; + struct mpi3mr_hdb_entry entry[1]; +}; + +/** + * struct mpi3mr_bsg_out_repost_hdb - Repost host diagnostic + * buffer request payload data to the driver. + * + * @buf_type: Buffer type + * @rsvd1: Reserved + * @rsvd2: Reserved + */ +struct mpi3mr_bsg_out_repost_hdb { + __u8 buf_type; + __u8 rsvd1; + __u16 rsvd2; +}; + +/** + * struct mpi3mr_bsg_out_upload_hdb - Upload host diagnostic + * buffer request payload data to the driver. + * + * @buf_type: Buffer type + * @rsvd1: Reserved + * @rsvd2: Reserved + * @start_offset: Start offset of the buffer from where to copy + * @length: Length of the buffer to copy + */ +struct mpi3mr_bsg_out_upload_hdb { + __u8 buf_type; + __u8 rsvd1; + __u16 rsvd2; + __u32 start_offset; + __u32 length; +}; + +/** + * struct mpi3mr_bsg_out_refresh_hdb_triggers - Refresh host + * diagnostic buffer triggers request payload data to the driver. + * + * @page_type: Page type + * @rsvd1: Reserved + * @rsvd2: Reserved + */ +struct mpi3mr_bsg_out_refresh_hdb_triggers { + __u8 page_type; + __u8 rsvd1; + __u16 rsvd2; +}; +/** + * struct mpi3mr_bsg_drv_cmd - Generic bsg data + * structure for all driver specific requests. + * + * @mrioc_id: Controller ID + * @opcode: Driver specific opcode + * @rsvd1: Reserved + * @rsvd2: Reserved + */ +struct mpi3mr_bsg_drv_cmd { + __u8 mrioc_id; + __u8 opcode; + __u16 rsvd1; + __u32 rsvd2[4]; +}; +/** + * struct mpi3mr_bsg_in_reply_buf - MPI reply buffer returned + * for MPI Passthrough request . + * + * @mpi_reply_type: Type of MPI reply + * @rsvd1: Reserved + * @rsvd2: Reserved + * @reply_buf: Variable Length buffer based on mpirep type + */ +struct mpi3mr_bsg_in_reply_buf { + __u8 mpi_reply_type; + __u8 rsvd1; + __u16 rsvd2; + __u8 reply_buf[1]; +}; + +/** + * struct mpi3mr_buf_entry - User buffer descriptor for MPI + * Passthrough requests. + * + * @buf_type: Buffer type + * @rsvd1: Reserved + * @rsvd2: Reserved + * @buf_len: Buffer length + */ +struct mpi3mr_buf_entry { + __u8 buf_type; + __u8 rsvd1; + __u16 rsvd2; + __u32 buf_len; +}; +/** + * struct mpi3mr_bsg_buf_entry_list - list of user buffer + * descriptor for MPI Passthrough requests. + * + * @num_of_entries: Number of buffer descriptors + * @rsvd1: Reserved + * @rsvd2: Reserved + * @rsvd3: Reserved + * @buf_entry: Variable length array of buffer descriptors + */ +struct mpi3mr_buf_entry_list { + __u8 num_of_entries; + __u8 rsvd1; + __u16 rsvd2; + __u32 rsvd3; + struct mpi3mr_buf_entry buf_entry[1]; +}; +/** + * struct mpi3mr_bsg_mptcmd - Generic bsg data + * structure for all MPI Passthrough requests . + * + * @mrioc_id: Controller ID + * @rsvd1: Reserved + * @timeout: MPI request timeout + * @buf_entry_list: Buffer descriptor list + */ +struct mpi3mr_bsg_mptcmd { + __u8 mrioc_id; + __u8 rsvd1; + __u16 timeout; + __u32 rsvd2; + struct mpi3mr_buf_entry_list buf_entry_list; +}; + +/** + * struct mpi3mr_bsg_packet - Generic bsg data + * structure for all supported requests . + * + * @cmd_type: represents drvrcmd or mptcmd + * @rsvd1: Reserved + * @rsvd2: Reserved + * @drvrcmd: driver request structure + * @mptcmd: mpt request structure + */ +struct mpi3mr_bsg_packet { + __u8 cmd_type; + __u8 rsvd1; + __u16 rsvd2; + __u32 rsvd3; + union { + struct mpi3mr_bsg_drv_cmd drvrcmd; + struct mpi3mr_bsg_mptcmd mptcmd; + } cmd; +}; +#endif -- cgit v1.2.3 From f3de4706c1e0c3b9fa39ec24a30c1996a33bc9e4 Mon Sep 17 00:00:00 2001 From: Sumit Saxena Date: Fri, 29 Apr 2022 17:16:36 -0400 Subject: scsi: mpi3mr: Move data structures/definitions from MPI headers to uapi header This patch moves the data structures/definitions which are used by userspace applications from MPI headers to uapi/scsi/scsi_bsg_mpi3mr.h Link: https://lore.kernel.org/r/20220429211641.642010-4-sumit.saxena@broadcom.com Reported by: Stephen Rothwell Reviewed-by: Himanshu Madhani Signed-off-by: Sumit Saxena Signed-off-by: Martin K. Petersen --- include/uapi/scsi/scsi_bsg_mpi3mr.h | 117 ++++++++++++++++++++++++++++++++++++ 1 file changed, 117 insertions(+) (limited to 'include') diff --git a/include/uapi/scsi/scsi_bsg_mpi3mr.h b/include/uapi/scsi/scsi_bsg_mpi3mr.h index 66697d963f64..b2c88d5d9c4c 100644 --- a/include/uapi/scsi/scsi_bsg_mpi3mr.h +++ b/include/uapi/scsi/scsi_bsg_mpi3mr.h @@ -454,4 +454,121 @@ struct mpi3mr_bsg_packet { struct mpi3mr_bsg_mptcmd mptcmd; } cmd; }; + + +/* MPI3: NVMe Encasulation related definitions */ +#ifndef MPI3_NVME_ENCAP_CMD_MAX +#define MPI3_NVME_ENCAP_CMD_MAX (1) +#endif + +struct mpi3_nvme_encapsulated_request { + __le16 host_tag; + __u8 ioc_use_only02; + __u8 function; + __le16 ioc_use_only04; + __u8 ioc_use_only06; + __u8 msg_flags; + __le16 change_count; + __le16 dev_handle; + __le16 encapsulated_command_length; + __le16 flags; + __le32 data_length; + __le32 reserved14[3]; + __le32 command[MPI3_NVME_ENCAP_CMD_MAX]; +}; + +struct mpi3_nvme_encapsulated_error_reply { + __le16 host_tag; + __u8 ioc_use_only02; + __u8 function; + __le16 ioc_use_only04; + __u8 ioc_use_only06; + __u8 msg_flags; + __le16 ioc_use_only08; + __le16 ioc_status; + __le32 ioc_log_info; + __le32 nvme_completion_entry[4]; +}; + +/* MPI3: task management related definitions */ +struct mpi3_scsi_task_mgmt_request { + __le16 host_tag; + __u8 ioc_use_only02; + __u8 function; + __le16 ioc_use_only04; + __u8 ioc_use_only06; + __u8 msg_flags; + __le16 change_count; + __le16 dev_handle; + __le16 task_host_tag; + __u8 task_type; + __u8 reserved0f; + __le16 task_request_queue_id; + __le16 reserved12; + __le32 reserved14; + __u8 lun[8]; +}; + +#define MPI3_SCSITASKMGMT_MSGFLAGS_DO_NOT_SEND_TASK_IU (0x08) +#define MPI3_SCSITASKMGMT_TASKTYPE_ABORT_TASK (0x01) +#define MPI3_SCSITASKMGMT_TASKTYPE_ABORT_TASK_SET (0x02) +#define MPI3_SCSITASKMGMT_TASKTYPE_TARGET_RESET (0x03) +#define MPI3_SCSITASKMGMT_TASKTYPE_LOGICAL_UNIT_RESET (0x05) +#define MPI3_SCSITASKMGMT_TASKTYPE_CLEAR_TASK_SET (0x06) +#define MPI3_SCSITASKMGMT_TASKTYPE_QUERY_TASK (0x07) +#define MPI3_SCSITASKMGMT_TASKTYPE_CLEAR_ACA (0x08) +#define MPI3_SCSITASKMGMT_TASKTYPE_QUERY_TASK_SET (0x09) +#define MPI3_SCSITASKMGMT_TASKTYPE_QUERY_ASYNC_EVENT (0x0a) +#define MPI3_SCSITASKMGMT_TASKTYPE_I_T_NEXUS_RESET (0x0b) +struct mpi3_scsi_task_mgmt_reply { + __le16 host_tag; + __u8 ioc_use_only02; + __u8 function; + __le16 ioc_use_only04; + __u8 ioc_use_only06; + __u8 msg_flags; + __le16 ioc_use_only08; + __le16 ioc_status; + __le32 ioc_log_info; + __le32 termination_count; + __le32 response_data; + __le32 reserved18; +}; + +#define MPI3_SCSITASKMGMT_RSPCODE_TM_COMPLETE (0x00) +#define MPI3_SCSITASKMGMT_RSPCODE_INVALID_FRAME (0x02) +#define MPI3_SCSITASKMGMT_RSPCODE_TM_FUNCTION_NOT_SUPPORTED (0x04) +#define MPI3_SCSITASKMGMT_RSPCODE_TM_FAILED (0x05) +#define MPI3_SCSITASKMGMT_RSPCODE_TM_SUCCEEDED (0x08) +#define MPI3_SCSITASKMGMT_RSPCODE_TM_INVALID_LUN (0x09) +#define MPI3_SCSITASKMGMT_RSPCODE_TM_OVERLAPPED_TAG (0x0a) +#define MPI3_SCSITASKMGMT_RSPCODE_IO_QUEUED_ON_IOC (0x80) +#define MPI3_SCSITASKMGMT_RSPCODE_TM_NVME_DENIED (0x81) + +/* MPI3: PEL related definitions */ +#define MPI3_PEL_LOCALE_FLAGS_NON_BLOCKING_BOOT_EVENT (0x0200) +#define MPI3_PEL_LOCALE_FLAGS_BLOCKING_BOOT_EVENT (0x0100) +#define MPI3_PEL_LOCALE_FLAGS_PCIE (0x0080) +#define MPI3_PEL_LOCALE_FLAGS_CONFIGURATION (0x0040) +#define MPI3_PEL_LOCALE_FLAGS_CONTROLER (0x0020) +#define MPI3_PEL_LOCALE_FLAGS_SAS (0x0010) +#define MPI3_PEL_LOCALE_FLAGS_EPACK (0x0008) +#define MPI3_PEL_LOCALE_FLAGS_ENCLOSURE (0x0004) +#define MPI3_PEL_LOCALE_FLAGS_PD (0x0002) +#define MPI3_PEL_LOCALE_FLAGS_VD (0x0001) +#define MPI3_PEL_CLASS_DEBUG (0x00) +#define MPI3_PEL_CLASS_PROGRESS (0x01) +#define MPI3_PEL_CLASS_INFORMATIONAL (0x02) +#define MPI3_PEL_CLASS_WARNING (0x03) +#define MPI3_PEL_CLASS_CRITICAL (0x04) +#define MPI3_PEL_CLASS_FATAL (0x05) +#define MPI3_PEL_CLASS_FAULT (0x06) + +/* MPI3: Function definitions */ +#define MPI3_BSG_FUNCTION_MGMT_PASSTHROUGH (0x0a) +#define MPI3_BSG_FUNCTION_SCSI_IO (0x20) +#define MPI3_BSG_FUNCTION_SCSI_TASK_MGMT (0x21) +#define MPI3_BSG_FUNCTION_SMP_PASSTHROUGH (0x22) +#define MPI3_BSG_FUNCTION_NVME_ENCAPSULATED (0x24) + #endif -- cgit v1.2.3 From 7dbd0dd8cde356d2a747d5c87dad7c2233dad8a4 Mon Sep 17 00:00:00 2001 From: Sumit Saxena Date: Fri, 29 Apr 2022 17:16:40 -0400 Subject: scsi: mpi3mr: Add support for NVMe passthrough Add support for management applications to send an MPI3 Encapsulated NVMe passthru command to the NVMe devices attached to an Avenger controller. Since the NVMe drives are exposed as SCSI devices by the controller, the standard NVMe applications cannot be used to interact with the drives and the command sets supported are also limited by the controller firmware. Special handling is required for MPI3 Encapsulated NVMe passthru commands for PRP/SGL setup in the commands. Link: https://lore.kernel.org/r/20220429211641.642010-8-sumit.saxena@broadcom.com Reviewed-by: Himanshu Madhani Signed-off-by: Sumit Saxena Signed-off-by: Martin K. Petersen --- include/uapi/scsi/scsi_bsg_mpi3mr.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/uapi/scsi/scsi_bsg_mpi3mr.h b/include/uapi/scsi/scsi_bsg_mpi3mr.h index b2c88d5d9c4c..fdc3517f9e19 100644 --- a/include/uapi/scsi/scsi_bsg_mpi3mr.h +++ b/include/uapi/scsi/scsi_bsg_mpi3mr.h @@ -490,6 +490,14 @@ struct mpi3_nvme_encapsulated_error_reply { __le32 nvme_completion_entry[4]; }; +#define MPI3MR_NVME_PRP_SIZE 8 /* PRP size */ +#define MPI3MR_NVME_CMD_PRP1_OFFSET 24 /* PRP1 offset in NVMe cmd */ +#define MPI3MR_NVME_CMD_PRP2_OFFSET 32 /* PRP2 offset in NVMe cmd */ +#define MPI3MR_NVME_CMD_SGL_OFFSET 24 /* SGL offset in NVMe cmd */ +#define MPI3MR_NVME_DATA_FORMAT_PRP 0 +#define MPI3MR_NVME_DATA_FORMAT_SGL1 1 +#define MPI3MR_NVME_DATA_FORMAT_SGL2 2 + /* MPI3: task management related definitions */ struct mpi3_scsi_task_mgmt_request { __le16 host_tag; -- cgit v1.2.3 From 05e4ed1ce585637958c8ad6121999dc3109633ad Mon Sep 17 00:00:00 2001 From: Colin Foster Date: Sat, 30 Apr 2022 16:23:26 -0700 Subject: net: mscc: ocelot: remove unnecessary variable Commit 2f187bfa6f35 ("net: ethernet: ocelot: remove the need for num_stats initializer") added a flags field to the ocelot stats structure. The same behavior can be achieved without this additional field taking up extra memory. Remove this structure element to free up RAM Suggested-by: Vladimir Oltean Signed-off-by: Colin Foster Reviewed-by: Vladimir Oltean Tested-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 5c4f57cfa785..75739766244b 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -105,11 +105,9 @@ #define REG_RESERVED_ADDR 0xffffffff #define REG_RESERVED(reg) REG(reg, REG_RESERVED_ADDR) -#define OCELOT_STAT_FLAG_END BIT(0) - #define for_each_stat(ocelot, stat) \ for ((stat) = ocelot->stats_layout; \ - !((stat)->flags & OCELOT_STAT_FLAG_END); \ + ((stat)->name[0] != '\0'); \ (stat)++) enum ocelot_target { @@ -542,11 +540,10 @@ enum ocelot_ptp_pins { struct ocelot_stat_layout { u32 offset; - u32 flags; char name[ETH_GSTRING_LEN]; }; -#define OCELOT_STAT_END { .flags = OCELOT_STAT_FLAG_END } +#define OCELOT_STAT_END { .name = "" } struct ocelot_stats_region { struct list_head node; -- cgit v1.2.3 From 8c5b07da9bc8c056a3ddca00b4e268358f643343 Mon Sep 17 00:00:00 2001 From: Colin Foster Date: Sat, 30 Apr 2022 16:23:27 -0700 Subject: net: mscc: ocelot: add missed parentheses around macro argument Commit 2f187bfa6f35 ("net: ethernet: ocelot: remove the need for num_stats initializer") added a macro that patchwork warned it lacked parentheses around an argument. Correct this mistake. Fixes: 2f187bfa6f35 ("net: ethernet: ocelot: remove the need for num_stats initializer") Signed-off-by: Colin Foster Reviewed-by: Vladimir Oltean Tested-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 75739766244b..8d8d46778f7e 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -106,7 +106,7 @@ #define REG_RESERVED(reg) REG(reg, REG_RESERVED_ADDR) #define for_each_stat(ocelot, stat) \ - for ((stat) = ocelot->stats_layout; \ + for ((stat) = (ocelot)->stats_layout; \ ((stat)->name[0] != '\0'); \ (stat)++) -- cgit v1.2.3 From d639af621600dc52dd9ed0dcf62b22595f2f5b52 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 22 Mar 2022 09:16:39 +0000 Subject: net/mlx5: fs, split software and IFC flow destination definitions Separate flow destinations between software and IFC. Flow destination type passed by callers was used as the input in firmware commands and over the years software only types were added which resulted in mixing between the two. Create an IFC enum that contains only the flow destinations defined when talking to the firmware. Now that there is a proper software only enum for flow destinations the hardcoded values can be removed as the values are no longer used in firmware commands. Signed-off-by: Mark Bloch Reviewed-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 11 +++++++++++ include/linux/mlx5/mlx5_ifc.h | 16 ++++++---------- 2 files changed, 17 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index e3bfed68b08a..9da9df9ae751 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -40,6 +40,17 @@ #define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v) +enum mlx5_flow_destination_type { + MLX5_FLOW_DESTINATION_TYPE_VPORT, + MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE, + MLX5_FLOW_DESTINATION_TYPE_TIR, + MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER, + MLX5_FLOW_DESTINATION_TYPE_UPLINK, + MLX5_FLOW_DESTINATION_TYPE_PORT, + MLX5_FLOW_DESTINATION_TYPE_COUNTER, + MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM, +}; + enum { MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO = 1 << 16, MLX5_FLOW_CONTEXT_ACTION_ENCRYPT = 1 << 17, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 7d2d0ba82144..7f4ec9faa180 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1806,16 +1806,12 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 reserved_at_c0[0x740]; }; -enum mlx5_flow_destination_type { - MLX5_FLOW_DESTINATION_TYPE_VPORT = 0x0, - MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE = 0x1, - MLX5_FLOW_DESTINATION_TYPE_TIR = 0x2, - MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER = 0x6, - MLX5_FLOW_DESTINATION_TYPE_UPLINK = 0x8, - - MLX5_FLOW_DESTINATION_TYPE_PORT = 0x99, - MLX5_FLOW_DESTINATION_TYPE_COUNTER = 0x100, - MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM = 0x101, +enum mlx5_ifc_flow_destination_type { + MLX5_IFC_FLOW_DESTINATION_TYPE_VPORT = 0x0, + MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_TABLE = 0x1, + MLX5_IFC_FLOW_DESTINATION_TYPE_TIR = 0x2, + MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_SAMPLER = 0x6, + MLX5_IFC_FLOW_DESTINATION_TYPE_UPLINK = 0x8, }; enum mlx5_flow_table_miss_action { -- cgit v1.2.3 From 6510bc0d7cb4119ebe10f9ab43aca6fd0e5f3e73 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 15 Mar 2022 14:08:23 +0000 Subject: net/mlx5: fs, add unused destination type When the caller doesn't pass a destination fs_core will create a unused rule just so a context can be returned. This unused rule is zeroed out and its type is 0 which can be mixed up with MLX5_FLOW_DESTINATION_TYPE_VPORT. Create a dedicated type to differentiate between the two named MLX5_FLOW_DESTINATION_TYPE_NONE. Signed-off-by: Mark Bloch Reviewed-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 9da9df9ae751..8135713b0d2d 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -41,6 +41,7 @@ #define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v) enum mlx5_flow_destination_type { + MLX5_FLOW_DESTINATION_TYPE_NONE, MLX5_FLOW_DESTINATION_TYPE_VPORT, MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE, MLX5_FLOW_DESTINATION_TYPE_TIR, -- cgit v1.2.3 From c9bc1a0ef9f613a7bc1adfff4c67dc5e5d7d1709 Mon Sep 17 00:00:00 2001 From: "Dustin L. Howett" Date: Thu, 17 Feb 2022 10:59:30 -0600 Subject: platform/chrome: cros_ec_lpcs: reserve the MEC LPC I/O ports first Some ChromeOS EC devices (such as the Framework Laptop) only map I/O ports 0x800-0x807. Making the larger reservation required by the non-MEC LPC (the 0xFF ports for the memory map, and the 0xFF ports for the parameter region) is non-viable on these devices. Since we probe the MEC EC first, we can get away with a smaller reservation that covers the MEC EC ports. If we fall back to classic LPC, we can grow the reservation to cover the memory map and the parameter region. cros_ec_lpc_probe also interacted with I/O ports 0x800-0x807 without a reservation. Restructuring the code to request the MEC LPC region first obviates the need to do so. Signed-off-by: Dustin L. Howett Signed-off-by: Tzung-Bi Shih Link: https://lore.kernel.org/r/20220217165930.15081-3-dustin@howett.net --- include/linux/platform_data/cros_ec_commands.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index c23554531961..8cfa8cfca77e 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -51,10 +51,14 @@ /* * The actual block is 0x800-0x8ff, but some BIOSes think it's 0x880-0x8ff * and they tell the kernel that so we have to think of it as two parts. + * + * Other BIOSes report only the I/O port region spanned by the Microchip + * MEC series EC; an attempt to address a larger region may fail. */ -#define EC_HOST_CMD_REGION0 0x800 -#define EC_HOST_CMD_REGION1 0x880 -#define EC_HOST_CMD_REGION_SIZE 0x80 +#define EC_HOST_CMD_REGION0 0x800 +#define EC_HOST_CMD_REGION1 0x880 +#define EC_HOST_CMD_REGION_SIZE 0x80 +#define EC_HOST_CMD_MEC_REGION_SIZE 0x8 /* EC command register bit functions */ #define EC_LPC_CMDR_DATA BIT(0) /* Data ready for host to read */ -- cgit v1.2.3 From 4c7f24f857c7cd0381dd92495db476066d1c6aec Mon Sep 17 00:00:00 2001 From: Tonghao Zhang Date: Sun, 1 May 2022 11:55:23 +0800 Subject: net: sysctl: introduce sysctl SYSCTL_THREE This patch introdues the SYSCTL_THREE. KUnit: [00:10:14] ================ sysctl_test (10 subtests) ================= [00:10:14] [PASSED] sysctl_test_api_dointvec_null_tbl_data [00:10:14] [PASSED] sysctl_test_api_dointvec_table_maxlen_unset [00:10:14] [PASSED] sysctl_test_api_dointvec_table_len_is_zero [00:10:14] [PASSED] sysctl_test_api_dointvec_table_read_but_position_set [00:10:14] [PASSED] sysctl_test_dointvec_read_happy_single_positive [00:10:14] [PASSED] sysctl_test_dointvec_read_happy_single_negative [00:10:14] [PASSED] sysctl_test_dointvec_write_happy_single_positive [00:10:14] [PASSED] sysctl_test_dointvec_write_happy_single_negative [00:10:14] [PASSED] sysctl_test_api_dointvec_write_single_less_int_min [00:10:14] [PASSED] sysctl_test_api_dointvec_write_single_greater_int_max [00:10:14] =================== [PASSED] sysctl_test =================== ./run_kselftest.sh -c sysctl ... ok 1 selftests: sysctl: sysctl.sh Cc: Luis Chamberlain Cc: Kees Cook Cc: Iurii Zaikin Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Paolo Abeni Cc: Hideaki YOSHIFUJI Cc: David Ahern Cc: Simon Horman Cc: Julian Anastasov Cc: Pablo Neira Ayuso Cc: Jozsef Kadlecsik Cc: Florian Westphal Cc: Shuah Khan Cc: Andrew Morton Cc: Alexei Starovoitov Cc: Eric Dumazet Cc: Lorenz Bauer Cc: Akhmat Karakotov Signed-off-by: Tonghao Zhang Reviewed-by: Simon Horman Signed-off-by: Paolo Abeni --- include/linux/sysctl.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 6353d6db69b2..80263f7cdb77 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -38,10 +38,10 @@ struct ctl_table_header; struct ctl_dir; /* Keep the same order as in fs/proc/proc_sysctl.c */ -#define SYSCTL_NEG_ONE ((void *)&sysctl_vals[0]) -#define SYSCTL_ZERO ((void *)&sysctl_vals[1]) -#define SYSCTL_ONE ((void *)&sysctl_vals[2]) -#define SYSCTL_TWO ((void *)&sysctl_vals[3]) +#define SYSCTL_ZERO ((void *)&sysctl_vals[0]) +#define SYSCTL_ONE ((void *)&sysctl_vals[1]) +#define SYSCTL_TWO ((void *)&sysctl_vals[2]) +#define SYSCTL_THREE ((void *)&sysctl_vals[3]) #define SYSCTL_FOUR ((void *)&sysctl_vals[4]) #define SYSCTL_ONE_HUNDRED ((void *)&sysctl_vals[5]) #define SYSCTL_TWO_HUNDRED ((void *)&sysctl_vals[6]) @@ -51,6 +51,7 @@ struct ctl_dir; /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ #define SYSCTL_MAXOLDUID ((void *)&sysctl_vals[10]) +#define SYSCTL_NEG_ONE ((void *)&sysctl_vals[11]) extern const int sysctl_vals[]; -- cgit v1.2.3 From 62139f52b7e588d565aa9df81ea0a0548a68b823 Mon Sep 17 00:00:00 2001 From: Per-Daniel Olsson Date: Fri, 29 Apr 2022 09:22:08 +0200 Subject: regulator: pca9450: Make I2C Level Translator configurable Make the I2C Level Translator included in PCA9450 configurable from devicetree. The reset state is off. By setting nxp,i2c-lt-enable, the I2C Level Translator will be enabled while in STANDBY or RUN state. Signed-off-by: Per-Daniel Olsson Signed-off-by: Rickard x Andersson Link: https://lore.kernel.org/r/20220429072211.24957-2-rickaran@axis.com Signed-off-by: Mark Brown --- include/linux/regulator/pca9450.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/regulator/pca9450.h b/include/linux/regulator/pca9450.h index 71902f41c919..3c01c2bf84f5 100644 --- a/include/linux/regulator/pca9450.h +++ b/include/linux/regulator/pca9450.h @@ -226,4 +226,11 @@ enum { #define WDOG_B_CFG_COLD_LDO12 0x80 #define WDOG_B_CFG_COLD 0xC0 +/* PCA9450_REG_CONFIG2 bits */ +#define I2C_LT_MASK 0x03 +#define I2C_LT_FORCE_DISABLE 0x00 +#define I2C_LT_ON_STANDBY_RUN 0x01 +#define I2C_LT_ON_RUN 0x02 +#define I2C_LT_FORCE_ENABLE 0x03 + #endif /* __LINUX_REG_PCA9450_H__ */ -- cgit v1.2.3 From 1dcbae86ee669bdb0338954cd0136863f5c96c0a Mon Sep 17 00:00:00 2001 From: Dave Gerlach Date: Thu, 14 Apr 2022 12:27:24 -0700 Subject: soc: ti: wkup_m3_ipc: Add support for IO Isolation AM43xx support isolation of the IOs so that control is taken from the peripheral they are connected to and overridden by values present in the CTRL_CONF_* registers for the pad in the control module. The actual toggling happens from the wkup_m3, so use a DT property from the wkup_m3_ipc node to allow the PM code to communicate the necessity for placing the IOs into isolation to the firmware. Signed-off-by: Dave Gerlach Signed-off-by: Keerthy Signed-off-by: Drew Fustini Signed-off-by: Nishanth Menon Link: https://lore.kernel.org/r/20220414192722.2978837-3-dfustini@baylibre.com --- include/linux/wkup_m3_ipc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/wkup_m3_ipc.h b/include/linux/wkup_m3_ipc.h index 2bc52c6381d5..b706eac58f92 100644 --- a/include/linux/wkup_m3_ipc.h +++ b/include/linux/wkup_m3_ipc.h @@ -34,6 +34,7 @@ struct wkup_m3_ipc { int mem_type; unsigned long resume_addr; int vtt_conf; + int isolation_conf; int state; struct completion sync_complete; -- cgit v1.2.3 From ea082040fe071d2ba1f8f73792743d7ca9fb218e Mon Sep 17 00:00:00 2001 From: Dave Gerlach Date: Tue, 26 Apr 2022 13:07:44 -0700 Subject: soc: ti: wkup_m3_ipc: Add support for i2c voltage scaling Allow loading of a binary containing i2c scaling sequences to be provided to the wkup_m3 firmware in order to properly scale voltage rails on the PMIC during low power modes like DeepSleep0. Proper binary format is determined by the FW in use. Code expects firmware to have 0x0C57 present as the first two bytes followed by one byte defining offset to sleep sequence followed by one byte defining offset to wake sequence and then lastly both sequences. Each sequence is a series of I2C transfers in the form: u8 length | u8 chip address | u8 byte0/reg address | u8 byte1 | u8 byteN .. The length indicates the number of bytes to transfer, including the register address. The length of each transfer is limited by the I2C buffer size of 32 bytes. Based on previous work by Russ Dill. [dfustini: replace FW_ACTION_HOTPLUG with FW_ACTION_UEVENT] Signed-off-by: Dave Gerlach Signed-off-by: Keerthy [dfustini: add NULL argument to rproc_da_to_va() call] Signed-off-by: Drew Fustini Signed-off-by: Nishanth Menon Link: https://lore.kernel.org/r/20220426200741.712842-3-dfustini@baylibre.com --- include/linux/wkup_m3_ipc.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/wkup_m3_ipc.h b/include/linux/wkup_m3_ipc.h index b706eac58f92..fef0fac60f8c 100644 --- a/include/linux/wkup_m3_ipc.h +++ b/include/linux/wkup_m3_ipc.h @@ -37,6 +37,9 @@ struct wkup_m3_ipc { int isolation_conf; int state; + unsigned long volt_scale_offsets; + const char *sd_fw_name; + struct completion sync_complete; struct mbox_client mbox_client; struct mbox_chan *mbox; @@ -50,6 +53,12 @@ struct wkup_m3_wakeup_src { char src[10]; }; +struct wkup_m3_scale_data_header { + u16 magic; + u8 sleep_offset; + u8 wake_offset; +} __packed; + struct wkup_m3_ipc_ops { void (*set_mem_type)(struct wkup_m3_ipc *m3_ipc, int mem_type); void (*set_resume_address)(struct wkup_m3_ipc *m3_ipc, void *addr); -- cgit v1.2.3 From 2a21f9e6d9a408dbd09a01caf5fff42c2f70fa82 Mon Sep 17 00:00:00 2001 From: Dave Gerlach Date: Sun, 1 May 2022 20:32:12 -0700 Subject: soc: ti: wkup_m3_ipc: Add debug option to halt m3 in suspend Add a debugfs option to allow configurable halting of the wkup_m3 during suspend at the last possible point before low power mode entry. This condition can only be resolved through JTAG and advancing beyond the while loop in a8_lp_ds0_handler [1]. Although this hangs the system it forces the system to remain active once it has been entirely configured for low power mode entry, allowing for register inspection through JTAG to help in debugging transition errors. Halt mode can be set using the enable_off_mode entry under wkup_m3_ipc in the debugfs. [1] https://git.ti.com/cgit/processor-firmware/ti-amx3-cm3-pm-firmware/tree/src/pm_services/pm_handlers.c?h=08.02.00.006#n141 Suggested-by: Brad Griffis Signed-off-by: Dave Gerlach [dfustini: add link for a8_lp_ds0_handler() in ti-amx3-cm3-pm-firmware] Signed-off-by: Drew Fustini Signed-off-by: Nishanth Menon Link: https://lore.kernel.org/r/20220502033211.1383158-1-dfustini@baylibre.com --- include/linux/wkup_m3_ipc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/wkup_m3_ipc.h b/include/linux/wkup_m3_ipc.h index fef0fac60f8c..26d1eb058fa3 100644 --- a/include/linux/wkup_m3_ipc.h +++ b/include/linux/wkup_m3_ipc.h @@ -36,6 +36,7 @@ struct wkup_m3_ipc { int vtt_conf; int isolation_conf; int state; + u32 halt; unsigned long volt_scale_offsets; const char *sd_fw_name; @@ -46,6 +47,7 @@ struct wkup_m3_ipc { struct wkup_m3_ipc_ops *ops; int is_rtc_only; + struct dentry *dbg_path; }; struct wkup_m3_wakeup_src { -- cgit v1.2.3 From 3ba75c1316390b2bc39c19cb8f0f85922ab3f9ed Mon Sep 17 00:00:00 2001 From: Baskov Evgeniy Date: Thu, 3 Mar 2022 17:21:19 +0300 Subject: efi: libstub: declare DXE services table UEFI DXE services are not yet used in kernel code but are required to manipulate page table memory protection flags. Add required declarations to use DXE services functions. Signed-off-by: Baskov Evgeniy Link: https://lore.kernel.org/r/20220303142120.1975-2-baskov@ispras.ru [ardb: ignore absent DXE table but warn if the signature check fails] Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index fd266198f9d8..b1f7c6a3e5bf 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -385,6 +385,7 @@ void efi_native_runtime_setup(void); #define EFI_LOAD_FILE_PROTOCOL_GUID EFI_GUID(0x56ec3091, 0x954c, 0x11d2, 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) #define EFI_LOAD_FILE2_PROTOCOL_GUID EFI_GUID(0x4006c0c1, 0xfcb3, 0x403e, 0x99, 0x6d, 0x4a, 0x6c, 0x87, 0x24, 0xe0, 0x6d) #define EFI_RT_PROPERTIES_TABLE_GUID EFI_GUID(0xeb66918a, 0x7eef, 0x402a, 0x84, 0x2e, 0x93, 0x1d, 0x21, 0xc3, 0x8a, 0xe9) +#define EFI_DXE_SERVICES_TABLE_GUID EFI_GUID(0x05ad34ba, 0x6f02, 0x4214, 0x95, 0x2e, 0x4d, 0xa0, 0x39, 0x8e, 0x2b, 0xb9) #define EFI_IMAGE_SECURITY_DATABASE_GUID EFI_GUID(0xd719b2cb, 0x3d3a, 0x4596, 0xa3, 0xbc, 0xda, 0xd0, 0x0e, 0x67, 0x65, 0x6f) #define EFI_SHIM_LOCK_GUID EFI_GUID(0x605dab50, 0xe046, 0x4300, 0xab, 0xb6, 0x3d, 0xd8, 0x10, 0xdd, 0x8b, 0x23) @@ -438,6 +439,7 @@ typedef struct { } efi_config_table_type_t; #define EFI_SYSTEM_TABLE_SIGNATURE ((u64)0x5453595320494249ULL) +#define EFI_DXE_SERVICES_TABLE_SIGNATURE ((u64)0x565245535f455844ULL) #define EFI_2_30_SYSTEM_TABLE_REVISION ((2 << 16) | (30)) #define EFI_2_20_SYSTEM_TABLE_REVISION ((2 << 16) | (20)) -- cgit v1.2.3 From 07768c55f9c2ad64ccae3ed82447a87d8af8a687 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Sat, 19 Mar 2022 19:00:20 +0100 Subject: efi/arm64: libstub: run image in place if randomized by the loader If the loader has already placed the EFI kernel image randomly in physical memory, and indicates having done so by installing the 'fixed placement' protocol onto the image handle, don't bother randomizing the placement again in the EFI stub. Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index b1f7c6a3e5bf..580ce607d6f5 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -410,6 +410,17 @@ void efi_native_runtime_setup(void); #define LINUX_EFI_MOK_VARIABLE_TABLE_GUID EFI_GUID(0xc451ed2b, 0x9694, 0x45d3, 0xba, 0xba, 0xed, 0x9f, 0x89, 0x88, 0xa3, 0x89) #define LINUX_EFI_COCO_SECRET_AREA_GUID EFI_GUID(0xadf956ad, 0xe98c, 0x484c, 0xae, 0x11, 0xb5, 0x1c, 0x7d, 0x33, 0x64, 0x47) +/* + * This GUID may be installed onto the kernel image's handle as a NULL protocol + * to signal to the stub that the placement of the image should be respected, + * and moving the image in physical memory is undesirable. To ensure + * compatibility with 64k pages kernels with virtually mapped stacks, and to + * avoid defeating physical randomization, this protocol should only be + * installed if the image was placed at a randomized 128k aligned address in + * memory. + */ +#define LINUX_EFI_LOADED_IMAGE_FIXED_GUID EFI_GUID(0xf5a37b6d, 0x3344, 0x42a5, 0xb6, 0xbb, 0x97, 0x86, 0x48, 0xc1, 0x89, 0x0a) + /* OEM GUIDs */ #define DELLEMC_EFI_RCI2_TABLE_GUID EFI_GUID(0x2d9f28a2, 0xa886, 0x456a, 0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55) #define AMD_SEV_MEM_ENCRYPT_GUID EFI_GUID(0x0cf29b71, 0x9e51, 0x433a, 0xa3, 0xb7, 0x81, 0xf3, 0xab, 0x16, 0xb8, 0x75) -- cgit v1.2.3 From 85fbe08e4da862dc64fc10071c4a03e51b6361d0 Mon Sep 17 00:00:00 2001 From: Raghavendra Rao Ananta Date: Mon, 2 May 2022 23:38:45 +0000 Subject: KVM: arm64: Factor out firmware register handling from psci.c Common hypercall firmware register handing is currently employed by psci.c. Since the upcoming patches add more of these registers, it's better to move the generic handling to hypercall.c for a cleaner presentation. While we are at it, collect all the firmware registers under fw_reg_ids[] to help implement kvm_arm_get_fw_num_regs() and kvm_arm_copy_fw_reg_indices() in a generic way. Also, define KVM_REG_FEATURE_LEVEL_MASK using a GENMASK instead. No functional change intended. Signed-off-by: Raghavendra Rao Ananta Reviewed-by: Oliver Upton Reviewed-by: Gavin Shan [maz: fixed KVM_REG_FEATURE_LEVEL_MASK] Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220502233853.1233742-2-rananta@google.com --- include/kvm/arm_hypercalls.h | 7 +++++++ include/kvm/arm_psci.h | 7 ------- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/kvm/arm_hypercalls.h b/include/kvm/arm_hypercalls.h index 0e2509d27910..5d38628a8d04 100644 --- a/include/kvm/arm_hypercalls.h +++ b/include/kvm/arm_hypercalls.h @@ -40,4 +40,11 @@ static inline void smccc_set_retval(struct kvm_vcpu *vcpu, vcpu_set_reg(vcpu, 3, a3); } +struct kvm_one_reg; + +int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu); +int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); +int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); +int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); + #endif diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h index 68b96c3826c3..6e55b9283789 100644 --- a/include/kvm/arm_psci.h +++ b/include/kvm/arm_psci.h @@ -39,11 +39,4 @@ static inline int kvm_psci_version(struct kvm_vcpu *vcpu) int kvm_psci_call(struct kvm_vcpu *vcpu); -struct kvm_one_reg; - -int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu); -int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); -int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); -int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); - #endif /* __KVM_ARM_PSCI_H__ */ -- cgit v1.2.3 From 56c134f7f1b58be08bdb0ca8372474a4a5165f31 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 29 Apr 2022 12:08:31 +0200 Subject: fbdev: Track deferred-I/O pages in pageref struct Store the per-page state for fbdev's deferred I/O in struct fb_deferred_io_pageref. Maintain a list of pagerefs for the pages that have to be written back to video memory. Update all affected drivers. As with pages before, fbdev acquires a pageref when an mmaped page of the framebuffer is being written to. It holds the pageref in a list of all currently written pagerefs until it flushes the written pages to video memory. Writeback occurs periodically. After writeback fbdev releases all pagerefs and builds up a new dirty list until the next writeback occurs. Using pagerefs has a number of benefits. For pages of the framebuffer, the deferred I/O code used struct page.lru as an entry into the list of dirty pages. The lru field is owned by the page cache, which makes deferred I/O incompatible with some memory pages (e.g., most notably DRM's GEM SHMEM allocator). struct fb_deferred_io_pageref now provides an entry into a list of dirty framebuffer pages, freeing lru for use with the page cache. Drivers also assumed that struct page.index is the page offset into the framebuffer. This is not true for DRM buffers, which are located at various offset within a mapped area. struct fb_deferred_io_pageref explicitly stores an offset into the framebuffer. struct page.index is now only the page offset into the mapped area. These changes will allow DRM to use fbdev deferred I/O without an intermediate shadow buffer. v3: * use pageref->offset for sorting * fix grammar in comment v2: * minor fixes in commit message Signed-off-by: Thomas Zimmermann Reviewed-by: Javier Martinez Canillas Link: https://patchwork.freedesktop.org/patch/msgid/20220429100834.18898-3-tzimmermann@suse.de --- include/linux/fb.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fb.h b/include/linux/fb.h index f95da1af9ff6..a332590c0fae 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -201,6 +201,13 @@ struct fb_pixmap { }; #ifdef CONFIG_FB_DEFERRED_IO +struct fb_deferred_io_pageref { + struct page *page; + unsigned long offset; + /* private */ + struct list_head list; +}; + struct fb_deferred_io { /* delay between mkwrite and deferred handler */ unsigned long delay; @@ -468,6 +475,8 @@ struct fb_info { #endif #ifdef CONFIG_FB_DEFERRED_IO struct delayed_work deferred_work; + unsigned long npagerefs; + struct fb_deferred_io_pageref *pagerefs; struct fb_deferred_io *fbdefio; #endif @@ -661,7 +670,7 @@ static inline void __fb_pad_aligned_buffer(u8 *dst, u32 d_pitch, /* drivers/video/fb_defio.c */ int fb_deferred_io_mmap(struct fb_info *info, struct vm_area_struct *vma); -extern void fb_deferred_io_init(struct fb_info *info); +extern int fb_deferred_io_init(struct fb_info *info); extern void fb_deferred_io_open(struct fb_info *info, struct inode *inode, struct file *file); -- cgit v1.2.3 From e80eec1b871a2acb8f5c92db4c237e9ae6dd322b Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 29 Apr 2022 12:08:33 +0200 Subject: fbdev: Rename pagelist to pagereflist for deferred I/O Rename various instances of pagelist to pagereflist. The list now stores pageref structures, so the new name is more appropriate. In their write-back helpers, several fbdev drivers refer to the pageref list in struct fb_deferred_io instead of using the one supplied as argument to the function. Convert them over to the supplied one. It's the same instance, so no change of behavior occurs. v4: * fix commit message (Javier) Suggested-by: Sam Ravnborg Signed-off-by: Thomas Zimmermann Reviewed-by: Javier Martinez Canillas Link: https://patchwork.freedesktop.org/patch/msgid/20220429100834.18898-5-tzimmermann@suse.de --- include/drm/drm_fb_helper.h | 3 +-- include/linux/fb.h | 6 +++--- 2 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h index 3af4624368d8..329607ca65c0 100644 --- a/include/drm/drm_fb_helper.h +++ b/include/drm/drm_fb_helper.h @@ -229,8 +229,7 @@ void drm_fb_helper_fill_info(struct fb_info *info, struct drm_fb_helper *fb_helper, struct drm_fb_helper_surface_size *sizes); -void drm_fb_helper_deferred_io(struct fb_info *info, - struct list_head *pagelist); +void drm_fb_helper_deferred_io(struct fb_info *info, struct list_head *pagereflist); ssize_t drm_fb_helper_sys_read(struct fb_info *info, char __user *buf, size_t count, loff_t *ppos); diff --git a/include/linux/fb.h b/include/linux/fb.h index a332590c0fae..69c67c70fa78 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -211,9 +211,9 @@ struct fb_deferred_io_pageref { struct fb_deferred_io { /* delay between mkwrite and deferred handler */ unsigned long delay; - bool sort_pagelist; /* sort pagelist by offset */ - struct mutex lock; /* mutex that protects the page list */ - struct list_head pagelist; /* list of touched pages */ + bool sort_pagereflist; /* sort pagelist by offset */ + struct mutex lock; /* mutex that protects the pageref list */ + struct list_head pagereflist; /* list of pagerefs for touched pages */ /* callback */ void (*first_io)(struct fb_info *info); void (*deferred_io)(struct fb_info *info, struct list_head *pagelist); -- cgit v1.2.3 From f2b6e79c7378542e03e42fd47c0c8bf00a2fcf6b Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 3 May 2022 16:44:02 +0200 Subject: Revert "usb: core: hcd: Create platform devices for onboard hubs in probe()" This reverts commit c40b62216c1aecc0dc00faf33d71bd71cb440337. The series still has built errors as reported in linux-next, so revert it for now. Reported-by: Stephen Rothwell Link: https://lore.kernel.org/r/20220502210728.0b36f3cd@canb.auug.org.au Cc: Stephen Boyd Cc: Douglas Anderson Cc: Matthias Kaehlcke Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 4ebc91c09182..548a028f2dab 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -198,7 +198,6 @@ struct usb_hcd { struct usb_hcd *shared_hcd; struct usb_hcd *primary_hcd; - struct list_head onboard_hub_devs; #define HCD_BUFFER_POOLS 4 struct dma_pool *pool[HCD_BUFFER_POOLS]; -- cgit v1.2.3 From 67a7570ad31f2a7f02550153e774bf4c630f0fef Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 3 May 2022 16:44:11 +0200 Subject: Revert "usb: misc: Add onboard_usb_hub driver" This reverts commit 0298b4b95cb373c21e6323c905589f8dac42c5b4. The series still has built errors as reported in linux-next, so revert it for now. Reported-by: Stephen Rothwell Link: https://lore.kernel.org/r/20220502210728.0b36f3cd@canb.auug.org.au Cc: Alan Stern Cc: Douglas Anderson Cc: Matthias Kaehlcke Cc: Ravi Chandra Sadineni Cc: Stephen Boyd Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/onboard_hub.h | 18 ------------------ 1 file changed, 18 deletions(-) delete mode 100644 include/linux/usb/onboard_hub.h (limited to 'include') diff --git a/include/linux/usb/onboard_hub.h b/include/linux/usb/onboard_hub.h deleted file mode 100644 index d9373230556e..000000000000 --- a/include/linux/usb/onboard_hub.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -#ifndef __LINUX_USB_ONBOARD_HUB_H -#define __LINUX_USB_ONBOARD_HUB_H - -struct usb_device; -struct list_head; - -#if IS_ENABLED(CONFIG_USB_ONBOARD_HUB) -void onboard_hub_create_pdevs(struct usb_device *parent_hub, struct list_head *pdev_list); -void onboard_hub_destroy_pdevs(struct list_head *pdev_list); -#else -static inline void onboard_hub_create_pdevs(struct usb_device *parent_hub, - struct list_head *pdev_list) {} -static inline void onboard_hub_destroy_pdevs(struct list_head *pdev_list) {} -#endif - -#endif /* __LINUX_USB_ONBOARD_HUB_H */ -- cgit v1.2.3 From 1a9517a0a43040b77b5ef64d9053df214ba33d17 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 3 May 2022 16:44:24 +0200 Subject: Revert "of/platform: Add stubs for of_platform_device_create/destroy()" This reverts commit 8e8b11956486e3fe8cacf54a1d492ebdd8cc1fb2. The series still has built errors as reported in linux-next, so revert it for now. Reported-by: Stephen Rothwell Link: https://lore.kernel.org/r/20220502210728.0b36f3cd@canb.auug.org.au Cc: Stephen Boyd Cc: Douglas Anderson Cc: Rob Herring Cc: Matthias Kaehlcke Signed-off-by: Greg Kroah-Hartman --- include/linux/of_platform.h | 22 ++++------------------ 1 file changed, 4 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index d15b6cd5e1c3..84a966623e78 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -61,18 +61,16 @@ static inline struct platform_device *of_find_device_by_node(struct device_node } #endif -extern int of_platform_bus_probe(struct device_node *root, - const struct of_device_id *matches, - struct device *parent); - -#ifdef CONFIG_OF_ADDRESS /* Platform devices and busses creation */ extern struct platform_device *of_platform_device_create(struct device_node *np, const char *bus_id, struct device *parent); extern int of_platform_device_destroy(struct device *dev, void *data); - +extern int of_platform_bus_probe(struct device_node *root, + const struct of_device_id *matches, + struct device *parent); +#ifdef CONFIG_OF_ADDRESS extern int of_platform_populate(struct device_node *root, const struct of_device_id *matches, const struct of_dev_auxdata *lookup, @@ -86,18 +84,6 @@ extern int devm_of_platform_populate(struct device *dev); extern void devm_of_platform_depopulate(struct device *dev); #else -/* Platform devices and busses creation */ -static inline struct platform_device *of_platform_device_create(struct device_node *np, - const char *bus_id, - struct device *parent) -{ - return NULL; -} -static inline int of_platform_device_destroy(struct device *dev, void *data) -{ - return -ENODEV; -} - static inline int of_platform_populate(struct device_node *root, const struct of_device_id *matches, const struct of_dev_auxdata *lookup, -- cgit v1.2.3 From 52f988d757c78cea06b1d5c75791a7fe1638ef86 Mon Sep 17 00:00:00 2001 From: Zelong Dong Date: Fri, 7 Jan 2022 10:39:30 +0800 Subject: dt-bindings: reset: add bindings for the Meson-S4 SoC Reset Controller Add DT bindings for the Meson-S4 SoC Reset Controller include file. Signed-off-by: Zelong Dong Reviewed-by: Martin Blumenstingl Signed-off-by: Philipp Zabel Link: https://lore.kernel.org/r/20220107023931.13251-3-zelong.dong@amlogic.com --- include/dt-bindings/reset/amlogic,meson-s4-reset.h | 125 +++++++++++++++++++++ 1 file changed, 125 insertions(+) create mode 100644 include/dt-bindings/reset/amlogic,meson-s4-reset.h (limited to 'include') diff --git a/include/dt-bindings/reset/amlogic,meson-s4-reset.h b/include/dt-bindings/reset/amlogic,meson-s4-reset.h new file mode 100644 index 000000000000..eab428eb8ad6 --- /dev/null +++ b/include/dt-bindings/reset/amlogic,meson-s4-reset.h @@ -0,0 +1,125 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR MIT) */ +/* + * Copyright (c) 2021 Amlogic, Inc. All rights reserved. + * Author: Zelong Dong + * + */ + +#ifndef _DT_BINDINGS_AMLOGIC_MESON_S4_RESET_H +#define _DT_BINDINGS_AMLOGIC_MESON_S4_RESET_H + +/* RESET0 */ +#define RESET_USB_DDR0 0 +#define RESET_USB_DDR1 1 +#define RESET_USB_DDR2 2 +#define RESET_USB_DDR3 3 +#define RESET_USBCTRL 4 +/* 5-7 */ +#define RESET_USBPHY20 8 +#define RESET_USBPHY21 9 +/* 10-15 */ +#define RESET_HDMITX_APB 16 +#define RESET_BRG_VCBUS_DEC 17 +#define RESET_VCBUS 18 +#define RESET_VID_PLL_DIV 19 +#define RESET_VDI6 20 +#define RESET_GE2D 21 +#define RESET_HDMITXPHY 22 +#define RESET_VID_LOCK 23 +#define RESET_VENCL 24 +#define RESET_VDAC 25 +#define RESET_VENCP 26 +#define RESET_VENCI 27 +#define RESET_RDMA 28 +#define RESET_HDMI_TX 29 +#define RESET_VIU 30 +#define RESET_VENC 31 + +/* RESET1 */ +#define RESET_AUDIO 32 +#define RESET_MALI_APB 33 +#define RESET_MALI 34 +#define RESET_DDR_APB 35 +#define RESET_DDR 36 +#define RESET_DOS_APB 37 +#define RESET_DOS 38 +/* 39-47 */ +#define RESET_ETH 48 +/* 49-51 */ +#define RESET_DEMOD 52 +/* 53-63 */ + +/* RESET2 */ +#define RESET_ABUS_ARB 64 +#define RESET_IR_CTRL 65 +#define RESET_TEMPSENSOR_DDR 66 +#define RESET_TEMPSENSOR_PLL 67 +/* 68-71 */ +#define RESET_SMART_CARD 72 +#define RESET_SPICC0 73 +/* 74 */ +#define RESET_RSA 75 +/* 76-79 */ +#define RESET_MSR_CLK 80 +#define RESET_SPIFC 81 +#define RESET_SARADC 82 +/* 83-87 */ +#define RESET_ACODEC 88 +#define RESET_CEC 89 +#define RESET_AFIFO 90 +#define RESET_WATCHDOG 91 +/* 92-95 */ + +/* RESET3 */ +/* 96-127 */ + +/* RESET4 */ +/* 128-131 */ +#define RESET_PWM_AB 132 +#define RESET_PWM_CD 133 +#define RESET_PWM_EF 134 +#define RESET_PWM_GH 135 +#define RESET_PWM_IJ 136 +/* 137 */ +#define RESET_UART_A 138 +#define RESET_UART_B 139 +#define RESET_UART_C 140 +#define RESET_UART_D 141 +#define RESET_UART_E 142 +/* 143 */ +#define RESET_I2C_S_A 144 +#define RESET_I2C_M_A 145 +#define RESET_I2C_M_B 146 +#define RESET_I2C_M_C 147 +#define RESET_I2C_M_D 148 +#define RESET_I2C_M_E 149 +/* 150-151 */ +#define RESET_SD_EMMC_A 152 +#define RESET_SD_EMMC_B 153 +#define RESET_NAND_EMMC 154 +/* 155-159 */ + +/* RESET5 */ +#define RESET_BRG_VDEC_PIPL0 160 +#define RESET_BRG_HEVCF_PIPL0 161 +/* 162 */ +#define RESET_BRG_HCODEC_PIPL0 163 +#define RESET_BRG_GE2D_PIPL0 164 +#define RESET_BRG_VPU_PIPL0 165 +#define RESET_BRG_CPU_PIPL0 166 +#define RESET_BRG_MALI_PIPL0 167 +/* 168 */ +#define RESET_BRG_MALI_PIPL1 169 +/* 170-171 */ +#define RESET_BRG_HEVCF_PIPL1 172 +#define RESET_BRG_HEVCB_PIPL1 173 +/* 174-183 */ +#define RESET_RAMA 184 +/* 185-186 */ +#define RESET_BRG_NIC_VAPB 187 +#define RESET_BRG_NIC_DSU 188 +#define RESET_BRG_NIC_SYSCLK 189 +#define RESET_BRG_NIC_MAIN 190 +#define RESET_BRG_NIC_ALL 191 + +#endif -- cgit v1.2.3 From 1ac17586c950a2c129393f8a92901a2b357acf24 Mon Sep 17 00:00:00 2001 From: Frank Rowand Date: Mon, 2 May 2022 13:17:40 -0500 Subject: of: overlay: add entry to of_overlay_action_name[] The values of enum of_overlay_notify_action are used to index into array of_overlay_action_name. Add an entry to of_overlay_action_name for the value recently added to of_overlay_notify_action. Array of_overlay_action_name[] is moved into include/linux/of.h adjacent to enum of_overlay_notify_action to make the connection between the two more obvious if either is modified in the future. The only use of of_overlay_action_name is for error reporting in overlay_notify(). All callers of overlay_notify() report the same error, but with fewer details. Remove the redundant error reports in the callers. Fixes: 067c098766c6 ("of: overlay: rework overlay apply and remove kfree()s") Reported-by: Dan Carpenter Signed-off-by: Frank Rowand Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20220502181742.1402826-2-frowand.list@gmail.com --- include/linux/of.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/of.h b/include/linux/of.h index 17741eee0ca4..f0a5d6b10c5a 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -1550,6 +1550,19 @@ enum of_overlay_notify_action { OF_OVERLAY_POST_REMOVE, }; +static inline char *of_overlay_action_name(enum of_overlay_notify_action action) +{ + static char *of_overlay_action_name[] = { + "init", + "pre-apply", + "post-apply", + "pre-remove", + "post-remove", + }; + + return of_overlay_action_name[action]; +} + struct of_overlay_notify_data { struct device_node *overlay; struct device_node *target; -- cgit v1.2.3 From 282d8998e9979c2186af7f7d22366f2fc3149838 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 8 Mar 2022 15:45:33 -0800 Subject: srcu: Prevent expedited GPs and blocking readers from consuming CPU If an SRCU reader blocks while a synchronize_srcu_expedited() waits for that same reader, then that grace period will spawn an endless series of workqueue handlers, consuming a full CPU. This quickly gets pointless because consuming more CPU isn't going to make that reader get done faster, especially if it is blocked waiting for an external event. This commit therefore spawns at most one pair of back-to-back workqueue handlers per expedited grace period phase, instead inserting increasing delays as that grace period phase grows older, but capped at 10 jiffies. In any case, if there have been at least 100 back-to-back workqueue handlers within a single jiffy, regardless of grace period or grace-period phase, then a one-jiffy delay is inserted. [ paulmck: Apply feedback from kernel test robot. ] Cc: Neeraj Upadhyay Reported-by: Song Liu Tested-by: kernel test robot Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 1b9ff4ed37e4..e3014319d1ad 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -71,9 +71,11 @@ struct srcu_struct { unsigned long srcu_gp_seq; /* Grace-period seq #. */ unsigned long srcu_gp_seq_needed; /* Latest gp_seq needed. */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ + unsigned long srcu_gp_start; /* Last GP start timestamp (jiffies) */ unsigned long srcu_last_gp_end; /* Last GP end timestamp (ns) */ unsigned long srcu_size_jiffies; /* Current contention-measurement interval. */ unsigned long srcu_n_lock_retries; /* Contention events in current interval. */ + unsigned long srcu_n_exp_nodelay; /* # expedited no-delays in current GP phase. */ struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ bool sda_is_static; /* May ->sda be passed to free_percpu()? */ unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */ @@ -83,6 +85,8 @@ struct srcu_struct { atomic_t srcu_barrier_cpu_cnt; /* # CPUs not yet posting a */ /* callback for the barrier */ /* operation. */ + unsigned long reschedule_jiffies; + unsigned long reschedule_count; struct delayed_work work; struct lockdep_map dep_map; }; -- cgit v1.2.3 From c29722fad4aabbf6bb841b8f058f858ec911df56 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20G=C3=B6ttsche?= Date: Tue, 8 Mar 2022 18:09:26 +0100 Subject: selinux: log anon inode class name MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Log the anonymous inode class name in the security hook inode_init_security_anon. This name is the key for name based type transitions on the anon_inode security class on creation. Example: type=AVC msg=audit(02/16/22 22:02:50.585:216) : avc: granted \ { create } for pid=2136 comm=mariadbd anonclass=[io_uring] \ scontext=system_u:system_r:mysqld_t:s0 \ tcontext=system_u:system_r:mysqld_iouring_t:s0 tclass=anon_inode Add a new LSM audit data type holding the inode and the class name. Signed-off-by: Christian Göttsche [PM: adjusted 'anonclass' to be a trusted string, cgzones approved] Signed-off-by: Paul Moore --- include/linux/lsm_audit.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h index 17d02eda9538..97a8b21eb033 100644 --- a/include/linux/lsm_audit.h +++ b/include/linux/lsm_audit.h @@ -76,6 +76,7 @@ struct common_audit_data { #define LSM_AUDIT_DATA_IBENDPORT 14 #define LSM_AUDIT_DATA_LOCKDOWN 15 #define LSM_AUDIT_DATA_NOTIFICATION 16 +#define LSM_AUDIT_DATA_ANONINODE 17 union { struct path path; struct dentry *dentry; @@ -96,6 +97,7 @@ struct common_audit_data { struct lsm_ibpkey_audit *ibpkey; struct lsm_ibendport_audit *ibendport; int reason; + const char *anonclass; } u; /* this union contains LSM specific data */ union { -- cgit v1.2.3 From 05714cab7d63b189894235cf310fae7d6ffc2e9b Mon Sep 17 00:00:00 2001 From: Raghavendra Rao Ananta Date: Mon, 2 May 2022 23:38:46 +0000 Subject: KVM: arm64: Setup a framework for hypercall bitmap firmware registers KVM regularly introduces new hypercall services to the guests without any consent from the userspace. This means, the guests can observe hypercall services in and out as they migrate across various host kernel versions. This could be a major problem if the guest discovered a hypercall, started using it, and after getting migrated to an older kernel realizes that it's no longer available. Depending on how the guest handles the change, there's a potential chance that the guest would just panic. As a result, there's a need for the userspace to elect the services that it wishes the guest to discover. It can elect these services based on the kernels spread across its (migration) fleet. To remedy this, extend the existing firmware pseudo-registers, such as KVM_REG_ARM_PSCI_VERSION, but by creating a new COPROC register space for all the hypercall services available. These firmware registers are categorized based on the service call owners, but unlike the existing firmware pseudo-registers, they hold the features supported in the form of a bitmap. During the VM initialization, the registers are set to upper-limit of the features supported by the corresponding registers. It's expected that the VMMs discover the features provided by each register via GET_ONE_REG, and write back the desired values using SET_ONE_REG. KVM allows this modification only until the VM has started. Some of the standard features are not mapped to any bits of the registers. But since they can recreate the original problem of making it available without userspace's consent, they need to be explicitly added to the case-list in kvm_hvc_call_default_allowed(). Any function-id that's not enabled via the bitmap, or not listed in kvm_hvc_call_default_allowed, will be returned as SMCCC_RET_NOT_SUPPORTED to the guest. Older userspace code can simply ignore the feature and the hypercall services will be exposed unconditionally to the guests, thus ensuring backward compatibility. In this patch, the framework adds the register only for ARM's standard secure services (owner value 4). Currently, this includes support only for ARM True Random Number Generator (TRNG) service, with bit-0 of the register representing mandatory features of v1.0. Other services are momentarily added in the upcoming patches. Signed-off-by: Raghavendra Rao Ananta Reviewed-by: Gavin Shan [maz: reduced the scope of some helpers, tidy-up bitmap max values, dropped error-only fast path] Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220502233853.1233742-3-rananta@google.com --- include/kvm/arm_hypercalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/kvm/arm_hypercalls.h b/include/kvm/arm_hypercalls.h index 5d38628a8d04..1188f116cf4e 100644 --- a/include/kvm/arm_hypercalls.h +++ b/include/kvm/arm_hypercalls.h @@ -42,6 +42,7 @@ static inline void smccc_set_retval(struct kvm_vcpu *vcpu, struct kvm_one_reg; +void kvm_arm_init_hypercalls(struct kvm *kvm); int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu); int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); -- cgit v1.2.3 From c2aa2dfef243efe213a480a1ee8566507a5152f4 Mon Sep 17 00:00:00 2001 From: Sargun Dhillon Date: Tue, 3 May 2022 01:09:56 -0700 Subject: seccomp: Add wait_killable semantic to seccomp user notifier This introduces a per-filter flag (SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV) that makes it so that when notifications are received by the supervisor the notifying process will transition to wait killable semantics. Although wait killable isn't a set of semantics formally exposed to userspace, the concept is searchable. If the notifying process is signaled prior to the notification being received by the userspace agent, it will be handled as normal. One quirk about how this is handled is that the notifying process only switches to TASK_KILLABLE if it receives a wakeup from either an addfd or a signal. This is to avoid an unnecessary wakeup of the notifying task. The reasons behind switching into wait_killable only after userspace receives the notification are: * Avoiding unncessary work - Often, workloads will perform work that they may abort (request racing comes to mind). This allows for syscalls to be aborted safely prior to the notification being received by the supervisor. In this, the supervisor doesn't end up doing work that the workload does not want to complete anyways. * Avoiding side effects - We don't want the syscall to be interruptible once the supervisor starts doing work because it may not be trivial to reverse the operation. For example, unmounting a file system may take a long time, and it's hard to rollback, or treat that as reentrant. * Avoid breaking runtimes - Various runtimes do not GC when they are during a syscall (or while running native code that subsequently calls a syscall). If many notifications are blocked, and not picked up by the supervisor, this can get the application into a bad state. Signed-off-by: Sargun Dhillon Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220503080958.20220-2-sargun@sargun.me --- include/linux/seccomp.h | 3 ++- include/uapi/linux/seccomp.h | 2 ++ 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 0c564e5d40ff..d31d76be4982 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -8,7 +8,8 @@ SECCOMP_FILTER_FLAG_LOG | \ SECCOMP_FILTER_FLAG_SPEC_ALLOW | \ SECCOMP_FILTER_FLAG_NEW_LISTENER | \ - SECCOMP_FILTER_FLAG_TSYNC_ESRCH) + SECCOMP_FILTER_FLAG_TSYNC_ESRCH | \ + SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV) /* sizeof() the first published struct seccomp_notif_addfd */ #define SECCOMP_NOTIFY_ADDFD_SIZE_VER0 24 diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h index 78074254ab98..0fdc6ef02b94 100644 --- a/include/uapi/linux/seccomp.h +++ b/include/uapi/linux/seccomp.h @@ -23,6 +23,8 @@ #define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2) #define SECCOMP_FILTER_FLAG_NEW_LISTENER (1UL << 3) #define SECCOMP_FILTER_FLAG_TSYNC_ESRCH (1UL << 4) +/* Received notifications wait in killable state (only respond to fatal signals) */ +#define SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV (1UL << 5) /* * All BPF programs must return a 32-bit value. -- cgit v1.2.3 From 41b3c69bf9414375319290c59f198ff5c71d273f Mon Sep 17 00:00:00 2001 From: Kishen Maloor Date: Mon, 2 May 2022 13:52:36 -0700 Subject: mptcp: expose server_side attribute in MPTCP netlink events This change records the 'server_side' attribute of MPTCP_EVENT_CREATED and MPTCP_EVENT_ESTABLISHED events to inform their recipient about the Client/Server role of the running MPTCP application. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/246 Acked-by: Paolo Abeni Signed-off-by: Kishen Maloor Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 9690efedb5fa..e41ea01a94bb 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -188,6 +188,7 @@ enum mptcp_event_attr { MPTCP_ATTR_IF_IDX, /* s32 */ MPTCP_ATTR_RESET_REASON,/* u32 */ MPTCP_ATTR_RESET_FLAGS, /* u32 */ + MPTCP_ATTR_SERVER_SIDE, /* u8 */ __MPTCP_ATTR_AFTER_LAST }; -- cgit v1.2.3 From 58caed3dacb4354a25a1aa8d2febc3e9648ba1f4 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 2 May 2022 16:27:03 -0700 Subject: netdev: reshuffle netif_napi_add() APIs to allow dropping weight Most drivers should not have to worry about selecting the right weight for their NAPI instances and pass NAPI_POLL_WEIGHT. It'd be best if we didn't require the argument at all and selected the default internally. This change prepares the ground for such reshuffling, allowing for a smooth transition. The following API should remain after the next release cycle: netif_napi_add() netif_napi_add_weight() netif_napi_add_tx() netif_napi_add_tx_weight() Where the _weight() variants take an explicit weight argument. I opted for a _weight() suffix rather than a __ prefix, because we use __ in places to mean that caller needs to also issue a synchronize_net() call. Signed-off-by: Jakub Kicinski Link: https://lore.kernel.org/r/20220502232703.396351-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 50 +++++++++++++++++++++++++++++++---------------- 1 file changed, 33 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4aba92a4042a..eaf66e57d891 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2499,37 +2499,53 @@ static inline void *netdev_priv(const struct net_device *dev) */ #define NAPI_POLL_WEIGHT 64 +void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), int weight); + /** - * netif_napi_add - initialize a NAPI context - * @dev: network device - * @napi: NAPI context - * @poll: polling function - * @weight: default weight + * netif_napi_add() - initialize a NAPI context + * @dev: network device + * @napi: NAPI context + * @poll: polling function + * @weight: default weight * * netif_napi_add() must be used to initialize a NAPI context prior to calling * *any* of the other NAPI-related functions. */ -void netif_napi_add(struct net_device *dev, struct napi_struct *napi, - int (*poll)(struct napi_struct *, int), int weight); +static inline void +netif_napi_add(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), int weight) +{ + netif_napi_add_weight(dev, napi, poll, weight); +} + +static inline void +netif_napi_add_tx_weight(struct net_device *dev, + struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), + int weight) +{ + set_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state); + netif_napi_add_weight(dev, napi, poll, weight); +} + +#define netif_tx_napi_add netif_napi_add_tx_weight /** - * netif_tx_napi_add - initialize a NAPI context - * @dev: network device - * @napi: NAPI context - * @poll: polling function - * @weight: default weight + * netif_napi_add_tx() - initialize a NAPI context to be used for Tx only + * @dev: network device + * @napi: NAPI context + * @poll: polling function * * This variant of netif_napi_add() should be used from drivers using NAPI * to exclusively poll a TX queue. * This will avoid we add it into napi_hash[], thus polluting this hash table. */ -static inline void netif_tx_napi_add(struct net_device *dev, +static inline void netif_napi_add_tx(struct net_device *dev, struct napi_struct *napi, - int (*poll)(struct napi_struct *, int), - int weight) + int (*poll)(struct napi_struct *, int)) { - set_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state); - netif_napi_add(dev, napi, poll, weight); + netif_napi_add_tx_weight(dev, napi, poll, NAPI_POLL_WEIGHT); } /** -- cgit v1.2.3 From c674df973ad8af2074c834788e167332d81309fa Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 8 Mar 2022 20:36:15 +0200 Subject: net/mlx5: Store IPsec ESN update work in XFRM state mlx5 IPsec code updated ESN through workqueue with allocation calls in the data path, which can be saved easily if the work is created during XFRM state initialization routine. The locking used later in the work didn't protect from anything because change of HW context is possible during XFRM state add or delete only, which can cancel work and make sure that it is not running. Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/accel.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h index 0f2596297f6a..a2720ebbb9fd 100644 --- a/include/linux/mlx5/accel.h +++ b/include/linux/mlx5/accel.h @@ -127,8 +127,8 @@ struct mlx5_accel_esp_xfrm * mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev, const struct mlx5_accel_esp_xfrm_attrs *attrs); void mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm); -int mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, - const struct mlx5_accel_esp_xfrm_attrs *attrs); +void mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, + const struct mlx5_accel_esp_xfrm_attrs *attrs); #else @@ -145,9 +145,11 @@ mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev, } static inline void mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm) {} -static inline int +static inline void mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, - const struct mlx5_accel_esp_xfrm_attrs *attrs) { return -EOPNOTSUPP; } + const struct mlx5_accel_esp_xfrm_attrs *attrs) +{ +} #endif /* CONFIG_MLX5_EN_IPSEC */ #endif /* __MLX5_ACCEL_H__ */ -- cgit v1.2.3 From 2ea36e2e4ad2b77bd5d45142a529b72eb5ca9156 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Tue, 8 Mar 2022 20:55:00 +0200 Subject: net/mlx5: Remove useless validity check All callers build xfrm attributes with help of mlx5e_ipsec_build_accel_xfrm_attrs() function that ensure validity of attributes. There is no need to recheck them again. Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/accel.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h index a2720ebbb9fd..9c511d466e55 100644 --- a/include/linux/mlx5/accel.h +++ b/include/linux/mlx5/accel.h @@ -36,10 +36,6 @@ #include -enum mlx5_accel_esp_aes_gcm_keymat_iv_algo { - MLX5_ACCEL_ESP_AES_GCM_IV_ALGO_SEQ, -}; - enum mlx5_accel_esp_flags { MLX5_ACCEL_ESP_FLAGS_TUNNEL = 0, /* Default */ MLX5_ACCEL_ESP_FLAGS_TRANSPORT = 1UL << 0, @@ -57,14 +53,9 @@ enum mlx5_accel_esp_keymats { MLX5_ACCEL_ESP_KEYMAT_AES_GCM, }; -enum mlx5_accel_esp_replay { - MLX5_ACCEL_ESP_REPLAY_NONE, - MLX5_ACCEL_ESP_REPLAY_BMP, -}; struct aes_gcm_keymat { u64 seq_iv; - enum mlx5_accel_esp_aes_gcm_keymat_iv_algo iv_algo; u32 salt; u32 icv_len; @@ -81,7 +72,6 @@ struct mlx5_accel_esp_xfrm_attrs { u32 tfc_pad; u32 flags; u32 sa_handle; - enum mlx5_accel_esp_replay replay_type; union { struct { u32 size; -- cgit v1.2.3 From c6e3b421c7079af67201351c9faff62613e06f40 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 9 Mar 2022 10:35:05 +0200 Subject: net/mlx5: Merge various control path IPsec headers into one file The mlx5 IPsec code has logical separation between code that operates with XFRM objects (ipsec.c), HW objects (ipsec_offload.c), flow steering logic (ipsec_fs.c) and data path (ipsec_rxtx.c). Such separation makes sense for C-files, but isn't needed at all for H-files as they are included in batch anyway. Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/accel.h | 145 --------------------------------------------- 1 file changed, 145 deletions(-) delete mode 100644 include/linux/mlx5/accel.h (limited to 'include') diff --git a/include/linux/mlx5/accel.h b/include/linux/mlx5/accel.h deleted file mode 100644 index 9c511d466e55..000000000000 --- a/include/linux/mlx5/accel.h +++ /dev/null @@ -1,145 +0,0 @@ -/* - * Copyright (c) 2018 Mellanox Technologies. All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - * - */ - -#ifndef __MLX5_ACCEL_H__ -#define __MLX5_ACCEL_H__ - -#include - -enum mlx5_accel_esp_flags { - MLX5_ACCEL_ESP_FLAGS_TUNNEL = 0, /* Default */ - MLX5_ACCEL_ESP_FLAGS_TRANSPORT = 1UL << 0, - MLX5_ACCEL_ESP_FLAGS_ESN_TRIGGERED = 1UL << 1, - MLX5_ACCEL_ESP_FLAGS_ESN_STATE_OVERLAP = 1UL << 2, -}; - -enum mlx5_accel_esp_action { - MLX5_ACCEL_ESP_ACTION_DECRYPT, - MLX5_ACCEL_ESP_ACTION_ENCRYPT, -}; - -enum mlx5_accel_esp_keymats { - MLX5_ACCEL_ESP_KEYMAT_AES_NONE, - MLX5_ACCEL_ESP_KEYMAT_AES_GCM, -}; - - -struct aes_gcm_keymat { - u64 seq_iv; - - u32 salt; - u32 icv_len; - - u32 key_len; - u32 aes_key[256 / 32]; -}; - -struct mlx5_accel_esp_xfrm_attrs { - enum mlx5_accel_esp_action action; - u32 esn; - __be32 spi; - u32 seq; - u32 tfc_pad; - u32 flags; - u32 sa_handle; - union { - struct { - u32 size; - - } bmp; - } replay; - enum mlx5_accel_esp_keymats keymat_type; - union { - struct aes_gcm_keymat aes_gcm; - } keymat; - - union { - __be32 a4; - __be32 a6[4]; - } saddr; - - union { - __be32 a4; - __be32 a6[4]; - } daddr; - - u8 is_ipv6; -}; - -struct mlx5_accel_esp_xfrm { - struct mlx5_core_dev *mdev; - struct mlx5_accel_esp_xfrm_attrs attrs; -}; - -enum mlx5_accel_ipsec_cap { - MLX5_ACCEL_IPSEC_CAP_DEVICE = 1 << 0, - MLX5_ACCEL_IPSEC_CAP_ESP = 1 << 1, - MLX5_ACCEL_IPSEC_CAP_IPV6 = 1 << 2, - MLX5_ACCEL_IPSEC_CAP_LSO = 1 << 3, - MLX5_ACCEL_IPSEC_CAP_ESN = 1 << 4, -}; - -#ifdef CONFIG_MLX5_EN_IPSEC - -u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev); - -struct mlx5_accel_esp_xfrm * -mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev, - const struct mlx5_accel_esp_xfrm_attrs *attrs); -void mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm); -void mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, - const struct mlx5_accel_esp_xfrm_attrs *attrs); - -#else - -static inline u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev) -{ - return 0; -} - -static inline struct mlx5_accel_esp_xfrm * -mlx5_accel_esp_create_xfrm(struct mlx5_core_dev *mdev, - const struct mlx5_accel_esp_xfrm_attrs *attrs) -{ - return ERR_PTR(-EOPNOTSUPP); -} -static inline void -mlx5_accel_esp_destroy_xfrm(struct mlx5_accel_esp_xfrm *xfrm) {} -static inline void -mlx5_accel_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm, - const struct mlx5_accel_esp_xfrm_attrs *attrs) -{ -} - -#endif /* CONFIG_MLX5_EN_IPSEC */ -#endif /* __MLX5_ACCEL_H__ */ -- cgit v1.2.3 From 1c4a59b9fa98c222bd6a8fa82bff942312165c1a Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Sun, 27 Mar 2022 19:23:19 +0300 Subject: net/mlx5: Remove not-supported ICV length mlx5 doesn't allow to configure any AEAD ICV length other than 128, so remove the logic that configures other unsupported values. Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 7f4ec9faa180..7bab3e51c61e 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -11379,8 +11379,6 @@ enum { enum { MLX5_IPSEC_OBJECT_ICV_LEN_16B, - MLX5_IPSEC_OBJECT_ICV_LEN_12B, - MLX5_IPSEC_OBJECT_ICV_LEN_8B, }; struct mlx5_ifc_ipsec_obj_bits { -- cgit v1.2.3 From 7b33a09d036ffd9a04506122840629c7e870cf08 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Wed, 4 May 2022 03:24:40 +0000 Subject: KVM: arm64: Add support for userspace to suspend a vCPU Introduce a new MP state, KVM_MP_STATE_SUSPENDED, which indicates a vCPU is in a suspended state. In the suspended state the vCPU will block until a wakeup event (pending interrupt) is recognized. Add a new system event type, KVM_SYSTEM_EVENT_WAKEUP, to indicate to userspace that KVM has recognized one such wakeup event. It is the responsibility of userspace to then make the vCPU runnable, or leave it suspended until the next wakeup event. Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220504032446.4133305-7-oupton@google.com --- include/uapi/linux/kvm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 6a184d260c7f..7f72fb7b05f2 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -444,6 +444,7 @@ struct kvm_run { #define KVM_SYSTEM_EVENT_SHUTDOWN 1 #define KVM_SYSTEM_EVENT_RESET 2 #define KVM_SYSTEM_EVENT_CRASH 3 +#define KVM_SYSTEM_EVENT_WAKEUP 4 __u32 type; __u32 ndata; union { @@ -646,6 +647,7 @@ struct kvm_vapic_addr { #define KVM_MP_STATE_OPERATING 7 #define KVM_MP_STATE_LOAD 8 #define KVM_MP_STATE_AP_RESET_HOLD 9 +#define KVM_MP_STATE_SUSPENDED 10 struct kvm_mp_state { __u32 mp_state; -- cgit v1.2.3 From bfbab44568779e1682bc6f63688bb9c965f0e74a Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Wed, 4 May 2022 03:24:41 +0000 Subject: KVM: arm64: Implement PSCI SYSTEM_SUSPEND ARM DEN0022D.b 5.19 "SYSTEM_SUSPEND" describes a PSCI call that allows software to request that a system be placed in the deepest possible low-power state. Effectively, software can use this to suspend itself to RAM. Unfortunately, there really is no good way to implement a system-wide PSCI call in KVM. Any precondition checks done in the kernel will need to be repeated by userspace since there is no good way to protect a critical section that spans an exit to userspace. SYSTEM_RESET and SYSTEM_OFF are equally plagued by this issue, although no users have seemingly cared for the relatively long time these calls have been supported. The solution is to just make the whole implementation userspace's problem. Introduce a new system event, KVM_SYSTEM_EVENT_SUSPEND, that indicates to userspace a calling vCPU has invoked PSCI SYSTEM_SUSPEND. Additionally, add a CAP to get buy-in from userspace for this new exit type. Only advertise the SYSTEM_SUSPEND PSCI call if userspace has opted in. If a vCPU calls SYSTEM_SUSPEND, punt straight to userspace. Provide explicit documentation of userspace's responsibilites for the exit and point to the PSCI specification to describe the actual PSCI call. Reviewed-by: Reiji Watanabe Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220504032446.4133305-8-oupton@google.com --- include/uapi/linux/kvm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 7f72fb7b05f2..32c56384fd08 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -445,6 +445,7 @@ struct kvm_run { #define KVM_SYSTEM_EVENT_RESET 2 #define KVM_SYSTEM_EVENT_CRASH 3 #define KVM_SYSTEM_EVENT_WAKEUP 4 +#define KVM_SYSTEM_EVENT_SUSPEND 5 __u32 type; __u32 ndata; union { @@ -1154,6 +1155,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_DISABLE_QUIRKS2 213 /* #define KVM_CAP_VM_TSC_CONTROL 214 */ #define KVM_CAP_SYSTEM_EVENT_DATA 215 +#define KVM_CAP_ARM_SYSTEM_SUSPEND 216 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 6625ffb90f44efc28a3fe1432191a4eacb08c915 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 3 May 2022 15:13:52 +0800 Subject: dt-bindings: mediatek: mt8195: Add binding for MM IOMMU This patch adds descriptions for mt8195 IOMMU which also use ARM Short-Descriptor translation table format. In mt8195, there are two smi-common HW and IOMMU, one is for vdo(video output), the other is for vpp(video processing pipe). They connects with different smi-larbs, then some setting(larbid_remap) is different. Differentiate them with the compatible string. Something like this: IOMMU(VDO) IOMMU(VPP) | | SMI_COMMON_VDO SMI_COMMON_VPP --------------- ---------------- | | ... | | ... larb0 larb2 ... larb1 larb3 ... Another change is that we have a new IOMMU that is for infra master like PCIe and USB. The infra master don't have the larb and ports, thus we rename the port header file to mt8195-memory-port.h rather than mt8195-larb-port.h. Also, the IOMMU is not only for MM, thus, we don't call it "m4u" which means "MultiMedia Memory Management UNIT". thus, use the "iommu" as the compatiable string. Signed-off-by: Yong Wu Acked-by: Krzysztof Kozlowski Reviewed-by: Rob Herring Reviewed-by: Matthias Brugger Link: https://lore.kernel.org/r/20220503071427.2285-2-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- include/dt-bindings/memory/mt8195-memory-port.h | 390 ++++++++++++++++++++++++ 1 file changed, 390 insertions(+) create mode 100644 include/dt-bindings/memory/mt8195-memory-port.h (limited to 'include') diff --git a/include/dt-bindings/memory/mt8195-memory-port.h b/include/dt-bindings/memory/mt8195-memory-port.h new file mode 100644 index 000000000000..c10e8b61f1e8 --- /dev/null +++ b/include/dt-bindings/memory/mt8195-memory-port.h @@ -0,0 +1,390 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Yong Wu + */ +#ifndef _DT_BINDINGS_MEMORY_MT8195_LARB_PORT_H_ +#define _DT_BINDINGS_MEMORY_MT8195_LARB_PORT_H_ + +#include + +/* + * MM IOMMU supports 16GB dma address. We separate it to four ranges: + * 0 ~ 4G; 4G ~ 8G; 8G ~ 12G; 12G ~ 16G, we could adjust these masters + * locate in anyone region. BUT: + * a) Make sure all the ports inside a larb are in one range. + * b) The iova of any master can NOT cross the 4G/8G/12G boundary. + * + * This is the suggested mapping in this SoC: + * + * modules dma-address-region larbs-ports + * disp 0 ~ 4G larb0/1/2/3 + * vcodec 4G ~ 8G larb19/20/21/22/23/24 + * cam/mdp 8G ~ 12G the other larbs. + * N/A 12G ~ 16G + * CCU0 0x24000_0000 ~ 0x243ff_ffff larb18: port 0/1 + * CCU1 0x24400_0000 ~ 0x247ff_ffff larb18: port 2/3 + * + * This SoC have two IOMMU HWs, this is the detailed connected information: + * iommu-vdo: larb0/2/5/7/9/10/11/13/17/19/21/24/25/28 + * iommu-vpp: larb1/3/4/6/8/12/14/16/18/20/22/23/26/27 + */ + +/* MM IOMMU ports */ +/* larb0 */ +#define M4U_PORT_L0_DISP_RDMA0 MTK_M4U_ID(0, 0) +#define M4U_PORT_L0_DISP_WDMA0 MTK_M4U_ID(0, 1) +#define M4U_PORT_L0_DISP_OVL0_RDMA0 MTK_M4U_ID(0, 2) +#define M4U_PORT_L0_DISP_OVL0_RDMA1 MTK_M4U_ID(0, 3) +#define M4U_PORT_L0_DISP_OVL0_HDR MTK_M4U_ID(0, 4) +#define M4U_PORT_L0_DISP_FAKE0 MTK_M4U_ID(0, 5) + +/* larb1 */ +#define M4U_PORT_L1_DISP_RDMA0 MTK_M4U_ID(1, 0) +#define M4U_PORT_L1_DISP_WDMA0 MTK_M4U_ID(1, 1) +#define M4U_PORT_L1_DISP_OVL0_RDMA0 MTK_M4U_ID(1, 2) +#define M4U_PORT_L1_DISP_OVL0_RDMA1 MTK_M4U_ID(1, 3) +#define M4U_PORT_L1_DISP_OVL0_HDR MTK_M4U_ID(1, 4) +#define M4U_PORT_L1_DISP_FAKE0 MTK_M4U_ID(1, 5) + +/* larb2 */ +#define M4U_PORT_L2_MDP_RDMA0 MTK_M4U_ID(2, 0) +#define M4U_PORT_L2_MDP_RDMA2 MTK_M4U_ID(2, 1) +#define M4U_PORT_L2_MDP_RDMA4 MTK_M4U_ID(2, 2) +#define M4U_PORT_L2_MDP_RDMA6 MTK_M4U_ID(2, 3) +#define M4U_PORT_L2_DISP_FAKE1 MTK_M4U_ID(2, 4) + +/* larb3 */ +#define M4U_PORT_L3_MDP_RDMA1 MTK_M4U_ID(3, 0) +#define M4U_PORT_L3_MDP_RDMA3 MTK_M4U_ID(3, 1) +#define M4U_PORT_L3_MDP_RDMA5 MTK_M4U_ID(3, 2) +#define M4U_PORT_L3_MDP_RDMA7 MTK_M4U_ID(3, 3) +#define M4U_PORT_L3_HDR_DS MTK_M4U_ID(3, 4) +#define M4U_PORT_L3_HDR_ADL MTK_M4U_ID(3, 5) +#define M4U_PORT_L3_DISP_FAKE1 MTK_M4U_ID(3, 6) + +/* larb4 */ +#define M4U_PORT_L4_MDP_RDMA MTK_M4U_ID(4, 0) +#define M4U_PORT_L4_MDP_FG MTK_M4U_ID(4, 1) +#define M4U_PORT_L4_MDP_OVL MTK_M4U_ID(4, 2) +#define M4U_PORT_L4_MDP_WROT MTK_M4U_ID(4, 3) +#define M4U_PORT_L4_FAKE MTK_M4U_ID(4, 4) + +/* larb5 */ +#define M4U_PORT_L5_SVPP1_MDP_RDMA MTK_M4U_ID(5, 0) +#define M4U_PORT_L5_SVPP1_MDP_FG MTK_M4U_ID(5, 1) +#define M4U_PORT_L5_SVPP1_MDP_OVL MTK_M4U_ID(5, 2) +#define M4U_PORT_L5_SVPP1_MDP_WROT MTK_M4U_ID(5, 3) +#define M4U_PORT_L5_SVPP2_MDP_RDMA MTK_M4U_ID(5, 4) +#define M4U_PORT_L5_SVPP2_MDP_FG MTK_M4U_ID(5, 5) +#define M4U_PORT_L5_SVPP2_MDP_WROT MTK_M4U_ID(5, 6) +#define M4U_PORT_L5_FAKE MTK_M4U_ID(5, 7) + +/* larb6 */ +#define M4U_PORT_L6_SVPP3_MDP_RDMA MTK_M4U_ID(6, 0) +#define M4U_PORT_L6_SVPP3_MDP_FG MTK_M4U_ID(6, 1) +#define M4U_PORT_L6_SVPP3_MDP_WROT MTK_M4U_ID(6, 2) +#define M4U_PORT_L6_FAKE MTK_M4U_ID(6, 3) + +/* larb7 */ +#define M4U_PORT_L7_IMG_WPE_RDMA0 MTK_M4U_ID(7, 0) +#define M4U_PORT_L7_IMG_WPE_RDMA1 MTK_M4U_ID(7, 1) +#define M4U_PORT_L7_IMG_WPE_WDMA0 MTK_M4U_ID(7, 2) + +/* larb8 */ +#define M4U_PORT_L8_IMG_WPE_RDMA0 MTK_M4U_ID(8, 0) +#define M4U_PORT_L8_IMG_WPE_RDMA1 MTK_M4U_ID(8, 1) +#define M4U_PORT_L8_IMG_WPE_WDMA0 MTK_M4U_ID(8, 2) + +/* larb9 */ +#define M4U_PORT_L9_IMG_IMGI_T1_A MTK_M4U_ID(9, 0) +#define M4U_PORT_L9_IMG_IMGBI_T1_A MTK_M4U_ID(9, 1) +#define M4U_PORT_L9_IMG_IMGCI_T1_A MTK_M4U_ID(9, 2) +#define M4U_PORT_L9_IMG_SMTI_T1_A MTK_M4U_ID(9, 3) +#define M4U_PORT_L9_IMG_TNCSTI_T1_A MTK_M4U_ID(9, 4) +#define M4U_PORT_L9_IMG_TNCSTI_T4_A MTK_M4U_ID(9, 5) +#define M4U_PORT_L9_IMG_YUVO_T1_A MTK_M4U_ID(9, 6) +#define M4U_PORT_L9_IMG_TIMGO_T1_A MTK_M4U_ID(9, 7) +#define M4U_PORT_L9_IMG_YUVO_T2_A MTK_M4U_ID(9, 8) +#define M4U_PORT_L9_IMG_IMGI_T1_B MTK_M4U_ID(9, 9) +#define M4U_PORT_L9_IMG_IMGBI_T1_B MTK_M4U_ID(9, 10) +#define M4U_PORT_L9_IMG_IMGCI_T1_B MTK_M4U_ID(9, 11) +#define M4U_PORT_L9_IMG_YUVO_T5_A MTK_M4U_ID(9, 12) +#define M4U_PORT_L9_IMG_SMTI_T1_B MTK_M4U_ID(9, 13) +#define M4U_PORT_L9_IMG_TNCSO_T1_A MTK_M4U_ID(9, 14) +#define M4U_PORT_L9_IMG_SMTO_T1_A MTK_M4U_ID(9, 15) +#define M4U_PORT_L9_IMG_TNCSTO_T1_A MTK_M4U_ID(9, 16) +#define M4U_PORT_L9_IMG_YUVO_T2_B MTK_M4U_ID(9, 17) +#define M4U_PORT_L9_IMG_YUVO_T5_B MTK_M4U_ID(9, 18) +#define M4U_PORT_L9_IMG_SMTO_T1_B MTK_M4U_ID(9, 19) + +/* larb10 */ +#define M4U_PORT_L10_IMG_IMGI_D1_A MTK_M4U_ID(10, 0) +#define M4U_PORT_L10_IMG_IMGCI_D1_A MTK_M4U_ID(10, 1) +#define M4U_PORT_L10_IMG_DEPI_D1_A MTK_M4U_ID(10, 2) +#define M4U_PORT_L10_IMG_DMGI_D1_A MTK_M4U_ID(10, 3) +#define M4U_PORT_L10_IMG_VIPI_D1_A MTK_M4U_ID(10, 4) +#define M4U_PORT_L10_IMG_TNRWI_D1_A MTK_M4U_ID(10, 5) +#define M4U_PORT_L10_IMG_RECI_D1_A MTK_M4U_ID(10, 6) +#define M4U_PORT_L10_IMG_SMTI_D1_A MTK_M4U_ID(10, 7) +#define M4U_PORT_L10_IMG_SMTI_D6_A MTK_M4U_ID(10, 8) +#define M4U_PORT_L10_IMG_PIMGI_P1_A MTK_M4U_ID(10, 9) +#define M4U_PORT_L10_IMG_PIMGBI_P1_A MTK_M4U_ID(10, 10) +#define M4U_PORT_L10_IMG_PIMGCI_P1_A MTK_M4U_ID(10, 11) +#define M4U_PORT_L10_IMG_PIMGI_P1_B MTK_M4U_ID(10, 12) +#define M4U_PORT_L10_IMG_PIMGBI_P1_B MTK_M4U_ID(10, 13) +#define M4U_PORT_L10_IMG_PIMGCI_P1_B MTK_M4U_ID(10, 14) +#define M4U_PORT_L10_IMG_IMG3O_D1_A MTK_M4U_ID(10, 15) +#define M4U_PORT_L10_IMG_IMG4O_D1_A MTK_M4U_ID(10, 16) +#define M4U_PORT_L10_IMG_IMG3CO_D1_A MTK_M4U_ID(10, 17) +#define M4U_PORT_L10_IMG_FEO_D1_A MTK_M4U_ID(10, 18) +#define M4U_PORT_L10_IMG_IMG2O_D1_A MTK_M4U_ID(10, 19) +#define M4U_PORT_L10_IMG_TNRWO_D1_A MTK_M4U_ID(10, 20) +#define M4U_PORT_L10_IMG_SMTO_D1_A MTK_M4U_ID(10, 21) +#define M4U_PORT_L10_IMG_WROT_P1_A MTK_M4U_ID(10, 22) +#define M4U_PORT_L10_IMG_WROT_P1_B MTK_M4U_ID(10, 23) + +/* larb11 */ +#define M4U_PORT_L11_IMG_WPE_EIS_RDMA0_A MTK_M4U_ID(11, 0) +#define M4U_PORT_L11_IMG_WPE_EIS_RDMA1_A MTK_M4U_ID(11, 1) +#define M4U_PORT_L11_IMG_WPE_EIS_WDMA0_A MTK_M4U_ID(11, 2) +#define M4U_PORT_L11_IMG_WPE_TNR_RDMA0_A MTK_M4U_ID(11, 3) +#define M4U_PORT_L11_IMG_WPE_TNR_RDMA1_A MTK_M4U_ID(11, 4) +#define M4U_PORT_L11_IMG_WPE_TNR_WDMA0_A MTK_M4U_ID(11, 5) +#define M4U_PORT_L11_IMG_WPE_EIS_CQ0_A MTK_M4U_ID(11, 6) +#define M4U_PORT_L11_IMG_WPE_EIS_CQ1_A MTK_M4U_ID(11, 7) +#define M4U_PORT_L11_IMG_WPE_TNR_CQ0_A MTK_M4U_ID(11, 8) +#define M4U_PORT_L11_IMG_WPE_TNR_CQ1_A MTK_M4U_ID(11, 9) + +/* larb12 */ +#define M4U_PORT_L12_IMG_FDVT_RDA MTK_M4U_ID(12, 0) +#define M4U_PORT_L12_IMG_FDVT_RDB MTK_M4U_ID(12, 1) +#define M4U_PORT_L12_IMG_FDVT_WRA MTK_M4U_ID(12, 2) +#define M4U_PORT_L12_IMG_FDVT_WRB MTK_M4U_ID(12, 3) +#define M4U_PORT_L12_IMG_ME_RDMA MTK_M4U_ID(12, 4) +#define M4U_PORT_L12_IMG_ME_WDMA MTK_M4U_ID(12, 5) +#define M4U_PORT_L12_IMG_DVS_RDMA MTK_M4U_ID(12, 6) +#define M4U_PORT_L12_IMG_DVS_WDMA MTK_M4U_ID(12, 7) +#define M4U_PORT_L12_IMG_DVP_RDMA MTK_M4U_ID(12, 8) +#define M4U_PORT_L12_IMG_DVP_WDMA MTK_M4U_ID(12, 9) + +/* larb13 */ +#define M4U_PORT_L13_CAM_CAMSV_CQI_E1 MTK_M4U_ID(13, 0) +#define M4U_PORT_L13_CAM_CAMSV_CQI_E2 MTK_M4U_ID(13, 1) +#define M4U_PORT_L13_CAM_GCAMSV_A_IMGO_0 MTK_M4U_ID(13, 2) +#define M4U_PORT_L13_CAM_SCAMSV_A_IMGO_0 MTK_M4U_ID(13, 3) +#define M4U_PORT_L13_CAM_GCAMSV_B_IMGO_0 MTK_M4U_ID(13, 4) +#define M4U_PORT_L13_CAM_GCAMSV_B_IMGO_1 MTK_M4U_ID(13, 5) +#define M4U_PORT_L13_CAM_GCAMSV_A_UFEO_0 MTK_M4U_ID(13, 6) +#define M4U_PORT_L13_CAM_GCAMSV_B_UFEO_0 MTK_M4U_ID(13, 7) +#define M4U_PORT_L13_CAM_PDAI_0 MTK_M4U_ID(13, 8) +#define M4U_PORT_L13_CAM_FAKE MTK_M4U_ID(13, 9) + +/* larb14 */ +#define M4U_PORT_L14_CAM_GCAMSV_A_IMGO_1 MTK_M4U_ID(14, 0) +#define M4U_PORT_L14_CAM_SCAMSV_A_IMGO_1 MTK_M4U_ID(14, 1) +#define M4U_PORT_L14_CAM_GCAMSV_B_IMGO_0 MTK_M4U_ID(14, 2) +#define M4U_PORT_L14_CAM_GCAMSV_B_IMGO_1 MTK_M4U_ID(14, 3) +#define M4U_PORT_L14_CAM_SCAMSV_B_IMGO_0 MTK_M4U_ID(14, 4) +#define M4U_PORT_L14_CAM_SCAMSV_B_IMGO_1 MTK_M4U_ID(14, 5) +#define M4U_PORT_L14_CAM_IPUI MTK_M4U_ID(14, 6) +#define M4U_PORT_L14_CAM_IPU2I MTK_M4U_ID(14, 7) +#define M4U_PORT_L14_CAM_IPUO MTK_M4U_ID(14, 8) +#define M4U_PORT_L14_CAM_IPU2O MTK_M4U_ID(14, 9) +#define M4U_PORT_L14_CAM_IPU3O MTK_M4U_ID(14, 10) +#define M4U_PORT_L14_CAM_GCAMSV_A_UFEO_1 MTK_M4U_ID(14, 11) +#define M4U_PORT_L14_CAM_GCAMSV_B_UFEO_1 MTK_M4U_ID(14, 12) +#define M4U_PORT_L14_CAM_PDAI_1 MTK_M4U_ID(14, 13) +#define M4U_PORT_L14_CAM_PDAO MTK_M4U_ID(14, 14) + +/* larb15: null */ + +/* larb16 */ +#define M4U_PORT_L16_CAM_IMGO_R1 MTK_M4U_ID(16, 0) +#define M4U_PORT_L16_CAM_CQI_R1 MTK_M4U_ID(16, 1) +#define M4U_PORT_L16_CAM_CQI_R2 MTK_M4U_ID(16, 2) +#define M4U_PORT_L16_CAM_BPCI_R1 MTK_M4U_ID(16, 3) +#define M4U_PORT_L16_CAM_LSCI_R1 MTK_M4U_ID(16, 4) +#define M4U_PORT_L16_CAM_RAWI_R2 MTK_M4U_ID(16, 5) +#define M4U_PORT_L16_CAM_RAWI_R3 MTK_M4U_ID(16, 6) +#define M4U_PORT_L16_CAM_UFDI_R2 MTK_M4U_ID(16, 7) +#define M4U_PORT_L16_CAM_UFDI_R3 MTK_M4U_ID(16, 8) +#define M4U_PORT_L16_CAM_RAWI_R4 MTK_M4U_ID(16, 9) +#define M4U_PORT_L16_CAM_RAWI_R5 MTK_M4U_ID(16, 10) +#define M4U_PORT_L16_CAM_AAI_R1 MTK_M4U_ID(16, 11) +#define M4U_PORT_L16_CAM_FHO_R1 MTK_M4U_ID(16, 12) +#define M4U_PORT_L16_CAM_AAO_R1 MTK_M4U_ID(16, 13) +#define M4U_PORT_L16_CAM_TSFSO_R1 MTK_M4U_ID(16, 14) +#define M4U_PORT_L16_CAM_FLKO_R1 MTK_M4U_ID(16, 15) + +/* larb17 */ +#define M4U_PORT_L17_CAM_YUVO_R1 MTK_M4U_ID(17, 0) +#define M4U_PORT_L17_CAM_YUVO_R3 MTK_M4U_ID(17, 1) +#define M4U_PORT_L17_CAM_YUVCO_R1 MTK_M4U_ID(17, 2) +#define M4U_PORT_L17_CAM_YUVO_R2 MTK_M4U_ID(17, 3) +#define M4U_PORT_L17_CAM_RZH1N2TO_R1 MTK_M4U_ID(17, 4) +#define M4U_PORT_L17_CAM_DRZS4NO_R1 MTK_M4U_ID(17, 5) +#define M4U_PORT_L17_CAM_TNCSO_R1 MTK_M4U_ID(17, 6) + +/* larb18 */ +#define M4U_PORT_L18_CAM_CCUI MTK_M4U_ID(18, 0) +#define M4U_PORT_L18_CAM_CCUO MTK_M4U_ID(18, 1) +#define M4U_PORT_L18_CAM_CCUI2 MTK_M4U_ID(18, 2) +#define M4U_PORT_L18_CAM_CCUO2 MTK_M4U_ID(18, 3) + +/* larb19 */ +#define M4U_PORT_L19_VENC_RCPU MTK_M4U_ID(19, 0) +#define M4U_PORT_L19_VENC_REC MTK_M4U_ID(19, 1) +#define M4U_PORT_L19_VENC_BSDMA MTK_M4U_ID(19, 2) +#define M4U_PORT_L19_VENC_SV_COMV MTK_M4U_ID(19, 3) +#define M4U_PORT_L19_VENC_RD_COMV MTK_M4U_ID(19, 4) +#define M4U_PORT_L19_VENC_NBM_RDMA MTK_M4U_ID(19, 5) +#define M4U_PORT_L19_VENC_NBM_RDMA_LITE MTK_M4U_ID(19, 6) +#define M4U_PORT_L19_JPGENC_Y_RDMA MTK_M4U_ID(19, 7) +#define M4U_PORT_L19_JPGENC_C_RDMA MTK_M4U_ID(19, 8) +#define M4U_PORT_L19_JPGENC_Q_TABLE MTK_M4U_ID(19, 9) +#define M4U_PORT_L19_VENC_SUB_W_LUMA MTK_M4U_ID(19, 10) +#define M4U_PORT_L19_VENC_FCS_NBM_RDMA MTK_M4U_ID(19, 11) +#define M4U_PORT_L19_JPGENC_BSDMA MTK_M4U_ID(19, 12) +#define M4U_PORT_L19_JPGDEC_WDMA0 MTK_M4U_ID(19, 13) +#define M4U_PORT_L19_JPGDEC_BSDMA0 MTK_M4U_ID(19, 14) +#define M4U_PORT_L19_VENC_NBM_WDMA MTK_M4U_ID(19, 15) +#define M4U_PORT_L19_VENC_NBM_WDMA_LITE MTK_M4U_ID(19, 16) +#define M4U_PORT_L19_VENC_FCS_NBM_WDMA MTK_M4U_ID(19, 17) +#define M4U_PORT_L19_JPGDEC_WDMA1 MTK_M4U_ID(19, 18) +#define M4U_PORT_L19_JPGDEC_BSDMA1 MTK_M4U_ID(19, 19) +#define M4U_PORT_L19_JPGDEC_BUFF_OFFSET1 MTK_M4U_ID(19, 20) +#define M4U_PORT_L19_JPGDEC_BUFF_OFFSET0 MTK_M4U_ID(19, 21) +#define M4U_PORT_L19_VENC_CUR_LUMA MTK_M4U_ID(19, 22) +#define M4U_PORT_L19_VENC_CUR_CHROMA MTK_M4U_ID(19, 23) +#define M4U_PORT_L19_VENC_REF_LUMA MTK_M4U_ID(19, 24) +#define M4U_PORT_L19_VENC_REF_CHROMA MTK_M4U_ID(19, 25) +#define M4U_PORT_L19_VENC_SUB_R_CHROMA MTK_M4U_ID(19, 26) + +/* larb20 */ +#define M4U_PORT_L20_VENC_RCPU MTK_M4U_ID(20, 0) +#define M4U_PORT_L20_VENC_REC MTK_M4U_ID(20, 1) +#define M4U_PORT_L20_VENC_BSDMA MTK_M4U_ID(20, 2) +#define M4U_PORT_L20_VENC_SV_COMV MTK_M4U_ID(20, 3) +#define M4U_PORT_L20_VENC_RD_COMV MTK_M4U_ID(20, 4) +#define M4U_PORT_L20_VENC_NBM_RDMA MTK_M4U_ID(20, 5) +#define M4U_PORT_L20_VENC_NBM_RDMA_LITE MTK_M4U_ID(20, 6) +#define M4U_PORT_L20_JPGENC_Y_RDMA MTK_M4U_ID(20, 7) +#define M4U_PORT_L20_JPGENC_C_RDMA MTK_M4U_ID(20, 8) +#define M4U_PORT_L20_JPGENC_Q_TABLE MTK_M4U_ID(20, 9) +#define M4U_PORT_L20_VENC_SUB_W_LUMA MTK_M4U_ID(20, 10) +#define M4U_PORT_L20_VENC_FCS_NBM_RDMA MTK_M4U_ID(20, 11) +#define M4U_PORT_L20_JPGENC_BSDMA MTK_M4U_ID(20, 12) +#define M4U_PORT_L20_JPGDEC_WDMA0 MTK_M4U_ID(20, 13) +#define M4U_PORT_L20_JPGDEC_BSDMA0 MTK_M4U_ID(20, 14) +#define M4U_PORT_L20_VENC_NBM_WDMA MTK_M4U_ID(20, 15) +#define M4U_PORT_L20_VENC_NBM_WDMA_LITE MTK_M4U_ID(20, 16) +#define M4U_PORT_L20_VENC_FCS_NBM_WDMA MTK_M4U_ID(20, 17) +#define M4U_PORT_L20_JPGDEC_WDMA1 MTK_M4U_ID(20, 18) +#define M4U_PORT_L20_JPGDEC_BSDMA1 MTK_M4U_ID(20, 19) +#define M4U_PORT_L20_JPGDEC_BUFF_OFFSET1 MTK_M4U_ID(20, 20) +#define M4U_PORT_L20_JPGDEC_BUFF_OFFSET0 MTK_M4U_ID(20, 21) +#define M4U_PORT_L20_VENC_CUR_LUMA MTK_M4U_ID(20, 22) +#define M4U_PORT_L20_VENC_CUR_CHROMA MTK_M4U_ID(20, 23) +#define M4U_PORT_L20_VENC_REF_LUMA MTK_M4U_ID(20, 24) +#define M4U_PORT_L20_VENC_REF_CHROMA MTK_M4U_ID(20, 25) +#define M4U_PORT_L20_VENC_SUB_R_CHROMA MTK_M4U_ID(20, 26) + +/* larb21 */ +#define M4U_PORT_L21_VDEC_MC_EXT MTK_M4U_ID(21, 0) +#define M4U_PORT_L21_VDEC_UFO_EXT MTK_M4U_ID(21, 1) +#define M4U_PORT_L21_VDEC_PP_EXT MTK_M4U_ID(21, 2) +#define M4U_PORT_L21_VDEC_PRED_RD_EXT MTK_M4U_ID(21, 3) +#define M4U_PORT_L21_VDEC_PRED_WR_EXT MTK_M4U_ID(21, 4) +#define M4U_PORT_L21_VDEC_PPWRAP_EXT MTK_M4U_ID(21, 5) +#define M4U_PORT_L21_VDEC_TILE_EXT MTK_M4U_ID(21, 6) +#define M4U_PORT_L21_VDEC_VLD_EXT MTK_M4U_ID(21, 7) +#define M4U_PORT_L21_VDEC_VLD2_EXT MTK_M4U_ID(21, 8) +#define M4U_PORT_L21_VDEC_AVC_MV_EXT MTK_M4U_ID(21, 9) + +/* larb22 */ +#define M4U_PORT_L22_VDEC_MC_EXT MTK_M4U_ID(22, 0) +#define M4U_PORT_L22_VDEC_UFO_EXT MTK_M4U_ID(22, 1) +#define M4U_PORT_L22_VDEC_PP_EXT MTK_M4U_ID(22, 2) +#define M4U_PORT_L22_VDEC_PRED_RD_EXT MTK_M4U_ID(22, 3) +#define M4U_PORT_L22_VDEC_PRED_WR_EXT MTK_M4U_ID(22, 4) +#define M4U_PORT_L22_VDEC_PPWRAP_EXT MTK_M4U_ID(22, 5) +#define M4U_PORT_L22_VDEC_TILE_EXT MTK_M4U_ID(22, 6) +#define M4U_PORT_L22_VDEC_VLD_EXT MTK_M4U_ID(22, 7) +#define M4U_PORT_L22_VDEC_VLD2_EXT MTK_M4U_ID(22, 8) +#define M4U_PORT_L22_VDEC_AVC_MV_EXT MTK_M4U_ID(22, 9) + +/* larb23 */ +#define M4U_PORT_L23_VDEC_UFO_ENC_EXT MTK_M4U_ID(23, 0) +#define M4U_PORT_L23_VDEC_RDMA_EXT MTK_M4U_ID(23, 1) + +/* larb24 */ +#define M4U_PORT_L24_VDEC_LAT0_VLD_EXT MTK_M4U_ID(24, 0) +#define M4U_PORT_L24_VDEC_LAT0_VLD2_EXT MTK_M4U_ID(24, 1) +#define M4U_PORT_L24_VDEC_LAT0_AVC_MC_EXT MTK_M4U_ID(24, 2) +#define M4U_PORT_L24_VDEC_LAT0_PRED_RD_EXT MTK_M4U_ID(24, 3) +#define M4U_PORT_L24_VDEC_LAT0_TILE_EXT MTK_M4U_ID(24, 4) +#define M4U_PORT_L24_VDEC_LAT0_WDMA_EXT MTK_M4U_ID(24, 5) +#define M4U_PORT_L24_VDEC_LAT1_VLD_EXT MTK_M4U_ID(24, 6) +#define M4U_PORT_L24_VDEC_LAT1_VLD2_EXT MTK_M4U_ID(24, 7) +#define M4U_PORT_L24_VDEC_LAT1_AVC_MC_EXT MTK_M4U_ID(24, 8) +#define M4U_PORT_L24_VDEC_LAT1_PRED_RD_EXT MTK_M4U_ID(24, 9) +#define M4U_PORT_L24_VDEC_LAT1_TILE_EXT MTK_M4U_ID(24, 10) +#define M4U_PORT_L24_VDEC_LAT1_WDMA_EXT MTK_M4U_ID(24, 11) + +/* larb25 */ +#define M4U_PORT_L25_CAM_MRAW0_LSCI_M1 MTK_M4U_ID(25, 0) +#define M4U_PORT_L25_CAM_MRAW0_CQI_M1 MTK_M4U_ID(25, 1) +#define M4U_PORT_L25_CAM_MRAW0_CQI_M2 MTK_M4U_ID(25, 2) +#define M4U_PORT_L25_CAM_MRAW0_IMGO_M1 MTK_M4U_ID(25, 3) +#define M4U_PORT_L25_CAM_MRAW0_IMGBO_M1 MTK_M4U_ID(25, 4) +#define M4U_PORT_L25_CAM_MRAW2_LSCI_M1 MTK_M4U_ID(25, 5) +#define M4U_PORT_L25_CAM_MRAW2_CQI_M1 MTK_M4U_ID(25, 6) +#define M4U_PORT_L25_CAM_MRAW2_CQI_M2 MTK_M4U_ID(25, 7) +#define M4U_PORT_L25_CAM_MRAW2_IMGO_M1 MTK_M4U_ID(25, 8) +#define M4U_PORT_L25_CAM_MRAW2_IMGBO_M1 MTK_M4U_ID(25, 9) +#define M4U_PORT_L25_CAM_MRAW0_AFO_M1 MTK_M4U_ID(25, 10) +#define M4U_PORT_L25_CAM_MRAW2_AFO_M1 MTK_M4U_ID(25, 11) + +/* larb26 */ +#define M4U_PORT_L26_CAM_MRAW1_LSCI_M1 MTK_M4U_ID(26, 0) +#define M4U_PORT_L26_CAM_MRAW1_CQI_M1 MTK_M4U_ID(26, 1) +#define M4U_PORT_L26_CAM_MRAW1_CQI_M2 MTK_M4U_ID(26, 2) +#define M4U_PORT_L26_CAM_MRAW1_IMGO_M1 MTK_M4U_ID(26, 3) +#define M4U_PORT_L26_CAM_MRAW1_IMGBO_M1 MTK_M4U_ID(26, 4) +#define M4U_PORT_L26_CAM_MRAW3_LSCI_M1 MTK_M4U_ID(26, 5) +#define M4U_PORT_L26_CAM_MRAW3_CQI_M1 MTK_M4U_ID(26, 6) +#define M4U_PORT_L26_CAM_MRAW3_CQI_M2 MTK_M4U_ID(26, 7) +#define M4U_PORT_L26_CAM_MRAW3_IMGO_M1 MTK_M4U_ID(26, 8) +#define M4U_PORT_L26_CAM_MRAW3_IMGBO_M1 MTK_M4U_ID(26, 9) +#define M4U_PORT_L26_CAM_MRAW1_AFO_M1 MTK_M4U_ID(26, 10) +#define M4U_PORT_L26_CAM_MRAW3_AFO_M1 MTK_M4U_ID(26, 11) + +/* larb27 */ +#define M4U_PORT_L27_CAM_IMGO_R1 MTK_M4U_ID(27, 0) +#define M4U_PORT_L27_CAM_CQI_R1 MTK_M4U_ID(27, 1) +#define M4U_PORT_L27_CAM_CQI_R2 MTK_M4U_ID(27, 2) +#define M4U_PORT_L27_CAM_BPCI_R1 MTK_M4U_ID(27, 3) +#define M4U_PORT_L27_CAM_LSCI_R1 MTK_M4U_ID(27, 4) +#define M4U_PORT_L27_CAM_RAWI_R2 MTK_M4U_ID(27, 5) +#define M4U_PORT_L27_CAM_RAWI_R3 MTK_M4U_ID(27, 6) +#define M4U_PORT_L27_CAM_UFDI_R2 MTK_M4U_ID(27, 7) +#define M4U_PORT_L27_CAM_UFDI_R3 MTK_M4U_ID(27, 8) +#define M4U_PORT_L27_CAM_RAWI_R4 MTK_M4U_ID(27, 9) +#define M4U_PORT_L27_CAM_RAWI_R5 MTK_M4U_ID(27, 10) +#define M4U_PORT_L27_CAM_AAI_R1 MTK_M4U_ID(27, 11) +#define M4U_PORT_L27_CAM_FHO_R1 MTK_M4U_ID(27, 12) +#define M4U_PORT_L27_CAM_AAO_R1 MTK_M4U_ID(27, 13) +#define M4U_PORT_L27_CAM_TSFSO_R1 MTK_M4U_ID(27, 14) +#define M4U_PORT_L27_CAM_FLKO_R1 MTK_M4U_ID(27, 15) + +/* larb28 */ +#define M4U_PORT_L28_CAM_YUVO_R1 MTK_M4U_ID(28, 0) +#define M4U_PORT_L28_CAM_YUVO_R3 MTK_M4U_ID(28, 1) +#define M4U_PORT_L28_CAM_YUVCO_R1 MTK_M4U_ID(28, 2) +#define M4U_PORT_L28_CAM_YUVO_R2 MTK_M4U_ID(28, 3) +#define M4U_PORT_L28_CAM_RZH1N2TO_R1 MTK_M4U_ID(28, 4) +#define M4U_PORT_L28_CAM_DRZS4NO_R1 MTK_M4U_ID(28, 5) +#define M4U_PORT_L28_CAM_TNCSO_R1 MTK_M4U_ID(28, 6) + +#endif -- cgit v1.2.3 From dc1d99342db705efbeec517f9c6187f3b93ab423 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 3 May 2022 15:13:53 +0800 Subject: dt-bindings: mediatek: mt8195: Add binding for infra IOMMU In mt8195, we have a new IOMMU that is for INFRA IOMMU. its masters mainly are PCIe and USB. Different with MM IOMMU, all these masters connect with IOMMU directly, there is no mediatek,larbs property for infra IOMMU. Another thing is about PCIe ports. currently the function "of_iommu_configure_dev_id" only support the id number is 1, But our PCIe have two ports, one is for reading and the other is for writing. see more about the PCIe patch in this patchset. Thus, I only list the reading id here and add the other id in our driver. Signed-off-by: Yong Wu Acked-by: Krzysztof Kozlowski Reviewed-by: Rob Herring Reviewed-by: Matthias Brugger Link: https://lore.kernel.org/r/20220503071427.2285-3-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- include/dt-bindings/memory/mt8195-memory-port.h | 18 ++++++++++++++++++ include/dt-bindings/memory/mtk-memory-port.h | 2 ++ 2 files changed, 20 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/memory/mt8195-memory-port.h b/include/dt-bindings/memory/mt8195-memory-port.h index c10e8b61f1e8..70ba9f498eeb 100644 --- a/include/dt-bindings/memory/mt8195-memory-port.h +++ b/include/dt-bindings/memory/mt8195-memory-port.h @@ -387,4 +387,22 @@ #define M4U_PORT_L28_CAM_DRZS4NO_R1 MTK_M4U_ID(28, 5) #define M4U_PORT_L28_CAM_TNCSO_R1 MTK_M4U_ID(28, 6) +/* Infra iommu ports */ +/* PCIe1: read: BIT16; write BIT17. */ +#define IOMMU_PORT_INFRA_PCIE1 MTK_IFAIOMMU_PERI_ID(16) +/* PCIe0: read: BIT18; write BIT19. */ +#define IOMMU_PORT_INFRA_PCIE0 MTK_IFAIOMMU_PERI_ID(18) +#define IOMMU_PORT_INFRA_SSUSB_P3_R MTK_IFAIOMMU_PERI_ID(20) +#define IOMMU_PORT_INFRA_SSUSB_P3_W MTK_IFAIOMMU_PERI_ID(21) +#define IOMMU_PORT_INFRA_SSUSB_P2_R MTK_IFAIOMMU_PERI_ID(22) +#define IOMMU_PORT_INFRA_SSUSB_P2_W MTK_IFAIOMMU_PERI_ID(23) +#define IOMMU_PORT_INFRA_SSUSB_P1_1_R MTK_IFAIOMMU_PERI_ID(24) +#define IOMMU_PORT_INFRA_SSUSB_P1_1_W MTK_IFAIOMMU_PERI_ID(25) +#define IOMMU_PORT_INFRA_SSUSB_P1_0_R MTK_IFAIOMMU_PERI_ID(26) +#define IOMMU_PORT_INFRA_SSUSB_P1_0_W MTK_IFAIOMMU_PERI_ID(27) +#define IOMMU_PORT_INFRA_SSUSB2_R MTK_IFAIOMMU_PERI_ID(28) +#define IOMMU_PORT_INFRA_SSUSB2_W MTK_IFAIOMMU_PERI_ID(29) +#define IOMMU_PORT_INFRA_SSUSB_R MTK_IFAIOMMU_PERI_ID(30) +#define IOMMU_PORT_INFRA_SSUSB_W MTK_IFAIOMMU_PERI_ID(31) + #endif diff --git a/include/dt-bindings/memory/mtk-memory-port.h b/include/dt-bindings/memory/mtk-memory-port.h index 7d64103209af..2f68a0511a25 100644 --- a/include/dt-bindings/memory/mtk-memory-port.h +++ b/include/dt-bindings/memory/mtk-memory-port.h @@ -12,4 +12,6 @@ #define MTK_M4U_TO_LARB(id) (((id) >> 5) & 0x1f) #define MTK_M4U_TO_PORT(id) ((id) & 0x1f) +#define MTK_IFAIOMMU_PERI_ID(port) MTK_M4U_ID(0, port) + #endif -- cgit v1.2.3 From 2d555a3844142b9e0f876925a8475cc830cd472a Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 3 May 2022 15:13:54 +0800 Subject: dt-bindings: mediatek: mt8186: Add binding for MM iommu Add mt8186 iommu binding. "-mm" means the iommu is for Multimedia. Signed-off-by: Yong Wu Acked-by: Krzysztof Kozlowski Reviewed-by: Rob Herring Reviewed-by: Matthias Brugger Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20220503071427.2285-4-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- include/dt-bindings/memory/mt8186-memory-port.h | 217 ++++++++++++++++++++++++ 1 file changed, 217 insertions(+) create mode 100644 include/dt-bindings/memory/mt8186-memory-port.h (limited to 'include') diff --git a/include/dt-bindings/memory/mt8186-memory-port.h b/include/dt-bindings/memory/mt8186-memory-port.h new file mode 100644 index 000000000000..2bc6e4433048 --- /dev/null +++ b/include/dt-bindings/memory/mt8186-memory-port.h @@ -0,0 +1,217 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2022 MediaTek Inc. + * + * Author: Anan Sun + * Author: Yong Wu + */ +#ifndef _DT_BINDINGS_MEMORY_MT8186_LARB_PORT_H_ +#define _DT_BINDINGS_MEMORY_MT8186_LARB_PORT_H_ + +#include + +/* + * MM IOMMU supports 16GB dma address. We separate it to four ranges: + * 0 ~ 4G; 4G ~ 8G; 8G ~ 12G; 12G ~ 16G, we could adjust these masters + * locate in anyone region. BUT: + * a) Make sure all the ports inside a larb are in one range. + * b) The iova of any master can NOT cross the 4G/8G/12G boundary. + * + * This is the suggested mapping in this SoC: + * + * modules dma-address-region larbs-ports + * disp 0 ~ 4G larb0/1/2 + * vcodec 4G ~ 8G larb4/7 + * cam/mdp 8G ~ 12G the other larbs. + * N/A 12G ~ 16G + * CCU0 0x24000_0000 ~ 0x243ff_ffff larb13: port 9/10 + * CCU1 0x24400_0000 ~ 0x247ff_ffff larb14: port 4/5 + */ + +/* MM IOMMU ports */ +/* LARB 0 -- MMSYS */ +#define IOMMU_PORT_L0_DISP_POSTMASK0 MTK_M4U_ID(0, 0) +#define IOMMU_PORT_L0_REVERSED MTK_M4U_ID(0, 1) +#define IOMMU_PORT_L0_OVL_RDMA0 MTK_M4U_ID(0, 2) +#define IOMMU_PORT_L0_DISP_FAKE0 MTK_M4U_ID(0, 3) + +/* LARB 1 -- MMSYS */ +#define IOMMU_PORT_L1_DISP_RDMA1 MTK_M4U_ID(1, 0) +#define IOMMU_PORT_L1_OVL_2L_RDMA0 MTK_M4U_ID(1, 1) +#define IOMMU_PORT_L1_DISP_RDMA0 MTK_M4U_ID(1, 2) +#define IOMMU_PORT_L1_DISP_WDMA0 MTK_M4U_ID(1, 3) +#define IOMMU_PORT_L1_DISP_FAKE1 MTK_M4U_ID(1, 4) + +/* LARB 2 -- MMSYS */ +#define IOMMU_PORT_L2_MDP_RDMA0 MTK_M4U_ID(2, 0) +#define IOMMU_PORT_L2_MDP_RDMA1 MTK_M4U_ID(2, 1) +#define IOMMU_PORT_L2_MDP_WROT0 MTK_M4U_ID(2, 2) +#define IOMMU_PORT_L2_MDP_WROT1 MTK_M4U_ID(2, 3) +#define IOMMU_PORT_L2_DISP_FAKE0 MTK_M4U_ID(2, 4) + +/* LARB 4 -- VDEC */ +#define IOMMU_PORT_L4_HW_VDEC_MC_EXT MTK_M4U_ID(4, 0) +#define IOMMU_PORT_L4_HW_VDEC_UFO_EXT MTK_M4U_ID(4, 1) +#define IOMMU_PORT_L4_HW_VDEC_PP_EXT MTK_M4U_ID(4, 2) +#define IOMMU_PORT_L4_HW_VDEC_PRED_RD_EXT MTK_M4U_ID(4, 3) +#define IOMMU_PORT_L4_HW_VDEC_PRED_WR_EXT MTK_M4U_ID(4, 4) +#define IOMMU_PORT_L4_HW_VDEC_PPWRAP_EXT MTK_M4U_ID(4, 5) +#define IOMMU_PORT_L4_HW_VDEC_TILE_EXT MTK_M4U_ID(4, 6) +#define IOMMU_PORT_L4_HW_VDEC_VLD_EXT MTK_M4U_ID(4, 7) +#define IOMMU_PORT_L4_HW_VDEC_VLD2_EXT MTK_M4U_ID(4, 8) +#define IOMMU_PORT_L4_HW_VDEC_AVC_MV_EXT MTK_M4U_ID(4, 9) +#define IOMMU_PORT_L4_HW_VDEC_UFO_ENC_EXT MTK_M4U_ID(4, 10) +#define IOMMU_PORT_L4_HW_VDEC_RG_CTRL_DMA_EXT MTK_M4U_ID(4, 11) +#define IOMMU_PORT_L4_HW_MINI_MDP_R0_EXT MTK_M4U_ID(4, 12) +#define IOMMU_PORT_L4_HW_MINI_MDP_W0_EXT MTK_M4U_ID(4, 13) + +/* LARB 7 -- VENC */ +#define IOMMU_PORT_L7_VENC_RCPU MTK_M4U_ID(7, 0) +#define IOMMU_PORT_L7_VENC_REC MTK_M4U_ID(7, 1) +#define IOMMU_PORT_L7_VENC_BSDMA MTK_M4U_ID(7, 2) +#define IOMMU_PORT_L7_VENC_SV_COMV MTK_M4U_ID(7, 3) +#define IOMMU_PORT_L7_VENC_RD_COMV MTK_M4U_ID(7, 4) +#define IOMMU_PORT_L7_VENC_CUR_LUMA MTK_M4U_ID(7, 5) +#define IOMMU_PORT_L7_VENC_CUR_CHROMA MTK_M4U_ID(7, 6) +#define IOMMU_PORT_L7_VENC_REF_LUMA MTK_M4U_ID(7, 7) +#define IOMMU_PORT_L7_VENC_REF_CHROMA MTK_M4U_ID(7, 8) +#define IOMMU_PORT_L7_JPGENC_Y_RDMA MTK_M4U_ID(7, 9) +#define IOMMU_PORT_L7_JPGENC_C_RDMA MTK_M4U_ID(7, 10) +#define IOMMU_PORT_L7_JPGENC_Q_TABLE MTK_M4U_ID(7, 11) +#define IOMMU_PORT_L7_JPGENC_BSDMA MTK_M4U_ID(7, 12) + +/* LARB 8 -- WPE */ +#define IOMMU_PORT_L8_WPE_RDMA_0 MTK_M4U_ID(8, 0) +#define IOMMU_PORT_L8_WPE_RDMA_1 MTK_M4U_ID(8, 1) +#define IOMMU_PORT_L8_WPE_WDMA_0 MTK_M4U_ID(8, 2) + +/* LARB 9 -- IMG-1 */ +#define IOMMU_PORT_L9_IMG_IMGI_D1 MTK_M4U_ID(9, 0) +#define IOMMU_PORT_L9_IMG_IMGBI_D1 MTK_M4U_ID(9, 1) +#define IOMMU_PORT_L9_IMG_DMGI_D1 MTK_M4U_ID(9, 2) +#define IOMMU_PORT_L9_IMG_DEPI_D1 MTK_M4U_ID(9, 3) +#define IOMMU_PORT_L9_IMG_LCE_D1 MTK_M4U_ID(9, 4) +#define IOMMU_PORT_L9_IMG_SMTI_D1 MTK_M4U_ID(9, 5) +#define IOMMU_PORT_L9_IMG_SMTO_D2 MTK_M4U_ID(9, 6) +#define IOMMU_PORT_L9_IMG_SMTO_D1 MTK_M4U_ID(9, 7) +#define IOMMU_PORT_L9_IMG_CRZO_D1 MTK_M4U_ID(9, 8) +#define IOMMU_PORT_L9_IMG_IMG3O_D1 MTK_M4U_ID(9, 9) +#define IOMMU_PORT_L9_IMG_VIPI_D1 MTK_M4U_ID(9, 10) +#define IOMMU_PORT_L9_IMG_SMTI_D5 MTK_M4U_ID(9, 11) +#define IOMMU_PORT_L9_IMG_TIMGO_D1 MTK_M4U_ID(9, 12) +#define IOMMU_PORT_L9_IMG_UFBC_W0 MTK_M4U_ID(9, 13) +#define IOMMU_PORT_L9_IMG_UFBC_R0 MTK_M4U_ID(9, 14) +#define IOMMU_PORT_L9_IMG_WPE_RDMA1 MTK_M4U_ID(9, 15) +#define IOMMU_PORT_L9_IMG_WPE_RDMA0 MTK_M4U_ID(9, 16) +#define IOMMU_PORT_L9_IMG_WPE_WDMA MTK_M4U_ID(9, 17) +#define IOMMU_PORT_L9_IMG_MFB_RDMA0 MTK_M4U_ID(9, 18) +#define IOMMU_PORT_L9_IMG_MFB_RDMA1 MTK_M4U_ID(9, 19) +#define IOMMU_PORT_L9_IMG_MFB_RDMA2 MTK_M4U_ID(9, 20) +#define IOMMU_PORT_L9_IMG_MFB_RDMA3 MTK_M4U_ID(9, 21) +#define IOMMU_PORT_L9_IMG_MFB_RDMA4 MTK_M4U_ID(9, 22) +#define IOMMU_PORT_L9_IMG_MFB_RDMA5 MTK_M4U_ID(9, 23) +#define IOMMU_PORT_L9_IMG_MFB_WDMA0 MTK_M4U_ID(9, 24) +#define IOMMU_PORT_L9_IMG_MFB_WDMA1 MTK_M4U_ID(9, 25) +#define IOMMU_PORT_L9_IMG_RESERVE6 MTK_M4U_ID(9, 26) +#define IOMMU_PORT_L9_IMG_RESERVE7 MTK_M4U_ID(9, 27) +#define IOMMU_PORT_L9_IMG_RESERVE8 MTK_M4U_ID(9, 28) + +/* LARB 11 -- IMG-2 */ +#define IOMMU_PORT_L11_IMG_IMGI_D1 MTK_M4U_ID(11, 0) +#define IOMMU_PORT_L11_IMG_IMGBI_D1 MTK_M4U_ID(11, 1) +#define IOMMU_PORT_L11_IMG_DMGI_D1 MTK_M4U_ID(11, 2) +#define IOMMU_PORT_L11_IMG_DEPI_D1 MTK_M4U_ID(11, 3) +#define IOMMU_PORT_L11_IMG_LCE_D1 MTK_M4U_ID(11, 4) +#define IOMMU_PORT_L11_IMG_SMTI_D1 MTK_M4U_ID(11, 5) +#define IOMMU_PORT_L11_IMG_SMTO_D2 MTK_M4U_ID(11, 6) +#define IOMMU_PORT_L11_IMG_SMTO_D1 MTK_M4U_ID(11, 7) +#define IOMMU_PORT_L11_IMG_CRZO_D1 MTK_M4U_ID(11, 8) +#define IOMMU_PORT_L11_IMG_IMG3O_D1 MTK_M4U_ID(11, 9) +#define IOMMU_PORT_L11_IMG_VIPI_D1 MTK_M4U_ID(11, 10) +#define IOMMU_PORT_L11_IMG_SMTI_D5 MTK_M4U_ID(11, 11) +#define IOMMU_PORT_L11_IMG_TIMGO_D1 MTK_M4U_ID(11, 12) +#define IOMMU_PORT_L11_IMG_UFBC_W0 MTK_M4U_ID(11, 13) +#define IOMMU_PORT_L11_IMG_UFBC_R0 MTK_M4U_ID(11, 14) +#define IOMMU_PORT_L11_IMG_WPE_RDMA1 MTK_M4U_ID(11, 15) +#define IOMMU_PORT_L11_IMG_WPE_RDMA0 MTK_M4U_ID(11, 16) +#define IOMMU_PORT_L11_IMG_WPE_WDMA MTK_M4U_ID(11, 17) +#define IOMMU_PORT_L11_IMG_MFB_RDMA0 MTK_M4U_ID(11, 18) +#define IOMMU_PORT_L11_IMG_MFB_RDMA1 MTK_M4U_ID(11, 19) +#define IOMMU_PORT_L11_IMG_MFB_RDMA2 MTK_M4U_ID(11, 20) +#define IOMMU_PORT_L11_IMG_MFB_RDMA3 MTK_M4U_ID(11, 21) +#define IOMMU_PORT_L11_IMG_MFB_RDMA4 MTK_M4U_ID(11, 22) +#define IOMMU_PORT_L11_IMG_MFB_RDMA5 MTK_M4U_ID(11, 23) +#define IOMMU_PORT_L11_IMG_MFB_WDMA0 MTK_M4U_ID(11, 24) +#define IOMMU_PORT_L11_IMG_MFB_WDMA1 MTK_M4U_ID(11, 25) +#define IOMMU_PORT_L11_IMG_RESERVE6 MTK_M4U_ID(11, 26) +#define IOMMU_PORT_L11_IMG_RESERVE7 MTK_M4U_ID(11, 27) +#define IOMMU_PORT_L11_IMG_RESERVE8 MTK_M4U_ID(11, 28) + +/* LARB 13 -- CAM */ +#define IOMMU_PORT_L13_CAM_MRAWI MTK_M4U_ID(13, 0) +#define IOMMU_PORT_L13_CAM_MRAWO_0 MTK_M4U_ID(13, 1) +#define IOMMU_PORT_L13_CAM_MRAWO_1 MTK_M4U_ID(13, 2) +#define IOMMU_PORT_L13_CAM_CAMSV_4 MTK_M4U_ID(13, 6) +#define IOMMU_PORT_L13_CAM_CAMSV_5 MTK_M4U_ID(13, 7) +#define IOMMU_PORT_L13_CAM_CAMSV_6 MTK_M4U_ID(13, 8) +#define IOMMU_PORT_L13_CAM_CCUI MTK_M4U_ID(13, 9) +#define IOMMU_PORT_L13_CAM_CCUO MTK_M4U_ID(13, 10) +#define IOMMU_PORT_L13_CAM_FAKE MTK_M4U_ID(13, 11) + +/* LARB 14 -- CAM */ +#define IOMMU_PORT_L14_CAM_CCUI MTK_M4U_ID(14, 4) +#define IOMMU_PORT_L14_CAM_CCUO MTK_M4U_ID(14, 5) + +/* LARB 16 -- RAW-A */ +#define IOMMU_PORT_L16_CAM_IMGO_R1_A MTK_M4U_ID(16, 0) +#define IOMMU_PORT_L16_CAM_RRZO_R1_A MTK_M4U_ID(16, 1) +#define IOMMU_PORT_L16_CAM_CQI_R1_A MTK_M4U_ID(16, 2) +#define IOMMU_PORT_L16_CAM_BPCI_R1_A MTK_M4U_ID(16, 3) +#define IOMMU_PORT_L16_CAM_YUVO_R1_A MTK_M4U_ID(16, 4) +#define IOMMU_PORT_L16_CAM_UFDI_R2_A MTK_M4U_ID(16, 5) +#define IOMMU_PORT_L16_CAM_RAWI_R2_A MTK_M4U_ID(16, 6) +#define IOMMU_PORT_L16_CAM_RAWI_R3_A MTK_M4U_ID(16, 7) +#define IOMMU_PORT_L16_CAM_AAO_R1_A MTK_M4U_ID(16, 8) +#define IOMMU_PORT_L16_CAM_AFO_R1_A MTK_M4U_ID(16, 9) +#define IOMMU_PORT_L16_CAM_FLKO_R1_A MTK_M4U_ID(16, 10) +#define IOMMU_PORT_L16_CAM_LCESO_R1_A MTK_M4U_ID(16, 11) +#define IOMMU_PORT_L16_CAM_CRZO_R1_A MTK_M4U_ID(16, 12) +#define IOMMU_PORT_L16_CAM_LTMSO_R1_A MTK_M4U_ID(16, 13) +#define IOMMU_PORT_L16_CAM_RSSO_R1_A MTK_M4U_ID(16, 14) +#define IOMMU_PORT_L16_CAM_AAHO_R1_A MTK_M4U_ID(16, 15) +#define IOMMU_PORT_L16_CAM_LSCI_R1_A MTK_M4U_ID(16, 16) + +/* LARB 17 -- RAW-B */ +#define IOMMU_PORT_L17_CAM_IMGO_R1_B MTK_M4U_ID(17, 0) +#define IOMMU_PORT_L17_CAM_RRZO_R1_B MTK_M4U_ID(17, 1) +#define IOMMU_PORT_L17_CAM_CQI_R1_B MTK_M4U_ID(17, 2) +#define IOMMU_PORT_L17_CAM_BPCI_R1_B MTK_M4U_ID(17, 3) +#define IOMMU_PORT_L17_CAM_YUVO_R1_B MTK_M4U_ID(17, 4) +#define IOMMU_PORT_L17_CAM_UFDI_R2_B MTK_M4U_ID(17, 5) +#define IOMMU_PORT_L17_CAM_RAWI_R2_B MTK_M4U_ID(17, 6) +#define IOMMU_PORT_L17_CAM_RAWI_R3_B MTK_M4U_ID(17, 7) +#define IOMMU_PORT_L17_CAM_AAO_R1_B MTK_M4U_ID(17, 8) +#define IOMMU_PORT_L17_CAM_AFO_R1_B MTK_M4U_ID(17, 9) +#define IOMMU_PORT_L17_CAM_FLKO_R1_B MTK_M4U_ID(17, 10) +#define IOMMU_PORT_L17_CAM_LCESO_R1_B MTK_M4U_ID(17, 11) +#define IOMMU_PORT_L17_CAM_CRZO_R1_B MTK_M4U_ID(17, 12) +#define IOMMU_PORT_L17_CAM_LTMSO_R1_B MTK_M4U_ID(17, 13) +#define IOMMU_PORT_L17_CAM_RSSO_R1_B MTK_M4U_ID(17, 14) +#define IOMMU_PORT_L17_CAM_AAHO_R1_B MTK_M4U_ID(17, 15) +#define IOMMU_PORT_L17_CAM_LSCI_R1_B MTK_M4U_ID(17, 16) + +/* LARB 19 -- IPE */ +#define IOMMU_PORT_L19_IPE_DVS_RDMA MTK_M4U_ID(19, 0) +#define IOMMU_PORT_L19_IPE_DVS_WDMA MTK_M4U_ID(19, 1) +#define IOMMU_PORT_L19_IPE_DVP_RDMA MTK_M4U_ID(19, 2) +#define IOMMU_PORT_L19_IPE_DVP_WDMA MTK_M4U_ID(19, 3) + +/* LARB 20 -- IPE */ +#define IOMMU_PORT_L20_IPE_FDVT_RDA MTK_M4U_ID(20, 0) +#define IOMMU_PORT_L20_IPE_FDVT_RDB MTK_M4U_ID(20, 1) +#define IOMMU_PORT_L20_IPE_FDVT_WRA MTK_M4U_ID(20, 2) +#define IOMMU_PORT_L20_IPE_FDVT_WRB MTK_M4U_ID(20, 3) +#define IOMMU_PORT_L20_IPE_RSC_RDMA0 MTK_M4U_ID(20, 4) +#define IOMMU_PORT_L20_IPE_RSC_WDMA MTK_M4U_ID(20, 5) + +#endif -- cgit v1.2.3 From 9b0df592522c6f86283679436f2eac49bd23cdce Mon Sep 17 00:00:00 2001 From: Alexandre Torgue Date: Fri, 22 Apr 2022 17:09:47 +0200 Subject: dt-bindings: clock: stm32mp15: rename CK_SCMI define As we only have one SCMI instance, it's not necessary to add an index to the name. Signed-off-by: Alexandre Torgue Acked-by: Rob Herring --- include/dt-bindings/clock/stm32mp1-clks.h | 46 ++++++++++++++----------------- 1 file changed, 21 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/clock/stm32mp1-clks.h b/include/dt-bindings/clock/stm32mp1-clks.h index e02770b98e6c..25e8cfd43459 100644 --- a/include/dt-bindings/clock/stm32mp1-clks.h +++ b/include/dt-bindings/clock/stm32mp1-clks.h @@ -249,30 +249,26 @@ #define STM32MP1_LAST_CLK 232 /* SCMI clock identifiers */ -#define CK_SCMI0_HSE 0 -#define CK_SCMI0_HSI 1 -#define CK_SCMI0_CSI 2 -#define CK_SCMI0_LSE 3 -#define CK_SCMI0_LSI 4 -#define CK_SCMI0_PLL2_Q 5 -#define CK_SCMI0_PLL2_R 6 -#define CK_SCMI0_MPU 7 -#define CK_SCMI0_AXI 8 -#define CK_SCMI0_BSEC 9 -#define CK_SCMI0_CRYP1 10 -#define CK_SCMI0_GPIOZ 11 -#define CK_SCMI0_HASH1 12 -#define CK_SCMI0_I2C4 13 -#define CK_SCMI0_I2C6 14 -#define CK_SCMI0_IWDG1 15 -#define CK_SCMI0_RNG1 16 -#define CK_SCMI0_RTC 17 -#define CK_SCMI0_RTCAPB 18 -#define CK_SCMI0_SPI6 19 -#define CK_SCMI0_USART1 20 - -#define CK_SCMI1_PLL3_Q 0 -#define CK_SCMI1_PLL3_R 1 -#define CK_SCMI1_MCU 2 +#define CK_SCMI_HSE 0 +#define CK_SCMI_HSI 1 +#define CK_SCMI_CSI 2 +#define CK_SCMI_LSE 3 +#define CK_SCMI_LSI 4 +#define CK_SCMI_PLL2_Q 5 +#define CK_SCMI_PLL2_R 6 +#define CK_SCMI_MPU 7 +#define CK_SCMI_AXI 8 +#define CK_SCMI_BSEC 9 +#define CK_SCMI_CRYP1 10 +#define CK_SCMI_GPIOZ 11 +#define CK_SCMI_HASH1 12 +#define CK_SCMI_I2C4 13 +#define CK_SCMI_I2C6 14 +#define CK_SCMI_IWDG1 15 +#define CK_SCMI_RNG1 16 +#define CK_SCMI_RTC 17 +#define CK_SCMI_RTCAPB 18 +#define CK_SCMI_SPI6 19 +#define CK_SCMI_USART1 20 #endif /* _DT_BINDINGS_STM32MP1_CLKS_H_ */ -- cgit v1.2.3 From 5f5d7decf046557876794c5686ee0ccf5907bfde Mon Sep 17 00:00:00 2001 From: Alexandre Torgue Date: Fri, 22 Apr 2022 17:09:48 +0200 Subject: dt-bindings: reset: stm32mp15: rename RST_SCMI define As we only have one SCMI instance, it's not necessary to add an index to the name. Signed-off-by: Alexandre Torgue Acked-by: Rob Herring --- include/dt-bindings/reset/stm32mp1-resets.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/reset/stm32mp1-resets.h b/include/dt-bindings/reset/stm32mp1-resets.h index f3a0ed317835..4ffa7c3612e6 100644 --- a/include/dt-bindings/reset/stm32mp1-resets.h +++ b/include/dt-bindings/reset/stm32mp1-resets.h @@ -107,17 +107,17 @@ #define GPIOK_R 19786 /* SCMI reset domain identifiers */ -#define RST_SCMI0_SPI6 0 -#define RST_SCMI0_I2C4 1 -#define RST_SCMI0_I2C6 2 -#define RST_SCMI0_USART1 3 -#define RST_SCMI0_STGEN 4 -#define RST_SCMI0_GPIOZ 5 -#define RST_SCMI0_CRYP1 6 -#define RST_SCMI0_HASH1 7 -#define RST_SCMI0_RNG1 8 -#define RST_SCMI0_MDMA 9 -#define RST_SCMI0_MCU 10 -#define RST_SCMI0_MCU_HOLD_BOOT 11 +#define RST_SCMI_SPI6 0 +#define RST_SCMI_I2C4 1 +#define RST_SCMI_I2C6 2 +#define RST_SCMI_USART1 3 +#define RST_SCMI_STGEN 4 +#define RST_SCMI_GPIOZ 5 +#define RST_SCMI_CRYP1 6 +#define RST_SCMI_HASH1 7 +#define RST_SCMI_RNG1 8 +#define RST_SCMI_MDMA 9 +#define RST_SCMI_MCU 10 +#define RST_SCMI_MCU_HOLD_BOOT 11 #endif /* _DT_BINDINGS_STM32MP1_RESET_H_ */ -- cgit v1.2.3 From 31ab09b4218879bc394c9faa6da983a82a694600 Mon Sep 17 00:00:00 2001 From: Dipen Patel Date: Fri, 22 Apr 2022 13:52:13 -0700 Subject: drivers: Add hardware timestamp engine (HTE) subsystem Some devices can timestamp system lines/signals/Buses in real-time using the hardware counter or other hardware means which can give finer granularity and help avoid jitter introduced by software timestamping. To utilize such functionality, this patchset creates HTE subsystem where devices can register themselves as providers so that the consumers devices can request specific line from the providers. The patch also adds compilation support in Makefile and menu options in Kconfig. The provider does following: - Registers chip with the framework. - Provides translation hook to convert logical line id. - Provides enable/disable, request/release callbacks. - Pushes timestamp data to HTE subsystem. The consumer does following: - Initializes line attribute. - Gets HTE timestamp descriptor. - Requests timestamp functionality. - Puts HTE timestamp descriptor. Signed-off-by: Dipen Patel Reported-by: kernel test robot Signed-off-by: Thierry Reding --- include/linux/hte.h | 271 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 271 insertions(+) create mode 100644 include/linux/hte.h (limited to 'include') diff --git a/include/linux/hte.h b/include/linux/hte.h new file mode 100644 index 000000000000..8289055061ab --- /dev/null +++ b/include/linux/hte.h @@ -0,0 +1,271 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __LINUX_HTE_H +#define __LINUX_HTE_H + +#include + +struct hte_chip; +struct hte_device; +struct of_phandle_args; + +/** + * enum hte_edge - HTE line edge flags. + * + * @HTE_EDGE_NO_SETUP: No edge setup. In this case consumer will setup edges, + * for example during request irq call. + * @HTE_RISING_EDGE_TS: Rising edge. + * @HTE_FALLING_EDGE_TS: Falling edge. + * + */ +enum hte_edge { + HTE_EDGE_NO_SETUP = 1U << 0, + HTE_RISING_EDGE_TS = 1U << 1, + HTE_FALLING_EDGE_TS = 1U << 2, +}; + +/** + * enum hte_return - HTE subsystem return values used during callback. + * + * @HTE_CB_HANDLED: The consumer handled the data. + * @HTE_RUN_SECOND_CB: The consumer needs further processing, in that case + * HTE subsystem calls secondary callback provided by the consumer where it + * is allowed to sleep. + */ +enum hte_return { + HTE_CB_HANDLED, + HTE_RUN_SECOND_CB, +}; + +/** + * struct hte_ts_data - HTE timestamp data. + * + * @tsc: Timestamp value. + * @seq: Sequence counter of the timestamps. + * @raw_level: Level of the line at the timestamp if provider supports it, + * -1 otherwise. + */ +struct hte_ts_data { + u64 tsc; + u64 seq; + int raw_level; +}; + +/** + * struct hte_clk_info - Clock source info that HTE provider uses to timestamp. + * + * @hz: Supported clock rate in HZ, for example 1KHz clock = 1000. + * @type: Supported clock type. + */ +struct hte_clk_info { + u64 hz; + clockid_t type; +}; + +/** + * typedef hte_ts_cb_t - HTE timestamp data processing primary callback. + * + * The callback is used to push timestamp data to the client and it is + * not allowed to sleep. + * + * @ts: HW timestamp data. + * @data: Client supplied data. + */ +typedef enum hte_return (*hte_ts_cb_t)(struct hte_ts_data *ts, void *data); + +/** + * typedef hte_ts_sec_cb_t - HTE timestamp data processing secondary callback. + * + * This is used when the client needs further processing where it is + * allowed to sleep. + * + * @data: Client supplied data. + * + */ +typedef enum hte_return (*hte_ts_sec_cb_t)(void *data); + +/** + * struct hte_line_attr - Line attributes. + * + * @line_id: The logical ID understood by the consumers and providers. + * @line_data: Line data related to line_id. + * @edge_flags: Edge setup flags. + * @name: Descriptive name of the entity that is being monitored for the + * hardware timestamping. If null, HTE core will construct the name. + * + */ +struct hte_line_attr { + u32 line_id; + void *line_data; + unsigned long edge_flags; + const char *name; +}; + +/** + * struct hte_ts_desc - HTE timestamp descriptor. + * + * This structure is a communication token between consumers to subsystem + * and subsystem to providers. + * + * @attr: The line attributes. + * @hte_data: Subsystem's private data, set by HTE subsystem. + */ +struct hte_ts_desc { + struct hte_line_attr attr; + void *hte_data; +}; + +/** + * struct hte_ops - HTE operations set by providers. + * + * @request: Hook for requesting a HTE timestamp. Returns 0 on success, + * non-zero for failures. + * @release: Hook for releasing a HTE timestamp. Returns 0 on success, + * non-zero for failures. + * @enable: Hook to enable the specified timestamp. Returns 0 on success, + * non-zero for failures. + * @disable: Hook to disable specified timestamp. Returns 0 on success, + * non-zero for failures. + * @get_clk_src_info: Hook to get the clock information the provider uses + * to timestamp. Returns 0 for success and negative error code for failure. On + * success HTE subsystem fills up provided struct hte_clk_info. + * + * xlated_id parameter is used to communicate between HTE subsystem and the + * providers and is translated by the provider. + */ +struct hte_ops { + int (*request)(struct hte_chip *chip, struct hte_ts_desc *desc, + u32 xlated_id); + int (*release)(struct hte_chip *chip, struct hte_ts_desc *desc, + u32 xlated_id); + int (*enable)(struct hte_chip *chip, u32 xlated_id); + int (*disable)(struct hte_chip *chip, u32 xlated_id); + int (*get_clk_src_info)(struct hte_chip *chip, + struct hte_clk_info *ci); +}; + +/** + * struct hte_chip - Abstract HTE chip. + * + * @name: functional name of the HTE IP block. + * @dev: device providing the HTE. + * @ops: callbacks for this HTE. + * @nlines: number of lines/signals supported by this chip. + * @xlate_of: Callback which translates consumer supplied logical ids to + * physical ids, return 0 for the success and negative for the failures. + * It stores (between 0 to @nlines) in xlated_id parameter for the success. + * @xlate_plat: Same as above but for the consumers with no DT node. + * @match_from_linedata: Match HTE device using the line_data. + * @of_hte_n_cells: Number of cells used to form the HTE specifier. + * @gdev: HTE subsystem abstract device, internal to the HTE subsystem. + * @data: chip specific private data. + */ +struct hte_chip { + const char *name; + struct device *dev; + const struct hte_ops *ops; + u32 nlines; + int (*xlate_of)(struct hte_chip *gc, + const struct of_phandle_args *args, + struct hte_ts_desc *desc, u32 *xlated_id); + int (*xlate_plat)(struct hte_chip *gc, struct hte_ts_desc *desc, + u32 *xlated_id); + bool (*match_from_linedata)(const struct hte_chip *chip, + const struct hte_ts_desc *hdesc); + u8 of_hte_n_cells; + + struct hte_device *gdev; + void *data; +}; + +#if IS_ENABLED(CONFIG_HTE) +/* HTE APIs for the providers */ +int devm_hte_register_chip(struct hte_chip *chip); +int hte_push_ts_ns(const struct hte_chip *chip, u32 xlated_id, + struct hte_ts_data *data); + +/* HTE APIs for the consumers */ +int hte_init_line_attr(struct hte_ts_desc *desc, u32 line_id, + unsigned long edge_flags, const char *name, + void *data); +int hte_ts_get(struct device *dev, struct hte_ts_desc *desc, int index); +int hte_ts_put(struct hte_ts_desc *desc); +int hte_request_ts_ns(struct hte_ts_desc *desc, hte_ts_cb_t cb, + hte_ts_sec_cb_t tcb, void *data); +int devm_hte_request_ts_ns(struct device *dev, struct hte_ts_desc *desc, + hte_ts_cb_t cb, hte_ts_sec_cb_t tcb, void *data); +int of_hte_req_count(struct device *dev); +int hte_enable_ts(struct hte_ts_desc *desc); +int hte_disable_ts(struct hte_ts_desc *desc); +int hte_get_clk_src_info(const struct hte_ts_desc *desc, + struct hte_clk_info *ci); + +#else /* !CONFIG_HTE */ +static inline int devm_hte_register_chip(struct hte_chip *chip) +{ + return -EOPNOTSUPP; +} + +static inline int hte_push_ts_ns(const struct hte_chip *chip, + u32 xlated_id, + const struct hte_ts_data *data) +{ + return -EOPNOTSUPP; +} + +static inline int hte_init_line_attr(struct hte_ts_desc *desc, u32 line_id, + unsigned long edge_flags, + const char *name, void *data) +{ + return -EOPNOTSUPP; +} + +static inline int hte_ts_get(struct device *dev, struct hte_ts_desc *desc, + int index) +{ + return -EOPNOTSUPP; +} + +static inline int hte_ts_put(struct hte_ts_desc *desc) +{ + return -EOPNOTSUPP; +} + +static inline int hte_request_ts_ns(struct hte_ts_desc *desc, hte_ts_cb_t cb, + hte_ts_sec_cb_t tcb, void *data) +{ + return -EOPNOTSUPP; +} + +static inline int devm_hte_request_ts_ns(struct device *dev, + struct hte_ts_desc *desc, + hte_ts_cb_t cb, + hte_ts_sec_cb_t tcb, + void *data) +{ + return -EOPNOTSUPP; +} + +static inline int of_hte_req_count(struct device *dev) +{ + return -EOPNOTSUPP; +} + +static inline int hte_enable_ts(struct hte_ts_desc *desc) +{ + return -EOPNOTSUPP; +} + +static inline int hte_disable_ts(struct hte_ts_desc *desc) +{ + return -EOPNOTSUPP; +} + +static inline int hte_get_clk_src_info(const struct hte_ts_desc *desc, + struct hte_clk_info *ci) +{ + return -EOPNOTSUPP; +} +#endif /* !CONFIG_HTE */ + +#endif -- cgit v1.2.3 From 42112dd77b74220e6a1f4a71bb51ca3f583d3842 Mon Sep 17 00:00:00 2001 From: Dipen Patel Date: Fri, 22 Apr 2022 13:52:16 -0700 Subject: gpiolib: Add HTE support Some GPIO chip can provide hardware timestamp support on its GPIO lines , in order to support that, additional API needs to be added which can talk to both GPIO chip and HTE (hardware timestamping engine) providers if there is any dependencies. This patch introduces optional hooks to enable and disable hardware timestamping related features in the GPIO controller chip. Signed-off-by: Dipen Patel Reviewed-by: Linus Walleij Reported-by: kernel test robot Signed-off-by: Thierry Reding --- include/linux/gpio/consumer.h | 16 ++++++++++++++-- include/linux/gpio/driver.h | 10 ++++++++++ 2 files changed, 24 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index c3aa8b330e1c..7eaec081ae6c 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -109,6 +109,8 @@ int gpiod_get_direction(struct gpio_desc *desc); int gpiod_direction_input(struct gpio_desc *desc); int gpiod_direction_output(struct gpio_desc *desc, int value); int gpiod_direction_output_raw(struct gpio_desc *desc, int value); +int gpiod_enable_hw_timestamp_ns(struct gpio_desc *desc, unsigned long flags); +int gpiod_disable_hw_timestamp_ns(struct gpio_desc *desc, unsigned long flags); /* Value get/set from non-sleeping context */ int gpiod_get_value(const struct gpio_desc *desc); @@ -350,8 +352,18 @@ static inline int gpiod_direction_output_raw(struct gpio_desc *desc, int value) WARN_ON(desc); return -ENOSYS; } - - +static inline int gpiod_enable_hw_timestamp_ns(struct gpio_desc *desc, + unsigned long flags) +{ + WARN_ON(desc); + return -ENOSYS; +} +static inline int gpiod_disable_hw_timestamp_ns(struct gpio_desc *desc, + unsigned long flags) +{ + WARN_ON(desc); + return -ENOSYS; +} static inline int gpiod_get_value(const struct gpio_desc *desc) { /* GPIO can never have been requested */ diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 98c93510640e..0ce96ebdaa36 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -323,6 +323,10 @@ struct gpio_irq_chip { * @add_pin_ranges: optional routine to initialize pin ranges, to be used when * requires special mapping of the pins that provides GPIO functionality. * It is called after adding GPIO chip and before adding IRQ chip. + * @en_hw_timestamp: Dependent on GPIO chip, an optional routine to + * enable hardware timestamp. + * @dis_hw_timestamp: Dependent on GPIO chip, an optional routine to + * disable hardware timestamp. * @base: identifies the first GPIO number handled by this chip; * or, if negative during registration, requests dynamic ID allocation. * DEPRECATION: providing anything non-negative and nailing the base @@ -419,6 +423,12 @@ struct gpio_chip { int (*add_pin_ranges)(struct gpio_chip *gc); + int (*en_hw_timestamp)(struct gpio_chip *gc, + u32 offset, + unsigned long flags); + int (*dis_hw_timestamp)(struct gpio_chip *gc, + u32 offset, + unsigned long flags); int base; u16 ngpio; u16 offset; -- cgit v1.2.3 From 2068339a6c35147847ba433fd0da67b313779059 Mon Sep 17 00:00:00 2001 From: Dipen Patel Date: Fri, 22 Apr 2022 13:52:18 -0700 Subject: gpiolib: cdev: Add hardware timestamp clock type This patch adds new clock type for the GPIO controller which can timestamp gpio lines in using hardware means. To expose such functionalities to the userspace, code has been added where during line create or set config API calls, it checks for new clock type and if requested, calls HTE API. During line change event, the HTE subsystem pushes timestamp data to userspace through gpiolib-cdev. Signed-off-by: Dipen Patel Acked-by: Linus Walleij Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Thierry Reding --- include/uapi/linux/gpio.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index eaaea3d8e6b4..cb9966d49a16 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -66,6 +66,8 @@ struct gpiochip_info { * @GPIO_V2_LINE_FLAG_BIAS_PULL_DOWN: line has pull-down bias enabled * @GPIO_V2_LINE_FLAG_BIAS_DISABLED: line has bias disabled * @GPIO_V2_LINE_FLAG_EVENT_CLOCK_REALTIME: line events contain REALTIME timestamps + * @GPIO_V2_LINE_FLAG_EVENT_CLOCK_HTE: line events contain timestamps from + * hardware timestamp engine */ enum gpio_v2_line_flag { GPIO_V2_LINE_FLAG_USED = _BITULL(0), @@ -80,6 +82,7 @@ enum gpio_v2_line_flag { GPIO_V2_LINE_FLAG_BIAS_PULL_DOWN = _BITULL(9), GPIO_V2_LINE_FLAG_BIAS_DISABLED = _BITULL(10), GPIO_V2_LINE_FLAG_EVENT_CLOCK_REALTIME = _BITULL(11), + GPIO_V2_LINE_FLAG_EVENT_CLOCK_HTE = _BITULL(12), }; /** -- cgit v1.2.3 From 9ab4807c84a4aacfc9b4f79cc81254035e0ec361 Mon Sep 17 00:00:00 2001 From: Kishen Maloor Date: Tue, 3 May 2022 19:38:52 -0700 Subject: mptcp: netlink: Add MPTCP_PM_CMD_ANNOUNCE This change adds a MPTCP netlink interface for issuing ADD_ADDR advertisements over the chosen MPTCP connection from a userspace path manager. The command requires the following parameters: { token, { loc_id, family, daddr4 | daddr6 [, dport] } [, if_idx], flags[signal] }. Acked-by: Paolo Abeni Signed-off-by: Kishen Maloor Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/uapi/linux/mptcp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index e41ea01a94bb..ac66c1263f02 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -55,6 +55,7 @@ enum { MPTCP_PM_ATTR_ADDR, /* nested address */ MPTCP_PM_ATTR_RCV_ADD_ADDRS, /* u32 */ MPTCP_PM_ATTR_SUBFLOWS, /* u32 */ + MPTCP_PM_ATTR_TOKEN, /* u32 */ __MPTCP_PM_ATTR_MAX }; @@ -93,6 +94,7 @@ enum { MPTCP_PM_CMD_SET_LIMITS, MPTCP_PM_CMD_GET_LIMITS, MPTCP_PM_CMD_SET_FLAGS, + MPTCP_PM_CMD_ANNOUNCE, __MPTCP_PM_CMD_AFTER_LAST }; -- cgit v1.2.3 From d9a4594edabf125dc17dfd52acc722c3de1cb44c Mon Sep 17 00:00:00 2001 From: Kishen Maloor Date: Tue, 3 May 2022 19:38:54 -0700 Subject: mptcp: netlink: Add MPTCP_PM_CMD_REMOVE This change adds a MPTCP netlink command for issuing a REMOVE_ADDR signal for an address over the chosen MPTCP connection from a userspace path manager. The command requires the following parameters: {token, loc_id}. Acked-by: Paolo Abeni Signed-off-by: Kishen Maloor Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/uapi/linux/mptcp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index ac66c1263f02..11f9fa001a3c 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -56,6 +56,7 @@ enum { MPTCP_PM_ATTR_RCV_ADD_ADDRS, /* u32 */ MPTCP_PM_ATTR_SUBFLOWS, /* u32 */ MPTCP_PM_ATTR_TOKEN, /* u32 */ + MPTCP_PM_ATTR_LOC_ID, /* u8 */ __MPTCP_PM_ATTR_MAX }; @@ -95,6 +96,7 @@ enum { MPTCP_PM_CMD_GET_LIMITS, MPTCP_PM_CMD_SET_FLAGS, MPTCP_PM_CMD_ANNOUNCE, + MPTCP_PM_CMD_REMOVE, __MPTCP_PM_CMD_AFTER_LAST }; -- cgit v1.2.3 From 702c2f646d42cfd9e31133d68a8283fea48fd810 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 3 May 2022 19:38:56 -0700 Subject: mptcp: netlink: allow userspace-driven subflow establishment This allows userspace to tell kernel to add a new subflow to an existing mptcp connection. Userspace provides the token to identify the mptcp-level connection that needs a change in active subflows and the local and remote addresses of the new or the to-be-removed subflow. MPTCP_PM_CMD_SUBFLOW_CREATE requires the following parameters: { token, { loc_id, family, loc_addr4 | loc_addr6 }, { family, rem_addr4 | rem_addr6, rem_port } MPTCP_PM_CMD_SUBFLOW_DESTROY requires the following parameters: { token, { family, loc_addr4 | loc_addr6, loc_port }, { family, rem_addr4 | rem_addr6, rem_port } Acked-by: Paolo Abeni Co-developed-by: Kishen Maloor Signed-off-by: Kishen Maloor Signed-off-by: Florian Westphal Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/uapi/linux/mptcp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 11f9fa001a3c..921963589904 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -57,6 +57,7 @@ enum { MPTCP_PM_ATTR_SUBFLOWS, /* u32 */ MPTCP_PM_ATTR_TOKEN, /* u32 */ MPTCP_PM_ATTR_LOC_ID, /* u8 */ + MPTCP_PM_ATTR_ADDR_REMOTE, /* nested address */ __MPTCP_PM_ATTR_MAX }; @@ -97,6 +98,8 @@ enum { MPTCP_PM_CMD_SET_FLAGS, MPTCP_PM_CMD_ANNOUNCE, MPTCP_PM_CMD_REMOVE, + MPTCP_PM_CMD_SUBFLOW_CREATE, + MPTCP_PM_CMD_SUBFLOW_DESTROY, __MPTCP_PM_CMD_AFTER_LAST }; -- cgit v1.2.3 From 3ae2722c93c916b47bfe47a4326e88cc4abb9bf4 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 27 Apr 2022 14:55:57 +0200 Subject: mmc: mmci: Remove custom ios handler The custom boardfile ios handler isn't used anywhere in the kernel. Delete it. Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20220427125557.1608825-1-linus.walleij@linaro.org Signed-off-by: Ulf Hansson --- include/linux/amba/mmci.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/amba/mmci.h b/include/linux/amba/mmci.h index c92ebc39fc1f..6f96dc2209c0 100644 --- a/include/linux/amba/mmci.h +++ b/include/linux/amba/mmci.h @@ -13,17 +13,11 @@ * @ocr_mask: available voltages on the 4 pins from the block, this * is ignored if a regulator is used, see the MMC_VDD_* masks in * mmc/host.h - * @ios_handler: a callback function to act on specfic ios changes, - * used for example to control a levelshifter - * mask into a value to be binary (or set some other custom bits - * in MMCIPWR) or:ed and written into the MMCIPWR register of the - * block. May also control external power based on the power_mode. * @status: if no GPIO line was given to the block in this function will * be called to determine whether a card is present in the MMC slot or not */ struct mmci_platform_data { unsigned int ocr_mask; - int (*ios_handler)(struct device *, struct mmc_ios *); unsigned int (*status)(struct device *); }; -- cgit v1.2.3 From 00ce3873f730fb24c657854ec04374358e711838 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 4 May 2022 10:17:32 +0200 Subject: opp: Add apis to retrieve opps with interconnect bandwidth Add dev_pm_opp_find_bw_ceil and dev_pm_opp_find_bw_floor to retrieve opps based on interconnect associated with the opp and bandwidth. The index variable is the index of the interconnect as specified in the opp table in Devicetree. Co-developed-by: Thara Gopinath Signed-off-by: Thara Gopinath Signed-off-by: Krzysztof Kozlowski Signed-off-by: Viresh Kumar --- include/linux/pm_opp.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 0d85a63a1f78..dcea178868c9 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -129,6 +129,13 @@ struct dev_pm_opp *dev_pm_opp_find_freq_ceil_by_volt(struct device *dev, struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev, unsigned long *freq); + +struct dev_pm_opp *dev_pm_opp_find_bw_ceil(struct device *dev, + unsigned int *bw, int index); + +struct dev_pm_opp *dev_pm_opp_find_bw_floor(struct device *dev, + unsigned int *bw, int index); + void dev_pm_opp_put(struct dev_pm_opp *opp); int dev_pm_opp_add(struct device *dev, unsigned long freq, @@ -279,6 +286,18 @@ static inline struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev, return ERR_PTR(-EOPNOTSUPP); } +static inline struct dev_pm_opp *dev_pm_opp_find_bw_ceil(struct device *dev, + unsigned int *bw, int index) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline struct dev_pm_opp *dev_pm_opp_find_bw_floor(struct device *dev, + unsigned int *bw, int index) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline void dev_pm_opp_put(struct dev_pm_opp *opp) {} static inline int dev_pm_opp_add(struct device *dev, unsigned long freq, -- cgit v1.2.3 From 22079af7df5a5dfef1c4d160abfd43035211759e Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 4 May 2022 15:40:22 +0530 Subject: opp: Reorder definition of ceil/floor helpers Reorder the helpers to keep all freq specific ones, followed by level and bw. No functional change. Signed-off-by: Viresh Kumar --- include/linux/pm_opp.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index dcea178868c9..6708b4ec244d 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -117,16 +117,16 @@ unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev); struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq, bool available); -struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev, - unsigned int level); -struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev, - unsigned int *level); - struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, unsigned long *freq); struct dev_pm_opp *dev_pm_opp_find_freq_ceil_by_volt(struct device *dev, unsigned long u_volt); +struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev, + unsigned int level); +struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev, + unsigned int *level); + struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev, unsigned long *freq); @@ -250,12 +250,6 @@ static inline unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev) return 0; } -static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, - unsigned long freq, bool available) -{ - return ERR_PTR(-EOPNOTSUPP); -} - static inline struct dev_pm_opp *dev_pm_opp_find_level_exact(struct device *dev, unsigned int level) { @@ -268,6 +262,12 @@ static inline struct dev_pm_opp *dev_pm_opp_find_level_ceil(struct device *dev, return ERR_PTR(-EOPNOTSUPP); } +static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, + unsigned long freq, bool available) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, unsigned long *freq) { -- cgit v1.2.3 From 34c9a0e71cbb316f360919353273b185c2780cd7 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 12 Apr 2022 22:09:59 +0200 Subject: cfg80211: remove cfg80211_get_chan_state() We haven't used this function for years, since commit c781944b71f8 ("cfg80211: Remove unused cfg80211_can_use_iftype_chan()") which itself removed a function unused since commit 97dc94f1d933 ("cfg80211: remove channel_switch combination check"), almost eight years ago. Also remove the now unused enum cfg80211_chan_mode and some struct members that were only used for this function. Link: https://lore.kernel.org/r/20220412220958.1a191dca19d7.Ide4448f02d0e2f1ca2992971421ffc1933a5370a@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 68713388b617..cd1212113901 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5549,8 +5549,6 @@ static inline void wiphy_unlock(struct wiphy *wiphy) * @conn_owner_nlportid: (private) connection owner socket port ID * @disconnect_wk: (private) auto-disconnect work * @disconnect_bssid: (private) the BSSID to use for auto-disconnect - * @ibss_fixed: (private) IBSS is using fixed BSSID - * @ibss_dfs_possible: (private) IBSS may change to a DFS channel * @event_list: (private) list for internal event processing * @event_lock: (private) lock for event list * @owner_nlportid: (private) owner socket port ID @@ -5599,9 +5597,6 @@ struct wireless_dev { struct cfg80211_chan_def preset_chandef; struct cfg80211_chan_def chandef; - bool ibss_fixed; - bool ibss_dfs_possible; - bool ps; int ps_timeout; -- cgit v1.2.3 From 604be85547ce4d61b89292d2f9a78c721b778c16 Mon Sep 17 00:00:00 2001 From: Andy Yan Date: Fri, 22 Apr 2022 09:28:39 +0200 Subject: drm/rockchip: Add VOP2 driver The VOP2 unit is found on Rockchip SoCs beginning with rk3566/rk3568. It replaces the VOP unit found in the older Rockchip SoCs. This driver has been derived from the downstream Rockchip Kernel and heavily modified: - All nonstandard DRM properties have been removed - dropped struct vop2_plane_state and pass around less data between functions - Dropped all DRM_FORMAT_* not known on upstream - rework register access to get rid of excessively used macros - Drop all waiting for framesyncs The driver is tested with HDMI and MIPI-DSI display on a RK3568-EVB board. Overlay support is tested with the modetest utility. AFBC support on the cluster windows is tested with weston-simple-dmabuf-egl on weston using the (yet to be upstreamed) panfrost driver support. Signed-off-by: Andy Yan Co-Developed-by: Sascha Hauer Signed-off-by: Sascha Hauer Tested-by: Michael Riesch [dt-binding-header:] Acked-by: Rob Herring [moved dt-binding header from dt-nodes patch to here and made checkpatch --strict happier] Signed-off-by: Heiko Stuebner Link: https://patchwork.freedesktop.org/patch/msgid/20220422072841.2206452-23-s.hauer@pengutronix.de --- include/dt-bindings/soc/rockchip,vop2.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 include/dt-bindings/soc/rockchip,vop2.h (limited to 'include') diff --git a/include/dt-bindings/soc/rockchip,vop2.h b/include/dt-bindings/soc/rockchip,vop2.h new file mode 100644 index 000000000000..6e66a802b96a --- /dev/null +++ b/include/dt-bindings/soc/rockchip,vop2.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause */ + +#ifndef __DT_BINDINGS_ROCKCHIP_VOP2_H +#define __DT_BINDINGS_ROCKCHIP_VOP2_H + +#define ROCKCHIP_VOP2_EP_RGB0 1 +#define ROCKCHIP_VOP2_EP_HDMI0 2 +#define ROCKCHIP_VOP2_EP_EDP0 3 +#define ROCKCHIP_VOP2_EP_MIPI0 4 +#define ROCKCHIP_VOP2_EP_LVDS0 5 +#define ROCKCHIP_VOP2_EP_MIPI1 6 +#define ROCKCHIP_VOP2_EP_LVDS1 7 + +#endif /* __DT_BINDINGS_ROCKCHIP_VOP2_H */ -- cgit v1.2.3 From 34453c2e9f799d02f5f379519495208bbd96a935 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 5 Apr 2022 19:23:24 +0100 Subject: irqchip/gic-v3: Exposes bit values for GICR_CTLR.{IR, CES} As we're about to expose GICR_CTLR.{IR,CES} to guests, populate the include file with the architectural values. Signed-off-by: Marc Zyngier Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20220405182327.205520-2-maz@kernel.org --- include/linux/irqchip/arm-gic-v3.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 12d91f0dedf9..728691365464 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -127,6 +127,8 @@ #define GICR_PIDR2 GICD_PIDR2 #define GICR_CTLR_ENABLE_LPIS (1UL << 0) +#define GICR_CTLR_CES (1UL << 1) +#define GICR_CTLR_IR (1UL << 2) #define GICR_CTLR_RWP (1UL << 3) #define GICR_TYPER_CPU_NUMBER(r) (((r) >> 8) & 0xffff) -- cgit v1.2.3 From 94828468a6085e6ae148986d300b634b87f86516 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 5 Apr 2022 19:23:25 +0100 Subject: KVM: arm64: vgic-v3: Expose GICR_CTLR.RWP when disabling LPIs When disabling LPIs, a guest needs to poll GICR_CTLR.RWP in order to be sure that the write has taken effect. We so far reported it as 0, as we didn't advertise that LPIs could be turned off the first place. Start tracking this state during which LPIs are being disabled, and expose the 'in progress' state via the RWP bit. We also take this opportunity to disallow enabling LPIs and programming GICR_{PEND,PROP}BASER while LPI disabling is in progress, as allowed by the architecture (UNPRED behaviour). We don't advertise the feature to the guest yet (which is allowed by the architecture). Reviewed-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220405182327.205520-3-maz@kernel.org --- include/kvm/arm_vgic.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index bb30a6803d9f..fdf1c2c322e5 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -347,8 +347,8 @@ struct vgic_cpu { /* Contains the attributes and gpa of the LPI pending tables. */ u64 pendbaser; - - bool lpis_enabled; + /* GICR_CTLR.{ENABLE_LPIS,RWP} */ + atomic_t ctlr; /* Cache guest priority bits */ u32 num_pri_bits; -- cgit v1.2.3 From 4645d11f4a5538ec1221f36e397cfb0115718ffe Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 5 Apr 2022 19:23:26 +0100 Subject: KVM: arm64: vgic-v3: Implement MMIO-based LPI invalidation Since GICv4.1, it has become legal for an implementation to advertise GICR_{INVLPIR,INVALLR,SYNCR} while having an ITS, allowing for a more efficient invalidation scheme (no guest command queue contention when multiple CPUs are generating invalidations). Provide the invalidation registers as a primitive to their ITS counterpart. Note that we don't advertise them to the guest yet (the architecture allows an implementation to do this). Signed-off-by: Marc Zyngier Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20220405182327.205520-4-maz@kernel.org --- include/kvm/arm_vgic.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index fdf1c2c322e5..401236f97cf2 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -344,6 +344,7 @@ struct vgic_cpu { struct vgic_io_device rd_iodev; struct vgic_redist_region *rdreg; u32 rdreg_index; + atomic_t syncr_busy; /* Contains the attributes and gpa of the LPI pending tables. */ u64 pendbaser; -- cgit v1.2.3 From 49a1a2c70a7fd820fe60a65a3e38ab9095082dc9 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 5 Apr 2022 19:23:27 +0100 Subject: KVM: arm64: vgic-v3: Advertise GICR_CTLR.{IR, CES} as a new GICD_IIDR revision Since adversising GICR_CTLR.{IC,CES} is directly observable from a guest, we need to make it selectable from userspace. For that, bump the default GICD_IIDR revision and let userspace downgrade it to the previous default. For GICv2, the two distributor revisions are strictly equivalent. Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220405182327.205520-5-maz@kernel.org --- include/kvm/arm_vgic.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 401236f97cf2..2d8f2e90edc2 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -231,6 +231,9 @@ struct vgic_dist { /* Implementation revision as reported in the GICD_IIDR */ u32 implementation_rev; +#define KVM_VGIC_IMP_REV_2 2 /* GICv2 restorable groups */ +#define KVM_VGIC_IMP_REV_3 3 /* GICv3 GICR_CTLR.{IW,CES,RWP} */ +#define KVM_VGIC_IMP_REV_LATEST KVM_VGIC_IMP_REV_3 /* Userspace can write to GICv2 IGROUPR */ bool v2_groups_user_writable; -- cgit v1.2.3 From 5eca8379c73d1bb8cd84e335b9529c263f699468 Mon Sep 17 00:00:00 2001 From: Hawking Zhang Date: Tue, 22 Feb 2022 13:38:51 +0800 Subject: drm/amdgpu: add GC v11_0_0 family id Add GC v11_0_0 family id Signed-off-by: Hawking Zhang Reviewed-by: Likun Gao Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 1d65c1fbc4ec..992851219441 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -1150,6 +1150,7 @@ struct drm_amdgpu_info_video_caps { #define AMDGPU_FAMILY_RV 142 /* Raven */ #define AMDGPU_FAMILY_NV 143 /* Navi10 */ #define AMDGPU_FAMILY_VGH 144 /* Van Gogh */ +#define AMDGPU_FAMILY_GC_11_0_0 145 /* GC 11.0.0 */ #define AMDGPU_FAMILY_YC 146 /* Yellow Carp */ #define AMDGPU_FAMILY_GC_10_3_6 149 /* GC 10.3.6 */ #define AMDGPU_FAMILY_GC_10_3_7 151 /* GC 10.3.7 */ -- cgit v1.2.3 From ec69dfbdc426f22a9557e5c5408d7902fe0e0144 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Mon, 2 May 2022 14:54:06 -0700 Subject: soc: qcom: llcc: Add sc8180x and sc8280xp configurations Add LLCC configuration data for the SC8180X and SC8280XP platforms, based on the downstream tables. Signed-off-by: Bjorn Andersson Reviewed-by: Sai Prakash Ranjan Link: https://lore.kernel.org/r/20220502215406.612967-3-bjorn.andersson@linaro.org --- include/linux/soc/qcom/llcc-qcom.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index 0bc21ee58fac..9ed5384c5ca1 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -29,6 +29,8 @@ #define LLCC_AUDHW 22 #define LLCC_NPU 23 #define LLCC_WLHW 24 +#define LLCC_PIMEM 25 +#define LLCC_DRE 26 #define LLCC_CVP 28 #define LLCC_MODPE 29 #define LLCC_APTCM 30 -- cgit v1.2.3 From 36f8423597000bd7d5e48b7b306e1d0958e72359 Mon Sep 17 00:00:00 2001 From: Muna Sinada Date: Wed, 23 Mar 2022 15:46:35 -0700 Subject: cfg80211: support disabling EHT mode Allow userspace to disable EHT mode during association. Signed-off-by: Muna Sinada Signed-off-by: Aloka Dixit Link: https://lore.kernel.org/r/20220323224636.20211-1-quic_alokad@quicinc.com Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 ++ include/uapi/linux/nl80211.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index cd1212113901..6a3e3f0a8615 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2735,6 +2735,7 @@ struct cfg80211_auth_request { * userspace if this flag is set. Only applicable for cfg80211_connect() * request (connect callback). * @ASSOC_REQ_DISABLE_HE: Disable HE + * @ASSOC_REQ_DISABLE_EHT: Disable EHT */ enum cfg80211_assoc_req_flags { ASSOC_REQ_DISABLE_HT = BIT(0), @@ -2742,6 +2743,7 @@ enum cfg80211_assoc_req_flags { ASSOC_REQ_USE_RRM = BIT(2), CONNECT_REQ_EXTERNAL_AUTH_SUPPORT = BIT(3), ASSOC_REQ_DISABLE_HE = BIT(4), + ASSOC_REQ_DISABLE_EHT = BIT(5), }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 0568a79097b8..d9490e3062a7 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3175,6 +3175,8 @@ enum nl80211_attrs { NL80211_ATTR_EHT_CAPABILITY, + NL80211_ATTR_DISABLE_EHT, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.2.3 From 8b3dd27bfe47abe30450d01077983497aa1a159f Mon Sep 17 00:00:00 2001 From: Paul Elder Date: Wed, 6 Apr 2022 17:33:54 +0200 Subject: dt-bindings: soc: Add i.MX8MP media block control DT bindings The i.MX8MP Media Block Control (MEDIA BLK_CTRL) is a top-level peripheral providing access to the NoC and ensuring proper power sequencing of the peripherals within the MEDIAMIX domain. Add DT bindings for it. There is already a driver for block controls of other SoCs in the i.MX8M family, so these bindings will expand upon that. Signed-off-by: Paul Elder Reviewed-by: Rob Herring Reviewed-by: Laurent Pinchart Signed-off-by: Laurent Pinchart Reviewed-by: Marek Vasut Signed-off-by: Lucas Stach Signed-off-by: Shawn Guo --- include/dt-bindings/power/imx8mp-power.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/power/imx8mp-power.h b/include/dt-bindings/power/imx8mp-power.h index 9f90c40a2c6c..bc8458f1e725 100644 --- a/include/dt-bindings/power/imx8mp-power.h +++ b/include/dt-bindings/power/imx8mp-power.h @@ -32,4 +32,14 @@ #define IMX8MP_HSIOBLK_PD_PCIE 3 #define IMX8MP_HSIOBLK_PD_PCIE_PHY 4 +#define IMX8MP_MEDIABLK_PD_MIPI_DSI_1 0 +#define IMX8MP_MEDIABLK_PD_MIPI_CSI2_1 1 +#define IMX8MP_MEDIABLK_PD_LCDIF_1 2 +#define IMX8MP_MEDIABLK_PD_ISI 3 +#define IMX8MP_MEDIABLK_PD_MIPI_CSI2_2 4 +#define IMX8MP_MEDIABLK_PD_LCDIF_2 5 +#define IMX8MP_MEDIABLK_PD_ISP 6 +#define IMX8MP_MEDIABLK_PD_DWE 7 +#define IMX8MP_MEDIABLK_PD_MIPI_DSI_2 8 + #endif -- cgit v1.2.3 From f11cf9e35e7f740d158e298baf5764bcdd8a199e Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Wed, 6 Apr 2022 17:33:56 +0200 Subject: dt-bindings: power: imx8mp: add defines for HDMI blk-ctrl domains This adds the defines for the power domains provided by the HDMI blk-ctrl on the i.MX8MP. Signed-off-by: Lucas Stach Acked-by: Rob Herring Signed-off-by: Shawn Guo --- include/dt-bindings/power/imx8mp-power.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/power/imx8mp-power.h b/include/dt-bindings/power/imx8mp-power.h index bc8458f1e725..7789bcca3223 100644 --- a/include/dt-bindings/power/imx8mp-power.h +++ b/include/dt-bindings/power/imx8mp-power.h @@ -42,4 +42,12 @@ #define IMX8MP_MEDIABLK_PD_DWE 7 #define IMX8MP_MEDIABLK_PD_MIPI_DSI_2 8 +#define IMX8MP_HDMIBLK_PD_IRQSTEER 0 +#define IMX8MP_HDMIBLK_PD_LCDIF 1 +#define IMX8MP_HDMIBLK_PD_PAI 2 +#define IMX8MP_HDMIBLK_PD_PVI 3 +#define IMX8MP_HDMIBLK_PD_TRNG 4 +#define IMX8MP_HDMIBLK_PD_HDMI_TX 5 +#define IMX8MP_HDMIBLK_PD_HDMI_TX_PHY 6 + #endif -- cgit v1.2.3 From b2d057560b8107c633b39aabe517ff9d93f285e3 Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Mon, 2 May 2022 10:46:08 +0200 Subject: secure_seq: use the 64 bits of the siphash for port offset calculation SipHash replaced MD5 in secure_ipv{4,6}_port_ephemeral() via commit 7cd23e5300c1 ("secure_seq: use SipHash in place of MD5"), but the output remained truncated to 32-bit only. In order to exploit more bits from the hash, let's make the functions return the full 64-bit of siphash_3u32(). We also make sure the port offset calculation in __inet_hash_connect() remains done on 32-bit to avoid the need for div_u64_rem() and an extra cost on 32-bit systems. Cc: Jason A. Donenfeld Cc: Moshe Kol Cc: Yossi Gilad Cc: Amit Klein Reviewed-by: Eric Dumazet Signed-off-by: Willy Tarreau Signed-off-by: Jakub Kicinski --- include/net/inet_hashtables.h | 2 +- include/net/secure_seq.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index f72ec113ae56..98e1ec1a14f0 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -425,7 +425,7 @@ static inline void sk_rcv_saddr_set(struct sock *sk, __be32 addr) } int __inet_hash_connect(struct inet_timewait_death_row *death_row, - struct sock *sk, u32 port_offset, + struct sock *sk, u64 port_offset, int (*check_established)(struct inet_timewait_death_row *, struct sock *, __u16, struct inet_timewait_sock **)); diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h index d7d2495f83c2..dac91aa38c5a 100644 --- a/include/net/secure_seq.h +++ b/include/net/secure_seq.h @@ -4,8 +4,8 @@ #include -u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); -u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, +u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); +u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport); u32 secure_tcp_seq(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport); -- cgit v1.2.3 From 170f37d6aa6ad4582eefd7459015de79e244536e Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 3 May 2022 00:09:31 -0400 Subject: block: Do not call folio_next() on an unreferenced folio It is unsafe to call folio_next() on a folio unless you hold a reference on it that prevents it from being split or freed. After returning from the iterator, iomap calls folio_end_writeback() which may drop the last reference to the page, or allow the page to be split. If that happens, the iterator will not advance far enough through the bio_vec, leading to assertion failures like the BUG() in folio_end_writeback() that checks we're not trying to end writeback on a page not currently under writeback. Other assertion failures were also seen, but they're all explained by this one bug. Fix the bug by remembering where the next folio starts before returning from the iterator. There are other ways of fixing this bug, but this seems the simplest. Reported-by: Darrick J. Wong Tested-by: Darrick J. Wong Reported-by: Brian Foster Tested-by: Brian Foster Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/bio.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 278cc81cc1e7..00450fd86bb4 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -269,6 +269,7 @@ struct folio_iter { size_t offset; size_t length; /* private: for use by the iterator */ + struct folio *_next; size_t _seg_count; int _i; }; @@ -283,6 +284,7 @@ static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio, PAGE_SIZE * (bvec->bv_page - &fi->folio->page); fi->_seg_count = bvec->bv_len; fi->length = min(folio_size(fi->folio) - fi->offset, fi->_seg_count); + fi->_next = folio_next(fi->folio); fi->_i = i; } @@ -290,9 +292,10 @@ static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio) { fi->_seg_count -= fi->length; if (fi->_seg_count) { - fi->folio = folio_next(fi->folio); + fi->folio = fi->_next; fi->offset = 0; fi->length = min(folio_size(fi->folio), fi->_seg_count); + fi->_next = folio_next(fi->folio); } else if (fi->_i + 1 < bio->bi_vcnt) { bio_first_folio(fi, bio, fi->_i + 1); } else { -- cgit v1.2.3 From 8e1de7042596abb7cb277ea751fc13a4c2b65aea Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Sun, 13 Feb 2022 16:44:45 +0200 Subject: thunderbolt: Add support for XDomain lane bonding The USB4 Inter-Domain Service specification defines a protocol that can be used to establish lane bonding between two USB4 domains (hosts). So far we have not implemented it because the host controller DMA was not fast enough to be able to go over 20 Gbits/s even if lanes were bonded. However, starting from Intel Alder Lake CPUs the DMA can go over 20 Gbits/s so now it makes more sense to add this support to the driver. Because both ends need to negotiate the bonding we add a simple state machine that tracks the connection state and does the necessary steps described by the USB4 Inter-Domain Service specification. We only establish lane bonding when both sides of the link support it. Otherwise we default to use the single lane. Also this is only done when software connection manager is used. On systems with firmware based connection manager, it handles the high-speed tunneling so bonding lanes is specific to the implementation (Intel firmware based connection manager does not support lane bonding). Signed-off-by: Mika Westerberg --- include/linux/thunderbolt.h | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index 124e13cb1469..e13fe15e6a51 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -198,15 +198,15 @@ void tb_unregister_property_dir(const char *key, struct tb_property_dir *dir); * @local_property_block_len: Length of the @local_property_block in dwords * @remote_properties: Properties exported by the remote domain * @remote_property_block_gen: Generation of @remote_properties - * @get_uuid_work: Work used to retrieve @remote_uuid - * @uuid_retries: Number of times left @remote_uuid is requested before - * giving up - * @get_properties_work: Work used to get remote domain properties - * @properties_retries: Number of times left to read properties + * @state: Next XDomain discovery state to run + * @state_work: Work used to run the next state + * @state_retries: Number of retries remain for the state * @properties_changed_work: Work used to notify the remote domain that * our properties have changed * @properties_changed_retries: Number of times left to send properties * changed notification + * @bonding_possible: True if lane bonding is possible on local side + * @target_link_width: Target link width from the remote host * @link: Root switch link the remote domain is connected (ICM only) * @depth: Depth in the chain the remote domain is connected (ICM only) * @@ -244,12 +244,13 @@ struct tb_xdomain { u32 local_property_block_len; struct tb_property_dir *remote_properties; u32 remote_property_block_gen; - struct delayed_work get_uuid_work; - int uuid_retries; - struct delayed_work get_properties_work; - int properties_retries; + int state; + struct delayed_work state_work; + int state_retries; struct delayed_work properties_changed_work; int properties_changed_retries; + bool bonding_possible; + u8 target_link_width; u8 link; u8 depth; }; -- cgit v1.2.3 From 680e1c8370a2ed7aff4f99ce3cebf79873d68f59 Mon Sep 17 00:00:00 2001 From: Chanho Park Date: Wed, 4 May 2022 16:51:43 +0900 Subject: dt-bindings: clock: add clock binding definitions for Exynos Auto v9 Add device tree clock binding definitions for below CMU blocks. - CMU_TOP - CMU_BUSMC - CMU_CORE - CMU_FYS2 - CMU_PERIC0 / C1 - CMU_PERIS Reviewed-by: Krzysztof Kozlowski Signed-off-by: Chanho Park Acked-by: Chanwoo Choi Link: https://lore.kernel.org/r/20220504075154.58819-2-chanho61.park@samsung.com Signed-off-by: Krzysztof Kozlowski --- include/dt-bindings/clock/samsung,exynosautov9.h | 299 +++++++++++++++++++++++ 1 file changed, 299 insertions(+) create mode 100644 include/dt-bindings/clock/samsung,exynosautov9.h (limited to 'include') diff --git a/include/dt-bindings/clock/samsung,exynosautov9.h b/include/dt-bindings/clock/samsung,exynosautov9.h new file mode 100644 index 000000000000..71ec0a955364 --- /dev/null +++ b/include/dt-bindings/clock/samsung,exynosautov9.h @@ -0,0 +1,299 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2022 Samsung Electronics Co., Ltd. + * Author: Chanho Park + * + * Device Tree binding constants for Exynos Auto V9 clock controller. + */ + +#ifndef _DT_BINDINGS_CLOCK_EXYNOSAUTOV9_H +#define _DT_BINDINGS_CLOCK_EXYNOSAUTOV9_H + +/* CMU_TOP */ +#define FOUT_SHARED0_PLL 1 +#define FOUT_SHARED1_PLL 2 +#define FOUT_SHARED2_PLL 3 +#define FOUT_SHARED3_PLL 4 +#define FOUT_SHARED4_PLL 5 + +/* MUX in CMU_TOP */ +#define MOUT_SHARED0_PLL 6 +#define MOUT_SHARED1_PLL 7 +#define MOUT_SHARED2_PLL 8 +#define MOUT_SHARED3_PLL 9 +#define MOUT_SHARED4_PLL 10 +#define MOUT_CLKCMU_CMU_BOOST 11 +#define MOUT_CLKCMU_CMU_CMUREF 12 +#define MOUT_CLKCMU_ACC_BUS 13 +#define MOUT_CLKCMU_APM_BUS 14 +#define MOUT_CLKCMU_AUD_CPU 15 +#define MOUT_CLKCMU_AUD_BUS 16 +#define MOUT_CLKCMU_BUSC_BUS 17 +#define MOUT_CLKCMU_BUSMC_BUS 19 +#define MOUT_CLKCMU_CORE_BUS 20 +#define MOUT_CLKCMU_CPUCL0_SWITCH 21 +#define MOUT_CLKCMU_CPUCL0_CLUSTER 22 +#define MOUT_CLKCMU_CPUCL1_SWITCH 24 +#define MOUT_CLKCMU_CPUCL1_CLUSTER 25 +#define MOUT_CLKCMU_DPTX_BUS 26 +#define MOUT_CLKCMU_DPTX_DPGTC 27 +#define MOUT_CLKCMU_DPUM_BUS 28 +#define MOUT_CLKCMU_DPUS0_BUS 29 +#define MOUT_CLKCMU_DPUS1_BUS 30 +#define MOUT_CLKCMU_FSYS0_BUS 31 +#define MOUT_CLKCMU_FSYS0_PCIE 32 +#define MOUT_CLKCMU_FSYS1_BUS 33 +#define MOUT_CLKCMU_FSYS1_USBDRD 34 +#define MOUT_CLKCMU_FSYS1_MMC_CARD 35 +#define MOUT_CLKCMU_FSYS2_BUS 36 +#define MOUT_CLKCMU_FSYS2_UFS_EMBD 37 +#define MOUT_CLKCMU_FSYS2_ETHERNET 38 +#define MOUT_CLKCMU_G2D_G2D 39 +#define MOUT_CLKCMU_G2D_MSCL 40 +#define MOUT_CLKCMU_G3D00_SWITCH 41 +#define MOUT_CLKCMU_G3D01_SWITCH 42 +#define MOUT_CLKCMU_G3D1_SWITCH 43 +#define MOUT_CLKCMU_ISPB_BUS 44 +#define MOUT_CLKCMU_MFC_MFC 45 +#define MOUT_CLKCMU_MFC_WFD 46 +#define MOUT_CLKCMU_MIF_SWITCH 47 +#define MOUT_CLKCMU_MIF_BUSP 48 +#define MOUT_CLKCMU_NPU_BUS 49 +#define MOUT_CLKCMU_PERIC0_BUS 50 +#define MOUT_CLKCMU_PERIC0_IP 51 +#define MOUT_CLKCMU_PERIC1_BUS 52 +#define MOUT_CLKCMU_PERIC1_IP 53 +#define MOUT_CLKCMU_PERIS_BUS 54 + +/* DIV in CMU_TOP */ +#define DOUT_SHARED0_DIV3 101 +#define DOUT_SHARED0_DIV2 102 +#define DOUT_SHARED1_DIV3 103 +#define DOUT_SHARED1_DIV2 104 +#define DOUT_SHARED1_DIV4 105 +#define DOUT_SHARED2_DIV3 106 +#define DOUT_SHARED2_DIV2 107 +#define DOUT_SHARED2_DIV4 108 +#define DOUT_SHARED4_DIV2 109 +#define DOUT_SHARED4_DIV4 110 +#define DOUT_CLKCMU_CMU_BOOST 111 +#define DOUT_CLKCMU_ACC_BUS 112 +#define DOUT_CLKCMU_APM_BUS 113 +#define DOUT_CLKCMU_AUD_CPU 114 +#define DOUT_CLKCMU_AUD_BUS 115 +#define DOUT_CLKCMU_BUSC_BUS 116 +#define DOUT_CLKCMU_BUSMC_BUS 118 +#define DOUT_CLKCMU_CORE_BUS 119 +#define DOUT_CLKCMU_CPUCL0_SWITCH 120 +#define DOUT_CLKCMU_CPUCL0_CLUSTER 121 +#define DOUT_CLKCMU_CPUCL1_SWITCH 123 +#define DOUT_CLKCMU_CPUCL1_CLUSTER 124 +#define DOUT_CLKCMU_DPTX_BUS 125 +#define DOUT_CLKCMU_DPTX_DPGTC 126 +#define DOUT_CLKCMU_DPUM_BUS 127 +#define DOUT_CLKCMU_DPUS0_BUS 128 +#define DOUT_CLKCMU_DPUS1_BUS 129 +#define DOUT_CLKCMU_FSYS0_BUS 130 +#define DOUT_CLKCMU_FSYS0_PCIE 131 +#define DOUT_CLKCMU_FSYS1_BUS 132 +#define DOUT_CLKCMU_FSYS1_USBDRD 133 +#define DOUT_CLKCMU_FSYS2_BUS 134 +#define DOUT_CLKCMU_FSYS2_UFS_EMBD 135 +#define DOUT_CLKCMU_FSYS2_ETHERNET 136 +#define DOUT_CLKCMU_G2D_G2D 137 +#define DOUT_CLKCMU_G2D_MSCL 138 +#define DOUT_CLKCMU_G3D00_SWITCH 139 +#define DOUT_CLKCMU_G3D01_SWITCH 140 +#define DOUT_CLKCMU_G3D1_SWITCH 141 +#define DOUT_CLKCMU_ISPB_BUS 142 +#define DOUT_CLKCMU_MFC_MFC 143 +#define DOUT_CLKCMU_MFC_WFD 144 +#define DOUT_CLKCMU_MIF_SWITCH 145 +#define DOUT_CLKCMU_MIF_BUSP 146 +#define DOUT_CLKCMU_NPU_BUS 147 +#define DOUT_CLKCMU_PERIC0_BUS 148 +#define DOUT_CLKCMU_PERIC0_IP 149 +#define DOUT_CLKCMU_PERIC1_BUS 150 +#define DOUT_CLKCMU_PERIC1_IP 151 +#define DOUT_CLKCMU_PERIS_BUS 152 + +/* GAT in CMU_TOP */ +#define GOUT_CLKCMU_CMU_BOOST 201 +#define GOUT_CLKCMU_CPUCL0_BOOST 202 +#define GOUT_CLKCMU_CPUCL1_BOOST 203 +#define GOUT_CLKCMU_CORE_BOOST 204 +#define GOUT_CLKCMU_BUSC_BOOST 205 +#define GOUT_CLKCMU_BUSMC_BOOST 206 +#define GOUT_CLKCMU_MIF_BOOST 207 +#define GOUT_CLKCMU_ACC_BUS 208 +#define GOUT_CLKCMU_APM_BUS 209 +#define GOUT_CLKCMU_AUD_CPU 210 +#define GOUT_CLKCMU_AUD_BUS 211 +#define GOUT_CLKCMU_BUSC_BUS 212 +#define GOUT_CLKCMU_BUSMC_BUS 214 +#define GOUT_CLKCMU_CORE_BUS 215 +#define GOUT_CLKCMU_CPUCL0_SWITCH 216 +#define GOUT_CLKCMU_CPUCL0_CLUSTER 217 +#define GOUT_CLKCMU_CPUCL1_SWITCH 219 +#define GOUT_CLKCMU_CPUCL1_CLUSTER 220 +#define GOUT_CLKCMU_DPTX_BUS 221 +#define GOUT_CLKCMU_DPTX_DPGTC 222 +#define GOUT_CLKCMU_DPUM_BUS 223 +#define GOUT_CLKCMU_DPUS0_BUS 224 +#define GOUT_CLKCMU_DPUS1_BUS 225 +#define GOUT_CLKCMU_FSYS0_BUS 226 +#define GOUT_CLKCMU_FSYS0_PCIE 227 +#define GOUT_CLKCMU_FSYS1_BUS 228 +#define GOUT_CLKCMU_FSYS1_USBDRD 229 +#define GOUT_CLKCMU_FSYS1_MMC_CARD 230 +#define GOUT_CLKCMU_FSYS2_BUS 231 +#define GOUT_CLKCMU_FSYS2_UFS_EMBD 232 +#define GOUT_CLKCMU_FSYS2_ETHERNET 233 +#define GOUT_CLKCMU_G2D_G2D 234 +#define GOUT_CLKCMU_G2D_MSCL 235 +#define GOUT_CLKCMU_G3D00_SWITCH 236 +#define GOUT_CLKCMU_G3D01_SWITCH 237 +#define GOUT_CLKCMU_G3D1_SWITCH 238 +#define GOUT_CLKCMU_ISPB_BUS 239 +#define GOUT_CLKCMU_MFC_MFC 240 +#define GOUT_CLKCMU_MFC_WFD 241 +#define GOUT_CLKCMU_MIF_SWITCH 242 +#define GOUT_CLKCMU_MIF_BUSP 243 +#define GOUT_CLKCMU_NPU_BUS 244 +#define GOUT_CLKCMU_PERIC0_BUS 245 +#define GOUT_CLKCMU_PERIC0_IP 246 +#define GOUT_CLKCMU_PERIC1_BUS 247 +#define GOUT_CLKCMU_PERIC1_IP 248 +#define GOUT_CLKCMU_PERIS_BUS 249 + +#define TOP_NR_CLK 249 + +/* CMU_BUSMC */ +#define CLK_MOUT_BUSMC_BUS_USER 1 +#define CLK_DOUT_BUSMC_BUSP 2 +#define CLK_GOUT_BUSMC_PDMA0_PCLK 3 +#define CLK_GOUT_BUSMC_SPDMA_PCLK 4 + +#define BUSMC_NR_CLK 4 + +/* CMU_CORE */ +#define CLK_MOUT_CORE_BUS_USER 1 +#define CLK_DOUT_CORE_BUSP 2 +#define CLK_GOUT_CORE_CCI_CLK 3 +#define CLK_GOUT_CORE_CCI_PCLK 4 +#define CLK_GOUT_CORE_CMU_CORE_PCLK 5 + +#define CORE_NR_CLK 5 + +/* CMU_FSYS2 */ +#define CLK_MOUT_FSYS2_BUS_USER 1 +#define CLK_MOUT_FSYS2_UFS_EMBD_USER 2 +#define CLK_MOUT_FSYS2_ETHERNET_USER 3 +#define CLK_GOUT_FSYS2_UFS_EMBD0_ACLK 4 +#define CLK_GOUT_FSYS2_UFS_EMBD0_UNIPRO 5 +#define CLK_GOUT_FSYS2_UFS_EMBD1_ACLK 6 +#define CLK_GOUT_FSYS2_UFS_EMBD1_UNIPRO 7 + +#define FSYS2_NR_CLK 7 + +/* CMU_PERIC0 */ +#define CLK_MOUT_PERIC0_BUS_USER 1 +#define CLK_MOUT_PERIC0_IP_USER 2 +#define CLK_MOUT_PERIC0_USI00_USI 3 +#define CLK_MOUT_PERIC0_USI01_USI 4 +#define CLK_MOUT_PERIC0_USI02_USI 5 +#define CLK_MOUT_PERIC0_USI03_USI 6 +#define CLK_MOUT_PERIC0_USI04_USI 7 +#define CLK_MOUT_PERIC0_USI05_USI 8 +#define CLK_MOUT_PERIC0_USI_I2C 9 + +#define CLK_DOUT_PERIC0_USI00_USI 10 +#define CLK_DOUT_PERIC0_USI01_USI 11 +#define CLK_DOUT_PERIC0_USI02_USI 12 +#define CLK_DOUT_PERIC0_USI03_USI 13 +#define CLK_DOUT_PERIC0_USI04_USI 14 +#define CLK_DOUT_PERIC0_USI05_USI 15 +#define CLK_DOUT_PERIC0_USI_I2C 16 + +#define CLK_GOUT_PERIC0_IPCLK_0 20 +#define CLK_GOUT_PERIC0_IPCLK_1 21 +#define CLK_GOUT_PERIC0_IPCLK_2 22 +#define CLK_GOUT_PERIC0_IPCLK_3 23 +#define CLK_GOUT_PERIC0_IPCLK_4 24 +#define CLK_GOUT_PERIC0_IPCLK_5 25 +#define CLK_GOUT_PERIC0_IPCLK_6 26 +#define CLK_GOUT_PERIC0_IPCLK_7 27 +#define CLK_GOUT_PERIC0_IPCLK_8 28 +#define CLK_GOUT_PERIC0_IPCLK_9 29 +#define CLK_GOUT_PERIC0_IPCLK_10 30 +#define CLK_GOUT_PERIC0_IPCLK_11 30 +#define CLK_GOUT_PERIC0_PCLK_0 31 +#define CLK_GOUT_PERIC0_PCLK_1 32 +#define CLK_GOUT_PERIC0_PCLK_2 33 +#define CLK_GOUT_PERIC0_PCLK_3 34 +#define CLK_GOUT_PERIC0_PCLK_4 35 +#define CLK_GOUT_PERIC0_PCLK_5 36 +#define CLK_GOUT_PERIC0_PCLK_6 37 +#define CLK_GOUT_PERIC0_PCLK_7 38 +#define CLK_GOUT_PERIC0_PCLK_8 39 +#define CLK_GOUT_PERIC0_PCLK_9 40 +#define CLK_GOUT_PERIC0_PCLK_10 41 +#define CLK_GOUT_PERIC0_PCLK_11 42 + +#define PERIC0_NR_CLK 42 + +/* CMU_PERIC1 */ +#define CLK_MOUT_PERIC1_BUS_USER 1 +#define CLK_MOUT_PERIC1_IP_USER 2 +#define CLK_MOUT_PERIC1_USI06_USI 3 +#define CLK_MOUT_PERIC1_USI07_USI 4 +#define CLK_MOUT_PERIC1_USI08_USI 5 +#define CLK_MOUT_PERIC1_USI09_USI 6 +#define CLK_MOUT_PERIC1_USI10_USI 7 +#define CLK_MOUT_PERIC1_USI11_USI 8 +#define CLK_MOUT_PERIC1_USI_I2C 9 + +#define CLK_DOUT_PERIC1_USI06_USI 10 +#define CLK_DOUT_PERIC1_USI07_USI 11 +#define CLK_DOUT_PERIC1_USI08_USI 12 +#define CLK_DOUT_PERIC1_USI09_USI 13 +#define CLK_DOUT_PERIC1_USI10_USI 14 +#define CLK_DOUT_PERIC1_USI11_USI 15 +#define CLK_DOUT_PERIC1_USI_I2C 16 + +#define CLK_GOUT_PERIC1_IPCLK_0 20 +#define CLK_GOUT_PERIC1_IPCLK_1 21 +#define CLK_GOUT_PERIC1_IPCLK_2 22 +#define CLK_GOUT_PERIC1_IPCLK_3 23 +#define CLK_GOUT_PERIC1_IPCLK_4 24 +#define CLK_GOUT_PERIC1_IPCLK_5 25 +#define CLK_GOUT_PERIC1_IPCLK_6 26 +#define CLK_GOUT_PERIC1_IPCLK_7 27 +#define CLK_GOUT_PERIC1_IPCLK_8 28 +#define CLK_GOUT_PERIC1_IPCLK_9 29 +#define CLK_GOUT_PERIC1_IPCLK_10 30 +#define CLK_GOUT_PERIC1_IPCLK_11 30 +#define CLK_GOUT_PERIC1_PCLK_0 31 +#define CLK_GOUT_PERIC1_PCLK_1 32 +#define CLK_GOUT_PERIC1_PCLK_2 33 +#define CLK_GOUT_PERIC1_PCLK_3 34 +#define CLK_GOUT_PERIC1_PCLK_4 35 +#define CLK_GOUT_PERIC1_PCLK_5 36 +#define CLK_GOUT_PERIC1_PCLK_6 37 +#define CLK_GOUT_PERIC1_PCLK_7 38 +#define CLK_GOUT_PERIC1_PCLK_8 39 +#define CLK_GOUT_PERIC1_PCLK_9 40 +#define CLK_GOUT_PERIC1_PCLK_10 41 +#define CLK_GOUT_PERIC1_PCLK_11 42 + +#define PERIC1_NR_CLK 42 + +/* CMU_PERIS */ +#define CLK_MOUT_PERIS_BUS_USER 1 +#define CLK_GOUT_SYSREG_PERIS_PCLK 2 +#define CLK_GOUT_WDT_CLUSTER0 3 +#define CLK_GOUT_WDT_CLUSTER1 4 + +#define PERIS_NR_CLK 4 + +#endif /* _DT_BINDINGS_CLOCK_EXYNOSAUTOV9_H */ -- cgit v1.2.3 From e13f13e039dc8f31168b5569120a7658035c80ee Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Mon, 2 May 2022 16:25:12 +0200 Subject: drm: Add DRM-managed mutex_init() Add drmm_mutex_init(), a helper that provides managed mutex cleanup. The mutex will be destroyed with the final reference of the DRM device. Signed-off-by: Thomas Zimmermann Reviewed-by: Jocelyn Falempe Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220502142514.2174-2-tzimmermann@suse.de --- include/drm/drm_managed.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/drm/drm_managed.h b/include/drm/drm_managed.h index b45c6fbf53ac..359883942612 100644 --- a/include/drm/drm_managed.h +++ b/include/drm/drm_managed.h @@ -8,6 +8,7 @@ #include struct drm_device; +struct mutex; typedef void (*drmres_release_t)(struct drm_device *dev, void *res); @@ -104,4 +105,6 @@ char *drmm_kstrdup(struct drm_device *dev, const char *s, gfp_t gfp); void drmm_kfree(struct drm_device *dev, void *data); +int drmm_mutex_init(struct drm_device *dev, struct mutex *lock); + #endif -- cgit v1.2.3 From 96055bf71ab1629cdedff15bcbc04609cfa1f198 Mon Sep 17 00:00:00 2001 From: Phil Edworthy Date: Tue, 3 May 2022 12:55:47 +0100 Subject: dt-bindings: clock: Add r9a09g011 CPG Clock Definitions Define RZ/V2M (R9A09G011) Clock Pulse Generator module clock outputs (CPG_CLK_ON* registers), and reset definitions (CPG_RST_* registers) in Section 48.5 ("Register Description") of the RZ/V2M Hardware User's Manual (Rev. 1.10, Sep. 2021). Signed-off-by: Phil Edworthy Reviewed-by: Biju Das Link: https://lore.kernel.org/r/20220503115557.53370-3-phil.edworthy@renesas.com Signed-off-by: Geert Uytterhoeven --- include/dt-bindings/clock/r9a09g011-cpg.h | 352 ++++++++++++++++++++++++++++++ 1 file changed, 352 insertions(+) create mode 100644 include/dt-bindings/clock/r9a09g011-cpg.h (limited to 'include') diff --git a/include/dt-bindings/clock/r9a09g011-cpg.h b/include/dt-bindings/clock/r9a09g011-cpg.h new file mode 100644 index 000000000000..41dd585d7115 --- /dev/null +++ b/include/dt-bindings/clock/r9a09g011-cpg.h @@ -0,0 +1,352 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + * + * Copyright (C) 2022 Renesas Electronics Corp. + */ +#ifndef __DT_BINDINGS_CLOCK_R9A09G011_CPG_H__ +#define __DT_BINDINGS_CLOCK_R9A09G011_CPG_H__ + +#include + +/* Module Clocks */ +#define R9A09G011_SYS_CLK 0 +#define R9A09G011_PFC_PCLK 1 +#define R9A09G011_PMC_CORE_CLOCK 2 +#define R9A09G011_GIC_CLK 3 +#define R9A09G011_RAMA_ACLK 4 +#define R9A09G011_ROMA_ACLK 5 +#define R9A09G011_SEC_ACLK 6 +#define R9A09G011_SEC_PCLK 7 +#define R9A09G011_SEC_TCLK 8 +#define R9A09G011_DMAA_ACLK 9 +#define R9A09G011_TSU0_PCLK 10 +#define R9A09G011_TSU1_PCLK 11 + +#define R9A09G011_CST_TRACECLK 12 +#define R9A09G011_CST_SB_CLK 13 +#define R9A09G011_CST_AHB_CLK 14 +#define R9A09G011_CST_ATB_SB_CLK 15 +#define R9A09G011_CST_TS_SB_CLK 16 + +#define R9A09G011_SDI0_ACLK 17 +#define R9A09G011_SDI0_IMCLK 18 +#define R9A09G011_SDI0_IMCLK2 19 +#define R9A09G011_SDI0_CLK_HS 20 +#define R9A09G011_SDI1_ACLK 21 +#define R9A09G011_SDI1_IMCLK 22 +#define R9A09G011_SDI1_IMCLK2 23 +#define R9A09G011_SDI1_CLK_HS 24 +#define R9A09G011_EMM_ACLK 25 +#define R9A09G011_EMM_IMCLK 26 +#define R9A09G011_EMM_IMCLK2 27 +#define R9A09G011_EMM_CLK_HS 28 +#define R9A09G011_NFI_ACLK 29 +#define R9A09G011_NFI_NF_CLK 30 + +#define R9A09G011_PCI_ACLK 31 +#define R9A09G011_PCI_CLK_PMU 32 +#define R9A09G011_PCI_APB_CLK 33 +#define R9A09G011_USB_ACLK_H 34 +#define R9A09G011_USB_ACLK_P 35 +#define R9A09G011_USB_PCLK 36 +#define R9A09G011_ETH0_CLK_AXI 37 +#define R9A09G011_ETH0_CLK_CHI 38 +#define R9A09G011_ETH0_GPTP_EXT 39 + +#define R9A09G011_SDT_CLK 40 +#define R9A09G011_SDT_CLKAPB 41 +#define R9A09G011_SDT_CLK48 42 +#define R9A09G011_GRP_CLK 43 +#define R9A09G011_CIF_P0_CLK 44 +#define R9A09G011_CIF_P1_CLK 45 +#define R9A09G011_CIF_APB_CLK 46 +#define R9A09G011_DCI_CLKAXI 47 +#define R9A09G011_DCI_CLKAPB 48 +#define R9A09G011_DCI_CLKDCI2 49 + +#define R9A09G011_HMI_PCLK 50 +#define R9A09G011_LCI_PCLK 51 +#define R9A09G011_LCI_ACLK 52 +#define R9A09G011_LCI_VCLK 53 +#define R9A09G011_LCI_LPCLK 54 + +#define R9A09G011_AUI_CLK 55 +#define R9A09G011_AUI_CLKAXI 56 +#define R9A09G011_AUI_CLKAPB 57 +#define R9A09G011_AUMCLK 58 +#define R9A09G011_GMCLK0 59 +#define R9A09G011_GMCLK1 60 +#define R9A09G011_MTR_CLK0 61 +#define R9A09G011_MTR_CLK1 62 +#define R9A09G011_MTR_CLKAPB 63 +#define R9A09G011_GFT_CLK 64 +#define R9A09G011_GFT_CLKAPB 65 +#define R9A09G011_GFT_MCLK 66 + +#define R9A09G011_ATGA_CLK 67 +#define R9A09G011_ATGA_CLKAPB 68 +#define R9A09G011_ATGB_CLK 69 +#define R9A09G011_ATGB_CLKAPB 70 +#define R9A09G011_SYC_CNT_CLK 71 + +#define R9A09G011_CPERI_GRPA_PCLK 72 +#define R9A09G011_TIM0_CLK 73 +#define R9A09G011_TIM1_CLK 74 +#define R9A09G011_TIM2_CLK 75 +#define R9A09G011_TIM3_CLK 76 +#define R9A09G011_TIM4_CLK 77 +#define R9A09G011_TIM5_CLK 78 +#define R9A09G011_TIM6_CLK 79 +#define R9A09G011_TIM7_CLK 80 +#define R9A09G011_IIC_PCLK0 81 + +#define R9A09G011_CPERI_GRPB_PCLK 82 +#define R9A09G011_TIM8_CLK 83 +#define R9A09G011_TIM9_CLK 84 +#define R9A09G011_TIM10_CLK 85 +#define R9A09G011_TIM11_CLK 86 +#define R9A09G011_TIM12_CLK 87 +#define R9A09G011_TIM13_CLK 88 +#define R9A09G011_TIM14_CLK 89 +#define R9A09G011_TIM15_CLK 90 +#define R9A09G011_IIC_PCLK1 91 + +#define R9A09G011_CPERI_GRPC_PCLK 92 +#define R9A09G011_TIM16_CLK 93 +#define R9A09G011_TIM17_CLK 94 +#define R9A09G011_TIM18_CLK 95 +#define R9A09G011_TIM19_CLK 96 +#define R9A09G011_TIM20_CLK 97 +#define R9A09G011_TIM21_CLK 98 +#define R9A09G011_TIM22_CLK 99 +#define R9A09G011_TIM23_CLK 100 +#define R9A09G011_WDT0_PCLK 101 +#define R9A09G011_WDT0_CLK 102 +#define R9A09G011_WDT1_PCLK 103 +#define R9A09G011_WDT1_CLK 104 + +#define R9A09G011_CPERI_GRPD_PCLK 105 +#define R9A09G011_TIM24_CLK 106 +#define R9A09G011_TIM25_CLK 107 +#define R9A09G011_TIM26_CLK 108 +#define R9A09G011_TIM27_CLK 109 +#define R9A09G011_TIM28_CLK 110 +#define R9A09G011_TIM29_CLK 111 +#define R9A09G011_TIM30_CLK 112 +#define R9A09G011_TIM31_CLK 113 + +#define R9A09G011_CPERI_GRPE_PCLK 114 +#define R9A09G011_PWM0_CLK 115 +#define R9A09G011_PWM1_CLK 116 +#define R9A09G011_PWM2_CLK 117 +#define R9A09G011_PWM3_CLK 118 +#define R9A09G011_PWM4_CLK 119 +#define R9A09G011_PWM5_CLK 120 +#define R9A09G011_PWM6_CLK 121 +#define R9A09G011_PWM7_CLK 122 + +#define R9A09G011_CPERI_GRPF_PCLK 123 +#define R9A09G011_PWM8_CLK 124 +#define R9A09G011_PWM9_CLK 125 +#define R9A09G011_PWM10_CLK 126 +#define R9A09G011_PWM11_CLK 127 +#define R9A09G011_PWM12_CLK 128 +#define R9A09G011_PWM13_CLK 129 +#define R9A09G011_PWM14_CLK 130 +#define R9A09G011_PWM15_CLK 131 + +#define R9A09G011_CPERI_GRPG_PCLK 132 +#define R9A09G011_CPERI_GRPH_PCLK 133 +#define R9A09G011_URT_PCLK 134 +#define R9A09G011_URT0_CLK 135 +#define R9A09G011_URT1_CLK 136 +#define R9A09G011_CSI0_CLK 137 +#define R9A09G011_CSI1_CLK 138 +#define R9A09G011_CSI2_CLK 139 +#define R9A09G011_CSI3_CLK 140 +#define R9A09G011_CSI4_CLK 141 +#define R9A09G011_CSI5_CLK 142 + +#define R9A09G011_ICB_ACLK1 143 +#define R9A09G011_ICB_GIC_CLK 144 +#define R9A09G011_ICB_MPCLK1 145 +#define R9A09G011_ICB_SPCLK1 146 +#define R9A09G011_ICB_CLK48 147 +#define R9A09G011_ICB_CLK48_2 148 +#define R9A09G011_ICB_CLK48_3 149 +#define R9A09G011_ICB_CLK48_4L 150 +#define R9A09G011_ICB_CLK48_4R 151 +#define R9A09G011_ICB_CLK48_5 152 +#define R9A09G011_ICB_CST_ATB_SB_CLK 153 +#define R9A09G011_ICB_CST_CS_CLK 154 +#define R9A09G011_ICB_CLK100_1 155 +#define R9A09G011_ICB_ETH0_CLK_AXI 156 +#define R9A09G011_ICB_DCI_CLKAXI 157 +#define R9A09G011_ICB_SYC_CNT_CLK 158 + +#define R9A09G011_ICB_DRPA_ACLK 159 +#define R9A09G011_ICB_RFX_ACLK 160 +#define R9A09G011_ICB_RFX_PCLK5 161 +#define R9A09G011_ICB_MMC_ACLK 162 + +#define R9A09G011_ICB_MPCLK3 163 +#define R9A09G011_ICB_CIMA_CLK 164 +#define R9A09G011_ICB_CIMB_CLK 165 +#define R9A09G011_ICB_BIMA_CLK 166 +#define R9A09G011_ICB_FCD_CLKAXI 167 +#define R9A09G011_ICB_VD_ACLK4 168 +#define R9A09G011_ICB_MPCLK4 169 +#define R9A09G011_ICB_VCD_PCLK4 170 + +#define R9A09G011_CA53_CLK 171 +#define R9A09G011_CA53_ACLK 172 +#define R9A09G011_CA53_APCLK_DBG 173 +#define R9A09G011_CST_APB_CA53_CLK 174 +#define R9A09G011_CA53_ATCLK 175 +#define R9A09G011_CST_CS_CLK 176 +#define R9A09G011_CA53_TSCLK 177 +#define R9A09G011_CST_TS_CLK 178 +#define R9A09G011_CA53_APCLK_REG 179 + +#define R9A09G011_DRPA_ACLK 180 +#define R9A09G011_DRPA_DCLK 181 +#define R9A09G011_DRPA_INITCLK 182 + +#define R9A09G011_RAMB0_ACLK 183 +#define R9A09G011_RAMB1_ACLK 184 +#define R9A09G011_RAMB2_ACLK 185 +#define R9A09G011_RAMB3_ACLK 186 + +#define R9A09G011_CIMA_CLKAPB 187 +#define R9A09G011_CIMA_CLK 188 +#define R9A09G011_CIMB_CLK 189 +#define R9A09G011_FAFA_CLK 190 +#define R9A09G011_STG_CLKAXI 191 +#define R9A09G011_STG_CLK0 192 + +#define R9A09G011_BIMA_CLKAPB 193 +#define R9A09G011_BIMA_CLK 194 +#define R9A09G011_FAFB_CLK 195 +#define R9A09G011_FCD_CLK 196 +#define R9A09G011_FCD_CLKAXI 197 + +#define R9A09G011_RIM_CLK 198 +#define R9A09G011_VCD_ACLK 199 +#define R9A09G011_VCD_PCLK 200 +#define R9A09G011_JPG0_CLK 201 +#define R9A09G011_JPG0_ACLK 202 + +#define R9A09G011_MMC_CORE_DDRC_CLK 203 +#define R9A09G011_MMC_ACLK 204 +#define R9A09G011_MMC_PCLK 205 +#define R9A09G011_DDI_APBCLK 206 + +/* Resets */ +#define R9A09G011_SYS_RST_N 0 +#define R9A09G011_PFC_PRESETN 1 +#define R9A09G011_RAMA_ARESETN 2 +#define R9A09G011_ROM_ARESETN 3 +#define R9A09G011_DMAA_ARESETN 4 +#define R9A09G011_SEC_ARESETN 5 +#define R9A09G011_SEC_PRESETN 6 +#define R9A09G011_SEC_RSTB 7 +#define R9A09G011_TSU0_RESETN 8 +#define R9A09G011_TSU1_RESETN 9 +#define R9A09G011_PMC_RESET_N 10 + +#define R9A09G011_CST_NTRST 11 +#define R9A09G011_CST_NPOTRST 12 +#define R9A09G011_CST_NTRST2 13 +#define R9A09G011_CST_CS_RESETN 14 +#define R9A09G011_CST_TS_RESETN 15 +#define R9A09G011_CST_TRESETN 16 +#define R9A09G011_CST_SB_RESETN 17 +#define R9A09G011_CST_AHB_RESETN 18 +#define R9A09G011_CST_TS_SB_RESETN 19 +#define R9A09G011_CST_APB_CA53_RESETN 20 +#define R9A09G011_CST_ATB_SB_RESETN 21 + +#define R9A09G011_SDI0_IXRST 22 +#define R9A09G011_SDI1_IXRST 23 +#define R9A09G011_EMM_IXRST 24 +#define R9A09G011_NFI_MARESETN 25 +#define R9A09G011_NFI_REG_RST_N 26 +#define R9A09G011_USB_PRESET_N 27 +#define R9A09G011_USB_DRD_RESET 28 +#define R9A09G011_USB_ARESETN_P 29 +#define R9A09G011_USB_ARESETN_H 30 +#define R9A09G011_ETH0_RST_HW_N 31 +#define R9A09G011_PCI_ARESETN 32 + +#define R9A09G011_SDT_RSTSYSAX 33 +#define R9A09G011_GRP_RESETN 34 +#define R9A09G011_CIF_RST_N 35 +#define R9A09G011_DCU_RSTSYSAX 36 +#define R9A09G011_HMI_RST_N 37 +#define R9A09G011_HMI_PRESETN 38 +#define R9A09G011_LCI_PRESETN 39 +#define R9A09G011_LCI_ARESETN 40 + +#define R9A09G011_AUI_RSTSYSAX 41 +#define R9A09G011_MTR_RSTSYSAX 42 +#define R9A09G011_GFT_RSTSYSAX 43 +#define R9A09G011_ATGA_RSTSYSAX 44 +#define R9A09G011_ATGB_RSTSYSAX 45 +#define R9A09G011_SYC_RST_N 46 + +#define R9A09G011_TIM_GPA_PRESETN 47 +#define R9A09G011_TIM_GPB_PRESETN 48 +#define R9A09G011_TIM_GPC_PRESETN 49 +#define R9A09G011_TIM_GPD_PRESETN 50 +#define R9A09G011_PWM_GPE_PRESETN 51 +#define R9A09G011_PWM_GPF_PRESETN 52 +#define R9A09G011_CSI_GPG_PRESETN 53 +#define R9A09G011_CSI_GPH_PRESETN 54 +#define R9A09G011_IIC_GPA_PRESETN 55 +#define R9A09G011_IIC_GPB_PRESETN 56 +#define R9A09G011_URT_PRESETN 57 +#define R9A09G011_WDT0_PRESETN 58 +#define R9A09G011_WDT1_PRESETN 59 + +#define R9A09G011_ICB_PD_AWO_RST_N 60 +#define R9A09G011_ICB_PD_MMC_RST_N 61 +#define R9A09G011_ICB_PD_VD0_RST_N 62 +#define R9A09G011_ICB_PD_VD1_RST_N 63 +#define R9A09G011_ICB_PD_RFX_RST_N 64 + +#define R9A09G011_CA53_NCPUPORESET0 65 +#define R9A09G011_CA53_NCPUPORESET1 66 +#define R9A09G011_CA53_NCORERESET0 67 +#define R9A09G011_CA53_NCORERESET1 68 +#define R9A09G011_CA53_NPRESETDBG 69 +#define R9A09G011_CA53_L2RESET 70 +#define R9A09G011_CA53_NMISCRESET_HM 71 +#define R9A09G011_CA53_NMISCRESET_SM 72 +#define R9A09G011_CA53_NARESET 73 + +#define R9A09G011_DRPA_ARESETN 74 + +#define R9A09G011_RAMB0_ARESETN 75 +#define R9A09G011_RAMB1_ARESETN 76 +#define R9A09G011_RAMB2_ARESETN 77 +#define R9A09G011_RAMB3_ARESETN 78 + +#define R9A09G011_CIMA_RSTSYSAX 79 +#define R9A09G011_CIMB_RSTSYSAX 80 +#define R9A09G011_FAFA_RSTSYSAX 81 +#define R9A09G011_STG_RSTSYSAX 82 + +#define R9A09G011_BIMA_RSTSYSAX 83 +#define R9A09G011_FAFB_RSTSYSAX 84 +#define R9A09G011_FCD_RSTSYSAX 85 +#define R9A09G011_RIM_RSTSYSAX 86 +#define R9A09G011_VCD_RESETN 87 +#define R9A09G011_JPG_XRESET 88 + +#define R9A09G011_MMC_CORE_DDRC_RSTN 89 +#define R9A09G011_MMC_ARESETN_N 90 +#define R9A09G011_MMC_PRESETN 91 +#define R9A09G011_DDI_PWROK 92 +#define R9A09G011_DDI_RESET 93 +#define R9A09G011_DDI_RESETN_APB 94 + +#endif /* __DT_BINDINGS_CLOCK_R9A09G011_CPG_H__ */ -- cgit v1.2.3 From 4b439e25e29ec336c0e71ef1d1b212c412526518 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 9 Apr 2022 19:17:27 +0200 Subject: mm, hugetlbfs: Allow an arch to always use generic versions of get_unmapped_area functions Unlike most architectures, powerpc can only define at runtime if it is going to use the generic arch_get_unmapped_area() or not. Today, powerpc has a copy of the generic arch_get_unmapped_area() because when selection HAVE_ARCH_UNMAPPED_AREA the generic arch_get_unmapped_area() is not available. Rename it generic_get_unmapped_area() and make it independent of HAVE_ARCH_UNMAPPED_AREA. Do the same for arch_get_unmapped_area_topdown() versus HAVE_ARCH_UNMAPPED_AREA_TOPDOWN. Do the same for hugetlb_get_unmapped_area() versus HAVE_ARCH_HUGETLB_UNMAPPED_AREA. Signed-off-by: Christophe Leroy Reviewed-by: Nicholas Piggin Acked-by: Andrew Morton Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/77f9d3e592f1c8511df9381aa1c4e754651da4d1.1649523076.git.christophe.leroy@csgroup.eu --- include/linux/hugetlb.h | 5 +++++ include/linux/sched/mm.h | 9 +++++++++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ac2a1d758a80..bc97c8458df6 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -519,6 +519,11 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long flags); #endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */ +unsigned long +generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); + /* * huegtlb page specific state flags. These flags are located in page.private * of the hugetlb head page. Functions created via the below macros should be diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 1ad1f4bfa025..da3a32d05b34 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -153,6 +153,15 @@ extern unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); + +unsigned long +generic_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); +unsigned long +generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); #else static inline void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) {} -- cgit v1.2.3 From 2cb4de085f383cb9289083d1bedbaad046f640eb Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 9 Apr 2022 19:17:28 +0200 Subject: mm: Add len and flags parameters to arch_get_mmap_end() Powerpc needs flags and len to make decision on arch_get_mmap_end(). So add them as parameters to arch_get_mmap_end(). Signed-off-by: Christophe Leroy Acked-by: Catalin Marinas Acked-by: Andrew Morton Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/b556daabe7d2bdb2361c4d6130280da7c1ba2c14.1649523076.git.christophe.leroy@csgroup.eu --- include/linux/sched/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index da3a32d05b34..8cd975a8bfeb 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -137,7 +137,7 @@ static inline void mm_update_next_owner(struct mm_struct *mm) #ifdef CONFIG_MMU #ifndef arch_get_mmap_end -#define arch_get_mmap_end(addr) (TASK_SIZE) +#define arch_get_mmap_end(addr, len, flags) (TASK_SIZE) #endif #ifndef arch_get_mmap_base -- cgit v1.2.3 From d77e745613680c54708470402e2b623dcd769681 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sat, 30 Apr 2022 04:51:44 +0200 Subject: regmap: Add bulk read/write callbacks into regmap_config Currently the regmap_config structure only allows the user to implement single element register read/write using .reg_read/.reg_write callbacks. The regmap_bus already implements bulk counterparts of both, and is being misused as a workaround for the missing bulk read/write callbacks in regmap_config by a couple of drivers. To stop this misuse, add the bulk read/write callbacks to regmap_config and call them from the regmap core code. Signed-off-by: Marek Vasut Cc: Jagan Teki Cc: Mark Brown Cc: Maxime Ripard Cc: Robert Foss Cc: Sam Ravnborg Cc: Thomas Zimmermann To: dri-devel@lists.freedesktop.org Link: https://lore.kernel.org/r/20220430025145.640305-1-marex@denx.de Signed-off-by: Mark Brown --- include/linux/regmap.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index de81a94d7b30..8952fa3d0d59 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -299,6 +299,12 @@ typedef void (*regmap_unlock)(void *); * if the function require special handling with lock and reg * handling and the operation cannot be represented as a simple * update_bits operation on a bus such as SPI, I2C, etc. + * @read: Optional callback that if filled will be used to perform all the + * bulk reads from the registers. Data is returned in the buffer used + * to transmit data. + * @write: Same as above for writing. + * @max_raw_read: Max raw read size that can be used on the device. + * @max_raw_write: Max raw write size that can be used on the device. * @fast_io: Register IO is fast. Use a spinlock instead of a mutex * to perform locking. This field is ignored if custom lock/unlock * functions are used (see fields lock/unlock of struct regmap_config). @@ -385,6 +391,12 @@ struct regmap_config { int (*reg_write)(void *context, unsigned int reg, unsigned int val); int (*reg_update_bits)(void *context, unsigned int reg, unsigned int mask, unsigned int val); + /* Bulk read/write */ + int (*read)(void *context, const void *reg_buf, size_t reg_size, + void *val_buf, size_t val_size); + int (*write)(void *context, const void *data, size_t count); + size_t max_raw_read; + size_t max_raw_write; bool fast_io; -- cgit v1.2.3 From ed85a6e6fe7c01faff4504af9d5569e8ba417999 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Thu, 5 May 2022 12:48:17 +0300 Subject: ASoC: SOF: Add initial header file for ipc4 The header file contains essential structure definitions, description of bit fields and bits in the ipc4 header and an internally used ipc4 message container definition. Signed-off-by: Peter Ujfalusi Reviewed-by: Bard Liao Reviewed-by: Rander Wang Reviewed-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Link: https://lore.kernel.org/r/20220505094818.10346-3-peter.ujfalusi@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof/ipc4/header.h | 460 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 460 insertions(+) create mode 100644 include/sound/sof/ipc4/header.h (limited to 'include') diff --git a/include/sound/sof/ipc4/header.h b/include/sound/sof/ipc4/header.h new file mode 100644 index 000000000000..b8b8e5b5e3e1 --- /dev/null +++ b/include/sound/sof/ipc4/header.h @@ -0,0 +1,460 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * Copyright(c) 2022 Intel Corporation. All rights reserved. + */ + +#ifndef __INCLUDE_SOUND_SOF_IPC4_HEADER_H__ +#define __INCLUDE_SOUND_SOF_IPC4_HEADER_H__ + +#include +#include + +/* maximum message size for mailbox Tx/Rx */ +#define SOF_IPC4_MSG_MAX_SIZE 4096 + +/** \addtogroup sof_uapi uAPI + * SOF uAPI specification. + * @{ + */ + +/** + * struct sof_ipc4_msg - Placeholder of an IPC4 message + * @header_u64: IPC4 header as single u64 number + * @primary: Primary, mandatory part of the header + * @extension: Extended part of the header, if not used it should be + * set to 0 + * @data_size: Size of data in bytes pointed by @data_ptr + * @data_ptr: Pointer to the optional payload of a message + */ +struct sof_ipc4_msg { + union { + u64 header_u64; + struct { + u32 primary; + u32 extension; + }; + }; + + size_t data_size; + void *data_ptr; +}; + +/** + * struct sof_ipc4_tuple - Generic type/ID and parameter tuple + * @type: type/ID + * @size: size of the @value array in bytes + * @value: value for the given type + */ +struct sof_ipc4_tuple { + uint32_t type; + uint32_t size; + uint32_t value[]; +} __packed; + +/* + * IPC4 messages have two 32 bit identifier made up as follows :- + * + * header - msg type, msg id, msg direction ... + * extension - extra params such as msg data size in mailbox + * + * These are sent at the start of the IPC message in the mailbox. Messages + * should not be sent in the doorbell (special exceptions for firmware). + */ + +/* + * IPC4 primary header bit allocation for messages + * bit 0-23: message type specific + * bit 24-28: type: enum sof_ipc4_global_msg if target is SOF_IPC4_FW_GEN_MSG + * enum sof_ipc4_module_type if target is SOF_IPC4_MODULE_MSG + * bit 29: response - sof_ipc4_msg_dir + * bit 30: target - enum sof_ipc4_msg_target + * bit 31: reserved, unused + */ + +/* Value of target field - must fit into 1 bit */ +enum sof_ipc4_msg_target { + /* Global FW message */ + SOF_IPC4_FW_GEN_MSG, + + /* Module message */ + SOF_IPC4_MODULE_MSG +}; + +/* Value of type field - must fit into 5 bits */ +enum sof_ipc4_global_msg { + SOF_IPC4_GLB_BOOT_CONFIG, + SOF_IPC4_GLB_ROM_CONTROL, + SOF_IPC4_GLB_IPCGATEWAY_CMD, + + /* 3 .. 12: RESERVED - do not use */ + + SOF_IPC4_GLB_PERF_MEASUREMENTS_CMD = 13, + SOF_IPC4_GLB_CHAIN_DMA, + + SOF_IPC4_GLB_LOAD_MULTIPLE_MODULES, + SOF_IPC4_GLB_UNLOAD_MULTIPLE_MODULES, + + /* pipeline settings */ + SOF_IPC4_GLB_CREATE_PIPELINE, + SOF_IPC4_GLB_DELETE_PIPELINE, + SOF_IPC4_GLB_SET_PIPELINE_STATE, + SOF_IPC4_GLB_GET_PIPELINE_STATE, + SOF_IPC4_GLB_GET_PIPELINE_CONTEXT_SIZE, + SOF_IPC4_GLB_SAVE_PIPELINE, + SOF_IPC4_GLB_RESTORE_PIPELINE, + + /* Loads library (using Code Load or HD/A Host Output DMA) */ + SOF_IPC4_GLB_LOAD_LIBRARY, + + /* 25: RESERVED - do not use */ + + SOF_IPC4_GLB_INTERNAL_MESSAGE = 26, + + /* Notification (FW to SW driver) */ + SOF_IPC4_GLB_NOTIFICATION, + + /* 28 .. 31: RESERVED - do not use */ + + SOF_IPC4_GLB_TYPE_LAST, +}; + +/* Value of response field - must fit into 1 bit */ +enum sof_ipc4_msg_dir { + SOF_IPC4_MSG_REQUEST, + SOF_IPC4_MSG_REPLY, +}; + +enum sof_ipc4_pipeline_state { + SOF_IPC4_PIPE_INVALID_STATE, + SOF_IPC4_PIPE_UNINITIALIZED, + SOF_IPC4_PIPE_RESET, + SOF_IPC4_PIPE_PAUSED, + SOF_IPC4_PIPE_RUNNING, + SOF_IPC4_PIPE_EOS +}; + +/* Generic message fields (bit 24-30) */ + +/* encoded to header's msg_tgt field */ +#define SOF_IPC4_MSG_TARGET_SHIFT 30 +#define SOF_IPC4_MSG_TARGET_MASK BIT(30) +#define SOF_IPC4_MSG_TARGET(x) ((x) << SOF_IPC4_MSG_TARGET_SHIFT) +#define SOF_IPC4_MSG_IS_MODULE_MSG(x) ((x) & SOF_IPC4_MSG_TARGET_MASK ? 1 : 0) + +/* encoded to header's rsp field */ +#define SOF_IPC4_MSG_DIR_SHIFT 29 +#define SOF_IPC4_MSG_DIR_MASK BIT(29) +#define SOF_IPC4_MSG_DIR(x) ((x) << SOF_IPC4_MSG_DIR_SHIFT) + +/* encoded to header's type field */ +#define SOF_IPC4_MSG_TYPE_SHIFT 24 +#define SOF_IPC4_MSG_TYPE_MASK GENMASK(28, 24) +#define SOF_IPC4_MSG_TYPE_SET(x) (((x) << SOF_IPC4_MSG_TYPE_SHIFT) & \ + SOF_IPC4_MSG_TYPE_MASK) +#define SOF_IPC4_MSG_TYPE_GET(x) (((x) & SOF_IPC4_MSG_TYPE_MASK) >> \ + SOF_IPC4_MSG_TYPE_SHIFT) + +/* Global message type specific field definitions */ + +/* pipeline creation ipc msg */ +#define SOF_IPC4_GLB_PIPE_INSTANCE_SHIFT 16 +#define SOF_IPC4_GLB_PIPE_INSTANCE_MASK GENMASK(23, 16) +#define SOF_IPC4_GLB_PIPE_INSTANCE_ID(x) ((x) << SOF_IPC4_GLB_PIPE_INSTANCE_SHIFT) + +#define SOF_IPC4_GLB_PIPE_PRIORITY_SHIFT 11 +#define SOF_IPC4_GLB_PIPE_PRIORITY_MASK GENMASK(15, 11) +#define SOF_IPC4_GLB_PIPE_PRIORITY(x) ((x) << SOF_IPC4_GLB_PIPE_PRIORITY_SHIFT) + +#define SOF_IPC4_GLB_PIPE_MEM_SIZE_SHIFT 0 +#define SOF_IPC4_GLB_PIPE_MEM_SIZE_MASK GENMASK(10, 0) +#define SOF_IPC4_GLB_PIPE_MEM_SIZE(x) ((x) << SOF_IPC4_GLB_PIPE_MEM_SIZE_SHIFT) + +#define SOF_IPC4_GLB_PIPE_EXT_LP_SHIFT 0 +#define SOF_IPC4_GLB_PIPE_EXT_LP_MASK BIT(0) +#define SOF_IPC4_GLB_PIPE_EXT_LP(x) ((x) << SOF_IPC4_GLB_PIPE_EXT_LP_SHIFT) + +/* pipeline set state ipc msg */ +#define SOF_IPC4_GLB_PIPE_STATE_ID_SHIFT 16 +#define SOF_IPC4_GLB_PIPE_STATE_ID_MASK GENMASK(23, 16) +#define SOF_IPC4_GLB_PIPE_STATE_ID(x) ((x) << SOF_IPC4_GLB_PIPE_STATE_ID_SHIFT) + +#define SOF_IPC4_GLB_PIPE_STATE_SHIFT 0 +#define SOF_IPC4_GLB_PIPE_STATE_MASK GENMASK(15, 0) +#define SOF_IPC4_GLB_PIPE_STATE(x) ((x) << SOF_IPC4_GLB_PIPE_STATE_SHIFT) + +enum sof_ipc4_channel_config { + /* one channel only. */ + SOF_IPC4_CHANNEL_CONFIG_MONO, + /* L & R. */ + SOF_IPC4_CHANNEL_CONFIG_STEREO, + /* L, R & LFE; PCM only. */ + SOF_IPC4_CHANNEL_CONFIG_2_POINT_1, + /* L, C & R; MP3 & AAC only. */ + SOF_IPC4_CHANNEL_CONFIG_3_POINT_0, + /* L, C, R & LFE; PCM only. */ + SOF_IPC4_CHANNEL_CONFIG_3_POINT_1, + /* L, R, Ls & Rs; PCM only. */ + SOF_IPC4_CHANNEL_CONFIG_QUATRO, + /* L, C, R & Cs; MP3 & AAC only. */ + SOF_IPC4_CHANNEL_CONFIG_4_POINT_0, + /* L, C, R, Ls & Rs. */ + SOF_IPC4_CHANNEL_CONFIG_5_POINT_0, + /* L, C, R, Ls, Rs & LFE. */ + SOF_IPC4_CHANNEL_CONFIG_5_POINT_1, + /* one channel replicated in two. */ + SOF_IPC4_CHANNEL_CONFIG_DUAL_MONO, + /* Stereo (L,R) in 4 slots, 1st stream: [ L, R, -, - ] */ + SOF_IPC4_CHANNEL_CONFIG_I2S_DUAL_STEREO_0, + /* Stereo (L,R) in 4 slots, 2nd stream: [ -, -, L, R ] */ + SOF_IPC4_CHANNEL_CONFIG_I2S_DUAL_STEREO_1, + /* L, C, R, Ls, Rs & LFE., LS, RS */ + SOF_IPC4_CHANNEL_CONFIG_7_POINT_1, +}; + +enum sof_ipc4_interleaved_style { + SOF_IPC4_CHANNELS_INTERLEAVED, + SOF_IPC4_CHANNELS_NONINTERLEAVED, +}; + +enum sof_ipc4_sample_type { + SOF_IPC4_MSB_INTEGER, /* integer with Most Significant Byte first */ + SOF_IPC4_LSB_INTEGER, /* integer with Least Significant Byte first */ +}; + +struct sof_ipc4_audio_format { + uint32_t sampling_frequency; + uint32_t bit_depth; + uint32_t ch_map; + uint32_t ch_cfg; /* sof_ipc4_channel_config */ + uint32_t interleaving_style; + uint32_t fmt_cfg; /* channels_count valid_bit_depth s_type */ +} __packed __aligned(4); + +#define SOF_IPC4_AUDIO_FORMAT_CFG_CHANNELS_COUNT_SHIFT 0 +#define SOF_IPC4_AUDIO_FORMAT_CFG_CHANNELS_COUNT_MASK GENMASK(7, 0) +#define SOF_IPC4_AUDIO_FORMAT_CFG_CHANNELS_COUNT(x) \ + ((x) & SOF_IPC4_AUDIO_FORMAT_CFG_CHANNELS_COUNT_MASK) +#define SOF_IPC4_AUDIO_FORMAT_CFG_V_BIT_DEPTH_SHIFT 8 +#define SOF_IPC4_AUDIO_FORMAT_CFG_V_BIT_DEPTH_MASK GENMASK(15, 8) +#define SOF_IPC4_AUDIO_FORMAT_CFG_V_BIT_DEPTH(x) \ + (((x) & SOF_IPC4_AUDIO_FORMAT_CFG_V_BIT_DEPTH_MASK) >> \ + SOF_IPC4_AUDIO_FORMAT_CFG_V_BIT_DEPTH_SHIFT) +#define SOF_IPC4_AUDIO_FORMAT_CFG_SAMPLE_TYPE_SHIFT 16 +#define SOF_IPC4_AUDIO_FORMAT_CFG_SAMPLE_TYPE_MASK GENMASK(23, 16) +#define SOF_IPC4_AUDIO_FORMAT_CFG_SAMPLE_TYPE(x) \ + (((x) & SOF_IPC4_AUDIO_FORMAT_CFG_SAMPLE_TYPE_MASK) >> \ + SOF_IPC4_AUDIO_FORMAT_CFG_SAMPLE_TYPE_SHIFT) + +/* Module message type specific field definitions */ + +enum sof_ipc4_module_type { + SOF_IPC4_MOD_INIT_INSTANCE, + SOF_IPC4_MOD_CONFIG_GET, + SOF_IPC4_MOD_CONFIG_SET, + SOF_IPC4_MOD_LARGE_CONFIG_GET, + SOF_IPC4_MOD_LARGE_CONFIG_SET, + SOF_IPC4_MOD_BIND, + SOF_IPC4_MOD_UNBIND, + SOF_IPC4_MOD_SET_DX, + SOF_IPC4_MOD_SET_D0IX, + SOF_IPC4_MOD_ENTER_MODULE_RESTORE, + SOF_IPC4_MOD_EXIT_MODULE_RESTORE, + SOF_IPC4_MOD_DELETE_INSTANCE, + + SOF_IPC4_MOD_TYPE_LAST, +}; + +struct sof_ipc4_base_module_cfg { + uint32_t cpc; /* the max count of Cycles Per Chunk processing */ + uint32_t ibs; /* input Buffer Size (in bytes) */ + uint32_t obs; /* output Buffer Size (in bytes) */ + uint32_t is_pages; /* number of physical pages used */ + struct sof_ipc4_audio_format audio_fmt; +} __packed __aligned(4); + +/* common module ipc msg */ +#define SOF_IPC4_MOD_INSTANCE_SHIFT 16 +#define SOF_IPC4_MOD_INSTANCE_MASK GENMASK(23, 16) +#define SOF_IPC4_MOD_INSTANCE(x) ((x) << SOF_IPC4_MOD_INSTANCE_SHIFT) + +#define SOF_IPC4_MOD_ID_SHIFT 0 +#define SOF_IPC4_MOD_ID_MASK GENMASK(15, 0) +#define SOF_IPC4_MOD_ID(x) ((x) << SOF_IPC4_MOD_ID_SHIFT) + +/* init module ipc msg */ +#define SOF_IPC4_MOD_EXT_PARAM_SIZE_SHIFT 0 +#define SOF_IPC4_MOD_EXT_PARAM_SIZE_MASK GENMASK(15, 0) +#define SOF_IPC4_MOD_EXT_PARAM_SIZE(x) ((x) << SOF_IPC4_MOD_EXT_PARAM_SIZE_SHIFT) + +#define SOF_IPC4_MOD_EXT_PPL_ID_SHIFT 16 +#define SOF_IPC4_MOD_EXT_PPL_ID_MASK GENMASK(23, 16) +#define SOF_IPC4_MOD_EXT_PPL_ID(x) ((x) << SOF_IPC4_MOD_EXT_PPL_ID_SHIFT) + +#define SOF_IPC4_MOD_EXT_CORE_ID_SHIFT 24 +#define SOF_IPC4_MOD_EXT_CORE_ID_MASK GENMASK(27, 24) +#define SOF_IPC4_MOD_EXT_CORE_ID(x) ((x) << SOF_IPC4_MOD_EXT_CORE_ID_SHIFT) + +#define SOF_IPC4_MOD_EXT_DOMAIN_SHIFT 28 +#define SOF_IPC4_MOD_EXT_DOMAIN_MASK BIT(28) +#define SOF_IPC4_MOD_EXT_DOMAIN(x) ((x) << SOF_IPC4_MOD_EXT_DOMAIN_SHIFT) + +/* bind/unbind module ipc msg */ +#define SOF_IPC4_MOD_EXT_DST_MOD_ID_SHIFT 0 +#define SOF_IPC4_MOD_EXT_DST_MOD_ID_MASK GENMASK(15, 0) +#define SOF_IPC4_MOD_EXT_DST_MOD_ID(x) ((x) << SOF_IPC4_MOD_EXT_DST_MOD_ID_SHIFT) + +#define SOF_IPC4_MOD_EXT_DST_MOD_INSTANCE_SHIFT 16 +#define SOF_IPC4_MOD_EXT_DST_MOD_INSTANCE_MASK GENMASK(23, 16) +#define SOF_IPC4_MOD_EXT_DST_MOD_INSTANCE(x) ((x) << SOF_IPC4_MOD_EXT_DST_MOD_INSTANCE_SHIFT) + +#define SOF_IPC4_MOD_EXT_DST_MOD_QUEUE_ID_SHIFT 24 +#define SOF_IPC4_MOD_EXT_DST_MOD_QUEUE_ID_MASK GENMASK(26, 24) +#define SOF_IPC4_MOD_EXT_DST_MOD_QUEUE_ID(x) ((x) << SOF_IPC4_MOD_EXT_DST_MOD_QUEUE_ID_SHIFT) + +#define SOF_IPC4_MOD_EXT_SRC_MOD_QUEUE_ID_SHIFT 27 +#define SOF_IPC4_MOD_EXT_SRC_MOD_QUEUE_ID_MASK GENMASK(29, 27) +#define SOF_IPC4_MOD_EXT_SRC_MOD_QUEUE_ID(x) ((x) << SOF_IPC4_MOD_EXT_SRC_MOD_QUEUE_ID_SHIFT) + +#define MOD_ENABLE_LOG 6 +#define MOD_SYSTEM_TIME 20 + +/* set module large config */ +#define SOF_IPC4_MOD_EXT_MSG_SIZE_SHIFT 0 +#define SOF_IPC4_MOD_EXT_MSG_SIZE_MASK GENMASK(19, 0) +#define SOF_IPC4_MOD_EXT_MSG_SIZE(x) ((x) << SOF_IPC4_MOD_EXT_MSG_SIZE_SHIFT) + +#define SOF_IPC4_MOD_EXT_MSG_PARAM_ID_SHIFT 20 +#define SOF_IPC4_MOD_EXT_MSG_PARAM_ID_MASK GENMASK(27, 20) +#define SOF_IPC4_MOD_EXT_MSG_PARAM_ID(x) ((x) << SOF_IPC4_MOD_EXT_MSG_PARAM_ID_SHIFT) + +#define SOF_IPC4_MOD_EXT_MSG_LAST_BLOCK_SHIFT 28 +#define SOF_IPC4_MOD_EXT_MSG_LAST_BLOCK_MASK BIT(28) +#define SOF_IPC4_MOD_EXT_MSG_LAST_BLOCK(x) ((x) << SOF_IPC4_MOD_EXT_MSG_LAST_BLOCK_SHIFT) + +#define SOF_IPC4_MOD_EXT_MSG_FIRST_BLOCK_SHIFT 29 +#define SOF_IPC4_MOD_EXT_MSG_FIRST_BLOCK_MASK BIT(29) +#define SOF_IPC4_MOD_EXT_MSG_FIRST_BLOCK(x) ((x) << SOF_IPC4_MOD_EXT_MSG_FIRST_BLOCK_SHIFT) + +/* Init instance messagees */ +#define SOF_IPC4_MOD_INIT_BASEFW_MOD_ID 0 +#define SOF_IPC4_MOD_INIT_BASEFW_INSTANCE_ID 0 + +enum sof_ipc4_base_fw_params { + SOF_IPC4_FW_PARAM_ENABLE_LOGS = 6, + SOF_IPC4_FW_PARAM_FW_CONFIG, + SOF_IPC4_FW_PARAM_HW_CONFIG_GET, + SOF_IPC4_FW_PARAM_MODULES_INFO_GET, + SOF_IPC4_FW_PARAM_LIBRARIES_INFO_GET = 16, + SOF_IPC4_FW_PARAM_SYSTEM_TIME = 20, +}; + +enum sof_ipc4_fw_config_params { + SOF_IPC4_FW_CFG_FW_VERSION, + SOF_IPC4_FW_CFG_MEMORY_RECLAIMED, + SOF_IPC4_FW_CFG_SLOW_CLOCK_FREQ_HZ, + SOF_IPC4_FW_CFG_FAST_CLOCK_FREQ_HZ, + SOF_IPC4_FW_CFG_DMA_BUFFER_CONFIG, + SOF_IPC4_FW_CFG_ALH_SUPPORT_LEVEL, + SOF_IPC4_FW_CFG_DL_MAILBOX_BYTES, + SOF_IPC4_FW_CFG_UL_MAILBOX_BYTES, + SOF_IPC4_FW_CFG_TRACE_LOG_BYTES, + SOF_IPC4_FW_CFG_MAX_PPL_COUNT, + SOF_IPC4_FW_CFG_MAX_ASTATE_COUNT, + SOF_IPC4_FW_CFG_MAX_MODULE_PIN_COUNT, + SOF_IPC4_FW_CFG_MODULES_COUNT, + SOF_IPC4_FW_CFG_MAX_MOD_INST_COUNT, + SOF_IPC4_FW_CFG_MAX_LL_TASKS_PER_PRI_COUNT, + SOF_IPC4_FW_CFG_LL_PRI_COUNT, + SOF_IPC4_FW_CFG_MAX_DP_TASKS_COUNT, + SOF_IPC4_FW_CFG_MAX_LIBS_COUNT, + SOF_IPC4_FW_CFG_SCHEDULER_CONFIG, + SOF_IPC4_FW_CFG_XTAL_FREQ_HZ, + SOF_IPC4_FW_CFG_CLOCKS_CONFIG, + SOF_IPC4_FW_CFG_RESERVED, + SOF_IPC4_FW_CFG_POWER_GATING_POLICY, + SOF_IPC4_FW_CFG_ASSERT_MODE, +}; + +struct sof_ipc4_fw_version { + uint16_t major; + uint16_t minor; + uint16_t hotfix; + uint16_t build; +} __packed; + +/* Reply messages */ + +/* + * IPC4 primary header bit allocation for replies + * bit 0-23: status + * bit 24-28: type: enum sof_ipc4_global_msg if target is SOF_IPC4_FW_GEN_MSG + * enum sof_ipc4_module_type if target is SOF_IPC4_MODULE_MSG + * bit 29: response - sof_ipc4_msg_dir + * bit 30: target - enum sof_ipc4_msg_target + * bit 31: reserved, unused + */ + +#define SOF_IPC4_REPLY_STATUS GENMASK(23, 0) + +/* Notification messages */ + +/* + * IPC4 primary header bit allocation for notifications + * bit 0-15: notification type specific + * bit 16-23: enum sof_ipc4_notification_type + * bit 24-28: SOF_IPC4_GLB_NOTIFICATION + * bit 29: response - sof_ipc4_msg_dir + * bit 30: target - enum sof_ipc4_msg_target + * bit 31: reserved, unused + */ + +#define SOF_IPC4_MSG_IS_NOTIFICATION(x) (SOF_IPC4_MSG_TYPE_GET(x) == \ + SOF_IPC4_GLB_NOTIFICATION) + +#define SOF_IPC4_NOTIFICATION_TYPE_SHIFT 16 +#define SOF_IPC4_NOTIFICATION_TYPE_MASK GENMASK(23, 16) +#define SOF_IPC4_NOTIFICATION_TYPE_GET(x) (((x) & SOF_IPC4_NOTIFICATION_TYPE_MASK) >> \ + SOF_IPC4_NOTIFICATION_TYPE_SHIFT) + +/* Value of notification type field - must fit into 8 bits */ +enum sof_ipc4_notification_type { + /* Phrase detected (notification from WoV module) */ + SOF_IPC4_NOTIFY_PHRASE_DETECTED = 4, + /* Event from a resource (pipeline or module instance) */ + SOF_IPC4_NOTIFY_RESOURCE_EVENT, + /* Debug log buffer status changed */ + SOF_IPC4_NOTIFY_LOG_BUFFER_STATUS, + /* Timestamp captured at the link */ + SOF_IPC4_NOTIFY_TIMESTAMP_CAPTURED, + /* FW complete initialization */ + SOF_IPC4_NOTIFY_FW_READY, + /* Audio classifier result (ACA) */ + SOF_IPC4_NOTIFY_FW_AUD_CLASS_RESULT, + /* Exception caught by DSP FW */ + SOF_IPC4_NOTIFY_EXCEPTION_CAUGHT, + /* 11 is skipped by the existing cavs firmware */ + /* Custom module notification */ + SOF_IPC4_NOTIFY_MODULE_NOTIFICATION = 12, + /* 13 is reserved - do not use */ + /* Probe notify data available */ + SOF_IPC4_NOTIFY_PROBE_DATA_AVAILABLE = 14, + /* AM module notifications */ + SOF_IPC4_NOTIFY_ASYNC_MSG_SRVC_MESSAGE, + + SOF_IPC4_NOTIFY_TYPE_LAST, +}; + +struct sof_ipc4_notify_resource_data { + uint32_t resource_type; + uint32_t resource_id; + uint32_t event_type; + uint32_t reserved; + uint32_t data[6]; +} __packed __aligned(4); + +/** @}*/ + +#endif -- cgit v1.2.3 From 6d5f2207447b28dc73c25b3907e7ee32ee66bdbd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 2 May 2022 19:08:27 +0200 Subject: gpio: max732x: Drop unused support for irq and setup code via platform data MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The only user of max732x_platform_data is arch/arm/mach-pxa/littleton.c and it only uses .gpio_base. So drop the other members from the data struct and simplify the driver accordingly. The motivating side effect of this change is that the .remove() callback cannot return a nonzero error code any more which prepares making i2c remove callbacks return void. Signed-off-by: Uwe Kleine-König Signed-off-by: Bartosz Golaszewski --- include/linux/platform_data/max732x.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/max732x.h b/include/linux/platform_data/max732x.h index f231c635faec..423999207cd5 100644 --- a/include/linux/platform_data/max732x.h +++ b/include/linux/platform_data/max732x.h @@ -7,17 +7,5 @@ struct max732x_platform_data { /* number of the first GPIO */ unsigned gpio_base; - - /* interrupt base */ - int irq_base; - - void *context; /* param to setup/teardown */ - - int (*setup)(struct i2c_client *client, - unsigned gpio, unsigned ngpio, - void *context); - int (*teardown)(struct i2c_client *client, - unsigned gpio, unsigned ngpio, - void *context); }; #endif /* __LINUX_I2C_MAX732X_H */ -- cgit v1.2.3 From 8221ecd4e4620cf2f0e942cafcdecac1685f8f16 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 14 Apr 2022 15:04:27 +0200 Subject: PCI/PM: Drop the runtime_d3cold device flag The runtime_d3cold flag is not needed any more, so drop it. Link: https://lore.kernel.org/r/8077784.T7Z3S40VBb@kreacher Signed-off-by: Rafael J. Wysocki Signed-off-by: Bjorn Helgaas Reviewed-by: Mika Westerberg --- include/linux/pci.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 60adf42460ab..3266ac08f8ec 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -379,10 +379,6 @@ struct pci_dev { unsigned int mmio_always_on:1; /* Disallow turning off io/mem decoding during BAR sizing */ unsigned int wakeup_prepared:1; - unsigned int runtime_d3cold:1; /* Whether go through runtime - D3cold, not set for devices - powered on/off by the - corresponding bridge */ unsigned int skip_bus_pm:1; /* Internal: Skip bus-level PM */ unsigned int ignore_hotplug:1; /* Ignore hotplug events */ unsigned int hotplug_user_indicators:1; /* SlotCtl indicators -- cgit v1.2.3 From 6808b7f5c8255d07d79cb8eac40047f59e4154ad Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Wed, 4 May 2022 10:20:46 +0300 Subject: termbits: Convert octal defines to hex MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Many archs have termbits.h as octal numbers. It makes hard for humans to parse the magnitude of large numbers correctly and to compare with hex ones of the same define. Convert octal values to hex. First step is an automated conversion with: for i in $(git ls-files | grep 'termbits\.h'); do awk --non-decimal-data '/^#define\s+[A-Z][A-Z0-9]*\s+0[0-9]/ { l=int(((length($3) - 1) * 3 + 3) / 4); repl = sprintf("0x%0" l "x", $3); print gensub(/[^[:blank:]]+/, repl, 3); next} {print}' $i > $i~; mv $i~ $i; done On top of that, some manual processing on alignment and number of zeros. In addition, small tweaks to formatting of a few comments on the same lines. Signed-off-by: Ilpo Järvinen Acked-by: Arnd Bergmann Acked-by: Michael Ellerman (powerpc) Link: https://lore.kernel.org/r/2c8c96f-a12f-aadc-18ac-34c1d371929c@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/asm-generic/termbits.h | 220 ++++++++++++++++++------------------ 1 file changed, 110 insertions(+), 110 deletions(-) (limited to 'include') diff --git a/include/uapi/asm-generic/termbits.h b/include/uapi/asm-generic/termbits.h index 2fbaf9ae89dd..470fd673ff84 100644 --- a/include/uapi/asm-generic/termbits.h +++ b/include/uapi/asm-generic/termbits.h @@ -60,126 +60,126 @@ struct ktermios { #define VEOL2 16 /* c_iflag bits */ -#define IGNBRK 0000001 -#define BRKINT 0000002 -#define IGNPAR 0000004 -#define PARMRK 0000010 -#define INPCK 0000020 -#define ISTRIP 0000040 -#define INLCR 0000100 -#define IGNCR 0000200 -#define ICRNL 0000400 -#define IUCLC 0001000 -#define IXON 0002000 -#define IXANY 0004000 -#define IXOFF 0010000 -#define IMAXBEL 0020000 -#define IUTF8 0040000 +#define IGNBRK 0x00001 +#define BRKINT 0x00002 +#define IGNPAR 0x00004 +#define PARMRK 0x00008 +#define INPCK 0x00010 +#define ISTRIP 0x00020 +#define INLCR 0x00040 +#define IGNCR 0x00080 +#define ICRNL 0x00100 +#define IUCLC 0x00200 +#define IXON 0x00400 +#define IXANY 0x00800 +#define IXOFF 0x01000 +#define IMAXBEL 0x02000 +#define IUTF8 0x04000 /* c_oflag bits */ -#define OPOST 0000001 -#define OLCUC 0000002 -#define ONLCR 0000004 -#define OCRNL 0000010 -#define ONOCR 0000020 -#define ONLRET 0000040 -#define OFILL 0000100 -#define OFDEL 0000200 -#define NLDLY 0000400 -#define NL0 0000000 -#define NL1 0000400 -#define CRDLY 0003000 -#define CR0 0000000 -#define CR1 0001000 -#define CR2 0002000 -#define CR3 0003000 -#define TABDLY 0014000 -#define TAB0 0000000 -#define TAB1 0004000 -#define TAB2 0010000 -#define TAB3 0014000 -#define XTABS 0014000 -#define BSDLY 0020000 -#define BS0 0000000 -#define BS1 0020000 -#define VTDLY 0040000 -#define VT0 0000000 -#define VT1 0040000 -#define FFDLY 0100000 -#define FF0 0000000 -#define FF1 0100000 +#define OPOST 0x00001 +#define OLCUC 0x00002 +#define ONLCR 0x00004 +#define OCRNL 0x00008 +#define ONOCR 0x00010 +#define ONLRET 0x00020 +#define OFILL 0x00040 +#define OFDEL 0x00080 +#define NLDLY 0x00100 +#define NL0 0x00000 +#define NL1 0x00100 +#define CRDLY 0x00600 +#define CR0 0x00000 +#define CR1 0x00200 +#define CR2 0x00400 +#define CR3 0x00600 +#define TABDLY 0x01800 +#define TAB0 0x00000 +#define TAB1 0x00800 +#define TAB2 0x01000 +#define TAB3 0x01800 +#define XTABS 0x01800 +#define BSDLY 0x02000 +#define BS0 0x00000 +#define BS1 0x02000 +#define VTDLY 0x04000 +#define VT0 0x00000 +#define VT1 0x04000 +#define FFDLY 0x08000 +#define FF0 0x00000 +#define FF1 0x08000 /* c_cflag bit meaning */ -#define CBAUD 0010017 -#define B0 0000000 /* hang up */ -#define B50 0000001 -#define B75 0000002 -#define B110 0000003 -#define B134 0000004 -#define B150 0000005 -#define B200 0000006 -#define B300 0000007 -#define B600 0000010 -#define B1200 0000011 -#define B1800 0000012 -#define B2400 0000013 -#define B4800 0000014 -#define B9600 0000015 -#define B19200 0000016 -#define B38400 0000017 +#define CBAUD 0x0000100f +#define B0 0x00000000 /* hang up */ +#define B50 0x00000001 +#define B75 0x00000002 +#define B110 0x00000003 +#define B134 0x00000004 +#define B150 0x00000005 +#define B200 0x00000006 +#define B300 0x00000007 +#define B600 0x00000008 +#define B1200 0x00000009 +#define B1800 0x0000000a +#define B2400 0x0000000b +#define B4800 0x0000000c +#define B9600 0x0000000d +#define B19200 0x0000000e +#define B38400 0x0000000f #define EXTA B19200 #define EXTB B38400 -#define CSIZE 0000060 -#define CS5 0000000 -#define CS6 0000020 -#define CS7 0000040 -#define CS8 0000060 -#define CSTOPB 0000100 -#define CREAD 0000200 -#define PARENB 0000400 -#define PARODD 0001000 -#define HUPCL 0002000 -#define CLOCAL 0004000 -#define CBAUDEX 0010000 -#define BOTHER 0010000 -#define B57600 0010001 -#define B115200 0010002 -#define B230400 0010003 -#define B460800 0010004 -#define B500000 0010005 -#define B576000 0010006 -#define B921600 0010007 -#define B1000000 0010010 -#define B1152000 0010011 -#define B1500000 0010012 -#define B2000000 0010013 -#define B2500000 0010014 -#define B3000000 0010015 -#define B3500000 0010016 -#define B4000000 0010017 -#define CIBAUD 002003600000 /* input baud rate */ -#define CMSPAR 010000000000 /* mark or space (stick) parity */ -#define CRTSCTS 020000000000 /* flow control */ +#define CSIZE 0x00000030 +#define CS5 0x00000000 +#define CS6 0x00000010 +#define CS7 0x00000020 +#define CS8 0x00000030 +#define CSTOPB 0x00000040 +#define CREAD 0x00000080 +#define PARENB 0x00000100 +#define PARODD 0x00000200 +#define HUPCL 0x00000400 +#define CLOCAL 0x00000800 +#define CBAUDEX 0x00001000 +#define BOTHER 0x00001000 +#define B57600 0x00001001 +#define B115200 0x00001002 +#define B230400 0x00001003 +#define B460800 0x00001004 +#define B500000 0x00001005 +#define B576000 0x00001006 +#define B921600 0x00001007 +#define B1000000 0x00001008 +#define B1152000 0x00001009 +#define B1500000 0x0000100a +#define B2000000 0x0000100b +#define B2500000 0x0000100c +#define B3000000 0x0000100d +#define B3500000 0x0000100e +#define B4000000 0x0000100f +#define CIBAUD 0x100f0000 /* input baud rate */ +#define CMSPAR 0x40000000 /* mark or space (stick) parity */ +#define CRTSCTS 0x80000000 /* flow control */ #define IBSHIFT 16 /* Shift from CBAUD to CIBAUD */ /* c_lflag bits */ -#define ISIG 0000001 -#define ICANON 0000002 -#define XCASE 0000004 -#define ECHO 0000010 -#define ECHOE 0000020 -#define ECHOK 0000040 -#define ECHONL 0000100 -#define NOFLSH 0000200 -#define TOSTOP 0000400 -#define ECHOCTL 0001000 -#define ECHOPRT 0002000 -#define ECHOKE 0004000 -#define FLUSHO 0010000 -#define PENDIN 0040000 -#define IEXTEN 0100000 -#define EXTPROC 0200000 +#define ISIG 0x00001 +#define ICANON 0x00002 +#define XCASE 0x00004 +#define ECHO 0x00008 +#define ECHOE 0x00010 +#define ECHOK 0x00020 +#define ECHONL 0x00040 +#define NOFLSH 0x00080 +#define TOSTOP 0x00100 +#define ECHOCTL 0x00200 +#define ECHOPRT 0x00400 +#define ECHOKE 0x00800 +#define FLUSHO 0x01000 +#define PENDIN 0x04000 +#define IEXTEN 0x08000 +#define EXTPROC 0x10000 /* tcflow() and TCXONC use these */ #define TCOOFF 0 -- cgit v1.2.3 From 26817fb7b066b21c66cd41d75ed2137e046045be Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 4 May 2022 09:27:10 -0400 Subject: Revert "fbdev: fbmem: add a helper to determine if an aperture is used by a fw fb" This reverts commit 9a45ac2320d0a6ae01880a30d4b86025fce4061b. This was added a helper for amdgpu to workaround a runtime pm regression caused by a runtime pm fix in efifb. We now have a better workaround in amdgpu in commit f95af4a9236695 ("drm/amdgpu: don't runtime suspend if there are displays attached (v3)") so this workaround is no longer necessary. Since amdgpu was the only user of this interface, we can remove it. Reviewed-by: Javier Martinez Canillas Acked-by: Daniel Vetter Signed-off-by: Alex Deucher --- include/linux/fb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/fb.h b/include/linux/fb.h index 9a77ab615c36..147d582dab41 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -612,7 +612,6 @@ extern int remove_conflicting_pci_framebuffers(struct pci_dev *pdev, const char *name); extern int remove_conflicting_framebuffers(struct apertures_struct *a, const char *name, bool primary); -extern bool is_firmware_framebuffer(struct apertures_struct *a); extern int fb_prepare_logo(struct fb_info *fb_info, int rotate); extern int fb_show_logo(struct fb_info *fb_info, int rotate); extern char* fb_get_buffer_offset(struct fb_info *info, struct fb_pixmap *buf, u32 size); -- cgit v1.2.3 From c4a67a21a6d255ddcbaa076c0412aad73c7e0c02 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 4 May 2022 08:40:37 -0700 Subject: Revert "Merge branch 'mlxsw-line-card-model'" This reverts commit 5e927a9f4b9f29d78a7c7d66ea717bb5c8bbad8e, reversing changes made to cfc1d91a7d78cf9de25b043d81efcc16966d55b3. The discussion is still ongoing so let's remove the uAPI until the discussion settles. Link: https://lore.kernel.org/all/20220425090021.32e9a98f@kernel.org/ Reviewed-by: Ido Schimmel Link: https://lore.kernel.org/r/20220504154037.539442-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 18 +----------------- include/uapi/linux/devlink.h | 5 ----- 2 files changed, 1 insertion(+), 22 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 062895973656..2a2a2a0c93f7 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -150,9 +150,6 @@ struct devlink_port_new_attrs { sfnum_valid:1; }; -struct devlink_info_req; -struct devlink_linecard_device; - /** * struct devlink_linecard_ops - Linecard operations * @provision: callback to provision the linecard slot with certain @@ -171,8 +168,6 @@ struct devlink_linecard_device; * provisioned. * @types_count: callback to get number of supported types * @types_get: callback to get next type in list - * @info_get: callback to get linecard info - * @device_info_get: callback to get linecard device info */ struct devlink_linecard_ops { int (*provision)(struct devlink_linecard *linecard, void *priv, @@ -187,12 +182,6 @@ struct devlink_linecard_ops { void (*types_get)(struct devlink_linecard *linecard, void *priv, unsigned int index, const char **type, const void **type_priv); - int (*info_get)(struct devlink_linecard *linecard, void *priv, - struct devlink_info_req *req, - struct netlink_ext_ack *extack); - int (*device_info_get)(struct devlink_linecard_device *device, - void *priv, struct devlink_info_req *req, - struct netlink_ext_ack *extack); }; struct devlink_sb_pool_info { @@ -639,6 +628,7 @@ struct devlink_flash_update_params { #define DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK BIT(1) struct devlink_region; +struct devlink_info_req; /** * struct devlink_region_ops - Region operations @@ -1588,12 +1578,6 @@ struct devlink_linecard * devlink_linecard_create(struct devlink *devlink, unsigned int linecard_index, const struct devlink_linecard_ops *ops, void *priv); void devlink_linecard_destroy(struct devlink_linecard *linecard); -struct devlink_linecard_device * -devlink_linecard_device_create(struct devlink_linecard *linecard, - unsigned int device_index, void *priv); -void -devlink_linecard_device_destroy(struct devlink_linecard *linecard, - struct devlink_linecard_device *linecard_device); void devlink_linecard_provision_set(struct devlink_linecard *linecard, const char *type); void devlink_linecard_provision_clear(struct devlink_linecard *linecard); diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index fb8c3864457f..b3d40a5d72ff 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -136,8 +136,6 @@ enum devlink_command { DEVLINK_CMD_LINECARD_NEW, DEVLINK_CMD_LINECARD_DEL, - DEVLINK_CMD_LINECARD_INFO_GET, /* can dump */ - /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 @@ -577,9 +575,6 @@ enum devlink_attr { DEVLINK_ATTR_LINECARD_STATE, /* u8 */ DEVLINK_ATTR_LINECARD_TYPE, /* string */ DEVLINK_ATTR_LINECARD_SUPPORTED_TYPES, /* nested */ - DEVLINK_ATTR_LINECARD_DEVICE_LIST, /* nested */ - DEVLINK_ATTR_LINECARD_DEVICE, /* nested */ - DEVLINK_ATTR_LINECARD_DEVICE_INDEX, /* u32 */ /* add new attributes above here, update the policy in devlink.c */ -- cgit v1.2.3 From 0455d4ccec548b0fb51db39a4d3350a7a80a0222 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 26 Apr 2022 12:11:33 -0600 Subject: io_uring: add POLL_FIRST support for send/sendmsg and recv/recvmsg If IORING_RECVSEND_POLL_FIRST is set for recv/recvmsg or send/sendmsg, then we arm poll first rather than attempt a receive or send upfront. This can be useful if we expect there to be no data (or space) available for the request, as we can then avoid wasting time on the initial issue attempt. Reviewed-by: Hao Xu Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index fad63564678a..06621a278cb6 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -213,6 +213,16 @@ enum { #define IORING_ASYNC_CANCEL_FD (1U << 1) #define IORING_ASYNC_CANCEL_ANY (1U << 2) +/* + * send/sendmsg and recv/recvmsg flags (sqe->addr2) + * + * IORING_RECVSEND_POLL_FIRST If set, instead of first attempting to send + * or receive and arm poll if that yields an + * -EAGAIN result, arm poll upfront and skip + * the initial transfer attempt. + */ +#define IORING_RECVSEND_POLL_FIRST (1U << 0) + /* * IO completion data structure (Completion Queue Entry) */ -- cgit v1.2.3 From c67b627e99affe4865b13557d68152ad4c35515c Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 4 May 2022 10:09:47 -0700 Subject: net: Make msg_zerocopy_alloc static msg_zerocopy_alloc is only used by msg_zerocopy_realloc; remove the export and make static in skbuff.c Signed-off-by: David Ahern Acked-by: Jonathan Lemon Link: https://lore.kernel.org/r/20220504170947.18773-1-dsahern@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3270cb72e4d8..5c2599e3fe7d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1665,7 +1665,6 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) } #endif -struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size); struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); -- cgit v1.2.3 From 85db6352fc8a158a893151baa1716463d34a20d0 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Wed, 4 May 2022 11:09:14 +0300 Subject: net: Fix features skip in for_each_netdev_feature() The find_next_netdev_feature() macro gets the "remaining length", not bit index. Passing "bit - 1" for the following iteration is wrong as it skips the adjacent bit. Pass "bit" instead. Fixes: 3b89ea9c5902 ("net: Fix for_each_netdev_feature on Big endian") Signed-off-by: Tariq Toukan Reviewed-by: Gal Pressman Link: https://lore.kernel.org/r/20220504080914.1918-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- include/linux/netdev_features.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 2c6b9e416225..7c2d77d75a88 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -169,7 +169,7 @@ enum { #define NETIF_F_HW_HSR_FWD __NETIF_F(HW_HSR_FWD) #define NETIF_F_HW_HSR_DUP __NETIF_F(HW_HSR_DUP) -/* Finds the next feature with the highest number of the range of start till 0. +/* Finds the next feature with the highest number of the range of start-1 till 0. */ static inline int find_next_netdev_feature(u64 feature, unsigned long start) { @@ -188,7 +188,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) for ((bit) = find_next_netdev_feature((mask_addr), \ NETDEV_FEATURE_COUNT); \ (bit) >= 0; \ - (bit) = find_next_netdev_feature((mask_addr), (bit) - 1)) + (bit) = find_next_netdev_feature((mask_addr), (bit))) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ -- cgit v1.2.3 From ea66758c1795cef81dc59cd5240e9d0f5c5207cf Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 4 May 2022 14:54:06 -0700 Subject: tcp: allow MPTCP to update the announced window The MPTCP RFC requires that the MPTCP-level receive window's right edge never moves backward. Currently the MPTCP code enforces such constraint while tracking the right edge, but it does not reflects it on the wire, as MPTCP lacks a suitable hook to update accordingly the TCP header. This change modifies the existing mptcp_write_options() hook, providing the current packet's TCP header to the MPTCP protocol, so that the next patch could implement the above mentioned constraint. No functional changes intended. Signed-off-by: Paolo Abeni Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- include/net/mptcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 8b1afd6f5cc4..d4ec894ce67b 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -125,7 +125,7 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, struct mptcp_out_options *opts); bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb); -void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, +void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp, struct mptcp_out_options *opts); void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info); -- cgit v1.2.3 From e1846cff2fe614d93a2f89461b5935678fd34bd9 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 5 May 2022 02:54:59 +0300 Subject: net: mscc: ocelot: mark traps with a bool instead of keeping them in a list Since the blamed commit, VCAP filters can appear on more than one list. If their action is "trap", they are chained on ocelot->traps via filter->trap_list. This is in addition to their normal placement on the VCAP block->rules list head. Therefore, when we free a VCAP filter, we must remove it from all lists it is a member of, including ocelot->traps. There are at least 2 bugs which are direct consequences of this design decision. First is the incorrect usage of list_empty(), meant to denote whether "filter" is chained into ocelot->traps via filter->trap_list. This does not do the correct thing, because list_empty() checks whether "head->next == head", but in our case, head->next == head->prev == NULL. So we dereference NULL pointers and die when we call list_del(). Second is the fact that not all places that should remove the filter from ocelot->traps do so. One example is ocelot_vcap_block_remove_filter(), which is where we have the main kfree(filter). By keeping freed filters in ocelot->traps we end up in a use-after-free in felix_update_trapping_destinations(). Attempting to fix all the buggy patterns is a whack-a-mole game which makes the driver unmaintainable. Actually this is what the previous patch version attempted to do: https://patchwork.kernel.org/project/netdevbpf/patch/20220503115728.834457-3-vladimir.oltean@nxp.com/ but it introduced another set of bugs, because there are other places in which create VCAP filters, not just ocelot_vcap_filter_create(): - ocelot_trap_add() - felix_tag_8021q_vlan_add_rx() - felix_tag_8021q_vlan_add_tx() Relying on the convention that all those code paths must call INIT_LIST_HEAD(&filter->trap_list) is not going to scale. So let's do what should have been done in the first place and keep a bool in struct ocelot_vcap_filter which denotes whether we are looking at a trapping rule or not. Iterating now happens over the main VCAP IS2 block->rules. The advantage is that we no longer risk having stale references to a freed filter, since it is only present in that list. Fixes: e42bd4ed09aa ("net: mscc: ocelot: keep traps in a list") Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot_vcap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index 7b2bf9b1fe69..de26c992f821 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -681,7 +681,6 @@ struct ocelot_vcap_id { struct ocelot_vcap_filter { struct list_head list; - struct list_head trap_list; enum ocelot_vcap_filter_type type; int block_id; @@ -695,6 +694,7 @@ struct ocelot_vcap_filter { struct ocelot_vcap_stats stats; /* For VCAP IS1 and IS2 */ bool take_ts; + bool is_trap; unsigned long ingress_port_mask; /* For VCAP ES0 */ struct ocelot_vcap_port ingress_port; -- cgit v1.2.3 From 7e555e9975698924d7f3ead154847bcf8f5cd40c Mon Sep 17 00:00:00 2001 From: Adam Skladowski Date: Tue, 26 Apr 2022 09:30:47 +0200 Subject: dt-bindings: clk: qcom: gcc-msm8976: Add modem reset Add modem reset for MSM8976. Signed-off-by: Adam Skladowski Acked-by: Krzysztof Kozlowski Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220426073048.11509-3-a39.skl@gmail.com --- include/dt-bindings/clock/qcom,gcc-msm8976.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,gcc-msm8976.h b/include/dt-bindings/clock/qcom,gcc-msm8976.h index 51955fd49426..5351f48b2068 100644 --- a/include/dt-bindings/clock/qcom,gcc-msm8976.h +++ b/include/dt-bindings/clock/qcom,gcc-msm8976.h @@ -224,6 +224,7 @@ #define RST_CAMSS_CSI_VFE1_BCR 7 #define RST_CAMSS_VFE1_BCR 8 #define RST_CAMSS_CPP_BCR 9 +#define RST_MSS_BCR 10 /* GDSCs */ #define VENUS_GDSC 0 -- cgit v1.2.3 From b01a277a0520edd5c815af346f05ef2c747919b6 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 5 May 2022 13:06:38 +0300 Subject: xfrm: free not used XFRM_ESP_NO_TRAILER flag After removal of Innova IPsec support from mlx5 driver, the last user of this XFRM_ESP_NO_TRAILER was gone too. This means that we can safely remove it as no other hardware is capable (or need) to remove ESP trailer. Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky Acked-by: David S. Miller Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 6fb899ff5afc..b41278abeeaa 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1006,7 +1006,7 @@ struct xfrm_offload { #define CRYPTO_FALLBACK 8 #define XFRM_GSO_SEGMENT 16 #define XFRM_GRO 32 -#define XFRM_ESP_NO_TRAILER 64 +/* 64 is free */ #define XFRM_DEV_RESUME 128 #define XFRM_XMIT 256 -- cgit v1.2.3 From a36708e646586f74d073199828ed878b223e988d Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 5 May 2022 13:06:39 +0300 Subject: xfrm: delete not used number of external headers num_exthdrs is set but never used, so delete it. Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky Acked-by: David S. Miller Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index b41278abeeaa..4e097423116c 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -131,7 +131,6 @@ struct xfrm_state_offload { netdevice_tracker dev_tracker; struct net_device *real_dev; unsigned long offload_handle; - unsigned int num_exthdrs; u8 flags; }; -- cgit v1.2.3 From 87e0a94e60ea2e29be9dec6bc146fbc9861a4055 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 5 May 2022 13:06:40 +0300 Subject: xfrm: rename xfrm_state_offload struct to allow reuse The struct xfrm_state_offload has all fields needed to hold information for offloaded policies too. In order to do not create new struct with same fields, let's rename existing one and reuse it later. Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky Acked-by: David S. Miller Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 4e097423116c..bb20278d689c 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -126,7 +126,7 @@ struct xfrm_state_walk { struct xfrm_address_filter *filter; }; -struct xfrm_state_offload { +struct xfrm_dev_offload { struct net_device *dev; netdevice_tracker dev_tracker; struct net_device *real_dev; @@ -246,7 +246,7 @@ struct xfrm_state { struct xfrm_lifetime_cur curlft; struct hrtimer mtimer; - struct xfrm_state_offload xso; + struct xfrm_dev_offload xso; /* used to fix curlft->add_time when changing date */ long saved_tmo; @@ -1865,7 +1865,7 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x); static inline void xfrm_dev_state_advance_esn(struct xfrm_state *x) { - struct xfrm_state_offload *xso = &x->xso; + struct xfrm_dev_offload *xso = &x->xso; if (xso->dev && xso->dev->xfrmdev_ops->xdo_dev_state_advance_esn) xso->dev->xfrmdev_ops->xdo_dev_state_advance_esn(x); @@ -1891,7 +1891,7 @@ static inline bool xfrm_dst_offload_ok(struct dst_entry *dst) static inline void xfrm_dev_state_delete(struct xfrm_state *x) { - struct xfrm_state_offload *xso = &x->xso; + struct xfrm_dev_offload *xso = &x->xso; if (xso->dev) xso->dev->xfrmdev_ops->xdo_dev_state_delete(x); @@ -1899,7 +1899,7 @@ static inline void xfrm_dev_state_delete(struct xfrm_state *x) static inline void xfrm_dev_state_free(struct xfrm_state *x) { - struct xfrm_state_offload *xso = &x->xso; + struct xfrm_dev_offload *xso = &x->xso; struct net_device *dev = xso->dev; if (dev && dev->xfrmdev_ops) { -- cgit v1.2.3 From 482db2f1dd211f73ad9d71e33ae15c1df6379982 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 5 May 2022 13:06:41 +0300 Subject: xfrm: store and rely on direction to construct offload flags XFRM state doesn't need anything from flags except to understand direction, so store it separately. For future patches, such change will allow us to reuse xfrm_dev_offload for policy offload too, which has three possible directions instead of two. Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index bb20278d689c..45422f7be0c5 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -126,12 +126,18 @@ struct xfrm_state_walk { struct xfrm_address_filter *filter; }; +enum { + XFRM_DEV_OFFLOAD_IN = 1, + XFRM_DEV_OFFLOAD_OUT, +}; + struct xfrm_dev_offload { struct net_device *dev; netdevice_tracker dev_tracker; struct net_device *real_dev; unsigned long offload_handle; u8 flags; + u8 dir : 2; }; struct xfrm_mode { -- cgit v1.2.3 From 254c4a824c7c6a53360bc4974710e4213b8b7f5d Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Thu, 5 May 2022 13:06:45 +0300 Subject: xfrm: drop not needed flags variable in XFRM offload struct After drivers were converted to rely on direction, the flags is not used anymore and can be removed. Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 45422f7be0c5..736c349de8bf 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -136,7 +136,6 @@ struct xfrm_dev_offload { netdevice_tracker dev_tracker; struct net_device *real_dev; unsigned long offload_handle; - u8 flags; u8 dir : 2; }; -- cgit v1.2.3 From bb17d110cbf270d5247a6e261c5ad50e362d1675 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 29 Apr 2022 21:59:45 +0200 Subject: rpmsg: Fix calling device_lock() on non-initialized device driver_set_override() helper uses device_lock() so it should not be called before rpmsg_register_device() (which calls device_register()). Effect can be seen with CONFIG_DEBUG_MUTEXES: DEBUG_LOCKS_WARN_ON(lock->magic != lock) WARNING: CPU: 3 PID: 57 at kernel/locking/mutex.c:582 __mutex_lock+0x1ec/0x430 ... Call trace: __mutex_lock+0x1ec/0x430 mutex_lock_nested+0x44/0x50 driver_set_override+0x124/0x150 qcom_glink_native_probe+0x30c/0x3b0 glink_rpm_probe+0x274/0x350 platform_probe+0x6c/0xe0 really_probe+0x17c/0x3d0 __driver_probe_device+0x114/0x190 driver_probe_device+0x3c/0xf0 ... Refactor the rpmsg_register_device() function to use two-step device registering (initialization + add) and call driver_set_override() in proper moment. This moves the code around, so while at it also NULL-ify the rpdev->driver_override in error path to be sure it won't be kfree() second time. Fixes: 42cd402b8fd4 ("rpmsg: Fix kfree() of static memory on setting driver_override") Reported-by: Marek Szyprowski Signed-off-by: Krzysztof Kozlowski Tested-by: Marek Szyprowski Link: https://lore.kernel.org/r/20220429195946.1061725-2-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/rpmsg.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/rpmsg.h b/include/linux/rpmsg.h index 20c8cd1cde21..523c98b96cb4 100644 --- a/include/linux/rpmsg.h +++ b/include/linux/rpmsg.h @@ -165,6 +165,8 @@ static inline __rpmsg64 cpu_to_rpmsg64(struct rpmsg_device *rpdev, u64 val) #if IS_ENABLED(CONFIG_RPMSG) +int rpmsg_register_device_override(struct rpmsg_device *rpdev, + const char *driver_override); int rpmsg_register_device(struct rpmsg_device *rpdev); int rpmsg_unregister_device(struct device *parent, struct rpmsg_channel_info *chinfo); @@ -192,6 +194,12 @@ ssize_t rpmsg_get_mtu(struct rpmsg_endpoint *ept); #else +static inline int rpmsg_register_device_override(struct rpmsg_device *rpdev, + const char *driver_override) +{ + return -ENXIO; +} + static inline int rpmsg_register_device(struct rpmsg_device *rpdev) { return -ENXIO; -- cgit v1.2.3 From d143b9db8069f0e2a0fa34484e806a55a0dd4855 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 27 Apr 2022 11:04:42 +0200 Subject: export: fix string handling of namespace in EXPORT_SYMBOL_NS Commit c3a6cf19e695 ("export: avoid code duplication in include/linux/export.h") broke the ability for a defined string to be used as a namespace value. Fix this up by using stringify to properly encode the namespace name. Fixes: c3a6cf19e695 ("export: avoid code duplication in include/linux/export.h") Cc: Miroslav Benes Cc: Emil Velikov Cc: Jessica Yu Cc: Quentin Perret Cc: Matthias Maennich Reviewed-by: Masahiro Yamada Link: https://lore.kernel.org/r/20220427090442.2105905-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/export.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/export.h b/include/linux/export.h index 27d848712b90..5910ccb66ca2 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -2,6 +2,8 @@ #ifndef _LINUX_EXPORT_H #define _LINUX_EXPORT_H +#include + /* * Export symbols from the kernel to modules. Forked from module.h * to reduce the amount of pointless cruft we feed to gcc when only @@ -154,7 +156,6 @@ struct kernel_symbol { #endif /* CONFIG_MODULES */ #ifdef DEFAULT_SYMBOL_NAMESPACE -#include #define _EXPORT_SYMBOL(sym, sec) __EXPORT_SYMBOL(sym, sec, __stringify(DEFAULT_SYMBOL_NAMESPACE)) #else #define _EXPORT_SYMBOL(sym, sec) __EXPORT_SYMBOL(sym, sec, "") @@ -162,8 +163,8 @@ struct kernel_symbol { #define EXPORT_SYMBOL(sym) _EXPORT_SYMBOL(sym, "") #define EXPORT_SYMBOL_GPL(sym) _EXPORT_SYMBOL(sym, "_gpl") -#define EXPORT_SYMBOL_NS(sym, ns) __EXPORT_SYMBOL(sym, "", #ns) -#define EXPORT_SYMBOL_NS_GPL(sym, ns) __EXPORT_SYMBOL(sym, "_gpl", #ns) +#define EXPORT_SYMBOL_NS(sym, ns) __EXPORT_SYMBOL(sym, "", __stringify(ns)) +#define EXPORT_SYMBOL_NS_GPL(sym, ns) __EXPORT_SYMBOL(sym, "_gpl", __stringify(ns)) #endif /* !__ASSEMBLY__ */ -- cgit v1.2.3 From c3d438eeb5413111889edef10cb5fcc2c0fb8bc9 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Wed, 27 Apr 2022 09:08:06 +0100 Subject: arch_topology: Trace the update thermal pressure Add trace event to capture the moment of the call for updating the thermal pressure value. It's helpful to investigate how often those events occur in a system dealing with throttling. This trace event is needed since the old 'cdev_update' might not be used by some drivers. The old 'cdev_update' trace event only provides a cooling state value: [0, n]. That state value then needs additional tools to translate it: state -> freq -> capacity -> thermal pressure. This new trace event just stores proper thermal pressure value in the trace buffer, no need for additional logic. This is helpful for cooperation when someone can simply sends to the list the trace buffer output from the platform (no need from additional information from other subsystems). There are also platforms which due to some design reasons don't use cooling devices and thus don't trigger old 'cdev_update' trace event. They are also important and measuring latency for the thermal signal raising/decaying characteristics is in scope. This new trace event would cover them as well. We already have a trace point 'pelt_thermal_tp' which after a change to trace event can be paired with this new 'thermal_pressure_update' and derive more insight what is going on in the system under thermal pressure (and why). Signed-off-by: Lukasz Luba Acked-by: Sudeep Holla Link: https://lore.kernel.org/r/20220427080806.1906-1-lukasz.luba@arm.com Signed-off-by: Greg Kroah-Hartman --- include/trace/events/thermal_pressure.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) create mode 100644 include/trace/events/thermal_pressure.h (limited to 'include') diff --git a/include/trace/events/thermal_pressure.h b/include/trace/events/thermal_pressure.h new file mode 100644 index 000000000000..b68680201360 --- /dev/null +++ b/include/trace/events/thermal_pressure.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM thermal_pressure + +#if !defined(_TRACE_THERMAL_PRESSURE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_THERMAL_PRESSURE_H + +#include + +TRACE_EVENT(thermal_pressure_update, + TP_PROTO(int cpu, unsigned long thermal_pressure), + TP_ARGS(cpu, thermal_pressure), + + TP_STRUCT__entry( + __field(unsigned long, thermal_pressure) + __field(int, cpu) + ), + + TP_fast_assign( + __entry->thermal_pressure = thermal_pressure; + __entry->cpu = cpu; + ), + + TP_printk("cpu=%d thermal_pressure=%lu", __entry->cpu, __entry->thermal_pressure) +); +#endif /* _TRACE_THERMAL_PRESSURE_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From 6de4d4eca9a2d0195f802bc97b0e9aeeaff05900 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Thu, 28 Apr 2022 02:24:27 -0400 Subject: platform/x86: pmc_atom: remove unused pmc_atom_write() This function isn't used anywhere in the driver or anywhere in tree. So remove it. It can always be re-added if/when a use arises. Cc: Andy Shevchenko Cc: Aubrey Li Cc: Hans de Goede Cc: Mark Gross Cc: platform-driver-x86@vger.kernel.org Signed-off-by: Paul Gortmaker Link: https://lore.kernel.org/r/20220428062430.31010-2-paul.gortmaker@windriver.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- include/linux/platform_data/x86/pmc_atom.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/platform_data/x86/pmc_atom.h b/include/linux/platform_data/x86/pmc_atom.h index 022bcea9edec..6807839c718b 100644 --- a/include/linux/platform_data/x86/pmc_atom.h +++ b/include/linux/platform_data/x86/pmc_atom.h @@ -144,6 +144,5 @@ #define SLEEP_ENABLE 0x2000 extern int pmc_atom_read(int offset, u32 *value); -extern int pmc_atom_write(int offset, u32 value); #endif /* PMC_ATOM_H */ -- cgit v1.2.3 From 6df6398f7c8b481ce83f28143bc08a5231616deb Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 5 May 2022 19:51:31 -0700 Subject: net: add netif_inherit_tso_max() To make later patches smaller create a helper for inheriting the TSO limitations of a lower device. The TSO in the name is not an accident, subsequent patches will replace GSO with TSO in more names. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index eaf66e57d891..006bb5c0e413 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4895,6 +4895,9 @@ static inline void netif_set_gro_max_size(struct net_device *dev, WRITE_ONCE(dev->gro_max_size, size); } +void netif_inherit_tso_max(struct net_device *to, + const struct net_device *from); + static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol, int pulled_hlen, u16 mac_offset, int mac_len) -- cgit v1.2.3 From 14d7b8122fd591693a2388b98563707ba72c6780 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 5 May 2022 19:51:32 -0700 Subject: net: don't allow user space to lift the device limits Up until commit 46e6b992c250 ("rtnetlink: allow GSO maximums to be set on device creation") the gso_max_segs and gso_max_size of a device were not controlled from user space. The quoted commit added the ability to control them because of the following setup: netns A | netns B veth<->veth eth0 If eth0 has TSO limitations and user wants to efficiently forward traffic between eth0 and the veths they should copy the TSO limitations of eth0 onto the veths. This would happen automatically for macvlans or ipvlan but veth users are not so lucky (given the loose coupling). Unfortunately the commit in question allowed users to also override the limits on real HW devices. It may be useful to control the max GSO size and someone may be using that ability (not that I know of any user), so create a separate set of knobs to reliably record the TSO limitations. Validate the user requests. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 006bb5c0e413..e12f7de6d6ae 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1917,8 +1917,10 @@ enum netdev_ml_priv_type { * @rtnl_link_ops: Rtnl_link_ops * * @gso_max_size: Maximum size of generic segmentation offload + * @tso_max_size: Device (as in HW) limit on the max TSO request size * @gso_max_segs: Maximum number of segments that can be passed to the * NIC for GSO + * @tso_max_segs: Device (as in HW) limit on the max TSO segment count * * @dcbnl_ops: Data Center Bridging netlink ops * @num_tc: Number of traffic classes in the net device @@ -2262,8 +2264,13 @@ struct net_device { /* for setting kernel sock attribute on TCP connection setup */ #define GSO_MAX_SIZE 65536 unsigned int gso_max_size; +#define TSO_LEGACY_MAX_SIZE 65536 +#define TSO_MAX_SIZE UINT_MAX + unsigned int tso_max_size; #define GSO_MAX_SEGS 65535 u16 gso_max_segs; +#define TSO_MAX_SEGS U16_MAX + u16 tso_max_segs; #ifdef CONFIG_DCB const struct dcbnl_rtnl_ops *dcbnl_ops; @@ -4895,6 +4902,8 @@ static inline void netif_set_gro_max_size(struct net_device *dev, WRITE_ONCE(dev->gro_max_size, size); } +void netif_set_tso_max_size(struct net_device *dev, unsigned int size); +void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs); void netif_inherit_tso_max(struct net_device *to, const struct net_device *from); -- cgit v1.2.3 From 744d49daf8bd3b17b345c836f2e6f97d49fa6ae8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 5 May 2022 19:51:34 -0700 Subject: net: move netif_set_gso_max helpers These are now internal to the core, no need to expose them. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 21 --------------------- 1 file changed, 21 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e12f7de6d6ae..8cf0ac616cb9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4881,27 +4881,6 @@ static inline bool netif_needs_gso(struct sk_buff *skb, (skb->ip_summed != CHECKSUM_UNNECESSARY))); } -static inline void netif_set_gso_max_size(struct net_device *dev, - unsigned int size) -{ - /* dev->gso_max_size is read locklessly from sk_setup_caps() */ - WRITE_ONCE(dev->gso_max_size, size); -} - -static inline void netif_set_gso_max_segs(struct net_device *dev, - unsigned int segs) -{ - /* dev->gso_max_segs is read locklessly from sk_setup_caps() */ - WRITE_ONCE(dev->gso_max_segs, segs); -} - -static inline void netif_set_gro_max_size(struct net_device *dev, - unsigned int size) -{ - /* This pairs with the READ_ONCE() in skb_gro_receive() */ - WRITE_ONCE(dev->gro_max_size, size); -} - void netif_set_tso_max_size(struct net_device *dev, unsigned int size); void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs); void netif_inherit_tso_max(struct net_device *to, -- cgit v1.2.3 From 3ff5f7840979aa36d47a6a00694826c78d63bf3c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 6 May 2022 14:14:36 +0200 Subject: linkage: Fix issue with missing symbol size Occasionally, typically when a function doesn't end with 'ret', an alias on that function will have 0 size. The difference between what GCC generates and our linkage magic, is that GCC doesn't appear to provide .size for the alias'ed symbol at all. And indeed, removing this directive cures the issue. Additionally, GCC also doesn't emit .type for alias symbols either, so also omit that. Fixes: e0891269a8c2 ("linkage: add SYM_FUNC_ALIAS{,_LOCAL,_WEAK}()") Suggested-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov Reviewed-by: Mark Rutland Acked-by: Josh Poimboeuf Link: https://lore.kernel.org/r/20220506121631.437480085@infradead.org --- include/linux/linkage.h | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/linkage.h b/include/linux/linkage.h index acb1ad2356f1..1feab6136b5b 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -171,12 +171,9 @@ /* SYM_ALIAS -- use only if you have to */ #ifndef SYM_ALIAS -#define SYM_ALIAS(alias, name, sym_type, linkage) \ - linkage(alias) ASM_NL \ - .set alias, name ASM_NL \ - .type alias sym_type ASM_NL \ - .set .L__sym_size_##alias, .L__sym_size_##name ASM_NL \ - .size alias, .L__sym_size_##alias +#define SYM_ALIAS(alias, name, linkage) \ + linkage(alias) ASM_NL \ + .set alias, name ASM_NL #endif /* === code annotations === */ @@ -261,7 +258,7 @@ */ #ifndef SYM_FUNC_ALIAS #define SYM_FUNC_ALIAS(alias, name) \ - SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_GLOBAL) + SYM_ALIAS(alias, name, SYM_L_GLOBAL) #endif /* @@ -269,7 +266,7 @@ */ #ifndef SYM_FUNC_ALIAS_LOCAL #define SYM_FUNC_ALIAS_LOCAL(alias, name) \ - SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_LOCAL) + SYM_ALIAS(alias, name, SYM_L_LOCAL) #endif /* @@ -277,7 +274,7 @@ */ #ifndef SYM_FUNC_ALIAS_WEAK #define SYM_FUNC_ALIAS_WEAK(alias, name) \ - SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_WEAK) + SYM_ALIAS(alias, name, SYM_L_WEAK) #endif /* SYM_CODE_START -- use for non-C (special) functions */ -- cgit v1.2.3 From 6b79738b6ed91a2d0fe958819469eeedac3bca81 Mon Sep 17 00:00:00 2001 From: Qi Liu Date: Fri, 15 Apr 2022 18:23:52 +0800 Subject: drivers/perf: hisi: Add Support for CPA PMU On HiSilicon Hip09 platform, there is a CPA (Coherency Protocol Agent) on each SICL (Super IO Cluster) which implements packet format translation, route parsing and traffic statistics. CPA PMU has 8 PMU counters and interrupt is supported to handle counter overflow. Let's support its driver under the framework of HiSilicon PMU driver. Signed-off-by: Qi Liu Reviewed-by: John Garry Reviewed-by: Shaokun Zhang Link: https://lore.kernel.org/r/20220415102352.6665-3-liuqi115@huawei.com Signed-off-by: Will Deacon --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 82e33137f917..b66c5f389159 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -222,6 +222,7 @@ enum cpuhp_state { CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, CPUHP_AP_PERF_ARM_CCN_ONLINE, + CPUHP_AP_PERF_ARM_HISI_CPA_ONLINE, CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE, CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE, CPUHP_AP_PERF_ARM_HISI_L3_ONLINE, -- cgit v1.2.3 From cbe757ecdb4b0c8ac4c62b03cda3fa58ba6d23fd Mon Sep 17 00:00:00 2001 From: Huang Rui Date: Mon, 2 Aug 2021 09:06:03 +0800 Subject: drm/amdgpu: add GC 11.0.1 family id Add a flag to define GC 11.0.1. Signed-off-by: Huang Rui Reviewed-by: Aaron Liu Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 992851219441..9a1d210d135d 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -1152,6 +1152,7 @@ struct drm_amdgpu_info_video_caps { #define AMDGPU_FAMILY_VGH 144 /* Van Gogh */ #define AMDGPU_FAMILY_GC_11_0_0 145 /* GC 11.0.0 */ #define AMDGPU_FAMILY_YC 146 /* Yellow Carp */ +#define AMDGPU_FAMILY_GC_11_0_1 148 /* GC 11.0.1 */ #define AMDGPU_FAMILY_GC_10_3_6 149 /* GC 10.3.6 */ #define AMDGPU_FAMILY_GC_10_3_7 151 /* GC 10.3.7 */ -- cgit v1.2.3 From 38d321b61bda32624bde46f662faac039905e3db Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Fri, 29 Apr 2022 00:09:28 +0100 Subject: clk: sunxi-ng: h6-r: Add RTC gate clock The H6 and H616 feature an (undocumented) bus clock gate for accessing the RTC registers. This seems to be enabled at reset (or by the BootROM), so we got away without it so far, but exists regardless. Since the new RTC clock binding for the H616 requires this "bus" clock to be specified in the DT, add this to R_CCU clock driver and expose it on the DT side with a new number. We do this for both the H6 and H616, but mark it as IGNORE_UNUSED, as we cannot reference it in any H6 DTs. Signed-off-by: Andre Przywara Reviewed-by: Samuel Holland Signed-off-by: Jernej Skrabec Link: https://lore.kernel.org/r/20220428230933.15262-2-andre.przywara@arm.com --- include/dt-bindings/clock/sun50i-h6-r-ccu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/clock/sun50i-h6-r-ccu.h b/include/dt-bindings/clock/sun50i-h6-r-ccu.h index 890368d252c4..a96087abc86f 100644 --- a/include/dt-bindings/clock/sun50i-h6-r-ccu.h +++ b/include/dt-bindings/clock/sun50i-h6-r-ccu.h @@ -22,5 +22,6 @@ #define CLK_W1 12 #define CLK_R_APB2_RSB 13 +#define CLK_R_APB1_RTC 14 #endif /* _DT_BINDINGS_CLK_SUN50I_H6_R_CCU_H_ */ -- cgit v1.2.3 From 31ab5169803ebc009e01d1ee4501ca9faf347161 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Fri, 29 Apr 2022 00:09:29 +0100 Subject: clk: sunxi-ng: h616: Add PLL derived 32KHz clock The RTC section of the H616 manual mentions in a half-sentence the existence of a clock "32K divided by PLL_PERI(2X)". This is used as one of the possible inputs for the mux that selects the clock for the 32 KHz fanout pad. On the H616 this is routed to pin PG10, and some boards use that clock output to compensate for a missing 32KHz crystal. On the OrangePi Zero2 this is for instance connected to the LPO pin of the WiFi/BT chip. The new RTC clock binding requires this clock to be named as one input clock, so we need to expose this to the DT. In contrast to the D1 SoC there does not seem to be a gate for this clock, so just use a fixed divider clock, using a newly assigned clock number. Signed-off-by: Andre Przywara Reviewed-by: Samuel Holland Signed-off-by: Jernej Skrabec Link: https://lore.kernel.org/r/20220428230933.15262-3-andre.przywara@arm.com --- include/dt-bindings/clock/sun50i-h616-ccu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/clock/sun50i-h616-ccu.h b/include/dt-bindings/clock/sun50i-h616-ccu.h index 4fc08b0df2f3..1191aca53ac6 100644 --- a/include/dt-bindings/clock/sun50i-h616-ccu.h +++ b/include/dt-bindings/clock/sun50i-h616-ccu.h @@ -111,5 +111,6 @@ #define CLK_BUS_TVE0 125 #define CLK_HDCP 126 #define CLK_BUS_HDCP 127 +#define CLK_PLL_SYSTEM_32K 128 #endif /* _DT_BINDINGS_CLK_SUN50I_H616_H_ */ -- cgit v1.2.3 From 343f4c49f2438d8920f1f76fa823ee59b91f02e4 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 11 Apr 2022 11:40:14 -0500 Subject: kthread: Don't allocate kthread_struct for init and umh MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If kthread_is_per_cpu runs concurrently with free_kthread_struct the kthread_struct that was just freed may be read from. This bug was introduced by commit 40966e316f86 ("kthread: Ensure struct kthread is present for all kthreads"). When kthread_struct started to be allocated for all tasks that have PF_KTHREAD set. This in turn required the kthread_struct to be freed in kernel_execve and violated the assumption that kthread_struct will have the same lifetime as the task. Looking a bit deeper this only applies to callers of kernel_execve which is just the init process and the user mode helper processes. These processes really don't want to be kernel threads but are for historical reasons. Mostly that copy_thread does not know how to take a kernel mode function to the process with for processes without PF_KTHREAD or PF_IO_WORKER set. Solve this by not allocating kthread_struct for the init process and the user mode helper processes. This is done by adding a kthread member to struct kernel_clone_args. Setting kthread in fork_idle and kernel_thread. Adding user_mode_thread that works like kernel_thread except it does not set kthread. In fork only allocating the kthread_struct if .kthread is set. I have looked at kernel/kthread.c and since commit 40966e316f86 ("kthread: Ensure struct kthread is present for all kthreads") there have been no assumptions added that to_kthread or __to_kthread will not return NULL. There are a few callers of to_kthread or __to_kthread that assume a non-NULL struct kthread pointer will be returned. These functions are kthread_data(), kthread_parmme(), kthread_exit(), kthread(), kthread_park(), kthread_unpark(), kthread_stop(). All of those functions can reasonably expected to be called when it is know that a task is a kthread so that assumption seems reasonable. Cc: stable@vger.kernel.org Fixes: 40966e316f86 ("kthread: Ensure struct kthread is present for all kthreads") Reported-by: Максим Кутявин Link: https://lkml.kernel.org/r/20220506141512.516114-1-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/sched/task.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 719c9a6cac8d..4492266935dd 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -32,6 +32,7 @@ struct kernel_clone_args { size_t set_tid_size; int cgroup; int io_thread; + int kthread; struct cgroup *cgrp; struct css_set *cset; }; @@ -89,6 +90,7 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); struct task_struct *fork_idle(int); struct mm_struct *copy_init_mm(void); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); +extern pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags); extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); int kernel_wait(pid_t pid, int *stat); -- cgit v1.2.3 From e2ef115813c34ea5380ac5b4879f515070150210 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 6 May 2022 14:14:37 +0200 Subject: objtool: Fix STACK_FRAME_NON_STANDARD reloc type STACK_FRAME_NON_STANDARD results in inconsistent relocation types depending on .c or .S usage: Relocation section '.rela.discard.func_stack_frame_non_standard' at offset 0x3c01090 contains 5 entries: Offset Info Type Symbol's Value Symbol's Name + Addend 0000000000000000 00020c2200000002 R_X86_64_PC32 0000000000047b40 do_suspend_lowlevel + 0 0000000000000008 0002461e00000001 R_X86_64_64 00000000000480a0 machine_real_restart + 0 0000000000000010 0000001400000001 R_X86_64_64 0000000000000000 .rodata + b3d4 0000000000000018 0002444600000002 R_X86_64_PC32 00000000000678a0 __efi64_thunk + 0 0000000000000020 0002659d00000001 R_X86_64_64 0000000000113160 __crash_kexec + 0 Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Borislav Petkov Link: https://lore.kernel.org/r/20220506121631.508692613@infradead.org --- include/linux/objtool.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 586d35720f13..b9c1474a571e 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -40,6 +40,8 @@ struct unwind_hint { #ifdef CONFIG_STACK_VALIDATION +#include + #ifndef __ASSEMBLY__ #define UNWIND_HINT(sp_reg, sp_offset, type, end) \ @@ -137,7 +139,7 @@ struct unwind_hint { .macro STACK_FRAME_NON_STANDARD func:req .pushsection .discard.func_stack_frame_non_standard, "aw" - .long \func - . + _ASM_PTR \func .popsection .endm -- cgit v1.2.3 From 28de0f9fec5a84bd5b56d6364432a8730eac410a Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 5 May 2022 19:22:12 +0300 Subject: net: dsa: felix: perform MDB migration based on ocelot->multicast list The felix driver is the only user of dsa_port_walk_mdbs(), and there isn't even a good reason for it, considering that the host MDB entries are already saved by the ocelot switch lib in the ocelot->multicast list. Rewrite the multicast entry migration procedure around the ocelot->multicast list so we can delete dsa_port_walk_mdbs(). Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 8d8d46778f7e..e88bcfe4b2cd 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -998,6 +998,9 @@ int ocelot_mact_learn_streamdata(struct ocelot *ocelot, int dst_idx, enum macaccess_entry_type type, int sfid, int ssid); +int ocelot_migrate_mdbs(struct ocelot *ocelot, unsigned long from_mask, + unsigned long to_mask); + int ocelot_vcap_policer_add(struct ocelot *ocelot, u32 pol_ix, struct ocelot_policer *pol); int ocelot_vcap_policer_del(struct ocelot *ocelot, u32 pol_ix); -- cgit v1.2.3 From fe5233b0ba0d2216d549f93e4540542b99b97642 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 5 May 2022 19:22:13 +0300 Subject: net: dsa: delete dsa_port_walk_{fdbs,mdbs} All the users of these functions are gone, delete them before they gain new ones. Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 934958fda962..efd33956df37 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -1239,12 +1239,6 @@ struct dsa_switch_driver { struct net_device *dsa_dev_to_net_device(struct device *dev); -typedef int dsa_fdb_walk_cb_t(struct dsa_switch *ds, int port, - const unsigned char *addr, u16 vid, - struct dsa_db db); - -int dsa_port_walk_fdbs(struct dsa_switch *ds, int port, dsa_fdb_walk_cb_t cb); -int dsa_port_walk_mdbs(struct dsa_switch *ds, int port, dsa_fdb_walk_cb_t cb); bool dsa_fdb_present_in_other_db(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); -- cgit v1.2.3 From c5febea0956fd3874e8fb59c6f84d68f128d68f8 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 8 Apr 2022 18:07:50 -0500 Subject: fork: Pass struct kernel_clone_args into copy_thread With io_uring we have started supporting tasks that are for most purposes user space tasks that exclusively run code in kernel mode. The kernel task that exec's init and tasks that exec user mode helpers are also user mode tasks that just run kernel code until they call kernel execve. Pass kernel_clone_args into copy_thread so these oddball tasks can be supported more cleanly and easily. v2: Fix spelling of kenrel_clone_args on h8300 Link: https://lkml.kernel.org/r/20220506141512.516114-2-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/sched/task.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 4492266935dd..fcdcba231aac 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -68,8 +68,7 @@ extern void fork_init(void); extern void release_task(struct task_struct * p); -extern int copy_thread(unsigned long, unsigned long, unsigned long, - struct task_struct *, unsigned long); +extern int copy_thread(struct task_struct *, const struct kernel_clone_args *); extern void flush_thread(void); -- cgit v1.2.3 From 36cb0e1cda645ee645b85a6ce652cb46a16e14e5 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 11 Apr 2022 16:17:28 -0500 Subject: fork: Explicity test for idle tasks in copy_thread The architectures ia64 and parisc have special handling for the idle thread in copy_process. Add a flag named idle to kernel_clone_args and use it to explicity test if an idle process is being created. Fullfill the expectations of the rest of the copy_thread implemetations and pass a function pointer in .stack from fork_idle(). This makes what is happening in copy_thread better defined, and is useful to make idle threads less special. Link: https://lkml.kernel.org/r/20220506141512.516114-3-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/sched/task.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index fcdcba231aac..3d6b99ce5408 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -33,6 +33,7 @@ struct kernel_clone_args { int cgroup; int io_thread; int kthread; + int idle; struct cgroup *cgrp; struct css_set *cset; }; -- cgit v1.2.3 From 5bd2e97c868a8a44470950ed01846cab6328e540 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 12 Apr 2022 10:18:48 -0500 Subject: fork: Generalize PF_IO_WORKER handling Add fn and fn_arg members into struct kernel_clone_args and test for them in copy_thread (instead of testing for PF_KTHREAD | PF_IO_WORKER). This allows any task that wants to be a user space task that only runs in kernel mode to use this functionality. The code on x86 is an exception and still retains a PF_KTHREAD test because x86 unlikely everything else handles kthreads slightly differently than user space tasks that start with a function. The functions that created tasks that start with a function have been updated to set ".fn" and ".fn_arg" instead of ".stack" and ".stack_size". These functions are fork_idle(), create_io_thread(), kernel_thread(), and user_mode_thread(). Link: https://lkml.kernel.org/r/20220506141512.516114-4-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/sched/task.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 3d6b99ce5408..505aaf9fe477 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -34,6 +34,8 @@ struct kernel_clone_args { int io_thread; int kthread; int idle; + int (*fn)(void *); + void *fn_arg; struct cgroup *cgrp; struct css_set *cset; }; -- cgit v1.2.3 From 3d1b0d351441c2be7de082b92f43d0bfdc95a8f3 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 7 May 2022 13:48:21 -0400 Subject: Revert "SUNRPC: Ensure gss-proxy connects on setup" This reverts commit 892de36fd4a98fab3298d417c051d9099af5448d. The gssproxy server is unresponsive when it calls into the kernel to start the upcall service, so it will not reply to our RPC ping at all. Reported-by: "J.Bruce Fields" Fixes: 892de36fd4a9 ("SUNRPC: Ensure gss-proxy connects on setup") Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index db5149567305..267b7aeaf1a6 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -160,7 +160,6 @@ struct rpc_add_xprt_test { #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT (1UL << 9) #define RPC_CLNT_CREATE_SOFTERR (1UL << 10) #define RPC_CLNT_CREATE_REUSEPORT (1UL << 11) -#define RPC_CLNT_CREATE_IGNORE_NULL_UNAVAIL (1UL << 12) struct rpc_clnt *rpc_create(struct rpc_create_args *args); struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, -- cgit v1.2.3 From fd13359f54ee854f00134abc6be32da94ec53dbf Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 7 May 2022 13:53:59 -0400 Subject: SUNRPC: Ensure that the gssproxy client can start in a connected state Ensure that the gssproxy client connects to the server from the gssproxy daemon process context so that the AF_LOCAL socket connection is done using the correct path and namespaces. Fixes: 1d658336b05f ("SUNRPC: Add RPC based upcall mechanism for RPCGSS auth") Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 267b7aeaf1a6..90501404fa49 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -160,6 +160,7 @@ struct rpc_add_xprt_test { #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT (1UL << 9) #define RPC_CLNT_CREATE_SOFTERR (1UL << 10) #define RPC_CLNT_CREATE_REUSEPORT (1UL << 11) +#define RPC_CLNT_CREATE_CONNECTED (1UL << 12) struct rpc_clnt *rpc_create(struct rpc_create_args *args); struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, -- cgit v1.2.3 From 813c2aee51dd7d7d9092251851e33f66719513cc Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 7 May 2022 14:33:31 +0200 Subject: ARM/pxa/mfd/power/sound: Switch Tosa to GPIO descriptors The Tosa device (Sharp SL-6000) has a mishmash driver set-up for the Toshiba TC6393xb MFD that includes a battery charger and touchscreen and has some kind of relationship to the SoC sound driver for the AC97 codec. Other devices define a chip like this but seem only half-implemented, not really handling battery charging etc. This patch switches the Toshiba MFD device to provide GPIO descriptors to the battery charger and SoC codec. As a result some descriptors need to be moved out of the Tosa boardfile and new one added: all SoC GPIO resources to these drivers now comes from the main boardfile, while the MFD provide GPIOs for its portions. As a result we can request one GPIO from our own GPIO chip and drop two hairy callbacks into the board file. This platform badly needs to have its drivers split up and converted to device tree probing to handle this quite complex relationship in an orderly manner. I just do my best in solving the GPIO descriptor part of the puzzle. Please don't ask me to fix everything that is wrong with these driver to todays standards, I am just trying to fix one aspect. I do try to use modern devres resource management and handle deferred probe using new functions where appropriate. Cc: Dmitry Eremin-Solenikov Cc: Dirk Opfer Cc: Robert Jarzmik Cc: Daniel Mack Cc: Haojian Zhuang Cc: Lee Jones Cc: Liam Girdwood Reviewed-by: Dmitry Baryshkov Acked-by: Mark Brown Acked-by: Sebastian Reichel Signed-off-by: Linus Walleij Signed-off-by: Arnd Bergmann --- include/linux/gpio/machine.h | 12 ++++++++++++ include/linux/mfd/tc6393xb.h | 3 --- 2 files changed, 12 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/gpio/machine.h b/include/linux/gpio/machine.h index 2647dd10b541..4d55da28e664 100644 --- a/include/linux/gpio/machine.h +++ b/include/linux/gpio/machine.h @@ -63,6 +63,18 @@ struct gpiod_hog { int dflags; }; +/* + * Helper for lookup tables with just one single lookup for a device. + */ +#define GPIO_LOOKUP_SINGLE(_name, _dev_id, _key, _chip_hwnum, _con_id, _flags) \ +static struct gpiod_lookup_table _name = { \ + .dev_id = _dev_id, \ + .table = { \ + GPIO_LOOKUP(_key, _chip_hwnum, _con_id, _flags), \ + {}, \ + }, \ +} + /* * Simple definition of a single GPIO under a con_id */ diff --git a/include/linux/mfd/tc6393xb.h b/include/linux/mfd/tc6393xb.h index fcc8e74f0e8d..d336c541b7df 100644 --- a/include/linux/mfd/tc6393xb.h +++ b/include/linux/mfd/tc6393xb.h @@ -27,9 +27,6 @@ struct tc6393xb_platform_data { int (*resume)(struct platform_device *dev); int irq_base; /* base for subdevice irqs */ - int gpio_base; - int (*setup)(struct platform_device *dev); - void (*teardown)(struct platform_device *dev); struct tmio_nand_data *nand_data; struct tmio_fb_data *fb_data; -- cgit v1.2.3 From ac70f4d80df414223130b04d9b4435bf56dda654 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 11 Sep 2019 10:58:26 +0200 Subject: ARM: pxa: poodle: use platform data for poodle asoc driver The poodle audio driver shows its age by using a custom gpio api for the "locomo" support chip. In a perfect world, this would get converted to use gpiolib and a gpio lookup table. As the world is not perfect, just pass all the required data in a custom platform_data structure. to avoid the globally visible mach/poodle.h header. Acked-by: Mark Brown Acked-by: Robert Jarzmik Cc: alsa-devel@alsa-project.org Signed-off-by: Arnd Bergmann --- include/linux/platform_data/asoc-poodle.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100644 include/linux/platform_data/asoc-poodle.h (limited to 'include') diff --git a/include/linux/platform_data/asoc-poodle.h b/include/linux/platform_data/asoc-poodle.h new file mode 100644 index 000000000000..2052fad55c5c --- /dev/null +++ b/include/linux/platform_data/asoc-poodle.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_PLATFORM_DATA_POODLE_AUDIO +#define __LINUX_PLATFORM_DATA_POODLE_AUDIO + +/* locomo is not a proper gpio driver, and uses its own api */ +struct poodle_audio_platform_data { + struct device *locomo_dev; + + int gpio_amp_on; + int gpio_mute_l; + int gpio_mute_r; + int gpio_232vcc_on; + int gpio_jk_b; +}; + +#endif -- cgit v1.2.3 From e217b085a1ac1c4108fe632bdaa08ea5b0ecd145 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Sep 2019 09:55:23 +0200 Subject: Input: touchscreen: use wrapper for pxa2xx ac97 registers To avoid a dependency on the pxa platform header files with hardcoded registers, change the driver to call a wrapper in the pxa2xx-ac97-lib that encapsulates all the other ac97 stuff. Acked-by: Dmitry Torokhov Acked-by: Robert Jarzmik Cc: linux-input@vger.kernel.org Cc: alsa-devel@alsa-project.org Signed-off-by: Arnd Bergmann --- include/sound/pxa2xx-lib.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/sound/pxa2xx-lib.h b/include/sound/pxa2xx-lib.h index 95100cff25d1..0a6f8dabf8c4 100644 --- a/include/sound/pxa2xx-lib.h +++ b/include/sound/pxa2xx-lib.h @@ -52,4 +52,8 @@ extern int pxa2xx_ac97_hw_resume(void); extern int pxa2xx_ac97_hw_probe(struct platform_device *dev); extern void pxa2xx_ac97_hw_remove(struct platform_device *dev); +/* modem registers, used by touchscreen driver */ +u32 pxa2xx_ac97_read_modr(void); +u32 pxa2xx_ac97_read_misr(void); + #endif -- cgit v1.2.3 From a2ef926143b84664f4823c82a437b29c4667a08c Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 18 Oct 2019 13:48:33 -0700 Subject: Input: wm97xx - switch to using threaded IRQ Instead of manually disabling and enabling interrupts and scheduling work to access the device, let's use threaded oneshot interrupt handler. It simplifies things. Signed-off-by: Dmitry Torokhov Signed-off-by: Arnd Bergmann --- include/linux/wm97xx.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/wm97xx.h b/include/linux/wm97xx.h index 462854f4f286..85bd8dd3caea 100644 --- a/include/linux/wm97xx.h +++ b/include/linux/wm97xx.h @@ -281,7 +281,6 @@ struct wm97xx { unsigned long ts_reader_min_interval; /* Minimum interval */ unsigned int pen_irq; /* Pen IRQ number in use */ struct workqueue_struct *ts_workq; - struct work_struct pen_event_work; u16 acc_slot; /* AC97 slot used for acc touch data */ u16 acc_rate; /* acc touch data rate */ unsigned pen_is_down:1; /* Pen is down */ -- cgit v1.2.3 From e1d8f31218aab302df9e18526345af189fd061f0 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 18 Oct 2019 13:48:34 -0700 Subject: Input: wm97xx - get rid of irq_enable method in wm97xx_mach_ops Now that we are using oneshot threaded IRQ this method is not used anymore. Signed-off-by: Dmitry Torokhov [arnd: add the db1300 change as well] Cc: Manuel Lauss Signed-off-by: Arnd Bergmann --- include/linux/wm97xx.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/wm97xx.h b/include/linux/wm97xx.h index 85bd8dd3caea..332d2b0f29b9 100644 --- a/include/linux/wm97xx.h +++ b/include/linux/wm97xx.h @@ -254,9 +254,6 @@ struct wm97xx_mach_ops { int (*acc_startup) (struct wm97xx *); void (*acc_shutdown) (struct wm97xx *); - /* interrupt mask control - required for accelerated operation */ - void (*irq_enable) (struct wm97xx *, int enable); - /* GPIO pin used for accelerated operation */ int irq_gpio; -- cgit v1.2.3 From 6a946f1bd5cc966c9dd377b14efa4cec388101ce Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Sep 2019 14:50:37 +0200 Subject: ARM: pxa: pcmcia: move smemc configuration back to arch Rather than poking at the smemc registers directly from the pcmcia/pxa2xx_base driver, move those bits into machine file to have a cleaner interface. Cc: Dominik Brodowski Link: https://lore.kernel.org/lkml/87d0egjzxk.fsf@belgarion.home/ Signed-off-by: Arnd Bergmann --- include/linux/soc/pxa/smemc.h | 10 ++++++++++ 1 file changed, 10 insertions(+) create mode 100644 include/linux/soc/pxa/smemc.h (limited to 'include') diff --git a/include/linux/soc/pxa/smemc.h b/include/linux/soc/pxa/smemc.h new file mode 100644 index 000000000000..cbf1a2d8af29 --- /dev/null +++ b/include/linux/soc/pxa/smemc.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __PXA_REGS_H +#define __PXA_REGS_H + +#include + +void pxa_smemc_set_pcmcia_timing(int sock, u32 mcmem, u32 mcatt, u32 mcio); +void pxa_smemc_set_pcmcia_socket(int nr); + +#endif -- cgit v1.2.3 From 5c6603e741921c75f67a724e798642ed50a6328e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Sep 2019 15:34:10 +0200 Subject: cpufreq: pxa3: move clk register access to clk driver The driver needs some low-level register access for setting the core and bus frequencies. These registers are owned by the clk driver, so move the low-level access into that driver with a slightly higher-level interface and avoid any machine header file dependencies. Cc: Michael Turquette Cc: Stephen Boyd Acked-by: Viresh Kumar Cc: linux-clk@vger.kernel.org Cc: linux-pm@vger.kernel.org Signed-off-by: Arnd Bergmann --- include/linux/clk/pxa.h | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 include/linux/clk/pxa.h (limited to 'include') diff --git a/include/linux/clk/pxa.h b/include/linux/clk/pxa.h new file mode 100644 index 000000000000..e5516c608c99 --- /dev/null +++ b/include/linux/clk/pxa.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifdef CONFIG_PXA3xx +extern unsigned pxa3xx_get_clk_frequency_khz(int); +extern void pxa3xx_clk_update_accr(u32 disable, u32 enable, u32 xclkcfg, u32 mask); +#else +#define pxa3xx_get_clk_frequency_khz(x) (0) +#define pxa3xx_clk_update_accr(disable, enable, xclkcfg, mask) do { } while (0) +#endif -- cgit v1.2.3 From fd13f8117f7a2d4054bf420ec1428e918a24a480 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Sep 2019 17:42:52 +0200 Subject: ARM: pxa: move smemc register access from clk to platform The get_sdram_rows() and get_memclkdiv() helpers need smemc register that are separate from the clk registers, move them out of the clk driver, and use an extern declaration instead. Cc: Michael Turquette Cc: Stephen Boyd Cc: linux-clk@vger.kernel.org Link: https://lore.kernel.org/lkml/87pnielzo4.fsf@belgarion.home/ Signed-off-by: Arnd Bergmann --- include/linux/soc/pxa/smemc.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/soc/pxa/smemc.h b/include/linux/soc/pxa/smemc.h index cbf1a2d8af29..f1ffea236c15 100644 --- a/include/linux/soc/pxa/smemc.h +++ b/include/linux/soc/pxa/smemc.h @@ -6,5 +6,8 @@ void pxa_smemc_set_pcmcia_timing(int sock, u32 mcmem, u32 mcatt, u32 mcio); void pxa_smemc_set_pcmcia_socket(int nr); +int pxa2xx_smemc_get_sdram_rows(void); +unsigned int pxa3xx_smemc_get_memclkdiv(void); +void __iomem *pxa_smemc_get_mdrefr(void); #endif -- cgit v1.2.3 From 3c816d950a494ae6e16b1fa017af29bc53cb7791 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Sep 2019 20:54:17 +0200 Subject: ARM: pxa: move clk register definitions to driver The clock register definitions are now used (almost) exclusively in the clk driver, and that relies on no other mach/*.h header files any more. Remove the dependency on mach/pxa*-regs.h by addressing the registers as offsets from a void __iomem * pointer, which is either passed from a board file, or (for the moment) ioremapped at boot time from a hardcoded address in case of DT (this should be moved into the DT of course). Cc: linux-clk@vger.kernel.org Acked-by: Stephen Boyd Acked-by: Robert Jarzmik Signed-off-by: Arnd Bergmann --- include/linux/clk/pxa.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/clk/pxa.h b/include/linux/clk/pxa.h index e5516c608c99..736b8bb91bd7 100644 --- a/include/linux/clk/pxa.h +++ b/include/linux/clk/pxa.h @@ -1,5 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0-only */ +#include +#include + +extern int pxa25x_clocks_init(void __iomem *regs); +extern int pxa27x_clocks_init(void __iomem *regs); +extern int pxa3xx_clocks_init(void __iomem *regs, void __iomem *oscc_reg); + #ifdef CONFIG_PXA3xx extern unsigned pxa3xx_get_clk_frequency_khz(int); extern void pxa3xx_clk_update_accr(u32 disable, u32 enable, u32 xclkcfg, u32 mask); -- cgit v1.2.3 From 64dbc4dd7a7cc6642c522963a6194b62480e2a68 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 20 Sep 2019 13:33:40 +0200 Subject: ARM: pxa: move plat-pxa to drivers/soc/ There are two drivers in arch/arm/plat-pxa: mfp and ssp. Both of them should ideally not be needed at all, as there are proper subsystems to replace them. OTOH, they are self-contained and can simply be normal SoC drivers, so move them over there to eliminate one more of the plat-* directories. Acked-by: Robert Jarzmik (mach-pxa) Acked-by: Lubomir Rintel (mach-mmp) Signed-off-by: Arnd Bergmann --- include/linux/soc/pxa/mfp.h | 470 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 470 insertions(+) create mode 100644 include/linux/soc/pxa/mfp.h (limited to 'include') diff --git a/include/linux/soc/pxa/mfp.h b/include/linux/soc/pxa/mfp.h new file mode 100644 index 000000000000..39779cbed0c0 --- /dev/null +++ b/include/linux/soc/pxa/mfp.h @@ -0,0 +1,470 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Common Multi-Function Pin Definitions + * + * Copyright (C) 2007 Marvell International Ltd. + * + * 2007-8-21: eric miao + * initial version + */ + +#ifndef __ASM_PLAT_MFP_H +#define __ASM_PLAT_MFP_H + +#define mfp_to_gpio(m) ((m) % 256) + +/* list of all the configurable MFP pins */ +enum { + MFP_PIN_INVALID = -1, + + MFP_PIN_GPIO0 = 0, + MFP_PIN_GPIO1, + MFP_PIN_GPIO2, + MFP_PIN_GPIO3, + MFP_PIN_GPIO4, + MFP_PIN_GPIO5, + MFP_PIN_GPIO6, + MFP_PIN_GPIO7, + MFP_PIN_GPIO8, + MFP_PIN_GPIO9, + MFP_PIN_GPIO10, + MFP_PIN_GPIO11, + MFP_PIN_GPIO12, + MFP_PIN_GPIO13, + MFP_PIN_GPIO14, + MFP_PIN_GPIO15, + MFP_PIN_GPIO16, + MFP_PIN_GPIO17, + MFP_PIN_GPIO18, + MFP_PIN_GPIO19, + MFP_PIN_GPIO20, + MFP_PIN_GPIO21, + MFP_PIN_GPIO22, + MFP_PIN_GPIO23, + MFP_PIN_GPIO24, + MFP_PIN_GPIO25, + MFP_PIN_GPIO26, + MFP_PIN_GPIO27, + MFP_PIN_GPIO28, + MFP_PIN_GPIO29, + MFP_PIN_GPIO30, + MFP_PIN_GPIO31, + MFP_PIN_GPIO32, + MFP_PIN_GPIO33, + MFP_PIN_GPIO34, + MFP_PIN_GPIO35, + MFP_PIN_GPIO36, + MFP_PIN_GPIO37, + MFP_PIN_GPIO38, + MFP_PIN_GPIO39, + MFP_PIN_GPIO40, + MFP_PIN_GPIO41, + MFP_PIN_GPIO42, + MFP_PIN_GPIO43, + MFP_PIN_GPIO44, + MFP_PIN_GPIO45, + MFP_PIN_GPIO46, + MFP_PIN_GPIO47, + MFP_PIN_GPIO48, + MFP_PIN_GPIO49, + MFP_PIN_GPIO50, + MFP_PIN_GPIO51, + MFP_PIN_GPIO52, + MFP_PIN_GPIO53, + MFP_PIN_GPIO54, + MFP_PIN_GPIO55, + MFP_PIN_GPIO56, + MFP_PIN_GPIO57, + MFP_PIN_GPIO58, + MFP_PIN_GPIO59, + MFP_PIN_GPIO60, + MFP_PIN_GPIO61, + MFP_PIN_GPIO62, + MFP_PIN_GPIO63, + MFP_PIN_GPIO64, + MFP_PIN_GPIO65, + MFP_PIN_GPIO66, + MFP_PIN_GPIO67, + MFP_PIN_GPIO68, + MFP_PIN_GPIO69, + MFP_PIN_GPIO70, + MFP_PIN_GPIO71, + MFP_PIN_GPIO72, + MFP_PIN_GPIO73, + MFP_PIN_GPIO74, + MFP_PIN_GPIO75, + MFP_PIN_GPIO76, + MFP_PIN_GPIO77, + MFP_PIN_GPIO78, + MFP_PIN_GPIO79, + MFP_PIN_GPIO80, + MFP_PIN_GPIO81, + MFP_PIN_GPIO82, + MFP_PIN_GPIO83, + MFP_PIN_GPIO84, + MFP_PIN_GPIO85, + MFP_PIN_GPIO86, + MFP_PIN_GPIO87, + MFP_PIN_GPIO88, + MFP_PIN_GPIO89, + MFP_PIN_GPIO90, + MFP_PIN_GPIO91, + MFP_PIN_GPIO92, + MFP_PIN_GPIO93, + MFP_PIN_GPIO94, + MFP_PIN_GPIO95, + MFP_PIN_GPIO96, + MFP_PIN_GPIO97, + MFP_PIN_GPIO98, + MFP_PIN_GPIO99, + MFP_PIN_GPIO100, + MFP_PIN_GPIO101, + MFP_PIN_GPIO102, + MFP_PIN_GPIO103, + MFP_PIN_GPIO104, + MFP_PIN_GPIO105, + MFP_PIN_GPIO106, + MFP_PIN_GPIO107, + MFP_PIN_GPIO108, + MFP_PIN_GPIO109, + MFP_PIN_GPIO110, + MFP_PIN_GPIO111, + MFP_PIN_GPIO112, + MFP_PIN_GPIO113, + MFP_PIN_GPIO114, + MFP_PIN_GPIO115, + MFP_PIN_GPIO116, + MFP_PIN_GPIO117, + MFP_PIN_GPIO118, + MFP_PIN_GPIO119, + MFP_PIN_GPIO120, + MFP_PIN_GPIO121, + MFP_PIN_GPIO122, + MFP_PIN_GPIO123, + MFP_PIN_GPIO124, + MFP_PIN_GPIO125, + MFP_PIN_GPIO126, + MFP_PIN_GPIO127, + + MFP_PIN_GPIO128, + MFP_PIN_GPIO129, + MFP_PIN_GPIO130, + MFP_PIN_GPIO131, + MFP_PIN_GPIO132, + MFP_PIN_GPIO133, + MFP_PIN_GPIO134, + MFP_PIN_GPIO135, + MFP_PIN_GPIO136, + MFP_PIN_GPIO137, + MFP_PIN_GPIO138, + MFP_PIN_GPIO139, + MFP_PIN_GPIO140, + MFP_PIN_GPIO141, + MFP_PIN_GPIO142, + MFP_PIN_GPIO143, + MFP_PIN_GPIO144, + MFP_PIN_GPIO145, + MFP_PIN_GPIO146, + MFP_PIN_GPIO147, + MFP_PIN_GPIO148, + MFP_PIN_GPIO149, + MFP_PIN_GPIO150, + MFP_PIN_GPIO151, + MFP_PIN_GPIO152, + MFP_PIN_GPIO153, + MFP_PIN_GPIO154, + MFP_PIN_GPIO155, + MFP_PIN_GPIO156, + MFP_PIN_GPIO157, + MFP_PIN_GPIO158, + MFP_PIN_GPIO159, + MFP_PIN_GPIO160, + MFP_PIN_GPIO161, + MFP_PIN_GPIO162, + MFP_PIN_GPIO163, + MFP_PIN_GPIO164, + MFP_PIN_GPIO165, + MFP_PIN_GPIO166, + MFP_PIN_GPIO167, + MFP_PIN_GPIO168, + MFP_PIN_GPIO169, + MFP_PIN_GPIO170, + MFP_PIN_GPIO171, + MFP_PIN_GPIO172, + MFP_PIN_GPIO173, + MFP_PIN_GPIO174, + MFP_PIN_GPIO175, + MFP_PIN_GPIO176, + MFP_PIN_GPIO177, + MFP_PIN_GPIO178, + MFP_PIN_GPIO179, + MFP_PIN_GPIO180, + MFP_PIN_GPIO181, + MFP_PIN_GPIO182, + MFP_PIN_GPIO183, + MFP_PIN_GPIO184, + MFP_PIN_GPIO185, + MFP_PIN_GPIO186, + MFP_PIN_GPIO187, + MFP_PIN_GPIO188, + MFP_PIN_GPIO189, + MFP_PIN_GPIO190, + MFP_PIN_GPIO191, + + MFP_PIN_GPIO255 = 255, + + MFP_PIN_GPIO0_2, + MFP_PIN_GPIO1_2, + MFP_PIN_GPIO2_2, + MFP_PIN_GPIO3_2, + MFP_PIN_GPIO4_2, + MFP_PIN_GPIO5_2, + MFP_PIN_GPIO6_2, + MFP_PIN_GPIO7_2, + MFP_PIN_GPIO8_2, + MFP_PIN_GPIO9_2, + MFP_PIN_GPIO10_2, + MFP_PIN_GPIO11_2, + MFP_PIN_GPIO12_2, + MFP_PIN_GPIO13_2, + MFP_PIN_GPIO14_2, + MFP_PIN_GPIO15_2, + MFP_PIN_GPIO16_2, + MFP_PIN_GPIO17_2, + + MFP_PIN_ULPI_STP, + MFP_PIN_ULPI_NXT, + MFP_PIN_ULPI_DIR, + + MFP_PIN_nXCVREN, + MFP_PIN_DF_CLE_nOE, + MFP_PIN_DF_nADV1_ALE, + MFP_PIN_DF_SCLK_E, + MFP_PIN_DF_SCLK_S, + MFP_PIN_nBE0, + MFP_PIN_nBE1, + MFP_PIN_DF_nADV2_ALE, + MFP_PIN_DF_INT_RnB, + MFP_PIN_DF_nCS0, + MFP_PIN_DF_nCS1, + MFP_PIN_nLUA, + MFP_PIN_nLLA, + MFP_PIN_DF_nWE, + MFP_PIN_DF_ALE_nWE, + MFP_PIN_DF_nRE_nOE, + MFP_PIN_DF_ADDR0, + MFP_PIN_DF_ADDR1, + MFP_PIN_DF_ADDR2, + MFP_PIN_DF_ADDR3, + MFP_PIN_DF_IO0, + MFP_PIN_DF_IO1, + MFP_PIN_DF_IO2, + MFP_PIN_DF_IO3, + MFP_PIN_DF_IO4, + MFP_PIN_DF_IO5, + MFP_PIN_DF_IO6, + MFP_PIN_DF_IO7, + MFP_PIN_DF_IO8, + MFP_PIN_DF_IO9, + MFP_PIN_DF_IO10, + MFP_PIN_DF_IO11, + MFP_PIN_DF_IO12, + MFP_PIN_DF_IO13, + MFP_PIN_DF_IO14, + MFP_PIN_DF_IO15, + MFP_PIN_DF_nCS0_SM_nCS2, + MFP_PIN_DF_nCS1_SM_nCS3, + MFP_PIN_SM_nCS0, + MFP_PIN_SM_nCS1, + MFP_PIN_DF_WEn, + MFP_PIN_DF_REn, + MFP_PIN_DF_CLE_SM_OEn, + MFP_PIN_DF_ALE_SM_WEn, + MFP_PIN_DF_RDY0, + MFP_PIN_DF_RDY1, + + MFP_PIN_SM_SCLK, + MFP_PIN_SM_BE0, + MFP_PIN_SM_BE1, + MFP_PIN_SM_ADV, + MFP_PIN_SM_ADVMUX, + MFP_PIN_SM_RDY, + + MFP_PIN_MMC1_DAT7, + MFP_PIN_MMC1_DAT6, + MFP_PIN_MMC1_DAT5, + MFP_PIN_MMC1_DAT4, + MFP_PIN_MMC1_DAT3, + MFP_PIN_MMC1_DAT2, + MFP_PIN_MMC1_DAT1, + MFP_PIN_MMC1_DAT0, + MFP_PIN_MMC1_CMD, + MFP_PIN_MMC1_CLK, + MFP_PIN_MMC1_CD, + MFP_PIN_MMC1_WP, + + /* additional pins on PXA930 */ + MFP_PIN_GSIM_UIO, + MFP_PIN_GSIM_UCLK, + MFP_PIN_GSIM_UDET, + MFP_PIN_GSIM_nURST, + MFP_PIN_PMIC_INT, + MFP_PIN_RDY, + + /* additional pins on MMP2 */ + MFP_PIN_TWSI1_SCL, + MFP_PIN_TWSI1_SDA, + MFP_PIN_TWSI4_SCL, + MFP_PIN_TWSI4_SDA, + MFP_PIN_CLK_REQ, + + MFP_PIN_MAX, +}; + +/* + * a possible MFP configuration is represented by a 32-bit integer + * + * bit 0.. 9 - MFP Pin Number (1024 Pins Maximum) + * bit 10..12 - Alternate Function Selection + * bit 13..15 - Drive Strength + * bit 16..18 - Low Power Mode State + * bit 19..20 - Low Power Mode Edge Detection + * bit 21..22 - Run Mode Pull State + * + * to facilitate the definition, the following macros are provided + * + * MFP_CFG_DEFAULT - default MFP configuration value, with + * alternate function = 0, + * drive strength = fast 3mA (MFP_DS03X) + * low power mode = default + * edge detection = none + * + * MFP_CFG - default MFPR value with alternate function + * MFP_CFG_DRV - default MFPR value with alternate function and + * pin drive strength + * MFP_CFG_LPM - default MFPR value with alternate function and + * low power mode + * MFP_CFG_X - default MFPR value with alternate function, + * pin drive strength and low power mode + */ + +typedef unsigned long mfp_cfg_t; + +#define MFP_PIN(x) ((x) & 0x3ff) + +#define MFP_AF0 (0x0 << 10) +#define MFP_AF1 (0x1 << 10) +#define MFP_AF2 (0x2 << 10) +#define MFP_AF3 (0x3 << 10) +#define MFP_AF4 (0x4 << 10) +#define MFP_AF5 (0x5 << 10) +#define MFP_AF6 (0x6 << 10) +#define MFP_AF7 (0x7 << 10) +#define MFP_AF_MASK (0x7 << 10) +#define MFP_AF(x) (((x) >> 10) & 0x7) + +#define MFP_DS01X (0x0 << 13) +#define MFP_DS02X (0x1 << 13) +#define MFP_DS03X (0x2 << 13) +#define MFP_DS04X (0x3 << 13) +#define MFP_DS06X (0x4 << 13) +#define MFP_DS08X (0x5 << 13) +#define MFP_DS10X (0x6 << 13) +#define MFP_DS13X (0x7 << 13) +#define MFP_DS_MASK (0x7 << 13) +#define MFP_DS(x) (((x) >> 13) & 0x7) + +#define MFP_LPM_DEFAULT (0x0 << 16) +#define MFP_LPM_DRIVE_LOW (0x1 << 16) +#define MFP_LPM_DRIVE_HIGH (0x2 << 16) +#define MFP_LPM_PULL_LOW (0x3 << 16) +#define MFP_LPM_PULL_HIGH (0x4 << 16) +#define MFP_LPM_FLOAT (0x5 << 16) +#define MFP_LPM_INPUT (0x6 << 16) +#define MFP_LPM_STATE_MASK (0x7 << 16) +#define MFP_LPM_STATE(x) (((x) >> 16) & 0x7) + +#define MFP_LPM_EDGE_NONE (0x0 << 19) +#define MFP_LPM_EDGE_RISE (0x1 << 19) +#define MFP_LPM_EDGE_FALL (0x2 << 19) +#define MFP_LPM_EDGE_BOTH (0x3 << 19) +#define MFP_LPM_EDGE_MASK (0x3 << 19) +#define MFP_LPM_EDGE(x) (((x) >> 19) & 0x3) + +#define MFP_PULL_NONE (0x0 << 21) +#define MFP_PULL_LOW (0x1 << 21) +#define MFP_PULL_HIGH (0x2 << 21) +#define MFP_PULL_BOTH (0x3 << 21) +#define MFP_PULL_FLOAT (0x4 << 21) +#define MFP_PULL_MASK (0x7 << 21) +#define MFP_PULL(x) (((x) >> 21) & 0x7) + +#define MFP_CFG_DEFAULT (MFP_AF0 | MFP_DS03X | MFP_LPM_DEFAULT |\ + MFP_LPM_EDGE_NONE | MFP_PULL_NONE) + +#define MFP_CFG(pin, af) \ + ((MFP_CFG_DEFAULT & ~MFP_AF_MASK) |\ + (MFP_PIN(MFP_PIN_##pin) | MFP_##af)) + +#define MFP_CFG_DRV(pin, af, drv) \ + ((MFP_CFG_DEFAULT & ~(MFP_AF_MASK | MFP_DS_MASK)) |\ + (MFP_PIN(MFP_PIN_##pin) | MFP_##af | MFP_##drv)) + +#define MFP_CFG_LPM(pin, af, lpm) \ + ((MFP_CFG_DEFAULT & ~(MFP_AF_MASK | MFP_LPM_STATE_MASK)) |\ + (MFP_PIN(MFP_PIN_##pin) | MFP_##af | MFP_LPM_##lpm)) + +#define MFP_CFG_X(pin, af, drv, lpm) \ + ((MFP_CFG_DEFAULT & ~(MFP_AF_MASK | MFP_DS_MASK | MFP_LPM_STATE_MASK)) |\ + (MFP_PIN(MFP_PIN_##pin) | MFP_##af | MFP_##drv | MFP_LPM_##lpm)) + +#if defined(CONFIG_PXA3xx) || defined(CONFIG_ARCH_MMP) +/* + * each MFP pin will have a MFPR register, since the offset of the + * register varies between processors, the processor specific code + * should initialize the pin offsets by mfp_init() + * + * mfp_init_base() - accepts a virtual base for all MFPR registers and + * initialize the MFP table to a default state + * + * mfp_init_addr() - accepts a table of "mfp_addr_map" structure, which + * represents a range of MFP pins from "start" to "end", with the offset + * beginning at "offset", to define a single pin, let "end" = -1. + * + * use + * + * MFP_ADDR_X() to define a range of pins + * MFP_ADDR() to define a single pin + * MFP_ADDR_END to signal the end of pin offset definitions + */ +struct mfp_addr_map { + unsigned int start; + unsigned int end; + unsigned long offset; +}; + +#define MFP_ADDR_X(start, end, offset) \ + { MFP_PIN_##start, MFP_PIN_##end, offset } + +#define MFP_ADDR(pin, offset) \ + { MFP_PIN_##pin, -1, offset } + +#define MFP_ADDR_END { MFP_PIN_INVALID, 0 } + +void mfp_init_base(void __iomem *mfpr_base); +void mfp_init_addr(struct mfp_addr_map *map); + +/* + * mfp_{read, write}() - for direct read/write access to the MFPR register + * mfp_config() - for configuring a group of MFPR registers + * mfp_config_lpm() - configuring all low power MFPR registers for suspend + * mfp_config_run() - configuring all run time MFPR registers after resume + */ +unsigned long mfp_read(int mfp); +void mfp_write(int mfp, unsigned long mfpr_val); +void mfp_config(unsigned long *mfp_cfgs, int num); +void mfp_config_run(void); +void mfp_config_lpm(void); +#endif /* CONFIG_PXA3xx || CONFIG_ARCH_MMP */ + +#endif /* __ASM_PLAT_MFP_H */ -- cgit v1.2.3 From 645b302673bb74930b5f38f1d5b7e7532f164595 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sun, 24 Apr 2022 14:36:35 +0200 Subject: ARM: pxa/sa1100: move I/O space to PCI_IOBASE PXA and StrongARM1100 traditionally map their I/O space 1:1 into virtual memory, using a per-bus io_offset that matches the base address of the ioremap mapping. In order for PXA to work in a multiplatform config, this needs to change so I/O space starts at PCI_IOBASE (0xfee00000). Since the pcmcia soc_common support is shared with StrongARM1100, both have to change at the same time. The affected machines are: - Anything with a PCMCIA slot now uses pci_remap_iospace, which is made available to PCMCIA configurations as well, rather than just PCI. The first PCMCIA slot now starts at port number 0x10000. - The Zeus and Viper platforms have PC/104-style ISA buses, which have a static mapping for both I/O and memory space at 0xf1000000, which can no longer work. It does not appear to have any in-tree users, so moving it to port number 0 makes them behave like a traditional PC. - SA1100 does support ISA slots in theory, but all machines that originally enabled this appear to have been removed from the tree ages ago, and the I/O space is never mapped anywhere. - The Nanoengine machine has support for PCI slots, but looks like this never included I/O space, the resources only define the location for memory and config space. With this, the definitions of __io() and IO_SPACE_LIMIT can be simplified, as the only remaining cases are the generic PCI_IOBASE and the custom inb()/outb() macros on RiscPC. S3C24xx still has a custom inb()/outb() in this here, but this is already removed in another branch. Signed-off-by: Arnd Bergmann --- include/pcmcia/soc_common.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/pcmcia/soc_common.h b/include/pcmcia/soc_common.h index 26f1473a06c5..d4f18f4679df 100644 --- a/include/pcmcia/soc_common.h +++ b/include/pcmcia/soc_common.h @@ -46,9 +46,9 @@ struct soc_pcmcia_socket { struct resource res_skt; struct resource res_io; + struct resource res_io_io; struct resource res_mem; struct resource res_attr; - void __iomem *virt_io; struct { int gpio; -- cgit v1.2.3 From 3b5eed3c71a2fb60aa4405ad92a2a6ad2677f220 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 3 May 2022 13:54:58 -0700 Subject: netfs: Eliminate Clang randstruct warning Clang's structure layout randomization feature gets upset when it sees struct inode (which is randomized) cast to struct netfs_i_context. This is due to seeing the inode pointer as being treated as an array of inodes, rather than "something else, following struct inode". Since netfs can't use container_of() (since it doesn't know what the true containing struct is), it uses this direct offset instead. Adjust the code to better reflect what is happening: an arbitrary pointer is being adjusted and cast to something else: use a "void *" for the math. The resulting binary output is the same, but Clang no longer sees an unexpected cross-structure cast: In file included from ../fs/nfs/inode.c:50: In file included from ../fs/nfs/fscache.h:15: In file included from ../include/linux/fscache.h:18: ../include/linux/netfs.h:298:9: error: casting from randomized structure pointer type 'struct inode *' to 'struct netfs_i_context *' return (struct netfs_i_context *)(inode + 1); ^ 1 error generated. Cc: David Howells Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220503205503.3054173-2-keescook@chromium.org Reviewed-by: Jeff Layton Link: https://lore.kernel.org/lkml/7562f8eccd7cc0e447becfe9912179088784e3b9.camel@kernel.org --- include/linux/netfs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index c7bf1eaf51d5..0c33b715cbfd 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -295,7 +295,7 @@ extern void netfs_stats_show(struct seq_file *); */ static inline struct netfs_i_context *netfs_i_context(struct inode *inode) { - return (struct netfs_i_context *)(inode + 1); + return (void *)inode + sizeof(*inode); } /** @@ -307,7 +307,7 @@ static inline struct netfs_i_context *netfs_i_context(struct inode *inode) */ static inline struct inode *netfs_inode(struct netfs_i_context *ctx) { - return ((struct inode *)ctx) - 1; + return (void *)ctx - sizeof(struct inode); } /** -- cgit v1.2.3 From 595b893e2087de306d0781795fb8ec47873596a6 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 3 May 2022 13:55:00 -0700 Subject: randstruct: Reorganize Kconfigs and attribute macros In preparation for Clang supporting randstruct, reorganize the Kconfigs, move the attribute macros, and generalize the feature to be named CONFIG_RANDSTRUCT for on/off, CONFIG_RANDSTRUCT_FULL for the full randomization mode, and CONFIG_RANDSTRUCT_PERFORMANCE for the cache-line sized mode. Cc: linux-hardening@vger.kernel.org Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220503205503.3054173-4-keescook@chromium.org --- include/linux/compiler-gcc.h | 8 -------- include/linux/compiler_types.h | 14 +++++++------- include/linux/vermagic.h | 8 ++++---- 3 files changed, 11 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 52299c957c98..a0c55eeaeaf1 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -66,14 +66,6 @@ __builtin_unreachable(); \ } while (0) -#if defined(RANDSTRUCT_PLUGIN) && !defined(__CHECKER__) -#define __randomize_layout __attribute__((randomize_layout)) -#define __no_randomize_layout __attribute__((no_randomize_layout)) -/* This anon struct can add padding, so only enable it under randstruct. */ -#define randomized_struct_fields_start struct { -#define randomized_struct_fields_end } __randomize_layout; -#endif - /* * GCC 'asm goto' miscompiles certain code sequences: * diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 1c2c33ae1b37..d08dfcb0ac68 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -242,15 +242,15 @@ struct ftrace_likely_data { # define __latent_entropy #endif -#ifndef __randomize_layout +#if defined(RANDSTRUCT) && !defined(__CHECKER__) +# define __randomize_layout __designated_init __attribute__((randomize_layout)) +# define __no_randomize_layout __attribute__((no_randomize_layout)) +/* This anon struct can add padding, so only enable it under randstruct. */ +# define randomized_struct_fields_start struct { +# define randomized_struct_fields_end } __randomize_layout; +#else # define __randomize_layout __designated_init -#endif - -#ifndef __no_randomize_layout # define __no_randomize_layout -#endif - -#ifndef randomized_struct_fields_start # define randomized_struct_fields_start # define randomized_struct_fields_end #endif diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h index 329d63babaeb..efb51a2da599 100644 --- a/include/linux/vermagic.h +++ b/include/linux/vermagic.h @@ -32,11 +32,11 @@ #else #define MODULE_VERMAGIC_MODVERSIONS "" #endif -#ifdef RANDSTRUCT_PLUGIN +#ifdef RANDSTRUCT #include -#define MODULE_RANDSTRUCT_PLUGIN "RANDSTRUCT_PLUGIN_" RANDSTRUCT_HASHED_SEED +#define MODULE_RANDSTRUCT "RANDSTRUCT_" RANDSTRUCT_HASHED_SEED #else -#define MODULE_RANDSTRUCT_PLUGIN +#define MODULE_RANDSTRUCT #endif #define VERMAGIC_STRING \ @@ -44,6 +44,6 @@ MODULE_VERMAGIC_SMP MODULE_VERMAGIC_PREEMPT \ MODULE_VERMAGIC_MODULE_UNLOAD MODULE_VERMAGIC_MODVERSIONS \ MODULE_ARCH_VERMAGIC \ - MODULE_RANDSTRUCT_PLUGIN + MODULE_RANDSTRUCT #endif /* _LINUX_VERMAGIC_H */ -- cgit v1.2.3 From be2b34fa9be31c60a95989f984c9a5d40cd781b6 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 3 May 2022 13:55:02 -0700 Subject: randstruct: Move seed generation into scripts/basic/ To enable Clang randstruct support, move the structure layout randomization seed generation out of scripts/gcc-plugins/ into scripts/basic/ so it happens early enough that it can be used by either compiler implementation. The gcc-plugin still builds its own header file, but now does so from the common "randstruct.seed" file. Cc: linux-hardening@vger.kernel.org Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220503205503.3054173-6-keescook@chromium.org --- include/linux/vermagic.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h index efb51a2da599..a54046bf37e5 100644 --- a/include/linux/vermagic.h +++ b/include/linux/vermagic.h @@ -33,7 +33,7 @@ #define MODULE_VERMAGIC_MODVERSIONS "" #endif #ifdef RANDSTRUCT -#include +#include #define MODULE_RANDSTRUCT "RANDSTRUCT_" RANDSTRUCT_HASHED_SEED #else #define MODULE_RANDSTRUCT -- cgit v1.2.3 From 9ec79840d6afaf472294588a6bbe145bcdffa28b Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 27 Apr 2022 18:31:19 +0100 Subject: stackleak: rework stack low bound handling In stackleak_task_init(), stackleak_track_stack(), and __stackleak_erase(), we open-code skipping the STACK_END_MAGIC at the bottom of the stack. Each case is implemented slightly differently, and only the __stackleak_erase() case is commented. In stackleak_task_init() and stackleak_track_stack() we unconditionally add sizeof(unsigned long) to the lowest stack address. In stackleak_task_init() we use end_of_stack() for this, and in stackleak_track_stack() we use task_stack_page(). In __stackleak_erase() we handle this by detecting if `kstack_ptr` has hit the stack end boundary, and if so, conditionally moving it above the magic. This patch adds a new stackleak_task_low_bound() helper which is used in all three cases, which unconditionally adds sizeof(unsigned long) to the lowest address on the task stack, with commentary as to why. This uses end_of_stack() as stackleak_task_init() did prior to this patch, as this is consistent with the code in kernel/fork.c which initializes the STACK_END_MAGIC value. In __stackleak_erase() we no longer need to check whether we've spilled into the STACK_END_MAGIC value, as stackleak_track_stack() ensures that `current->lowest_stack` stops immediately above this, and similarly the poison scan will stop immediately above this. For stackleak_task_init() and stackleak_track_stack() this results in no change to code generation. For __stackleak_erase() the generated assembly is slightly simpler and shorter. Signed-off-by: Mark Rutland Cc: Alexander Popov Cc: Andrew Morton Cc: Andy Lutomirski Cc: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220427173128.2603085-5-mark.rutland@arm.com --- include/linux/stackleak.h | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index ccaab2043fcd..67430faa5c51 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -15,9 +15,22 @@ #ifdef CONFIG_GCC_PLUGIN_STACKLEAK #include +/* + * The lowest address on tsk's stack which we can plausibly erase. + */ +static __always_inline unsigned long +stackleak_task_low_bound(const struct task_struct *tsk) +{ + /* + * The lowest unsigned long on the task stack contains STACK_END_MAGIC, + * which we must not corrupt. + */ + return (unsigned long)end_of_stack(tsk) + sizeof(unsigned long); +} + static inline void stackleak_task_init(struct task_struct *t) { - t->lowest_stack = (unsigned long)end_of_stack(t) + sizeof(unsigned long); + t->lowest_stack = stackleak_task_low_bound(t); # ifdef CONFIG_STACKLEAK_METRICS t->prev_lowest_stack = t->lowest_stack; # endif -- cgit v1.2.3 From 0cfa2ccd285d98ad62218add2eebdcfff69fb2c0 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 27 Apr 2022 18:31:21 +0100 Subject: stackleak: rework stack high bound handling Prior to returning to userspace, we reset current->lowest_stack to a reasonable high bound. Currently we do this by subtracting the arbitrary value `THREAD_SIZE/64` from the top of the stack, for reasons lost to history. Looking at configurations today: * On i386 where THREAD_SIZE is 8K, the bound will be 128 bytes. The pt_regs at the top of the stack is 68 bytes (with 0 to 16 bytes of padding above), and so this covers an additional portion of 44 to 60 bytes. * On x86_64 where THREAD_SIZE is at least 16K (up to 32K with KASAN) the bound will be at least 256 bytes (up to 512 with KASAN). The pt_regs at the top of the stack is 168 bytes, and so this cover an additional 88 bytes of stack (up to 344 with KASAN). * On arm64 where THREAD_SIZE is at least 16K (up to 64K with 64K pages and VMAP_STACK), the bound will be at least 256 bytes (up to 1024 with KASAN). The pt_regs at the top of the stack is 336 bytes, so this can fall within the pt_regs, or can cover an additional 688 bytes of stack. Clearly the `THREAD_SIZE/64` value doesn't make much sense -- in the worst case, this will cause more than 600 bytes of stack to be erased for every syscall, even if actual stack usage were substantially smaller. This patches makes this slightly less nonsensical by consistently resetting current->lowest_stack to the base of the task pt_regs. For clarity and for consistency with the handling of the low bound, the generation of the high bound is split into a helper with commentary explaining why. Since the pt_regs at the top of the stack will be clobbered upon the next exception entry, we don't need to poison these at exception exit. By using task_pt_regs() as the high stack boundary instead of current_top_of_stack() we avoid some redundant poisoning, and the compiler can share the address generation between the poisoning and resetting of `current->lowest_stack`, making the generated code more optimal. It's not clear to me whether the existing `THREAD_SIZE/64` offset was a dodgy heuristic to skip the pt_regs, or whether it was attempting to minimize the number of times stackleak_check_stack() would have to update `current->lowest_stack` when stack usage was shallow at the cost of unconditionally poisoning a small portion of the stack for every exit to userspace. For now I've simply removed the offset, and if we need/want to minimize updates for shallow stack usage it should be easy to add a better heuristic atop, with appropriate commentary so we know what's going on. Signed-off-by: Mark Rutland Cc: Alexander Popov Cc: Andrew Morton Cc: Andy Lutomirski Cc: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220427173128.2603085-7-mark.rutland@arm.com --- include/linux/stackleak.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index 67430faa5c51..467661aeb413 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -28,6 +28,20 @@ stackleak_task_low_bound(const struct task_struct *tsk) return (unsigned long)end_of_stack(tsk) + sizeof(unsigned long); } +/* + * The address immediately after the highest address on tsk's stack which we + * can plausibly erase. + */ +static __always_inline unsigned long +stackleak_task_high_bound(const struct task_struct *tsk) +{ + /* + * The task's pt_regs lives at the top of the task stack and will be + * overwritten by exception entry, so there's no need to erase them. + */ + return (unsigned long)task_pt_regs(tsk); +} + static inline void stackleak_task_init(struct task_struct *t) { t->lowest_stack = stackleak_task_low_bound(t); -- cgit v1.2.3 From 77cf2b6dee6680536a3109d894f1b1ccda3fc5bf Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 27 Apr 2022 18:31:22 +0100 Subject: stackleak: rework poison scanning Currently we over-estimate the region of stack which must be erased. To determine the region to be erased, we scan downwards for a contiguous block of poison values (or the low bound of the stack). There are a few minor problems with this today: * When we find a block of poison values, we include this block within the region to erase. As this is included within the region to erase, this causes us to redundantly overwrite 'STACKLEAK_SEARCH_DEPTH' (128) bytes with poison. * As the loop condition checks 'poison_count <= depth', it will run an additional iteration after finding the contiguous block of poison, decrementing 'erase_low' once more than necessary. As this is included within the region to erase, this causes us to redundantly overwrite an additional unsigned long with poison. * As we always decrement 'erase_low' after checking an element on the stack, we always include the element below this within the region to erase. As this is included within the region to erase, this causes us to redundantly overwrite an additional unsigned long with poison. Note that this is not a functional problem. As the loop condition checks 'erase_low > task_stack_low', we'll never clobber the STACK_END_MAGIC. As we always decrement 'erase_low' after this, we'll never fail to erase the element immediately above the STACK_END_MAGIC. In total, this can cause us to erase `128 + 2 * sizeof(unsigned long)` bytes more than necessary, which is unfortunate. This patch reworks the logic to find the address immediately above the poisoned region, by finding the lowest non-poisoned address. This is factored into a stackleak_find_top_of_poison() helper both for clarity and so that this can be shared with the LKDTM test in subsequent patches. Signed-off-by: Mark Rutland Cc: Alexander Popov Cc: Andrew Morton Cc: Andy Lutomirski Cc: Kees Cook Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220427173128.2603085-8-mark.rutland@arm.com --- include/linux/stackleak.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include') diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index 467661aeb413..c36e7a3b45e7 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -42,6 +42,32 @@ stackleak_task_high_bound(const struct task_struct *tsk) return (unsigned long)task_pt_regs(tsk); } +/* + * Find the address immediately above the poisoned region of the stack, where + * that region falls between 'low' (inclusive) and 'high' (exclusive). + */ +static __always_inline unsigned long +stackleak_find_top_of_poison(const unsigned long low, const unsigned long high) +{ + const unsigned int depth = STACKLEAK_SEARCH_DEPTH / sizeof(unsigned long); + unsigned int poison_count = 0; + unsigned long poison_high = high; + unsigned long sp = high; + + while (sp > low && poison_count < depth) { + sp -= sizeof(unsigned long); + + if (*(unsigned long *)sp == STACKLEAK_POISON) { + poison_count++; + } else { + poison_count = 0; + poison_high = sp; + } + } + + return poison_high; +} + static inline void stackleak_task_init(struct task_struct *t) { t->lowest_stack = stackleak_task_low_bound(t); -- cgit v1.2.3 From 1d6866e8f15c978e82ef16ce6d21ee96b2eca7ee Mon Sep 17 00:00:00 2001 From: Runyang Chen Date: Tue, 1 Mar 2022 13:37:32 +0800 Subject: dt-bindings: reset: mt8186: add reset-controller header file 1. Add toprgu reset-controller header file for MT8186. 2. Add DSI software reset bit which is controlled in MMSYS for MT8186. Signed-off-by: Runyang Chen Signed-off-by: Rex-BC Chen Acked-by: Rob Herring Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20220301054405.25021-3-rex-bc.chen@mediatek.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- include/dt-bindings/reset/mt8186-resets.h | 36 +++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 include/dt-bindings/reset/mt8186-resets.h (limited to 'include') diff --git a/include/dt-bindings/reset/mt8186-resets.h b/include/dt-bindings/reset/mt8186-resets.h new file mode 100644 index 000000000000..5f850370c42c --- /dev/null +++ b/include/dt-bindings/reset/mt8186-resets.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Runyang Chen + */ + +#ifndef _DT_BINDINGS_RESET_CONTROLLER_MT8186 +#define _DT_BINDINGS_RESET_CONTROLLER_MT8186 + +#define MT8186_TOPRGU_INFRA_SW_RST 0 +#define MT8186_TOPRGU_MM_SW_RST 1 +#define MT8186_TOPRGU_MFG_SW_RST 2 +#define MT8186_TOPRGU_VENC_SW_RST 3 +#define MT8186_TOPRGU_VDEC_SW_RST 4 +#define MT8186_TOPRGU_IMG_SW_RST 5 +#define MT8186_TOPRGU_DDR_SW_RST 6 +#define MT8186_TOPRGU_INFRA_AO_SW_RST 8 +#define MT8186_TOPRGU_CONNSYS_SW_RST 9 +#define MT8186_TOPRGU_APMIXED_SW_RST 10 +#define MT8186_TOPRGU_PWRAP_SW_RST 11 +#define MT8186_TOPRGU_CONN_MCU_SW_RST 12 +#define MT8186_TOPRGU_IPNNA_SW_RST 13 +#define MT8186_TOPRGU_WPE_SW_RST 14 +#define MT8186_TOPRGU_ADSP_SW_RST 15 +#define MT8186_TOPRGU_AUDIO_SW_RST 17 +#define MT8186_TOPRGU_CAM_MAIN_SW_RST 18 +#define MT8186_TOPRGU_CAM_RAWA_SW_RST 19 +#define MT8186_TOPRGU_CAM_RAWB_SW_RST 20 +#define MT8186_TOPRGU_IPE_SW_RST 21 +#define MT8186_TOPRGU_IMG2_SW_RST 22 +#define MT8186_TOPRGU_SW_RST_NUM 23 + +/* MMSYS resets */ +#define MT8186_MMSYS_SW0_RST_B_DISP_DSI0 19 + +#endif /* _DT_BINDINGS_RESET_CONTROLLER_MT8186 */ -- cgit v1.2.3 From 5794dda109fc870fce48a8cdf580750b40bf9d15 Mon Sep 17 00:00:00 2001 From: Sam Shih Date: Wed, 5 Jan 2022 18:04:55 +0800 Subject: dt-bindings: reset: mt7986: Add reset-controller header file Add infracfg, toprgu, and ethsys reset-controller header file for MT7986 platform. Signed-off-by: Sam Shih Acked-by: Rob Herring Acked-by: Guenter Roeck Link: https://lore.kernel.org/r/20220105100456.7126-2-sam.shih@mediatek.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- include/dt-bindings/reset/mt7986-resets.h | 55 +++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) create mode 100644 include/dt-bindings/reset/mt7986-resets.h (limited to 'include') diff --git a/include/dt-bindings/reset/mt7986-resets.h b/include/dt-bindings/reset/mt7986-resets.h new file mode 100644 index 000000000000..af3d16c81192 --- /dev/null +++ b/include/dt-bindings/reset/mt7986-resets.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Sam Shih + */ + +#ifndef _DT_BINDINGS_RESET_CONTROLLER_MT7986 +#define _DT_BINDINGS_RESET_CONTROLLER_MT7986 + +/* INFRACFG resets */ +#define MT7986_INFRACFG_PEXTP_MAC_SW_RST 6 +#define MT7986_INFRACFG_SSUSB_SW_RST 7 +#define MT7986_INFRACFG_EIP97_SW_RST 8 +#define MT7986_INFRACFG_AUDIO_SW_RST 13 +#define MT7986_INFRACFG_CQ_DMA_SW_RST 14 + +#define MT7986_INFRACFG_TRNG_SW_RST 17 +#define MT7986_INFRACFG_AP_DMA_SW_RST 32 +#define MT7986_INFRACFG_I2C_SW_RST 33 +#define MT7986_INFRACFG_NFI_SW_RST 34 +#define MT7986_INFRACFG_SPI0_SW_RST 35 +#define MT7986_INFRACFG_SPI1_SW_RST 36 +#define MT7986_INFRACFG_UART0_SW_RST 37 +#define MT7986_INFRACFG_UART1_SW_RST 38 +#define MT7986_INFRACFG_UART2_SW_RST 39 +#define MT7986_INFRACFG_AUXADC_SW_RST 43 + +#define MT7986_INFRACFG_APXGPT_SW_RST 66 +#define MT7986_INFRACFG_PWM_SW_RST 68 + +#define MT7986_INFRACFG_SW_RST_NUM 69 + +/* TOPRGU resets */ +#define MT7986_TOPRGU_APMIXEDSYS_SW_RST 0 +#define MT7986_TOPRGU_SGMII0_SW_RST 1 +#define MT7986_TOPRGU_SGMII1_SW_RST 2 +#define MT7986_TOPRGU_INFRA_SW_RST 3 +#define MT7986_TOPRGU_U2PHY_SW_RST 5 +#define MT7986_TOPRGU_PCIE_SW_RST 6 +#define MT7986_TOPRGU_SSUSB_SW_RST 7 +#define MT7986_TOPRGU_ETHDMA_SW_RST 20 +#define MT7986_TOPRGU_CONSYS_SW_RST 23 + +#define MT7986_TOPRGU_SW_RST_NUM 24 + +/* ETHSYS Subsystem resets */ +#define MT7986_ETHSYS_FE_SW_RST 6 +#define MT7986_ETHSYS_PMTR_SW_RST 8 +#define MT7986_ETHSYS_GMAC_SW_RST 23 +#define MT7986_ETHSYS_PPE0_SW_RST 30 +#define MT7986_ETHSYS_PPE1_SW_RST 31 + +#define MT7986_ETHSYS_SW_RST_NUM 32 + +#endif /* _DT_BINDINGS_RESET_CONTROLLER_MT7986 */ -- cgit v1.2.3 From 2e3afb42dd480d755cd7d97ca04586a5616c1a5e Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Sun, 8 May 2022 11:37:09 +0200 Subject: blk-mq: remove the error_count from struct request The last two users were floppy.c and ataflop.c respectively, it was verified that no other drivers makes use of this, so let's remove it. Suggested-by: Linus Torvalds Cc: Minh Yuan Cc: Denis Efremov , Cc: Geert Uytterhoeven Cc: Christoph Hellwig Signed-off-by: Willy Tarreau Signed-off-by: Linus Torvalds --- include/linux/blk-mq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 7aa5c54901a9..9f07061418db 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -163,7 +163,6 @@ struct request { struct rb_node rb_node; /* sort/lookup */ struct bio_vec special_vec; void *completion_data; - int error_count; /* for legacy drivers, don't use */ }; -- cgit v1.2.3 From 56f5746c414d92ae8e8314f46760822b4ecf8be3 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 22 Feb 2022 09:40:54 -0500 Subject: namei: Merge page_symlink() and __page_symlink() There are no callers of __page_symlink() left, so we can remove that entry point. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Christian Brauner --- include/linux/fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index bbde95387a23..e108aff23a28 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3109,8 +3109,6 @@ extern int page_readlink(struct dentry *, char __user *, int); extern const char *page_get_link(struct dentry *, struct inode *, struct delayed_call *); extern void page_put_link(void *); -extern int __page_symlink(struct inode *inode, const char *symname, int len, - int nofs); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); -- cgit v1.2.3 From 236d93c4bf2d6da83241cc8e4625e89d9604cb43 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 22 Feb 2022 10:40:11 -0500 Subject: fs: Remove AOP_FLAG_NOFS With all users of this flag gone, we can stop testing whether it's set. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/fs.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index e108aff23a28..f81bc5cbcbb6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -275,10 +275,6 @@ enum positive_aop_returns { AOP_TRUNCATED_PAGE = 0x80001, }; -#define AOP_FLAG_NOFS 0x0002 /* used by filesystem to direct - * helper code (eg buffer layer) - * to clear GFP_FS from alloc */ - /* * oh the beauties of C type declarations. */ -- cgit v1.2.3 From de2a931150177957d37e9c975025604f4a1fe853 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 22 Feb 2022 10:47:09 -0500 Subject: fs: Remove aop_flags parameter from netfs_write_begin() There are no more aop flags left, so remove the parameter. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/netfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index c7bf1eaf51d5..1c29f317d907 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -276,7 +276,7 @@ struct readahead_control; extern void netfs_readahead(struct readahead_control *); extern int netfs_readpage(struct file *, struct page *); extern int netfs_write_begin(struct file *, struct address_space *, - loff_t, unsigned int, unsigned int, struct folio **, + loff_t, unsigned int, struct folio **, void **); extern void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool); -- cgit v1.2.3 From b3992d1e2ebcd478e0614494a6abd95e902a029b Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 22 Feb 2022 11:25:12 -0500 Subject: fs: Remove aop flags parameter from block_write_begin() There are no more aop flags left, so remove the parameter. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/buffer_head.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index bcb4fe9b8575..63e49dfa7738 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -226,7 +226,7 @@ int __block_write_full_page(struct inode *inode, struct page *page, int block_read_full_page(struct page*, get_block_t*); bool block_is_partially_uptodate(struct folio *, size_t from, size_t count); int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, - unsigned flags, struct page **pagep, get_block_t *get_block); + struct page **pagep, get_block_t *get_block); int __block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block); int block_write_end(struct file *, struct address_space *, -- cgit v1.2.3 From be3bbbc588118bdc10e21fdd7bfa6ee6b8c2555d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 22 Feb 2022 11:25:12 -0500 Subject: fs: Remove aop flags parameter from cont_write_begin() There are no more aop flags left, so remove the parameter. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/buffer_head.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 63e49dfa7738..127b60fad77e 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -238,7 +238,7 @@ int generic_write_end(struct file *, struct address_space *, void page_zero_new_buffers(struct page *page, unsigned from, unsigned to); void clean_page_buffers(struct page *page); int cont_write_begin(struct file *, struct address_space *, loff_t, - unsigned, unsigned, struct page **, void **, + unsigned, struct page **, void **, get_block_t *, loff_t *); int generic_cont_expand_simple(struct inode *inode, loff_t size); int block_commit_write(struct page *page, unsigned from, unsigned to); -- cgit v1.2.3 From b7446e7cf15f0926866c8e5de90ab278998bf8c8 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 22 Feb 2022 11:25:12 -0500 Subject: fs: Remove aop flags parameter from grab_cache_page_write_begin() There are no more aop flags left, so remove the parameter. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/pagemap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 993994cd943a..65ae8f96554b 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -735,7 +735,7 @@ static inline unsigned find_get_pages_tag(struct address_space *mapping, } struct page *grab_cache_page_write_begin(struct address_space *mapping, - pgoff_t index, unsigned flags); + pgoff_t index); /* * Returns locked page at given index in given cache, creating it if needed. -- cgit v1.2.3 From 8371f30cf774a20fd627a0f7b1ecf00e8257f3bc Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 22 Feb 2022 11:54:56 -0500 Subject: fs: Remove aop flags parameter from nobh_write_begin() There are no more aop flags left, so remove the parameter. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/buffer_head.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 127b60fad77e..6e5a64005fef 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -258,7 +258,7 @@ static inline vm_fault_t block_page_mkwrite_return(int err) } sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *); int block_truncate_page(struct address_space *, loff_t, get_block_t *); -int nobh_write_begin(struct address_space *, loff_t, unsigned, unsigned, +int nobh_write_begin(struct address_space *, loff_t, unsigned len, struct page **, void **, get_block_t*); int nobh_write_end(struct file *, struct address_space *, loff_t, unsigned, unsigned, -- cgit v1.2.3 From 9d6b0cd7579844761ed68926eb3073bab1dca87b Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 22 Feb 2022 14:31:43 -0500 Subject: fs: Remove flags parameter from aops->write_begin There are no more aop flags left, so remove the parameter. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/fs.h | 4 ++-- include/trace/events/ext4.h | 21 ++++++++------------- include/trace/events/f2fs.h | 12 ++++-------- 3 files changed, 14 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index f81bc5cbcbb6..a0e73432526f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -346,7 +346,7 @@ struct address_space_operations { void (*readahead)(struct readahead_control *); int (*write_begin)(struct file *, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata); int (*write_end)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, @@ -3179,7 +3179,7 @@ extern int noop_fsync(struct file *, loff_t, loff_t, int); extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); extern int simple_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, struct page **pagep, void **fsdata); extern const struct address_space_operations ram_aops; extern int always_delete_dentry(const struct dentry *); diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index d06ffffad434..229e8fae66a3 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -335,17 +335,15 @@ TRACE_EVENT(ext4_begin_ordered_truncate, DECLARE_EVENT_CLASS(ext4__write_begin, - TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, - unsigned int flags), + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), - TP_ARGS(inode, pos, len, flags), + TP_ARGS(inode, pos, len), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, pos ) __field( unsigned int, len ) - __field( unsigned int, flags ) ), TP_fast_assign( @@ -353,29 +351,26 @@ DECLARE_EVENT_CLASS(ext4__write_begin, __entry->ino = inode->i_ino; __entry->pos = pos; __entry->len = len; - __entry->flags = flags; ), - TP_printk("dev %d,%d ino %lu pos %lld len %u flags %u", + TP_printk("dev %d,%d ino %lu pos %lld len %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - __entry->pos, __entry->len, __entry->flags) + __entry->pos, __entry->len) ); DEFINE_EVENT(ext4__write_begin, ext4_write_begin, - TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, - unsigned int flags), + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), - TP_ARGS(inode, pos, len, flags) + TP_ARGS(inode, pos, len) ); DEFINE_EVENT(ext4__write_begin, ext4_da_write_begin, - TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, - unsigned int flags), + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), - TP_ARGS(inode, pos, len, flags) + TP_ARGS(inode, pos, len) ); DECLARE_EVENT_CLASS(ext4__write_end, diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 1779e133cea0..bea654a85e6b 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -1159,17 +1159,15 @@ DEFINE_EVENT_CONDITION(f2fs__bio, f2fs_submit_write_bio, TRACE_EVENT(f2fs_write_begin, - TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, - unsigned int flags), + TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), - TP_ARGS(inode, pos, len, flags), + TP_ARGS(inode, pos, len), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) __field(loff_t, pos) __field(unsigned int, len) - __field(unsigned int, flags) ), TP_fast_assign( @@ -1177,14 +1175,12 @@ TRACE_EVENT(f2fs_write_begin, __entry->ino = inode->i_ino; __entry->pos = pos; __entry->len = len; - __entry->flags = flags; ), - TP_printk("dev = (%d,%d), ino = %lu, pos = %llu, len = %u, flags = %u", + TP_printk("dev = (%d,%d), ino = %lu, pos = %llu, len = %u", show_dev_ino(__entry), (unsigned long long)__entry->pos, - __entry->len, - __entry->flags) + __entry->len) ); TRACE_EVENT(f2fs_write_end, -- cgit v1.2.3 From defec178df76e0caadd4e8ef68f3d655a2088198 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Tue, 5 Apr 2022 18:48:41 -0700 Subject: soc: rockchip: power-domain: Manage resource conflicts with firmware On RK3399 platforms, power domains are managed mostly by the kernel (drivers/soc/rockchip/pm_domains.c), but there are a few exceptions where ARM Trusted Firmware has to be involved: (1) system suspend/resume (2) DRAM DVFS (a.k.a., "ddrfreq") Exception (1) does not cause much conflict, since the kernel has quiesced itself by the time we make the relevant PSCI call. Exception (2) can cause conflict, because of two actions: (a) ARM Trusted Firmware needs to read/modify/write the PMU_BUS_IDLE_REQ register to idle the memory controller domain; the kernel driver also has to touch this register for other domains. (b) ARM Trusted Firmware needs to manage the clocks associated with these domains. To elaborate on (b): idling a power domain has always required ungating an array of clocks; see this old explanation from Rockchip: https://lore.kernel.org/linux-arm-kernel/54503C19.9060607@rock-chips.com/ Historically, ARM Trusted Firmware has avoided this issue by using a special PMU_CRU_GATEDIS_CON0 register -- this register ungates all the necessary clocks -- when idling the memory controller. Unfortunately, we've found that this register is not 100% sufficient; it does not turn the relevant PLLs on [0]. So it's possible to trigger issues with something like the following: 1. enable a power domain (e.g., RK3399_PD_VDU) -- kernel will temporarily enable relevant clocks/PLLs, then turn them back off 2. a PLL (e.g., PLL_NPLL) is part of the clock tree for RK3399_PD_VDU's clocks but otherwise unused; NPLL is disabled 3. perform a ddrfreq transition (rk3399_dmcfreq_target() -> ... drivers/clk/rockchip/clk-ddr.c / ROCKCHIP_SIP_DRAM_FREQ) 4. ARM Trusted Firmware unagates VDU clocks (via PMU_CRU_GATEDIS_CON0) 5. ARM Trusted firmware idles the memory controller domain 6. Step 5 waits on the VDU domain/clocks, but NPLL is still off i.e., we hang the system. So for (b), we need to at a minimum manage the relevant PLLs on behalf of firmware. It's easier to simply manage the whole clock tree, in a similar way we do in rockchip_pd_power(). For (a), we need to provide mutual exclusion betwen rockchip_pd_power() and firmware. To resolve that, we simply grab the PMU mutex and release it when ddrfreq is done. The Chromium OS kernel has been carrying versions of part of this hack for a while, based on some new custom notifiers [1]. I've rewritten as a simple function call between the drivers, which is OK because: * the PMU driver isn't enabled, and we don't have this problem at all (the firmware should have left us in an OK state, and there are no runtime conflicts); or * the PMU driver is present, and is a single instance. And the power-domain driver cannot be removed, so there's no lifetime management to worry about. For completeness, there's a 'dmc_pmu_mutex' to guard (likely theoretical?) probe()-time races. It's OK for the memory controller driver to start running before the PMU, because the PMU will avoid any critical actions during the block() sequence. [0] The RK3399 TRM for PMU_CRU_GATEDIS_CON0 only talks about ungating clocks. Based on experimentation, we've found that it does not power up the necessary PLLs. [1] CHROMIUM: soc: rockchip: power-domain: Add notifier to dmc driver https://chromium-review.googlesource.com/q/I242dbd706d352f74ff706f5cbf42ebb92f9bcc60 Notably, the Chromium solution only handled conflict (a), not (b). In practice, item (b) wasn't a problem in many cases because we never managed to fully power off PLLs. Now that the (upstream) video decoder driver performs runtime clock management, we often power off NPLL. Signed-off-by: Brian Norris Tested-by: Peter Geis Reviewed-by: Heiko Stuebner Signed-off-by: Chanwoo Choi --- include/soc/rockchip/pm_domains.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 include/soc/rockchip/pm_domains.h (limited to 'include') diff --git a/include/soc/rockchip/pm_domains.h b/include/soc/rockchip/pm_domains.h new file mode 100644 index 000000000000..7dbd941fc937 --- /dev/null +++ b/include/soc/rockchip/pm_domains.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2022, The Chromium OS Authors. All rights reserved. + */ + +#ifndef __SOC_ROCKCHIP_PM_DOMAINS_H__ +#define __SOC_ROCKCHIP_PM_DOMAINS_H__ + +#ifdef CONFIG_ROCKCHIP_PM_DOMAINS + +int rockchip_pmu_block(void); +void rockchip_pmu_unblock(void); + +#else /* CONFIG_ROCKCHIP_PM_DOMAINS */ + +static inline int rockchip_pmu_block(void) +{ + return 0; +} + +static inline void rockchip_pmu_unblock(void) { } + +#endif /* CONFIG_ROCKCHIP_PM_DOMAINS */ + +#endif /* __SOC_ROCKCHIP_PM_DOMAINS_H__ */ -- cgit v1.2.3 From 84a1041c60ff8f648a09d28af7b2e50a8f6345ed Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 3 Mar 2022 15:00:20 -0500 Subject: fs: Remove pagecache_write_begin() and pagecache_write_end() These wrappers have no more users; remove them. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/fs.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index a0e73432526f..b35ce086a7a1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -380,18 +380,6 @@ struct address_space_operations { extern const struct address_space_operations empty_aops; -/* - * pagecache_write_begin/pagecache_write_end must be used by general code - * to write into the pagecache. - */ -int pagecache_write_begin(struct file *, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata); - -int pagecache_write_end(struct file *, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata); - /** * struct address_space - Contents of a cacheable, mappable object. * @host: Owner, either the inode or the block_device. -- cgit v1.2.3 From 65aa6b5a18294b3713a90c120312ed5d63a16b82 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Mon, 4 Apr 2022 11:38:20 -0400 Subject: filemap: Remove obsolete comment in lock_page We no longer need the page's inode pinned. This comment dates back to commit db37648cd6ce ("[PATCH] mm: non syncing lock_page()") which added lock_page_nosync(). That was removed by commit 7eaceaccab5f ("block: remove per-queue plugging") which also made this comment obsolete. Signed-off-by: Miaohe Lin Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/pagemap.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 65ae8f96554b..ab47579af434 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -908,9 +908,6 @@ static inline void folio_lock(struct folio *folio) __folio_lock(folio); } -/* - * lock_page may only be called if we have the page's inode pinned. - */ static inline void lock_page(struct page *page) { struct folio *folio; -- cgit v1.2.3 From cd125eeab2de8ef8ca3a0f3a284bc695375c73af Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 4 Apr 2022 13:24:36 -0400 Subject: filemap: Update the folio_lock documentation Add kernel-doc for several functions relating to take the folio lock. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/pagemap.h | 59 +++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 57 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ab47579af434..60657132080f 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -888,6 +888,18 @@ bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm, void unlock_page(struct page *page); void folio_unlock(struct folio *folio); +/** + * folio_trylock() - Attempt to lock a folio. + * @folio: The folio to attempt to lock. + * + * Sometimes it is undesirable to wait for a folio to be unlocked (eg + * when the locks are being taken in the wrong order, or if making + * progress through a batch of folios is more important than processing + * them in order). Usually folio_lock() is the correct function to call. + * + * Context: Any context. + * Return: Whether the lock was successfully acquired. + */ static inline bool folio_trylock(struct folio *folio) { return likely(!test_and_set_bit_lock(PG_locked, folio_flags(folio, 0))); @@ -901,6 +913,28 @@ static inline int trylock_page(struct page *page) return folio_trylock(page_folio(page)); } +/** + * folio_lock() - Lock this folio. + * @folio: The folio to lock. + * + * The folio lock protects against many things, probably more than it + * should. It is primarily held while a folio is being brought uptodate, + * either from its backing file or from swap. It is also held while a + * folio is being truncated from its address_space, so holding the lock + * is sufficient to keep folio->mapping stable. + * + * The folio lock is also held while write() is modifying the page to + * provide POSIX atomicity guarantees (as long as the write does not + * cross a page boundary). Other modifications to the data in the folio + * do not hold the folio lock and can race with writes, eg DMA and stores + * to mapped pages. + * + * Context: May sleep. If you need to acquire the locks of two or + * more folios, they must be in order of ascending index, if they are + * in the same address_space. If they are in different address_spaces, + * acquire the lock of the folio which belongs to the address_space which + * has the lowest address in memory first. + */ static inline void folio_lock(struct folio *folio) { might_sleep(); @@ -908,6 +942,17 @@ static inline void folio_lock(struct folio *folio) __folio_lock(folio); } +/** + * lock_page() - Lock the folio containing this page. + * @page: The page to lock. + * + * See folio_lock() for a description of what the lock protects. + * This is a legacy function and new code should probably use folio_lock() + * instead. + * + * Context: May sleep. Pages in the same folio share a lock, so do not + * attempt to lock two pages which share a folio. + */ static inline void lock_page(struct page *page) { struct folio *folio; @@ -918,6 +963,16 @@ static inline void lock_page(struct page *page) __folio_lock(folio); } +/** + * folio_lock_killable() - Lock this folio, interruptible by a fatal signal. + * @folio: The folio to lock. + * + * Attempts to lock the folio, like folio_lock(), except that the sleep + * to acquire the lock is interruptible by a fatal signal. + * + * Context: May sleep; see folio_lock(). + * Return: 0 if the lock was acquired; -EINTR if a fatal signal was received. + */ static inline int folio_lock_killable(struct folio *folio) { might_sleep(); @@ -964,8 +1019,8 @@ int folio_wait_bit_killable(struct folio *folio, int bit_nr); * Wait for a folio to be unlocked. * * This must be called with the caller "holding" the folio, - * ie with increased "page->count" so that the folio won't - * go away during the wait.. + * ie with increased folio reference count so that the folio won't + * go away during the wait. */ static inline void folio_wait_locked(struct folio *folio) { -- cgit v1.2.3 From 520f301c54faa3484e820b80d4505d48ee587163 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 17 Jan 2022 14:35:22 -0500 Subject: fs: Convert is_dirty_writeback() to take a folio Pass a folio instead of a page to aops->is_dirty_writeback(). Convert both implementations and the caller. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/buffer_head.h | 2 +- include/linux/fs.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 6e5a64005fef..805c4e12700a 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -146,7 +146,7 @@ BUFFER_FNS(Defer_Completion, defer_completion) #define page_has_buffers(page) PagePrivate(page) #define folio_buffers(folio) folio_get_private(folio) -void buffer_check_dirty_writeback(struct page *page, +void buffer_check_dirty_writeback(struct folio *folio, bool *dirty, bool *writeback); /* diff --git a/include/linux/fs.h b/include/linux/fs.h index b35ce086a7a1..2be852661a29 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -369,7 +369,7 @@ struct address_space_operations { int (*launder_folio)(struct folio *); bool (*is_partially_uptodate) (struct folio *, size_t from, size_t count); - void (*is_dirty_writeback) (struct page *, bool *, bool *); + void (*is_dirty_writeback) (struct folio *, bool *dirty, bool *wb); int (*error_remove_page)(struct address_space *, struct page *); /* swapfile support */ -- cgit v1.2.3 From 2ebdd1df316636c2faf25a1780e12553adf09cf7 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 17 Mar 2021 22:38:26 -0400 Subject: mm/readahead: Convert page_cache_async_readahead to take a folio Removes a couple of calls to compound_head and saves a few bytes. Also convert verity's read_file_data_page() to be folio-based. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig --- include/linux/pagemap.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 60657132080f..b70192f56454 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1242,7 +1242,7 @@ void page_cache_sync_readahead(struct address_space *mapping, * @mapping: address_space which holds the pagecache and I/O vectors * @ra: file_ra_state which holds the readahead state * @file: Used by the filesystem for authentication. - * @page: The page at @index which triggered the readahead call. + * @folio: The folio at @index which triggered the readahead call. * @index: Index of first page to be read. * @req_count: Total number of pages being read by the caller. * @@ -1254,10 +1254,10 @@ void page_cache_sync_readahead(struct address_space *mapping, static inline void page_cache_async_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *file, - struct page *page, pgoff_t index, unsigned long req_count) + struct folio *folio, pgoff_t index, unsigned long req_count) { DEFINE_READAHEAD(ractl, file, ra, mapping, index); - page_cache_async_ra(&ractl, page_folio(page), req_count); + page_cache_async_ra(&ractl, folio, req_count); } static inline struct folio *__readahead_folio(struct readahead_control *ractl) -- cgit v1.2.3 From 7b43e6d795623e23834dd528c36023f692468480 Mon Sep 17 00:00:00 2001 From: Stefan Binding Date: Wed, 4 May 2022 17:12:34 +0100 Subject: ASoC: cs42l42: Move CS42L42 register descriptions to general include This is to allow the hda driver to have access to the register names, for improved maintainability. Also ensure new header is aligned to 100 columns. Signed-off-by: Stefan Binding Acked-by: Mark Brown Link: https://lore.kernel.org/r/20220504161236.2490532-2-sbinding@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs42l42.h | 810 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 810 insertions(+) create mode 100644 include/sound/cs42l42.h (limited to 'include') diff --git a/include/sound/cs42l42.h b/include/sound/cs42l42.h new file mode 100644 index 000000000000..a55d522f1772 --- /dev/null +++ b/include/sound/cs42l42.h @@ -0,0 +1,810 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * linux/sound/cs42l42.h -- Platform data for CS42L42 ALSA SoC audio driver header + * + * Copyright 2016-2022 Cirrus Logic, Inc. + * + * Author: James Schulman + * Author: Brian Austin + * Author: Michael White + */ + +#ifndef __CS42L42_H +#define __CS42L42_H + +#define CS42L42_PAGE_REGISTER 0x00 /* Page Select Register */ +#define CS42L42_WIN_START 0x00 +#define CS42L42_WIN_LEN 0x100 +#define CS42L42_RANGE_MIN 0x00 +#define CS42L42_RANGE_MAX 0x7F + +#define CS42L42_PAGE_10 0x1000 +#define CS42L42_PAGE_11 0x1100 +#define CS42L42_PAGE_12 0x1200 +#define CS42L42_PAGE_13 0x1300 +#define CS42L42_PAGE_15 0x1500 +#define CS42L42_PAGE_19 0x1900 +#define CS42L42_PAGE_1B 0x1B00 +#define CS42L42_PAGE_1C 0x1C00 +#define CS42L42_PAGE_1D 0x1D00 +#define CS42L42_PAGE_1F 0x1F00 +#define CS42L42_PAGE_20 0x2000 +#define CS42L42_PAGE_21 0x2100 +#define CS42L42_PAGE_23 0x2300 +#define CS42L42_PAGE_24 0x2400 +#define CS42L42_PAGE_25 0x2500 +#define CS42L42_PAGE_26 0x2600 +#define CS42L42_PAGE_28 0x2800 +#define CS42L42_PAGE_29 0x2900 +#define CS42L42_PAGE_2A 0x2A00 +#define CS42L42_PAGE_30 0x3000 + +#define CS42L42_CHIP_ID 0x42A42 + +/* Page 0x10 Global Registers */ +#define CS42L42_DEVID_AB (CS42L42_PAGE_10 + 0x01) +#define CS42L42_DEVID_CD (CS42L42_PAGE_10 + 0x02) +#define CS42L42_DEVID_E (CS42L42_PAGE_10 + 0x03) +#define CS42L42_FABID (CS42L42_PAGE_10 + 0x04) +#define CS42L42_REVID (CS42L42_PAGE_10 + 0x05) +#define CS42L42_FRZ_CTL (CS42L42_PAGE_10 + 0x06) + +#define CS42L42_SRC_CTL (CS42L42_PAGE_10 + 0x07) +#define CS42L42_SRC_BYPASS_DAC_SHIFT 1 +#define CS42L42_SRC_BYPASS_DAC_MASK (1 << CS42L42_SRC_BYPASS_DAC_SHIFT) + +#define CS42L42_MCLK_STATUS (CS42L42_PAGE_10 + 0x08) + +#define CS42L42_MCLK_CTL (CS42L42_PAGE_10 + 0x09) +#define CS42L42_INTERNAL_FS_SHIFT 1 +#define CS42L42_INTERNAL_FS_MASK (1 << CS42L42_INTERNAL_FS_SHIFT) + +#define CS42L42_SFTRAMP_RATE (CS42L42_PAGE_10 + 0x0A) +#define CS42L42_SLOW_START_ENABLE (CS42L42_PAGE_10 + 0x0B) +#define CS42L42_SLOW_START_EN_MASK GENMASK(6, 4) +#define CS42L42_SLOW_START_EN_SHIFT 4 +#define CS42L42_I2C_DEBOUNCE (CS42L42_PAGE_10 + 0x0E) +#define CS42L42_I2C_STRETCH (CS42L42_PAGE_10 + 0x0F) +#define CS42L42_I2C_TIMEOUT (CS42L42_PAGE_10 + 0x10) + +/* Page 0x11 Power and Headset Detect Registers */ +#define CS42L42_PWR_CTL1 (CS42L42_PAGE_11 + 0x01) +#define CS42L42_ASP_DAO_PDN_SHIFT 7 +#define CS42L42_ASP_DAO_PDN_MASK (1 << CS42L42_ASP_DAO_PDN_SHIFT) +#define CS42L42_ASP_DAI_PDN_SHIFT 6 +#define CS42L42_ASP_DAI_PDN_MASK (1 << CS42L42_ASP_DAI_PDN_SHIFT) +#define CS42L42_MIXER_PDN_SHIFT 5 +#define CS42L42_MIXER_PDN_MASK (1 << CS42L42_MIXER_PDN_SHIFT) +#define CS42L42_EQ_PDN_SHIFT 4 +#define CS42L42_EQ_PDN_MASK (1 << CS42L42_EQ_PDN_SHIFT) +#define CS42L42_HP_PDN_SHIFT 3 +#define CS42L42_HP_PDN_MASK (1 << CS42L42_HP_PDN_SHIFT) +#define CS42L42_ADC_PDN_SHIFT 2 +#define CS42L42_ADC_PDN_MASK (1 << CS42L42_ADC_PDN_SHIFT) +#define CS42L42_PDN_ALL_SHIFT 0 +#define CS42L42_PDN_ALL_MASK (1 << CS42L42_PDN_ALL_SHIFT) + +#define CS42L42_PWR_CTL2 (CS42L42_PAGE_11 + 0x02) +#define CS42L42_ADC_SRC_PDNB_SHIFT 0 +#define CS42L42_ADC_SRC_PDNB_MASK (1 << CS42L42_ADC_SRC_PDNB_SHIFT) +#define CS42L42_DAC_SRC_PDNB_SHIFT 1 +#define CS42L42_DAC_SRC_PDNB_MASK (1 << CS42L42_DAC_SRC_PDNB_SHIFT) +#define CS42L42_ASP_DAI1_PDN_SHIFT 2 +#define CS42L42_ASP_DAI1_PDN_MASK (1 << CS42L42_ASP_DAI1_PDN_SHIFT) +#define CS42L42_SRC_PDN_OVERRIDE_SHIFT 3 +#define CS42L42_SRC_PDN_OVERRIDE_MASK (1 << CS42L42_SRC_PDN_OVERRIDE_SHIFT) +#define CS42L42_DISCHARGE_FILT_SHIFT 4 +#define CS42L42_DISCHARGE_FILT_MASK (1 << CS42L42_DISCHARGE_FILT_SHIFT) + +#define CS42L42_PWR_CTL3 (CS42L42_PAGE_11 + 0x03) +#define CS42L42_RING_SENSE_PDNB_SHIFT 1 +#define CS42L42_RING_SENSE_PDNB_MASK (1 << CS42L42_RING_SENSE_PDNB_SHIFT) +#define CS42L42_VPMON_PDNB_SHIFT 2 +#define CS42L42_VPMON_PDNB_MASK (1 << CS42L42_VPMON_PDNB_SHIFT) +#define CS42L42_SW_CLK_STP_STAT_SEL_SHIFT 5 +#define CS42L42_SW_CLK_STP_STAT_SEL_MASK (3 << CS42L42_SW_CLK_STP_STAT_SEL_SHIFT) + +#define CS42L42_RSENSE_CTL1 (CS42L42_PAGE_11 + 0x04) +#define CS42L42_RS_TRIM_R_SHIFT 0 +#define CS42L42_RS_TRIM_R_MASK (1 << CS42L42_RS_TRIM_R_SHIFT) +#define CS42L42_RS_TRIM_T_SHIFT 1 +#define CS42L42_RS_TRIM_T_MASK (1 << CS42L42_RS_TRIM_T_SHIFT) +#define CS42L42_HPREF_RS_SHIFT 2 +#define CS42L42_HPREF_RS_MASK (1 << CS42L42_HPREF_RS_SHIFT) +#define CS42L42_HSBIAS_FILT_REF_RS_SHIFT 3 +#define CS42L42_HSBIAS_FILT_REF_RS_MASK (1 << CS42L42_HSBIAS_FILT_REF_RS_SHIFT) +#define CS42L42_RING_SENSE_PU_HIZ_SHIFT 6 +#define CS42L42_RING_SENSE_PU_HIZ_MASK (1 << CS42L42_RING_SENSE_PU_HIZ_SHIFT) + +#define CS42L42_RSENSE_CTL2 (CS42L42_PAGE_11 + 0x05) +#define CS42L42_TS_RS_GATE_SHIFT 7 +#define CS42L42_TS_RS_GATE_MAS (1 << CS42L42_TS_RS_GATE_SHIFT) + +#define CS42L42_OSC_SWITCH (CS42L42_PAGE_11 + 0x07) +#define CS42L42_SCLK_PRESENT_SHIFT 0 +#define CS42L42_SCLK_PRESENT_MASK (1 << CS42L42_SCLK_PRESENT_SHIFT) + +#define CS42L42_OSC_SWITCH_STATUS (CS42L42_PAGE_11 + 0x09) +#define CS42L42_OSC_SW_SEL_STAT_SHIFT 0 +#define CS42L42_OSC_SW_SEL_STAT_MASK (3 << CS42L42_OSC_SW_SEL_STAT_SHIFT) +#define CS42L42_OSC_PDNB_STAT_SHIFT 2 +#define CS42L42_OSC_PDNB_STAT_MASK (1 << CS42L42_OSC_SW_SEL_STAT_SHIFT) + +#define CS42L42_RSENSE_CTL3 (CS42L42_PAGE_11 + 0x12) +#define CS42L42_RS_RISE_DBNCE_TIME_SHIFT 0 +#define CS42L42_RS_RISE_DBNCE_TIME_MASK (7 << CS42L42_RS_RISE_DBNCE_TIME_SHIFT) +#define CS42L42_RS_FALL_DBNCE_TIME_SHIFT 3 +#define CS42L42_RS_FALL_DBNCE_TIME_MASK (7 << CS42L42_RS_FALL_DBNCE_TIME_SHIFT) +#define CS42L42_RS_PU_EN_SHIFT 6 +#define CS42L42_RS_PU_EN_MASK (1 << CS42L42_RS_PU_EN_SHIFT) +#define CS42L42_RS_INV_SHIFT 7 +#define CS42L42_RS_INV_MASK (1 << CS42L42_RS_INV_SHIFT) + +#define CS42L42_TSENSE_CTL (CS42L42_PAGE_11 + 0x13) +#define CS42L42_TS_RISE_DBNCE_TIME_SHIFT 0 +#define CS42L42_TS_RISE_DBNCE_TIME_MASK (7 << CS42L42_TS_RISE_DBNCE_TIME_SHIFT) +#define CS42L42_TS_FALL_DBNCE_TIME_SHIFT 3 +#define CS42L42_TS_FALL_DBNCE_TIME_MASK (7 << CS42L42_TS_FALL_DBNCE_TIME_SHIFT) +#define CS42L42_TS_INV_SHIFT 7 +#define CS42L42_TS_INV_MASK (1 << CS42L42_TS_INV_SHIFT) + +#define CS42L42_TSRS_INT_DISABLE (CS42L42_PAGE_11 + 0x14) +#define CS42L42_D_RS_PLUG_DBNC_SHIFT 0 +#define CS42L42_D_RS_PLUG_DBNC_MASK (1 << CS42L42_D_RS_PLUG_DBNC_SHIFT) +#define CS42L42_D_RS_UNPLUG_DBNC_SHIFT 1 +#define CS42L42_D_RS_UNPLUG_DBNC_MASK (1 << CS42L42_D_RS_UNPLUG_DBNC_SHIFT) +#define CS42L42_D_TS_PLUG_DBNC_SHIFT 2 +#define CS42L42_D_TS_PLUG_DBNC_MASK (1 << CS42L42_D_TS_PLUG_DBNC_SHIFT) +#define CS42L42_D_TS_UNPLUG_DBNC_SHIFT 3 +#define CS42L42_D_TS_UNPLUG_DBNC_MASK (1 << CS42L42_D_TS_UNPLUG_DBNC_SHIFT) + +#define CS42L42_TRSENSE_STATUS (CS42L42_PAGE_11 + 0x15) +#define CS42L42_RS_PLUG_DBNC_SHIFT 0 +#define CS42L42_RS_PLUG_DBNC_MASK (1 << CS42L42_RS_PLUG_DBNC_SHIFT) +#define CS42L42_RS_UNPLUG_DBNC_SHIFT 1 +#define CS42L42_RS_UNPLUG_DBNC_MASK (1 << CS42L42_RS_UNPLUG_DBNC_SHIFT) +#define CS42L42_TS_PLUG_DBNC_SHIFT 2 +#define CS42L42_TS_PLUG_DBNC_MASK (1 << CS42L42_TS_PLUG_DBNC_SHIFT) +#define CS42L42_TS_UNPLUG_DBNC_SHIFT 3 +#define CS42L42_TS_UNPLUG_DBNC_MASK (1 << CS42L42_TS_UNPLUG_DBNC_SHIFT) + +#define CS42L42_HSDET_CTL1 (CS42L42_PAGE_11 + 0x1F) +#define CS42L42_HSDET_COMP1_LVL_SHIFT 0 +#define CS42L42_HSDET_COMP1_LVL_MASK (15 << CS42L42_HSDET_COMP1_LVL_SHIFT) +#define CS42L42_HSDET_COMP2_LVL_SHIFT 4 +#define CS42L42_HSDET_COMP2_LVL_MASK (15 << CS42L42_HSDET_COMP2_LVL_SHIFT) + +#define CS42L42_HSDET_COMP1_LVL_VAL 12 /* 1.25V Comparator */ +#define CS42L42_HSDET_COMP2_LVL_VAL 2 /* 1.75V Comparator */ +#define CS42L42_HSDET_COMP1_LVL_DEFAULT 7 /* 1V Comparator */ +#define CS42L42_HSDET_COMP2_LVL_DEFAULT 7 /* 2V Comparator */ + +#define CS42L42_HSDET_CTL2 (CS42L42_PAGE_11 + 0x20) +#define CS42L42_HSDET_AUTO_TIME_SHIFT 0 +#define CS42L42_HSDET_AUTO_TIME_MASK (3 << CS42L42_HSDET_AUTO_TIME_SHIFT) +#define CS42L42_HSBIAS_REF_SHIFT 3 +#define CS42L42_HSBIAS_REF_MASK (1 << CS42L42_HSBIAS_REF_SHIFT) +#define CS42L42_HSDET_SET_SHIFT 4 +#define CS42L42_HSDET_SET_MASK (3 << CS42L42_HSDET_SET_SHIFT) +#define CS42L42_HSDET_CTRL_SHIFT 6 +#define CS42L42_HSDET_CTRL_MASK (3 << CS42L42_HSDET_CTRL_SHIFT) + +#define CS42L42_HS_SWITCH_CTL (CS42L42_PAGE_11 + 0x21) +#define CS42L42_SW_GNDHS_HS4_SHIFT 0 +#define CS42L42_SW_GNDHS_HS4_MASK (1 << CS42L42_SW_GNDHS_HS4_SHIFT) +#define CS42L42_SW_GNDHS_HS3_SHIFT 1 +#define CS42L42_SW_GNDHS_HS3_MASK (1 << CS42L42_SW_GNDHS_HS3_SHIFT) +#define CS42L42_SW_HSB_HS4_SHIFT 2 +#define CS42L42_SW_HSB_HS4_MASK (1 << CS42L42_SW_HSB_HS4_SHIFT) +#define CS42L42_SW_HSB_HS3_SHIFT 3 +#define CS42L42_SW_HSB_HS3_MASK (1 << CS42L42_SW_HSB_HS3_SHIFT) +#define CS42L42_SW_HSB_FILT_HS4_SHIFT 4 +#define CS42L42_SW_HSB_FILT_HS4_MASK (1 << CS42L42_SW_HSB_FILT_HS4_SHIFT) +#define CS42L42_SW_HSB_FILT_HS3_SHIFT 5 +#define CS42L42_SW_HSB_FILT_HS3_MASK (1 << CS42L42_SW_HSB_FILT_HS3_SHIFT) +#define CS42L42_SW_REF_HS4_SHIFT 6 +#define CS42L42_SW_REF_HS4_MASK (1 << CS42L42_SW_REF_HS4_SHIFT) +#define CS42L42_SW_REF_HS3_SHIFT 7 +#define CS42L42_SW_REF_HS3_MASK (1 << CS42L42_SW_REF_HS3_SHIFT) + +#define CS42L42_HS_DET_STATUS (CS42L42_PAGE_11 + 0x24) +#define CS42L42_HSDET_TYPE_SHIFT 0 +#define CS42L42_HSDET_TYPE_MASK (3 << CS42L42_HSDET_TYPE_SHIFT) +#define CS42L42_HSDET_COMP1_OUT_SHIFT 6 +#define CS42L42_HSDET_COMP1_OUT_MASK (1 << CS42L42_HSDET_COMP1_OUT_SHIFT) +#define CS42L42_HSDET_COMP2_OUT_SHIFT 7 +#define CS42L42_HSDET_COMP2_OUT_MASK (1 << CS42L42_HSDET_COMP2_OUT_SHIFT) +#define CS42L42_PLUG_CTIA 0 +#define CS42L42_PLUG_OMTP 1 +#define CS42L42_PLUG_HEADPHONE 2 +#define CS42L42_PLUG_INVALID 3 + +#define CS42L42_HSDET_SW_COMP1 ((0 << CS42L42_SW_GNDHS_HS4_SHIFT) | \ + (1 << CS42L42_SW_GNDHS_HS3_SHIFT) | \ + (1 << CS42L42_SW_HSB_HS4_SHIFT) | \ + (0 << CS42L42_SW_HSB_HS3_SHIFT) | \ + (0 << CS42L42_SW_HSB_FILT_HS4_SHIFT) | \ + (1 << CS42L42_SW_HSB_FILT_HS3_SHIFT) | \ + (0 << CS42L42_SW_REF_HS4_SHIFT) | \ + (1 << CS42L42_SW_REF_HS3_SHIFT)) +#define CS42L42_HSDET_SW_COMP2 ((1 << CS42L42_SW_GNDHS_HS4_SHIFT) | \ + (0 << CS42L42_SW_GNDHS_HS3_SHIFT) | \ + (0 << CS42L42_SW_HSB_HS4_SHIFT) | \ + (1 << CS42L42_SW_HSB_HS3_SHIFT) | \ + (1 << CS42L42_SW_HSB_FILT_HS4_SHIFT) | \ + (0 << CS42L42_SW_HSB_FILT_HS3_SHIFT) | \ + (1 << CS42L42_SW_REF_HS4_SHIFT) | \ + (0 << CS42L42_SW_REF_HS3_SHIFT)) +#define CS42L42_HSDET_SW_TYPE1 ((0 << CS42L42_SW_GNDHS_HS4_SHIFT) | \ + (1 << CS42L42_SW_GNDHS_HS3_SHIFT) | \ + (1 << CS42L42_SW_HSB_HS4_SHIFT) | \ + (0 << CS42L42_SW_HSB_HS3_SHIFT) | \ + (0 << CS42L42_SW_HSB_FILT_HS4_SHIFT) | \ + (1 << CS42L42_SW_HSB_FILT_HS3_SHIFT) | \ + (0 << CS42L42_SW_REF_HS4_SHIFT) | \ + (1 << CS42L42_SW_REF_HS3_SHIFT)) +#define CS42L42_HSDET_SW_TYPE2 ((1 << CS42L42_SW_GNDHS_HS4_SHIFT) | \ + (0 << CS42L42_SW_GNDHS_HS3_SHIFT) | \ + (0 << CS42L42_SW_HSB_HS4_SHIFT) | \ + (1 << CS42L42_SW_HSB_HS3_SHIFT) | \ + (1 << CS42L42_SW_HSB_FILT_HS4_SHIFT) | \ + (0 << CS42L42_SW_HSB_FILT_HS3_SHIFT) | \ + (1 << CS42L42_SW_REF_HS4_SHIFT) | \ + (0 << CS42L42_SW_REF_HS3_SHIFT)) +#define CS42L42_HSDET_SW_TYPE3 ((1 << CS42L42_SW_GNDHS_HS4_SHIFT) | \ + (1 << CS42L42_SW_GNDHS_HS3_SHIFT) | \ + (0 << CS42L42_SW_HSB_HS4_SHIFT) | \ + (0 << CS42L42_SW_HSB_HS3_SHIFT) | \ + (1 << CS42L42_SW_HSB_FILT_HS4_SHIFT) | \ + (1 << CS42L42_SW_HSB_FILT_HS3_SHIFT) | \ + (1 << CS42L42_SW_REF_HS4_SHIFT) | \ + (1 << CS42L42_SW_REF_HS3_SHIFT)) +#define CS42L42_HSDET_SW_TYPE4 ((0 << CS42L42_SW_GNDHS_HS4_SHIFT) | \ + (1 << CS42L42_SW_GNDHS_HS3_SHIFT) | \ + (1 << CS42L42_SW_HSB_HS4_SHIFT) | \ + (0 << CS42L42_SW_HSB_HS3_SHIFT) | \ + (0 << CS42L42_SW_HSB_FILT_HS4_SHIFT) | \ + (1 << CS42L42_SW_HSB_FILT_HS3_SHIFT) | \ + (0 << CS42L42_SW_REF_HS4_SHIFT) | \ + (1 << CS42L42_SW_REF_HS3_SHIFT)) + +#define CS42L42_HSDET_COMP_TYPE1 1 +#define CS42L42_HSDET_COMP_TYPE2 2 +#define CS42L42_HSDET_COMP_TYPE3 0 +#define CS42L42_HSDET_COMP_TYPE4 3 + +#define CS42L42_HS_CLAMP_DISABLE (CS42L42_PAGE_11 + 0x29) +#define CS42L42_HS_CLAMP_DISABLE_SHIFT 0 +#define CS42L42_HS_CLAMP_DISABLE_MASK (1 << CS42L42_HS_CLAMP_DISABLE_SHIFT) + +/* Page 0x12 Clocking Registers */ +#define CS42L42_MCLK_SRC_SEL (CS42L42_PAGE_12 + 0x01) +#define CS42L42_MCLKDIV_SHIFT 1 +#define CS42L42_MCLKDIV_MASK (1 << CS42L42_MCLKDIV_SHIFT) +#define CS42L42_MCLK_SRC_SEL_SHIFT 0 +#define CS42L42_MCLK_SRC_SEL_MASK (1 << CS42L42_MCLK_SRC_SEL_SHIFT) + +#define CS42L42_SPDIF_CLK_CFG (CS42L42_PAGE_12 + 0x02) +#define CS42L42_FSYNC_PW_LOWER (CS42L42_PAGE_12 + 0x03) + +#define CS42L42_FSYNC_PW_UPPER (CS42L42_PAGE_12 + 0x04) +#define CS42L42_FSYNC_PULSE_WIDTH_SHIFT 0 +#define CS42L42_FSYNC_PULSE_WIDTH_MASK (0xff << \ + CS42L42_FSYNC_PULSE_WIDTH_SHIFT) + +#define CS42L42_FSYNC_P_LOWER (CS42L42_PAGE_12 + 0x05) + +#define CS42L42_FSYNC_P_UPPER (CS42L42_PAGE_12 + 0x06) +#define CS42L42_FSYNC_PERIOD_SHIFT 0 +#define CS42L42_FSYNC_PERIOD_MASK (0xff << CS42L42_FSYNC_PERIOD_SHIFT) + +#define CS42L42_ASP_CLK_CFG (CS42L42_PAGE_12 + 0x07) +#define CS42L42_ASP_SCLK_EN_SHIFT 5 +#define CS42L42_ASP_SCLK_EN_MASK (1 << CS42L42_ASP_SCLK_EN_SHIFT) +#define CS42L42_ASP_MASTER_MODE 0x01 +#define CS42L42_ASP_SLAVE_MODE 0x00 +#define CS42L42_ASP_MODE_SHIFT 4 +#define CS42L42_ASP_MODE_MASK (1 << CS42L42_ASP_MODE_SHIFT) +#define CS42L42_ASP_SCPOL_SHIFT 2 +#define CS42L42_ASP_SCPOL_MASK (3 << CS42L42_ASP_SCPOL_SHIFT) +#define CS42L42_ASP_SCPOL_NOR 3 +#define CS42L42_ASP_LCPOL_SHIFT 0 +#define CS42L42_ASP_LCPOL_MASK (3 << CS42L42_ASP_LCPOL_SHIFT) +#define CS42L42_ASP_LCPOL_INV 3 + +#define CS42L42_ASP_FRM_CFG (CS42L42_PAGE_12 + 0x08) +#define CS42L42_ASP_STP_SHIFT 4 +#define CS42L42_ASP_STP_MASK (1 << CS42L42_ASP_STP_SHIFT) +#define CS42L42_ASP_5050_SHIFT 3 +#define CS42L42_ASP_5050_MASK (1 << CS42L42_ASP_5050_SHIFT) +#define CS42L42_ASP_FSD_SHIFT 0 +#define CS42L42_ASP_FSD_MASK (7 << CS42L42_ASP_FSD_SHIFT) +#define CS42L42_ASP_FSD_0_5 1 +#define CS42L42_ASP_FSD_1_0 2 +#define CS42L42_ASP_FSD_1_5 3 +#define CS42L42_ASP_FSD_2_0 4 + +#define CS42L42_FS_RATE_EN (CS42L42_PAGE_12 + 0x09) +#define CS42L42_FS_EN_SHIFT 0 +#define CS42L42_FS_EN_MASK (0xf << CS42L42_FS_EN_SHIFT) +#define CS42L42_FS_EN_IASRC_96K 0x1 +#define CS42L42_FS_EN_OASRC_96K 0x2 + +#define CS42L42_IN_ASRC_CLK (CS42L42_PAGE_12 + 0x0A) +#define CS42L42_CLK_IASRC_SEL_SHIFT 0 +#define CS42L42_CLK_IASRC_SEL_MASK (1 << CS42L42_CLK_IASRC_SEL_SHIFT) +#define CS42L42_CLK_IASRC_SEL_6 0 +#define CS42L42_CLK_IASRC_SEL_12 1 + +#define CS42L42_OUT_ASRC_CLK (CS42L42_PAGE_12 + 0x0B) +#define CS42L42_CLK_OASRC_SEL_SHIFT 0 +#define CS42L42_CLK_OASRC_SEL_MASK (1 << CS42L42_CLK_OASRC_SEL_SHIFT) +#define CS42L42_CLK_OASRC_SEL_12 1 + +#define CS42L42_PLL_DIV_CFG1 (CS42L42_PAGE_12 + 0x0C) +#define CS42L42_SCLK_PREDIV_SHIFT 0 +#define CS42L42_SCLK_PREDIV_MASK (3 << CS42L42_SCLK_PREDIV_SHIFT) + +/* Page 0x13 Interrupt Registers */ +/* Interrupts */ +#define CS42L42_ADC_OVFL_STATUS (CS42L42_PAGE_13 + 0x01) +#define CS42L42_MIXER_STATUS (CS42L42_PAGE_13 + 0x02) +#define CS42L42_SRC_STATUS (CS42L42_PAGE_13 + 0x03) +#define CS42L42_ASP_RX_STATUS (CS42L42_PAGE_13 + 0x04) +#define CS42L42_ASP_TX_STATUS (CS42L42_PAGE_13 + 0x05) +#define CS42L42_CODEC_STATUS (CS42L42_PAGE_13 + 0x08) +#define CS42L42_DET_INT_STATUS1 (CS42L42_PAGE_13 + 0x09) +#define CS42L42_DET_INT_STATUS2 (CS42L42_PAGE_13 + 0x0A) +#define CS42L42_SRCPL_INT_STATUS (CS42L42_PAGE_13 + 0x0B) +#define CS42L42_VPMON_STATUS (CS42L42_PAGE_13 + 0x0D) +#define CS42L42_PLL_LOCK_STATUS (CS42L42_PAGE_13 + 0x0E) +#define CS42L42_TSRS_PLUG_STATUS (CS42L42_PAGE_13 + 0x0F) +/* Masks */ +#define CS42L42_ADC_OVFL_INT_MASK (CS42L42_PAGE_13 + 0x16) +#define CS42L42_ADC_OVFL_SHIFT 0 +#define CS42L42_ADC_OVFL_MASK (1 << CS42L42_ADC_OVFL_SHIFT) +#define CS42L42_ADC_OVFL_VAL_MASK CS42L42_ADC_OVFL_MASK + +#define CS42L42_MIXER_INT_MASK (CS42L42_PAGE_13 + 0x17) +#define CS42L42_MIX_CHB_OVFL_SHIFT 0 +#define CS42L42_MIX_CHB_OVFL_MASK (1 << CS42L42_MIX_CHB_OVFL_SHIFT) +#define CS42L42_MIX_CHA_OVFL_SHIFT 1 +#define CS42L42_MIX_CHA_OVFL_MASK (1 << CS42L42_MIX_CHA_OVFL_SHIFT) +#define CS42L42_EQ_OVFL_SHIFT 2 +#define CS42L42_EQ_OVFL_MASK (1 << CS42L42_EQ_OVFL_SHIFT) +#define CS42L42_EQ_BIQUAD_OVFL_SHIFT 3 +#define CS42L42_EQ_BIQUAD_OVFL_MASK (1 << CS42L42_EQ_BIQUAD_OVFL_SHIFT) +#define CS42L42_MIXER_VAL_MASK (CS42L42_MIX_CHB_OVFL_MASK | \ + CS42L42_MIX_CHA_OVFL_MASK | \ + CS42L42_EQ_OVFL_MASK | \ + CS42L42_EQ_BIQUAD_OVFL_MASK) + +#define CS42L42_SRC_INT_MASK (CS42L42_PAGE_13 + 0x18) +#define CS42L42_SRC_ILK_SHIFT 0 +#define CS42L42_SRC_ILK_MASK (1 << CS42L42_SRC_ILK_SHIFT) +#define CS42L42_SRC_OLK_SHIFT 1 +#define CS42L42_SRC_OLK_MASK (1 << CS42L42_SRC_OLK_SHIFT) +#define CS42L42_SRC_IUNLK_SHIFT 2 +#define CS42L42_SRC_IUNLK_MASK (1 << CS42L42_SRC_IUNLK_SHIFT) +#define CS42L42_SRC_OUNLK_SHIFT 3 +#define CS42L42_SRC_OUNLK_MASK (1 << CS42L42_SRC_OUNLK_SHIFT) +#define CS42L42_SRC_VAL_MASK (CS42L42_SRC_ILK_MASK | \ + CS42L42_SRC_OLK_MASK | \ + CS42L42_SRC_IUNLK_MASK | \ + CS42L42_SRC_OUNLK_MASK) + +#define CS42L42_ASP_RX_INT_MASK (CS42L42_PAGE_13 + 0x19) +#define CS42L42_ASPRX_NOLRCK_SHIFT 0 +#define CS42L42_ASPRX_NOLRCK_MASK (1 << CS42L42_ASPRX_NOLRCK_SHIFT) +#define CS42L42_ASPRX_EARLY_SHIFT 1 +#define CS42L42_ASPRX_EARLY_MASK (1 << CS42L42_ASPRX_EARLY_SHIFT) +#define CS42L42_ASPRX_LATE_SHIFT 2 +#define CS42L42_ASPRX_LATE_MASK (1 << CS42L42_ASPRX_LATE_SHIFT) +#define CS42L42_ASPRX_ERROR_SHIFT 3 +#define CS42L42_ASPRX_ERROR_MASK (1 << CS42L42_ASPRX_ERROR_SHIFT) +#define CS42L42_ASPRX_OVLD_SHIFT 4 +#define CS42L42_ASPRX_OVLD_MASK (1 << CS42L42_ASPRX_OVLD_SHIFT) +#define CS42L42_ASP_RX_VAL_MASK (CS42L42_ASPRX_NOLRCK_MASK | \ + CS42L42_ASPRX_EARLY_MASK | \ + CS42L42_ASPRX_LATE_MASK | \ + CS42L42_ASPRX_ERROR_MASK | \ + CS42L42_ASPRX_OVLD_MASK) + +#define CS42L42_ASP_TX_INT_MASK (CS42L42_PAGE_13 + 0x1A) +#define CS42L42_ASPTX_NOLRCK_SHIFT 0 +#define CS42L42_ASPTX_NOLRCK_MASK (1 << CS42L42_ASPTX_NOLRCK_SHIFT) +#define CS42L42_ASPTX_EARLY_SHIFT 1 +#define CS42L42_ASPTX_EARLY_MASK (1 << CS42L42_ASPTX_EARLY_SHIFT) +#define CS42L42_ASPTX_LATE_SHIFT 2 +#define CS42L42_ASPTX_LATE_MASK (1 << CS42L42_ASPTX_LATE_SHIFT) +#define CS42L42_ASPTX_SMERROR_SHIFT 3 +#define CS42L42_ASPTX_SMERROR_MASK (1 << CS42L42_ASPTX_SMERROR_SHIFT) +#define CS42L42_ASP_TX_VAL_MASK (CS42L42_ASPTX_NOLRCK_MASK | \ + CS42L42_ASPTX_EARLY_MASK | \ + CS42L42_ASPTX_LATE_MASK | \ + CS42L42_ASPTX_SMERROR_MASK) + +#define CS42L42_CODEC_INT_MASK (CS42L42_PAGE_13 + 0x1B) +#define CS42L42_PDN_DONE_SHIFT 0 +#define CS42L42_PDN_DONE_MASK (1 << CS42L42_PDN_DONE_SHIFT) +#define CS42L42_HSDET_AUTO_DONE_SHIFT 1 +#define CS42L42_HSDET_AUTO_DONE_MASK (1 << CS42L42_HSDET_AUTO_DONE_SHIFT) +#define CS42L42_CODEC_VAL_MASK (CS42L42_PDN_DONE_MASK | \ + CS42L42_HSDET_AUTO_DONE_MASK) + +#define CS42L42_SRCPL_INT_MASK (CS42L42_PAGE_13 + 0x1C) +#define CS42L42_SRCPL_ADC_LK_SHIFT 0 +#define CS42L42_SRCPL_ADC_LK_MASK (1 << CS42L42_SRCPL_ADC_LK_SHIFT) +#define CS42L42_SRCPL_DAC_LK_SHIFT 2 +#define CS42L42_SRCPL_DAC_LK_MASK (1 << CS42L42_SRCPL_DAC_LK_SHIFT) +#define CS42L42_SRCPL_ADC_UNLK_SHIFT 5 +#define CS42L42_SRCPL_ADC_UNLK_MASK (1 << CS42L42_SRCPL_ADC_UNLK_SHIFT) +#define CS42L42_SRCPL_DAC_UNLK_SHIFT 6 +#define CS42L42_SRCPL_DAC_UNLK_MASK (1 << CS42L42_SRCPL_DAC_UNLK_SHIFT) +#define CS42L42_SRCPL_VAL_MASK (CS42L42_SRCPL_ADC_LK_MASK | \ + CS42L42_SRCPL_DAC_LK_MASK | \ + CS42L42_SRCPL_ADC_UNLK_MASK | \ + CS42L42_SRCPL_DAC_UNLK_MASK) + +#define CS42L42_VPMON_INT_MASK (CS42L42_PAGE_13 + 0x1E) +#define CS42L42_VPMON_SHIFT 0 +#define CS42L42_VPMON_MASK (1 << CS42L42_VPMON_SHIFT) +#define CS42L42_VPMON_VAL_MASK CS42L42_VPMON_MASK + +#define CS42L42_PLL_LOCK_INT_MASK (CS42L42_PAGE_13 + 0x1F) +#define CS42L42_PLL_LOCK_SHIFT 0 +#define CS42L42_PLL_LOCK_MASK (1 << CS42L42_PLL_LOCK_SHIFT) +#define CS42L42_PLL_LOCK_VAL_MASK CS42L42_PLL_LOCK_MASK + +#define CS42L42_TSRS_PLUG_INT_MASK (CS42L42_PAGE_13 + 0x20) +#define CS42L42_RS_PLUG_SHIFT 0 +#define CS42L42_RS_PLUG_MASK (1 << CS42L42_RS_PLUG_SHIFT) +#define CS42L42_RS_UNPLUG_SHIFT 1 +#define CS42L42_RS_UNPLUG_MASK (1 << CS42L42_RS_UNPLUG_SHIFT) +#define CS42L42_TS_PLUG_SHIFT 2 +#define CS42L42_TS_PLUG_MASK (1 << CS42L42_TS_PLUG_SHIFT) +#define CS42L42_TS_UNPLUG_SHIFT 3 +#define CS42L42_TS_UNPLUG_MASK (1 << CS42L42_TS_UNPLUG_SHIFT) +#define CS42L42_TSRS_PLUG_VAL_MASK (CS42L42_RS_PLUG_MASK | \ + CS42L42_RS_UNPLUG_MASK | \ + CS42L42_TS_PLUG_MASK | \ + CS42L42_TS_UNPLUG_MASK) +#define CS42L42_TS_PLUG 3 +#define CS42L42_TS_UNPLUG 0 +#define CS42L42_TS_TRANS 1 + +/* + * NOTE: PLL_START must be 0 while both ADC_PDN=1 and HP_PDN=1. + * Otherwise it will prevent FILT+ from charging properly. + */ +#define CS42L42_PLL_CTL1 (CS42L42_PAGE_15 + 0x01) +#define CS42L42_PLL_START_SHIFT 0 +#define CS42L42_PLL_START_MASK (1 << CS42L42_PLL_START_SHIFT) + +#define CS42L42_PLL_DIV_FRAC0 (CS42L42_PAGE_15 + 0x02) +#define CS42L42_PLL_DIV_FRAC_SHIFT 0 +#define CS42L42_PLL_DIV_FRAC_MASK (0xff << CS42L42_PLL_DIV_FRAC_SHIFT) + +#define CS42L42_PLL_DIV_FRAC1 (CS42L42_PAGE_15 + 0x03) +#define CS42L42_PLL_DIV_FRAC2 (CS42L42_PAGE_15 + 0x04) + +#define CS42L42_PLL_DIV_INT (CS42L42_PAGE_15 + 0x05) +#define CS42L42_PLL_DIV_INT_SHIFT 0 +#define CS42L42_PLL_DIV_INT_MASK (0xff << CS42L42_PLL_DIV_INT_SHIFT) + +#define CS42L42_PLL_CTL3 (CS42L42_PAGE_15 + 0x08) +#define CS42L42_PLL_DIVOUT_SHIFT 0 +#define CS42L42_PLL_DIVOUT_MASK (0xff << CS42L42_PLL_DIVOUT_SHIFT) + +#define CS42L42_PLL_CAL_RATIO (CS42L42_PAGE_15 + 0x0A) +#define CS42L42_PLL_CAL_RATIO_SHIFT 0 +#define CS42L42_PLL_CAL_RATIO_MASK (0xff << CS42L42_PLL_CAL_RATIO_SHIFT) + +#define CS42L42_PLL_CTL4 (CS42L42_PAGE_15 + 0x1B) +#define CS42L42_PLL_MODE_SHIFT 0 +#define CS42L42_PLL_MODE_MASK (3 << CS42L42_PLL_MODE_SHIFT) + +/* Page 0x19 HP Load Detect Registers */ +#define CS42L42_LOAD_DET_RCSTAT (CS42L42_PAGE_19 + 0x25) +#define CS42L42_RLA_STAT_SHIFT 0 +#define CS42L42_RLA_STAT_MASK (3 << CS42L42_RLA_STAT_SHIFT) +#define CS42L42_RLA_STAT_15_OHM 0 + +#define CS42L42_LOAD_DET_DONE (CS42L42_PAGE_19 + 0x26) +#define CS42L42_HPLOAD_DET_DONE_SHIFT 0 +#define CS42L42_HPLOAD_DET_DONE_MASK (1 << CS42L42_HPLOAD_DET_DONE_SHIFT) + +#define CS42L42_LOAD_DET_EN (CS42L42_PAGE_19 + 0x27) +#define CS42L42_HP_LD_EN_SHIFT 0 +#define CS42L42_HP_LD_EN_MASK (1 << CS42L42_HP_LD_EN_SHIFT) + +/* Page 0x1B Headset Interface Registers */ +#define CS42L42_HSBIAS_SC_AUTOCTL (CS42L42_PAGE_1B + 0x70) +#define CS42L42_HSBIAS_SENSE_TRIP_SHIFT 0 +#define CS42L42_HSBIAS_SENSE_TRIP_MASK (7 << CS42L42_HSBIAS_SENSE_TRIP_SHIFT) +#define CS42L42_TIP_SENSE_EN_SHIFT 5 +#define CS42L42_TIP_SENSE_EN_MASK (1 << CS42L42_TIP_SENSE_EN_SHIFT) +#define CS42L42_AUTO_HSBIAS_HIZ_SHIFT 6 +#define CS42L42_AUTO_HSBIAS_HIZ_MASK (1 << CS42L42_AUTO_HSBIAS_HIZ_SHIFT) +#define CS42L42_HSBIAS_SENSE_EN_SHIFT 7 +#define CS42L42_HSBIAS_SENSE_EN_MASK (1 << CS42L42_HSBIAS_SENSE_EN_SHIFT) + +#define CS42L42_WAKE_CTL (CS42L42_PAGE_1B + 0x71) +#define CS42L42_WAKEB_CLEAR_SHIFT 0 +#define CS42L42_WAKEB_CLEAR_MASK (1 << CS42L42_WAKEB_CLEAR_SHIFT) +#define CS42L42_WAKEB_MODE_SHIFT 5 +#define CS42L42_WAKEB_MODE_MASK (1 << CS42L42_WAKEB_MODE_SHIFT) +#define CS42L42_M_HP_WAKE_SHIFT 6 +#define CS42L42_M_HP_WAKE_MASK (1 << CS42L42_M_HP_WAKE_SHIFT) +#define CS42L42_M_MIC_WAKE_SHIFT 7 +#define CS42L42_M_MIC_WAKE_MASK (1 << CS42L42_M_MIC_WAKE_SHIFT) + +#define CS42L42_ADC_DISABLE_MUTE (CS42L42_PAGE_1B + 0x72) +#define CS42L42_ADC_DISABLE_S0_MUTE_SHIFT 7 +#define CS42L42_ADC_DISABLE_S0_MUTE_MASK (1 << CS42L42_ADC_DISABLE_S0_MUTE_SHIFT) + +#define CS42L42_TIPSENSE_CTL (CS42L42_PAGE_1B + 0x73) +#define CS42L42_TIP_SENSE_DEBOUNCE_SHIFT 0 +#define CS42L42_TIP_SENSE_DEBOUNCE_MASK (3 << CS42L42_TIP_SENSE_DEBOUNCE_SHIFT) +#define CS42L42_TIP_SENSE_INV_SHIFT 5 +#define CS42L42_TIP_SENSE_INV_MASK (1 << CS42L42_TIP_SENSE_INV_SHIFT) +#define CS42L42_TIP_SENSE_CTRL_SHIFT 6 +#define CS42L42_TIP_SENSE_CTRL_MASK (3 << CS42L42_TIP_SENSE_CTRL_SHIFT) + +/* + * NOTE: DETECT_MODE must be 0 while both ADC_PDN=1 and HP_PDN=1. + * Otherwise it will prevent FILT+ from charging properly. + */ +#define CS42L42_MISC_DET_CTL (CS42L42_PAGE_1B + 0x74) +#define CS42L42_PDN_MIC_LVL_DET_SHIFT 0 +#define CS42L42_PDN_MIC_LVL_DET_MASK (1 << CS42L42_PDN_MIC_LVL_DET_SHIFT) +#define CS42L42_HSBIAS_CTL_SHIFT 1 +#define CS42L42_HSBIAS_CTL_MASK (3 << CS42L42_HSBIAS_CTL_SHIFT) +#define CS42L42_DETECT_MODE_SHIFT 3 +#define CS42L42_DETECT_MODE_MASK (3 << CS42L42_DETECT_MODE_SHIFT) + +#define CS42L42_MIC_DET_CTL1 (CS42L42_PAGE_1B + 0x75) +#define CS42L42_HS_DET_LEVEL_SHIFT 0 +#define CS42L42_HS_DET_LEVEL_MASK (0x3F << CS42L42_HS_DET_LEVEL_SHIFT) +#define CS42L42_EVENT_STAT_SEL_SHIFT 6 +#define CS42L42_EVENT_STAT_SEL_MASK (1 << CS42L42_EVENT_STAT_SEL_SHIFT) +#define CS42L42_LATCH_TO_VP_SHIFT 7 +#define CS42L42_LATCH_TO_VP_MASK (1 << CS42L42_LATCH_TO_VP_SHIFT) + +#define CS42L42_MIC_DET_CTL2 (CS42L42_PAGE_1B + 0x76) +#define CS42L42_DEBOUNCE_TIME_SHIFT 5 +#define CS42L42_DEBOUNCE_TIME_MASK (0x07 << CS42L42_DEBOUNCE_TIME_SHIFT) + +#define CS42L42_DET_STATUS1 (CS42L42_PAGE_1B + 0x77) +#define CS42L42_HSBIAS_HIZ_MODE_SHIFT 6 +#define CS42L42_HSBIAS_HIZ_MODE_MASK (1 << CS42L42_HSBIAS_HIZ_MODE_SHIFT) +#define CS42L42_TIP_SENSE_SHIFT 7 +#define CS42L42_TIP_SENSE_MASK (1 << CS42L42_TIP_SENSE_SHIFT) + +#define CS42L42_DET_STATUS2 (CS42L42_PAGE_1B + 0x78) +#define CS42L42_SHORT_TRUE_SHIFT 0 +#define CS42L42_SHORT_TRUE_MASK (1 << CS42L42_SHORT_TRUE_SHIFT) +#define CS42L42_HS_TRUE_SHIFT 1 +#define CS42L42_HS_TRUE_MASK (1 << CS42L42_HS_TRUE_SHIFT) + +#define CS42L42_DET_INT1_MASK (CS42L42_PAGE_1B + 0x79) +#define CS42L42_TIP_SENSE_UNPLUG_SHIFT 5 +#define CS42L42_TIP_SENSE_UNPLUG_MASK (1 << CS42L42_TIP_SENSE_UNPLUG_SHIFT) +#define CS42L42_TIP_SENSE_PLUG_SHIFT 6 +#define CS42L42_TIP_SENSE_PLUG_MASK (1 << CS42L42_TIP_SENSE_PLUG_SHIFT) +#define CS42L42_HSBIAS_SENSE_SHIFT 7 +#define CS42L42_HSBIAS_SENSE_MASK (1 << CS42L42_HSBIAS_SENSE_SHIFT) +#define CS42L42_DET_INT_VAL1_MASK (CS42L42_TIP_SENSE_UNPLUG_MASK | \ + CS42L42_TIP_SENSE_PLUG_MASK | \ + CS42L42_HSBIAS_SENSE_MASK) + +#define CS42L42_DET_INT2_MASK (CS42L42_PAGE_1B + 0x7A) +#define CS42L42_M_SHORT_DET_SHIFT 0 +#define CS42L42_M_SHORT_DET_MASK (1 << CS42L42_M_SHORT_DET_SHIFT) +#define CS42L42_M_SHORT_RLS_SHIFT 1 +#define CS42L42_M_SHORT_RLS_MASK (1 << CS42L42_M_SHORT_RLS_SHIFT) +#define CS42L42_M_HSBIAS_HIZ_SHIFT 2 +#define CS42L42_M_HSBIAS_HIZ_MASK (1 << CS42L42_M_HSBIAS_HIZ_SHIFT) +#define CS42L42_M_DETECT_FT_SHIFT 6 +#define CS42L42_M_DETECT_FT_MASK (1 << CS42L42_M_DETECT_FT_SHIFT) +#define CS42L42_M_DETECT_TF_SHIFT 7 +#define CS42L42_M_DETECT_TF_MASK (1 << CS42L42_M_DETECT_TF_SHIFT) +#define CS42L42_DET_INT_VAL2_MASK (CS42L42_M_SHORT_DET_MASK | \ + CS42L42_M_SHORT_RLS_MASK | \ + CS42L42_M_HSBIAS_HIZ_MASK | \ + CS42L42_M_DETECT_FT_MASK | \ + CS42L42_M_DETECT_TF_MASK) + +/* Page 0x1C Headset Bias Registers */ +#define CS42L42_HS_BIAS_CTL (CS42L42_PAGE_1C + 0x03) +#define CS42L42_HSBIAS_RAMP_SHIFT 0 +#define CS42L42_HSBIAS_RAMP_MASK (3 << CS42L42_HSBIAS_RAMP_SHIFT) +#define CS42L42_HSBIAS_PD_SHIFT 4 +#define CS42L42_HSBIAS_PD_MASK (1 << CS42L42_HSBIAS_PD_SHIFT) +#define CS42L42_HSBIAS_CAPLESS_SHIFT 7 +#define CS42L42_HSBIAS_CAPLESS_MASK (1 << CS42L42_HSBIAS_CAPLESS_SHIFT) + +/* Page 0x1D ADC Registers */ +#define CS42L42_ADC_CTL (CS42L42_PAGE_1D + 0x01) +#define CS42L42_ADC_NOTCH_DIS_SHIFT 5 +#define CS42L42_ADC_FORCE_WEAK_VCM_SHIFT 4 +#define CS42L42_ADC_INV_SHIFT 2 +#define CS42L42_ADC_DIG_BOOST_SHIFT 0 + +#define CS42L42_ADC_VOLUME (CS42L42_PAGE_1D + 0x03) +#define CS42L42_ADC_VOL_SHIFT 0 + +#define CS42L42_ADC_WNF_HPF_CTL (CS42L42_PAGE_1D + 0x04) +#define CS42L42_ADC_WNF_CF_SHIFT 4 +#define CS42L42_ADC_WNF_EN_SHIFT 3 +#define CS42L42_ADC_HPF_CF_SHIFT 1 +#define CS42L42_ADC_HPF_EN_SHIFT 0 + +/* Page 0x1F DAC Registers */ +#define CS42L42_DAC_CTL1 (CS42L42_PAGE_1F + 0x01) +#define CS42L42_DACB_INV_SHIFT 1 +#define CS42L42_DACA_INV_SHIFT 0 + +#define CS42L42_DAC_CTL2 (CS42L42_PAGE_1F + 0x06) +#define CS42L42_HPOUT_PULLDOWN_SHIFT 4 +#define CS42L42_HPOUT_PULLDOWN_MASK (15 << CS42L42_HPOUT_PULLDOWN_SHIFT) +#define CS42L42_HPOUT_LOAD_SHIFT 3 +#define CS42L42_HPOUT_LOAD_MASK (1 << CS42L42_HPOUT_LOAD_SHIFT) +#define CS42L42_HPOUT_CLAMP_SHIFT 2 +#define CS42L42_HPOUT_CLAMP_MASK (1 << CS42L42_HPOUT_CLAMP_SHIFT) +#define CS42L42_DAC_HPF_EN_SHIFT 1 +#define CS42L42_DAC_HPF_EN_MASK (1 << CS42L42_DAC_HPF_EN_SHIFT) +#define CS42L42_DAC_MON_EN_SHIFT 0 +#define CS42L42_DAC_MON_EN_MASK (1 << CS42L42_DAC_MON_EN_SHIFT) + +/* Page 0x20 HP CTL Registers */ +#define CS42L42_HP_CTL (CS42L42_PAGE_20 + 0x01) +#define CS42L42_HP_ANA_BMUTE_SHIFT 3 +#define CS42L42_HP_ANA_BMUTE_MASK (1 << CS42L42_HP_ANA_BMUTE_SHIFT) +#define CS42L42_HP_ANA_AMUTE_SHIFT 2 +#define CS42L42_HP_ANA_AMUTE_MASK (1 << CS42L42_HP_ANA_AMUTE_SHIFT) +#define CS42L42_HP_FULL_SCALE_VOL_SHIFT 1 +#define CS42L42_HP_FULL_SCALE_VOL_MASK (1 << CS42L42_HP_FULL_SCALE_VOL_SHIFT) + +/* Page 0x21 Class H Registers */ +#define CS42L42_CLASSH_CTL (CS42L42_PAGE_21 + 0x01) + +/* Page 0x23 Mixer Volume Registers */ +#define CS42L42_MIXER_CHA_VOL (CS42L42_PAGE_23 + 0x01) +#define CS42L42_MIXER_ADC_VOL (CS42L42_PAGE_23 + 0x02) + +#define CS42L42_MIXER_CHB_VOL (CS42L42_PAGE_23 + 0x03) +#define CS42L42_MIXER_CH_VOL_SHIFT 0 +#define CS42L42_MIXER_CH_VOL_MASK (0x3f << CS42L42_MIXER_CH_VOL_SHIFT) + +/* Page 0x24 EQ Registers */ +#define CS42L42_EQ_COEF_IN0 (CS42L42_PAGE_24 + 0x01) +#define CS42L42_EQ_COEF_IN1 (CS42L42_PAGE_24 + 0x02) +#define CS42L42_EQ_COEF_IN2 (CS42L42_PAGE_24 + 0x03) +#define CS42L42_EQ_COEF_IN3 (CS42L42_PAGE_24 + 0x04) +#define CS42L42_EQ_COEF_RW (CS42L42_PAGE_24 + 0x06) +#define CS42L42_EQ_COEF_OUT0 (CS42L42_PAGE_24 + 0x07) +#define CS42L42_EQ_COEF_OUT1 (CS42L42_PAGE_24 + 0x08) +#define CS42L42_EQ_COEF_OUT2 (CS42L42_PAGE_24 + 0x09) +#define CS42L42_EQ_COEF_OUT3 (CS42L42_PAGE_24 + 0x0A) +#define CS42L42_EQ_INIT_STAT (CS42L42_PAGE_24 + 0x0B) +#define CS42L42_EQ_START_FILT (CS42L42_PAGE_24 + 0x0C) +#define CS42L42_EQ_MUTE_CTL (CS42L42_PAGE_24 + 0x0E) + +/* Page 0x25 Audio Port Registers */ +#define CS42L42_SP_RX_CH_SEL (CS42L42_PAGE_25 + 0x01) +#define CS42L42_SP_RX_CHB_SEL_SHIFT 2 +#define CS42L42_SP_RX_CHB_SEL_MASK (3 << CS42L42_SP_RX_CHB_SEL_SHIFT) + +#define CS42L42_SP_RX_ISOC_CTL (CS42L42_PAGE_25 + 0x02) +#define CS42L42_SP_RX_RSYNC_SHIFT 6 +#define CS42L42_SP_RX_RSYNC_MASK (1 << CS42L42_SP_RX_RSYNC_SHIFT) +#define CS42L42_SP_RX_NSB_POS_SHIFT 3 +#define CS42L42_SP_RX_NSB_POS_MASK (7 << CS42L42_SP_RX_NSB_POS_SHIFT) +#define CS42L42_SP_RX_NFS_NSBB_SHIFT 2 +#define CS42L42_SP_RX_NFS_NSBB_MASK (1 << CS42L42_SP_RX_NFS_NSBB_SHIFT) +#define CS42L42_SP_RX_ISOC_MODE_SHIFT 0 +#define CS42L42_SP_RX_ISOC_MODE_MASK (3 << CS42L42_SP_RX_ISOC_MODE_SHIFT) + +#define CS42L42_SP_RX_FS (CS42L42_PAGE_25 + 0x03) +#define CS42l42_SPDIF_CH_SEL (CS42L42_PAGE_25 + 0x04) +#define CS42L42_SP_TX_ISOC_CTL (CS42L42_PAGE_25 + 0x05) +#define CS42L42_SP_TX_FS (CS42L42_PAGE_25 + 0x06) +#define CS42L42_SPDIF_SW_CTL1 (CS42L42_PAGE_25 + 0x07) + +/* Page 0x26 SRC Registers */ +#define CS42L42_SRC_SDIN_FS (CS42L42_PAGE_26 + 0x01) +#define CS42L42_SRC_SDIN_FS_SHIFT 0 +#define CS42L42_SRC_SDIN_FS_MASK (0x1f << CS42L42_SRC_SDIN_FS_SHIFT) + +#define CS42L42_SRC_SDOUT_FS (CS42L42_PAGE_26 + 0x09) + +/* Page 0x28 S/PDIF Registers */ +#define CS42L42_SPDIF_CTL1 (CS42L42_PAGE_28 + 0x01) +#define CS42L42_SPDIF_CTL2 (CS42L42_PAGE_28 + 0x02) +#define CS42L42_SPDIF_CTL3 (CS42L42_PAGE_28 + 0x03) +#define CS42L42_SPDIF_CTL4 (CS42L42_PAGE_28 + 0x04) + +/* Page 0x29 Serial Port TX Registers */ +#define CS42L42_ASP_TX_SZ_EN (CS42L42_PAGE_29 + 0x01) +#define CS42L42_ASP_TX_EN_SHIFT 0 +#define CS42L42_ASP_TX_CH_EN (CS42L42_PAGE_29 + 0x02) +#define CS42L42_ASP_TX0_CH2_SHIFT 1 +#define CS42L42_ASP_TX0_CH1_SHIFT 0 + +#define CS42L42_ASP_TX_CH_AP_RES (CS42L42_PAGE_29 + 0x03) +#define CS42L42_ASP_TX_CH1_AP_SHIFT 7 +#define CS42L42_ASP_TX_CH1_AP_MASK (1 << CS42L42_ASP_TX_CH1_AP_SHIFT) +#define CS42L42_ASP_TX_CH2_AP_SHIFT 6 +#define CS42L42_ASP_TX_CH2_AP_MASK (1 << CS42L42_ASP_TX_CH2_AP_SHIFT) +#define CS42L42_ASP_TX_CH2_RES_SHIFT 2 +#define CS42L42_ASP_TX_CH2_RES_MASK (3 << CS42L42_ASP_TX_CH2_RES_SHIFT) +#define CS42L42_ASP_TX_CH1_RES_SHIFT 0 +#define CS42L42_ASP_TX_CH1_RES_MASK (3 << CS42L42_ASP_TX_CH1_RES_SHIFT) +#define CS42L42_ASP_TX_CH1_BIT_MSB (CS42L42_PAGE_29 + 0x04) +#define CS42L42_ASP_TX_CH1_BIT_LSB (CS42L42_PAGE_29 + 0x05) +#define CS42L42_ASP_TX_HIZ_DLY_CFG (CS42L42_PAGE_29 + 0x06) +#define CS42L42_ASP_TX_CH2_BIT_MSB (CS42L42_PAGE_29 + 0x0A) +#define CS42L42_ASP_TX_CH2_BIT_LSB (CS42L42_PAGE_29 + 0x0B) + +/* Page 0x2A Serial Port RX Registers */ +#define CS42L42_ASP_RX_DAI0_EN (CS42L42_PAGE_2A + 0x01) +#define CS42L42_ASP_RX0_CH_EN_SHIFT 2 +#define CS42L42_ASP_RX0_CH_EN_MASK (0xf << CS42L42_ASP_RX0_CH_EN_SHIFT) +#define CS42L42_ASP_RX0_CH1_SHIFT 2 +#define CS42L42_ASP_RX0_CH2_SHIFT 3 +#define CS42L42_ASP_RX0_CH3_SHIFT 4 +#define CS42L42_ASP_RX0_CH4_SHIFT 5 + +#define CS42L42_ASP_RX_DAI0_CH1_AP_RES (CS42L42_PAGE_2A + 0x02) +#define CS42L42_ASP_RX_DAI0_CH1_BIT_MSB (CS42L42_PAGE_2A + 0x03) +#define CS42L42_ASP_RX_DAI0_CH1_BIT_LSB (CS42L42_PAGE_2A + 0x04) +#define CS42L42_ASP_RX_DAI0_CH2_AP_RES (CS42L42_PAGE_2A + 0x05) +#define CS42L42_ASP_RX_DAI0_CH2_BIT_MSB (CS42L42_PAGE_2A + 0x06) +#define CS42L42_ASP_RX_DAI0_CH2_BIT_LSB (CS42L42_PAGE_2A + 0x07) +#define CS42L42_ASP_RX_DAI0_CH3_AP_RES (CS42L42_PAGE_2A + 0x08) +#define CS42L42_ASP_RX_DAI0_CH3_BIT_MSB (CS42L42_PAGE_2A + 0x09) +#define CS42L42_ASP_RX_DAI0_CH3_BIT_LSB (CS42L42_PAGE_2A + 0x0A) +#define CS42L42_ASP_RX_DAI0_CH4_AP_RES (CS42L42_PAGE_2A + 0x0B) +#define CS42L42_ASP_RX_DAI0_CH4_BIT_MSB (CS42L42_PAGE_2A + 0x0C) +#define CS42L42_ASP_RX_DAI0_CH4_BIT_LSB (CS42L42_PAGE_2A + 0x0D) +#define CS42L42_ASP_RX_DAI1_CH1_AP_RES (CS42L42_PAGE_2A + 0x0E) +#define CS42L42_ASP_RX_DAI1_CH1_BIT_MSB (CS42L42_PAGE_2A + 0x0F) +#define CS42L42_ASP_RX_DAI1_CH1_BIT_LSB (CS42L42_PAGE_2A + 0x10) +#define CS42L42_ASP_RX_DAI1_CH2_AP_RES (CS42L42_PAGE_2A + 0x11) +#define CS42L42_ASP_RX_DAI1_CH2_BIT_MSB (CS42L42_PAGE_2A + 0x12) +#define CS42L42_ASP_RX_DAI1_CH2_BIT_LSB (CS42L42_PAGE_2A + 0x13) + +#define CS42L42_ASP_RX_CH_AP_SHIFT 6 +#define CS42L42_ASP_RX_CH_AP_MASK (1 << CS42L42_ASP_RX_CH_AP_SHIFT) +#define CS42L42_ASP_RX_CH_AP_LOW 0 +#define CS42L42_ASP_RX_CH_AP_HI 1 +#define CS42L42_ASP_RX_CH_RES_SHIFT 0 +#define CS42L42_ASP_RX_CH_RES_MASK (3 << CS42L42_ASP_RX_CH_RES_SHIFT) +#define CS42L42_ASP_RX_CH_RES_32 3 +#define CS42L42_ASP_RX_CH_RES_16 1 +#define CS42L42_ASP_RX_CH_BIT_ST_SHIFT 0 +#define CS42L42_ASP_RX_CH_BIT_ST_MASK (0xff << CS42L42_ASP_RX_CH_BIT_ST_SHIFT) + +/* Page 0x30 ID Registers */ +#define CS42L42_SUB_REVID (CS42L42_PAGE_30 + 0x14) +#define CS42L42_MAX_REGISTER (CS42L42_PAGE_30 + 0x14) + +/* Defines for fracturing values spread across multiple registers */ +#define CS42L42_FRAC0_VAL(val) ((val) & 0x0000ff) +#define CS42L42_FRAC1_VAL(val) (((val) & 0x00ff00) >> 8) +#define CS42L42_FRAC2_VAL(val) (((val) & 0xff0000) >> 16) + +#define CS42L42_NUM_SUPPLIES 5 +#define CS42L42_BOOT_TIME_US 3000 +#define CS42L42_PLL_DIVOUT_TIME_US 800 +#define CS42L42_CLOCK_SWITCH_DELAY_US 150 +#define CS42L42_PLL_LOCK_POLL_US 250 +#define CS42L42_PLL_LOCK_TIMEOUT_US 1250 +#define CS42L42_HP_ADC_EN_TIME_US 20000 +#define CS42L42_PDN_DONE_POLL_US 1000 +#define CS42L42_PDN_DONE_TIMEOUT_US 200000 +#define CS42L42_PDN_DONE_TIME_MS 100 +#define CS42L42_FILT_DISCHARGE_TIME_MS 46 + +#endif /* __CS42L42_H */ -- cgit v1.2.3 From a7cffa11fa9232eabf0c4f441dc53002978ab526 Mon Sep 17 00:00:00 2001 From: Ashish Mhetre Date: Fri, 6 May 2022 15:23:11 +0200 Subject: memory: tegra: Add memory controller channels support From Tegra186 onwards, the memory controller supports multiple channels. Add support for mapping the address spaces of these channels and specify the number of channels supported by Tegra186, Tegra194 and Tegra234. In case of old bindings, channels won't be present. If channels are not present then print a warning and continue so that backward compatibility will be preserved in driver. During error interrupts from memory controller, appropriate registers from these channels need to be accessed for logging error info. Signed-off-by: Ashish Mhetre Reviewed-by: Dmitry Osipenko Signed-off-by: Thierry Reding Link: https://lore.kernel.org/r/20220506132312.3910637-4-thierry.reding@gmail.com Signed-off-by: Krzysztof Kozlowski --- include/soc/tegra/mc.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/soc/tegra/mc.h b/include/soc/tegra/mc.h index 1066b1194a5a..40f1d02a1358 100644 --- a/include/soc/tegra/mc.h +++ b/include/soc/tegra/mc.h @@ -194,6 +194,7 @@ struct tegra_mc_soc { unsigned int atom_size; u8 client_id_mask; + u8 num_channels; const struct tegra_smmu_soc *smmu; @@ -212,6 +213,8 @@ struct tegra_mc { struct tegra_smmu *smmu; struct gart_device *gart; void __iomem *regs; + void __iomem *bcast_ch_regs; + void __iomem **ch_regs; struct clk *clk; int irq; -- cgit v1.2.3 From 54a85e09f44c5fa322a2d186f50862d09f517225 Mon Sep 17 00:00:00 2001 From: Ashish Mhetre Date: Fri, 6 May 2022 15:23:12 +0200 Subject: memory: tegra: Add MC error logging on Tegra186 onward Add support for logging memory controller errors on Tegra186, Tegra194 and Tegra234. On these SoCs, interrupts can occur on multiple channels. Add support required to read the status of interrupts across multiple channels, log and clear them. Also add new interrupts supported on these SoCs. Reviewed-by: Dmitry Osipenko Signed-off-by: Ashish Mhetre Signed-off-by: Thierry Reding Link: https://lore.kernel.org/r/20220506132312.3910637-5-thierry.reding@gmail.com Signed-off-by: Krzysztof Kozlowski --- include/soc/tegra/mc.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/soc/tegra/mc.h b/include/soc/tegra/mc.h index 40f1d02a1358..47ce6d434427 100644 --- a/include/soc/tegra/mc.h +++ b/include/soc/tegra/mc.h @@ -193,12 +193,15 @@ struct tegra_mc_soc { unsigned int num_address_bits; unsigned int atom_size; - u8 client_id_mask; + u16 client_id_mask; u8 num_channels; const struct tegra_smmu_soc *smmu; u32 intmask; + u32 ch_intmask; + u32 global_intstatus_channel_shift; + bool has_addr_hi_reg; const struct tegra_mc_reset_ops *reset_ops; const struct tegra_mc_reset *resets; -- cgit v1.2.3 From 6d97af487dee3176cb1342d4ab16637e495440ad Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Wed, 4 May 2022 08:23:50 +0200 Subject: entry: Rename arch_check_user_regs() to arch_enter_from_user_mode() arch_check_user_regs() is used at the moment to verify that struct pt_regs contains valid values when entering the kernel from userspace. s390 needs a place in the generic entry code to modify a cpu data structure when switching from userspace to kernel mode. As arch_check_user_regs() is exactly this, rename it to arch_enter_from_user_mode(). When entering the kernel from userspace, arch_check_user_regs() is used to verify that struct pt_regs contains valid values. Note that the NMI codepath doesn't call this function. s390 needs a place in the generic entry code to modify a cpu data structure when switching from userspace to kernel mode. As arch_check_user_regs() is exactly this, rename it to arch_enter_from_user_mode(). Signed-off-by: Sven Schnelle Reviewed-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Cc: Andy Lutomirski Link: https://lore.kernel.org/r/20220504062351.2954280-2-tmricht@linux.ibm.com Signed-off-by: Heiko Carstens --- include/linux/entry-common.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index ab78bd4c2eb0..c92ac75d6556 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -63,7 +63,7 @@ ARCH_EXIT_TO_USER_MODE_WORK) /** - * arch_check_user_regs - Architecture specific sanity check for user mode regs + * arch_enter_from_user_mode - Architecture specific sanity check for user mode regs * @regs: Pointer to currents pt_regs * * Defaults to an empty implementation. Can be replaced by architecture @@ -73,10 +73,10 @@ * section. Use __always_inline so the compiler cannot push it out of line * and make it instrumentable. */ -static __always_inline void arch_check_user_regs(struct pt_regs *regs); +static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs); -#ifndef arch_check_user_regs -static __always_inline void arch_check_user_regs(struct pt_regs *regs) {} +#ifndef arch_enter_from_user_mode +static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs) {} #endif /** -- cgit v1.2.3 From 2fbdf45d7d26361a0c3ec8833fd96edf0f5812da Mon Sep 17 00:00:00 2001 From: Ricardo Martinez Date: Fri, 6 May 2022 11:12:57 -0700 Subject: list: Add list_next_entry_circular() and list_prev_entry_circular() Add macros to get the next or previous entries and wraparound if needed. For example, calling list_next_entry_circular() on the last element should return the first element in the list. Signed-off-by: Ricardo Martinez Reviewed-by: Andy Shevchenko Signed-off-by: David S. Miller --- include/linux/list.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include') diff --git a/include/linux/list.h b/include/linux/list.h index dd6c2041d09c..c147eeb2d39d 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -563,6 +563,19 @@ static inline void list_splice_tail_init(struct list_head *list, #define list_next_entry(pos, member) \ list_entry((pos)->member.next, typeof(*(pos)), member) +/** + * list_next_entry_circular - get the next element in list + * @pos: the type * to cursor. + * @head: the list head to take the element from. + * @member: the name of the list_head within the struct. + * + * Wraparound if pos is the last element (return the first element). + * Note, that list is expected to be not empty. + */ +#define list_next_entry_circular(pos, head, member) \ + (list_is_last(&(pos)->member, head) ? \ + list_first_entry(head, typeof(*(pos)), member) : list_next_entry(pos, member)) + /** * list_prev_entry - get the prev element in list * @pos: the type * to cursor @@ -571,6 +584,19 @@ static inline void list_splice_tail_init(struct list_head *list, #define list_prev_entry(pos, member) \ list_entry((pos)->member.prev, typeof(*(pos)), member) +/** + * list_prev_entry_circular - get the prev element in list + * @pos: the type * to cursor. + * @head: the list head to take the element from. + * @member: the name of the list_head within the struct. + * + * Wraparound if pos is the first element (return the last element). + * Note, that list is expected to be not empty. + */ +#define list_prev_entry_circular(pos, head, member) \ + (list_is_first(&(pos)->member, head) ? \ + list_last_entry(head, typeof(*(pos)), member) : list_prev_entry(pos, member)) + /** * list_for_each - iterate over a list * @pos: the &struct list_head to use as a loop cursor. -- cgit v1.2.3 From a4ff365346c98081311c299955d91d657123e8aa Mon Sep 17 00:00:00 2001 From: Ricardo Martinez Date: Fri, 6 May 2022 11:12:58 -0700 Subject: net: skb: introduce skb_data_area_size() Helper to calculate the linear data space in the skb. Signed-off-by: Ricardo Martinez Reviewed-by: Sergey Ryazanov Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5c2599e3fe7d..d58669d6cb91 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1665,6 +1665,11 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) } #endif +static inline unsigned int skb_data_area_size(struct sk_buff *skb) +{ + return skb_end_pointer(skb) - skb->data; +} + struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); -- cgit v1.2.3 From 6cc2df8e3a3967e7c13a424f87f6efb1d4a62d80 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= Date: Fri, 6 May 2022 18:05:07 +0200 Subject: landlock: Add clang-format exceptions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation to a following commit, add clang-format on and clang-format off stanzas around constant definitions. This enables to keep aligned values, which is much more readable than packed definitions. Link: https://lore.kernel.org/r/20220506160513.523257-2-mic@digikod.net Cc: stable@vger.kernel.org Signed-off-by: Mickaël Salaün --- include/uapi/linux/landlock.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index b3d952067f59..15c31abb0d76 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -33,7 +33,9 @@ struct landlock_ruleset_attr { * - %LANDLOCK_CREATE_RULESET_VERSION: Get the highest supported Landlock ABI * version. */ +/* clang-format off */ #define LANDLOCK_CREATE_RULESET_VERSION (1U << 0) +/* clang-format on */ /** * enum landlock_rule_type - Landlock rule type @@ -120,6 +122,7 @@ struct landlock_path_beneath_attr { * :manpage:`access(2)`. * Future Landlock evolutions will enable to restrict them. */ +/* clang-format off */ #define LANDLOCK_ACCESS_FS_EXECUTE (1ULL << 0) #define LANDLOCK_ACCESS_FS_WRITE_FILE (1ULL << 1) #define LANDLOCK_ACCESS_FS_READ_FILE (1ULL << 2) @@ -133,5 +136,6 @@ struct landlock_path_beneath_attr { #define LANDLOCK_ACCESS_FS_MAKE_FIFO (1ULL << 10) #define LANDLOCK_ACCESS_FS_MAKE_BLOCK (1ULL << 11) #define LANDLOCK_ACCESS_FS_MAKE_SYM (1ULL << 12) +/* clang-format on */ #endif /* _UAPI_LINUX_LANDLOCK_H */ -- cgit v1.2.3 From ca4567f1e6f660f86fcd04f3563c0045b0d4772f Mon Sep 17 00:00:00 2001 From: Alaa Mohamed Date: Thu, 5 May 2022 17:09:57 +0200 Subject: rtnetlink: add extack support in fdb del handlers Add extack support to .ndo_fdb_del in netdevice.h and all related methods. Signed-off-by: Alaa Mohamed Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8cf0ac616cb9..74c97a34921d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1513,7 +1513,7 @@ struct net_device_ops { struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, - u16 vid); + u16 vid, struct netlink_ext_ack *extack); int (*ndo_fdb_del_bulk)(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, -- cgit v1.2.3 From 90532850eb210dff70423eaf20e323a91ef542d8 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Fri, 6 May 2022 06:23:52 +0200 Subject: net: phy: introduce genphy_c45_pma_baset1_setup_master_slave() Move baset1 specific part of genphy_c45_pma_setup_forced() code to separate function to make it reusable by PHY drivers. Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index 2d12054932ba..d3f924d3b235 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1614,6 +1614,7 @@ int genphy_c45_read_link(struct phy_device *phydev); int genphy_c45_read_lpa(struct phy_device *phydev); int genphy_c45_read_pma(struct phy_device *phydev); int genphy_c45_pma_setup_forced(struct phy_device *phydev); +int genphy_c45_pma_baset1_setup_master_slave(struct phy_device *phydev); int genphy_c45_an_config_aneg(struct phy_device *phydev); int genphy_c45_an_disable_aneg(struct phy_device *phydev); int genphy_c45_read_mdix(struct phy_device *phydev); -- cgit v1.2.3 From b9a366f3d874ce1c9c0148ec399f2ce4ab05a467 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Fri, 6 May 2022 06:23:54 +0200 Subject: net: phy: introduce genphy_c45_pma_baset1_read_master_slave() Move baset1 specific part of genphy_c45_read_pma() code to separate function to make it reusable by PHY drivers. Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index d3f924d3b235..4713c95d65fb 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1619,6 +1619,7 @@ int genphy_c45_an_config_aneg(struct phy_device *phydev); int genphy_c45_an_disable_aneg(struct phy_device *phydev); int genphy_c45_read_mdix(struct phy_device *phydev); int genphy_c45_pma_read_abilities(struct phy_device *phydev); +int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev); int genphy_c45_read_status(struct phy_device *phydev); int genphy_c45_config_aneg(struct phy_device *phydev); int genphy_c45_loopback(struct phy_device *phydev, bool enable); -- cgit v1.2.3 From 2013ad8836aceb828c0fb5b16fa8bb98fd3d9b28 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Fri, 6 May 2022 06:23:56 +0200 Subject: net: phy: export genphy_c45_baset1_read_status() Export genphy_c45_baset1_read_status() to make it reusable by PHY drivers. Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index 4713c95d65fb..508f1149665b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1621,6 +1621,7 @@ int genphy_c45_read_mdix(struct phy_device *phydev); int genphy_c45_pma_read_abilities(struct phy_device *phydev); int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev); int genphy_c45_read_status(struct phy_device *phydev); +int genphy_c45_baset1_read_status(struct phy_device *phydev); int genphy_c45_config_aneg(struct phy_device *phydev); int genphy_c45_loopback(struct phy_device *phydev, bool enable); int genphy_c45_pma_resume(struct phy_device *phydev); -- cgit v1.2.3 From 0257be79fc4a16a3252ce80aa13b3640f728c425 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Fri, 29 Apr 2022 12:20:18 +0200 Subject: mtd: spi-nor: expose internal parameters via debugfs There is no way to gather all information to verify support for a new flash chip. Also if you want to convert an existing flash chip to the new SFDP parsing, there is not enough information to determine if the flash will work like before. To ease this development, expose internal parameters via the debugfs. Signed-off-by: Michael Walle Signed-off-by: Pratyush Yadav Reviewed-by: Pratyush Yadav Link: https://lore.kernel.org/r/20220429102018.2361038-2-michael@walle.cc --- include/linux/mtd/spi-nor.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index e505c4a5c530..1ede4c89805a 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -363,6 +363,7 @@ struct spi_nor_flash_parameter; * @write_proto: the SPI protocol for write operations * @reg_proto: the SPI protocol for read_reg/write_reg/erase operations * @sfdp: the SFDP data of the flash + * @debugfs_root: pointer to the debugfs directory * @controller_ops: SPI NOR controller driver specific operations. * @params: [FLASH-SPECIFIC] SPI NOR flash parameters and settings. * The structure includes legacy flash parameters and @@ -392,6 +393,7 @@ struct spi_nor { u32 flags; enum spi_nor_cmd_ext cmd_ext_type; struct sfdp *sfdp; + struct dentry *debugfs_root; const struct spi_nor_controller_ops *controller_ops; -- cgit v1.2.3 From 5c832efdbf8651e2800a0169a870786bd85ee230 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Wed, 4 May 2022 18:08:28 +0100 Subject: ASoC: soc-component: Add comment for the endianness flag Add a comment to make the purpose of the endianness flag on the snd_soc_component structure more clear. Signed-off-by: Charles Keepax Link: https://lore.kernel.org/r/20220504170905.332415-2-ckeepax@opensource.cirrus.com Signed-off-by: Mark Brown --- include/sound/soc-component.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/sound/soc-component.h b/include/sound/soc-component.h index 766dc6f009c0..5a764c3099d3 100644 --- a/include/sound/soc-component.h +++ b/include/sound/soc-component.h @@ -169,6 +169,15 @@ struct snd_soc_component_driver { unsigned int idle_bias_on:1; unsigned int suspend_bias_off:1; unsigned int use_pmdown_time:1; /* care pmdown_time at stop */ + /* + * Indicates that the component does not care about the endianness of + * PCM audio data and the core will ensure that both LE and BE variants + * of each used format are present. Typically this is because the + * component sits behind a bus that abstracts away the endian of the + * original data, ie. one for which the transmission endian is defined + * (I2S/SLIMbus/SoundWire), or the concept of endian doesn't exist (PDM, + * analogue). + */ unsigned int endianness:1; unsigned int non_legacy_dai_naming:1; -- cgit v1.2.3 From a36e07dfe6ee71e209383ea9288cd8d1617e14f9 Mon Sep 17 00:00:00 2001 From: Gleb Fotengauer-Malinovskiy Date: Fri, 6 May 2022 17:24:54 +0000 Subject: rfkill: uapi: fix RFKILL_IOCTL_MAX_SIZE ioctl request definition The definition of RFKILL_IOCTL_MAX_SIZE introduced by commit 54f586a91532 ("rfkill: make new event layout opt-in") is unusable since it is based on RFKILL_IOC_EXT_SIZE which has not been defined. Fix that by replacing the undefined constant with the constant which is intended to be used in this definition. Fixes: 54f586a91532 ("rfkill: make new event layout opt-in") Cc: stable@vger.kernel.org # 5.11+ Signed-off-by: Gleb Fotengauer-Malinovskiy Signed-off-by: Dmitry V. Levin Link: https://lore.kernel.org/r/20220506172454.120319-1-glebfm@altlinux.org [add commit message provided later by Dmitry] Signed-off-by: Johannes Berg --- include/uapi/linux/rfkill.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/rfkill.h b/include/uapi/linux/rfkill.h index 283c5a7b3f2c..db6c8588c1d0 100644 --- a/include/uapi/linux/rfkill.h +++ b/include/uapi/linux/rfkill.h @@ -184,7 +184,7 @@ struct rfkill_event_ext { #define RFKILL_IOC_NOINPUT 1 #define RFKILL_IOCTL_NOINPUT _IO(RFKILL_IOC_MAGIC, RFKILL_IOC_NOINPUT) #define RFKILL_IOC_MAX_SIZE 2 -#define RFKILL_IOCTL_MAX_SIZE _IOW(RFKILL_IOC_MAGIC, RFKILL_IOC_EXT_SIZE, __u32) +#define RFKILL_IOCTL_MAX_SIZE _IOW(RFKILL_IOC_MAGIC, RFKILL_IOC_MAX_SIZE, __u32) /* and that's all userspace gets */ -- cgit v1.2.3 From ebdeb7c01d025cb059f05dc26b9dc914e46dd43f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 31 Mar 2022 19:27:52 -0600 Subject: io_uring: add support for 128-byte SQEs Normal SQEs are 64-bytes in length, which is fine for all the commands we support. However, in preparation for supporting passthrough IO, provide an option for setting up a ring with 128-byte SQEs. We continue to use the same type for io_uring_sqe, it's marked and commented with a zero sized array pad at the end. This provides up to 80 bytes of data for a passthrough command - 64 bytes for the extra added data, and 16 bytes available at the end of the existing SQE. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 31e719f38615..ee84132cadad 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -63,6 +63,12 @@ struct io_uring_sqe { }; __u64 addr3; __u64 __pad2[1]; + + /* + * If the ring is initialized with IORING_SETUP_SQE128, then this field + * contains 64-bytes of padding, doubling the size of the SQE. + */ + __u64 __big_sqe_pad[0]; }; enum { @@ -119,6 +125,8 @@ enum { */ #define IORING_SETUP_TASKRUN_FLAG (1U << 9) +#define IORING_SETUP_SQE128 (1U << 10) /* SQEs are 128 byte */ + enum io_uring_op { IORING_OP_NOP, IORING_OP_READV, -- cgit v1.2.3 From 7a51e5b44b92686eebd3e1b46b86e1eb4db975db Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Tue, 26 Apr 2022 11:21:23 -0700 Subject: io_uring: support CQE32 in io_uring_cqe This adds the big_cqe array to the struct io_uring_cqe to support large CQE's. Co-developed-by: Jens Axboe Signed-off-by: Stefan Roesch Reviewed-by: Kanchan Joshi Link: https://lore.kernel.org/r/20220426182134.136504-2-shr@fb.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index ee84132cadad..ac2d90d669c3 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -126,6 +126,7 @@ enum { #define IORING_SETUP_TASKRUN_FLAG (1U << 9) #define IORING_SETUP_SQE128 (1U << 10) /* SQEs are 128 byte */ +#define IORING_SETUP_CQE32 (1U << 11) /* CQEs are 32 byte */ enum io_uring_op { IORING_OP_NOP, @@ -245,6 +246,12 @@ struct io_uring_cqe { __u64 user_data; /* sqe->data submission passed back */ __s32 res; /* result code for this event */ __u32 flags; + + /* + * If the ring is initialized with IORING_SETUP_CQE32, then this field + * contains 16-bytes of padding, doubling the size of the CQE. + */ + __u64 big_cqe[]; }; /* -- cgit v1.2.3 From c4bb964fa092fb68645a852365dfe9855fef178a Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Tue, 26 Apr 2022 11:21:31 -0700 Subject: io_uring: add tracing for additional CQE32 fields This adds tracing for the extra1 and extra2 fields. Co-developed-by: Jens Axboe Signed-off-by: Stefan Roesch Reviewed-by: Kanchan Joshi Link: https://lore.kernel.org/r/20220426182134.136504-10-shr@fb.com Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 3f2961baebcc..630982b3c34c 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -321,13 +321,16 @@ TRACE_EVENT(io_uring_fail_link, * @user_data: user data associated with the request * @res: result of the request * @cflags: completion flags + * @extra1: extra 64-bit data for CQE32 + * @extra2: extra 64-bit data for CQE32 * */ TRACE_EVENT(io_uring_complete, - TP_PROTO(void *ctx, void *req, u64 user_data, int res, unsigned cflags), + TP_PROTO(void *ctx, void *req, u64 user_data, int res, unsigned cflags, + u64 extra1, u64 extra2), - TP_ARGS(ctx, req, user_data, res, cflags), + TP_ARGS(ctx, req, user_data, res, cflags, extra1, extra2), TP_STRUCT__entry ( __field( void *, ctx ) @@ -335,6 +338,8 @@ TRACE_EVENT(io_uring_complete, __field( u64, user_data ) __field( int, res ) __field( unsigned, cflags ) + __field( u64, extra1 ) + __field( u64, extra2 ) ), TP_fast_assign( @@ -343,12 +348,17 @@ TRACE_EVENT(io_uring_complete, __entry->user_data = user_data; __entry->res = res; __entry->cflags = cflags; + __entry->extra1 = extra1; + __entry->extra2 = extra2; ), - TP_printk("ring %p, req %p, user_data 0x%llx, result %d, cflags 0x%x", + TP_printk("ring %p, req %p, user_data 0x%llx, result %d, cflags 0x%x " + "extra1 %llu extra2 %llu ", __entry->ctx, __entry->req, __entry->user_data, - __entry->res, __entry->cflags) + __entry->res, __entry->cflags, + (unsigned long long) __entry->extra1, + (unsigned long long) __entry->extra2) ); /** -- cgit v1.2.3 From b1c5f3085149e9643b125eb10aae0e74644d7dcc Mon Sep 17 00:00:00 2001 From: Ricky WU Date: Mon, 21 Mar 2022 11:18:30 +0000 Subject: misc: rtsx: add rts5261 efuse function move rts5261_fetch_vendor_settings() to rts5261_init_from_hw() make sure it be called from S3 or D3 add more register setting when efuse is set read efuse setting to register on init flow Signed-off-by: Ricky Wu Link: https://lore.kernel.org/r/18101ecb0f0749ccb9f564eda171ba40@realtek.com Signed-off-by: Greg Kroah-Hartman --- include/linux/rtsx_pci.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h index 3d780b44e678..534038d962e4 100644 --- a/include/linux/rtsx_pci.h +++ b/include/linux/rtsx_pci.h @@ -1067,6 +1067,9 @@ #define PCR_SETTING_REG1 0x724 #define PCR_SETTING_REG2 0x814 #define PCR_SETTING_REG3 0x747 +#define PCR_SETTING_REG4 0x818 +#define PCR_SETTING_REG5 0x81C + #define rtsx_pci_init_cmd(pcr) ((pcr)->ci = 0) -- cgit v1.2.3 From bd32889e841c12533d09a1bd02bba932baa9ed8f Mon Sep 17 00:00:00 2001 From: Carlos Llamas Date: Fri, 29 Apr 2022 23:56:41 +0000 Subject: binder: add BINDER_GET_EXTENDED_ERROR ioctl Provide a userspace mechanism to pull precise error information upon failed operations. Extending the current error codes returned by the interfaces allows userspace to better determine the course of action. This could be for instance, retrying a failed transaction at a later point and thus offloading the error handling from the driver. Acked-by: Christian Brauner (Microsoft) Acked-by: Todd Kjos Signed-off-by: Carlos Llamas Link: https://lore.kernel.org/r/20220429235644.697372-3-cmllamas@google.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/android/binder.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index 11157fae8a8e..e6ee8cae303b 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -236,6 +236,21 @@ struct binder_frozen_status_info { __u32 async_recv; }; +/* struct binder_extened_error - extended error information + * @id: identifier for the failed operation + * @command: command as defined by binder_driver_return_protocol + * @param: parameter holding a negative errno value + * + * Used with BINDER_GET_EXTENDED_ERROR. This extends the error information + * returned by the driver upon a failed operation. Userspace can pull this + * data to properly handle specific error scenarios. + */ +struct binder_extended_error { + __u32 id; + __u32 command; + __s32 param; +}; + #define BINDER_WRITE_READ _IOWR('b', 1, struct binder_write_read) #define BINDER_SET_IDLE_TIMEOUT _IOW('b', 3, __s64) #define BINDER_SET_MAX_THREADS _IOW('b', 5, __u32) @@ -249,6 +264,7 @@ struct binder_frozen_status_info { #define BINDER_FREEZE _IOW('b', 14, struct binder_freeze_info) #define BINDER_GET_FROZEN_INFO _IOWR('b', 15, struct binder_frozen_status_info) #define BINDER_ENABLE_ONEWAY_SPAM_DETECTION _IOW('b', 16, __u32) +#define BINDER_GET_EXTENDED_ERROR _IOWR('b', 17, struct binder_extended_error) /* * NOTE: Two special error codes you should check for when calling -- cgit v1.2.3 From dbc2f62061c6bfba0aee93161ee3194dcee84bd0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Fri, 29 Apr 2022 17:26:46 +0100 Subject: nvmem: core: support passing DT node in cell info MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some hardware may have NVMEM cells described in Device Tree using individual nodes. Let drivers pass such nodes to the NVMEM subsystem so they can be later used by NVMEM consumers. Signed-off-by: Rafał Miłecki Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20220429162701.2222-2-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index c0c0cefc3b92..980f9c9ac0bc 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -25,6 +25,7 @@ struct nvmem_cell_info { unsigned int bytes; unsigned int bit_offset; unsigned int nbits; + struct device_node *np; }; /** -- cgit v1.2.3 From 5efe7448a1426250b5747c10ad438517f44f1e51 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Apr 2022 08:43:23 -0400 Subject: fs: Introduce aops->read_folio Change all the callers of ->readpage to call ->read_folio in preference, if it exists. This is a transitional duplication, and will be removed by the end of the series. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2be852661a29..5ad942183a2c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -336,6 +336,7 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb) struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); int (*readpage)(struct file *, struct page *); + int (*read_folio)(struct file *, struct folio *); /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); -- cgit v1.2.3 From 6c62371b7fd77628feb5b806bc29433caecedff8 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Apr 2022 08:49:28 -0400 Subject: fs: Convert netfs_readpage to netfs_read_folio This is straightforward because netfs already worked in terms of folios. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/netfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 1c29f317d907..4bd5ee709daa 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -274,7 +274,7 @@ struct netfs_cache_ops { struct readahead_control; extern void netfs_readahead(struct readahead_control *); -extern int netfs_readpage(struct file *, struct page *); +int netfs_read_folio(struct file *, struct folio *); extern int netfs_write_begin(struct file *, struct address_space *, loff_t, unsigned int, struct folio **, void **); -- cgit v1.2.3 From 7479c505b4ab5ed5f81f35fdd68c44c58d6f0439 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Apr 2022 08:54:32 -0400 Subject: fs: Convert iomap_readpage to iomap_read_folio A straightforward conversion as iomap_readpage already worked in folios. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/iomap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index b76f0dd149fb..5b2aa45ddda3 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -225,7 +225,7 @@ static inline const struct iomap *iomap_iter_srcmap(const struct iomap_iter *i) ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops); -int iomap_readpage(struct page *page, const struct iomap_ops *ops); +int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops); void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops); bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count); int iomap_releasepage(struct page *page, gfp_t gfp_mask); -- cgit v1.2.3 From 2c69e2057962b6bd76d72446453862eb59325b49 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Apr 2022 10:40:40 -0400 Subject: fs: Convert block_read_full_page() to block_read_full_folio() This function is NOT converted to handle large folios, so include an assert that the filesystem isn't passing one in. Otherwise, use the folio functions instead of the page functions, where they exist. Convert all filesystems which use block_read_full_page(). Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/buffer_head.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 805c4e12700a..31d82fd9abe8 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -223,7 +223,7 @@ int block_write_full_page(struct page *page, get_block_t *get_block, int __block_write_full_page(struct inode *inode, struct page *page, get_block_t *get_block, struct writeback_control *wbc, bh_end_io_t *handler); -int block_read_full_page(struct page*, get_block_t*); +int block_read_full_folio(struct folio *, get_block_t *); bool block_is_partially_uptodate(struct folio *, size_t from, size_t count); int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, struct page **pagep, get_block_t *get_block); -- cgit v1.2.3 From f132ab7d3ab03c5bae28d31fb80ba77c4da05500 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Apr 2022 11:47:39 -0400 Subject: fs: Convert mpage_readpage to mpage_read_folio mpage_readpage still works in terms of pages, and has not been audited for correctness with large folios, so include an assertion that the filesystem is not passing it large folios. Convert all the filesystems to call mpage_read_folio() instead of mpage_readpage(). Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/mpage.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mpage.h b/include/linux/mpage.h index f4f5e90a6844..43986f7ec4dd 100644 --- a/include/linux/mpage.h +++ b/include/linux/mpage.h @@ -16,7 +16,7 @@ struct writeback_control; struct readahead_control; void mpage_readahead(struct readahead_control *, get_block_t get_block); -int mpage_readpage(struct page *page, get_block_t get_block); +int mpage_read_folio(struct folio *folio, get_block_t get_block); int mpage_writepages(struct address_space *mapping, struct writeback_control *wbc, get_block_t get_block); int mpage_writepage(struct page *page, get_block_t *get_block, -- cgit v1.2.3 From 65d023af7f29eb1250a6105141a74776bae7e1f8 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Apr 2022 11:12:16 -0400 Subject: nfs: Convert nfs to read_folio This is a "weak" conversion which converts straight back to using pages. A full conversion should be performed at some point, hopefully by someone familiar with the filesystem. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/nfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index b48b9259e02c..1bba71757d62 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -594,7 +594,7 @@ static inline bool nfs_have_writebacks(const struct inode *inode) /* * linux/fs/nfs/read.c */ -extern int nfs_readpage(struct file *, struct page *); +int nfs_read_folio(struct file *, struct folio *); void nfs_readahead(struct readahead_control *); /* -- cgit v1.2.3 From 7e0a126519b82648b254afcd95a168c15f65ea40 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Apr 2022 11:53:28 -0400 Subject: mm,fs: Remove aops->readpage With all implementations of aops->readpage converted to aops->read_folio, we can stop checking whether it's set and remove the member from aops. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/fs.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 5ad942183a2c..f812f5aa07dd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -262,7 +262,7 @@ struct iattr { * trying again. The aop will be taking reasonable * precautions not to livelock. If the caller held a page * reference, it should drop it before retrying. Returned - * by readpage(). + * by read_folio(). * * address_space_operation functions return these large constants to indicate * special semantics to the caller. These are much larger than the bytes in a @@ -335,7 +335,6 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb) struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); - int (*readpage)(struct file *, struct page *); int (*read_folio)(struct file *, struct folio *); /* Write back some dirty pages from this mapping. */ -- cgit v1.2.3 From e9b5b23e957ef9260fec811d8d8081125889308a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 1 May 2022 21:39:29 -0400 Subject: fs: Change the type of filler_t By making filler_t the same as read_folio, we can use the same function for both in gfs2. We can push the use of folios down one more level in jffs2 and nfs. We also increase type safety for future users of the various read_cache_page() family of functions by forcing the parameter to be a pointer to struct file (or NULL). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Andreas Gruenbacher --- include/linux/pagemap.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index b70192f56454..831b28dab01a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -492,7 +492,7 @@ static inline gfp_t readahead_gfp_mask(struct address_space *x) return mapping_gfp_mask(x) | __GFP_NORETRY | __GFP_NOWARN; } -typedef int filler_t(void *, struct page *); +typedef int filler_t(struct file *, struct folio *); pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); @@ -747,9 +747,9 @@ static inline struct page *grab_cache_page(struct address_space *mapping, } struct folio *read_cache_folio(struct address_space *, pgoff_t index, - filler_t *filler, void *data); + filler_t *filler, struct file *file); struct page *read_cache_page(struct address_space *, pgoff_t index, - filler_t *filler, void *data); + filler_t *filler, struct file *file); extern struct page * read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); -- cgit v1.2.3 From 218d921b581eadf312c8ef0e09113b111f104eeb Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Sat, 30 Apr 2022 22:08:54 -0700 Subject: fscrypt: add new helper functions for test_dummy_encryption Unfortunately the design of fscrypt_set_test_dummy_encryption() doesn't work properly for the new mount API, as it combines too many steps into one function: - Parse the argument to test_dummy_encryption - Check the setting against the filesystem instance - Apply the setting to the filesystem instance The new mount API has split these into separate steps. ext4 partially worked around this by duplicating some of the logic, but it still had some bugs. To address this, add some new helper functions that split up the steps of fscrypt_set_test_dummy_encryption(): - fscrypt_parse_test_dummy_encryption() - fscrypt_dummy_policies_equal() - fscrypt_add_test_dummy_key() While we're add it, also add a function fscrypt_is_dummy_policy_set() which will be useful to avoid some #ifdef's. Signed-off-by: Eric Biggers Link: https://lore.kernel.org/r/20220501050857.538984-5-ebiggers@kernel.org --- include/linux/fscrypt.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'include') diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index efc7f96e5e26..e60d57c99cb6 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -32,6 +32,7 @@ union fscrypt_policy; struct fscrypt_info; +struct fs_parameter; struct seq_file; struct fscrypt_str { @@ -289,10 +290,19 @@ struct fscrypt_dummy_policy { const union fscrypt_policy *policy; }; +int fscrypt_parse_test_dummy_encryption(const struct fs_parameter *param, + struct fscrypt_dummy_policy *dummy_policy); +bool fscrypt_dummy_policies_equal(const struct fscrypt_dummy_policy *p1, + const struct fscrypt_dummy_policy *p2); int fscrypt_set_test_dummy_encryption(struct super_block *sb, const char *arg, struct fscrypt_dummy_policy *dummy_policy); void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep, struct super_block *sb); +static inline bool +fscrypt_is_dummy_policy_set(const struct fscrypt_dummy_policy *dummy_policy) +{ + return dummy_policy->policy != NULL; +} static inline void fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) { @@ -303,6 +313,8 @@ fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) /* keyring.c */ void fscrypt_sb_free(struct super_block *sb); int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); +int fscrypt_add_test_dummy_key(struct super_block *sb, + const struct fscrypt_dummy_policy *dummy_policy); int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg); int fscrypt_ioctl_remove_key_all_users(struct file *filp, void __user *arg); int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg); @@ -477,12 +489,32 @@ static inline int fscrypt_set_context(struct inode *inode, void *fs_data) struct fscrypt_dummy_policy { }; +static inline int +fscrypt_parse_test_dummy_encryption(const struct fs_parameter *param, + struct fscrypt_dummy_policy *dummy_policy) +{ + return -EINVAL; +} + +static inline bool +fscrypt_dummy_policies_equal(const struct fscrypt_dummy_policy *p1, + const struct fscrypt_dummy_policy *p2) +{ + return true; +} + static inline void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep, struct super_block *sb) { } +static inline bool +fscrypt_is_dummy_policy_set(const struct fscrypt_dummy_policy *dummy_policy) +{ + return false; +} + static inline void fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy) { @@ -498,6 +530,13 @@ static inline int fscrypt_ioctl_add_key(struct file *filp, void __user *arg) return -EOPNOTSUPP; } +static inline int +fscrypt_add_test_dummy_key(struct super_block *sb, + const struct fscrypt_dummy_policy *dummy_policy) +{ + return 0; +} + static inline int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg) { return -EOPNOTSUPP; -- cgit v1.2.3 From 623a1ddfeb232526275ddd0c8378771e6712aad4 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:42 -0700 Subject: mm/hugetlb: take src_mm->write_protect_seq in copy_hugetlb_page_range() Let's do it just like copy_page_range(), taking the seqlock and making sure the mmap_lock is held in write mode. This allows for add a VM_BUG_ON to page_needs_cow_for_dma() and properly synchronizes concurrent fork() with GUP-fast of hugetlb pages, which will be relevant for further changes. Link: https://lkml.kernel.org/r/20220428083441.37290-3-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/mm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index b9316b2c11ce..a02812178562 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1576,6 +1576,8 @@ static inline bool page_maybe_dma_pinned(struct page *page) /* * This should most likely only be called during fork() to see whether we * should break the cow immediately for a page on the src mm. + * + * The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq. */ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, struct page *page) @@ -1583,6 +1585,8 @@ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, if (!is_cow_mapping(vma->vm_flags)) return false; + VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1)); + if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) return false; -- cgit v1.2.3 From fb3d824d1a46c5bb0584ea88f32dc2495544aebf Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:43 -0700 Subject: mm/rmap: split page_dup_rmap() into page_dup_file_rmap() and page_try_dup_anon_rmap() ... and move the special check for pinned pages into page_try_dup_anon_rmap() to prepare for tracking exclusive anonymous pages via a new pageflag, clearing it only after making sure that there are no GUP pins on the anonymous page. We really only care about pins on anonymous pages, because they are prone to getting replaced in the COW handler once mapped R/O. For !anon pages in cow-mappings (!VM_SHARED && VM_MAYWRITE) we shouldn't really care about that, at least not that I could come up with an example. Let's drop the is_cow_mapping() check from page_needs_cow_for_dma(), as we know we're dealing with anonymous pages. Also, drop the handling of pinned pages from copy_huge_pud() and add a comment if ever supporting anonymous pages on the PUD level. This is a preparation for tracking exclusivity of anonymous pages in the rmap code, and disallowing marking a page shared (-> failing to duplicate) if there are GUP pins on a page. Link: https://lkml.kernel.org/r/20220428083441.37290-5-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/mm.h | 5 +---- include/linux/rmap.h | 49 ++++++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 49 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index a02812178562..9ee3ae51e8e3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1575,16 +1575,13 @@ static inline bool page_maybe_dma_pinned(struct page *page) /* * This should most likely only be called during fork() to see whether we - * should break the cow immediately for a page on the src mm. + * should break the cow immediately for an anon page on the src mm. * * The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq. */ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, struct page *page) { - if (!is_cow_mapping(vma->vm_flags)) - return false; - VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1)); if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 8573aae50d96..73f41544084f 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -12,6 +12,7 @@ #include #include #include +#include /* * The anon_vma heads a list of private "related" vmas, to scan if @@ -182,11 +183,57 @@ void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address); -static inline void page_dup_rmap(struct page *page, bool compound) +static inline void __page_dup_rmap(struct page *page, bool compound) { atomic_inc(compound ? compound_mapcount_ptr(page) : &page->_mapcount); } +static inline void page_dup_file_rmap(struct page *page, bool compound) +{ + __page_dup_rmap(page, compound); +} + +/** + * page_try_dup_anon_rmap - try duplicating a mapping of an already mapped + * anonymous page + * @page: the page to duplicate the mapping for + * @compound: the page is mapped as compound or as a small page + * @vma: the source vma + * + * The caller needs to hold the PT lock and the vma->vma_mm->write_protect_seq. + * + * Duplicating the mapping can only fail if the page may be pinned; device + * private pages cannot get pinned and consequently this function cannot fail. + * + * If duplicating the mapping succeeds, the page has to be mapped R/O into + * the parent and the child. It must *not* get mapped writable after this call. + * + * Returns 0 if duplicating the mapping succeeded. Returns -EBUSY otherwise. + */ +static inline int page_try_dup_anon_rmap(struct page *page, bool compound, + struct vm_area_struct *vma) +{ + VM_BUG_ON_PAGE(!PageAnon(page), page); + + /* + * If this page may have been pinned by the parent process, + * don't allow to duplicate the mapping but instead require to e.g., + * copy the page immediately for the child so that we'll always + * guarantee the pinned page won't be randomly replaced in the + * future on write faults. + */ + if (likely(!is_device_private_page(page) && + unlikely(page_needs_cow_for_dma(vma, page)))) + return -EBUSY; + + /* + * It's okay to share the anon page between both processes, mapping + * the page R/O into both processes. + */ + __page_dup_rmap(page, compound); + return 0; +} + /* * Called from mm/vmscan.c to handle paging out */ -- cgit v1.2.3 From 14f9135d547060d1d0c182501201f8da19895fe3 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:43 -0700 Subject: mm/rmap: convert RMAP flags to a proper distinct rmap_t type We want to pass the flags to more than one anon rmap function, getting rid of special "do_page_add_anon_rmap()". So let's pass around a distinct __bitwise type and refine documentation. Link: https://lkml.kernel.org/r/20220428083441.37290-6-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/rmap.h | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 73f41544084f..c53a38151089 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -160,9 +160,23 @@ static inline void anon_vma_merge(struct vm_area_struct *vma, struct anon_vma *page_get_anon_vma(struct page *page); -/* bitflags for do_page_add_anon_rmap() */ -#define RMAP_EXCLUSIVE 0x01 -#define RMAP_COMPOUND 0x02 +/* RMAP flags, currently only relevant for some anon rmap operations. */ +typedef int __bitwise rmap_t; + +/* + * No special request: if the page is a subpage of a compound page, it is + * mapped via a PTE. The mapped (sub)page is possibly shared between processes. + */ +#define RMAP_NONE ((__force rmap_t)0) + +/* The (sub)page is exclusive to a single process. */ +#define RMAP_EXCLUSIVE ((__force rmap_t)BIT(0)) + +/* + * The compound page is not mapped via PTEs, but instead via a single PMD and + * should be accounted accordingly. + */ +#define RMAP_COMPOUND ((__force rmap_t)BIT(1)) /* * rmap interfaces called when adding or removing pte of page @@ -171,7 +185,7 @@ void page_move_anon_rmap(struct page *, struct vm_area_struct *); void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address, bool compound); void do_page_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long address, int flags); + unsigned long address, rmap_t flags); void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address, bool compound); void page_add_file_rmap(struct page *, struct vm_area_struct *, -- cgit v1.2.3 From f1e2db12e45baaa2d366f87c885968096c2ff5aa Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:43 -0700 Subject: mm/rmap: remove do_page_add_anon_rmap() ... and instead convert page_add_anon_rmap() to accept flags. Passing flags instead of bools is usually nicer either way, and we want to more often also pass RMAP_EXCLUSIVE in follow up patches when detecting that an anonymous page is exclusive: for example, when restoring an anonymous page from a writable migration entry. This is a preparation for marking an anonymous page inside page_add_anon_rmap() as exclusive when RMAP_EXCLUSIVE is passed. Link: https://lkml.kernel.org/r/20220428083441.37290-7-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/rmap.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index c53a38151089..643801a937f3 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -183,8 +183,6 @@ typedef int __bitwise rmap_t; */ void page_move_anon_rmap(struct page *, struct vm_area_struct *); void page_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long address, bool compound); -void do_page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address, rmap_t flags); void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address, bool compound); -- cgit v1.2.3 From 28c5209dfd5f86f4398ce01bfac8508b2c4d4050 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:43 -0700 Subject: mm/rmap: pass rmap flags to hugepage_add_anon_rmap() Let's prepare for passing RMAP_EXCLUSIVE, similarly as we do for page_add_anon_rmap() now. RMAP_COMPOUND is implicit for hugetlb pages and ignored. Link: https://lkml.kernel.org/r/20220428083441.37290-8-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/rmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 643801a937f3..90e1e6925789 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -191,7 +191,7 @@ void page_add_file_rmap(struct page *, struct vm_area_struct *, void page_remove_rmap(struct page *, struct vm_area_struct *, bool compound); void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long address); + unsigned long address, rmap_t flags); void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address); -- cgit v1.2.3 From 40f2bbf71161fa9195c7869004290003af152375 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:43 -0700 Subject: mm/rmap: drop "compound" parameter from page_add_new_anon_rmap() New anonymous pages are always mapped natively: only THP/khugepaged code maps a new compound anonymous page and passes "true". Otherwise, we're just dealing with simple, non-compound pages. Let's give the interface clearer semantics and document these. Remove the PageTransCompound() sanity check from page_add_new_anon_rmap(). Link: https://lkml.kernel.org/r/20220428083441.37290-9-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/rmap.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 90e1e6925789..e4156921eea9 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -185,11 +185,12 @@ void page_move_anon_rmap(struct page *, struct vm_area_struct *); void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address, rmap_t flags); void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long address, bool compound); + unsigned long address); void page_add_file_rmap(struct page *, struct vm_area_struct *, bool compound); void page_remove_rmap(struct page *, struct vm_area_struct *, bool compound); + void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address, rmap_t flags); void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, -- cgit v1.2.3 From 78fbe906cc900b33ce078102e13e0e99b5b8c406 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:44 -0700 Subject: mm/page-flags: reuse PG_mappedtodisk as PG_anon_exclusive for PageAnon() pages The basic question we would like to have a reliable and efficient answer to is: is this anonymous page exclusive to a single process or might it be shared? We need that information for ordinary/single pages, hugetlb pages, and possibly each subpage of a THP. Introduce a way to mark an anonymous page as exclusive, with the ultimate goal of teaching our COW logic to not do "wrong COWs", whereby GUP pins lose consistency with the pages mapped into the page table, resulting in reported memory corruptions. Most pageflags already have semantics for anonymous pages, however, PG_mappedtodisk should never apply to pages in the swapcache, so let's reuse that flag. As PG_has_hwpoisoned also uses that flag on the second tail page of a compound page, convert it to PG_error instead, which is marked as PF_NO_TAIL, so never used for tail pages. Use custom page flag modification functions such that we can do additional sanity checks. The semantics we'll put into some kernel doc in the future are: " PG_anon_exclusive is *usually* only expressive in combination with a page table entry. Depending on the page table entry type it might store the following information: Is what's mapped via this page table entry exclusive to the single process and can be mapped writable without further checks? If not, it might be shared and we might have to COW. For now, we only expect PTE-mapped THPs to make use of PG_anon_exclusive in subpages. For other anonymous compound folios (i.e., hugetlb), only the head page is logically mapped and holds this information. For example, an exclusive, PMD-mapped THP only has PG_anon_exclusive set on the head page. When replacing the PMD by a page table full of PTEs, PG_anon_exclusive, if set on the head page, will be set on all tail pages accordingly. Note that converting from a PTE-mapping to a PMD mapping using the same compound page is currently not possible and consequently doesn't require care. If GUP wants to take a reliable pin (FOLL_PIN) on an anonymous page, it should only pin if the relevant PG_anon_exclusive is set. In that case, the pin will be fully reliable and stay consistent with the pages mapped into the page table, as the bit cannot get cleared (e.g., by fork(), KSM) while the page is pinned. For anonymous pages that are mapped R/W, PG_anon_exclusive can be assumed to always be set because such pages cannot possibly be shared. The page table lock protecting the page table entry is the primary synchronization mechanism for PG_anon_exclusive; GUP-fast that does not take the PT lock needs special care when trying to clear the flag. Page table entry types and PG_anon_exclusive: * Present: PG_anon_exclusive applies. * Swap: the information is lost. PG_anon_exclusive was cleared. * Migration: the entry holds this information instead. PG_anon_exclusive was cleared. * Device private: PG_anon_exclusive applies. * Device exclusive: PG_anon_exclusive applies. * HW Poison: PG_anon_exclusive is stale and not changed. If the page may be pinned (FOLL_PIN), clearing PG_anon_exclusive is not allowed and the flag will stick around until the page is freed and folio->mapping is cleared. " We won't be clearing PG_anon_exclusive on destructive unmapping (i.e., zapping) of page table entries, page freeing code will handle that when also invalidate page->mapping to not indicate PageAnon() anymore. Letting information about exclusivity stick around will be an important property when adding sanity checks to unpinning code. Note that we properly clear the flag in free_pages_prepare() via PAGE_FLAGS_CHECK_AT_PREP for each individual subpage of a compound page, so there is no need to manually clear the flag. Link: https://lkml.kernel.org/r/20220428083441.37290-12-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 39 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 38 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 1ea896887ee4..b70124b9c7c1 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -142,6 +142,15 @@ enum pageflags { PG_readahead = PG_reclaim, + /* + * Depending on the way an anonymous folio can be mapped into a page + * table (e.g., single PMD/PUD/CONT of the head page vs. PTE-mapped + * THP), PG_anon_exclusive may be set only for the head page or for + * tail pages of an anonymous folio. For now, we only expect it to be + * set on tail pages for PTE-mapped THP. + */ + PG_anon_exclusive = PG_mappedtodisk, + /* Filesystems */ PG_checked = PG_owner_priv_1, @@ -176,7 +185,7 @@ enum pageflags { * Indicates that at least one subpage is hwpoisoned in the * THP. */ - PG_has_hwpoisoned = PG_mappedtodisk, + PG_has_hwpoisoned = PG_error, #endif /* non-lru isolated movable page */ @@ -1002,6 +1011,34 @@ extern bool is_free_buddy_page(struct page *page); PAGEFLAG(Isolated, isolated, PF_ANY); +static __always_inline int PageAnonExclusive(struct page *page) +{ + VM_BUG_ON_PGFLAGS(!PageAnon(page), page); + VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); + return test_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); +} + +static __always_inline void SetPageAnonExclusive(struct page *page) +{ + VM_BUG_ON_PGFLAGS(!PageAnon(page) || PageKsm(page), page); + VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); + set_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); +} + +static __always_inline void ClearPageAnonExclusive(struct page *page) +{ + VM_BUG_ON_PGFLAGS(!PageAnon(page) || PageKsm(page), page); + VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); + clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); +} + +static __always_inline void __ClearPageAnonExclusive(struct page *page) +{ + VM_BUG_ON_PGFLAGS(!PageAnon(page), page); + VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); + __clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); +} + #ifdef CONFIG_MMU #define __PG_MLOCKED (1UL << PG_mlocked) #else -- cgit v1.2.3 From 6c287605fd56466e645693eff3ae7c08fba56e0a Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:44 -0700 Subject: mm: remember exclusively mapped anonymous pages with PG_anon_exclusive Let's mark exclusively mapped anonymous pages with PG_anon_exclusive as exclusive, and use that information to make GUP pins reliable and stay consistent with the page mapped into the page table even if the page table entry gets write-protected. With that information at hand, we can extend our COW logic to always reuse anonymous pages that are exclusive. For anonymous pages that might be shared, the existing logic applies. As already documented, PG_anon_exclusive is usually only expressive in combination with a page table entry. Especially PTE vs. PMD-mapped anonymous pages require more thought, some examples: due to mremap() we can easily have a single compound page PTE-mapped into multiple page tables exclusively in a single process -- multiple page table locks apply. Further, due to MADV_WIPEONFORK we might not necessarily write-protect all PTEs, and only some subpages might be pinned. Long story short: once PTE-mapped, we have to track information about exclusivity per sub-page, but until then, we can just track it for the compound page in the head page and not having to update a whole bunch of subpages all of the time for a simple PMD mapping of a THP. For simplicity, this commit mostly talks about "anonymous pages", while it's for THP actually "the part of an anonymous folio referenced via a page table entry". To not spill PG_anon_exclusive code all over the mm code-base, we let the anon rmap code to handle all PG_anon_exclusive logic it can easily handle. If a writable, present page table entry points at an anonymous (sub)page, that (sub)page must be PG_anon_exclusive. If GUP wants to take a reliably pin (FOLL_PIN) on an anonymous page references via a present page table entry, it must only pin if PG_anon_exclusive is set for the mapped (sub)page. This commit doesn't adjust GUP, so this is only implicitly handled for FOLL_WRITE, follow-up commits will teach GUP to also respect it for FOLL_PIN without FOLL_WRITE, to make all GUP pins of anonymous pages fully reliable. Whenever an anonymous page is to be shared (fork(), KSM), or when temporarily unmapping an anonymous page (swap, migration), the relevant PG_anon_exclusive bit has to be cleared to mark the anonymous page possibly shared. Clearing will fail if there are GUP pins on the page: * For fork(), this means having to copy the page and not being able to share it. fork() protects against concurrent GUP using the PT lock and the src_mm->write_protect_seq. * For KSM, this means sharing will fail. For swap this means, unmapping will fail, For migration this means, migration will fail early. All three cases protect against concurrent GUP using the PT lock and a proper clear/invalidate+flush of the relevant page table entry. This fixes memory corruptions reported for FOLL_PIN | FOLL_WRITE, when a pinned page gets mapped R/O and the successive write fault ends up replacing the page instead of reusing it. It improves the situation for O_DIRECT/vmsplice/... that still use FOLL_GET instead of FOLL_PIN, if fork() is *not* involved, however swapout and fork() are still problematic. Properly using FOLL_PIN instead of FOLL_GET for these GUP users will fix the issue for them. I. Details about basic handling I.1. Fresh anonymous pages page_add_new_anon_rmap() and hugepage_add_new_anon_rmap() will mark the given page exclusive via __page_set_anon_rmap(exclusive=1). As that is the mechanism fresh anonymous pages come into life (besides migration code where we copy the page->mapping), all fresh anonymous pages will start out as exclusive. I.2. COW reuse handling of anonymous pages When a COW handler stumbles over a (sub)page that's marked exclusive, it simply reuses it. Otherwise, the handler tries harder under page lock to detect if the (sub)page is exclusive and can be reused. If exclusive, page_move_anon_rmap() will mark the given (sub)page exclusive. Note that hugetlb code does not yet check for PageAnonExclusive(), as it still uses the old COW logic that is prone to the COW security issue because hugetlb code cannot really tolerate unnecessary/wrong COW as huge pages are a scarce resource. I.3. Migration handling try_to_migrate() has to try marking an exclusive anonymous page shared via page_try_share_anon_rmap(). If it fails because there are GUP pins on the page, unmap fails. migrate_vma_collect_pmd() and __split_huge_pmd_locked() are handled similarly. Writable migration entries implicitly point at shared anonymous pages. For readable migration entries that information is stored via a new "readable-exclusive" migration entry, specific to anonymous pages. When restoring a migration entry in remove_migration_pte(), information about exlusivity is detected via the migration entry type, and RMAP_EXCLUSIVE is set accordingly for page_add_anon_rmap()/hugepage_add_anon_rmap() to restore that information. I.4. Swapout handling try_to_unmap() has to try marking the mapped page possibly shared via page_try_share_anon_rmap(). If it fails because there are GUP pins on the page, unmap fails. For now, information about exclusivity is lost. In the future, we might want to remember that information in the swap entry in some cases, however, it requires more thought, care, and a way to store that information in swap entries. I.5. Swapin handling do_swap_page() will never stumble over exclusive anonymous pages in the swap cache, as try_to_migrate() prohibits that. do_swap_page() always has to detect manually if an anonymous page is exclusive and has to set RMAP_EXCLUSIVE for page_add_anon_rmap() accordingly. I.6. THP handling __split_huge_pmd_locked() has to move the information about exclusivity from the PMD to the PTEs. a) In case we have a readable-exclusive PMD migration entry, simply insert readable-exclusive PTE migration entries. b) In case we have a present PMD entry and we don't want to freeze ("convert to migration entries"), simply forward PG_anon_exclusive to all sub-pages, no need to temporarily clear the bit. c) In case we have a present PMD entry and want to freeze, handle it similar to try_to_migrate(): try marking the page shared first. In case we fail, we ignore the "freeze" instruction and simply split ordinarily. try_to_migrate() will properly fail because the THP is still mapped via PTEs. When splitting a compound anonymous folio (THP), the information about exclusivity is implicitly handled via the migration entries: no need to replicate PG_anon_exclusive manually. I.7. fork() handling fork() handling is relatively easy, because PG_anon_exclusive is only expressive for some page table entry types. a) Present anonymous pages page_try_dup_anon_rmap() will mark the given subpage shared -- which will fail if the page is pinned. If it failed, we have to copy (or PTE-map a PMD to handle it on the PTE level). Note that device exclusive entries are just a pointer at a PageAnon() page. fork() will first convert a device exclusive entry to a present page table and handle it just like present anonymous pages. b) Device private entry Device private entries point at PageAnon() pages that cannot be mapped directly and, therefore, cannot get pinned. page_try_dup_anon_rmap() will mark the given subpage shared, which cannot fail because they cannot get pinned. c) HW poison entries PG_anon_exclusive will remain untouched and is stale -- the page table entry is just a placeholder after all. d) Migration entries Writable and readable-exclusive entries are converted to readable entries: possibly shared. I.8. mprotect() handling mprotect() only has to properly handle the new readable-exclusive migration entry: When write-protecting a migration entry that points at an anonymous page, remember the information about exclusivity via the "readable-exclusive" migration entry type. II. Migration and GUP-fast Whenever replacing a present page table entry that maps an exclusive anonymous page by a migration entry, we have to mark the page possibly shared and synchronize against GUP-fast by a proper clear/invalidate+flush to make the following scenario impossible: 1. try_to_migrate() places a migration entry after checking for GUP pins and marks the page possibly shared. 2. GUP-fast pins the page due to lack of synchronization 3. fork() converts the "writable/readable-exclusive" migration entry into a readable migration entry 4. Migration fails due to the GUP pin (failing to freeze the refcount) 5. Migration entries are restored. PG_anon_exclusive is lost -> We have a pinned page that is not marked exclusive anymore. Note that we move information about exclusivity from the page to the migration entry as it otherwise highly overcomplicates fork() and PTE-mapping a THP. III. Swapout and GUP-fast Whenever replacing a present page table entry that maps an exclusive anonymous page by a swap entry, we have to mark the page possibly shared and synchronize against GUP-fast by a proper clear/invalidate+flush to make the following scenario impossible: 1. try_to_unmap() places a swap entry after checking for GUP pins and clears exclusivity information on the page. 2. GUP-fast pins the page due to lack of synchronization. -> We have a pinned page that is not marked exclusive anymore. If we'd ever store information about exclusivity in the swap entry, similar to migration handling, the same considerations as in II would apply. This is future work. Link: https://lkml.kernel.org/r/20220428083441.37290-13-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/rmap.h | 40 ++++++++++++++++++++++++++++++++++++++++ include/linux/swap.h | 15 +++++++++++---- include/linux/swapops.h | 25 +++++++++++++++++++++++++ 3 files changed, 76 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index e4156921eea9..cbe279a6f0de 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -228,6 +228,13 @@ static inline int page_try_dup_anon_rmap(struct page *page, bool compound, { VM_BUG_ON_PAGE(!PageAnon(page), page); + /* + * No need to check+clear for already shared pages, including KSM + * pages. + */ + if (!PageAnonExclusive(page)) + goto dup; + /* * If this page may have been pinned by the parent process, * don't allow to duplicate the mapping but instead require to e.g., @@ -239,14 +246,47 @@ static inline int page_try_dup_anon_rmap(struct page *page, bool compound, unlikely(page_needs_cow_for_dma(vma, page)))) return -EBUSY; + ClearPageAnonExclusive(page); /* * It's okay to share the anon page between both processes, mapping * the page R/O into both processes. */ +dup: __page_dup_rmap(page, compound); return 0; } +/** + * page_try_share_anon_rmap - try marking an exclusive anonymous page possibly + * shared to prepare for KSM or temporary unmapping + * @page: the exclusive anonymous page to try marking possibly shared + * + * The caller needs to hold the PT lock and has to have the page table entry + * cleared/invalidated+flushed, to properly sync against GUP-fast. + * + * This is similar to page_try_dup_anon_rmap(), however, not used during fork() + * to duplicate a mapping, but instead to prepare for KSM or temporarily + * unmapping a page (swap, migration) via page_remove_rmap(). + * + * Marking the page shared can only fail if the page may be pinned; device + * private pages cannot get pinned and consequently this function cannot fail. + * + * Returns 0 if marking the page possibly shared succeeded. Returns -EBUSY + * otherwise. + */ +static inline int page_try_share_anon_rmap(struct page *page) +{ + VM_BUG_ON_PAGE(!PageAnon(page) || !PageAnonExclusive(page), page); + + /* See page_try_dup_anon_rmap(). */ + if (likely(!is_device_private_page(page) && + unlikely(page_maybe_dma_pinned(page)))) + return -EBUSY; + + ClearPageAnonExclusive(page); + return 0; +} + /* * Called from mm/vmscan.c to handle paging out */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 27093b477c5f..e6d70a4156e8 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -78,12 +78,19 @@ static inline int current_is_kswapd(void) #endif /* - * NUMA node memory migration support + * Page migration support. + * + * SWP_MIGRATION_READ_EXCLUSIVE is only applicable to anonymous pages and + * indicates that the referenced (part of) an anonymous page is exclusive to + * a single process. For SWP_MIGRATION_WRITE, that information is implicit: + * (part of) an anonymous page that are mapped writable are exclusive to a + * single process. */ #ifdef CONFIG_MIGRATION -#define SWP_MIGRATION_NUM 2 -#define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) -#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) +#define SWP_MIGRATION_NUM 3 +#define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) +#define SWP_MIGRATION_READ_EXCLUSIVE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) +#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 2) #else #define SWP_MIGRATION_NUM 0 #endif diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 5af852b68805..6648b97244e7 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -194,6 +194,7 @@ static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) static inline int is_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ || + swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE || swp_type(entry) == SWP_MIGRATION_WRITE); } @@ -202,11 +203,26 @@ static inline int is_writable_migration_entry(swp_entry_t entry) return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE); } +static inline int is_readable_migration_entry(swp_entry_t entry) +{ + return unlikely(swp_type(entry) == SWP_MIGRATION_READ); +} + +static inline int is_readable_exclusive_migration_entry(swp_entry_t entry) +{ + return unlikely(swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE); +} + static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_READ, offset); } +static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset) +{ + return swp_entry(SWP_MIGRATION_READ_EXCLUSIVE, offset); +} + static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_WRITE, offset); @@ -224,6 +240,11 @@ static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) return swp_entry(0, 0); } +static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset) +{ + return swp_entry(0, 0); +} + static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { return swp_entry(0, 0); @@ -244,6 +265,10 @@ static inline int is_writable_migration_entry(swp_entry_t entry) { return 0; } +static inline int is_readable_migration_entry(swp_entry_t entry) +{ + return 0; +} #endif -- cgit v1.2.3 From 7f5abe609b3dcbc62a36e18b1437f4f3521ecb75 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:44 -0700 Subject: mm/rmap: fail try_to_migrate() early when setting a PMD migration entry fails Let's fail right away in case we cannot clear PG_anon_exclusive because the anon THP may be pinned. Right now, we continue trying to install migration entries and the caller of try_to_migrate() will realize that the page is still mapped and has to restore the migration entries. Let's just fail fast just like for PTE migration entries. Link: https://lkml.kernel.org/r/20220428083441.37290-14-david@redhat.com Signed-off-by: David Hildenbrand Suggested-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/swapops.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 6648b97244e7..e476a8fed537 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -299,7 +299,7 @@ static inline bool is_pfn_swap_entry(swp_entry_t entry) struct page_vma_mapped_walk; #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION -extern void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, +extern int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page); extern void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, @@ -332,7 +332,7 @@ static inline int is_pmd_migration_entry(pmd_t pmd) return !pmd_present(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); } #else -static inline void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, +static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page) { BUILD_BUG(); -- cgit v1.2.3 From c89357e27f20dda3fff6791d27bb6c91eae99f4a Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:45 -0700 Subject: mm: support GUP-triggered unsharing of anonymous pages Whenever GUP currently ends up taking a R/O pin on an anonymous page that might be shared -- mapped R/O and !PageAnonExclusive() -- any write fault on the page table entry will end up replacing the mapped anonymous page due to COW, resulting in the GUP pin no longer being consistent with the page actually mapped into the page table. The possible ways to deal with this situation are: (1) Ignore and pin -- what we do right now. (2) Fail to pin -- which would be rather surprising to callers and could break user space. (3) Trigger unsharing and pin the now exclusive page -- reliable R/O pins. We want to implement 3) because it provides the clearest semantics and allows for checking in unpin_user_pages() and friends for possible BUGs: when trying to unpin a page that's no longer exclusive, clearly something went very wrong and might result in memory corruptions that might be hard to debug. So we better have a nice way to spot such issues. To implement 3), we need a way for GUP to trigger unsharing: FAULT_FLAG_UNSHARE. FAULT_FLAG_UNSHARE is only applicable to R/O mapped anonymous pages and resembles COW logic during a write fault. However, in contrast to a write fault, GUP-triggered unsharing will, for example, still maintain the write protection. Let's implement FAULT_FLAG_UNSHARE by hooking into the existing write fault handlers for all applicable anonymous page types: ordinary pages, THP and hugetlb. * If FAULT_FLAG_UNSHARE finds a R/O-mapped anonymous page that has been marked exclusive in the meantime by someone else, there is nothing to do. * If FAULT_FLAG_UNSHARE finds a R/O-mapped anonymous page that's not marked exclusive, it will try detecting if the process is the exclusive owner. If exclusive, it can be set exclusive similar to reuse logic during write faults via page_move_anon_rmap() and there is nothing else to do; otherwise, we either have to copy and map a fresh, anonymous exclusive page R/O (ordinary pages, hugetlb), or split the THP. This commit is heavily based on patches by Andrea. Link: https://lkml.kernel.org/r/20220428083441.37290-16-david@redhat.com Signed-off-by: Andrea Arcangeli Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Co-developed-by: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 87eddd509de2..7216d77a5884 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -819,6 +819,9 @@ typedef struct { * @FAULT_FLAG_REMOTE: The fault is not for current task/mm. * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch. * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals. + * @FAULT_FLAG_UNSHARE: The fault is an unsharing request to unshare (and mark + * exclusive) a possibly shared anonymous page that is + * mapped R/O. * * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify * whether we would allow page faults to retry by specifying these two @@ -838,6 +841,10 @@ typedef struct { * continuous faults with flags (b). We should always try to detect pending * signals before a retry to make sure the continuous page faults can still be * interrupted if necessary. + * + * The combination FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE is illegal. + * FAULT_FLAG_UNSHARE is ignored and treated like an ordinary read fault when + * no existing R/O-mapped anonymous page is encountered. */ enum fault_flag { FAULT_FLAG_WRITE = 1 << 0, @@ -850,6 +857,7 @@ enum fault_flag { FAULT_FLAG_REMOTE = 1 << 7, FAULT_FLAG_INSTRUCTION = 1 << 8, FAULT_FLAG_INTERRUPTIBLE = 1 << 9, + FAULT_FLAG_UNSHARE = 1 << 10, }; #endif /* _LINUX_MM_TYPES_H */ -- cgit v1.2.3 From a7f226604170acd6b142b76472c1a49c12ebb83d Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:45 -0700 Subject: mm/gup: trigger FAULT_FLAG_UNSHARE when R/O-pinning a possibly shared anonymous page Whenever GUP currently ends up taking a R/O pin on an anonymous page that might be shared -- mapped R/O and !PageAnonExclusive() -- any write fault on the page table entry will end up replacing the mapped anonymous page due to COW, resulting in the GUP pin no longer being consistent with the page actually mapped into the page table. The possible ways to deal with this situation are: (1) Ignore and pin -- what we do right now. (2) Fail to pin -- which would be rather surprising to callers and could break user space. (3) Trigger unsharing and pin the now exclusive page -- reliable R/O pins. Let's implement 3) because it provides the clearest semantics and allows for checking in unpin_user_pages() and friends for possible BUGs: when trying to unpin a page that's no longer exclusive, clearly something went very wrong and might result in memory corruptions that might be hard to debug. So we better have a nice way to spot such issues. This change implies that whenever user space *wrote* to a private mapping (IOW, we have an anonymous page mapped), that GUP pins will always remain consistent: reliable R/O GUP pins of anonymous pages. As a side note, this commit fixes the COW security issue for hugetlb with FOLL_PIN as documented in: https://lore.kernel.org/r/3ae33b08-d9ef-f846-56fb-645e3b9b4c66@redhat.com The vmsplice reproducer still applies, because vmsplice uses FOLL_GET instead of FOLL_PIN. Note that follow_huge_pmd() doesn't apply because we cannot end up in there with FOLL_PIN. This commit is heavily based on prototype patches by Andrea. Link: https://lkml.kernel.org/r/20220428083441.37290-17-david@redhat.com Signed-off-by: Andrea Arcangeli Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Co-developed-by: Andrea Arcangeli Cc: Christoph Hellwig Cc: David Rientjes Cc: Don Dutile Cc: Hugh Dickins Cc: Jan Kara Cc: Jann Horn Cc: Jason Gunthorpe Cc: John Hubbard Cc: Khalid Aziz Cc: "Kirill A. Shutemov" Cc: Liang Zhang Cc: "Matthew Wilcox (Oracle)" Cc: Michal Hocko Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Cc: Oded Gabbay Cc: Oleg Nesterov Cc: Pedro Demarchi Gomes Cc: Peter Xu Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/mm.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9ee3ae51e8e3..5dc5005ccc9b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3002,6 +3002,45 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) return 0; } +/* + * Indicates for which pages that are write-protected in the page table, + * whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the + * GUP pin will remain consistent with the pages mapped into the page tables + * of the MM. + * + * Temporary unmapping of PageAnonExclusive() pages or clearing of + * PageAnonExclusive() has to protect against concurrent GUP: + * * Ordinary GUP: Using the PT lock + * * GUP-fast and fork(): mm->write_protect_seq + * * GUP-fast and KSM or temporary unmapping (swap, migration): + * clear/invalidate+flush of the page table entry + * + * Must be called with the (sub)page that's actually referenced via the + * page table entry, which might not necessarily be the head page for a + * PTE-mapped THP. + */ +static inline bool gup_must_unshare(unsigned int flags, struct page *page) +{ + /* + * FOLL_WRITE is implicitly handled correctly as the page table entry + * has to be writable -- and if it references (part of) an anonymous + * folio, that part is required to be marked exclusive. + */ + if ((flags & (FOLL_WRITE | FOLL_PIN)) != FOLL_PIN) + return false; + /* + * Note: PageAnon(page) is stable until the page is actually getting + * freed. + */ + if (!PageAnon(page)) + return false; + /* + * Note that PageKsm() pages cannot be exclusive, and consequently, + * cannot get pinned. + */ + return !PageAnonExclusive(page); +} + typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data); extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); -- cgit v1.2.3 From 1493a1913e34b0ac366e33f9ebad721e69fd06ac Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 9 May 2022 18:20:45 -0700 Subject: mm/swap: remember PG_anon_exclusive via a swp pte bit Patch series "mm: COW fixes part 3: reliable GUP R/W FOLL_GET of anonymous pages", v2. This series fixes memory corruptions when a GUP R/W reference (FOLL_WRITE | FOLL_GET) was taken on an anonymous page and COW logic fails to detect exclusivity of the page to then replacing the anonymous page by a copy in the page table: The GUP reference lost synchronicity with the pages mapped into the page tables. This series focuses on x86, arm64, s390x and ppc64/book3s -- other architectures are fairly easy to support by implementing __HAVE_ARCH_PTE_SWP_EXCLUSIVE. This primarily fixes the O_DIRECT memory corruptions that can happen on concurrent swapout, whereby we lose DMA reads to a page (modifying the user page by writing to it). O_DIRECT currently uses FOLL_GET for short-term (!FOLL_LONGTERM) DMA from/to a user page. In the long run, we want to convert it to properly use FOLL_PIN, and John is working on it, but that might take a while and might not be easy to backport. In the meantime, let's restore what used to work before we started modifying our COW logic: make R/W FOLL_GET references reliable as long as there is no fork() after GUP involved. This is just the natural follow-up of part 2, that will also further reduce "wrong COW" on the swapin path, for example, when we cannot remove a page from the swapcache due to concurrent writeback, or if we have two threads faulting on the same swapped-out page. Fixing O_DIRECT is just a nice side-product This issue, including other related COW issues, has been summarized in [3] under 2): " 2. Intra Process Memory Corruptions due to Wrong COW (FOLL_GET) It was discovered that we can create a memory corruption by reading a file via O_DIRECT to a part (e.g., first 512 bytes) of a page, concurrently writing to an unrelated part (e.g., last byte) of the same page, and concurrently write-protecting the page via clear_refs SOFTDIRTY tracking [6]. For the reproducer, the issue is that O_DIRECT grabs a reference of the target page (via FOLL_GET) and clear_refs write-protects the relevant page table entry. On successive write access to the page from the process itself, we wrongly COW the page when resolving the write fault, resulting in a loss of synchronicity and consequently a memory corruption. While some people might think that using clear_refs in this combination is a corner cases, it turns out to be a more generic problem unfortunately. For example, it was just recently discovered that we can similarly create a memory corruption without clear_refs, simply by concurrently swapping out the buffer pages [7]. Note that we nowadays even use the swap infrastructure in Linux without an actual swap disk/partition: the prime example is zram which is enabled as default under Fedora [10]. The root issue is that a write-fault on a page that has additional references results in a COW and thereby a loss of synchronicity and consequently a memory corruption if two parties believe they are referencing the same page. " We don't particularly care about R/O FOLL_GET references: they were never reliable and O_DIRECT doesn't expect to observe modifications from a page after DMA was started. Note that: * this only fixes the issue on x86, arm64, s390x and ppc64/book3s ("enterprise architectures"). Other architectures have to implement __HAVE_ARCH_PTE_SWP_EXCLUSIVE to achieve the same. * this does *not * consider any kind of fork() after taking the reference: fork() after GUP never worked reliably with FOLL_GET. * Not losing PG_anon_exclusive during swapout was the last remaining piece. KSM already makes sure that there are no other references on a page before considering it for sharing. Page migration maintains PG_anon_exclusive and simply fails when there are additional references (freezing the refcount fails). Only swapout code dropped the PG_anon_exclusive flag because it requires more work to remember + restore it. With this series in place, most COW issues of [3] are fixed on said architectures. Other architectures can implement __HAVE_ARCH_PTE_SWP_EXCLUSIVE fairly easily. [1] https://lkml.kernel.org/r/20220329160440.193848-1-david@redhat.com [2] https://lkml.kernel.org/r/20211217113049.23850-1-david@redhat.com [3] https://lore.kernel.org/r/3ae33b08-d9ef-f846-56fb-645e3b9b4c66@redhat.com This patch (of 8): Currently, we clear PG_anon_exclusive in try_to_unmap() and forget about it. We do this, to keep fork() logic on swap entries easy and efficient: for example, if we wouldn't clear it when unmapping, we'd have to lookup the page in the swapcache for each and every swap entry during fork() and clear PG_anon_exclusive if set. Instead, we want to store that information directly in the swap pte, protected by the page table lock, similarly to how we handle SWP_MIGRATION_READ_EXCLUSIVE for migration entries. However, for actual swap entries, we don't want to mess with the swap type (e.g., still one bit) because it overcomplicates swap code. In try_to_unmap(), we already reject to unmap in case the page might be pinned, because we must not lose PG_anon_exclusive on pinned pages ever. Checking if there are other unexpected references reliably *before* completely unmapping a page is unfortunately not really possible: THP heavily overcomplicate the situation. Once fully unmapped it's easier -- we, for example, make sure that there are no unexpected references *after* unmapping a page before starting writeback on that page. So, we currently might end up unmapping a page and clearing PG_anon_exclusive if that page has additional references, for example, due to a FOLL_GET. do_swap_page() has to re-determine if a page is exclusive, which will easily fail if there are other references on a page, most prominently GUP references via FOLL_GET. This can currently result in memory corruptions when taking a FOLL_GET | FOLL_WRITE reference on a page even when fork() is never involved: try_to_unmap() will succeed, and when refaulting the page, it cannot be marked exclusive and will get replaced by a copy in the page tables on the next write access, resulting in writes via the GUP reference to the page being lost. In an ideal world, everybody that uses GUP and wants to modify page content, such as O_DIRECT, would properly use FOLL_PIN. However, that conversion will take a while. It's easier to fix what used to work in the past (FOLL_GET | FOLL_WRITE) remembering PG_anon_exclusive. In addition, by remembering PG_anon_exclusive we can further reduce unnecessary COW in some cases, so it's the natural thing to do. So let's transfer the PG_anon_exclusive information to the swap pte and store it via an architecture-dependant pte bit; use that information when restoring the swap pte in do_swap_page() and unuse_pte(). During fork(), we simply have to clear the pte bit and are done. Of course, there is one corner case to handle: swap backends that don't support concurrent page modifications while the page is under writeback. Special case these, and drop the exclusive marker. Add a comment why that is just fine (also, reuse_swap_page() would have done the same in the past). In the future, we'll hopefully have all architectures support __HAVE_ARCH_PTE_SWP_EXCLUSIVE, such that we can get rid of the empty stubs and the define completely. Then, we can also convert SWP_MIGRATION_READ_EXCLUSIVE. For architectures it's fairly easy to support: either simply use a yet unused pte bit that can be used for swap entries, steal one from the arch type bits if they exceed 5, or steal one from the offset bits. Note: R/O FOLL_GET references were never really reliable, especially when taking one on a shared page and then writing to the page (e.g., GUP after fork()). FOLL_GET, including R/W references, were never really reliable once fork was involved (e.g., GUP before fork(), GUP during fork()). KSM steps back in case it stumbles over unexpected references and is, therefore, fine. [david@redhat.com: fix SWP_STABLE_WRITES test] Link: https://lkml.kernel.org/r/ac725bcb-313a-4fff-250a-68ba9a8f85fb@redhat.comLink: https://lkml.kernel.org/r/20220329164329.208407-1-david@redhat.com Link: https://lkml.kernel.org/r/20220329164329.208407-2-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Hugh Dickins Cc: Shakeel Butt Cc: John Hubbard Cc: Jason Gunthorpe Cc: Mike Kravetz Cc: Mike Rapoport Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox (Oracle) Cc: Jann Horn Cc: Michal Hocko Cc: Nadav Amit Cc: Rik van Riel Cc: Roman Gushchin Cc: Andrea Arcangeli Cc: Peter Xu Cc: Don Dutile Cc: Christoph Hellwig Cc: Oleg Nesterov Cc: Jan Kara Cc: Liang Zhang Cc: Pedro Demarchi Gomes Cc: Oded Gabbay Cc: Catalin Marinas Cc: Will Deacon Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: Gerald Schaefer Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 29 +++++++++++++++++++++++++++++ include/linux/swapops.h | 2 ++ 2 files changed, 31 insertions(+) (limited to 'include') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index f4f4077b97aa..53750224e176 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1003,6 +1003,35 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) #define arch_start_context_switch(prev) do {} while (0) #endif +/* + * When replacing an anonymous page by a real (!non) swap entry, we clear + * PG_anon_exclusive from the page and instead remember whether the flag was + * set in the swp pte. During fork(), we have to mark the entry as !exclusive + * (possibly shared). On swapin, we use that information to restore + * PG_anon_exclusive, which is very helpful in cases where we might have + * additional (e.g., FOLL_GET) references on a page and wouldn't be able to + * detect exclusivity. + * + * These functions don't apply to non-swap entries (e.g., migration, hwpoison, + * ...). + */ +#ifndef __HAVE_ARCH_PTE_SWP_EXCLUSIVE +static inline pte_t pte_swp_mkexclusive(pte_t pte) +{ + return pte; +} + +static inline int pte_swp_exclusive(pte_t pte) +{ + return false; +} + +static inline pte_t pte_swp_clear_exclusive(pte_t pte) +{ + return pte; +} +#endif + #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY #ifndef CONFIG_ARCH_ENABLE_THP_MIGRATION static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) diff --git a/include/linux/swapops.h b/include/linux/swapops.h index e476a8fed537..d1b728904d4e 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -26,6 +26,8 @@ /* Clear all flags but only keep swp_entry_t related information */ static inline pte_t pte_swp_clear_flags(pte_t pte) { + if (pte_swp_exclusive(pte)) + pte = pte_swp_clear_exclusive(pte); if (pte_swp_soft_dirty(pte)) pte = pte_swp_clear_soft_dirty(pte); if (pte_swp_uffd_wp(pte)) -- cgit v1.2.3 From 014bb1de4fc17d54907d54418126a9a9736f4aff Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 9 May 2022 18:20:47 -0700 Subject: mm: create new mm/swap.h header file Patch series "MM changes to improve swap-over-NFS support". Assorted improvements for swap-via-filesystem. This is a resend of these patches, rebased on current HEAD. The only substantial changes is that swap_dirty_folio has replaced swap_set_page_dirty. Currently swap-via-fs (SWP_FS_OPS) doesn't work for any filesystem. It has previously worked for NFS but that broke a few releases back. This series changes to use a new ->swap_rw rather than ->readpage and ->direct_IO. It also makes other improvements. There is a companion series already in linux-next which fixes various issues with NFS. Once both series land, a final patch is needed which changes NFS over to use ->swap_rw. This patch (of 10): Many functions declared in include/linux/swap.h are only used within mm/ Create a new "mm/swap.h" and move some of these declarations there. Remove the redundant 'extern' from the function declarations. [akpm@linux-foundation.org: mm/memory-failure.c needs mm/swap.h] Link: https://lkml.kernel.org/r/164859751830.29473.5309689752169286816.stgit@noble.brown Link: https://lkml.kernel.org/r/164859778120.29473.11725907882296224053.stgit@noble.brown Signed-off-by: NeilBrown Reviewed-by: Christoph Hellwig Tested-by: David Howells Tested-by: Geert Uytterhoeven Cc: Trond Myklebust Cc: Hugh Dickins Cc: Mel Gorman Cc: Miaohe Lin Signed-off-by: Andrew Morton --- include/linux/swap.h | 121 --------------------------------------------------- 1 file changed, 121 deletions(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index e6d70a4156e8..def67112dce4 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -427,62 +427,19 @@ extern void kswapd_stop(int nid); #ifdef CONFIG_SWAP -#include /* for bio_end_io_t */ - -/* linux/mm/page_io.c */ -extern int swap_readpage(struct page *page, bool do_poll); -extern int swap_writepage(struct page *page, struct writeback_control *wbc); -extern void end_swap_bio_write(struct bio *bio); -extern int __swap_writepage(struct page *page, struct writeback_control *wbc, - bio_end_io_t end_write_func); bool swap_dirty_folio(struct address_space *mapping, struct folio *folio); - int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block); int generic_swapfile_activate(struct swap_info_struct *, struct file *, sector_t *); -/* linux/mm/swap_state.c */ -/* One swap address space for each 64M swap space */ -#define SWAP_ADDRESS_SPACE_SHIFT 14 -#define SWAP_ADDRESS_SPACE_PAGES (1 << SWAP_ADDRESS_SPACE_SHIFT) -extern struct address_space *swapper_spaces[]; -#define swap_address_space(entry) \ - (&swapper_spaces[swp_type(entry)][swp_offset(entry) \ - >> SWAP_ADDRESS_SPACE_SHIFT]) static inline unsigned long total_swapcache_pages(void) { return global_node_page_state(NR_SWAPCACHE); } -extern void show_swap_cache_info(void); -extern int add_to_swap(struct page *page); -extern void *get_shadow_from_swap_cache(swp_entry_t entry); -extern int add_to_swap_cache(struct page *page, swp_entry_t entry, - gfp_t gfp, void **shadowp); -extern void __delete_from_swap_cache(struct page *page, - swp_entry_t entry, void *shadow); -extern void delete_from_swap_cache(struct page *); -extern void clear_shadow_from_swap_cache(int type, unsigned long begin, - unsigned long end); -extern void free_swap_cache(struct page *); extern void free_page_and_swap_cache(struct page *); extern void free_pages_and_swap_cache(struct page **, int); -extern struct page *lookup_swap_cache(swp_entry_t entry, - struct vm_area_struct *vma, - unsigned long addr); -struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index); -extern struct page *read_swap_cache_async(swp_entry_t, gfp_t, - struct vm_area_struct *vma, unsigned long addr, - bool do_poll); -extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t, - struct vm_area_struct *vma, unsigned long addr, - bool *new_page_allocated); -extern struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t flag, - struct vm_fault *vmf); -extern struct page *swapin_readahead(swp_entry_t entry, gfp_t flag, - struct vm_fault *vmf); - /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; @@ -535,12 +492,6 @@ static inline void put_swap_device(struct swap_info_struct *si) } #else /* CONFIG_SWAP */ - -static inline int swap_readpage(struct page *page, bool do_poll) -{ - return 0; -} - static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return NULL; @@ -555,11 +506,6 @@ static inline void put_swap_device(struct swap_info_struct *si) { } -static inline struct address_space *swap_address_space(swp_entry_t entry) -{ - return NULL; -} - #define get_nr_swap_pages() 0L #define total_swap_pages 0L #define total_swapcache_pages() 0UL @@ -574,14 +520,6 @@ static inline struct address_space *swap_address_space(swp_entry_t entry) #define free_pages_and_swap_cache(pages, nr) \ release_pages((pages), (nr)); -static inline void free_swap_cache(struct page *page) -{ -} - -static inline void show_swap_cache_info(void) -{ -} - /* used to sanity check ptes in zap_pte_range when CONFIG_SWAP=0 */ #define free_swap_and_cache(e) is_pfn_swap_entry(e) @@ -607,65 +545,6 @@ static inline void put_swap_page(struct page *page, swp_entry_t swp) { } -static inline struct page *swap_cluster_readahead(swp_entry_t entry, - gfp_t gfp_mask, struct vm_fault *vmf) -{ - return NULL; -} - -static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask, - struct vm_fault *vmf) -{ - return NULL; -} - -static inline int swap_writepage(struct page *p, struct writeback_control *wbc) -{ - return 0; -} - -static inline struct page *lookup_swap_cache(swp_entry_t swp, - struct vm_area_struct *vma, - unsigned long addr) -{ - return NULL; -} - -static inline -struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index) -{ - return find_get_page(mapping, index); -} - -static inline int add_to_swap(struct page *page) -{ - return 0; -} - -static inline void *get_shadow_from_swap_cache(swp_entry_t entry) -{ - return NULL; -} - -static inline int add_to_swap_cache(struct page *page, swp_entry_t entry, - gfp_t gfp_mask, void **shadowp) -{ - return -1; -} - -static inline void __delete_from_swap_cache(struct page *page, - swp_entry_t entry, void *shadow) -{ -} - -static inline void delete_from_swap_cache(struct page *page) -{ -} - -static inline void clear_shadow_from_swap_cache(int type, unsigned long begin, - unsigned long end) -{ -} static inline int page_swapcount(struct page *page) { -- cgit v1.2.3 From 4c4a763406ef903b78334bd2ccea168d2f7a741a Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 9 May 2022 18:20:47 -0700 Subject: mm: drop swap_dirty_folio folios that are written to swap are owned by the MM subsystem - not any filesystem. When such a folio is passed to a filesystem to be written out to a swap-file, the filesystem handles the data, but the folio itself does not belong to the filesystem. So calling the filesystem's ->dirty_folio() address_space operation makes no sense. This is for folios in the given address space, and a folio to be written to swap does not exist in the given address space. So drop swap_dirty_folio() which calls the address-space's ->dirty_folio(), and always use noop_dirty_folio(), which is appropriate for folios being swapped out. Link: https://lkml.kernel.org/r/164859778123.29473.6900942583784889976.stgit@noble.brown Signed-off-by: NeilBrown Reviewed-by: Christoph Hellwig Tested-by: David Howells Tested-by: Geert Uytterhoeven Cc: Hugh Dickins Cc: Mel Gorman Cc: Trond Myklebust Cc: Miaohe Lin Signed-off-by: Andrew Morton --- include/linux/swap.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index def67112dce4..8170254c56b0 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -427,7 +427,6 @@ extern void kswapd_stop(int nid); #ifdef CONFIG_SWAP -bool swap_dirty_folio(struct address_space *mapping, struct folio *folio); int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block); int generic_swapfile_activate(struct swap_info_struct *, struct file *, -- cgit v1.2.3 From 4b60c0ff2f2021ab99b7fb9da63b7ed1579ef1d8 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 9 May 2022 18:20:48 -0700 Subject: mm: move responsibility for setting SWP_FS_OPS to ->swap_activate If a filesystem wishes to handle all swap IO itself (via ->direct_IO and ->readpage), rather than just providing devices addresses for submit_bio(), SWP_FS_OPS must be set. Currently the protocol for setting this it to have ->swap_activate return zero. In that case SWP_FS_OPS is set, and add_swap_extent() is called for the entire file. This is a little clumsy as different return values for ->swap_activate have quite different meanings, and it makes it hard to search for which filesystems require SWP_FS_OPS to be set. So remove the special meaning of a zero return, and require the filesystem to set SWP_FS_OPS if it so desires, and to always call add_swap_extent() as required. Currently only NFS and CIFS return zero for add_swap_extent(). Link: https://lkml.kernel.org/r/164859778123.29473.17908205846599043598.stgit@noble.brown Signed-off-by: NeilBrown Reviewed-by: Christoph Hellwig Tested-by: David Howells Tested-by: Geert Uytterhoeven Cc: Hugh Dickins Cc: Mel Gorman Cc: Trond Myklebust Cc: Miaohe Lin Signed-off-by: Andrew Morton --- include/linux/swap.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 8170254c56b0..7daae5a4b3e1 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -577,6 +577,12 @@ static inline swp_entry_t get_swap_page(struct page *page) return entry; } +static inline int add_swap_extent(struct swap_info_struct *sis, + unsigned long start_page, + unsigned long nr_pages, sector_t start_block) +{ + return -EINVAL; +} #endif /* CONFIG_SWAP */ #ifdef CONFIG_THP_SWAP -- cgit v1.2.3 From e1209d3a7a67c281260ba9989621060ba7328b8c Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 9 May 2022 18:20:48 -0700 Subject: mm: introduce ->swap_rw and use it for reads from SWP_FS_OPS swap-space swap currently uses ->readpage to read swap pages. This can only request one page at a time from the filesystem, which is not most efficient. swap uses ->direct_IO for writes which while this is adequate is an inappropriate over-loading. ->direct_IO may need to had handle allocate space for holes or other details that are not relevant for swap. So this patch introduces a new address_space operation: ->swap_rw. In this patch it is used for reads, and a subsequent patch will switch writes to use it. No filesystem yet supports ->swap_rw, but that is not a problem because no filesystem actually works with filesystem-based swap. Only two filesystems set SWP_FS_OPS: - cifs sets the flag, but ->direct_IO always fails so swap cannot work. - nfs sets the flag, but ->direct_IO calls generic_write_checks() which has failed on swap files for several releases. To ensure that a NULL ->swap_rw isn't called, ->activate_swap() for both NFS and cifs are changed to fail if ->swap_rw is not set. This can be removed if/when the function is added. Future patches will restore swap-over-NFS functionality. To submit an async read with ->swap_rw() we need to allocate a structure to hold the kiocb and other details. swap_readpage() cannot handle transient failure, so we create a mempool to provide the structures. Link: https://lkml.kernel.org/r/164859778125.29473.13430559328221330589.stgit@noble.brown Signed-off-by: NeilBrown Reviewed-by: Christoph Hellwig Tested-by: David Howells Tested-by: Geert Uytterhoeven Cc: Hugh Dickins Cc: Mel Gorman Cc: Trond Myklebust Cc: Miaohe Lin Signed-off-by: Andrew Morton --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index bbde95387a23..dbc5d10328df 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -380,6 +380,7 @@ struct address_space_operations { int (*swap_activate)(struct swap_info_struct *sis, struct file *file, sector_t *span); void (*swap_deactivate)(struct file *file); + int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter); }; extern const struct address_space_operations empty_aops; -- cgit v1.2.3 From eb79f3af9395fbe448e91b0940a6c395b7d06be4 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 9 May 2022 18:20:48 -0700 Subject: nfs: rename nfs_direct_IO and use as ->swap_rw The nfs_direct_IO() exists to support SWAP IO, but hasn't worked for a while. We now need a ->swap_rw function which behaves slightly differently, returning zero for success rather than a byte count. So modify nfs_direct_IO accordingly, rename it, and use it as the ->swap_rw function. Link: https://lkml.kernel.org/r/165119301493.15698.7491285551903597618.stgit@noble.brown Signed-off-by: NeilBrown Reviewed-by: Christoph Hellwig Tested-by: Geert Uytterhoeven (on Renesas RSK+RZA1 with 32 MiB of SDRAM) Cc: David Howells Cc: Hugh Dickins Cc: Mel Gorman Cc: Miaohe Lin Cc: Trond Myklebust Signed-off-by: Andrew Morton --- include/linux/nfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index b48b9259e02c..fd5543486a3f 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -507,7 +507,7 @@ static inline const struct cred *nfs_file_cred(struct file *file) /* * linux/fs/nfs/direct.c */ -extern ssize_t nfs_direct_IO(struct kiocb *, struct iov_iter *); +int nfs_swap_rw(struct kiocb *iocb, struct iov_iter *iter); ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, bool swap); ssize_t nfs_file_direct_write(struct kiocb *iocb, -- cgit v1.2.3 From 2282679fb20bf036a714ed49fadd0230c278a203 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 9 May 2022 18:20:49 -0700 Subject: mm: submit multipage write for SWP_FS_OPS swap-space swap_writepage() is given one page at a time, but may be called repeatedly in succession. For block-device swapspace, the blk_plug functionality allows the multiple pages to be combined together at lower layers. That cannot be used for SWP_FS_OPS as blk_plug may not exist - it is only active when CONFIG_BLOCK=y. Consequently all swap reads over NFS are single page reads. With this patch we pass a pointer-to-pointer via the wbc. swap_writepage can store state between calls - much like the pointer passed explicitly to swap_readpage. After calling swap_writepage() some number of times, the state will be passed to swap_write_unplug() which can submit the combined request. Link: https://lkml.kernel.org/r/164859778128.29473.5191868522654408537.stgit@noble.brown Signed-off-by: NeilBrown Reviewed-by: Christoph Hellwig Tested-by: David Howells Tested-by: Geert Uytterhoeven Cc: Hugh Dickins Cc: Mel Gorman Cc: Trond Myklebust Cc: Miaohe Lin Signed-off-by: Andrew Morton --- include/linux/writeback.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index fec248ab1fec..32b35f21cb97 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -80,6 +80,13 @@ struct writeback_control { unsigned punt_to_cgroup:1; /* cgrp punting, see __REQ_CGROUP_PUNT */ + /* To enable batching of swap writes to non-block-device backends, + * "plug" can be set point to a 'struct swap_iocb *'. When all swap + * writes have been submitted, if with swap_iocb is not NULL, + * swap_write_unplug() should be called. + */ + struct swap_iocb **swap_plug; + #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb; /* wb this writeback is issued under */ struct inode *inode; /* inode being written out */ -- cgit v1.2.3 From a2ad63daa88b9d6846976fd2a0b5e4f5cfc58377 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 9 May 2022 18:20:49 -0700 Subject: VFS: add FMODE_CAN_ODIRECT file flag Currently various places test if direct IO is possible on a file by checking for the existence of the direct_IO address space operation. This is a poor choice, as the direct_IO operation may not be used - it is only used if the generic_file_*_iter functions are called for direct IO and some filesystems - particularly NFS - don't do this. Instead, introduce a new f_mode flag: FMODE_CAN_ODIRECT and change the various places to check this (avoiding pointer dereferences). do_dentry_open() will set this flag if ->direct_IO is present, so filesystems do not need to be changed. NFS *is* changed, to set the flag explicitly and discard the direct_IO entry in the address_space_operations for files. Other filesystems which currently use noop_direct_IO could usefully be changed to set this flag instead. Link: https://lkml.kernel.org/r/164859778128.29473.15189737957277399416.stgit@noble.brown Reviewed-by: Christoph Hellwig Signed-off-by: NeilBrown Tested-by: David Howells Tested-by: Geert Uytterhoeven Cc: Hugh Dickins Cc: Mel Gorman Cc: Trond Myklebust Cc: Miaohe Lin Signed-off-by: Andrew Morton --- include/linux/fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index dbc5d10328df..b81cacc51d2f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -162,6 +162,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File is stream-like */ #define FMODE_STREAM ((__force fmode_t)0x200000) +/* File supports DIRECT IO */ +#define FMODE_CAN_ODIRECT ((__force fmode_t)0x400000) + /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) -- cgit v1.2.3 From fa29000b6b2603ec2bfdc4c73249fcb00cd54f85 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 29 Apr 2022 17:00:05 -0400 Subject: fs: Add aops->release_folio This replaces aops->releasepage. Update the documentation, and call it if it exists. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Jeff Layton --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index f812f5aa07dd..ad768f13f485 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -355,6 +355,7 @@ struct address_space_operations { /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); void (*invalidate_folio) (struct folio *, size_t offset, size_t len); + bool (*release_folio)(struct folio *, gfp_t); int (*releasepage) (struct page *, gfp_t); void (*freepage)(struct page *); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); -- cgit v1.2.3 From 8597447dc565a6a3fa7bc503674452b7ae2b914c Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 30 Apr 2022 23:01:08 -0400 Subject: iomap: Convert to release_folio Change all the filesystems which used iomap_releasepage to use the new function. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Jeff Layton --- include/linux/iomap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 5b2aa45ddda3..0d674695b6d3 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -228,7 +228,7 @@ ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops); void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops); bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count); -int iomap_releasepage(struct page *page, gfp_t gfp_mask); +bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags); void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len); #ifdef CONFIG_MIGRATION int iomap_migrate_page(struct address_space *mapping, struct page *newpage, -- cgit v1.2.3 From 704ead2bed202579f025a4754e52e9ab21ff3ada Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 1 May 2022 00:27:53 -0400 Subject: fs: Remove last vestiges of releasepage All users are now converted to release_folio Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Jeff Layton --- include/linux/fs.h | 1 - include/linux/page-flags.h | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index ad768f13f485..1cee64d9724b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -356,7 +356,6 @@ struct address_space_operations { sector_t (*bmap)(struct address_space *, sector_t); void (*invalidate_folio) (struct folio *, size_t offset, size_t len); bool (*release_folio)(struct folio *, gfp_t); - int (*releasepage) (struct page *, gfp_t); void (*freepage)(struct page *); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 9d8eeaa67d05..af10149a6c31 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -516,7 +516,7 @@ PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) /* * Private page markings that may be used by the filesystem that owns the page * for its own purposes. - * - PG_private and PG_private_2 cause releasepage() and co to be invoked + * - PG_private and PG_private_2 cause release_folio() and co to be invoked */ PAGEFLAG(Private, private, PF_ANY) PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY) -- cgit v1.2.3 From c56a6eb03deb187c989a966fda5a254249b56c2a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 1 May 2022 00:46:03 -0400 Subject: jbd2: Convert jbd2_journal_try_to_free_buffers to take a folio Also convert it to return a bool since it's called from release_folio(). Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Theodore Ts'o Reviewed-by: Jeff Layton --- include/linux/jbd2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index de9536680b2b..e79d6e0b14e8 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1529,7 +1529,7 @@ extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); int jbd2_journal_invalidate_folio(journal_t *, struct folio *, size_t offset, size_t length); -extern int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page); +bool jbd2_journal_try_to_free_buffers(journal_t *journal, struct folio *folio); extern int jbd2_journal_stop(handle_t *); extern int jbd2_journal_flush(journal_t *journal, unsigned int flags); extern void jbd2_journal_lock_updates (journal_t *); -- cgit v1.2.3 From 68189fef88c7d02eb92e038be3d6428ebd0d2945 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 1 May 2022 01:08:08 -0400 Subject: fs: Change try_to_free_buffers() to take a folio All but two of the callers already have a folio; pass a folio into try_to_free_buffers(). This removes the last user of cancel_dirty_page() so remove that wrapper function too. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Jeff Layton --- include/linux/buffer_head.h | 4 ++-- include/linux/pagemap.h | 4 ---- 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 31d82fd9abe8..c9d1463bb20f 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -158,7 +158,7 @@ void mark_buffer_write_io_error(struct buffer_head *bh); void touch_buffer(struct buffer_head *bh); void set_bh_page(struct buffer_head *bh, struct page *page, unsigned long offset); -int try_to_free_buffers(struct page *); +bool try_to_free_buffers(struct folio *); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry); void create_empty_buffers(struct page *, unsigned long, @@ -402,7 +402,7 @@ bool block_dirty_folio(struct address_space *mapping, struct folio *folio); #else /* CONFIG_BLOCK */ static inline void buffer_init(void) {} -static inline int try_to_free_buffers(struct page *page) { return 1; } +static inline bool try_to_free_buffers(struct folio *folio) { return true; } static inline int inode_has_buffers(struct inode *inode) { return 0; } static inline void invalidate_inode_buffers(struct inode *inode) {} static inline int remove_inode_buffers(struct inode *inode) { return 1; } diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 831b28dab01a..82dfb279e0c4 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1067,10 +1067,6 @@ static inline void folio_cancel_dirty(struct folio *folio) if (folio_test_dirty(folio)) __folio_cancel_dirty(folio); } -static inline void cancel_dirty_page(struct page *page) -{ - folio_cancel_dirty(page_folio(page)); -} bool folio_clear_dirty_for_io(struct folio *folio); bool clear_page_dirty_for_io(struct page *page); void folio_invalidate(struct folio *folio, size_t offset, size_t length); -- cgit v1.2.3 From d2329aa0c78f4a8dd368bb706f196ab99f692eaa Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 1 May 2022 07:35:31 -0400 Subject: fs: Add free_folio address space operation Include documentation and convert the callers to use ->free_folio as well as ->freepage. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1cee64d9724b..915844e6293e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -356,6 +356,7 @@ struct address_space_operations { sector_t (*bmap)(struct address_space *, sector_t); void (*invalidate_folio) (struct folio *, size_t offset, size_t len); bool (*release_folio)(struct folio *, gfp_t); + void (*free_folio)(struct folio *folio); void (*freepage)(struct page *); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* -- cgit v1.2.3 From 8560cb1a7d75048af275dd23fb0cf05382b3c2b9 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 5 May 2022 00:43:09 -0400 Subject: fs: Remove aops->freepage All implementations now use free_folio so we can delete the callers and the method. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 915844e6293e..6f305f1097a5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -357,7 +357,6 @@ struct address_space_operations { void (*invalidate_folio) (struct folio *, size_t offset, size_t len); bool (*release_folio)(struct folio *, gfp_t); void (*free_folio)(struct folio *folio); - void (*freepage)(struct page *); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* * migrate the contents of a page to the specified target. If -- cgit v1.2.3 From 8324a02c342a36336114a497130826612ed5520d Mon Sep 17 00:00:00 2001 From: Gavin Li Date: Sun, 27 Mar 2022 17:45:32 +0300 Subject: net/mlx5: Add exit route when waiting for FW Currently, removing a device needs to get the driver interface lock before doing any cleanup. If the driver is waiting in a loop for FW init, there is no way to cancel the wait, instead the device cleanup waits for the loop to conclude and release the lock. To allow immediate response to remove device commands, check the TEARDOWN flag while waiting for FW init, and exit the loop if it has been set. Signed-off-by: Gavin Li Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index ff47d49d8be4..f327d0544038 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -632,6 +632,7 @@ enum mlx5_device_state { enum mlx5_interface_state { MLX5_INTERFACE_STATE_UP = BIT(0), + MLX5_BREAK_FW_WAIT = BIT(1), }; enum mlx5_pci_status { -- cgit v1.2.3 From 34a30d7635a8e37275a7b63bec09035ed762969b Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 1 Mar 2022 15:42:01 +0000 Subject: net/mlx5: Lag, expose number of lag ports Downstream patches will add support for hardware lag with more than 2 ports. Add a way for users to query the number of lag ports. Signed-off-by: Mark Bloch Reviewed-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f327d0544038..62ea1120de9c 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1142,6 +1142,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, int num_counters, size_t *offsets); struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev); +u8 mlx5_lag_get_num_ports(struct mlx5_core_dev *dev); struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev); void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up); int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, -- cgit v1.2.3 From 4cd14d44b11dabf195d1e66dadbb954336224658 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 1 Mar 2022 17:34:58 +0000 Subject: net/mlx5: Support devices with more than 2 ports Increase the define MLX5_MAX_PORTS to 4 as the driver is ready to support NICs with 4 ports. Signed-off-by: Mark Bloch Reviewed-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 62ea1120de9c..fdb9d07a05a4 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -84,7 +84,7 @@ enum mlx5_sqp_t { }; enum { - MLX5_MAX_PORTS = 2, + MLX5_MAX_PORTS = 4, }; enum { -- cgit v1.2.3 From 7f46a0b7327ae261f9981888708dbca22c283900 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 15 Mar 2022 16:56:50 +0000 Subject: net/mlx5: Lag, add debugfs to query hardware lag state Lag state has become very complicated with many modes, flags, types and port selections methods and future work will add additional features. Add a debugfs to query the current lag state. A new directory named "lag" will be created under the mlx5 debugfs directory. As the driver has debugfs per pci function the location will be: /mlx5//lag For example: /sys/kernel/debug/mlx5/0000:08:00.0/lag The following files are exposed: - state: Returns "active" or "disabled". If "active" it means hardware lag is active. - members: Returns the BDFs of all the members of lag object. - type: Returns the type of the lag currently configured. Valid only if hardware lag is active. * "roce" - Members are bare metal PFs. * "switchdev" - Members are in switchdev mode. * "multipath" - ECMP offloads. - port_sel_mode: Returns the egress port selection method, valid only if hardware lag is active. * "queue_affinity" - Egress port is selected by the QP/SQ affinity. * "hash" - Egress port is selected by hash done on each packet. Controlled by: xmit_hash_policy of the bond device. - flags: Returns flags that are specific per lag @type. Valid only if hardware lag is active. * "shared_fdb" - "on" or "off", if "on" single FDB is used. - mapping: Returns the mapping which is used to select egress port. Valid only if hardware lag is active. If @port_sel_mode is "hash" returns the active egress ports. The hash result will select only active ports. if @port_sel_mode is "queue_affinity" returns the mapping between the configured port affinity of the QP/SQ and actual egress port. For example: * 1:1 - Mapping means if the configured affinity is port 1 traffic will egress via port 1. * 1:2 - Mapping means if the configured affinity is port 1 traffic will egress via port 2. This can happen if port 1 is down or in active/backup mode and port 1 is backup. Signed-off-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index fdb9d07a05a4..d6bac3976913 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -558,6 +558,7 @@ struct mlx5_debugfs_entries { struct dentry *cq_debugfs; struct dentry *cmdif_debugfs; struct dentry *pages_debugfs; + struct dentry *lag_debugfs; }; struct mlx5_ft_pool; -- cgit v1.2.3 From 42704b26b0f1d891f6cf4ebc877dbac0d17c690d Mon Sep 17 00:00:00 2001 From: Gerhard Engleder Date: Fri, 6 May 2022 22:01:37 +0200 Subject: ptp: Add cycles support for virtual clocks ptp vclocks require a free running time for their timecounter. Currently only a physical clock forced to free running is supported. If vclocks are used, then the physical clock cannot be synchronized anymore. The synchronized time is not available in hardware in this case. As a result, timed transmission with TAPRIO hardware support is not possible anymore. If hardware would support a free running time additionally to the physical clock, then the physical clock does not need to be forced to free running. Thus, the physical clocks can still be synchronized while vclocks are in use. The physical clock could be used to synchronize the time domain of the TSN network and trigger TAPRIO. In parallel vclocks can be used to synchronize other time domains. Introduce support for a free running cycle counter called cycles to physical clocks. Rework ptp vclocks to use this free running cycle counter. Default implementation is based on time of physical clock. Thus, behavior of ptp vclocks based on physical clocks without free running cycle counter is identical to previous behavior. Signed-off-by: Gerhard Engleder Acked-by: Richard Cochran Signed-off-by: Paolo Abeni --- include/linux/ptp_clock_kernel.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index e8cc8b6bbf50..ad309202cf9f 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -108,6 +108,32 @@ struct ptp_system_timestamp { * @settime64: Set the current time on the hardware clock. * parameter ts: Time value to set. * + * @getcycles64: Reads the current free running cycle counter from the hardware + * clock. + * If @getcycles64 and @getcyclesx64 are not supported, then + * @gettime64 or @gettimex64 will be used as default + * implementation. + * parameter ts: Holds the result. + * + * @getcyclesx64: Reads the current free running cycle counter from the + * hardware clock and optionally also the system clock. + * If @getcycles64 and @getcyclesx64 are not supported, then + * @gettimex64 will be used as default implementation if + * available. + * parameter ts: Holds the PHC timestamp. + * parameter sts: If not NULL, it holds a pair of timestamps + * from the system clock. The first reading is made right before + * reading the lowest bits of the PHC timestamp and the second + * reading immediately follows that. + * + * @getcrosscycles: Reads the current free running cycle counter from the + * hardware clock and system clock simultaneously. + * If @getcycles64 and @getcyclesx64 are not supported, then + * @getcrosststamp will be used as default implementation if + * available. + * parameter cts: Contains timestamp (device,system) pair, + * where system time is realtime and monotonic. + * * @enable: Request driver to enable or disable an ancillary feature. * parameter request: Desired resource to enable or disable. * parameter on: Caller passes one to enable or zero to disable. @@ -155,6 +181,11 @@ struct ptp_clock_info { int (*getcrosststamp)(struct ptp_clock_info *ptp, struct system_device_crosststamp *cts); int (*settime64)(struct ptp_clock_info *p, const struct timespec64 *ts); + int (*getcycles64)(struct ptp_clock_info *ptp, struct timespec64 *ts); + int (*getcyclesx64)(struct ptp_clock_info *ptp, struct timespec64 *ts, + struct ptp_system_timestamp *sts); + int (*getcrosscycles)(struct ptp_clock_info *ptp, + struct system_device_crosststamp *cts); int (*enable)(struct ptp_clock_info *ptp, struct ptp_clock_request *request, int on); int (*verify)(struct ptp_clock_info *ptp, unsigned int pin, -- cgit v1.2.3 From 51eb7492af276b5b4d27cfa4474d40bdac7b9cf8 Mon Sep 17 00:00:00 2001 From: Gerhard Engleder Date: Fri, 6 May 2022 22:01:38 +0200 Subject: ptp: Request cycles for TX timestamp The free running cycle counter of physical clocks called cycles shall be used for hardware timestamps to enable synchronisation. Introduce new flag SKBTX_HW_TSTAMP_USE_CYCLES, which signals driver to provide a TX timestamp based on cycles if cycles are supported. Signed-off-by: Gerhard Engleder Acked-by: Richard Cochran Signed-off-by: Paolo Abeni --- include/linux/skbuff.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d58669d6cb91..4a4f25975ca2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -615,6 +615,9 @@ enum { /* device driver is going to provide hardware time stamp */ SKBTX_IN_PROGRESS = 1 << 2, + /* generate hardware time stamp based on cycles if supported */ + SKBTX_HW_TSTAMP_USE_CYCLES = 1 << 3, + /* generate wifi status information (where possible) */ SKBTX_WIFI_STATUS = 1 << 4, @@ -624,7 +627,9 @@ enum { #define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ SKBTX_SCHED_TSTAMP) -#define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | SKBTX_ANY_SW_TSTAMP) +#define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | \ + SKBTX_HW_TSTAMP_USE_CYCLES | \ + SKBTX_ANY_SW_TSTAMP) /* Definitions for flags in struct skb_shared_info */ enum { -- cgit v1.2.3 From d58809d854c9ee19e4cd41023e137e65e9dc3f94 Mon Sep 17 00:00:00 2001 From: Gerhard Engleder Date: Fri, 6 May 2022 22:01:39 +0200 Subject: ptp: Pass hwtstamp to ptp_convert_timestamp() ptp_convert_timestamp() converts only the timestamp hwtstamp, which is a field of the argument with the type struct skb_shared_hwtstamps *. So a pointer to the hwtstamp field of this structure is sufficient. Rework ptp_convert_timestamp() to use an argument of type ktime_t *. This allows to add additional timestamp manipulation stages before the call of ptp_convert_timestamp(). Signed-off-by: Gerhard Engleder Acked-by: Richard Cochran Signed-off-by: Paolo Abeni --- include/linux/ptp_clock_kernel.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index ad309202cf9f..92b44161408e 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -384,17 +384,16 @@ int ptp_get_vclocks_index(int pclock_index, int **vclock_index); /** * ptp_convert_timestamp() - convert timestamp to a ptp vclock time * - * @hwtstamps: skb_shared_hwtstamps structure pointer + * @hwtstamp: timestamp * @vclock_index: phc index of ptp vclock. * * Returns converted timestamp, or 0 on error. */ -ktime_t ptp_convert_timestamp(const struct skb_shared_hwtstamps *hwtstamps, - int vclock_index); +ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp, int vclock_index); #else static inline int ptp_get_vclocks_index(int pclock_index, int **vclock_index) { return 0; } -static inline ktime_t ptp_convert_timestamp(const struct skb_shared_hwtstamps *hwtstamps, +static inline ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp, int vclock_index) { return 0; } -- cgit v1.2.3 From 97dc7cd92ac67f6e05df418df1772ba4a7fbf693 Mon Sep 17 00:00:00 2001 From: Gerhard Engleder Date: Fri, 6 May 2022 22:01:40 +0200 Subject: ptp: Support late timestamp determination If a physical clock supports a free running cycle counter, then timestamps shall be based on this time too. For TX it is known in advance before the transmission if a timestamp based on the free running cycle counter is needed. For RX it is impossible to know which timestamp is needed before the packet is received and assigned to a socket. Support late timestamp determination by a network device. Therefore, an address/cookie is stored within the new netdev_data field of struct skb_shared_hwtstamps. This address/cookie is provided to a new network device function called ndo_get_tstamp(), which returns a timestamp based on the normal/adjustable time or based on the free running cycle counter. If function is not supported, then timestamp handling is not changed. This mechanism is intended for RX, but TX use is also possible. Signed-off-by: Gerhard Engleder Acked-by: Jonathan Lemon Acked-by: Richard Cochran Signed-off-by: Paolo Abeni --- include/linux/netdevice.h | 21 +++++++++++++++++++++ include/linux/skbuff.h | 14 +++++++++++--- 2 files changed, 32 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 74c97a34921d..51fe143091cf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1356,6 +1356,12 @@ struct netdev_net_notifier { * The caller must be under RCU read context. * int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path); * Get the forwarding path to reach the real device from the HW destination address + * ktime_t (*ndo_get_tstamp)(struct net_device *dev, + * const struct skb_shared_hwtstamps *hwtstamps, + * bool cycles); + * Get hardware timestamp based on normal/adjustable time or free running + * cycle counter. This function is required if physical clock supports a + * free running cycle counter. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1578,6 +1584,9 @@ struct net_device_ops { struct net_device * (*ndo_get_peer_dev)(struct net_device *dev); int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path); + ktime_t (*ndo_get_tstamp)(struct net_device *dev, + const struct skb_shared_hwtstamps *hwtstamps, + bool cycles); }; /** @@ -4761,6 +4770,18 @@ static inline void netdev_rx_csum_fault(struct net_device *dev, void net_enable_timestamp(void); void net_disable_timestamp(void); +static inline ktime_t netdev_get_tstamp(struct net_device *dev, + const struct skb_shared_hwtstamps *hwtstamps, + bool cycles) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (ops->ndo_get_tstamp) + return ops->ndo_get_tstamp(dev, hwtstamps, cycles); + + return hwtstamps->hwtstamp; +} + static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops, struct sk_buff *skb, struct net_device *dev, bool more) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4a4f25975ca2..97de40bcfef6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -588,8 +588,10 @@ static inline bool skb_frag_must_loop(struct page *p) /** * struct skb_shared_hwtstamps - hardware time stamps - * @hwtstamp: hardware time stamp transformed into duration - * since arbitrary point in time + * @hwtstamp: hardware time stamp transformed into duration + * since arbitrary point in time + * @netdev_data: address/cookie of network device driver used as + * reference to actual hardware time stamp * * Software time stamps generated by ktime_get_real() are stored in * skb->tstamp. @@ -601,7 +603,10 @@ static inline bool skb_frag_must_loop(struct page *p) * &skb_shared_info. Use skb_hwtstamps() to get a pointer. */ struct skb_shared_hwtstamps { - ktime_t hwtstamp; + union { + ktime_t hwtstamp; + void *netdev_data; + }; }; /* Definitions for tx_flags in struct skb_shared_info */ @@ -621,6 +626,9 @@ enum { /* generate wifi status information (where possible) */ SKBTX_WIFI_STATUS = 1 << 4, + /* determine hardware time stamp based on time or cycles */ + SKBTX_HW_TSTAMP_NETDEV = 1 << 5, + /* generate software time stamp when entering packet scheduling */ SKBTX_SCHED_TSTAMP = 1 << 6, }; -- cgit v1.2.3 From 57ce2e406fe1fa005e8fdbf20936c791252ac7bc Mon Sep 17 00:00:00 2001 From: Nava kishore Manne Date: Sat, 23 Apr 2022 22:32:32 +0530 Subject: fpga: fix for coding style issues fixes the below checks reported by checkpatch.pl: - Lines should not end with a '(' - Alignment should match open parenthesis Signed-off-by: Nava kishore Manne Link: https://lore.kernel.org/r/20220423170235.2115479-3-nava.manne@xilinx.com Signed-off-by: Xu Yilun --- include/linux/fpga/fpga-region.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/fpga/fpga-region.h b/include/linux/fpga/fpga-region.h index 3b87f232425c..9d4d32909340 100644 --- a/include/linux/fpga/fpga-region.h +++ b/include/linux/fpga/fpga-region.h @@ -52,9 +52,9 @@ struct fpga_region { #define to_fpga_region(d) container_of(d, struct fpga_region, dev) -struct fpga_region *fpga_region_class_find( - struct device *start, const void *data, - int (*match)(struct device *, const void *)); +struct fpga_region * +fpga_region_class_find(struct device *start, const void *data, + int (*match)(struct device *, const void *)); int fpga_region_program_fpga(struct fpga_region *region); -- cgit v1.2.3 From 7ff960a6fe399fdcbca6159063684671ae57eee9 Mon Sep 17 00:00:00 2001 From: Shunsuke Mie Date: Tue, 10 May 2022 19:27:23 +0900 Subject: virtio: fix virtio transitional ids This commit fixes the transitional PCI device ID. Fixes: d61914ea6ada ("virtio: update virtio id table, add transitional ids") Signed-off-by: Shunsuke Mie Link: https://lore.kernel.org/r/20220510102723.87666-1-mie@igel.co.jp Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_ids.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h index 80d76b75bccd..7aa2eb766205 100644 --- a/include/uapi/linux/virtio_ids.h +++ b/include/uapi/linux/virtio_ids.h @@ -73,12 +73,12 @@ * Virtio Transitional IDs */ -#define VIRTIO_TRANS_ID_NET 1000 /* transitional virtio net */ -#define VIRTIO_TRANS_ID_BLOCK 1001 /* transitional virtio block */ -#define VIRTIO_TRANS_ID_BALLOON 1002 /* transitional virtio balloon */ -#define VIRTIO_TRANS_ID_CONSOLE 1003 /* transitional virtio console */ -#define VIRTIO_TRANS_ID_SCSI 1004 /* transitional virtio SCSI */ -#define VIRTIO_TRANS_ID_RNG 1005 /* transitional virtio rng */ -#define VIRTIO_TRANS_ID_9P 1009 /* transitional virtio 9p console */ +#define VIRTIO_TRANS_ID_NET 0x1000 /* transitional virtio net */ +#define VIRTIO_TRANS_ID_BLOCK 0x1001 /* transitional virtio block */ +#define VIRTIO_TRANS_ID_BALLOON 0x1002 /* transitional virtio balloon */ +#define VIRTIO_TRANS_ID_CONSOLE 0x1003 /* transitional virtio console */ +#define VIRTIO_TRANS_ID_SCSI 0x1004 /* transitional virtio SCSI */ +#define VIRTIO_TRANS_ID_RNG 0x1005 /* transitional virtio rng */ +#define VIRTIO_TRANS_ID_9P 0x1009 /* transitional virtio 9p console */ #endif /* _LINUX_VIRTIO_IDS_H */ -- cgit v1.2.3 From c23d47abee3a54e4991ed3993340596d04aabd6a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Apr 2022 08:33:03 +0200 Subject: loop: remove most the top-of-file boilerplate comment from the UAPI header Just leave the SPDX marker and the copyright notice and remove the irrelevant rest. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220419063303.583106-5-hch@lst.de Signed-off-by: Jens Axboe --- include/uapi/linux/loop.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h index 98e60801195e..6f63527dd2ed 100644 --- a/include/uapi/linux/loop.h +++ b/include/uapi/linux/loop.h @@ -1,11 +1,6 @@ /* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ /* - * include/linux/loop.h - * - * Written by Theodore Ts'o, 3/29/93. - * - * Copyright 1993 by Theodore Ts'o. Redistribution of this file is - * permitted under the GNU General Public License. + * Copyright 1993 by Theodore Ts'o. */ #ifndef _UAPI_LINUX_LOOP_H #define _UAPI_LINUX_LOOP_H -- cgit v1.2.3 From 846e437387e74c44ddc9f3eeec472fd37ca3cdb9 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Tue, 10 May 2022 12:02:03 +0300 Subject: net/mlx5: Expose mlx5_sriov_blocking_notifier_register / unregister APIs Expose mlx5_sriov_blocking_notifier_register / unregister APIs to let a VF register to be notified for its enablement / disablement by the PF. Upon VF probe it will call mlx5_sriov_blocking_notifier_register() with its notifier block and upon VF remove it will call mlx5_sriov_blocking_notifier_unregister() to drop its registration. This can give a VF the ability to clean some resources upon disable before that the command interface goes down and on the other hand sets some stuff before that it's enabled. This may be used by a VF which is migration capable in few cases.(e.g. PF load/unload upon an health recovery). Link: https://lore.kernel.org/r/20220510090206.90374-2-yishaih@nvidia.com Signed-off-by: Yishai Hadas Signed-off-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- include/linux/mlx5/driver.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index ff47d49d8be4..6fac5427d899 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -445,6 +445,11 @@ struct mlx5_qp_table { struct radix_tree_root tree; }; +enum { + MLX5_PF_NOTIFY_DISABLE_VF, + MLX5_PF_NOTIFY_ENABLE_VF, +}; + struct mlx5_vf_context { int enabled; u64 port_guid; @@ -455,6 +460,7 @@ struct mlx5_vf_context { u8 port_guid_valid:1; u8 node_guid_valid:1; enum port_state_policy policy; + struct blocking_notifier_head notifier; }; struct mlx5_core_sriov { @@ -1152,6 +1158,12 @@ int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type struct mlx5_core_dev *mlx5_vf_get_core_dev(struct pci_dev *pdev); void mlx5_vf_put_core_dev(struct mlx5_core_dev *mdev); +int mlx5_sriov_blocking_notifier_register(struct mlx5_core_dev *mdev, + int vf_id, + struct notifier_block *nb); +void mlx5_sriov_blocking_notifier_unregister(struct mlx5_core_dev *mdev, + int vf_id, + struct notifier_block *nb); #ifdef CONFIG_MLX5_CORE_IPOIB struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, struct ib_device *ibdev, -- cgit v1.2.3 From 2cb29da3f2c29e62311eec6446be92aa5f2c1620 Mon Sep 17 00:00:00 2001 From: YC Hung Date: Mon, 9 May 2022 12:04:25 -0500 Subject: ASoC: SOF: ipc: introduce cont_update_posn in sof_ipc_stream_params struct The host stream position is updated when no_stream_position is set as 0. However current implementation updates host stream position only when report data is larger than or equal to host period size which is decided by the period size of host side. It maybe cause host stream position update not in time. Therefore this patch introduces another field "cont_update_posn", a boolean value aimed to update host stream position continuously and based on period size of pipeline. It can get better precise when need to update host stream position from firmware. Reviewed-by: Daniel Baluta Reviewed-by: Ranjani Sridharan Reviewed-by: Kai Vehmanen Signed-off-by: YC Hung Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20220509170425.54640-1-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof/stream.h | 3 ++- include/uapi/sound/sof/abi.h | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/sound/sof/stream.h b/include/sound/sof/stream.h index 58a0d49977d6..1db3bbc3e65d 100644 --- a/include/sound/sof/stream.h +++ b/include/sound/sof/stream.h @@ -85,8 +85,9 @@ struct sof_ipc_stream_params { uint32_t host_period_bytes; uint16_t no_stream_position; /**< 1 means don't send stream position */ + uint8_t cont_update_posn; /**< 1 means continuous update stream position */ - uint16_t reserved[3]; + uint8_t reserved[5]; uint16_t chmap[SOF_IPC_MAX_CHANNELS]; /**< channel map - SOF_CHMAP_ */ } __packed; diff --git a/include/uapi/sound/sof/abi.h b/include/uapi/sound/sof/abi.h index b87e46684623..0e7dccdc25fd 100644 --- a/include/uapi/sound/sof/abi.h +++ b/include/uapi/sound/sof/abi.h @@ -26,7 +26,7 @@ /* SOF ABI version major, minor and patch numbers */ #define SOF_ABI_MAJOR 3 -#define SOF_ABI_MINOR 20 +#define SOF_ABI_MINOR 21 #define SOF_ABI_PATCH 0 /* SOF ABI version number. Format within 32bit word is MMmmmppp */ -- cgit v1.2.3 From 1ff297584fad2eef390f212b860e0fbb7363e0e8 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 10 May 2022 10:29:36 -0700 Subject: randomize_kstack: Improve docs on requirements/rationale There were some recent questions about where and why to use the random_kstack routines when applying them to new architectures[1]. Update the header comments to reflect the design choices for the routines. [1] https://lore.kernel.org/lkml/1652173338.7bltwybi0c.astroid@bobo.none Cc: Nicholas Piggin Cc: Xiu Jianfeng Signed-off-by: Kees Cook --- include/linux/randomize_kstack.h | 27 ++++++++++++++++++++++++--- 1 file changed, 24 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h index 1468caf001c0..5d868505a94e 100644 --- a/include/linux/randomize_kstack.h +++ b/include/linux/randomize_kstack.h @@ -40,10 +40,14 @@ DECLARE_PER_CPU(u32, kstack_offset); */ #define KSTACK_OFFSET_MAX(x) ((x) & 0x3FF) -/* - * These macros must be used during syscall entry when interrupts and +/** + * add_random_kstack_offset - Increase stack utilization by previously + * chosen random offset + * + * This should be used in the syscall entry path when interrupts and * preempt are disabled, and after user registers have been stored to - * the stack. + * the stack. For testing the resulting entropy, please see: + * tools/testing/selftests/lkdtm/stack-entropy.sh */ #define add_random_kstack_offset() do { \ if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \ @@ -55,6 +59,23 @@ DECLARE_PER_CPU(u32, kstack_offset); } \ } while (0) +/** + * choose_random_kstack_offset - Choose the random offset for the next + * add_random_kstack_offset() + * + * This should only be used during syscall exit when interrupts and + * preempt are disabled. This position in the syscall flow is done to + * frustrate attacks from userspace attempting to learn the next offset: + * - Maximize the timing uncertainty visible from userspace: if the + * offset is chosen at syscall entry, userspace has much more control + * over the timing between choosing offsets. "How long will we be in + * kernel mode?" tends to be more difficult to predict than "how long + * will we be in user mode?" + * - Reduce the lifetime of the new offset sitting in memory during + * kernel mode execution. Exposure of "thread-local" memory content + * (e.g. current, percpu, etc) tends to be easier than arbitrary + * location memory exposure. + */ #define choose_random_kstack_offset(rand) do { \ if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \ &randomize_kstack_offset)) { \ -- cgit v1.2.3 From 26101f5ab6bdf30ac25c8e578e0b4873e7849e0c Mon Sep 17 00:00:00 2001 From: Kaixi Fan Date: Sat, 30 Apr 2022 15:48:42 +0800 Subject: bpf: Add source ip in "struct bpf_tunnel_key" Add tunnel source ip field in "struct bpf_tunnel_key". Add related code to set and get tunnel source field. Signed-off-by: Kaixi Fan Link: https://lore.kernel.org/r/20220430074844.69214-2-fankaixi.li@bytedance.com Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 444fe6f1cf35..95a3d1ff6255 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5604,6 +5604,10 @@ struct bpf_tunnel_key { __u8 tunnel_ttl; __u16 tunnel_ext; /* Padding, future use. */ __u32 tunnel_label; + union { + __u32 local_ipv4; + __u32 local_ipv6[4]; + }; }; /* user accessible mirror of in-kernel xfrm_state. -- cgit v1.2.3 From 9f88361273082825d9f0d13a543d49f9fa0d44a8 Mon Sep 17 00:00:00 2001 From: Dmitrii Dolgov <9erthalion6@gmail.com> Date: Tue, 10 May 2022 17:52:30 +0200 Subject: bpf: Add bpf_link iterator Implement bpf_link iterator to traverse links via bpf_seq_file operations. The changeset is mostly shamelessly copied from commit a228a64fc1e4 ("bpf: Add bpf_prog iterator") Signed-off-by: Dmitrii Dolgov <9erthalion6@gmail.com> Acked-by: Yonghong Song Link: https://lore.kernel.org/r/20220510155233.9815-2-9erthalion6@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index be94833d390a..551b7198ae8a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1544,6 +1544,7 @@ void bpf_link_put(struct bpf_link *link); int bpf_link_new_fd(struct bpf_link *link); struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd); struct bpf_link *bpf_link_get_from_fd(u32 ufd); +struct bpf_link *bpf_link_get_curr_or_next(u32 *id); int bpf_obj_pin_user(u32 ufd, const char __user *pathname); int bpf_obj_get_user(const char __user *pathname, int flags); -- cgit v1.2.3 From d721def7392a7348ffb9f3583b264239cbd3702c Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 10 May 2022 14:26:12 +0200 Subject: kallsyms: Make kallsyms_on_each_symbol generally available Making kallsyms_on_each_symbol generally available, so it can be used outside CONFIG_LIVEPATCH option in following changes. Rather than adding another ifdef option let's make the function generally available (when CONFIG_KALLSYMS option is defined). Cc: Christoph Hellwig Reviewed-by: Masami Hiramatsu Signed-off-by: Jiri Olsa Link: https://lore.kernel.org/r/20220510122616.2652285-2-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/kallsyms.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index ce1bd2fbf23e..ad39636e0c3f 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -65,11 +65,11 @@ static inline void *dereference_symbol_descriptor(void *ptr) return ptr; } +#ifdef CONFIG_KALLSYMS int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, unsigned long), void *data); -#ifdef CONFIG_KALLSYMS /* Lookup the address for a symbol. Returns 0 if not found. */ unsigned long kallsyms_lookup_name(const char *name); @@ -163,6 +163,11 @@ static inline bool kallsyms_show_value(const struct cred *cred) return false; } +static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, + unsigned long), void *data) +{ + return -EOPNOTSUPP; +} #endif /*CONFIG_KALLSYMS*/ static inline void print_ip_sym(const char *loglvl, unsigned long ip) -- cgit v1.2.3 From bed0d9a50dacee6fcf785c555cfb0d2573355afc Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 10 May 2022 14:26:13 +0200 Subject: ftrace: Add ftrace_lookup_symbols function Adding ftrace_lookup_symbols function that resolves array of symbols with single pass over kallsyms. The user provides array of string pointers with count and pointer to allocated array for resolved values. int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *addrs) It iterates all kallsyms symbols and tries to loop up each in provided symbols array with bsearch. The symbols array needs to be sorted by name for this reason. We also check each symbol to pass ftrace_location, because this API will be used for fprobe symbols resolving. Suggested-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Reviewed-by: Masami Hiramatsu Signed-off-by: Jiri Olsa Link: https://lore.kernel.org/r/20220510122616.2652285-3-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/ftrace.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 4816b7e11047..820500430eae 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -303,6 +303,8 @@ int unregister_ftrace_function(struct ftrace_ops *ops); extern void ftrace_stub(unsigned long a0, unsigned long a1, struct ftrace_ops *op, struct ftrace_regs *fregs); + +int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *addrs); #else /* !CONFIG_FUNCTION_TRACER */ /* * (un)register_ftrace_function must be a macro since the ops parameter @@ -313,6 +315,10 @@ extern void ftrace_stub(unsigned long a0, unsigned long a1, static inline void ftrace_kill(void) { } static inline void ftrace_free_init_mem(void) { } static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { } +static inline int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *addrs) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_FUNCTION_TRACER */ struct ftrace_func_entry { -- cgit v1.2.3 From ddccc9ef55992716ad477d38fbcd9f8f1d34fc67 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 9 May 2022 09:04:54 -0700 Subject: skbuff: add a basic intro doc Add basic skb documentation. It's mostly an intro to the subsequent patches - it would looks strange if we documented advanced topics without covering the basics in any way. Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 97de40bcfef6..69802624276d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -800,6 +800,46 @@ typedef unsigned int sk_buff_data_t; typedef unsigned char *sk_buff_data_t; #endif +/** + * DOC: Basic sk_buff geometry + * + * struct sk_buff itself is a metadata structure and does not hold any packet + * data. All the data is held in associated buffers. + * + * &sk_buff.head points to the main "head" buffer. The head buffer is divided + * into two parts: + * + * - data buffer, containing headers and sometimes payload; + * this is the part of the skb operated on by the common helpers + * such as skb_put() or skb_pull(); + * - shared info (struct skb_shared_info) which holds an array of pointers + * to read-only data in the (page, offset, length) format. + * + * Optionally &skb_shared_info.frag_list may point to another skb. + * + * Basic diagram may look like this:: + * + * --------------- + * | sk_buff | + * --------------- + * ,--------------------------- + head + * / ,----------------- + data + * / / ,----------- + tail + * | | | , + end + * | | | | + * v v v v + * ----------------------------------------------- + * | headroom | data | tailroom | skb_shared_info | + * ----------------------------------------------- + * + [page frag] + * + [page frag] + * + [page frag] + * + [page frag] --------- + * + frag_list --> | sk_buff | + * --------- + * + */ + /** * struct sk_buff - socket buffer * @next: Next buffer in list -- cgit v1.2.3 From 9ec7ea1462084df695f34c5ac2d2d2250d9d6897 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 9 May 2022 09:04:55 -0700 Subject: skbuff: rewrite the doc for data-only skbs The comment about shinfo->dataref split is really unhelpful, at least to me. Rewrite it and render it to skb documentation. Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 42 ++++++++++++++++++++++++++++++------------ 1 file changed, 30 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 69802624276d..0e492f9bf532 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -727,16 +727,32 @@ struct skb_shared_info { skb_frag_t frags[MAX_SKB_FRAGS]; }; -/* We divide dataref into two halves. The higher 16 bits hold references - * to the payload part of skb->data. The lower 16 bits hold references to - * the entire skb->data. A clone of a headerless skb holds the length of - * the header in skb->hdr_len. - * - * All users must obey the rule that the skb->data reference count must be - * greater than or equal to the payload reference count. - * - * Holding a reference to the payload part means that the user does not - * care about modifications to the header part of skb->data. +/** + * DOC: dataref and headerless skbs + * + * Transport layers send out clones of payload skbs they hold for + * retransmissions. To allow lower layers of the stack to prepend their headers + * we split &skb_shared_info.dataref into two halves. + * The lower 16 bits count the overall number of references. + * The higher 16 bits indicate how many of the references are payload-only. + * skb_header_cloned() checks if skb is allowed to add / write the headers. + * + * The creator of the skb (e.g. TCP) marks its skb as &sk_buff.nohdr + * (via __skb_header_release()). Any clone created from marked skb will get + * &sk_buff.hdr_len populated with the available headroom. + * If there's the only clone in existence it's able to modify the headroom + * at will. The sequence of calls inside the transport layer is:: + * + * + * skb_reserve() + * __skb_header_release() + * skb_clone() + * // send the clone down the stack + * + * This is not a very generic construct and it depends on the transport layers + * doing the right thing. In practice there's usually only one payload-only skb. + * Having multiple payload-only skbs with different lengths of hdr_len is not + * possible. The payload-only skbs should never leave their owner. */ #define SKB_DATAREF_SHIFT 16 #define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1) @@ -2027,8 +2043,10 @@ static inline int skb_header_unclone(struct sk_buff *skb, gfp_t pri) } /** - * __skb_header_release - release reference to header - * @skb: buffer to operate on + * __skb_header_release() - allow clones to use the headroom + * @skb: buffer to operate on + * + * See "DOC: dataref and headerless skbs". */ static inline void __skb_header_release(struct sk_buff *skb) { -- cgit v1.2.3 From 9facd94114b59afebd405e74b3bc2bf184efe986 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 9 May 2022 09:04:56 -0700 Subject: skbuff: render the checksum comment to documentation Long time ago Tom added a giant comment to skbuff.h explaining checksums. Now that we have a place in Documentation for skbuff docs we should render it. Sprinkle some markup while at it. Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 219 ++++++++++++++++++++++++++++--------------------- 1 file changed, 124 insertions(+), 95 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0e492f9bf532..5296b2c37f62 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -43,98 +43,112 @@ #include #endif -/* The interface for checksum offload between the stack and networking drivers +/** + * DOC: skb checksums + * + * The interface for checksum offload between the stack and networking drivers * is as follows... * - * A. IP checksum related features + * IP checksum related features + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * Drivers advertise checksum offload capabilities in the features of a device. * From the stack's point of view these are capabilities offered by the driver. * A driver typically only advertises features that it is capable of offloading * to its device. * - * The checksum related features are: - * - * NETIF_F_HW_CSUM - The driver (or its device) is able to compute one - * IP (one's complement) checksum for any combination - * of protocols or protocol layering. The checksum is - * computed and set in a packet per the CHECKSUM_PARTIAL - * interface (see below). - * - * NETIF_F_IP_CSUM - Driver (device) is only able to checksum plain - * TCP or UDP packets over IPv4. These are specifically - * unencapsulated packets of the form IPv4|TCP or - * IPv4|UDP where the Protocol field in the IPv4 header - * is TCP or UDP. The IPv4 header may contain IP options. - * This feature cannot be set in features for a device - * with NETIF_F_HW_CSUM also set. This feature is being - * DEPRECATED (see below). - * - * NETIF_F_IPV6_CSUM - Driver (device) is only able to checksum plain - * TCP or UDP packets over IPv6. These are specifically - * unencapsulated packets of the form IPv6|TCP or - * IPv6|UDP where the Next Header field in the IPv6 - * header is either TCP or UDP. IPv6 extension headers - * are not supported with this feature. This feature - * cannot be set in features for a device with - * NETIF_F_HW_CSUM also set. This feature is being - * DEPRECATED (see below). - * - * NETIF_F_RXCSUM - Driver (device) performs receive checksum offload. - * This flag is only used to disable the RX checksum - * feature for a device. The stack will accept receive - * checksum indication in packets received on a device - * regardless of whether NETIF_F_RXCSUM is set. - * - * B. Checksumming of received packets by device. Indication of checksum - * verification is set in skb->ip_summed. Possible values are: - * - * CHECKSUM_NONE: + * .. flat-table:: Checksum related device features + * :widths: 1 10 + * + * * - %NETIF_F_HW_CSUM + * - The driver (or its device) is able to compute one + * IP (one's complement) checksum for any combination + * of protocols or protocol layering. The checksum is + * computed and set in a packet per the CHECKSUM_PARTIAL + * interface (see below). + * + * * - %NETIF_F_IP_CSUM + * - Driver (device) is only able to checksum plain + * TCP or UDP packets over IPv4. These are specifically + * unencapsulated packets of the form IPv4|TCP or + * IPv4|UDP where the Protocol field in the IPv4 header + * is TCP or UDP. The IPv4 header may contain IP options. + * This feature cannot be set in features for a device + * with NETIF_F_HW_CSUM also set. This feature is being + * DEPRECATED (see below). + * + * * - %NETIF_F_IPV6_CSUM + * - Driver (device) is only able to checksum plain + * TCP or UDP packets over IPv6. These are specifically + * unencapsulated packets of the form IPv6|TCP or + * IPv6|UDP where the Next Header field in the IPv6 + * header is either TCP or UDP. IPv6 extension headers + * are not supported with this feature. This feature + * cannot be set in features for a device with + * NETIF_F_HW_CSUM also set. This feature is being + * DEPRECATED (see below). + * + * * - %NETIF_F_RXCSUM + * - Driver (device) performs receive checksum offload. + * This flag is only used to disable the RX checksum + * feature for a device. The stack will accept receive + * checksum indication in packets received on a device + * regardless of whether NETIF_F_RXCSUM is set. + * + * Checksumming of received packets by device + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * Indication of checksum verification is set in &sk_buff.ip_summed. + * Possible values are: + * + * - %CHECKSUM_NONE * * Device did not checksum this packet e.g. due to lack of capabilities. * The packet contains full (though not verified) checksum in packet but * not in skb->csum. Thus, skb->csum is undefined in this case. * - * CHECKSUM_UNNECESSARY: + * - %CHECKSUM_UNNECESSARY * * The hardware you're dealing with doesn't calculate the full checksum - * (as in CHECKSUM_COMPLETE), but it does parse headers and verify checksums - * for specific protocols. For such packets it will set CHECKSUM_UNNECESSARY - * if their checksums are okay. skb->csum is still undefined in this case + * (as in %CHECKSUM_COMPLETE), but it does parse headers and verify checksums + * for specific protocols. For such packets it will set %CHECKSUM_UNNECESSARY + * if their checksums are okay. &sk_buff.csum is still undefined in this case * though. A driver or device must never modify the checksum field in the * packet even if checksum is verified. * - * CHECKSUM_UNNECESSARY is applicable to following protocols: - * TCP: IPv6 and IPv4. - * UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a + * %CHECKSUM_UNNECESSARY is applicable to following protocols: + * + * - TCP: IPv6 and IPv4. + * - UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a * zero UDP checksum for either IPv4 or IPv6, the networking stack * may perform further validation in this case. - * GRE: only if the checksum is present in the header. - * SCTP: indicates the CRC in SCTP header has been validated. - * FCOE: indicates the CRC in FC frame has been validated. + * - GRE: only if the checksum is present in the header. + * - SCTP: indicates the CRC in SCTP header has been validated. + * - FCOE: indicates the CRC in FC frame has been validated. * - * skb->csum_level indicates the number of consecutive checksums found in - * the packet minus one that have been verified as CHECKSUM_UNNECESSARY. + * &sk_buff.csum_level indicates the number of consecutive checksums found in + * the packet minus one that have been verified as %CHECKSUM_UNNECESSARY. * For instance if a device receives an IPv6->UDP->GRE->IPv4->TCP packet * and a device is able to verify the checksums for UDP (possibly zero), - * GRE (checksum flag is set) and TCP, skb->csum_level would be set to + * GRE (checksum flag is set) and TCP, &sk_buff.csum_level would be set to * two. If the device were only able to verify the UDP checksum and not * GRE, either because it doesn't support GRE checksum or because GRE * checksum is bad, skb->csum_level would be set to zero (TCP checksum is * not considered in this case). * - * CHECKSUM_COMPLETE: + * - %CHECKSUM_COMPLETE * * This is the most generic way. The device supplied checksum of the _whole_ - * packet as seen by netif_rx() and fills in skb->csum. This means the + * packet as seen by netif_rx() and fills in &sk_buff.csum. This means the * hardware doesn't need to parse L3/L4 headers to implement this. * * Notes: + * * - Even if device supports only some protocols, but is able to produce * skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY. * - CHECKSUM_COMPLETE is not applicable to SCTP and FCoE protocols. * - * CHECKSUM_PARTIAL: + * - %CHECKSUM_PARTIAL * * A checksum is set up to be offloaded to a device as described in the * output description for CHECKSUM_PARTIAL. This may occur on a packet @@ -146,14 +160,18 @@ * packet that are after the checksum being offloaded are not considered to * be verified. * - * C. Checksumming on transmit for non-GSO. The stack requests checksum offload - * in the skb->ip_summed for a packet. Values are: + * Checksumming on transmit for non-GSO + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * The stack requests checksum offload in the &sk_buff.ip_summed for a packet. + * Values are: * - * CHECKSUM_PARTIAL: + * - %CHECKSUM_PARTIAL * * The driver is required to checksum the packet as seen by hard_start_xmit() - * from skb->csum_start up to the end, and to record/write the checksum at - * offset skb->csum_start + skb->csum_offset. A driver may verify that the + * from &sk_buff.csum_start up to the end, and to record/write the checksum at + * offset &sk_buff.csum_start + &sk_buff.csum_offset. + * A driver may verify that the * csum_start and csum_offset values are valid values given the length and * offset of the packet, but it should not attempt to validate that the * checksum refers to a legitimate transport layer checksum -- it is the @@ -165,55 +183,66 @@ * checksum calculation to the device, or call skb_checksum_help (in the case * that the device does not support offload for a particular checksum). * - * NETIF_F_IP_CSUM and NETIF_F_IPV6_CSUM are being deprecated in favor of - * NETIF_F_HW_CSUM. New devices should use NETIF_F_HW_CSUM to indicate + * %NETIF_F_IP_CSUM and %NETIF_F_IPV6_CSUM are being deprecated in favor of + * %NETIF_F_HW_CSUM. New devices should use %NETIF_F_HW_CSUM to indicate * checksum offload capability. - * skb_csum_hwoffload_help() can be called to resolve CHECKSUM_PARTIAL based + * skb_csum_hwoffload_help() can be called to resolve %CHECKSUM_PARTIAL based * on network device checksumming capabilities: if a packet does not match - * them, skb_checksum_help or skb_crc32c_help (depending on the value of - * csum_not_inet, see item D.) is called to resolve the checksum. + * them, skb_checksum_help() or skb_crc32c_help() (depending on the value of + * &sk_buff.csum_not_inet, see :ref:`crc`) + * is called to resolve the checksum. * - * CHECKSUM_NONE: + * - %CHECKSUM_NONE * * The skb was already checksummed by the protocol, or a checksum is not * required. * - * CHECKSUM_UNNECESSARY: + * - %CHECKSUM_UNNECESSARY * * This has the same meaning as CHECKSUM_NONE for checksum offload on * output. * - * CHECKSUM_COMPLETE: + * - %CHECKSUM_COMPLETE + * * Not used in checksum output. If a driver observes a packet with this value - * set in skbuff, it should treat the packet as if CHECKSUM_NONE were set. - * - * D. Non-IP checksum (CRC) offloads - * - * NETIF_F_SCTP_CRC - This feature indicates that a device is capable of - * offloading the SCTP CRC in a packet. To perform this offload the stack - * will set csum_start and csum_offset accordingly, set ip_summed to - * CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication in - * the skbuff that the CHECKSUM_PARTIAL refers to CRC32c. - * A driver that supports both IP checksum offload and SCTP CRC32c offload - * must verify which offload is configured for a packet by testing the - * value of skb->csum_not_inet; skb_crc32c_csum_help is provided to resolve - * CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1. - * - * NETIF_F_FCOE_CRC - This feature indicates that a device is capable of - * offloading the FCOE CRC in a packet. To perform this offload the stack - * will set ip_summed to CHECKSUM_PARTIAL and set csum_start and csum_offset - * accordingly. Note that there is no indication in the skbuff that the - * CHECKSUM_PARTIAL refers to an FCOE checksum, so a driver that supports - * both IP checksum offload and FCOE CRC offload must verify which offload - * is configured for a packet, presumably by inspecting packet headers. - * - * E. Checksumming on output with GSO. - * - * In the case of a GSO packet (skb_is_gso(skb) is true), checksum offload + * set in skbuff, it should treat the packet as if %CHECKSUM_NONE were set. + * + * .. _crc: + * + * Non-IP checksum (CRC) offloads + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * .. flat-table:: + * :widths: 1 10 + * + * * - %NETIF_F_SCTP_CRC + * - This feature indicates that a device is capable of + * offloading the SCTP CRC in a packet. To perform this offload the stack + * will set csum_start and csum_offset accordingly, set ip_summed to + * %CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication + * in the skbuff that the %CHECKSUM_PARTIAL refers to CRC32c. + * A driver that supports both IP checksum offload and SCTP CRC32c offload + * must verify which offload is configured for a packet by testing the + * value of &sk_buff.csum_not_inet; skb_crc32c_csum_help() is provided to + * resolve %CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1. + * + * * - %NETIF_F_FCOE_CRC + * - This feature indicates that a device is capable of offloading the FCOE + * CRC in a packet. To perform this offload the stack will set ip_summed + * to %CHECKSUM_PARTIAL and set csum_start and csum_offset + * accordingly. Note that there is no indication in the skbuff that the + * %CHECKSUM_PARTIAL refers to an FCOE checksum, so a driver that supports + * both IP checksum offload and FCOE CRC offload must verify which offload + * is configured for a packet, presumably by inspecting packet headers. + * + * Checksumming on output with GSO + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * In the case of a GSO packet (skb_is_gso() is true), checksum offload * is implied by the SKB_GSO_* flags in gso_type. Most obviously, if the - * gso_type is SKB_GSO_TCPV4 or SKB_GSO_TCPV6, TCP checksum offload as + * gso_type is %SKB_GSO_TCPV4 or %SKB_GSO_TCPV6, TCP checksum offload as * part of the GSO operation is implied. If a checksum is being offloaded - * with GSO then ip_summed is CHECKSUM_PARTIAL, and both csum_start and + * with GSO then ip_summed is %CHECKSUM_PARTIAL, and both csum_start and * csum_offset are set to refer to the outermost checksum being offloaded * (two offloaded checksums are possible with UDP encapsulation). */ -- cgit v1.2.3 From f7e0beaf39d3868dc700d4954b26cf8443c5d423 Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Tue, 10 May 2022 13:59:19 -0700 Subject: bpf, x86: Generate trampolines from bpf_tramp_links Replace struct bpf_tramp_progs with struct bpf_tramp_links to collect struct bpf_tramp_link(s) for a trampoline. struct bpf_tramp_link extends bpf_link to act as a linked list node. arch_prepare_bpf_trampoline() accepts a struct bpf_tramp_links to collects all bpf_tramp_link(s) that a trampoline should call. Change BPF trampoline and bpf_struct_ops to pass bpf_tramp_links instead of bpf_tramp_progs. Signed-off-by: Kui-Feng Lee Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220510205923.3206889-2-kuifeng@fb.com --- include/linux/bpf.h | 36 ++++++++++++++++++++++++------------ include/linux/bpf_types.h | 1 + include/uapi/linux/bpf.h | 1 + 3 files changed, 26 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 551b7198ae8a..75e0110a65e1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -723,11 +723,11 @@ struct btf_func_model { /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2 */ -#define BPF_MAX_TRAMP_PROGS 38 +#define BPF_MAX_TRAMP_LINKS 38 -struct bpf_tramp_progs { - struct bpf_prog *progs[BPF_MAX_TRAMP_PROGS]; - int nr_progs; +struct bpf_tramp_links { + struct bpf_tramp_link *links[BPF_MAX_TRAMP_LINKS]; + int nr_links; }; /* Different use cases for BPF trampoline: @@ -753,7 +753,7 @@ struct bpf_tramp_progs { struct bpf_tramp_image; int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end, const struct btf_func_model *m, u32 flags, - struct bpf_tramp_progs *tprogs, + struct bpf_tramp_links *tlinks, void *orig_call); /* these two functions are called from generated trampoline */ u64 notrace __bpf_prog_enter(struct bpf_prog *prog); @@ -852,9 +852,10 @@ static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func( { return bpf_func(ctx, insnsi); } + #ifdef CONFIG_BPF_JIT -int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr); -int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr); +int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); +int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info); void bpf_trampoline_put(struct bpf_trampoline *tr); @@ -905,12 +906,12 @@ int bpf_jit_charge_modmem(u32 size); void bpf_jit_uncharge_modmem(u32 size); bool bpf_prog_has_trampoline(const struct bpf_prog *prog); #else -static inline int bpf_trampoline_link_prog(struct bpf_prog *prog, +static inline int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr) { return -ENOTSUPP; } -static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog, +static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr) { return -ENOTSUPP; @@ -1009,7 +1010,6 @@ struct bpf_prog_aux { bool tail_call_reachable; bool xdp_has_frags; bool use_bpf_prog_pack; - struct hlist_node tramp_hlist; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; /* function name for valid attach_btf_id */ @@ -1096,6 +1096,18 @@ struct bpf_link_ops { struct bpf_link_info *info); }; +struct bpf_tramp_link { + struct bpf_link link; + struct hlist_node tramp_hlist; +}; + +struct bpf_tracing_link { + struct bpf_tramp_link link; + enum bpf_attach_type attach_type; + struct bpf_trampoline *trampoline; + struct bpf_prog *tgt_prog; +}; + struct bpf_link_primer { struct bpf_link *link; struct file *file; @@ -1133,8 +1145,8 @@ bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, void *value); -int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_progs *tprogs, - struct bpf_prog *prog, +int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, + struct bpf_tramp_link *link, const struct btf_func_model *model, void *image, void *image_end); static inline bool bpf_try_module_get(const void *data, struct module *owner) diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 3e24ad0c4b3c..2b9112b80171 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -141,3 +141,4 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp) BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf) #endif BPF_LINK_TYPE(BPF_LINK_TYPE_KPROBE_MULTI, kprobe_multi) +BPF_LINK_TYPE(BPF_LINK_TYPE_STRUCT_OPS, struct_ops) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 95a3d1ff6255..3d032ea1b6a3 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1013,6 +1013,7 @@ enum bpf_link_type { BPF_LINK_TYPE_XDP = 6, BPF_LINK_TYPE_PERF_EVENT = 7, BPF_LINK_TYPE_KPROBE_MULTI = 8, + BPF_LINK_TYPE_STRUCT_OPS = 9, MAX_BPF_LINK_TYPE, }; -- cgit v1.2.3 From e384c7b7b46d0a5f4bf3c554f963e6e9622d0ab1 Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Tue, 10 May 2022 13:59:20 -0700 Subject: bpf, x86: Create bpf_tramp_run_ctx on the caller thread's stack BPF trampolines will create a bpf_tramp_run_ctx, a bpf_run_ctx, on stacks and set/reset the current bpf_run_ctx before/after calling a bpf_prog. Signed-off-by: Kui-Feng Lee Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220510205923.3206889-3-kuifeng@fb.com --- include/linux/bpf.h | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 75e0110a65e1..256fb802e580 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -730,6 +730,8 @@ struct bpf_tramp_links { int nr_links; }; +struct bpf_tramp_run_ctx; + /* Different use cases for BPF trampoline: * 1. replace nop at the function entry (kprobe equivalent) * flags = BPF_TRAMP_F_RESTORE_REGS @@ -756,10 +758,11 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *i struct bpf_tramp_links *tlinks, void *orig_call); /* these two functions are called from generated trampoline */ -u64 notrace __bpf_prog_enter(struct bpf_prog *prog); -void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); -u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog); -void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start); +u64 notrace __bpf_prog_enter(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); +void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx); +u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); +void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr); void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr); @@ -1351,6 +1354,12 @@ struct bpf_trace_run_ctx { u64 bpf_cookie; }; +struct bpf_tramp_run_ctx { + struct bpf_run_ctx run_ctx; + u64 bpf_cookie; + struct bpf_run_ctx *saved_run_ctx; +}; + static inline struct bpf_run_ctx *bpf_set_run_ctx(struct bpf_run_ctx *new_ctx) { struct bpf_run_ctx *old_ctx = NULL; -- cgit v1.2.3 From 66cd9d4ef74ae1ad459e3db3a3280182275c2ce9 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Thu, 28 Apr 2022 12:29:37 +0300 Subject: scsi: target: iscsi: Rename iscsi_cmd to iscsit_cmd The structure iscsi_cmd naming is used by the iSCSI initiator driver. Rename the target cmd to iscsit_cmd to have more readable code. Link: https://lore.kernel.org/r/20220428092939.36768-1-mgurtovoy@nvidia.com Reviewed-by: Mike Christie Signed-off-by: Max Gurtovoy Signed-off-by: Martin K. Petersen --- include/target/iscsi/iscsi_target_core.h | 34 ++++++------ include/target/iscsi/iscsi_transport.h | 92 ++++++++++++++++---------------- 2 files changed, 63 insertions(+), 63 deletions(-) (limited to 'include') diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index adc87de0362b..4f9ef2899488 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -143,7 +143,7 @@ enum tiqn_state_table { TIQN_STATE_SHUTDOWN = 2, }; -/* struct iscsi_cmd->cmd_flags */ +/* struct iscsit_cmd->cmd_flags */ enum cmd_flags_table { ICF_GOT_LAST_DATAOUT = 0x00000001, ICF_GOT_DATACK_SNACK = 0x00000002, @@ -157,7 +157,7 @@ enum cmd_flags_table { ICF_SENDTARGETS_SINGLE = 0x00000200, }; -/* struct iscsi_cmd->i_state */ +/* struct iscsit_cmd->i_state */ enum cmd_i_state_table { ISTATE_NO_STATE = 0, ISTATE_NEW_CMD = 1, @@ -297,7 +297,7 @@ struct iscsi_sess_ops { struct iscsi_queue_req { int state; - struct iscsi_cmd *cmd; + struct iscsit_cmd *cmd; struct list_head qr_list; }; @@ -327,7 +327,7 @@ struct iscsi_ooo_cmdsn { u32 batch_count; u32 cmdsn; u32 exp_cmdsn; - struct iscsi_cmd *cmd; + struct iscsit_cmd *cmd; struct list_head ooo_list; } ____cacheline_aligned; @@ -349,7 +349,7 @@ struct iscsi_r2t { struct list_head r2t_list; } ____cacheline_aligned; -struct iscsi_cmd { +struct iscsit_cmd { enum iscsi_timer_flags_table dataout_timer_flags; /* DataOUT timeout retries */ u8 dataout_timeout_retries; @@ -405,22 +405,22 @@ struct iscsi_cmd { u32 outstanding_r2ts; /* Next R2T Offset when DataSequenceInOrder=Yes */ u32 r2t_offset; - /* Iovec current and orig count for iscsi_cmd->iov_data */ + /* Iovec current and orig count for iscsit_cmd->iov_data */ u32 iov_data_count; u32 orig_iov_data_count; /* Number of miscellaneous iovecs used for IP stack calls */ u32 iov_misc_count; - /* Number of struct iscsi_pdu in struct iscsi_cmd->pdu_list */ + /* Number of struct iscsi_pdu in struct iscsit_cmd->pdu_list */ u32 pdu_count; - /* Next struct iscsi_pdu to send in struct iscsi_cmd->pdu_list */ + /* Next struct iscsi_pdu to send in struct iscsit_cmd->pdu_list */ u32 pdu_send_order; - /* Current struct iscsi_pdu in struct iscsi_cmd->pdu_list */ + /* Current struct iscsi_pdu in struct iscsit_cmd->pdu_list */ u32 pdu_start; - /* Next struct iscsi_seq to send in struct iscsi_cmd->seq_list */ + /* Next struct iscsi_seq to send in struct iscsit_cmd->seq_list */ u32 seq_send_order; - /* Number of struct iscsi_seq in struct iscsi_cmd->seq_list */ + /* Number of struct iscsi_seq in struct iscsit_cmd->seq_list */ u32 seq_count; - /* Current struct iscsi_seq in struct iscsi_cmd->seq_list */ + /* Current struct iscsi_seq in struct iscsit_cmd->seq_list */ u32 seq_no; /* Lowest offset in current DataOUT sequence */ u32 seq_start_offset; @@ -444,12 +444,12 @@ struct iscsi_cmd { enum dma_data_direction data_direction; /* iSCSI PDU Header + CRC */ unsigned char pdu[ISCSI_HDR_LEN + ISCSI_CRC_LEN]; - /* Number of times struct iscsi_cmd is present in immediate queue */ + /* Number of times struct iscsit_cmd is present in immediate queue */ atomic_t immed_queue_count; atomic_t response_queue_count; spinlock_t datain_lock; spinlock_t dataout_timeout_lock; - /* spinlock for protecting struct iscsi_cmd->i_state */ + /* spinlock for protecting struct iscsit_cmd->i_state */ spinlock_t istate_lock; /* spinlock for adding within command recovery entries */ spinlock_t error_lock; @@ -503,7 +503,7 @@ struct iscsi_cmd { struct iscsi_tmr_req { bool task_reassign:1; u32 exp_data_sn; - struct iscsi_cmd *ref_cmd; + struct iscsit_cmd *ref_cmd; struct iscsi_conn_recovery *conn_recovery; struct se_tmr_req *se_tmr_req; }; @@ -583,7 +583,7 @@ struct iscsi_conn { cpumask_var_t allowed_cpumask; unsigned int conn_rx_reset_cpumask:1; unsigned int conn_tx_reset_cpumask:1; - /* list_head of struct iscsi_cmd for this connection */ + /* list_head of struct iscsit_cmd for this connection */ struct list_head conn_cmd_list; struct list_head immed_queue_list; struct list_head response_queue_list; @@ -898,7 +898,7 @@ static inline u32 session_get_next_ttt(struct iscsi_session *session) return ttt; } -extern struct iscsi_cmd *iscsit_find_cmd_from_itt(struct iscsi_conn *, itt_t); +extern struct iscsit_cmd *iscsit_find_cmd_from_itt(struct iscsi_conn *, itt_t); extern void iscsit_thread_check_cpumask(struct iscsi_conn *conn, struct task_struct *p, diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h index b8feba7ffebc..645de3542022 100644 --- a/include/target/iscsi/iscsi_transport.h +++ b/include/target/iscsi/iscsi_transport.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#include "iscsi_target_core.h" /* struct iscsi_cmd */ +#include "iscsi_target_core.h" /* struct iscsit_cmd */ struct sockaddr_storage; @@ -18,23 +18,23 @@ struct iscsit_transport { void (*iscsit_free_conn)(struct iscsi_conn *); int (*iscsit_get_login_rx)(struct iscsi_conn *, struct iscsi_login *); int (*iscsit_put_login_tx)(struct iscsi_conn *, struct iscsi_login *, u32); - int (*iscsit_immediate_queue)(struct iscsi_conn *, struct iscsi_cmd *, int); - int (*iscsit_response_queue)(struct iscsi_conn *, struct iscsi_cmd *, int); - int (*iscsit_get_dataout)(struct iscsi_conn *, struct iscsi_cmd *, bool); - int (*iscsit_queue_data_in)(struct iscsi_conn *, struct iscsi_cmd *); - int (*iscsit_queue_status)(struct iscsi_conn *, struct iscsi_cmd *); - void (*iscsit_aborted_task)(struct iscsi_conn *, struct iscsi_cmd *); - int (*iscsit_xmit_pdu)(struct iscsi_conn *, struct iscsi_cmd *, + int (*iscsit_immediate_queue)(struct iscsi_conn *, struct iscsit_cmd *, int); + int (*iscsit_response_queue)(struct iscsi_conn *, struct iscsit_cmd *, int); + int (*iscsit_get_dataout)(struct iscsi_conn *, struct iscsit_cmd *, bool); + int (*iscsit_queue_data_in)(struct iscsi_conn *, struct iscsit_cmd *); + int (*iscsit_queue_status)(struct iscsi_conn *, struct iscsit_cmd *); + void (*iscsit_aborted_task)(struct iscsi_conn *, struct iscsit_cmd *); + int (*iscsit_xmit_pdu)(struct iscsi_conn *, struct iscsit_cmd *, struct iscsi_datain_req *, const void *, u32); - void (*iscsit_unmap_cmd)(struct iscsi_conn *, struct iscsi_cmd *); + void (*iscsit_unmap_cmd)(struct iscsi_conn *, struct iscsit_cmd *); void (*iscsit_get_rx_pdu)(struct iscsi_conn *); int (*iscsit_validate_params)(struct iscsi_conn *); - void (*iscsit_get_r2t_ttt)(struct iscsi_conn *, struct iscsi_cmd *, + void (*iscsit_get_r2t_ttt)(struct iscsi_conn *, struct iscsit_cmd *, struct iscsi_r2t *); enum target_prot_op (*iscsit_get_sup_prot_ops)(struct iscsi_conn *); }; -static inline void *iscsit_priv_cmd(struct iscsi_cmd *cmd) +static inline void *iscsit_priv_cmd(struct iscsit_cmd *cmd) { return (void *)(cmd + 1); } @@ -51,61 +51,61 @@ extern void iscsit_put_transport(struct iscsit_transport *); /* * From iscsi_target.c */ -extern int iscsit_setup_scsi_cmd(struct iscsi_conn *, struct iscsi_cmd *, +extern int iscsit_setup_scsi_cmd(struct iscsi_conn *, struct iscsit_cmd *, unsigned char *); -extern void iscsit_set_unsolicited_dataout(struct iscsi_cmd *); -extern int iscsit_process_scsi_cmd(struct iscsi_conn *, struct iscsi_cmd *, +extern void iscsit_set_unsolicited_dataout(struct iscsit_cmd *); +extern int iscsit_process_scsi_cmd(struct iscsi_conn *, struct iscsit_cmd *, struct iscsi_scsi_req *); extern int __iscsit_check_dataout_hdr(struct iscsi_conn *, void *, - struct iscsi_cmd *, u32, bool *); + struct iscsit_cmd *, u32, bool *); extern int iscsit_check_dataout_hdr(struct iscsi_conn *conn, void *buf, - struct iscsi_cmd **out_cmd); -extern int iscsit_check_dataout_payload(struct iscsi_cmd *, struct iscsi_data *, + struct iscsit_cmd **out_cmd); +extern int iscsit_check_dataout_payload(struct iscsit_cmd *, struct iscsi_data *, bool); -extern int iscsit_setup_nop_out(struct iscsi_conn *, struct iscsi_cmd *, +extern int iscsit_setup_nop_out(struct iscsi_conn *, struct iscsit_cmd *, struct iscsi_nopout *); -extern int iscsit_process_nop_out(struct iscsi_conn *, struct iscsi_cmd *, +extern int iscsit_process_nop_out(struct iscsi_conn *, struct iscsit_cmd *, struct iscsi_nopout *); -extern int iscsit_handle_logout_cmd(struct iscsi_conn *, struct iscsi_cmd *, +extern int iscsit_handle_logout_cmd(struct iscsi_conn *, struct iscsit_cmd *, unsigned char *); -extern int iscsit_handle_task_mgt_cmd(struct iscsi_conn *, struct iscsi_cmd *, +extern int iscsit_handle_task_mgt_cmd(struct iscsi_conn *, struct iscsit_cmd *, unsigned char *); -extern int iscsit_setup_text_cmd(struct iscsi_conn *, struct iscsi_cmd *, +extern int iscsit_setup_text_cmd(struct iscsi_conn *, struct iscsit_cmd *, struct iscsi_text *); -extern int iscsit_process_text_cmd(struct iscsi_conn *, struct iscsi_cmd *, +extern int iscsit_process_text_cmd(struct iscsi_conn *, struct iscsit_cmd *, struct iscsi_text *); -extern void iscsit_build_rsp_pdu(struct iscsi_cmd *, struct iscsi_conn *, +extern void iscsit_build_rsp_pdu(struct iscsit_cmd *, struct iscsi_conn *, bool, struct iscsi_scsi_rsp *); -extern void iscsit_build_nopin_rsp(struct iscsi_cmd *, struct iscsi_conn *, +extern void iscsit_build_nopin_rsp(struct iscsit_cmd *, struct iscsi_conn *, struct iscsi_nopin *, bool); -extern void iscsit_build_task_mgt_rsp(struct iscsi_cmd *, struct iscsi_conn *, +extern void iscsit_build_task_mgt_rsp(struct iscsit_cmd *, struct iscsi_conn *, struct iscsi_tm_rsp *); -extern int iscsit_build_text_rsp(struct iscsi_cmd *, struct iscsi_conn *, +extern int iscsit_build_text_rsp(struct iscsit_cmd *, struct iscsi_conn *, struct iscsi_text_rsp *, enum iscsit_transport_type); -extern void iscsit_build_reject(struct iscsi_cmd *, struct iscsi_conn *, +extern void iscsit_build_reject(struct iscsit_cmd *, struct iscsi_conn *, struct iscsi_reject *); -extern int iscsit_build_logout_rsp(struct iscsi_cmd *, struct iscsi_conn *, +extern int iscsit_build_logout_rsp(struct iscsit_cmd *, struct iscsi_conn *, struct iscsi_logout_rsp *); -extern int iscsit_logout_post_handler(struct iscsi_cmd *, struct iscsi_conn *); -extern int iscsit_queue_rsp(struct iscsi_conn *, struct iscsi_cmd *); -extern void iscsit_aborted_task(struct iscsi_conn *, struct iscsi_cmd *); +extern int iscsit_logout_post_handler(struct iscsit_cmd *, struct iscsi_conn *); +extern int iscsit_queue_rsp(struct iscsi_conn *, struct iscsit_cmd *); +extern void iscsit_aborted_task(struct iscsi_conn *, struct iscsit_cmd *); extern int iscsit_add_reject(struct iscsi_conn *, u8, unsigned char *); -extern int iscsit_reject_cmd(struct iscsi_cmd *, u8, unsigned char *); +extern int iscsit_reject_cmd(struct iscsit_cmd *, u8, unsigned char *); extern int iscsit_handle_snack(struct iscsi_conn *, unsigned char *); -extern void iscsit_build_datain_pdu(struct iscsi_cmd *, struct iscsi_conn *, +extern void iscsit_build_datain_pdu(struct iscsit_cmd *, struct iscsi_conn *, struct iscsi_datain *, struct iscsi_data_rsp *, bool); -extern int iscsit_build_r2ts_for_cmd(struct iscsi_conn *, struct iscsi_cmd *, +extern int iscsit_build_r2ts_for_cmd(struct iscsi_conn *, struct iscsit_cmd *, bool); -extern int iscsit_immediate_queue(struct iscsi_conn *, struct iscsi_cmd *, int); -extern int iscsit_response_queue(struct iscsi_conn *, struct iscsi_cmd *, int); +extern int iscsit_immediate_queue(struct iscsi_conn *, struct iscsit_cmd *, int); +extern int iscsit_response_queue(struct iscsi_conn *, struct iscsit_cmd *, int); /* * From iscsi_target_device.c */ -extern void iscsit_increment_maxcmdsn(struct iscsi_cmd *, struct iscsi_session *); +extern void iscsit_increment_maxcmdsn(struct iscsit_cmd *, struct iscsi_session *); /* * From iscsi_target_erl0.c */ @@ -113,24 +113,24 @@ extern void iscsit_cause_connection_reinstatement(struct iscsi_conn *, int); /* * From iscsi_target_erl1.c */ -extern void iscsit_stop_dataout_timer(struct iscsi_cmd *); +extern void iscsit_stop_dataout_timer(struct iscsit_cmd *); /* * From iscsi_target_tmr.c */ -extern int iscsit_tmr_post_handler(struct iscsi_cmd *, struct iscsi_conn *); +extern int iscsit_tmr_post_handler(struct iscsit_cmd *, struct iscsi_conn *); /* * From iscsi_target_util.c */ -extern struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *, int); -extern int iscsit_sequence_cmd(struct iscsi_conn *, struct iscsi_cmd *, +extern struct iscsit_cmd *iscsit_allocate_cmd(struct iscsi_conn *, int); +extern int iscsit_sequence_cmd(struct iscsi_conn *, struct iscsit_cmd *, unsigned char *, __be32); -extern void iscsit_release_cmd(struct iscsi_cmd *); -extern void iscsit_free_cmd(struct iscsi_cmd *, bool); -extern void iscsit_add_cmd_to_immediate_queue(struct iscsi_cmd *, +extern void iscsit_release_cmd(struct iscsit_cmd *); +extern void iscsit_free_cmd(struct iscsit_cmd *, bool); +extern void iscsit_add_cmd_to_immediate_queue(struct iscsit_cmd *, struct iscsi_conn *, u8); -extern struct iscsi_cmd * +extern struct iscsit_cmd * iscsit_find_cmd_from_itt_or_dump(struct iscsi_conn *conn, itt_t init_task_tag, u32 length); -- cgit v1.2.3 From be36d683fc29e74bbd29347717be72beb6a74219 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Thu, 28 Apr 2022 12:29:38 +0300 Subject: scsi: target: iscsi: Rename iscsi_conn to iscsit_conn The structure iscsi_conn naming is used by the iSCSI initiator driver. Rename the target conn to iscsit_conn to have more readable code. Link: https://lore.kernel.org/r/20220428092939.36768-2-mgurtovoy@nvidia.com Reviewed-by: Mike Christie Signed-off-by: Max Gurtovoy Signed-off-by: Martin K. Petersen --- include/target/iscsi/iscsi_target_core.h | 10 ++-- include/target/iscsi/iscsi_transport.h | 100 +++++++++++++++---------------- 2 files changed, 55 insertions(+), 55 deletions(-) (limited to 'include') diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index 4f9ef2899488..76581e0f3d98 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -478,7 +478,7 @@ struct iscsit_cmd { /* TMR Request when iscsi_opcode == ISCSI_OP_SCSI_TMFUNC */ struct iscsi_tmr_req *tmr_req; /* Connection this command is alligient to */ - struct iscsi_conn *conn; + struct iscsit_conn *conn; /* Pointer to connection recovery entry */ struct iscsi_conn_recovery *cr; /* Session the command is part of, used for connection recovery */ @@ -508,7 +508,7 @@ struct iscsi_tmr_req { struct se_tmr_req *se_tmr_req; }; -struct iscsi_conn { +struct iscsit_conn { wait_queue_head_t queues_wq; /* Authentication Successful for this connection */ u8 auth_complete; @@ -710,7 +710,7 @@ struct iscsi_login { char rsp[ISCSI_HDR_LEN]; char *req_buf; char *rsp_buf; - struct iscsi_conn *conn; + struct iscsit_conn *conn; struct iscsi_np *np; } ____cacheline_aligned; @@ -898,9 +898,9 @@ static inline u32 session_get_next_ttt(struct iscsi_session *session) return ttt; } -extern struct iscsit_cmd *iscsit_find_cmd_from_itt(struct iscsi_conn *, itt_t); +extern struct iscsit_cmd *iscsit_find_cmd_from_itt(struct iscsit_conn *, itt_t); -extern void iscsit_thread_check_cpumask(struct iscsi_conn *conn, +extern void iscsit_thread_check_cpumask(struct iscsit_conn *conn, struct task_struct *p, int mode); diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h index 645de3542022..2ab26bb6f808 100644 --- a/include/target/iscsi/iscsi_transport.h +++ b/include/target/iscsi/iscsi_transport.h @@ -12,26 +12,26 @@ struct iscsit_transport { struct module *owner; struct list_head t_node; int (*iscsit_setup_np)(struct iscsi_np *, struct sockaddr_storage *); - int (*iscsit_accept_np)(struct iscsi_np *, struct iscsi_conn *); + int (*iscsit_accept_np)(struct iscsi_np *, struct iscsit_conn *); void (*iscsit_free_np)(struct iscsi_np *); - void (*iscsit_wait_conn)(struct iscsi_conn *); - void (*iscsit_free_conn)(struct iscsi_conn *); - int (*iscsit_get_login_rx)(struct iscsi_conn *, struct iscsi_login *); - int (*iscsit_put_login_tx)(struct iscsi_conn *, struct iscsi_login *, u32); - int (*iscsit_immediate_queue)(struct iscsi_conn *, struct iscsit_cmd *, int); - int (*iscsit_response_queue)(struct iscsi_conn *, struct iscsit_cmd *, int); - int (*iscsit_get_dataout)(struct iscsi_conn *, struct iscsit_cmd *, bool); - int (*iscsit_queue_data_in)(struct iscsi_conn *, struct iscsit_cmd *); - int (*iscsit_queue_status)(struct iscsi_conn *, struct iscsit_cmd *); - void (*iscsit_aborted_task)(struct iscsi_conn *, struct iscsit_cmd *); - int (*iscsit_xmit_pdu)(struct iscsi_conn *, struct iscsit_cmd *, + void (*iscsit_wait_conn)(struct iscsit_conn *); + void (*iscsit_free_conn)(struct iscsit_conn *); + int (*iscsit_get_login_rx)(struct iscsit_conn *, struct iscsi_login *); + int (*iscsit_put_login_tx)(struct iscsit_conn *, struct iscsi_login *, u32); + int (*iscsit_immediate_queue)(struct iscsit_conn *, struct iscsit_cmd *, int); + int (*iscsit_response_queue)(struct iscsit_conn *, struct iscsit_cmd *, int); + int (*iscsit_get_dataout)(struct iscsit_conn *, struct iscsit_cmd *, bool); + int (*iscsit_queue_data_in)(struct iscsit_conn *, struct iscsit_cmd *); + int (*iscsit_queue_status)(struct iscsit_conn *, struct iscsit_cmd *); + void (*iscsit_aborted_task)(struct iscsit_conn *, struct iscsit_cmd *); + int (*iscsit_xmit_pdu)(struct iscsit_conn *, struct iscsit_cmd *, struct iscsi_datain_req *, const void *, u32); - void (*iscsit_unmap_cmd)(struct iscsi_conn *, struct iscsit_cmd *); - void (*iscsit_get_rx_pdu)(struct iscsi_conn *); - int (*iscsit_validate_params)(struct iscsi_conn *); - void (*iscsit_get_r2t_ttt)(struct iscsi_conn *, struct iscsit_cmd *, + void (*iscsit_unmap_cmd)(struct iscsit_conn *, struct iscsit_cmd *); + void (*iscsit_get_rx_pdu)(struct iscsit_conn *); + int (*iscsit_validate_params)(struct iscsit_conn *); + void (*iscsit_get_r2t_ttt)(struct iscsit_conn *, struct iscsit_cmd *, struct iscsi_r2t *); - enum target_prot_op (*iscsit_get_sup_prot_ops)(struct iscsi_conn *); + enum target_prot_op (*iscsit_get_sup_prot_ops)(struct iscsit_conn *); }; static inline void *iscsit_priv_cmd(struct iscsit_cmd *cmd) @@ -51,57 +51,57 @@ extern void iscsit_put_transport(struct iscsit_transport *); /* * From iscsi_target.c */ -extern int iscsit_setup_scsi_cmd(struct iscsi_conn *, struct iscsit_cmd *, +extern int iscsit_setup_scsi_cmd(struct iscsit_conn *, struct iscsit_cmd *, unsigned char *); extern void iscsit_set_unsolicited_dataout(struct iscsit_cmd *); -extern int iscsit_process_scsi_cmd(struct iscsi_conn *, struct iscsit_cmd *, +extern int iscsit_process_scsi_cmd(struct iscsit_conn *, struct iscsit_cmd *, struct iscsi_scsi_req *); extern int -__iscsit_check_dataout_hdr(struct iscsi_conn *, void *, +__iscsit_check_dataout_hdr(struct iscsit_conn *, void *, struct iscsit_cmd *, u32, bool *); extern int -iscsit_check_dataout_hdr(struct iscsi_conn *conn, void *buf, +iscsit_check_dataout_hdr(struct iscsit_conn *conn, void *buf, struct iscsit_cmd **out_cmd); extern int iscsit_check_dataout_payload(struct iscsit_cmd *, struct iscsi_data *, bool); -extern int iscsit_setup_nop_out(struct iscsi_conn *, struct iscsit_cmd *, +extern int iscsit_setup_nop_out(struct iscsit_conn *, struct iscsit_cmd *, struct iscsi_nopout *); -extern int iscsit_process_nop_out(struct iscsi_conn *, struct iscsit_cmd *, +extern int iscsit_process_nop_out(struct iscsit_conn *, struct iscsit_cmd *, struct iscsi_nopout *); -extern int iscsit_handle_logout_cmd(struct iscsi_conn *, struct iscsit_cmd *, +extern int iscsit_handle_logout_cmd(struct iscsit_conn *, struct iscsit_cmd *, unsigned char *); -extern int iscsit_handle_task_mgt_cmd(struct iscsi_conn *, struct iscsit_cmd *, +extern int iscsit_handle_task_mgt_cmd(struct iscsit_conn *, struct iscsit_cmd *, unsigned char *); -extern int iscsit_setup_text_cmd(struct iscsi_conn *, struct iscsit_cmd *, +extern int iscsit_setup_text_cmd(struct iscsit_conn *, struct iscsit_cmd *, struct iscsi_text *); -extern int iscsit_process_text_cmd(struct iscsi_conn *, struct iscsit_cmd *, +extern int iscsit_process_text_cmd(struct iscsit_conn *, struct iscsit_cmd *, struct iscsi_text *); -extern void iscsit_build_rsp_pdu(struct iscsit_cmd *, struct iscsi_conn *, +extern void iscsit_build_rsp_pdu(struct iscsit_cmd *, struct iscsit_conn *, bool, struct iscsi_scsi_rsp *); -extern void iscsit_build_nopin_rsp(struct iscsit_cmd *, struct iscsi_conn *, +extern void iscsit_build_nopin_rsp(struct iscsit_cmd *, struct iscsit_conn *, struct iscsi_nopin *, bool); -extern void iscsit_build_task_mgt_rsp(struct iscsit_cmd *, struct iscsi_conn *, +extern void iscsit_build_task_mgt_rsp(struct iscsit_cmd *, struct iscsit_conn *, struct iscsi_tm_rsp *); -extern int iscsit_build_text_rsp(struct iscsit_cmd *, struct iscsi_conn *, +extern int iscsit_build_text_rsp(struct iscsit_cmd *, struct iscsit_conn *, struct iscsi_text_rsp *, enum iscsit_transport_type); -extern void iscsit_build_reject(struct iscsit_cmd *, struct iscsi_conn *, +extern void iscsit_build_reject(struct iscsit_cmd *, struct iscsit_conn *, struct iscsi_reject *); -extern int iscsit_build_logout_rsp(struct iscsit_cmd *, struct iscsi_conn *, +extern int iscsit_build_logout_rsp(struct iscsit_cmd *, struct iscsit_conn *, struct iscsi_logout_rsp *); -extern int iscsit_logout_post_handler(struct iscsit_cmd *, struct iscsi_conn *); -extern int iscsit_queue_rsp(struct iscsi_conn *, struct iscsit_cmd *); -extern void iscsit_aborted_task(struct iscsi_conn *, struct iscsit_cmd *); -extern int iscsit_add_reject(struct iscsi_conn *, u8, unsigned char *); +extern int iscsit_logout_post_handler(struct iscsit_cmd *, struct iscsit_conn *); +extern int iscsit_queue_rsp(struct iscsit_conn *, struct iscsit_cmd *); +extern void iscsit_aborted_task(struct iscsit_conn *, struct iscsit_cmd *); +extern int iscsit_add_reject(struct iscsit_conn *, u8, unsigned char *); extern int iscsit_reject_cmd(struct iscsit_cmd *, u8, unsigned char *); -extern int iscsit_handle_snack(struct iscsi_conn *, unsigned char *); -extern void iscsit_build_datain_pdu(struct iscsit_cmd *, struct iscsi_conn *, +extern int iscsit_handle_snack(struct iscsit_conn *, unsigned char *); +extern void iscsit_build_datain_pdu(struct iscsit_cmd *, struct iscsit_conn *, struct iscsi_datain *, struct iscsi_data_rsp *, bool); -extern int iscsit_build_r2ts_for_cmd(struct iscsi_conn *, struct iscsit_cmd *, +extern int iscsit_build_r2ts_for_cmd(struct iscsit_conn *, struct iscsit_cmd *, bool); -extern int iscsit_immediate_queue(struct iscsi_conn *, struct iscsit_cmd *, int); -extern int iscsit_response_queue(struct iscsi_conn *, struct iscsit_cmd *, int); +extern int iscsit_immediate_queue(struct iscsit_conn *, struct iscsit_cmd *, int); +extern int iscsit_response_queue(struct iscsit_conn *, struct iscsit_cmd *, int); /* * From iscsi_target_device.c */ @@ -109,7 +109,7 @@ extern void iscsit_increment_maxcmdsn(struct iscsit_cmd *, struct iscsi_session /* * From iscsi_target_erl0.c */ -extern void iscsit_cause_connection_reinstatement(struct iscsi_conn *, int); +extern void iscsit_cause_connection_reinstatement(struct iscsit_conn *, int); /* * From iscsi_target_erl1.c */ @@ -118,33 +118,33 @@ extern void iscsit_stop_dataout_timer(struct iscsit_cmd *); /* * From iscsi_target_tmr.c */ -extern int iscsit_tmr_post_handler(struct iscsit_cmd *, struct iscsi_conn *); +extern int iscsit_tmr_post_handler(struct iscsit_cmd *, struct iscsit_conn *); /* * From iscsi_target_util.c */ -extern struct iscsit_cmd *iscsit_allocate_cmd(struct iscsi_conn *, int); -extern int iscsit_sequence_cmd(struct iscsi_conn *, struct iscsit_cmd *, +extern struct iscsit_cmd *iscsit_allocate_cmd(struct iscsit_conn *, int); +extern int iscsit_sequence_cmd(struct iscsit_conn *, struct iscsit_cmd *, unsigned char *, __be32); extern void iscsit_release_cmd(struct iscsit_cmd *); extern void iscsit_free_cmd(struct iscsit_cmd *, bool); extern void iscsit_add_cmd_to_immediate_queue(struct iscsit_cmd *, - struct iscsi_conn *, u8); + struct iscsit_conn *, u8); extern struct iscsit_cmd * -iscsit_find_cmd_from_itt_or_dump(struct iscsi_conn *conn, +iscsit_find_cmd_from_itt_or_dump(struct iscsit_conn *conn, itt_t init_task_tag, u32 length); /* * From iscsi_target_nego.c */ -extern int iscsi_target_check_login_request(struct iscsi_conn *, +extern int iscsi_target_check_login_request(struct iscsit_conn *, struct iscsi_login *); /* * From iscsi_target_login.c */ extern __printf(2, 3) int iscsi_change_param_sprintf( - struct iscsi_conn *, const char *, ...); + struct iscsit_conn *, const char *, ...); /* * From iscsi_target_parameters.c -- cgit v1.2.3 From 0873fe44e780eb8ff7932aed347de8dd4103cea7 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Thu, 28 Apr 2022 12:29:39 +0300 Subject: scsi: target: iscsi: Rename iscsi_session to iscsit_session The structure iscsi_session naming is used by the iSCSI initiator driver. Rename the target session to iscsit_session to have more readable code. Link: https://lore.kernel.org/r/20220428092939.36768-3-mgurtovoy@nvidia.com Reviewed-by: Mike Christie Signed-off-by: Max Gurtovoy Signed-off-by: Martin K. Petersen --- include/target/iscsi/iscsi_target_core.h | 10 +++++----- include/target/iscsi/iscsi_transport.h | 2 +- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index 76581e0f3d98..8e68ace428d9 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -482,7 +482,7 @@ struct iscsit_cmd { /* Pointer to connection recovery entry */ struct iscsi_conn_recovery *cr; /* Session the command is part of, used for connection recovery */ - struct iscsi_session *sess; + struct iscsit_session *sess; /* list_head for connection list */ struct list_head i_conn_node; /* The TCM I/O descriptor that is accessed via container_of() */ @@ -598,7 +598,7 @@ struct iscsit_conn { struct iscsi_portal_group *tpg; struct iscsi_tpg_np *tpg_np; /* Pointer to parent session */ - struct iscsi_session *sess; + struct iscsit_session *sess; int bitmap_id; int rx_thread_active; struct task_struct *rx_thread; @@ -618,11 +618,11 @@ struct iscsi_conn_recovery { struct list_head conn_recovery_cmd_list; spinlock_t conn_recovery_cmd_lock; struct timer_list time2retain_timer; - struct iscsi_session *sess; + struct iscsit_session *sess; struct list_head cr_list; } ____cacheline_aligned; -struct iscsi_session { +struct iscsit_session { u8 initiator_vendor; u8 isid[6]; enum iscsi_timer_flags_table time2retain_timer_flags; @@ -885,7 +885,7 @@ struct iscsit_global { struct iscsi_portal_group *discovery_tpg; }; -static inline u32 session_get_next_ttt(struct iscsi_session *session) +static inline u32 session_get_next_ttt(struct iscsit_session *session) { u32 ttt; diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h index 2ab26bb6f808..42cfe02ea909 100644 --- a/include/target/iscsi/iscsi_transport.h +++ b/include/target/iscsi/iscsi_transport.h @@ -105,7 +105,7 @@ extern int iscsit_response_queue(struct iscsit_conn *, struct iscsit_cmd *, int) /* * From iscsi_target_device.c */ -extern void iscsit_increment_maxcmdsn(struct iscsit_cmd *, struct iscsi_session *); +extern void iscsit_increment_maxcmdsn(struct iscsit_cmd *, struct iscsit_session *); /* * From iscsi_target_erl0.c */ -- cgit v1.2.3 From 2fcc82411e74e5e6aba336561cf56fb899bfae4e Mon Sep 17 00:00:00 2001 From: Kui-Feng Lee Date: Tue, 10 May 2022 13:59:21 -0700 Subject: bpf, x86: Attach a cookie to fentry/fexit/fmod_ret/lsm. Pass a cookie along with BPF_LINK_CREATE requests. Add a bpf_cookie field to struct bpf_tracing_link to attach a cookie. The cookie of a bpf_tracing_link is available by calling bpf_get_attach_cookie when running the BPF program of the attached link. The value of a cookie will be set at bpf_tramp_run_ctx by the trampoline of the link. Signed-off-by: Kui-Feng Lee Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220510205923.3206889-4-kuifeng@fb.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 9 +++++++++ 2 files changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 256fb802e580..aba7ded56436 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1102,6 +1102,7 @@ struct bpf_link_ops { struct bpf_tramp_link { struct bpf_link link; struct hlist_node tramp_hlist; + u64 cookie; }; struct bpf_tracing_link { diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3d032ea1b6a3..bc7f89948f54 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1490,6 +1490,15 @@ union bpf_attr { __aligned_u64 addrs; __aligned_u64 cookies; } kprobe_multi; + struct { + /* this is overlaid with the target_btf_id above. */ + __u32 target_btf_id; + /* black box user-provided value passed through + * to BPF program at the execution time and + * accessible through bpf_get_attach_cookie() BPF helper + */ + __u64 cookie; + } tracing; }; } link_create; -- cgit v1.2.3 From 5b87be9e4978fe507c7e14c0bdff147d10d39aec Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 9 May 2022 20:57:37 -0700 Subject: net: add include/net/net_debug.h Remove from include/linux/netdevice.h helpers that send debug/info/warnings to syslog. We plan adding more helpers in following patches. v2: added two includes, and 'struct net_device' forward declaration to avoid compile errors (kernel bots) Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 141 +------------------------------------------ include/net/net_debug.h | 151 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 152 insertions(+), 140 deletions(-) create mode 100644 include/net/net_debug.h (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 51fe143091cf..536321691c72 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -50,6 +50,7 @@ #include #include #include +#include struct netpoll_info; struct device; @@ -5071,81 +5072,9 @@ static inline const char *netdev_reg_state(const struct net_device *dev) return " (unknown)"; } -__printf(3, 4) __cold -void netdev_printk(const char *level, const struct net_device *dev, - const char *format, ...); -__printf(2, 3) __cold -void netdev_emerg(const struct net_device *dev, const char *format, ...); -__printf(2, 3) __cold -void netdev_alert(const struct net_device *dev, const char *format, ...); -__printf(2, 3) __cold -void netdev_crit(const struct net_device *dev, const char *format, ...); -__printf(2, 3) __cold -void netdev_err(const struct net_device *dev, const char *format, ...); -__printf(2, 3) __cold -void netdev_warn(const struct net_device *dev, const char *format, ...); -__printf(2, 3) __cold -void netdev_notice(const struct net_device *dev, const char *format, ...); -__printf(2, 3) __cold -void netdev_info(const struct net_device *dev, const char *format, ...); - -#define netdev_level_once(level, dev, fmt, ...) \ -do { \ - static bool __section(".data.once") __print_once; \ - \ - if (!__print_once) { \ - __print_once = true; \ - netdev_printk(level, dev, fmt, ##__VA_ARGS__); \ - } \ -} while (0) - -#define netdev_emerg_once(dev, fmt, ...) \ - netdev_level_once(KERN_EMERG, dev, fmt, ##__VA_ARGS__) -#define netdev_alert_once(dev, fmt, ...) \ - netdev_level_once(KERN_ALERT, dev, fmt, ##__VA_ARGS__) -#define netdev_crit_once(dev, fmt, ...) \ - netdev_level_once(KERN_CRIT, dev, fmt, ##__VA_ARGS__) -#define netdev_err_once(dev, fmt, ...) \ - netdev_level_once(KERN_ERR, dev, fmt, ##__VA_ARGS__) -#define netdev_warn_once(dev, fmt, ...) \ - netdev_level_once(KERN_WARNING, dev, fmt, ##__VA_ARGS__) -#define netdev_notice_once(dev, fmt, ...) \ - netdev_level_once(KERN_NOTICE, dev, fmt, ##__VA_ARGS__) -#define netdev_info_once(dev, fmt, ...) \ - netdev_level_once(KERN_INFO, dev, fmt, ##__VA_ARGS__) - #define MODULE_ALIAS_NETDEV(device) \ MODULE_ALIAS("netdev-" device) -#if defined(CONFIG_DYNAMIC_DEBUG) || \ - (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) -#define netdev_dbg(__dev, format, args...) \ -do { \ - dynamic_netdev_dbg(__dev, format, ##args); \ -} while (0) -#elif defined(DEBUG) -#define netdev_dbg(__dev, format, args...) \ - netdev_printk(KERN_DEBUG, __dev, format, ##args) -#else -#define netdev_dbg(__dev, format, args...) \ -({ \ - if (0) \ - netdev_printk(KERN_DEBUG, __dev, format, ##args); \ -}) -#endif - -#if defined(VERBOSE_DEBUG) -#define netdev_vdbg netdev_dbg -#else - -#define netdev_vdbg(dev, format, args...) \ -({ \ - if (0) \ - netdev_printk(KERN_DEBUG, dev, format, ##args); \ - 0; \ -}) -#endif - /* * netdev_WARN() acts like dev_printk(), but with the key difference * of using a WARN/WARN_ON to get the message out, including the @@ -5159,74 +5088,6 @@ do { \ WARN_ONCE(1, "netdevice: %s%s: " format, netdev_name(dev), \ netdev_reg_state(dev), ##args) -/* netif printk helpers, similar to netdev_printk */ - -#define netif_printk(priv, type, level, dev, fmt, args...) \ -do { \ - if (netif_msg_##type(priv)) \ - netdev_printk(level, (dev), fmt, ##args); \ -} while (0) - -#define netif_level(level, priv, type, dev, fmt, args...) \ -do { \ - if (netif_msg_##type(priv)) \ - netdev_##level(dev, fmt, ##args); \ -} while (0) - -#define netif_emerg(priv, type, dev, fmt, args...) \ - netif_level(emerg, priv, type, dev, fmt, ##args) -#define netif_alert(priv, type, dev, fmt, args...) \ - netif_level(alert, priv, type, dev, fmt, ##args) -#define netif_crit(priv, type, dev, fmt, args...) \ - netif_level(crit, priv, type, dev, fmt, ##args) -#define netif_err(priv, type, dev, fmt, args...) \ - netif_level(err, priv, type, dev, fmt, ##args) -#define netif_warn(priv, type, dev, fmt, args...) \ - netif_level(warn, priv, type, dev, fmt, ##args) -#define netif_notice(priv, type, dev, fmt, args...) \ - netif_level(notice, priv, type, dev, fmt, ##args) -#define netif_info(priv, type, dev, fmt, args...) \ - netif_level(info, priv, type, dev, fmt, ##args) - -#if defined(CONFIG_DYNAMIC_DEBUG) || \ - (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) -#define netif_dbg(priv, type, netdev, format, args...) \ -do { \ - if (netif_msg_##type(priv)) \ - dynamic_netdev_dbg(netdev, format, ##args); \ -} while (0) -#elif defined(DEBUG) -#define netif_dbg(priv, type, dev, format, args...) \ - netif_printk(priv, type, KERN_DEBUG, dev, format, ##args) -#else -#define netif_dbg(priv, type, dev, format, args...) \ -({ \ - if (0) \ - netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \ - 0; \ -}) -#endif - -/* if @cond then downgrade to debug, else print at @level */ -#define netif_cond_dbg(priv, type, netdev, cond, level, fmt, args...) \ - do { \ - if (cond) \ - netif_dbg(priv, type, netdev, fmt, ##args); \ - else \ - netif_ ## level(priv, type, netdev, fmt, ##args); \ - } while (0) - -#if defined(VERBOSE_DEBUG) -#define netif_vdbg netif_dbg -#else -#define netif_vdbg(priv, type, dev, format, args...) \ -({ \ - if (0) \ - netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \ - 0; \ -}) -#endif - /* * The list of packet types we will receive (as opposed to discard) * and the routines to invoke. diff --git a/include/net/net_debug.h b/include/net/net_debug.h new file mode 100644 index 000000000000..19cd2700c20e --- /dev/null +++ b/include/net/net_debug.h @@ -0,0 +1,151 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_NET_DEBUG_H +#define _LINUX_NET_DEBUG_H + +#include +#include + +struct net_device; + +__printf(3, 4) __cold +void netdev_printk(const char *level, const struct net_device *dev, + const char *format, ...); +__printf(2, 3) __cold +void netdev_emerg(const struct net_device *dev, const char *format, ...); +__printf(2, 3) __cold +void netdev_alert(const struct net_device *dev, const char *format, ...); +__printf(2, 3) __cold +void netdev_crit(const struct net_device *dev, const char *format, ...); +__printf(2, 3) __cold +void netdev_err(const struct net_device *dev, const char *format, ...); +__printf(2, 3) __cold +void netdev_warn(const struct net_device *dev, const char *format, ...); +__printf(2, 3) __cold +void netdev_notice(const struct net_device *dev, const char *format, ...); +__printf(2, 3) __cold +void netdev_info(const struct net_device *dev, const char *format, ...); + +#define netdev_level_once(level, dev, fmt, ...) \ +do { \ + static bool __section(".data.once") __print_once; \ + \ + if (!__print_once) { \ + __print_once = true; \ + netdev_printk(level, dev, fmt, ##__VA_ARGS__); \ + } \ +} while (0) + +#define netdev_emerg_once(dev, fmt, ...) \ + netdev_level_once(KERN_EMERG, dev, fmt, ##__VA_ARGS__) +#define netdev_alert_once(dev, fmt, ...) \ + netdev_level_once(KERN_ALERT, dev, fmt, ##__VA_ARGS__) +#define netdev_crit_once(dev, fmt, ...) \ + netdev_level_once(KERN_CRIT, dev, fmt, ##__VA_ARGS__) +#define netdev_err_once(dev, fmt, ...) \ + netdev_level_once(KERN_ERR, dev, fmt, ##__VA_ARGS__) +#define netdev_warn_once(dev, fmt, ...) \ + netdev_level_once(KERN_WARNING, dev, fmt, ##__VA_ARGS__) +#define netdev_notice_once(dev, fmt, ...) \ + netdev_level_once(KERN_NOTICE, dev, fmt, ##__VA_ARGS__) +#define netdev_info_once(dev, fmt, ...) \ + netdev_level_once(KERN_INFO, dev, fmt, ##__VA_ARGS__) + +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) +#define netdev_dbg(__dev, format, args...) \ +do { \ + dynamic_netdev_dbg(__dev, format, ##args); \ +} while (0) +#elif defined(DEBUG) +#define netdev_dbg(__dev, format, args...) \ + netdev_printk(KERN_DEBUG, __dev, format, ##args) +#else +#define netdev_dbg(__dev, format, args...) \ +({ \ + if (0) \ + netdev_printk(KERN_DEBUG, __dev, format, ##args); \ +}) +#endif + +#if defined(VERBOSE_DEBUG) +#define netdev_vdbg netdev_dbg +#else + +#define netdev_vdbg(dev, format, args...) \ +({ \ + if (0) \ + netdev_printk(KERN_DEBUG, dev, format, ##args); \ + 0; \ +}) +#endif + +/* netif printk helpers, similar to netdev_printk */ + +#define netif_printk(priv, type, level, dev, fmt, args...) \ +do { \ + if (netif_msg_##type(priv)) \ + netdev_printk(level, (dev), fmt, ##args); \ +} while (0) + +#define netif_level(level, priv, type, dev, fmt, args...) \ +do { \ + if (netif_msg_##type(priv)) \ + netdev_##level(dev, fmt, ##args); \ +} while (0) + +#define netif_emerg(priv, type, dev, fmt, args...) \ + netif_level(emerg, priv, type, dev, fmt, ##args) +#define netif_alert(priv, type, dev, fmt, args...) \ + netif_level(alert, priv, type, dev, fmt, ##args) +#define netif_crit(priv, type, dev, fmt, args...) \ + netif_level(crit, priv, type, dev, fmt, ##args) +#define netif_err(priv, type, dev, fmt, args...) \ + netif_level(err, priv, type, dev, fmt, ##args) +#define netif_warn(priv, type, dev, fmt, args...) \ + netif_level(warn, priv, type, dev, fmt, ##args) +#define netif_notice(priv, type, dev, fmt, args...) \ + netif_level(notice, priv, type, dev, fmt, ##args) +#define netif_info(priv, type, dev, fmt, args...) \ + netif_level(info, priv, type, dev, fmt, ##args) + +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) +#define netif_dbg(priv, type, netdev, format, args...) \ +do { \ + if (netif_msg_##type(priv)) \ + dynamic_netdev_dbg(netdev, format, ##args); \ +} while (0) +#elif defined(DEBUG) +#define netif_dbg(priv, type, dev, format, args...) \ + netif_printk(priv, type, KERN_DEBUG, dev, format, ##args) +#else +#define netif_dbg(priv, type, dev, format, args...) \ +({ \ + if (0) \ + netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \ + 0; \ +}) +#endif + +/* if @cond then downgrade to debug, else print at @level */ +#define netif_cond_dbg(priv, type, netdev, cond, level, fmt, args...) \ + do { \ + if (cond) \ + netif_dbg(priv, type, netdev, fmt, ##args); \ + else \ + netif_ ## level(priv, type, netdev, fmt, ##args); \ + } while (0) + +#if defined(VERBOSE_DEBUG) +#define netif_vdbg netif_dbg +#else +#define netif_vdbg(priv, type, dev, format, args...) \ +({ \ + if (0) \ + netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \ + 0; \ +}) +#endif + + +#endif /* _LINUX_NET_DEBUG_H */ -- cgit v1.2.3 From d268c1f5cfc92eb5bb605f7365769aacd93be234 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 9 May 2022 20:57:38 -0700 Subject: net: add CONFIG_DEBUG_NET This config option enables network debugging checks. This patch adds DEBUG_NET_WARN_ON_ONCE(cond) Note that this is not a replacement for WARN_ON_ONCE(cond) as (cond) is not evaluated if CONFIG_DEBUG_NET is not set. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/net_debug.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/net_debug.h b/include/net/net_debug.h index 19cd2700c20e..1e74684cbbdb 100644 --- a/include/net/net_debug.h +++ b/include/net/net_debug.h @@ -148,4 +148,10 @@ do { \ #endif +#if defined(CONFIG_DEBUG_NET) +#define DEBUG_NET_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond) +#else +#define DEBUG_NET_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond) +#endif + #endif /* _LINUX_NET_DEBUG_H */ -- cgit v1.2.3 From 66e4c8d950083df8e12981babca788e1635c92b6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 9 May 2022 20:57:39 -0700 Subject: net: warn if transport header was not set Make sure skb_transport_header() and skb_transport_offset() uses are not fooled if the transport header has not been set. This change will likely expose existing bugs in linux networking stacks. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5296b2c37f62..b91d225fdc13 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -42,6 +42,7 @@ #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include #endif +#include /** * DOC: skb checksums @@ -2904,6 +2905,7 @@ static inline bool skb_transport_header_was_set(const struct sk_buff *skb) static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { + DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); return skb->head + skb->transport_header; } -- cgit v1.2.3 From a8641d7d8500d41d312350470464e03f3df3672a Mon Sep 17 00:00:00 2001 From: Basavaraj Natikar Date: Mon, 9 May 2022 18:50:25 +0530 Subject: HID: amd_sfh: Move bus declaration outside of amd-sfh This should allow external drivers to reference this bus ID reservation and detect data coming from amd-sfh. Signed-off-by: Mario Limonciello Signed-off-by: Basavaraj Natikar Signed-off-by: Jiri Kosina --- include/uapi/linux/input.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index ee3127461ee0..ef4257ab3026 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -271,6 +271,7 @@ struct input_mask { #define BUS_RMI 0x1D #define BUS_CEC 0x1E #define BUS_INTEL_ISHTP 0x1F +#define BUS_AMD_SFH 0x20 /* * MT_TOOL types -- cgit v1.2.3 From ee692a21e9bf8354bd3ec816f1cf4bff8619ed77 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 11 May 2022 11:17:45 +0530 Subject: fs,io_uring: add infrastructure for uring-cmd file_operations->uring_cmd is a file private handler. This is somewhat similar to ioctl but hopefully a lot more sane and useful as it can be used to enable many io_uring capabilities for the underlying operation. IORING_OP_URING_CMD is a file private kind of request. io_uring doesn't know what is in this command type, it's for the provider of ->uring_cmd() to deal with. Co-developed-by: Kanchan Joshi Signed-off-by: Kanchan Joshi Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220511054750.20432-2-joshi.k@samsung.com Signed-off-by: Jens Axboe --- include/linux/fs.h | 2 ++ include/linux/io_uring.h | 33 +++++++++++++++++++++++++++++++++ include/uapi/linux/io_uring.h | 21 +++++++++++++-------- 3 files changed, 48 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index bbde95387a23..87b5af1d9fbe 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1953,6 +1953,7 @@ struct dir_context { #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) struct iov_iter; +struct io_uring_cmd; struct file_operations { struct module *owner; @@ -1995,6 +1996,7 @@ struct file_operations { struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); + int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags); } __randomize_layout; struct inode_operations { diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 24651c229ed2..4a2f6cc5a492 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -5,7 +5,32 @@ #include #include +enum io_uring_cmd_flags { + IO_URING_F_COMPLETE_DEFER = 1, + IO_URING_F_UNLOCKED = 2, + /* int's last bit, sign checks are usually faster than a bit test */ + IO_URING_F_NONBLOCK = INT_MIN, + + /* ctx state flags, for URING_CMD */ + IO_URING_F_SQE128 = 4, + IO_URING_F_CQE32 = 8, + IO_URING_F_IOPOLL = 16, +}; + +struct io_uring_cmd { + struct file *file; + const void *cmd; + /* callback to defer completions to task context */ + void (*task_work_cb)(struct io_uring_cmd *cmd); + u32 cmd_op; + u32 pad; + u8 pdu[32]; /* available inline for free use */ +}; + #if defined(CONFIG_IO_URING) +void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2); +void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *)); struct sock *io_uring_get_socket(struct file *file); void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); @@ -30,6 +55,14 @@ static inline void io_uring_free(struct task_struct *tsk) __io_uring_free(tsk); } #else +static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, + ssize_t ret2) +{ +} +static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *)) +{ +} static inline struct sock *io_uring_get_socket(struct file *file) { return NULL; diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index ac2d90d669c3..23618be55dd2 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -22,6 +22,7 @@ struct io_uring_sqe { union { __u64 off; /* offset into file */ __u64 addr2; + __u32 cmd_op; }; union { __u64 addr; /* pointer to buffer or iovecs */ @@ -61,14 +62,17 @@ struct io_uring_sqe { __s32 splice_fd_in; __u32 file_index; }; - __u64 addr3; - __u64 __pad2[1]; - - /* - * If the ring is initialized with IORING_SETUP_SQE128, then this field - * contains 64-bytes of padding, doubling the size of the SQE. - */ - __u64 __big_sqe_pad[0]; + union { + struct { + __u64 addr3; + __u64 __pad2[1]; + }; + /* + * If the ring is initialized with IORING_SETUP_SQE128, then + * this field is used for 80 bytes of arbitrary command data + */ + __u8 cmd[0]; + }; }; enum { @@ -175,6 +179,7 @@ enum io_uring_op { IORING_OP_FGETXATTR, IORING_OP_GETXATTR, IORING_OP_SOCKET, + IORING_OP_URING_CMD, /* this goes last, obviously */ IORING_OP_LAST, -- cgit v1.2.3 From 456cba386e94f22fa1b1426303fdcac9e66b1417 Mon Sep 17 00:00:00 2001 From: Kanchan Joshi Date: Wed, 11 May 2022 11:17:48 +0530 Subject: nvme: wire-up uring-cmd support for io-passthru on char-device. Introduce handler for fops->uring_cmd(), implementing async passthru on char device (/dev/ngX). The handler supports newly introduced operation NVME_URING_CMD_IO. This operates on a new structure nvme_uring_cmd, which is similar to struct nvme_passthru_cmd64 but without the embedded 8b result field. This field is not needed since uring-cmd allows to return additional result via big-CQE. Signed-off-by: Kanchan Joshi Signed-off-by: Anuj Gupta Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220511054750.20432-5-joshi.k@samsung.com Signed-off-by: Jens Axboe --- include/uapi/linux/nvme_ioctl.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h index b2e43185e3b5..04e458c649ab 100644 --- a/include/uapi/linux/nvme_ioctl.h +++ b/include/uapi/linux/nvme_ioctl.h @@ -70,6 +70,28 @@ struct nvme_passthru_cmd64 { __u64 result; }; +/* same as struct nvme_passthru_cmd64, minus the 8b result field */ +struct nvme_uring_cmd { + __u8 opcode; + __u8 flags; + __u16 rsvd1; + __u32 nsid; + __u32 cdw2; + __u32 cdw3; + __u64 metadata; + __u64 addr; + __u32 metadata_len; + __u32 data_len; + __u32 cdw10; + __u32 cdw11; + __u32 cdw12; + __u32 cdw13; + __u32 cdw14; + __u32 cdw15; + __u32 timeout_ms; + __u32 rsvd2; +}; + #define nvme_admin_cmd nvme_passthru_cmd #define NVME_IOCTL_ID _IO('N', 0x40) @@ -83,4 +105,7 @@ struct nvme_passthru_cmd64 { #define NVME_IOCTL_IO64_CMD _IOWR('N', 0x48, struct nvme_passthru_cmd64) #define NVME_IOCTL_IO64_CMD_VEC _IOWR('N', 0x49, struct nvme_passthru_cmd64) +/* io_uring async commands: */ +#define NVME_URING_CMD_IO _IOWR('N', 0x80, struct nvme_uring_cmd) + #endif /* _UAPI_LINUX_NVME_IOCTL_H */ -- cgit v1.2.3 From f569add47119fa910ed7711b26b8d38e21f7ea77 Mon Sep 17 00:00:00 2001 From: Anuj Gupta Date: Wed, 11 May 2022 11:17:49 +0530 Subject: nvme: add vectored-io support for uring-cmd wire up support for async passthru that takes an array of buffers (using iovec). Exposed via a new op NVME_URING_CMD_IO_VEC. Same 'struct nvme_uring_cmd' is to be used with - 1. cmd.addr as base address of user iovec array 2. cmd.data_len as count of iovec array elements Signed-off-by: Kanchan Joshi Signed-off-by: Anuj Gupta Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220511054750.20432-6-joshi.k@samsung.com Signed-off-by: Jens Axboe --- include/uapi/linux/nvme_ioctl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h index 04e458c649ab..0b1876aa5a59 100644 --- a/include/uapi/linux/nvme_ioctl.h +++ b/include/uapi/linux/nvme_ioctl.h @@ -107,5 +107,6 @@ struct nvme_uring_cmd { /* io_uring async commands: */ #define NVME_URING_CMD_IO _IOWR('N', 0x80, struct nvme_uring_cmd) +#define NVME_URING_CMD_IO_VEC _IOWR('N', 0x81, struct nvme_uring_cmd) #endif /* _UAPI_LINUX_NVME_IOCTL_H */ -- cgit v1.2.3 From deaf7c4b4bf8b802cc465bb9b33fe6c76e812924 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 9 May 2022 21:03:43 +0200 Subject: lockdep: Delete local_irq_enable_in_hardirq() No more users and there is no desire to grow new ones. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/8735hir0j4.ffs@tglx --- include/linux/interrupt.h | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'include') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index f40754caaefa..b5e06a6e4019 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -222,24 +222,6 @@ devm_request_any_context_irq(struct device *dev, unsigned int irq, extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id); -/* - * On lockdep we dont want to enable hardirqs in hardirq - * context. Use local_irq_enable_in_hardirq() to annotate - * kernel code that has to do this nevertheless (pretty much - * the only valid case is for old/broken hardware that is - * insanely slow). - * - * NOTE: in theory this might break fragile code that relies - * on hardirq delivery - in practice we dont seem to have such - * places left. So the only effect should be slightly increased - * irqs-off latencies. - */ -#ifdef CONFIG_LOCKDEP -# define local_irq_enable_in_hardirq() do { } while (0) -#else -# define local_irq_enable_in_hardirq() local_irq_enable() -#endif - bool irq_has_action(unsigned int irq); extern void disable_irq_nosync(unsigned int irq); extern bool disable_hardirq(unsigned int irq); -- cgit v1.2.3 From 434e09e7575b02e014931bc5672289fabd7a825c Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Tue, 10 May 2022 15:21:33 -0400 Subject: locking/qrwlock: Change "queue rwlock" to "queued rwlock" Queued rwlock was originally named "queue rwlock" which wasn't quite grammatically correct. However there are still some "queue rwlock" references in the code. Change those to "queued rwlock" for consistency. Signed-off-by: Waiman Long Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20220510192134.434753-1-longman@redhat.com --- include/asm-generic/qrwlock.h | 28 ++++++++++++++-------------- include/asm-generic/qrwlock_types.h | 2 +- 2 files changed, 15 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h index 7ae0ece07b4e..d4cd4cc4389c 100644 --- a/include/asm-generic/qrwlock.h +++ b/include/asm-generic/qrwlock.h @@ -33,8 +33,8 @@ extern void queued_read_lock_slowpath(struct qrwlock *lock); extern void queued_write_lock_slowpath(struct qrwlock *lock); /** - * queued_read_trylock - try to acquire read lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_read_trylock - try to acquire read lock of a queued rwlock + * @lock : Pointer to queued rwlock structure * Return: 1 if lock acquired, 0 if failed */ static inline int queued_read_trylock(struct qrwlock *lock) @@ -52,8 +52,8 @@ static inline int queued_read_trylock(struct qrwlock *lock) } /** - * queued_write_trylock - try to acquire write lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_write_trylock - try to acquire write lock of a queued rwlock + * @lock : Pointer to queued rwlock structure * Return: 1 if lock acquired, 0 if failed */ static inline int queued_write_trylock(struct qrwlock *lock) @@ -68,8 +68,8 @@ static inline int queued_write_trylock(struct qrwlock *lock) _QW_LOCKED)); } /** - * queued_read_lock - acquire read lock of a queue rwlock - * @lock: Pointer to queue rwlock structure + * queued_read_lock - acquire read lock of a queued rwlock + * @lock: Pointer to queued rwlock structure */ static inline void queued_read_lock(struct qrwlock *lock) { @@ -84,8 +84,8 @@ static inline void queued_read_lock(struct qrwlock *lock) } /** - * queued_write_lock - acquire write lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_write_lock - acquire write lock of a queued rwlock + * @lock : Pointer to queued rwlock structure */ static inline void queued_write_lock(struct qrwlock *lock) { @@ -98,8 +98,8 @@ static inline void queued_write_lock(struct qrwlock *lock) } /** - * queued_read_unlock - release read lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_read_unlock - release read lock of a queued rwlock + * @lock : Pointer to queued rwlock structure */ static inline void queued_read_unlock(struct qrwlock *lock) { @@ -110,8 +110,8 @@ static inline void queued_read_unlock(struct qrwlock *lock) } /** - * queued_write_unlock - release write lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_write_unlock - release write lock of a queued rwlock + * @lock : Pointer to queued rwlock structure */ static inline void queued_write_unlock(struct qrwlock *lock) { @@ -120,7 +120,7 @@ static inline void queued_write_unlock(struct qrwlock *lock) /** * queued_rwlock_is_contended - check if the lock is contended - * @lock : Pointer to queue rwlock structure + * @lock : Pointer to queued rwlock structure * Return: 1 if lock contended, 0 otherwise */ static inline int queued_rwlock_is_contended(struct qrwlock *lock) @@ -130,7 +130,7 @@ static inline int queued_rwlock_is_contended(struct qrwlock *lock) /* * Remapping rwlock architecture specific functions to the corresponding - * queue rwlock functions. + * queued rwlock functions. */ #define arch_read_lock(l) queued_read_lock(l) #define arch_write_lock(l) queued_write_lock(l) diff --git a/include/asm-generic/qrwlock_types.h b/include/asm-generic/qrwlock_types.h index c36f1d5a2572..12392c14c4d0 100644 --- a/include/asm-generic/qrwlock_types.h +++ b/include/asm-generic/qrwlock_types.h @@ -7,7 +7,7 @@ #include /* - * The queue read/write lock data structure + * The queued read/write lock data structure */ typedef struct qrwlock { -- cgit v1.2.3 From abcebcd39fe094b68826cc04f2eca835606697f9 Mon Sep 17 00:00:00 2001 From: Michael Shych Date: Sat, 30 Apr 2022 14:58:07 +0300 Subject: platform_data/mlxreg: Add field for notification callback Add notification callback to inform caller that platform driver probing has been completed. It allows to caller to perform some initialization flow steps depending on specific driver probing completion. Signed-off-by: Michael Shych Reviewed-by: Vadim Pasternak Link: https://lore.kernel.org/r/20220430115809.54565-2-michaelsh@nvidia.com Signed-off-by: Hans de Goede --- include/linux/platform_data/mlxreg.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h index 40185f9d7c14..a6bd74e29b6b 100644 --- a/include/linux/platform_data/mlxreg.h +++ b/include/linux/platform_data/mlxreg.h @@ -216,6 +216,8 @@ struct mlxreg_core_platform_data { * @mask_low: low aggregation interrupt common mask; * @deferred_nr: I2C adapter number must be exist prior probing execution; * @shift_nr: I2C adapter numbers must be incremented by this value; + * @handle: handle to be passed by callback; + * @completion_notify: callback to notify when platform driver probing is done; */ struct mlxreg_core_hotplug_platform_data { struct mlxreg_core_item *items; @@ -228,6 +230,8 @@ struct mlxreg_core_hotplug_platform_data { u32 mask_low; int deferred_nr; int shift_nr; + void *handle; + int (*completion_notify)(void *handle, int id); }; #endif /* __LINUX_PLATFORM_DATA_MLXREG_H */ -- cgit v1.2.3 From f9d76d15072caf1ec5558fa7cc6d93c7b9d33488 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Tue, 10 May 2022 11:51:29 -0400 Subject: USB: gadget: Add ID numbers to gadget names Putting USB gadgets on a new bus of their own encounters a problem when multiple gadgets are present: They all have the same name! The driver core fails with a "sys: cannot create duplicate filename" error when creating any of the /sys/bus/gadget/devices/ symbolic links after the first. This patch fixes the problem by adding a ".N" suffix to each gadget's name when the gadget is registered (where N is a unique ID number), thus making the names distinct. Reported-and-tested-by: Geert Uytterhoeven Signed-off-by: Alan Stern Reviewed-by: Geert Uytterhoeven Fixes: fc274c1e9973 ("USB: gadget: Add a new bus for gadgets") Link: https://lore.kernel.org/r/YnqKAXKyp9Vq/pbn@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/gadget.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index cf7af8a0a6e9..3ad58b7a0824 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -386,6 +386,7 @@ struct usb_gadget_ops { * @lpm_capable: If the gadget max_speed is FULL or HIGH, this flag * indicates that it supports LPM as per the LPM ECN & errata. * @irq: the interrupt number for device controller. + * @id_number: a unique ID number for ensuring that gadget names are distinct * * Gadgets have a mostly-portable "gadget driver" implementing device * functions, handling all usb configurations and interfaces. Gadget @@ -446,6 +447,7 @@ struct usb_gadget { unsigned connected:1; unsigned lpm_capable:1; int irq; + int id_number; }; #define work_to_gadget(w) (container_of((w), struct usb_gadget, work)) -- cgit v1.2.3 From 566fb90e050dfa2132340bbdab9533b727dda6f1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 22 Apr 2022 06:37:57 +0200 Subject: swiotlb-xen: fix DMA_ATTR_NO_KERNEL_MAPPING on arm swiotlb-xen uses very different ways to allocate coherent memory on x86 vs arm. On the former it allocates memory from the page allocator, while on the later it reuses the dma-direct allocator the handles the complexities of non-coherent DMA on arm platforms. Unfortunately the complexities of trying to deal with the two cases in the swiotlb-xen.c code lead to a bug in the handling of DMA_ATTR_NO_KERNEL_MAPPING on arm. With the DMA_ATTR_NO_KERNEL_MAPPING flag the coherent memory allocator does not actually allocate coherent memory, but just a DMA handle for some memory that is DMA addressable by the device, but which does not have to have a kernel mapping. Thus dereferencing the return value will lead to kernel crashed and memory corruption. Fix this by using the dma-direct allocator directly for arm, which works perfectly fine because on arm swiotlb-xen is only used when the domain is 1:1 mapped, and then simplifying the remaining code to only cater for the x86 case with DMA coherent device. Reported-by: Rahul Singh Signed-off-by: Christoph Hellwig Reviewed-by: Rahul Singh Reviewed-by: Stefano Stabellini Tested-by: Rahul Singh --- include/xen/arm/page-coherent.h | 20 -------------------- include/xen/swiotlb-xen.h | 6 ------ include/xen/xen-ops.h | 7 ------- 3 files changed, 33 deletions(-) delete mode 100644 include/xen/arm/page-coherent.h (limited to 'include') diff --git a/include/xen/arm/page-coherent.h b/include/xen/arm/page-coherent.h deleted file mode 100644 index b9cc11e887ed..000000000000 --- a/include/xen/arm/page-coherent.h +++ /dev/null @@ -1,20 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _XEN_ARM_PAGE_COHERENT_H -#define _XEN_ARM_PAGE_COHERENT_H - -#include -#include - -static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size, - dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs) -{ - return dma_direct_alloc(hwdev, size, dma_handle, flags, attrs); -} - -static inline void xen_free_coherent_pages(struct device *hwdev, size_t size, - void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs) -{ - dma_direct_free(hwdev, size, cpu_addr, dma_handle, attrs); -} - -#endif /* _XEN_ARM_PAGE_COHERENT_H */ diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h index 590ceb923f0c..808d17ad8d57 100644 --- a/include/xen/swiotlb-xen.h +++ b/include/xen/swiotlb-xen.h @@ -10,12 +10,6 @@ void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle, void xen_dma_sync_for_device(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir); -#ifdef CONFIG_SWIOTLB_XEN -int xen_swiotlb_fixup(void *buf, unsigned long nslabs); -#else -#define xen_swiotlb_fixup NULL -#endif - extern const struct dma_map_ops xen_swiotlb_dma_ops; #endif /* __LINUX_SWIOTLB_XEN_H */ diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index a3584a357f35..c7c1b46ff4cd 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -42,13 +42,6 @@ int xen_setup_shutdown_event(void); extern unsigned long *xen_contiguous_bitmap; -#if defined(CONFIG_XEN_PV) || defined(CONFIG_ARM) || defined(CONFIG_ARM64) -int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, - unsigned int address_bits, - dma_addr_t *dma_handle); -void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order); -#endif - #if defined(CONFIG_XEN_PV) int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, -- cgit v1.2.3 From a6b94c6b49198266eaf78095a632df7245ef5196 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Mon, 2 May 2022 09:36:28 -0700 Subject: Drivers: hv: vmbus: Remove support for Hyper-V 2008 and Hyper-V 2008R2/Win7 The VMbus driver has special case code for running on the first released versions of Hyper-V: 2008 and 2008 R2/Windows 7. These versions are now out of support (except for extended security updates) and lack the performance features needed for effective production usage of Linux guests. Simplify the code by removing the negotiation of the VMbus protocol versions required for these releases of Hyper-V, and by removing the special case code for handling these VMbus protocol versions. Signed-off-by: Michael Kelley Reviewed-by: Andrea Parri (Microsoft) Link: https://lore.kernel.org/r/1651509391-2058-2-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- include/linux/hyperv.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index c440c45887c2..a2464295c14a 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -230,15 +230,19 @@ static inline u32 hv_get_avail_to_write_percent( * two 16 bit quantities: major_number. minor_number. * * 0 . 13 (Windows Server 2008) - * 1 . 1 (Windows 7) - * 2 . 4 (Windows 8) - * 3 . 0 (Windows 8 R2) + * 1 . 1 (Windows 7, WS2008 R2) + * 2 . 4 (Windows 8, WS2012) + * 3 . 0 (Windows 8.1, WS2012 R2) * 4 . 0 (Windows 10) * 4 . 1 (Windows 10 RS3) * 5 . 0 (Newer Windows 10) * 5 . 1 (Windows 10 RS4) * 5 . 2 (Windows Server 2019, RS5) * 5 . 3 (Windows Server 2022) + * + * The WS2008 and WIN7 versions are listed here for + * completeness but are no longer supported in the + * Linux kernel. */ #define VERSION_WS2008 ((0 << 16) | (13)) -- cgit v1.2.3 From 1bce11126d57dde90a02ecf9bfe98175ab4e729e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 16 Mar 2022 15:53:54 -0700 Subject: asm-generic: ticket-lock: New generic ticket-based spinlock This is a simple, fair spinlock. Specifically it doesn't have all the subtle memory model dependencies that qspinlock has, which makes it more suitable for simple systems as it is more likely to be correct. It is implemented entirely in terms of standard atomics and thus works fine without any arch-specific code. This replaces the existing asm-generic/spinlock.h, which just errored out on SMP systems. Signed-off-by: Peter Zijlstra (Intel) Tested-by: Heiko Stuebner Reviewed-by: Guo Ren Reviewed-by: Arnd Bergmann Signed-off-by: Palmer Dabbelt --- include/asm-generic/spinlock.h | 94 +++++++++++++++++++++++++++++++++--- include/asm-generic/spinlock_types.h | 17 +++++++ 2 files changed, 104 insertions(+), 7 deletions(-) create mode 100644 include/asm-generic/spinlock_types.h (limited to 'include') diff --git a/include/asm-generic/spinlock.h b/include/asm-generic/spinlock.h index adaf6acab172..fdfebcb050f4 100644 --- a/include/asm-generic/spinlock.h +++ b/include/asm-generic/spinlock.h @@ -1,12 +1,92 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_GENERIC_SPINLOCK_H -#define __ASM_GENERIC_SPINLOCK_H + /* - * You need to implement asm/spinlock.h for SMP support. The generic - * version does not handle SMP. + * 'Generic' ticket-lock implementation. + * + * It relies on atomic_fetch_add() having well defined forward progress + * guarantees under contention. If your architecture cannot provide this, stick + * to a test-and-set lock. + * + * It also relies on atomic_fetch_add() being safe vs smp_store_release() on a + * sub-word of the value. This is generally true for anything LL/SC although + * you'd be hard pressed to find anything useful in architecture specifications + * about this. If your architecture cannot do this you might be better off with + * a test-and-set. + * + * It further assumes atomic_*_release() + atomic_*_acquire() is RCpc and hence + * uses atomic_fetch_add() which is RCsc to create an RCsc hot path, along with + * a full fence after the spin to upgrade the otherwise-RCpc + * atomic_cond_read_acquire(). + * + * The implementation uses smp_cond_load_acquire() to spin, so if the + * architecture has WFE like instructions to sleep instead of poll for word + * modifications be sure to implement that (see ARM64 for example). + * */ -#ifdef CONFIG_SMP -#error need an architecture specific asm/spinlock.h -#endif + +#ifndef __ASM_GENERIC_SPINLOCK_H +#define __ASM_GENERIC_SPINLOCK_H + +#include +#include + +static __always_inline void arch_spin_lock(arch_spinlock_t *lock) +{ + u32 val = atomic_fetch_add(1<<16, lock); + u16 ticket = val >> 16; + + if (ticket == (u16)val) + return; + + /* + * atomic_cond_read_acquire() is RCpc, but rather than defining a + * custom cond_read_rcsc() here we just emit a full fence. We only + * need the prior reads before subsequent writes ordering from + * smb_mb(), but as atomic_cond_read_acquire() just emits reads and we + * have no outstanding writes due to the atomic_fetch_add() the extra + * orderings are free. + */ + atomic_cond_read_acquire(lock, ticket == (u16)VAL); + smp_mb(); +} + +static __always_inline bool arch_spin_trylock(arch_spinlock_t *lock) +{ + u32 old = atomic_read(lock); + + if ((old >> 16) != (old & 0xffff)) + return false; + + return atomic_try_cmpxchg(lock, &old, old + (1<<16)); /* SC, for RCsc */ +} + +static __always_inline void arch_spin_unlock(arch_spinlock_t *lock) +{ + u16 *ptr = (u16 *)lock + IS_ENABLED(CONFIG_CPU_BIG_ENDIAN); + u32 val = atomic_read(lock); + + smp_store_release(ptr, (u16)val + 1); +} + +static __always_inline int arch_spin_is_locked(arch_spinlock_t *lock) +{ + u32 val = atomic_read(lock); + + return ((val >> 16) != (val & 0xffff)); +} + +static __always_inline int arch_spin_is_contended(arch_spinlock_t *lock) +{ + u32 val = atomic_read(lock); + + return (s16)((val >> 16) - (val & 0xffff)) > 1; +} + +static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) +{ + return !arch_spin_is_locked(&lock); +} + +#include #endif /* __ASM_GENERIC_SPINLOCK_H */ diff --git a/include/asm-generic/spinlock_types.h b/include/asm-generic/spinlock_types.h new file mode 100644 index 000000000000..8962bb730945 --- /dev/null +++ b/include/asm-generic/spinlock_types.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_GENERIC_SPINLOCK_TYPES_H +#define __ASM_GENERIC_SPINLOCK_TYPES_H + +#include +typedef atomic_t arch_spinlock_t; + +/* + * qrwlock_types depends on arch_spinlock_t, so we must typedef that before the + * include. + */ +#include + +#define __ARCH_SPIN_LOCK_UNLOCKED ATOMIC_INIT(0) + +#endif /* __ASM_GENERIC_SPINLOCK_TYPES_H */ -- cgit v1.2.3 From a8ad07e5240c9e78633270be2fa2356b7e0f0af5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 16 Mar 2022 15:48:29 -0700 Subject: asm-generic: qspinlock: Indicate the use of mixed-size atomics The qspinlock implementation depends on having well behaved mixed-size atomics. This is true on the more widely-used platforms, but these requirements are somewhat subtle and may not be satisfied by all the platforms that qspinlock is used on. Document these requirements, so ports that use qspinlock can more easily determine if they meet these requirements. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Waiman Long Reviewed-by: Arnd Bergmann Signed-off-by: Palmer Dabbelt --- include/asm-generic/qspinlock.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include') diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h index d74b13825501..995513fa2690 100644 --- a/include/asm-generic/qspinlock.h +++ b/include/asm-generic/qspinlock.h @@ -2,6 +2,35 @@ /* * Queued spinlock * + * A 'generic' spinlock implementation that is based on MCS locks. For an + * architecture that's looking for a 'generic' spinlock, please first consider + * ticket-lock.h and only come looking here when you've considered all the + * constraints below and can show your hardware does actually perform better + * with qspinlock. + * + * qspinlock relies on atomic_*_release()/atomic_*_acquire() to be RCsc (or no + * weaker than RCtso if you're power), where regular code only expects atomic_t + * to be RCpc. + * + * qspinlock relies on a far greater (compared to asm-generic/spinlock.h) set + * of atomic operations to behave well together, please audit them carefully to + * ensure they all have forward progress. Many atomic operations may default to + * cmpxchg() loops which will not have good forward progress properties on + * LL/SC architectures. + * + * One notable example is atomic_fetch_or_acquire(), which x86 cannot (cheaply) + * do. Carefully read the patches that introduced + * queued_fetch_set_pending_acquire(). + * + * qspinlock also heavily relies on mixed size atomic operations, in specific + * it requires architectures to have xchg16; something which many LL/SC + * architectures need to implement as a 32bit and+or in order to satisfy the + * forward progress guarantees mentioned above. + * + * Further reading on mixed size atomics that might be relevant: + * + * http://www.cl.cam.ac.uk/~pes20/popl17/mixed-size.pdf + * * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P. * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP * -- cgit v1.2.3 From 493e2ba27635971565a991dc9f689553242890a4 Mon Sep 17 00:00:00 2001 From: Palmer Dabbelt Date: Thu, 14 Apr 2022 09:34:29 -0700 Subject: asm-generic: qrwlock: Document the spinlock fairness requirements I could only find the fairness requirements documented as the C code, this calls them out in a comment just to be a bit more explicit. Reviewed-by: Arnd Bergmann Signed-off-by: Palmer Dabbelt --- include/asm-generic/qrwlock.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h index 7ae0ece07b4e..24ae09c1db9f 100644 --- a/include/asm-generic/qrwlock.h +++ b/include/asm-generic/qrwlock.h @@ -2,6 +2,10 @@ /* * Queue read/write lock * + * These use generic atomic and locking routines, but depend on a fair spinlock + * implementation in order to be fair themselves. The implementation in + * asm-generic/spinlock.h meets these requirements. + * * (C) Copyright 2013-2014 Hewlett-Packard Development Company, L.P. * * Authors: Waiman Long -- cgit v1.2.3 From 09ea48efffa3156218980e20aaf23dcc7d6000fc Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 11 May 2022 13:12:58 -0600 Subject: vfio: Make vfio_(un)register_notifier accept a vfio_device All callers have a struct vfio_device trivially available, pass it in directly and avoid calling the expensive vfio_group_get_from_dev(). Acked-by: Eric Farman Reviewed-by: Jason J. Herne Reviewed-by: Tony Krowiak Reviewed-by: Kevin Tian Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/1-v4-8045e76bf00b+13d-vfio_mdev_no_group_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 66dda06ec42d..a00fd722f044 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -178,11 +178,11 @@ enum vfio_notify_type { /* events for VFIO_GROUP_NOTIFY */ #define VFIO_GROUP_NOTIFY_SET_KVM BIT(0) -extern int vfio_register_notifier(struct device *dev, +extern int vfio_register_notifier(struct vfio_device *device, enum vfio_notify_type type, unsigned long *required_events, struct notifier_block *nb); -extern int vfio_unregister_notifier(struct device *dev, +extern int vfio_unregister_notifier(struct vfio_device *device, enum vfio_notify_type type, struct notifier_block *nb); -- cgit v1.2.3 From 8e432bb015b6c327d016b1dca509964e189c4770 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 11 May 2022 13:12:59 -0600 Subject: vfio/mdev: Pass in a struct vfio_device * to vfio_pin/unpin_pages() Every caller has a readily available vfio_device pointer, use that instead of passing in a generic struct device. The struct vfio_device already contains the group we need so this avoids complexity, extra refcountings, and a confusing lifecycle model. Reviewed-by: Christoph Hellwig Acked-by: Eric Farman Reviewed-by: Jason J. Herne Reviewed-by: Tony Krowiak Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/3-v4-8045e76bf00b+13d-vfio_mdev_no_group_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index a00fd722f044..bddc70f88899 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -150,9 +150,9 @@ extern long vfio_external_check_extension(struct vfio_group *group, #define VFIO_PIN_PAGES_MAX_ENTRIES (PAGE_SIZE/sizeof(unsigned long)) -extern int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, +extern int vfio_pin_pages(struct vfio_device *device, unsigned long *user_pfn, int npage, int prot, unsigned long *phys_pfn); -extern int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn, +extern int vfio_unpin_pages(struct vfio_device *device, unsigned long *user_pfn, int npage); extern int vfio_group_pin_pages(struct vfio_group *group, -- cgit v1.2.3 From c6250ffbacc5989a5db3b9acce34b93570938f60 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 11 May 2022 13:12:59 -0600 Subject: vfio/mdev: Pass in a struct vfio_device * to vfio_dma_rw() Every caller has a readily available vfio_device pointer, use that instead of passing in a generic struct device. Change vfio_dma_rw() to take in the struct vfio_device and move the container users that would have been held by vfio_group_get_external_user_from_dev() to vfio_dma_rw() directly, like vfio_pin/unpin_pages(). Reviewed-by: Christoph Hellwig Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/4-v4-8045e76bf00b+13d-vfio_mdev_no_group_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index bddc70f88899..8a1510258717 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -161,7 +161,7 @@ extern int vfio_group_pin_pages(struct vfio_group *group, extern int vfio_group_unpin_pages(struct vfio_group *group, unsigned long *user_iova_pfn, int npage); -extern int vfio_dma_rw(struct vfio_group *group, dma_addr_t user_iova, +extern int vfio_dma_rw(struct vfio_device *device, dma_addr_t user_iova, void *data, size_t len, bool write); extern struct iommu_domain *vfio_group_iommu_domain(struct vfio_group *group); -- cgit v1.2.3 From 231657b345046552b35670b45b892cfce2610e12 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 11 May 2022 13:13:00 -0600 Subject: vfio: Remove dead code Now that callers have been updated to use the vfio_device APIs the driver facing group interface is no longer used, delete it: - vfio_group_get_external_user_from_dev() - vfio_group_pin_pages() - vfio_group_unpin_pages() - vfio_group_iommu_domain() -- Reviewed-by: Christoph Hellwig Reviewed-by: Kevin Tian Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/6-v4-8045e76bf00b+13d-vfio_mdev_no_group_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 8a1510258717..6195edd2edcd 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -140,8 +140,6 @@ int vfio_mig_get_next_state(struct vfio_device *device, */ extern struct vfio_group *vfio_group_get_external_user(struct file *filep); extern void vfio_group_put_external_user(struct vfio_group *group); -extern struct vfio_group *vfio_group_get_external_user_from_dev(struct device - *dev); extern bool vfio_external_group_match_file(struct vfio_group *group, struct file *filep); extern int vfio_external_user_iommu_id(struct vfio_group *group); @@ -154,18 +152,9 @@ extern int vfio_pin_pages(struct vfio_device *device, unsigned long *user_pfn, int npage, int prot, unsigned long *phys_pfn); extern int vfio_unpin_pages(struct vfio_device *device, unsigned long *user_pfn, int npage); - -extern int vfio_group_pin_pages(struct vfio_group *group, - unsigned long *user_iova_pfn, int npage, - int prot, unsigned long *phys_pfn); -extern int vfio_group_unpin_pages(struct vfio_group *group, - unsigned long *user_iova_pfn, int npage); - extern int vfio_dma_rw(struct vfio_device *device, dma_addr_t user_iova, void *data, size_t len, bool write); -extern struct iommu_domain *vfio_group_iommu_domain(struct vfio_group *group); - /* each type has independent events */ enum vfio_notify_type { VFIO_IOMMU_NOTIFY = 0, -- cgit v1.2.3 From ff806cbd90bd2cc3d08a026e26157e5b5a6b5e03 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 11 May 2022 13:19:07 -0600 Subject: vfio/pci: Remove vfio_device_get_from_dev() The last user of this function is in PCI callbacks that want to convert their struct pci_dev to a vfio_device. Instead of searching use the vfio_device available trivially through the drvdata. When a callback in the device_driver is called, the caller must hold the device_lock() on dev. The purpose of the device_lock is to prevent remove() from being called (see __device_release_driver), and allow the driver to safely interact with its drvdata without races. The PCI core correctly follows this and holds the device_lock() when calling error_detected (see report_error_detected) and sriov_configure (see sriov_numvfs_store). Further, since the drvdata holds a positive refcount on the vfio_device any access of the drvdata, under the device_lock(), from a driver callback needs no further protection or refcounting. Thus the remark in the vfio_device_get_from_dev() comment does not apply here, VFIO PCI drivers all call vfio_unregister_group_dev() from their remove callbacks under the device_lock() and cannot race with the remaining callers. Reviewed-by: Kevin Tian Reviewed-by: Shameer Kolothum Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/2-v4-c841817a0349+8f-vfio_get_from_dev_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 2 -- include/linux/vfio_pci_core.h | 3 ++- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 6195edd2edcd..be1e7db4a314 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -125,8 +125,6 @@ void vfio_uninit_group_dev(struct vfio_device *device); int vfio_register_group_dev(struct vfio_device *device); int vfio_register_emulated_iommu_dev(struct vfio_device *device); void vfio_unregister_group_dev(struct vfio_device *device); -extern struct vfio_device *vfio_device_get_from_dev(struct device *dev); -extern void vfio_device_put(struct vfio_device *device); int vfio_assign_device_set(struct vfio_device *device, void *set_id); diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 48f2dd3c568c..23c176d4b073 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -227,8 +227,9 @@ void vfio_pci_core_init_device(struct vfio_pci_core_device *vdev, int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev); void vfio_pci_core_uninit_device(struct vfio_pci_core_device *vdev); void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev); -int vfio_pci_core_sriov_configure(struct pci_dev *pdev, int nr_virtfn); extern const struct pci_error_handlers vfio_pci_core_err_handlers; +int vfio_pci_core_sriov_configure(struct vfio_pci_core_device *vdev, + int nr_virtfn); long vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd, unsigned long arg); int vfio_pci_core_ioctl_feature(struct vfio_device *device, u32 flags, -- cgit v1.2.3 From 157cc18122b4a1456d19048e151a164216c4a704 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 22 Apr 2022 09:48:54 -0500 Subject: signal: Rename send_signal send_signal_locked Rename send_signal and __send_signal to send_signal_locked and __send_signal_locked to make send_signal usable outside of signal.c. Tested-by: Kees Cook Reviewed-by: Oleg Nesterov Link: https://lkml.kernel.org/r/20220505182645.497868-1-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/signal.h b/include/linux/signal.h index a6db6f2ae113..55605bdf5ce9 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -283,6 +283,8 @@ extern int do_send_sig_info(int sig, struct kernel_siginfo *info, extern int group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); extern int __group_send_sig_info(int, struct kernel_siginfo *, struct task_struct *); +extern int send_signal_locked(int sig, struct kernel_siginfo *info, + struct task_struct *p, enum pid_type type); extern int sigprocmask(int, sigset_t *, sigset_t *); extern void set_current_blocked(sigset_t *); extern void __set_current_blocked(const sigset_t *); -- cgit v1.2.3 From e71ba124078e391879e0bf111529fa2d630d106c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 22 Apr 2022 09:28:50 -0500 Subject: signal: Replace __group_send_sig_info with send_signal_locked The function __group_send_sig_info is just a light wrapper around send_signal_locked with one parameter fixed to a constant value. As the wrapper adds no real value update the code to directly call the wrapped function. Tested-by: Kees Cook Reviewed-by: Oleg Nesterov Link: https://lkml.kernel.org/r/20220505182645.497868-2-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/signal.h b/include/linux/signal.h index 55605bdf5ce9..3b98e7a28538 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -282,7 +282,6 @@ extern int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); extern int group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); -extern int __group_send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern int send_signal_locked(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); extern int sigprocmask(int, sigset_t *, sigset_t *); -- cgit v1.2.3 From c200e4bb44e80b343c09841e7caaaca0aac5e5fa Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 26 Apr 2022 16:30:17 -0500 Subject: ptrace/um: Replace PT_DTRACE with TIF_SINGLESTEP User mode linux is the last user of the PT_DTRACE flag. Using the flag to indicate single stepping is a little confusing and worse changing tsk->ptrace without locking could potentionally cause problems. So use a thread info flag with a better name instead of flag in tsk->ptrace. Remove the definition PT_DTRACE as uml is the last user. Cc: stable@vger.kernel.org Acked-by: Johannes Berg Tested-by: Kees Cook Reviewed-by: Oleg Nesterov Link: https://lkml.kernel.org/r/20220505182645.497868-3-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/ptrace.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 15b3d176b6b4..4c06f9f8ef3f 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -30,7 +30,6 @@ extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, #define PT_SEIZED 0x00010000 /* SEIZE used, enable new behavior */ #define PT_PTRACED 0x00000001 -#define PT_DTRACE 0x00000002 /* delayed trace (used on m68k, i386) */ #define PT_OPT_FLAG_SHIFT 3 /* PT_TRACE_* event enable flags */ -- cgit v1.2.3 From 4a3d2717d140401df7501a95e454180831a0c5af Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 26 Apr 2022 16:45:37 -0500 Subject: ptrace/xtensa: Replace PT_SINGLESTEP with TIF_SINGLESTEP xtensa is the last user of the PT_SINGLESTEP flag. Changing tsk->ptrace in user_enable_single_step and user_disable_single_step without locking could potentiallly cause problems. So use a thread info flag instead of a flag in tsk->ptrace. Use TIF_SINGLESTEP that xtensa already had defined but unused. Remove the definitions of PT_SINGLESTEP and PT_BLOCKSTEP as they have no more users. Cc: stable@vger.kernel.org Acked-by: Max Filippov Tested-by: Kees Cook Reviewed-by: Oleg Nesterov Link: https://lkml.kernel.org/r/20220505182645.497868-4-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/ptrace.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 4c06f9f8ef3f..c952c5ba8fab 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -46,12 +46,6 @@ extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, #define PT_EXITKILL (PTRACE_O_EXITKILL << PT_OPT_FLAG_SHIFT) #define PT_SUSPEND_SECCOMP (PTRACE_O_SUSPEND_SECCOMP << PT_OPT_FLAG_SHIFT) -/* single stepping state bits (used on ARM and PA-RISC) */ -#define PT_SINGLESTEP_BIT 31 -#define PT_SINGLESTEP (1< Date: Fri, 29 Apr 2022 08:43:34 -0500 Subject: ptrace: Don't change __state Stop playing with tsk->__state to remove TASK_WAKEKILL while a ptrace command is executing. Instead remove TASK_WAKEKILL from the definition of TASK_TRACED, and implement a new jobctl flag TASK_PTRACE_FROZEN. This new flag is set in jobctl_freeze_task and cleared when ptrace_stop is awoken or in jobctl_unfreeze_task (when ptrace_stop remains asleep). In signal_wake_up add __TASK_TRACED to state along with TASK_WAKEKILL when the wake up is for a fatal signal. Skip adding __TASK_TRACED when TASK_PTRACE_FROZEN is not set. This has the same effect as changing TASK_TRACED to __TASK_TRACED as all of the wake_ups that use TASK_KILLABLE go through signal_wake_up. Handle a ptrace_stop being called with a pending fatal signal. Previously it would have been handled by schedule simply failing to sleep. As TASK_WAKEKILL is no longer part of TASK_TRACED schedule will sleep with a fatal_signal_pending. The code in signal_wake_up guarantees that the code will be awaked by any fatal signal that codes after TASK_TRACED is set. Previously the __state value of __TASK_TRACED was changed to TASK_RUNNING when woken up or back to TASK_TRACED when the code was left in ptrace_stop. Now when woken up ptrace_stop now clears JOBCTL_PTRACE_FROZEN and when left sleeping ptrace_unfreezed_traced clears JOBCTL_PTRACE_FROZEN. Tested-by: Kees Cook Reviewed-by: Oleg Nesterov Link: https://lkml.kernel.org/r/20220505182645.497868-10-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/sched.h | 2 +- include/linux/sched/jobctl.h | 2 ++ include/linux/sched/signal.h | 5 +++-- 3 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index d5e3c00b74e1..610f2fdb1e2c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -103,7 +103,7 @@ struct task_group; /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) #define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED) -#define TASK_TRACED (TASK_WAKEKILL | __TASK_TRACED) +#define TASK_TRACED __TASK_TRACED #define TASK_IDLE (TASK_UNINTERRUPTIBLE | TASK_NOLOAD) diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h index fa067de9f1a9..d556c3425963 100644 --- a/include/linux/sched/jobctl.h +++ b/include/linux/sched/jobctl.h @@ -19,6 +19,7 @@ struct task_struct; #define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */ #define JOBCTL_LISTENING_BIT 22 /* ptracer is listening for events */ #define JOBCTL_TRAP_FREEZE_BIT 23 /* trap for cgroup freezer */ +#define JOBCTL_PTRACE_FROZEN_BIT 24 /* frozen for ptrace */ #define JOBCTL_STOP_DEQUEUED (1UL << JOBCTL_STOP_DEQUEUED_BIT) #define JOBCTL_STOP_PENDING (1UL << JOBCTL_STOP_PENDING_BIT) @@ -28,6 +29,7 @@ struct task_struct; #define JOBCTL_TRAPPING (1UL << JOBCTL_TRAPPING_BIT) #define JOBCTL_LISTENING (1UL << JOBCTL_LISTENING_BIT) #define JOBCTL_TRAP_FREEZE (1UL << JOBCTL_TRAP_FREEZE_BIT) +#define JOBCTL_PTRACE_FROZEN (1UL << JOBCTL_PTRACE_FROZEN_BIT) #define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY) #define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK) diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 3c8b34876744..e66948abbee4 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -435,9 +435,10 @@ extern void calculate_sigpending(void); extern void signal_wake_up_state(struct task_struct *t, unsigned int state); -static inline void signal_wake_up(struct task_struct *t, bool resume) +static inline void signal_wake_up(struct task_struct *t, bool fatal) { - signal_wake_up_state(t, resume ? TASK_WAKEKILL : 0); + fatal = fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN); + signal_wake_up_state(t, fatal ? TASK_WAKEKILL | __TASK_TRACED : 0); } static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) { -- cgit v1.2.3 From 31cae1eaae4fd65095ad6a3659db467bc3c2599e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 3 May 2022 15:57:47 -0500 Subject: sched,signal,ptrace: Rework TASK_TRACED, TASK_STOPPED state Currently ptrace_stop() / do_signal_stop() rely on the special states TASK_TRACED and TASK_STOPPED resp. to keep unique state. That is, this state exists only in task->__state and nowhere else. There's two spots of bother with this: - PREEMPT_RT has task->saved_state which complicates matters, meaning task_is_{traced,stopped}() needs to check an additional variable. - An alternative freezer implementation that itself relies on a special TASK state would loose TASK_TRACED/TASK_STOPPED and will result in misbehaviour. As such, add additional state to task->jobctl to track this state outside of task->__state. NOTE: this doesn't actually fix anything yet, just adds extra state. --EWB * didn't add a unnecessary newline in signal.h * Update t->jobctl in signal_wake_up and ptrace_signal_wake_up instead of in signal_wake_up_state. This prevents the clearing of TASK_STOPPED and TASK_TRACED from getting lost. * Added warnings if JOBCTL_STOPPED or JOBCTL_TRACED are not cleared Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20220421150654.757693825@infradead.org Tested-by: Kees Cook Reviewed-by: Oleg Nesterov Link: https://lkml.kernel.org/r/20220505182645.497868-12-ebiederm@xmission.com Signed-off-by: Eric W. Biederman --- include/linux/sched.h | 8 +++----- include/linux/sched/jobctl.h | 6 ++++++ include/linux/sched/signal.h | 19 +++++++++++++++---- 3 files changed, 24 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 610f2fdb1e2c..cbe5c899599c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -118,11 +118,9 @@ struct task_group; #define task_is_running(task) (READ_ONCE((task)->__state) == TASK_RUNNING) -#define task_is_traced(task) ((READ_ONCE(task->__state) & __TASK_TRACED) != 0) - -#define task_is_stopped(task) ((READ_ONCE(task->__state) & __TASK_STOPPED) != 0) - -#define task_is_stopped_or_traced(task) ((READ_ONCE(task->__state) & (__TASK_STOPPED | __TASK_TRACED)) != 0) +#define task_is_traced(task) ((READ_ONCE(task->jobctl) & JOBCTL_TRACED) != 0) +#define task_is_stopped(task) ((READ_ONCE(task->jobctl) & JOBCTL_STOPPED) != 0) +#define task_is_stopped_or_traced(task) ((READ_ONCE(task->jobctl) & (JOBCTL_STOPPED | JOBCTL_TRACED)) != 0) /* * Special states are those that do not use the normal wait-loop pattern. See diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h index d556c3425963..68876d0a7ef9 100644 --- a/include/linux/sched/jobctl.h +++ b/include/linux/sched/jobctl.h @@ -21,6 +21,9 @@ struct task_struct; #define JOBCTL_TRAP_FREEZE_BIT 23 /* trap for cgroup freezer */ #define JOBCTL_PTRACE_FROZEN_BIT 24 /* frozen for ptrace */ +#define JOBCTL_STOPPED_BIT 26 /* do_signal_stop() */ +#define JOBCTL_TRACED_BIT 27 /* ptrace_stop() */ + #define JOBCTL_STOP_DEQUEUED (1UL << JOBCTL_STOP_DEQUEUED_BIT) #define JOBCTL_STOP_PENDING (1UL << JOBCTL_STOP_PENDING_BIT) #define JOBCTL_STOP_CONSUME (1UL << JOBCTL_STOP_CONSUME_BIT) @@ -31,6 +34,9 @@ struct task_struct; #define JOBCTL_TRAP_FREEZE (1UL << JOBCTL_TRAP_FREEZE_BIT) #define JOBCTL_PTRACE_FROZEN (1UL << JOBCTL_PTRACE_FROZEN_BIT) +#define JOBCTL_STOPPED (1UL << JOBCTL_STOPPED_BIT) +#define JOBCTL_TRACED (1UL << JOBCTL_TRACED_BIT) + #define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY) #define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK) diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index e66948abbee4..07ba3404fcde 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -294,8 +294,10 @@ static inline int kernel_dequeue_signal(void) static inline void kernel_signal_stop(void) { spin_lock_irq(¤t->sighand->siglock); - if (current->jobctl & JOBCTL_STOP_DEQUEUED) + if (current->jobctl & JOBCTL_STOP_DEQUEUED) { + current->jobctl |= JOBCTL_STOPPED; set_special_state(TASK_STOPPED); + } spin_unlock_irq(¤t->sighand->siglock); schedule(); @@ -437,12 +439,21 @@ extern void signal_wake_up_state(struct task_struct *t, unsigned int state); static inline void signal_wake_up(struct task_struct *t, bool fatal) { - fatal = fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN); - signal_wake_up_state(t, fatal ? TASK_WAKEKILL | __TASK_TRACED : 0); + unsigned int state = 0; + if (fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN)) { + t->jobctl &= ~(JOBCTL_STOPPED | JOBCTL_TRACED); + state = TASK_WAKEKILL | __TASK_TRACED; + } + signal_wake_up_state(t, state); } static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) { - signal_wake_up_state(t, resume ? __TASK_TRACED : 0); + unsigned int state = 0; + if (resume) { + t->jobctl &= ~JOBCTL_TRACED; + state = __TASK_TRACED; + } + signal_wake_up_state(t, state); } void task_join_group_stop(struct task_struct *task); -- cgit v1.2.3 From 8b796475fd7882663a870456466a4fb315cc1bd6 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 10 May 2022 16:57:34 +0200 Subject: net/sched: act_pedit: really ensure the skb is writable Currently pedit tries to ensure that the accessed skb offset is writable via skb_unclone(). The action potentially allows touching any skb bytes, so it may end-up modifying shared data. The above causes some sporadic MPTCP self-test failures, due to this code: tc -n $ns2 filter add dev ns2eth$i egress \ protocol ip prio 1000 \ handle 42 fw \ action pedit munge offset 148 u8 invert \ pipe csum tcp \ index 100 The above modifies a data byte outside the skb head and the skb is a cloned one, carrying a TCP output packet. This change addresses the issue by keeping track of a rough over-estimate highest skb offset accessed by the action and ensuring such offset is really writable. Note that this may cause performance regressions in some scenarios, but hopefully pedit is not in the critical path. Fixes: db2c24175d14 ("act_pedit: access skb->data safely") Acked-by: Mat Martineau Tested-by: Geliang Tang Signed-off-by: Paolo Abeni Acked-by: Jamal Hadi Salim Link: https://lore.kernel.org/r/1fcf78e6679d0a287dd61bb0f04730ce33b3255d.1652194627.git.pabeni@redhat.com Signed-off-by: Jakub Kicinski --- include/net/tc_act/tc_pedit.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h index 748cf87a4d7e..3e02709a1df6 100644 --- a/include/net/tc_act/tc_pedit.h +++ b/include/net/tc_act/tc_pedit.h @@ -14,6 +14,7 @@ struct tcf_pedit { struct tc_action common; unsigned char tcfp_nkeys; unsigned char tcfp_flags; + u32 tcfp_off_max_hint; struct tc_pedit_key *tcfp_keys; struct tcf_pedit_key_ex *tcfp_keys_ex; }; -- cgit v1.2.3 From 9c2136be0878c88c53dea26943ce40bb03ad8d8d Mon Sep 17 00:00:00 2001 From: Delyan Kratunov Date: Wed, 11 May 2022 18:28:36 +0000 Subject: sched/tracing: Append prev_state to tp args instead Commit fa2c3254d7cf (sched/tracing: Don't re-read p->state when emitting sched_switch event, 2022-01-20) added a new prev_state argument to the sched_switch tracepoint, before the prev task_struct pointer. This reordering of arguments broke BPF programs that use the raw tracepoint (e.g. tp_btf programs). The type of the second argument has changed and existing programs that assume a task_struct* argument (e.g. for bpf_task_storage access) will now fail to verify. If we instead append the new argument to the end, all existing programs would continue to work and can conditionally extract the prev_state argument on supported kernel versions. Fixes: fa2c3254d7cf (sched/tracing: Don't re-read p->state when emitting sched_switch event, 2022-01-20) Signed-off-by: Delyan Kratunov Signed-off-by: Peter Zijlstra (Intel) Acked-by: Steven Rostedt (Google) Link: https://lkml.kernel.org/r/c8a6930dfdd58a4a5755fc01732675472979732b.camel@fb.com --- include/trace/events/sched.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 65e786756321..fbb99a61f714 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -222,11 +222,11 @@ static inline long __trace_sched_switch_state(bool preempt, TRACE_EVENT(sched_switch, TP_PROTO(bool preempt, - unsigned int prev_state, struct task_struct *prev, - struct task_struct *next), + struct task_struct *next, + unsigned int prev_state), - TP_ARGS(preempt, prev_state, prev, next), + TP_ARGS(preempt, prev, next, prev_state), TP_STRUCT__entry( __array( char, prev_comm, TASK_COMM_LEN ) -- cgit v1.2.3 From 5b74c690e1c55953ec99fd9dab74f72dbee4fe95 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 12 May 2022 01:16:51 +0530 Subject: bpf: Fix sparse warning for bpf_kptr_xchg_proto Kernel Test Robot complained about missing static storage class annotation for bpf_kptr_xchg_proto variable. sparse: symbol 'bpf_kptr_xchg_proto' was not declared. Should it be static? This caused by missing extern definition in the header. Add it to suppress the sparse warning. Fixes: c0a5a21c25f3 ("bpf: Allow storing referenced kptr in map") Reported-by: kernel test robot Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220511194654.765705-2-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index aba7ded56436..3ded8711457f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2246,6 +2246,7 @@ extern const struct bpf_func_proto bpf_find_vma_proto; extern const struct bpf_func_proto bpf_loop_proto; extern const struct bpf_func_proto bpf_strncmp_proto; extern const struct bpf_func_proto bpf_copy_from_user_task_proto; +extern const struct bpf_func_proto bpf_kptr_xchg_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); -- cgit v1.2.3 From 103a2f3255a95991252f8f13375c3a96a75011cd Mon Sep 17 00:00:00 2001 From: Itay Iellin Date: Sat, 7 May 2022 08:32:48 -0400 Subject: Bluetooth: Fix the creation of hdev->name Set a size limit of 8 bytes of the written buffer to "hdev->name" including the terminating null byte, as the size of "hdev->name" is 8 bytes. If an id value which is greater than 9999 is allocated, then the "snprintf(hdev->name, sizeof(hdev->name), "hci%d", id)" function call would lead to a truncation of the id value in decimal notation. Set an explicit maximum id parameter in the id allocation function call. The id allocation function defines the maximum allocated id value as the maximum id parameter value minus one. Therefore, HCI_MAX_ID is defined as 10000. Signed-off-by: Itay Iellin Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 8abd08245326..62d7b81b1cb7 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -36,6 +36,9 @@ /* HCI priority */ #define HCI_PRIO_MAX 7 +/* HCI maximum id value */ +#define HCI_MAX_ID 10000 + /* HCI Core structures */ struct inquiry_data { bdaddr_t bdaddr; -- cgit v1.2.3 From 07343110b293456d30393e89b86c4dee1ac051c8 Mon Sep 17 00:00:00 2001 From: Feng Zhou Date: Wed, 11 May 2022 17:38:53 +0800 Subject: bpf: add bpf_map_lookup_percpu_elem for percpu map Add new ebpf helpers bpf_map_lookup_percpu_elem. The implementation method is relatively simple, refer to the implementation method of map_lookup_elem of percpu map, increase the parameters of cpu, and obtain it according to the specified cpu. Signed-off-by: Feng Zhou Link: https://lore.kernel.org/r/20220511093854.411-2-zhoufeng.zf@bytedance.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 ++ include/uapi/linux/bpf.h | 9 +++++++++ 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3ded8711457f..5061ccd8b2dc 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -89,6 +89,7 @@ struct bpf_map_ops { int (*map_push_elem)(struct bpf_map *map, void *value, u64 flags); int (*map_pop_elem)(struct bpf_map *map, void *value); int (*map_peek_elem)(struct bpf_map *map, void *value); + void *(*map_lookup_percpu_elem)(struct bpf_map *map, void *key, u32 cpu); /* funcs called by prog_array and perf_event_array map */ void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, @@ -2184,6 +2185,7 @@ extern const struct bpf_func_proto bpf_map_delete_elem_proto; extern const struct bpf_func_proto bpf_map_push_elem_proto; extern const struct bpf_func_proto bpf_map_pop_elem_proto; extern const struct bpf_func_proto bpf_map_peek_elem_proto; +extern const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto; extern const struct bpf_func_proto bpf_get_prandom_u32_proto; extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bc7f89948f54..0210f85131b3 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5164,6 +5164,14 @@ union bpf_attr { * if not NULL, is a reference which must be released using its * corresponding release function, or moved into a BPF map before * program exit. + * + * void *bpf_map_lookup_percpu_elem(struct bpf_map *map, const void *key, u32 cpu) + * Description + * Perform a lookup in *percpu map* for an entry associated to + * *key* on *cpu*. + * Return + * Map value associated to *key* on *cpu*, or **NULL** if no entry + * was found or *cpu* is invalid. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5361,6 +5369,7 @@ union bpf_attr { FN(skb_set_tstamp), \ FN(ima_file_hash), \ FN(kptr_xchg), \ + FN(map_lookup_percpu_elem), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 43213daed6d6cb60e8cf69058a6db8648a556d9d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 10 May 2022 19:53:01 -0700 Subject: fortify: Provide a memcpy trap door for sharp corners As we continue to narrow the scope of what the FORTIFY memcpy() will accept and build alternative APIs that give the compiler appropriate visibility into more complex memcpy scenarios, there is a need for "unfortified" memcpy use in rare cases where combinations of compiler behaviors, source code layout, etc, result in cases where the stricter memcpy checks need to be bypassed until appropriate solutions can be developed (i.e. fix compiler bugs, code refactoring, new API, etc). The intention is for this to be used only if there's no other reasonable solution, for its use to include a justification that can be used to assess future solutions, and for it to be temporary. Example usage included, based on analysis and discussion from: https://lore.kernel.org/netdev/CANn89iLS_2cshtuXPyNUGDPaic=sJiYfvTb_wNLgWrZRyBxZ_g@mail.gmail.com Cc: Jakub Kicinski Cc: Eric Dumazet Cc: "David S. Miller" Cc: Paolo Abeni Cc: Coco Li Cc: Tariq Toukan Cc: Saeed Mahameed Cc: Leon Romanovsky Cc: netdev@vger.kernel.org Cc: linux-hardening@vger.kernel.org Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220511025301.3636666-1-keescook@chromium.org Signed-off-by: Paolo Abeni --- include/linux/fortify-string.h | 16 ++++++++++++++++ include/linux/string.h | 4 ++++ 2 files changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 295637a66c46..3b401fa0f374 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -52,6 +52,22 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) #define __underlying_strncpy __builtin_strncpy #endif +/** + * unsafe_memcpy - memcpy implementation with no FORTIFY bounds checking + * + * @dst: Destination memory address to write to + * @src: Source memory address to read from + * @bytes: How many bytes to write to @dst from @src + * @justification: Free-form text or comment describing why the use is needed + * + * This should be used for corner cases where the compiler cannot do the + * right thing, or during transitions between APIs, etc. It should be used + * very rarely, and includes a place for justification detailing where bounds + * checking has happened, and why existing solutions cannot be employed. + */ +#define unsafe_memcpy(dst, src, bytes, justification) \ + __underlying_memcpy(dst, src, bytes) + /* * Clang's use of __builtin_object_size() within inlines needs hinting via * __pass_object_size(). The preference is to only ever use type 1 (member diff --git a/include/linux/string.h b/include/linux/string.h index b6572aeca2f5..61ec7e4f6311 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -252,6 +252,10 @@ static inline const char *kbasename(const char *path) #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) #include #endif +#ifndef unsafe_memcpy +#define unsafe_memcpy(dst, src, bytes, justification) \ + memcpy(dst, src, bytes) +#endif void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, int pad); -- cgit v1.2.3 From 71cb8ad1a78043ca0eec1686bdd2e65143943b78 Mon Sep 17 00:00:00 2001 From: Ranjani Sridharan Date: Wed, 11 May 2022 10:16:46 -0700 Subject: ASoC: SOF: Add header for IPC4 manifest Add the header for the IPC4 manifest. Co-developed-by: Rander Wang Signed-off-by: Rander Wang Co-developed-by: Bard Liao Signed-off-by: Bard Liao Reviewed-by: Bard Liao Reviewed-by: Rander Wang Reviewed-by: Pierre-Louis Bossart Signed-off-by: Ranjani Sridharan Link: https://lore.kernel.org/r/20220511171648.1622993-4-ranjani.sridharan@linux.intel.com Signed-off-by: Mark Brown --- include/sound/sof/ext_manifest4.h | 119 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 119 insertions(+) create mode 100644 include/sound/sof/ext_manifest4.h (limited to 'include') diff --git a/include/sound/sof/ext_manifest4.h b/include/sound/sof/ext_manifest4.h new file mode 100644 index 000000000000..ec97edcbbfc3 --- /dev/null +++ b/include/sound/sof/ext_manifest4.h @@ -0,0 +1,119 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * Copyright(c) 2022 Intel Corporation. All rights reserved. + */ + +/* + * Extended manifest is a place to store metadata about firmware, known during + * compilation time - for example firmware version or used compiler. + * Given information are read on host side before firmware startup. + * This part of output binary is not signed. + */ + +#ifndef __SOF_FIRMWARE_EXT_MANIFEST4_H__ +#define __SOF_FIRMWARE_EXT_MANIFEST4_H__ + +#include + +/* In ASCII $AE1 */ +#define SOF_EXT_MAN4_MAGIC_NUMBER 0x31454124 + +#define MAX_MODULE_NAME_LEN 8 +#define MAX_FW_BINARY_NAME 8 +#define DEFAULT_HASH_SHA256_LEN 32 +#define SOF_MAN4_FW_HDR_OFFSET 0x2000 +#define SOF_MAN4_FW_HDR_OFFSET_CAVS_1_5 0x284 + +/********************************************************************* + * extended manifest (struct sof_ext_manifest4_hdr) + *------------------- + * css_manifest hdr + *------------------- + * offset reserved for future + *------------------- + * fw_hdr (struct sof_man4_fw_binary_header) + *------------------- + * module_entry[0] (struct sof_man4_module) + *------------------- + * module_entry[1] + *------------------- + * ... + *------------------- + * module_entry[n] + *------------------- + * module_config[0] (struct sof_man4_module_config) + *------------------- + * module_config[1] + *------------------- + * ... + *------------------- + * module_config[m] + *------------------- + * FW content + *------------------- + *********************************************************************/ + +struct sof_ext_manifest4_hdr { + uint32_t id; + uint32_t len; /* length of extension manifest */ + uint16_t version_major; /* header version */ + uint16_t version_minor; + uint32_t num_module_entries; +} __packed; + +struct sof_man4_fw_binary_header { + /* This part must be unchanged to be backward compatible with SPT-LP ROM */ + uint32_t id; + uint32_t len; /* sizeof(sof_man4_fw_binary_header) in bytes */ + uint8_t name[MAX_FW_BINARY_NAME]; + uint32_t preload_page_count; /* number of pages of preloaded image */ + uint32_t fw_image_flags; + uint32_t feature_mask; + uint16_t major_version; /* Firmware version */ + uint16_t minor_version; + uint16_t hotfix_version; + uint16_t build_version; + uint32_t num_module_entries; + + /* This part may change to contain any additional data for BaseFw that is skipped by ROM */ + uint32_t hw_buf_base_addr; + uint32_t hw_buf_length; + uint32_t load_offset; /* This value is used by ROM */ +} __packed; + +struct sof_man4_segment_desc { + uint32_t flags; + uint32_t v_base_addr; + uint32_t file_offset; +} __packed; + +struct sof_man4_module { + uint32_t id; + uint8_t name[MAX_MODULE_NAME_LEN]; + guid_t uuid; + uint32_t type; + uint8_t hash[DEFAULT_HASH_SHA256_LEN]; + uint32_t entry_point; + uint16_t cfg_offset; + uint16_t cfg_count; + uint32_t affinity_mask; + uint16_t instance_max_count; + uint16_t instance_stack_size; + struct sof_man4_segment_desc segments[3]; +} __packed; + +struct sof_man4_module_config { + uint32_t par[4]; /* module parameters */ + uint32_t is_bytes; /* actual size of instance .bss (bytes) */ + uint32_t cps; /* cycles per second */ + uint32_t ibs; /* input buffer size (bytes) */ + uint32_t obs; /* output buffer size (bytes) */ + uint32_t module_flags; /* flags, reserved for future use */ + uint32_t cpc; /* cycles per single run */ + uint32_t obls; /* output block size, reserved for future use */ +} __packed; + +#endif /* __SOF_FIRMWARE_EXT_MANIFEST4_H__ */ -- cgit v1.2.3 From a44623d9279086c89f631201d993aa332f7c9e66 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Tue, 10 May 2022 14:46:29 +0530 Subject: usb: core: hcd: Add support for deferring roothub registration It has been observed with certain PCIe USB cards (like Inateck connected to AM64 EVM or J7200 EVM) that as soon as the primary roothub is registered, port status change is handled even before xHC is running leading to cold plug USB devices not detected. For such cases, registering both the root hubs along with the second HCD is required. Add support for deferring roothub registration in usb_add_hcd(), so that both primary and secondary roothubs are registered along with the second HCD. This patch has been added and reverted earier as it triggered a race in usb device enumeration. That race is now fixed in 5.16-rc3, and in stable back to 5.4 commit 6cca13de26ee ("usb: hub: Fix locking issues with address0_mutex") commit 6ae6dc22d2d1 ("usb: hub: Fix usb enumeration issue due to address0 race") CC: stable@vger.kernel.org # 5.4+ Suggested-by: Mathias Nyman Tested-by: Chris Chiu Acked-by: Alan Stern Signed-off-by: Kishon Vijay Abraham I Link: https://lore.kernel.org/r/20220510091630.16564-2-kishon@ti.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 548a028f2dab..2c1fc9212cf2 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -124,6 +124,7 @@ struct usb_hcd { #define HCD_FLAG_RH_RUNNING 5 /* root hub is running? */ #define HCD_FLAG_DEAD 6 /* controller has died? */ #define HCD_FLAG_INTF_AUTHORIZED 7 /* authorize interfaces? */ +#define HCD_FLAG_DEFER_RH_REGISTER 8 /* Defer roothub registration */ /* The flags can be tested using these macros; they are likely to * be slightly faster than test_bit(). @@ -134,6 +135,7 @@ struct usb_hcd { #define HCD_WAKEUP_PENDING(hcd) ((hcd)->flags & (1U << HCD_FLAG_WAKEUP_PENDING)) #define HCD_RH_RUNNING(hcd) ((hcd)->flags & (1U << HCD_FLAG_RH_RUNNING)) #define HCD_DEAD(hcd) ((hcd)->flags & (1U << HCD_FLAG_DEAD)) +#define HCD_DEFER_RH_REGISTER(hcd) ((hcd)->flags & (1U << HCD_FLAG_DEFER_RH_REGISTER)) /* * Specifies if interfaces are authorized by default -- cgit v1.2.3 From 2d2d5cb6ca8424fa849ebb4edb8e8022c13860c7 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Thu, 12 May 2022 02:18:33 -0700 Subject: io_uring: fix ordering of args in io_uring_queue_async_work Fix arg ordering in TP_ARGS macro, which fixes the output. Fixes: 502c87d65564c ("io-uring: Make tracepoints consistent.") Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220512091834.728610-2-dylany@fb.com Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index cddf5b6fbeb4..80d2588a090c 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -147,7 +147,7 @@ TRACE_EVENT(io_uring_queue_async_work, TP_PROTO(void *ctx, void * req, unsigned long long user_data, u8 opcode, unsigned int flags, struct io_wq_work *work, int rw), - TP_ARGS(ctx, req, user_data, flags, opcode, work, rw), + TP_ARGS(ctx, req, user_data, opcode, flags, work, rw), TP_STRUCT__entry ( __field( void *, ctx ) -- cgit v1.2.3 From 5ce7729f25c16d5045deff4c9577e6d565da2d8d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 12 May 2022 08:14:08 +0200 Subject: block: reorder the REQ_ flags Keep the op-specific flag last so that they are clearly separate from the generic flags. Various recent commits just kept adding new flags at the end. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220512061408.1826595-1-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 4968cb17b13b..30f9a5391fd5 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -408,16 +408,17 @@ enum req_flag_bits { * work item to avoid such priority inversions. */ __REQ_CGROUP_PUNT, - - /* command specific flags for REQ_OP_WRITE_ZEROES: */ - __REQ_NOUNMAP, /* do not free blocks when zeroing */ - __REQ_POLLED, /* caller polls for completion using bio_poll */ __REQ_ALLOC_CACHE, /* allocate IO from cache if available */ + __REQ_SWAP, /* swap I/O */ + __REQ_DRV, /* for driver use */ + + /* + * Command specific flags, keep last: + */ + /* for REQ_OP_WRITE_ZEROES: */ + __REQ_NOUNMAP, /* do not free blocks when zeroing */ - /* for driver use */ - __REQ_DRV, - __REQ_SWAP, /* swapping request. */ __REQ_NR_BITS, /* stops here */ }; -- cgit v1.2.3 From 5d2ae14276e698c76fa0c8ce870103f343b38263 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 11 May 2022 16:51:52 -0700 Subject: block: Fix the bio.bi_opf comment Commit ef295ecf090d modified the Linux kernel such that the bottom bits of the bi_opf member contain the operation instead of the topmost bits. That commit did not update the comment next to bi_opf. Hence this patch. From commit ef295ecf090d: -#define bio_op(bio) ((bio)->bi_opf >> BIO_OP_SHIFT) +#define bio_op(bio) ((bio)->bi_opf & REQ_OP_MASK) Cc: Christoph Hellwig Cc: Ming Lei Fixes: ef295ecf090d ("block: better op and flags encoding") Signed-off-by: Bart Van Assche Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220511235152.1082246-1-bvanassche@acm.org Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 30f9a5391fd5..40e815400611 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -246,9 +246,8 @@ typedef unsigned int blk_qc_t; struct bio { struct bio *bi_next; /* request queue link */ struct block_device *bi_bdev; - unsigned int bi_opf; /* bottom bits req flags, - * top bits REQ_OP. Use - * accessors. + unsigned int bi_opf; /* bottom bits REQ_OP, top bits + * req_flags. */ unsigned short bi_flags; /* BIO_* below */ unsigned short bi_ioprio; -- cgit v1.2.3 From 2760f5a415c3b86c6394738c6cff740c8b4ce664 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 6 May 2022 15:54:01 -0700 Subject: stop_machine: Add stop_core_cpuslocked() for per-core operations Hardware core level testing features require near simultaneous execution of WRMSR instructions on all threads of a core to initiate a test. Provide a customized cut down version of stop_machine_cpuslocked() that just operates on the threads of a single core. Suggested-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Tony Luck Reviewed-by: Thomas Gleixner Link: https://lore.kernel.org/r/20220506225410.1652287-4-tony.luck@intel.com Signed-off-by: Hans de Goede --- include/linux/stop_machine.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 46fb3ebdd16e..ea7a74ea7389 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -124,6 +124,22 @@ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); */ int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); +/** + * stop_core_cpuslocked: - stop all threads on just one core + * @cpu: any cpu in the targeted core + * @fn: the function to run + * @data: the data ptr for @fn() + * + * Same as above, but instead of every CPU, only the logical CPUs of a + * single core are affected. + * + * Context: Must be called from within a cpus_read_lock() protected region. + * + * Return: 0 if all executions of @fn returned 0, any non zero return + * value if any returned non zero. + */ +int stop_core_cpuslocked(unsigned int cpu, cpu_stop_fn_t fn, void *data); + int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); #else /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ -- cgit v1.2.3 From 51af802fc05152e84727a4293ccaa7e7e1b64d7e Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Fri, 6 May 2022 15:54:08 -0700 Subject: trace: platform/x86/intel/ifs: Add trace point to track Intel IFS operations Add tracing support which may be useful for debugging systems that fail to complete In Field Scan tests. Acked-by: Steven Rostedt (Google) Reviewed-by: Dan Williams Signed-off-by: Tony Luck Acked-by: Hans de Goede Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20220506225410.1652287-11-tony.luck@intel.com Signed-off-by: Hans de Goede --- include/trace/events/intel_ifs.h | 41 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) create mode 100644 include/trace/events/intel_ifs.h (limited to 'include') diff --git a/include/trace/events/intel_ifs.h b/include/trace/events/intel_ifs.h new file mode 100644 index 000000000000..d7353024016c --- /dev/null +++ b/include/trace/events/intel_ifs.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM intel_ifs + +#if !defined(_TRACE_IFS_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_IFS_H + +#include +#include + +TRACE_EVENT(ifs_status, + + TP_PROTO(int cpu, union ifs_scan activate, union ifs_status status), + + TP_ARGS(cpu, activate, status), + + TP_STRUCT__entry( + __field( u64, status ) + __field( int, cpu ) + __field( u8, start ) + __field( u8, stop ) + ), + + TP_fast_assign( + __entry->cpu = cpu; + __entry->start = activate.start; + __entry->stop = activate.stop; + __entry->status = status.data; + ), + + TP_printk("cpu: %d, start: %.2x, stop: %.2x, status: %llx", + __entry->cpu, + __entry->start, + __entry->stop, + __entry->status) +); + +#endif /* _TRACE_IFS_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From 75d6fe48a21a0ea1565228c12b9c16f3fb37b673 Mon Sep 17 00:00:00 2001 From: Siddh Raman Pant Date: Thu, 12 May 2022 20:06:45 +0530 Subject: spi: Doc fix - Describe add_lock and dma_map_dev in spi_controller This fixes the corresponding warnings during building the docs. Signed-off-by: Siddh Raman Pant Link: https://lore.kernel.org/r/4e6187a4-d0f8-4750-e407-e09cc1c91789@gmail.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 5f8c063ddff4..df70eb1a671e 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -347,6 +347,7 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @max_message_size: function that returns the max message size for * a &spi_device; may be %NULL, so the default %SIZE_MAX will be used. * @io_mutex: mutex for physical bus access + * @add_lock: mutex to avoid adding devices to the same chipselect * @bus_lock_spinlock: spinlock for SPI bus locking * @bus_lock_mutex: mutex for exclusion of multiple callers * @bus_lock_flag: indicates that the SPI bus is locked for exclusive use @@ -361,6 +362,7 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @transfer: adds a message to the controller's transfer queue. * @cleanup: frees controller-specific state * @can_dma: determine whether this controller supports DMA + * @dma_map_dev: device which can be used for DMA mapping * @queued: whether this controller is providing an internal message queue * @kworker: pointer to thread struct for message pump * @pump_messages: work struct for scheduling work to the message pump -- cgit v1.2.3 From 9824117dd964ecebf5d81990dbf21dfb56445049 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Tue, 12 Apr 2022 15:38:51 -0500 Subject: ipmi: Add an intializer for ipmi_smi_msg struct There was a "type" element added to this structure, but some static values were missed. The default value will be zero, which is correct, but create an initializer for the type and initialize the type properly in the initializer to avoid future issues. Reported-by: Joe Wiese Signed-off-by: Corey Minyard --- include/linux/ipmi_smi.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index 9277d21c2690..5d69820d8b02 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -125,6 +125,12 @@ struct ipmi_smi_msg { void (*done)(struct ipmi_smi_msg *msg); }; +#define INIT_IPMI_SMI_MSG(done_handler) \ +{ \ + .done = done_handler, \ + .type = IPMI_SMI_MSG_TYPE_NORMAL \ +} + struct ipmi_smi_handlers { struct module *owner; -- cgit v1.2.3 From f214549d717310f795c20db9497db3938116399d Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Tue, 12 Apr 2022 15:49:47 -0500 Subject: ipmi: Add an intializer for ipmi_recv_msg struct Don't hand-initialize the struct here, create a macro to initialize it so new fields added don't get forgotten in places. Signed-off-by: Corey Minyard --- include/linux/ipmi.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index 163831a087ef..a1c9c0d48ebf 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -72,6 +72,11 @@ struct ipmi_recv_msg { unsigned char msg_data[IPMI_MAX_MSG_LENGTH]; }; +#define INIT_IPMI_RECV_MSG(done_handler) \ +{ \ + .done = done_handler \ +} + /* Allocate and free the receive message. */ void ipmi_free_recv_msg(struct ipmi_recv_msg *msg); -- cgit v1.2.3 From 3db1de0e582c358dd013f3703cd55b5fe4076436 Mon Sep 17 00:00:00 2001 From: Daeho Jeong Date: Thu, 28 Apr 2022 11:18:09 -0700 Subject: f2fs: change the current atomic write way Current atomic write has three major issues like below. - keeps the updates in non-reclaimable memory space and they are even hard to be migrated, which is not good for contiguous memory allocation. - disk spaces used for atomic files cannot be garbage collected, so this makes it difficult for the filesystem to be defragmented. - If atomic write operations hit the threshold of either memory usage or garbage collection failure count, All the atomic write operations will fail immediately. To resolve the issues, I will keep a COW inode internally for all the updates to be flushed from memory, when we need to flush them out in a situation like high memory pressure. These COW inodes will be tagged as orphan inodes to be reclaimed in case of sudden power-cut or system failure during atomic writes. Signed-off-by: Daeho Jeong Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 4d1ad64d4cab..7e915dbf3674 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -15,10 +15,6 @@ TRACE_DEFINE_ENUM(NODE); TRACE_DEFINE_ENUM(DATA); TRACE_DEFINE_ENUM(META); TRACE_DEFINE_ENUM(META_FLUSH); -TRACE_DEFINE_ENUM(INMEM); -TRACE_DEFINE_ENUM(INMEM_DROP); -TRACE_DEFINE_ENUM(INMEM_INVALIDATE); -TRACE_DEFINE_ENUM(INMEM_REVOKE); TRACE_DEFINE_ENUM(IPU); TRACE_DEFINE_ENUM(OPU); TRACE_DEFINE_ENUM(HOT); @@ -59,10 +55,6 @@ TRACE_DEFINE_ENUM(CP_RESIZE); { DATA, "DATA" }, \ { META, "META" }, \ { META_FLUSH, "META_FLUSH" }, \ - { INMEM, "INMEM" }, \ - { INMEM_DROP, "INMEM_DROP" }, \ - { INMEM_INVALIDATE, "INMEM_INVALIDATE" }, \ - { INMEM_REVOKE, "INMEM_REVOKE" }, \ { IPU, "IN-PLACE" }, \ { OPU, "OUT-OF-PLACE" }) @@ -1289,20 +1281,6 @@ DEFINE_EVENT(f2fs__page, f2fs_vm_page_mkwrite, TP_ARGS(page, type) ); -DEFINE_EVENT(f2fs__page, f2fs_register_inmem_page, - - TP_PROTO(struct page *page, int type), - - TP_ARGS(page, type) -); - -DEFINE_EVENT(f2fs__page, f2fs_commit_inmem_page, - - TP_PROTO(struct page *page, int type), - - TP_ARGS(page, type) -); - TRACE_EVENT(f2fs_filemap_fault, TP_PROTO(struct inode *inode, pgoff_t index, unsigned long ret), -- cgit v1.2.3 From ad69172ec930075d25e14220841dd96375088d28 Mon Sep 17 00:00:00 2001 From: David Gow Date: Sat, 2 Apr 2022 12:35:30 +0800 Subject: kunit: Rework kunit_resource allocation policy KUnit's test-managed resources can be created in two ways: - Using the kunit_add_resource() family of functions, which accept a struct kunit_resource pointer, typically allocated statically or on the stack during the test. - Using the kunit_alloc_resource() family of functions, which allocate a struct kunit_resource using kzalloc() behind the scenes. Both of these families of functions accept a 'free' function to be called when the resource is finally disposed of. At present, KUnit will kfree() the resource if this 'free' function is specified, and will not if it is NULL. However, this can lead kunit_alloc_resource() to leak memory (if no 'free' function is passed in), or kunit_add_resource() to incorrectly kfree() memory which was allocated by some other means (on the stack, as part of a larger allocation, etc), if a 'free' function is provided. Instead, always kfree() if the resource was allocated with kunit_alloc_resource(), and never kfree() if it was passed into kunit_add_resource() by the user. (If the user of kunit_add_resource() wishes the resource be kfree()ed, they can call kfree() on the resource from within the 'free' function. This is implemented by adding a 'should_free' member to struct kunit_resource and setting it appropriately. To facilitate this, the various resource add/alloc functions have been refactored somewhat, making them all call a __kunit_add_resource() helper after setting the 'should_free' member appropriately. In the process, all other functions have been made static inline functions. Signed-off-by: David Gow Tested-by: Daniel Latypov Reviewed-by: Brendan Higgins Signed-off-by: Shuah Khan --- include/kunit/resource.h | 142 ++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 115 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/include/kunit/resource.h b/include/kunit/resource.h index 7ab1fd83972b..09c2b34d1c61 100644 --- a/include/kunit/resource.h +++ b/include/kunit/resource.h @@ -25,11 +25,13 @@ typedef void (*kunit_resource_free_t)(struct kunit_resource *); * struct kunit_resource - represents a *test managed resource* * @data: for the user to store arbitrary data. * @name: optional name - * @free: a user supplied function to free the resource. Populated by - * kunit_resource_alloc(). + * @free: a user supplied function to free the resource. * * Represents a *test managed resource*, a resource which will automatically be - * cleaned up at the end of a test case. + * cleaned up at the end of a test case. This cleanup is performed by the 'free' + * function. The struct kunit_resource itself is freed automatically with + * kfree() if it was allocated by KUnit (e.g., by kunit_alloc_resource()), but + * must be freed by the user otherwise. * * Resources are reference counted so if a resource is retrieved via * kunit_alloc_and_get_resource() or kunit_find_resource(), we need @@ -86,18 +88,9 @@ struct kunit_resource { /* private: internal use only. */ struct kref refcount; struct list_head node; + bool should_kfree; }; -/* - * Like kunit_alloc_resource() below, but returns the struct kunit_resource - * object that contains the allocation. This is mostly for testing purposes. - */ -struct kunit_resource *kunit_alloc_and_get_resource(struct kunit *test, - kunit_resource_init_t init, - kunit_resource_free_t free, - gfp_t internal_gfp, - void *context); - /** * kunit_get_resource() - Hold resource for use. Should not need to be used * by most users as we automatically get resources @@ -118,11 +111,14 @@ static inline void kunit_release_resource(struct kref *kref) struct kunit_resource *res = container_of(kref, struct kunit_resource, refcount); - /* If free function is defined, resource was dynamically allocated. */ - if (res->free) { + if (res->free) res->free(res); + + /* 'res' is valid here, as if should_kfree is set, res->free may not free + * 'res' itself, just res->data + */ + if (res->should_kfree) kfree(res); - } } /** @@ -142,6 +138,24 @@ static inline void kunit_put_resource(struct kunit_resource *res) kref_put(&res->refcount, kunit_release_resource); } +/** + * __kunit_add_resource() - Internal helper to add a resource. + * + * res->should_kfree is not initialised. + * @test: The test context object. + * @init: a user-supplied function to initialize the result (if needed). If + * none is supplied, the resource data value is simply set to @data. + * If an init function is supplied, @data is passed to it instead. + * @free: a user-supplied function to free the resource (if needed). + * @res: The resource. + * @data: value to pass to init function or set in resource data field. + */ +int __kunit_add_resource(struct kunit *test, + kunit_resource_init_t init, + kunit_resource_free_t free, + struct kunit_resource *res, + void *data); + /** * kunit_add_resource() - Add a *test managed resource*. * @test: The test context object. @@ -152,11 +166,18 @@ static inline void kunit_put_resource(struct kunit_resource *res) * @res: The resource. * @data: value to pass to init function or set in resource data field. */ -int kunit_add_resource(struct kunit *test, - kunit_resource_init_t init, - kunit_resource_free_t free, - struct kunit_resource *res, - void *data); +static inline int kunit_add_resource(struct kunit *test, + kunit_resource_init_t init, + kunit_resource_free_t free, + struct kunit_resource *res, + void *data) +{ + res->should_kfree = false; + return __kunit_add_resource(test, init, free, res, data); +} + +static inline struct kunit_resource * +kunit_find_named_resource(struct kunit *test, const char *name); /** * kunit_add_named_resource() - Add a named *test managed resource*. @@ -167,18 +188,84 @@ int kunit_add_resource(struct kunit *test, * @name: name to be set for resource. * @data: value to pass to init function or set in resource data field. */ -int kunit_add_named_resource(struct kunit *test, +static inline int kunit_add_named_resource(struct kunit *test, + kunit_resource_init_t init, + kunit_resource_free_t free, + struct kunit_resource *res, + const char *name, + void *data) +{ + struct kunit_resource *existing; + + if (!name) + return -EINVAL; + + existing = kunit_find_named_resource(test, name); + if (existing) { + kunit_put_resource(existing); + return -EEXIST; + } + + res->name = name; + res->should_kfree = false; + + return __kunit_add_resource(test, init, free, res, data); +} + +/** + * kunit_alloc_and_get_resource() - Allocates and returns a *test managed resource*. + * @test: The test context object. + * @init: a user supplied function to initialize the resource. + * @free: a user supplied function to free the resource (if needed). + * @internal_gfp: gfp to use for internal allocations, if unsure, use GFP_KERNEL + * @context: for the user to pass in arbitrary data to the init function. + * + * Allocates a *test managed resource*, a resource which will automatically be + * cleaned up at the end of a test case. See &struct kunit_resource for an + * example. + * + * This is effectively identical to kunit_alloc_resource, but returns the + * struct kunit_resource pointer, not just the 'data' pointer. It therefore + * also increments the resource's refcount, so kunit_put_resource() should be + * called when you've finished with it. + * + * Note: KUnit needs to allocate memory for a kunit_resource object. You must + * specify an @internal_gfp that is compatible with the use context of your + * resource. + */ +static inline struct kunit_resource * +kunit_alloc_and_get_resource(struct kunit *test, kunit_resource_init_t init, kunit_resource_free_t free, - struct kunit_resource *res, - const char *name, - void *data); + gfp_t internal_gfp, + void *context) +{ + struct kunit_resource *res; + int ret; + + res = kzalloc(sizeof(*res), internal_gfp); + if (!res) + return NULL; + + res->should_kfree = true; + + ret = __kunit_add_resource(test, init, free, res, context); + if (!ret) { + /* + * bump refcount for get; kunit_resource_put() should be called + * when done. + */ + kunit_get_resource(res); + return res; + } + return NULL; +} /** * kunit_alloc_resource() - Allocates a *test managed resource*. * @test: The test context object. * @init: a user supplied function to initialize the resource. - * @free: a user supplied function to free the resource. + * @free: a user supplied function to free the resource (if needed). * @internal_gfp: gfp to use for internal allocations, if unsure, use GFP_KERNEL * @context: for the user to pass in arbitrary data to the init function. * @@ -202,7 +289,8 @@ static inline void *kunit_alloc_resource(struct kunit *test, if (!res) return NULL; - if (!kunit_add_resource(test, init, free, res, context)) + res->should_kfree = true; + if (!__kunit_add_resource(test, init, free, res, context)) return res->data; return NULL; -- cgit v1.2.3 From 80140a81f7f833998d732102eea0fea230b88067 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 27 Apr 2022 11:03:21 +0200 Subject: module.h: simplify MODULE_IMPORT_NS In commit ca321ec74322 ("module.h: allow #define strings to work with MODULE_IMPORT_NS") I fixed up the MODULE_IMPORT_NS() macro to allow defined strings to work with it. Unfortunatly I did it in a two-stage process, when it could just be done with the __stringify() macro as pointed out by Masahiro Yamada. Clean this up to only be one macro instead of two steps to achieve the same end result. Fixes: ca321ec74322 ("module.h: allow #define strings to work with MODULE_IMPORT_NS") Reported-by: Masahiro Yamada Cc: Luis Chamberlain Cc: Jessica Yu Cc: Matthias Maennich Signed-off-by: Greg Kroah-Hartman Signed-off-by: Luis Chamberlain --- include/linux/module.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index 46d4d5f2516e..abd9fa916b7d 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -290,8 +290,7 @@ extern typeof(name) __mod_##type##__##name##_device_table \ * files require multiple MODULE_FIRMWARE() specifiers */ #define MODULE_FIRMWARE(_firmware) MODULE_INFO(firmware, _firmware) -#define _MODULE_IMPORT_NS(ns) MODULE_INFO(import_ns, #ns) -#define MODULE_IMPORT_NS(ns) _MODULE_IMPORT_NS(ns) +#define MODULE_IMPORT_NS(ns) MODULE_INFO(import_ns, __stringify(ns)) struct notifier_block; -- cgit v1.2.3 From d147ea4adb969b03f7f1c7613cc6f44b70760eb3 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Fri, 6 May 2022 11:40:33 -0700 Subject: f2fs: introduce f2fs_gc_control to consolidate f2fs_gc parameters No functional change. - remove checkpoint=disable check for f2fs_write_checkpoint - get sec_freed all the time Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 7e915dbf3674..54ec9e543f09 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -644,19 +644,19 @@ TRACE_EVENT(f2fs_background_gc, TRACE_EVENT(f2fs_gc_begin, - TP_PROTO(struct super_block *sb, bool sync, bool background, + TP_PROTO(struct super_block *sb, int gc_type, bool no_bg_gc, long long dirty_nodes, long long dirty_dents, long long dirty_imeta, unsigned int free_sec, unsigned int free_seg, int reserved_seg, unsigned int prefree_seg), - TP_ARGS(sb, sync, background, dirty_nodes, dirty_dents, dirty_imeta, + TP_ARGS(sb, gc_type, no_bg_gc, dirty_nodes, dirty_dents, dirty_imeta, free_sec, free_seg, reserved_seg, prefree_seg), TP_STRUCT__entry( __field(dev_t, dev) - __field(bool, sync) - __field(bool, background) + __field(int, gc_type) + __field(bool, no_bg_gc) __field(long long, dirty_nodes) __field(long long, dirty_dents) __field(long long, dirty_imeta) @@ -668,8 +668,8 @@ TRACE_EVENT(f2fs_gc_begin, TP_fast_assign( __entry->dev = sb->s_dev; - __entry->sync = sync; - __entry->background = background; + __entry->gc_type = gc_type; + __entry->no_bg_gc = no_bg_gc; __entry->dirty_nodes = dirty_nodes; __entry->dirty_dents = dirty_dents; __entry->dirty_imeta = dirty_imeta; @@ -679,12 +679,12 @@ TRACE_EVENT(f2fs_gc_begin, __entry->prefree_seg = prefree_seg; ), - TP_printk("dev = (%d,%d), sync = %d, background = %d, nodes = %lld, " + TP_printk("dev = (%d,%d), gc_type = %s, no_background_GC = %d, nodes = %lld, " "dents = %lld, imeta = %lld, free_sec:%u, free_seg:%u, " "rsv_seg:%d, prefree_seg:%u", show_dev(__entry->dev), - __entry->sync, - __entry->background, + show_gc_type(__entry->gc_type), + (__entry->gc_type == BG_GC) ? __entry->no_bg_gc : -1, __entry->dirty_nodes, __entry->dirty_dents, __entry->dirty_imeta, -- cgit v1.2.3 From 0df65743537dd6e1c8b0924714f14dc367cba2be Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 11 May 2022 10:23:05 -0700 Subject: skbuff: replace a BUG_ON() with the new DEBUG_NET_WARN_ON_ONCE() Very few drivers actually have Kconfig knobs for adding -DDEBUG. 8 according to a quick grep, while there are 93 users of skb_checksum_none_assert(). Switch to the new DEBUG_NET_WARN_ON_ONCE() to catch bad skbs. Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20220511172305.1382810-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b91d225fdc13..9d82a8b6c8f1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -5048,9 +5048,7 @@ static inline void skb_forward_csum(struct sk_buff *skb) */ static inline void skb_checksum_none_assert(const struct sk_buff *skb) { -#ifdef DEBUG - BUG_ON(skb->ip_summed != CHECKSUM_NONE); -#endif + DEBUG_NET_WARN_ON_ONCE(skb->ip_summed != CHECKSUM_NONE); } bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off); -- cgit v1.2.3 From 465c3de42b5dcdf0fa8cf996a81de6ba0e8553a3 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 11 May 2022 12:50:16 +0300 Subject: net: dsa: introduce the dsa_cpu_ports() helper Similar to dsa_user_ports() which retrieves a port mask of all user ports, introduce dsa_cpu_ports() which retrieves the mask of all CPU ports of a switch. Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index efd33956df37..76257a9f0e1b 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -590,6 +590,17 @@ static inline u32 dsa_user_ports(struct dsa_switch *ds) return mask; } +static inline u32 dsa_cpu_ports(struct dsa_switch *ds) +{ + struct dsa_port *cpu_dp; + u32 mask = 0; + + dsa_switch_for_each_cpu_port(cpu_dp, ds) + mask |= BIT(cpu_dp->index); + + return mask; +} + /* Return the local port used to reach an arbitrary switch device */ static inline unsigned int dsa_routing_port(struct dsa_switch *ds, int device) { -- cgit v1.2.3 From 72c3b0c7359a6f91dd03e08b839adccd9d4268a8 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 11 May 2022 12:50:17 +0300 Subject: net: dsa: felix: manage host flooding using a specific driver callback At the time - commit 7569459a52c9 ("net: dsa: manage flooding on the CPU ports") - not introducing a dedicated switch callback for host flooding made sense, because for the only user, the felix driver, there was nothing different to do for the CPU port than set the flood flags on the CPU port just like on any other bridge port. There are 2 reasons why this approach is not good enough, however. (1) Other drivers, like sja1105, support configuring flooding as a function of {ingress port, egress port}, whereas the DSA ->port_bridge_flags() function only operates on an egress port. So with that driver we'd have useless host flooding from user ports which don't need it. (2) Even with the felix driver, support for multiple CPU ports makes it difficult to piggyback on ->port_bridge_flags(). The way in which the felix driver is going to support host-filtered addresses with multiple CPU ports is that it will direct these addresses towards both CPU ports (in a sort of multicast fashion), then restrict the forwarding to only one of the two using the forwarding masks. Consequently, flooding will also be enabled towards both CPU ports. However, ->port_bridge_flags() gets passed the index of a single CPU port, and that leaves the flood settings out of sync between the 2 CPU ports. This is to say, it's better to have a specific driver method for host flooding, which takes the user port as argument. This solves problem (1) by allowing the driver to do different things for different user ports, and problem (2) by abstracting the operation and letting the driver do whatever, rather than explicitly making the DSA core point to the CPU port it thinks needs to be touched. This new method also creates a problem, which is that cross-chip setups are not handled. However I don't have hardware right now where I can test what is the proper thing to do, and there isn't hardware compatible with multi-switch trees that supports host flooding. So it remains a problem to be tackled in the future. Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 76257a9f0e1b..cfb287b0d311 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -978,6 +978,8 @@ struct dsa_switch_ops { int (*port_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); + void (*port_set_host_flood)(struct dsa_switch *ds, int port, + bool uc, bool mc); /* * VLAN support -- cgit v1.2.3 From bacf93b0561937695e9c6c1dc1d8ed10ca80eb81 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 11 May 2022 12:50:18 +0300 Subject: net: dsa: remove port argument from ->change_tag_protocol() DSA has not supported (and probably will not support in the future either) independent tagging protocols per CPU port. Different switch drivers have different requirements, some may need to replicate some settings for each CPU port, some may need to apply some settings on a single CPU port, while some may have to configure some global settings and then some per-CPU-port settings. In any case, the current model where DSA calls ->change_tag_protocol for each CPU port turns out to be impractical for drivers where there are global things to be done. For example, felix calls dsa_tag_8021q_register(), which makes no sense per CPU port, so it suppresses the second call. Let drivers deal with replication towards all CPU ports, and remove the CPU port argument from the function prototype. Signed-off-by: Vladimir Oltean Acked-by: Luiz Angelo Daros de Luca Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index cfb287b0d311..14f07275852b 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -579,6 +579,10 @@ static inline bool dsa_is_user_port(struct dsa_switch *ds, int p) dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) +#define dsa_switch_for_each_cpu_port_continue_reverse(_dp, _ds) \ + dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \ + if (dsa_port_is_cpu((_dp))) + static inline u32 dsa_user_ports(struct dsa_switch *ds) { struct dsa_port *dp; @@ -803,7 +807,7 @@ struct dsa_switch_ops { enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds, int port, enum dsa_tag_protocol mprot); - int (*change_tag_protocol)(struct dsa_switch *ds, int port, + int (*change_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); /* * Method for switch drivers to connect to the tagging protocol driver -- cgit v1.2.3 From 15f6d01e4829cd2a2dc4f02a00c51d7cec1c736d Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 11 May 2022 13:06:35 +0300 Subject: net: mscc: ocelot: delete ocelot_port :: xmit_template This is no longer used since commit 7c4bb540e917 ("net: dsa: tag_ocelot: create separate tagger for Seville"). Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index e88bcfe4b2cd..919be1989c7c 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -670,7 +670,6 @@ struct ocelot_port { phy_interface_t phy_mode; - u8 *xmit_template; bool is_dsa_8021q_cpu; bool learn_ena; -- cgit v1.2.3 From 6d0be600477089026c76fe529bd96fad4cf69c3b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 11 May 2022 13:06:36 +0300 Subject: net: mscc: ocelot: minimize holes in struct ocelot_port Reorder members of struct ocelot_port to eliminate holes and reduce structure size. Pahole says: Before: struct ocelot_port { struct ocelot * ocelot; /* 0 8 */ struct regmap * target; /* 8 8 */ bool vlan_aware; /* 16 1 */ /* XXX 7 bytes hole, try to pack */ const struct ocelot_bridge_vlan * pvid_vlan; /* 24 8 */ unsigned int ptp_skbs_in_flight; /* 32 4 */ u8 ptp_cmd; /* 36 1 */ /* XXX 3 bytes hole, try to pack */ struct sk_buff_head tx_skbs; /* 40 96 */ /* --- cacheline 2 boundary (128 bytes) was 8 bytes ago --- */ u8 ts_id; /* 136 1 */ /* XXX 3 bytes hole, try to pack */ phy_interface_t phy_mode; /* 140 4 */ bool is_dsa_8021q_cpu; /* 144 1 */ bool learn_ena; /* 145 1 */ /* XXX 6 bytes hole, try to pack */ struct net_device * bond; /* 152 8 */ bool lag_tx_active; /* 160 1 */ /* XXX 1 byte hole, try to pack */ u16 mrp_ring_id; /* 162 2 */ /* XXX 4 bytes hole, try to pack */ struct net_device * bridge; /* 168 8 */ int bridge_num; /* 176 4 */ u8 stp_state; /* 180 1 */ /* XXX 3 bytes hole, try to pack */ int speed; /* 184 4 */ /* size: 192, cachelines: 3, members: 18 */ /* sum members: 161, holes: 7, sum holes: 27 */ /* padding: 4 */ }; After: struct ocelot_port { struct ocelot * ocelot; /* 0 8 */ struct regmap * target; /* 8 8 */ struct net_device * bond; /* 16 8 */ struct net_device * bridge; /* 24 8 */ const struct ocelot_bridge_vlan * pvid_vlan; /* 32 8 */ phy_interface_t phy_mode; /* 40 4 */ unsigned int ptp_skbs_in_flight; /* 44 4 */ struct sk_buff_head tx_skbs; /* 48 96 */ /* --- cacheline 2 boundary (128 bytes) was 16 bytes ago --- */ u16 mrp_ring_id; /* 144 2 */ u8 ptp_cmd; /* 146 1 */ u8 ts_id; /* 147 1 */ u8 stp_state; /* 148 1 */ bool vlan_aware; /* 149 1 */ bool is_dsa_8021q_cpu; /* 150 1 */ bool learn_ena; /* 151 1 */ bool lag_tx_active; /* 152 1 */ /* XXX 3 bytes hole, try to pack */ int bridge_num; /* 156 4 */ int speed; /* 160 4 */ /* size: 168, cachelines: 3, members: 18 */ /* sum members: 161, holes: 1, sum holes: 3 */ /* padding: 4 */ /* last cacheline: 40 bytes */ }; Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 919be1989c7c..904c15ca145e 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -659,28 +659,30 @@ struct ocelot_port { struct regmap *target; - bool vlan_aware; + struct net_device *bond; + struct net_device *bridge; + /* VLAN that untagged frames are classified to, on ingress */ const struct ocelot_bridge_vlan *pvid_vlan; + phy_interface_t phy_mode; + unsigned int ptp_skbs_in_flight; - u8 ptp_cmd; struct sk_buff_head tx_skbs; - u8 ts_id; - phy_interface_t phy_mode; + u16 mrp_ring_id; + u8 ptp_cmd; + u8 ts_id; + + u8 stp_state; + bool vlan_aware; bool is_dsa_8021q_cpu; bool learn_ena; - struct net_device *bond; bool lag_tx_active; - u16 mrp_ring_id; - - struct net_device *bridge; int bridge_num; - u8 stp_state; int speed; }; -- cgit v1.2.3 From 7e708760fc114f049df9dccb994e23d20866b310 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 11 May 2022 13:06:37 +0300 Subject: net: mscc: ocelot: move ocelot_port_private :: chip_port to ocelot_port :: index Currently the ocelot switch lib is unaware of the index of a struct ocelot_port, since that is kept in the encapsulating structures of outer drivers (struct dsa_port :: index, struct ocelot_port_private :: chip_port). With the upcoming increase in complexity associated with assigning DSA tag_8021q CPU ports to certain user ports, it becomes necessary for the switch lib to be able to retrieve the index of a certain ocelot_port. Therefore, introduce a new u8 to ocelot_port (same size as the chip_port used by the ocelot switchdev driver) and rework the existing code to populate and use it. Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 904c15ca145e..3b8c5a54fb00 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -675,6 +675,8 @@ struct ocelot_port { u8 ptp_cmd; u8 ts_id; + u8 index; + u8 stp_state; bool vlan_aware; bool is_dsa_8021q_cpu; -- cgit v1.2.3 From 8ea1eebb49a2dfee1dce621a638cc1626e542392 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 11 May 2022 17:05:52 -0700 Subject: net: inet: Remove count from inet_listen_hashbucket After commit 0ee58dad5b06 ("net: tcp6: prefer listeners bound to an address") and commit d9fbc7f6431f ("net: tcp: prefer listeners bound to an address"), the count is no longer used. This patch removes it. Signed-off-by: Martin KaFai Lau Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/net/inet_hashtables.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 98e1ec1a14f0..103fc7a30e60 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -111,7 +111,6 @@ struct inet_bind_hashbucket { #define LISTENING_NULLS_BASE (1U << 29) struct inet_listen_hashbucket { spinlock_t lock; - unsigned int count; union { struct hlist_head head; struct hlist_nulls_head nulls_head; -- cgit v1.2.3 From cae3873c5b3a4fcd9706fb461ff4e91bdf1f0120 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 11 May 2022 17:06:05 -0700 Subject: net: inet: Retire port only listening_hash The listen sk is currently stored in two hash tables, listening_hash (hashed by port) and lhash2 (hashed by port and address). After commit 0ee58dad5b06 ("net: tcp6: prefer listeners bound to an address") and commit d9fbc7f6431f ("net: tcp: prefer listeners bound to an address"), the TCP-SYN lookup fast path does not use listening_hash. The commit 05c0b35709c5 ("tcp: seq_file: Replace listening_hash with lhash2") also moved the seq_file (/proc/net/tcp) iteration usage from listening_hash to lhash2. There are still a few listening_hash usages left. One of them is inet_reuseport_add_sock() which uses the listening_hash to search a listen sk during the listen() system call. This turns out to be very slow on use cases that listen on many different VIPs at a popular port (e.g. 443). [ On top of the slowness in adding to the tail in the IPv6 case ]. The latter patch has a selftest to demonstrate this case. This patch takes this chance to move all remaining listening_hash usages to lhash2 and then retire listening_hash. Since most changes need to be done together, it is hard to cut the listening_hash to lhash2 switch into small patches. The changes in this patch is highlighted here for the review purpose. 1. Because of the listening_hash removal, lhash2 can use the sk->sk_nulls_node instead of the icsk->icsk_listen_portaddr_node. This will also keep the sk_unhashed() check to work as is after stop adding sk to listening_hash. The union is removed from inet_listen_hashbucket because only nulls_head is needed. 2. icsk->icsk_listen_portaddr_node and its helpers are removed. 3. The current lhash2 users needs to iterate with sk_nulls_node instead of icsk_listen_portaddr_node. One case is in the inet[6]_lhash2_lookup(). Another case is the seq_file iterator in tcp_ipv4.c. One thing to note is sk_nulls_next() is needed because the old inet_lhash2_for_each_icsk_continue() does a "next" first before iterating. 4. Move the remaining listening_hash usage to lhash2 inet_reuseport_add_sock() which this series is trying to improve. inet_diag.c and mptcp_diag.c are the final two remaining use cases and is moved to lhash2 now also. Signed-off-by: Martin KaFai Lau Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/net/inet_connection_sock.h | 2 -- include/net/inet_hashtables.h | 41 +------------------------------------- 2 files changed, 1 insertion(+), 42 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 3908296d103f..85cd695e7fd1 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -66,7 +66,6 @@ struct inet_connection_sock_af_ops { * @icsk_ulp_ops Pluggable ULP control hook * @icsk_ulp_data ULP private data * @icsk_clean_acked Clean acked data hook - * @icsk_listen_portaddr_node hash to the portaddr listener hashtable * @icsk_ca_state: Congestion control state * @icsk_retransmits: Number of unrecovered [RTO] timeouts * @icsk_pending: Scheduled timer event @@ -96,7 +95,6 @@ struct inet_connection_sock { const struct tcp_ulp_ops *icsk_ulp_ops; void __rcu *icsk_ulp_data; void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq); - struct hlist_node icsk_listen_portaddr_node; unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu); __u8 icsk_ca_state:5, icsk_ca_initialized:1, diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 103fc7a30e60..1b8706719d4f 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -111,10 +111,7 @@ struct inet_bind_hashbucket { #define LISTENING_NULLS_BASE (1U << 29) struct inet_listen_hashbucket { spinlock_t lock; - union { - struct hlist_head head; - struct hlist_nulls_head nulls_head; - }; + struct hlist_nulls_head nulls_head; }; /* This is for listening sockets, thus all sockets which possess wildcards. */ @@ -142,32 +139,8 @@ struct inet_hashinfo { /* The 2nd listener table hashed by local port and address */ unsigned int lhash2_mask; struct inet_listen_hashbucket *lhash2; - - /* All the above members are written once at bootup and - * never written again _or_ are predominantly read-access. - * - * Now align to a new cache line as all the following members - * might be often dirty. - */ - /* All sockets in TCP_LISTEN state will be in listening_hash. - * This is the only table where wildcard'd TCP sockets can - * exist. listening_hash is only hashed by local port number. - * If lhash2 is initialized, the same socket will also be hashed - * to lhash2 by port and address. - */ - struct inet_listen_hashbucket listening_hash[INET_LHTABLE_SIZE] - ____cacheline_aligned_in_smp; }; -#define inet_lhash2_for_each_icsk_continue(__icsk) \ - hlist_for_each_entry_continue(__icsk, icsk_listen_portaddr_node) - -#define inet_lhash2_for_each_icsk(__icsk, list) \ - hlist_for_each_entry(__icsk, list, icsk_listen_portaddr_node) - -#define inet_lhash2_for_each_icsk_rcu(__icsk, list) \ - hlist_for_each_entry_rcu(__icsk, list, icsk_listen_portaddr_node) - static inline struct inet_listen_hashbucket * inet_lhash2_bucket(struct inet_hashinfo *h, u32 hash) { @@ -229,23 +202,11 @@ static inline u32 inet_bhashfn(const struct net *net, const __u16 lport, void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, const unsigned short snum); -/* These can have wildcards, don't try too hard. */ -static inline u32 inet_lhashfn(const struct net *net, const unsigned short num) -{ - return (num + net_hash_mix(net)) & (INET_LHTABLE_SIZE - 1); -} - -static inline int inet_sk_listen_hashfn(const struct sock *sk) -{ - return inet_lhashfn(sock_net(sk), inet_sk(sk)->inet_num); -} - /* Caller must disable local BH processing. */ int __inet_inherit_port(const struct sock *sk, struct sock *child); void inet_put_port(struct sock *sk); -void inet_hashinfo_init(struct inet_hashinfo *h); void inet_hashinfo2_init(struct inet_hashinfo *h, const char *name, unsigned long numentries, int scale, unsigned long low_limit, -- cgit v1.2.3 From c9b516f16be5896a3d798f8efb03acbd2ceec715 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 12 May 2022 20:38:36 -0700 Subject: ELF, uapi: fixup ELF_ST_TYPE definition This is very theoretical compile failure: ELF_ST_TYPE(st_info = A) Cast will bind first and st_info will stop being lvalue: error: lvalue required as left operand of assignment Given that the only use of this macro is ELF_ST_TYPE(sym->st_info) where st_info is "unsigned char" I've decided to remove cast especially given that companion macro ELF_ST_BIND doesn't use cast. Link: https://lkml.kernel.org/r/Ymv7G1BeX4kt3obz@localhost.localdomain Signed-off-by: Alexey Dobriyan Acked-by: Kees Cook Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton --- include/uapi/linux/elf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 787c657bfae8..237f21a5e0f6 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -134,7 +134,7 @@ typedef __s64 Elf64_Sxword; #define STT_TLS 6 #define ELF_ST_BIND(x) ((x) >> 4) -#define ELF_ST_TYPE(x) (((unsigned int) x) & 0xf) +#define ELF_ST_TYPE(x) ((x) & 0xf) #define ELF32_ST_BIND(x) ELF_ST_BIND(x) #define ELF32_ST_TYPE(x) ELF_ST_TYPE(x) #define ELF64_ST_BIND(x) ELF_ST_BIND(x) -- cgit v1.2.3 From 58e4a2d27d3255e4e8c507fdc13734dccc9fc4c7 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 17 Dec 2021 09:28:46 +0300 Subject: extcon: Fix extcon_get_extcon_dev() error handling The extcon_get_extcon_dev() function returns error pointers on error, NULL when it's a -EPROBE_DEFER defer situation, and ERR_PTR(-ENODEV) when the CONFIG_EXTCON option is disabled. This is very complicated for the callers to handle and a number of them had bugs that would lead to an Oops. In real life, there are two things which prevented crashes. First, error pointers would only be returned if there was bug in the caller where they passed a NULL "extcon_name" and none of them do that. Second, only two out of the eight drivers will build when CONFIG_EXTCON is disabled. The normal way to write this would be to return -EPROBE_DEFER directly when appropriate and return NULL when CONFIG_EXTCON is disabled. Then the error handling is simple and just looks like: dev->edev = extcon_get_extcon_dev(acpi_dev_name(adev)); if (IS_ERR(dev->edev)) return PTR_ERR(dev->edev); For the two drivers which can build with CONFIG_EXTCON disabled, then extcon_get_extcon_dev() will now return NULL which is not treated as an error and the probe will continue successfully. Those two drivers are "typec_fusb302" and "max8997-battery". In the original code, the typec_fusb302 driver had an 800ms hang in tcpm_get_current_limit() but now that function is a no-op. For the max8997-battery driver everything should continue working as is. Signed-off-by: Dan Carpenter Reviewed-by: Hans de Goede Reviewed-by: Heikki Krogerus Reviewed-by: Guenter Roeck Acked-by: Sebastian Reichel Signed-off-by: Chanwoo Choi --- include/linux/extcon.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/extcon.h b/include/linux/extcon.h index 0c19010da77f..685401d94d39 100644 --- a/include/linux/extcon.h +++ b/include/linux/extcon.h @@ -296,7 +296,7 @@ static inline void devm_extcon_unregister_notifier_all(struct device *dev, static inline struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name) { - return ERR_PTR(-ENODEV); + return NULL; } static inline struct extcon_dev *extcon_find_edev_by_node(struct device_node *node) -- cgit v1.2.3 From 783eb354fb3dcd598e8e7e8a2ed88c0fb6ce5d2f Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 4 Apr 2022 15:19:41 +0900 Subject: agpgart.h: do not include from exported header Commit 35d0f1d54ecd ("include/uapi/linux/agpgart.h: include stdlib.h in userspace") included to fix the unknown size_t error, but I do not think it is the right fix. This header already uses __kernel_size_t a few lines below. Replace the remaining size_t, and stop including . Signed-off-by: Masahiro Yamada Signed-off-by: Arnd Bergmann Reviewed-by: Christoph Hellwig Reviewed-by: Nick Desaulniers --- include/uapi/linux/agpgart.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/agpgart.h b/include/uapi/linux/agpgart.h index f5251045181a..9cc3448c0b5b 100644 --- a/include/uapi/linux/agpgart.h +++ b/include/uapi/linux/agpgart.h @@ -52,7 +52,6 @@ #ifndef __KERNEL__ #include -#include struct agp_version { __u16 major; @@ -64,10 +63,10 @@ typedef struct _agp_info { __u32 bridge_id; /* bridge vendor/device */ __u32 agp_mode; /* mode info of bridge */ unsigned long aper_base;/* base of aperture */ - size_t aper_size; /* size of aperture */ - size_t pg_total; /* max pages (swap + system) */ - size_t pg_system; /* max pages (system) */ - size_t pg_used; /* current pages used */ + __kernel_size_t aper_size; /* size of aperture */ + __kernel_size_t pg_total; /* max pages (swap + system) */ + __kernel_size_t pg_system; /* max pages (system) */ + __kernel_size_t pg_used; /* current pages used */ } agp_info; typedef struct _agp_setup { -- cgit v1.2.3 From 7101d1279917e5c7fe897c275c5a0727fe90f3e3 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Fri, 18 Mar 2022 18:44:35 +0100 Subject: media: videobuf2-v4l2: Expose vb2_queue_is_busy() to drivers vb2 queue ownership is managed by the ioctl handler helpers (vb2_ioctl_*). There are however use cases where drivers can benefit from checking queue ownership, for instance when open-coding an ioctl handler that needs to perform additional checks before calling the corresponding vb2 operation. Expose the vb2_queue_is_busy() function in the videobuf2-v4l2.h header, and change its first argument to a struct vb2_queue pointer as the function name implies it operates on a queue, not a video_device. Signed-off-by: Laurent Pinchart Reviewed-by: Kieran Bingham Signed-off-by: Mauro Carvalho Chehab --- include/media/videobuf2-v4l2.h | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/videobuf2-v4l2.h b/include/media/videobuf2-v4l2.h index b66585e304e2..d818d9707695 100644 --- a/include/media/videobuf2-v4l2.h +++ b/include/media/videobuf2-v4l2.h @@ -302,10 +302,29 @@ __poll_t vb2_poll(struct vb2_queue *q, struct file *file, poll_table *wait); * The following functions are not part of the vb2 core API, but are simple * helper functions that you can use in your struct v4l2_file_operations, * struct v4l2_ioctl_ops and struct vb2_ops. They will serialize if vb2_queue->lock - * or video_device->lock is set, and they will set and test vb2_queue->owner - * to check if the calling filehandle is permitted to do the queuing operation. + * or video_device->lock is set, and they will set and test the queue owner + * (vb2_queue->owner) to check if the calling filehandle is permitted to do the + * queuing operation. */ +/** + * vb2_queue_is_busy() - check if the queue is busy + * @q: pointer to &struct vb2_queue with videobuf2 queue. + * @file: file through which the vb2 queue access is performed + * + * The queue is considered busy if it has an owner and the owner is not the + * @file. + * + * Queue ownership is acquired and checked by some of the v4l2_ioctl_ops helpers + * below. Drivers can also use this function directly when they need to + * open-code ioctl handlers, for instance to add additional checks between the + * queue ownership test and the call to the corresponding vb2 operation. + */ +static inline bool vb2_queue_is_busy(struct vb2_queue *q, struct file *file) +{ + return q->owner && q->owner != file->private_data; +} + /* struct v4l2_ioctl_ops helpers */ int vb2_ioctl_reqbufs(struct file *file, void *priv, -- cgit v1.2.3 From e3891b36364e85914fcb7a535656695a67e876a7 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 6 May 2022 14:46:46 +0200 Subject: media: cec-adap.c: reconfigure if the PA changes during configuration If the physical address changes (i.e. becomes invalid, then valid again) while the adapter is still claiming free logical addresses, then trigger a reconfiguration since any claimed LAs may now be stale. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/cec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/media/cec.h b/include/media/cec.h index 6f13b0222aa3..6c9b41fe9802 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -184,6 +184,7 @@ struct cec_adap_ops { * in order to transmit or receive CEC messages. This is usually a HW * limitation. * @is_configuring: the CEC adapter is configuring (i.e. claiming LAs) + * @must_reconfigure: while configuring, the PA changed, so reclaim LAs * @is_configured: the CEC adapter is configured (i.e. has claimed LAs) * @cec_pin_is_high: if true then the CEC pin is high. Only used with the * CEC pin framework. @@ -243,6 +244,7 @@ struct cec_adapter { u16 phys_addr; bool needs_hpd; bool is_configuring; + bool must_reconfigure; bool is_configured; bool cec_pin_is_high; bool adap_controls_phys_addr; -- cgit v1.2.3 From f9222f8ca18bcb1d55dd749b493b29fd8092fb82 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 10 May 2022 10:53:05 +0200 Subject: media: cec-adap.c: drop activate_cnt, use state info instead Using an activation counter to decide when the enable or disable the cec adapter is not the best approach and can lead to race conditions. Change this to determining the current status of the adapter, and enable or disable the adapter accordingly. It now only needs to be called whenever there is a chance that the state changes, and it can handle enabling/disabling monitoring as well if needed. This simplifies the code and it should be a more robust approach as well. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/cec.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/cec.h b/include/media/cec.h index 6c9b41fe9802..abee41ae02d0 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -183,6 +183,7 @@ struct cec_adap_ops { * @needs_hpd: if true, then the HDMI HotPlug Detect pin must be high * in order to transmit or receive CEC messages. This is usually a HW * limitation. + * @is_enabled: the CEC adapter is enabled * @is_configuring: the CEC adapter is configuring (i.e. claiming LAs) * @must_reconfigure: while configuring, the PA changed, so reclaim LAs * @is_configured: the CEC adapter is configured (i.e. has claimed LAs) @@ -194,7 +195,6 @@ struct cec_adap_ops { * Drivers that need this can set this field to true after the * cec_allocate_adapter() call. * @last_initiator: the initiator of the last transmitted message. - * @activate_cnt: number of times that CEC is activated * @monitor_all_cnt: number of filehandles monitoring all msgs * @monitor_pin_cnt: number of filehandles monitoring pin changes * @follower_cnt: number of filehandles in follower mode @@ -243,13 +243,13 @@ struct cec_adapter { u16 phys_addr; bool needs_hpd; + bool is_enabled; bool is_configuring; bool must_reconfigure; bool is_configured; bool cec_pin_is_high; bool adap_controls_phys_addr; u8 last_initiator; - u32 activate_cnt; u32 monitor_all_cnt; u32 monitor_pin_cnt; u32 follower_cnt; -- cgit v1.2.3 From 05abad857277dda198063017b00ba5b9fed2c0cb Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Fri, 1 Apr 2022 16:38:23 -0700 Subject: Bluetooth: HCI: Add HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN quirk This adds HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN quirk which can be used to mark HCI_Enhanced_Setup_Synchronous_Connection as broken even if its support command bit are set since some controller report it as supported but the command don't work properly with some configurations (e.g. BT_VOICE_TRANSPARENT/mSBC). Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 9 +++++++++ include/net/bluetooth/hci_core.h | 8 ++++++-- 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 69ef31cea582..62a9bb022aed 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -265,6 +265,15 @@ enum { * runtime suspend, because event filtering takes place there. */ HCI_QUIRK_BROKEN_FILTER_CLEAR_ALL, + + /* + * When this quirk is set, disables the use of + * HCI_OP_ENHANCED_SETUP_SYNC_CONN command to setup SCO connections. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. + */ + HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN, }; /* HCI device flags */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 62d7b81b1cb7..5a52a2018b56 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1495,8 +1495,12 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define privacy_mode_capable(dev) (use_ll_privacy(dev) && \ (hdev->commands[39] & 0x04)) -/* Use enhanced synchronous connection if command is supported */ -#define enhanced_sco_capable(dev) ((dev)->commands[29] & 0x08) +/* Use enhanced synchronous connection if command is supported and its quirk + * has not been set. + */ +#define enhanced_sync_conn_capable(dev) \ + (((dev)->commands[29] & 0x08) && \ + !test_bit(HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN, &(dev)->quirks)) /* Use ext scanning if set ext scan param and ext scan enable is supported */ #define use_ext_scan(dev) (((dev)->commands[37] & 0x20) && \ -- cgit v1.2.3 From 4915d50e300e96929d2462041d6f6c6f061167fd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 12 May 2022 09:56:01 -0700 Subject: inet: add READ_ONCE(sk->sk_bound_dev_if) in INET_MATCH() INET_MATCH() runs without holding a lock on the socket. We probably need to annotate most reads. This patch makes INET_MATCH() an inline function to ease our changes. v2: We remove the 32bit version of it, as modern compilers should generate the same code really, no need to try to be smarter. Also make 'struct net *net' the first argument. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 35 ++++++++++++++++------------------- include/net/sock.h | 3 --- 2 files changed, 16 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 1b8706719d4f..59d72024ad1d 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -255,7 +255,6 @@ static inline struct sock *inet_lookup_listener(struct net *net, ((__force __portpair)(((__u32)(__dport) << 16) | (__force __u32)(__be16)(__sport))) #endif -#if (BITS_PER_LONG == 64) #ifdef __BIG_ENDIAN #define INET_ADDR_COOKIE(__name, __saddr, __daddr) \ const __addrpair __name = (__force __addrpair) ( \ @@ -267,24 +266,22 @@ static inline struct sock *inet_lookup_listener(struct net *net, (((__force __u64)(__be32)(__daddr)) << 32) | \ ((__force __u64)(__be32)(__saddr))) #endif /* __BIG_ENDIAN */ -#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \ - (((__sk)->sk_portpair == (__ports)) && \ - ((__sk)->sk_addrpair == (__cookie)) && \ - (((__sk)->sk_bound_dev_if == (__dif)) || \ - ((__sk)->sk_bound_dev_if == (__sdif))) && \ - net_eq(sock_net(__sk), (__net))) -#else /* 32-bit arch */ -#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \ - const int __name __deprecated __attribute__((unused)) - -#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \ - (((__sk)->sk_portpair == (__ports)) && \ - ((__sk)->sk_daddr == (__saddr)) && \ - ((__sk)->sk_rcv_saddr == (__daddr)) && \ - (((__sk)->sk_bound_dev_if == (__dif)) || \ - ((__sk)->sk_bound_dev_if == (__sdif))) && \ - net_eq(sock_net(__sk), (__net))) -#endif /* 64-bit arch */ + +static inline bool INET_MATCH(struct net *net, const struct sock *sk, + const __addrpair cookie, const __portpair ports, + int dif, int sdif) +{ + int bound_dev_if; + + if (!net_eq(sock_net(sk), net) || + sk->sk_portpair != ports || + sk->sk_addrpair != cookie) + return false; + + /* Paired with WRITE_ONCE() from sock_bindtoindex_locked() */ + bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); + return bound_dev_if == dif || bound_dev_if == sdif; +} /* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need * not check it for lookups anymore, thanks Alexey. -DaveM diff --git a/include/net/sock.h b/include/net/sock.h index 73063c88a249..01edfde4257d 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -161,9 +161,6 @@ typedef __u64 __bitwise __addrpair; * for struct sock and struct inet_timewait_sock. */ struct sock_common { - /* skc_daddr and skc_rcv_saddr must be grouped on a 8 bytes aligned - * address on 64bit arches : cf INET_MATCH() - */ union { __addrpair skc_addrpair; struct { -- cgit v1.2.3 From 04c494e68a1340cb5c70d4704ac32d863dc64293 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 12 May 2022 14:14:56 -0700 Subject: Revert "tcp/dccp: get rid of inet_twsk_purge()" This reverts commits: 0dad4087a86a2cbe177404dc73f18ada26a2c390 ("tcp/dccp: get rid of inet_twsk_purge()") d507204d3c5cc57d9a8bdf0a477615bb59ea1611 ("tcp/dccp: add tw->tw_bslot") As Leonard pointed out, a newly allocated netns can happen to reuse a freed 'struct net'. While TCP TW timers were covered by my patches, other things were not: 1) Lookups in rx path (INET_MATCH() and INET6_MATCH()), as they look at 4-tuple plus the 'struct net' pointer. 2) /proc/net/tcp[6] and inet_diag, same reason. 3) hashinfo->bhash[], same reason. Fixing all this seems risky, lets instead revert. In the future, we might have a per netns tcp hash table, or a per netns list of timewait sockets... Fixes: 0dad4087a86a ("tcp/dccp: get rid of inet_twsk_purge()") Signed-off-by: Eric Dumazet Reported-by: Leonard Crestez Tested-by: Leonard Crestez Signed-off-by: David S. Miller --- include/net/inet_timewait_sock.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 463ae5d33eb0..5b47545f22d3 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -71,7 +71,6 @@ struct inet_timewait_sock { tw_tos : 8; u32 tw_txhash; u32 tw_priority; - u32 tw_bslot; /* bind bucket slot */ struct timer_list tw_timer; struct inet_bind_bucket *tw_tb; }; @@ -110,6 +109,8 @@ static inline void inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo void inet_twsk_deschedule_put(struct inet_timewait_sock *tw); +void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family); + static inline struct net *twsk_net(const struct inet_timewait_sock *twsk) { -- cgit v1.2.3 From 1339f24b336db5ded9811f3fe7b948e0de207785 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 7 May 2022 14:18:44 -0600 Subject: io_uring: allow allocated fixed files for openat/openat2 If the application passes in IORING_FILE_INDEX_ALLOC as the file_slot, then that's a hint to allocate a fixed file descriptor rather than have one be passed in directly. This can be useful for having io_uring manage the direct descriptor space. Normal open direct requests will complete with 0 for success, and < 0 in case of error. If io_uring is asked to allocated the direct descriptor, then the direct descriptor is returned in case of success. Reviewed-by: Hao Xu Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 06621a278cb6..b7f02a55032a 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -63,6 +63,15 @@ struct io_uring_sqe { __u64 __pad2[2]; }; +/* + * If sqe->file_index is set to this for opcodes that instantiate a new + * direct descriptor (like openat/openat2/accept), then io_uring will allocate + * an available direct descriptor instead of having the application pass one + * in. The picked direct descriptor will be returned in cqe->res, or -ENFILE + * if the space is full. + */ +#define IORING_FILE_INDEX_ALLOC (~0U) + enum { IOSQE_FIXED_FILE_BIT, IOSQE_IO_DRAIN_BIT, -- cgit v1.2.3 From a8da73a32b6e9271a613e5a0e90a8c35f40abeb8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 9 May 2022 09:29:14 -0600 Subject: io_uring: add flag for allocating a fully sparse direct descriptor space Currently to setup a fully sparse descriptor space upfront, the app needs to alloate an array of the full size and memset it to -1 and then pass that in. Make this a bit easier by allowing a flag that simply does this internally rather than needing to copy each slot separately. This works with IORING_REGISTER_FILES2 as the flag is set in struct io_uring_rsrc_register, and is only allow when the type is IORING_RSRC_FILE as this doesn't make sense for registered buffers. Reviewed-by: Hao Xu Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index b7f02a55032a..36ec43dc7bf9 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -396,9 +396,15 @@ struct io_uring_files_update { __aligned_u64 /* __s32 * */ fds; }; +/* + * Register a fully sparse file space, rather than pass in an array of all + * -1 file descriptors. + */ +#define IORING_RSRC_REGISTER_SPARSE (1U << 0) + struct io_uring_rsrc_register { __u32 nr; - __u32 resv; + __u32 flags; __u64 resv2; __aligned_u64 data; __aligned_u64 tags; -- cgit v1.2.3 From 59fba9eed5a736caa257df4738c57ff72492365f Mon Sep 17 00:00:00 2001 From: Yunfei Dong Date: Thu, 12 May 2022 04:19:47 +0200 Subject: media: mediatek: vcodec: support stateless H.264 decoding for mt8192 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Adds h264 lat and core architecture driver for mt8192, and the decode mode is frame based for stateless decoder. Signed-off-by: Yunfei Dong Tested-by: Nícolas F. R. A. Prado Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/remoteproc/mtk_scp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/remoteproc/mtk_scp.h b/include/linux/remoteproc/mtk_scp.h index b47416f7aeb8..7c2b7cc9fe6c 100644 --- a/include/linux/remoteproc/mtk_scp.h +++ b/include/linux/remoteproc/mtk_scp.h @@ -41,6 +41,8 @@ enum scp_ipi_id { SCP_IPI_ISP_FRAME, SCP_IPI_FD_CMD, SCP_IPI_CROS_HOST_CMD, + SCP_IPI_VDEC_LAT, + SCP_IPI_VDEC_CORE, SCP_IPI_NS_SERVICE = 0xFF, SCP_IPI_MAX = 0x100, }; -- cgit v1.2.3 From ea661ad6e1573d5b08c27444ff2ed403bf39ff66 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 10 May 2022 10:34:03 +0800 Subject: iommu/vt-d: Size Page Request Queue to avoid overflow condition PRQ overflow may cause I/O throughput congestion, resulting in unnecessary degradation of I/O performance. Appropriately increasing the length of PRQ can greatly reduce the occurrence of PRQ overflow. The count of maximum page requests that can be generated in parallel by a PCIe device is statically defined in the Outstanding Page Request Capacity field of the PCIe ATS configure space. The new length of PRQ is calculated by summing up the value of Outstanding Page Request Capacity register across all devices where Page Requests are supported on the real PR-capable platform (Intel Sapphire Rapids). The result is round to the nearest higher power of 2. The PRQ length is also double sized as the VT-d IOMMU driver only updates the Page Request Queue Head Register (PQH_REG) after processing the entire queue. Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20220421113558.3504874-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20220510023407.2759143-5-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-svm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index b3b125b332aa..207ef06ba3e1 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -9,7 +9,7 @@ #define __INTEL_SVM_H__ /* Page Request Queue depth */ -#define PRQ_ORDER 2 +#define PRQ_ORDER 4 #define PRQ_RING_MASK ((0x1000 << PRQ_ORDER) - 0x20) #define PRQ_DEPTH ((0x1000 << PRQ_ORDER) >> 5) -- cgit v1.2.3 From fc0051cb95909ab56bd8c929f24d48c9870c3e3a Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 10 May 2022 10:34:05 +0800 Subject: iommu/vt-d: Check domain force_snooping against attached devices As domain->force_snooping only impacts the devices attached with the domain, there's no need to check against all IOMMU units. On the other hand, force_snooping could be set on a domain no matter whether it has been attached or not, and once set it is an immutable flag. If no device attached, the operation always succeeds. Then this empty domain can be only attached to a device of which the IOMMU supports snoop control. Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20220508123525.1973626-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20220510023407.2759143-7-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 72e5d7900e71..4f29139bbfc3 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -540,6 +540,7 @@ struct dmar_domain { u8 has_iotlb_device: 1; u8 iommu_coherency: 1; /* indicate coherency of iommu access */ u8 force_snooping : 1; /* Create IOPTEs with snoop control */ + u8 set_pte_snp:1; struct list_head devices; /* all devices' list */ struct iova_domain iovad; /* iova's that belong to this domain */ -- cgit v1.2.3 From 4a18419f71cdf9155d2d2a6c79546f720978b990 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Mon, 9 May 2022 18:20:50 -0700 Subject: mm/mprotect: use mmu_gather Patch series "mm/mprotect: avoid unnecessary TLB flushes", v6. This patchset is intended to remove unnecessary TLB flushes during mprotect() syscalls. Once this patch-set make it through, similar and further optimizations for MADV_COLD and userfaultfd would be possible. Basically, there are 3 optimizations in this patch-set: 1. Use TLB batching infrastructure to batch flushes across VMAs and do better/fewer flushes. This would also be handy for later userfaultfd enhancements. 2. Avoid unnecessary TLB flushes. This optimization is the one that provides most of the performance benefits. Unlike previous versions, we now only avoid flushes that would not result in spurious page-faults. 3. Avoiding TLB flushes on change_huge_pmd() that are only needed to prevent the A/D bits from changing. Andrew asked for some benchmark numbers. I do not have an easy determinate macrobenchmark in which it is easy to show benefit. I therefore ran a microbenchmark: a loop that does the following on anonymous memory, just as a sanity check to see that time is saved by avoiding TLB flushes. The loop goes: mprotect(p, PAGE_SIZE, PROT_READ) mprotect(p, PAGE_SIZE, PROT_READ|PROT_WRITE) *p = 0; // make the page writable The test was run in KVM guest with 1 or 2 threads (the second thread was busy-looping). I measured the time (cycles) of each operation: 1 thread 2 threads mmots +patch mmots +patch PROT_READ 3494 2725 (-22%) 8630 7788 (-10%) PROT_READ|WRITE 3952 2724 (-31%) 9075 2865 (-68%) [ mmots = v5.17-rc6-mmots-2022-03-06-20-38 ] The exact numbers are really meaningless, but the benefit is clear. There are 2 interesting results though. (1) PROT_READ is cheaper, while one can expect it not to be affected. This is presumably due to TLB miss that is saved (2) Without memory access (*p = 0), the speedup of the patch is even greater. In that scenario mprotect(PROT_READ) also avoids the TLB flush. As a result both operations on the patched kernel take roughly ~1500 cycles (with either 1 or 2 threads), whereas on mmotm their cost is as high as presented in the table. This patch (of 3): change_pXX_range() currently does not use mmu_gather, but instead implements its own deferred TLB flushes scheme. This both complicates the code, as developers need to be aware of different invalidation schemes, and prevents opportunities to avoid TLB flushes or perform them in finer granularity. The use of mmu_gather for modified PTEs has benefits in various scenarios even if pages are not released. For instance, if only a single page needs to be flushed out of a range of many pages, only that page would be flushed. If a THP page is flushed, on x86 a single TLB invlpg instruction can be used instead of 512 instructions (or a full TLB flush, which would Linux would actually use by default). mprotect() over multiple VMAs requires a single flush. Use mmu_gather in change_pXX_range(). As the pages are not released, only record the flushed range using tlb_flush_pXX_range(). Handle THP similarly and get rid of flush_cache_range() which becomes redundant since tlb_start_vma() calls it when needed. Link: https://lkml.kernel.org/r/20220401180821.1986781-1-namit@vmware.com Link: https://lkml.kernel.org/r/20220401180821.1986781-2-namit@vmware.com Signed-off-by: Nadav Amit Acked-by: Peter Zijlstra (Intel) Cc: Andrea Arcangeli Cc: Andrew Cooper Cc: Andy Lutomirski Cc: Dave Hansen Cc: Peter Xu Cc: Thomas Gleixner Cc: Will Deacon Cc: Yu Zhao Cc: Nick Piggin Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 5 +++-- include/linux/mm.h | 5 +++-- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 2999190adc22..9a26bd10e083 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -36,8 +36,9 @@ int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr); bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd); -int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, - pgprot_t newprot, unsigned long cp_flags); +int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, + pmd_t *pmd, unsigned long addr, pgprot_t newprot, + unsigned long cp_flags); vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn, pgprot_t pgprot, bool write); diff --git a/include/linux/mm.h b/include/linux/mm.h index 5dc5005ccc9b..d63ba0e0e068 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1967,10 +1967,11 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma, #define MM_CP_UFFD_WP_ALL (MM_CP_UFFD_WP | \ MM_CP_UFFD_WP_RESOLVE) -extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start, +extern unsigned long change_protection(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long start, unsigned long end, pgprot_t newprot, unsigned long cp_flags); -extern int mprotect_fixup(struct vm_area_struct *vma, +extern int mprotect_fixup(struct mmu_gather *tlb, struct vm_area_struct *vma, struct vm_area_struct **pprev, unsigned long start, unsigned long end, unsigned long newflags); -- cgit v1.2.3 From c9fe66560bf2dc7d109754414e309888cb8c9ba9 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Mon, 9 May 2022 18:20:50 -0700 Subject: mm/mprotect: do not flush when not required architecturally Currently, using mprotect() to unprotect a memory region or uffd to unprotect a memory region causes a TLB flush. However, in such cases the PTE is often not modified (i.e., remain RO) and therefore not TLB flush is needed. Add an arch-specific pte_needs_flush() which tells whether a TLB flush is needed based on the old PTE and the new one. Implement an x86 pte_needs_flush(). Always flush the TLB when it is architecturally needed even when skipping a TLB flush might only result in a spurious page-faults by skipping the flush. Even with such conservative manner, we can in the future further refine the checks to test whether a PTE is present by only considering the architectural _PAGE_PRESENT flag instead of {pte|pmd}_preesnt(). For not be careful and use the latter. Link: https://lkml.kernel.org/r/20220401180821.1986781-3-namit@vmware.com Signed-off-by: Nadav Amit Cc: Andrea Arcangeli Cc: Andy Lutomirski Cc: Dave Hansen Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Cc: Yu Zhao Cc: Nick Piggin Cc: Andrew Cooper Cc: Peter Xu Signed-off-by: Andrew Morton --- include/asm-generic/tlb.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index eee6f7763a39..ff3e82553a76 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -658,6 +658,20 @@ static inline void tlb_flush_p4d_range(struct mmu_gather *tlb, } while (0) #endif +#ifndef pte_needs_flush +static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte) +{ + return true; +} +#endif + +#ifndef huge_pmd_needs_flush +static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd) +{ + return true; +} +#endif + #endif /* CONFIG_MMU */ #endif /* _ASM_GENERIC__TLB_H */ -- cgit v1.2.3 From 4f83145721f362c2f4d312edc4755269a2069488 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Mon, 9 May 2022 18:20:50 -0700 Subject: mm: avoid unnecessary flush on change_huge_pmd() Calls to change_protection_range() on THP can trigger, at least on x86, two TLB flushes for one page: one immediately, when pmdp_invalidate() is called by change_huge_pmd(), and then another one later (that can be batched) when change_protection_range() finishes. The first TLB flush is only necessary to prevent the dirty bit (and with a lesser importance the access bit) from changing while the PTE is modified. However, this is not necessary as the x86 CPUs set the dirty-bit atomically with an additional check that the PTE is (still) present. One caveat is Intel's Knights Landing that has a bug and does not do so. Leverage this behavior to eliminate the unnecessary TLB flush in change_huge_pmd(). Introduce a new arch specific pmdp_invalidate_ad() that only invalidates the access and dirty bit from further changes. Link: https://lkml.kernel.org/r/20220401180821.1986781-4-namit@vmware.com Signed-off-by: Nadav Amit Cc: Andrea Arcangeli Cc: Andrew Cooper Cc: Andy Lutomirski Cc: Dave Hansen Cc: Peter Xu Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Cc: Yu Zhao Cc: Nick Piggin Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 53750224e176..530b1817b58c 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -570,6 +570,26 @@ extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #endif +#ifndef __HAVE_ARCH_PMDP_INVALIDATE_AD + +/* + * pmdp_invalidate_ad() invalidates the PMD while changing a transparent + * hugepage mapping in the page tables. This function is similar to + * pmdp_invalidate(), but should only be used if the access and dirty bits would + * not be cleared by the software in the new PMD value. The function ensures + * that hardware changes of the access and dirty bits updates would not be lost. + * + * Doing so can allow in certain architectures to avoid a TLB flush in most + * cases. Yet, another TLB flush might be necessary later if the PMD update + * itself requires such flush (e.g., if protection was set to be stricter). Yet, + * even when a TLB flush is needed because of the update, the caller may be able + * to batch these TLB flushing operations, so fewer TLB flush operations are + * needed. + */ +extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); +#endif + #ifndef __HAVE_ARCH_PTE_SAME static inline int pte_same(pte_t pte_a, pte_t pte_b) { -- cgit v1.2.3 From f38adfef7e6bfe681d6602b6668be31fe1310ed0 Mon Sep 17 00:00:00 2001 From: "Fabio M. De Francesco" Date: Mon, 9 May 2022 18:20:51 -0700 Subject: mm/highmem: VM_BUG_ON() if offset + len > PAGE_SIZE Add VM_BUG_ON() bounds checking to make sure that, if "offset + len> PAGE_SIZE", memset() does not corrupt data in adjacent pages. Mainly to match all the similar functions in highmem.h. Link: https://lkml.kernel.org/r/20220426193020.8710-1-fmdefrancesco@gmail.com Signed-off-by: Fabio M. De Francesco Reviewed-by: Andrew Morton Cc: Ira Weiny Cc: Catalin Marinas Cc: "Matthew Wilcox (Oracle)" Cc: Peter Collingbourne Signed-off-by: Andrew Morton --- include/linux/highmem.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 39bb9b47fa9c..67720bfd6ade 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -358,6 +358,8 @@ static inline void memcpy_to_page(struct page *page, size_t offset, static inline void memzero_page(struct page *page, size_t offset, size_t len) { char *addr = kmap_local_page(page); + + VM_BUG_ON(offset + len > PAGE_SIZE); memset(addr + offset, 0, len); flush_dcache_page(page); kunmap_local(addr); -- cgit v1.2.3 From 152e56178ad72037bc6a2f08d4a608543bc67cdf Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Mon, 9 May 2022 18:20:51 -0700 Subject: mm/damon/core: add a function for damon_operations registration checks Patch series "mm/damon: allow users know which monitoring ops are available". DAMON users can configure it for vaious address spaces including virtual address spaces and the physical address space by setting its monitoring operations set with appropriate one for their purpose. However, there is no celan and simple way to know exactly which monitoring operations sets are available on the currently running kernel. This patchset adds functions for the purpose on DAMON's kernel API ('damon_is_registered_ops()') and sysfs interface ('avail_operations' file under each context directory). This patch (of 4): To know if a specific 'damon_operations' is registered, users need to check the kernel config or try 'damon_select_ops()' with the ops of the question, and then see if it successes. In the latter case, the user should also revert the change. To make the process simple and convenient, this commit adds a function for checking if a specific 'damon_operations' is registered or not. Link: https://lkml.kernel.org/r/20220426203843.45238-1-sj@kernel.org Link: https://lkml.kernel.org/r/20220426203843.45238-2-sj@kernel.org Signed-off-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/damon.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/damon.h b/include/linux/damon.h index f23cbfa4248d..73ff0e2d2a4d 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -509,6 +509,7 @@ int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, int damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes, ssize_t nr_schemes); int damon_nr_running_ctxs(void); +bool damon_is_registered_ops(enum damon_ops_id id); int damon_register_ops(struct damon_operations *ops); int damon_select_ops(struct damon_ctx *ctx, enum damon_ops_id id); -- cgit v1.2.3 From de6d01542a5c4f6fe6f0c65c14694b760f896acc Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Mon, 9 May 2022 18:20:52 -0700 Subject: mm/damon/vaddr: register a damon_operations for fixed virtual address ranges monitoring Patch series "support fixed virtual address ranges monitoring". The monitoring operations set for virtual address spaces automatically updates the monitoring target regions to cover entire mappings of the virtual address spaces as much as possible. Some users could have more information about their programs than kernel and therefore have interest in not entire regions but only specific regions. For such cases, the automatic monitoring target regions updates are only unnecessary overhead or distractions. This patchset adds supports for the use case on DAMON's kernel API (DAMON_OPS_FVADDR) and sysfs interface ('fvaddr' keyword for 'operations' sysfs file). This patch (of 3): The monitoring operations set for virtual address spaces automatically updates the monitoring target regions to cover entire mappings of the virtual address spaces as much as possible. Some users could have more information about their programs than kernel and therefore have interest in not entire regions but only specific regions. For such cases, the automatic monitoring target regions updates are only unnecessary overheads or distractions. For such cases, DAMON's API users can simply set the '->init()' and '->update()' of the DAMON context's '->ops' NULL, and set the target monitoring regions when creating the context. But, that would be a dirty hack. Worse yet, the hack is unavailable for DAMON user space interface users. To support the use case in a clean way that can easily exported to the user space, this commit adds another monitoring operations set called 'fvaddr', which is same to 'vaddr' but does not automatically update the monitoring regions. Instead, it will only respect the virtual address regions which have explicitly passed at the initial context creation. Note that this commit leave sysfs interface not supporting the feature yet. The support will be made in a following commit. Link: https://lkml.kernel.org/r/20220426231750.48822-1-sj@kernel.org Link: https://lkml.kernel.org/r/20220426231750.48822-2-sj@kernel.org Signed-off-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/damon.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/damon.h b/include/linux/damon.h index 73ff0e2d2a4d..09a5d0d02c00 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -261,10 +261,13 @@ struct damos { * enum damon_ops_id - Identifier for each monitoring operations implementation * * @DAMON_OPS_VADDR: Monitoring operations for virtual address spaces + * @DAMON_OPS_FVADDR: Monitoring operations for only fixed ranges of virtual + * address spaces * @DAMON_OPS_PADDR: Monitoring operations for the physical address space */ enum damon_ops_id { DAMON_OPS_VADDR, + DAMON_OPS_FVADDR, DAMON_OPS_PADDR, NR_DAMON_OPS, }; -- cgit v1.2.3 From 534aa1dc975ac883ad89110534585a96630802a0 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Mon, 9 May 2022 18:20:53 -0700 Subject: printk: stop including cache.h from printk.h An inclusion of cache.h in printk.h was added in 2014 in commit c28aa1f0a847 ("printk/cache: mark printk_once test variable __read_mostly") in order to bring in the definition of __read_mostly. The usage of __read_mostly was later removed in commit 3ec25826ae33 ("printk: Tie printk_once / printk_deferred_once into .data.once for reset") which made the inclusion of cache.h unnecessary, so remove it. We have a small amount of code that depended on the inclusion of cache.h from printk.h; fix that code to include the appropriate header. This fixes a circular inclusion on arm64 (linux/printk.h -> linux/cache.h -> asm/cache.h -> linux/kasan-enabled.h -> linux/static_key.h -> linux/jump_label.h -> linux/bug.h -> asm/bug.h -> linux/printk.h) that would otherwise be introduced by the next patch. Build tested using {allyesconfig,defconfig} x {arm64,x86_64}. Link: https://linux-review.googlesource.com/id/I8fd51f72c9ef1f2d6afd3b2cbc875aa4792c1fba Link: https://lkml.kernel.org/r/20220427195820.1716975-1-pcc@google.com Signed-off-by: Peter Collingbourne Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: David Rientjes Cc: Dmitry Vyukov Cc: Eric W. Biederman Cc: Herbert Xu Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Joonsoo Kim Cc: Kees Cook Cc: Pekka Enberg Cc: Roman Gushchin Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/printk.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index 1522df223c0f..8e8d74edf121 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -6,7 +6,6 @@ #include #include #include -#include #include #include -- cgit v1.2.3 From d949a8155d139aa890795b802004a196b7f00598 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Mon, 9 May 2022 18:20:53 -0700 Subject: mm: make minimum slab alignment a runtime property When CONFIG_KASAN_HW_TAGS is enabled we currently increase the minimum slab alignment to 16. This happens even if MTE is not supported in hardware or disabled via kasan=off, which creates an unnecessary memory overhead in those cases. Eliminate this overhead by making the minimum slab alignment a runtime property and only aligning to 16 if KASAN is enabled at runtime. On a DragonBoard 845c (non-MTE hardware) with a kernel built with CONFIG_KASAN_HW_TAGS, waiting for quiescence after a full Android boot I see the following Slab measurements in /proc/meminfo (median of 3 reboots): Before: 169020 kB After: 167304 kB [akpm@linux-foundation.org: make slab alignment type `unsigned int' to avoid casting] Link: https://linux-review.googlesource.com/id/I752e725179b43b144153f4b6f584ceb646473ead Link: https://lkml.kernel.org/r/20220427195820.1716975-2-pcc@google.com Signed-off-by: Peter Collingbourne Reviewed-by: Andrey Konovalov Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Acked-by: David Rientjes Reviewed-by: Catalin Marinas Acked-by: Vlastimil Babka Cc: Pekka Enberg Cc: Roman Gushchin Cc: Joonsoo Kim Cc: Herbert Xu Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Eric W. Biederman Cc: Kees Cook Signed-off-by: Andrew Morton --- include/linux/slab.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/slab.h b/include/linux/slab.h index 373b3ef99f4e..3d2f2a3ca17e 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -209,6 +209,18 @@ void kmem_dump_obj(void *object); #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) #endif +/* + * Arches can define this function if they want to decide the minimum slab + * alignment at runtime. The value returned by the function must be a power + * of two and >= ARCH_SLAB_MINALIGN. + */ +#ifndef arch_slab_minalign +static inline unsigned int arch_slab_minalign(void) +{ + return ARCH_SLAB_MINALIGN; +} +#endif + /* * kmalloc and friends return ARCH_KMALLOC_MINALIGN aligned * pointers. kmem_cache_alloc and friends return ARCH_SLAB_MINALIGN -- cgit v1.2.3 From b304c6f0d39d927a87e72a8ac6c89b96ac25f355 Mon Sep 17 00:00:00 2001 From: Hongchen Zhang Date: Mon, 9 May 2022 18:20:53 -0700 Subject: mm/swapops: make is_pmd_migration_entry more strict A pmd migration entry should first be a swap pmd,so use is_swap_pmd(pmd) instead of !pmd_present(pmd). On the other hand, some architecture (MIPS for example) may misjudge a pmd_none entry as a pmd migration entry. Link: https://lkml.kernel.org/r/1651131333-6386-1-git-send-email-zhanghongchen@loongson.cn Signed-off-by: Hongchen Zhang Acked-by: Peter Xu Cc: Alistair Popple Cc: Ralph Campbell Cc: Naoya Horiguchi Cc: Hugh Dickins Signed-off-by: Andrew Morton --- include/linux/swapops.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index d1b728904d4e..82265b055a0d 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -331,7 +331,7 @@ static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) static inline int is_pmd_migration_entry(pmd_t pmd) { - return !pmd_present(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); + return is_swap_pmd(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); } #else static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, -- cgit v1.2.3 From 6e74d2bf5a265113ca54a8323783d2f3fdde96b7 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Mon, 9 May 2022 18:20:54 -0700 Subject: mm/damon/core: add a new callback for watermarks checks Patch series "mm/damon: Support online tuning". Effects of DAMON and DAMON-based Operation Schemes highly depends on the configurations. Wrong configurations could even result in unexpected efficiency degradations. For finding a best configuration, repeating incremental configuration changes and results measurements, in other words, online tuning, could be helpful. Nevertheless, DAMON kernel API supports only restrictive online tuning. Worse yet, the sysfs-based DAMON user interface doesn't support online tuning at all. DAMON_RECLAIM also doesn't support online tuning. This patchset makes the DAMON kernel API, DAMON sysfs interface, and DAMON_RECLAIM supports online tuning. Sequence of patches ------------------- First two patches enhance DAMON online tuning for kernel API users. Specifically, patch 1 let kernel API users to be able to do DAMON online tuning without a restriction, and patch 2 makes error handling easier. Following seven patches (patches 3-9) refactor code for better readability and easier reuse of code fragments that will be useful for online tuning support. Patch 10 introduces DAMON callback based user request handling structure for DAMON sysfs interface, and patch 11 enables DAMON online tuning via DAMON sysfs interface. Documentation patch (patch 12) for usage of it follows. Patch 13 enables online tuning of DAMON_RECLAIM and finally patch 14 documents the DAMON_RECLAIM online tuning usage. This patch (of 14): For updating input parameters for running DAMON contexts, DAMON kernel API users can use the contexts' callbacks, as it is the safe place for context internal data accesses. When the context has DAMON-based operation schemes and all schemes are deactivated due to their watermarks, however, DAMON does nothing but only watermarks checks. As a result, no callbacks will be called back, and therefore the kernel API users cannot update the input parameters including monitoring attributes, DAMON-based operation schemes, and watermarks. To let users easily update such DAMON input parameters in such a case, this commit adds a new callback, 'after_wmarks_check()'. It will be called after each watermarks check. Users can do the online input parameters update in the callback even under the schemes deactivated case. Link: https://lkml.kernel.org/r/20220429160606.127307-2-sj@kernel.org Signed-off-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/damon.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/damon.h b/include/linux/damon.h index 09a5d0d02c00..6cb5ab5d8e9d 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -343,6 +343,7 @@ struct damon_operations { * struct damon_callback - Monitoring events notification callbacks. * * @before_start: Called before starting the monitoring. + * @after_wmarks_check: Called after each schemes' watermarks check. * @after_sampling: Called after each sampling. * @after_aggregation: Called after each aggregation. * @before_terminate: Called before terminating the monitoring. @@ -353,6 +354,11 @@ struct damon_operations { * respectively. Therefore, those are good places for installing and cleaning * @private. * + * The monitoring thread calls @after_wmarks_check after each DAMON-based + * operation schemes' watermarks check. If users need to make changes to the + * attributes of the monitoring context while it's deactivated due to the + * watermarks, this is the good place to do. + * * The monitoring thread calls @after_sampling and @after_aggregation for each * of the sampling intervals and aggregation intervals, respectively. * Therefore, users can safely access the monitoring results without additional @@ -365,6 +371,7 @@ struct damon_callback { void *private; int (*before_start)(struct damon_ctx *context); + int (*after_wmarks_check)(struct damon_ctx *context); int (*after_sampling)(struct damon_ctx *context); int (*after_aggregation)(struct damon_ctx *context); void (*before_terminate)(struct damon_ctx *context); -- cgit v1.2.3 From d0723bc04185b15ed96ade0a0bf9277ef00008db Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Mon, 9 May 2022 18:20:55 -0700 Subject: mm/damon/vaddr: move 'damon_set_regions()' to core This commit moves 'damon_set_regions()' from vaddr to core, as it is aimed to be used by not only 'vaddr' but also other parts of DAMON. Link: https://lkml.kernel.org/r/20220429160606.127307-5-sj@kernel.org Signed-off-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/damon.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/damon.h b/include/linux/damon.h index 6cb5ab5d8e9d..d1e6ee28a2ff 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -494,6 +494,8 @@ static inline void damon_insert_region(struct damon_region *r, void damon_add_region(struct damon_region *r, struct damon_target *t); void damon_destroy_region(struct damon_region *r, struct damon_target *t); +int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges, + unsigned int nr_ranges); struct damos *damon_new_scheme( unsigned long min_sz_region, unsigned long max_sz_region, -- cgit v1.2.3 From 679d103319101800567c8bb7e341b5eee39f6685 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:52 -0700 Subject: mm: introduce PTE_MARKER swap entry Patch series "userfaultfd-wp: Support shmem and hugetlbfs", v8. Overview ======== Userfaultfd-wp anonymous support was merged two years ago. There're quite a few applications that started to leverage this capability either to take snapshots for user-app memory, or use it for full user controled swapping. This series tries to complete the feature for uffd-wp so as to cover all the RAM-based memory types. So far uffd-wp is the only missing piece of the rest features (uffd-missing & uffd-minor mode). One major reason to do so is that anonymous pages are sometimes not satisfying the need of applications, and there're growing users of either shmem and hugetlbfs for either sharing purpose (e.g., sharing guest mem between hypervisor process and device emulation process, shmem local live migration for upgrades), or for performance on tlb hits. All these mean that if a uffd-wp app wants to switch to any of the memory types, it'll stop working. I think it's worthwhile to have the kernel to cover all these aspects. This series chose to protect pages in pte level not page level. One major reason is safety. I have no idea how we could make it safe if any of the uffd-privileged app can wr-protect a page that any other application can use. It means this app can block any process potentially for any time it wants. The other reason is that it aligns very well with not only the anonymous uffd-wp solution, but also uffd as a whole. For example, userfaultfd is implemented fundamentally based on VMAs. We set flags to VMAs showing the status of uffd tracking. For another per-page based protection solution, it'll be crossing the fundation line on VMA-based, and it could simply be too far away already from what's called userfaultfd. PTE markers =========== The patchset is based on the idea called PTE markers. It was discussed in one of the mm alignment sessions, proposed starting from v6, and this is the 2nd version of it using PTE marker idea. PTE marker is a new type of swap entry that is ony applicable to file backed memories like shmem and hugetlbfs. It's used to persist some pte-level information even if the original present ptes in pgtable are zapped. Logically pte markers can store more than uffd-wp information, but so far only one bit is used for uffd-wp purpose. When the pte marker is installed with uffd-wp bit set, it means this pte is wr-protected by uffd. It solves the problem on e.g. file-backed memory mapped ptes got zapped due to any reason (e.g. thp split, or swapped out), we can still keep the wr-protect information in the ptes. Then when the page fault triggers again, we'll know this pte is wr-protected so we can treat the pte the same as a normal uffd wr-protected pte. The extra information is encoded into the swap entry, or swp_offset to be explicit, with the swp_type being PTE_MARKER. So far uffd-wp only uses one bit out of the swap entry, the rest bits of swp_offset are still reserved for other purposes. There're two configs to enable/disable PTE markers: CONFIG_PTE_MARKER CONFIG_PTE_MARKER_UFFD_WP We can set !PTE_MARKER to completely disable all the PTE markers, along with uffd-wp support. I made two config so we can also enable PTE marker but disable uffd-wp file-backed for other purposes. At the end of current series, I'll enable CONFIG_PTE_MARKER by default, but that patch is standalone and if anyone worries about having it by default, we can also consider turn it off by dropping that oneliner patch. So far I don't see a huge risk of doing so, so I kept that patch. In most cases, PTE markers should be treated as none ptes. It is because that unlike most of the other swap entry types, there's no PFN or block offset information encoded into PTE markers but some extra well-defined bits showing the status of the pte. These bits should only be used as extra data when servicing an upcoming page fault, and then we behave as if it's a none pte. I did spend a lot of time observing all the pte_none() users this time. It is indeed a challenge because there're a lot, and I hope I didn't miss a single of them when we should take care of pte markers. Luckily, I don't think it'll need to be considered in many cases, for example: boot code, arch code (especially non-x86), kernel-only page handlings (e.g. CPA), or device driver codes when we're tackling with pure PFN mappings. I introduced pte_none_mostly() in this series when we need to handle pte markers the same as none pte, the "mostly" is the other way to write "either none pte or a pte marker". I didn't replace pte_none() to cover pte markers for below reasons: - Very rare case of pte_none() callers will handle pte markers. E.g., all the kernel pages do not require knowledge of pte markers. So we don't pollute the major use cases. - Unconditionally change pte_none() semantics could confuse people, because pte_none() existed for so long a time. - Unconditionally change pte_none() semantics could make pte_none() slower even if in many cases pte markers do not exist. - There're cases where we'd like to handle pte markers differntly from pte_none(), so a full replace is also impossible. E.g. khugepaged should still treat pte markers as normal swap ptes rather than none ptes, because pte markers will always need a fault-in to merge the marker with a valid pte. Or the smap code will need to parse PTE markers not none ptes. Patch Layout ============ Introducing PTE marker and uffd-wp bit in PTE marker: mm: Introduce PTE_MARKER swap entry mm: Teach core mm about pte markers mm: Check against orig_pte for finish_fault() mm/uffd: PTE_MARKER_UFFD_WP Adding support for shmem uffd-wp: mm/shmem: Take care of UFFDIO_COPY_MODE_WP mm/shmem: Handle uffd-wp special pte in page fault handler mm/shmem: Persist uffd-wp bit across zapping for file-backed mm/shmem: Allow uffd wr-protect none pte for file-backed mem mm/shmem: Allows file-back mem to be uffd wr-protected on thps mm/shmem: Handle uffd-wp during fork() Adding support for hugetlbfs uffd-wp: mm/hugetlb: Introduce huge pte version of uffd-wp helpers mm/hugetlb: Hook page faults for uffd write protection mm/hugetlb: Take care of UFFDIO_COPY_MODE_WP mm/hugetlb: Handle UFFDIO_WRITEPROTECT mm/hugetlb: Handle pte markers in page faults mm/hugetlb: Allow uffd wr-protect none ptes mm/hugetlb: Only drop uffd-wp special pte if required mm/hugetlb: Handle uffd-wp during fork() Misc handling on the rest mm for uffd-wp file-backed: mm/khugepaged: Don't recycle vma pgtable if uffd-wp registered mm/pagemap: Recognize uffd-wp bit for shmem/hugetlbfs Enabling of uffd-wp on file-backed memory: mm/uffd: Enable write protection for shmem & hugetlbfs mm: Enable PTE markers by default selftests/uffd: Enable uffd-wp for shmem/hugetlbfs Tests ===== - Compile test on x86_64 and aarch64 on different configs - Kernel selftests - uffd-test [0] - Umapsort [1,2] test for shmem/hugetlb, with swap on/off [0] https://github.com/xzpeter/clibs/tree/master/uffd-test [1] https://github.com/xzpeter/umap-apps/tree/peter [2] https://github.com/xzpeter/umap/tree/peter-shmem-hugetlbfs This patch (of 23): Introduces a new swap entry type called PTE_MARKER. It can be installed for any pte that maps a file-backed memory when the pte is temporarily zapped, so as to maintain per-pte information. The information that kept in the pte is called a "marker". Here we define the marker as "unsigned long" just to match pgoff_t, however it will only work if it still fits in swp_offset(), which is e.g. currently 58 bits on x86_64. A new config CONFIG_PTE_MARKER is introduced too; it's by default off. A bunch of helpers are defined altogether to service the rest of the pte marker code. [peterx@redhat.com: fixup] Link: https://lkml.kernel.org/r/Yk2rdB7SXZf+2BDF@xz-m1.local Link: https://lkml.kernel.org/r/20220405014646.13522-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20220405014646.13522-2-peterx@redhat.com Signed-off-by: Peter Xu Cc: Mike Kravetz Cc: David Hildenbrand Cc: Matthew Wilcox Cc: Alistair Popple Cc: Nadav Amit Cc: Axel Rasmussen Cc: Andrea Arcangeli Cc: "Kirill A . Shutemov" Cc: Hugh Dickins Cc: Jerome Glisse Cc: Mike Rapoport Signed-off-by: Andrew Morton --- include/asm-generic/hugetlb.h | 9 +++++ include/linux/swap.h | 15 ++++++++- include/linux/swapops.h | 78 +++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 101 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h index 8e1e6244a89d..f39cad20ffc6 100644 --- a/include/asm-generic/hugetlb.h +++ b/include/asm-generic/hugetlb.h @@ -2,6 +2,9 @@ #ifndef _ASM_GENERIC_HUGETLB_H #define _ASM_GENERIC_HUGETLB_H +#include +#include + static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot) { return mk_pte(page, pgprot); @@ -80,6 +83,12 @@ static inline int huge_pte_none(pte_t pte) } #endif +/* Please refer to comments above pte_none_mostly() for the usage */ +static inline int huge_pte_none_mostly(pte_t pte) +{ + return huge_pte_none(pte) || is_pte_marker(pte); +} + #ifndef __HAVE_ARCH_HUGE_PTE_WRPROTECT static inline pte_t huge_pte_wrprotect(pte_t pte) { diff --git a/include/linux/swap.h b/include/linux/swap.h index 7daae5a4b3e1..5553189d0215 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -55,6 +55,19 @@ static inline int current_is_kswapd(void) * actions on faults. */ +/* + * PTE markers are used to persist information onto PTEs that are mapped with + * file-backed memories. As its name "PTE" hints, it should only be applied to + * the leaves of pgtables. + */ +#ifdef CONFIG_PTE_MARKER +#define SWP_PTE_MARKER_NUM 1 +#define SWP_PTE_MARKER (MAX_SWAPFILES + SWP_HWPOISON_NUM + \ + SWP_MIGRATION_NUM + SWP_DEVICE_NUM) +#else +#define SWP_PTE_MARKER_NUM 0 +#endif + /* * Unaddressable device memory support. See include/linux/hmm.h and * Documentation/vm/hmm.rst. Short description is we need struct pages for @@ -107,7 +120,7 @@ static inline int current_is_kswapd(void) #define MAX_SWAPFILES \ ((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \ - SWP_MIGRATION_NUM - SWP_HWPOISON_NUM) + SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - SWP_PTE_MARKER_NUM) /* * Magic header for a swap area. The first part of the union is diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 82265b055a0d..bb70da461b7d 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -274,6 +274,84 @@ static inline int is_readable_migration_entry(swp_entry_t entry) #endif +typedef unsigned long pte_marker; + +#define PTE_MARKER_MASK (0) + +#ifdef CONFIG_PTE_MARKER + +static inline swp_entry_t make_pte_marker_entry(pte_marker marker) +{ + return swp_entry(SWP_PTE_MARKER, marker); +} + +static inline bool is_pte_marker_entry(swp_entry_t entry) +{ + return swp_type(entry) == SWP_PTE_MARKER; +} + +static inline pte_marker pte_marker_get(swp_entry_t entry) +{ + return swp_offset(entry) & PTE_MARKER_MASK; +} + +static inline bool is_pte_marker(pte_t pte) +{ + return is_swap_pte(pte) && is_pte_marker_entry(pte_to_swp_entry(pte)); +} + +#else /* CONFIG_PTE_MARKER */ + +static inline swp_entry_t make_pte_marker_entry(pte_marker marker) +{ + /* This should never be called if !CONFIG_PTE_MARKER */ + WARN_ON_ONCE(1); + return swp_entry(0, 0); +} + +static inline bool is_pte_marker_entry(swp_entry_t entry) +{ + return false; +} + +static inline pte_marker pte_marker_get(swp_entry_t entry) +{ + return 0; +} + +static inline bool is_pte_marker(pte_t pte) +{ + return false; +} + +#endif /* CONFIG_PTE_MARKER */ + +static inline pte_t make_pte_marker(pte_marker marker) +{ + return swp_entry_to_pte(make_pte_marker_entry(marker)); +} + +/* + * This is a special version to check pte_none() just to cover the case when + * the pte is a pte marker. It existed because in many cases the pte marker + * should be seen as a none pte; it's just that we have stored some information + * onto the none pte so it becomes not-none any more. + * + * It should be used when the pte is file-backed, ram-based and backing + * userspace pages, like shmem. It is not needed upon pgtables that do not + * support pte markers at all. For example, it's not needed on anonymous + * memory, kernel-only memory (including when the system is during-boot), + * non-ram based generic file-system. It's fine to be used even there, but the + * extra pte marker check will be pure overhead. + * + * For systems configured with !CONFIG_PTE_MARKER this will be automatically + * optimized to pte_none(). + */ +static inline int pte_none_mostly(pte_t pte) +{ + return pte_none(pte) || is_pte_marker(pte); +} + static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) { struct page *p = pfn_to_page(swp_offset(entry)); -- cgit v1.2.3 From f46f2adecdcc1ba0799383e67fe98f65f41fea5c Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:52 -0700 Subject: mm: check against orig_pte for finish_fault() This patch allows do_fault() to trigger on !pte_none() cases too. This prepares for the pte markers to be handled by do_fault() just like none pte. To achieve this, instead of unconditionally check against pte_none() in finish_fault(), we may hit the case that the orig_pte was some pte marker so what we want to do is to replace the pte marker with some valid pte entry. Then if orig_pte was set we'd want to check the current *pte (under pgtable lock) against orig_pte rather than none pte. Right now there's no solid way to safely reference orig_pte because when pmd is not allocated handle_pte_fault() will not initialize orig_pte, so it's not safe to reference it. There's another solution proposed before this patch to do pte_clear() for vmf->orig_pte for pmd==NULL case, however it turns out it'll break arm32 because arm32 could have assumption that pte_t* pointer will always reside on a real ram32 pgtable, not any kernel stack variable. To solve this, we add a new flag FAULT_FLAG_ORIG_PTE_VALID, and it'll be set along with orig_pte when there is valid orig_pte, or it'll be cleared when orig_pte was not initialized. It'll be updated every time we call handle_pte_fault(), so e.g. if a page fault retry happened it'll be properly updated along with orig_pte. [1] https://lore.kernel.org/lkml/710c48c9-406d-e4c5-a394-10501b951316@samsung.com/ [akpm@linux-foundation.org: coding-style cleanups] [peterx@redhat.com: fix crash reported by Marek] Link: https://lkml.kernel.org/r/Ylb9rXJyPm8/ao8f@xz-m1.local Link: https://lkml.kernel.org/r/20220405014836.14077-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Alistair Popple Tested-by: Marek Szyprowski Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7216d77a5884..dd382270ae40 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -822,6 +822,8 @@ typedef struct { * @FAULT_FLAG_UNSHARE: The fault is an unsharing request to unshare (and mark * exclusive) a possibly shared anonymous page that is * mapped R/O. + * @FAULT_FLAG_ORIG_PTE_VALID: whether the fault has vmf->orig_pte cached. + * We should only access orig_pte if this flag set. * * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify * whether we would allow page faults to retry by specifying these two @@ -858,6 +860,7 @@ enum fault_flag { FAULT_FLAG_INSTRUCTION = 1 << 8, FAULT_FLAG_INTERRUPTIBLE = 1 << 9, FAULT_FLAG_UNSHARE = 1 << 10, + FAULT_FLAG_ORIG_PTE_VALID = 1 << 11, }; #endif /* _LINUX_MM_TYPES_H */ -- cgit v1.2.3 From 1db9dbc2ef05205bf1022f9b14aa29b1dd8efd7e Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:52 -0700 Subject: mm/uffd: PTE_MARKER_UFFD_WP This patch introduces the 1st user of pte marker: the uffd-wp marker. When the pte marker is installed with the uffd-wp bit set, it means this pte was wr-protected by uffd. We will use this special pte to arm the ptes that got either unmapped or swapped out for a file-backed region that was previously wr-protected. This special pte could trigger a page fault just like swap entries. This idea is greatly inspired by Hugh and Andrea in the discussion, which is referenced in the links below. Some helpers are introduced to detect whether a swap pte is uffd wr-protected. After the pte marker introduced, one swap pte can be wr-protected in two forms: either it is a normal swap pte and it has _PAGE_SWP_UFFD_WP set, or it's a pte marker that has PTE_MARKER_UFFD_WP set. [peterx@redhat.com: fixup] Link: https://lkml.kernel.org/r/YkzKiM8tI4+qOfXF@xz-m1.local Link: https://lore.kernel.org/lkml/20201126222359.8120-1-peterx@redhat.com/ Link: https://lore.kernel.org/lkml/20201130230603.46187-1-peterx@redhat.com/ Link: https://lkml.kernel.org/r/20220405014838.14131-1-peterx@redhat.com Signed-off-by: Peter Xu Suggested-by: Andrea Arcangeli Suggested-by: Hugh Dickins Cc: Alistair Popple Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/swapops.h | 3 ++- include/linux/userfaultfd_k.h | 47 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 49 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index bb70da461b7d..09945342bf76 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -276,7 +276,8 @@ static inline int is_readable_migration_entry(swp_entry_t entry) typedef unsigned long pte_marker; -#define PTE_MARKER_MASK (0) +#define PTE_MARKER_UFFD_WP BIT(0) +#define PTE_MARKER_MASK (PTE_MARKER_UFFD_WP) #ifdef CONFIG_PTE_MARKER diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 33cea484d1ad..3354d9ddc35f 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -15,6 +15,8 @@ #include #include +#include +#include #include /* The set of all possible UFFD-related VM flags. */ @@ -236,4 +238,49 @@ static inline void userfaultfd_unmap_complete(struct mm_struct *mm, #endif /* CONFIG_USERFAULTFD */ +static inline bool pte_marker_entry_uffd_wp(swp_entry_t entry) +{ +#ifdef CONFIG_PTE_MARKER_UFFD_WP + return is_pte_marker_entry(entry) && + (pte_marker_get(entry) & PTE_MARKER_UFFD_WP); +#else + return false; +#endif +} + +static inline bool pte_marker_uffd_wp(pte_t pte) +{ +#ifdef CONFIG_PTE_MARKER_UFFD_WP + swp_entry_t entry; + + if (!is_swap_pte(pte)) + return false; + + entry = pte_to_swp_entry(pte); + + return pte_marker_entry_uffd_wp(entry); +#else + return false; +#endif +} + +/* + * Returns true if this is a swap pte and was uffd-wp wr-protected in either + * forms (pte marker or a normal swap pte), false otherwise. + */ +static inline bool pte_swp_uffd_wp_any(pte_t pte) +{ +#ifdef CONFIG_PTE_MARKER_UFFD_WP + if (!is_swap_pte(pte)) + return false; + + if (pte_swp_uffd_wp(pte)) + return true; + + if (pte_marker_uffd_wp(pte)) + return true; +#endif + return false; +} + #endif /* _LINUX_USERFAULTFD_K_H */ -- cgit v1.2.3 From 8ee79edff6d3b43b2d0c1e41f92b32e128988b22 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:52 -0700 Subject: mm/shmem: take care of UFFDIO_COPY_MODE_WP Pass wp_copy into shmem_mfill_atomic_pte() through the stack, then apply the UFFD_WP bit properly when the UFFDIO_COPY on shmem is with UFFDIO_COPY_MODE_WP. wp_copy lands mfill_atomic_install_pte() finally. Note: we must do pte_wrprotect() if !writable in mfill_atomic_install_pte(), as mk_pte() could return a writable pte (e.g., when VM_SHARED on a shmem file). Link: https://lkml.kernel.org/r/20220405014841.14185-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/shmem_fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 3e915cc550bc..a68f982f22d1 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -145,11 +145,11 @@ extern int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, - bool zeropage, + bool zeropage, bool wp_copy, struct page **pagep); #else /* !CONFIG_SHMEM */ #define shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, \ - src_addr, zeropage, pagep) ({ BUG(); 0; }) + src_addr, zeropage, wp_copy, pagep) ({ BUG(); 0; }) #endif /* CONFIG_SHMEM */ #endif /* CONFIG_USERFAULTFD */ -- cgit v1.2.3 From 9c28a205c06123b9f0a0c4d819ece9f5f552d004 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:53 -0700 Subject: mm/shmem: handle uffd-wp special pte in page fault handler File-backed memories are prone to unmap/swap so the ptes are always unstable, because they can be easily faulted back later using the page cache. This could lead to uffd-wp getting lost when unmapping or swapping out such memory. One example is shmem. PTE markers are needed to store those information. This patch prepares it by handling uffd-wp pte markers first it is applied elsewhere, so that the page fault handler can recognize uffd-wp pte markers. The handling of uffd-wp pte markers is similar to missing fault, it's just that we'll handle this "missing fault" when we see the pte markers, meanwhile we need to make sure the marker information is kept during processing the fault. This is a slow path of uffd-wp handling, because zapping of wr-protected shmem ptes should be rare. So far it should only trigger in two conditions: (1) When trying to punch holes in shmem_fallocate(), there is an optimization to zap the pgtables before evicting the page. (2) When swapping out shmem pages. Because of this, the page fault handling is simplifed too by not sending the wr-protect message in the 1st page fault, instead the page will be installed read-only, so the uffd-wp message will be generated in the next fault, which will trigger the do_wp_page() path of general uffd-wp handling. Disable fault-around for all uffd-wp registered ranges for extra safety just like uffd-minor fault, and clean the code up. Link: https://lkml.kernel.org/r/20220405014844.14239-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/userfaultfd_k.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 3354d9ddc35f..e7afcdfd4b46 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -96,6 +96,18 @@ static inline bool uffd_disable_huge_pmd_share(struct vm_area_struct *vma) return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR); } +/* + * Don't do fault around for either WP or MINOR registered uffd range. For + * MINOR registered range, fault around will be a total disaster and ptes can + * be installed without notifications; for WP it should mostly be fine as long + * as the fault around checks for pte_none() before the installation, however + * to be super safe we just forbid it. + */ +static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) +{ + return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR); +} + static inline bool userfaultfd_missing(struct vm_area_struct *vma) { return vma->vm_flags & VM_UFFD_MISSING; @@ -236,6 +248,11 @@ static inline void userfaultfd_unmap_complete(struct mm_struct *mm, { } +static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) +{ + return false; +} + #endif /* CONFIG_USERFAULTFD */ static inline bool pte_marker_entry_uffd_wp(swp_entry_t entry) -- cgit v1.2.3 From 999dad824c39ed14dee7c4412aae531ba9e74a90 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:53 -0700 Subject: mm/shmem: persist uffd-wp bit across zapping for file-backed File-backed memory is prone to being unmapped at any time. It means all information in the pte will be dropped, including the uffd-wp flag. To persist the uffd-wp flag, we'll use the pte markers. This patch teaches the zap code to understand uffd-wp and know when to keep or drop the uffd-wp bit. Add a new flag ZAP_FLAG_DROP_MARKER and set it in zap_details when we don't want to persist such an information, for example, when destroying the whole vma, or punching a hole in a shmem file. For the rest cases we should never drop the uffd-wp bit, or the wr-protect information will get lost. The new ZAP_FLAG_DROP_MARKER needs to be put into mm.h rather than memory.c because it'll be further referenced in hugetlb files later. Link: https://lkml.kernel.org/r/20220405014847.14295-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/mm.h | 10 ++++++++++ include/linux/mm_inline.h | 43 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 53 insertions(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index d63ba0e0e068..61786259e52a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3428,4 +3428,14 @@ madvise_set_anon_name(struct mm_struct *mm, unsigned long start, } #endif +typedef unsigned int __bitwise zap_flags_t; + +/* + * Whether to drop the pte markers, for example, the uffd-wp information for + * file-backed memory. This should only be specified when we will completely + * drop the page in the mm, either by truncation or unmapping of the vma. By + * default, the flag is not set. + */ +#define ZAP_FLAG_DROP_MARKER ((__force zap_flags_t) BIT(0)) + #endif /* _LINUX_MM_H */ diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index ac32125745ab..7b25b53c474a 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -6,6 +6,8 @@ #include #include #include +#include +#include /** * folio_is_file_lru - Should the folio be on a file LRU or anon LRU? @@ -316,5 +318,46 @@ static inline bool mm_tlb_flush_nested(struct mm_struct *mm) return atomic_read(&mm->tlb_flush_pending) > 1; } +/* + * If this pte is wr-protected by uffd-wp in any form, arm the special pte to + * replace a none pte. NOTE! This should only be called when *pte is already + * cleared so we will never accidentally replace something valuable. Meanwhile + * none pte also means we are not demoting the pte so tlb flushed is not needed. + * E.g., when pte cleared the caller should have taken care of the tlb flush. + * + * Must be called with pgtable lock held so that no thread will see the none + * pte, and if they see it, they'll fault and serialize at the pgtable lock. + * + * This function is a no-op if PTE_MARKER_UFFD_WP is not enabled. + */ +static inline void +pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, + pte_t *pte, pte_t pteval) +{ +#ifdef CONFIG_PTE_MARKER_UFFD_WP + bool arm_uffd_pte = false; + + /* The current status of the pte should be "cleared" before calling */ + WARN_ON_ONCE(!pte_none(*pte)); + + if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) + return; + + /* A uffd-wp wr-protected normal pte */ + if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval))) + arm_uffd_pte = true; + + /* + * A uffd-wp wr-protected swap pte. Note: this should even cover an + * existing pte marker with uffd-wp bit set. + */ + if (unlikely(pte_swp_uffd_wp_any(pteval))) + arm_uffd_pte = true; + + if (unlikely(arm_uffd_pte)) + set_pte_at(vma->vm_mm, addr, pte, + make_pte_marker(PTE_MARKER_UFFD_WP)); +#endif +} #endif -- cgit v1.2.3 From 229f3fa778c50edf12b34bd91b2025645a11bb94 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:54 -0700 Subject: mm/hugetlb: introduce huge pte version of uffd-wp helpers They will be used in the follow up patches to either check/set/clear uffd-wp bit of a huge pte. So far it reuses all the small pte helpers. Archs can overwrite these versions when necessary (with __HAVE_ARCH_HUGE_PTE_UFFD_WP* macros) in the future. Link: https://lkml.kernel.org/r/20220405014858.14531-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/asm-generic/hugetlb.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h index f39cad20ffc6..896f341f614d 100644 --- a/include/asm-generic/hugetlb.h +++ b/include/asm-generic/hugetlb.h @@ -35,6 +35,21 @@ static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot) return pte_modify(pte, newprot); } +static inline pte_t huge_pte_mkuffd_wp(pte_t pte) +{ + return pte_mkuffd_wp(pte); +} + +static inline pte_t huge_pte_clear_uffd_wp(pte_t pte) +{ + return pte_clear_uffd_wp(pte); +} + +static inline int huge_pte_uffd_wp(pte_t pte) +{ + return pte_uffd_wp(pte); +} + #ifndef __HAVE_ARCH_HUGE_PTE_CLEAR static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long sz) -- cgit v1.2.3 From 6041c69179034278ac6d57f90a55b09e588f4b90 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:54 -0700 Subject: mm/hugetlb: take care of UFFDIO_COPY_MODE_WP Pass the wp_copy variable into hugetlb_mcopy_atomic_pte() thoughout the stack. Apply the UFFD_WP bit if UFFDIO_COPY_MODE_WP is with UFFDIO_COPY. Hugetlb pages are only managed by hugetlbfs, so we're safe even without setting dirty bit in the huge pte if the page is installed as read-only. However we'd better still keep the dirty bit set for a read-only UFFDIO_COPY pte (when UFFDIO_COPY_MODE_WP bit is set), not only to match what we do with shmem, but also because the page does contain dirty data that the kernel just copied from the userspace. Link: https://lkml.kernel.org/r/20220405014904.14643-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ac2ece9e9c79..159b253e523d 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -160,7 +160,8 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, unsigned long dst_addr, unsigned long src_addr, enum mcopy_atomic_mode mode, - struct page **pagep); + struct page **pagep, + bool wp_copy); #endif /* CONFIG_USERFAULTFD */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, @@ -356,7 +357,8 @@ static inline int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, unsigned long dst_addr, unsigned long src_addr, enum mcopy_atomic_mode mode, - struct page **pagep) + struct page **pagep, + bool wp_copy) { BUG(); return 0; -- cgit v1.2.3 From 5a90d5a103c2badfcf12d48e2fec350969e3f486 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:54 -0700 Subject: mm/hugetlb: handle UFFDIO_WRITEPROTECT This starts from passing cp_flags into hugetlb_change_protection() so hugetlb will be able to handle MM_CP_UFFD_WP[_RESOLVE] requests. huge_pte_clear_uffd_wp() is introduced to handle the case where the UFFDIO_WRITEPROTECT is requested upon migrating huge page entries. Link: https://lkml.kernel.org/r/20220405014906.14708-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Mike Kravetz Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 159b253e523d..f1143f1fb444 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -211,7 +211,8 @@ struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address, int pmd_huge(pmd_t pmd); int pud_huge(pud_t pud); unsigned long hugetlb_change_protection(struct vm_area_struct *vma, - unsigned long address, unsigned long end, pgprot_t newprot); + unsigned long address, unsigned long end, pgprot_t newprot, + unsigned long cp_flags); bool is_hugetlb_entry_migration(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); @@ -397,7 +398,8 @@ static inline void move_hugetlb_state(struct page *oldpage, static inline unsigned long hugetlb_change_protection( struct vm_area_struct *vma, unsigned long address, - unsigned long end, pgprot_t newprot) + unsigned long end, pgprot_t newprot, + unsigned long cp_flags) { return 0; } -- cgit v1.2.3 From 05e90bd05eea33fc77d6b11e121e2da01fee379f Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:55 -0700 Subject: mm/hugetlb: only drop uffd-wp special pte if required As with shmem uffd-wp special ptes, only drop the uffd-wp special swap pte if unmapping an entire vma or synchronized such that faults can not race with the unmap operation. This requires passing zap_flags all the way to the lowest level hugetlb unmap routine: __unmap_hugepage_range. In general, unmap calls originated in hugetlbfs code will pass the ZAP_FLAG_DROP_MARKER flag as synchronization is in place to prevent faults. The exception is hole punch which will first unmap without any synchronization. Later when hole punch actually removes the page from the file, it will check to see if there was a subsequent fault and if so take the hugetlb fault mutex while unmapping again. This second unmap will pass in ZAP_FLAG_DROP_MARKER. The justification of "whether to apply ZAP_FLAG_DROP_MARKER flag when unmap a hugetlb range" is (IMHO): we should never reach a state when a page fault could errornously fault in a page-cache page that was wr-protected to be writable, even in an extremely short period. That could happen if e.g. we pass ZAP_FLAG_DROP_MARKER when hugetlbfs_punch_hole() calls hugetlb_vmdelete_list(), because if a page faults after that call and before remove_inode_hugepages() is executed, the page cache can be mapped writable again in the small racy window, that can cause unexpected data overwritten. [peterx@redhat.com: fix sparse warning] Link: https://lkml.kernel.org/r/Ylcdw8I1L5iAoWhb@xz-m1.local [akpm@linux-foundation.org: move zap_flags_t from mm.h to mm_types.h to fix build issues] Link: https://lkml.kernel.org/r/20220405014915.14873-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Mike Kravetz Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 8 +++++--- include/linux/mm.h | 2 -- include/linux/mm_types.h | 2 ++ 3 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index f1143f1fb444..19cec415f546 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -143,11 +143,12 @@ long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, unsigned long *, unsigned long *, long, unsigned int, int *); void unmap_hugepage_range(struct vm_area_struct *, - unsigned long, unsigned long, struct page *); + unsigned long, unsigned long, struct page *, + zap_flags_t); void __unmap_hugepage_range_final(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, - struct page *ref_page); + struct page *ref_page, zap_flags_t zap_flags); void hugetlb_report_meminfo(struct seq_file *); int hugetlb_report_node_meminfo(char *buf, int len, int nid); void hugetlb_show_meminfo(void); @@ -406,7 +407,8 @@ static inline unsigned long hugetlb_change_protection( static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, - unsigned long end, struct page *ref_page) + unsigned long end, struct page *ref_page, + zap_flags_t zap_flags) { BUG(); } diff --git a/include/linux/mm.h b/include/linux/mm.h index 61786259e52a..de32c0383387 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3428,8 +3428,6 @@ madvise_set_anon_name(struct mm_struct *mm, unsigned long start, } #endif -typedef unsigned int __bitwise zap_flags_t; - /* * Whether to drop the pte markers, for example, the uffd-wp information for * file-backed memory. This should only be specified when we will completely diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index dd382270ae40..b34ff2cdbc4f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -863,4 +863,6 @@ enum fault_flag { FAULT_FLAG_ORIG_PTE_VALID = 1 << 11, }; +typedef unsigned int __bitwise zap_flags_t; + #endif /* _LINUX_MM_TYPES_H */ -- cgit v1.2.3 From bc70fbf269fdff410b0b6d75c3770b9f59117b90 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:55 -0700 Subject: mm/hugetlb: handle uffd-wp during fork() Firstly, we'll need to pass in dst_vma into copy_hugetlb_page_range() because for uffd-wp it's the dst vma that matters on deciding how we should treat uffd-wp protected ptes. We should recognize pte markers during fork and do the pte copy if needed. [lkp@intel.com: vma_needs_copy can be static] Link: https://lkml.kernel.org/r/Ylb0CGeFJlc4EzLk@7ec4ff11d4ae Link: https://lkml.kernel.org/r/20220405014918.14932-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 19cec415f546..04f0186b089b 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -137,7 +137,8 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len); -int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); +int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, + struct vm_area_struct *, struct vm_area_struct *); long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, unsigned long *, unsigned long *, long, unsigned int, @@ -269,7 +270,9 @@ static inline struct page *follow_huge_addr(struct mm_struct *mm, } static inline int copy_hugetlb_page_range(struct mm_struct *dst, - struct mm_struct *src, struct vm_area_struct *vma) + struct mm_struct *src, + struct vm_area_struct *dst_vma, + struct vm_area_struct *src_vma) { BUG(); return 0; -- cgit v1.2.3 From b1f9e876862d8f7176299ec4fb2108bc1045cbc8 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 12 May 2022 20:22:56 -0700 Subject: mm/uffd: enable write protection for shmem & hugetlbfs We've had all the necessary changes ready for both shmem and hugetlbfs. Turn on all the shmem/hugetlbfs switches for userfaultfd-wp. We can expand UFFD_API_RANGE_IOCTLS_BASIC with _UFFDIO_WRITEPROTECT too because all existing types now support write protection mode. Since vma_can_userfault() will be used elsewhere, move into userfaultfd_k.h. Link: https://lkml.kernel.org/r/20220405014926.15101-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- include/linux/userfaultfd_k.h | 20 ++++++++++++++++++++ include/uapi/linux/userfaultfd.h | 10 ++++++++-- 2 files changed, 28 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index e7afcdfd4b46..732b522bacb7 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -18,6 +18,7 @@ #include #include #include +#include /* The set of all possible UFFD-related VM flags. */ #define __VM_UFFD_FLAGS (VM_UFFD_MISSING | VM_UFFD_WP | VM_UFFD_MINOR) @@ -140,6 +141,25 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma) return vma->vm_flags & __VM_UFFD_FLAGS; } +static inline bool vma_can_userfault(struct vm_area_struct *vma, + unsigned long vm_flags) +{ + if (vm_flags & VM_UFFD_MINOR) + return is_vm_hugetlb_page(vma) || vma_is_shmem(vma); + +#ifndef CONFIG_PTE_MARKER_UFFD_WP + /* + * If user requested uffd-wp but not enabled pte markers for + * uffd-wp, then shmem & hugetlbfs are not supported but only + * anonymous. + */ + if ((vm_flags & VM_UFFD_WP) && !vma_is_anonymous(vma)) + return false; +#endif + return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) || + vma_is_shmem(vma); +} + extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); extern void dup_userfaultfd_complete(struct list_head *); diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index ef739054cb1c..7d32b1e797fb 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -33,7 +33,8 @@ UFFD_FEATURE_THREAD_ID | \ UFFD_FEATURE_MINOR_HUGETLBFS | \ UFFD_FEATURE_MINOR_SHMEM | \ - UFFD_FEATURE_EXACT_ADDRESS) + UFFD_FEATURE_EXACT_ADDRESS | \ + UFFD_FEATURE_WP_HUGETLBFS_SHMEM) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -47,7 +48,8 @@ #define UFFD_API_RANGE_IOCTLS_BASIC \ ((__u64)1 << _UFFDIO_WAKE | \ (__u64)1 << _UFFDIO_COPY | \ - (__u64)1 << _UFFDIO_CONTINUE) + (__u64)1 << _UFFDIO_CONTINUE | \ + (__u64)1 << _UFFDIO_WRITEPROTECT) /* * Valid ioctl command number range with this API is from 0x00 to @@ -194,6 +196,9 @@ struct uffdio_api { * UFFD_FEATURE_EXACT_ADDRESS indicates that the exact address of page * faults would be provided and the offset within the page would not be * masked. + * + * UFFD_FEATURE_WP_HUGETLBFS_SHMEM indicates that userfaultfd + * write-protection mode is supported on both shmem and hugetlbfs. */ #define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) #define UFFD_FEATURE_EVENT_FORK (1<<1) @@ -207,6 +212,7 @@ struct uffdio_api { #define UFFD_FEATURE_MINOR_HUGETLBFS (1<<9) #define UFFD_FEATURE_MINOR_SHMEM (1<<10) #define UFFD_FEATURE_EXACT_ADDRESS (1<<11) +#define UFFD_FEATURE_WP_HUGETLBFS_SHMEM (1<<12) __u64 features; __u64 ioctls; -- cgit v1.2.3 From b48d8a8e5ce53e3114a1ffe96563e3555b51d40b Mon Sep 17 00:00:00 2001 From: Zi Yan Date: Thu, 12 May 2022 20:22:57 -0700 Subject: mm: page_isolation: move has_unmovable_pages() to mm/page_isolation.c Patch series "Use pageblock_order for cma and alloc_contig_range alignment", v11. This patchset tries to remove the MAX_ORDER-1 alignment requirement for CMA and alloc_contig_range(). It prepares for my upcoming changes to make MAX_ORDER adjustable at boot time[1]. The MAX_ORDER - 1 alignment requirement comes from that alloc_contig_range() isolates pageblocks to remove free memory from buddy allocator but isolating only a subset of pageblocks within a page spanning across multiple pageblocks causes free page accounting issues. Isolated page might not be put into the right free list, since the code assumes the migratetype of the first pageblock as the whole free page migratetype. This is based on the discussion at [2]. To remove the requirement, this patchset: 1. isolates pages at pageblock granularity instead of max(MAX_ORDER_NR_PAEGS, pageblock_nr_pages); 2. splits free pages across the specified range or migrates in-use pages across the specified range then splits the freed page to avoid free page accounting issues (it happens when multiple pageblocks within a single page have different migratetypes); 3. only checks unmovable pages within the range instead of MAX_ORDER - 1 aligned range during isolation to avoid alloc_contig_range() failure when pageblocks within a MAX_ORDER - 1 aligned range are allocated separately. 4. returns pages not in the range as it did before. One optimization might come later: 1. make MIGRATE_ISOLATE a separate bit to be able to restore the original migratetypes when isolation fails in the middle of the range. [1] https://lore.kernel.org/linux-mm/20210805190253.2795604-1-zi.yan@sent.com/ [2] https://lore.kernel.org/linux-mm/d19fb078-cb9b-f60f-e310-fdeea1b947d2@redhat.com/ This patch (of 6): has_unmovable_pages() is only used in mm/page_isolation.c. Move it from mm/page_alloc.c and make it static. Link: https://lkml.kernel.org/r/20220425143118.2850746-2-zi.yan@sent.com Signed-off-by: Zi Yan Reviewed-by: Oscar Salvador Reviewed-by: Mike Rapoport Acked-by: David Hildenbrand Cc: Vlastimil Babka Cc: Mel Gorman Cc: Eric Ren Cc: Christophe Leroy Cc: Minchan Kim Cc: kernel test robot Signed-off-by: Andrew Morton --- include/linux/page-isolation.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 572458016331..e14eddf6741a 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -33,8 +33,6 @@ static inline bool is_migrate_isolate(int migratetype) #define MEMORY_OFFLINE 0x1 #define REPORT_FAILURE 0x2 -struct page *has_unmovable_pages(struct zone *zone, struct page *page, - int migratetype, int flags); void set_pageblock_migratetype(struct page *page, int migratetype); int move_freepages_block(struct zone *zone, struct page *page, int migratetype, int *num_movable); -- cgit v1.2.3 From b2c9e2fbba32539626522b6aed30d1dde7b7e971 Mon Sep 17 00:00:00 2001 From: Zi Yan Date: Thu, 12 May 2022 20:22:58 -0700 Subject: mm: make alloc_contig_range work at pageblock granularity alloc_contig_range() worked at MAX_ORDER_NR_PAGES granularity to avoid merging pageblocks with different migratetypes. It might unnecessarily convert extra pageblocks at the beginning and at the end of the range. Change alloc_contig_range() to work at pageblock granularity. Special handling is needed for free pages and in-use pages across the boundaries of the range specified by alloc_contig_range(). Because these= Partially isolated pages causes free page accounting issues. The free pages will be split and freed into separate migratetype lists; the in-use= Pages will be migrated then the freed pages will be handled in the aforementioned way. [ziy@nvidia.com: fix deadlock/crash] Link: https://lkml.kernel.org/r/23A7297E-6C84-4138-A9FE-3598234004E6@nvidia.com Link: https://lkml.kernel.org/r/20220425143118.2850746-4-zi.yan@sent.com Signed-off-by: Zi Yan Reported-by: kernel test robot Cc: Christophe Leroy Cc: David Hildenbrand Cc: Eric Ren Cc: Mel Gorman Cc: Mike Rapoport Cc: Minchan Kim Cc: Oscar Salvador Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/page-isolation.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index e14eddf6741a..5456b7be38ae 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -42,7 +42,7 @@ int move_freepages_block(struct zone *zone, struct page *page, */ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, - unsigned migratetype, int flags); + int migratetype, int flags, gfp_t gfp_flags); /* * Changes MIGRATE_ISOLATE to MIGRATE_MOVABLE. @@ -50,7 +50,7 @@ start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, */ void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, - unsigned migratetype); + int migratetype); /* * Test all pages in [start_pfn, end_pfn) are isolated or not. -- cgit v1.2.3 From 11ac3e87ce09c27f4587a8c4fe0829d814021a82 Mon Sep 17 00:00:00 2001 From: Zi Yan Date: Thu, 12 May 2022 20:22:58 -0700 Subject: mm: cma: use pageblock_order as the single alignment Now alloc_contig_range() works at pageblock granularity. Change CMA allocation, which uses alloc_contig_range(), to use pageblock_nr_pages alignment. Link: https://lkml.kernel.org/r/20220425143118.2850746-6-zi.yan@sent.com Signed-off-by: Zi Yan Cc: Christophe Leroy Cc: David Hildenbrand Cc: Eric Ren Cc: kernel test robot Cc: Mel Gorman Cc: Mike Rapoport Cc: Minchan Kim Cc: Oscar Salvador Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/cma.h | 4 ++-- include/linux/mmzone.h | 5 +---- 2 files changed, 3 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/cma.h b/include/linux/cma.h index a6f637342740..63873b93deaa 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -17,11 +17,11 @@ #define CMA_MAX_NAME 64 /* - * TODO: once the buddy -- especially pageblock merging and alloc_contig_range() + * the buddy -- especially pageblock merging and alloc_contig_range() * -- can deal with only some pageblocks of a higher-order page being * MIGRATE_CMA, we can use pageblock_nr_pages. */ -#define CMA_MIN_ALIGNMENT_PAGES MAX_ORDER_NR_PAGES +#define CMA_MIN_ALIGNMENT_PAGES pageblock_nr_pages #define CMA_MIN_ALIGNMENT_BYTES (PAGE_SIZE * CMA_MIN_ALIGNMENT_PAGES) struct cma; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 46ffab808f03..aab70355d64f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -54,10 +54,7 @@ enum migratetype { * * The way to use it is to change migratetype of a range of * pageblocks to MIGRATE_CMA which can be done by - * __free_pageblock_cma() function. What is important though - * is that a range of pageblocks must be aligned to - * MAX_ORDER_NR_PAGES should biggest page be bigger than - * a single pageblock. + * __free_pageblock_cma() function. */ MIGRATE_CMA, #endif -- cgit v1.2.3 From adf88aa8ea7ff143825a2a8a7193f92e0e6fc79b Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 12 May 2022 20:23:01 -0700 Subject: mm: remove alloc_pages_vma() All callers have now been converted to use vma_alloc_folio(), so convert the body of alloc_pages_vma() to allocate folios instead. Link: https://lkml.kernel.org/r/20220504182857.4013401-5-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Signed-off-by: Andrew Morton --- include/linux/gfp.h | 18 +++++++----------- 1 file changed, 7 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 3e3d36fc2109..2a08a3c4ba95 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -613,13 +613,8 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, #ifdef CONFIG_NUMA struct page *alloc_pages(gfp_t gfp, unsigned int order); struct folio *folio_alloc(gfp_t gfp, unsigned order); -struct page *alloc_pages_vma(gfp_t gfp_mask, int order, - struct vm_area_struct *vma, unsigned long addr, - bool hugepage); struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr, bool hugepage); -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ - alloc_pages_vma(gfp_mask, order, vma, addr, true) #else static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) { @@ -629,16 +624,17 @@ static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order) { return __folio_alloc_node(gfp, order, numa_node_id()); } -#define alloc_pages_vma(gfp_mask, order, vma, addr, hugepage) \ - alloc_pages(gfp_mask, order) #define vma_alloc_folio(gfp, order, vma, addr, hugepage) \ folio_alloc(gfp, order) -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ - alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) -#define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, false) +static inline struct page *alloc_page_vma(gfp_t gfp, + struct vm_area_struct *vma, unsigned long addr) +{ + struct folio *folio = vma_alloc_folio(gfp, 0, vma, addr, false); + + return &folio->page; +} extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); -- cgit v1.2.3 From e2e3fdc7d4afdb8e7ba981eba7827993f2d390a8 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 12 May 2022 20:23:02 -0700 Subject: swap: turn get_swap_page() into folio_alloc_swap() This removes an assumption that a large folio is HPAGE_PMD_NR pages in size. Link: https://lkml.kernel.org/r/20220504182857.4013401-8-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Signed-off-by: Andrew Morton --- include/linux/swap.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 5553189d0215..252c23a6667f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -470,7 +470,7 @@ static inline long get_nr_swap_pages(void) } extern void si_swapinfo(struct sysinfo *); -extern swp_entry_t get_swap_page(struct page *page); +swp_entry_t folio_alloc_swap(struct folio *folio); extern void put_swap_page(struct page *page, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size); @@ -583,7 +583,7 @@ static inline int try_to_free_swap(struct page *page) return 0; } -static inline swp_entry_t get_swap_page(struct page *page) +static inline swp_entry_t folio_alloc_swap(struct folio *folio) { swp_entry_t entry; entry.val = 0; @@ -643,12 +643,13 @@ static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) #ifdef CONFIG_MEMCG_SWAP void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry); -extern int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry); -static inline int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) +int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry); +static inline int mem_cgroup_try_charge_swap(struct folio *folio, + swp_entry_t entry) { if (mem_cgroup_disabled()) return 0; - return __mem_cgroup_try_charge_swap(page, entry); + return __mem_cgroup_try_charge_swap(folio, entry); } extern void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); @@ -666,7 +667,7 @@ static inline void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry) { } -static inline int mem_cgroup_try_charge_swap(struct page *page, +static inline int mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) { return 0; -- cgit v1.2.3 From 64daa5d818ae3430f0785206b0af13ef528cb9ef Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 12 May 2022 20:23:03 -0700 Subject: vmscan: convert lazy freeing to folios Remove a hidden call to compound_head(), and account nr_pages instead of a single page. This matches the code in lru_lazyfree_fn() that accounts nr_pages to PGLAZYFREE. Link: https://lkml.kernel.org/r/20220504182857.4013401-12-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index fe580cb96683..8ea4b541c31e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1057,6 +1057,15 @@ static inline void count_memcg_page_event(struct page *page, count_memcg_events(memcg, idx, 1); } +static inline void count_memcg_folio_events(struct folio *folio, + enum vm_event_item idx, unsigned long nr) +{ + struct mem_cgroup *memcg = folio_memcg(folio); + + if (memcg) + count_memcg_events(memcg, idx, nr); +} + static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { @@ -1494,6 +1503,11 @@ static inline void count_memcg_page_event(struct page *page, { } +static inline void count_memcg_folio_events(struct folio *folio, + enum vm_event_item idx, unsigned long nr) +{ +} + static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { -- cgit v1.2.3 From dc786690a6a1d9a680e6872821291ad7ca9f520d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 12 May 2022 20:23:03 -0700 Subject: mm: allow can_split_folio() to be called when THP are disabled The call to can_split_folio() in vmscan is currently guarded by a test of PageTransHuge() so the BUILD_BUG() is eliminated if THP are disabled. The next patch replaces that test with folio_test_large() which may be true, even when THP are disabled. However, if THP are disabled, we cannot split, so an unconditional return of false is appropriate. Link: https://lkml.kernel.org/r/20220504182857.4013401-15-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 9a26bd10e083..fbf36bb1be22 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -348,7 +348,6 @@ static inline void prep_transhuge_page(struct page *page) {} static inline bool can_split_folio(struct folio *folio, int *pextra_pins) { - BUILD_BUG(); return false; } static inline int -- cgit v1.2.3 From 039bc1240165c99b932fb4be2f784948d1038eea Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 12 May 2022 20:23:04 -0700 Subject: mm/swap: add folio_throttle_swaprate The only use of the page argument to cgroup_throttle_swaprate() is to get the node ID, and this will be the same for all pages in the folio, so just pass in the first page of the folio. Link: https://lkml.kernel.org/r/20220504182857.4013401-18-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Signed-off-by: Andrew Morton --- include/linux/swap.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 252c23a6667f..6bf1506e5080 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -640,6 +640,10 @@ static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) { } #endif +static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) +{ + cgroup_throttle_swaprate(&folio->page, gfp); +} #ifdef CONFIG_MEMCG_SWAP void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry); -- cgit v1.2.3 From da08e9b7932345aff0a748c55f8a25709505f2a3 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 12 May 2022 20:23:05 -0700 Subject: mm/shmem: convert shmem_swapin_page() to shmem_swapin_folio() shmem_swapin_page() only brings in order-0 pages, which are folios by definition. Link: https://lkml.kernel.org/r/20220504182857.4013401-24-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 530b1817b58c..39fa93e94b80 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -758,7 +758,7 @@ static inline void arch_swap_invalidate_area(int type) #endif #ifndef __HAVE_ARCH_SWAP_RESTORE -static inline void arch_swap_restore(swp_entry_t entry, struct page *page) +static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) { } #endif -- cgit v1.2.3 From a9595b305c0f6cbbf9505325509d95637f6a7062 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 12 May 2022 20:23:05 -0700 Subject: mm: add folio_mapping_flags() This is the equivalent of PageMappingFlags and is needed for converting mm/migrate.c to folios. Link: https://lkml.kernel.org/r/20220504182857.4013401-25-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index b70124b9c7c1..97eb88dbcbbc 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -650,6 +650,11 @@ __PAGEFLAG(Reported, reported, PF_NO_COMPOUND) #define PAGE_MAPPING_KSM (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) #define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) +static __always_inline bool folio_mapping_flags(struct folio *folio) +{ + return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) != 0; +} + static __always_inline int PageMappingFlags(struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0; -- cgit v1.2.3 From 8b463be3a0241558071e6ba9bf11e4bf42ccc856 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 12 May 2022 20:23:05 -0700 Subject: mm: add folio_test_movable() This is the folio equivalent of PageMovable() which is needed to convert mm/migrate.c to folios. Link: https://lkml.kernel.org/r/20220504182857.4013401-26-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Signed-off-by: Andrew Morton --- include/linux/migrate.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 2707bfd43a0d..069a89e847f3 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -105,6 +105,11 @@ static inline void __ClearPageMovable(struct page *page) } #endif +static inline bool folio_test_movable(struct folio *folio) +{ + return PageMovable(&folio->page); +} + #ifdef CONFIG_NUMA_BALANCING extern int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int node); -- cgit v1.2.3 From de8c8e52836d0082188508548d0b939f49f7f0e6 Mon Sep 17 00:00:00 2001 From: Tong Tiangen Date: Thu, 12 May 2022 20:23:06 -0700 Subject: mm: page_table_check: add hooks to public helpers Move ptep_clear() to the include/linux/pgtable.h and add page table check relate hooks to some helpers, it's prepare for support page table check feature on new architecture. Optimize the implementation of ptep_clear(), page table hooks added page table check stubs, the interface control should be at stubs, there is no rationale for doing a IS_ENABLED() check here. For architectures that do not enable CONFIG_PAGE_TABLE_CHECK, they will call a fallback page table check stubs[1] when getting their page table helpers[2] in include/linux/pgtable.h. [1] page table check stubs defined in include/linux/page_table_check.h [2] ptep_clear() ptep_get_and_clear() pmdp_huge_get_and_clear() pudp_huge_get_and_clear() Link: https://lkml.kernel.org/r/20220507110114.4128854-4-tongtiangen@huawei.com Signed-off-by: Tong Tiangen Acked-by: Pasha Tatashin Cc: Anshuman Khandual Cc: Borislav Petkov Cc: Catalin Marinas Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Kefeng Wang Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 39fa93e94b80..e0a449b477c5 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -12,6 +12,7 @@ #include #include #include +#include #if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \ defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS @@ -259,14 +260,6 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma, #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif -#ifndef __HAVE_ARCH_PTEP_CLEAR -static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) -{ - pte_clear(mm, addr, ptep); -} -#endif - #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long address, @@ -274,10 +267,19 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, { pte_t pte = *ptep; pte_clear(mm, address, ptep); + page_table_check_pte_clear(mm, address, pte); return pte; } #endif +#ifndef __HAVE_ARCH_PTEP_CLEAR +static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + ptep_get_and_clear(mm, addr, ptep); +} +#endif + #ifndef __HAVE_ARCH_PTEP_GET static inline pte_t ptep_get(pte_t *ptep) { @@ -347,7 +349,10 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, pmd_t *pmdp) { pmd_t pmd = *pmdp; + pmd_clear(pmdp); + page_table_check_pmd_clear(mm, address, pmd); + return pmd; } #endif /* __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR */ @@ -359,6 +364,8 @@ static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, pud_t pud = *pudp; pud_clear(pudp); + page_table_check_pud_clear(mm, address, pud); + return pud; } #endif /* __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR */ -- cgit v1.2.3 From 2e7dc2b632a324c670ff11dd6c84d711043c683f Mon Sep 17 00:00:00 2001 From: Tong Tiangen Date: Thu, 12 May 2022 20:23:06 -0700 Subject: mm: remove __HAVE_ARCH_PTEP_CLEAR in pgtable.h Currently, there is no architecture definition __HAVE_ARCH_PTEP_CLEAR, Generic ptep_clear() is the only definition for all architecture, So drop the "#ifndef __HAVE_ARCH_PTEP_CLEAR". Link: https://lkml.kernel.org/r/20220507110114.4128854-5-tongtiangen@huawei.com Signed-off-by: Tong Tiangen Suggested-by: Anshuman Khandual Cc: Borislav Petkov Cc: Catalin Marinas Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Kefeng Wang Cc: Palmer Dabbelt Cc: Pasha Tatashin Cc: Paul Walmsley Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index e0a449b477c5..ecb4c762d760 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -272,13 +272,11 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, } #endif -#ifndef __HAVE_ARCH_PTEP_CLEAR static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { ptep_get_and_clear(mm, addr, ptep); } -#endif #ifndef __HAVE_ARCH_PTEP_GET static inline pte_t ptep_get(pte_t *ptep) -- cgit v1.2.3 From c8db8c2628afc7088a43de3f7cfbcc2ef1f182f7 Mon Sep 17 00:00:00 2001 From: Li kunyu Date: Thu, 12 May 2022 20:23:07 -0700 Subject: mm: functions may simplify the use of return values p4d_clear_huge may be optimized for void return type and function usage. vunmap_p4d_range function saves a few steps here. Link: https://lkml.kernel.org/r/20220507150630.90399-1-kunyu@nfschina.com Signed-off-by: Li kunyu Cc: Dave Hansen Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index ecb4c762d760..3cdc16cfd867 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1448,16 +1448,13 @@ static inline int pmd_protnone(pmd_t pmd) #ifndef __PAGETABLE_P4D_FOLDED int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot); -int p4d_clear_huge(p4d_t *p4d); +void p4d_clear_huge(p4d_t *p4d); #else static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { return 0; } -static inline int p4d_clear_huge(p4d_t *p4d) -{ - return 0; -} +static inline void p4d_clear_huge(p4d_t *p4d) { } #endif /* !__PAGETABLE_P4D_FOLDED */ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot); @@ -1480,10 +1477,7 @@ static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) { return 0; } -static inline int p4d_clear_huge(p4d_t *p4d) -{ - return 0; -} +static inline void p4d_clear_huge(p4d_t *p4d) { } static inline int pud_clear_huge(pud_t *pud) { return 0; -- cgit v1.2.3 From f67bed134a053663852a1a3ab1b3223bfc2104a2 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Thu, 12 May 2022 20:23:07 -0700 Subject: percpu: improve percpu_alloc_percpu event trace Add call_site, bytes_alloc and gfp_flags fields to the output of the percpu_alloc_percpu ftrace event: mkdir-4393 [001] 169.334788: percpu_alloc_percpu: call_site=mem_cgroup_css_alloc+0xa6 reserved=0 is_atomic=0 size=2408 align=8 base_addr=0xffffc7117fc00000 off=402176 ptr=0x3dc867a62300 bytes_alloc=14448 gfp_flags=GFP_KERNEL_ACCOUNT This is required to track memcg-accounted percpu allocations. Link: https://lkml.kernel.org/r/a07be858-c8a3-7851-9086-e3262cbcf707@openvz.org Signed-off-by: Vasily Averin Acked-by: Roman Gushchin Cc: Shakeel Butt Cc: Steven Rostedt Cc: Ingo Molnar Cc: Vlastimil Babka Cc: Michal Hocko Cc: Dennis Zhou Cc: Tejun Heo Cc: Christoph Lameter Signed-off-by: Andrew Morton --- include/trace/events/percpu.h | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/trace/events/percpu.h b/include/trace/events/percpu.h index df112a64f6c9..e989cefc0def 100644 --- a/include/trace/events/percpu.h +++ b/include/trace/events/percpu.h @@ -6,15 +6,20 @@ #define _TRACE_PERCPU_H #include +#include TRACE_EVENT(percpu_alloc_percpu, - TP_PROTO(bool reserved, bool is_atomic, size_t size, - size_t align, void *base_addr, int off, void __percpu *ptr), + TP_PROTO(unsigned long call_site, + bool reserved, bool is_atomic, size_t size, + size_t align, void *base_addr, int off, + void __percpu *ptr, size_t bytes_alloc, gfp_t gfp_flags), - TP_ARGS(reserved, is_atomic, size, align, base_addr, off, ptr), + TP_ARGS(call_site, reserved, is_atomic, size, align, base_addr, off, + ptr, bytes_alloc, gfp_flags), TP_STRUCT__entry( + __field( unsigned long, call_site ) __field( bool, reserved ) __field( bool, is_atomic ) __field( size_t, size ) @@ -22,9 +27,11 @@ TRACE_EVENT(percpu_alloc_percpu, __field( void *, base_addr ) __field( int, off ) __field( void __percpu *, ptr ) + __field( size_t, bytes_alloc ) + __field( gfp_t, gfp_flags ) ), - TP_fast_assign( + __entry->call_site = call_site; __entry->reserved = reserved; __entry->is_atomic = is_atomic; __entry->size = size; @@ -32,12 +39,16 @@ TRACE_EVENT(percpu_alloc_percpu, __entry->base_addr = base_addr; __entry->off = off; __entry->ptr = ptr; + __entry->bytes_alloc = bytes_alloc; + __entry->gfp_flags = gfp_flags; ), - TP_printk("reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p", + TP_printk("call_site=%pS reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p bytes_alloc=%zu gfp_flags=%s", + (void *)__entry->call_site, __entry->reserved, __entry->is_atomic, __entry->size, __entry->align, - __entry->base_addr, __entry->off, __entry->ptr) + __entry->base_addr, __entry->off, __entry->ptr, + __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags)) ); TRACE_EVENT(percpu_free_percpu, -- cgit v1.2.3 From fe573327ffb1deba802c91dd1d4ff41dafa97a0e Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Thu, 12 May 2022 20:23:08 -0700 Subject: tracing: incorrect gfp_t conversion Fixes the following sparse warnings: include/trace/events/*: sparse: cast to restricted gfp_t include/trace/events/*: sparse: restricted gfp_t degrades to integer gfp_t type is bitwise and requires __force attributes for any casts. Link: https://lkml.kernel.org/r/331d88fe-f4f7-657c-02a2-d977f15fbff6@openvz.org Signed-off-by: Vasily Averin Cc: Steven Rostedt Cc: Ingo Molnar Signed-off-by: Andrew Morton --- include/linux/gfp.h | 2 +- include/trace/events/btrfs.h | 4 +- include/trace/events/compaction.h | 4 +- include/trace/events/kmem.h | 12 +++--- include/trace/events/mmflags.h | 78 +++++++++++++++++++-------------------- include/trace/events/vmscan.h | 16 ++++---- 6 files changed, 58 insertions(+), 58 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 2a08a3c4ba95..2d2ccae933c2 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -367,7 +367,7 @@ static inline int gfp_migratetype(const gfp_t gfp_flags) return MIGRATE_UNMOVABLE; /* Group based on mobility */ - return (gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; + return (__force unsigned long)(gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; } #undef GFP_MOVABLE_MASK #undef GFP_MOVABLE_SHIFT diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index f068ff30d654..ed92c80331ea 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -1344,13 +1344,13 @@ TRACE_EVENT(alloc_extent_state, TP_STRUCT__entry( __field(const struct extent_state *, state) - __field(gfp_t, mask) + __field(unsigned long, mask) __field(const void*, ip) ), TP_fast_assign( __entry->state = state, - __entry->mask = mask, + __entry->mask = (__force unsigned long)mask, __entry->ip = (const void *)IP ), diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h index c6d5d70dc7a5..3313eb83c117 100644 --- a/include/trace/events/compaction.h +++ b/include/trace/events/compaction.h @@ -162,13 +162,13 @@ TRACE_EVENT(mm_compaction_try_to_compact_pages, TP_STRUCT__entry( __field(int, order) - __field(gfp_t, gfp_mask) + __field(unsigned long, gfp_mask) __field(int, prio) ), TP_fast_assign( __entry->order = order; - __entry->gfp_mask = gfp_mask; + __entry->gfp_mask = (__force unsigned long)gfp_mask; __entry->prio = prio; ), diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index ddc8c944f417..71c141804222 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -24,7 +24,7 @@ DECLARE_EVENT_CLASS(kmem_alloc, __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) ), TP_fast_assign( @@ -32,7 +32,7 @@ DECLARE_EVENT_CLASS(kmem_alloc, __entry->ptr = ptr; __entry->bytes_req = bytes_req; __entry->bytes_alloc = bytes_alloc; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s", @@ -75,7 +75,7 @@ DECLARE_EVENT_CLASS(kmem_alloc_node, __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) __field( int, node ) ), @@ -84,7 +84,7 @@ DECLARE_EVENT_CLASS(kmem_alloc_node, __entry->ptr = ptr; __entry->bytes_req = bytes_req; __entry->bytes_alloc = bytes_alloc; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; ), @@ -208,14 +208,14 @@ TRACE_EVENT(mm_page_alloc, TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->migratetype = migratetype; ), diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 6532119a6bf1..fcb1ffb2cc8d 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -14,48 +14,48 @@ */ #define __def_gfpflag_names \ - {(unsigned long)GFP_TRANSHUGE, "GFP_TRANSHUGE"}, \ - {(unsigned long)GFP_TRANSHUGE_LIGHT, "GFP_TRANSHUGE_LIGHT"}, \ - {(unsigned long)GFP_HIGHUSER_MOVABLE, "GFP_HIGHUSER_MOVABLE"},\ - {(unsigned long)GFP_HIGHUSER, "GFP_HIGHUSER"}, \ - {(unsigned long)GFP_USER, "GFP_USER"}, \ - {(unsigned long)GFP_KERNEL_ACCOUNT, "GFP_KERNEL_ACCOUNT"}, \ - {(unsigned long)GFP_KERNEL, "GFP_KERNEL"}, \ - {(unsigned long)GFP_NOFS, "GFP_NOFS"}, \ - {(unsigned long)GFP_ATOMIC, "GFP_ATOMIC"}, \ - {(unsigned long)GFP_NOIO, "GFP_NOIO"}, \ - {(unsigned long)GFP_NOWAIT, "GFP_NOWAIT"}, \ - {(unsigned long)GFP_DMA, "GFP_DMA"}, \ - {(unsigned long)__GFP_HIGHMEM, "__GFP_HIGHMEM"}, \ - {(unsigned long)GFP_DMA32, "GFP_DMA32"}, \ - {(unsigned long)__GFP_HIGH, "__GFP_HIGH"}, \ - {(unsigned long)__GFP_ATOMIC, "__GFP_ATOMIC"}, \ - {(unsigned long)__GFP_IO, "__GFP_IO"}, \ - {(unsigned long)__GFP_FS, "__GFP_FS"}, \ - {(unsigned long)__GFP_NOWARN, "__GFP_NOWARN"}, \ - {(unsigned long)__GFP_RETRY_MAYFAIL, "__GFP_RETRY_MAYFAIL"}, \ - {(unsigned long)__GFP_NOFAIL, "__GFP_NOFAIL"}, \ - {(unsigned long)__GFP_NORETRY, "__GFP_NORETRY"}, \ - {(unsigned long)__GFP_COMP, "__GFP_COMP"}, \ - {(unsigned long)__GFP_ZERO, "__GFP_ZERO"}, \ - {(unsigned long)__GFP_NOMEMALLOC, "__GFP_NOMEMALLOC"}, \ - {(unsigned long)__GFP_MEMALLOC, "__GFP_MEMALLOC"}, \ - {(unsigned long)__GFP_HARDWALL, "__GFP_HARDWALL"}, \ - {(unsigned long)__GFP_THISNODE, "__GFP_THISNODE"}, \ - {(unsigned long)__GFP_RECLAIMABLE, "__GFP_RECLAIMABLE"}, \ - {(unsigned long)__GFP_MOVABLE, "__GFP_MOVABLE"}, \ - {(unsigned long)__GFP_ACCOUNT, "__GFP_ACCOUNT"}, \ - {(unsigned long)__GFP_WRITE, "__GFP_WRITE"}, \ - {(unsigned long)__GFP_RECLAIM, "__GFP_RECLAIM"}, \ - {(unsigned long)__GFP_DIRECT_RECLAIM, "__GFP_DIRECT_RECLAIM"},\ - {(unsigned long)__GFP_KSWAPD_RECLAIM, "__GFP_KSWAPD_RECLAIM"},\ - {(unsigned long)__GFP_ZEROTAGS, "__GFP_ZEROTAGS"} \ + {(__force unsigned long)GFP_TRANSHUGE, "GFP_TRANSHUGE"}, \ + {(__force unsigned long)GFP_TRANSHUGE_LIGHT, "GFP_TRANSHUGE_LIGHT"}, \ + {(__force unsigned long)GFP_HIGHUSER_MOVABLE, "GFP_HIGHUSER_MOVABLE"},\ + {(__force unsigned long)GFP_HIGHUSER, "GFP_HIGHUSER"}, \ + {(__force unsigned long)GFP_USER, "GFP_USER"}, \ + {(__force unsigned long)GFP_KERNEL_ACCOUNT, "GFP_KERNEL_ACCOUNT"}, \ + {(__force unsigned long)GFP_KERNEL, "GFP_KERNEL"}, \ + {(__force unsigned long)GFP_NOFS, "GFP_NOFS"}, \ + {(__force unsigned long)GFP_ATOMIC, "GFP_ATOMIC"}, \ + {(__force unsigned long)GFP_NOIO, "GFP_NOIO"}, \ + {(__force unsigned long)GFP_NOWAIT, "GFP_NOWAIT"}, \ + {(__force unsigned long)GFP_DMA, "GFP_DMA"}, \ + {(__force unsigned long)__GFP_HIGHMEM, "__GFP_HIGHMEM"}, \ + {(__force unsigned long)GFP_DMA32, "GFP_DMA32"}, \ + {(__force unsigned long)__GFP_HIGH, "__GFP_HIGH"}, \ + {(__force unsigned long)__GFP_ATOMIC, "__GFP_ATOMIC"}, \ + {(__force unsigned long)__GFP_IO, "__GFP_IO"}, \ + {(__force unsigned long)__GFP_FS, "__GFP_FS"}, \ + {(__force unsigned long)__GFP_NOWARN, "__GFP_NOWARN"}, \ + {(__force unsigned long)__GFP_RETRY_MAYFAIL, "__GFP_RETRY_MAYFAIL"}, \ + {(__force unsigned long)__GFP_NOFAIL, "__GFP_NOFAIL"}, \ + {(__force unsigned long)__GFP_NORETRY, "__GFP_NORETRY"}, \ + {(__force unsigned long)__GFP_COMP, "__GFP_COMP"}, \ + {(__force unsigned long)__GFP_ZERO, "__GFP_ZERO"}, \ + {(__force unsigned long)__GFP_NOMEMALLOC, "__GFP_NOMEMALLOC"}, \ + {(__force unsigned long)__GFP_MEMALLOC, "__GFP_MEMALLOC"}, \ + {(__force unsigned long)__GFP_HARDWALL, "__GFP_HARDWALL"}, \ + {(__force unsigned long)__GFP_THISNODE, "__GFP_THISNODE"}, \ + {(__force unsigned long)__GFP_RECLAIMABLE, "__GFP_RECLAIMABLE"}, \ + {(__force unsigned long)__GFP_MOVABLE, "__GFP_MOVABLE"}, \ + {(__force unsigned long)__GFP_ACCOUNT, "__GFP_ACCOUNT"}, \ + {(__force unsigned long)__GFP_WRITE, "__GFP_WRITE"}, \ + {(__force unsigned long)__GFP_RECLAIM, "__GFP_RECLAIM"}, \ + {(__force unsigned long)__GFP_DIRECT_RECLAIM, "__GFP_DIRECT_RECLAIM"},\ + {(__force unsigned long)__GFP_KSWAPD_RECLAIM, "__GFP_KSWAPD_RECLAIM"},\ + {(__force unsigned long)__GFP_ZEROTAGS, "__GFP_ZEROTAGS"} \ #ifdef CONFIG_KASAN_HW_TAGS #define __def_gfpflag_names_kasan , \ - {(unsigned long)__GFP_SKIP_ZERO, "__GFP_SKIP_ZERO"}, \ - {(unsigned long)__GFP_SKIP_KASAN_POISON, "__GFP_SKIP_KASAN_POISON"}, \ - {(unsigned long)__GFP_SKIP_KASAN_UNPOISON, "__GFP_SKIP_KASAN_UNPOISON"} + {(__force unsigned long)__GFP_SKIP_ZERO, "__GFP_SKIP_ZERO"}, \ + {(__force unsigned long)__GFP_SKIP_KASAN_POISON, "__GFP_SKIP_KASAN_POISON"}, \ + {(__force unsigned long)__GFP_SKIP_KASAN_UNPOISON, "__GFP_SKIP_KASAN_UNPOISON"} #else #define __def_gfpflag_names_kasan #endif diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index de136dbd623a..408c86244d64 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -96,14 +96,14 @@ TRACE_EVENT(mm_vmscan_wakeup_kswapd, __field( int, nid ) __field( int, zid ) __field( int, order ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->nid = nid; __entry->zid = zid; __entry->order = order; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("nid=%d order=%d gfp_flags=%s", @@ -120,12 +120,12 @@ DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template, TP_STRUCT__entry( __field( int, order ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->order = order; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("order=%d gfp_flags=%s", @@ -210,7 +210,7 @@ TRACE_EVENT(mm_shrink_slab_start, __field(void *, shrink) __field(int, nid) __field(long, nr_objects_to_shrink) - __field(gfp_t, gfp_flags) + __field(unsigned long, gfp_flags) __field(unsigned long, cache_items) __field(unsigned long long, delta) __field(unsigned long, total_scan) @@ -222,7 +222,7 @@ TRACE_EVENT(mm_shrink_slab_start, __entry->shrink = shr->scan_objects; __entry->nid = sc->nid; __entry->nr_objects_to_shrink = nr_objects_to_shrink; - __entry->gfp_flags = sc->gfp_mask; + __entry->gfp_flags = (__force unsigned long)sc->gfp_mask; __entry->cache_items = cache_items; __entry->delta = delta; __entry->total_scan = total_scan; @@ -446,13 +446,13 @@ TRACE_EVENT(mm_vmscan_node_reclaim_begin, TP_STRUCT__entry( __field(int, nid) __field(int, order) - __field(gfp_t, gfp_flags) + __field(unsigned long, gfp_flags) ), TP_fast_assign( __entry->nid = nid; __entry->order = order; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("nid=%d order=%d gfp_flags=%s", -- cgit v1.2.3 From 50d63b5bbfd12262069ad062611cd5e69c5e9e05 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 4 May 2022 16:14:41 -0300 Subject: vfio: Change vfio_external_user_iommu_id() to vfio_file_iommu_group() The only caller wants to get a pointer to the struct iommu_group associated with the VFIO group file. Instead of returning the group ID then searching sysfs for that string to get the struct iommu_group just directly return the iommu_group pointer already held by the vfio_group struct. It already has a safe lifetime due to the struct file kref, the vfio_group and thus the iommu_group cannot be destroyed while the group file is open. Reviewed-by: Kevin Tian Reviewed-by: Christoph Hellwig Reviewed-by: Yi Liu Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/3-v3-f7729924a7ea+25e33-vfio_kvm_no_group_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index be1e7db4a314..d8c34c8490cb 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -140,7 +140,7 @@ extern struct vfio_group *vfio_group_get_external_user(struct file *filep); extern void vfio_group_put_external_user(struct vfio_group *group); extern bool vfio_external_group_match_file(struct vfio_group *group, struct file *filep); -extern int vfio_external_user_iommu_id(struct vfio_group *group); +extern struct iommu_group *vfio_file_iommu_group(struct file *file); extern long vfio_external_check_extension(struct vfio_group *group, unsigned long arg); -- cgit v1.2.3 From c38ff5b0c373fbbd6a249eb461ffd4ae0f9dbfa0 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 4 May 2022 16:14:42 -0300 Subject: vfio: Remove vfio_external_group_match_file() vfio_group_fops_open() ensures there is only ever one struct file open for any struct vfio_group at any time: /* Do we need multiple instances of the group open? Seems not. */ opened = atomic_cmpxchg(&group->opened, 0, 1); if (opened) { vfio_group_put(group); return -EBUSY; Therefor the struct file * can be used directly to search the list of VFIO groups that KVM keeps instead of using the vfio_external_group_match_file() callback to try to figure out if the passed in FD matches the list or not. Delete vfio_external_group_match_file(). Reviewed-by: Kevin Tian Reviewed-by: Christoph Hellwig Reviewed-by: Yi Liu Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/4-v3-f7729924a7ea+25e33-vfio_kvm_no_group_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index d8c34c8490cb..df0adecdf1ea 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -138,8 +138,6 @@ int vfio_mig_get_next_state(struct vfio_device *device, */ extern struct vfio_group *vfio_group_get_external_user(struct file *filep); extern void vfio_group_put_external_user(struct vfio_group *group); -extern bool vfio_external_group_match_file(struct vfio_group *group, - struct file *filep); extern struct iommu_group *vfio_file_iommu_group(struct file *file); extern long vfio_external_check_extension(struct vfio_group *group, unsigned long arg); -- cgit v1.2.3 From a905ad043f32bbb0c35d4325036397f20f30c8a9 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 4 May 2022 16:14:43 -0300 Subject: vfio: Change vfio_external_check_extension() to vfio_file_enforced_coherent() Instead of a general extension check change the function into a limited test if the iommu_domain has enforced coherency, which is the only thing kvm needs to query. Make the new op self contained by properly refcounting the container before touching it. Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/5-v3-f7729924a7ea+25e33-vfio_kvm_no_group_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index df0adecdf1ea..7cc374da4839 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -139,8 +139,7 @@ int vfio_mig_get_next_state(struct vfio_device *device, extern struct vfio_group *vfio_group_get_external_user(struct file *filep); extern void vfio_group_put_external_user(struct vfio_group *group); extern struct iommu_group *vfio_file_iommu_group(struct file *file); -extern long vfio_external_check_extension(struct vfio_group *group, - unsigned long arg); +extern bool vfio_file_enforced_coherent(struct file *file); #define VFIO_PIN_PAGES_MAX_ENTRIES (PAGE_SIZE/sizeof(unsigned long)) -- cgit v1.2.3 From ba70a89f3c2a8279809ea0fc7684857c91938b8a Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 4 May 2022 16:14:44 -0300 Subject: vfio: Change vfio_group_set_kvm() to vfio_file_set_kvm() Just change the argument from struct vfio_group to struct file *. Reviewed-by: Kevin Tian Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/6-v3-f7729924a7ea+25e33-vfio_kvm_no_group_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 7cc374da4839..b298a26c4f07 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -15,6 +15,8 @@ #include #include +struct kvm; + /* * VFIO devices can be placed in a set, this allows all devices to share this * structure and the VFIO core will provide a lock that is held around @@ -140,6 +142,7 @@ extern struct vfio_group *vfio_group_get_external_user(struct file *filep); extern void vfio_group_put_external_user(struct vfio_group *group); extern struct iommu_group *vfio_file_iommu_group(struct file *file); extern bool vfio_file_enforced_coherent(struct file *file); +extern void vfio_file_set_kvm(struct file *file, struct kvm *kvm); #define VFIO_PIN_PAGES_MAX_ENTRIES (PAGE_SIZE/sizeof(unsigned long)) @@ -170,8 +173,6 @@ extern int vfio_unregister_notifier(struct vfio_device *device, enum vfio_notify_type type, struct notifier_block *nb); -struct kvm; -extern void vfio_group_set_kvm(struct vfio_group *group, struct kvm *kvm); /* * Sub-module helpers -- cgit v1.2.3 From 6a985ae80befcf2c00e7c889336bfe9e9739e2ef Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 4 May 2022 16:14:46 -0300 Subject: vfio/pci: Use the struct file as the handle not the vfio_group VFIO PCI does a security check as part of hot reset to prove that the user has permission to manipulate all the devices that will be impacted by the reset. Use a new API vfio_file_has_dev() to perform this security check against the struct file directly and remove the vfio_group from VFIO PCI. Since VFIO PCI was the last user of vfio_group_get_external_user() and vfio_group_put_external_user() remove it as well. Reviewed-by: Kevin Tian Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/8-v3-f7729924a7ea+25e33-vfio_kvm_no_group_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index b298a26c4f07..45b287826ce6 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -138,11 +138,10 @@ int vfio_mig_get_next_state(struct vfio_device *device, /* * External user API */ -extern struct vfio_group *vfio_group_get_external_user(struct file *filep); -extern void vfio_group_put_external_user(struct vfio_group *group); extern struct iommu_group *vfio_file_iommu_group(struct file *file); extern bool vfio_file_enforced_coherent(struct file *file); extern void vfio_file_set_kvm(struct file *file, struct kvm *kvm); +extern bool vfio_file_has_dev(struct file *file, struct vfio_device *device); #define VFIO_PIN_PAGES_MAX_ENTRIES (PAGE_SIZE/sizeof(unsigned long)) -- cgit v1.2.3 From 2ed3bf188b33630cf9d93b996ebf001847a00b5a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 11 Apr 2022 13:01:16 +0200 Subject: netfilter: ecache: use dedicated list for event redelivery This disentangles event redelivery and the percpu dying list. Because entries are now stored on a dedicated list, all entries are in NFCT_ECACHE_DESTROY_FAIL state and all entries still have confirmed bit set -- the reference count is at least 1. The 'struct net' back-pointer can be removed as well. The pcpu dying list will be removed eventually, it has no functionality. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 3 ++- include/net/netfilter/nf_conntrack_ecache.h | 2 -- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 69e6c6a218be..28672a944499 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -45,7 +45,8 @@ union nf_conntrack_expect_proto { struct nf_conntrack_net_ecache { struct delayed_work dwork; - struct netns_ct *ct_net; + spinlock_t dying_lock; + struct hlist_nulls_head dying_list; }; struct nf_conntrack_net { diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 6c4c490a3e34..a6135b5030dd 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -14,7 +14,6 @@ #include enum nf_ct_ecache_state { - NFCT_ECACHE_UNKNOWN, /* destroy event not sent */ NFCT_ECACHE_DESTROY_FAIL, /* tried but failed to send destroy event */ NFCT_ECACHE_DESTROY_SENT, /* sent destroy event after failure */ }; @@ -23,7 +22,6 @@ struct nf_conntrack_ecache { unsigned long cache; /* bitops want long */ u16 ctmask; /* bitmask of ct events to be delivered */ u16 expmask; /* bitmask of expect events to be delivered */ - enum nf_ct_ecache_state state:8;/* ecache state */ u32 missed; /* missed events */ u32 portid; /* netlink portid of destroyer */ }; -- cgit v1.2.3 From 0d3cc504ba9cdcff76346306c37eb1ea01e60a86 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 11 Apr 2022 13:01:17 +0200 Subject: netfilter: conntrack: include ecache dying list in dumps The new pernet dying list includes conntrack entries that await delivery of the 'destroy' event via ctnetlink. The old percpu dying list will be removed soon. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_ecache.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index a6135b5030dd..b57d73785e4d 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -164,6 +164,8 @@ void nf_conntrack_ecache_work(struct net *net, enum nf_ct_ecache_state state); void nf_conntrack_ecache_pernet_init(struct net *net); void nf_conntrack_ecache_pernet_fini(struct net *net); +struct nf_conntrack_net_ecache *nf_conn_pernet_ecache(const struct net *net); + static inline bool nf_conntrack_ecache_dwork_pending(const struct net *net) { return net->ct.ecache_dwork_pending; -- cgit v1.2.3 From 1397af5bfd7d32b0cf2adb70a78c9a9e8f11d912 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 11 Apr 2022 13:01:18 +0200 Subject: netfilter: conntrack: remove the percpu dying list Its no longer needed. Entries that need event redelivery are placed on the new pernet dying list. The advantage is that there is no need to take additional spinlock on conntrack removal unless event redelivery failed or the conntrack entry was never added to the table in the first place (confirmed bit not set). The IPS_CONFIRMED bit now needs to be set as soon as the entry has been unlinked from the unconfirmed list, else the destroy function may attempt to unlink it a second time. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netns/conntrack.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index 0294f3d473af..e985a3010b89 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -96,7 +96,6 @@ struct nf_ip_net { struct ct_pcpu { spinlock_t lock; struct hlist_nulls_head unconfirmed; - struct hlist_nulls_head dying; }; struct netns_ct { -- cgit v1.2.3 From 78222bacfca97cb18505df1ba5f3591864498a7e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 11 Apr 2022 13:01:19 +0200 Subject: netfilter: cttimeout: decouple unlink and free on netns destruction Make it so netns pre_exit unlinks the objects from the pernet list, so they cannot be found anymore. netns core issues a synchronize_rcu() before calling the exit hooks so any the time the exit hooks run unconfirmed nf_conn entries have been free'd or they have been committed to the hashtable. The exit hook still tags unconfirmed entries as dying, this can now be removed in a followup change. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_timeout.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h index 3ea94f6f3844..fea258983d23 100644 --- a/include/net/netfilter/nf_conntrack_timeout.h +++ b/include/net/netfilter/nf_conntrack_timeout.h @@ -17,14 +17,6 @@ struct nf_ct_timeout { char data[]; }; -struct ctnl_timeout { - struct list_head head; - struct rcu_head rcu_head; - refcount_t refcnt; - char name[CTNL_TIMEOUT_NAME_MAX]; - struct nf_ct_timeout timeout; -}; - struct nf_conn_timeout { struct nf_ct_timeout __rcu *timeout; }; -- cgit v1.2.3 From 17438b42ce14cb60ceda9ae62ad5dd022d55a216 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 11 Apr 2022 13:01:20 +0200 Subject: netfilter: remove nf_ct_unconfirmed_destroy helper This helper tags connections not yet in the conntrack table as dying. These nf_conn entries will be dropped instead when the core attempts to insert them from the input or postrouting 'confirm' hook. After the previous change, the entries get unlinked from the list earlier, so that by the time the actual exit hook runs, new connections no longer have a timeout policy assigned. Its enough to walk the hashtable instead. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 28672a944499..f60212244b13 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -237,9 +237,6 @@ static inline bool nf_ct_kill(struct nf_conn *ct) return nf_ct_delete(ct, 0, 0); } -/* Set all unconfirmed conntrack as dying */ -void nf_ct_unconfirmed_destroy(struct net *); - /* Iterate over all conntracks: if iter returns true, it's deleted. */ void nf_ct_iterate_cleanup_net(struct net *net, int (*iter)(struct nf_conn *i, void *data), -- cgit v1.2.3 From c56716c69ce1ac320432fb1ea5654196ba24d2f8 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 11 Apr 2022 13:01:21 +0200 Subject: netfilter: extensions: introduce extension genid count Multiple netfilter extensions store pointers to external data in their extension area struct. Examples: 1. Timeout policies 2. Connection tracking helpers. No references are taken for these. When a helper or timeout policy is removed, the conntrack table gets traversed and affected extensions are cleared. Conntrack entries not yet in the hashtable are referenced via a special list, the unconfirmed list. On removal of a policy or connection tracking helper, the unconfirmed list gets traversed an all entries are marked as dying, this prevents them from getting committed to the table at insertion time: core checks for dying bit, if set, the conntrack entry gets destroyed at confirm time. The disadvantage is that each new conntrack has to be added to the percpu unconfirmed list, and each insertion needs to remove it from this list. The list is only ever needed when a policy or helper is removed -- a rare occurrence. Add a generation ID count: Instead of adding to the list and then traversing that list on policy/helper removal, increment a counter that is stored in the extension area. For unconfirmed conntracks, the extension has the genid valid at ct allocation time. Removal of a helper/policy etc. increments the counter. At confirmation time, validate that ext->genid == global_id. If the stored number is not the same, do not allow the conntrack insertion, just like as if a confirmed-list traversal would have flagged the entry as dying. After insertion, the genid is no longer relevant (conntrack entries are now reachable via the conntrack table iterators and is set to 0. This allows removal of the percpu unconfirmed list. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_extend.h | 31 +++++++++++++++-------------- include/net/netfilter/nf_conntrack_labels.h | 10 +++++++++- 2 files changed, 25 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 96635ad2acc7..0b247248b032 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -34,21 +34,11 @@ enum nf_ct_ext_id { NF_CT_EXT_NUM, }; -#define NF_CT_EXT_HELPER_TYPE struct nf_conn_help -#define NF_CT_EXT_NAT_TYPE struct nf_conn_nat -#define NF_CT_EXT_SEQADJ_TYPE struct nf_conn_seqadj -#define NF_CT_EXT_ACCT_TYPE struct nf_conn_acct -#define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache -#define NF_CT_EXT_TSTAMP_TYPE struct nf_conn_tstamp -#define NF_CT_EXT_TIMEOUT_TYPE struct nf_conn_timeout -#define NF_CT_EXT_LABELS_TYPE struct nf_conn_labels -#define NF_CT_EXT_SYNPROXY_TYPE struct nf_conn_synproxy -#define NF_CT_EXT_ACT_CT_TYPE struct nf_conn_act_ct_ext - /* Extensions: optional stuff which isn't permanently in struct. */ struct nf_ct_ext { u8 offset[NF_CT_EXT_NUM]; u8 len; + unsigned int gen_id; char data[] __aligned(8); }; @@ -62,17 +52,28 @@ static inline bool nf_ct_ext_exist(const struct nf_conn *ct, u8 id) return (ct->ext && __nf_ct_ext_exist(ct->ext, id)); } -static inline void *__nf_ct_ext_find(const struct nf_conn *ct, u8 id) +void *__nf_ct_ext_find(const struct nf_ct_ext *ext, u8 id); + +static inline void *nf_ct_ext_find(const struct nf_conn *ct, u8 id) { - if (!nf_ct_ext_exist(ct, id)) + struct nf_ct_ext *ext = ct->ext; + + if (!ext || !__nf_ct_ext_exist(ext, id)) return NULL; + if (unlikely(ext->gen_id)) + return __nf_ct_ext_find(ext, id); + return (void *)ct->ext + ct->ext->offset[id]; } -#define nf_ct_ext_find(ext, id) \ - ((id##_TYPE *)__nf_ct_ext_find((ext), (id))) /* Add this type, returns pointer to data or NULL. */ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp); +/* ext genid. if ext->id != ext_genid, extensions cannot be used + * anymore unless conntrack has CONFIRMED bit set. + */ +extern atomic_t nf_conntrack_ext_genid; +void nf_ct_ext_bump_genid(void); + #endif /* _NF_CONNTRACK_EXTEND_H */ diff --git a/include/net/netfilter/nf_conntrack_labels.h b/include/net/netfilter/nf_conntrack_labels.h index 3c23298e68ca..66bab6c60d12 100644 --- a/include/net/netfilter/nf_conntrack_labels.h +++ b/include/net/netfilter/nf_conntrack_labels.h @@ -17,10 +17,18 @@ struct nf_conn_labels { unsigned long bits[NF_CT_LABELS_MAX_SIZE / sizeof(long)]; }; +/* Can't use nf_ct_ext_find(), flow dissector cannot use symbols + * exported by nf_conntrack module. + */ static inline struct nf_conn_labels *nf_ct_labels_find(const struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_LABELS - return nf_ct_ext_find(ct, NF_CT_EXT_LABELS); + struct nf_ct_ext *ext = ct->ext; + + if (!ext || !__nf_ct_ext_exist(ext, NF_CT_EXT_LABELS)) + return NULL; + + return (void *)ct->ext + ct->ext->offset[NF_CT_EXT_LABELS]; #else return NULL; #endif -- cgit v1.2.3 From 8a75a2c1741073f0c2d7bee146648e717527e048 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 11 Apr 2022 13:01:24 +0200 Subject: netfilter: conntrack: remove unconfirmed list It has no function anymore and can be removed. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 1 - include/net/netns/conntrack.h | 6 ------ 2 files changed, 7 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index f60212244b13..3ce9a5b42fe5 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -101,7 +101,6 @@ struct nf_conn { /* Have we seen traffic both ways yet? (bitset) */ unsigned long status; - u16 cpu; possible_net_t ct_net; #if IS_ENABLED(CONFIG_NF_NAT) diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index e985a3010b89..a71cfd4e2f21 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -93,11 +93,6 @@ struct nf_ip_net { #endif }; -struct ct_pcpu { - spinlock_t lock; - struct hlist_nulls_head unconfirmed; -}; - struct netns_ct { #ifdef CONFIG_NF_CONNTRACK_EVENTS bool ecache_dwork_pending; @@ -109,7 +104,6 @@ struct netns_ct { u8 sysctl_tstamp; u8 sysctl_checksum; - struct ct_pcpu __percpu *pcpu_lists; struct ip_conntrack_stat __percpu *stat; struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb; struct nf_ip_net nf_ct_proto; -- cgit v1.2.3 From 8169ff584003c871a226719e998bb034231954d6 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 8 Apr 2022 13:10:19 +0200 Subject: netfilter: conntrack: add nf_ct_iter_data object for nf_ct_iterate_cleanup*() This patch adds a structure to collect all the context data that is passed to the cleanup iterator. struct nf_ct_iter_data { struct net *net; void *data; u32 portid; int report; }; There is a netns field that allows to clean up conntrack entries specifically owned by the specified netns. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 3ce9a5b42fe5..a32be8aa7ed2 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -236,10 +236,16 @@ static inline bool nf_ct_kill(struct nf_conn *ct) return nf_ct_delete(ct, 0, 0); } +struct nf_ct_iter_data { + struct net *net; + void *data; + u32 portid; + int report; +}; + /* Iterate over all conntracks: if iter returns true, it's deleted. */ -void nf_ct_iterate_cleanup_net(struct net *net, - int (*iter)(struct nf_conn *i, void *data), - void *data, u32 portid, int report); +void nf_ct_iterate_cleanup_net(int (*iter)(struct nf_conn *i, void *data), + const struct nf_ct_iter_data *iter_data); /* also set unconfirmed conntracks as dying. Only use in module exit path. */ void nf_ct_iterate_destroy(int (*iter)(struct nf_conn *i, void *data), -- cgit v1.2.3 From 2794cdb0b97bfe62d25c996c8afe4832207e78bc Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 25 Apr 2022 15:15:41 +0200 Subject: netfilter: nfnetlink: allow to detect if ctnetlink listeners exist At this time, every new conntrack gets the 'event cache extension' enabled for it. This is because the 'net.netfilter.nf_conntrack_events' sysctl defaults to 1. Changing the default to 0 means that commands that rely on the event notification extension, e.g. 'conntrack -E' or conntrackd, stop working. We COULD detect if there is a listener by means of 'nfnetlink_has_listeners()' and only add the extension if this is true. The downside is a dependency from conntrack module to nfnetlink module. This adds a different way: inc/dec a counter whenever a ctnetlink group is being (un)subscribed and toggle a flag in struct net. Next patches will take advantage of this and will only add the event extension if the flag is set. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netns/conntrack.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index a71cfd4e2f21..0677cd3de034 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -95,6 +95,7 @@ struct nf_ip_net { struct netns_ct { #ifdef CONFIG_NF_CONNTRACK_EVENTS + bool ctnetlink_has_listener; bool ecache_dwork_pending; #endif u8 sysctl_log_invalid; /* Log invalid packets */ -- cgit v1.2.3 From b0a7ab4a776583b4344e8313638dc795f7589209 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 25 Apr 2022 15:15:42 +0200 Subject: netfilter: conntrack: un-inline nf_ct_ecache_ext_add Only called when new ct is allocated or the extension isn't present. This function will be extended, place this in the conntrack module instead of inlining. The callers already depend on nf_conntrack module. Return value is changed to bool, noone used the returned pointer. Make sure that the core drops the newly allocated conntrack if the extension is requested but can't be added. This makes it necessary to ifdef the section, as the stub always returns false we'd drop every new conntrack if the the ecache extension is disabled in kconfig. Add from data path (xt_CT, nft_ct) is unchanged. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_ecache.h | 30 +++++------------------------ 1 file changed, 5 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index b57d73785e4d..2e3d58439e34 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -36,31 +36,6 @@ nf_ct_ecache_find(const struct nf_conn *ct) #endif } -static inline struct nf_conntrack_ecache * -nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp) -{ -#ifdef CONFIG_NF_CONNTRACK_EVENTS - struct net *net = nf_ct_net(ct); - struct nf_conntrack_ecache *e; - - if (!ctmask && !expmask && net->ct.sysctl_events) { - ctmask = ~0; - expmask = ~0; - } - if (!ctmask && !expmask) - return NULL; - - e = nf_ct_ext_add(ct, NF_CT_EXT_ECACHE, gfp); - if (e) { - e->ctmask = ctmask; - e->expmask = expmask; - } - return e; -#else - return NULL; -#endif -} - #ifdef CONFIG_NF_CONNTRACK_EVENTS /* This structure is passed to event handler */ @@ -89,6 +64,7 @@ void nf_ct_deliver_cached_events(struct nf_conn *ct); int nf_conntrack_eventmask_report(unsigned int eventmask, struct nf_conn *ct, u32 portid, int report); +bool nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp); #else static inline void nf_ct_deliver_cached_events(const struct nf_conn *ct) @@ -103,6 +79,10 @@ static inline int nf_conntrack_eventmask_report(unsigned int eventmask, return 0; } +static inline bool nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp) +{ + return false; +} #endif static inline void -- cgit v1.2.3 From 8edc813111001e9be3cce066d3d4091d2ef04a1d Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 25 Apr 2022 15:15:44 +0200 Subject: netfilter: prefer extension check to pointer check The pointer check usually results in a 'false positive': its likely that the ctnetlink module is loaded but no event monitoring is enabled. After recent change to autodetect ctnetlink usage and only allocate the ecache extension if a listener is active, check if the extension is present on a given conntrack. If its not there, there is nothing to report and calls to the notification framework can be elided. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_core.h | 2 +- include/net/netfilter/nf_conntrack_ecache.h | 31 ++++++++++++++--------------- 2 files changed, 16 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 13807ea94cd2..6406cfee34c2 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -60,7 +60,7 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb) if (ct) { if (!nf_ct_is_confirmed(ct)) ret = __nf_conntrack_confirm(skb); - if (likely(ret == NF_ACCEPT)) + if (ret == NF_ACCEPT && nf_ct_ecache_exist(ct)) nf_ct_deliver_cached_events(ct); } return ret; diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 2e3d58439e34..0c1dac318e02 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -36,6 +36,15 @@ nf_ct_ecache_find(const struct nf_conn *ct) #endif } +static inline bool nf_ct_ecache_exist(const struct nf_conn *ct) +{ +#ifdef CONFIG_NF_CONNTRACK_EVENTS + return nf_ct_ext_exist(ct, NF_CT_EXT_ECACHE); +#else + return false; +#endif +} + #ifdef CONFIG_NF_CONNTRACK_EVENTS /* This structure is passed to event handler */ @@ -108,30 +117,20 @@ nf_conntrack_event_report(enum ip_conntrack_events event, struct nf_conn *ct, u32 portid, int report) { #ifdef CONFIG_NF_CONNTRACK_EVENTS - const struct net *net = nf_ct_net(ct); - - if (!rcu_access_pointer(net->ct.nf_conntrack_event_cb)) - return 0; - - return nf_conntrack_eventmask_report(1 << event, ct, portid, report); -#else - return 0; + if (nf_ct_ecache_exist(ct)) + return nf_conntrack_eventmask_report(1 << event, ct, portid, report); #endif + return 0; } static inline int nf_conntrack_event(enum ip_conntrack_events event, struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_EVENTS - const struct net *net = nf_ct_net(ct); - - if (!rcu_access_pointer(net->ct.nf_conntrack_event_cb)) - return 0; - - return nf_conntrack_eventmask_report(1 << event, ct, 0, 0); -#else - return 0; + if (nf_ct_ecache_exist(ct)) + return nf_conntrack_eventmask_report(1 << event, ct, 0, 0); #endif + return 0; } #ifdef CONFIG_NF_CONNTRACK_EVENTS -- cgit v1.2.3 From 4f9bd53084d18c2f9f1ec68fa56587b99a2cef00 Mon Sep 17 00:00:00 2001 From: Kevin Mitchell Date: Fri, 29 Apr 2022 20:40:27 -0700 Subject: netfilter: conntrack: skip verification of zero UDP checksum The checksum is optional for UDP packets. However nf_reject would previously require a valid checksum to elicit a response such as ICMP_DEST_UNREACH. Add some logic to nf_reject_verify_csum to determine if a UDP packet has a zero checksum and should therefore not be verified. Signed-off-by: Kevin Mitchell Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_reject.h | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_reject.h b/include/net/netfilter/nf_reject.h index 9051c3a0c8e7..7c669792fb9c 100644 --- a/include/net/netfilter/nf_reject.h +++ b/include/net/netfilter/nf_reject.h @@ -5,12 +5,28 @@ #include #include -static inline bool nf_reject_verify_csum(__u8 proto) +static inline bool nf_reject_verify_csum(struct sk_buff *skb, int dataoff, + __u8 proto) { /* Skip protocols that don't use 16-bit one's complement checksum * of the entire payload. */ switch (proto) { + /* Protocols with optional checksums. */ + case IPPROTO_UDP: { + const struct udphdr *udp_hdr; + struct udphdr _udp_hdr; + + udp_hdr = skb_header_pointer(skb, dataoff, + sizeof(_udp_hdr), + &_udp_hdr); + if (!udp_hdr || udp_hdr->check) + return true; + + return false; + } + case IPPROTO_GRE: + /* Protocols with other integrity checks. */ case IPPROTO_AH: case IPPROTO_ESP: @@ -19,9 +35,6 @@ static inline bool nf_reject_verify_csum(__u8 proto) /* Protocols with partial checksums. */ case IPPROTO_UDPLITE: case IPPROTO_DCCP: - - /* Protocols with optional checksums. */ - case IPPROTO_GRE: return false; } return true; -- cgit v1.2.3 From 1af0e4a0233fea7e8226cb977d379dc20f9bbe11 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20G=C3=B6ttsche?= Date: Thu, 17 Feb 2022 15:18:57 +0100 Subject: security: declare member holding string literal const MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The struct security_hook_list member lsm is assigned in security_add_hooks() with string literals passed from the individual security modules. Declare the function parameter and the struct member const to signal their immutability. Reported by Clang [-Wwrite-strings]: security/selinux/hooks.c:7388:63: error: passing 'const char [8]' to parameter of type 'char *' discards qualifiers [-Werror,-Wincompatible-pointer-types-discards-qualifiers] security_add_hooks(selinux_hooks, ARRAY_SIZE(selinux_hooks), selinux); ^~~~~~~~~ ./include/linux/lsm_hooks.h:1629:11: note: passing argument to parameter 'lsm' here char *lsm); ^ Signed-off-by: Christian Göttsche Reviewed-by: Paul Moore Reviewed-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hooks.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 419b5febc3ca..47cdf3fbecef 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1595,7 +1595,7 @@ struct security_hook_list { struct hlist_node list; struct hlist_head *head; union security_list_options hook; - char *lsm; + const char *lsm; } __randomize_layout; /* @@ -1630,7 +1630,7 @@ extern struct security_hook_heads security_hook_heads; extern char *lsm_names; extern void security_add_hooks(struct security_hook_list *hooks, int count, - char *lsm); + const char *lsm); #define LSM_FLAG_LEGACY_MAJOR BIT(0) #define LSM_FLAG_EXCLUSIVE BIT(1) -- cgit v1.2.3 From 1366992e16bddd5e2d9a561687f367f9f802e2e4 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Sun, 10 Apr 2022 16:49:50 +0200 Subject: timekeeping: Add raw clock fallback for random_get_entropy() The addition of random_get_entropy_fallback() provides access to whichever time source has the highest frequency, which is useful for gathering entropy on platforms without available cycle counters. It's not necessarily as good as being able to quickly access a cycle counter that the CPU has, but it's still something, even when it falls back to being jiffies-based. In the event that a given arch does not define get_cycles(), falling back to the get_cycles() default implementation that returns 0 is really not the best we can do. Instead, at least calling random_get_entropy_fallback() would be preferable, because that always needs to return _something_, even falling back to jiffies eventually. It's not as though random_get_entropy_fallback() is super high precision or guaranteed to be entropic, but basically anything that's not zero all the time is better than returning zero all the time. Finally, since random_get_entropy_fallback() is used during extremely early boot when randomizing freelists in mm_init(), it can be called before timekeeping has been initialized. In that case there really is nothing we can do; jiffies hasn't even started ticking yet. So just give up and return 0. Suggested-by: Thomas Gleixner Signed-off-by: Jason A. Donenfeld Reviewed-by: Thomas Gleixner Cc: Arnd Bergmann Cc: Theodore Ts'o --- include/linux/timex.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/timex.h b/include/linux/timex.h index 5745c90c8800..3871b06bd302 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -62,6 +62,8 @@ #include #include +unsigned long random_get_entropy_fallback(void); + #include #ifndef random_get_entropy @@ -74,8 +76,14 @@ * * By default we use get_cycles() for this purpose, but individual * architectures may override this in their asm/timex.h header file. + * If a given arch does not have get_cycles(), then we fallback to + * using random_get_entropy_fallback(). */ +#ifdef get_cycles #define random_get_entropy() ((unsigned long)get_cycles()) +#else +#define random_get_entropy() random_get_entropy_fallback() +#endif #endif /* -- cgit v1.2.3 From 16d1e00c7e8a4950e914223b3112144289a82913 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Mon, 9 May 2022 15:42:52 -0700 Subject: bpf: Add MEM_UNINIT as a bpf_type_flag Instead of having uninitialized versions of arguments as separate bpf_arg_types (eg ARG_PTR_TO_UNINIT_MEM as the uninitialized version of ARG_PTR_TO_MEM), we can instead use MEM_UNINIT as a bpf_type_flag modifier to denote that the argument is uninitialized. Doing so cleans up some of the logic in the verifier. We no longer need to do two checks against an argument type (eg "if (base_type(arg_type) == ARG_PTR_TO_MEM || base_type(arg_type) == ARG_PTR_TO_UNINIT_MEM)"), since uninitialized and initialized versions of the same argument type will now share the same base type. In the near future, MEM_UNINIT will be used by dynptr helper functions as well. Signed-off-by: Joanne Koong Acked-by: Andrii Nakryiko Acked-by: David Vernet Link: https://lore.kernel.org/r/20220509224257.3222614-2-joannelkoong@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5061ccd8b2dc..c107392b0ba7 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -390,7 +390,10 @@ enum bpf_type_flag { */ PTR_UNTRUSTED = BIT(6 + BPF_BASE_TYPE_BITS), - __BPF_TYPE_LAST_FLAG = PTR_UNTRUSTED, + MEM_UNINIT = BIT(7 + BPF_BASE_TYPE_BITS), + + __BPF_TYPE_FLAG_MAX, + __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; /* Max number of base types. */ @@ -409,16 +412,11 @@ enum bpf_arg_type { ARG_CONST_MAP_PTR, /* const argument used as pointer to bpf_map */ ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */ ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */ - ARG_PTR_TO_UNINIT_MAP_VALUE, /* pointer to valid memory used to store a map value */ - /* the following constraints used to prototype bpf_memcmp() and other - * functions that access data on eBPF program stack + /* Used to prototype bpf_memcmp() and other functions that access data + * on eBPF program stack */ ARG_PTR_TO_MEM, /* pointer to valid memory (stack, packet, map value) */ - ARG_PTR_TO_UNINIT_MEM, /* pointer to memory does not need to be initialized, - * helper function must fill all bytes or clear - * them in error case. - */ ARG_CONST_SIZE, /* number of bytes accessed from memory */ ARG_CONST_SIZE_OR_ZERO, /* number of bytes accessed from memory or 0 */ @@ -450,6 +448,10 @@ enum bpf_arg_type { ARG_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_ALLOC_MEM, ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK, ARG_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID, + /* pointer to memory does not need to be initialized, helper function must fill + * all bytes or clear them in error case. + */ + ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | ARG_PTR_TO_MEM, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. -- cgit v1.2.3 From e7392b4eca84e86718a7b73aea8fa5573b06ba76 Mon Sep 17 00:00:00 2001 From: "Fabio M. De Francesco" Date: Fri, 13 May 2022 16:48:55 -0700 Subject: mm/highmem: fix kernel-doc warnings in highmem*.h Patch series "Extend and reorganize Highmem's documentation", v4. This series has the purpose to extend and reorganize Highmem's documentation. This is a work in progress because some information should still be moved from highmem.rst to highmem.h and highmem-internal.h. Specifically I'm talking about moving the "how to" information to the relevant headers, as it as been suggested by Ira Weiny (Intel). Also, this is a work in progress because some kdocs in highmem.h and highmem-internal.h should be improved. This patch (of 4): `scripts/kernel-doc -v -none include/linux/highmem*` reports the following warnings: include/linux/highmem.h:160: warning: expecting prototype for kunmap_atomic(). Prototype was for nr_free_highpages() instead include/linux/highmem.h:204: warning: No description found for return value of 'alloc_zeroed_user_highpage_movable' include/linux/highmem-internal.h:256: warning: Function parameter or member '__addr' not described in 'kunmap_atomic' include/linux/highmem-internal.h:256: warning: Excess function parameter 'addr' description in 'kunmap_atomic' Fix these warnings by (1) moving the kernel-doc comments from highmem.h to highmem-internal.h (which is the file were the kunmap_atomic() macro is actually defined), (2) extending and merging it with the comment which was already in highmem-internal.h, and (3) using correct parameter names (4) correcting a few technical inaccuracies in comments, and (5) adding a deprecation notice in kunmap_atomic() for consistency with kmap_atomic(). Link: https://lkml.kernel.org/r/20220428212455.892-1-fmdefrancesco@gmail.com Link: https://lkml.kernel.org/r/20220428212455.892-2-fmdefrancesco@gmail.com Signed-off-by: Fabio M. De Francesco Reviewed-by: Sebastian Andrzej Siewior Reviewed-by: Ira Weiny Cc: Matthew Wilcox Cc: Mike Rapoport Cc: Catalin Marinas Cc: Will Deacon Cc: Peter Collingbourne Cc: Vlastimil Babka Cc: Jonathan Corbet Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Jonathan Corbet Signed-off-by: Andrew Morton --- include/linux/highmem-internal.h | 18 +++++++++++++++--- include/linux/highmem.h | 22 ++++++++-------------- 2 files changed, 23 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index a77be5630209..a694ca95c4ed 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -236,9 +236,21 @@ static inline unsigned long totalhigh_pages(void) { return 0UL; } #endif /* CONFIG_HIGHMEM */ -/* - * Prevent people trying to call kunmap_atomic() as if it were kunmap() - * kunmap_atomic() should get the return value of kmap_atomic, not the page. +/** + * kunmap_atomic - Unmap the virtual address mapped by kmap_atomic() - deprecated! + * @__addr: Virtual address to be unmapped + * + * Unmaps an address previously mapped by kmap_atomic() and re-enables + * pagefaults. Depending on PREEMP_RT configuration, re-enables also + * migration and preemption. Users should not count on these side effects. + * + * Mappings should be unmapped in the reverse order that they were mapped. + * See kmap_local_page() for details on nesting. + * + * @__addr can be any address within the mapped page, so there is no need + * to subtract any offset that has been added. In contrast to kunmap(), + * this function takes the address returned from kmap_atomic(), not the + * page passed to it. The compiler will warn you if you pass the page. */ #define kunmap_atomic(__addr) \ do { \ diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 67720bfd6ade..c05ae395898a 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -37,7 +37,7 @@ static inline void *kmap(struct page *page); /** * kunmap - Unmap the virtual address mapped by kmap() - * @addr: Virtual address to be unmapped + * @page: Pointer to the page which was mapped by kmap() * * Counterpart to kmap(). A NOOP for CONFIG_HIGHMEM=n and for mappings of * pages in the low memory area. @@ -138,24 +138,16 @@ static inline void *kmap_local_folio(struct folio *folio, size_t offset); * * Returns: The virtual address of the mapping * - * Effectively a wrapper around kmap_local_page() which disables pagefaults - * and preemption. + * In fact a wrapper around kmap_local_page() which also disables pagefaults + * and, depending on PREEMPT_RT configuration, also CPU migration and + * preemption. Therefore users should not count on the latter two side effects. + * + * Mappings should always be released by kunmap_atomic(). * * Do not use in new code. Use kmap_local_page() instead. */ static inline void *kmap_atomic(struct page *page); -/** - * kunmap_atomic - Unmap the virtual address mapped by kmap_atomic() - * @addr: Virtual address to be unmapped - * - * Counterpart to kmap_atomic(). - * - * Effectively a wrapper around kunmap_local() which additionally undoes - * the side effects of kmap_atomic(), i.e. reenabling pagefaults and - * preemption. - */ - /* Highmem related interfaces for management code */ static inline unsigned int nr_free_highpages(void); static inline unsigned long totalhigh_pages(void); @@ -191,6 +183,8 @@ static inline void clear_user_highpage(struct page *page, unsigned long vaddr) * @vma: The VMA the page is to be allocated for * @vaddr: The virtual address the page will be inserted into * + * Returns: The allocated and zeroed HIGHMEM page + * * This function will allocate a page for a VMA that the caller knows will * be able to migrate in the future using move_pages() or reclaimed * -- cgit v1.2.3 From 85a85e7601263f2b4edc86136dd0172c2cfbfaa1 Mon Sep 17 00:00:00 2001 From: "Fabio M. De Francesco" Date: Fri, 13 May 2022 16:48:55 -0700 Subject: Documentation/vm: move "Using kmap-atomic" to highmem.h The use of kmap_atomic() is new code is being deprecated in favor of kmap_local_page(). For this reason the "Using kmap_atomic" section in highmem.rst is obsolete and unnecessary, but it can still help developers if it were moved to kdocs in highmem.h. Therefore, move the relevant parts of this section from highmem.rst and merge them with the kdocs in highmem.h. Link: https://lkml.kernel.org/r/20220428212455.892-4-fmdefrancesco@gmail.com Signed-off-by: Fabio M. De Francesco Suggested-by: Ira Weiny Reviewed-by: Sebastian Andrzej Siewior Reviewed-by: Ira Weiny Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Catalin Marinas Cc: Mike Rapoport Cc: Peter Collingbourne Cc: Vlastimil Babka Cc: Will Deacon Cc: Jonathan Corbet Signed-off-by: Andrew Morton --- include/linux/highmem.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index c05ae395898a..3af34de54330 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -145,6 +145,37 @@ static inline void *kmap_local_folio(struct folio *folio, size_t offset); * Mappings should always be released by kunmap_atomic(). * * Do not use in new code. Use kmap_local_page() instead. + * + * It is used in atomic context when code wants to access the contents of a + * page that might be allocated from high memory (see __GFP_HIGHMEM), for + * example a page in the pagecache. The API has two functions, and they + * can be used in a manner similar to the following: + * + * -- Find the page of interest. -- + * struct page *page = find_get_page(mapping, offset); + * + * -- Gain access to the contents of that page. -- + * void *vaddr = kmap_atomic(page); + * + * -- Do something to the contents of that page. -- + * memset(vaddr, 0, PAGE_SIZE); + * + * -- Unmap that page. -- + * kunmap_atomic(vaddr); + * + * Note that the kunmap_atomic() call takes the result of the kmap_atomic() + * call, not the argument. + * + * If you need to map two pages because you want to copy from one page to + * another you need to keep the kmap_atomic calls strictly nested, like: + * + * vaddr1 = kmap_atomic(page1); + * vaddr2 = kmap_atomic(page2); + * + * memcpy(vaddr1, vaddr2, PAGE_SIZE); + * + * kunmap_atomic(vaddr2); + * kunmap_atomic(vaddr1); */ static inline void *kmap_atomic(struct page *page); -- cgit v1.2.3 From ae07562909f3dfcdff40f87e51965728dab50485 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Fri, 13 May 2022 16:48:55 -0700 Subject: mm: change huge_ptep_clear_flush() to return the original pte Patch series "Fix CONT-PTE/PMD size hugetlb issue when unmapping or migrating", v4. presently, migrating a hugetlb page or unmapping a poisoned hugetlb page, we'll use ptep_clear_flush() and set_pte_at() to nuke the page table entry and remap it, and this is incorrect for CONT-PTE or CONT-PMD size hugetlb page, which will cause potential data consistent issue. This patch set will change to use hugetlb related APIs to fix this issue. Note: Mike pointed out the huge_ptep_get() will only return the one specific value, and it would not take into account the dirty or young bits of CONT-PTE/PMDs like the huge_ptep_get_and_clear() [1]. This inconsistent issue is not introduced by this patch set, and this issue will be addressed in another thread [2]. Meanwhile the uffd for hugetlb case [3] pointed out by Gerald also needs another patch to address. [1] https://lore.kernel.org/linux-mm/85bd80b4-b4fd-0d3f-a2e5-149559f2f387@oracle.com/ [2] https://lore.kernel.org/all/cover.1651998586.git.baolin.wang@linux.alibaba.com/ [3] https://lore.kernel.org/linux-mm/20220503120343.6264e126@thinkpad/ This patch (of 3): It is incorrect to use ptep_clear_flush() to nuke a hugetlb page table when unmapping or migrating a hugetlb page, and will change to use huge_ptep_clear_flush() instead in the following patches. So this is a preparation patch, which changes the huge_ptep_clear_flush() to return the original pte to help to nuke a hugetlb page table. [baolin.wang@linux.alibaba.com: fix build in several more architectures] Link: https://lkml.kernel.org/r/0009a4cd-2826-e8be-e671-f050d4f18d5d@linux.alibaba.com [sfr@canb.auug.org.au: fixup] Link: https://lkml.kernel.org/r/20220511181531.7f27a5c1@canb.auug.org.au Link: https://lkml.kernel.org/r/cover.1652270205.git.baolin.wang@linux.alibaba.com Link: https://lkml.kernel.org/r/20f77ddab90baa249bd24504c413189b82acde69.1652270205.git.baolin.wang@linux.alibaba.com Link: https://lkml.kernel.org/r/cover.1652147571.git.baolin.wang@linux.alibaba.com Link: https://lkml.kernel.org/r/dcf065868cce35bceaf138613ad27f17bb7c0c19.1652147571.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Signed-off-by: Stephen Rothwell Acked-by: Mike Kravetz Reviewed-by: Muchun Song Cc: Catalin Marinas Cc: Will Deacon Cc: Thomas Bogendoerfer Cc: James Bottomley Cc: Helge Deller Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Alexander Gordeev Cc: Christian Borntraeger Cc: Sven Schnelle Cc: Yoshinori Sato Cc: Rich Felker Cc: David S. Miller Cc: Arnd Bergmann Cc: Gerald Schaefer Signed-off-by: Andrew Morton --- include/asm-generic/hugetlb.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h index 896f341f614d..a57d667addd2 100644 --- a/include/asm-generic/hugetlb.h +++ b/include/asm-generic/hugetlb.h @@ -84,10 +84,10 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, #endif #ifndef __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH -static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, +static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { - ptep_clear_flush(vma, addr, ptep); + return ptep_clear_flush(vma, addr, ptep); } #endif -- cgit v1.2.3 From 5d4af6195c87c6b162b7963e0ad00a214b80d764 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Fri, 13 May 2022 16:48:55 -0700 Subject: mm: rmap: fix CONT-PTE/PMD size hugetlb issue when migration On some architectures (like ARM64), it can support CONT-PTE/PMD size hugetlb, which means it can support not only PMD/PUD size hugetlb: 2M and 1G, but also CONT-PTE/PMD size: 64K and 32M if a 4K page size specified. When migrating a hugetlb page, we will get the relevant page table entry by huge_pte_offset() only once to nuke it and remap it with a migration pte entry. This is correct for PMD or PUD size hugetlb, since they always contain only one pmd entry or pud entry in the page table. However this is incorrect for CONT-PTE and CONT-PMD size hugetlb, since they can contain several continuous pte or pmd entry with same page table attributes. So we will nuke or remap only one pte or pmd entry for this CONT-PTE/PMD size hugetlb page, which is not expected for hugetlb migration. The problem is we can still continue to modify the subpages' data of a hugetlb page during migrating a hugetlb page, which can cause a serious data consistent issue, since we did not nuke the page table entry and set a migration pte for the subpages of a hugetlb page. To fix this issue, we should change to use huge_ptep_clear_flush() to nuke a hugetlb page table, and remap it with set_huge_pte_at() and set_huge_swap_pte_at() when migrating a hugetlb page, which already considered the CONT-PTE or CONT-PMD size hugetlb. [akpm@linux-foundation.org: fix nommu build] [baolin.wang@linux.alibaba.com: fix build errors for !CONFIG_MMU] Link: https://lkml.kernel.org/r/a4baca670aca637e7198d9ae4543b8873cb224dc.1652270205.git.baolin.wang@linux.alibaba.com Link: https://lkml.kernel.org/r/ea5abf529f0997b5430961012bfda6166c1efc8c.1652147571.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: Muchun Song Reviewed-by: Mike Kravetz Acked-by: David Hildenbrand Cc: Alexander Gordeev Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Christian Borntraeger Cc: David S. Miller Cc: Gerald Schaefer Cc: Heiko Carstens Cc: Helge Deller Cc: James Bottomley Cc: Michael Ellerman Cc: Paul Mackerras Cc: Rich Felker Cc: Sven Schnelle Cc: Thomas Bogendoerfer Cc: Vasily Gorbik Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 04f0186b089b..0f2894d01333 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -1093,6 +1093,17 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr pte_t *ptep, pte_t pte, unsigned long sz) { } + +static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + return *ptep; +} + +static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ +} #endif /* CONFIG_HUGETLB_PAGE */ static inline spinlock_t *huge_pte_lock(struct hstate *h, -- cgit v1.2.3 From 78f39084b41d287aedb2ea55f2c1895cfa11d61a Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Fri, 13 May 2022 16:48:56 -0700 Subject: mm: hugetlb_vmemmap: add hugetlb_optimize_vmemmap sysctl We must add hugetlb_free_vmemmap=on (or "off") to the boot cmdline and reboot the server to enable or disable the feature of optimizing vmemmap pages associated with HugeTLB pages. However, rebooting usually takes a long time. So add a sysctl to enable or disable the feature at runtime without rebooting. Why we need this? There are 3 use cases. 1) The feature of minimizing overhead of struct page associated with each HugeTLB is disabled by default without passing "hugetlb_free_vmemmap=on" to the boot cmdline. When we (ByteDance) deliver the servers to the users who want to enable this feature, they have to configure the grub (change boot cmdline) and reboot the servers, whereas rebooting usually takes a long time (we have thousands of servers). It's a very bad experience for the users. So we need a approach to enable this feature after rebooting. This is a use case in our practical environment. 2) Some use cases are that HugeTLB pages are allocated 'on the fly' instead of being pulled from the HugeTLB pool, those workloads would be affected with this feature enabled. Those workloads could be identified by the characteristics of they never explicitly allocating huge pages with 'nr_hugepages' but only set 'nr_overcommit_hugepages' and then let the pages be allocated from the buddy allocator at fault time. We can confirm it is a real use case from the commit 099730d67417. For those workloads, the page fault time could be ~2x slower than before. We suspect those users want to disable this feature if the system has enabled this before and they don't think the memory savings benefit is enough to make up for the performance drop. 3) If the workload which wants vmemmap pages to be optimized and the workload which wants to set 'nr_overcommit_hugepages' and does not want the extera overhead at fault time when the overcommitted pages be allocated from the buddy allocator are deployed in the same server. The user could enable this feature and set 'nr_hugepages' and 'nr_overcommit_hugepages', then disable the feature. In this case, the overcommited HugeTLB pages will not encounter the extra overhead at fault time. Link: https://lkml.kernel.org/r/20220512041142.39501-5-songmuchun@bytedance.com Signed-off-by: Muchun Song Reviewed-by: Mike Kravetz Cc: Jonathan Corbet Cc: Luis Chamberlain Cc: Kees Cook Cc: Iurii Zaikin Cc: Oscar Salvador Cc: David Hildenbrand Cc: Masahiro Yamada Cc: Xiongchun Duan Signed-off-by: Andrew Morton --- include/linux/memory_hotplug.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index e0b2209ab71c..20d7edf62a6a 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -351,4 +351,13 @@ void arch_remove_linear_mapping(u64 start, u64 size); extern bool mhp_supports_memmap_on_memory(unsigned long size); #endif /* CONFIG_MEMORY_HOTPLUG */ +#ifdef CONFIG_MHP_MEMMAP_ON_MEMORY +bool mhp_memmap_on_memory(void); +#else +static inline bool mhp_memmap_on_memory(void) +{ + return false; +} +#endif + #endif /* __LINUX_MEMORY_HOTPLUG_H */ -- cgit v1.2.3 From d4a157f5a26fbf1f1fd5da47a4772a738306348f Mon Sep 17 00:00:00 2001 From: Gautam Menghani Date: Fri, 13 May 2022 16:48:57 -0700 Subject: mm/damon: add documentation for Enum value Fix the warning - "Enum value 'NR_DAMON_OPS' not described in enum 'damon_ops_id'" generated by the command "make pdfdocs" Link: https://lkml.kernel.org/r/20220508073316.141401-1-gautammenghani201@gmail.com Signed-off-by: Gautam Menghani Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/damon.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/damon.h b/include/linux/damon.h index d1e6ee28a2ff..7c62da31ce4b 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -264,6 +264,7 @@ struct damos { * @DAMON_OPS_FVADDR: Monitoring operations for only fixed ranges of virtual * address spaces * @DAMON_OPS_PADDR: Monitoring operations for the physical address space + * @NR_DAMON_OPS: Number of monitoring operations implementations */ enum damon_ops_id { DAMON_OPS_VADDR, -- cgit v1.2.3 From 390ed29b5e425ba00da2b6113b74a14949f71b02 Mon Sep 17 00:00:00 2001 From: Hao Xu Date: Sat, 14 May 2022 22:20:43 +0800 Subject: io_uring: add IORING_ACCEPT_MULTISHOT for accept add an accept_flag IORING_ACCEPT_MULTISHOT for accept, which is to support multishot. Signed-off-by: Hao Xu Link: https://lore.kernel.org/r/20220514142046.58072-2-haoxu.linux@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 36ec43dc7bf9..15f821af9242 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -232,6 +232,11 @@ enum { */ #define IORING_RECVSEND_POLL_FIRST (1U << 0) +/* + * accept flags stored in sqe->ioprio + */ +#define IORING_ACCEPT_MULTISHOT (1U << 0) + /* * IO completion data structure (Completion Queue Entry) */ -- cgit v1.2.3 From 81132a39c152ca09832b9e4cb748129cee5f55ec Mon Sep 17 00:00:00 2001 From: Gou Hao Date: Tue, 2 Nov 2021 10:46:48 +0800 Subject: fs: remove fget_many and fput_many interface These two interface were added in 091141a42 commit, but now there is no place to call them. The only user of fput/fget_many() was removed in commit 62906e89e63b ("io_uring: remove file batch-get optimisation"). A user of get_file_rcu_many() were removed in commit f073531070d2 ("init: add an init_dup helper"). And replace atomic_long_sub/add to atomic_long_dec/inc can improve performance. Here are the test results of unixbench: Cmd: ./Run -c 64 context1 Without patch: System Benchmarks Partial Index BASELINE RESULT INDEX Pipe-based Context Switching 4000.0 2798407.0 6996.0 ======== System Benchmarks Index Score (Partial Only) 6996.0 With patch: System Benchmarks Partial Index BASELINE RESULT INDEX Pipe-based Context Switching 4000.0 3486268.8 8715.7 ======== System Benchmarks Index Score (Partial Only) 8715.7 Signed-off-by: Gou Hao Signed-off-by: Al Viro --- include/linux/file.h | 2 -- include/linux/fs.h | 4 +--- 2 files changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/file.h b/include/linux/file.h index 51e830b4fe3a..39704eae83e2 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -14,7 +14,6 @@ struct file; extern void fput(struct file *); -extern void fput_many(struct file *, unsigned int); struct file_operations; struct task_struct; @@ -47,7 +46,6 @@ static inline void fdput(struct fd fd) } extern struct file *fget(unsigned int fd); -extern struct file *fget_many(unsigned int fd, unsigned int refs); extern struct file *fget_raw(unsigned int fd); extern struct file *fget_task(struct task_struct *task, unsigned int fd); extern unsigned long __fdget(unsigned int fd); diff --git a/include/linux/fs.h b/include/linux/fs.h index bbde95387a23..3660c338bb16 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -981,9 +981,7 @@ static inline struct file *get_file(struct file *f) atomic_long_inc(&f->f_count); return f; } -#define get_file_rcu_many(x, cnt) \ - atomic_long_add_unless(&(x)->f_count, (cnt), 0) -#define get_file_rcu(x) get_file_rcu_many((x), 1) +#define get_file_rcu(x) atomic_long_inc_not_zero(&(x)->f_count) #define file_count(x) atomic_long_read(&(x)->f_count) #define MAX_NON_LFS ((1UL<<31) - 1) -- cgit v1.2.3 From 6319194ec57b0452dcda4589d24c4e7db299c5bf Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 12 May 2022 17:08:03 -0400 Subject: Unify the primitives for file descriptor closing Currently we have 3 primitives for removing an opened file from descriptor table - pick_file(), __close_fd_get_file() and close_fd_get_file(). Their calling conventions are rather odd and there's a code duplication for no good reason. They can be unified - 1) have __range_close() cap max_fd in the very beginning; that way we don't need separate way for pick_file() to report being past the end of descriptor table. 2) make {__,}close_fd_get_file() return file (or NULL) directly, rather than returning it via struct file ** argument. Don't bother with (bogus) return value - nobody wants that -ENOENT. 3) make pick_file() return NULL on unopened descriptor - the only caller that used to care about the distinction between descriptor past the end of descriptor table and finding NULL in descriptor table doesn't give a damn after (1). 4) lift ->files_lock out of pick_file() That actually simplifies the callers, as well as the primitives themselves. Code duplication is also gone... Reviewed-by: Christian Brauner (Microsoft) Signed-off-by: Al Viro --- include/linux/fdtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index d0e78174874a..e066816f3519 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -125,7 +125,7 @@ int iterate_fd(struct files_struct *, unsigned, extern int close_fd(unsigned int fd); extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags); -extern int close_fd_get_file(unsigned int fd, struct file **res); +extern struct file *close_fd_get_file(unsigned int fd); extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds, struct files_struct **new_fdp); -- cgit v1.2.3 From e987a4c60f9755b2f7a19bf1b5ef2eb74c90579b Mon Sep 17 00:00:00 2001 From: Fuad Tabba Date: Tue, 10 May 2022 09:57:08 +0000 Subject: KVM: arm64: Repack struct kvm_pmu to reduce size struct kvm_pmu has 2 holes using 10 bytes. This is instantiated in all vcpus, so it adds up. Repack the structures to remove the holes. No functional change intended. Reviewed-by: Oliver Upton Signed-off-by: Fuad Tabba Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220510095710.148178-3-tabba@google.com --- include/kvm/arm_pmu.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index 20193416d214..eaa8290b116f 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -21,12 +21,12 @@ struct kvm_pmc { }; struct kvm_pmu { - int irq_num; + struct irq_work overflow_work; struct kvm_pmc pmc[ARMV8_PMU_MAX_COUNTERS]; DECLARE_BITMAP(chained, ARMV8_PMU_MAX_COUNTER_PAIRS); + int irq_num; bool created; bool irq_level; - struct irq_work overflow_work; }; struct arm_pmu_entry { -- cgit v1.2.3 From 84d751a019a9792f5b4884e1d598b603c360ec22 Mon Sep 17 00:00:00 2001 From: Fuad Tabba Date: Tue, 10 May 2022 09:57:09 +0000 Subject: KVM: arm64: Pass pmu events to hyp via vcpu Instead of the host accessing hyp data directly, pass the pmu events of the current cpu to hyp via the vcpu. This adds 64 bits (in two fields) to the vcpu that need to be synced before every vcpu run in nvhe and protected modes. However, it isolates the hypervisor from the host, which allows us to use pmu in protected mode in a subsequent patch. No visible side effects in behavior intended. Signed-off-by: Fuad Tabba Reviewed-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20220510095710.148178-4-tabba@google.com --- include/kvm/arm_pmu.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index eaa8290b116f..35a0903cae32 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -20,8 +20,14 @@ struct kvm_pmc { struct perf_event *perf_event; }; +struct kvm_pmu_events { + u32 events_host; + u32 events_guest; +}; + struct kvm_pmu { struct irq_work overflow_work; + struct kvm_pmu_events events; struct kvm_pmc pmc[ARMV8_PMU_MAX_COUNTERS]; DECLARE_BITMAP(chained, ARMV8_PMU_MAX_COUNTER_PAIRS); int irq_num; -- cgit v1.2.3 From 03fea699b050805ad6ee111f9db04f223f3e835e Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Sun, 15 May 2022 21:58:30 +0100 Subject: cdrom: remove the unused driver specific disc change ioctl This was only used by the ide-cd driver, which went away in commit b7fb14d3ac63 ("ide: remove the legacy ide driver") so we might as well take advantage of that and get rid of this hook as well. Cc: Christoph Hellwig Cc: Jens Axboe Cc: Phillip Potter Signed-off-by: Paul Gortmaker Link: https://lore.kernel.org/all/20220427132436.12795-2-paul.gortmaker@windriver.com Signed-off-by: Phillip Potter Link: https://lore.kernel.org/r/20220515205833.944139-3-phil@philpotter.co.uk Signed-off-by: Jens Axboe --- include/linux/cdrom.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 0a89f111e00e..67caa909e3e6 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -77,7 +77,6 @@ struct cdrom_device_ops { int (*tray_move) (struct cdrom_device_info *, int); int (*lock_door) (struct cdrom_device_info *, int); int (*select_speed) (struct cdrom_device_info *, int); - int (*select_disc) (struct cdrom_device_info *, int); int (*get_last_session) (struct cdrom_device_info *, struct cdrom_multisession *); int (*get_mcn) (struct cdrom_device_info *, -- cgit v1.2.3 From 8fa10ee183c3a1ecb53e81c95895ed5bc2a5530a Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Sun, 15 May 2022 21:58:31 +0100 Subject: cdrom: mark CDROMGETSPINDOWN/CDROMSETSPINDOWN obsolete These were only implemented by the IDE CD driver, which has since been removed. Given that nobody is likely to create new CD/DVD hardware (and associated drivers) we can mark these appropriately. Cc: Jens Axboe Cc: Christoph Hellwig Cc: Phillip Potter Signed-off-by: Paul Gortmaker Link: https://lore.kernel.org/all/20220427132436.12795-3-paul.gortmaker@windriver.com Signed-off-by: Phillip Potter Link: https://lore.kernel.org/r/20220515205833.944139-4-phil@philpotter.co.uk Signed-off-by: Jens Axboe --- include/uapi/linux/cdrom.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/cdrom.h b/include/uapi/linux/cdrom.h index 804ff8d98f71..011e594e4a0d 100644 --- a/include/uapi/linux/cdrom.h +++ b/include/uapi/linux/cdrom.h @@ -103,7 +103,7 @@ #define CDROMREADALL 0x5318 /* read all 2646 bytes */ /* - * These ioctls are (now) only in ide-cd.c for controlling + * These ioctls were only in (now removed) ide-cd.c for controlling * drive spindown time. They should be implemented in the * Uniform driver, via generic packet commands, GPCMD_MODE_SELECT_10, * GPCMD_MODE_SENSE_10 and the GPMODE_POWER_PAGE... -- cgit v1.2.3 From ca2d89925ae3f3d5c65182ff75e58bc9b484e69c Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Thu, 28 Apr 2022 12:19:35 +0300 Subject: nvme: add missing status values to verbose logging Log a few more path related status codes. Signed-off-by: Max Gurtovoy Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index f626a445d1a8..bbabdc7600da 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -1679,9 +1679,11 @@ enum { /* * Path-related Errors: */ + NVME_SC_INTERNAL_PATH_ERROR = 0x300, NVME_SC_ANA_PERSISTENT_LOSS = 0x301, NVME_SC_ANA_INACCESSIBLE = 0x302, NVME_SC_ANA_TRANSITION = 0x303, + NVME_SC_CTRL_PATH_ERROR = 0x360, NVME_SC_HOST_PATH_ERROR = 0x370, NVME_SC_HOST_ABORTED_CMD = 0x371, -- cgit v1.2.3 From 4273d3fa8aa594e37c295bef3e73073608644241 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 10 May 2022 13:37:59 +0200 Subject: mac80211: fix typo in documentation This is called offload_flags, remove the extra 'a'. Signed-off-by: Johannes Berg --- include/net/mac80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 75880fc70700..7b74c695a83a 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1701,7 +1701,7 @@ enum ieee80211_offload_flags { * these need to be set (or cleared) when the interface is added * or, if supported by the driver, the interface type is changed * at runtime, mac80211 will never touch this field - * @offloaad_flags: hardware offload capabilities/flags for this interface. + * @offload_flags: hardware offload capabilities/flags for this interface. * These are initialized by mac80211 before calling .add_interface, * .change_interface or .update_vif_offload and updated by the driver * within these ops, based on supported features or runtime change -- cgit v1.2.3 From f5bf586aadddd9803a1f16bc18621fd819377130 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 10 May 2022 16:38:19 +0200 Subject: mac80211: remove stray multi_sta_back_32bit docs This field doesn't exist, remove the docs for it. Signed-off-by: Johannes Berg --- include/net/mac80211.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 7b74c695a83a..944b31f0eb0d 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -514,7 +514,6 @@ struct ieee80211_fils_discovery { * to that BSS) that can change during the lifetime of the BSS. * * @htc_trig_based_pkt_ext: default PE in 4us units, if BSS supports HE - * @multi_sta_back_32bit: supports BA bitmap of 32-bits in Multi-STA BACK * @uora_exists: is the UORA element advertised by AP * @ack_enabled: indicates support to receive a multi-TID that solicits either * ACK, BACK or both -- cgit v1.2.3 From e6175a2ed1f18bf2f649625bf725e07adcfa6a28 Mon Sep 17 00:00:00 2001 From: Eyal Birger Date: Fri, 13 May 2022 23:34:02 +0300 Subject: xfrm: fix "disable_policy" flag use when arriving from different devices In IPv4 setting the "disable_policy" flag on a device means no policy should be enforced for traffic originating from the device. This was implemented by seting the DST_NOPOLICY flag in the dst based on the originating device. However, dsts are cached in nexthops regardless of the originating devices, in which case, the DST_NOPOLICY flag value may be incorrect. Consider the following setup: +------------------------------+ | ROUTER | +-------------+ | +-----------------+ | | ipsec src |----|-|ipsec0 | | +-------------+ | |disable_policy=0 | +----+ | | +-----------------+ |eth1|-|----- +-------------+ | +-----------------+ +----+ | | noipsec src |----|-|eth0 | | +-------------+ | |disable_policy=1 | | | +-----------------+ | +------------------------------+ Where ROUTER has a default route towards eth1. dst entries for traffic arriving from eth0 would have DST_NOPOLICY and would be cached and therefore can be reused by traffic originating from ipsec0, skipping policy check. Fix by setting a IPSKB_NOPOLICY flag in IPCB and observing it instead of the DST in IN/FWD IPv4 policy checks. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Shmulik Ladkani Signed-off-by: Eyal Birger Signed-off-by: Steffen Klassert --- include/net/ip.h | 1 + include/net/xfrm.h | 14 +++++++++++++- 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 3984f2c39c4b..0161137914cf 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -56,6 +56,7 @@ struct inet_skb_parm { #define IPSKB_DOREDIRECT BIT(5) #define IPSKB_FRAG_PMTU BIT(6) #define IPSKB_L3SLAVE BIT(7) +#define IPSKB_NOPOLICY BIT(8) u16 frag_max_size; }; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 6fb899ff5afc..d2efddce65d4 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1093,6 +1093,18 @@ static inline bool __xfrm_check_nopolicy(struct net *net, struct sk_buff *skb, return false; } +static inline bool __xfrm_check_dev_nopolicy(struct sk_buff *skb, + int dir, unsigned short family) +{ + if (dir != XFRM_POLICY_OUT && family == AF_INET) { + /* same dst may be used for traffic originating from + * devices with different policy settings. + */ + return IPCB(skb)->flags & IPSKB_NOPOLICY; + } + return skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY); +} + static inline int __xfrm_policy_check2(struct sock *sk, int dir, struct sk_buff *skb, unsigned int family, int reverse) @@ -1104,7 +1116,7 @@ static inline int __xfrm_policy_check2(struct sock *sk, int dir, return __xfrm_policy_check(sk, ndir, skb, family); return __xfrm_check_nopolicy(net, skb, dir) || - (skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY)) || + __xfrm_check_dev_nopolicy(skb, dir, family) || __xfrm_policy_check(sk, ndir, skb, family); } -- cgit v1.2.3 From 3d48cb74816d8468f0235ce9a867a2d7b9832693 Mon Sep 17 00:00:00 2001 From: Rameshkumar Sundaram Date: Wed, 13 Apr 2022 21:58:14 +0530 Subject: nl80211: Parse NL80211_ATTR_HE_BSS_COLOR as a part of nl80211_parse_beacon NL80211_ATTR_HE_BSS_COLOR attribute can be included in both NL80211_CMD_START_AP and NL80211_CMD_SET_BEACON commands. Move he_bss_color from cfg80211_ap_settings to cfg80211_beacon_data and parse NL80211_ATTR_HE_BSS_COLOR as a part of nl80211_parse_beacon() to have bss color settings parsed for both start ap and set beacon commands. Add a new flag he_bss_color_valid to indicate whether NL80211_ATTR_HE_BSS_COLOR attribute is included. Signed-off-by: Rameshkumar Sundaram Link: https://lore.kernel.org/r/1649867295-7204-2-git-send-email-quic_ramess@quicinc.com [fix build ...] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 6a3e3f0a8615..97a5804ccdcf 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1183,6 +1183,9 @@ struct cfg80211_mbssid_elems { * Token (measurement type 11) * @lci_len: LCI data length * @civicloc_len: Civic location data length + * @he_bss_color: BSS Color settings + * @he_bss_color_valid: indicates whether bss color + attribute is present in beacon data or not. */ struct cfg80211_beacon_data { const u8 *head, *tail; @@ -1202,6 +1205,8 @@ struct cfg80211_beacon_data { size_t probe_resp_len; size_t lci_len; size_t civicloc_len; + struct cfg80211_he_bss_color he_bss_color; + bool he_bss_color_valid; }; struct mac_address { @@ -1292,7 +1297,6 @@ struct cfg80211_unsol_bcast_probe_resp { * @sae_h2e_required: stations must support direct H2E technique in SAE * @flags: flags, as defined in enum cfg80211_ap_settings_flags * @he_obss_pd: OBSS Packet Detection settings - * @he_bss_color: BSS Color settings * @he_oper: HE operation IE (or %NULL if HE isn't enabled) * @fils_discovery: FILS discovery transmission parameters * @unsol_bcast_probe_resp: Unsolicited broadcast probe response parameters @@ -1326,7 +1330,6 @@ struct cfg80211_ap_settings { bool twt_responder; u32 flags; struct ieee80211_he_obss_pd he_obss_pd; - struct cfg80211_he_bss_color he_bss_color; struct cfg80211_fils_discovery fils_discovery; struct cfg80211_unsol_bcast_probe_resp unsol_bcast_probe_resp; struct cfg80211_mbssid_config mbssid_config; -- cgit v1.2.3 From aa4a38af97e9f117450bcafd25ef02f9f1a37215 Mon Sep 17 00:00:00 2001 From: Stefan Binding Date: Mon, 9 May 2022 22:46:41 +0100 Subject: ALSA: hda: cs35l41: Add Support for Interrupts The CS35L41 can produce interrupts on error. When the interrupts occur, the driver will report the error, but errors will only be fixed after playback finishes. Signed-off-by: Stefan Binding Signed-off-by: Vitaly Rodionov Link: https://lore.kernel.org/r/20220509214703.4482-5-vitalyr@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs35l41.h | 54 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index dbe8d9c0191b..8e4b125c81c8 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -691,6 +691,13 @@ #define CS35L41_TEMP_WARN_ERR_RLS 0x20 #define CS35L41_TEMP_ERR_RLS 0x40 +#define CS35L41_AMP_SHORT_ERR_RLS_SHIFT 1 +#define CS35L41_BST_SHORT_ERR_RLS_SHIFT 2 +#define CS35L41_BST_OVP_ERR_RLS_SHIFT 3 +#define CS35L41_BST_UVP_ERR_RLS_SHIFT 4 +#define CS35L41_TEMP_WARN_ERR_RLS_SHIFT 5 +#define CS35L41_TEMP_ERR_RLS_SHIFT 6 + #define CS35L41_INT1_MASK_DEFAULT 0x7FFCFE3F #define CS35L41_INT1_UNMASK_PUP 0xFEFFFFFF #define CS35L41_INT1_UNMASK_PDN 0xFF7FFFFF @@ -794,6 +801,53 @@ struct cs35l41_otp_map_element_t { u32 word_offset; }; +/* + * IRQs + */ +#define CS35L41_IRQ(_irq, _name, _hand) \ + { \ + .irq = CS35L41_ ## _irq ## _IRQ,\ + .name = _name, \ + .handler = _hand, \ + } + +struct cs35l41_irq { + int irq; + const char *name; + irqreturn_t (*handler)(int irq, void *data); +}; + +#define CS35L41_REG_IRQ(_reg, _irq) \ + [CS35L41_ ## _irq ## _IRQ] = { \ + .reg_offset = (CS35L41_ ## _reg) - CS35L41_IRQ1_STATUS1,\ + .mask = CS35L41_ ## _irq ## _MASK \ + } + +/* (0x0000E010) CS35L41_IRQ1_STATUS1 */ +#define CS35L41_BST_OVP_ERR_SHIFT 6 +#define CS35L41_BST_OVP_ERR_MASK BIT(CS35L41_BST_OVP_ERR_SHIFT) +#define CS35L41_BST_DCM_UVP_ERR_SHIFT 7 +#define CS35L41_BST_DCM_UVP_ERR_MASK BIT(CS35L41_BST_DCM_UVP_ERR_SHIFT) +#define CS35L41_BST_SHORT_ERR_SHIFT 8 +#define CS35L41_BST_SHORT_ERR_MASK BIT(CS35L41_BST_SHORT_ERR_SHIFT) +#define CS35L41_TEMP_WARN_SHIFT 15 +#define CS35L41_TEMP_WARN_MASK BIT(CS35L41_TEMP_WARN_SHIFT) +#define CS35L41_TEMP_ERR_SHIFT 17 +#define CS35L41_TEMP_ERR_MASK BIT(CS35L41_TEMP_ERR_SHIFT) +#define CS35L41_AMP_SHORT_ERR_SHIFT 31 +#define CS35L41_AMP_SHORT_ERR_MASK BIT(CS35L41_AMP_SHORT_ERR_SHIFT) + +enum cs35l41_irq_list { + CS35L41_BST_OVP_ERR_IRQ, + CS35L41_BST_DCM_UVP_ERR_IRQ, + CS35L41_BST_SHORT_ERR_IRQ, + CS35L41_TEMP_WARN_IRQ, + CS35L41_TEMP_ERR_IRQ, + CS35L41_AMP_SHORT_ERR_IRQ, + + CS35L41_NUM_IRQ +}; + extern struct regmap_config cs35l41_regmap_i2c; extern struct regmap_config cs35l41_regmap_spi; -- cgit v1.2.3 From caf7c1f1de9f011ea0e6494fcb1b2ba203bd3422 Mon Sep 17 00:00:00 2001 From: Stefan Binding Date: Mon, 9 May 2022 22:46:43 +0100 Subject: ASoC: cs35l41: Move cs35l41_set_cspl_mbox_cmd to shared code This function is used to control the DSP Firmware for cs35l41, and will be needed by the cs35l41 hda driver, when firmware support is added. Signed-off-by: Stefan Binding Signed-off-by: Vitaly Rodionov Acked-by: Charles Keepax Link: https://lore.kernel.org/r/20220509214703.4482-7-vitalyr@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs35l41.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index 8e4b125c81c8..2271471225b1 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -801,6 +801,24 @@ struct cs35l41_otp_map_element_t { u32 word_offset; }; +enum cs35l41_cspl_mbox_status { + CSPL_MBOX_STS_RUNNING = 0, + CSPL_MBOX_STS_PAUSED = 1, + CSPL_MBOX_STS_RDY_FOR_REINIT = 2, +}; + +enum cs35l41_cspl_mbox_cmd { + CSPL_MBOX_CMD_NONE = 0, + CSPL_MBOX_CMD_PAUSE = 1, + CSPL_MBOX_CMD_RESUME = 2, + CSPL_MBOX_CMD_REINIT = 3, + CSPL_MBOX_CMD_STOP_PRE_REINIT = 4, + CSPL_MBOX_CMD_HIBERNATE = 5, + CSPL_MBOX_CMD_OUT_OF_HIBERNATE = 6, + CSPL_MBOX_CMD_UNKNOWN_CMD = -1, + CSPL_MBOX_CMD_INVALID_SEQUENCE = -2, +}; + /* * IRQs */ @@ -859,6 +877,8 @@ int cs35l41_set_channels(struct device *dev, struct regmap *reg, unsigned int tx_num, unsigned int *tx_slot, unsigned int rx_num, unsigned int *rx_slot); int cs35l41_gpio_config(struct regmap *regmap, struct cs35l41_hw_cfg *hw_cfg); +int cs35l41_set_cspl_mbox_cmd(struct device *dev, struct regmap *regmap, + enum cs35l41_cspl_mbox_cmd cmd); int cs35l41_init_boost(struct device *dev, struct regmap *regmap, struct cs35l41_hw_cfg *hw_cfg); bool cs35l41_safe_reset(struct regmap *regmap, enum cs35l41_boost_type b_type); -- cgit v1.2.3 From ff8aad072e6388243fb0c76db4154d0883988384 Mon Sep 17 00:00:00 2001 From: Stefan Binding Date: Mon, 9 May 2022 22:46:44 +0100 Subject: ASoC: cs35l41: Move cs35l41 fs errata into shared code This sequence is required to setup firmware, and will be needed for hda driver. Signed-off-by: Stefan Binding Signed-off-by: Vitaly Rodionov Acked-by: Charles Keepax Link: https://lore.kernel.org/r/20220509214703.4482-8-vitalyr@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs35l41.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index 2271471225b1..d0cfb41495b0 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -879,6 +879,7 @@ int cs35l41_set_channels(struct device *dev, struct regmap *reg, int cs35l41_gpio_config(struct regmap *regmap, struct cs35l41_hw_cfg *hw_cfg); int cs35l41_set_cspl_mbox_cmd(struct device *dev, struct regmap *regmap, enum cs35l41_cspl_mbox_cmd cmd); +int cs35l41_write_fs_errata(struct device *dev, struct regmap *regmap); int cs35l41_init_boost(struct device *dev, struct regmap *regmap, struct cs35l41_hw_cfg *hw_cfg); bool cs35l41_safe_reset(struct regmap *regmap, enum cs35l41_boost_type b_type); -- cgit v1.2.3 From 0db99577c4cddc45447701aeb7b4d7d7b03d626f Mon Sep 17 00:00:00 2001 From: Stefan Binding Date: Mon, 9 May 2022 22:46:45 +0100 Subject: ASoC: cs35l41: Move cs_dsp config struct into shared code This can then be used by HDA code to configure cs_dsp. Signed-off-by: Stefan Binding Signed-off-by: Vitaly Rodionov Acked-by: Charles Keepax Link: https://lore.kernel.org/r/20220509214703.4482-9-vitalyr@opensource.cirrus.com Signed-off-by: Takashi Iwai --- include/sound/cs35l41.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h index d0cfb41495b0..dd70fb8dd860 100644 --- a/include/sound/cs35l41.h +++ b/include/sound/cs35l41.h @@ -11,6 +11,7 @@ #define __CS35L41_H #include +#include #define CS35L41_FIRSTREG 0x00000000 #define CS35L41_LASTREG 0x03804FE8 @@ -877,6 +878,7 @@ int cs35l41_set_channels(struct device *dev, struct regmap *reg, unsigned int tx_num, unsigned int *tx_slot, unsigned int rx_num, unsigned int *rx_slot); int cs35l41_gpio_config(struct regmap *regmap, struct cs35l41_hw_cfg *hw_cfg); +void cs35l41_configure_cs_dsp(struct device *dev, struct regmap *reg, struct cs_dsp *dsp); int cs35l41_set_cspl_mbox_cmd(struct device *dev, struct regmap *regmap, enum cs35l41_cspl_mbox_cmd cmd); int cs35l41_write_fs_errata(struct device *dev, struct regmap *regmap); -- cgit v1.2.3 From 44fa75f207d8a106bc75e6230db61e961fdbf8a8 Mon Sep 17 00:00:00 2001 From: Jonas Jelonek Date: Mon, 9 May 2022 19:39:57 +0200 Subject: mac80211: extend current rate control tx status API This patch adds the new struct ieee80211_rate_status and replaces 'struct rate_info *rate' in ieee80211_tx_status with pointer and length annotation. The struct ieee80211_rate_status allows to: (1) receive tx power status feedback for transmit power control (TPC) per packet or packet retry (2) dynamic mapping of wifi chip specific multi-rate retry (mrr) chains with different lengths (3) increase the limit of annotatable rate indices to support IEEE802.11ac rate sets and beyond ieee80211_tx_info, control and status buffer, and ieee80211_tx_rate cannot be used to achieve these goals due to fixed size limitations. Our new struct contains a struct rate_info to annotate the rate that was used, retry count of the rate and tx power. It is intended for all information related to RC and TPC that needs to be passed from driver to mac80211 and its RC/TPC algorithms like Minstrel_HT. It corresponds to one stage in an mrr. Multiple subsequent instances of this struct can be included in struct ieee80211_tx_status via a pointer and a length variable. Those instances can be allocated on-stack. The former reference to a single instance of struct rate_info is replaced with our new annotation. An extension is introduced to struct ieee80211_hw. There are two new members called 'tx_power_levels' and 'max_txpwr_levels_idx' acting as a tx power level table. When a wifi device is registered, the driver shall supply all supported power levels in this list. This allows to support several quirks like differing power steps in power level ranges or alike. TPC can use this for algorithm and thus be designed more abstract instead of handling all possible step widths individually. Further mandatory changes in status.c, mt76 and ath11k drivers due to the removal of 'struct rate_info *rate' are also included. status.c already uses the information in ieee80211_tx_status->rate in radiotap, this is now changed to use ieee80211_rate_status->rate_idx. mt76 driver already uses struct rate_info to pass the tx rate to status path. The new members of the ieee80211_tx_status are set to NULL and 0 because the previously passed rate is not relevant to rate control and accurate information is passed via tx_info->status.rates. For ath11k, the txrate can be passed via this struct because ath11k uses firmware RC and thus the information does not interfere with software RC. Compile-Tested: current wireless-next tree with all flags on Tested-on: Xiaomi 4A Gigabit (MediaTek MT7603E, MT7612E) with OpenWrt Linux 5.10.113 Signed-off-by: Jonas Jelonek Link: https://lore.kernel.org/r/20220509173958.1398201-2-jelonek.jonas@gmail.com Signed-off-by: Johannes Berg --- include/net/mac80211.h | 33 +++++++++++++++++++++++++++++++-- 1 file changed, 31 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 944b31f0eb0d..ebadb2103968 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1143,20 +1143,41 @@ ieee80211_info_get_tx_time_est(struct ieee80211_tx_info *info) return info->tx_time_est << 2; } +/*** + * struct ieee80211_rate_status - mrr stage for status path + * + * This struct is used in struct ieee80211_tx_status to provide drivers a + * dynamic way to report about used rates and power levels per packet. + * + * @rate_idx The actual used rate. + * @try_count How often the rate was tried. + * @tx_power_idx An idx into the ieee80211_hw->tx_power_levels list of the + * corresponding wifi hardware. The idx shall point to the power level + * that was used when sending the packet. + */ +struct ieee80211_rate_status { + struct rate_info rate_idx; + u8 try_count; + u8 tx_power_idx; +}; + /** * struct ieee80211_tx_status - extended tx status info for rate control * * @sta: Station that the packet was transmitted for * @info: Basic tx status information * @skb: Packet skb (can be NULL if not provided by the driver) - * @rate: The TX rate that was used when sending the packet + * @rates: Mrr stages that were used when sending the packet + * @n_rates: Number of mrr stages (count of instances for @rates) * @free_list: list where processed skbs are stored to be free'd by the driver */ struct ieee80211_tx_status { struct ieee80211_sta *sta; struct ieee80211_tx_info *info; struct sk_buff *skb; - struct rate_info *rate; + struct ieee80211_rate_status *rates; + u8 n_rates; + struct list_head *free_list; }; @@ -2657,6 +2678,12 @@ enum ieee80211_hw_flags { * refilling deficit of each TXQ. * * @max_mtu: the max mtu could be set. + * + * @tx_power_levels: a list of power levels supported by the wifi hardware. + * The power levels can be specified either as integer or fractions. + * The power level at idx 0 shall be the maximum positive power level. + * + * @max_txpwr_levels_idx: the maximum valid idx of 'tx_power_levels' list. */ struct ieee80211_hw { struct ieee80211_conf conf; @@ -2695,6 +2722,8 @@ struct ieee80211_hw { u8 tx_sk_pacing_shift; u8 weight_multiplier; u32 max_mtu; + const s8 *tx_power_levels; + u8 max_txpwr_levels_idx; }; static inline bool _ieee80211_hw_check(struct ieee80211_hw *hw, -- cgit v1.2.3 From 89527be8d8d672773eeaec910118a6e84fb597e3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 May 2022 11:33:56 -0700 Subject: net: add IFLA_TSO_{MAX_SIZE|SEGS} attributes New netlink attributes IFLA_TSO_MAX_SIZE and IFLA_TSO_MAX_SEGS are used to report to user-space the device TSO limits. ip -d link sh dev eth1 ... tso_max_size 65536 tso_max_segs 65535 Signed-off-by: Eric Dumazet Acked-by: Alexander Duyck Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index d1e600816b82..5f58dcfe2787 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -368,6 +368,8 @@ enum { IFLA_PARENT_DEV_NAME, IFLA_PARENT_DEV_BUS_NAME, IFLA_GRO_MAX_SIZE, + IFLA_TSO_MAX_SIZE, + IFLA_TSO_MAX_SEGS, __IFLA_MAX }; -- cgit v1.2.3 From 7c4e983c4f3cf94fcd879730c6caa877e0768a4d Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 13 May 2022 11:33:57 -0700 Subject: net: allow gso_max_size to exceed 65536 The code for gso_max_size was added originally to allow for debugging and workaround of buggy devices that couldn't support TSO with blocks 64K in size. The original reason for limiting it to 64K was because that was the existing limits of IPv4 and non-jumbogram IPv6 length fields. With the addition of Big TCP we can remove this limit and allow the value to potentially go up to UINT_MAX and instead be limited by the tso_max_size value. So in order to support this we need to go through and clean up the remaining users of the gso_max_size value so that the values will cap at 64K for non-TCPv6 flows. In addition we can clean up the GSO_MAX_SIZE value so that 64K becomes GSO_LEGACY_MAX_SIZE and UINT_MAX will now be the upper limit for GSO_MAX_SIZE. v6: (edumazet) fixed a compile error if CONFIG_IPV6=n, in a new sk_trim_gso_size() helper. netif_set_tso_max_size() caps the requested TSO size with GSO_MAX_SIZE. Signed-off-by: Alexander Duyck Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 536321691c72..ce780e352f43 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2272,7 +2272,9 @@ struct net_device { const struct rtnl_link_ops *rtnl_link_ops; /* for setting kernel sock attribute on TCP connection setup */ -#define GSO_MAX_SIZE 65536 +#define GSO_LEGACY_MAX_SIZE 65536u +#define GSO_MAX_SIZE UINT_MAX + unsigned int gso_max_size; #define TSO_LEGACY_MAX_SIZE 65536 #define TSO_MAX_SIZE UINT_MAX -- cgit v1.2.3 From 34b92e8d19da1e44070dc0ecc2747871469ac534 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 May 2022 11:33:58 -0700 Subject: net: limit GSO_MAX_SIZE to 524280 bytes Make sure we will not overflow shinfo->gso_segs Minimal TCP MSS size is 8 bytes, and shinfo->gso_segs is a 16bit field. TCP_MIN_GSO_SIZE is currently defined in include/net/tcp.h, it seems cleaner to not bring tcp details into include/linux/netdevice.h Signed-off-by: Eric Dumazet Acked-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ce780e352f43..fd38847d0dc7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2272,14 +2272,17 @@ struct net_device { const struct rtnl_link_ops *rtnl_link_ops; /* for setting kernel sock attribute on TCP connection setup */ +#define GSO_MAX_SEGS 65535u #define GSO_LEGACY_MAX_SIZE 65536u -#define GSO_MAX_SIZE UINT_MAX +/* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE), + * and shinfo->gso_segs is a 16bit field. + */ +#define GSO_MAX_SIZE (8 * GSO_MAX_SEGS) unsigned int gso_max_size; #define TSO_LEGACY_MAX_SIZE 65536 #define TSO_MAX_SIZE UINT_MAX unsigned int tso_max_size; -#define GSO_MAX_SEGS 65535 u16 gso_max_segs; #define TSO_MAX_SEGS U16_MAX u16 tso_max_segs; -- cgit v1.2.3 From 7c96d8ec96bb71aac54c9f872aaa65d7411ab864 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 May 2022 11:34:00 -0700 Subject: ipv6: add struct hop_jumbo_hdr definition Following patches will need to add and remove local IPv6 jumbogram options to enable BIG TCP. Signed-off-by: Eric Dumazet Acked-by: Alexander Duyck Signed-off-by: David S. Miller --- include/net/ipv6.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 213612f1680c..63d019953c47 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -151,6 +151,17 @@ struct frag_hdr { __be32 identification; }; +/* + * Jumbo payload option, as described in RFC 2675 2. + */ +struct hop_jumbo_hdr { + u8 nexthdr; + u8 hdrlen; + u8 tlv_type; /* IPV6_TLV_JUMBO, 0xC2 */ + u8 tlv_len; /* 4 */ + __be32 jumbo_payload_len; +}; + #define IP6_MF 0x0001 #define IP6_OFFSET 0xFFF8 -- cgit v1.2.3 From 09f3d1a3a52c696208008618a67e2c7c3fb16d41 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 May 2022 11:34:01 -0700 Subject: ipv6/gso: remove temporary HBH/jumbo header ipv6 tcp and gro stacks will soon be able to build big TCP packets, with an added temporary Hop By Hop header. If GSO is involved for these large packets, we need to remove the temporary HBH header before segmentation happens. v2: perform HBH removal from ipv6_gso_segment() instead of skb_segment() (Alexander feedback) Signed-off-by: Eric Dumazet Acked-by: Alexander Duyck Signed-off-by: David S. Miller --- include/net/ipv6.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 63d019953c47..b6df0314aa02 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -467,6 +467,39 @@ bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, struct ipv6_txoptions *ipv6_update_options(struct sock *sk, struct ipv6_txoptions *opt); +/* This helper is specialized for BIG TCP needs. + * It assumes the hop_jumbo_hdr will immediately follow the IPV6 header. + * It assumes headers are already in skb->head. + * Returns 0, or IPPROTO_TCP if a BIG TCP packet is there. + */ +static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb) +{ + const struct hop_jumbo_hdr *jhdr; + const struct ipv6hdr *nhdr; + + if (likely(skb->len <= GRO_MAX_SIZE)) + return 0; + + if (skb->protocol != htons(ETH_P_IPV6)) + return 0; + + if (skb_network_offset(skb) + + sizeof(struct ipv6hdr) + + sizeof(struct hop_jumbo_hdr) > skb_headlen(skb)) + return 0; + + nhdr = ipv6_hdr(skb); + + if (nhdr->nexthdr != NEXTHDR_HOP) + return 0; + + jhdr = (const struct hop_jumbo_hdr *) (nhdr + 1); + if (jhdr->tlv_type != IPV6_TLV_JUMBO || jhdr->hdrlen != 0 || + jhdr->nexthdr != IPPROTO_TCP) + return 0; + return jhdr->nexthdr; +} + static inline bool ipv6_accept_ra(struct inet6_dev *idev) { /* If forwarding is enabled, RA are not accepted unless the special -- cgit v1.2.3 From 0fe79f28bfaf73b66b7b1562d2468f94aa03bd12 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 13 May 2022 11:34:03 -0700 Subject: net: allow gro_max_size to exceed 65536 Allow the gro_max_size to exceed a value larger than 65536. There weren't really any external limitations that prevented this other than the fact that IPv4 only supports a 16 bit length field. Since we have the option of adding a hop-by-hop header for IPv6 we can allow IPv6 to exceed this value and for IPv4 and non-TCP flows we can cap things at 65536 via a constant rather than relying on gro_max_size. [edumazet] limit GRO_MAX_SIZE to (8 * 65535) to avoid overflows. Signed-off-by: Alexander Duyck Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 +++++- include/net/ipv6.h | 2 +- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fd38847d0dc7..d57ce248004c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2161,7 +2161,11 @@ struct net_device { struct bpf_prog __rcu *xdp_prog; unsigned long gro_flush_timeout; int napi_defer_hard_irqs; -#define GRO_MAX_SIZE 65536 +#define GRO_LEGACY_MAX_SIZE 65536u +/* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE), + * and shinfo->gso_segs is a 16bit field. + */ +#define GRO_MAX_SIZE (8 * 65535u) unsigned int gro_max_size; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; diff --git a/include/net/ipv6.h b/include/net/ipv6.h index b6df0314aa02..5b38bf1a586b 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -477,7 +477,7 @@ static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb) const struct hop_jumbo_hdr *jhdr; const struct ipv6hdr *nhdr; - if (likely(skb->len <= GRO_MAX_SIZE)) + if (likely(skb->len <= GRO_LEGACY_MAX_SIZE)) return 0; if (skb->protocol != htons(ETH_P_IPV6)) -- cgit v1.2.3 From 80e425b613421911f89664663a7060216abcaed2 Mon Sep 17 00:00:00 2001 From: Coco Li Date: Fri, 13 May 2022 11:34:04 -0700 Subject: ipv6: Add hop-by-hop header to jumbograms in ip6_output Instead of simply forcing a 0 payload_len in IPv6 header, implement RFC 2675 and insert a custom extension header. Note that only TCP stack is currently potentially generating jumbograms, and that this extension header is purely local, it wont be sent on a physical link. This is needed so that packet capture (tcpdump and friends) can properly dissect these large packets. Signed-off-by: Coco Li Signed-off-by: Eric Dumazet Acked-by: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index ec5ca392eaa3..38c8203d52cb 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -145,6 +145,7 @@ struct inet6_skb_parm { #define IP6SKB_L3SLAVE 64 #define IP6SKB_JUMBOGRAM 128 #define IP6SKB_SEG6 256 +#define IP6SKB_FAKEJUMBO 512 }; #if defined(CONFIG_NET_L3_MASTER_DEV) -- cgit v1.2.3 From 4c971d2f3548e4f11b1460ac048f5307e4b39fdb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 May 2022 11:55:41 -0700 Subject: net: annotate races around sk->sk_bound_dev_if UDP sendmsg() is lockless, and reads sk->sk_bound_dev_if while this field can be changed by another thread. Adds minimal annotations to avoid KCSAN splats for UDP. Following patches will add more annotations to potential lockless readers. BUG: KCSAN: data-race in __ip6_datagram_connect / udpv6_sendmsg write to 0xffff888136d47a94 of 4 bytes by task 7681 on cpu 0: __ip6_datagram_connect+0x6e2/0x930 net/ipv6/datagram.c:221 ip6_datagram_connect+0x2a/0x40 net/ipv6/datagram.c:272 inet_dgram_connect+0x107/0x190 net/ipv4/af_inet.c:576 __sys_connect_file net/socket.c:1900 [inline] __sys_connect+0x197/0x1b0 net/socket.c:1917 __do_sys_connect net/socket.c:1927 [inline] __se_sys_connect net/socket.c:1924 [inline] __x64_sys_connect+0x3d/0x50 net/socket.c:1924 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x50 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff888136d47a94 of 4 bytes by task 7670 on cpu 1: udpv6_sendmsg+0xc60/0x16e0 net/ipv6/udp.c:1436 inet6_sendmsg+0x5f/0x80 net/ipv6/af_inet6.c:652 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmmsg+0x267/0x4c0 net/socket.c:2553 __do_sys_sendmmsg net/socket.c:2582 [inline] __se_sys_sendmmsg net/socket.c:2579 [inline] __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2579 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x50 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x00000000 -> 0xffffff9b Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 7670 Comm: syz-executor.3 Tainted: G W 5.18.0-rc1-syzkaller-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 I chose to not add Fixes: tag because race has minor consequences and stable teams busy enough. Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- include/net/ip.h | 2 +- include/net/sock.h | 5 +++-- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 3984f2c39c4b..8ad04f60b413 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -93,7 +93,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, ipcm->sockc.mark = inet->sk.sk_mark; ipcm->sockc.tsflags = inet->sk.sk_tsflags; - ipcm->oif = inet->sk.sk_bound_dev_if; + ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; } diff --git a/include/net/sock.h b/include/net/sock.h index 01edfde4257d..72ca97ccb460 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2875,13 +2875,14 @@ static inline void sk_pacing_shift_update(struct sock *sk, int val) */ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif) { + int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); int mdif; - if (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dif) + if (!bound_dev_if || bound_dev_if == dif) return true; mdif = l3mdev_master_ifindex_by_index(sock_net(sk), dif); - if (mdif && mdif == sk->sk_bound_dev_if) + if (mdif && mdif == bound_dev_if) return true; return false; -- cgit v1.2.3 From fdb5fd7f736ec7ae9fb36d2842ea6d9ebc4e7269 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 May 2022 11:55:43 -0700 Subject: tcp: sk->sk_bound_dev_if once in inet_request_bound_dev_if() inet_request_bound_dev_if() reads sk->sk_bound_dev_if twice while listener socket is not locked. Another cpu could change this field under us. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_sock.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 234d70ae5f4c..c1b5dcd6597c 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -116,14 +116,15 @@ static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb) static inline int inet_request_bound_dev_if(const struct sock *sk, struct sk_buff *skb) { + int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); #ifdef CONFIG_NET_L3_MASTER_DEV struct net *net = sock_net(sk); - if (!sk->sk_bound_dev_if && net->ipv4.sysctl_tcp_l3mdev_accept) + if (!bound_dev_if && net->ipv4.sysctl_tcp_l3mdev_accept) return l3mdev_master_ifindex_by_index(net, skb->skb_iif); #endif - return sk->sk_bound_dev_if; + return bound_dev_if; } static inline int inet_sk_bound_l3mdev(const struct sock *sk) -- cgit v1.2.3 From 5d368f03280d3678433a7f119efe15dfbbb87bc8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 May 2022 11:55:49 -0700 Subject: ipv6: add READ_ONCE(sk->sk_bound_dev_if) in INET6_MATCH() INET6_MATCH() runs without holding a lock on the socket. We probably need to annotate most reads. This patch makes INET6_MATCH() an inline function to ease our changes. v2: inline function only defined if IS_ENABLED(CONFIG_IPV6) Change the name to inet6_match(), this is no longer a macro. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet6_hashtables.h | 28 +++++++++++++++++++--------- 1 file changed, 19 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 81b965953036..f259e1ae14ba 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -103,15 +103,25 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, const int dif); int inet6_hash(struct sock *sk); -#endif /* IS_ENABLED(CONFIG_IPV6) */ -#define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif, __sdif) \ - (((__sk)->sk_portpair == (__ports)) && \ - ((__sk)->sk_family == AF_INET6) && \ - ipv6_addr_equal(&(__sk)->sk_v6_daddr, (__saddr)) && \ - ipv6_addr_equal(&(__sk)->sk_v6_rcv_saddr, (__daddr)) && \ - (((__sk)->sk_bound_dev_if == (__dif)) || \ - ((__sk)->sk_bound_dev_if == (__sdif))) && \ - net_eq(sock_net(__sk), (__net))) +static inline bool inet6_match(struct net *net, const struct sock *sk, + const struct in6_addr *saddr, + const struct in6_addr *daddr, + const __portpair ports, + const int dif, const int sdif) +{ + int bound_dev_if; + + if (!net_eq(sock_net(sk), net) || + sk->sk_family != AF_INET6 || + sk->sk_portpair != ports || + !ipv6_addr_equal(&sk->sk_v6_daddr, saddr) || + !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) + return false; + + bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); + return bound_dev_if == dif || bound_dev_if == sdif; +} +#endif /* IS_ENABLED(CONFIG_IPV6) */ #endif /* _INET6_HASHTABLES_H */ -- cgit v1.2.3 From eda090c31fe923ab9463b884469744ec903ab0cc Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 May 2022 11:55:50 -0700 Subject: inet: rename INET_MATCH() This is no longer a macro, but an inlined function. INET_MATCH() -> inet_match() Signed-off-by: Eric Dumazet Suggested-by: Olivier Hartkopp Suggested-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 59d72024ad1d..ebfa3df6f8dc 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -267,7 +267,7 @@ static inline struct sock *inet_lookup_listener(struct net *net, ((__force __u64)(__be32)(__saddr))) #endif /* __BIG_ENDIAN */ -static inline bool INET_MATCH(struct net *net, const struct sock *sk, +static inline bool inet_match(struct net *net, const struct sock *sk, const __addrpair cookie, const __portpair ports, int dif, int sdif) { -- cgit v1.2.3 From 7ebd3f3ee51a9e02994cd0a1be44fbd325d1e0dc Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Fri, 13 May 2022 11:03:38 +0800 Subject: net: skb: change the definition SKB_DR_SET() The SKB_DR_OR() is used to set the drop reason to a value when it is not set or specified yet. SKB_NOT_DROPPED_YET should also be considered as not set. Reviewed-by: Jiang Biao Reviewed-by: Hao Peng Signed-off-by: Menglong Dong Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9d82a8b6c8f1..5a2b29df6cab 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -510,7 +510,8 @@ enum skb_drop_reason { (name = SKB_DROP_REASON_##reason) #define SKB_DR_OR(name, reason) \ do { \ - if (name == SKB_DROP_REASON_NOT_SPECIFIED) \ + if (name == SKB_DROP_REASON_NOT_SPECIFIED || \ + name == SKB_NOT_DROPPED_YET) \ SKB_DR_SET(name, reason); \ } while (0) -- cgit v1.2.3 From 97e719a82b43c6c2bb5eebdb3c5d479a332ac2ac Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 15 May 2022 21:24:53 -0700 Subject: net: fix possible race in skb_attempt_defer_free() A cpu can observe sd->defer_count reaching 128, and call smp_call_function_single_async() Problem is that the remote CPU can clear sd->defer_count before the IPI is run/acknowledged. Other cpus can queue more packets and also decide to call smp_call_function_single_async() while the pending IPI was not yet delivered. This is a common issue with smp_call_function_single_async(). Callers must ensure correct synchronization and serialization. I triggered this issue while experimenting smaller threshold. Performing the call to smp_call_function_single_async() under sd->defer_lock protection did not solve the problem. Commit 5a18ceca6350 ("smp: Allow smp_call_function_single_async() to insert locked csd") replaced an informative WARN_ON_ONCE() with a return of -EBUSY, which is often ignored. Test of CSD_FLAG_LOCK presence is racy anyway. Fixes: 68822bdf76f1 ("net: generalize skb freeing deferral to per-cpu lists") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d57ce248004c..cbaf312e365b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3136,6 +3136,7 @@ struct softnet_data { /* Another possibly contended cache line */ spinlock_t defer_lock ____cacheline_aligned_in_smp; int defer_count; + int defer_ipi_scheduled; struct sk_buff *defer_list; call_single_data_t defer_csd; }; -- cgit v1.2.3 From cf2df74e202d81b09f09d84c2d8903e0e87e9274 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Mon, 9 May 2022 14:26:15 +0200 Subject: net: fix dev_fill_forward_path with pppoe + bridge When calling dev_fill_forward_path on a pppoe device, the provided destination address is invalid. In order for the bridge fdb lookup to succeed, the pppoe code needs to update ctx->daddr to the correct value. Fix this by storing the address inside struct net_device_path_ctx Fixes: f6efc675c9dd ("net: ppp: resolve forwarding path for bridge pppoe devices") Signed-off-by: Felix Fietkau Signed-off-by: Pablo Neira Ayuso --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b1fbe21650bb..f736c020cde2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -900,7 +900,7 @@ struct net_device_path_stack { struct net_device_path_ctx { const struct net_device *dev; - const u8 *daddr; + u8 daddr[ETH_ALEN]; int num_vlans; struct { -- cgit v1.2.3 From d265929930e2ffafc744c0ae05fb70acd53be1ee Mon Sep 17 00:00:00 2001 From: William Tu Date: Wed, 4 May 2022 08:35:59 -0700 Subject: netfilter: nf_conncount: reduce unnecessary GC Currently nf_conncount can trigger garbage collection (GC) at multiple places. Each GC process takes a spin_lock_bh to traverse the nf_conncount_list. We found that when testing port scanning use two parallel nmap, because the number of connection increase fast, the nf_conncount_count and its subsequent call to __nf_conncount_add take too much time, causing several CPU lockup. This happens when user set the conntrack limit to +20,000, because the larger the limit, the longer the list that GC has to traverse. The patch mitigate the performance issue by avoiding unnecessary GC with a timestamp. Whenever nf_conncount has done a GC, a timestamp is updated, and beforce the next time GC is triggered, we make sure it's more than a jiffies. By doin this we can greatly reduce the CPU cycles and avoid the softirq lockup. To reproduce it in OVS, $ ovs-appctl dpctl/ct-set-limits zone=1,limit=20000 $ ovs-appctl dpctl/ct-get-limits At another machine, runs two nmap $ nmap -p1- $ nmap -p1- Signed-off-by: William Tu Co-authored-by: Yifeng Sun Reported-by: Greg Rose Suggested-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_count.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h index 9645b47fa7e4..e227d997fc71 100644 --- a/include/net/netfilter/nf_conntrack_count.h +++ b/include/net/netfilter/nf_conntrack_count.h @@ -10,6 +10,7 @@ struct nf_conncount_data; struct nf_conncount_list { spinlock_t list_lock; + u32 last_gc; /* jiffies at most recent gc */ struct list_head head; /* connections with the same filtering key */ unsigned int count; /* length of list */ }; -- cgit v1.2.3 From 9db69df4bdd37eb1f65b6931ee067fb15b9a4d5c Mon Sep 17 00:00:00 2001 From: TingHan Shen Date: Thu, 12 May 2022 16:22:13 +0800 Subject: firmware: mediatek: Add adsp ipc protocol interface Some of mediatek processors contain the Tensilica HiFix DSP for audio processing. The communication between Host CPU and DSP firmware is taking place using a shared memory area for message passing. ADSP IPC protocol offers (send/recv) interfaces using mediatek-mailbox APIs. We use two mbox channels to implement a request-reply protocol. Signed-off-by: Allen-KH Cheng Signed-off-by: TingHan Shen Reviewed-by: Pierre-Louis Bossart Reviewed-by: Curtis Malainey Reviewed-by: Tzung-Bi Shih Reviewed-by: YC Hung Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20220512082215.3018-2-tinghan.shen@mediatek.com Signed-off-by: Mark Brown --- include/linux/firmware/mediatek/mtk-adsp-ipc.h | 65 ++++++++++++++++++++++++++ 1 file changed, 65 insertions(+) create mode 100644 include/linux/firmware/mediatek/mtk-adsp-ipc.h (limited to 'include') diff --git a/include/linux/firmware/mediatek/mtk-adsp-ipc.h b/include/linux/firmware/mediatek/mtk-adsp-ipc.h new file mode 100644 index 000000000000..28fd313340b8 --- /dev/null +++ b/include/linux/firmware/mediatek/mtk-adsp-ipc.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022 MediaTek Inc. + */ + +#ifndef MTK_ADSP_IPC_H +#define MTK_ADSP_IPC_H + +#include +#include +#include +#include + +#define MTK_ADSP_IPC_REQ 0 +#define MTK_ADSP_IPC_RSP 1 +#define MTK_ADSP_IPC_OP_REQ 0x1 +#define MTK_ADSP_IPC_OP_RSP 0x2 + +enum { + MTK_ADSP_MBOX_REPLY, + MTK_ADSP_MBOX_REQUEST, + MTK_ADSP_MBOX_NUM, +}; + +struct mtk_adsp_ipc; + +struct mtk_adsp_ipc_ops { + void (*handle_reply)(struct mtk_adsp_ipc *ipc); + void (*handle_request)(struct mtk_adsp_ipc *ipc); +}; + +struct mtk_adsp_chan { + struct mtk_adsp_ipc *ipc; + struct mbox_client cl; + struct mbox_chan *ch; + char *name; + int idx; +}; + +struct mtk_adsp_ipc { + struct mtk_adsp_chan chans[MTK_ADSP_MBOX_NUM]; + struct device *dev; + struct mtk_adsp_ipc_ops *ops; + void *private_data; +}; + +static inline void mtk_adsp_ipc_set_data(struct mtk_adsp_ipc *ipc, void *data) +{ + if (!ipc) + return; + + ipc->private_data = data; +} + +static inline void *mtk_adsp_ipc_get_data(struct mtk_adsp_ipc *ipc) +{ + if (!ipc) + return NULL; + + return ipc->private_data; +} + +int mtk_adsp_ipc_send(struct mtk_adsp_ipc *ipc, unsigned int idx, uint32_t op); + +#endif /* MTK_ADSP_IPC_H */ -- cgit v1.2.3 From 64c917d1cfd70ff827c9ea37277a97762ea372d4 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Fri, 13 May 2022 10:05:30 +0100 Subject: ASoC: core: Correct spelling fliped -> flipped Signed-off-by: Charles Keepax Link: https://lore.kernel.org/r/20220513090532.1450944-1-ckeepax@opensource.cirrus.com Signed-off-by: Mark Brown --- include/sound/soc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index f906e5a70830..f20f5f890794 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -1259,7 +1259,7 @@ int snd_soc_of_parse_audio_routing(struct snd_soc_card *card, const char *propname); int snd_soc_of_parse_aux_devs(struct snd_soc_card *card, const char *propname); -unsigned int snd_soc_daifmt_clock_provider_fliped(unsigned int dai_fmt); +unsigned int snd_soc_daifmt_clock_provider_flipped(unsigned int dai_fmt); unsigned int snd_soc_daifmt_clock_provider_from_bitmap(unsigned int bit_frame); unsigned int snd_soc_daifmt_parse_format(struct device_node *np, const char *prefix); -- cgit v1.2.3 From 20492a62b99bd4367b79a76ca288d018f11980db Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 16 May 2022 13:02:24 +0100 Subject: KVM: arm64: pmu: Restore compilation when HW_PERF_EVENTS isn't selected Moving kvm_pmu_events into the vcpu (and refering to it) broke the somewhat unusual case where the kernel has no support for a PMU at all. In order to solve this, move things around a bit so that we can easily avoid refering to the pmu structure outside of PMU-aware code. As a bonus, pmu.c isn't compiled in when HW_PERF_EVENTS isn't selected. Reported-by: kernel test robot Reviewed-by: Fuad Tabba Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/202205161814.KQHpOzsJ-lkp@intel.com --- include/kvm/arm_pmu.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include') diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index 35a0903cae32..c0b868ce6a8f 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -72,6 +72,25 @@ int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu); + +struct kvm_pmu_events *kvm_get_pmu_events(void); +void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu); +void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu); + +#define kvm_vcpu_has_pmu(vcpu) \ + (test_bit(KVM_ARM_VCPU_PMU_V3, (vcpu)->arch.features)) + +/* + * Updates the vcpu's view of the pmu events for this cpu. + * Must be called before every vcpu run after disabling interrupts, to ensure + * that an interrupt cannot fire and update the structure. + */ +#define kvm_pmu_update_vcpu_events(vcpu) \ + do { \ + if (!has_vhe() && kvm_vcpu_has_pmu(vcpu)) \ + vcpu->arch.pmu.events = *kvm_get_pmu_events(); \ + } while (0) + #else struct kvm_pmu { }; @@ -133,6 +152,11 @@ static inline u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) return 0; } +#define kvm_vcpu_has_pmu(vcpu) ({ false; }) +static inline void kvm_pmu_update_vcpu_events(struct kvm_vcpu *vcpu) {} +static inline void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) {} +static inline void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) {} + #endif #endif -- cgit v1.2.3 From 7f8d12ea96352275c2850c24a1367166179392d2 Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Tue, 29 Mar 2022 15:55:59 +0900 Subject: fs: add a lockdep check function for sb_start_write() Add a function sb_write_started() to allow callers to verify if sb_start_write() is properly called. It will be used for assertion in btrfs. Reviewed-by: Filipe Manana Signed-off-by: Naohiro Aota Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/linux/fs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index bbde95387a23..01d61984ce7a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1708,6 +1708,11 @@ static inline bool __sb_start_write_trylock(struct super_block *sb, int level) #define __sb_writers_release(sb, lev) \ percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) +static inline bool sb_write_started(const struct super_block *sb) +{ + return lockdep_is_held_type(sb->s_writers.rw_sem + SB_FREEZE_WRITE - 1, 1); +} + /** * sb_end_write - drop write access to a superblock * @sb: the super we wrote to -- cgit v1.2.3 From a31b4a4368d28c5e780f0906588fbd1dcfe4ad54 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 18 Apr 2022 06:43:09 +0200 Subject: btrfs: simplify WQ_HIGHPRI handling in struct btrfs_workqueue Just let the one caller that wants optional WQ_HIGHPRI handling allocate a separate btrfs_workqueue for that. This allows to rename struct __btrfs_workqueue to btrfs_workqueue, remove a pointer indirection and separate allocation for all btrfs_workqueue users and generally simplify the code. Reviewed-by: Qu Wenruo Signed-off-by: Christoph Hellwig Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/trace/events/btrfs.h | 30 ++++++++++++------------------ 1 file changed, 12 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index f068ff30d654..290f07eb050a 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -24,7 +24,7 @@ struct btrfs_free_cluster; struct map_lookup; struct extent_buffer; struct btrfs_work; -struct __btrfs_workqueue; +struct btrfs_workqueue; struct btrfs_qgroup_extent_record; struct btrfs_qgroup; struct extent_io_tree; @@ -1457,42 +1457,36 @@ DEFINE_EVENT(btrfs__work, btrfs_ordered_sched, TP_ARGS(work) ); -DECLARE_EVENT_CLASS(btrfs__workqueue, +DECLARE_EVENT_CLASS(btrfs_workqueue, - TP_PROTO(const struct __btrfs_workqueue *wq, - const char *name, int high), + TP_PROTO(const struct btrfs_workqueue *wq, const char *name), - TP_ARGS(wq, name, high), + TP_ARGS(wq, name), TP_STRUCT__entry_btrfs( __field( const void *, wq ) __string( name, name ) - __field( int , high ) ), TP_fast_assign_btrfs(btrfs_workqueue_owner(wq), __entry->wq = wq; __assign_str(name, name); - __entry->high = high; ), - TP_printk_btrfs("name=%s%s wq=%p", __get_str(name), - __print_flags(__entry->high, "", - {(WQ_HIGHPRI), "-high"}), + TP_printk_btrfs("name=%s wq=%p", __get_str(name), __entry->wq) ); -DEFINE_EVENT(btrfs__workqueue, btrfs_workqueue_alloc, +DEFINE_EVENT(btrfs_workqueue, btrfs_workqueue_alloc, - TP_PROTO(const struct __btrfs_workqueue *wq, - const char *name, int high), + TP_PROTO(const struct btrfs_workqueue *wq, const char *name), - TP_ARGS(wq, name, high) + TP_ARGS(wq, name) ); -DECLARE_EVENT_CLASS(btrfs__workqueue_done, +DECLARE_EVENT_CLASS(btrfs_workqueue_done, - TP_PROTO(const struct __btrfs_workqueue *wq), + TP_PROTO(const struct btrfs_workqueue *wq), TP_ARGS(wq), @@ -1507,9 +1501,9 @@ DECLARE_EVENT_CLASS(btrfs__workqueue_done, TP_printk_btrfs("wq=%p", __entry->wq) ); -DEFINE_EVENT(btrfs__workqueue_done, btrfs_workqueue_destroy, +DEFINE_EVENT(btrfs_workqueue_done, btrfs_workqueue_destroy, - TP_PROTO(const struct __btrfs_workqueue *wq), + TP_PROTO(const struct btrfs_workqueue *wq), TP_ARGS(wq) ); -- cgit v1.2.3 From f04fbcc64e4be16185151f9fca44ea1b3d074bd0 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Wed, 20 Apr 2022 16:08:27 +0800 Subject: btrfs: move definition of btrfs_raid_types to volumes.h It's only internally used as another way to represent btrfs profiles, it's not exposed through any on-disk format, in fact this btrfs_raid_types is diverted from the on-disk format values. Furthermore, since it's internal structure, its definition can change in the future. Reviewed-by: Johannes Thumshirn Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/uapi/linux/btrfs_tree.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index b069752a8ecf..d4117152d907 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -880,19 +880,6 @@ struct btrfs_dev_replace_item { #define BTRFS_BLOCK_GROUP_RESERVED (BTRFS_AVAIL_ALLOC_BIT_SINGLE | \ BTRFS_SPACE_INFO_GLOBAL_RSV) -enum btrfs_raid_types { - BTRFS_RAID_RAID10, - BTRFS_RAID_RAID1, - BTRFS_RAID_DUP, - BTRFS_RAID_RAID0, - BTRFS_RAID_SINGLE, - BTRFS_RAID_RAID5, - BTRFS_RAID_RAID6, - BTRFS_RAID_RAID1C3, - BTRFS_RAID_RAID1C4, - BTRFS_NR_RAID_TYPES -}; - #define BTRFS_BLOCK_GROUP_TYPE_MASK (BTRFS_BLOCK_GROUP_DATA | \ BTRFS_BLOCK_GROUP_SYSTEM | \ BTRFS_BLOCK_GROUP_METADATA) -- cgit v1.2.3 From 908c54909ae72dcbf1d7e1440f7297187d06c275 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 5 May 2022 15:11:10 -0500 Subject: iomap: allow the file system to provide a bio_set for direct I/O Allow the file system to provide a specific bio_set for allocating direct I/O bios. This will allow file systems that use the ->submit_io hook to stash away additional information for file system use. To make use of this additional space for information in the completion path, the file system needs to override the ->bi_end_io callback and then call back into iomap, so export iomap_dio_bio_end_io for that. Reviewed-by: Darrick J. Wong Reviewed-by: Nikolay Borisov Signed-off-by: Christoph Hellwig Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/linux/iomap.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index b76f0dd149fb..cf903f1a230f 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -320,6 +320,16 @@ struct iomap_dio_ops { unsigned flags); void (*submit_io)(const struct iomap_iter *iter, struct bio *bio, loff_t file_offset); + + /* + * Filesystems wishing to attach private information to a direct io bio + * must provide a ->submit_io method that attaches the additional + * information to the bio and changes the ->bi_end_io callback to a + * custom function. This function should, at a minimum, perform any + * relevant post-processing of the bio and end with a call to + * iomap_dio_bio_end_io. + */ + struct bio_set *bio_set; }; /* @@ -349,6 +359,7 @@ struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, unsigned int dio_flags, size_t done_before); ssize_t iomap_dio_complete(struct iomap_dio *dio); +void iomap_dio_bio_end_io(struct bio *bio); #ifdef CONFIG_SWAP struct file; -- cgit v1.2.3 From 786f847f43a54e63161474fe85a4f1764d871a35 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 5 May 2022 15:11:11 -0500 Subject: iomap: add per-iomap_iter private data Allow the file system to keep state for all iterations. For now only wire it up for direct I/O as there is an immediate need for it there. Reviewed-by: Darrick J. Wong Reviewed-by: Nikolay Borisov Signed-off-by: Christoph Hellwig Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/linux/iomap.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index cf903f1a230f..5b6f64f4d771 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -188,6 +188,7 @@ struct iomap_iter { unsigned flags; struct iomap iomap; struct iomap srcmap; + void *private; }; int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops); @@ -354,10 +355,10 @@ struct iomap_dio_ops { ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, - unsigned int dio_flags, size_t done_before); + unsigned int dio_flags, void *private, size_t done_before); struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, - unsigned int dio_flags, size_t done_before); + unsigned int dio_flags, void *private, size_t done_before); ssize_t iomap_dio_complete(struct iomap_dio *dio); void iomap_dio_bio_end_io(struct bio *bio); -- cgit v1.2.3 From 1c05bb947f6464756174830b778aabf8f9d6ed0e Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Mon, 16 May 2022 12:12:02 +0200 Subject: include/uapi/linux/vfio.h: Fix trivial typo - _IORW should be _IOWR instead There is no macro called _IORW, so use _IOWR in the comment instead. Signed-off-by: Thomas Huth Reviewed-by: Cornelia Huck Link: https://lore.kernel.org/r/20220516101202.88373-1-thuth@redhat.com Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index fea86061b44e..733a1cddde30 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -643,7 +643,7 @@ enum { }; /** - * VFIO_DEVICE_GET_PCI_HOT_RESET_INFO - _IORW(VFIO_TYPE, VFIO_BASE + 12, + * VFIO_DEVICE_GET_PCI_HOT_RESET_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 12, * struct vfio_pci_hot_reset_info) * * Return: 0 on success, -errno on failure: @@ -770,7 +770,7 @@ struct vfio_device_ioeventfd { #define VFIO_DEVICE_IOEVENTFD _IO(VFIO_TYPE, VFIO_BASE + 16) /** - * VFIO_DEVICE_FEATURE - _IORW(VFIO_TYPE, VFIO_BASE + 17, + * VFIO_DEVICE_FEATURE - _IOWR(VFIO_TYPE, VFIO_BASE + 17, * struct vfio_device_feature) * * Get, set, or probe feature data of the device. The feature is selected -- cgit v1.2.3 From b3fdf9398a16f01dc013967a4ab25e99c3f4fc12 Mon Sep 17 00:00:00 2001 From: Jane Chu Date: Mon, 16 May 2022 11:21:46 -0700 Subject: x86/mce: relocate set{clear}_mce_nospec() functions Relocate the twin mce functions to arch/x86/mm/pat/set_memory.c file where they belong. While at it, fixup a function name in a comment. Reviewed-by: Christoph Hellwig Reviewed-by: Dan Williams Signed-off-by: Jane Chu Acked-by: Borislav Petkov Cc: Stephen Rothwell [sfr: gate {set,clear}_mce_nospec() by CONFIG_X86_64] Link: https://lore.kernel.org/r/165272527328.90175.8336008202048685278.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/linux/set_memory.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h index f36be5166c19..683a6c3f7179 100644 --- a/include/linux/set_memory.h +++ b/include/linux/set_memory.h @@ -42,14 +42,14 @@ static inline bool can_set_direct_map(void) #endif #endif /* CONFIG_ARCH_HAS_SET_DIRECT_MAP */ -#ifndef set_mce_nospec +#ifdef CONFIG_X86_64 +int set_mce_nospec(unsigned long pfn, bool unmap); +int clear_mce_nospec(unsigned long pfn); +#else static inline int set_mce_nospec(unsigned long pfn, bool unmap) { return 0; } -#endif - -#ifndef clear_mce_nospec static inline int clear_mce_nospec(unsigned long pfn) { return 0; -- cgit v1.2.3 From 5898b43af954b83c4a4ee4ab85c4dbafa395822a Mon Sep 17 00:00:00 2001 From: Jane Chu Date: Mon, 16 May 2022 11:38:10 -0700 Subject: mce: fix set_mce_nospec to always unmap the whole page The set_memory_uc() approach doesn't work well in all cases. As Dan pointed out when "The VMM unmapped the bad page from guest physical space and passed the machine check to the guest." "The guest gets virtual #MC on an access to that page. When the guest tries to do set_memory_uc() and instructs cpa_flush() to do clean caches that results in taking another fault / exception perhaps because the VMM unmapped the page from the guest." Since the driver has special knowledge to handle NP or UC, mark the poisoned page with NP and let driver handle it when it comes down to repair. Please refer to discussions here for more details. https://lore.kernel.org/all/CAPcyv4hrXPb1tASBZUg-GgdVs0OOFKXMXLiHmktg_kFi7YBMyQ@mail.gmail.com/ Now since poisoned page is marked as not-present, in order to avoid writing to a not-present page and trigger kernel Oops, also fix pmem_do_write(). Fixes: 284ce4011ba6 ("x86/memory_failure: Introduce {set, clear}_mce_nospec()") Reviewed-by: Christoph Hellwig Reviewed-by: Dan Williams Signed-off-by: Jane Chu Acked-by: Tony Luck Link: https://lore.kernel.org/r/165272615484.103830.2563950688772226611.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/linux/set_memory.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h index 683a6c3f7179..369769ce7399 100644 --- a/include/linux/set_memory.h +++ b/include/linux/set_memory.h @@ -43,10 +43,10 @@ static inline bool can_set_direct_map(void) #endif /* CONFIG_ARCH_HAS_SET_DIRECT_MAP */ #ifdef CONFIG_X86_64 -int set_mce_nospec(unsigned long pfn, bool unmap); +int set_mce_nospec(unsigned long pfn); int clear_mce_nospec(unsigned long pfn); #else -static inline int set_mce_nospec(unsigned long pfn, bool unmap) +static inline int set_mce_nospec(unsigned long pfn) { return 0; } -- cgit v1.2.3 From 7466886b400b1904ce30fa311904849e314a2cf4 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Mon, 2 May 2022 11:36:25 +0200 Subject: kunit: take `kunit_assert` as `const` The `kunit_do_failed_assertion` function passes its `struct kunit_assert` argument to `kunit_fail`. This one, in turn, calls its `format` field passing the assert again as a `const` pointer. Therefore, the whole chain may be made `const`. Signed-off-by: Miguel Ojeda Reviewed-by: Daniel Latypov Reviewed-by: Kees Cook Signed-off-by: Shuah Khan --- include/kunit/test.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/kunit/test.h b/include/kunit/test.h index 607e02b8e167..8ffcd7de9607 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -508,7 +508,7 @@ void __printf(2, 3) kunit_log_append(char *log, const char *fmt, ...); void kunit_do_failed_assertion(struct kunit *test, const struct kunit_loc *loc, enum kunit_assert_type type, - struct kunit_assert *assert, + const struct kunit_assert *assert, const char *fmt, ...); #define KUNIT_ASSERTION(test, assert_type, pass, assert_class, INITIALIZER, fmt, ...) do { \ -- cgit v1.2.3 From 9f39d36530e5678d092d53c5c2c60d82b4dcc169 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Sat, 7 May 2022 13:55:58 +0200 Subject: can: isotp: add support for transmission without flow control Usually the ISO 15765-2 protocol is a point-to-point protocol to transfer segmented PDUs to a dedicated receiver. This receiver sends a flow control message to specify protocol options and timings (e.g. block size / STmin). The so called functional addressing communication allows a 1:N communication but is limited to a single frame length. This new CAN_ISOTP_CF_BROADCAST allows an unconfirmed 1:N communication with PDU length that would not fit into a single frame. This feature is not covered by the ISO 15765-2 standard. Link: https://lore.kernel.org/all/20220507115558.19065-1-socketcan@hartkopp.net Signed-off-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/isotp.h | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/can/isotp.h b/include/uapi/linux/can/isotp.h index 590f8aea2b6d..439c982f7e81 100644 --- a/include/uapi/linux/can/isotp.h +++ b/include/uapi/linux/can/isotp.h @@ -124,18 +124,19 @@ struct can_isotp_ll_options { /* flags for isotp behaviour */ -#define CAN_ISOTP_LISTEN_MODE 0x001 /* listen only (do not send FC) */ -#define CAN_ISOTP_EXTEND_ADDR 0x002 /* enable extended addressing */ -#define CAN_ISOTP_TX_PADDING 0x004 /* enable CAN frame padding tx path */ -#define CAN_ISOTP_RX_PADDING 0x008 /* enable CAN frame padding rx path */ -#define CAN_ISOTP_CHK_PAD_LEN 0x010 /* check received CAN frame padding */ -#define CAN_ISOTP_CHK_PAD_DATA 0x020 /* check received CAN frame padding */ -#define CAN_ISOTP_HALF_DUPLEX 0x040 /* half duplex error state handling */ -#define CAN_ISOTP_FORCE_TXSTMIN 0x080 /* ignore stmin from received FC */ -#define CAN_ISOTP_FORCE_RXSTMIN 0x100 /* ignore CFs depending on rx stmin */ -#define CAN_ISOTP_RX_EXT_ADDR 0x200 /* different rx extended addressing */ -#define CAN_ISOTP_WAIT_TX_DONE 0x400 /* wait for tx completion */ -#define CAN_ISOTP_SF_BROADCAST 0x800 /* 1-to-N functional addressing */ +#define CAN_ISOTP_LISTEN_MODE 0x0001 /* listen only (do not send FC) */ +#define CAN_ISOTP_EXTEND_ADDR 0x0002 /* enable extended addressing */ +#define CAN_ISOTP_TX_PADDING 0x0004 /* enable CAN frame padding tx path */ +#define CAN_ISOTP_RX_PADDING 0x0008 /* enable CAN frame padding rx path */ +#define CAN_ISOTP_CHK_PAD_LEN 0x0010 /* check received CAN frame padding */ +#define CAN_ISOTP_CHK_PAD_DATA 0x0020 /* check received CAN frame padding */ +#define CAN_ISOTP_HALF_DUPLEX 0x0040 /* half duplex error state handling */ +#define CAN_ISOTP_FORCE_TXSTMIN 0x0080 /* ignore stmin from received FC */ +#define CAN_ISOTP_FORCE_RXSTMIN 0x0100 /* ignore CFs depending on rx stmin */ +#define CAN_ISOTP_RX_EXT_ADDR 0x0200 /* different rx extended addressing */ +#define CAN_ISOTP_WAIT_TX_DONE 0x0400 /* wait for tx completion */ +#define CAN_ISOTP_SF_BROADCAST 0x0800 /* 1-to-N functional addressing */ +#define CAN_ISOTP_CF_BROADCAST 0x1000 /* 1-to-N transmission w/o FC */ /* protocol machine default values */ -- cgit v1.2.3 From e511c4a3d2a1f64aafc1f5df37a2ffcf7ef91b55 Mon Sep 17 00:00:00 2001 From: Jane Chu Date: Fri, 13 May 2022 15:10:58 -0700 Subject: dax: introduce DAX_RECOVERY_WRITE dax access mode Up till now, dax_direct_access() is used implicitly for normal access, but for the purpose of recovery write, dax range with poison is requested. To make the interface clear, introduce enum dax_access_mode { DAX_ACCESS, DAX_RECOVERY_WRITE, } where DAX_ACCESS is used for normal dax access, and DAX_RECOVERY_WRITE is used for dax recovery write. Suggested-by: Dan Williams Signed-off-by: Jane Chu Reviewed-by: Christoph Hellwig Cc: Mike Snitzer Reviewed-by: Vivek Goyal Link: https://lore.kernel.org/r/165247982851.52965.11024212198889762949.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- include/linux/dax.h | 9 +++++++-- include/linux/device-mapper.h | 4 +++- 2 files changed, 10 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/dax.h b/include/linux/dax.h index 9fc5f99a0ae2..3f1339bce3c0 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -14,6 +14,11 @@ struct iomap_ops; struct iomap_iter; struct iomap; +enum dax_access_mode { + DAX_ACCESS, + DAX_RECOVERY_WRITE, +}; + struct dax_operations { /* * direct_access: translate a device-relative @@ -21,7 +26,7 @@ struct dax_operations { * number of pages available for DAX at that pfn. */ long (*direct_access)(struct dax_device *, pgoff_t, long, - void **, pfn_t *); + enum dax_access_mode, void **, pfn_t *); /* * Validate whether this device is usable as an fsdax backing * device. @@ -178,7 +183,7 @@ static inline void dax_read_unlock(int id) bool dax_alive(struct dax_device *dax_dev); void *dax_get_private(struct dax_device *dax_dev); long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, - void **kaddr, pfn_t *pfn); + enum dax_access_mode mode, void **kaddr, pfn_t *pfn); size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index c2a3758c4aaa..acdedda0d12b 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -20,6 +20,7 @@ struct dm_table; struct dm_report_zones_args; struct mapped_device; struct bio_vec; +enum dax_access_mode; /* * Type of table, mapped_device's mempool and request_queue @@ -146,7 +147,8 @@ typedef int (*dm_busy_fn) (struct dm_target *ti); * >= 0 : the number of bytes accessible at the address */ typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff, - long nr_pages, void **kaddr, pfn_t *pfn); + long nr_pages, enum dax_access_mode node, void **kaddr, + pfn_t *pfn); typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages); -- cgit v1.2.3 From 047218ec904da19c45c4a70274fc3f818a1fcba1 Mon Sep 17 00:00:00 2001 From: Jane Chu Date: Fri, 22 Apr 2022 16:45:06 -0600 Subject: dax: add .recovery_write dax_operation Introduce dax_recovery_write() operation. The function is used to recover a dax range that contains poison. Typical use case is when a user process receives a SIGBUS with si_code BUS_MCEERR_AR indicating poison(s) in a dax range, in response, the user process issues a pwrite() to the page-aligned dax range, thus clears the poison and puts valid data in the range. Reviewed-by: Christoph Hellwig Signed-off-by: Jane Chu Link: https://lore.kernel.org/r/20220422224508.440670-6-jane.chu@oracle.com Signed-off-by: Dan Williams --- include/linux/dax.h | 13 +++++++++++++ include/linux/device-mapper.h | 9 +++++++++ 2 files changed, 22 insertions(+) (limited to 'include') diff --git a/include/linux/dax.h b/include/linux/dax.h index 3f1339bce3c0..e7b81634c52a 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -35,6 +35,12 @@ struct dax_operations { sector_t, sector_t); /* zero_page_range: required operation. Zero page range */ int (*zero_page_range)(struct dax_device *, pgoff_t, size_t); + /* + * recovery_write: recover a poisoned range by DAX device driver + * capable of clearing poison. + */ + size_t (*recovery_write)(struct dax_device *dax_dev, pgoff_t pgoff, + void *addr, size_t bytes, struct iov_iter *iter); }; #if IS_ENABLED(CONFIG_DAX) @@ -45,6 +51,8 @@ void dax_write_cache(struct dax_device *dax_dev, bool wc); bool dax_write_cache_enabled(struct dax_device *dax_dev); bool dax_synchronous(struct dax_device *dax_dev); void set_dax_synchronous(struct dax_device *dax_dev); +size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff, + void *addr, size_t bytes, struct iov_iter *i); /* * Check if given mapping is supported by the file / underlying device. */ @@ -92,6 +100,11 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, { return !(vma->vm_flags & VM_SYNC); } +static inline size_t dax_recovery_write(struct dax_device *dax_dev, + pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) +{ + return 0; +} #endif void set_dax_nocache(struct dax_device *dax_dev); diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index acdedda0d12b..47a01c7cffdf 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -152,6 +152,14 @@ typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff, typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages); +/* + * Returns: + * != 0 : number of bytes transferred + * 0 : recovery write failed + */ +typedef size_t (*dm_dax_recovery_write_fn)(struct dm_target *ti, pgoff_t pgoff, + void *addr, size_t bytes, struct iov_iter *i); + void dm_error(const char *message); struct dm_dev { @@ -201,6 +209,7 @@ struct target_type { dm_io_hints_fn io_hints; dm_dax_direct_access_fn direct_access; dm_dax_zero_page_range_fn dax_zero_page_range; + dm_dax_recovery_write_fn dax_recovery_write; /* For internal device-mapper use. */ struct list_head list; -- cgit v1.2.3 From 89af2ce2d95c80f6da9388d9da2e35c84c2573b1 Mon Sep 17 00:00:00 2001 From: Ricardo Martinez Date: Fri, 13 May 2022 10:34:00 -0700 Subject: net: skb: Remove skb_data_area_size() skb_data_area_size() is not needed. As Jakub pointed out [1]: For Rx, drivers can use the size passed during skb allocation or use skb_tailroom(). For Tx, drivers should use skb_headlen(). [1] https://lore.kernel.org/netdev/CAHNKnsTmH-rGgWi3jtyC=ktM1DW2W1VJkYoTMJV2Z_Bt498bsg@mail.gmail.com/ Signed-off-by: Ricardo Martinez Reviewed-by: Andy Shevchenko Reviewed-by: Sergey Ryazanov Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5a2b29df6cab..da96f0d3e753 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1765,11 +1765,6 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) } #endif -static inline unsigned int skb_data_area_size(struct sk_buff *skb) -{ - return skb_end_pointer(skb) - skb->data; -} - struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); -- cgit v1.2.3 From 848b89778ed53e6c9f9e3ed01c90109ee970b3d1 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Fri, 6 May 2022 12:57:55 +0200 Subject: scsi: fcoe: Add a local_lock to fcoe_percpu fcoe_get_paged_crc_eof() relies on the caller having preemption disabled to ensure the per-CPU fcoe_percpu context remains valid throughout the call. This is done by either holding spinlocks (such as bnx2fc_global_lock or qedf_global_lock) or the get_cpu() from fcoe_alloc_paged_crc_eof(). This last one breaks PREEMPT_RT semantics as there can be memory allocation and end up sleeping in atomic contexts. Introduce a local_lock_t to struct fcoe_percpu that will keep the non-RT case the same, mapping to preempt_disable/enable, while RT will use a per-CPU spinlock allowing the region to be preemptible but still maintain CPU locality. The other users of fcoe_percpu are already safe in this regard and do not require local_lock()ing. Link: https://lore.kernel.org/r/20211117025956.79616-3-dave@stgolabs.net Link: https://lore.kernel.org/r/20220506105758.283887-2-bigeasy@linutronix.de Acked-by: Sebastian Andrzej Siewior Signed-off-by: Davidlohr Bueso Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Martin K. Petersen --- include/scsi/libfcoe.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/scsi/libfcoe.h b/include/scsi/libfcoe.h index fac8e89aed81..6e79fb87fea2 100644 --- a/include/scsi/libfcoe.h +++ b/include/scsi/libfcoe.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -326,6 +327,7 @@ struct fcoe_percpu_s { struct sk_buff_head fcoe_rx_list; struct page *crc_eof_page; int crc_eof_offset; + local_lock_t lock; }; /** -- cgit v1.2.3 From e626f37e657adbab2a7abe51480925891662a5f3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 May 2022 14:29:43 +0200 Subject: nvme: split the enum used for various register constants Instead of having one big enum add one for each register or field. Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Reviewed-by: Chaitanya Kulkarni --- include/linux/nvme.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index bbabdc7600da..5f6d432fa06a 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -204,8 +204,9 @@ enum { NVME_CC_SHN_MASK = 3 << NVME_CC_SHN_SHIFT, NVME_CC_IOSQES = NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT, NVME_CC_IOCQES = NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT, - NVME_CAP_CSS_NVM = 1 << 0, - NVME_CAP_CSS_CSI = 1 << 6, +}; + +enum { NVME_CSTS_RDY = 1 << 0, NVME_CSTS_CFS = 1 << 1, NVME_CSTS_NSSRO = 1 << 4, @@ -214,10 +215,18 @@ enum { NVME_CSTS_SHST_OCCUR = 1 << 2, NVME_CSTS_SHST_CMPLT = 2 << 2, NVME_CSTS_SHST_MASK = 3 << 2, +}; + +enum { NVME_CMBMSC_CRE = 1 << 0, NVME_CMBMSC_CMSE = 1 << 1, }; +enum { + NVME_CAP_CSS_NVM = 1 << 0, + NVME_CAP_CSS_CSI = 1 << 6, +}; + struct nvme_id_power_state { __le16 max_power; /* centiwatts */ __u8 rsvd2; -- cgit v1.2.3 From 5e052a4d2a47eec3ac1e707ed415b2948bba54ef Mon Sep 17 00:00:00 2001 From: Xin Ji Date: Fri, 22 Apr 2022 10:47:15 +0200 Subject: media: media/v4l2-core: Add enum V4L2_FWNODE_BUS_TYPE_DPI As V4L2_FWNODE_BUS_TYPE_PARALLEL is not used for DPI interface, this patch add V4L2_FWNODE_BUS_TYPE_DPI for video DPI interface. Signed-off-by: Xin Ji Reviewed-by: Robert Foss Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-fwnode.h | 2 ++ include/media/v4l2-mediabus.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/media/v4l2-fwnode.h b/include/media/v4l2-fwnode.h index feb132df45a3..15e4ab672223 100644 --- a/include/media/v4l2-fwnode.h +++ b/include/media/v4l2-fwnode.h @@ -173,6 +173,7 @@ struct v4l2_fwnode_connector { * @V4L2_FWNODE_BUS_TYPE_CSI2_DPHY: MIPI CSI-2 bus, D-PHY physical layer * @V4L2_FWNODE_BUS_TYPE_PARALLEL: Camera Parallel Interface bus * @V4L2_FWNODE_BUS_TYPE_BT656: BT.656 video format bus-type + * @V4L2_FWNODE_BUS_TYPE_DPI: Video Parallel Interface bus * @NR_OF_V4L2_FWNODE_BUS_TYPE: Number of bus-types */ enum v4l2_fwnode_bus_type { @@ -183,6 +184,7 @@ enum v4l2_fwnode_bus_type { V4L2_FWNODE_BUS_TYPE_CSI2_DPHY, V4L2_FWNODE_BUS_TYPE_PARALLEL, V4L2_FWNODE_BUS_TYPE_BT656, + V4L2_FWNODE_BUS_TYPE_DPI, NR_OF_V4L2_FWNODE_BUS_TYPE }; diff --git a/include/media/v4l2-mediabus.h b/include/media/v4l2-mediabus.h index e0db3bcff9ed..f67a74daf799 100644 --- a/include/media/v4l2-mediabus.h +++ b/include/media/v4l2-mediabus.h @@ -129,6 +129,7 @@ struct v4l2_mbus_config_mipi_csi1 { * @V4L2_MBUS_CCP2: CCP2 (Compact Camera Port 2) * @V4L2_MBUS_CSI2_DPHY: MIPI CSI-2 serial interface, with D-PHY * @V4L2_MBUS_CSI2_CPHY: MIPI CSI-2 serial interface, with C-PHY + * @V4L2_MBUS_DPI: MIPI VIDEO DPI interface * @V4L2_MBUS_INVALID: invalid bus type (keep as last) */ enum v4l2_mbus_type { @@ -139,6 +140,7 @@ enum v4l2_mbus_type { V4L2_MBUS_CCP2, V4L2_MBUS_CSI2_DPHY, V4L2_MBUS_CSI2_CPHY, + V4L2_MBUS_DPI, V4L2_MBUS_INVALID, }; -- cgit v1.2.3 From a34cc79c9623ea2c12eca22c16e70047fbd7c26e Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Tue, 26 Apr 2022 09:02:38 +0200 Subject: media: Add bus type to frame descriptors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add the media bus type to the frame descriptor. CSI-2 specific information will be added in next patch to the frame descriptor. - Make the bus type a named enum Signed-off-by: Sakari Ailus Reviewed-by: Niklas Söderlund Signed-off-by: Jacopo Mondi Signed-off-by: Tomi Valkeinen Reviewed-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index 33a7201edb61..544ddd1bdcbe 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -344,12 +344,32 @@ struct v4l2_mbus_frame_desc_entry { #define V4L2_FRAME_DESC_ENTRY_MAX 4 +/** + * enum v4l2_mbus_frame_desc_type - media bus frame description type + * + * @V4L2_MBUS_FRAME_DESC_TYPE_UNDEFINED: + * Undefined frame desc type. Drivers should not use this, it is + * for backwards compatibility. + * @V4L2_MBUS_FRAME_DESC_TYPE_PARALLEL: + * Parallel media bus. + * @V4L2_MBUS_FRAME_DESC_TYPE_CSI2: + * CSI-2 media bus. Frame desc parameters must be set in + * &struct v4l2_mbus_frame_desc_entry->csi2. + */ +enum v4l2_mbus_frame_desc_type { + V4L2_MBUS_FRAME_DESC_TYPE_UNDEFINED = 0, + V4L2_MBUS_FRAME_DESC_TYPE_PARALLEL, + V4L2_MBUS_FRAME_DESC_TYPE_CSI2, +}; + /** * struct v4l2_mbus_frame_desc - media bus data frame description + * @type: type of the bus (enum v4l2_mbus_frame_desc_type) * @entry: frame descriptors array * @num_entries: number of entries in @entry array */ struct v4l2_mbus_frame_desc { + enum v4l2_mbus_frame_desc_type type; struct v4l2_mbus_frame_desc_entry entry[V4L2_FRAME_DESC_ENTRY_MAX]; unsigned short num_entries; }; -- cgit v1.2.3 From 897c45df291ff063d6a0acb20b3a0c276c6adf6a Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Tue, 26 Apr 2022 09:02:39 +0200 Subject: media: Add CSI-2 bus configuration to frame descriptors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add CSI-2 bus specific configuration to the frame descriptors. This allows obtaining the virtual channel and data type information for each stream the transmitter is sending. Signed-off-by: Sakari Ailus Reviewed-by: Niklas Söderlund Reviewed-by: Jacopo Mondi Signed-off-by: Tomi Valkeinen Reviewed-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index 544ddd1bdcbe..b661e1817470 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -312,6 +312,17 @@ struct v4l2_subdev_audio_ops { int (*s_stream)(struct v4l2_subdev *sd, int enable); }; +/** + * struct v4l2_mbus_frame_desc_entry_csi2 + * + * @vc: CSI-2 virtual channel + * @dt: CSI-2 data type ID + */ +struct v4l2_mbus_frame_desc_entry_csi2 { + u8 vc; + u8 dt; +}; + /** * enum v4l2_mbus_frame_desc_flags - media bus frame description flags * @@ -335,11 +346,16 @@ enum v4l2_mbus_frame_desc_flags { * %FRAME_DESC_FL_BLOB is not set. * @length: number of octets per frame, valid if @flags * %V4L2_MBUS_FRAME_DESC_FL_LEN_MAX is set. + * @bus: Bus-specific frame descriptor parameters + * @bus.csi2: CSI-2-specific bus configuration */ struct v4l2_mbus_frame_desc_entry { enum v4l2_mbus_frame_desc_flags flags; u32 pixelcode; u32 length; + union { + struct v4l2_mbus_frame_desc_entry_csi2 csi2; + } bus; }; #define V4L2_FRAME_DESC_ENTRY_MAX 4 -- cgit v1.2.3 From e74e476834f810d99261988e501d460235269158 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Fri, 29 Apr 2022 00:52:06 +0200 Subject: media: Add MIPI CSI-2 28 bits per pixel raw data type Add CSI-2 data type for 28 bits per pixel data. Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/mipi-csi2.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/media/mipi-csi2.h b/include/media/mipi-csi2.h index 392794e5badd..c3d8f12234b1 100644 --- a/include/media/mipi-csi2.h +++ b/include/media/mipi-csi2.h @@ -31,6 +31,7 @@ #define MIPI_CSI2_DT_RGB565 0x22 #define MIPI_CSI2_DT_RGB666 0x23 #define MIPI_CSI2_DT_RGB888 0x24 +#define MIPI_CSI2_DT_RAW28 0x26 #define MIPI_CSI2_DT_RAW24 0x27 #define MIPI_CSI2_DT_RAW6 0x28 #define MIPI_CSI2_DT_RAW7 0x29 -- cgit v1.2.3 From b87f5e25b2f9deb503a61c6957c7b1680d91cfea Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Fri, 6 May 2022 01:03:48 +0200 Subject: media: uapi: Add IPU3 packed Y10 format Some platforms with an Intel IPU3 have an IR sensor producing 10 bit greyscale format data that is transmitted over a CSI-2 bus to a CIO2 device - this packs the data into 32 bytes per 25 pixels. Add an entry to the uAPI header defining that format. Signed-off-by: Daniel Scally Acked-by: Andy Shevchenko Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 6d465dc443b7..343b95107fce 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -569,6 +569,7 @@ struct v4l2_pix_format { /* Grey bit-packed formats */ #define V4L2_PIX_FMT_Y10BPACK v4l2_fourcc('Y', '1', '0', 'B') /* 10 Greyscale bit-packed */ #define V4L2_PIX_FMT_Y10P v4l2_fourcc('Y', '1', '0', 'P') /* 10 Greyscale, MIPI RAW10 packed */ +#define V4L2_PIX_FMT_IPU3_Y10 v4l2_fourcc('i', 'p', '3', 'y') /* IPU3 packed 10-bit greyscale */ /* Palette formats */ #define V4L2_PIX_FMT_PAL8 v4l2_fourcc('P', 'A', 'L', '8') /* 8 8-bit palette */ @@ -749,7 +750,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_QC08C v4l2_fourcc('Q', '0', '8', 'C') /* Qualcomm 8-bit compressed */ #define V4L2_PIX_FMT_QC10C v4l2_fourcc('Q', '1', '0', 'C') /* Qualcomm 10-bit compressed */ -/* 10bit raw bayer packed, 32 bytes for every 25 pixels, last LSB 6 bits unused */ +/* 10bit raw packed, 32 bytes for every 25 pixels, last LSB 6 bits unused */ #define V4L2_PIX_FMT_IPU3_SBGGR10 v4l2_fourcc('i', 'p', '3', 'b') /* IPU3 packed 10-bit BGGR bayer */ #define V4L2_PIX_FMT_IPU3_SGBRG10 v4l2_fourcc('i', 'p', '3', 'g') /* IPU3 packed 10-bit GBRG bayer */ #define V4L2_PIX_FMT_IPU3_SGRBG10 v4l2_fourcc('i', 'p', '3', 'G') /* IPU3 packed 10-bit GRBG bayer */ -- cgit v1.2.3 From 2e2c3d6c0ef88ffac0d6b5079ee88cf8408f5f3b Mon Sep 17 00:00:00 2001 From: Nicolas Dufresne Date: Fri, 13 May 2022 22:29:03 +0200 Subject: media: h264: Use v4l2_h264_reference for reflist In preparation for adding field decoding support, convert the byte arrays for reflist into array of struct v4l2_h264_reference. That struct will allow us to mark which field of the reference picture is being referenced. [hverkuil: top_field_order_cnt -> pic_order_count] Signed-off-by: Nicolas Dufresne Reviewed-by: Ezequiel Garcia Tested-by: Dmitry Osipenko Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-h264.h | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-h264.h b/include/media/v4l2-h264.h index 4b1c71c935e0..ef9a894e3c32 100644 --- a/include/media/v4l2-h264.h +++ b/include/media/v4l2-h264.h @@ -37,7 +37,7 @@ struct v4l2_h264_reflist_builder { u16 longterm : 1; } refs[V4L2_H264_NUM_DPB_ENTRIES]; s32 cur_pic_order_count; - u8 unordered_reflist[V4L2_H264_NUM_DPB_ENTRIES]; + struct v4l2_h264_reference unordered_reflist[V4L2_H264_NUM_DPB_ENTRIES]; u8 num_valid; }; @@ -51,10 +51,10 @@ v4l2_h264_init_reflist_builder(struct v4l2_h264_reflist_builder *b, * v4l2_h264_build_b_ref_lists() - Build the B0/B1 reference lists * * @builder: reference list builder context - * @b0_reflist: 16-bytes array used to store the B0 reference list. Each entry - * is an index in the DPB - * @b1_reflist: 16-bytes array used to store the B1 reference list. Each entry - * is an index in the DPB + * @b0_reflist: 16 sized array used to store the B0 reference list. Each entry + * is a v4l2_h264_reference structure + * @b1_reflist: 16 sized array used to store the B1 reference list. Each entry + * is a v4l2_h264_reference structure * * This functions builds the B0/B1 reference lists. This procedure is described * in section '8.2.4 Decoding process for reference picture lists construction' @@ -63,14 +63,15 @@ v4l2_h264_init_reflist_builder(struct v4l2_h264_reflist_builder *b, */ void v4l2_h264_build_b_ref_lists(const struct v4l2_h264_reflist_builder *builder, - u8 *b0_reflist, u8 *b1_reflist); + struct v4l2_h264_reference *b0_reflist, + struct v4l2_h264_reference *b1_reflist); /** * v4l2_h264_build_p_ref_list() - Build the P reference list * * @builder: reference list builder context - * @reflist: 16-bytes array used to store the P reference list. Each entry - * is an index in the DPB + * @reflist: 16 sized array used to store the P reference list. Each entry + * is a v4l2_h264_reference structure * * This functions builds the P reference lists. This procedure is describe in * section '8.2.4 Decoding process for reference picture lists construction' @@ -79,6 +80,6 @@ v4l2_h264_build_b_ref_lists(const struct v4l2_h264_reflist_builder *builder, */ void v4l2_h264_build_p_ref_list(const struct v4l2_h264_reflist_builder *builder, - u8 *reflist); + struct v4l2_h264_reference *reflist); #endif /* _MEDIA_V4L2_H264_H */ -- cgit v1.2.3 From 26e4520509ffa4bec3d679f7cb3de9adfabef4b3 Mon Sep 17 00:00:00 2001 From: Nicolas Dufresne Date: Fri, 13 May 2022 22:29:04 +0200 Subject: media: h264: Increase reference lists size to 32 This is to accommodate support for field decoding, which splits the top and the bottom references into the reference list. Signed-off-by: Nicolas Dufresne Reviewed-by: Sebastian Fricke Reviewed-by: Ezequiel Garcia Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-h264.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-h264.h b/include/media/v4l2-h264.h index ef9a894e3c32..e282fb16ac58 100644 --- a/include/media/v4l2-h264.h +++ b/include/media/v4l2-h264.h @@ -37,7 +37,7 @@ struct v4l2_h264_reflist_builder { u16 longterm : 1; } refs[V4L2_H264_NUM_DPB_ENTRIES]; s32 cur_pic_order_count; - struct v4l2_h264_reference unordered_reflist[V4L2_H264_NUM_DPB_ENTRIES]; + struct v4l2_h264_reference unordered_reflist[V4L2_H264_REF_LIST_LEN]; u8 num_valid; }; @@ -51,9 +51,9 @@ v4l2_h264_init_reflist_builder(struct v4l2_h264_reflist_builder *b, * v4l2_h264_build_b_ref_lists() - Build the B0/B1 reference lists * * @builder: reference list builder context - * @b0_reflist: 16 sized array used to store the B0 reference list. Each entry + * @b0_reflist: 32 sized array used to store the B0 reference list. Each entry * is a v4l2_h264_reference structure - * @b1_reflist: 16 sized array used to store the B1 reference list. Each entry + * @b1_reflist: 32 sized array used to store the B1 reference list. Each entry * is a v4l2_h264_reference structure * * This functions builds the B0/B1 reference lists. This procedure is described @@ -70,7 +70,7 @@ v4l2_h264_build_b_ref_lists(const struct v4l2_h264_reflist_builder *builder, * v4l2_h264_build_p_ref_list() - Build the P reference list * * @builder: reference list builder context - * @reflist: 16 sized array used to store the P reference list. Each entry + * @reflist: 32 sized array used to store the P reference list. Each entry * is a v4l2_h264_reference structure * * This functions builds the P reference lists. This procedure is describe in -- cgit v1.2.3 From adc8a8d6c98a5c996aad41bf1625d87829bd76ba Mon Sep 17 00:00:00 2001 From: Nicolas Dufresne Date: Fri, 13 May 2022 22:29:05 +0200 Subject: media: h264: Store current picture fields This information, also called picture structure, is required in field decoding mode to construct reference lists. Signed-off-by: Nicolas Dufresne Reviewed-by: Sebastian Fricke Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-h264.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/media/v4l2-h264.h b/include/media/v4l2-h264.h index e282fb16ac58..e165a54c68fa 100644 --- a/include/media/v4l2-h264.h +++ b/include/media/v4l2-h264.h @@ -21,6 +21,7 @@ * @refs.longterm: set to true for a long term reference * @refs: array of references * @cur_pic_order_count: picture order count of the frame being decoded + * @cur_pic_fields: fields present in the frame being decoded * @unordered_reflist: unordered list of references. Will be used to generate * ordered P/B0/B1 lists * @num_valid: number of valid references in the refs array @@ -36,7 +37,10 @@ struct v4l2_h264_reflist_builder { u32 pic_num; u16 longterm : 1; } refs[V4L2_H264_NUM_DPB_ENTRIES]; + s32 cur_pic_order_count; + u8 cur_pic_fields; + struct v4l2_h264_reference unordered_reflist[V4L2_H264_REF_LIST_LEN]; u8 num_valid; }; -- cgit v1.2.3 From e5991e1fd90295b1eb8326a4a6c09012d6c5fc8d Mon Sep 17 00:00:00 2001 From: Nicolas Dufresne Date: Fri, 13 May 2022 22:29:06 +0200 Subject: media: h264: Store all fields into the unordered list When the current picture is a field, store each field into the unordered_list and preserve both top and bottom picture order count. Signed-off-by: Nicolas Dufresne Reviewed-by: Sebastian Fricke Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-h264.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-h264.h b/include/media/v4l2-h264.h index e165a54c68fa..4cef717b3f18 100644 --- a/include/media/v4l2-h264.h +++ b/include/media/v4l2-h264.h @@ -15,7 +15,8 @@ /** * struct v4l2_h264_reflist_builder - Reference list builder object * - * @refs.pic_order_count: reference picture order count + * @refs.top_field_order_cnt: top field order count + * @refs.bottom_field_order_cnt: bottom field order count * @refs.frame_num: reference frame number * @refs.pic_num: reference picture number * @refs.longterm: set to true for a long term reference @@ -32,7 +33,8 @@ */ struct v4l2_h264_reflist_builder { struct { - s32 pic_order_count; + s32 top_field_order_cnt; + s32 bottom_field_order_cnt; int frame_num; u32 pic_num; u16 longterm : 1; -- cgit v1.2.3 From 6cafdc8cc0da0ddffad25ca9c70bab990ab9130f Mon Sep 17 00:00:00 2001 From: Nicolas Dufresne Date: Fri, 13 May 2022 22:29:08 +0200 Subject: media: h264: Sort p/b reflist using frame_num In the reference list builder, frame_num refers to FrameNumWrap in the spec, which is the same as the pic_num for frame decoding. The same applies for long_term_pic_num and long_term_frame_idx. Sort all type of references by frame_num so the sort can be reused for fields reflist were the sorting is done using frame_num instead. In short, pic_num is never actually used for building reference lists. Signed-off-by: Nicolas Dufresne Reviewed-by: Sebastian Fricke Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-h264.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-h264.h b/include/media/v4l2-h264.h index 4cef717b3f18..0d9eaa956123 100644 --- a/include/media/v4l2-h264.h +++ b/include/media/v4l2-h264.h @@ -18,7 +18,6 @@ * @refs.top_field_order_cnt: top field order count * @refs.bottom_field_order_cnt: bottom field order count * @refs.frame_num: reference frame number - * @refs.pic_num: reference picture number * @refs.longterm: set to true for a long term reference * @refs: array of references * @cur_pic_order_count: picture order count of the frame being decoded @@ -36,7 +35,6 @@ struct v4l2_h264_reflist_builder { s32 top_field_order_cnt; s32 bottom_field_order_cnt; int frame_num; - u32 pic_num; u16 longterm : 1; } refs[V4L2_H264_NUM_DPB_ENTRIES]; -- cgit v1.2.3 From a03dacb0316f74400846aaf144d6c73f4217ca08 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Tue, 2 Mar 2021 15:58:21 +0900 Subject: PM / devfreq: Add cpu based scaling support to passive governor Many CPU architectures have caches that can scale independent of the CPUs. Frequency scaling of the caches is necessary to make sure that the cache is not a performance bottleneck that leads to poor performance and power. The same idea applies for RAM/DDR. To achieve this, this patch adds support for cpu based scaling to the passive governor. This is accomplished by taking the current frequency of each CPU frequency domain and then adjust the frequency of the cache (or any devfreq device) based on the frequency of the CPUs. It listens to CPU frequency transition notifiers to keep itself up to date on the current CPU frequency. To decide the frequency of the device, the governor does one of the following: * Derives the optimal devfreq device opp from required-opps property of the parent cpu opp_table. * Scales the device frequency in proportion to the CPU frequency. So, if the CPUs are running at their max frequency, the device runs at its max frequency. If the CPUs are running at their min frequency, the device runs at its min frequency. It is interpolated for frequencies in between. Tested-by: Chen-Yu Tsai Tested-by: Johnson Wang Signed-off-by: Saravana Kannan [Sibi: Integrated cpu-freqmap governor into passive_governor] Signed-off-by: Sibi Sankar [Chanwoo: Fix conflict with latest code and cleanup code] Signed-off-by: Chanwoo Choi --- include/linux/devfreq.h | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 142474b4af96..b1e4a6f796ce 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -38,6 +38,7 @@ enum devfreq_timer { struct devfreq; struct devfreq_governor; +struct devfreq_cpu_data; struct thermal_cooling_device; /** @@ -288,6 +289,11 @@ struct devfreq_simple_ondemand_data { #endif #if IS_ENABLED(CONFIG_DEVFREQ_GOV_PASSIVE) +enum devfreq_parent_dev_type { + DEVFREQ_PARENT_DEV, + CPUFREQ_PARENT_DEV, +}; + /** * struct devfreq_passive_data - ``void *data`` fed to struct devfreq * and devfreq_add_device @@ -299,8 +305,11 @@ struct devfreq_simple_ondemand_data { * using governors except for passive governor. * If the devfreq device has the specific method to decide * the next frequency, should use this callback. - * @this: the devfreq instance of own device. - * @nb: the notifier block for DEVFREQ_TRANSITION_NOTIFIER list + * @parent_type: the parent type of the device. + * @this: the devfreq instance of own device. + * @nb: the notifier block for DEVFREQ_TRANSITION_NOTIFIER or + * CPUFREQ_TRANSITION_NOTIFIER list. + * @parent_cpu_data: the state min/max/current frequency of all online cpu's. * * The devfreq_passive_data have to set the devfreq instance of parent * device with governors except for the passive governor. But, don't need to @@ -314,9 +323,13 @@ struct devfreq_passive_data { /* Optional callback to decide the next frequency of passvice device */ int (*get_target_freq)(struct devfreq *this, unsigned long *freq); + /* Should set the type of parent device */ + enum devfreq_parent_dev_type parent_type; + /* For passive governor's internal use. Don't need to set them */ struct devfreq *this; struct notifier_block nb; + struct devfreq_cpu_data *parent_cpu_data[NR_CPUS]; }; #endif -- cgit v1.2.3 From 26984d9d581e5049bd75091d2e789b9cc3ea12e0 Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Wed, 27 Apr 2022 03:49:19 +0900 Subject: PM / devfreq: passive: Keep cpufreq_policy for possible cpus The passive governor requires the cpu data to get the next target frequency of devfreq device if depending on cpu. In order to reduce the unnecessary memory data, keep cpufreq_policy data for possible cpus instead of NR_CPU. Tested-by: Chen-Yu Tsai Tested-by: Johnson Wang Signed-off-by: Chanwoo Choi --- include/linux/devfreq.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index b1e4a6f796ce..dc10bee75a72 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -309,7 +309,7 @@ enum devfreq_parent_dev_type { * @this: the devfreq instance of own device. * @nb: the notifier block for DEVFREQ_TRANSITION_NOTIFIER or * CPUFREQ_TRANSITION_NOTIFIER list. - * @parent_cpu_data: the state min/max/current frequency of all online cpu's. + * @cpu_data_list: the list of cpu frequency data for all cpufreq_policy. * * The devfreq_passive_data have to set the devfreq instance of parent * device with governors except for the passive governor. But, don't need to @@ -329,7 +329,7 @@ struct devfreq_passive_data { /* For passive governor's internal use. Don't need to set them */ struct devfreq *this; struct notifier_block nb; - struct devfreq_cpu_data *parent_cpu_data[NR_CPUS]; + struct list_head cpu_data_list; }; #endif -- cgit v1.2.3 From ee0e2f51e2115c2578d40e5a8ac33737984fe477 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 17 May 2022 12:43:46 +0200 Subject: cfg80211: fix kernel-doc for cfg80211_beacon_data The kernel-doc comment is formatted badly, resulting in a warning: include/net/cfg80211.h:1188: warning: bad line: [...] Fix that. Reported-by: Stephen Rothwell Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 97a5804ccdcf..cc8a9880b9d6 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1185,7 +1185,7 @@ struct cfg80211_mbssid_elems { * @civicloc_len: Civic location data length * @he_bss_color: BSS Color settings * @he_bss_color_valid: indicates whether bss color - attribute is present in beacon data or not. + * attribute is present in beacon data or not. */ struct cfg80211_beacon_data { const u8 *head, *tail; -- cgit v1.2.3 From f1b3b320bd6519b16e3480f74f2926d106e3bcba Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Mon, 16 May 2022 12:11:03 +0200 Subject: ASoC: Intel: avs: Generic soc component driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Prepare for concrete PCM operations over HDA, DMIC and I2S interfaces by providing generic soc component implementation. Interface-specific components re-use this code as majority of flow is shared. Signed-off-by: Amadeusz Sławiński Signed-off-by: Cezary Rojewski Link: https://lore.kernel.org/r/20220516101116.190192-3-cezary.rojewski@intel.com Signed-off-by: Mark Brown --- include/sound/soc-acpi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h index d33cf8df14b1..b38fd25c5729 100644 --- a/include/sound/soc-acpi.h +++ b/include/sound/soc-acpi.h @@ -156,6 +156,7 @@ struct snd_soc_acpi_link_adr { * @links: array of link _ADR descriptors, null terminated. * @drv_name: machine driver name * @fw_filename: firmware file name. Used when SOF is not enabled. + * @tplg_filename: topology file name. Used when SOF is not enabled. * @board: board name * @machine_quirk: pointer to quirk, usually based on DMI information when * ACPI ID alone is not sufficient, wrong or misleading @@ -174,6 +175,7 @@ struct snd_soc_acpi_mach { const struct snd_soc_acpi_link_adr *links; const char *drv_name; const char *fw_filename; + const char *tplg_filename; const char *board; struct snd_soc_acpi_mach * (*machine_quirk)(void *arg); const void *quirk_data; -- cgit v1.2.3 From 1affc44ea5dd554c103e0ce1e809f3aa5d942349 Mon Sep 17 00:00:00 2001 From: Cezary Rojewski Date: Mon, 16 May 2022 12:11:13 +0200 Subject: ASoC: Intel: avs: PCI driver implementation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit HD-Audio bus is a PCI device. Add all functions necessary to probe such device along with its removal sequence. Behaviour implemented for all standard operations is similar to existing solutions: sound/pci/hda and sound/soc/intel/skylake. Signed-off-by: Amadeusz Sławiński Signed-off-by: Cezary Rojewski Link: https://lore.kernel.org/r/20220516101116.190192-13-cezary.rojewski@intel.com Signed-off-by: Mark Brown --- include/sound/intel-dsp-config.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/intel-dsp-config.h b/include/sound/intel-dsp-config.h index d4609077c258..34c975910574 100644 --- a/include/sound/intel-dsp-config.h +++ b/include/sound/intel-dsp-config.h @@ -15,7 +15,8 @@ enum { SND_INTEL_DSP_DRIVER_LEGACY, SND_INTEL_DSP_DRIVER_SST, SND_INTEL_DSP_DRIVER_SOF, - SND_INTEL_DSP_DRIVER_LAST = SND_INTEL_DSP_DRIVER_SOF + SND_INTEL_DSP_DRIVER_AVS, + SND_INTEL_DSP_DRIVER_LAST = SND_INTEL_DSP_DRIVER_AVS }; #if IS_ENABLED(CONFIG_SND_INTEL_DSP_CONFIG) -- cgit v1.2.3 From 7c3e9fcad9c7d8bb5d69a576044fb16b1d2e8a01 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Pouiller?= Date: Tue, 17 May 2022 09:27:08 +0200 Subject: dma-buf: fix use of DMA_BUF_SET_NAME_{A,B} in userspace MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The typedefs u32 and u64 are not available in userspace. Thus user get an error he try to use DMA_BUF_SET_NAME_A or DMA_BUF_SET_NAME_B: $ gcc -Wall -c -MMD -c -o ioctls_list.o ioctls_list.c In file included from /usr/include/x86_64-linux-gnu/asm/ioctl.h:1, from /usr/include/linux/ioctl.h:5, from /usr/include/asm-generic/ioctls.h:5, from ioctls_list.c:11: ioctls_list.c:463:29: error: ‘u32’ undeclared here (not in a function) 463 | { "DMA_BUF_SET_NAME_A", DMA_BUF_SET_NAME_A, -1, -1 }, // linux/dma-buf.h | ^~~~~~~~~~~~~~~~~~ ioctls_list.c:464:29: error: ‘u64’ undeclared here (not in a function) 464 | { "DMA_BUF_SET_NAME_B", DMA_BUF_SET_NAME_B, -1, -1 }, // linux/dma-buf.h | ^~~~~~~~~~~~~~~~~~ The issue was initially reported here[1]. [1]: https://github.com/jerome-pouiller/ioctl/pull/14 Signed-off-by: Jérôme Pouiller Reviewed-by: Christian König Fixes: a5bff92eaac4 ("dma-buf: Fix SET_NAME ioctl uapi") CC: stable@vger.kernel.org Link: https://patchwork.freedesktop.org/patch/msgid/20220517072708.245265-1-Jerome.Pouiller@silabs.com Signed-off-by: Christian König --- include/uapi/linux/dma-buf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/dma-buf.h b/include/uapi/linux/dma-buf.h index 8e4a2ca0bcbf..b1523cb8ab30 100644 --- a/include/uapi/linux/dma-buf.h +++ b/include/uapi/linux/dma-buf.h @@ -92,7 +92,7 @@ struct dma_buf_sync { * between them in actual uapi, they're just different numbers. */ #define DMA_BUF_SET_NAME _IOW(DMA_BUF_BASE, 1, const char *) -#define DMA_BUF_SET_NAME_A _IOW(DMA_BUF_BASE, 1, u32) -#define DMA_BUF_SET_NAME_B _IOW(DMA_BUF_BASE, 1, u64) +#define DMA_BUF_SET_NAME_A _IOW(DMA_BUF_BASE, 1, __u32) +#define DMA_BUF_SET_NAME_B _IOW(DMA_BUF_BASE, 1, __u64) #endif -- cgit v1.2.3 From 1ad6c3b7ef132e1d8c5d606008069724625c8daf Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Tue, 5 Apr 2022 11:24:51 +0200 Subject: hwmon: introduce hwmon_sanitize_name() More and more drivers will check for bad characters in the hwmon name and all are using the same code snippet. Consolidate that code by adding a new hwmon_sanitize_name() function. Signed-off-by: Michael Walle Reviewed-by: Tom Rix Link: https://lore.kernel.org/r/20220405092452.4033674-2-michael@walle.cc Signed-off-by: Guenter Roeck --- include/linux/hwmon.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index eba380b76d15..4efaf06fd2b8 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -461,6 +461,9 @@ void devm_hwmon_device_unregister(struct device *dev); int hwmon_notify_event(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel); +char *hwmon_sanitize_name(const char *name); +char *devm_hwmon_sanitize_name(struct device *dev, const char *name); + /** * hwmon_is_bad_char - Is the char invalid in a hwmon name * @ch: the char to be considered -- cgit v1.2.3 From c8383054506c77b814489c09877b5db83fd4abf2 Mon Sep 17 00:00:00 2001 From: Jeffle Xu Date: Mon, 25 Apr 2022 20:21:24 +0800 Subject: cachefiles: notify the user daemon when looking up cookie Fscache/CacheFiles used to serve as a local cache for a remote networking fs. A new on-demand read mode will be introduced for CacheFiles, which can boost the scenario where on-demand read semantics are needed, e.g. container image distribution. The essential difference between these two modes is seen when a cache miss occurs: In the original mode, the netfs will fetch the data from the remote server and then write it to the cache file; in on-demand read mode, fetching the data and writing it into the cache is delegated to a user daemon. As the first step, notify the user daemon when looking up cookie. In this case, an anonymous fd is sent to the user daemon, through which the user daemon can write the fetched data to the cache file. Since the user daemon may move the anonymous fd around, e.g. through dup(), an object ID uniquely identifying the cache file is also attached. Also add one advisory flag (FSCACHE_ADV_WANT_CACHE_SIZE) suggesting that the cache file size shall be retrieved at runtime. This helps the scenario where one cache file contains multiple netfs files, e.g. for the purpose of deduplication. In this case, netfs itself has no idea the size of the cache file, whilst the user daemon should give the hint on it. Signed-off-by: Jeffle Xu Link: https://lore.kernel.org/r/20220509074028.74954-3-jefflexu@linux.alibaba.com Acked-by: David Howells Signed-off-by: Gao Xiang --- include/linux/fscache.h | 1 + include/trace/events/cachefiles.h | 2 ++ include/uapi/linux/cachefiles.h | 50 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 53 insertions(+) create mode 100644 include/uapi/linux/cachefiles.h (limited to 'include') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index e25539072463..72585c9729a2 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -39,6 +39,7 @@ struct fscache_cookie; #define FSCACHE_ADV_SINGLE_CHUNK 0x01 /* The object is a single chunk of data */ #define FSCACHE_ADV_WRITE_CACHE 0x00 /* Do cache if written to locally */ #define FSCACHE_ADV_WRITE_NOCACHE 0x02 /* Don't cache if written to locally */ +#define FSCACHE_ADV_WANT_CACHE_SIZE 0x04 /* Retrieve cache size at runtime */ #define FSCACHE_INVAL_DIO_WRITE 0x01 /* Invalidate due to DIO write */ diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index 311c14a20e70..93df9391bd7f 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -31,6 +31,8 @@ enum cachefiles_obj_ref_trace { cachefiles_obj_see_lookup_failed, cachefiles_obj_see_withdraw_cookie, cachefiles_obj_see_withdrawal, + cachefiles_obj_get_ondemand_fd, + cachefiles_obj_put_ondemand_fd, }; enum fscache_why_object_killed { diff --git a/include/uapi/linux/cachefiles.h b/include/uapi/linux/cachefiles.h new file mode 100644 index 000000000000..521f2fe4fe9c --- /dev/null +++ b/include/uapi/linux/cachefiles.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_CACHEFILES_H +#define _LINUX_CACHEFILES_H + +#include + +/* + * Fscache ensures that the maximum length of cookie key is 255. The volume key + * is controlled by netfs, and generally no bigger than 255. + */ +#define CACHEFILES_MSG_MAX_SIZE 1024 + +enum cachefiles_opcode { + CACHEFILES_OP_OPEN, +}; + +/* + * Message Header + * + * @msg_id a unique ID identifying this message + * @opcode message type, CACHEFILE_OP_* + * @len message length, including message header and following data + * @object_id a unique ID identifying a cache file + * @data message type specific payload + */ +struct cachefiles_msg { + __u32 msg_id; + __u32 opcode; + __u32 len; + __u32 object_id; + __u8 data[]; +}; + +/* + * @data contains the volume_key followed directly by the cookie_key. volume_key + * is a NUL-terminated string; @volume_key_size indicates the size of the volume + * key in bytes. cookie_key is binary data, which is netfs specific; + * @cookie_key_size indicates the size of the cookie key in bytes. + * + * @fd identifies an anon_fd referring to the cache file. + */ +struct cachefiles_open { + __u32 volume_key_size; + __u32 cookie_key_size; + __u32 fd; + __u32 flags; + __u8 data[]; +}; + +#endif -- cgit v1.2.3 From 324b954ac80cff0d11ddb6bde9b6631e45e98620 Mon Sep 17 00:00:00 2001 From: Jeffle Xu Date: Mon, 25 Apr 2022 20:21:26 +0800 Subject: cachefiles: notify the user daemon when withdrawing cookie Notify the user daemon that cookie is going to be withdrawn, providing a hint that the associated anonymous fd can be closed. Be noted that this is only a hint. The user daemon may close the associated anonymous fd when receiving the CLOSE request, then it will receive another anonymous fd when the cookie gets looked up. Or it may ignore the CLOSE request, and keep writing data through the anonymous fd. However the next time the cookie gets looked up, the user daemon will still receive another new anonymous fd. Signed-off-by: Jeffle Xu Acked-by: David Howells Link: https://lore.kernel.org/r/20220425122143.56815-5-jefflexu@linux.alibaba.com Signed-off-by: Gao Xiang --- include/uapi/linux/cachefiles.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/cachefiles.h b/include/uapi/linux/cachefiles.h index 521f2fe4fe9c..37a0071037c8 100644 --- a/include/uapi/linux/cachefiles.h +++ b/include/uapi/linux/cachefiles.h @@ -12,6 +12,7 @@ enum cachefiles_opcode { CACHEFILES_OP_OPEN, + CACHEFILES_OP_CLOSE, }; /* -- cgit v1.2.3 From 9032b6e8589f269743984aac53e82e4835be16dc Mon Sep 17 00:00:00 2001 From: Jeffle Xu Date: Mon, 25 Apr 2022 20:21:27 +0800 Subject: cachefiles: implement on-demand read Implement the data plane of on-demand read mode. The early implementation [1] place the entry to cachefiles_ondemand_read() in fscache_read(). However, fscache_read() can only detect if the requested file range is fully cache miss, whilst we need to notify the user daemon as long as there's a hole inside the requested file range. Thus the entry is now placed in cachefiles_prepare_read(). When working in on-demand read mode, once a hole detected, the read routine will send a READ request to the user daemon. The user daemon needs to fetch the data and write it to the cache file. After sending the READ request, the read routine will hang there, until the READ request is handled by the user daemon. Then it will retry to read from the same file range. If no progress encountered, the read routine will fail then. A new NETFS_SREQ_ONDEMAND flag is introduced to indicate that on-demand read should be done when a cache miss encountered. [1] https://lore.kernel.org/all/20220406075612.60298-6-jefflexu@linux.alibaba.com/ #v8 Signed-off-by: Jeffle Xu Acked-by: David Howells Link: https://lore.kernel.org/r/20220425122143.56815-6-jefflexu@linux.alibaba.com Signed-off-by: Gao Xiang --- include/linux/netfs.h | 1 + include/uapi/linux/cachefiles.h | 17 +++++++++++++++++ 2 files changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index c7bf1eaf51d5..057d04efaf79 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -159,6 +159,7 @@ struct netfs_io_subrequest { #define NETFS_SREQ_SHORT_IO 2 /* Set if the I/O was short */ #define NETFS_SREQ_SEEK_DATA_READ 3 /* Set if ->read() should SEEK_DATA first */ #define NETFS_SREQ_NO_PROGRESS 4 /* Set if we didn't manage to read any data */ +#define NETFS_SREQ_ONDEMAND 5 /* Set if it's from on-demand read mode */ }; enum netfs_io_origin { diff --git a/include/uapi/linux/cachefiles.h b/include/uapi/linux/cachefiles.h index 37a0071037c8..78caa73e5343 100644 --- a/include/uapi/linux/cachefiles.h +++ b/include/uapi/linux/cachefiles.h @@ -3,6 +3,7 @@ #define _LINUX_CACHEFILES_H #include +#include /* * Fscache ensures that the maximum length of cookie key is 255. The volume key @@ -13,6 +14,7 @@ enum cachefiles_opcode { CACHEFILES_OP_OPEN, CACHEFILES_OP_CLOSE, + CACHEFILES_OP_READ, }; /* @@ -48,4 +50,19 @@ struct cachefiles_open { __u8 data[]; }; +/* + * @off indicates the starting offset of the requested file range + * @len indicates the length of the requested file range + */ +struct cachefiles_read { + __u64 off; + __u64 len; +}; + +/* + * Reply for READ request + * @arg for this ioctl is the @id field of READ request. + */ +#define CACHEFILES_IOC_READ_COMPLETE _IOW(0x98, 1, int) + #endif -- cgit v1.2.3 From 1519670e4fecc6063fa2f0c10f0666d3331f219b Mon Sep 17 00:00:00 2001 From: Jeffle Xu Date: Mon, 25 Apr 2022 20:21:29 +0800 Subject: cachefiles: add tracepoints for on-demand read mode Add tracepoints for on-demand read mode. Currently following tracepoints are added: OPEN request / COPEN reply CLOSE request READ request / CREAD reply write through anonymous fd release of anonymous fd Signed-off-by: Jeffle Xu Acked-by: David Howells Link: https://lore.kernel.org/r/20220425122143.56815-8-jefflexu@linux.alibaba.com Signed-off-by: Gao Xiang --- include/trace/events/cachefiles.h | 174 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 174 insertions(+) (limited to 'include') diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index 93df9391bd7f..d8d4d73fe7b6 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -673,6 +673,180 @@ TRACE_EVENT(cachefiles_io_error, __entry->error) ); +TRACE_EVENT(cachefiles_ondemand_open, + TP_PROTO(struct cachefiles_object *obj, struct cachefiles_msg *msg, + struct cachefiles_open *load), + + TP_ARGS(obj, msg, load), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + __field(unsigned int, object_id ) + __field(unsigned int, fd ) + __field(unsigned int, flags ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg->msg_id; + __entry->object_id = msg->object_id; + __entry->fd = load->fd; + __entry->flags = load->flags; + ), + + TP_printk("o=%08x mid=%x oid=%x fd=%d f=%x", + __entry->obj, + __entry->msg_id, + __entry->object_id, + __entry->fd, + __entry->flags) + ); + +TRACE_EVENT(cachefiles_ondemand_copen, + TP_PROTO(struct cachefiles_object *obj, unsigned int msg_id, + long len), + + TP_ARGS(obj, msg_id, len), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + __field(long, len ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg_id; + __entry->len = len; + ), + + TP_printk("o=%08x mid=%x l=%lx", + __entry->obj, + __entry->msg_id, + __entry->len) + ); + +TRACE_EVENT(cachefiles_ondemand_close, + TP_PROTO(struct cachefiles_object *obj, struct cachefiles_msg *msg), + + TP_ARGS(obj, msg), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + __field(unsigned int, object_id ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg->msg_id; + __entry->object_id = msg->object_id; + ), + + TP_printk("o=%08x mid=%x oid=%x", + __entry->obj, + __entry->msg_id, + __entry->object_id) + ); + +TRACE_EVENT(cachefiles_ondemand_read, + TP_PROTO(struct cachefiles_object *obj, struct cachefiles_msg *msg, + struct cachefiles_read *load), + + TP_ARGS(obj, msg, load), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + __field(unsigned int, object_id ) + __field(loff_t, start ) + __field(size_t, len ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg->msg_id; + __entry->object_id = msg->object_id; + __entry->start = load->off; + __entry->len = load->len; + ), + + TP_printk("o=%08x mid=%x oid=%x s=%llx l=%zx", + __entry->obj, + __entry->msg_id, + __entry->object_id, + __entry->start, + __entry->len) + ); + +TRACE_EVENT(cachefiles_ondemand_cread, + TP_PROTO(struct cachefiles_object *obj, unsigned int msg_id), + + TP_ARGS(obj, msg_id), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, msg_id ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->msg_id = msg_id; + ), + + TP_printk("o=%08x mid=%x", + __entry->obj, + __entry->msg_id) + ); + +TRACE_EVENT(cachefiles_ondemand_fd_write, + TP_PROTO(struct cachefiles_object *obj, struct inode *backer, + loff_t start, size_t len), + + TP_ARGS(obj, backer, start, len), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, backer ) + __field(loff_t, start ) + __field(size_t, len ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->backer = backer->i_ino; + __entry->start = start; + __entry->len = len; + ), + + TP_printk("o=%08x iB=%x s=%llx l=%zx", + __entry->obj, + __entry->backer, + __entry->start, + __entry->len) + ); + +TRACE_EVENT(cachefiles_ondemand_fd_release, + TP_PROTO(struct cachefiles_object *obj, int object_id), + + TP_ARGS(obj, object_id), + + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(unsigned int, object_id ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->object_id = object_id; + ), + + TP_printk("o=%08x oid=%x", + __entry->obj, + __entry->object_id) + ); + #endif /* _TRACE_CACHEFILES_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 7b8b44eb7710e34a1ea5278392417993a549fabf Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 14 May 2022 10:36:58 -0400 Subject: NFSv4: Specify the type of ACL to cache When caching a NFSv4 ACL, we want to specify whether we are caching an NFSv4.0 type acl, the NFSv4.1 dacl or the NFSv4.1 sacl. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/nfs4.h | 2 ++ include/linux/nfs_xdr.h | 7 +++++++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 5662d8be04eb..8d04b6a5964c 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -451,6 +451,8 @@ enum lock_type4 { #define FATTR4_WORD1_TIME_MODIFY (1UL << 21) #define FATTR4_WORD1_TIME_MODIFY_SET (1UL << 22) #define FATTR4_WORD1_MOUNTED_ON_FILEID (1UL << 23) +#define FATTR4_WORD1_DACL (1UL << 26) +#define FATTR4_WORD1_SACL (1UL << 27) #define FATTR4_WORD1_FS_LAYOUT_TYPES (1UL << 30) #define FATTR4_WORD2_LAYOUT_TYPES (1UL << 0) #define FATTR4_WORD2_LAYOUT_BLKSIZE (1UL << 1) diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 2863e5a69c6a..13d068c57d8d 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -800,6 +800,13 @@ struct nfs_setattrargs { const struct nfs4_label *label; }; +enum nfs4_acl_type { + NFS4ACL_NONE = 0, + NFS4ACL_ACL, + NFS4ACL_DACL, + NFS4ACL_SACL, +}; + struct nfs_setaclargs { struct nfs4_sequence_args seq_args; struct nfs_fh * fh; -- cgit v1.2.3 From db145db021abf75aa1a5810e631425055cfbed47 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 14 May 2022 10:36:59 -0400 Subject: NFSv4: Add encoders/decoders for the NFSv4.1 dacl and sacl attributes Add the ability to set or retrieve the acl using the NFSv4.1 'dacl' and 'sacl' attributes to the NFSv4 xdr encoders/decoders. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- include/linux/nfs_xdr.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 13d068c57d8d..4a8ba84f848e 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -810,6 +810,7 @@ enum nfs4_acl_type { struct nfs_setaclargs { struct nfs4_sequence_args seq_args; struct nfs_fh * fh; + enum nfs4_acl_type acl_type; size_t acl_len; struct page ** acl_pages; }; @@ -821,6 +822,7 @@ struct nfs_setaclres { struct nfs_getaclargs { struct nfs4_sequence_args seq_args; struct nfs_fh * fh; + enum nfs4_acl_type acl_type; size_t acl_len; struct page ** acl_pages; }; @@ -829,6 +831,7 @@ struct nfs_getaclargs { #define NFS4_ACL_TRUNC 0x0001 /* ACL was truncated */ struct nfs_getaclres { struct nfs4_sequence_res seq_res; + enum nfs4_acl_type acl_type; size_t acl_len; size_t acl_data_offset; int acl_flags; -- cgit v1.2.3 From c81d5bae404abc6b257667e84d39b9b50c7063d4 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Fri, 6 May 2022 13:34:41 -0700 Subject: f2fs: do not stop GC when requiring a free section The f2fs_gc uses a bitmap to indicate pinned sections, but when disabling chckpoint, we call f2fs_gc() with NULL_SEGNO which selects the same dirty segment as a victim all the time, resulting in checkpoint=disable failure, for example. Let's pick another one, if we fail to collect it. Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/trace/events/f2fs.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 54ec9e543f09..16c67ede85b6 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -645,18 +645,21 @@ TRACE_EVENT(f2fs_background_gc, TRACE_EVENT(f2fs_gc_begin, TP_PROTO(struct super_block *sb, int gc_type, bool no_bg_gc, + unsigned int nr_free_secs, long long dirty_nodes, long long dirty_dents, long long dirty_imeta, unsigned int free_sec, unsigned int free_seg, int reserved_seg, unsigned int prefree_seg), - TP_ARGS(sb, gc_type, no_bg_gc, dirty_nodes, dirty_dents, dirty_imeta, + TP_ARGS(sb, gc_type, no_bg_gc, nr_free_secs, dirty_nodes, + dirty_dents, dirty_imeta, free_sec, free_seg, reserved_seg, prefree_seg), TP_STRUCT__entry( __field(dev_t, dev) __field(int, gc_type) __field(bool, no_bg_gc) + __field(unsigned int, nr_free_secs) __field(long long, dirty_nodes) __field(long long, dirty_dents) __field(long long, dirty_imeta) @@ -670,6 +673,7 @@ TRACE_EVENT(f2fs_gc_begin, __entry->dev = sb->s_dev; __entry->gc_type = gc_type; __entry->no_bg_gc = no_bg_gc; + __entry->nr_free_secs = nr_free_secs; __entry->dirty_nodes = dirty_nodes; __entry->dirty_dents = dirty_dents; __entry->dirty_imeta = dirty_imeta; @@ -679,12 +683,13 @@ TRACE_EVENT(f2fs_gc_begin, __entry->prefree_seg = prefree_seg; ), - TP_printk("dev = (%d,%d), gc_type = %s, no_background_GC = %d, nodes = %lld, " - "dents = %lld, imeta = %lld, free_sec:%u, free_seg:%u, " + TP_printk("dev = (%d,%d), gc_type = %s, no_background_GC = %d, nr_free_secs = %u, " + "nodes = %lld, dents = %lld, imeta = %lld, free_sec:%u, free_seg:%u, " "rsv_seg:%d, prefree_seg:%u", show_dev(__entry->dev), show_gc_type(__entry->gc_type), (__entry->gc_type == BG_GC) ? __entry->no_bg_gc : -1, + __entry->nr_free_secs, __entry->dirty_nodes, __entry->dirty_dents, __entry->dirty_imeta, -- cgit v1.2.3 From 69e9cd66ae1392437234a63a3a1d60b6655f92ef Mon Sep 17 00:00:00 2001 From: Julian Orth Date: Tue, 17 May 2022 12:32:53 +0200 Subject: audit,io_uring,io-wq: call __audit_uring_exit for dummy contexts Not calling the function for dummy contexts will cause the context to not be reset. During the next syscall, this will cause an error in __audit_syscall_entry: WARN_ON(context->context != AUDIT_CTX_UNUSED); WARN_ON(context->name_count); if (context->context != AUDIT_CTX_UNUSED || context->name_count) { audit_panic("unrecoverable error in audit_syscall_entry()"); return; } These problematic dummy contexts are created via the following call chain: exit_to_user_mode_prepare -> arch_do_signal_or_restart -> get_signal -> task_work_run -> tctx_task_work -> io_req_task_submit -> io_issue_sqe -> audit_uring_entry Cc: stable@vger.kernel.org Fixes: 5bd2182d58e9 ("audit,io_uring,io-wq: add some basic audit support to io_uring") Signed-off-by: Julian Orth [PM: subject line tweaks] Signed-off-by: Paul Moore --- include/linux/audit.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/audit.h b/include/linux/audit.h index d06134ac6245..cece70231138 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -339,7 +339,7 @@ static inline void audit_uring_entry(u8 op) } static inline void audit_uring_exit(int success, long code) { - if (unlikely(!audit_dummy_context())) + if (unlikely(audit_context())) __audit_uring_exit(success, code); } static inline void audit_syscall_entry(int major, unsigned long a0, -- cgit v1.2.3 From 0aa7be05d83cc584da0782405e8007e351dfb6cc Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Sun, 15 May 2022 20:42:03 +0200 Subject: locking/atomic: Add generic try_cmpxchg64 support Add generic support for try_cmpxchg64{,_acquire,_release,_relaxed} and their falbacks involving cmpxchg64. Signed-off-by: Uros Bizjak Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20220515184205.103089-2-ubizjak@gmail.com --- include/linux/atomic/atomic-arch-fallback.h | 72 ++++++++++++++++++++++++++++- include/linux/atomic/atomic-instrumented.h | 40 +++++++++++++++- 2 files changed, 110 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index 6db58d180866..77bc5522e61c 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -147,6 +147,76 @@ #endif /* arch_try_cmpxchg_relaxed */ +#ifndef arch_try_cmpxchg64_relaxed +#ifdef arch_try_cmpxchg64 +#define arch_try_cmpxchg64_acquire arch_try_cmpxchg64 +#define arch_try_cmpxchg64_release arch_try_cmpxchg64 +#define arch_try_cmpxchg64_relaxed arch_try_cmpxchg64 +#endif /* arch_try_cmpxchg64 */ + +#ifndef arch_try_cmpxchg64 +#define arch_try_cmpxchg64(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64 */ + +#ifndef arch_try_cmpxchg64_acquire +#define arch_try_cmpxchg64_acquire(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64_acquire((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64_acquire */ + +#ifndef arch_try_cmpxchg64_release +#define arch_try_cmpxchg64_release(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64_release((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64_release */ + +#ifndef arch_try_cmpxchg64_relaxed +#define arch_try_cmpxchg64_relaxed(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64_relaxed((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64_relaxed */ + +#else /* arch_try_cmpxchg64_relaxed */ + +#ifndef arch_try_cmpxchg64_acquire +#define arch_try_cmpxchg64_acquire(...) \ + __atomic_op_acquire(arch_try_cmpxchg64, __VA_ARGS__) +#endif + +#ifndef arch_try_cmpxchg64_release +#define arch_try_cmpxchg64_release(...) \ + __atomic_op_release(arch_try_cmpxchg64, __VA_ARGS__) +#endif + +#ifndef arch_try_cmpxchg64 +#define arch_try_cmpxchg64(...) \ + __atomic_op_fence(arch_try_cmpxchg64, __VA_ARGS__) +#endif + +#endif /* arch_try_cmpxchg64_relaxed */ + #ifndef arch_atomic_read_acquire static __always_inline int arch_atomic_read_acquire(const atomic_t *v) @@ -2386,4 +2456,4 @@ arch_atomic64_dec_if_positive(atomic64_t *v) #endif #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// 8e2cc06bc0d2c0967d2f8424762bd48555ee40ae +// b5e87bdd5ede61470c29f7a7e4de781af3770f09 diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index 5d69b143c28e..7a139ec030b0 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -2006,6 +2006,44 @@ atomic_long_dec_if_positive(atomic_long_t *v) arch_try_cmpxchg_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) +#define try_cmpxchg64(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + kcsan_mb(); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg64_acquire(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg64_release(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + kcsan_release(); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg64_relaxed(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + #define cmpxchg_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ @@ -2045,4 +2083,4 @@ atomic_long_dec_if_positive(atomic_long_t *v) }) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// 87c974b93032afd42143613434d1a7788fa598f9 +// 764f741eb77a7ad565dc8d99ce2837d5542e8aee -- cgit v1.2.3 From 42c4e3f670b97df0c9e23ca2f7080ff7cd591837 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 3 May 2022 14:19:24 -0700 Subject: interconnect: qcom: sc8180x: Fix QUP0 nodes The QUP0 BCM relates to some internal property of the QUPs, and should be configured independently of the path to the QUP. In line with other platforms expose QUP_CORE endpoints in order allow this configuration. Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20220503211925.1022169-4-bjorn.andersson@linaro.org Signed-off-by: Georgi Djakov --- include/dt-bindings/interconnect/qcom,sc8180x.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/interconnect/qcom,sc8180x.h b/include/dt-bindings/interconnect/qcom,sc8180x.h index 235b525d2803..e84cfec5afdd 100644 --- a/include/dt-bindings/interconnect/qcom,sc8180x.h +++ b/include/dt-bindings/interconnect/qcom,sc8180x.h @@ -182,4 +182,11 @@ #define SLAVE_MNOC_SF_MEM_NOC_DISPLAY 3 #define SLAVE_MNOC_HF_MEM_NOC_DISPLAY 4 +#define MASTER_QUP_CORE_0 0 +#define MASTER_QUP_CORE_1 1 +#define MASTER_QUP_CORE_2 2 +#define SLAVE_QUP_CORE_0 3 +#define SLAVE_QUP_CORE_1 4 +#define SLAVE_QUP_CORE_2 5 + #endif -- cgit v1.2.3 From bec67592521ec816371f5f072b1a340e1c2ad434 Mon Sep 17 00:00:00 2001 From: Min Li Date: Mon, 16 May 2022 10:47:06 -0400 Subject: ptp: ptp_clockmatrix: Add PTP_CLK_REQ_EXTTS support Use TOD_READ_SECONDARY for extts to keep TOD_READ_PRIMARY for gettime and settime exclusively. Before this change, TOD_READ_PRIMARY was used for both extts and gettime/settime, which would result in changing TOD read/write triggers between operations. Using TOD_READ_SECONDARY would make extts independent of gettime/settime operation Signed-off-by: Min Li Acked-by: Richard Cochran Link: https://lore.kernel.org/r/1652712427-14703-1-git-send-email-min.li.xe@renesas.com Signed-off-by: Jakub Kicinski --- include/linux/mfd/idt8a340_reg.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mfd/idt8a340_reg.h b/include/linux/mfd/idt8a340_reg.h index a18c1539a152..0c706085c205 100644 --- a/include/linux/mfd/idt8a340_reg.h +++ b/include/linux/mfd/idt8a340_reg.h @@ -407,7 +407,7 @@ #define TOD_READ_PRIMARY_0 0xcc40 #define TOD_READ_PRIMARY_0_V520 0xcc50 /* 8-bit subns, 32-bit ns, 48-bit seconds */ -#define TOD_READ_PRIMARY 0x0000 +#define TOD_READ_PRIMARY_BASE 0x0000 /* Counter increments after TOD write is completed */ #define TOD_READ_PRIMARY_COUNTER 0x000b /* Read trigger configuration */ @@ -424,6 +424,16 @@ #define TOD_READ_SECONDARY_0 0xcc90 #define TOD_READ_SECONDARY_0_V520 0xcca0 +/* 8-bit subns, 32-bit ns, 48-bit seconds */ +#define TOD_READ_SECONDARY_BASE 0x0000 +/* Counter increments after TOD write is completed */ +#define TOD_READ_SECONDARY_COUNTER 0x000b +/* Read trigger configuration */ +#define TOD_READ_SECONDARY_SEL_CFG_0 0x000c +/* Read trigger selection */ +#define TOD_READ_SECONDARY_CMD 0x000e +#define TOD_READ_SECONDARY_CMD_V520 0x000f + #define TOD_READ_SECONDARY_1 0xcca0 #define TOD_READ_SECONDARY_1_V520 0xccb0 #define TOD_READ_SECONDARY_2 0xccb0 -- cgit v1.2.3 From 1d2c717bc7f7fd3c9cf38d4a0d5d7ede06adf05b Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Fri, 13 May 2022 06:19:31 +0300 Subject: net/mlx5: Add last command failure syndrome to debugfs Add syndrome of last command failure per command type to debugfs to ease debugging of such failure. last_failed_syndrome - last command failed syndrome returned by FW. Signed-off-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index d6bac3976913..74c8cfb771a2 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -272,6 +272,8 @@ struct mlx5_cmd_stats { u32 last_failed_errno; /* last bad status returned by FW */ u8 last_failed_mbox_status; + /* last command failed syndrome returned by FW */ + u32 last_failed_syndrome; struct dentry *root; /* protect command average calculations */ spinlock_t lock; -- cgit v1.2.3 From 9b45bde82c229fda94618896ff530dcba9d66fe0 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Tue, 25 Jan 2022 14:47:36 +0200 Subject: net/mlx5: Inline db alloc API function Take the wrapper version which picks default node into a header file. This reduces the number of exported functions. Signed-off-by: Tariq Toukan Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 74c8cfb771a2..b064bc278f52 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1053,9 +1053,14 @@ int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in, void *data_out, int size_out, u16 reg_num, int arg, int write); -int mlx5_db_alloc(struct mlx5_core_dev *dev, struct mlx5_db *db); int mlx5_db_alloc_node(struct mlx5_core_dev *dev, struct mlx5_db *db, int node); + +static inline int mlx5_db_alloc(struct mlx5_core_dev *dev, struct mlx5_db *db) +{ + return mlx5_db_alloc_node(dev, db, dev->priv.numa_node); +} + void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db); const char *mlx5_command_str(int command); -- cgit v1.2.3 From 94db3317781922ba52722c58061e0e8517d4d80d Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Mon, 31 Jan 2022 07:49:51 +0200 Subject: net/mlx5: Support multiport eswitch mode Multiport eswitch mode is a LAG mode that allows to add rules that forward traffic to a specific physical port without being affected by LAG affinity configuration. This mode of operation is mutual exclusive with the other LAG modes used by multipath and bonding. To make the transition between the modes, we maintain a counter on the number of rules specifying one of the uplink representors as the target of mirred egress redirect action. An example of such rule would be: $ tc filter add dev enp8s0f0_0 prot all root flower dst_mac \ 00:11:22:33:44:55 action mirred egress redirect dev enp8s0f0 If the reference count just grows to one and LAG is not in use, we create the LAG in multiport eswitch mode. Other mode changes are not allowed while in this mode. When the reference count reaches zero, we destroy the LAG and let other modes be used if needed. logic also changed such that if forwarding to some uplink destination cannot be guaranteed, we fail the operation so the rule will eventually be in software and not in hardware. Signed-off-by: Eli Cohen Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 7bab3e51c61e..78b3d3465dd7 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1359,7 +1359,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 vhca_resource_manager[0x1]; u8 hca_cap_2[0x1]; - u8 reserved_at_21[0x1]; + u8 create_lag_when_not_master_up[0x1]; u8 dtor[0x1]; u8 event_on_vhca_state_teardown_request[0x1]; u8 event_on_vhca_state_in_use[0x1]; @@ -10816,7 +10816,8 @@ struct mlx5_ifc_dcbx_param_bits { enum { MLX5_LAG_PORT_SELECT_MODE_QUEUE_AFFINITY = 0, - MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_FT, + MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_FT = 1, + MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_MPESW = 2, }; struct mlx5_ifc_lagc_bits { -- cgit v1.2.3 From 41929c9f628b9990d33a200c54bb0c919e089aa8 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 6 Apr 2022 22:55:05 +0200 Subject: clocksource/drivers/ixp4xx: Drop boardfile probe path The boardfiles for IXP4xx have been deleted. Delete all the quirks and code dealing with that boot path and rely solely on device tree boot. Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20220406205505.2332821-1-linus.walleij@linaro.org Signed-off-by: Daniel Lezcano --- include/linux/platform_data/timer-ixp4xx.h | 11 ----------- 1 file changed, 11 deletions(-) delete mode 100644 include/linux/platform_data/timer-ixp4xx.h (limited to 'include') diff --git a/include/linux/platform_data/timer-ixp4xx.h b/include/linux/platform_data/timer-ixp4xx.h deleted file mode 100644 index ee92ae7edaed..000000000000 --- a/include/linux/platform_data/timer-ixp4xx.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __TIMER_IXP4XX_H -#define __TIMER_IXP4XX_H - -#include - -void __init ixp4xx_timer_setup(resource_size_t timerbase, - int timer_irq, - unsigned int timer_freq); - -#endif -- cgit v1.2.3 From c7fb19428d67dd0a2a78a4f237af01d39c78dc5a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 30 Apr 2022 14:38:53 -0600 Subject: io_uring: add support for ring mapped supplied buffers Provided buffers allow an application to supply io_uring with buffers that can then be grabbed for a read/receive request, when the data source is ready to deliver data. The existing scheme relies on using IORING_OP_PROVIDE_BUFFERS to do that, but it can be difficult to use in real world applications. It's pretty efficient if the application is able to supply back batches of provided buffers when they have been consumed and the application is ready to recycle them, but if fragmentation occurs in the buffer space, it can become difficult to supply enough buffers at the time. This hurts efficiency. Add a register op, IORING_REGISTER_PBUF_RING, which allows an application to setup a shared queue for each buffer group of provided buffers. The application can then supply buffers simply by adding them to this ring, and the kernel can consume then just as easily. The ring shares the head with the application, the tail remains private in the kernel. Provided buffers setup with IORING_REGISTER_PBUF_RING cannot use IORING_OP_{PROVIDE,REMOVE}_BUFFERS for adding or removing entries to the ring, they must use the mapped ring. Mapped provided buffer rings can co-exist with normal provided buffers, just not within the same group ID. To gauge overhead of the existing scheme and evaluate the mapped ring approach, a simple NOP benchmark was written. It uses a ring of 128 entries, and submits/completes 32 at the time. 'Replenish' is how many buffers are provided back at the time after they have been consumed: Test Replenish NOPs/sec ================================================================ No provided buffers NA ~30M Provided buffers 32 ~16M Provided buffers 1 ~10M Ring buffers 32 ~27M Ring buffers 1 ~27M The ring mapped buffers perform almost as well as not using provided buffers at all, and they don't care if you provided 1 or more back at the same time. This means application can just replenish as they go, rather than need to batch and compact, further reducing overhead in the application. The NOP benchmark above doesn't need to do any compaction, so that overhead isn't even reflected in the above test. Co-developed-by: Dylan Yudaken Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 15f821af9242..ddf969ae5a79 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -384,6 +384,10 @@ enum { IORING_REGISTER_RING_FDS = 20, IORING_UNREGISTER_RING_FDS = 21, + /* register ring based provide buffer group */ + IORING_REGISTER_PBUF_RING = 22, + IORING_UNREGISTER_PBUF_RING = 23, + /* this goes last */ IORING_REGISTER_LAST }; @@ -461,6 +465,38 @@ struct io_uring_restriction { __u32 resv2[3]; }; +struct io_uring_buf { + __u64 addr; + __u32 len; + __u16 bid; + __u16 resv; +}; + +struct io_uring_buf_ring { + union { + /* + * To avoid spilling into more pages than we need to, the + * ring tail is overlaid with the io_uring_buf->resv field. + */ + struct { + __u64 resv1; + __u32 resv2; + __u16 resv3; + __u16 tail; + }; + struct io_uring_buf bufs[0]; + }; +}; + +/* argument for IORING_(UN)REGISTER_PBUF_RING */ +struct io_uring_buf_reg { + __u64 ring_addr; + __u32 ring_entries; + __u16 bgid; + __u16 pad; + __u64 resv[3]; +}; + /* * io_uring_restriction->opcode values */ -- cgit v1.2.3 From 14362a2541797cf9df0e86fb12dcd7950baf566e Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 11 May 2022 22:02:12 +0300 Subject: fsnotify: introduce mark type iterator fsnotify_foreach_iter_mark_type() is used to reduce boilerplate code of iterating all marks of a specific group interested in an event by consulting the iterator report_mask. Use an open coded version of that iterator in fsnotify_iter_next() that collects all marks of the current iteration group without consulting the iterator report_mask. At the moment, the two iterator variants are the same, but this decoupling will allow us to exclude some of the group's marks from reporting the event, for example for event on child and inode marks on parent did not request to watch events on children. Fixes: 2f02fd3fa13e ("fanotify: fix ignore mask logic for events on child and on dir") Reported-by: Jan Kara Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20220511190213.831646-2-amir73il@gmail.com --- include/linux/fsnotify_backend.h | 31 ++++++++++++++++++++++++------- 1 file changed, 24 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 9a1a9e78f69f..9560734759fa 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -399,6 +399,7 @@ static inline bool fsnotify_valid_obj_type(unsigned int obj_type) struct fsnotify_iter_info { struct fsnotify_mark *marks[FSNOTIFY_ITER_TYPE_COUNT]; + struct fsnotify_group *current_group; unsigned int report_mask; int srcu_idx; }; @@ -415,20 +416,31 @@ static inline void fsnotify_iter_set_report_type( iter_info->report_mask |= (1U << iter_type); } -static inline void fsnotify_iter_set_report_type_mark( - struct fsnotify_iter_info *iter_info, int iter_type, - struct fsnotify_mark *mark) +static inline struct fsnotify_mark *fsnotify_iter_mark( + struct fsnotify_iter_info *iter_info, int iter_type) { - iter_info->marks[iter_type] = mark; - iter_info->report_mask |= (1U << iter_type); + if (fsnotify_iter_should_report_type(iter_info, iter_type)) + return iter_info->marks[iter_type]; + return NULL; +} + +static inline int fsnotify_iter_step(struct fsnotify_iter_info *iter, int type, + struct fsnotify_mark **markp) +{ + while (type < FSNOTIFY_ITER_TYPE_COUNT) { + *markp = fsnotify_iter_mark(iter, type); + if (*markp) + break; + type++; + } + return type; } #define FSNOTIFY_ITER_FUNCS(name, NAME) \ static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \ struct fsnotify_iter_info *iter_info) \ { \ - return (iter_info->report_mask & (1U << FSNOTIFY_ITER_TYPE_##NAME)) ? \ - iter_info->marks[FSNOTIFY_ITER_TYPE_##NAME] : NULL; \ + return fsnotify_iter_mark(iter_info, FSNOTIFY_ITER_TYPE_##NAME); \ } FSNOTIFY_ITER_FUNCS(inode, INODE) @@ -438,6 +450,11 @@ FSNOTIFY_ITER_FUNCS(sb, SB) #define fsnotify_foreach_iter_type(type) \ for (type = 0; type < FSNOTIFY_ITER_TYPE_COUNT; type++) +#define fsnotify_foreach_iter_mark_type(iter, mark, type) \ + for (type = 0; \ + type = fsnotify_iter_step(iter, type, &mark), \ + type < FSNOTIFY_ITER_TYPE_COUNT; \ + type++) /* * fsnotify_connp_t is what we embed in objects which connector can be attached -- cgit v1.2.3 From e73aaae2fa9024832e1f42e30c787c7baf61d014 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Sat, 7 May 2022 14:03:46 +0200 Subject: siphash: use one source of truth for siphash permutations The SipHash family of permutations is currently used in three places: - siphash.c itself, used in the ordinary way it was intended. - random32.c, in a construction from an anonymous contributor. - random.c, as part of its fast_mix function. Each one of these places reinvents the wheel with the same C code, same rotation constants, and same symmetry-breaking constants. This commit tidies things up a bit by placing macros for the permutations and constants into siphash.h, where each of the three .c users can access them. It also leaves a note dissuading more users of them from emerging. Signed-off-by: Jason A. Donenfeld --- include/linux/prandom.h | 23 +++++++---------------- include/linux/siphash.h | 28 ++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/linux/prandom.h b/include/linux/prandom.h index 056d31317e49..a4aadd2dc153 100644 --- a/include/linux/prandom.h +++ b/include/linux/prandom.h @@ -10,6 +10,7 @@ #include #include +#include u32 prandom_u32(void); void prandom_bytes(void *buf, size_t nbytes); @@ -27,15 +28,10 @@ DECLARE_PER_CPU(unsigned long, net_rand_noise); * The core SipHash round function. Each line can be executed in * parallel given enough CPU resources. */ -#define PRND_SIPROUND(v0, v1, v2, v3) ( \ - v0 += v1, v1 = rol64(v1, 13), v2 += v3, v3 = rol64(v3, 16), \ - v1 ^= v0, v0 = rol64(v0, 32), v3 ^= v2, \ - v0 += v3, v3 = rol64(v3, 21), v2 += v1, v1 = rol64(v1, 17), \ - v3 ^= v0, v1 ^= v2, v2 = rol64(v2, 32) \ -) +#define PRND_SIPROUND(v0, v1, v2, v3) SIPHASH_PERMUTATION(v0, v1, v2, v3) -#define PRND_K0 (0x736f6d6570736575 ^ 0x6c7967656e657261) -#define PRND_K1 (0x646f72616e646f6d ^ 0x7465646279746573) +#define PRND_K0 (SIPHASH_CONST_0 ^ SIPHASH_CONST_2) +#define PRND_K1 (SIPHASH_CONST_1 ^ SIPHASH_CONST_3) #elif BITS_PER_LONG == 32 /* @@ -43,14 +39,9 @@ DECLARE_PER_CPU(unsigned long, net_rand_noise); * This is weaker, but 32-bit machines are not used for high-traffic * applications, so there is less output for an attacker to analyze. */ -#define PRND_SIPROUND(v0, v1, v2, v3) ( \ - v0 += v1, v1 = rol32(v1, 5), v2 += v3, v3 = rol32(v3, 8), \ - v1 ^= v0, v0 = rol32(v0, 16), v3 ^= v2, \ - v0 += v3, v3 = rol32(v3, 7), v2 += v1, v1 = rol32(v1, 13), \ - v3 ^= v0, v1 ^= v2, v2 = rol32(v2, 16) \ -) -#define PRND_K0 0x6c796765 -#define PRND_K1 0x74656462 +#define PRND_SIPROUND(v0, v1, v2, v3) HSIPHASH_PERMUTATION(v0, v1, v2, v3) +#define PRND_K0 (HSIPHASH_CONST_0 ^ HSIPHASH_CONST_2) +#define PRND_K1 (HSIPHASH_CONST_1 ^ HSIPHASH_CONST_3) #else #error Unsupported BITS_PER_LONG diff --git a/include/linux/siphash.h b/include/linux/siphash.h index cce8a9acc76c..3af1428da559 100644 --- a/include/linux/siphash.h +++ b/include/linux/siphash.h @@ -138,4 +138,32 @@ static inline u32 hsiphash(const void *data, size_t len, return ___hsiphash_aligned(data, len, key); } +/* + * These macros expose the raw SipHash and HalfSipHash permutations. + * Do not use them directly! If you think you have a use for them, + * be sure to CC the maintainer of this file explaining why. + */ + +#define SIPHASH_PERMUTATION(a, b, c, d) ( \ + (a) += (b), (b) = rol64((b), 13), (b) ^= (a), (a) = rol64((a), 32), \ + (c) += (d), (d) = rol64((d), 16), (d) ^= (c), \ + (a) += (d), (d) = rol64((d), 21), (d) ^= (a), \ + (c) += (b), (b) = rol64((b), 17), (b) ^= (c), (c) = rol64((c), 32)) + +#define SIPHASH_CONST_0 0x736f6d6570736575ULL +#define SIPHASH_CONST_1 0x646f72616e646f6dULL +#define SIPHASH_CONST_2 0x6c7967656e657261ULL +#define SIPHASH_CONST_3 0x7465646279746573ULL + +#define HSIPHASH_PERMUTATION(a, b, c, d) ( \ + (a) += (b), (b) = rol32((b), 5), (b) ^= (a), (a) = rol32((a), 16), \ + (c) += (d), (d) = rol32((d), 8), (d) ^= (c), \ + (a) += (d), (d) = rol32((d), 7), (d) ^= (a), \ + (c) += (b), (b) = rol32((b), 13), (b) ^= (c), (c) = rol32((c), 16)) + +#define HSIPHASH_CONST_0 0U +#define HSIPHASH_CONST_1 0U +#define HSIPHASH_CONST_2 0x6c796765U +#define HSIPHASH_CONST_3 0x74656462U + #endif /* _LINUX_SIPHASH_H */ -- cgit v1.2.3 From d4150779e60fb6c49be25572596b2cdfc5d46a09 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 11 May 2022 16:11:29 +0200 Subject: random32: use real rng for non-deterministic randomness MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit random32.c has two random number generators in it: one that is meant to be used deterministically, with some predefined seed, and one that does the same exact thing as random.c, except does it poorly. The first one has some use cases. The second one no longer does and can be replaced with calls to random.c's proper random number generator. The relatively recent siphash-based bad random32.c code was added in response to concerns that the prior random32.c was too deterministic. Out of fears that random.c was (at the time) too slow, this code was anonymously contributed. Then out of that emerged a kind of shadow entropy gathering system, with its own tentacles throughout various net code, added willy nilly. Stop👏making👏bespoke👏random👏number👏generators👏. Fortunately, recent advances in random.c mean that we can stop playing with this sketchiness, and just use get_random_u32(), which is now fast enough. In micro benchmarks using RDPMC, I'm seeing the same median cycle count between the two functions, with the mean being _slightly_ higher due to batches refilling (which we can optimize further need be). However, when doing *real* benchmarks of the net functions that actually use these random numbers, the mean cycles actually *decreased* slightly (with the median still staying the same), likely because the additional prandom code means icache misses and complexity, whereas random.c is generally already being used by something else nearby. The biggest benefit of this is that there are many users of prandom who probably should be using cryptographically secure random numbers. This makes all of those accidental cases become secure by just flipping a switch. Later on, we can do a tree-wide cleanup to remove the static inline wrapper functions that this commit adds. There are also some low-ish hanging fruits for making this even faster in the future: a get_random_u16() function for use in the networking stack will give a 2x performance boost there, using SIMD for ChaCha20 will let us compute 4 or 8 or 16 blocks of output in parallel, instead of just one, giving us large buffers for cheap, and introducing a get_random_*_bh() function that assumes irqs are already disabled will shave off a few cycles for ordinary calls. These are things we can chip away at down the road. Acked-by: Jakub Kicinski Acked-by: Theodore Ts'o Signed-off-by: Jason A. Donenfeld --- include/linux/prandom.h | 52 +++++++------------------------------------------ 1 file changed, 7 insertions(+), 45 deletions(-) (limited to 'include') diff --git a/include/linux/prandom.h b/include/linux/prandom.h index a4aadd2dc153..deace5fb4e62 100644 --- a/include/linux/prandom.h +++ b/include/linux/prandom.h @@ -10,53 +10,16 @@ #include #include -#include +#include -u32 prandom_u32(void); -void prandom_bytes(void *buf, size_t nbytes); -void prandom_seed(u32 seed); -void prandom_reseed_late(void); - -DECLARE_PER_CPU(unsigned long, net_rand_noise); - -#define PRANDOM_ADD_NOISE(a, b, c, d) \ - prandom_u32_add_noise((unsigned long)(a), (unsigned long)(b), \ - (unsigned long)(c), (unsigned long)(d)) - -#if BITS_PER_LONG == 64 -/* - * The core SipHash round function. Each line can be executed in - * parallel given enough CPU resources. - */ -#define PRND_SIPROUND(v0, v1, v2, v3) SIPHASH_PERMUTATION(v0, v1, v2, v3) - -#define PRND_K0 (SIPHASH_CONST_0 ^ SIPHASH_CONST_2) -#define PRND_K1 (SIPHASH_CONST_1 ^ SIPHASH_CONST_3) - -#elif BITS_PER_LONG == 32 -/* - * On 32-bit machines, we use HSipHash, a reduced-width version of SipHash. - * This is weaker, but 32-bit machines are not used for high-traffic - * applications, so there is less output for an attacker to analyze. - */ -#define PRND_SIPROUND(v0, v1, v2, v3) HSIPHASH_PERMUTATION(v0, v1, v2, v3) -#define PRND_K0 (HSIPHASH_CONST_0 ^ HSIPHASH_CONST_2) -#define PRND_K1 (HSIPHASH_CONST_1 ^ HSIPHASH_CONST_3) - -#else -#error Unsupported BITS_PER_LONG -#endif +static inline u32 prandom_u32(void) +{ + return get_random_u32(); +} -static inline void prandom_u32_add_noise(unsigned long a, unsigned long b, - unsigned long c, unsigned long d) +static inline void prandom_bytes(void *buf, size_t nbytes) { - /* - * This is not used cryptographically; it's just - * a convenient 4-word hash function. (3 xor, 2 add, 2 rol) - */ - a ^= raw_cpu_read(net_rand_noise); - PRND_SIPROUND(a, b, c, d); - raw_cpu_write(net_rand_noise, d); + return get_random_bytes(buf, nbytes); } struct rnd_state { @@ -108,7 +71,6 @@ static inline void prandom_seed_state(struct rnd_state *state, u64 seed) state->s2 = __seed(i, 8U); state->s3 = __seed(i, 16U); state->s4 = __seed(i, 128U); - PRANDOM_ADD_NOISE(state, i, 0, 0); } /* Pseudo random number generator from numerical recipes. */ -- cgit v1.2.3 From 2f14062bb14b0fcfcc21e6dc7d5b5c0d25966164 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Thu, 5 May 2022 02:20:22 +0200 Subject: random: handle latent entropy and command line from random_init() Currently, start_kernel() adds latent entropy and the command line to the entropy bool *after* the RNG has been initialized, deferring when it's actually used by things like stack canaries until the next time the pool is seeded. This surely is not intended. Rather than splitting up which entropy gets added where and when between start_kernel() and random_init(), just do everything in random_init(), which should eliminate these kinds of bugs in the future. While we're at it, rename the awkwardly titled "rand_initialize()" to the more standard "random_init()" nomenclature. Reviewed-by: Dominik Brodowski Signed-off-by: Jason A. Donenfeld --- include/linux/random.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index f673fbb838b3..b52963955a99 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -14,22 +14,21 @@ struct notifier_block; extern void add_device_randomness(const void *, size_t); extern void add_bootloader_randomness(const void *, size_t); +extern void add_input_randomness(unsigned int type, unsigned int code, + unsigned int value) __latent_entropy; +extern void add_interrupt_randomness(int irq) __latent_entropy; +extern void add_hwgenerator_randomness(const void *buffer, size_t count, + size_t entropy); #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) static inline void add_latent_entropy(void) { - add_device_randomness((const void *)&latent_entropy, - sizeof(latent_entropy)); + add_device_randomness((const void *)&latent_entropy, sizeof(latent_entropy)); } #else static inline void add_latent_entropy(void) {} #endif -extern void add_input_randomness(unsigned int type, unsigned int code, - unsigned int value) __latent_entropy; -extern void add_interrupt_randomness(int irq) __latent_entropy; -extern void add_hwgenerator_randomness(const void *buffer, size_t count, - size_t entropy); #if IS_ENABLED(CONFIG_VMGENID) extern void add_vmfork_randomness(const void *unique_vm_id, size_t size); extern int register_random_vmfork_notifier(struct notifier_block *nb); @@ -41,7 +40,7 @@ static inline int unregister_random_vmfork_notifier(struct notifier_block *nb) { extern void get_random_bytes(void *buf, size_t nbytes); extern int wait_for_random_bytes(void); -extern int __init rand_initialize(void); +extern int __init random_init(const char *command_line); extern bool rng_is_initialized(void); extern int register_random_ready_notifier(struct notifier_block *nb); extern int unregister_random_ready_notifier(struct notifier_block *nb); -- cgit v1.2.3 From 354201c53e61e493017b15327294b0c8ab522d69 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 16 May 2022 15:09:21 +0200 Subject: nvme: add support for TP4084 - Time-to-Ready Enhancements Add support for using longer timeouts during controller initialization and letting the controller come up with namespaces that are not ready for I/O yet. We skip these not ready namespaces during scanning and only bring them online once anoter scan is kicked off by the AEN that is set when the NRDY bit gets set in the I/O Command Set Independent Identify Namespace Data Structure. This asynchronous probing avoids blocking the kernel boot when controllers take a very long time to recover after unclean shutdowns (up to minutes). Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Reviewed-by: Chaitanya Kulkarni Reviewed-by: Hannes Reinecke --- include/linux/nvme.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 5f6d432fa06a..29ec3e3481ff 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -137,6 +137,7 @@ enum { NVME_REG_CMBMSC = 0x0050, /* Controller Memory Buffer Memory * Space Control */ + NVME_REG_CRTO = 0x0068, /* Controller Ready Timeouts */ NVME_REG_PMRCAP = 0x0e00, /* Persistent Memory Capabilities */ NVME_REG_PMRCTL = 0x0e04, /* Persistent Memory Region Control */ NVME_REG_PMRSTS = 0x0e08, /* Persistent Memory Region Status */ @@ -161,6 +162,9 @@ enum { #define NVME_CMB_BIR(cmbloc) ((cmbloc) & 0x7) #define NVME_CMB_OFST(cmbloc) (((cmbloc) >> 12) & 0xfffff) +#define NVME_CRTO_CRIMT(crto) ((crto) >> 16) +#define NVME_CRTO_CRWMT(crto) ((crto) & 0xffff) + enum { NVME_CMBSZ_SQS = 1 << 0, NVME_CMBSZ_CQS = 1 << 1, @@ -204,6 +208,7 @@ enum { NVME_CC_SHN_MASK = 3 << NVME_CC_SHN_SHIFT, NVME_CC_IOSQES = NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT, NVME_CC_IOCQES = NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT, + NVME_CC_CRIME = 1 << 24, }; enum { @@ -227,6 +232,11 @@ enum { NVME_CAP_CSS_CSI = 1 << 6, }; +enum { + NVME_CAP_CRMS_CRIMS = 1ULL << 59, + NVME_CAP_CRMS_CRWMS = 1ULL << 60, +}; + struct nvme_id_power_state { __le16 max_power; /* centiwatts */ __u8 rsvd2; @@ -414,6 +424,21 @@ struct nvme_id_ns { __u8 vs[3712]; }; +/* I/O Command Set Independent Identify Namespace Data Structure */ +struct nvme_id_ns_cs_indep { + __u8 nsfeat; + __u8 nmic; + __u8 rescap; + __u8 fpi; + __le32 anagrpid; + __u8 nsattr; + __u8 rsvd9; + __le16 nvmsetid; + __le16 endgid; + __u8 nstat; + __u8 rsvd15[4081]; +}; + struct nvme_zns_lbafe { __le64 zsze; __u8 zdes; @@ -478,6 +503,7 @@ enum { NVME_ID_CNS_NS_DESC_LIST = 0x03, NVME_ID_CNS_CS_NS = 0x05, NVME_ID_CNS_CS_CTRL = 0x06, + NVME_ID_CNS_NS_CS_INDEP = 0x08, NVME_ID_CNS_NS_PRESENT_LIST = 0x10, NVME_ID_CNS_NS_PRESENT = 0x11, NVME_ID_CNS_CTRL_NS_LIST = 0x12, @@ -531,6 +557,10 @@ enum { NVME_NS_DPS_PI_TYPE3 = 3, }; +enum { + NVME_NSTAT_NRDY = 1 << 0, +}; + enum { NVME_NVM_NS_16B_GUARD = 0, NVME_NVM_NS_32B_GUARD = 1, @@ -1592,6 +1622,7 @@ enum { NVME_SC_NS_WRITE_PROTECTED = 0x20, NVME_SC_CMD_INTERRUPTED = 0x21, NVME_SC_TRANSIENT_TR_ERR = 0x22, + NVME_SC_ADMIN_COMMAND_MEDIA_NOT_READY = 0x24, NVME_SC_INVALID_IO_CMD_SET = 0x2C, NVME_SC_LBA_RANGE = 0x80, -- cgit v1.2.3 From 75dbb685f4e8786c33ddef8279bab0eadfb0731f Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Sat, 14 May 2022 12:16:47 +0200 Subject: libceph: fix potential use-after-free on linger ping and resends request_reinit() is not only ugly as the comment rightfully suggests, but also unsafe. Even though it is called with osdc->lock held for write in all cases, resetting the OSD request refcount can still race with handle_reply() and result in use-after-free. Taking linger ping as an example: handle_timeout thread handle_reply thread down_read(&osdc->lock) req = lookup_request(...) ... finish_request(req) # unregisters up_read(&osdc->lock) __complete_request(req) linger_ping_cb(req) # req->r_kref == 2 because handle_reply still holds its ref down_write(&osdc->lock) send_linger_ping(lreq) req = lreq->ping_req # same req # cancel_linger_request is NOT # called - handle_reply already # unregistered request_reinit(req) WARN_ON(req->r_kref != 1) # fires request_init(req) kref_init(req->r_kref) # req->r_kref == 1 after kref_init ceph_osdc_put_request(req) kref_put(req->r_kref) # req->r_kref == 0 after kref_put, req is freed !!! This happens because send_linger_ping() always (re)uses the same OSD request for watch ping requests, relying on cancel_linger_request() to unregister it from the OSD client and rip its messages out from the messenger. send_linger() does the same for watch/notify registration and watch reconnect requests. Unfortunately cancel_request() doesn't guarantee that after it returns the OSD client would be completely done with the OSD request -- a ref could still be held and the callback (if specified) could still be invoked too. The original motivation for request_reinit() was inability to deal with allocation failures in send_linger() and send_linger_ping(). Switching to using osdc->req_mempool (currently only used by CephFS) respects that and allows us to get rid of request_reinit(). Cc: stable@vger.kernel.org Signed-off-by: Ilya Dryomov Reviewed-by: Xiubo Li Acked-by: Jeff Layton --- include/linux/ceph/osd_client.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 3431011f364d..cba8a6ffc329 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -287,6 +287,9 @@ struct ceph_osd_linger_request { rados_watcherrcb_t errcb; void *data; + struct ceph_pagelist *request_pl; + struct page **notify_id_pages; + struct page ***preply_pages; size_t *preply_len; }; -- cgit v1.2.3 From 3f68e69520d3d52d66a6ad872a75b7d8f2ea7665 Mon Sep 17 00:00:00 2001 From: Sunil V L Date: Thu, 19 May 2022 10:45:12 +0530 Subject: riscv/efi_stub: Add support for RISCV_EFI_BOOT_PROTOCOL Add support for getting the boot hart ID from the Linux EFI stub using RISCV_EFI_BOOT_PROTOCOL. This method is preferred over the existing DT based approach since it works irrespective of DT or ACPI. The specification of the protocol is hosted at: https://github.com/riscv-non-isa/riscv-uefi Signed-off-by: Sunil V L Acked-by: Palmer Dabbelt Reviewed-by: Heinrich Schuchardt Link: https://lore.kernel.org/r/20220519051512.136724-2-sunilvl@ventanamicro.com [ardb: minor tweaks for coding style and whitespace] Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index 580ce607d6f5..0412304ce34e 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -410,6 +410,8 @@ void efi_native_runtime_setup(void); #define LINUX_EFI_MOK_VARIABLE_TABLE_GUID EFI_GUID(0xc451ed2b, 0x9694, 0x45d3, 0xba, 0xba, 0xed, 0x9f, 0x89, 0x88, 0xa3, 0x89) #define LINUX_EFI_COCO_SECRET_AREA_GUID EFI_GUID(0xadf956ad, 0xe98c, 0x484c, 0xae, 0x11, 0xb5, 0x1c, 0x7d, 0x33, 0x64, 0x47) +#define RISCV_EFI_BOOT_PROTOCOL_GUID EFI_GUID(0xccd15fec, 0x6f73, 0x4eec, 0x83, 0x95, 0x3e, 0x69, 0xe4, 0xb9, 0x40, 0xbf) + /* * This GUID may be installed onto the kernel image's handle as a NULL protocol * to signal to the stub that the placement of the image should be respected, -- cgit v1.2.3 From 238e34ad7d5ce36939ac1442c98c7cbb7771f4de Mon Sep 17 00:00:00 2001 From: Jishnu Prakash Date: Sun, 3 Apr 2022 18:47:47 +0530 Subject: iio: adc: qcom-vadc-common: add reverse scaling for PMIC5 Gen2 ADC_TM Add reverse scaling function for PMIC5 Gen2 ADC_TM, to convert temperature to raw ADC code, for setting thresholds for thermistor channels. Signed-off-by: Jishnu Prakash Acked-by: Jonathan Cameron Link: https://lore.kernel.org/r/1648991869-20899-3-git-send-email-quic_jprakash@quicinc.com Signed-off-by: Daniel Lezcano --- include/linux/iio/adc/qcom-vadc-common.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/iio/adc/qcom-vadc-common.h b/include/linux/iio/adc/qcom-vadc-common.h index ce78d4804994..aa21b032e861 100644 --- a/include/linux/iio/adc/qcom-vadc-common.h +++ b/include/linux/iio/adc/qcom-vadc-common.h @@ -152,6 +152,8 @@ int qcom_adc5_hw_scale(enum vadc_scale_fn_type scaletype, u16 qcom_adc_tm5_temp_volt_scale(unsigned int prescale_ratio, u32 full_scale_code_volt, int temp); +u16 qcom_adc_tm5_gen2_temp_res_scale(int temp); + int qcom_adc5_prescaling_from_dt(u32 num, u32 den); int qcom_adc5_hw_settle_time_from_dt(u32 value, const unsigned int *hw_settle); -- cgit v1.2.3 From bf70c577516b8d9fbe703371aa98bbea13661cec Mon Sep 17 00:00:00 2001 From: Manaf Meethalavalappu Pallikunhi Date: Wed, 9 Mar 2022 00:56:26 +0530 Subject: thermal/drivers/thermal_of: Add change_mode ops support for thermal_of sensor The sensor driver which register through thermal_of interface doesn't have an option to get thermal zone mode change notification from thermal core. Add support for change_mode ops in thermal_of interface so that sensor driver can use this ops for mode change notification. Signed-off-by: Manaf Meethalavalappu Pallikunhi Link: https://lore.kernel.org/r/1646767586-31908-1-git-send-email-quic_manafm@quicinc.com Signed-off-by: Daniel Lezcano --- include/linux/thermal.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index c314893970b3..365733b428d8 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -299,6 +299,8 @@ struct thermal_zone_params { * temperature. * @set_trip_temp: a pointer to a function that sets the trip temperature on * hardware. + * @change_mode: a pointer to a function that notifies the thermal zone + * mode change. */ struct thermal_zone_of_device_ops { int (*get_temp)(void *, int *); @@ -306,6 +308,7 @@ struct thermal_zone_of_device_ops { int (*set_trips)(void *, int, int); int (*set_emul_temp)(void *, int); int (*set_trip_temp)(void *, int, int); + int (*change_mode) (void *, enum thermal_device_mode); }; /* Function declarations */ -- cgit v1.2.3 From c1318b39c7d36bd5139a9c71044ff2b2d3c6f9d8 Mon Sep 17 00:00:00 2001 From: Boris Pismenny Date: Wed, 18 May 2022 12:27:31 +0300 Subject: tls: Add opt-in zerocopy mode of sendfile() TLS device offload copies sendfile data to a bounce buffer before transmitting. It allows to maintain the valid MAC on TLS records when the file contents change and a part of TLS record has to be retransmitted on TCP level. In many common use cases (like serving static files over HTTPS) the file contents are not changed on the fly. In many use cases breaking the connection is totally acceptable if the file is changed during transmission, because it would be received corrupted in any case. This commit allows to optimize performance for such use cases to providing a new optional mode of TLS sendfile(), in which the extra copy is skipped. Removing this copy improves performance significantly, as TLS and TCP sendfile perform the same operations, and the only overhead is TLS header/trailer insertion. The new mode can only be enabled with the new socket option named TLS_TX_ZEROCOPY_SENDFILE on per-socket basis. It preserves backwards compatibility with existing applications that rely on the copying behavior. The new mode is safe, meaning that unsolicited modifications of the file being sent can't break integrity of the kernel. The worst thing that can happen is sending a corrupted TLS record, which is in any case not forbidden when using regular TCP sockets. Sockets other than TLS device offload are not affected by the new socket option. The actual status of zerocopy sendfile can be queried with sock_diag. Performance numbers in a single-core test with 24 HTTPS streams on nginx, under 100% CPU load: * non-zerocopy: 33.6 Gbit/s * zerocopy: 79.92 Gbit/s CPU: Intel(R) Xeon(R) Platinum 8380 CPU @ 2.30GHz Signed-off-by: Boris Pismenny Signed-off-by: Tariq Toukan Signed-off-by: Maxim Mikityanskiy Reviewed-by: Jakub Kicinski Link: https://lore.kernel.org/r/20220518092731.1243494-1-maximmi@nvidia.com Signed-off-by: Paolo Abeni --- include/net/tls.h | 1 + include/uapi/linux/tls.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index b59f0a63292b..8017f1703447 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -238,6 +238,7 @@ struct tls_context { u8 tx_conf:3; u8 rx_conf:3; + u8 zerocopy_sendfile:1; int (*push_pending_record)(struct sock *sk, int flags); void (*sk_write_space)(struct sock *sk); diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h index 5f38be0ec0f3..ac39328eabe7 100644 --- a/include/uapi/linux/tls.h +++ b/include/uapi/linux/tls.h @@ -39,6 +39,7 @@ /* TLS socket options */ #define TLS_TX 1 /* Set transmit parameters */ #define TLS_RX 2 /* Set receive parameters */ +#define TLS_TX_ZEROCOPY_SENDFILE 3 /* transmit zerocopy sendfile */ /* Supported versions */ #define TLS_VERSION_MINOR(ver) ((ver) & 0xFF) @@ -160,6 +161,7 @@ enum { TLS_INFO_CIPHER, TLS_INFO_TXCONF, TLS_INFO_RXCONF, + TLS_INFO_ZC_SENDFILE, __TLS_INFO_MAX, }; #define TLS_INFO_MAX (__TLS_INFO_MAX - 1) -- cgit v1.2.3 From 5ce9231c5b961596ebf948777c9c5a6981f067d9 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 28 Apr 2022 09:53:20 +0200 Subject: xen: update vscsiif.h Update include/xen/interface/io/vscsiif.h to its newest version. Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Link: https://lore.kernel.org/r/20220428075323.12853-2-jgross@suse.com Signed-off-by: Juergen Gross --- include/xen/interface/io/vscsiif.h | 133 +++++++++++++++++++++++++++++++++++-- 1 file changed, 129 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/xen/interface/io/vscsiif.h b/include/xen/interface/io/vscsiif.h index 1f6047d3de44..7ea4dc9611c4 100644 --- a/include/xen/interface/io/vscsiif.h +++ b/include/xen/interface/io/vscsiif.h @@ -43,7 +43,7 @@ * * A string specifying the backend device: either a 4-tuple "h:c:t:l" * (host, controller, target, lun, all integers), or a WWN (e.g. - * "naa.60014054ac780582"). + * "naa.60014054ac780582:0"). * * v-dev * Values: string @@ -87,6 +87,75 @@ * response structures. */ +/* + * Xenstore format in practice + * =========================== + * + * The backend driver uses a single_host:many_devices notation to manage domU + * devices. Everything is stored in /local/domain//backend/vscsi/. + * The xenstore layout looks like this (dom0 is assumed to be the backend_domid): + * + * //feature-host = "0" + * //frontend = "/local/domain//device/vscsi/0" + * //frontend-id = "" + * //online = "1" + * //state = "4" + * //vscsi-devs/dev-0/p-dev = "8:0:2:1" or "naa.wwn:lun" + * //vscsi-devs/dev-0/state = "4" + * //vscsi-devs/dev-0/v-dev = "0:0:0:0" + * //vscsi-devs/dev-1/p-dev = "8:0:2:2" + * //vscsi-devs/dev-1/state = "4" + * //vscsi-devs/dev-1/v-dev = "0:0:1:0" + * + * The frontend driver maintains its state in + * /local/domain//device/vscsi/. + * + * /backend = "/local/domain/0/backend/vscsi//" + * /backend-id = "0" + * /event-channel = "20" + * /ring-ref = "43" + * /state = "4" + * /vscsi-devs/dev-0/state = "4" + * /vscsi-devs/dev-1/state = "4" + * + * In addition to the entries for backend and frontend these flags are stored + * for the toolstack: + * + * //vscsi-devs/dev-1/p-devname = "/dev/$device" + * //libxl_ctrl_index = "0" + * + * + * Backend/frontend protocol + * ========================= + * + * To create a vhost along with a device: + * //feature-host = "0" + * //frontend = "/local/domain//device/vscsi/0" + * //frontend-id = "" + * //online = "1" + * //state = "1" + * //vscsi-devs/dev-0/p-dev = "8:0:2:1" + * //vscsi-devs/dev-0/state = "1" + * //vscsi-devs/dev-0/v-dev = "0:0:0:0" + * Wait for //state + //vscsi-devs/dev-0/state become 4 + * + * To add another device to a vhost: + * //state = "7" + * //vscsi-devs/dev-1/p-dev = "8:0:2:2" + * //vscsi-devs/dev-1/state = "1" + * //vscsi-devs/dev-1/v-dev = "0:0:1:0" + * Wait for //state + //vscsi-devs/dev-1/state become 4 + * + * To remove a device from a vhost: + * //state = "7" + * //vscsi-devs/dev-1/state = "5" + * Wait for //state to become 4 + * Wait for //vscsi-devs/dev-1/state become 6 + * Remove //vscsi-devs/dev-1/{state,p-dev,v-dev,p-devname} + * Remove //vscsi-devs/dev-1/ + * + */ + /* Requests from the frontend to the backend */ /* @@ -117,7 +186,8 @@ * (plus the set VSCSIIF_SG_GRANT bit), the number of scsiif_request_segment * elements referencing the target data buffers is calculated from the lengths * of the seg[] elements (the sum of all valid seg[].length divided by the - * size of one scsiif_request_segment structure). + * size of one scsiif_request_segment structure). The frontend may use a mix of + * direct and indirect requests. */ #define VSCSIIF_ACT_SCSI_CDB 1 @@ -154,12 +224,14 @@ /* * based on Linux kernel 2.6.18, still valid + * * Changing these values requires support of multiple protocols via the rings * as "old clients" will blindly use these values and the resulting structure * sizes. */ #define VSCSIIF_MAX_COMMAND_SIZE 16 #define VSCSIIF_SENSE_BUFFERSIZE 96 +#define VSCSIIF_PAGE_SIZE 4096 struct scsiif_request_segment { grant_ref_t gref; @@ -167,7 +239,8 @@ struct scsiif_request_segment { uint16_t length; }; -#define VSCSIIF_SG_PER_PAGE (PAGE_SIZE / sizeof(struct scsiif_request_segment)) +#define VSCSIIF_SG_PER_PAGE (VSCSIIF_PAGE_SIZE / \ + sizeof(struct scsiif_request_segment)) /* Size of one request is 252 bytes */ struct vscsiif_request { @@ -207,6 +280,58 @@ struct vscsiif_response { uint32_t reserved[36]; }; +/* SCSI I/O status from vscsiif_response->rslt */ +#define XEN_VSCSIIF_RSLT_STATUS(x) ((x) & 0x00ff) + +/* Host I/O status from vscsiif_response->rslt */ +#define XEN_VSCSIIF_RSLT_HOST(x) (((x) & 0x00ff0000) >> 16) +#define XEN_VSCSIIF_RSLT_HOST_OK 0 +/* Couldn't connect before timeout */ +#define XEN_VSCSIIF_RSLT_HOST_NO_CONNECT 1 +/* Bus busy through timeout */ +#define XEN_VSCSIIF_RSLT_HOST_BUS_BUSY 2 +/* Timed out for other reason */ +#define XEN_VSCSIIF_RSLT_HOST_TIME_OUT 3 +/* Bad target */ +#define XEN_VSCSIIF_RSLT_HOST_BAD_TARGET 4 +/* Abort for some other reason */ +#define XEN_VSCSIIF_RSLT_HOST_ABORT 5 +/* Parity error */ +#define XEN_VSCSIIF_RSLT_HOST_PARITY 6 +/* Internal error */ +#define XEN_VSCSIIF_RSLT_HOST_ERROR 7 +/* Reset by somebody */ +#define XEN_VSCSIIF_RSLT_HOST_RESET 8 +/* Unexpected interrupt */ +#define XEN_VSCSIIF_RSLT_HOST_BAD_INTR 9 +/* Force command past mid-layer */ +#define XEN_VSCSIIF_RSLT_HOST_PASSTHROUGH 10 +/* Retry requested */ +#define XEN_VSCSIIF_RSLT_HOST_SOFT_ERROR 11 +/* Hidden retry requested */ +#define XEN_VSCSIIF_RSLT_HOST_IMM_RETRY 12 +/* Requeue command requested */ +#define XEN_VSCSIIF_RSLT_HOST_REQUEUE 13 +/* Transport error disrupted I/O */ +#define XEN_VSCSIIF_RSLT_HOST_TRANSPORT_DISRUPTED 14 +/* Transport class fastfailed */ +#define XEN_VSCSIIF_RSLT_HOST_TRANSPORT_FAILFAST 15 +/* Permanent target failure */ +#define XEN_VSCSIIF_RSLT_HOST_TARGET_FAILURE 16 +/* Permanent nexus failure on path */ +#define XEN_VSCSIIF_RSLT_HOST_NEXUS_FAILURE 17 +/* Space allocation on device failed */ +#define XEN_VSCSIIF_RSLT_HOST_ALLOC_FAILURE 18 +/* Medium error */ +#define XEN_VSCSIIF_RSLT_HOST_MEDIUM_ERROR 19 +/* Transport marginal errors */ +#define XEN_VSCSIIF_RSLT_HOST_TRANSPORT_MARGINAL 20 + +/* Result values of reset operations */ +#define XEN_VSCSIIF_RSLT_RESET_SUCCESS 0x2002 +#define XEN_VSCSIIF_RSLT_RESET_FAILED 0x2003 + DEFINE_RING_TYPES(vscsiif, struct vscsiif_request, struct vscsiif_response); -#endif /*__XEN__PUBLIC_IO_SCSI_H__*/ + +#endif /*__XEN__PUBLIC_IO_SCSI_H__*/ -- cgit v1.2.3 From 79c22318f89f3e6cafeabddd5894cad13c7e5957 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 5 May 2022 08:49:52 +0200 Subject: xen: update grant_table.h Update include/xen/interface/grant_table.h to its newest version. This allows to drop some private definitions in grant-table.c and include/xen/grant_table.h. Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Signed-off-by: Juergen Gross --- include/xen/grant_table.h | 2 - include/xen/interface/grant_table.h | 161 ++++++++++++++++++++++-------------- 2 files changed, 100 insertions(+), 63 deletions(-) (limited to 'include') diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index dfd5bf31cfb9..7d0f2f0037b8 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -57,8 +57,6 @@ #define INVALID_GRANT_REF ((grant_ref_t)-1) #define INVALID_GRANT_HANDLE ((grant_handle_t)-1) -#define GNTTAB_RESERVED_XENSTORE 1 - /* NR_GRANT_FRAMES must be less than or equal to that configured in Xen */ #define NR_GRANT_FRAMES 4 diff --git a/include/xen/interface/grant_table.h b/include/xen/interface/grant_table.h index 3eeabbc7ee09..cebbd99f1f84 100644 --- a/include/xen/interface/grant_table.h +++ b/include/xen/interface/grant_table.h @@ -19,7 +19,8 @@ /* Some rough guidelines on accessing and updating grant-table entries * in a concurrency-safe manner. For more information, Linux contains a - * reference implementation for guest OSes (arch/xen/kernel/grant_table.c). + * reference implementation for guest OSes (drivers/xen/grant_table.c, see + * http://git.kernel.org/?p=linux/kernel/git/torvalds/linux.git;a=blob;f=drivers/xen/grant-table.c;hb=HEAD * * NB. WMB is a no-op on current-generation x86 processors. However, a * compiler barrier will still be required. @@ -80,8 +81,9 @@ typedef uint32_t grant_ref_t; */ /* - * Version 1 of the grant table entry structure is maintained purely - * for backwards compatibility. New guests should use version 2. + * Version 1 of the grant table entry structure is maintained largely for + * backwards compatibility. New guests are recommended to support using + * version 2 to overcome version 1 limitations, but to default to version 1. */ struct grant_entry_v1 { /* GTF_xxx: various type and flag information. [XEN,GST] */ @@ -89,12 +91,21 @@ struct grant_entry_v1 { /* The domain being granted foreign privileges. [GST] */ domid_t domid; /* - * GTF_permit_access: Frame that @domid is allowed to map and access. [GST] - * GTF_accept_transfer: Frame whose ownership transferred by @domid. [XEN] + * GTF_permit_access: GFN that @domid is allowed to map and access. [GST] + * GTF_accept_transfer: GFN that @domid is allowed to transfer into. [GST] + * GTF_transfer_completed: MFN whose ownership transferred by @domid + * (non-translated guests only). [XEN] */ uint32_t frame; }; +/* The first few grant table entries will be preserved across grant table + * version changes and may be pre-populated at domain creation by tools. + */ +#define GNTTAB_NR_RESERVED_ENTRIES 8 +#define GNTTAB_RESERVED_CONSOLE 0 +#define GNTTAB_RESERVED_XENSTORE 1 + /* * Type of grant entry. * GTF_invalid: This grant entry grants no privileges. @@ -111,10 +122,13 @@ struct grant_entry_v1 { #define GTF_type_mask (3U<<0) /* - * Subflags for GTF_permit_access. + * Subflags for GTF_permit_access and GTF_transitive. * GTF_readonly: Restrict @domid to read-only mappings and accesses. [GST] * GTF_reading: Grant entry is currently mapped for reading by @domid. [XEN] * GTF_writing: Grant entry is currently mapped for writing by @domid. [XEN] + * Further subflags for GTF_permit_access only. + * GTF_PAT, GTF_PWT, GTF_PCD: (x86) cache attribute flags to be used for + * mappings of the grant [GST] * GTF_sub_page: Grant access to only a subrange of the page. @domid * will only be allowed to copy from the grant, and not * map it. [GST] @@ -125,6 +139,12 @@ struct grant_entry_v1 { #define GTF_reading (1U<<_GTF_reading) #define _GTF_writing (4) #define GTF_writing (1U<<_GTF_writing) +#define _GTF_PWT (5) +#define GTF_PWT (1U<<_GTF_PWT) +#define _GTF_PCD (6) +#define GTF_PCD (1U<<_GTF_PCD) +#define _GTF_PAT (7) +#define GTF_PAT (1U<<_GTF_PAT) #define _GTF_sub_page (8) #define GTF_sub_page (1U<<_GTF_sub_page) @@ -164,8 +184,7 @@ struct grant_entry_header { }; /* - * Version 2 of the grant entry structure, here is a union because three - * different types are suppotted: full_page, sub_page and transitive. + * Version 2 of the grant entry structure. */ union grant_entry_v2 { struct grant_entry_header hdr; @@ -180,9 +199,9 @@ union grant_entry_v2 { * field of the same name in the V1 entry structure. */ struct { - struct grant_entry_header hdr; - uint32_t pad0; - uint64_t frame; + struct grant_entry_header hdr; + uint32_t pad0; + uint64_t frame; } full_page; /* @@ -191,10 +210,10 @@ union grant_entry_v2 { * in frame @frame. */ struct { - struct grant_entry_header hdr; - uint16_t page_off; - uint16_t length; - uint64_t frame; + struct grant_entry_header hdr; + uint16_t page_off; + uint16_t length; + uint64_t frame; } sub_page; /* @@ -202,12 +221,15 @@ union grant_entry_v2 { * grant @gref in domain @trans_domid, as if it was the local * domain. Obviously, the transitive access must be compatible * with the original grant. + * + * The current version of Xen does not allow transitive grants + * to be mapped. */ struct { - struct grant_entry_header hdr; - domid_t trans_domid; - uint16_t pad0; - grant_ref_t gref; + struct grant_entry_header hdr; + domid_t trans_domid; + uint16_t pad0; + grant_ref_t gref; } transitive; uint32_t __spacer[4]; /* Pad to a power of two */ @@ -219,6 +241,21 @@ typedef uint16_t grant_status_t; * GRANT TABLE QUERIES AND USES */ +#define GNTTABOP_map_grant_ref 0 +#define GNTTABOP_unmap_grant_ref 1 +#define GNTTABOP_setup_table 2 +#define GNTTABOP_dump_table 3 +#define GNTTABOP_transfer 4 +#define GNTTABOP_copy 5 +#define GNTTABOP_query_size 6 +#define GNTTABOP_unmap_and_replace 7 +#define GNTTABOP_set_version 8 +#define GNTTABOP_get_status_frames 9 +#define GNTTABOP_get_version 10 +#define GNTTABOP_swap_grant_ref 11 +#define GNTTABOP_cache_flush 12 +/* ` } */ + /* * Handle to track a mapping created via a grant reference. */ @@ -227,7 +264,7 @@ typedef uint32_t grant_handle_t; /* * GNTTABOP_map_grant_ref: Map the grant entry (,) for access * by devices and/or host CPUs. If successful, is a tracking number - * that must be presented later to destroy the mapping(s). On error, + * that must be presented later to destroy the mapping(s). On error, * is a negative status code. * NOTES: * 1. If GNTMAP_device_map is specified then is the address @@ -241,7 +278,6 @@ typedef uint32_t grant_handle_t; * host mapping is destroyed by other means then it is *NOT* guaranteed * to be accounted to the correct grant reference! */ -#define GNTTABOP_map_grant_ref 0 struct gnttab_map_grant_ref { /* IN parameters. */ uint64_t host_addr; @@ -266,7 +302,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_map_grant_ref); * 3. After executing a batch of unmaps, it is guaranteed that no stale * mappings will remain in the device or host TLBs. */ -#define GNTTABOP_unmap_grant_ref 1 struct gnttab_unmap_grant_ref { /* IN parameters. */ uint64_t host_addr; @@ -286,7 +321,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_unmap_grant_ref); * 2. Only a sufficiently-privileged domain may specify != DOMID_SELF. * 3. Xen may not support more than a single grant-table page per domain. */ -#define GNTTABOP_setup_table 2 struct gnttab_setup_table { /* IN parameters. */ domid_t dom; @@ -301,7 +335,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_setup_table); * GNTTABOP_dump_table: Dump the contents of the grant table to the * xen console. Debugging use only. */ -#define GNTTABOP_dump_table 3 struct gnttab_dump_table { /* IN parameters. */ domid_t dom; @@ -311,17 +344,17 @@ struct gnttab_dump_table { DEFINE_GUEST_HANDLE_STRUCT(gnttab_dump_table); /* - * GNTTABOP_transfer_grant_ref: Transfer to a foreign domain. The - * foreign domain has previously registered its interest in the transfer via - * . + * GNTTABOP_transfer: Transfer to a foreign domain. The foreign domain + * has previously registered its interest in the transfer via . * * Note that, even if the transfer fails, the specified page no longer belongs * to the calling domain *unless* the error is GNTST_bad_page. + * + * Note further that only PV guests can use this operation. */ -#define GNTTABOP_transfer 4 struct gnttab_transfer { /* IN parameters. */ - xen_pfn_t mfn; + xen_pfn_t mfn; domid_t domid; grant_ref_t ref; /* OUT parameters. */ @@ -352,21 +385,20 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_transfer); #define _GNTCOPY_dest_gref (1) #define GNTCOPY_dest_gref (1<<_GNTCOPY_dest_gref) -#define GNTTABOP_copy 5 struct gnttab_copy { - /* IN parameters. */ - struct { - union { - grant_ref_t ref; - xen_pfn_t gmfn; - } u; - domid_t domid; - uint16_t offset; - } source, dest; - uint16_t len; - uint16_t flags; /* GNTCOPY_* */ - /* OUT parameters. */ - int16_t status; + /* IN parameters. */ + struct gnttab_copy_ptr { + union { + grant_ref_t ref; + xen_pfn_t gmfn; + } u; + domid_t domid; + uint16_t offset; + } source, dest; + uint16_t len; + uint16_t flags; /* GNTCOPY_* */ + /* OUT parameters. */ + int16_t status; }; DEFINE_GUEST_HANDLE_STRUCT(gnttab_copy); @@ -377,7 +409,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_copy); * 1. may be specified as DOMID_SELF. * 2. Only a sufficiently-privileged domain may specify != DOMID_SELF. */ -#define GNTTABOP_query_size 6 struct gnttab_query_size { /* IN parameters. */ domid_t dom; @@ -399,7 +430,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_query_size); * 2. After executing a batch of unmaps, it is guaranteed that no stale * mappings will remain in the device or host TLBs. */ -#define GNTTABOP_unmap_and_replace 7 struct gnttab_unmap_and_replace { /* IN parameters. */ uint64_t host_addr; @@ -412,14 +442,12 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_unmap_and_replace); /* * GNTTABOP_set_version: Request a particular version of the grant - * table shared table structure. This operation can only be performed - * once in any given domain. It must be performed before any grants - * are activated; otherwise, the domain will be stuck with version 1. - * The only defined versions are 1 and 2. + * table shared table structure. This operation may be used to toggle + * between different versions, but must be performed while no grants + * are active. The only defined versions are 1 and 2. */ -#define GNTTABOP_set_version 8 struct gnttab_set_version { - /* IN parameters */ + /* IN/OUT parameters */ uint32_t version; }; DEFINE_GUEST_HANDLE_STRUCT(gnttab_set_version); @@ -436,7 +464,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_set_version); * 1. may be specified as DOMID_SELF. * 2. Only a sufficiently-privileged domain may specify != DOMID_SELF. */ -#define GNTTABOP_get_status_frames 9 struct gnttab_get_status_frames { /* IN parameters. */ uint32_t nr_frames; @@ -451,7 +478,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_get_status_frames); * GNTTABOP_get_version: Get the grant table version which is in * effect for domain . */ -#define GNTTABOP_get_version 10 struct gnttab_get_version { /* IN parameters */ domid_t dom; @@ -461,27 +487,38 @@ struct gnttab_get_version { }; DEFINE_GUEST_HANDLE_STRUCT(gnttab_get_version); +/* + * GNTTABOP_swap_grant_ref: Swap the contents of two grant entries. + */ +struct gnttab_swap_grant_ref { + /* IN parameters */ + grant_ref_t ref_a; + grant_ref_t ref_b; + /* OUT parameters */ + int16_t status; /* GNTST_* */ +}; +DEFINE_GUEST_HANDLE_STRUCT(gnttab_swap_grant_ref); + /* * Issue one or more cache maintenance operations on a portion of a * page granted to the calling domain by a foreign domain. */ -#define GNTTABOP_cache_flush 12 struct gnttab_cache_flush { union { uint64_t dev_bus_addr; grant_ref_t ref; } a; - uint16_t offset; /* offset from start of grant */ - uint16_t length; /* size within the grant */ -#define GNTTAB_CACHE_CLEAN (1<<0) -#define GNTTAB_CACHE_INVAL (1<<1) -#define GNTTAB_CACHE_SOURCE_GREF (1<<31) + uint16_t offset; /* offset from start of grant */ + uint16_t length; /* size within the grant */ +#define GNTTAB_CACHE_CLEAN (1u<<0) +#define GNTTAB_CACHE_INVAL (1u<<1) +#define GNTTAB_CACHE_SOURCE_GREF (1u<<31) uint32_t op; }; DEFINE_GUEST_HANDLE_STRUCT(gnttab_cache_flush); /* - * Bitfield values for update_pin_status.flags. + * Bitfield values for gnttab_map_grant_ref.flags. */ /* Map the grant entry for access by I/O devices. */ #define _GNTMAP_device_map (0) @@ -531,6 +568,7 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_cache_flush); #define GNTST_bad_copy_arg (-10) /* copy arguments cross page boundary. */ #define GNTST_address_too_big (-11) /* transfer page address too large. */ #define GNTST_eagain (-12) /* Operation not done; try again. */ +#define GNTST_no_space (-13) /* Out of space (handles etc). */ #define GNTTABOP_error_msgs { \ "okay", \ @@ -545,7 +583,8 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_cache_flush); "bad page", \ "copy arguments cross page boundary", \ "page address size too large", \ - "operation not done; try again" \ + "operation not done; try again", \ + "out of space", \ } #endif /* __XEN_PUBLIC_GRANT_TABLE_H__ */ -- cgit v1.2.3 From 6fac592cca60dca0b2a524c303c83e958c2003bb Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 28 Apr 2022 09:59:01 +0200 Subject: xen: update ring.h Update include/xen/interface/io/ring.h to its newest version. Switch the two improper use cases of RING_HAS_UNCONSUMED_RESPONSES() to XEN_RING_NR_UNCONSUMED_RESPONSES() in order to avoid the nasty XEN_RING_HAS_UNCONSUMED_IS_BOOL #define. Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Signed-off-by: Juergen Gross --- include/xen/interface/io/ring.h | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/xen/interface/io/ring.h b/include/xen/interface/io/ring.h index 2470ec45ebb2..ba4c4274b714 100644 --- a/include/xen/interface/io/ring.h +++ b/include/xen/interface/io/ring.h @@ -72,9 +72,8 @@ typedef unsigned int RING_IDX; * of the shared memory area (PAGE_SIZE, for instance). To initialise * the front half: * - * mytag_front_ring_t front_ring; - * SHARED_RING_INIT((mytag_sring_t *)shared_page); - * FRONT_RING_INIT(&front_ring, (mytag_sring_t *)shared_page, PAGE_SIZE); + * mytag_front_ring_t ring; + * XEN_FRONT_RING_INIT(&ring, (mytag_sring_t *)shared_page, PAGE_SIZE); * * Initializing the back follows similarly (note that only the front * initializes the shared ring): @@ -146,6 +145,11 @@ struct __name##_back_ring { \ #define FRONT_RING_INIT(_r, _s, __size) FRONT_RING_ATTACH(_r, _s, 0, __size) +#define XEN_FRONT_RING_INIT(r, s, size) do { \ + SHARED_RING_INIT(s); \ + FRONT_RING_INIT(r, s, size); \ +} while (0) + #define BACK_RING_ATTACH(_r, _s, _i, __size) do { \ (_r)->rsp_prod_pvt = (_i); \ (_r)->req_cons = (_i); \ @@ -170,16 +174,21 @@ struct __name##_back_ring { \ (RING_FREE_REQUESTS(_r) == 0) /* Test if there are outstanding messages to be processed on a ring. */ -#define RING_HAS_UNCONSUMED_RESPONSES(_r) \ +#define XEN_RING_NR_UNCONSUMED_RESPONSES(_r) \ ((_r)->sring->rsp_prod - (_r)->rsp_cons) -#define RING_HAS_UNCONSUMED_REQUESTS(_r) ({ \ +#define XEN_RING_NR_UNCONSUMED_REQUESTS(_r) ({ \ unsigned int req = (_r)->sring->req_prod - (_r)->req_cons; \ unsigned int rsp = RING_SIZE(_r) - \ ((_r)->req_cons - (_r)->rsp_prod_pvt); \ req < rsp ? req : rsp; \ }) +#define RING_HAS_UNCONSUMED_RESPONSES(_r) \ + (!!XEN_RING_NR_UNCONSUMED_RESPONSES(_r)) +#define RING_HAS_UNCONSUMED_REQUESTS(_r) \ + (!!XEN_RING_NR_UNCONSUMED_REQUESTS(_r)) + /* Direct access to individual ring elements, by index. */ #define RING_GET_REQUEST(_r, _idx) \ (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].req)) -- cgit v1.2.3 From 7050096d07755c53f71e486af18475050cc4e04b Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 28 Apr 2022 09:01:03 +0200 Subject: xen/xenbus: add xenbus_setup_ring() service function Most PV device frontends share very similar code for setting up shared ring buffers: - allocate page(s) - init the ring admin data - give the backend access to the ring via grants Tearing down the ring requires similar actions in all frontends again: - remove grants - free the page(s) Provide service functions xenbus_setup_ring() and xenbus_teardown_ring() for that purpose. Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Signed-off-by: Juergen Gross --- include/xen/xenbus.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index b13eb86395e0..b533b4adc835 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -226,6 +226,10 @@ int xenbus_watch_pathfmt(struct xenbus_device *dev, struct xenbus_watch *watch, int xenbus_switch_state(struct xenbus_device *dev, enum xenbus_state new_state); int xenbus_grant_ring(struct xenbus_device *dev, void *vaddr, unsigned int nr_pages, grant_ref_t *grefs); +int xenbus_setup_ring(struct xenbus_device *dev, gfp_t gfp, void **vaddr, + unsigned int nr_pages, grant_ref_t *grefs); +void xenbus_teardown_ring(void **vaddr, unsigned int nr_pages, + grant_ref_t *grefs); int xenbus_map_ring_valloc(struct xenbus_device *dev, grant_ref_t *gnt_refs, unsigned int nr_grefs, void **vaddr); -- cgit v1.2.3 From 4573240f0764ee79d7558d74fc535baa1e110d20 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 28 Apr 2022 09:01:05 +0200 Subject: xen/xenbus: eliminate xenbus_grant_ring() There is no external user of xenbus_grant_ring() left, so merge it into the only caller xenbus_setup_ring(). Signed-off-by: Juergen Gross Reviewed-by: Oleksandr Tyshchenko Reviewed-by: Boris Ostrovsky Signed-off-by: Juergen Gross --- include/xen/xenbus.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index b533b4adc835..eaa932b99d8a 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -224,8 +224,6 @@ int xenbus_watch_pathfmt(struct xenbus_device *dev, struct xenbus_watch *watch, const char *pathfmt, ...); int xenbus_switch_state(struct xenbus_device *dev, enum xenbus_state new_state); -int xenbus_grant_ring(struct xenbus_device *dev, void *vaddr, - unsigned int nr_pages, grant_ref_t *grefs); int xenbus_setup_ring(struct xenbus_device *dev, gfp_t gfp, void **vaddr, unsigned int nr_pages, grant_ref_t *grefs); void xenbus_teardown_ring(void **vaddr, unsigned int nr_pages, -- cgit v1.2.3 From 62db0fafa8fc0f6c9f901e7eefdfc6bbd9731ec9 Mon Sep 17 00:00:00 2001 From: Stefano Stabellini Date: Fri, 13 May 2022 14:19:37 -0700 Subject: xen: sync xs_wire.h header with upstream xen Sync the xs_wire.h header file in Linux with the one in Xen. Signed-off-by: Stefano Stabellini Reviewed-by: Boris Ostrovsky Link: https://lore.kernel.org/r/20220513211938.719341-1-sstabellini@kernel.org Signed-off-by: Juergen Gross --- include/xen/interface/io/xs_wire.h | 37 +++++++++++++++++++++++++++++++++---- 1 file changed, 33 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/xen/interface/io/xs_wire.h b/include/xen/interface/io/xs_wire.h index d40a44f09b16..b62365478ac0 100644 --- a/include/xen/interface/io/xs_wire.h +++ b/include/xen/interface/io/xs_wire.h @@ -10,7 +10,8 @@ enum xsd_sockmsg_type { - XS_DEBUG, + XS_CONTROL, +#define XS_DEBUG XS_CONTROL XS_DIRECTORY, XS_READ, XS_GET_PERMS, @@ -30,8 +31,13 @@ enum xsd_sockmsg_type XS_IS_DOMAIN_INTRODUCED, XS_RESUME, XS_SET_TARGET, - XS_RESTRICT, - XS_RESET_WATCHES, + /* XS_RESTRICT has been removed */ + XS_RESET_WATCHES = XS_SET_TARGET + 2, + XS_DIRECTORY_PART, + + XS_TYPE_COUNT, /* Number of valid types. */ + + XS_INVALID = 0xffff /* Guaranteed to remain an invalid type */ }; #define XS_WRITE_NONE "NONE" @@ -59,7 +65,8 @@ static struct xsd_errors xsd_errors[] __attribute__((unused)) = { XSD_ERROR(EROFS), XSD_ERROR(EBUSY), XSD_ERROR(EAGAIN), - XSD_ERROR(EISCONN) + XSD_ERROR(EISCONN), + XSD_ERROR(E2BIG) }; struct xsd_sockmsg @@ -87,9 +94,31 @@ struct xenstore_domain_interface { char rsp[XENSTORE_RING_SIZE]; /* Replies and async watch events. */ XENSTORE_RING_IDX req_cons, req_prod; XENSTORE_RING_IDX rsp_cons, rsp_prod; + uint32_t server_features; /* Bitmap of features supported by the server */ + uint32_t connection; + uint32_t error; }; /* Violating this is very bad. See docs/misc/xenstore.txt. */ #define XENSTORE_PAYLOAD_MAX 4096 +/* Violating these just gets you an error back */ +#define XENSTORE_ABS_PATH_MAX 3072 +#define XENSTORE_REL_PATH_MAX 2048 + +/* The ability to reconnect a ring */ +#define XENSTORE_SERVER_FEATURE_RECONNECTION 1 +/* The presence of the "error" field in the ring page */ +#define XENSTORE_SERVER_FEATURE_ERROR 2 + +/* Valid values for the connection field */ +#define XENSTORE_CONNECTED 0 /* the steady-state */ +#define XENSTORE_RECONNECT 1 /* guest has initiated a reconnect */ + +/* Valid values for the error field */ +#define XENSTORE_ERROR_NONE 0 /* No error */ +#define XENSTORE_ERROR_COMM 1 /* Communication problem */ +#define XENSTORE_ERROR_RINGIDX 2 /* Invalid ring index */ +#define XENSTORE_ERROR_PROTO 3 /* Protocol violation (payload too long) */ + #endif /* _XS_WIRE_H */ -- cgit v1.2.3 From 81557a71564a8c44ee5b9262d08438b0170a25f3 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Tue, 17 May 2022 10:39:56 +0200 Subject: dt-bindings: pinctrl: Add MediaTek MT6795 pinctrl bindings Add devicetree and pinfunc bindings for MediaTek Helio X10 MT6795. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20220517083957.11816-2-angelogioacchino.delregno@collabora.com Signed-off-by: Linus Walleij --- include/dt-bindings/pinctrl/mt6795-pinfunc.h | 908 +++++++++++++++++++++++++++ 1 file changed, 908 insertions(+) create mode 100644 include/dt-bindings/pinctrl/mt6795-pinfunc.h (limited to 'include') diff --git a/include/dt-bindings/pinctrl/mt6795-pinfunc.h b/include/dt-bindings/pinctrl/mt6795-pinfunc.h new file mode 100644 index 000000000000..bd1c5a9fad06 --- /dev/null +++ b/include/dt-bindings/pinctrl/mt6795-pinfunc.h @@ -0,0 +1,908 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2022 Collabora Ltd. + * Author: AngeloGioacchino Del Regno + */ + +#ifndef __DTS_MT8173_PINFUNC_H +#define __DTS_MT8173_PINFUNC_H + +#include + +#define PINMUX_GPIO0__FUNC_GPIO0 (MTK_PIN_NO(0) | 0) +#define PINMUX_GPIO0__FUNC_IRDA_PDN (MTK_PIN_NO(0) | 1) +#define PINMUX_GPIO0__FUNC_I2S1_WS (MTK_PIN_NO(0) | 2) +#define PINMUX_GPIO0__FUNC_TDD_TMS (MTK_PIN_NO(0) | 4) +#define PINMUX_GPIO0__FUNC_UTXD0 (MTK_PIN_NO(0) | 5) + +#define PINMUX_GPIO1__FUNC_GPIO1 (MTK_PIN_NO(1) | 0) +#define PINMUX_GPIO1__FUNC_IRDA_RXD (MTK_PIN_NO(1) | 1) +#define PINMUX_GPIO1__FUNC_I2S1_BCK (MTK_PIN_NO(1) | 2) +#define PINMUX_GPIO1__FUNC_SDA4 (MTK_PIN_NO(1) | 3) +#define PINMUX_GPIO1__FUNC_TDD_TCK (MTK_PIN_NO(1) | 4) +#define PINMUX_GPIO1__FUNC_URXD0 (MTK_PIN_NO(1) | 5) + +#define PINMUX_GPIO2__FUNC_GPIO2 (MTK_PIN_NO(2) | 0) +#define PINMUX_GPIO2__FUNC_IRDA_TXD (MTK_PIN_NO(2) | 1) +#define PINMUX_GPIO2__FUNC_I2S1_MCK (MTK_PIN_NO(2) | 2) +#define PINMUX_GPIO2__FUNC_SCL4 (MTK_PIN_NO(2) | 3) +#define PINMUX_GPIO2__FUNC_TDD_TDI (MTK_PIN_NO(2) | 4) +#define PINMUX_GPIO2__FUNC_UTXD3 (MTK_PIN_NO(2) | 5) + +#define PINMUX_GPIO3__FUNC_GPIO3 (MTK_PIN_NO(3) | 0) +#define PINMUX_GPIO3__FUNC_DSI1_TE (MTK_PIN_NO(3) | 1) +#define PINMUX_GPIO3__FUNC_I2S1_DO_1 (MTK_PIN_NO(3) | 2) +#define PINMUX_GPIO3__FUNC_SDA3 (MTK_PIN_NO(3) | 3) +#define PINMUX_GPIO3__FUNC_TDD_TDO (MTK_PIN_NO(3) | 4) +#define PINMUX_GPIO3__FUNC_URXD3 (MTK_PIN_NO(3) | 5) + +#define PINMUX_GPIO4__FUNC_GPIO4 (MTK_PIN_NO(4) | 0) +#define PINMUX_GPIO4__FUNC_DISP_PWM1 (MTK_PIN_NO(4) | 1) +#define PINMUX_GPIO4__FUNC_I2S1_DO_2 (MTK_PIN_NO(4) | 2) +#define PINMUX_GPIO4__FUNC_SCL3 (MTK_PIN_NO(4) | 3) +#define PINMUX_GPIO4__FUNC_TDD_TRSTN (MTK_PIN_NO(4) | 4) + +#define PINMUX_GPIO5__FUNC_GPIO5 (MTK_PIN_NO(5) | 0) +#define PINMUX_GPIO5__FUNC_PCM1_CLK (MTK_PIN_NO(5) | 1) +#define PINMUX_GPIO5__FUNC_I2S2_WS (MTK_PIN_NO(5) | 2) +#define PINMUX_GPIO5__FUNC_SPI_CK_3 (MTK_PIN_NO(5) | 3) +#define PINMUX_GPIO5__FUNC_LTE_MD32_JTAG_TMS (MTK_PIN_NO(5) | 4) +#define PINMUX_GPIO5__FUNC_AP_MD32_JTAG_TMS (MTK_PIN_NO(5) | 5) + +#define PINMUX_GPIO6__FUNC_GPIO6 (MTK_PIN_NO(6) | 0) +#define PINMUX_GPIO6__FUNC_PCM1_SYNC (MTK_PIN_NO(6) | 1) +#define PINMUX_GPIO6__FUNC_I2S2_BCK (MTK_PIN_NO(6) | 2) +#define PINMUX_GPIO6__FUNC_SPI_MI_3 (MTK_PIN_NO(6) | 3) +#define PINMUX_GPIO6__FUNC_LTE_MD32_JTAG_TCK (MTK_PIN_NO(6) | 4) +#define PINMUX_GPIO6__FUNC_AP_MD32_JTAG_TCK (MTK_PIN_NO(6) | 5) + +#define PINMUX_GPIO7__FUNC_GPIO7 (MTK_PIN_NO(7) | 0) +#define PINMUX_GPIO7__FUNC_PCM1_DI (MTK_PIN_NO(7) | 1) +#define PINMUX_GPIO7__FUNC_I2S2_DI_1 (MTK_PIN_NO(7) | 2) +#define PINMUX_GPIO7__FUNC_SPI_MO_3 (MTK_PIN_NO(7) | 3) +#define PINMUX_GPIO7__FUNC_LTE_MD32_JTAG_TDI (MTK_PIN_NO(7) | 4) +#define PINMUX_GPIO7__FUNC_AP_MD32_JTAG_TDI (MTK_PIN_NO(7) | 5) + +#define PINMUX_GPIO8__FUNC_GPIO8 (MTK_PIN_NO(8) | 0) +#define PINMUX_GPIO8__FUNC_PCM1_DO (MTK_PIN_NO(8) | 1) +#define PINMUX_GPIO8__FUNC_I2S2_DI_2 (MTK_PIN_NO(8) | 2) +#define PINMUX_GPIO8__FUNC_SPI_CS_3 (MTK_PIN_NO(8) | 3) +#define PINMUX_GPIO8__FUNC_LTE_MD32_JTAG_TDO (MTK_PIN_NO(8) | 4) +#define PINMUX_GPIO8__FUNC_AP_MD32_JTAG_TDO (MTK_PIN_NO(8) | 5) + +#define PINMUX_GPIO9__FUNC_GPIO9 (MTK_PIN_NO(9) | 0) +#define PINMUX_GPIO9__FUNC_USB_DRVVBUS (MTK_PIN_NO(9) | 1) +#define PINMUX_GPIO9__FUNC_I2S2_MCK (MTK_PIN_NO(9) | 2) +#define PINMUX_GPIO9__FUNC_LTE_MD32_JTAG_TRST (MTK_PIN_NO(9) | 4) +#define PINMUX_GPIO9__FUNC_AP_MD32_JTAG_TRST (MTK_PIN_NO(9) | 5) + +#define PINMUX_GPIO10__FUNC_GPIO10 (MTK_PIN_NO(10) | 0) +#define PINMUX_GPIO10__FUNC_I2S0_WS (MTK_PIN_NO(10) | 2) + +#define PINMUX_GPIO11__FUNC_GPIO11 (MTK_PIN_NO(11) | 0) +#define PINMUX_GPIO11__FUNC_I2S0_BCK (MTK_PIN_NO(11) | 2) + +#define PINMUX_GPIO12__FUNC_GPIO12 (MTK_PIN_NO(12) | 0) +#define PINMUX_GPIO12__FUNC_I2S0_MCK (MTK_PIN_NO(12) | 2) + +#define PINMUX_GPIO13__FUNC_GPIO13 (MTK_PIN_NO(13) | 0) +#define PINMUX_GPIO13__FUNC_I2S0_DO (MTK_PIN_NO(13) | 2) + +#define PINMUX_GPIO14__FUNC_GPIO14 (MTK_PIN_NO(14) | 0) +#define PINMUX_GPIO14__FUNC_I2S0_DI (MTK_PIN_NO(14) | 2) +#define PINMUX_GPIO14__FUNC_DISP_PWM1 (MTK_PIN_NO(14) | 3) +#define PINMUX_GPIO14__FUNC_PWM4 (MTK_PIN_NO(14) | 4) +#define PINMUX_GPIO14__FUNC_IRDA_RXD (MTK_PIN_NO(14) | 5) +#define PINMUX_GPIO14__FUNC_I2S1_BCK (MTK_PIN_NO(14) | 6) + +#define PINMUX_GPIO15__FUNC_GPIO15 (MTK_PIN_NO(15) | 0) +#define PINMUX_GPIO15__FUNC_DSI1_TE (MTK_PIN_NO(15) | 2) +#define PINMUX_GPIO15__FUNC_USB_DRVVBUS (MTK_PIN_NO(15) | 3) +#define PINMUX_GPIO15__FUNC_PWM5 (MTK_PIN_NO(15) | 4) +#define PINMUX_GPIO15__FUNC_IRDA_TXD (MTK_PIN_NO(15) | 5) +#define PINMUX_GPIO15__FUNC_I2S1_MCK (MTK_PIN_NO(15) | 6) + +#define PINMUX_GPIO16__FUNC_GPIO16 (MTK_PIN_NO(16) | 0) +#define PINMUX_GPIO16__FUNC_IDDIG (MTK_PIN_NO(16) | 1) +#define PINMUX_GPIO16__FUNC_FLASH (MTK_PIN_NO(16) | 2) +#define PINMUX_GPIO16__FUNC_EXT_FRAME_SYNC (MTK_PIN_NO(16) | 3) +#define PINMUX_GPIO16__FUNC_PWM5 (MTK_PIN_NO(16) | 4) + +#define PINMUX_GPIO17__FUNC_GPIO17 (MTK_PIN_NO(17) | 0) +#define PINMUX_GPIO17__FUNC_SIM1_SCLK (MTK_PIN_NO(17) | 1) +#define PINMUX_GPIO17__FUNC_SIM2_SCLK (MTK_PIN_NO(17) | 2) + +#define PINMUX_GPIO18__FUNC_GPIO18 (MTK_PIN_NO(18) | 0) +#define PINMUX_GPIO18__FUNC_SIM1_SRST (MTK_PIN_NO(18) | 1) +#define PINMUX_GPIO18__FUNC_SIM2_SRST (MTK_PIN_NO(18) | 2) + +#define PINMUX_GPIO19__FUNC_GPIO19 (MTK_PIN_NO(19) | 0) +#define PINMUX_GPIO19__FUNC_SIM1_SDAT (MTK_PIN_NO(19) | 1) +#define PINMUX_GPIO19__FUNC_SIM2_SDAT (MTK_PIN_NO(19) | 2) + +#define PINMUX_GPIO20__FUNC_GPIO20 (MTK_PIN_NO(20) | 0) +#define PINMUX_GPIO20__FUNC_SIM2_SCLK (MTK_PIN_NO(20) | 1) +#define PINMUX_GPIO20__FUNC_SIM1_SCLK (MTK_PIN_NO(20) | 2) + +#define PINMUX_GPIO21__FUNC_GPIO21 (MTK_PIN_NO(21) | 0) +#define PINMUX_GPIO21__FUNC_SIM2_SRST (MTK_PIN_NO(21) | 1) +#define PINMUX_GPIO21__FUNC_SIM1_SRST (MTK_PIN_NO(21) | 2) + +#define PINMUX_GPIO22__FUNC_GPIO22 (MTK_PIN_NO(22) | 0) +#define PINMUX_GPIO22__FUNC_SIM2_SDAT (MTK_PIN_NO(22) | 1) +#define PINMUX_GPIO22__FUNC_SIM1_SDAT (MTK_PIN_NO(22) | 2) + +#define PINMUX_GPIO23__FUNC_GPIO23 (MTK_PIN_NO(23) | 0) +#define PINMUX_GPIO23__FUNC_MSDC3_DAT0 (MTK_PIN_NO(23) | 1) + +#define PINMUX_GPIO24__FUNC_GPIO24 (MTK_PIN_NO(24) | 0) +#define PINMUX_GPIO24__FUNC_MSDC3_DAT1 (MTK_PIN_NO(24) | 1) + +#define PINMUX_GPIO25__FUNC_GPIO25 (MTK_PIN_NO(25) | 0) +#define PINMUX_GPIO25__FUNC_MSDC3_DAT2 (MTK_PIN_NO(25) | 1) + +#define PINMUX_GPIO26__FUNC_GPIO26 (MTK_PIN_NO(26) | 0) +#define PINMUX_GPIO26__FUNC_MSDC3_DAT3 (MTK_PIN_NO(26) | 1) + +#define PINMUX_GPIO27__FUNC_GPIO27 (MTK_PIN_NO(27) | 0) +#define PINMUX_GPIO27__FUNC_MSDC3_CLK (MTK_PIN_NO(27) | 1) + +#define PINMUX_GPIO28__FUNC_GPIO28 (MTK_PIN_NO(28) | 0) +#define PINMUX_GPIO28__FUNC_MSDC3_CMD (MTK_PIN_NO(28) | 1) + +#define PINMUX_GPIO29__FUNC_GPIO29 (MTK_PIN_NO(29) | 0) +#define PINMUX_GPIO29__FUNC_PTA_RXD (MTK_PIN_NO(29) | 1) +#define PINMUX_GPIO29__FUNC_UCTS2 (MTK_PIN_NO(29) | 2) + +#define PINMUX_GPIO30__FUNC_GPIO30 (MTK_PIN_NO(30) | 0) +#define PINMUX_GPIO30__FUNC_PTA_TXD (MTK_PIN_NO(30) | 1) +#define PINMUX_GPIO30__FUNC_URTS2 (MTK_PIN_NO(30) | 2) + +#define PINMUX_GPIO31__FUNC_GPIO31 (MTK_PIN_NO(31) | 0) +#define PINMUX_GPIO31__FUNC_URXD2 (MTK_PIN_NO(31) | 1) +#define PINMUX_GPIO31__FUNC_UTXD2 (MTK_PIN_NO(31) | 2) + +#define PINMUX_GPIO32__FUNC_GPIO32 (MTK_PIN_NO(32) | 0) +#define PINMUX_GPIO32__FUNC_UTXD2 (MTK_PIN_NO(32) | 1) +#define PINMUX_GPIO32__FUNC_URXD2 (MTK_PIN_NO(32) | 2) + +#define PINMUX_GPIO33__FUNC_GPIO33 (MTK_PIN_NO(33) | 0) +#define PINMUX_GPIO33__FUNC_MRG_CLK (MTK_PIN_NO(33) | 1) +#define PINMUX_GPIO33__FUNC_PCM0_CLK (MTK_PIN_NO(33) | 2) + +#define PINMUX_GPIO34__FUNC_GPIO34 (MTK_PIN_NO(34) | 0) +#define PINMUX_GPIO34__FUNC_MRG_DI (MTK_PIN_NO(34) | 1) +#define PINMUX_GPIO34__FUNC_PCM0_DI (MTK_PIN_NO(34) | 2) + +#define PINMUX_GPIO35__FUNC_GPIO35 (MTK_PIN_NO(35) | 0) +#define PINMUX_GPIO35__FUNC_MRG_DO (MTK_PIN_NO(35) | 1) +#define PINMUX_GPIO35__FUNC_PCM0_DO (MTK_PIN_NO(35) | 2) + +#define PINMUX_GPIO36__FUNC_GPIO36 (MTK_PIN_NO(36) | 0) +#define PINMUX_GPIO36__FUNC_MRG_SYNC (MTK_PIN_NO(36) | 1) +#define PINMUX_GPIO36__FUNC_PCM0_SYNC (MTK_PIN_NO(36) | 2) + +#define PINMUX_GPIO37__FUNC_GPIO37 (MTK_PIN_NO(37) | 0) +#define PINMUX_GPIO37__FUNC_GPS_SYNC (MTK_PIN_NO(37) | 1) + +#define PINMUX_GPIO38__FUNC_GPIO38 (MTK_PIN_NO(38) | 0) +#define PINMUX_GPIO38__FUNC_DAIRSTB (MTK_PIN_NO(38) | 1) + +#define PINMUX_GPIO39__FUNC_GPIO39 (MTK_PIN_NO(39) | 0) +#define PINMUX_GPIO39__FUNC_CM2MCLK (MTK_PIN_NO(39) | 1) + +#define PINMUX_GPIO40__FUNC_GPIO40 (MTK_PIN_NO(40) | 0) +#define PINMUX_GPIO40__FUNC_CM3MCLK (MTK_PIN_NO(40) | 1) +#define PINMUX_GPIO40__FUNC_IRDA_PDN (MTK_PIN_NO(40) | 2) +#define PINMUX_GPIO40__FUNC_PWM6 (MTK_PIN_NO(40) | 3) +#define PINMUX_GPIO40__FUNC_I2S1_WS (MTK_PIN_NO(40) | 4) + +#define PINMUX_GPIO41__FUNC_GPIO41 (MTK_PIN_NO(41) | 0) +#define PINMUX_GPIO41__FUNC_CMPCLK (MTK_PIN_NO(41) | 1) +#define PINMUX_GPIO41__FUNC_CMCSK (MTK_PIN_NO(41) | 2) +#define PINMUX_GPIO41__FUNC_FLASH (MTK_PIN_NO(41) | 3) + +#define PINMUX_GPIO42__FUNC_GPIO42 (MTK_PIN_NO(42) | 0) +#define PINMUX_GPIO42__FUNC_CMMCLK (MTK_PIN_NO(42) | 1) + +#define PINMUX_GPIO43__FUNC_GPIO43 (MTK_PIN_NO(43) | 0) +#define PINMUX_GPIO43__FUNC_SDA2 (MTK_PIN_NO(43) | 1) + +#define PINMUX_GPIO44__FUNC_GPIO44 (MTK_PIN_NO(44) | 0) +#define PINMUX_GPIO44__FUNC_SCL2 (MTK_PIN_NO(44) | 1) + +#define PINMUX_GPIO45__FUNC_GPIO45 (MTK_PIN_NO(45) | 0) +#define PINMUX_GPIO45__FUNC_SDA0 (MTK_PIN_NO(45) | 1) + +#define PINMUX_GPIO46__FUNC_GPIO46 (MTK_PIN_NO(46) | 0) +#define PINMUX_GPIO46__FUNC_SCL0 (MTK_PIN_NO(46) | 1) + +#define PINMUX_GPIO47__FUNC_GPIO47 (MTK_PIN_NO(47) | 0) +#define PINMUX_GPIO47__FUNC_BPI_BUS0 (MTK_PIN_NO(47) | 1) + +#define PINMUX_GPIO48__FUNC_GPIO48 (MTK_PIN_NO(48) | 0) +#define PINMUX_GPIO48__FUNC_BPI_BUS1 (MTK_PIN_NO(48) | 1) + +#define PINMUX_GPIO49__FUNC_GPIO49 (MTK_PIN_NO(49) | 0) +#define PINMUX_GPIO49__FUNC_BPI_BUS2 (MTK_PIN_NO(49) | 1) + +#define PINMUX_GPIO50__FUNC_GPIO50 (MTK_PIN_NO(50) | 0) +#define PINMUX_GPIO50__FUNC_BPI_BUS3 (MTK_PIN_NO(50) | 1) + +#define PINMUX_GPIO51__FUNC_GPIO51 (MTK_PIN_NO(51) | 0) +#define PINMUX_GPIO51__FUNC_BPI_BUS4 (MTK_PIN_NO(51) | 1) + +#define PINMUX_GPIO52__FUNC_GPIO52 (MTK_PIN_NO(52) | 0) +#define PINMUX_GPIO52__FUNC_BPI_BUS5 (MTK_PIN_NO(52) | 1) + +#define PINMUX_GPIO53__FUNC_GPIO53 (MTK_PIN_NO(53) | 0) +#define PINMUX_GPIO53__FUNC_BPI_BUS6 (MTK_PIN_NO(53) | 1) + +#define PINMUX_GPIO54__FUNC_GPIO54 (MTK_PIN_NO(54) | 0) +#define PINMUX_GPIO54__FUNC_BPI_BUS7 (MTK_PIN_NO(54) | 1) + +#define PINMUX_GPIO55__FUNC_GPIO55 (MTK_PIN_NO(55) | 0) +#define PINMUX_GPIO55__FUNC_BPI_BUS8 (MTK_PIN_NO(55) | 1) + +#define PINMUX_GPIO56__FUNC_GPIO56 (MTK_PIN_NO(56) | 0) +#define PINMUX_GPIO56__FUNC_BPI_BUS9 (MTK_PIN_NO(56) | 1) + +#define PINMUX_GPIO57__FUNC_GPIO57 (MTK_PIN_NO(57) | 0) +#define PINMUX_GPIO57__FUNC_BPI_BUS10 (MTK_PIN_NO(57) | 1) + +#define PINMUX_GPIO58__FUNC_GPIO58 (MTK_PIN_NO(58) | 0) +#define PINMUX_GPIO58__FUNC_BPI_BUS11 (MTK_PIN_NO(58) | 1) + +#define PINMUX_GPIO59__FUNC_GPIO59 (MTK_PIN_NO(59) | 0) +#define PINMUX_GPIO59__FUNC_BPI_BUS12 (MTK_PIN_NO(59) | 1) + +#define PINMUX_GPIO60__FUNC_GPIO60 (MTK_PIN_NO(60) | 0) +#define PINMUX_GPIO60__FUNC_BPI_BUS13 (MTK_PIN_NO(60) | 1) + +#define PINMUX_GPIO61__FUNC_GPIO61 (MTK_PIN_NO(61) | 0) +#define PINMUX_GPIO61__FUNC_BPI_BUS14 (MTK_PIN_NO(61) | 1) + +#define PINMUX_GPIO62__FUNC_GPIO62 (MTK_PIN_NO(62) | 0) +#define PINMUX_GPIO62__FUNC_RFIC1_BSI_CK (MTK_PIN_NO(62) | 1) + +#define PINMUX_GPIO63__FUNC_GPIO63 (MTK_PIN_NO(63) | 0) +#define PINMUX_GPIO63__FUNC_RFIC1_BSI_D0 (MTK_PIN_NO(63) | 1) + +#define PINMUX_GPIO64__FUNC_GPIO64 (MTK_PIN_NO(64) | 0) +#define PINMUX_GPIO64__FUNC_RFIC1_BSI_D1 (MTK_PIN_NO(64) | 1) + +#define PINMUX_GPIO65__FUNC_GPIO65 (MTK_PIN_NO(65) | 0) +#define PINMUX_GPIO65__FUNC_RFIC1_BSI_D2 (MTK_PIN_NO(65) | 1) + +#define PINMUX_GPIO66__FUNC_GPIO66 (MTK_PIN_NO(66) | 0) +#define PINMUX_GPIO66__FUNC_RFIC1_BSI_CS (MTK_PIN_NO(66) | 1) + +#define PINMUX_GPIO67__FUNC_GPIO67 (MTK_PIN_NO(67) | 0) +#define PINMUX_GPIO67__FUNC_TD_TXBPI (MTK_PIN_NO(67) | 1) + +#define PINMUX_GPIO68__FUNC_GPIO68 (MTK_PIN_NO(68) | 0) +#define PINMUX_GPIO68__FUNC_RFIC0_BSI_CK (MTK_PIN_NO(68) | 1) + +#define PINMUX_GPIO69__FUNC_GPIO69 (MTK_PIN_NO(69) | 0) +#define PINMUX_GPIO69__FUNC_RFIC0_BSI_D0 (MTK_PIN_NO(69) | 1) + +#define PINMUX_GPIO70__FUNC_GPIO70 (MTK_PIN_NO(70) | 0) +#define PINMUX_GPIO70__FUNC_RFIC0_BSI_D1 (MTK_PIN_NO(70) | 1) + +#define PINMUX_GPIO71__FUNC_GPIO71 (MTK_PIN_NO(71) | 0) +#define PINMUX_GPIO71__FUNC_RFIC0_BSI_D2 (MTK_PIN_NO(71) | 1) + +#define PINMUX_GPIO72__FUNC_GPIO72 (MTK_PIN_NO(72) | 0) +#define PINMUX_GPIO72__FUNC_RFIC0_BSI_CS (MTK_PIN_NO(72) | 1) + +#define PINMUX_GPIO73__FUNC_GPIO73 (MTK_PIN_NO(73) | 0) +#define PINMUX_GPIO73__FUNC_MISC_BSI_DO (MTK_PIN_NO(73) | 1) + +#define PINMUX_GPIO74__FUNC_GPIO74 (MTK_PIN_NO(74) | 0) +#define PINMUX_GPIO74__FUNC_MISC_BSI_CK (MTK_PIN_NO(74) | 1) + +#define PINMUX_GPIO75__FUNC_GPIO75 (MTK_PIN_NO(75) | 0) +#define PINMUX_GPIO75__FUNC_MISC_BSI_CS0B (MTK_PIN_NO(75) | 1) +#define PINMUX_GPIO75__FUNC_MIPI1_SCLK (MTK_PIN_NO(75) | 2) + +#define PINMUX_GPIO76__FUNC_GPIO76 (MTK_PIN_NO(76) | 0) +#define PINMUX_GPIO76__FUNC_MISC_BSI_CS1B (MTK_PIN_NO(76) | 1) + +#define PINMUX_GPIO77__FUNC_GPIO77 (MTK_PIN_NO(77) | 0) +#define PINMUX_GPIO77__FUNC_MISC_BSI_DI (MTK_PIN_NO(77) | 1) +#define PINMUX_GPIO77__FUNC_MIPI1_SDATA (MTK_PIN_NO(77) | 2) + +#define PINMUX_GPIO78__FUNC_GPIO78 (MTK_PIN_NO(78) | 0) +#define PINMUX_GPIO78__FUNC_LTE_TXBPI (MTK_PIN_NO(78) | 1) + +#define PINMUX_GPIO79__FUNC_GPIO79 (MTK_PIN_NO(79) | 0) +#define PINMUX_GPIO79__FUNC_BPI_BUS15 (MTK_PIN_NO(79) | 1) + +#define PINMUX_GPIO80__FUNC_GPIO80 (MTK_PIN_NO(80) | 0) +#define PINMUX_GPIO80__FUNC_BPI_BUS16 (MTK_PIN_NO(80) | 1) + +#define PINMUX_GPIO81__FUNC_GPIO81 (MTK_PIN_NO(81) | 0) +#define PINMUX_GPIO81__FUNC_BPI_BUS17 (MTK_PIN_NO(81) | 1) + +#define PINMUX_GPIO82__FUNC_GPIO82 (MTK_PIN_NO(82) | 0) +#define PINMUX_GPIO82__FUNC_BPI_BUS18 (MTK_PIN_NO(82) | 1) + +#define PINMUX_GPIO83__FUNC_GPIO83 (MTK_PIN_NO(83) | 0) +#define PINMUX_GPIO83__FUNC_BPI_BUS19 (MTK_PIN_NO(83) | 1) + +#define PINMUX_GPIO84__FUNC_GPIO84 (MTK_PIN_NO(84) | 0) +#define PINMUX_GPIO84__FUNC_BPI_BUS20 (MTK_PIN_NO(84) | 1) + +#define PINMUX_GPIO85__FUNC_GPIO85 (MTK_PIN_NO(85) | 0) +#define PINMUX_GPIO85__FUNC_BPI_BUS21 (MTK_PIN_NO(85) | 1) + +#define PINMUX_GPIO86__FUNC_GPIO86 (MTK_PIN_NO(86) | 0) +#define PINMUX_GPIO86__FUNC_BPI_BUS22 (MTK_PIN_NO(86) | 1) + +#define PINMUX_GPIO87__FUNC_GPIO87 (MTK_PIN_NO(87) | 0) +#define PINMUX_GPIO87__FUNC_BPI_BUS23 (MTK_PIN_NO(87) | 1) + +#define PINMUX_GPIO88__FUNC_GPIO88 (MTK_PIN_NO(88) | 0) +#define PINMUX_GPIO88__FUNC_BPI_BUS24 (MTK_PIN_NO(88) | 1) + +#define PINMUX_GPIO89__FUNC_GPIO89 (MTK_PIN_NO(89) | 0) +#define PINMUX_GPIO89__FUNC_BPI_BUS25 (MTK_PIN_NO(89) | 1) + +#define PINMUX_GPIO90__FUNC_GPIO90 (MTK_PIN_NO(90) | 0) +#define PINMUX_GPIO90__FUNC_BPI_BUS26 (MTK_PIN_NO(90) | 1) + +#define PINMUX_GPIO91__FUNC_GPIO91 (MTK_PIN_NO(91) | 0) +#define PINMUX_GPIO91__FUNC_BPI_BUS27 (MTK_PIN_NO(91) | 1) + +#define PINMUX_GPIO92__FUNC_GPIO92 (MTK_PIN_NO(92) | 0) +#define PINMUX_GPIO92__FUNC_PCM1_CLK (MTK_PIN_NO(92) | 1) +#define PINMUX_GPIO92__FUNC_I2S0_BCK (MTK_PIN_NO(92) | 2) +#define PINMUX_GPIO92__FUNC_NLD6 (MTK_PIN_NO(92) | 3) + +#define PINMUX_GPIO93__FUNC_GPIO93 (MTK_PIN_NO(93) | 0) +#define PINMUX_GPIO93__FUNC_PCM1_SYNC (MTK_PIN_NO(93) | 1) +#define PINMUX_GPIO93__FUNC_I2S0_WS (MTK_PIN_NO(93) | 2) +#define PINMUX_GPIO93__FUNC_NLD7 (MTK_PIN_NO(93) | 3) + +#define PINMUX_GPIO94__FUNC_GPIO94 (MTK_PIN_NO(94) | 0) +#define PINMUX_GPIO94__FUNC_PCM1_DI (MTK_PIN_NO(94) | 1) +#define PINMUX_GPIO94__FUNC_I2S0_DI (MTK_PIN_NO(94) | 2) +#define PINMUX_GPIO94__FUNC_NREB (MTK_PIN_NO(94) | 3) + +#define PINMUX_GPIO95__FUNC_GPIO95 (MTK_PIN_NO(95) | 0) +#define PINMUX_GPIO95__FUNC_PCM1_DO (MTK_PIN_NO(95) | 1) +#define PINMUX_GPIO95__FUNC_I2S0_DO (MTK_PIN_NO(95) | 2) +#define PINMUX_GPIO95__FUNC_NRNB0 (MTK_PIN_NO(95) | 3) + +#define PINMUX_GPIO96__FUNC_GPIO96 (MTK_PIN_NO(96) | 0) +#define PINMUX_GPIO96__FUNC_URXD1 (MTK_PIN_NO(96) | 1) +#define PINMUX_GPIO96__FUNC_UTXD1 (MTK_PIN_NO(96) | 2) +#define PINMUX_GPIO96__FUNC_NWEB (MTK_PIN_NO(96) | 3) + +#define PINMUX_GPIO97__FUNC_GPIO97 (MTK_PIN_NO(97) | 0) +#define PINMUX_GPIO97__FUNC_UTXD1 (MTK_PIN_NO(97) | 1) +#define PINMUX_GPIO97__FUNC_URXD1 (MTK_PIN_NO(97) | 2) +#define PINMUX_GPIO97__FUNC_NCEB0 (MTK_PIN_NO(97) | 3) + +#define PINMUX_GPIO98__FUNC_GPIO98 (MTK_PIN_NO(98) | 0) +#define PINMUX_GPIO98__FUNC_URTS1 (MTK_PIN_NO(98) | 1) +#define PINMUX_GPIO98__FUNC_UCTS1 (MTK_PIN_NO(98) | 2) +#define PINMUX_GPIO98__FUNC_NALE (MTK_PIN_NO(98) | 3) + +#define PINMUX_GPIO99__FUNC_GPIO99 (MTK_PIN_NO(99) | 0) +#define PINMUX_GPIO99__FUNC_UCTS1 (MTK_PIN_NO(99) | 1) +#define PINMUX_GPIO99__FUNC_URTS1 (MTK_PIN_NO(99) | 2) +#define PINMUX_GPIO99__FUNC_NCLE (MTK_PIN_NO(99) | 3) + +#define PINMUX_GPIO100__FUNC_GPIO100 (MTK_PIN_NO(100) | 0) +#define PINMUX_GPIO100__FUNC_MSDC2_DAT0 (MTK_PIN_NO(100) | 1) +#define PINMUX_GPIO100__FUNC_URXD1 (MTK_PIN_NO(100) | 2) +#define PINMUX_GPIO100__FUNC_USB_DRVVBUS (MTK_PIN_NO(100) | 3) +#define PINMUX_GPIO100__FUNC_SDA4 (MTK_PIN_NO(100) | 4) + +#define PINMUX_GPIO101__FUNC_GPIO101 (MTK_PIN_NO(101) | 0) +#define PINMUX_GPIO101__FUNC_MSDC2_DAT1 (MTK_PIN_NO(101) | 1) +#define PINMUX_GPIO101__FUNC_UTXD1 (MTK_PIN_NO(101) | 2) +#define PINMUX_GPIO101__FUNC_SCL4 (MTK_PIN_NO(101) | 4) + +#define PINMUX_GPIO102__FUNC_GPIO102 (MTK_PIN_NO(102) | 0) +#define PINMUX_GPIO102__FUNC_MSDC2_DAT2 (MTK_PIN_NO(102) | 1) +#define PINMUX_GPIO102__FUNC_URTS1 (MTK_PIN_NO(102) | 2) +#define PINMUX_GPIO102__FUNC_UTXD0 (MTK_PIN_NO(102) | 3) +#define PINMUX_GPIO102__FUNC_PWM0 (MTK_PIN_NO(102) | 5) +#define PINMUX_GPIO102__FUNC_SPI_CK_1 (MTK_PIN_NO(102) | 6) + +#define PINMUX_GPIO103__FUNC_GPIO103 (MTK_PIN_NO(103) | 0) +#define PINMUX_GPIO103__FUNC_MSDC2_DAT3 (MTK_PIN_NO(103) | 1) +#define PINMUX_GPIO103__FUNC_UCTS1 (MTK_PIN_NO(103) | 2) +#define PINMUX_GPIO103__FUNC_URXD0 (MTK_PIN_NO(103) | 3) +#define PINMUX_GPIO103__FUNC_PWM1 (MTK_PIN_NO(103) | 5) +#define PINMUX_GPIO103__FUNC_SPI_MI_1 (MTK_PIN_NO(103) | 6) + +#define PINMUX_GPIO104__FUNC_GPIO104 (MTK_PIN_NO(104) | 0) +#define PINMUX_GPIO104__FUNC_MSDC2_CLK (MTK_PIN_NO(104) | 1) +#define PINMUX_GPIO104__FUNC_NLD4 (MTK_PIN_NO(104) | 2) +#define PINMUX_GPIO104__FUNC_UTXD3 (MTK_PIN_NO(104) | 3) +#define PINMUX_GPIO104__FUNC_SDA3 (MTK_PIN_NO(104) | 4) +#define PINMUX_GPIO104__FUNC_PWM2 (MTK_PIN_NO(104) | 5) +#define PINMUX_GPIO104__FUNC_SPI_MO_1 (MTK_PIN_NO(104) | 6) + +#define PINMUX_GPIO105__FUNC_GPIO105 (MTK_PIN_NO(105) | 0) +#define PINMUX_GPIO105__FUNC_MSDC2_CMD (MTK_PIN_NO(105) | 1) +#define PINMUX_GPIO105__FUNC_NLD5 (MTK_PIN_NO(105) | 2) +#define PINMUX_GPIO105__FUNC_URXD3 (MTK_PIN_NO(105) | 3) +#define PINMUX_GPIO105__FUNC_SCL3 (MTK_PIN_NO(105) | 4) +#define PINMUX_GPIO105__FUNC_PWM3 (MTK_PIN_NO(105) | 5) +#define PINMUX_GPIO105__FUNC_SPI_CS_1 (MTK_PIN_NO(105) | 6) + +#define PINMUX_GPIO106__FUNC_GPIO106 (MTK_PIN_NO(106) | 0) +#define PINMUX_GPIO106__FUNC_LCM_RST (MTK_PIN_NO(106) | 1) + +#define PINMUX_GPIO107__FUNC_GPIO107 (MTK_PIN_NO(107) | 0) +#define PINMUX_GPIO107__FUNC_DSI_TE (MTK_PIN_NO(107) | 1) + +#define PINMUX_GPIO108__FUNC_GPIO108 (MTK_PIN_NO(108) | 0) +#define PINMUX_GPIO108__FUNC_JTMS (MTK_PIN_NO(108) | 1) +#define PINMUX_GPIO108__FUNC_MFG_JTAG_TMS (MTK_PIN_NO(108) | 2) +#define PINMUX_GPIO108__FUNC_TDD_TMS (MTK_PIN_NO(108) | 3) +#define PINMUX_GPIO108__FUNC_LTE_MD32_JTAG_TMS (MTK_PIN_NO(108) | 4) +#define PINMUX_GPIO108__FUNC_AP_MD32_JTAG_TMS (MTK_PIN_NO(108) | 5) +#define PINMUX_GPIO108__FUNC_DFD_TMS (MTK_PIN_NO(108) | 6) + +#define PINMUX_GPIO109__FUNC_GPIO109 (MTK_PIN_NO(109) | 0) +#define PINMUX_GPIO109__FUNC_JTCK (MTK_PIN_NO(109) | 1) +#define PINMUX_GPIO109__FUNC_MFG_JTAG_TCK (MTK_PIN_NO(109) | 2) +#define PINMUX_GPIO109__FUNC_TDD_TCK (MTK_PIN_NO(109) | 3) +#define PINMUX_GPIO109__FUNC_LTE_MD32_JTAG_TCK (MTK_PIN_NO(109) | 4) +#define PINMUX_GPIO109__FUNC_AP_MD32_JTAG_TCK (MTK_PIN_NO(109) | 5) +#define PINMUX_GPIO109__FUNC_DFD_TCK (MTK_PIN_NO(109) | 6) + +#define PINMUX_GPIO110__FUNC_GPIO110 (MTK_PIN_NO(110) | 0) +#define PINMUX_GPIO110__FUNC_JTDI (MTK_PIN_NO(110) | 1) +#define PINMUX_GPIO110__FUNC_MFG_JTAG_TDI (MTK_PIN_NO(110) | 2) +#define PINMUX_GPIO110__FUNC_TDD_TDI (MTK_PIN_NO(110) | 3) +#define PINMUX_GPIO110__FUNC_LTE_MD32_JTAG_TDI (MTK_PIN_NO(110) | 4) +#define PINMUX_GPIO110__FUNC_AP_MD32_JTAG_TDI (MTK_PIN_NO(110) | 5) +#define PINMUX_GPIO110__FUNC_DFD_TDI (MTK_PIN_NO(110) | 6) + +#define PINMUX_GPIO111__FUNC_GPIO111 (MTK_PIN_NO(111) | 0) +#define PINMUX_GPIO111__FUNC_JTDO (MTK_PIN_NO(111) | 1) +#define PINMUX_GPIO111__FUNC_MFG_JTAG_TDO (MTK_PIN_NO(111) | 2) +#define PINMUX_GPIO111__FUNC_TDD_TDO (MTK_PIN_NO(111) | 3) +#define PINMUX_GPIO111__FUNC_LTE_MD32_JTAG_TDO (MTK_PIN_NO(111) | 4) +#define PINMUX_GPIO111__FUNC_AP_MD32_JTAG_TDO (MTK_PIN_NO(111) | 5) +#define PINMUX_GPIO111__FUNC_DFD_TDO (MTK_PIN_NO(111) | 6) + +#define PINMUX_GPIO112__FUNC_GPIO112 (MTK_PIN_NO(112) | 0) +#define PINMUX_GPIO112__FUNC_JTRST_B (MTK_PIN_NO(112) | 1) +#define PINMUX_GPIO112__FUNC_MFG_JTAG_TRSTN (MTK_PIN_NO(112) | 2) +#define PINMUX_GPIO112__FUNC_TDD_TRSTN (MTK_PIN_NO(112) | 3) +#define PINMUX_GPIO112__FUNC_LTE_MD32_JTAG_TRST (MTK_PIN_NO(112) | 4) +#define PINMUX_GPIO112__FUNC_AP_MD32_JTAG_TRST (MTK_PIN_NO(112) | 5) +#define PINMUX_GPIO112__FUNC_DFD_NTRST (MTK_PIN_NO(112) | 6) + +#define PINMUX_GPIO113__FUNC_GPIO113 (MTK_PIN_NO(113) | 0) +#define PINMUX_GPIO113__FUNC_URXD0 (MTK_PIN_NO(113) | 1) +#define PINMUX_GPIO113__FUNC_UTXD0 (MTK_PIN_NO(113) | 2) +#define PINMUX_GPIO113__FUNC_MD_URXD (MTK_PIN_NO(113) | 3) +#define PINMUX_GPIO113__FUNC_LTE_URXD (MTK_PIN_NO(113) | 4) +#define PINMUX_GPIO113__FUNC_TDD_TXD (MTK_PIN_NO(113) | 5) +#define PINMUX_GPIO113__FUNC_I2S2_WS (MTK_PIN_NO(113) | 6) + +#define PINMUX_GPIO114__FUNC_GPIO114 (MTK_PIN_NO(114) | 0) +#define PINMUX_GPIO114__FUNC_UTXD0 (MTK_PIN_NO(114) | 1) +#define PINMUX_GPIO114__FUNC_URXD0 (MTK_PIN_NO(114) | 2) +#define PINMUX_GPIO114__FUNC_MD_UTXD (MTK_PIN_NO(114) | 3) +#define PINMUX_GPIO114__FUNC_LTE_UTXD (MTK_PIN_NO(114) | 4) +#define PINMUX_GPIO114__FUNC_TDD_TXD (MTK_PIN_NO(114) | 5) +#define PINMUX_GPIO114__FUNC_I2S2_BCK (MTK_PIN_NO(114) | 6) + +#define PINMUX_GPIO115__FUNC_GPIO115 (MTK_PIN_NO(115) | 0) +#define PINMUX_GPIO115__FUNC_URTS0 (MTK_PIN_NO(115) | 1) +#define PINMUX_GPIO115__FUNC_UCTS0 (MTK_PIN_NO(115) | 2) +#define PINMUX_GPIO115__FUNC_MD_URXD (MTK_PIN_NO(115) | 3) +#define PINMUX_GPIO115__FUNC_LTE_URXD (MTK_PIN_NO(115) | 4) +#define PINMUX_GPIO115__FUNC_TDD_TXD (MTK_PIN_NO(115) | 5) +#define PINMUX_GPIO115__FUNC_I2S2_MCK (MTK_PIN_NO(115) | 6) + +#define PINMUX_GPIO116__FUNC_GPIO116 (MTK_PIN_NO(116) | 0) +#define PINMUX_GPIO116__FUNC_UCTS0 (MTK_PIN_NO(116) | 1) +#define PINMUX_GPIO116__FUNC_URTS0 (MTK_PIN_NO(116) | 2) +#define PINMUX_GPIO116__FUNC_MD_UTXD (MTK_PIN_NO(116) | 3) +#define PINMUX_GPIO116__FUNC_LTE_UTXD (MTK_PIN_NO(116) | 4) +#define PINMUX_GPIO116__FUNC_TDD_TXD (MTK_PIN_NO(116) | 5) +#define PINMUX_GPIO116__FUNC_I2S2_DI_1 (MTK_PIN_NO(116) | 6) + +#define PINMUX_GPIO117__FUNC_GPIO117 (MTK_PIN_NO(117) | 0) +#define PINMUX_GPIO117__FUNC_URXD3 (MTK_PIN_NO(117) | 1) +#define PINMUX_GPIO117__FUNC_UTXD3 (MTK_PIN_NO(117) | 2) +#define PINMUX_GPIO117__FUNC_MD_URXD (MTK_PIN_NO(117) | 3) +#define PINMUX_GPIO117__FUNC_LTE_URXD (MTK_PIN_NO(117) | 4) +#define PINMUX_GPIO117__FUNC_TDD_TXD (MTK_PIN_NO(117) | 5) + +#define PINMUX_GPIO118__FUNC_GPIO118 (MTK_PIN_NO(118) | 0) +#define PINMUX_GPIO118__FUNC_UTXD3 (MTK_PIN_NO(118) | 1) +#define PINMUX_GPIO118__FUNC_URXD3 (MTK_PIN_NO(118) | 2) +#define PINMUX_GPIO118__FUNC_MD_UTXD (MTK_PIN_NO(118) | 3) +#define PINMUX_GPIO118__FUNC_LTE_UTXD (MTK_PIN_NO(118) | 4) +#define PINMUX_GPIO118__FUNC_TDD_TXD (MTK_PIN_NO(118) | 5) + +#define PINMUX_GPIO119__FUNC_GPIO119 (MTK_PIN_NO(119) | 0) +#define PINMUX_GPIO119__FUNC_KROW0 (MTK_PIN_NO(119) | 1) + +#define PINMUX_GPIO120__FUNC_GPIO120 (MTK_PIN_NO(120) | 0) +#define PINMUX_GPIO120__FUNC_KROW1 (MTK_PIN_NO(120) | 1) +#define PINMUX_GPIO120__FUNC_PWM6 (MTK_PIN_NO(120) | 3) + +#define PINMUX_GPIO121__FUNC_GPIO121 (MTK_PIN_NO(121) | 0) +#define PINMUX_GPIO121__FUNC_KROW2 (MTK_PIN_NO(121) | 1) +#define PINMUX_GPIO121__FUNC_IRDA_PDN (MTK_PIN_NO(121) | 2) +#define PINMUX_GPIO121__FUNC_I2S1_DO_1 (MTK_PIN_NO(121) | 3) +#define PINMUX_GPIO121__FUNC_USB_DRVVBUS (MTK_PIN_NO(121) | 4) +#define PINMUX_GPIO121__FUNC_SPI_CK_2 (MTK_PIN_NO(121) | 5) +#define PINMUX_GPIO121__FUNC_PWM4 (MTK_PIN_NO(121) | 6) + +#define PINMUX_GPIO122__FUNC_GPIO122 (MTK_PIN_NO(122) | 0) +#define PINMUX_GPIO122__FUNC_KCOL0 (MTK_PIN_NO(122) | 1) + +#define PINMUX_GPIO123__FUNC_GPIO123 (MTK_PIN_NO(123) | 0) +#define PINMUX_GPIO123__FUNC_KCOL1 (MTK_PIN_NO(123) | 1) +#define PINMUX_GPIO123__FUNC_IRDA_RXD (MTK_PIN_NO(123) | 2) +#define PINMUX_GPIO123__FUNC_I2S2_DI_2 (MTK_PIN_NO(123) | 3) +#define PINMUX_GPIO123__FUNC_PWM5 (MTK_PIN_NO(123) | 4) + +#define PINMUX_GPIO124__FUNC_GPIO124 (MTK_PIN_NO(124) | 0) +#define PINMUX_GPIO124__FUNC_KCOL2 (MTK_PIN_NO(124) | 1) +#define PINMUX_GPIO124__FUNC_IRDA_TXD (MTK_PIN_NO(124) | 2) +#define PINMUX_GPIO124__FUNC_I2S1_DO_2 (MTK_PIN_NO(124) | 3) +#define PINMUX_GPIO124__FUNC_USB_DRVVBUS (MTK_PIN_NO(124) | 4) +#define PINMUX_GPIO124__FUNC_SPI_MI_2 (MTK_PIN_NO(124) | 5) +#define PINMUX_GPIO124__FUNC_PWM3 (MTK_PIN_NO(124) | 6) + +#define PINMUX_GPIO125__FUNC_GPIO125 (MTK_PIN_NO(125) | 0) +#define PINMUX_GPIO125__FUNC_SDA1 (MTK_PIN_NO(125) | 1) + +#define PINMUX_GPIO126__FUNC_GPIO126 (MTK_PIN_NO(126) | 0) +#define PINMUX_GPIO126__FUNC_SCL1 (MTK_PIN_NO(126) | 1) + +#define PINMUX_GPIO127__FUNC_GPIO127 (MTK_PIN_NO(127) | 0) +#define PINMUX_GPIO127__FUNC_MD_EINT1 (MTK_PIN_NO(127) | 1) +#define PINMUX_GPIO127__FUNC_DISP_PWM1 (MTK_PIN_NO(127) | 2) +#define PINMUX_GPIO127__FUNC_SPI_MO_2 (MTK_PIN_NO(127) | 3) + +#define PINMUX_GPIO128__FUNC_GPIO128 (MTK_PIN_NO(128) | 0) +#define PINMUX_GPIO128__FUNC_MD_EINT2 (MTK_PIN_NO(128) | 1) +#define PINMUX_GPIO128__FUNC_DSI1_TE (MTK_PIN_NO(128) | 2) +#define PINMUX_GPIO128__FUNC_SPI_CS_2 (MTK_PIN_NO(128) | 3) + +#define PINMUX_GPIO129__FUNC_GPIO129 (MTK_PIN_NO(129) | 0) +#define PINMUX_GPIO129__FUNC_I2S3_WS (MTK_PIN_NO(129) | 1) +#define PINMUX_GPIO129__FUNC_I2S2_WS (MTK_PIN_NO(129) | 2) +#define PINMUX_GPIO129__FUNC_PWM0 (MTK_PIN_NO(129) | 3) + +#define PINMUX_GPIO130__FUNC_GPIO130 (MTK_PIN_NO(130) | 0) +#define PINMUX_GPIO130__FUNC_I2S3_BCK (MTK_PIN_NO(130) | 1) +#define PINMUX_GPIO130__FUNC_I2S2_BCK (MTK_PIN_NO(130) | 2) +#define PINMUX_GPIO130__FUNC_PWM1 (MTK_PIN_NO(130) | 3) + +#define PINMUX_GPIO131__FUNC_GPIO131 (MTK_PIN_NO(131) | 0) +#define PINMUX_GPIO131__FUNC_I2S3_MCK (MTK_PIN_NO(131) | 1) +#define PINMUX_GPIO131__FUNC_I2S2_MCK (MTK_PIN_NO(131) | 2) +#define PINMUX_GPIO131__FUNC_PWM2 (MTK_PIN_NO(131) | 3) + +#define PINMUX_GPIO132__FUNC_GPIO132 (MTK_PIN_NO(132) | 0) +#define PINMUX_GPIO132__FUNC_I2S3_DO_1 (MTK_PIN_NO(132) | 1) +#define PINMUX_GPIO132__FUNC_I2S2_DI_1 (MTK_PIN_NO(132) | 2) +#define PINMUX_GPIO132__FUNC_PWM3 (MTK_PIN_NO(132) | 3) + +#define PINMUX_GPIO133__FUNC_GPIO133 (MTK_PIN_NO(133) | 0) +#define PINMUX_GPIO133__FUNC_I2S3_DO_2 (MTK_PIN_NO(133) | 1) +#define PINMUX_GPIO133__FUNC_I2S2_DI_2 (MTK_PIN_NO(133) | 2) +#define PINMUX_GPIO133__FUNC_PWM4 (MTK_PIN_NO(133) | 3) + +#define PINMUX_GPIO134__FUNC_GPIO134 (MTK_PIN_NO(134) | 0) +#define PINMUX_GPIO134__FUNC_I2S3_DO_3 (MTK_PIN_NO(134) | 1) +#define PINMUX_GPIO134__FUNC_DISP_PWM1 (MTK_PIN_NO(134) | 2) +#define PINMUX_GPIO134__FUNC_I2S1_DO_1 (MTK_PIN_NO(134) | 3) +#define PINMUX_GPIO134__FUNC_PWM5 (MTK_PIN_NO(134) | 4) + +#define PINMUX_GPIO135__FUNC_GPIO135 (MTK_PIN_NO(135) | 0) +#define PINMUX_GPIO135__FUNC_I2S3_DO_4 (MTK_PIN_NO(135) | 1) +#define PINMUX_GPIO135__FUNC_DSI1_TE (MTK_PIN_NO(135) | 2) +#define PINMUX_GPIO135__FUNC_I2S1_DO_2 (MTK_PIN_NO(135) | 3) +#define PINMUX_GPIO135__FUNC_PWM6 (MTK_PIN_NO(135) | 4) + +#define PINMUX_GPIO136__FUNC_GPIO136 (MTK_PIN_NO(136) | 0) +#define PINMUX_GPIO136__FUNC_SDA3 (MTK_PIN_NO(136) | 1) + +#define PINMUX_GPIO137__FUNC_GPIO137 (MTK_PIN_NO(137) | 0) +#define PINMUX_GPIO137__FUNC_SCL3 (MTK_PIN_NO(137) | 1) + +#define PINMUX_GPIO138__FUNC_GPIO138 (MTK_PIN_NO(138) | 0) +#define PINMUX_GPIO138__FUNC_DPI_CK (MTK_PIN_NO(138) | 1) +#define PINMUX_GPIO138__FUNC_NLD6 (MTK_PIN_NO(138) | 2) +#define PINMUX_GPIO138__FUNC_UTXD0 (MTK_PIN_NO(138) | 3) +#define PINMUX_GPIO138__FUNC_USB_DRVVBUS (MTK_PIN_NO(138) | 4) +#define PINMUX_GPIO138__FUNC_IRDA_PDN (MTK_PIN_NO(138) | 5) + +#define PINMUX_GPIO139__FUNC_GPIO139 (MTK_PIN_NO(139) | 0) +#define PINMUX_GPIO139__FUNC_DPI_DE (MTK_PIN_NO(139) | 1) +#define PINMUX_GPIO139__FUNC_NLD7 (MTK_PIN_NO(139) | 2) +#define PINMUX_GPIO139__FUNC_URXD0 (MTK_PIN_NO(139) | 3) +#define PINMUX_GPIO139__FUNC_MD_UTXD (MTK_PIN_NO(139) | 4) +#define PINMUX_GPIO139__FUNC_IRDA_RXD (MTK_PIN_NO(139) | 5) + +#define PINMUX_GPIO140__FUNC_GPIO140 (MTK_PIN_NO(140) | 0) +#define PINMUX_GPIO140__FUNC_DPI_D0 (MTK_PIN_NO(140) | 1) +#define PINMUX_GPIO140__FUNC_NREB (MTK_PIN_NO(140) | 2) +#define PINMUX_GPIO140__FUNC_UCTS0 (MTK_PIN_NO(140) | 3) +#define PINMUX_GPIO140__FUNC_MD_URXD (MTK_PIN_NO(140) | 4) +#define PINMUX_GPIO140__FUNC_IRDA_TXD (MTK_PIN_NO(140) | 5) + +#define PINMUX_GPIO141__FUNC_GPIO141 (MTK_PIN_NO(141) | 0) +#define PINMUX_GPIO141__FUNC_DPI_D1 (MTK_PIN_NO(141) | 1) +#define PINMUX_GPIO141__FUNC_NRNB0 (MTK_PIN_NO(141) | 2) +#define PINMUX_GPIO141__FUNC_URTS0 (MTK_PIN_NO(141) | 3) +#define PINMUX_GPIO141__FUNC_LTE_UTXD (MTK_PIN_NO(141) | 4) +#define PINMUX_GPIO141__FUNC_I2S2_WS (MTK_PIN_NO(141) | 5) + +#define PINMUX_GPIO142__FUNC_GPIO142 (MTK_PIN_NO(142) | 0) +#define PINMUX_GPIO142__FUNC_DPI_D2 (MTK_PIN_NO(142) | 1) +#define PINMUX_GPIO142__FUNC_NWEB (MTK_PIN_NO(142) | 2) +#define PINMUX_GPIO142__FUNC_UTXD1 (MTK_PIN_NO(142) | 3) +#define PINMUX_GPIO142__FUNC_LTE_URXD (MTK_PIN_NO(142) | 4) +#define PINMUX_GPIO142__FUNC_I2S2_BCK (MTK_PIN_NO(142) | 5) + +#define PINMUX_GPIO143__FUNC_GPIO143 (MTK_PIN_NO(143) | 0) +#define PINMUX_GPIO143__FUNC_DPI_D3 (MTK_PIN_NO(143) | 1) +#define PINMUX_GPIO143__FUNC_NCEB0 (MTK_PIN_NO(143) | 2) +#define PINMUX_GPIO143__FUNC_URXD1 (MTK_PIN_NO(143) | 3) +#define PINMUX_GPIO143__FUNC_TDD_TXD (MTK_PIN_NO(143) | 4) +#define PINMUX_GPIO143__FUNC_I2S2_MCK (MTK_PIN_NO(143) | 5) + +#define PINMUX_GPIO144__FUNC_GPIO144 (MTK_PIN_NO(144) | 0) +#define PINMUX_GPIO144__FUNC_DPI_D4 (MTK_PIN_NO(144) | 1) +#define PINMUX_GPIO144__FUNC_NALE (MTK_PIN_NO(144) | 2) +#define PINMUX_GPIO144__FUNC_UCTS1 (MTK_PIN_NO(144) | 3) +#define PINMUX_GPIO144__FUNC_TDD_TMS (MTK_PIN_NO(144) | 4) +#define PINMUX_GPIO144__FUNC_I2S2_DI_1 (MTK_PIN_NO(144) | 5) + +#define PINMUX_GPIO145__FUNC_GPIO145 (MTK_PIN_NO(145) | 0) +#define PINMUX_GPIO145__FUNC_DPI_D5 (MTK_PIN_NO(145) | 1) +#define PINMUX_GPIO145__FUNC_NCLE (MTK_PIN_NO(145) | 2) +#define PINMUX_GPIO145__FUNC_URTS1 (MTK_PIN_NO(145) | 3) +#define PINMUX_GPIO145__FUNC_TDD_TCK (MTK_PIN_NO(145) | 4) +#define PINMUX_GPIO145__FUNC_I2S2_DI_2 (MTK_PIN_NO(145) | 5) + +#define PINMUX_GPIO146__FUNC_GPIO146 (MTK_PIN_NO(146) | 0) +#define PINMUX_GPIO146__FUNC_DPI_D6 (MTK_PIN_NO(146) | 1) +#define PINMUX_GPIO146__FUNC_NLD8 (MTK_PIN_NO(146) | 2) +#define PINMUX_GPIO146__FUNC_UTXD2 (MTK_PIN_NO(146) | 3) +#define PINMUX_GPIO146__FUNC_TDD_TDI (MTK_PIN_NO(146) | 4) + +#define PINMUX_GPIO147__FUNC_GPIO147 (MTK_PIN_NO(147) | 0) +#define PINMUX_GPIO147__FUNC_DPI_D7 (MTK_PIN_NO(147) | 1) +#define PINMUX_GPIO147__FUNC_NLD9 (MTK_PIN_NO(147) | 2) +#define PINMUX_GPIO147__FUNC_URXD2 (MTK_PIN_NO(147) | 3) +#define PINMUX_GPIO147__FUNC_TDD_TDO (MTK_PIN_NO(147) | 4) +#define PINMUX_GPIO147__FUNC_I2S1_WS (MTK_PIN_NO(147) | 5) + +#define PINMUX_GPIO148__FUNC_GPIO148 (MTK_PIN_NO(148) | 0) +#define PINMUX_GPIO148__FUNC_DPI_D8 (MTK_PIN_NO(148) | 1) +#define PINMUX_GPIO148__FUNC_NLD10 (MTK_PIN_NO(148) | 2) +#define PINMUX_GPIO148__FUNC_UCTS2 (MTK_PIN_NO(148) | 3) +#define PINMUX_GPIO148__FUNC_TDD_TRSTN (MTK_PIN_NO(148) | 4) +#define PINMUX_GPIO148__FUNC_I2S1_BCK (MTK_PIN_NO(148) | 5) + +#define PINMUX_GPIO149__FUNC_GPIO149 (MTK_PIN_NO(149) | 0) +#define PINMUX_GPIO149__FUNC_DPI_D9 (MTK_PIN_NO(149) | 1) +#define PINMUX_GPIO149__FUNC_NLD11 (MTK_PIN_NO(149) | 2) +#define PINMUX_GPIO149__FUNC_URTS2 (MTK_PIN_NO(149) | 3) +#define PINMUX_GPIO149__FUNC_LTE_MD32_JTAG_TMS (MTK_PIN_NO(149) | 4) +#define PINMUX_GPIO149__FUNC_I2S1_MCK (MTK_PIN_NO(149) | 5) + +#define PINMUX_GPIO150__FUNC_GPIO150 (MTK_PIN_NO(150) | 0) +#define PINMUX_GPIO150__FUNC_DPI_D10 (MTK_PIN_NO(150) | 1) +#define PINMUX_GPIO150__FUNC_NLD12 (MTK_PIN_NO(150) | 2) +#define PINMUX_GPIO150__FUNC_UTXD3 (MTK_PIN_NO(150) | 3) +#define PINMUX_GPIO150__FUNC_LTE_MD32_JTAG_TCK (MTK_PIN_NO(150) | 4) +#define PINMUX_GPIO150__FUNC_I2S1_DO_1 (MTK_PIN_NO(150) | 5) + +#define PINMUX_GPIO151__FUNC_GPIO151 (MTK_PIN_NO(151) | 0) +#define PINMUX_GPIO151__FUNC_DPI_D11 (MTK_PIN_NO(151) | 1) +#define PINMUX_GPIO151__FUNC_NLD13 (MTK_PIN_NO(151) | 2) +#define PINMUX_GPIO151__FUNC_URXD3 (MTK_PIN_NO(151) | 3) +#define PINMUX_GPIO151__FUNC_LTE_MD32_JTAG_TDI (MTK_PIN_NO(151) | 4) +#define PINMUX_GPIO151__FUNC_I2S1_DO_2 (MTK_PIN_NO(151) | 5) + +#define PINMUX_GPIO152__FUNC_GPIO152 (MTK_PIN_NO(152) | 0) +#define PINMUX_GPIO152__FUNC_DPI_HSYNC (MTK_PIN_NO(152) | 1) +#define PINMUX_GPIO152__FUNC_NLD14 (MTK_PIN_NO(152) | 2) +#define PINMUX_GPIO152__FUNC_UCTS3 (MTK_PIN_NO(152) | 3) +#define PINMUX_GPIO152__FUNC_LTE_MD32_JTAG_TDO (MTK_PIN_NO(152) | 4) +#define PINMUX_GPIO152__FUNC_DSI1_TE (MTK_PIN_NO(152) | 5) + +#define PINMUX_GPIO153__FUNC_GPIO153 (MTK_PIN_NO(153) | 0) +#define PINMUX_GPIO153__FUNC_DPI_VSYNC (MTK_PIN_NO(153) | 1) +#define PINMUX_GPIO153__FUNC_NLD15 (MTK_PIN_NO(153) | 2) +#define PINMUX_GPIO153__FUNC_URTS3 (MTK_PIN_NO(153) | 3) +#define PINMUX_GPIO153__FUNC_LTE_MD32_JTAG_TRST (MTK_PIN_NO(153) | 4) +#define PINMUX_GPIO153__FUNC_DISP_PWM1 (MTK_PIN_NO(153) | 5) + +#define PINMUX_GPIO154__FUNC_GPIO154 (MTK_PIN_NO(154) | 0) +#define PINMUX_GPIO154__FUNC_MSDC0_DAT0 (MTK_PIN_NO(154) | 1) +#define PINMUX_GPIO154__FUNC_NLD8 (MTK_PIN_NO(154) | 2) + +#define PINMUX_GPIO155__FUNC_GPIO155 (MTK_PIN_NO(155) | 0) +#define PINMUX_GPIO155__FUNC_MSDC0_DAT1 (MTK_PIN_NO(155) | 1) +#define PINMUX_GPIO155__FUNC_NLD9 (MTK_PIN_NO(155) | 2) + +#define PINMUX_GPIO156__FUNC_GPIO156 (MTK_PIN_NO(156) | 0) +#define PINMUX_GPIO156__FUNC_MSDC0_DAT2 (MTK_PIN_NO(156) | 1) +#define PINMUX_GPIO156__FUNC_NLD10 (MTK_PIN_NO(156) | 2) + +#define PINMUX_GPIO157__FUNC_GPIO157 (MTK_PIN_NO(157) | 0) +#define PINMUX_GPIO157__FUNC_MSDC0_DAT3 (MTK_PIN_NO(157) | 1) +#define PINMUX_GPIO157__FUNC_NLD11 (MTK_PIN_NO(157) | 2) + +#define PINMUX_GPIO158__FUNC_GPIO158 (MTK_PIN_NO(158) | 0) +#define PINMUX_GPIO158__FUNC_MSDC0_DAT4 (MTK_PIN_NO(158) | 1) +#define PINMUX_GPIO158__FUNC_NLD12 (MTK_PIN_NO(158) | 2) + +#define PINMUX_GPIO159__FUNC_GPIO159 (MTK_PIN_NO(159) | 0) +#define PINMUX_GPIO159__FUNC_MSDC0_DAT5 (MTK_PIN_NO(159) | 1) +#define PINMUX_GPIO159__FUNC_NLD13 (MTK_PIN_NO(159) | 2) + +#define PINMUX_GPIO160__FUNC_GPIO160 (MTK_PIN_NO(160) | 0) +#define PINMUX_GPIO160__FUNC_MSDC0_DAT6 (MTK_PIN_NO(160) | 1) +#define PINMUX_GPIO160__FUNC_NLD14 (MTK_PIN_NO(160) | 2) + +#define PINMUX_GPIO161__FUNC_GPIO161 (MTK_PIN_NO(161) | 0) +#define PINMUX_GPIO161__FUNC_MSDC0_DAT7 (MTK_PIN_NO(161) | 1) +#define PINMUX_GPIO161__FUNC_NLD15 (MTK_PIN_NO(161) | 2) + +#define PINMUX_GPIO162__FUNC_GPIO162 (MTK_PIN_NO(162) | 0) +#define PINMUX_GPIO162__FUNC_MSDC0_CMD (MTK_PIN_NO(162) | 1) + +#define PINMUX_GPIO163__FUNC_GPIO163 (MTK_PIN_NO(163) | 0) +#define PINMUX_GPIO163__FUNC_MSDC0_CLK (MTK_PIN_NO(163) | 1) + +#define PINMUX_GPIO164__FUNC_GPIO164 (MTK_PIN_NO(164) | 0) +#define PINMUX_GPIO164__FUNC_MSDC0_DSL (MTK_PIN_NO(164) | 1) + +#define PINMUX_GPIO165__FUNC_GPIO165 (MTK_PIN_NO(165) | 0) +#define PINMUX_GPIO165__FUNC_MSDC0_RSTB (MTK_PIN_NO(165) | 1) + +#define PINMUX_GPIO166__FUNC_GPIO166 (MTK_PIN_NO(166) | 0) +#define PINMUX_GPIO166__FUNC_SPI_CK_0 (MTK_PIN_NO(166) | 1) +#define PINMUX_GPIO166__FUNC_PWM0 (MTK_PIN_NO(166) | 3) + +#define PINMUX_GPIO167__FUNC_GPIO167 (MTK_PIN_NO(167) | 0) +#define PINMUX_GPIO167__FUNC_SPI_MI_0 (MTK_PIN_NO(167) | 1) +#define PINMUX_GPIO167__FUNC_PWM1 (MTK_PIN_NO(167) | 3) +#define PINMUX_GPIO167__FUNC_SPI_MO_0 (MTK_PIN_NO(167) | 4) + +#define PINMUX_GPIO168__FUNC_GPIO168 (MTK_PIN_NO(168) | 0) +#define PINMUX_GPIO168__FUNC_SPI_MO_0 (MTK_PIN_NO(168) | 1) +#define PINMUX_GPIO168__FUNC_MD_EINT3 (MTK_PIN_NO(168) | 2) +#define PINMUX_GPIO168__FUNC_PWM2 (MTK_PIN_NO(168) | 3) +#define PINMUX_GPIO168__FUNC_SPI_MI_0 (MTK_PIN_NO(168) | 4) + +#define PINMUX_GPIO169__FUNC_GPIO169 (MTK_PIN_NO(169) | 0) +#define PINMUX_GPIO169__FUNC_SPI_CS_0 (MTK_PIN_NO(169) | 1) +#define PINMUX_GPIO169__FUNC_MD_EINT4 (MTK_PIN_NO(169) | 2) +#define PINMUX_GPIO169__FUNC_PWM3 (MTK_PIN_NO(169) | 3) + +#define PINMUX_GPIO170__FUNC_GPIO170 (MTK_PIN_NO(170) | 0) +#define PINMUX_GPIO170__FUNC_MSDC1_CMD (MTK_PIN_NO(170) | 1) + +#define PINMUX_GPIO171__FUNC_GPIO171 (MTK_PIN_NO(171) | 0) +#define PINMUX_GPIO171__FUNC_MSDC1_DAT0 (MTK_PIN_NO(171) | 1) + +#define PINMUX_GPIO172__FUNC_GPIO172 (MTK_PIN_NO(172) | 0) +#define PINMUX_GPIO172__FUNC_MSDC1_DAT1 (MTK_PIN_NO(172) | 1) + +#define PINMUX_GPIO173__FUNC_GPIO173 (MTK_PIN_NO(173) | 0) +#define PINMUX_GPIO173__FUNC_MSDC1_DAT2 (MTK_PIN_NO(173) | 1) + +#define PINMUX_GPIO174__FUNC_GPIO174 (MTK_PIN_NO(174) | 0) +#define PINMUX_GPIO174__FUNC_MSDC1_DAT3 (MTK_PIN_NO(174) | 1) + +#define PINMUX_GPIO175__FUNC_GPIO175 (MTK_PIN_NO(175) | 0) +#define PINMUX_GPIO175__FUNC_MSDC1_CLK (MTK_PIN_NO(175) | 1) + +#define PINMUX_GPIO176__FUNC_GPIO176 (MTK_PIN_NO(176) | 0) +#define PINMUX_GPIO176__FUNC_PWRAP_SPIMI (MTK_PIN_NO(176) | 1) +#define PINMUX_GPIO176__FUNC_PWRAP_SPIMO (MTK_PIN_NO(176) | 2) + +#define PINMUX_GPIO177__FUNC_GPIO177 (MTK_PIN_NO(177) | 0) +#define PINMUX_GPIO177__FUNC_PWRAP_SPIMO (MTK_PIN_NO(177) | 1) +#define PINMUX_GPIO177__FUNC_PWRAP_SPIMI (MTK_PIN_NO(177) | 2) + +#define PINMUX_GPIO178__FUNC_GPIO178 (MTK_PIN_NO(178) | 0) +#define PINMUX_GPIO178__FUNC_PWRAP_SPICK (MTK_PIN_NO(178) | 1) + +#define PINMUX_GPIO179__FUNC_GPIO179 (MTK_PIN_NO(179) | 0) +#define PINMUX_GPIO179__FUNC_PWRAP_SPICS (MTK_PIN_NO(179) | 1) + +#define PINMUX_GPIO180__FUNC_GPIO180 (MTK_PIN_NO(180) | 0) +#define PINMUX_GPIO180__FUNC_AUD_CLK_MOSI (MTK_PIN_NO(180) | 1) +#define PINMUX_GPIO180__FUNC_I2S1_WS (MTK_PIN_NO(180) | 2) +#define PINMUX_GPIO180__FUNC_I2S2_WS (MTK_PIN_NO(180) | 3) +#define PINMUX_GPIO180__FUNC_I2S0_WS (MTK_PIN_NO(180) | 4) + +#define PINMUX_GPIO181__FUNC_GPIO181 (MTK_PIN_NO(181) | 0) +#define PINMUX_GPIO181__FUNC_AUD_DAT_MISO_1 (MTK_PIN_NO(181) | 1) +#define PINMUX_GPIO181__FUNC_I2S1_BCK (MTK_PIN_NO(181) | 2) +#define PINMUX_GPIO181__FUNC_I2S2_BCK (MTK_PIN_NO(181) | 3) +#define PINMUX_GPIO181__FUNC_I2S0_BCK (MTK_PIN_NO(181) | 4) + +#define PINMUX_GPIO182__FUNC_GPIO182 (MTK_PIN_NO(182) | 0) +#define PINMUX_GPIO182__FUNC_AUD_DAT_MOSI_1 (MTK_PIN_NO(182) | 1) +#define PINMUX_GPIO182__FUNC_I2S1_MCK (MTK_PIN_NO(182) | 2) +#define PINMUX_GPIO182__FUNC_I2S2_MCK (MTK_PIN_NO(182) | 3) +#define PINMUX_GPIO182__FUNC_I2S0_MCK (MTK_PIN_NO(182) | 4) + +#define PINMUX_GPIO183__FUNC_GPIO183 (MTK_PIN_NO(183) | 0) +#define PINMUX_GPIO183__FUNC_AUD_DAT_MISO_2 (MTK_PIN_NO(183) | 1) +#define PINMUX_GPIO183__FUNC_I2S1_DO_1 (MTK_PIN_NO(183) | 2) +#define PINMUX_GPIO183__FUNC_I2S2_DI_1 (MTK_PIN_NO(183) | 3) +#define PINMUX_GPIO183__FUNC_I2S0_DO (MTK_PIN_NO(183) | 4) + +#define PINMUX_GPIO184__FUNC_GPIO184 (MTK_PIN_NO(184) | 0) +#define PINMUX_GPIO184__FUNC_AUD_DAT_MOSI_2 (MTK_PIN_NO(184) | 1) +#define PINMUX_GPIO184__FUNC_I2S1_DO_2 (MTK_PIN_NO(184) | 2) +#define PINMUX_GPIO184__FUNC_I2S2_DI_2 (MTK_PIN_NO(184) | 3) +#define PINMUX_GPIO184__FUNC_I2S0_DI (MTK_PIN_NO(184) | 4) + +#define PINMUX_GPIO185__FUNC_GPIO185 (MTK_PIN_NO(185) | 0) +#define PINMUX_GPIO185__FUNC_RTC32K_CK (MTK_PIN_NO(185) | 1) + +#define PINMUX_GPIO186__FUNC_GPIO186 (MTK_PIN_NO(186) | 0) +#define PINMUX_GPIO186__FUNC_DISP_PWM0 (MTK_PIN_NO(186) | 1) +#define PINMUX_GPIO186__FUNC_DISP_PWM1 (MTK_PIN_NO(186) | 2) + +#define PINMUX_GPIO187__FUNC_GPIO187 (MTK_PIN_NO(187) | 0) +#define PINMUX_GPIO187__FUNC_SRCLKENAI (MTK_PIN_NO(187) | 1) + +#define PINMUX_GPIO188__FUNC_GPIO188 (MTK_PIN_NO(188) | 0) +#define PINMUX_GPIO188__FUNC_SRCLKENAI2 (MTK_PIN_NO(188) | 1) + +#define PINMUX_GPIO189__FUNC_GPIO189 (MTK_PIN_NO(189) | 0) +#define PINMUX_GPIO189__FUNC_SRCLKENA0 (MTK_PIN_NO(189) | 1) + +#define PINMUX_GPIO190__FUNC_GPIO190 (MTK_PIN_NO(190) | 0) +#define PINMUX_GPIO190__FUNC_SRCLKENA1 (MTK_PIN_NO(190) | 1) + +#define PINMUX_GPIO191__FUNC_GPIO191 (MTK_PIN_NO(191) | 0) +#define PINMUX_GPIO191__FUNC_WATCHDOG_AO (MTK_PIN_NO(191) | 1) + +#define PINMUX_GPIO192__FUNC_GPIO192 (MTK_PIN_NO(192) | 0) +#define PINMUX_GPIO192__FUNC_I2S0_WS (MTK_PIN_NO(192) | 1) +#define PINMUX_GPIO192__FUNC_I2S1_WS (MTK_PIN_NO(192) | 2) +#define PINMUX_GPIO192__FUNC_I2S2_WS (MTK_PIN_NO(192) | 3) +#define PINMUX_GPIO192__FUNC_NCEB1 (MTK_PIN_NO(192) | 4) + +#define PINMUX_GPIO193__FUNC_GPIO193 (MTK_PIN_NO(193) | 0) +#define PINMUX_GPIO193__FUNC_I2S0_BCK (MTK_PIN_NO(193) | 1) +#define PINMUX_GPIO193__FUNC_I2S1_BCK (MTK_PIN_NO(193) | 2) +#define PINMUX_GPIO193__FUNC_I2S2_BCK (MTK_PIN_NO(193) | 3) +#define PINMUX_GPIO193__FUNC_NRNB1 (MTK_PIN_NO(193) | 4) + +#define PINMUX_GPIO194__FUNC_GPIO194 (MTK_PIN_NO(194) | 0) +#define PINMUX_GPIO194__FUNC_I2S0_MCK (MTK_PIN_NO(194) | 1) +#define PINMUX_GPIO194__FUNC_I2S1_MCK (MTK_PIN_NO(194) | 2) +#define PINMUX_GPIO194__FUNC_I2S2_MCK (MTK_PIN_NO(194) | 3) + +#define PINMUX_GPIO195__FUNC_GPIO195 (MTK_PIN_NO(195) | 0) +#define PINMUX_GPIO195__FUNC_I2S0_DO (MTK_PIN_NO(195) | 1) +#define PINMUX_GPIO195__FUNC_I2S1_DO_1 (MTK_PIN_NO(195) | 2) +#define PINMUX_GPIO195__FUNC_I2S2_DI_1 (MTK_PIN_NO(195) | 3) + +#define PINMUX_GPIO196__FUNC_GPIO196 (MTK_PIN_NO(196) | 0) +#define PINMUX_GPIO196__FUNC_I2S0_DI (MTK_PIN_NO(196) | 1) +#define PINMUX_GPIO196__FUNC_I2S1_DO_2 (MTK_PIN_NO(196) | 2) +#define PINMUX_GPIO196__FUNC_I2S2_DI_2 (MTK_PIN_NO(196) | 3) + + +#endif -- cgit v1.2.3 From 7782cfeca7d420e8bb707613d4cfb0f7ff29bb3a Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Fri, 13 May 2022 12:29:38 +0200 Subject: random: remove extern from functions in header Accoriding to the kernel style guide, having `extern` on functions in headers is old school and deprecated, and doesn't add anything. So remove them from random.h, and tidy up the file a little bit too. Signed-off-by: Jason A. Donenfeld --- include/linux/random.h | 77 ++++++++++++++++++++------------------------------ 1 file changed, 31 insertions(+), 46 deletions(-) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index b52963955a99..97f879ea78a5 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -12,13 +12,12 @@ struct notifier_block; -extern void add_device_randomness(const void *, size_t); -extern void add_bootloader_randomness(const void *, size_t); -extern void add_input_randomness(unsigned int type, unsigned int code, - unsigned int value) __latent_entropy; -extern void add_interrupt_randomness(int irq) __latent_entropy; -extern void add_hwgenerator_randomness(const void *buffer, size_t count, - size_t entropy); +void add_device_randomness(const void *, size_t); +void add_bootloader_randomness(const void *, size_t); +void add_input_randomness(unsigned int type, unsigned int code, + unsigned int value) __latent_entropy; +void add_interrupt_randomness(int irq) __latent_entropy; +void add_hwgenerator_randomness(const void *buffer, size_t count, size_t entropy); #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) static inline void add_latent_entropy(void) @@ -26,30 +25,20 @@ static inline void add_latent_entropy(void) add_device_randomness((const void *)&latent_entropy, sizeof(latent_entropy)); } #else -static inline void add_latent_entropy(void) {} +static inline void add_latent_entropy(void) { } #endif #if IS_ENABLED(CONFIG_VMGENID) -extern void add_vmfork_randomness(const void *unique_vm_id, size_t size); -extern int register_random_vmfork_notifier(struct notifier_block *nb); -extern int unregister_random_vmfork_notifier(struct notifier_block *nb); +void add_vmfork_randomness(const void *unique_vm_id, size_t size); +int register_random_vmfork_notifier(struct notifier_block *nb); +int unregister_random_vmfork_notifier(struct notifier_block *nb); #else static inline int register_random_vmfork_notifier(struct notifier_block *nb) { return 0; } static inline int unregister_random_vmfork_notifier(struct notifier_block *nb) { return 0; } #endif -extern void get_random_bytes(void *buf, size_t nbytes); -extern int wait_for_random_bytes(void); -extern int __init random_init(const char *command_line); -extern bool rng_is_initialized(void); -extern int register_random_ready_notifier(struct notifier_block *nb); -extern int unregister_random_ready_notifier(struct notifier_block *nb); -extern size_t __must_check get_random_bytes_arch(void *buf, size_t nbytes); - -#ifndef MODULE -extern const struct file_operations random_fops, urandom_fops; -#endif - +void get_random_bytes(void *buf, size_t nbytes); +size_t __must_check get_random_bytes_arch(void *buf, size_t nbytes); u32 get_random_u32(void); u64 get_random_u64(void); static inline unsigned int get_random_int(void) @@ -81,11 +70,17 @@ static inline unsigned long get_random_long(void) static inline unsigned long get_random_canary(void) { - unsigned long val = get_random_long(); - - return val & CANARY_MASK; + return get_random_long() & CANARY_MASK; } +unsigned long randomize_page(unsigned long start, unsigned long range); + +int __init random_init(const char *command_line); +bool rng_is_initialized(void); +int wait_for_random_bytes(void); +int register_random_ready_notifier(struct notifier_block *nb); +int unregister_random_ready_notifier(struct notifier_block *nb); + /* Calls wait_for_random_bytes() and then calls get_random_bytes(buf, nbytes). * Returns the result of the call to wait_for_random_bytes. */ static inline int get_random_bytes_wait(void *buf, size_t nbytes) @@ -109,8 +104,6 @@ declare_get_random_var_wait(int) declare_get_random_var_wait(long) #undef declare_get_random_var -unsigned long randomize_page(unsigned long start, unsigned long range); - /* * This is designed to be standalone for just prandom * users, but for now we include it from @@ -121,22 +114,10 @@ unsigned long randomize_page(unsigned long start, unsigned long range); #ifdef CONFIG_ARCH_RANDOM # include #else -static inline bool __must_check arch_get_random_long(unsigned long *v) -{ - return false; -} -static inline bool __must_check arch_get_random_int(unsigned int *v) -{ - return false; -} -static inline bool __must_check arch_get_random_seed_long(unsigned long *v) -{ - return false; -} -static inline bool __must_check arch_get_random_seed_int(unsigned int *v) -{ - return false; -} +static inline bool __must_check arch_get_random_long(unsigned long *v) { return false; } +static inline bool __must_check arch_get_random_int(unsigned int *v) { return false; } +static inline bool __must_check arch_get_random_seed_long(unsigned long *v) { return false; } +static inline bool __must_check arch_get_random_seed_int(unsigned int *v) { return false; } #endif /* @@ -160,8 +141,12 @@ static inline bool __init arch_get_random_long_early(unsigned long *v) #endif #ifdef CONFIG_SMP -extern int random_prepare_cpu(unsigned int cpu); -extern int random_online_cpu(unsigned int cpu); +int random_prepare_cpu(unsigned int cpu); +int random_online_cpu(unsigned int cpu); +#endif + +#ifndef MODULE +extern const struct file_operations random_fops, urandom_fops; #endif #endif /* _LINUX_RANDOM_H */ -- cgit v1.2.3 From 7c3a8a1db5e03d02cc0abb3357a84b8b326dfac3 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Fri, 13 May 2022 12:32:23 +0200 Subject: random: use proper return types on get_random_{int,long}_wait() Before these were returning signed values, but the API is intended to be used with unsigned values. Signed-off-by: Jason A. Donenfeld --- include/linux/random.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index 97f879ea78a5..883bf9a23d84 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -90,18 +90,18 @@ static inline int get_random_bytes_wait(void *buf, size_t nbytes) return ret; } -#define declare_get_random_var_wait(var) \ - static inline int get_random_ ## var ## _wait(var *out) { \ +#define declare_get_random_var_wait(name, ret_type) \ + static inline int get_random_ ## name ## _wait(ret_type *out) { \ int ret = wait_for_random_bytes(); \ if (unlikely(ret)) \ return ret; \ - *out = get_random_ ## var(); \ + *out = get_random_ ## name(); \ return 0; \ } -declare_get_random_var_wait(u32) -declare_get_random_var_wait(u64) -declare_get_random_var_wait(int) -declare_get_random_var_wait(long) +declare_get_random_var_wait(u32, u32) +declare_get_random_var_wait(u64, u32) +declare_get_random_var_wait(int, unsigned int) +declare_get_random_var_wait(long, unsigned long) #undef declare_get_random_var /* -- cgit v1.2.3 From a19402634c435a4eae226df53c141cdbb9922e7b Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Fri, 13 May 2022 13:18:46 +0200 Subject: random: make consistent use of buf and len The current code was a mix of "nbytes", "count", "size", "buffer", "in", and so forth. Instead, let's clean this up by naming input parameters "buf" (or "ubuf") and "len", so that you always understand that you're reading this variety of function argument. Signed-off-by: Jason A. Donenfeld --- include/linux/random.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index 883bf9a23d84..fc82f1dc36f1 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -12,12 +12,12 @@ struct notifier_block; -void add_device_randomness(const void *, size_t); -void add_bootloader_randomness(const void *, size_t); +void add_device_randomness(const void *buf, size_t len); +void add_bootloader_randomness(const void *buf, size_t len); void add_input_randomness(unsigned int type, unsigned int code, unsigned int value) __latent_entropy; void add_interrupt_randomness(int irq) __latent_entropy; -void add_hwgenerator_randomness(const void *buffer, size_t count, size_t entropy); +void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy); #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) static inline void add_latent_entropy(void) @@ -29,7 +29,7 @@ static inline void add_latent_entropy(void) { } #endif #if IS_ENABLED(CONFIG_VMGENID) -void add_vmfork_randomness(const void *unique_vm_id, size_t size); +void add_vmfork_randomness(const void *unique_vm_id, size_t len); int register_random_vmfork_notifier(struct notifier_block *nb); int unregister_random_vmfork_notifier(struct notifier_block *nb); #else @@ -37,8 +37,8 @@ static inline int register_random_vmfork_notifier(struct notifier_block *nb) { r static inline int unregister_random_vmfork_notifier(struct notifier_block *nb) { return 0; } #endif -void get_random_bytes(void *buf, size_t nbytes); -size_t __must_check get_random_bytes_arch(void *buf, size_t nbytes); +void get_random_bytes(void *buf, size_t len); +size_t __must_check get_random_bytes_arch(void *buf, size_t len); u32 get_random_u32(void); u64 get_random_u64(void); static inline unsigned int get_random_int(void) -- cgit v1.2.3 From 248561ad25a8ba4ecbc7df42f9a5a82fd5fbb4f6 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Sat, 14 May 2022 13:09:17 +0200 Subject: random: remove get_random_bytes_arch() and add rng_has_arch_random() The RNG incorporates RDRAND into its state at boot and every time it reseeds, so there's no reason for callers to use it directly. The hashing that the RNG does on it is preferable to using the bytes raw. The only current use case of get_random_bytes_arch() is vsprintf's siphash key for pointer hashing, which uses it to initialize the pointer secret earlier than usual if RDRAND is available. In order to replace this narrow use case, just expose whether RDRAND is mixed into the RNG, with a new function called rng_has_arch_random(). With that taken care of, there are no users of get_random_bytes_arch() left, so it can be removed. Later, if trust_cpu gets turned on by default (as most distros are doing), this one use of rng_has_arch_random() can probably go away as well. Cc: Steven Rostedt Cc: Sergey Senozhatsky Acked-by: Petr Mladek # for vsprintf.c Signed-off-by: Jason A. Donenfeld --- include/linux/random.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index fc82f1dc36f1..6af130c6edb9 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -38,7 +38,6 @@ static inline int unregister_random_vmfork_notifier(struct notifier_block *nb) { #endif void get_random_bytes(void *buf, size_t len); -size_t __must_check get_random_bytes_arch(void *buf, size_t len); u32 get_random_u32(void); u64 get_random_u64(void); static inline unsigned int get_random_int(void) @@ -77,6 +76,7 @@ unsigned long randomize_page(unsigned long start, unsigned long range); int __init random_init(const char *command_line); bool rng_is_initialized(void); +bool rng_has_arch_random(void); int wait_for_random_bytes(void); int register_random_ready_notifier(struct notifier_block *nb); int unregister_random_ready_notifier(struct notifier_block *nb); -- cgit v1.2.3 From 6701de6c51c172b5de5633374479503c81fefc0b Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Sun, 15 May 2022 15:06:18 +0200 Subject: random: remove mostly unused async readiness notifier The register_random_ready_notifier() notifier is somewhat complicated, and was already recently rewritten to use notifier blocks. It is only used now by one consumer in the kernel, vsprintf.c, for which the async mechanism is really overly complex for what it actually needs. This commit removes register_random_ready_notifier() and unregister_random_ ready_notifier(), because it just adds complication with little utility, and changes vsprintf.c to just check on `!rng_is_initialized() && !rng_has_arch_random()`, which will eventually be true. Performance- wise, that code was already using a static branch, so there's basically no overhead at all to this change. Cc: Steven Rostedt Cc: Sergey Senozhatsky Acked-by: Petr Mladek # for vsprintf.c Reviewed-by: Petr Mladek Signed-off-by: Jason A. Donenfeld --- include/linux/random.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index 6af130c6edb9..d2360b2825b6 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -78,8 +78,6 @@ int __init random_init(const char *command_line); bool rng_is_initialized(void); bool rng_has_arch_random(void); int wait_for_random_bytes(void); -int register_random_ready_notifier(struct notifier_block *nb); -int unregister_random_ready_notifier(struct notifier_block *nb); /* Calls wait_for_random_bytes() and then calls get_random_bytes(buf, nbytes). * Returns the result of the call to wait_for_random_bytes. */ -- cgit v1.2.3 From 5ad7dd882e45d7fe432c32e896e2aaa0b21746ea Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Sat, 14 May 2022 13:59:30 +0200 Subject: random: move randomize_page() into mm where it belongs randomize_page is an mm function. It is documented like one. It contains the history of one. It has the naming convention of one. It looks just like another very similar function in mm, randomize_stack_top(). And it has always been maintained and updated by mm people. There is no need for it to be in random.c. In the "which shape does not look like the other ones" test, pointing to randomize_page() is correct. So move randomize_page() into mm/util.c, right next to the similar randomize_stack_top() function. This commit contains no actual code changes. Cc: Andrew Morton Signed-off-by: Jason A. Donenfeld --- include/linux/mm.h | 1 + include/linux/random.h | 2 -- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9f44254af8ce..b0183450e484 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2677,6 +2677,7 @@ extern int install_special_mapping(struct mm_struct *mm, unsigned long flags, struct page **pages); unsigned long randomize_stack_top(unsigned long stack_top); +unsigned long randomize_page(unsigned long start, unsigned long range); extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); diff --git a/include/linux/random.h b/include/linux/random.h index d2360b2825b6..fae0c84027fd 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -72,8 +72,6 @@ static inline unsigned long get_random_canary(void) return get_random_long() & CANARY_MASK; } -unsigned long randomize_page(unsigned long start, unsigned long range); - int __init random_init(const char *command_line); bool rng_is_initialized(void); bool rng_has_arch_random(void); -- cgit v1.2.3 From 135c579d77d066aece83609329150b87fe81e454 Mon Sep 17 00:00:00 2001 From: Hector Martin Date: Mon, 2 May 2022 18:25:05 +0900 Subject: tty: serial: samsung_tty: Fix suspend/resume on S5L We were restoring the IRQ masks then clearing them again, because ucon_mask wasn't set properly. Adding that makes suspend/resume work as intended. Signed-off-by: Hector Martin Link: https://lore.kernel.org/r/20220502092505.30934-1-marcan@marcan.st Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_s3c.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/serial_s3c.h b/include/linux/serial_s3c.h index f6c3323fc4c5..dec15f5b3dec 100644 --- a/include/linux/serial_s3c.h +++ b/include/linux/serial_s3c.h @@ -256,6 +256,9 @@ #define APPLE_S5L_UCON_DEFAULT (S3C2410_UCON_TXIRQMODE | \ S3C2410_UCON_RXIRQMODE | \ S3C2410_UCON_RXFIFO_TOI) +#define APPLE_S5L_UCON_MASK (APPLE_S5L_UCON_RXTO_ENA_MSK | \ + APPLE_S5L_UCON_RXTHRESH_ENA_MSK | \ + APPLE_S5L_UCON_TXTHRESH_ENA_MSK) #define APPLE_S5L_UTRSTAT_RXTHRESH (1<<4) #define APPLE_S5L_UTRSTAT_TXTHRESH (1<<5) -- cgit v1.2.3 From 0b46ac44f2673be2ee51bb52149cab3546ff1696 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 9 May 2022 12:34:44 +0300 Subject: termbits.h: create termbits-common.h for identical bits MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some defines are the same across all archs. Move the most obvious intersection to termbits-common.h. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20220509093446.6677-2-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/asm-generic/termbits-common.h | 65 ++++++++++++++++++++++++++++++ include/uapi/asm-generic/termbits.h | 53 +----------------------- 2 files changed, 67 insertions(+), 51 deletions(-) create mode 100644 include/uapi/asm-generic/termbits-common.h (limited to 'include') diff --git a/include/uapi/asm-generic/termbits-common.h b/include/uapi/asm-generic/termbits-common.h new file mode 100644 index 000000000000..4d084fe8def5 --- /dev/null +++ b/include/uapi/asm-generic/termbits-common.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __ASM_GENERIC_TERMBITS_COMMON_H +#define __ASM_GENERIC_TERMBITS_COMMON_H + +typedef unsigned char cc_t; +typedef unsigned int speed_t; + +/* c_iflag bits */ +#define IGNBRK 0x001 /* Ignore break condition */ +#define BRKINT 0x002 /* Signal interrupt on break */ +#define IGNPAR 0x004 /* Ignore characters with parity errors */ +#define PARMRK 0x008 /* Mark parity and framing errors */ +#define INPCK 0x010 /* Enable input parity check */ +#define ISTRIP 0x020 /* Strip 8th bit off characters */ +#define INLCR 0x040 /* Map NL to CR on input */ +#define IGNCR 0x080 /* Ignore CR */ +#define ICRNL 0x100 /* Map CR to NL on input */ +#define IXANY 0x800 /* Any character will restart after stop */ + +/* c_oflag bits */ +#define OPOST 0x01 /* Perform output processing */ +#define OCRNL 0x08 +#define ONOCR 0x10 +#define ONLRET 0x20 +#define OFILL 0x40 +#define OFDEL 0x80 + +/* c_cflag bit meaning */ +/* Common CBAUD rates */ +#define B0 0x00000000 /* hang up */ +#define B50 0x00000001 +#define B75 0x00000002 +#define B110 0x00000003 +#define B134 0x00000004 +#define B150 0x00000005 +#define B200 0x00000006 +#define B300 0x00000007 +#define B600 0x00000008 +#define B1200 0x00000009 +#define B1800 0x0000000a +#define B2400 0x0000000b +#define B4800 0x0000000c +#define B9600 0x0000000d +#define B19200 0x0000000e +#define B38400 0x0000000f +#define EXTA B19200 +#define EXTB B38400 + +#define CMSPAR 0x40000000 /* mark or space (stick) parity */ +#define CRTSCTS 0x80000000 /* flow control */ + +#define IBSHIFT 16 /* Shift from CBAUD to CIBAUD */ + +/* tcflow() ACTION argument and TCXONC use these */ +#define TCOOFF 0 /* Suspend output */ +#define TCOON 1 /* Restart suspended output */ +#define TCIOFF 2 /* Send a STOP character */ +#define TCION 3 /* Send a START character */ + +/* tcflush() QUEUE_SELECTOR argument and TCFLSH use these */ +#define TCIFLUSH 0 /* Discard data received but not yet read */ +#define TCOFLUSH 1 /* Discard data written but not yet sent */ +#define TCIOFLUSH 2 /* Discard all pending data */ + +#endif /* __ASM_GENERIC_TERMBITS_COMMON_H */ diff --git a/include/uapi/asm-generic/termbits.h b/include/uapi/asm-generic/termbits.h index 470fd673ff84..78a85c326eef 100644 --- a/include/uapi/asm-generic/termbits.h +++ b/include/uapi/asm-generic/termbits.h @@ -4,8 +4,8 @@ #include -typedef unsigned char cc_t; -typedef unsigned int speed_t; +#include + typedef unsigned int tcflag_t; #define NCCS 19 @@ -60,31 +60,15 @@ struct ktermios { #define VEOL2 16 /* c_iflag bits */ -#define IGNBRK 0x00001 -#define BRKINT 0x00002 -#define IGNPAR 0x00004 -#define PARMRK 0x00008 -#define INPCK 0x00010 -#define ISTRIP 0x00020 -#define INLCR 0x00040 -#define IGNCR 0x00080 -#define ICRNL 0x00100 #define IUCLC 0x00200 #define IXON 0x00400 -#define IXANY 0x00800 #define IXOFF 0x01000 #define IMAXBEL 0x02000 #define IUTF8 0x04000 /* c_oflag bits */ -#define OPOST 0x00001 #define OLCUC 0x00002 #define ONLCR 0x00004 -#define OCRNL 0x00008 -#define ONOCR 0x00010 -#define ONLRET 0x00020 -#define OFILL 0x00040 -#define OFDEL 0x00080 #define NLDLY 0x00100 #define NL0 0x00000 #define NL1 0x00100 @@ -111,24 +95,6 @@ struct ktermios { /* c_cflag bit meaning */ #define CBAUD 0x0000100f -#define B0 0x00000000 /* hang up */ -#define B50 0x00000001 -#define B75 0x00000002 -#define B110 0x00000003 -#define B134 0x00000004 -#define B150 0x00000005 -#define B200 0x00000006 -#define B300 0x00000007 -#define B600 0x00000008 -#define B1200 0x00000009 -#define B1800 0x0000000a -#define B2400 0x0000000b -#define B4800 0x0000000c -#define B9600 0x0000000d -#define B19200 0x0000000e -#define B38400 0x0000000f -#define EXTA B19200 -#define EXTB B38400 #define CSIZE 0x00000030 #define CS5 0x00000000 #define CS6 0x00000010 @@ -158,10 +124,6 @@ struct ktermios { #define B3500000 0x0000100e #define B4000000 0x0000100f #define CIBAUD 0x100f0000 /* input baud rate */ -#define CMSPAR 0x40000000 /* mark or space (stick) parity */ -#define CRTSCTS 0x80000000 /* flow control */ - -#define IBSHIFT 16 /* Shift from CBAUD to CIBAUD */ /* c_lflag bits */ #define ISIG 0x00001 @@ -181,17 +143,6 @@ struct ktermios { #define IEXTEN 0x08000 #define EXTPROC 0x10000 -/* tcflow() and TCXONC use these */ -#define TCOOFF 0 -#define TCOON 1 -#define TCIOFF 2 -#define TCION 3 - -/* tcflush() and TCFLSH use these */ -#define TCIFLUSH 0 -#define TCOFLUSH 1 -#define TCIOFLUSH 2 - /* tcsetattr uses these */ #define TCSANOW 0 #define TCSADRAIN 1 -- cgit v1.2.3 From c9b34088e80efe30459517fa3834cf78532c9a02 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 9 May 2022 12:34:45 +0300 Subject: termbits.h: Align lines & format MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - Align c_cc defines. - Remove extra newlines. - Realign & adjust number of leading zeros. - Reorder c_cflag defines to ascending order - Make comment ending shorted (=remove period and one extra space from the comments in mips). Co-developed-by: Arnd Bergmann Signed-off-by: Arnd Bergmann Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20220509093446.6677-3-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/asm-generic/termbits.h | 76 ++++++++++++++++++------------------- 1 file changed, 38 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/include/uapi/asm-generic/termbits.h b/include/uapi/asm-generic/termbits.h index 78a85c326eef..c92179563289 100644 --- a/include/uapi/asm-generic/termbits.h +++ b/include/uapi/asm-generic/termbits.h @@ -41,30 +41,30 @@ struct ktermios { }; /* c_cc characters */ -#define VINTR 0 -#define VQUIT 1 -#define VERASE 2 -#define VKILL 3 -#define VEOF 4 -#define VTIME 5 -#define VMIN 6 -#define VSWTC 7 -#define VSTART 8 -#define VSTOP 9 -#define VSUSP 10 -#define VEOL 11 -#define VREPRINT 12 -#define VDISCARD 13 -#define VWERASE 14 -#define VLNEXT 15 -#define VEOL2 16 +#define VINTR 0 +#define VQUIT 1 +#define VERASE 2 +#define VKILL 3 +#define VEOF 4 +#define VTIME 5 +#define VMIN 6 +#define VSWTC 7 +#define VSTART 8 +#define VSTOP 9 +#define VSUSP 10 +#define VEOL 11 +#define VREPRINT 12 +#define VDISCARD 13 +#define VWERASE 14 +#define VLNEXT 15 +#define VEOL2 16 /* c_iflag bits */ -#define IUCLC 0x00200 -#define IXON 0x00400 -#define IXOFF 0x01000 -#define IMAXBEL 0x02000 -#define IUTF8 0x04000 +#define IUCLC 0x0200 +#define IXON 0x0400 +#define IXOFF 0x1000 +#define IMAXBEL 0x2000 +#define IUTF8 0x4000 /* c_oflag bits */ #define OLCUC 0x00002 @@ -107,22 +107,22 @@ struct ktermios { #define HUPCL 0x00000400 #define CLOCAL 0x00000800 #define CBAUDEX 0x00001000 -#define BOTHER 0x00001000 -#define B57600 0x00001001 -#define B115200 0x00001002 -#define B230400 0x00001003 -#define B460800 0x00001004 -#define B500000 0x00001005 -#define B576000 0x00001006 -#define B921600 0x00001007 -#define B1000000 0x00001008 -#define B1152000 0x00001009 -#define B1500000 0x0000100a -#define B2000000 0x0000100b -#define B2500000 0x0000100c -#define B3000000 0x0000100d -#define B3500000 0x0000100e -#define B4000000 0x0000100f +#define BOTHER 0x00001000 +#define B57600 0x00001001 +#define B115200 0x00001002 +#define B230400 0x00001003 +#define B460800 0x00001004 +#define B500000 0x00001005 +#define B576000 0x00001006 +#define B921600 0x00001007 +#define B1000000 0x00001008 +#define B1152000 0x00001009 +#define B1500000 0x0000100a +#define B2000000 0x0000100b +#define B2500000 0x0000100c +#define B3000000 0x0000100d +#define B3500000 0x0000100e +#define B4000000 0x0000100f #define CIBAUD 0x100f0000 /* input baud rate */ /* c_lflag bits */ -- cgit v1.2.3 From 44e0b165b6c078b84767da4ba06ffa27af562c96 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 9 May 2022 12:34:46 +0300 Subject: termbits.h: Remove posix_types.h include MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Nothing in termbits seems to require anything from linux/posix_types.h. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20220509093446.6677-4-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/asm-generic/termbits.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/uapi/asm-generic/termbits.h b/include/uapi/asm-generic/termbits.h index c92179563289..890ef29053e2 100644 --- a/include/uapi/asm-generic/termbits.h +++ b/include/uapi/asm-generic/termbits.h @@ -2,8 +2,6 @@ #ifndef __ASM_GENERIC_TERMBITS_H #define __ASM_GENERIC_TERMBITS_H -#include - #include typedef unsigned int tcflag_t; -- cgit v1.2.3 From 45cb7955c180a2a34d291e68938250c4f9bd294f Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 14 Apr 2022 15:50:12 -0400 Subject: SUNRPC: Clean up svc_deferred_class trace events Replace the temporary fix from commit 4d5004451ab2 ("SUNRPC: Fix the svc_deferred_event trace class") with the use of __sockaddr and friends, which is the preferred solution (but only available in 5.18 and newer). Signed-off-by: Chuck Lever --- include/trace/events/sunrpc.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 3995c58a1c51..ee84e9289707 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -2015,19 +2015,18 @@ DECLARE_EVENT_CLASS(svc_deferred_event, TP_STRUCT__entry( __field(const void *, dr) __field(u32, xid) - __array(__u8, addr, INET6_ADDRSTRLEN + 10) + __sockaddr(addr, dr->addrlen) ), TP_fast_assign( __entry->dr = dr; __entry->xid = be32_to_cpu(*(__be32 *)(dr->args + (dr->xprt_hlen>>2))); - snprintf(__entry->addr, sizeof(__entry->addr) - 1, - "%pISpc", (struct sockaddr *)&dr->addr); + __assign_sockaddr(addr, &dr->addr, dr->addrlen); ), - TP_printk("addr=%s dr=%p xid=0x%08x", __entry->addr, __entry->dr, - __entry->xid) + TP_printk("addr=%pISpc dr=%p xid=0x%08x", __get_sockaddr(addr), + __entry->dr, __entry->xid) ); #define DEFINE_SVC_DEFERRED_EVENT(name) \ -- cgit v1.2.3 From 0b6c14bdd908879078ec85d65cfb78472a97e4e7 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 1 Apr 2022 13:10:31 -0400 Subject: SUNRPC: Make cache_req::thread_wait an unsigned long The second parameter of wait_for_completion_interruptible_timeout() is a jiffies value whose type is "unsigned long". Avoid an unnecessary and potentially fraught implicit type conversion at the wait_for_completion_interruptible_timeout() call site in cache_wait_req(). Signed-off-by: Chuck Lever --- include/linux/sunrpc/cache.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index b134b2b3371c..ec5a555df96f 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -121,17 +121,17 @@ struct cache_detail { struct net *net; }; - /* this must be embedded in any request structure that * identifies an object that will want a callback on * a cache fill */ struct cache_req { struct cache_deferred_req *(*defer)(struct cache_req *req); - int thread_wait; /* How long (jiffies) we can block the - * current thread to wait for updates. - */ + unsigned long thread_wait; /* How long (jiffies) we can block the + * current thread to wait for updates. + */ }; + /* this must be embedded in a deferred_request that is being * delayed awaiting cache-fill */ -- cgit v1.2.3 From 983084b2672c593959e3148d6a17c8b920797dde Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 6 Apr 2022 14:38:59 -0400 Subject: SUNRPC: Remove svc_rqst::rq_xprt_hlen Clean up: This field is now always set to zero. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 2 -- include/trace/events/sunrpc.h | 3 +-- 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 217711fc9cac..b73704fbd09b 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -257,7 +257,6 @@ struct svc_rqst { void * rq_xprt_ctxt; /* transport specific context ptr */ struct svc_deferred_req*rq_deferred; /* deferred request we are replaying */ - size_t rq_xprt_hlen; /* xprt header len */ struct xdr_buf rq_arg; struct xdr_stream rq_arg_stream; struct xdr_stream rq_res_stream; @@ -397,7 +396,6 @@ struct svc_deferred_req { size_t daddrlen; void *xprt_ctxt; struct cache_deferred_req handle; - size_t xprt_hlen; int argslen; __be32 args[]; }; diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index ee84e9289707..b61d9c90fa26 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -2020,8 +2020,7 @@ DECLARE_EVENT_CLASS(svc_deferred_event, TP_fast_assign( __entry->dr = dr; - __entry->xid = be32_to_cpu(*(__be32 *)(dr->args + - (dr->xprt_hlen>>2))); + __entry->xid = be32_to_cpu(*(__be32 *)dr->args); __assign_sockaddr(addr, &dr->addr, dr->addrlen); ), -- cgit v1.2.3 From 591502c5cb325b1c6ec59ab161927d606b918aa0 Mon Sep 17 00:00:00 2001 From: Dai Ngo Date: Mon, 2 May 2022 14:19:24 -0700 Subject: fs/lock: add helper locks_owner_has_blockers to check for blockers Add helper locks_owner_has_blockers to check if there is any blockers for a given lockowner. Reviewed-by: J. Bruce Fields Signed-off-by: Dai Ngo Signed-off-by: Chuck Lever Reviewed-by: Jeff Layton --- include/linux/fs.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index bbde95387a23..b8ed7f974fb4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1174,6 +1174,8 @@ extern void lease_unregister_notifier(struct notifier_block *); struct files_struct; extern void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files); +extern bool locks_owner_has_blockers(struct file_lock_context *flctx, + fl_owner_t owner); #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, unsigned int cmd, struct flock __user *user) @@ -1309,6 +1311,11 @@ static inline int lease_modify(struct file_lock *fl, int arg, struct files_struct; static inline void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) {} +static inline bool locks_owner_has_blockers(struct file_lock_context *flctx, + fl_owner_t owner) +{ + return false; +} #endif /* !CONFIG_FILE_LOCKING */ static inline struct inode *file_inode(const struct file *f) -- cgit v1.2.3 From 2443da2259e97688f93d64d17ab69b15f466078a Mon Sep 17 00:00:00 2001 From: Dai Ngo Date: Mon, 2 May 2022 14:19:25 -0700 Subject: fs/lock: add 2 callbacks to lock_manager_operations to resolve conflict Add 2 new callbacks, lm_lock_expirable and lm_expire_lock, to lock_manager_operations to allow the lock manager to take appropriate action to resolve the lock conflict if possible. A new field, lm_mod_owner, is also added to lock_manager_operations. The lm_mod_owner is used by the fs/lock code to make sure the lock manager module such as nfsd, is not freed while lock conflict is being resolved. lm_lock_expirable checks and returns true to indicate that the lock conflict can be resolved else return false. This callback must be called with the flc_lock held so it can not block. lm_expire_lock is called to resolve the lock conflict if the returned value from lm_lock_expirable is true. This callback is called without the flc_lock held since it's allowed to block. Upon returning from this callback, the lock conflict should be resolved and the caller is expected to restart the conflict check from the beginnning of the list. Lock manager, such as NFSv4 courteous server, uses this callback to resolve conflict by destroying lock owner, or the NFSv4 courtesy client (client that has expired but allowed to maintains its states) that owns the lock. Reviewed-by: J. Bruce Fields Signed-off-by: Dai Ngo Signed-off-by: Chuck Lever Reviewed-by: Jeff Layton --- include/linux/fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index b8ed7f974fb4..aa6c1bbdb8c4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1029,6 +1029,7 @@ struct file_lock_operations { }; struct lock_manager_operations { + void *lm_mod_owner; fl_owner_t (*lm_get_owner)(fl_owner_t); void (*lm_put_owner)(fl_owner_t); void (*lm_notify)(struct file_lock *); /* unblock callback */ @@ -1037,6 +1038,8 @@ struct lock_manager_operations { int (*lm_change)(struct file_lock *, int, struct list_head *); void (*lm_setup)(struct file_lock *, void **); bool (*lm_breaker_owns_lease)(struct file_lock *); + bool (*lm_lock_expirable)(struct file_lock *cfl); + void (*lm_expire_lock)(void); }; struct lock_manager { -- cgit v1.2.3 From 2059b698a2efcce3c67b0e61eab7d7680bbe10bd Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 10 May 2022 11:45:53 -0400 Subject: SUNRPC: Simplify synopsis of svc_pool_for_cpu() Clean up: There is one caller. The @cpu argument can be made implicit now that a get_cpu/put_cpu pair is no longer needed. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index b73704fbd09b..daecb009c05b 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -504,7 +504,7 @@ int svc_register(const struct svc_serv *, struct net *, const int, void svc_wake_up(struct svc_serv *); void svc_reserve(struct svc_rqst *rqstp, int space); -struct svc_pool * svc_pool_for_cpu(struct svc_serv *serv, int cpu); +struct svc_pool *svc_pool_for_cpu(struct svc_serv *serv); char * svc_print_addr(struct svc_rqst *, char *, size_t); const char * svc_proc_name(const struct svc_rqst *rqstp); int svc_encode_result_payload(struct svc_rqst *rqstp, -- cgit v1.2.3 From 53c83d6d8e399fad3d3d25df0ea0d54eb0f94f88 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 18 May 2022 15:23:45 +0200 Subject: siphash: add SPDX tags as sole licensing authority The text "dual BSD/GPLv2 license" is somewhat ambiguous, and moving this over to SPDX is overdue. This commit adds SPDX tags to the relevant files and clarifies that it's GPLv2 only and 3-clause BSD. It also removes the old text, so that the SPDX tags are the only source of the information. Suggested-by: Thomas Gleixner Signed-off-by: Jason A. Donenfeld Signed-off-by: Greg Kroah-Hartman --- include/linux/siphash.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/siphash.h b/include/linux/siphash.h index cce8a9acc76c..9e822311b29e 100644 --- a/include/linux/siphash.h +++ b/include/linux/siphash.h @@ -1,6 +1,5 @@ -/* Copyright (C) 2016 Jason A. Donenfeld . All Rights Reserved. - * - * This file is provided under a dual BSD/GPLv2 license. +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* Copyright (C) 2016-2022 Jason A. Donenfeld . All Rights Reserved. * * SipHash: a fast short-input PRF * https://131002.net/siphash/ -- cgit v1.2.3 From e6d3c99adf54fc1dcd07729990dc32acd3be874b Mon Sep 17 00:00:00 2001 From: Abhyuday Godhasara Date: Wed, 27 Apr 2022 00:48:03 -0700 Subject: driver: soc: xilinx: Update function prototype for xlnx_unregister_event As per the current implementation only single callback data gets saved per event, driver is throwing an error if try to register multiple callback for same event. So at time of unregistration of any event required things are event details and callback handler as parameter of xlnx_unregister_event(). As part of adding support of multiple callbacks for same event also require change in prototype of xlnx_unregister_event(). During unregistration of any events, now required things are event details, callback handler and agent's private data as parameter of xlnx_unregister_event(). Also modify the usage of xlnx_unregister_event() in xilinx/zynqmp_power.c driver as per new implementation. Signed-off-by: Abhyuday Godhasara Link: https://lore.kernel.org/r/20220427074803.19009-3-abhyuday.godhasara@xilinx.com Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware/xlnx-event-manager.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/firmware/xlnx-event-manager.h b/include/linux/firmware/xlnx-event-manager.h index 3f87c4929d21..82e8254b0f80 100644 --- a/include/linux/firmware/xlnx-event-manager.h +++ b/include/linux/firmware/xlnx-event-manager.h @@ -17,7 +17,7 @@ int xlnx_register_event(const enum pm_api_cb_id cb_type, const u32 node_id, event_cb_func_t cb_fun, void *data); int xlnx_unregister_event(const enum pm_api_cb_id cb_type, const u32 node_id, - const u32 event, event_cb_func_t cb_fun); + const u32 event, event_cb_func_t cb_fun, void *data); #else static inline int xlnx_register_event(const enum pm_api_cb_id cb_type, const u32 node_id, const u32 event, const bool wake, @@ -27,7 +27,7 @@ static inline int xlnx_register_event(const enum pm_api_cb_id cb_type, const u32 } static inline int xlnx_unregister_event(const enum pm_api_cb_id cb_type, const u32 node_id, - const u32 event, event_cb_func_t cb_fun) + const u32 event, event_cb_func_t cb_fun, void *data) { return -ENODEV; } -- cgit v1.2.3 From 885525c1e7e27ea6207d648a8db20dfbbd9e4238 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Wed, 27 Apr 2022 11:56:48 +0200 Subject: clk: renesas: r9a06g032: Export function to set dmamux The dmamux register is located within the system controller. Without syscon, we need an extra helper in order to give write access to this register to a dmamux driver. Signed-off-by: Miquel Raynal Acked-by: Stephen Boyd Reviewed-by: Geert Uytterhoeven Acked-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20220427095653.91804-5-miquel.raynal@bootlin.com Signed-off-by: Vinod Koul --- include/linux/soc/renesas/r9a06g032-sysctrl.h | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 include/linux/soc/renesas/r9a06g032-sysctrl.h (limited to 'include') diff --git a/include/linux/soc/renesas/r9a06g032-sysctrl.h b/include/linux/soc/renesas/r9a06g032-sysctrl.h new file mode 100644 index 000000000000..066dfb15cbdd --- /dev/null +++ b/include/linux/soc/renesas/r9a06g032-sysctrl.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_SOC_RENESAS_R9A06G032_SYSCTRL_H__ +#define __LINUX_SOC_RENESAS_R9A06G032_SYSCTRL_H__ + +#ifdef CONFIG_CLK_R9A06G032 +int r9a06g032_sysctrl_set_dmamux(u32 mask, u32 val); +#else +static inline int r9a06g032_sysctrl_set_dmamux(u32 mask, u32 val) { return -ENODEV; } +#endif + +#endif /* __LINUX_SOC_RENESAS_R9A06G032_SYSCTRL_H__ */ -- cgit v1.2.3 From 13dfd97a341a5cf9d15f415dd469f45e971ef12a Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Thu, 19 May 2022 14:02:32 +0300 Subject: notifier: Add atomic_notifier_call_chain_is_empty() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add atomic_notifier_call_chain_is_empty() that returns true if given atomic call chain is empty. The first user of this new notifier API function will be the kernel power-off core code that will support power-off call chains. The core code will need to check whether there is a power-off handler registered at all in order to decide whether to halt machine or power it off. Reviewed-by: Michał Mirosław Signed-off-by: Dmitry Osipenko Signed-off-by: Rafael J. Wysocki --- include/linux/notifier.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 87069b8459af..95e2440037de 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -173,6 +173,8 @@ extern int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh extern int raw_notifier_call_chain_robust(struct raw_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v); +extern bool atomic_notifier_call_chain_is_empty(struct atomic_notifier_head *nh); + #define NOTIFY_DONE 0x0000 /* Don't care */ #define NOTIFY_OK 0x0001 /* Suits me */ #define NOTIFY_STOP_MASK 0x8000 /* Don't call further */ -- cgit v1.2.3 From c82f898d873ce10d88f8d60b38c8dd19f1ed7c66 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 10 May 2022 02:32:10 +0300 Subject: notifier: Add blocking/atomic_notifier_chain_register_unique_prio() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add variant of blocking/atomic_notifier_chain_register() functions that allow registration of a notifier only if it has unique priority, otherwise -EBUSY error code is returned by the new functions. Reviewed-by: Michał Mirosław Signed-off-by: Dmitry Osipenko Signed-off-by: Rafael J. Wysocki --- include/linux/notifier.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 95e2440037de..aef88c2d1173 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -150,6 +150,11 @@ extern int raw_notifier_chain_register(struct raw_notifier_head *nh, extern int srcu_notifier_chain_register(struct srcu_notifier_head *nh, struct notifier_block *nb); +extern int atomic_notifier_chain_register_unique_prio( + struct atomic_notifier_head *nh, struct notifier_block *nb); +extern int blocking_notifier_chain_register_unique_prio( + struct blocking_notifier_head *nh, struct notifier_block *nb); + extern int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh, -- cgit v1.2.3 From 232edc2f72f5beda3586360de6254d443820050a Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 10 May 2022 02:32:11 +0300 Subject: kernel/reboot: Introduce sys-off handler API In order to support power-off chaining we need to get rid of the global pm_* variables, replacing them with the new kernel API functions that support chaining. Introduce new generic sys-off handler API that brings the following features: 1. Power-off and restart handlers are registered using same API function that supports chaining, hence all power-off and restart modes will support chaining using this unified function. 2. Prevents notifier priority collisions by disallowing registration of multiple handlers at the non-default priority level. 3. Supports passing opaque user argument to callback, which allows us to remove global variables from drivers. This patch adds support of the following sys-off modes: - SYS_OFF_MODE_POWER_OFF_PREPARE that replaces global pm_power_off_prepare variable and provides chaining support for power-off-prepare handlers. - SYS_OFF_MODE_POWER_OFF that replaces global pm_power_off variable and provides chaining support for power-off handlers. - SYS_OFF_MODE_RESTART that provides a better restart API, removing a need from drivers to have a global scratch variable by utilizing the opaque callback argument. Signed-off-by: Dmitry Osipenko Signed-off-by: Rafael J. Wysocki --- include/linux/reboot.h | 77 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 77 insertions(+) (limited to 'include') diff --git a/include/linux/reboot.h b/include/linux/reboot.h index af907a3d68d1..b79f8942ea5f 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -7,6 +7,7 @@ #include struct device; +struct sys_off_handler; #define SYS_DOWN 0x0001 /* Notify of system down */ #define SYS_RESTART SYS_DOWN @@ -62,6 +63,82 @@ extern void machine_shutdown(void); struct pt_regs; extern void machine_crash_shutdown(struct pt_regs *); +/* + * sys-off handler API. + */ + +/* + * Standard sys-off priority levels. Users are expected to set priorities + * relative to the standard levels. + * + * SYS_OFF_PRIO_PLATFORM: Use this for platform-level handlers. + * + * SYS_OFF_PRIO_LOW: Use this for handler of last resort. + * + * SYS_OFF_PRIO_DEFAULT: Use this for normal handlers. + * + * SYS_OFF_PRIO_HIGH: Use this for higher priority handlers. + * + * SYS_OFF_PRIO_FIRMWARE: Use this if handler uses firmware call. + */ +#define SYS_OFF_PRIO_PLATFORM -256 +#define SYS_OFF_PRIO_LOW -128 +#define SYS_OFF_PRIO_DEFAULT 0 +#define SYS_OFF_PRIO_HIGH 192 +#define SYS_OFF_PRIO_FIRMWARE 224 + +enum sys_off_mode { + /** + * @SYS_OFF_MODE_POWER_OFF_PREPARE: + * + * Handlers prepare system to be powered off. Handlers are + * allowed to sleep. + */ + SYS_OFF_MODE_POWER_OFF_PREPARE, + + /** + * @SYS_OFF_MODE_POWER_OFF: + * + * Handlers power-off system. Handlers are disallowed to sleep. + */ + SYS_OFF_MODE_POWER_OFF, + + /** + * @SYS_OFF_MODE_RESTART: + * + * Handlers restart system. Handlers are disallowed to sleep. + */ + SYS_OFF_MODE_RESTART, +}; + +/** + * struct sys_off_data - sys-off callback argument + * + * @mode: Mode ID. Currently used only by the sys-off restart mode, + * see enum reboot_mode for the available modes. + * @cb_data: User's callback data. + * @cmd: Command string. Currently used only by the sys-off restart mode, + * NULL otherwise. + */ +struct sys_off_data { + int mode; + void *cb_data; + const char *cmd; +}; + +struct sys_off_handler * +register_sys_off_handler(enum sys_off_mode mode, + int priority, + int (*callback)(struct sys_off_data *data), + void *cb_data); +void unregister_sys_off_handler(struct sys_off_handler *handler); + +int devm_register_sys_off_handler(struct device *dev, + enum sys_off_mode mode, + int priority, + int (*callback)(struct sys_off_data *data), + void *cb_data); + /* * Architecture independent implemenations of sys_reboot commands. */ -- cgit v1.2.3 From 2b6aa7332f8020dfdaffe340ff038aac4df35238 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 10 May 2022 02:32:13 +0300 Subject: kernel/reboot: Add do_kernel_power_off() Add do_kernel_power_off() helper that will remove open-coded pm_power_off invocations from the architecture code. This is the first step on the way to remove the global pm_power_off variable, which will allow us to implement consistent power-off chaining support. Signed-off-by: Dmitry Osipenko Signed-off-by: Rafael J. Wysocki --- include/linux/reboot.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/reboot.h b/include/linux/reboot.h index b79f8942ea5f..99a9753e77bc 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -63,6 +63,8 @@ extern void machine_shutdown(void); struct pt_regs; extern void machine_crash_shutdown(struct pt_regs *); +void do_kernel_power_off(void); + /* * sys-off handler API. */ -- cgit v1.2.3 From 0e2110d2e910e44cc7cf23fce14613e232602602 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 10 May 2022 02:32:15 +0300 Subject: kernel/reboot: Add kernel_can_power_off() Add kernel_can_power_off() helper that replaces open-coded checks of the global pm_power_off variable. This is a necessary step towards supporting chained power-off handlers. Signed-off-by: Dmitry Osipenko Signed-off-by: Rafael J. Wysocki --- include/linux/reboot.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/reboot.h b/include/linux/reboot.h index 99a9753e77bc..5837c6c2fb40 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -149,6 +149,7 @@ extern void kernel_restart_prepare(char *cmd); extern void kernel_restart(char *cmd); extern void kernel_halt(void); extern void kernel_power_off(void); +extern bool kernel_can_power_off(void); extern int C_A_D; /* for sysctl */ void ctrl_alt_del(void); -- cgit v1.2.3 From fb61375ecfba49e153af561402f49f6fe3bebd39 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 10 May 2022 02:32:16 +0300 Subject: kernel/reboot: Add register_platform_power_off() Add platform-level registration helpers that will ease transition of the arch/platform power-off callbacks to the new sys-off based API, allowing us to remove the global pm_power_off variable in the future. Signed-off-by: Dmitry Osipenko Signed-off-by: Rafael J. Wysocki --- include/linux/reboot.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/reboot.h b/include/linux/reboot.h index 5837c6c2fb40..a8fee1d09c65 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -141,6 +141,9 @@ int devm_register_sys_off_handler(struct device *dev, int (*callback)(struct sys_off_data *data), void *cb_data); +int register_platform_power_off(void (*power_off)(void)); +void unregister_platform_power_off(void (*power_off)(void)); + /* * Architecture independent implemenations of sys_reboot commands. */ -- cgit v1.2.3 From 5b71808eb7c97815fc3b9c386ca0ef6daf2dc053 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 10 May 2022 02:32:32 +0300 Subject: reboot: Remove pm_power_off_prepare() All pm_power_off_prepare() users were converted to sys-off handler API. Remove the obsolete global callback variable. Signed-off-by: Dmitry Osipenko Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/pm.h b/include/linux/pm.h index e65b3ab28377..3786d306dad2 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -21,7 +21,6 @@ * Callbacks for platform drivers to implement. */ extern void (*pm_power_off)(void); -extern void (*pm_power_off_prepare)(void); struct device; /* we have a circular dep with device.h */ #ifdef CONFIG_VT_CONSOLE_SLEEP -- cgit v1.2.3 From d2c5415327171e6c1bca2dc4d8a77f450ecf7150 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 10 May 2022 02:32:34 +0300 Subject: kernel/reboot: Add devm_register_power_off_handler() Add devm_register_power_off_handler() helper that registers sys-off handler using power-off mode and with a default priority. Most drivers will want to register power-off handler with a default priority, so this helper will reduce the boilerplate code and make code easier to read and follow. Signed-off-by: Dmitry Osipenko Signed-off-by: Rafael J. Wysocki --- include/linux/reboot.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/reboot.h b/include/linux/reboot.h index a8fee1d09c65..3b063c5b6118 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -141,6 +141,10 @@ int devm_register_sys_off_handler(struct device *dev, int (*callback)(struct sys_off_data *data), void *cb_data); +int devm_register_power_off_handler(struct device *dev, + int (*callback)(struct sys_off_data *data), + void *cb_data); + int register_platform_power_off(void (*power_off)(void)); void unregister_platform_power_off(void (*power_off)(void)); -- cgit v1.2.3 From 6779db970bd287bb35b28bd5dc256fd7aef19d1c Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Tue, 10 May 2022 02:32:35 +0300 Subject: kernel/reboot: Add devm_register_restart_handler() Add devm_register_restart_handler() helper that registers sys-off handler using restart mode and with a default priority. Most drivers will want to register restart handler with a default priority, so this helper will reduce the boilerplate code and make code easier to read and follow. Signed-off-by: Dmitry Osipenko Signed-off-by: Rafael J. Wysocki --- include/linux/reboot.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/reboot.h b/include/linux/reboot.h index 3b063c5b6118..d29d37a2abb6 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -145,6 +145,10 @@ int devm_register_power_off_handler(struct device *dev, int (*callback)(struct sys_off_data *data), void *cb_data); +int devm_register_restart_handler(struct device *dev, + int (*callback)(struct sys_off_data *data), + void *cb_data); + int register_platform_power_off(void (*power_off)(void)); void unregister_platform_power_off(void (*power_off)(void)); -- cgit v1.2.3 From 15f214f9bdb7c1f560b4bf863c5a72ff53b442a4 Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Fri, 13 May 2022 11:34:33 +0200 Subject: topology: Remove unused cpu_cluster_mask() default_topology[] uses cpu_clustergroup_mask() for the CLS level (guarded by CONFIG_SCHED_CLUSTER) which is currently provided by x86 (arch/x86/kernel/smpboot.c) and arm64 (drivers/base/arch_topology.c). Fixes: 778c558f49a2 ("sched: Add cluster scheduler level in core and related Kconfig for ARM64") Acked-by: Barry Song Signed-off-by: Dietmar Eggemann Link: https://lore.kernel.org/r/20220513093433.425163-1-dietmar.eggemann@arm.com Signed-off-by: Greg Kroah-Hartman --- include/linux/topology.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/linux/topology.h b/include/linux/topology.h index f19bc3626297..4564faafd0e1 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -240,13 +240,6 @@ static inline const struct cpumask *cpu_smt_mask(int cpu) } #endif -#if defined(CONFIG_SCHED_CLUSTER) && !defined(cpu_cluster_mask) -static inline const struct cpumask *cpu_cluster_mask(int cpu) -{ - return topology_cluster_cpumask(cpu); -} -#endif - static inline const struct cpumask *cpu_cpu_mask(int cpu) { return cpumask_of_node(cpu_to_node(cpu)); -- cgit v1.2.3 From 0651ab90e4ade17f1d4f4367b70f6120480410f3 Mon Sep 17 00:00:00 2001 From: Pierre Gondois Date: Wed, 18 May 2022 11:08:57 +0200 Subject: ACPI: CPPC: Check _OSC for flexible address space MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ACPI 6.2 Section 6.2.11.2 'Platform-Wide OSPM Capabilities': Starting with ACPI Specification 6.2, all _CPC registers can be in PCC, System Memory, System IO, or Functional Fixed Hardware address spaces. OSPM support for this more flexible register space scheme is indicated by the “Flexible Address Space for CPPC Registers” _OSC bit Otherwise (cf ACPI 6.1, s8.4.7.1.1.X), _CPC registers must be in: - PCC or Functional Fixed Hardware address space if defined - SystemMemory address space (NULL register) if not defined Add the corresponding _OSC bit and check it when parsing _CPC objects. Signed-off-by: Pierre Gondois Reviewed-by: Sudeep Holla Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index d7136d13aa44..03465db16b68 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -574,6 +574,7 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); #define OSC_SB_OSLPI_SUPPORT 0x00000100 #define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT 0x00001000 #define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00002000 +#define OSC_SB_CPC_FLEXIBLE_ADR_SPACE 0x00004000 #define OSC_SB_NATIVE_USB4_SUPPORT 0x00040000 #define OSC_SB_PRM_SUPPORT 0x00200000 @@ -581,6 +582,7 @@ extern bool osc_sb_apei_support_acked; extern bool osc_pc_lpi_support_confirmed; extern bool osc_sb_native_usb4_support_confirmed; extern bool osc_sb_cppc_not_supported; +extern bool osc_cpc_flexible_adr_space_confirmed; /* USB4 Capabilities */ #define OSC_USB_USB3_TUNNELING 0x00000001 -- cgit v1.2.3 From 3cc30dd00a580ca0c9c0b01639841cfd72d10129 Mon Sep 17 00:00:00 2001 From: Pierre Gondois Date: Wed, 18 May 2022 11:09:00 +0200 Subject: cpufreq: CPPC: Enable fast_switch The communication mean of the _CPC desired performance can be PCC, System Memory, System IO, or Functional Fixed Hardware. commit b7898fda5bc7 ("cpufreq: Support for fast frequency switching") fast_switching is 'for switching CPU frequencies from interrupt context'. Writes to SystemMemory and SystemIo are fast and suitable this. This is not the case for PCC and might not be the case for FFH. Enable fast_switching for the cppc_cpufreq driver in above cases. Add cppc_allow_fast_switch() to check the desired performance register address space and set fast_switching accordingly. Signed-off-by: Pierre Gondois Reviewed-by: Sudeep Holla Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/acpi/cppc_acpi.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h index 92b7ea8d8f5e..c6108581d97d 100644 --- a/include/acpi/cppc_acpi.h +++ b/include/acpi/cppc_acpi.h @@ -141,6 +141,7 @@ extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls); extern int cppc_set_enable(int cpu, bool enable); extern int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps); extern bool acpi_cpc_valid(void); +extern bool cppc_allow_fast_switch(void); extern int acpi_get_psd_map(unsigned int cpu, struct cppc_cpudata *cpu_data); extern unsigned int cppc_get_transition_latency(int cpu); extern bool cpc_ffh_supported(void); @@ -175,6 +176,10 @@ static inline bool acpi_cpc_valid(void) { return false; } +static inline bool cppc_allow_fast_switch(void) +{ + return false; +} static inline unsigned int cppc_get_transition_latency(int cpu) { return CPUFREQ_ETERNAL; -- cgit v1.2.3 From 8f9ae5b3ae80f168a6224529e3787f4fb27f299a Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Wed, 4 May 2022 17:06:28 -0700 Subject: Bluetooth: eir: Add helpers for managing service data This adds helpers for accessing and appending service data (0x16) ad type. Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 62a9bb022aed..fe7935be7dc4 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -625,6 +625,7 @@ enum { #define EIR_SSP_RAND_R192 0x0F /* Simple Pairing Randomizer R-192 */ #define EIR_DEVICE_ID 0x10 /* device ID */ #define EIR_APPEARANCE 0x19 /* Device appearance */ +#define EIR_SERVICE_DATA 0x16 /* Service Data */ #define EIR_LE_BDADDR 0x1B /* LE Bluetooth device address */ #define EIR_LE_ROLE 0x1C /* LE role */ #define EIR_SSP_HASH_C256 0x1D /* Simple Pairing Hash C-256 */ -- cgit v1.2.3 From 66d29d802ef3bf55a49b07568b0048823d4a72a6 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Wed, 11 May 2022 16:56:56 +0200 Subject: PM: domains: Allocate gpd_timing_data dynamically based on governor If a genpd doesn't have an associated governor assigned, there's really no point to allocate the per device gpd_timing_data, as the data isn't being used by a governor anyway. To avoid wasting memory, let's therefore convert the corresponding td variable in the struct generic_pm_domain_data into a pointer and manage the allocation of its data dynamically. Signed-off-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 043d48e4420a..126a4b9ab215 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -193,7 +193,7 @@ struct pm_domain_data { struct generic_pm_domain_data { struct pm_domain_data base; - struct gpd_timing_data td; + struct gpd_timing_data *td; struct notifier_block nb; struct notifier_block *power_nb; int cpu; -- cgit v1.2.3 From 9c74f2ac4801473d03b0e29fab74eb94a9944521 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Wed, 11 May 2022 16:56:57 +0200 Subject: PM: domains: Move the next_wakeup variable into the struct gpd_timing_data If the corresponding genpd for the device doesn't use a governor, the variable next_wakeup within the struct generic_pm_domain_data becomes superfluous. To avoid wasting memory, let's move it into the struct gpd_timing_data, which is already being allocated based upon if there is governor assigned. Signed-off-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 126a4b9ab215..1f370f074f30 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -182,6 +182,7 @@ struct gpd_timing_data { s64 suspend_latency_ns; s64 resume_latency_ns; s64 effective_constraint_ns; + ktime_t next_wakeup; bool constraint_changed; bool cached_suspend_ok; }; @@ -200,7 +201,6 @@ struct generic_pm_domain_data { unsigned int performance_state; unsigned int default_pstate; unsigned int rpm_pstate; - ktime_t next_wakeup; void *data; }; -- cgit v1.2.3 From f38d1a6d002526a4e8840e9bb19733e9d4ce1a67 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Wed, 11 May 2022 16:57:02 +0200 Subject: PM: domains: Allocate governor data dynamically based on a genpd governor If a genpd doesn't have an associated governor assigned, several variables in the struct generic_pm_domain becomes superfluous. Rather than wasting memory in allocated genpds, let's move the variables from the struct generic_pm_domain into a new separate struct. In this way, we can instead dynamically decide when we need to allocate the corresponding data for it. Signed-off-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 1f370f074f30..ebc351698090 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -91,6 +91,14 @@ struct gpd_dev_ops { int (*stop)(struct device *dev); }; +struct genpd_governor_data { + s64 max_off_time_ns; + bool max_off_time_changed; + ktime_t next_wakeup; + bool cached_power_down_ok; + bool cached_power_down_state_idx; +}; + struct genpd_power_state { s64 power_off_latency_ns; s64 power_on_latency_ns; @@ -114,6 +122,7 @@ struct generic_pm_domain { struct list_head child_links; /* Links with PM domain as a child */ struct list_head dev_list; /* List of devices */ struct dev_power_governor *gov; + struct genpd_governor_data *gd; /* Data used by a genpd governor. */ struct work_struct power_off_work; struct fwnode_handle *provider; /* Identity of the domain provider */ bool has_provider; @@ -134,11 +143,6 @@ struct generic_pm_domain { int (*set_performance_state)(struct generic_pm_domain *genpd, unsigned int state); struct gpd_dev_ops dev_ops; - s64 max_off_time_ns; /* Maximum allowed "suspended" time. */ - ktime_t next_wakeup; /* Maintained by the domain governor */ - bool max_off_time_changed; - bool cached_power_down_ok; - bool cached_power_down_state_idx; int (*attach_dev)(struct generic_pm_domain *domain, struct device *dev); void (*detach_dev)(struct generic_pm_domain *domain, -- cgit v1.2.3 From 0e7579ca732a39cc377e17509dda9bfc4f6ba78e Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Thu, 19 May 2022 17:30:49 +0300 Subject: io_uring: fix incorrect __kernel_rwf_t cast Currently 'make C=1 fs/io_uring.o' generates sparse warning: CHECK fs/io_uring.c fs/io_uring.c: note: in included file (through include/trace/trace_events.h, include/trace/define_trace.h, i nclude/trace/events/io_uring.h): ./include/trace/events/io_uring.h:488:1: warning: incorrect type in assignment (different base types) expected unsigned int [usertype] op_flags got restricted __kernel_rwf_t const [usertype] rw_flags This happen on cast of sqe->rw_flags which is defined as __kernel_rwf_t, this type is bitwise and requires __force attribute for any casts. However rw_flags is a member of the union, and its access can be safely replaced by using of its neighbours, so let's use poll32_events to fix the sparse warning. Signed-off-by: Vasily Averin Link: https://lore.kernel.org/r/6f009241-a63f-ae43-a04b-62841aaef293@openvz.org Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 42534ec2ab9d..7cfd9c5cff37 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -520,7 +520,7 @@ TRACE_EVENT(io_uring_req_failed, __entry->off = sqe->off; __entry->addr = sqe->addr; __entry->len = sqe->len; - __entry->op_flags = sqe->rw_flags; + __entry->op_flags = sqe->poll32_events; __entry->buf_index = sqe->buf_index; __entry->personality = sqe->personality; __entry->file_index = sqe->file_index; -- cgit v1.2.3 From 4853f68d158ac59b05985a6af5b7da7ccdbc14c8 Mon Sep 17 00:00:00 2001 From: Liao Chang Date: Fri, 8 Apr 2022 18:09:09 +0800 Subject: kexec_file: Fix kexec_file.c build error for riscv platform When CONFIG_KEXEC_FILE is set for riscv platform, the compilation of kernel/kexec_file.c generate build error: kernel/kexec_file.c: In function 'crash_prepare_elf64_headers': ./arch/riscv/include/asm/page.h:110:71: error: request for member 'virt_addr' in something not a structure or union 110 | ((x) >= PAGE_OFFSET && (!IS_ENABLED(CONFIG_64BIT) || (x) < kernel_map.virt_addr)) | ^ ./arch/riscv/include/asm/page.h:131:2: note: in expansion of macro 'is_linear_mapping' 131 | is_linear_mapping(_x) ? \ | ^~~~~~~~~~~~~~~~~ ./arch/riscv/include/asm/page.h:140:31: note: in expansion of macro '__va_to_pa_nodebug' 140 | #define __phys_addr_symbol(x) __va_to_pa_nodebug(x) | ^~~~~~~~~~~~~~~~~~ ./arch/riscv/include/asm/page.h:143:24: note: in expansion of macro '__phys_addr_symbol' 143 | #define __pa_symbol(x) __phys_addr_symbol(RELOC_HIDE((unsigned long)(x), 0)) | ^~~~~~~~~~~~~~~~~~ kernel/kexec_file.c:1327:36: note: in expansion of macro '__pa_symbol' 1327 | phdr->p_offset = phdr->p_paddr = __pa_symbol(_text); This occurs is because the "kernel_map" referenced in macro is_linear_mapping() is suppose to be the one of struct kernel_mapping defined in arch/riscv/mm/init.c, but the 2nd argument of crash_prepare_elf64_header() has same symbol name, in expansion of macro is_linear_mapping in function crash_prepare_elf64_header(), "kernel_map" actually is the local variable. Signed-off-by: Liao Chang Link: https://lore.kernel.org/r/20220408100914.150110-2-lizhengyu3@huawei.com Signed-off-by: Palmer Dabbelt --- include/linux/kexec.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 58d1b58a971e..ebb1bffbf068 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -227,7 +227,7 @@ struct crash_mem { extern int crash_exclude_mem_range(struct crash_mem *mem, unsigned long long mstart, unsigned long long mend); -extern int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map, +extern int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map, void **addr, unsigned long *sz); #endif /* CONFIG_KEXEC_FILE */ -- cgit v1.2.3 From 6c1e423a3c84953edcf91ff03ab97829b287184a Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Wed, 18 May 2022 17:45:27 +0200 Subject: can: can-dev: remove obsolete CAN LED support Since commit 30f3b42147ba6f ("can: mark led trigger as broken") the CAN specific LED support was disabled and marked as BROKEN. As the common LED support with CONFIG_LEDS_TRIGGER_NETDEV should do this work now the code can be removed as preparation for a CAN netdevice Kconfig rework. Link: https://lore.kernel.org/all/20220518154527.29046-1-socketcan@hartkopp.net Suggested-by: Vincent Mailhol Signed-off-by: Oliver Hartkopp [mkl: remove led.h from MAINTAINERS] Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 10 ---------- include/linux/can/led.h | 51 ------------------------------------------------- 2 files changed, 61 deletions(-) delete mode 100644 include/linux/can/led.h (limited to 'include') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index c2ea47f30046..e22dc03c850e 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -17,7 +17,6 @@ #include #include #include -#include #include #include #include @@ -85,15 +84,6 @@ struct can_priv { int (*do_get_berr_counter)(const struct net_device *dev, struct can_berr_counter *bec); int (*do_get_auto_tdcv)(const struct net_device *dev, u32 *tdcv); - -#ifdef CONFIG_CAN_LEDS - struct led_trigger *tx_led_trig; - char tx_led_trig_name[CAN_LED_NAME_SZ]; - struct led_trigger *rx_led_trig; - char rx_led_trig_name[CAN_LED_NAME_SZ]; - struct led_trigger *rxtx_led_trig; - char rxtx_led_trig_name[CAN_LED_NAME_SZ]; -#endif }; static inline bool can_tdc_is_enabled(const struct can_priv *priv) diff --git a/include/linux/can/led.h b/include/linux/can/led.h deleted file mode 100644 index 7c3cfd798c56..000000000000 --- a/include/linux/can/led.h +++ /dev/null @@ -1,51 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright 2012, Fabio Baltieri - */ - -#ifndef _CAN_LED_H -#define _CAN_LED_H - -#include -#include -#include - -enum can_led_event { - CAN_LED_EVENT_OPEN, - CAN_LED_EVENT_STOP, - CAN_LED_EVENT_TX, - CAN_LED_EVENT_RX, -}; - -#ifdef CONFIG_CAN_LEDS - -/* keep space for interface name + "-tx"/"-rx"/"-rxtx" - * suffix and null terminator - */ -#define CAN_LED_NAME_SZ (IFNAMSIZ + 6) - -void can_led_event(struct net_device *netdev, enum can_led_event event); -void devm_can_led_init(struct net_device *netdev); -int __init can_led_notifier_init(void); -void __exit can_led_notifier_exit(void); - -#else - -static inline void can_led_event(struct net_device *netdev, - enum can_led_event event) -{ -} -static inline void devm_can_led_init(struct net_device *netdev) -{ -} -static inline int can_led_notifier_init(void) -{ - return 0; -} -static inline void can_led_notifier_exit(void) -{ -} - -#endif - -#endif /* !_CAN_LED_H */ -- cgit v1.2.3 From 2c8a81dc0cc533c666c64f4139a608b0ae55d96f Mon Sep 17 00:00:00 2001 From: Tong Tiangen Date: Tue, 17 May 2022 07:45:47 +0000 Subject: riscv/mm: fix two page table check related issues Two page table check related issues have been fixed here. 1. Open CONFIG_PAGE_TABLE_CHECK in riscv32, we got a compile error[1]: error: implicit declaration of function 'pud_leaf' Add pud_leaf() definition to incluce/asm-generic/pgtable-nopmd.h to fix this issue. 2. Keep consistent with other pud_xxx() helpers, move pud_user() to pgtable-64.h and add pud_user() to pgtable-nopmd.h. [1]https://lore.kernel.org/linux-mm/202205161811.2nLxmN2O-lkp@intel.com/T/ Link: https://lkml.kernel.org/r/20220517074548.2227779-2-tongtiangen@huawei.com Fixes: 856eed79f8d3 ("riscv/mm: enable ARCH_SUPPORTS_PAGE_TABLE_CHECK") Signed-off-by: Tong Tiangen Reported-by: kernel test robot Cc: Anshuman Khandual Cc: Pasha Tatashin Cc: Anshuman Khandual Cc: Albert Ou Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Guohanjun Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Will Deacon Cc: Xie XiuQi Signed-off-by: Andrew Morton --- include/asm-generic/pgtable-nopmd.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/asm-generic/pgtable-nopmd.h b/include/asm-generic/pgtable-nopmd.h index 10789cf51d16..8ffd64e7a24c 100644 --- a/include/asm-generic/pgtable-nopmd.h +++ b/include/asm-generic/pgtable-nopmd.h @@ -30,6 +30,8 @@ typedef struct { pud_t pud; } pmd_t; static inline int pud_none(pud_t pud) { return 0; } static inline int pud_bad(pud_t pud) { return 0; } static inline int pud_present(pud_t pud) { return 1; } +static inline int pud_user(pud_t pud) { return 0; } +static inline int pud_leaf(pud_t pud) { return 0; } static inline void pud_clear(pud_t *pud) { } #define pmd_ERROR(pmd) (pud_ERROR((pmd).pud)) -- cgit v1.2.3 From b265cdebdfefbee4ef1ae2972af36f7a7cac5148 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Thu, 19 May 2022 14:08:48 -0700 Subject: sched: coredump.h: clarify the use of MMF_VM_HUGEPAGE Patch series "Make khugepaged collapse readonly FS THP more consistent", v4. The readonly FS THP relies on khugepaged to collapse THP for suitable vmas. But the behavior is inconsistent for "always" mode (https://lore.kernel.org/linux-mm/00f195d4-d039-3cf2-d3a1-a2c88de397a0@suse.cz/). The "always" mode means THP allocation should be tried all the time and khugepaged should try to collapse THP all the time. Of course the allocation and collapse may fail due to other factors and conditions. Currently file THP may not be collapsed by khugepaged even though all the conditions are met. That does break the semantics of "always" mode. So make sure readonly FS vmas are registered to khugepaged to fix the break. Register suitable vmas in common mmap path, that could cover both readonly FS vmas and shmem vmas, so remove the khugepaged calls in shmem.c. The patch 1-7 are minor bug fixes, clean up and preparation patches. Patch 8 is the real meat. Tested with khugepaged test in selftests and the testcase provided by Vlastimil Babka in https://lore.kernel.org/lkml/df3b5d1c-a36b-2c73-3e27-99e74983de3a@suse.cz/ by commenting out MADV_HUGEPAGE call. This patch (of 8): MMF_VM_HUGEPAGE is set as long as the mm is available for khugepaged by khugepaged_enter(), not only when VM_HUGEPAGE is set on vma. Correct the comment to avoid confusion. Link: https://lkml.kernel.org/r/20220510203222.24246-1-shy828301@gmail.com Link: https://lkml.kernel.org/r/20220510203222.24246-2-shy828301@gmail.com Signed-off-by: Yang Shi Reviewed-by: Miaohe Lin Acked-by: Song Liu Acked-by: Vlastmil Babka Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Cc: Rik van Riel Cc: Song Liu Cc: Theodore Ts'o Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/sched/coredump.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 4d9e3a656875..4d0a5be28b70 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -57,7 +57,8 @@ static inline int get_dumpable(struct mm_struct *mm) #endif /* leave room for more dump flags */ #define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */ -#define MMF_VM_HUGEPAGE 17 /* set when VM_HUGEPAGE is set on vma */ +#define MMF_VM_HUGEPAGE 17 /* set when mm is available for + khugepaged */ /* * This one-shot flag is dropped due to necessity of changing exe once again * on NFS restore -- cgit v1.2.3 From 78d12c19e02d8151b1c82228ae6bb10f174a68e2 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Thu, 19 May 2022 14:08:49 -0700 Subject: mm: thp: only regular file could be THP eligible Since commit a4aeaa06d45e ("mm: khugepaged: skip huge page collapse for special files"), khugepaged just collapses THP for regular file which is the intended usecase for readonly fs THP. Only show regular file as THP eligible accordingly. And make file_thp_enabled() available for khugepaged too in order to remove duplicate code. Link: https://lkml.kernel.org/r/20220510203222.24246-5-shy828301@gmail.com Signed-off-by: Yang Shi Acked-by: Song Liu Acked-by: Vlastmil Babka Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Cc: Miaohe Lin Cc: Rik van Riel Cc: Song Liu Cc: Theodore Ts'o Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index fbf36bb1be22..de29821231c9 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -173,6 +173,20 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) return false; } +static inline bool file_thp_enabled(struct vm_area_struct *vma) +{ + struct inode *inode; + + if (!vma->vm_file) + return false; + + inode = vma->vm_file->f_inode; + + return (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS)) && + (vma->vm_flags & VM_EXEC) && + !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode); +} + bool transparent_hugepage_active(struct vm_area_struct *vma); #define transparent_hugepage_use_zero_page() \ -- cgit v1.2.3 From d2081b2bf8195b8239c67fdd61518e077da7cbec Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Thu, 19 May 2022 14:08:49 -0700 Subject: mm: khugepaged: make khugepaged_enter() void function The most callers of khugepaged_enter() don't care about the return value. Only dup_mmap(), anonymous THP page fault and MADV_HUGEPAGE handle the error by returning -ENOMEM. Actually it is not harmful for them to ignore the error case either. It also sounds overkilling to fail fork() and page fault early due to khugepaged_enter() error, and MADV_HUGEPAGE does set VM_HUGEPAGE flag regardless of the error. Link: https://lkml.kernel.org/r/20220510203222.24246-6-shy828301@gmail.com Signed-off-by: Yang Shi Acked-by: Song Liu Acked-by: Vlastmil Babka Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Cc: Miaohe Lin Cc: Rik van Riel Cc: Song Liu Cc: Theodore Ts'o Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/khugepaged.h | 30 ++++++++++++------------------ 1 file changed, 12 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index 2fcc01891b47..0423d3619f26 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -12,10 +12,10 @@ extern struct attribute_group khugepaged_attr_group; extern int khugepaged_init(void); extern void khugepaged_destroy(void); extern int start_stop_khugepaged(void); -extern int __khugepaged_enter(struct mm_struct *mm); +extern void __khugepaged_enter(struct mm_struct *mm); extern void __khugepaged_exit(struct mm_struct *mm); -extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma, - unsigned long vm_flags); +extern void khugepaged_enter_vma_merge(struct vm_area_struct *vma, + unsigned long vm_flags); extern void khugepaged_min_free_kbytes_update(void); #ifdef CONFIG_SHMEM extern void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr); @@ -40,11 +40,10 @@ static inline void collapse_pte_mapped_thp(struct mm_struct *mm, (transparent_hugepage_flags & \ (1<flags)) - return __khugepaged_enter(mm); - return 0; + __khugepaged_enter(mm); } static inline void khugepaged_exit(struct mm_struct *mm) @@ -53,7 +52,7 @@ static inline void khugepaged_exit(struct mm_struct *mm) __khugepaged_exit(mm); } -static inline int khugepaged_enter(struct vm_area_struct *vma, +static inline void khugepaged_enter(struct vm_area_struct *vma, unsigned long vm_flags) { if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags)) @@ -62,27 +61,22 @@ static inline int khugepaged_enter(struct vm_area_struct *vma, (khugepaged_req_madv() && (vm_flags & VM_HUGEPAGE))) && !(vm_flags & VM_NOHUGEPAGE) && !test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) - if (__khugepaged_enter(vma->vm_mm)) - return -ENOMEM; - return 0; + __khugepaged_enter(vma->vm_mm); } #else /* CONFIG_TRANSPARENT_HUGEPAGE */ -static inline int khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) +static inline void khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) { - return 0; } static inline void khugepaged_exit(struct mm_struct *mm) { } -static inline int khugepaged_enter(struct vm_area_struct *vma, - unsigned long vm_flags) +static inline void khugepaged_enter(struct vm_area_struct *vma, + unsigned long vm_flags) { - return 0; } -static inline int khugepaged_enter_vma_merge(struct vm_area_struct *vma, - unsigned long vm_flags) +static inline void khugepaged_enter_vma_merge(struct vm_area_struct *vma, + unsigned long vm_flags) { - return 0; } static inline void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) -- cgit v1.2.3 From 2647d11b9e71d495b2d4985ebaf7a734373a4b80 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Thu, 19 May 2022 14:08:49 -0700 Subject: mm: khugepaged: make hugepage_vma_check() non-static The hugepage_vma_check() could be reused by khugepaged_enter() and khugepaged_enter_vma_merge(), but it is static in khugepaged.c. Make it non-static and declare it in khugepaged.h. Link: https://lkml.kernel.org/r/20220510203222.24246-7-shy828301@gmail.com Signed-off-by: Yang Shi Suggested-by: Vlastimil Babka Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Cc: Miaohe Lin Cc: Rik van Riel Cc: Song Liu Cc: Song Liu Cc: Theodore Ts'o Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/khugepaged.h | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index 0423d3619f26..c340f6bb39d6 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -3,8 +3,6 @@ #define _LINUX_KHUGEPAGED_H #include /* MMF_VM_HUGEPAGE */ -#include - #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern struct attribute_group khugepaged_attr_group; @@ -12,6 +10,8 @@ extern struct attribute_group khugepaged_attr_group; extern int khugepaged_init(void); extern void khugepaged_destroy(void); extern int start_stop_khugepaged(void); +extern bool hugepage_vma_check(struct vm_area_struct *vma, + unsigned long vm_flags); extern void __khugepaged_enter(struct mm_struct *mm); extern void __khugepaged_exit(struct mm_struct *mm); extern void khugepaged_enter_vma_merge(struct vm_area_struct *vma, @@ -55,13 +55,11 @@ static inline void khugepaged_exit(struct mm_struct *mm) static inline void khugepaged_enter(struct vm_area_struct *vma, unsigned long vm_flags) { - if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags)) - if ((khugepaged_always() || - (shmem_file(vma->vm_file) && shmem_huge_enabled(vma)) || - (khugepaged_req_madv() && (vm_flags & VM_HUGEPAGE))) && - !(vm_flags & VM_NOHUGEPAGE) && - !test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) && + khugepaged_enabled()) { + if (hugepage_vma_check(vma, vm_flags)) __khugepaged_enter(vma->vm_mm); + } } #else /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline void khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) -- cgit v1.2.3 From c791576c60288c89b351ea2d2098f6a872d78fa7 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Thu, 19 May 2022 14:08:50 -0700 Subject: mm: khugepaged: introduce khugepaged_enter_vma() helper The khugepaged_enter_vma_merge() actually does as the same thing as the khugepaged_enter() section called by shmem_mmap(), so consolidate them into one helper and rename it to khugepaged_enter_vma(). Link: https://lkml.kernel.org/r/20220510203222.24246-8-shy828301@gmail.com Signed-off-by: Yang Shi Acked-by: Vlastmil Babka Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Cc: Miaohe Lin Cc: Rik van Riel Cc: Song Liu Cc: Song Liu Cc: Theodore Ts'o Cc: Zi Yan Signed-off-by: Andrew Morton --- include/linux/khugepaged.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index c340f6bb39d6..392d34c3c59a 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -14,8 +14,8 @@ extern bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags); extern void __khugepaged_enter(struct mm_struct *mm); extern void __khugepaged_exit(struct mm_struct *mm); -extern void khugepaged_enter_vma_merge(struct vm_area_struct *vma, - unsigned long vm_flags); +extern void khugepaged_enter_vma(struct vm_area_struct *vma, + unsigned long vm_flags); extern void khugepaged_min_free_kbytes_update(void); #ifdef CONFIG_SHMEM extern void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr); @@ -72,8 +72,8 @@ static inline void khugepaged_enter(struct vm_area_struct *vma, unsigned long vm_flags) { } -static inline void khugepaged_enter_vma_merge(struct vm_area_struct *vma, - unsigned long vm_flags) +static inline void khugepaged_enter_vma(struct vm_area_struct *vma, + unsigned long vm_flags) { } static inline void collapse_pte_mapped_thp(struct mm_struct *mm, -- cgit v1.2.3 From bc4a68adb151f08b50822158c7767f5726346370 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 19 May 2022 14:08:50 -0700 Subject: mm/swap: remove unneeded return value of free_swap_slot The return value of free_swap_slot is always 0 and also ignored now. Remove it to clean up the code. Link: https://lkml.kernel.org/r/20220509131416.17553-5-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Alistair Popple Cc: David Howells Cc: Matthew Wilcox Cc: Naoya Horiguchi Cc: NeilBrown Cc: Peter Xu Cc: Suren Baghdasaryan Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/swap_slots.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/swap_slots.h b/include/linux/swap_slots.h index 347f1a304190..15adfb8c813a 100644 --- a/include/linux/swap_slots.h +++ b/include/linux/swap_slots.h @@ -24,7 +24,7 @@ struct swap_slots_cache { void disable_swap_slots_cache_lock(void); void reenable_swap_slots_cache_unlock(void); void enable_swap_slots_cache(void); -int free_swap_slot(swp_entry_t entry); +void free_swap_slot(swp_entry_t entry); extern bool swap_slot_cache_enabled; -- cgit v1.2.3 From 3db3264d8a5f4816c022eb9052694ce51e657bfc Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 19 May 2022 14:08:51 -0700 Subject: mm/swap: make page_swapcount and __lru_add_drain_all static Make page_swapcount and __lru_add_drain_all static. They are only used within the file now. Link: https://lkml.kernel.org/r/20220509131416.17553-9-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Alistair Popple Cc: David Howells Cc: Matthew Wilcox Cc: Naoya Horiguchi Cc: NeilBrown Cc: Peter Xu Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Oscar Salvador Signed-off-by: Andrew Morton --- include/linux/swap.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 6bf1506e5080..0ff887cad383 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -485,7 +485,6 @@ int swap_type_of(dev_t device, sector_t offset); int find_first_swap(dev_t *device); extern unsigned int count_swap_pages(int, int); extern sector_t swapdev_block(int, pgoff_t); -extern int page_swapcount(struct page *); extern int __swap_count(swp_entry_t entry); extern int __swp_swapcount(swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); @@ -557,12 +556,6 @@ static inline void put_swap_page(struct page *page, swp_entry_t swp) { } - -static inline int page_swapcount(struct page *page) -{ - return 0; -} - static inline int __swap_count(swp_entry_t entry) { return 0; -- cgit v1.2.3 From a930c210c42dec32b031ad7645bd6904701b5297 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 19 May 2022 14:08:52 -0700 Subject: mm/swap: fix the obsolete comment for SWP_TYPE_SHIFT Since commit 3159f943aafd ("xarray: Replace exceptional entries"), there is only one bit of 'type' can be shifted up. Update the corresponding comment. Link: https://lkml.kernel.org/r/20220509131416.17553-13-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: David Hildenbrand Cc: Alistair Popple Cc: David Howells Cc: Matthew Wilcox Cc: Naoya Horiguchi Cc: NeilBrown Cc: Peter Xu Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Oscar Salvador Signed-off-by: Andrew Morton --- include/linux/swapops.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 09945342bf76..fe220df499f1 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -13,10 +13,10 @@ * get good packing density in that tree, so the index should be dense in * the low-order bits. * - * We arrange the `type' and `offset' fields so that `type' is at the seven + * We arrange the `type' and `offset' fields so that `type' is at the six * high-order bits of the swp_entry_t and `offset' is right-aligned in the * remaining bits. Although `type' itself needs only five bits, we allow for - * shmem/tmpfs to shift it all up a further two bits: see swp_to_radix_entry(). + * shmem/tmpfs to shift it all up a further one bit: see swp_to_radix_entry(). * * swp_entry_t's are *never* stored anywhere in their arch-dependent format. */ -- cgit v1.2.3 From ff351f4bb9606a6c9a1f3fcdd918635b51514779 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 19 May 2022 14:08:52 -0700 Subject: mm/swap: fix comment about swap extent Since commit 4efaceb1c5f8 ("mm, swap: use rbtree for swap_extent"), rbtree is used for swap extent. Also curr_swap_extent is removed at that time. Update the corresponding comment. Link: https://lkml.kernel.org/r/20220509131416.17553-16-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Cc: Alistair Popple Cc: David Hildenbrand Cc: David Howells Cc: Matthew Wilcox Cc: Naoya Horiguchi Cc: NeilBrown Cc: Peter Xu Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Oscar Salvador Signed-off-by: Andrew Morton --- include/linux/swap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 0ff887cad383..04c0713c1d6e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -168,8 +168,8 @@ struct zone; /* * A swap extent maps a range of a swapfile's PAGE_SIZE pages onto a range of - * disk blocks. A list of swap extents maps the entire swapfile. (Where the - * term `swapfile' refers to either a blockdevice or an IS_REG file. Apart + * disk blocks. A rbtree of swap extents maps the entire swapfile (Where the + * term `swapfile' refers to either a blockdevice or an IS_REG file). Apart * from setup, they're handled identically. * * We always assume that blocks are of size PAGE_SIZE. -- cgit v1.2.3 From f6498b776d280b30a4614d8261840961e993c2c8 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 19 May 2022 14:08:53 -0700 Subject: mm: zswap: add basic meminfo and vmstat coverage Currently it requires poking at debugfs to figure out the size and population of the zswap cache on a host. There are no counters for reads and writes against the cache. As a result, it's difficult to understand zswap behavior on production systems. Print zswap memory consumption and how many pages are zswapped out in /proc/meminfo. Count zswapouts and zswapins in /proc/vmstat. Link: https://lkml.kernel.org/r/20220510152847.230957-6-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: David Hildenbrand Cc: Dan Streetman Cc: Michal Hocko Cc: Minchan Kim Cc: Roman Gushchin Cc: Seth Jennings Cc: Shakeel Butt Signed-off-by: Andrew Morton --- include/linux/swap.h | 5 +++++ include/linux/vm_event_item.h | 4 ++++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 04c0713c1d6e..f3ae17b43f20 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -620,6 +620,11 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) } #endif +#ifdef CONFIG_ZSWAP +extern u64 zswap_pool_total_size; +extern atomic_t zswap_stored_pages; +#endif + #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) extern void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask); static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index e83967e4c20e..404024486fa5 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -136,6 +136,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_KSM COW_KSM, #endif +#ifdef CONFIG_ZSWAP + ZSWPIN, + ZSWPOUT, +#endif #ifdef CONFIG_X86 DIRECT_MAP_LEVEL2_SPLIT, DIRECT_MAP_LEVEL3_SPLIT, -- cgit v1.2.3 From f4840ccfca25db225b3371a8f7b5770febee87c5 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 19 May 2022 14:08:53 -0700 Subject: zswap: memcg accounting Applications can currently escape their cgroup memory containment when zswap is enabled. This patch adds per-cgroup tracking and limiting of zswap backend memory to rectify this. The existing cgroup2 memory.stat file is extended to show zswap statistics analogous to what's in meminfo and vmstat. Furthermore, two new control files, memory.zswap.current and memory.zswap.max, are added to allow tuning zswap usage on a per-workload basis. This is important since not all workloads benefit from zswap equally; some even suffer compared to disk swap when memory contents don't compress well. The optimal size of the zswap pool, and the threshold for writeback, also depends on the size of the workload's warm set. The implementation doesn't use a traditional page_counter transaction. zswap is unconventional as a memory consumer in that we only know the amount of memory to charge once expensive compression has occurred. If zwap is disabled or the limit is already exceeded we obviously don't want to compress page upon page only to reject them all. Instead, the limit is checked against current usage, then we compress and charge. This allows some limit overrun, but not enough to matter in practice. [hannes@cmpxchg.org: fix for CONFIG_SLOB builds] Link: https://lkml.kernel.org/r/YnwD14zxYjUJPc2w@cmpxchg.org [hannes@cmpxchg.org: opt out of cgroups v1] Link: https://lkml.kernel.org/r/Yn6it9mBYFA+/lTb@cmpxchg.org Link: https://lkml.kernel.org/r/20220510152847.230957-7-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Cc: Michal Hocko Cc: Roman Gushchin Cc: Shakeel Butt Cc: Seth Jennings Cc: Dan Streetman Cc: Minchan Kim Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 54 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 8ea4b541c31e..9ecead1042b9 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -35,6 +35,8 @@ enum memcg_stat_item { MEMCG_PERCPU_B, MEMCG_VMALLOC, MEMCG_KMEM, + MEMCG_ZSWAP_B, + MEMCG_ZSWAPPED, MEMCG_NR_STAT, }; @@ -252,6 +254,10 @@ struct mem_cgroup { /* Range enforcement for interrupt charges */ struct work_struct high_work; +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) + unsigned long zswap_max; +#endif + unsigned long soft_limit; /* vmpressure notifications */ @@ -1273,6 +1279,10 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css) return NULL; } +static inline void obj_cgroup_put(struct obj_cgroup *objcg) +{ +} + static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } @@ -1694,6 +1704,7 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge_page(struct page *page, int order); struct obj_cgroup *get_obj_cgroup_from_current(void); +struct obj_cgroup *get_obj_cgroup_from_page(struct page *page); int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size); void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size); @@ -1730,6 +1741,20 @@ static inline int memcg_kmem_id(struct mem_cgroup *memcg) struct mem_cgroup *mem_cgroup_from_obj(void *p); +static inline void count_objcg_event(struct obj_cgroup *objcg, + enum vm_event_item idx) +{ + struct mem_cgroup *memcg; + + if (mem_cgroup_kmem_disabled()) + return; + + rcu_read_lock(); + memcg = obj_cgroup_memcg(objcg); + count_memcg_events(memcg, idx, 1); + rcu_read_unlock(); +} + #else static inline bool mem_cgroup_kmem_disabled(void) { @@ -1756,6 +1781,11 @@ static inline void __memcg_kmem_uncharge_page(struct page *page, int order) { } +static inline struct obj_cgroup *get_obj_cgroup_from_page(struct page *page) +{ + return NULL; +} + static inline bool memcg_kmem_enabled(void) { return false; @@ -1771,6 +1801,30 @@ static inline struct mem_cgroup *mem_cgroup_from_obj(void *p) return NULL; } +static inline void count_objcg_event(struct obj_cgroup *objcg, + enum vm_event_item idx) +{ +} + #endif /* CONFIG_MEMCG_KMEM */ +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) +bool obj_cgroup_may_zswap(struct obj_cgroup *objcg); +void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size); +void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size); +#else +static inline bool obj_cgroup_may_zswap(struct obj_cgroup *objcg) +{ + return true; +} +static inline void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, + size_t size) +{ +} +static inline void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, + size_t size) +{ +} +#endif + #endif /* _LINUX_MEMCONTROL_H */ -- cgit v1.2.3 From 6d4675e601357834dadd2ba1d803f6484596015c Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 19 May 2022 14:08:54 -0700 Subject: mm: don't be stuck to rmap lock on reclaim path The rmap locks(i_mmap_rwsem and anon_vma->root->rwsem) could be contended under memory pressure if processes keep working on their vmas(e.g., fork, mmap, munmap). It makes reclaim path stuck. In our real workload traces, we see kswapd is waiting the lock for 300ms+(worst case, a sec) and it makes other processes entering direct reclaim, which were also stuck on the lock. This patch makes lru aging path try_lock mode like shink_page_list so the reclaim context will keep working with next lru pages without being stuck. if it found the rmap lock contended, it rotates the page back to head of lru in both active/inactive lrus to make them consistent behavior, which is basic starting point rather than adding more heristic. Since this patch introduces a new "contended" field as out-param along with try_lock in-param in rmap_walk_control, it's not immutable any longer if the try_lock is set so remove const keywords on rmap related functions. Since rmap walking is already expensive operation, I doubt the const would help sizable benefit( And we didn't have it until 5.17). In a heavy app workload in Android, trace shows following statistics. It almost removes rmap lock contention from reclaim path. Martin Liu reported: Before: max_dur(ms) min_dur(ms) max-min(dur)ms avg_dur(ms) sum_dur(ms) count blocked_function 1632 0 1631 151.542173 31672 209 page_lock_anon_vma_read 601 0 601 145.544681 28817 198 rmap_walk_file After: max_dur(ms) min_dur(ms) max-min(dur)ms avg_dur(ms) sum_dur(ms) count blocked_function NaN NaN NaN NaN NaN 0.0 NaN 0 0 0 0.127645 1 12 rmap_walk_file [minchan@kernel.org: add comment, per Matthew] Link: https://lkml.kernel.org/r/YnNqeB5tUf6LZ57b@google.com Link: https://lkml.kernel.org/r/20220510215423.164547-1-minchan@kernel.org Signed-off-by: Minchan Kim Acked-by: Johannes Weiner Cc: Suren Baghdasaryan Cc: Michal Hocko Cc: John Dias Cc: Tim Murray Cc: Matthew Wilcox Cc: Vladimir Davydov Cc: Martin Liu Cc: Minchan Kim Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- include/linux/fs.h | 5 +++++ include/linux/ksm.h | 4 ++-- include/linux/rmap.h | 28 ++++++++++++++++++++-------- 3 files changed, 27 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index b81cacc51d2f..044b67f8d861 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -477,6 +477,11 @@ static inline void i_mmap_unlock_write(struct address_space *mapping) up_write(&mapping->i_mmap_rwsem); } +static inline int i_mmap_trylock_read(struct address_space *mapping) +{ + return down_read_trylock(&mapping->i_mmap_rwsem); +} + static inline void i_mmap_lock_read(struct address_space *mapping) { down_read(&mapping->i_mmap_rwsem); diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 0630e545f4cb..0b4f17418f64 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -51,7 +51,7 @@ static inline void ksm_exit(struct mm_struct *mm) struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address); -void rmap_walk_ksm(struct folio *folio, const struct rmap_walk_control *rwc); +void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); #else /* !CONFIG_KSM */ @@ -79,7 +79,7 @@ static inline struct page *ksm_might_need_to_copy(struct page *page, } static inline void rmap_walk_ksm(struct folio *folio, - const struct rmap_walk_control *rwc) + struct rmap_walk_control *rwc) { } diff --git a/include/linux/rmap.h b/include/linux/rmap.h index cbe279a6f0de..9ec23138e410 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -128,6 +128,11 @@ static inline void anon_vma_lock_read(struct anon_vma *anon_vma) down_read(&anon_vma->root->rwsem); } +static inline int anon_vma_trylock_read(struct anon_vma *anon_vma) +{ + return down_read_trylock(&anon_vma->root->rwsem); +} + static inline void anon_vma_unlock_read(struct anon_vma *anon_vma) { up_read(&anon_vma->root->rwsem); @@ -366,17 +371,14 @@ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked); -/* - * Called by memory-failure.c to kill processes. - */ -struct anon_vma *folio_lock_anon_vma_read(struct folio *folio); -void page_unlock_anon_vma_read(struct anon_vma *anon_vma); int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); /* * rmap_walk_control: To control rmap traversing for specific needs * * arg: passed to rmap_one() and invalid_vma() + * try_lock: bail out if the rmap lock is contended + * contended: indicate the rmap traversal bailed out due to lock contention * rmap_one: executed on each vma where page is mapped * done: for checking traversing termination condition * anon_lock: for getting anon_lock by optimized way rather than default @@ -384,6 +386,8 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); */ struct rmap_walk_control { void *arg; + bool try_lock; + bool contended; /* * Return false if page table scanning in rmap_walk should be stopped. * Otherwise, return true. @@ -391,12 +395,20 @@ struct rmap_walk_control { bool (*rmap_one)(struct folio *folio, struct vm_area_struct *vma, unsigned long addr, void *arg); int (*done)(struct folio *folio); - struct anon_vma *(*anon_lock)(struct folio *folio); + struct anon_vma *(*anon_lock)(struct folio *folio, + struct rmap_walk_control *rwc); bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; -void rmap_walk(struct folio *folio, const struct rmap_walk_control *rwc); -void rmap_walk_locked(struct folio *folio, const struct rmap_walk_control *rwc); +void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc); +void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc); + +/* + * Called by memory-failure.c to kill processes. + */ +struct anon_vma *folio_lock_anon_vma_read(struct folio *folio, + struct rmap_walk_control *rwc); +void page_unlock_anon_vma_read(struct anon_vma *anon_vma); #else /* !CONFIG_MMU */ -- cgit v1.2.3 From 10e0f7530205799e7e971aba699a7cb3a47456de Mon Sep 17 00:00:00 2001 From: Wonhyuk Yang Date: Thu, 19 May 2022 14:08:54 -0700 Subject: mm/page_alloc: fix tracepoint mm_page_alloc_zone_locked() Currently, trace point mm_page_alloc_zone_locked() doesn't show correct information. First, when alloc_flag has ALLOC_HARDER/ALLOC_CMA, page can be allocated from MIGRATE_HIGHATOMIC/MIGRATE_CMA. Nevertheless, tracepoint use requested migration type not MIGRATE_HIGHATOMIC and MIGRATE_CMA. Second, after commit 44042b4498728 ("mm/page_alloc: allow high-order pages to be stored on the per-cpu lists") percpu-list can store high order pages. But trace point determine whether it is a refiil of percpu-list by comparing requested order and 0. To handle these problems, make mm_page_alloc_zone_locked() only be called by __rmqueue_smallest with correct migration type. With a new argument called percpu_refill, it can show roughly whether it is a refill of percpu-list. Link: https://lkml.kernel.org/r/20220512025307.57924-1-vvghjk1234@gmail.com Signed-off-by: Wonhyuk Yang Acked-by: Mel Gorman Cc: Baik Song An Cc: Hong Yeon Kim Cc: Taeung Song Cc: Cc: Steven Rostedt Cc: Ingo Molnar Signed-off-by: Andrew Morton --- include/trace/events/kmem.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index 71c141804222..f76668305ac5 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -229,20 +229,23 @@ TRACE_EVENT(mm_page_alloc, DECLARE_EVENT_CLASS(mm_page, - TP_PROTO(struct page *page, unsigned int order, int migratetype), + TP_PROTO(struct page *page, unsigned int order, int migratetype, + int percpu_refill), - TP_ARGS(page, order, migratetype), + TP_ARGS(page, order, migratetype, percpu_refill), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) + __field( int, percpu_refill ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; + __entry->percpu_refill = percpu_refill; ), TP_printk("page=%p pfn=0x%lx order=%u migratetype=%d percpu_refill=%d", @@ -250,14 +253,15 @@ DECLARE_EVENT_CLASS(mm_page, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, - __entry->order == 0) + __entry->percpu_refill) ); DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked, - TP_PROTO(struct page *page, unsigned int order, int migratetype), + TP_PROTO(struct page *page, unsigned int order, int migratetype, + int percpu_refill), - TP_ARGS(page, order, migratetype) + TP_ARGS(page, order, migratetype, percpu_refill) ); TRACE_EVENT(mm_page_pcpu_drain, -- cgit v1.2.3 From 3f913fc5f9745613088d3c569778c9813ab9c129 Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Thu, 19 May 2022 14:08:55 -0700 Subject: mm: fix missing handler for __GFP_NOWARN We expect no warnings to be issued when we specify __GFP_NOWARN, but currently in paths like alloc_pages() and kmalloc(), there are still some warnings printed, fix it. But for some warnings that report usage problems, we don't deal with them. If such warnings are printed, then we should fix the usage problems. Such as the following case: WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1)); [zhengqi.arch@bytedance.com: v2] Link: https://lkml.kernel.org/r/20220511061951.1114-1-zhengqi.arch@bytedance.com Link: https://lkml.kernel.org/r/20220510113809.80626-1-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng Cc: Akinobu Mita Cc: Vlastimil Babka Cc: Greg Kroah-Hartman Cc: Jiri Slaby Cc: Steven Rostedt (Google) Signed-off-by: Andrew Morton --- include/linux/fault-inject.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index 2d04f6448cde..9f6e25467844 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -20,6 +20,7 @@ struct fault_attr { atomic_t space; unsigned long verbose; bool task_filter; + bool no_warn; unsigned long stacktrace_depth; unsigned long require_start; unsigned long require_end; @@ -39,6 +40,7 @@ struct fault_attr { .ratelimit_state = RATELIMIT_STATE_INIT_DISABLED, \ .verbose = 2, \ .dname = NULL, \ + .no_warn = false, \ } #define DECLARE_FAULT_ATTR(name) struct fault_attr name = FAULT_ATTR_INITIALIZER -- cgit v1.2.3 From 37462a920392cb86541650a6f4121155f11f1199 Mon Sep 17 00:00:00 2001 From: Christophe de Dinechin Date: Thu, 14 Apr 2022 17:08:54 +0200 Subject: nodemask.h: fix compilation error with GCC12 With gcc version 12.0.1 20220401 (Red Hat 12.0.1-0), building with defconfig results in the following compilation error: | CC mm/swapfile.o | mm/swapfile.c: In function `setup_swap_info': | mm/swapfile.c:2291:47: error: array subscript -1 is below array bounds | of `struct plist_node[]' [-Werror=array-bounds] | 2291 | p->avail_lists[i].prio = 1; | | ~~~~~~~~~~~~~~^~~ | In file included from mm/swapfile.c:16: | ./include/linux/swap.h:292:27: note: while referencing `avail_lists' | 292 | struct plist_node avail_lists[]; /* | | ^~~~~~~~~~~ This is due to the compiler detecting that the mask in node_states[__state] could theoretically be zero, which would lead to first_node() returning -1 through find_first_bit. I believe that the warning/error is legitimate. I first tried adding a test to check that the node mask is not emtpy, since a similar test exists in the case where MAX_NUMNODES == 1. However, adding the if statement causes other warnings to appear in for_each_cpu_node_but, because it introduces a dangling else ambiguity. And unfortunately, GCC is not smart enough to detect that the added test makes the case where (node) == -1 impossible, so it still complains with the same message. This is why I settled on replacing that with a harmless, but relatively useless (node) >= 0 test. Based on the warning for the dangling else, I also decided to fix the case where MAX_NUMNODES == 1 by moving the condition inside the for loop. It will still only be tested once. This ensures that the meaning of an else following for_each_node_mask or derivatives would not silently have a different meaning depending on the configuration. Link: https://lkml.kernel.org/r/20220414150855.2407137-3-dinechin@redhat.com Signed-off-by: Christophe de Dinechin Signed-off-by: Christophe de Dinechin Reviewed-by: Andrew Morton Cc: Ben Segall Cc: "Michael S. Tsirkin" Cc: Steven Rostedt Cc: Ingo Molnar Cc: Mel Gorman Cc: Dietmar Eggemann Cc: Vincent Guittot Cc: Paolo Bonzini Cc: Daniel Bristot de Oliveira Cc: Jason Wang Cc: Zhen Lei Cc: Juri Lelli Cc: Peter Zijlstra Cc: Signed-off-by: Andrew Morton --- include/linux/nodemask.h | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 567c3ddba2c4..c6199dbe2591 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -375,14 +375,13 @@ static inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp, } #if MAX_NUMNODES > 1 -#define for_each_node_mask(node, mask) \ - for ((node) = first_node(mask); \ - (node) < MAX_NUMNODES; \ - (node) = next_node((node), (mask))) +#define for_each_node_mask(node, mask) \ + for ((node) = first_node(mask); \ + (node >= 0) && (node) < MAX_NUMNODES; \ + (node) = next_node((node), (mask))) #else /* MAX_NUMNODES == 1 */ -#define for_each_node_mask(node, mask) \ - if (!nodes_empty(mask)) \ - for ((node) = 0; (node) < 1; (node)++) +#define for_each_node_mask(node, mask) \ + for ((node) = 0; (node) < 1 && !nodes_empty(mask); (node)++) #endif /* MAX_NUMNODES */ /* -- cgit v1.2.3 From 2b132903de7124dd9a758be0c27562e91a510848 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Wed, 11 May 2022 12:46:53 +0300 Subject: tracing: incorrect isolate_mote_t cast in mm_vmscan_lru_isolate Fixes following sparse warnings: CHECK mm/vmscan.c mm/vmscan.c: note: in included file (through include/trace/trace_events.h, include/trace/define_trace.h, include/trace/events/vmscan.h): ./include/trace/events/vmscan.h:281:1: sparse: warning: cast to restricted isolate_mode_t ./include/trace/events/vmscan.h:281:1: sparse: warning: restricted isolate_mode_t degrades to integer Link: https://lkml.kernel.org/r/e85d7ff2-fd10-53f8-c24e-ba0458439c1b@openvz.org Signed-off-by: Vasily Averin Acked-by: Steven Rostedt (Google) Signed-off-by: Andrew Morton --- include/trace/events/vmscan.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 408c86244d64..d2123dd960d5 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -297,7 +297,7 @@ TRACE_EVENT(mm_vmscan_lru_isolate, __field(unsigned long, nr_scanned) __field(unsigned long, nr_skipped) __field(unsigned long, nr_taken) - __field(isolate_mode_t, isolate_mode) + __field(unsigned int, isolate_mode) __field(int, lru) ), @@ -308,7 +308,7 @@ TRACE_EVENT(mm_vmscan_lru_isolate, __entry->nr_scanned = nr_scanned; __entry->nr_skipped = nr_skipped; __entry->nr_taken = nr_taken; - __entry->isolate_mode = isolate_mode; + __entry->isolate_mode = (__force unsigned int)isolate_mode; __entry->lru = lru; ), -- cgit v1.2.3 From a66a82f2a55ef1f47daeb45e0b4074d88ce5ca99 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Wed, 4 May 2022 19:54:56 -0700 Subject: dt-bindings: clock: Add Qualcomm SC8280XP GCC bindings Add binding for the Qualcomm SC8280XP Global Clock controller. The clock-names property is purposefully omitted, to clearly communicate to the writer (and reader) of the DeviceTree source based on this binding that the order of "clocks" is significant, in contrast to previous GCC bindings. Signed-off-by: Bjorn Andersson Reviewed-by: Stephen Boyd Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220505025457.1693716-2-bjorn.andersson@linaro.org --- include/dt-bindings/clock/qcom,gcc-sc8280xp.h | 496 ++++++++++++++++++++++++++ 1 file changed, 496 insertions(+) create mode 100644 include/dt-bindings/clock/qcom,gcc-sc8280xp.h (limited to 'include') diff --git a/include/dt-bindings/clock/qcom,gcc-sc8280xp.h b/include/dt-bindings/clock/qcom,gcc-sc8280xp.h new file mode 100644 index 000000000000..cb2fb638825c --- /dev/null +++ b/include/dt-bindings/clock/qcom,gcc-sc8280xp.h @@ -0,0 +1,496 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2021, The Linux Foundation. All rights reserved. + * Copyright (c) 2022, Linaro Ltd. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_GCC_DIREWOLF_H +#define _DT_BINDINGS_CLK_QCOM_GCC_DIREWOLF_H + +/* GCC clocks */ +#define GCC_GPLL0 0 +#define GCC_GPLL0_OUT_EVEN 1 +#define GCC_GPLL2 2 +#define GCC_GPLL4 3 +#define GCC_GPLL7 4 +#define GCC_GPLL8 5 +#define GCC_GPLL9 6 +#define GCC_AGGRE_NOC_PCIE0_TUNNEL_AXI_CLK 7 +#define GCC_AGGRE_NOC_PCIE1_TUNNEL_AXI_CLK 8 +#define GCC_AGGRE_NOC_PCIE_4_AXI_CLK 9 +#define GCC_AGGRE_NOC_PCIE_SOUTH_SF_AXI_CLK 10 +#define GCC_AGGRE_UFS_CARD_AXI_CLK 11 +#define GCC_AGGRE_UFS_PHY_AXI_CLK 12 +#define GCC_AGGRE_USB3_MP_AXI_CLK 13 +#define GCC_AGGRE_USB3_PRIM_AXI_CLK 14 +#define GCC_AGGRE_USB3_SEC_AXI_CLK 15 +#define GCC_AGGRE_USB4_1_AXI_CLK 16 +#define GCC_AGGRE_USB4_AXI_CLK 17 +#define GCC_AGGRE_USB_NOC_AXI_CLK 18 +#define GCC_AGGRE_USB_NOC_NORTH_AXI_CLK 19 +#define GCC_AGGRE_USB_NOC_SOUTH_AXI_CLK 20 +#define GCC_AHB2PHY0_CLK 21 +#define GCC_AHB2PHY2_CLK 22 +#define GCC_BOOT_ROM_AHB_CLK 23 +#define GCC_CAMERA_AHB_CLK 24 +#define GCC_CAMERA_HF_AXI_CLK 25 +#define GCC_CAMERA_SF_AXI_CLK 26 +#define GCC_CAMERA_THROTTLE_NRT_AXI_CLK 27 +#define GCC_CAMERA_THROTTLE_RT_AXI_CLK 28 +#define GCC_CAMERA_THROTTLE_XO_CLK 29 +#define GCC_CAMERA_XO_CLK 30 +#define GCC_CFG_NOC_USB3_MP_AXI_CLK 31 +#define GCC_CFG_NOC_USB3_PRIM_AXI_CLK 32 +#define GCC_CFG_NOC_USB3_SEC_AXI_CLK 33 +#define GCC_CNOC_PCIE0_TUNNEL_CLK 34 +#define GCC_CNOC_PCIE1_TUNNEL_CLK 35 +#define GCC_CNOC_PCIE4_QX_CLK 36 +#define GCC_DDRSS_GPU_AXI_CLK 37 +#define GCC_DDRSS_PCIE_SF_TBU_CLK 38 +#define GCC_DISP1_AHB_CLK 39 +#define GCC_DISP1_HF_AXI_CLK 40 +#define GCC_DISP1_SF_AXI_CLK 41 +#define GCC_DISP1_THROTTLE_NRT_AXI_CLK 42 +#define GCC_DISP1_THROTTLE_RT_AXI_CLK 43 +#define GCC_DISP1_XO_CLK 44 +#define GCC_DISP_AHB_CLK 45 +#define GCC_DISP_HF_AXI_CLK 46 +#define GCC_DISP_SF_AXI_CLK 47 +#define GCC_DISP_THROTTLE_NRT_AXI_CLK 48 +#define GCC_DISP_THROTTLE_RT_AXI_CLK 49 +#define GCC_DISP_XO_CLK 50 +#define GCC_EMAC0_AXI_CLK 51 +#define GCC_EMAC0_PTP_CLK 52 +#define GCC_EMAC0_PTP_CLK_SRC 53 +#define GCC_EMAC0_RGMII_CLK 54 +#define GCC_EMAC0_RGMII_CLK_SRC 55 +#define GCC_EMAC0_SLV_AHB_CLK 56 +#define GCC_EMAC1_AXI_CLK 57 +#define GCC_EMAC1_PTP_CLK 58 +#define GCC_EMAC1_PTP_CLK_SRC 59 +#define GCC_EMAC1_RGMII_CLK 60 +#define GCC_EMAC1_RGMII_CLK_SRC 61 +#define GCC_EMAC1_SLV_AHB_CLK 62 +#define GCC_GP1_CLK 63 +#define GCC_GP1_CLK_SRC 64 +#define GCC_GP2_CLK 65 +#define GCC_GP2_CLK_SRC 66 +#define GCC_GP3_CLK 67 +#define GCC_GP3_CLK_SRC 68 +#define GCC_GP4_CLK 69 +#define GCC_GP4_CLK_SRC 70 +#define GCC_GP5_CLK 71 +#define GCC_GP5_CLK_SRC 72 +#define GCC_GPU_CFG_AHB_CLK 73 +#define GCC_GPU_GPLL0_CLK_SRC 74 +#define GCC_GPU_GPLL0_DIV_CLK_SRC 75 +#define GCC_GPU_IREF_EN 76 +#define GCC_GPU_MEMNOC_GFX_CLK 77 +#define GCC_GPU_SNOC_DVM_GFX_CLK 78 +#define GCC_GPU_TCU_THROTTLE_AHB_CLK 79 +#define GCC_GPU_TCU_THROTTLE_CLK 80 +#define GCC_PCIE0_PHY_RCHNG_CLK 81 +#define GCC_PCIE1_PHY_RCHNG_CLK 82 +#define GCC_PCIE2A_PHY_RCHNG_CLK 83 +#define GCC_PCIE2B_PHY_RCHNG_CLK 84 +#define GCC_PCIE3A_PHY_RCHNG_CLK 85 +#define GCC_PCIE3B_PHY_RCHNG_CLK 86 +#define GCC_PCIE4_PHY_RCHNG_CLK 87 +#define GCC_PCIE_0_AUX_CLK 88 +#define GCC_PCIE_0_AUX_CLK_SRC 89 +#define GCC_PCIE_0_CFG_AHB_CLK 90 +#define GCC_PCIE_0_MSTR_AXI_CLK 91 +#define GCC_PCIE_0_PHY_RCHNG_CLK_SRC 92 +#define GCC_PCIE_0_PIPE_CLK 93 +#define GCC_PCIE_0_SLV_AXI_CLK 94 +#define GCC_PCIE_0_SLV_Q2A_AXI_CLK 95 +#define GCC_PCIE_1_AUX_CLK 96 +#define GCC_PCIE_1_AUX_CLK_SRC 97 +#define GCC_PCIE_1_CFG_AHB_CLK 98 +#define GCC_PCIE_1_MSTR_AXI_CLK 99 +#define GCC_PCIE_1_PHY_RCHNG_CLK_SRC 100 +#define GCC_PCIE_1_PIPE_CLK 101 +#define GCC_PCIE_1_SLV_AXI_CLK 102 +#define GCC_PCIE_1_SLV_Q2A_AXI_CLK 103 +#define GCC_PCIE_2A2B_CLKREF_CLK 104 +#define GCC_PCIE_2A_AUX_CLK 105 +#define GCC_PCIE_2A_AUX_CLK_SRC 106 +#define GCC_PCIE_2A_CFG_AHB_CLK 107 +#define GCC_PCIE_2A_MSTR_AXI_CLK 108 +#define GCC_PCIE_2A_PHY_RCHNG_CLK_SRC 109 +#define GCC_PCIE_2A_PIPE_CLK 110 +#define GCC_PCIE_2A_PIPE_CLK_SRC 111 +#define GCC_PCIE_2A_PIPE_DIV_CLK_SRC 112 +#define GCC_PCIE_2A_PIPEDIV2_CLK 113 +#define GCC_PCIE_2A_SLV_AXI_CLK 114 +#define GCC_PCIE_2A_SLV_Q2A_AXI_CLK 115 +#define GCC_PCIE_2B_AUX_CLK 116 +#define GCC_PCIE_2B_AUX_CLK_SRC 117 +#define GCC_PCIE_2B_CFG_AHB_CLK 118 +#define GCC_PCIE_2B_MSTR_AXI_CLK 119 +#define GCC_PCIE_2B_PHY_RCHNG_CLK_SRC 120 +#define GCC_PCIE_2B_PIPE_CLK 121 +#define GCC_PCIE_2B_PIPE_CLK_SRC 122 +#define GCC_PCIE_2B_PIPE_DIV_CLK_SRC 123 +#define GCC_PCIE_2B_PIPEDIV2_CLK 124 +#define GCC_PCIE_2B_SLV_AXI_CLK 125 +#define GCC_PCIE_2B_SLV_Q2A_AXI_CLK 126 +#define GCC_PCIE_3A3B_CLKREF_CLK 127 +#define GCC_PCIE_3A_AUX_CLK 128 +#define GCC_PCIE_3A_AUX_CLK_SRC 129 +#define GCC_PCIE_3A_CFG_AHB_CLK 130 +#define GCC_PCIE_3A_MSTR_AXI_CLK 131 +#define GCC_PCIE_3A_PHY_RCHNG_CLK_SRC 132 +#define GCC_PCIE_3A_PIPE_CLK 133 +#define GCC_PCIE_3A_PIPE_CLK_SRC 134 +#define GCC_PCIE_3A_PIPE_DIV_CLK_SRC 135 +#define GCC_PCIE_3A_PIPEDIV2_CLK 136 +#define GCC_PCIE_3A_SLV_AXI_CLK 137 +#define GCC_PCIE_3A_SLV_Q2A_AXI_CLK 138 +#define GCC_PCIE_3B_AUX_CLK 139 +#define GCC_PCIE_3B_AUX_CLK_SRC 140 +#define GCC_PCIE_3B_CFG_AHB_CLK 141 +#define GCC_PCIE_3B_MSTR_AXI_CLK 142 +#define GCC_PCIE_3B_PHY_RCHNG_CLK_SRC 143 +#define GCC_PCIE_3B_PIPE_CLK 144 +#define GCC_PCIE_3B_PIPE_CLK_SRC 145 +#define GCC_PCIE_3B_PIPE_DIV_CLK_SRC 146 +#define GCC_PCIE_3B_PIPEDIV2_CLK 147 +#define GCC_PCIE_3B_SLV_AXI_CLK 148 +#define GCC_PCIE_3B_SLV_Q2A_AXI_CLK 149 +#define GCC_PCIE_4_AUX_CLK 150 +#define GCC_PCIE_4_AUX_CLK_SRC 151 +#define GCC_PCIE_4_CFG_AHB_CLK 152 +#define GCC_PCIE_4_CLKREF_CLK 153 +#define GCC_PCIE_4_MSTR_AXI_CLK 154 +#define GCC_PCIE_4_PHY_RCHNG_CLK_SRC 155 +#define GCC_PCIE_4_PIPE_CLK 156 +#define GCC_PCIE_4_PIPE_CLK_SRC 157 +#define GCC_PCIE_4_PIPE_DIV_CLK_SRC 158 +#define GCC_PCIE_4_PIPEDIV2_CLK 159 +#define GCC_PCIE_4_SLV_AXI_CLK 160 +#define GCC_PCIE_4_SLV_Q2A_AXI_CLK 161 +#define GCC_PCIE_RSCC_AHB_CLK 162 +#define GCC_PCIE_RSCC_XO_CLK 163 +#define GCC_PCIE_RSCC_XO_CLK_SRC 164 +#define GCC_PCIE_THROTTLE_CFG_CLK 165 +#define GCC_PDM2_CLK 166 +#define GCC_PDM2_CLK_SRC 167 +#define GCC_PDM_AHB_CLK 168 +#define GCC_PDM_XO4_CLK 169 +#define GCC_QMIP_CAMERA_NRT_AHB_CLK 170 +#define GCC_QMIP_CAMERA_RT_AHB_CLK 171 +#define GCC_QMIP_DISP1_AHB_CLK 172 +#define GCC_QMIP_DISP1_ROT_AHB_CLK 173 +#define GCC_QMIP_DISP_AHB_CLK 174 +#define GCC_QMIP_DISP_ROT_AHB_CLK 175 +#define GCC_QMIP_VIDEO_CVP_AHB_CLK 176 +#define GCC_QMIP_VIDEO_VCODEC_AHB_CLK 177 +#define GCC_QUPV3_WRAP0_CORE_2X_CLK 178 +#define GCC_QUPV3_WRAP0_CORE_CLK 179 +#define GCC_QUPV3_WRAP0_QSPI0_CLK 180 +#define GCC_QUPV3_WRAP0_S0_CLK 181 +#define GCC_QUPV3_WRAP0_S0_CLK_SRC 182 +#define GCC_QUPV3_WRAP0_S1_CLK 183 +#define GCC_QUPV3_WRAP0_S1_CLK_SRC 184 +#define GCC_QUPV3_WRAP0_S2_CLK 185 +#define GCC_QUPV3_WRAP0_S2_CLK_SRC 186 +#define GCC_QUPV3_WRAP0_S3_CLK 187 +#define GCC_QUPV3_WRAP0_S3_CLK_SRC 188 +#define GCC_QUPV3_WRAP0_S4_CLK 189 +#define GCC_QUPV3_WRAP0_S4_CLK_SRC 190 +#define GCC_QUPV3_WRAP0_S4_DIV_CLK_SRC 191 +#define GCC_QUPV3_WRAP0_S5_CLK 192 +#define GCC_QUPV3_WRAP0_S5_CLK_SRC 193 +#define GCC_QUPV3_WRAP0_S6_CLK 194 +#define GCC_QUPV3_WRAP0_S6_CLK_SRC 195 +#define GCC_QUPV3_WRAP0_S7_CLK 196 +#define GCC_QUPV3_WRAP0_S7_CLK_SRC 197 +#define GCC_QUPV3_WRAP1_CORE_2X_CLK 198 +#define GCC_QUPV3_WRAP1_CORE_CLK 199 +#define GCC_QUPV3_WRAP1_QSPI0_CLK 200 +#define GCC_QUPV3_WRAP1_S0_CLK 201 +#define GCC_QUPV3_WRAP1_S0_CLK_SRC 202 +#define GCC_QUPV3_WRAP1_S1_CLK 203 +#define GCC_QUPV3_WRAP1_S1_CLK_SRC 204 +#define GCC_QUPV3_WRAP1_S2_CLK 205 +#define GCC_QUPV3_WRAP1_S2_CLK_SRC 206 +#define GCC_QUPV3_WRAP1_S3_CLK 207 +#define GCC_QUPV3_WRAP1_S3_CLK_SRC 208 +#define GCC_QUPV3_WRAP1_S4_CLK 209 +#define GCC_QUPV3_WRAP1_S4_CLK_SRC 210 +#define GCC_QUPV3_WRAP1_S4_DIV_CLK_SRC 211 +#define GCC_QUPV3_WRAP1_S5_CLK 212 +#define GCC_QUPV3_WRAP1_S5_CLK_SRC 213 +#define GCC_QUPV3_WRAP1_S6_CLK 214 +#define GCC_QUPV3_WRAP1_S6_CLK_SRC 215 +#define GCC_QUPV3_WRAP1_S7_CLK 216 +#define GCC_QUPV3_WRAP1_S7_CLK_SRC 217 +#define GCC_QUPV3_WRAP2_CORE_2X_CLK 218 +#define GCC_QUPV3_WRAP2_CORE_CLK 219 +#define GCC_QUPV3_WRAP2_QSPI0_CLK 220 +#define GCC_QUPV3_WRAP2_S0_CLK 221 +#define GCC_QUPV3_WRAP2_S0_CLK_SRC 222 +#define GCC_QUPV3_WRAP2_S1_CLK 223 +#define GCC_QUPV3_WRAP2_S1_CLK_SRC 224 +#define GCC_QUPV3_WRAP2_S2_CLK 225 +#define GCC_QUPV3_WRAP2_S2_CLK_SRC 226 +#define GCC_QUPV3_WRAP2_S3_CLK 227 +#define GCC_QUPV3_WRAP2_S3_CLK_SRC 228 +#define GCC_QUPV3_WRAP2_S4_CLK 229 +#define GCC_QUPV3_WRAP2_S4_CLK_SRC 230 +#define GCC_QUPV3_WRAP2_S4_DIV_CLK_SRC 231 +#define GCC_QUPV3_WRAP2_S5_CLK 232 +#define GCC_QUPV3_WRAP2_S5_CLK_SRC 233 +#define GCC_QUPV3_WRAP2_S6_CLK 234 +#define GCC_QUPV3_WRAP2_S6_CLK_SRC 235 +#define GCC_QUPV3_WRAP2_S7_CLK 236 +#define GCC_QUPV3_WRAP2_S7_CLK_SRC 237 +#define GCC_QUPV3_WRAP_0_M_AHB_CLK 238 +#define GCC_QUPV3_WRAP_0_S_AHB_CLK 239 +#define GCC_QUPV3_WRAP_1_M_AHB_CLK 240 +#define GCC_QUPV3_WRAP_1_S_AHB_CLK 241 +#define GCC_QUPV3_WRAP_2_M_AHB_CLK 242 +#define GCC_QUPV3_WRAP_2_S_AHB_CLK 243 +#define GCC_SDCC2_AHB_CLK 244 +#define GCC_SDCC2_APPS_CLK 245 +#define GCC_SDCC2_APPS_CLK_SRC 246 +#define GCC_SDCC4_AHB_CLK 247 +#define GCC_SDCC4_APPS_CLK 248 +#define GCC_SDCC4_APPS_CLK_SRC 249 +#define GCC_SYS_NOC_USB_AXI_CLK 250 +#define GCC_UFS_1_CARD_CLKREF_CLK 251 +#define GCC_UFS_CARD_AHB_CLK 252 +#define GCC_UFS_CARD_AXI_CLK 253 +#define GCC_UFS_CARD_AXI_CLK_SRC 254 +#define GCC_UFS_CARD_CLKREF_CLK 255 +#define GCC_UFS_CARD_ICE_CORE_CLK 256 +#define GCC_UFS_CARD_ICE_CORE_CLK_SRC 257 +#define GCC_UFS_CARD_PHY_AUX_CLK 258 +#define GCC_UFS_CARD_PHY_AUX_CLK_SRC 259 +#define GCC_UFS_CARD_RX_SYMBOL_0_CLK 260 +#define GCC_UFS_CARD_RX_SYMBOL_0_CLK_SRC 261 +#define GCC_UFS_CARD_RX_SYMBOL_1_CLK 262 +#define GCC_UFS_CARD_RX_SYMBOL_1_CLK_SRC 263 +#define GCC_UFS_CARD_TX_SYMBOL_0_CLK 264 +#define GCC_UFS_CARD_TX_SYMBOL_0_CLK_SRC 265 +#define GCC_UFS_CARD_UNIPRO_CORE_CLK 266 +#define GCC_UFS_CARD_UNIPRO_CORE_CLK_SRC 267 +#define GCC_UFS_PHY_AHB_CLK 268 +#define GCC_UFS_PHY_AXI_CLK 269 +#define GCC_UFS_PHY_AXI_CLK_SRC 270 +#define GCC_UFS_PHY_ICE_CORE_CLK 271 +#define GCC_UFS_PHY_ICE_CORE_CLK_SRC 272 +#define GCC_UFS_PHY_PHY_AUX_CLK 273 +#define GCC_UFS_PHY_PHY_AUX_CLK_SRC 274 +#define GCC_UFS_PHY_RX_SYMBOL_0_CLK 275 +#define GCC_UFS_PHY_RX_SYMBOL_0_CLK_SRC 276 +#define GCC_UFS_PHY_RX_SYMBOL_1_CLK 277 +#define GCC_UFS_PHY_RX_SYMBOL_1_CLK_SRC 278 +#define GCC_UFS_PHY_TX_SYMBOL_0_CLK 279 +#define GCC_UFS_PHY_TX_SYMBOL_0_CLK_SRC 280 +#define GCC_UFS_PHY_UNIPRO_CORE_CLK 281 +#define GCC_UFS_PHY_UNIPRO_CORE_CLK_SRC 282 +#define GCC_UFS_REF_CLKREF_CLK 283 +#define GCC_USB2_HS0_CLKREF_CLK 284 +#define GCC_USB2_HS1_CLKREF_CLK 285 +#define GCC_USB2_HS2_CLKREF_CLK 286 +#define GCC_USB2_HS3_CLKREF_CLK 287 +#define GCC_USB30_MP_MASTER_CLK 288 +#define GCC_USB30_MP_MASTER_CLK_SRC 289 +#define GCC_USB30_MP_MOCK_UTMI_CLK 290 +#define GCC_USB30_MP_MOCK_UTMI_CLK_SRC 291 +#define GCC_USB30_MP_MOCK_UTMI_POSTDIV_CLK_SRC 292 +#define GCC_USB30_MP_SLEEP_CLK 293 +#define GCC_USB30_PRIM_MASTER_CLK 294 +#define GCC_USB30_PRIM_MASTER_CLK_SRC 295 +#define GCC_USB30_PRIM_MOCK_UTMI_CLK 296 +#define GCC_USB30_PRIM_MOCK_UTMI_CLK_SRC 297 +#define GCC_USB30_PRIM_MOCK_UTMI_POSTDIV_CLK_SRC 298 +#define GCC_USB30_PRIM_SLEEP_CLK 299 +#define GCC_USB30_SEC_MASTER_CLK 300 +#define GCC_USB30_SEC_MASTER_CLK_SRC 301 +#define GCC_USB30_SEC_MOCK_UTMI_CLK 302 +#define GCC_USB30_SEC_MOCK_UTMI_CLK_SRC 303 +#define GCC_USB30_SEC_MOCK_UTMI_POSTDIV_CLK_SRC 304 +#define GCC_USB30_SEC_SLEEP_CLK 305 +#define GCC_USB34_PRIM_PHY_PIPE_CLK_SRC 306 +#define GCC_USB34_SEC_PHY_PIPE_CLK_SRC 307 +#define GCC_USB3_MP0_CLKREF_CLK 308 +#define GCC_USB3_MP1_CLKREF_CLK 309 +#define GCC_USB3_MP_PHY_AUX_CLK 310 +#define GCC_USB3_MP_PHY_AUX_CLK_SRC 311 +#define GCC_USB3_MP_PHY_COM_AUX_CLK 312 +#define GCC_USB3_MP_PHY_PIPE_0_CLK 313 +#define GCC_USB3_MP_PHY_PIPE_0_CLK_SRC 314 +#define GCC_USB3_MP_PHY_PIPE_1_CLK 315 +#define GCC_USB3_MP_PHY_PIPE_1_CLK_SRC 316 +#define GCC_USB3_PRIM_PHY_AUX_CLK 317 +#define GCC_USB3_PRIM_PHY_AUX_CLK_SRC 318 +#define GCC_USB3_PRIM_PHY_COM_AUX_CLK 319 +#define GCC_USB3_PRIM_PHY_PIPE_CLK 320 +#define GCC_USB3_PRIM_PHY_PIPE_CLK_SRC 321 +#define GCC_USB3_SEC_PHY_AUX_CLK 322 +#define GCC_USB3_SEC_PHY_AUX_CLK_SRC 323 +#define GCC_USB3_SEC_PHY_COM_AUX_CLK 324 +#define GCC_USB3_SEC_PHY_PIPE_CLK 325 +#define GCC_USB3_SEC_PHY_PIPE_CLK_SRC 326 +#define GCC_USB4_1_CFG_AHB_CLK 327 +#define GCC_USB4_1_DP_CLK 328 +#define GCC_USB4_1_MASTER_CLK 329 +#define GCC_USB4_1_MASTER_CLK_SRC 330 +#define GCC_USB4_1_PHY_DP_CLK_SRC 331 +#define GCC_USB4_1_PHY_P2RR2P_PIPE_CLK 332 +#define GCC_USB4_1_PHY_P2RR2P_PIPE_CLK_SRC 333 +#define GCC_USB4_1_PHY_PCIE_PIPE_CLK 334 +#define GCC_USB4_1_PHY_PCIE_PIPE_CLK_SRC 335 +#define GCC_USB4_1_PHY_PCIE_PIPE_MUX_CLK_SRC 336 +#define GCC_USB4_1_PHY_PCIE_PIPEGMUX_CLK_SRC 337 +#define GCC_USB4_1_PHY_RX0_CLK 338 +#define GCC_USB4_1_PHY_RX0_CLK_SRC 339 +#define GCC_USB4_1_PHY_RX1_CLK 340 +#define GCC_USB4_1_PHY_RX1_CLK_SRC 341 +#define GCC_USB4_1_PHY_SYS_CLK_SRC 342 +#define GCC_USB4_1_PHY_USB_PIPE_CLK 343 +#define GCC_USB4_1_SB_IF_CLK 344 +#define GCC_USB4_1_SB_IF_CLK_SRC 345 +#define GCC_USB4_1_SYS_CLK 346 +#define GCC_USB4_1_TMU_CLK 347 +#define GCC_USB4_1_TMU_CLK_SRC 348 +#define GCC_USB4_CFG_AHB_CLK 349 +#define GCC_USB4_CLKREF_CLK 350 +#define GCC_USB4_DP_CLK 351 +#define GCC_USB4_EUD_CLKREF_CLK 352 +#define GCC_USB4_MASTER_CLK 353 +#define GCC_USB4_MASTER_CLK_SRC 354 +#define GCC_USB4_PHY_DP_CLK_SRC 355 +#define GCC_USB4_PHY_P2RR2P_PIPE_CLK 356 +#define GCC_USB4_PHY_P2RR2P_PIPE_CLK_SRC 357 +#define GCC_USB4_PHY_PCIE_PIPE_CLK 358 +#define GCC_USB4_PHY_PCIE_PIPE_CLK_SRC 359 +#define GCC_USB4_PHY_PCIE_PIPE_MUX_CLK_SRC 360 +#define GCC_USB4_PHY_PCIE_PIPEGMUX_CLK_SRC 361 +#define GCC_USB4_PHY_RX0_CLK 362 +#define GCC_USB4_PHY_RX0_CLK_SRC 363 +#define GCC_USB4_PHY_RX1_CLK 364 +#define GCC_USB4_PHY_RX1_CLK_SRC 365 +#define GCC_USB4_PHY_SYS_CLK_SRC 366 +#define GCC_USB4_PHY_USB_PIPE_CLK 367 +#define GCC_USB4_SB_IF_CLK 368 +#define GCC_USB4_SB_IF_CLK_SRC 369 +#define GCC_USB4_SYS_CLK 370 +#define GCC_USB4_TMU_CLK 371 +#define GCC_USB4_TMU_CLK_SRC 372 +#define GCC_VIDEO_AHB_CLK 373 +#define GCC_VIDEO_AXI0_CLK 374 +#define GCC_VIDEO_AXI1_CLK 375 +#define GCC_VIDEO_CVP_THROTTLE_CLK 376 +#define GCC_VIDEO_VCODEC_THROTTLE_CLK 377 +#define GCC_VIDEO_XO_CLK 378 +#define GCC_AGGRE_UFS_CARD_AXI_HW_CTL_CLK 379 +#define GCC_AGGRE_UFS_PHY_AXI_HW_CTL_CLK 380 +#define GCC_UFS_CARD_AXI_HW_CTL_CLK 381 +#define GCC_UFS_CARD_ICE_CORE_HW_CTL_CLK 382 +#define GCC_UFS_CARD_PHY_AUX_HW_CTL_CLK 383 +#define GCC_UFS_CARD_UNIPRO_CORE_HW_CTL_CLK 384 +#define GCC_UFS_PHY_AXI_HW_CTL_CLK 385 +#define GCC_UFS_PHY_ICE_CORE_HW_CTL_CLK 386 +#define GCC_UFS_PHY_PHY_AUX_HW_CTL_CLK 387 +#define GCC_UFS_PHY_UNIPRO_CORE_HW_CTL_CLK 388 + +/* GCC resets */ +#define GCC_EMAC0_BCR 0 +#define GCC_EMAC1_BCR 1 +#define GCC_PCIE_0_LINK_DOWN_BCR 2 +#define GCC_PCIE_0_NOCSR_COM_PHY_BCR 3 +#define GCC_PCIE_0_PHY_BCR 4 +#define GCC_PCIE_0_PHY_NOCSR_COM_PHY_BCR 5 +#define GCC_PCIE_0_TUNNEL_BCR 6 +#define GCC_PCIE_1_LINK_DOWN_BCR 7 +#define GCC_PCIE_1_NOCSR_COM_PHY_BCR 8 +#define GCC_PCIE_1_PHY_BCR 9 +#define GCC_PCIE_1_PHY_NOCSR_COM_PHY_BCR 10 +#define GCC_PCIE_1_TUNNEL_BCR 11 +#define GCC_PCIE_2A_BCR 12 +#define GCC_PCIE_2A_LINK_DOWN_BCR 13 +#define GCC_PCIE_2A_NOCSR_COM_PHY_BCR 14 +#define GCC_PCIE_2A_PHY_BCR 15 +#define GCC_PCIE_2A_PHY_NOCSR_COM_PHY_BCR 16 +#define GCC_PCIE_2B_BCR 17 +#define GCC_PCIE_2B_LINK_DOWN_BCR 18 +#define GCC_PCIE_2B_NOCSR_COM_PHY_BCR 19 +#define GCC_PCIE_2B_PHY_BCR 20 +#define GCC_PCIE_2B_PHY_NOCSR_COM_PHY_BCR 21 +#define GCC_PCIE_3A_BCR 22 +#define GCC_PCIE_3A_LINK_DOWN_BCR 23 +#define GCC_PCIE_3A_NOCSR_COM_PHY_BCR 24 +#define GCC_PCIE_3A_PHY_BCR 25 +#define GCC_PCIE_3A_PHY_NOCSR_COM_PHY_BCR 26 +#define GCC_PCIE_3B_BCR 27 +#define GCC_PCIE_3B_LINK_DOWN_BCR 28 +#define GCC_PCIE_3B_NOCSR_COM_PHY_BCR 29 +#define GCC_PCIE_3B_PHY_BCR 30 +#define GCC_PCIE_3B_PHY_NOCSR_COM_PHY_BCR 31 +#define GCC_PCIE_4_BCR 32 +#define GCC_PCIE_4_LINK_DOWN_BCR 33 +#define GCC_PCIE_4_NOCSR_COM_PHY_BCR 34 +#define GCC_PCIE_4_PHY_BCR 35 +#define GCC_PCIE_4_PHY_NOCSR_COM_PHY_BCR 36 +#define GCC_PCIE_PHY_CFG_AHB_BCR 37 +#define GCC_PCIE_PHY_COM_BCR 38 +#define GCC_PCIE_RSCC_BCR 39 +#define GCC_QUSB2PHY_HS0_MP_BCR 40 +#define GCC_QUSB2PHY_HS1_MP_BCR 41 +#define GCC_QUSB2PHY_HS2_MP_BCR 42 +#define GCC_QUSB2PHY_HS3_MP_BCR 43 +#define GCC_QUSB2PHY_PRIM_BCR 44 +#define GCC_QUSB2PHY_SEC_BCR 45 +#define GCC_SDCC2_BCR 46 +#define GCC_SDCC4_BCR 47 +#define GCC_UFS_CARD_BCR 48 +#define GCC_UFS_PHY_BCR 49 +#define GCC_USB2_PHY_PRIM_BCR 50 +#define GCC_USB2_PHY_SEC_BCR 51 +#define GCC_USB30_MP_BCR 52 +#define GCC_USB30_PRIM_BCR 53 +#define GCC_USB30_SEC_BCR 54 +#define GCC_USB3_DP_PHY_PRIM_BCR 55 +#define GCC_USB3_DP_PHY_SEC_BCR 56 +#define GCC_USB3_PHY_PRIM_BCR 57 +#define GCC_USB3_PHY_SEC_BCR 58 +#define GCC_USB3_UNIPHY_MP0_BCR 59 +#define GCC_USB3_UNIPHY_MP1_BCR 60 +#define GCC_USB3PHY_PHY_PRIM_BCR 61 +#define GCC_USB3PHY_PHY_SEC_BCR 62 +#define GCC_USB3UNIPHY_PHY_MP0_BCR 63 +#define GCC_USB3UNIPHY_PHY_MP1_BCR 64 +#define GCC_USB4_1_BCR 65 +#define GCC_USB4_1_DP_PHY_PRIM_BCR 66 +#define GCC_USB4_1_DPPHY_AUX_BCR 67 +#define GCC_USB4_1_PHY_PRIM_BCR 68 +#define GCC_USB4_BCR 69 +#define GCC_USB4_DP_PHY_PRIM_BCR 70 +#define GCC_USB4_DPPHY_AUX_BCR 71 +#define GCC_USB4_PHY_PRIM_BCR 72 +#define GCC_USB4PHY_1_PHY_PRIM_BCR 73 +#define GCC_USB4PHY_PHY_PRIM_BCR 74 +#define GCC_USB_PHY_CFG_AHB2PHY_BCR 75 +#define GCC_VIDEO_BCR 76 +#define GCC_VIDEO_AXI0_CLK_ARES 77 +#define GCC_VIDEO_AXI1_CLK_ARES 78 + +/* GCC GDSCs */ +#define PCIE_0_TUNNEL_GDSC 0 +#define PCIE_1_TUNNEL_GDSC 1 +#define PCIE_2A_GDSC 2 +#define PCIE_2B_GDSC 3 +#define PCIE_3A_GDSC 4 +#define PCIE_3B_GDSC 5 +#define PCIE_4_GDSC 6 +#define UFS_CARD_GDSC 7 +#define UFS_PHY_GDSC 8 +#define USB30_MP_GDSC 9 +#define USB30_PRIM_GDSC 10 +#define USB30_SEC_GDSC 11 + +#endif -- cgit v1.2.3 From 546a3fee174969ff323d70ff27b1ef181f0d7ceb Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 17 May 2022 13:46:54 +0200 Subject: sched: Reverse sched_class layout Because GCC-12 is fully stupid about array bounds and it's just really hard to get a solid array definition from a linker script, flip the array order to avoid needing negative offsets :-/ This makes the whole relational pointer magic a little less obvious, but alas. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/YoOLLmLG7HRTXeEm@hirez.programming.kicks-ass.net --- include/asm-generic/vmlinux.lds.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 69138e9db787..7515a465ec03 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -126,13 +126,13 @@ */ #define SCHED_DATA \ STRUCT_ALIGN(); \ - __begin_sched_classes = .; \ - *(__idle_sched_class) \ - *(__fair_sched_class) \ - *(__rt_sched_class) \ - *(__dl_sched_class) \ + __sched_class_highest = .; \ *(__stop_sched_class) \ - __end_sched_classes = .; + *(__dl_sched_class) \ + *(__rt_sched_class) \ + *(__fair_sched_class) \ + *(__idle_sched_class) \ + __sched_class_lowest = .; /* The actual configuration determine if the init/exit sections * are handled as text/data or they can be discarded (which -- cgit v1.2.3 From 991d8d8142cad94f9c5c05db25e67fa83d6f772a Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann Date: Fri, 13 May 2022 11:34:33 +0200 Subject: topology: Remove unused cpu_cluster_mask() default_topology[] uses cpu_clustergroup_mask() for the CLS level (guarded by CONFIG_SCHED_CLUSTER) which is currently provided by x86 (arch/x86/kernel/smpboot.c) and arm64 (drivers/base/arch_topology.c). Fixes: 778c558f49a2c ("sched: Add cluster scheduler level in core and related Kconfig for ARM64") Signed-off-by: Dietmar Eggemann Signed-off-by: Peter Zijlstra (Intel) Acked-by: Barry Song Link: https://lore.kernel.org/r/20220513093433.425163-1-dietmar.eggemann@arm.com --- include/linux/topology.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include') diff --git a/include/linux/topology.h b/include/linux/topology.h index f19bc3626297..4564faafd0e1 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -240,13 +240,6 @@ static inline const struct cpumask *cpu_smt_mask(int cpu) } #endif -#if defined(CONFIG_SCHED_CLUSTER) && !defined(cpu_cluster_mask) -static inline const struct cpumask *cpu_cluster_mask(int cpu) -{ - return topology_cluster_cpumask(cpu); -} -#endif - static inline const struct cpumask *cpu_cpu_mask(int cpu) { return cpumask_of_node(cpu_to_node(cpu)); -- cgit v1.2.3 From 5cebb40bc9554aafcc492431181f43c6231b0459 Mon Sep 17 00:00:00 2001 From: Harini Katakam Date: Wed, 18 May 2022 22:37:56 +0530 Subject: net: macb: Fix PTP one step sync support PTP one step sync packets cannot have CSUM padding and insertion in SW since time stamp is inserted on the fly by HW. In addition, ptp4l version 3.0 and above report an error when skb timestamps are reported for packets that not processed for TX TS after transmission. Add a helper to identify PTP one step sync and fix the above two errors. Add a common mask for PTP header flag field "twoStepflag". Also reset ptp OSS bit when one step is not selected. Fixes: ab91f0a9b5f4 ("net: macb: Add hardware PTP support") Fixes: 653e92a9175e ("net: macb: add support for padding and fcs computation") Signed-off-by: Harini Katakam Reviewed-by: Radhey Shyam Pandey Reviewed-by: Claudiu Beznea Link: https://lore.kernel.org/r/20220518170756.7752-1-harini.katakam@xilinx.com Signed-off-by: Jakub Kicinski --- include/linux/ptp_classify.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index fefa7790dc46..2b6ea36ad162 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -43,6 +43,9 @@ #define OFF_PTP_SOURCE_UUID 22 /* PTPv1 only */ #define OFF_PTP_SEQUENCE_ID 30 +/* PTP header flag fields */ +#define PTP_FLAG_TWOSTEP BIT(1) + /* Below defines should actually be removed at some point in time. */ #define IP6_HLEN 40 #define UDP_HLEN 8 -- cgit v1.2.3 From 057e5fc03369f8f2ed9b2ca884754b1d80b83620 Mon Sep 17 00:00:00 2001 From: John Garry Date: Thu, 12 May 2022 19:15:32 +0800 Subject: scsi: libsas: Refactor sas_ata_hard_reset() Create function sas_ata_wait_after_reset() from sas_ata_hard_reset() as some LLDDs may want to check for a remote ATA phy is up after reset. Link: https://lore.kernel.org/r/1652354134-171343-2-git-send-email-john.garry@huawei.com Tested-by: Yihang Li Reviewed-by: Xiang Chen Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/sas_ata.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/scsi/sas_ata.h b/include/scsi/sas_ata.h index d47dea70855d..a1df4f9d57a3 100644 --- a/include/scsi/sas_ata.h +++ b/include/scsi/sas_ata.h @@ -34,6 +34,7 @@ void sas_resume_sata(struct asd_sas_port *port); void sas_ata_end_eh(struct ata_port *ap); int sas_execute_ata_cmd(struct domain_device *device, u8 *fis, int force_phy_id); +int sas_ata_wait_after_reset(struct domain_device *dev, unsigned long deadline); #else @@ -91,6 +92,12 @@ static inline int sas_execute_ata_cmd(struct domain_device *device, u8 *fis, { return 0; } + +static inline int sas_ata_wait_after_reset(struct domain_device *dev, + unsigned long deadline) +{ + return -ETIMEDOUT; +} #endif #endif /* _SAS_ATA_H_ */ -- cgit v1.2.3 From 827fc630e4c8087df5a8e8ee013b686bd6f13736 Mon Sep 17 00:00:00 2001 From: Muneendra Kumar Date: Thu, 19 May 2022 05:31:07 -0700 Subject: scsi: nvme-fc: Add new routine nvme_fc_io_getuuid() Add nvme_fc_io_getuuid() to the nvme-fc transport. The routine is invoked by the FC LLDD on a per-I/O request basis. The routine translates from the FC-specific request structure to the bio and the cgroup structure in order to obtain the FC appid stored in the cgroup structure. If a value is not set or a bio is not found, a NULL appid (aka uuid) will be returned to the LLDD. Link: https://lore.kernel.org/r/20220519123110.17361-2-jsmart2021@gmail.com Reviewed-by: Hannes Reinecke Reviewed-by: Himanshu Madhani Acked-by: Christoph Hellwig Signed-off-by: Muneendra Kumar Signed-off-by: James Smart Signed-off-by: Martin K. Petersen --- include/linux/nvme-fc-driver.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 5358a5facdee..fa092b9be2fd 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -564,6 +564,15 @@ int nvme_fc_rcv_ls_req(struct nvme_fc_remote_port *remoteport, void *lsreqbuf, u32 lsreqbuf_len); +/* + * Routine called to get the appid field associated with request by the lldd + * + * If the return value is NULL : the user/libvirt has not set the appid to VM + * If the return value is non-zero: Returns the appid associated with VM + * + * @req: IO request from nvme fc to driver + */ +char *nvme_fc_io_getuuid(struct nvmefc_fcp_req *req); /* * *************** LLDD FC-NVME Target/Subsystem API *************** @@ -1048,5 +1057,10 @@ int nvmet_fc_rcv_fcp_req(struct nvmet_fc_target_port *tgtport, void nvmet_fc_rcv_fcp_abort(struct nvmet_fc_target_port *tgtport, struct nvmefc_tgt_fcp_req *fcpreq); +/* + * add a define, visible to the compiler, that indicates support + * for feature. Allows for conditional compilation in LLDDs. + */ +#define NVME_FC_FEAT_UUID 0x0001 #endif /* _NVME_FC_DRIVER_H */ -- cgit v1.2.3 From dd11376b9f1b73aca3f8c6eb541486bbb6996f05 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 11 May 2022 14:25:52 -0700 Subject: scsi: ufs: Split the drivers/scsi/ufs directory Split the drivers/scsi/ufs directory into 'core' and 'host' directories under the drivers/ufs/ directory. Move shared header files into the include/ufs/ directory. This separation makes it clear which header files UFS drivers are allowed to include (include/ufs/*.h) and which header files UFS drivers are not allowed to include (drivers/ufs/core/*.h). Update the MAINTAINERS file. Add myself as a UFS reviewer. Link: https://lore.kernel.org/r/20220511212552.655341-1-bvanassche@acm.org Cc: Adrian Hunter Cc: Avri Altman Cc: Bean Huo Cc: Bjorn Andersson Cc: Keoseong Park Tested-by: Bean Huo Tested-by: Adrian Hunter Reviewed-by: Bean Huo Acked-by: Avri Altman Acked-by: Adrian Hunter Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- include/ufs/ufs.h | 623 +++++++++++++++++++++++ include/ufs/ufs_quirks.h | 116 +++++ include/ufs/ufshcd.h | 1230 ++++++++++++++++++++++++++++++++++++++++++++++ include/ufs/ufshci.h | 510 +++++++++++++++++++ include/ufs/unipro.h | 316 ++++++++++++ 5 files changed, 2795 insertions(+) create mode 100644 include/ufs/ufs.h create mode 100644 include/ufs/ufs_quirks.h create mode 100644 include/ufs/ufshcd.h create mode 100644 include/ufs/ufshci.h create mode 100644 include/ufs/unipro.h (limited to 'include') diff --git a/include/ufs/ufs.h b/include/ufs/ufs.h new file mode 100644 index 000000000000..1bba3fead2ce --- /dev/null +++ b/include/ufs/ufs.h @@ -0,0 +1,623 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Universal Flash Storage Host controller driver + * Copyright (C) 2011-2013 Samsung India Software Operations + * + * Authors: + * Santosh Yaraganavi + * Vinayak Holikatti + */ + +#ifndef _UFS_H +#define _UFS_H + +#include +#include +#include + +#define GENERAL_UPIU_REQUEST_SIZE (sizeof(struct utp_upiu_req)) +#define QUERY_DESC_MAX_SIZE 255 +#define QUERY_DESC_MIN_SIZE 2 +#define QUERY_DESC_HDR_SIZE 2 +#define QUERY_OSF_SIZE (GENERAL_UPIU_REQUEST_SIZE - \ + (sizeof(struct utp_upiu_header))) +#define UFS_SENSE_SIZE 18 + +#define UPIU_HEADER_DWORD(byte3, byte2, byte1, byte0)\ + cpu_to_be32((byte3 << 24) | (byte2 << 16) |\ + (byte1 << 8) | (byte0)) +/* + * UFS device may have standard LUs and LUN id could be from 0x00 to + * 0x7F. Standard LUs use "Peripheral Device Addressing Format". + * UFS device may also have the Well Known LUs (also referred as W-LU) + * which again could be from 0x00 to 0x7F. For W-LUs, device only use + * the "Extended Addressing Format" which means the W-LUNs would be + * from 0xc100 (SCSI_W_LUN_BASE) onwards. + * This means max. LUN number reported from UFS device could be 0xC17F. + */ +#define UFS_UPIU_MAX_UNIT_NUM_ID 0x7F +#define UFS_MAX_LUNS (SCSI_W_LUN_BASE + UFS_UPIU_MAX_UNIT_NUM_ID) +#define UFS_UPIU_WLUN_ID (1 << 7) +#define UFS_RPMB_UNIT 0xC4 + +/* WriteBooster buffer is available only for the logical unit from 0 to 7 */ +#define UFS_UPIU_MAX_WB_LUN_ID 8 + +/* + * WriteBooster buffer lifetime has a limit setted by vendor. + * If it is over the limit, WriteBooster feature will be disabled. + */ +#define UFS_WB_EXCEED_LIFETIME 0x0B + +/* Well known logical unit id in LUN field of UPIU */ +enum { + UFS_UPIU_REPORT_LUNS_WLUN = 0x81, + UFS_UPIU_UFS_DEVICE_WLUN = 0xD0, + UFS_UPIU_BOOT_WLUN = 0xB0, + UFS_UPIU_RPMB_WLUN = 0xC4, +}; + +/* + * UFS Protocol Information Unit related definitions + */ + +/* Task management functions */ +enum { + UFS_ABORT_TASK = 0x01, + UFS_ABORT_TASK_SET = 0x02, + UFS_CLEAR_TASK_SET = 0x04, + UFS_LOGICAL_RESET = 0x08, + UFS_QUERY_TASK = 0x80, + UFS_QUERY_TASK_SET = 0x81, +}; + +/* UTP UPIU Transaction Codes Initiator to Target */ +enum { + UPIU_TRANSACTION_NOP_OUT = 0x00, + UPIU_TRANSACTION_COMMAND = 0x01, + UPIU_TRANSACTION_DATA_OUT = 0x02, + UPIU_TRANSACTION_TASK_REQ = 0x04, + UPIU_TRANSACTION_QUERY_REQ = 0x16, +}; + +/* UTP UPIU Transaction Codes Target to Initiator */ +enum { + UPIU_TRANSACTION_NOP_IN = 0x20, + UPIU_TRANSACTION_RESPONSE = 0x21, + UPIU_TRANSACTION_DATA_IN = 0x22, + UPIU_TRANSACTION_TASK_RSP = 0x24, + UPIU_TRANSACTION_READY_XFER = 0x31, + UPIU_TRANSACTION_QUERY_RSP = 0x36, + UPIU_TRANSACTION_REJECT_UPIU = 0x3F, +}; + +/* UPIU Read/Write flags */ +enum { + UPIU_CMD_FLAGS_NONE = 0x00, + UPIU_CMD_FLAGS_WRITE = 0x20, + UPIU_CMD_FLAGS_READ = 0x40, +}; + +/* UPIU Task Attributes */ +enum { + UPIU_TASK_ATTR_SIMPLE = 0x00, + UPIU_TASK_ATTR_ORDERED = 0x01, + UPIU_TASK_ATTR_HEADQ = 0x02, + UPIU_TASK_ATTR_ACA = 0x03, +}; + +/* UPIU Query request function */ +enum { + UPIU_QUERY_FUNC_STANDARD_READ_REQUEST = 0x01, + UPIU_QUERY_FUNC_STANDARD_WRITE_REQUEST = 0x81, +}; + +/* Flag idn for Query Requests*/ +enum flag_idn { + QUERY_FLAG_IDN_FDEVICEINIT = 0x01, + QUERY_FLAG_IDN_PERMANENT_WPE = 0x02, + QUERY_FLAG_IDN_PWR_ON_WPE = 0x03, + QUERY_FLAG_IDN_BKOPS_EN = 0x04, + QUERY_FLAG_IDN_LIFE_SPAN_MODE_ENABLE = 0x05, + QUERY_FLAG_IDN_PURGE_ENABLE = 0x06, + QUERY_FLAG_IDN_RESERVED2 = 0x07, + QUERY_FLAG_IDN_FPHYRESOURCEREMOVAL = 0x08, + QUERY_FLAG_IDN_BUSY_RTC = 0x09, + QUERY_FLAG_IDN_RESERVED3 = 0x0A, + QUERY_FLAG_IDN_PERMANENTLY_DISABLE_FW_UPDATE = 0x0B, + QUERY_FLAG_IDN_WB_EN = 0x0E, + QUERY_FLAG_IDN_WB_BUFF_FLUSH_EN = 0x0F, + QUERY_FLAG_IDN_WB_BUFF_FLUSH_DURING_HIBERN8 = 0x10, + QUERY_FLAG_IDN_HPB_RESET = 0x11, + QUERY_FLAG_IDN_HPB_EN = 0x12, +}; + +/* Attribute idn for Query requests */ +enum attr_idn { + QUERY_ATTR_IDN_BOOT_LU_EN = 0x00, + QUERY_ATTR_IDN_MAX_HPB_SINGLE_CMD = 0x01, + QUERY_ATTR_IDN_POWER_MODE = 0x02, + QUERY_ATTR_IDN_ACTIVE_ICC_LVL = 0x03, + QUERY_ATTR_IDN_OOO_DATA_EN = 0x04, + QUERY_ATTR_IDN_BKOPS_STATUS = 0x05, + QUERY_ATTR_IDN_PURGE_STATUS = 0x06, + QUERY_ATTR_IDN_MAX_DATA_IN = 0x07, + QUERY_ATTR_IDN_MAX_DATA_OUT = 0x08, + QUERY_ATTR_IDN_DYN_CAP_NEEDED = 0x09, + QUERY_ATTR_IDN_REF_CLK_FREQ = 0x0A, + QUERY_ATTR_IDN_CONF_DESC_LOCK = 0x0B, + QUERY_ATTR_IDN_MAX_NUM_OF_RTT = 0x0C, + QUERY_ATTR_IDN_EE_CONTROL = 0x0D, + QUERY_ATTR_IDN_EE_STATUS = 0x0E, + QUERY_ATTR_IDN_SECONDS_PASSED = 0x0F, + QUERY_ATTR_IDN_CNTX_CONF = 0x10, + QUERY_ATTR_IDN_CORR_PRG_BLK_NUM = 0x11, + QUERY_ATTR_IDN_RESERVED2 = 0x12, + QUERY_ATTR_IDN_RESERVED3 = 0x13, + QUERY_ATTR_IDN_FFU_STATUS = 0x14, + QUERY_ATTR_IDN_PSA_STATE = 0x15, + QUERY_ATTR_IDN_PSA_DATA_SIZE = 0x16, + QUERY_ATTR_IDN_REF_CLK_GATING_WAIT_TIME = 0x17, + QUERY_ATTR_IDN_CASE_ROUGH_TEMP = 0x18, + QUERY_ATTR_IDN_HIGH_TEMP_BOUND = 0x19, + QUERY_ATTR_IDN_LOW_TEMP_BOUND = 0x1A, + QUERY_ATTR_IDN_WB_FLUSH_STATUS = 0x1C, + QUERY_ATTR_IDN_AVAIL_WB_BUFF_SIZE = 0x1D, + QUERY_ATTR_IDN_WB_BUFF_LIFE_TIME_EST = 0x1E, + QUERY_ATTR_IDN_CURR_WB_BUFF_SIZE = 0x1F, +}; + +/* Descriptor idn for Query requests */ +enum desc_idn { + QUERY_DESC_IDN_DEVICE = 0x0, + QUERY_DESC_IDN_CONFIGURATION = 0x1, + QUERY_DESC_IDN_UNIT = 0x2, + QUERY_DESC_IDN_RFU_0 = 0x3, + QUERY_DESC_IDN_INTERCONNECT = 0x4, + QUERY_DESC_IDN_STRING = 0x5, + QUERY_DESC_IDN_RFU_1 = 0x6, + QUERY_DESC_IDN_GEOMETRY = 0x7, + QUERY_DESC_IDN_POWER = 0x8, + QUERY_DESC_IDN_HEALTH = 0x9, + QUERY_DESC_IDN_MAX, +}; + +enum desc_header_offset { + QUERY_DESC_LENGTH_OFFSET = 0x00, + QUERY_DESC_DESC_TYPE_OFFSET = 0x01, +}; + +/* Unit descriptor parameters offsets in bytes*/ +enum unit_desc_param { + UNIT_DESC_PARAM_LEN = 0x0, + UNIT_DESC_PARAM_TYPE = 0x1, + UNIT_DESC_PARAM_UNIT_INDEX = 0x2, + UNIT_DESC_PARAM_LU_ENABLE = 0x3, + UNIT_DESC_PARAM_BOOT_LUN_ID = 0x4, + UNIT_DESC_PARAM_LU_WR_PROTECT = 0x5, + UNIT_DESC_PARAM_LU_Q_DEPTH = 0x6, + UNIT_DESC_PARAM_PSA_SENSITIVE = 0x7, + UNIT_DESC_PARAM_MEM_TYPE = 0x8, + UNIT_DESC_PARAM_DATA_RELIABILITY = 0x9, + UNIT_DESC_PARAM_LOGICAL_BLK_SIZE = 0xA, + UNIT_DESC_PARAM_LOGICAL_BLK_COUNT = 0xB, + UNIT_DESC_PARAM_ERASE_BLK_SIZE = 0x13, + UNIT_DESC_PARAM_PROVISIONING_TYPE = 0x17, + UNIT_DESC_PARAM_PHY_MEM_RSRC_CNT = 0x18, + UNIT_DESC_PARAM_CTX_CAPABILITIES = 0x20, + UNIT_DESC_PARAM_LARGE_UNIT_SIZE_M1 = 0x22, + UNIT_DESC_PARAM_HPB_LU_MAX_ACTIVE_RGNS = 0x23, + UNIT_DESC_PARAM_HPB_PIN_RGN_START_OFF = 0x25, + UNIT_DESC_PARAM_HPB_NUM_PIN_RGNS = 0x27, + UNIT_DESC_PARAM_WB_BUF_ALLOC_UNITS = 0x29, +}; + +/* Device descriptor parameters offsets in bytes*/ +enum device_desc_param { + DEVICE_DESC_PARAM_LEN = 0x0, + DEVICE_DESC_PARAM_TYPE = 0x1, + DEVICE_DESC_PARAM_DEVICE_TYPE = 0x2, + DEVICE_DESC_PARAM_DEVICE_CLASS = 0x3, + DEVICE_DESC_PARAM_DEVICE_SUB_CLASS = 0x4, + DEVICE_DESC_PARAM_PRTCL = 0x5, + DEVICE_DESC_PARAM_NUM_LU = 0x6, + DEVICE_DESC_PARAM_NUM_WLU = 0x7, + DEVICE_DESC_PARAM_BOOT_ENBL = 0x8, + DEVICE_DESC_PARAM_DESC_ACCSS_ENBL = 0x9, + DEVICE_DESC_PARAM_INIT_PWR_MODE = 0xA, + DEVICE_DESC_PARAM_HIGH_PR_LUN = 0xB, + DEVICE_DESC_PARAM_SEC_RMV_TYPE = 0xC, + DEVICE_DESC_PARAM_SEC_LU = 0xD, + DEVICE_DESC_PARAM_BKOP_TERM_LT = 0xE, + DEVICE_DESC_PARAM_ACTVE_ICC_LVL = 0xF, + DEVICE_DESC_PARAM_SPEC_VER = 0x10, + DEVICE_DESC_PARAM_MANF_DATE = 0x12, + DEVICE_DESC_PARAM_MANF_NAME = 0x14, + DEVICE_DESC_PARAM_PRDCT_NAME = 0x15, + DEVICE_DESC_PARAM_SN = 0x16, + DEVICE_DESC_PARAM_OEM_ID = 0x17, + DEVICE_DESC_PARAM_MANF_ID = 0x18, + DEVICE_DESC_PARAM_UD_OFFSET = 0x1A, + DEVICE_DESC_PARAM_UD_LEN = 0x1B, + DEVICE_DESC_PARAM_RTT_CAP = 0x1C, + DEVICE_DESC_PARAM_FRQ_RTC = 0x1D, + DEVICE_DESC_PARAM_UFS_FEAT = 0x1F, + DEVICE_DESC_PARAM_FFU_TMT = 0x20, + DEVICE_DESC_PARAM_Q_DPTH = 0x21, + DEVICE_DESC_PARAM_DEV_VER = 0x22, + DEVICE_DESC_PARAM_NUM_SEC_WPA = 0x24, + DEVICE_DESC_PARAM_PSA_MAX_DATA = 0x25, + DEVICE_DESC_PARAM_PSA_TMT = 0x29, + DEVICE_DESC_PARAM_PRDCT_REV = 0x2A, + DEVICE_DESC_PARAM_HPB_VER = 0x40, + DEVICE_DESC_PARAM_HPB_CONTROL = 0x42, + DEVICE_DESC_PARAM_EXT_UFS_FEATURE_SUP = 0x4F, + DEVICE_DESC_PARAM_WB_PRESRV_USRSPC_EN = 0x53, + DEVICE_DESC_PARAM_WB_TYPE = 0x54, + DEVICE_DESC_PARAM_WB_SHARED_ALLOC_UNITS = 0x55, +}; + +/* Interconnect descriptor parameters offsets in bytes*/ +enum interconnect_desc_param { + INTERCONNECT_DESC_PARAM_LEN = 0x0, + INTERCONNECT_DESC_PARAM_TYPE = 0x1, + INTERCONNECT_DESC_PARAM_UNIPRO_VER = 0x2, + INTERCONNECT_DESC_PARAM_MPHY_VER = 0x4, +}; + +/* Geometry descriptor parameters offsets in bytes*/ +enum geometry_desc_param { + GEOMETRY_DESC_PARAM_LEN = 0x0, + GEOMETRY_DESC_PARAM_TYPE = 0x1, + GEOMETRY_DESC_PARAM_DEV_CAP = 0x4, + GEOMETRY_DESC_PARAM_MAX_NUM_LUN = 0xC, + GEOMETRY_DESC_PARAM_SEG_SIZE = 0xD, + GEOMETRY_DESC_PARAM_ALLOC_UNIT_SIZE = 0x11, + GEOMETRY_DESC_PARAM_MIN_BLK_SIZE = 0x12, + GEOMETRY_DESC_PARAM_OPT_RD_BLK_SIZE = 0x13, + GEOMETRY_DESC_PARAM_OPT_WR_BLK_SIZE = 0x14, + GEOMETRY_DESC_PARAM_MAX_IN_BUF_SIZE = 0x15, + GEOMETRY_DESC_PARAM_MAX_OUT_BUF_SIZE = 0x16, + GEOMETRY_DESC_PARAM_RPMB_RW_SIZE = 0x17, + GEOMETRY_DESC_PARAM_DYN_CAP_RSRC_PLC = 0x18, + GEOMETRY_DESC_PARAM_DATA_ORDER = 0x19, + GEOMETRY_DESC_PARAM_MAX_NUM_CTX = 0x1A, + GEOMETRY_DESC_PARAM_TAG_UNIT_SIZE = 0x1B, + GEOMETRY_DESC_PARAM_TAG_RSRC_SIZE = 0x1C, + GEOMETRY_DESC_PARAM_SEC_RM_TYPES = 0x1D, + GEOMETRY_DESC_PARAM_MEM_TYPES = 0x1E, + GEOMETRY_DESC_PARAM_SCM_MAX_NUM_UNITS = 0x20, + GEOMETRY_DESC_PARAM_SCM_CAP_ADJ_FCTR = 0x24, + GEOMETRY_DESC_PARAM_NPM_MAX_NUM_UNITS = 0x26, + GEOMETRY_DESC_PARAM_NPM_CAP_ADJ_FCTR = 0x2A, + GEOMETRY_DESC_PARAM_ENM1_MAX_NUM_UNITS = 0x2C, + GEOMETRY_DESC_PARAM_ENM1_CAP_ADJ_FCTR = 0x30, + GEOMETRY_DESC_PARAM_ENM2_MAX_NUM_UNITS = 0x32, + GEOMETRY_DESC_PARAM_ENM2_CAP_ADJ_FCTR = 0x36, + GEOMETRY_DESC_PARAM_ENM3_MAX_NUM_UNITS = 0x38, + GEOMETRY_DESC_PARAM_ENM3_CAP_ADJ_FCTR = 0x3C, + GEOMETRY_DESC_PARAM_ENM4_MAX_NUM_UNITS = 0x3E, + GEOMETRY_DESC_PARAM_ENM4_CAP_ADJ_FCTR = 0x42, + GEOMETRY_DESC_PARAM_OPT_LOG_BLK_SIZE = 0x44, + GEOMETRY_DESC_PARAM_HPB_REGION_SIZE = 0x48, + GEOMETRY_DESC_PARAM_HPB_NUMBER_LU = 0x49, + GEOMETRY_DESC_PARAM_HPB_SUBREGION_SIZE = 0x4A, + GEOMETRY_DESC_PARAM_HPB_MAX_ACTIVE_REGS = 0x4B, + GEOMETRY_DESC_PARAM_WB_MAX_ALLOC_UNITS = 0x4F, + GEOMETRY_DESC_PARAM_WB_MAX_WB_LUNS = 0x53, + GEOMETRY_DESC_PARAM_WB_BUFF_CAP_ADJ = 0x54, + GEOMETRY_DESC_PARAM_WB_SUP_RED_TYPE = 0x55, + GEOMETRY_DESC_PARAM_WB_SUP_WB_TYPE = 0x56, +}; + +/* Health descriptor parameters offsets in bytes*/ +enum health_desc_param { + HEALTH_DESC_PARAM_LEN = 0x0, + HEALTH_DESC_PARAM_TYPE = 0x1, + HEALTH_DESC_PARAM_EOL_INFO = 0x2, + HEALTH_DESC_PARAM_LIFE_TIME_EST_A = 0x3, + HEALTH_DESC_PARAM_LIFE_TIME_EST_B = 0x4, +}; + +/* WriteBooster buffer mode */ +enum { + WB_BUF_MODE_LU_DEDICATED = 0x0, + WB_BUF_MODE_SHARED = 0x1, +}; + +/* + * Logical Unit Write Protect + * 00h: LU not write protected + * 01h: LU write protected when fPowerOnWPEn =1 + * 02h: LU permanently write protected when fPermanentWPEn =1 + */ +enum ufs_lu_wp_type { + UFS_LU_NO_WP = 0x00, + UFS_LU_POWER_ON_WP = 0x01, + UFS_LU_PERM_WP = 0x02, +}; + +/* bActiveICCLevel parameter current units */ +enum { + UFSHCD_NANO_AMP = 0, + UFSHCD_MICRO_AMP = 1, + UFSHCD_MILI_AMP = 2, + UFSHCD_AMP = 3, +}; + +/* Possible values for dExtendedUFSFeaturesSupport */ +enum { + UFS_DEV_LOW_TEMP_NOTIF = BIT(4), + UFS_DEV_HIGH_TEMP_NOTIF = BIT(5), + UFS_DEV_EXT_TEMP_NOTIF = BIT(6), + UFS_DEV_HPB_SUPPORT = BIT(7), + UFS_DEV_WRITE_BOOSTER_SUP = BIT(8), +}; +#define UFS_DEV_HPB_SUPPORT_VERSION 0x310 + +#define POWER_DESC_MAX_ACTV_ICC_LVLS 16 + +/* Attribute bActiveICCLevel parameter bit masks definitions */ +#define ATTR_ICC_LVL_UNIT_OFFSET 14 +#define ATTR_ICC_LVL_UNIT_MASK (0x3 << ATTR_ICC_LVL_UNIT_OFFSET) +#define ATTR_ICC_LVL_VALUE_MASK 0x3FF + +/* Power descriptor parameters offsets in bytes */ +enum power_desc_param_offset { + PWR_DESC_LEN = 0x0, + PWR_DESC_TYPE = 0x1, + PWR_DESC_ACTIVE_LVLS_VCC_0 = 0x2, + PWR_DESC_ACTIVE_LVLS_VCCQ_0 = 0x22, + PWR_DESC_ACTIVE_LVLS_VCCQ2_0 = 0x42, +}; + +/* Exception event mask values */ +enum { + MASK_EE_STATUS = 0xFFFF, + MASK_EE_DYNCAP_EVENT = BIT(0), + MASK_EE_SYSPOOL_EVENT = BIT(1), + MASK_EE_URGENT_BKOPS = BIT(2), + MASK_EE_TOO_HIGH_TEMP = BIT(3), + MASK_EE_TOO_LOW_TEMP = BIT(4), + MASK_EE_WRITEBOOSTER_EVENT = BIT(5), + MASK_EE_PERFORMANCE_THROTTLING = BIT(6), +}; +#define MASK_EE_URGENT_TEMP (MASK_EE_TOO_HIGH_TEMP | MASK_EE_TOO_LOW_TEMP) + +/* Background operation status */ +enum bkops_status { + BKOPS_STATUS_NO_OP = 0x0, + BKOPS_STATUS_NON_CRITICAL = 0x1, + BKOPS_STATUS_PERF_IMPACT = 0x2, + BKOPS_STATUS_CRITICAL = 0x3, + BKOPS_STATUS_MAX = BKOPS_STATUS_CRITICAL, +}; + +/* UTP QUERY Transaction Specific Fields OpCode */ +enum query_opcode { + UPIU_QUERY_OPCODE_NOP = 0x0, + UPIU_QUERY_OPCODE_READ_DESC = 0x1, + UPIU_QUERY_OPCODE_WRITE_DESC = 0x2, + UPIU_QUERY_OPCODE_READ_ATTR = 0x3, + UPIU_QUERY_OPCODE_WRITE_ATTR = 0x4, + UPIU_QUERY_OPCODE_READ_FLAG = 0x5, + UPIU_QUERY_OPCODE_SET_FLAG = 0x6, + UPIU_QUERY_OPCODE_CLEAR_FLAG = 0x7, + UPIU_QUERY_OPCODE_TOGGLE_FLAG = 0x8, +}; + +/* bRefClkFreq attribute values */ +enum ufs_ref_clk_freq { + REF_CLK_FREQ_19_2_MHZ = 0, + REF_CLK_FREQ_26_MHZ = 1, + REF_CLK_FREQ_38_4_MHZ = 2, + REF_CLK_FREQ_52_MHZ = 3, + REF_CLK_FREQ_INVAL = -1, +}; + +/* Query response result code */ +enum { + QUERY_RESULT_SUCCESS = 0x00, + QUERY_RESULT_NOT_READABLE = 0xF6, + QUERY_RESULT_NOT_WRITEABLE = 0xF7, + QUERY_RESULT_ALREADY_WRITTEN = 0xF8, + QUERY_RESULT_INVALID_LENGTH = 0xF9, + QUERY_RESULT_INVALID_VALUE = 0xFA, + QUERY_RESULT_INVALID_SELECTOR = 0xFB, + QUERY_RESULT_INVALID_INDEX = 0xFC, + QUERY_RESULT_INVALID_IDN = 0xFD, + QUERY_RESULT_INVALID_OPCODE = 0xFE, + QUERY_RESULT_GENERAL_FAILURE = 0xFF, +}; + +/* UTP Transfer Request Command Type (CT) */ +enum { + UPIU_COMMAND_SET_TYPE_SCSI = 0x0, + UPIU_COMMAND_SET_TYPE_UFS = 0x1, + UPIU_COMMAND_SET_TYPE_QUERY = 0x2, +}; + +/* UTP Transfer Request Command Offset */ +#define UPIU_COMMAND_TYPE_OFFSET 28 + +/* Offset of the response code in the UPIU header */ +#define UPIU_RSP_CODE_OFFSET 8 + +enum { + MASK_SCSI_STATUS = 0xFF, + MASK_TASK_RESPONSE = 0xFF00, + MASK_RSP_UPIU_RESULT = 0xFFFF, + MASK_QUERY_DATA_SEG_LEN = 0xFFFF, + MASK_RSP_UPIU_DATA_SEG_LEN = 0xFFFF, + MASK_RSP_EXCEPTION_EVENT = 0x10000, + MASK_TM_SERVICE_RESP = 0xFF, + MASK_TM_FUNC = 0xFF, +}; + +/* Task management service response */ +enum { + UPIU_TASK_MANAGEMENT_FUNC_COMPL = 0x00, + UPIU_TASK_MANAGEMENT_FUNC_NOT_SUPPORTED = 0x04, + UPIU_TASK_MANAGEMENT_FUNC_SUCCEEDED = 0x08, + UPIU_TASK_MANAGEMENT_FUNC_FAILED = 0x05, + UPIU_INCORRECT_LOGICAL_UNIT_NO = 0x09, +}; + +/* UFS device power modes */ +enum ufs_dev_pwr_mode { + UFS_ACTIVE_PWR_MODE = 1, + UFS_SLEEP_PWR_MODE = 2, + UFS_POWERDOWN_PWR_MODE = 3, + UFS_DEEPSLEEP_PWR_MODE = 4, +}; + +#define UFS_WB_BUF_REMAIN_PERCENT(val) ((val) / 10) + +/** + * struct utp_cmd_rsp - Response UPIU structure + * @residual_transfer_count: Residual transfer count DW-3 + * @reserved: Reserved double words DW-4 to DW-7 + * @sense_data_len: Sense data length DW-8 U16 + * @sense_data: Sense data field DW-8 to DW-12 + */ +struct utp_cmd_rsp { + __be32 residual_transfer_count; + __be32 reserved[4]; + __be16 sense_data_len; + u8 sense_data[UFS_SENSE_SIZE]; +}; + +struct ufshpb_active_field { + __be16 active_rgn; + __be16 active_srgn; +}; +#define HPB_ACT_FIELD_SIZE 4 + +/** + * struct utp_hpb_rsp - Response UPIU structure + * @residual_transfer_count: Residual transfer count DW-3 + * @reserved1: Reserved double words DW-4 to DW-7 + * @sense_data_len: Sense data length DW-8 U16 + * @desc_type: Descriptor type of sense data + * @additional_len: Additional length of sense data + * @hpb_op: HPB operation type + * @lun: LUN of response UPIU + * @active_rgn_cnt: Active region count + * @inactive_rgn_cnt: Inactive region count + * @hpb_active_field: Recommended to read HPB region and subregion + * @hpb_inactive_field: To be inactivated HPB region and subregion + */ +struct utp_hpb_rsp { + __be32 residual_transfer_count; + __be32 reserved1[4]; + __be16 sense_data_len; + u8 desc_type; + u8 additional_len; + u8 hpb_op; + u8 lun; + u8 active_rgn_cnt; + u8 inactive_rgn_cnt; + struct ufshpb_active_field hpb_active_field[2]; + __be16 hpb_inactive_field[2]; +}; +#define UTP_HPB_RSP_SIZE 40 + +/** + * struct utp_upiu_rsp - general upiu response structure + * @header: UPIU header structure DW-0 to DW-2 + * @sr: fields structure for scsi command DW-3 to DW-12 + * @qr: fields structure for query request DW-3 to DW-7 + */ +struct utp_upiu_rsp { + struct utp_upiu_header header; + union { + struct utp_cmd_rsp sr; + struct utp_hpb_rsp hr; + struct utp_upiu_query qr; + }; +}; + +/** + * struct ufs_query_req - parameters for building a query request + * @query_func: UPIU header query function + * @upiu_req: the query request data + */ +struct ufs_query_req { + u8 query_func; + struct utp_upiu_query upiu_req; +}; + +/** + * struct ufs_query_resp - UPIU QUERY + * @response: device response code + * @upiu_res: query response data + */ +struct ufs_query_res { + u8 response; + struct utp_upiu_query upiu_res; +}; + +/* + * VCCQ & VCCQ2 current requirement when UFS device is in sleep state + * and link is in Hibern8 state. + */ +#define UFS_VREG_LPM_LOAD_UA 1000 /* uA */ + +struct ufs_vreg { + struct regulator *reg; + const char *name; + bool always_on; + bool enabled; + int max_uA; +}; + +struct ufs_vreg_info { + struct ufs_vreg *vcc; + struct ufs_vreg *vccq; + struct ufs_vreg *vccq2; + struct ufs_vreg *vdd_hba; +}; + +struct ufs_dev_info { + bool f_power_on_wp_en; + /* Keeps information if any of the LU is power on write protected */ + bool is_lu_power_on_wp; + /* Maximum number of general LU supported by the UFS device */ + u8 max_lu_supported; + u16 wmanufacturerid; + /*UFS device Product Name */ + u8 *model; + u16 wspecversion; + u32 clk_gating_wait_us; + + /* UFS HPB related flag */ + bool hpb_enabled; + + /* UFS WB related flags */ + bool wb_enabled; + bool wb_buf_flush_enabled; + u8 wb_dedicated_lu; + u8 wb_buffer_type; + + bool b_rpm_dev_flush_capable; + u8 b_presrv_uspc_en; +}; + +/* + * This enum is used in string mapping in include/trace/events/ufs.h. + */ +enum ufs_trace_str_t { + UFS_CMD_SEND, UFS_CMD_COMP, UFS_DEV_COMP, + UFS_QUERY_SEND, UFS_QUERY_COMP, UFS_QUERY_ERR, + UFS_TM_SEND, UFS_TM_COMP, UFS_TM_ERR +}; + +/* + * Transaction Specific Fields (TSF) type in the UPIU package, this enum is + * used in include/trace/events/ufs.h for UFS command trace. + */ +enum ufs_trace_tsf_t { + UFS_TSF_CDB, UFS_TSF_OSF, UFS_TSF_TM_INPUT, UFS_TSF_TM_OUTPUT +}; + +#endif /* End of Header */ diff --git a/include/ufs/ufs_quirks.h b/include/ufs/ufs_quirks.h new file mode 100644 index 000000000000..bcb4f004bed5 --- /dev/null +++ b/include/ufs/ufs_quirks.h @@ -0,0 +1,116 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2014-2016, The Linux Foundation. All rights reserved. + */ + +#ifndef _UFS_QUIRKS_H_ +#define _UFS_QUIRKS_H_ + +/* return true if s1 is a prefix of s2 */ +#define STR_PRFX_EQUAL(s1, s2) !strncmp(s1, s2, strlen(s1)) + +#define UFS_ANY_VENDOR 0xFFFF +#define UFS_ANY_MODEL "ANY_MODEL" + +#define UFS_VENDOR_MICRON 0x12C +#define UFS_VENDOR_SAMSUNG 0x1CE +#define UFS_VENDOR_SKHYNIX 0x1AD +#define UFS_VENDOR_TOSHIBA 0x198 +#define UFS_VENDOR_WDC 0x145 + +/** + * ufs_dev_quirk - ufs device quirk info + * @card: ufs card details + * @quirk: device quirk + */ +struct ufs_dev_quirk { + u16 wmanufacturerid; + const u8 *model; + unsigned int quirk; +}; + +/* + * Some vendor's UFS device sends back to back NACs for the DL data frames + * causing the host controller to raise the DFES error status. Sometimes + * such UFS devices send back to back NAC without waiting for new + * retransmitted DL frame from the host and in such cases it might be possible + * the Host UniPro goes into bad state without raising the DFES error + * interrupt. If this happens then all the pending commands would timeout + * only after respective SW command (which is generally too large). + * + * We can workaround such device behaviour like this: + * - As soon as SW sees the DL NAC error, it should schedule the error handler + * - Error handler would sleep for 50ms to see if there are any fatal errors + * raised by UFS controller. + * - If there are fatal errors then SW does normal error recovery. + * - If there are no fatal errors then SW sends the NOP command to device + * to check if link is alive. + * - If NOP command times out, SW does normal error recovery + * - If NOP command succeed, skip the error handling. + * + * If DL NAC error is seen multiple times with some vendor's UFS devices then + * enable this quirk to initiate quick error recovery and also silence related + * error logs to reduce spamming of kernel logs. + */ +#define UFS_DEVICE_QUIRK_RECOVERY_FROM_DL_NAC_ERRORS (1 << 2) + +/* + * Few Toshiba UFS device models advertise RX_MIN_ACTIVATETIME_CAPABILITY as + * 600us which may not be enough for reliable hibern8 exit hardware sequence + * from UFS device. + * To workaround this issue, host should set its PA_TACTIVATE time to 1ms even + * if device advertises RX_MIN_ACTIVATETIME_CAPABILITY less than 1ms. + */ +#define UFS_DEVICE_QUIRK_PA_TACTIVATE (1 << 4) + +/* + * It seems some UFS devices may keep drawing more than sleep current + * (atleast for 500us) from UFS rails (especially from VCCQ rail). + * To avoid this situation, add 2ms delay before putting these UFS + * rails in LPM mode. + */ +#define UFS_DEVICE_QUIRK_DELAY_BEFORE_LPM (1 << 6) + +/* + * Some UFS devices require host PA_TACTIVATE to be lower than device + * PA_TACTIVATE, enabling this quirk ensure this. + */ +#define UFS_DEVICE_QUIRK_HOST_PA_TACTIVATE (1 << 7) + +/* + * The max. value PA_SaveConfigTime is 250 (10us) but this is not enough for + * some vendors. + * Gear switch from PWM to HS may fail even with this max. PA_SaveConfigTime. + * Gear switch can be issued by host controller as an error recovery and any + * software delay will not help on this case so we need to increase + * PA_SaveConfigTime to >32us as per vendor recommendation. + */ +#define UFS_DEVICE_QUIRK_HOST_PA_SAVECONFIGTIME (1 << 8) + +/* + * Some UFS devices require VS_DebugSaveConfigTime is 0x10, + * enabling this quirk ensure this. + */ +#define UFS_DEVICE_QUIRK_HOST_VS_DEBUGSAVECONFIGTIME (1 << 9) + +/* + * Some pre-3.1 UFS devices can support extended features by upgrading + * the firmware. Enable this quirk to make UFS core driver probe and enable + * supported features on such devices. + */ +#define UFS_DEVICE_QUIRK_SUPPORT_EXTENDED_FEATURES (1 << 10) + +/* + * Some UFS devices require delay after VCC power rail is turned-off. + * Enable this quirk to introduce 5ms delays after VCC power-off during + * suspend flow. + */ +#define UFS_DEVICE_QUIRK_DELAY_AFTER_LPM (1 << 11) + +/* + * Some UFS devices require L2P entry should be swapped before being sent to the + * UFS device for HPB READ command. + */ +#define UFS_DEVICE_QUIRK_SWAP_L2P_ENTRY_FOR_HPB_READ (1 << 12) + +#endif /* UFS_QUIRKS_H_ */ diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h new file mode 100644 index 000000000000..a92271421718 --- /dev/null +++ b/include/ufs/ufshcd.h @@ -0,0 +1,1230 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Universal Flash Storage Host controller driver + * Copyright (C) 2011-2013 Samsung India Software Operations + * Copyright (c) 2013-2016, The Linux Foundation. All rights reserved. + * + * Authors: + * Santosh Yaraganavi + * Vinayak Holikatti + */ + +#ifndef _UFSHCD_H +#define _UFSHCD_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define UFSHCD "ufshcd" + +struct ufs_hba; + +enum dev_cmd_type { + DEV_CMD_TYPE_NOP = 0x0, + DEV_CMD_TYPE_QUERY = 0x1, +}; + +enum ufs_event_type { + /* uic specific errors */ + UFS_EVT_PA_ERR = 0, + UFS_EVT_DL_ERR, + UFS_EVT_NL_ERR, + UFS_EVT_TL_ERR, + UFS_EVT_DME_ERR, + + /* fatal errors */ + UFS_EVT_AUTO_HIBERN8_ERR, + UFS_EVT_FATAL_ERR, + UFS_EVT_LINK_STARTUP_FAIL, + UFS_EVT_RESUME_ERR, + UFS_EVT_SUSPEND_ERR, + UFS_EVT_WL_SUSP_ERR, + UFS_EVT_WL_RES_ERR, + + /* abnormal events */ + UFS_EVT_DEV_RESET, + UFS_EVT_HOST_RESET, + UFS_EVT_ABORT, + + UFS_EVT_CNT, +}; + +/** + * struct uic_command - UIC command structure + * @command: UIC command + * @argument1: UIC command argument 1 + * @argument2: UIC command argument 2 + * @argument3: UIC command argument 3 + * @cmd_active: Indicate if UIC command is outstanding + * @done: UIC command completion + */ +struct uic_command { + u32 command; + u32 argument1; + u32 argument2; + u32 argument3; + int cmd_active; + struct completion done; +}; + +/* Used to differentiate the power management options */ +enum ufs_pm_op { + UFS_RUNTIME_PM, + UFS_SYSTEM_PM, + UFS_SHUTDOWN_PM, +}; + +/* Host <-> Device UniPro Link state */ +enum uic_link_state { + UIC_LINK_OFF_STATE = 0, /* Link powered down or disabled */ + UIC_LINK_ACTIVE_STATE = 1, /* Link is in Fast/Slow/Sleep state */ + UIC_LINK_HIBERN8_STATE = 2, /* Link is in Hibernate state */ + UIC_LINK_BROKEN_STATE = 3, /* Link is in broken state */ +}; + +#define ufshcd_is_link_off(hba) ((hba)->uic_link_state == UIC_LINK_OFF_STATE) +#define ufshcd_is_link_active(hba) ((hba)->uic_link_state == \ + UIC_LINK_ACTIVE_STATE) +#define ufshcd_is_link_hibern8(hba) ((hba)->uic_link_state == \ + UIC_LINK_HIBERN8_STATE) +#define ufshcd_is_link_broken(hba) ((hba)->uic_link_state == \ + UIC_LINK_BROKEN_STATE) +#define ufshcd_set_link_off(hba) ((hba)->uic_link_state = UIC_LINK_OFF_STATE) +#define ufshcd_set_link_active(hba) ((hba)->uic_link_state = \ + UIC_LINK_ACTIVE_STATE) +#define ufshcd_set_link_hibern8(hba) ((hba)->uic_link_state = \ + UIC_LINK_HIBERN8_STATE) +#define ufshcd_set_link_broken(hba) ((hba)->uic_link_state = \ + UIC_LINK_BROKEN_STATE) + +#define ufshcd_set_ufs_dev_active(h) \ + ((h)->curr_dev_pwr_mode = UFS_ACTIVE_PWR_MODE) +#define ufshcd_set_ufs_dev_sleep(h) \ + ((h)->curr_dev_pwr_mode = UFS_SLEEP_PWR_MODE) +#define ufshcd_set_ufs_dev_poweroff(h) \ + ((h)->curr_dev_pwr_mode = UFS_POWERDOWN_PWR_MODE) +#define ufshcd_set_ufs_dev_deepsleep(h) \ + ((h)->curr_dev_pwr_mode = UFS_DEEPSLEEP_PWR_MODE) +#define ufshcd_is_ufs_dev_active(h) \ + ((h)->curr_dev_pwr_mode == UFS_ACTIVE_PWR_MODE) +#define ufshcd_is_ufs_dev_sleep(h) \ + ((h)->curr_dev_pwr_mode == UFS_SLEEP_PWR_MODE) +#define ufshcd_is_ufs_dev_poweroff(h) \ + ((h)->curr_dev_pwr_mode == UFS_POWERDOWN_PWR_MODE) +#define ufshcd_is_ufs_dev_deepsleep(h) \ + ((h)->curr_dev_pwr_mode == UFS_DEEPSLEEP_PWR_MODE) + +/* + * UFS Power management levels. + * Each level is in increasing order of power savings, except DeepSleep + * which is lower than PowerDown with power on but not PowerDown with + * power off. + */ +enum ufs_pm_level { + UFS_PM_LVL_0, + UFS_PM_LVL_1, + UFS_PM_LVL_2, + UFS_PM_LVL_3, + UFS_PM_LVL_4, + UFS_PM_LVL_5, + UFS_PM_LVL_6, + UFS_PM_LVL_MAX +}; + +struct ufs_pm_lvl_states { + enum ufs_dev_pwr_mode dev_state; + enum uic_link_state link_state; +}; + +/** + * struct ufshcd_lrb - local reference block + * @utr_descriptor_ptr: UTRD address of the command + * @ucd_req_ptr: UCD address of the command + * @ucd_rsp_ptr: Response UPIU address for this command + * @ucd_prdt_ptr: PRDT address of the command + * @utrd_dma_addr: UTRD dma address for debug + * @ucd_prdt_dma_addr: PRDT dma address for debug + * @ucd_rsp_dma_addr: UPIU response dma address for debug + * @ucd_req_dma_addr: UPIU request dma address for debug + * @cmd: pointer to SCSI command + * @scsi_status: SCSI status of the command + * @command_type: SCSI, UFS, Query. + * @task_tag: Task tag of the command + * @lun: LUN of the command + * @intr_cmd: Interrupt command (doesn't participate in interrupt aggregation) + * @issue_time_stamp: time stamp for debug purposes + * @compl_time_stamp: time stamp for statistics + * @crypto_key_slot: the key slot to use for inline crypto (-1 if none) + * @data_unit_num: the data unit number for the first block for inline crypto + * @req_abort_skip: skip request abort task flag + */ +struct ufshcd_lrb { + struct utp_transfer_req_desc *utr_descriptor_ptr; + struct utp_upiu_req *ucd_req_ptr; + struct utp_upiu_rsp *ucd_rsp_ptr; + struct ufshcd_sg_entry *ucd_prdt_ptr; + + dma_addr_t utrd_dma_addr; + dma_addr_t ucd_req_dma_addr; + dma_addr_t ucd_rsp_dma_addr; + dma_addr_t ucd_prdt_dma_addr; + + struct scsi_cmnd *cmd; + int scsi_status; + + int command_type; + int task_tag; + u8 lun; /* UPIU LUN id field is only 8-bit wide */ + bool intr_cmd; + ktime_t issue_time_stamp; + ktime_t compl_time_stamp; +#ifdef CONFIG_SCSI_UFS_CRYPTO + int crypto_key_slot; + u64 data_unit_num; +#endif + + bool req_abort_skip; +}; + +/** + * struct ufs_query - holds relevant data structures for query request + * @request: request upiu and function + * @descriptor: buffer for sending/receiving descriptor + * @response: response upiu and response + */ +struct ufs_query { + struct ufs_query_req request; + u8 *descriptor; + struct ufs_query_res response; +}; + +/** + * struct ufs_dev_cmd - all assosiated fields with device management commands + * @type: device management command type - Query, NOP OUT + * @lock: lock to allow one command at a time + * @complete: internal commands completion + * @query: Device management query information + */ +struct ufs_dev_cmd { + enum dev_cmd_type type; + struct mutex lock; + struct completion *complete; + struct ufs_query query; +}; + +/** + * struct ufs_clk_info - UFS clock related info + * @list: list headed by hba->clk_list_head + * @clk: clock node + * @name: clock name + * @max_freq: maximum frequency supported by the clock + * @min_freq: min frequency that can be used for clock scaling + * @curr_freq: indicates the current frequency that it is set to + * @keep_link_active: indicates that the clk should not be disabled if + * link is active + * @enabled: variable to check against multiple enable/disable + */ +struct ufs_clk_info { + struct list_head list; + struct clk *clk; + const char *name; + u32 max_freq; + u32 min_freq; + u32 curr_freq; + bool keep_link_active; + bool enabled; +}; + +enum ufs_notify_change_status { + PRE_CHANGE, + POST_CHANGE, +}; + +struct ufs_pa_layer_attr { + u32 gear_rx; + u32 gear_tx; + u32 lane_rx; + u32 lane_tx; + u32 pwr_rx; + u32 pwr_tx; + u32 hs_rate; +}; + +struct ufs_pwr_mode_info { + bool is_valid; + struct ufs_pa_layer_attr info; +}; + +/** + * struct ufs_hba_variant_ops - variant specific callbacks + * @name: variant name + * @init: called when the driver is initialized + * @exit: called to cleanup everything done in init + * @get_ufs_hci_version: called to get UFS HCI version + * @clk_scale_notify: notifies that clks are scaled up/down + * @setup_clocks: called before touching any of the controller registers + * @hce_enable_notify: called before and after HCE enable bit is set to allow + * variant specific Uni-Pro initialization. + * @link_startup_notify: called before and after Link startup is carried out + * to allow variant specific Uni-Pro initialization. + * @pwr_change_notify: called before and after a power mode change + * is carried out to allow vendor spesific capabilities + * to be set. + * @setup_xfer_req: called before any transfer request is issued + * to set some things + * @setup_task_mgmt: called before any task management request is issued + * to set some things + * @hibern8_notify: called around hibern8 enter/exit + * @apply_dev_quirks: called to apply device specific quirks + * @fixup_dev_quirks: called to modify device specific quirks + * @suspend: called during host controller PM callback + * @resume: called during host controller PM callback + * @dbg_register_dump: used to dump controller debug information + * @phy_initialization: used to initialize phys + * @device_reset: called to issue a reset pulse on the UFS device + * @config_scaling_param: called to configure clock scaling parameters + * @program_key: program or evict an inline encryption key + * @event_notify: called to notify important events + */ +struct ufs_hba_variant_ops { + const char *name; + int (*init)(struct ufs_hba *); + void (*exit)(struct ufs_hba *); + u32 (*get_ufs_hci_version)(struct ufs_hba *); + int (*clk_scale_notify)(struct ufs_hba *, bool, + enum ufs_notify_change_status); + int (*setup_clocks)(struct ufs_hba *, bool, + enum ufs_notify_change_status); + int (*hce_enable_notify)(struct ufs_hba *, + enum ufs_notify_change_status); + int (*link_startup_notify)(struct ufs_hba *, + enum ufs_notify_change_status); + int (*pwr_change_notify)(struct ufs_hba *, + enum ufs_notify_change_status status, + struct ufs_pa_layer_attr *, + struct ufs_pa_layer_attr *); + void (*setup_xfer_req)(struct ufs_hba *hba, int tag, + bool is_scsi_cmd); + void (*setup_task_mgmt)(struct ufs_hba *, int, u8); + void (*hibern8_notify)(struct ufs_hba *, enum uic_cmd_dme, + enum ufs_notify_change_status); + int (*apply_dev_quirks)(struct ufs_hba *hba); + void (*fixup_dev_quirks)(struct ufs_hba *hba); + int (*suspend)(struct ufs_hba *, enum ufs_pm_op, + enum ufs_notify_change_status); + int (*resume)(struct ufs_hba *, enum ufs_pm_op); + void (*dbg_register_dump)(struct ufs_hba *hba); + int (*phy_initialization)(struct ufs_hba *); + int (*device_reset)(struct ufs_hba *hba); + void (*config_scaling_param)(struct ufs_hba *hba, + struct devfreq_dev_profile *profile, + struct devfreq_simple_ondemand_data *data); + int (*program_key)(struct ufs_hba *hba, + const union ufs_crypto_cfg_entry *cfg, int slot); + void (*event_notify)(struct ufs_hba *hba, + enum ufs_event_type evt, void *data); +}; + +/* clock gating state */ +enum clk_gating_state { + CLKS_OFF, + CLKS_ON, + REQ_CLKS_OFF, + REQ_CLKS_ON, +}; + +/** + * struct ufs_clk_gating - UFS clock gating related info + * @gate_work: worker to turn off clocks after some delay as specified in + * delay_ms + * @ungate_work: worker to turn on clocks that will be used in case of + * interrupt context + * @state: the current clocks state + * @delay_ms: gating delay in ms + * @is_suspended: clk gating is suspended when set to 1 which can be used + * during suspend/resume + * @delay_attr: sysfs attribute to control delay_attr + * @enable_attr: sysfs attribute to enable/disable clock gating + * @is_enabled: Indicates the current status of clock gating + * @is_initialized: Indicates whether clock gating is initialized or not + * @active_reqs: number of requests that are pending and should be waited for + * completion before gating clocks. + * @clk_gating_workq: workqueue for clock gating work. + */ +struct ufs_clk_gating { + struct delayed_work gate_work; + struct work_struct ungate_work; + enum clk_gating_state state; + unsigned long delay_ms; + bool is_suspended; + struct device_attribute delay_attr; + struct device_attribute enable_attr; + bool is_enabled; + bool is_initialized; + int active_reqs; + struct workqueue_struct *clk_gating_workq; +}; + +struct ufs_saved_pwr_info { + struct ufs_pa_layer_attr info; + bool is_valid; +}; + +/** + * struct ufs_clk_scaling - UFS clock scaling related data + * @active_reqs: number of requests that are pending. If this is zero when + * devfreq ->target() function is called then schedule "suspend_work" to + * suspend devfreq. + * @tot_busy_t: Total busy time in current polling window + * @window_start_t: Start time (in jiffies) of the current polling window + * @busy_start_t: Start time of current busy period + * @enable_attr: sysfs attribute to enable/disable clock scaling + * @saved_pwr_info: UFS power mode may also be changed during scaling and this + * one keeps track of previous power mode. + * @workq: workqueue to schedule devfreq suspend/resume work + * @suspend_work: worker to suspend devfreq + * @resume_work: worker to resume devfreq + * @min_gear: lowest HS gear to scale down to + * @is_enabled: tracks if scaling is currently enabled or not, controlled by + * clkscale_enable sysfs node + * @is_allowed: tracks if scaling is currently allowed or not, used to block + * clock scaling which is not invoked from devfreq governor + * @is_initialized: Indicates whether clock scaling is initialized or not + * @is_busy_started: tracks if busy period has started or not + * @is_suspended: tracks if devfreq is suspended or not + */ +struct ufs_clk_scaling { + int active_reqs; + unsigned long tot_busy_t; + ktime_t window_start_t; + ktime_t busy_start_t; + struct device_attribute enable_attr; + struct ufs_saved_pwr_info saved_pwr_info; + struct workqueue_struct *workq; + struct work_struct suspend_work; + struct work_struct resume_work; + u32 min_gear; + bool is_enabled; + bool is_allowed; + bool is_initialized; + bool is_busy_started; + bool is_suspended; +}; + +#define UFS_EVENT_HIST_LENGTH 8 +/** + * struct ufs_event_hist - keeps history of errors + * @pos: index to indicate cyclic buffer position + * @val: cyclic buffer for registers value + * @tstamp: cyclic buffer for time stamp + * @cnt: error counter + */ +struct ufs_event_hist { + int pos; + u32 val[UFS_EVENT_HIST_LENGTH]; + ktime_t tstamp[UFS_EVENT_HIST_LENGTH]; + unsigned long long cnt; +}; + +/** + * struct ufs_stats - keeps usage/err statistics + * @last_intr_status: record the last interrupt status. + * @last_intr_ts: record the last interrupt timestamp. + * @hibern8_exit_cnt: Counter to keep track of number of exits, + * reset this after link-startup. + * @last_hibern8_exit_tstamp: Set time after the hibern8 exit. + * Clear after the first successful command completion. + * @event: array with event history. + */ +struct ufs_stats { + u32 last_intr_status; + ktime_t last_intr_ts; + + u32 hibern8_exit_cnt; + ktime_t last_hibern8_exit_tstamp; + struct ufs_event_hist event[UFS_EVT_CNT]; +}; + +/** + * enum ufshcd_state - UFS host controller state + * @UFSHCD_STATE_RESET: Link is not operational. Postpone SCSI command + * processing. + * @UFSHCD_STATE_OPERATIONAL: The host controller is operational and can process + * SCSI commands. + * @UFSHCD_STATE_EH_SCHEDULED_NON_FATAL: The error handler has been scheduled. + * SCSI commands may be submitted to the controller. + * @UFSHCD_STATE_EH_SCHEDULED_FATAL: The error handler has been scheduled. Fail + * newly submitted SCSI commands with error code DID_BAD_TARGET. + * @UFSHCD_STATE_ERROR: An unrecoverable error occurred, e.g. link recovery + * failed. Fail all SCSI commands with error code DID_ERROR. + */ +enum ufshcd_state { + UFSHCD_STATE_RESET, + UFSHCD_STATE_OPERATIONAL, + UFSHCD_STATE_EH_SCHEDULED_NON_FATAL, + UFSHCD_STATE_EH_SCHEDULED_FATAL, + UFSHCD_STATE_ERROR, +}; + +enum ufshcd_quirks { + /* Interrupt aggregation support is broken */ + UFSHCD_QUIRK_BROKEN_INTR_AGGR = 1 << 0, + + /* + * delay before each dme command is required as the unipro + * layer has shown instabilities + */ + UFSHCD_QUIRK_DELAY_BEFORE_DME_CMDS = 1 << 1, + + /* + * If UFS host controller is having issue in processing LCC (Line + * Control Command) coming from device then enable this quirk. + * When this quirk is enabled, host controller driver should disable + * the LCC transmission on UFS device (by clearing TX_LCC_ENABLE + * attribute of device to 0). + */ + UFSHCD_QUIRK_BROKEN_LCC = 1 << 2, + + /* + * The attribute PA_RXHSUNTERMCAP specifies whether or not the + * inbound Link supports unterminated line in HS mode. Setting this + * attribute to 1 fixes moving to HS gear. + */ + UFSHCD_QUIRK_BROKEN_PA_RXHSUNTERMCAP = 1 << 3, + + /* + * This quirk needs to be enabled if the host controller only allows + * accessing the peer dme attributes in AUTO mode (FAST AUTO or + * SLOW AUTO). + */ + UFSHCD_QUIRK_DME_PEER_ACCESS_AUTO_MODE = 1 << 4, + + /* + * This quirk needs to be enabled if the host controller doesn't + * advertise the correct version in UFS_VER register. If this quirk + * is enabled, standard UFS host driver will call the vendor specific + * ops (get_ufs_hci_version) to get the correct version. + */ + UFSHCD_QUIRK_BROKEN_UFS_HCI_VERSION = 1 << 5, + + /* + * Clear handling for transfer/task request list is just opposite. + */ + UFSHCI_QUIRK_BROKEN_REQ_LIST_CLR = 1 << 6, + + /* + * This quirk needs to be enabled if host controller doesn't allow + * that the interrupt aggregation timer and counter are reset by s/w. + */ + UFSHCI_QUIRK_SKIP_RESET_INTR_AGGR = 1 << 7, + + /* + * This quirks needs to be enabled if host controller cannot be + * enabled via HCE register. + */ + UFSHCI_QUIRK_BROKEN_HCE = 1 << 8, + + /* + * This quirk needs to be enabled if the host controller regards + * resolution of the values of PRDTO and PRDTL in UTRD as byte. + */ + UFSHCD_QUIRK_PRDT_BYTE_GRAN = 1 << 9, + + /* + * This quirk needs to be enabled if the host controller reports + * OCS FATAL ERROR with device error through sense data + */ + UFSHCD_QUIRK_BROKEN_OCS_FATAL_ERROR = 1 << 10, + + /* + * This quirk needs to be enabled if the host controller has + * auto-hibernate capability but it doesn't work. + */ + UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8 = 1 << 11, + + /* + * This quirk needs to disable manual flush for write booster + */ + UFSHCI_QUIRK_SKIP_MANUAL_WB_FLUSH_CTRL = 1 << 12, + + /* + * This quirk needs to disable unipro timeout values + * before power mode change + */ + UFSHCD_QUIRK_SKIP_DEF_UNIPRO_TIMEOUT_SETTING = 1 << 13, + + /* + * This quirk allows only sg entries aligned with page size. + */ + UFSHCD_QUIRK_ALIGN_SG_WITH_PAGE_SIZE = 1 << 14, + + /* + * This quirk needs to be enabled if the host controller does not + * support UIC command + */ + UFSHCD_QUIRK_BROKEN_UIC_CMD = 1 << 15, + + /* + * This quirk needs to be enabled if the host controller cannot + * support physical host configuration. + */ + UFSHCD_QUIRK_SKIP_PH_CONFIGURATION = 1 << 16, +}; + +enum ufshcd_caps { + /* Allow dynamic clk gating */ + UFSHCD_CAP_CLK_GATING = 1 << 0, + + /* Allow hiberb8 with clk gating */ + UFSHCD_CAP_HIBERN8_WITH_CLK_GATING = 1 << 1, + + /* Allow dynamic clk scaling */ + UFSHCD_CAP_CLK_SCALING = 1 << 2, + + /* Allow auto bkops to enabled during runtime suspend */ + UFSHCD_CAP_AUTO_BKOPS_SUSPEND = 1 << 3, + + /* + * This capability allows host controller driver to use the UFS HCI's + * interrupt aggregation capability. + * CAUTION: Enabling this might reduce overall UFS throughput. + */ + UFSHCD_CAP_INTR_AGGR = 1 << 4, + + /* + * This capability allows the device auto-bkops to be always enabled + * except during suspend (both runtime and suspend). + * Enabling this capability means that device will always be allowed + * to do background operation when it's active but it might degrade + * the performance of ongoing read/write operations. + */ + UFSHCD_CAP_KEEP_AUTO_BKOPS_ENABLED_EXCEPT_SUSPEND = 1 << 5, + + /* + * This capability allows host controller driver to automatically + * enable runtime power management by itself instead of waiting + * for userspace to control the power management. + */ + UFSHCD_CAP_RPM_AUTOSUSPEND = 1 << 6, + + /* + * This capability allows the host controller driver to turn-on + * WriteBooster, if the underlying device supports it and is + * provisioned to be used. This would increase the write performance. + */ + UFSHCD_CAP_WB_EN = 1 << 7, + + /* + * This capability allows the host controller driver to use the + * inline crypto engine, if it is present + */ + UFSHCD_CAP_CRYPTO = 1 << 8, + + /* + * This capability allows the controller regulators to be put into + * lpm mode aggressively during clock gating. + * This would increase power savings. + */ + UFSHCD_CAP_AGGR_POWER_COLLAPSE = 1 << 9, + + /* + * This capability allows the host controller driver to use DeepSleep, + * if it is supported by the UFS device. The host controller driver must + * support device hardware reset via the hba->device_reset() callback, + * in order to exit DeepSleep state. + */ + UFSHCD_CAP_DEEPSLEEP = 1 << 10, + + /* + * This capability allows the host controller driver to use temperature + * notification if it is supported by the UFS device. + */ + UFSHCD_CAP_TEMP_NOTIF = 1 << 11, +}; + +struct ufs_hba_variant_params { + struct devfreq_dev_profile devfreq_profile; + struct devfreq_simple_ondemand_data ondemand_data; + u16 hba_enable_delay_us; + u32 wb_flush_threshold; +}; + +#ifdef CONFIG_SCSI_UFS_HPB +/** + * struct ufshpb_dev_info - UFSHPB device related info + * @num_lu: the number of user logical unit to check whether all lu finished + * initialization + * @rgn_size: device reported HPB region size + * @srgn_size: device reported HPB sub-region size + * @slave_conf_cnt: counter to check all lu finished initialization + * @hpb_disabled: flag to check if HPB is disabled + * @max_hpb_single_cmd: device reported bMAX_DATA_SIZE_FOR_SINGLE_CMD value + * @is_legacy: flag to check HPB 1.0 + * @control_mode: either host or device + */ +struct ufshpb_dev_info { + int num_lu; + int rgn_size; + int srgn_size; + atomic_t slave_conf_cnt; + bool hpb_disabled; + u8 max_hpb_single_cmd; + bool is_legacy; + u8 control_mode; +}; +#endif + +struct ufs_hba_monitor { + unsigned long chunk_size; + + unsigned long nr_sec_rw[2]; + ktime_t total_busy[2]; + + unsigned long nr_req[2]; + /* latencies*/ + ktime_t lat_sum[2]; + ktime_t lat_max[2]; + ktime_t lat_min[2]; + + u32 nr_queued[2]; + ktime_t busy_start_ts[2]; + + ktime_t enabled_ts; + bool enabled; +}; + +/** + * struct ufs_hba - per adapter private structure + * @mmio_base: UFSHCI base register address + * @ucdl_base_addr: UFS Command Descriptor base address + * @utrdl_base_addr: UTP Transfer Request Descriptor base address + * @utmrdl_base_addr: UTP Task Management Descriptor base address + * @ucdl_dma_addr: UFS Command Descriptor DMA address + * @utrdl_dma_addr: UTRDL DMA address + * @utmrdl_dma_addr: UTMRDL DMA address + * @host: Scsi_Host instance of the driver + * @dev: device handle + * @ufs_device_wlun: WLUN that controls the entire UFS device. + * @hwmon_device: device instance registered with the hwmon core. + * @curr_dev_pwr_mode: active UFS device power mode. + * @uic_link_state: active state of the link to the UFS device. + * @rpm_lvl: desired UFS power management level during runtime PM. + * @spm_lvl: desired UFS power management level during system PM. + * @pm_op_in_progress: whether or not a PM operation is in progress. + * @ahit: value of Auto-Hibernate Idle Timer register. + * @lrb: local reference block + * @outstanding_tasks: Bits representing outstanding task requests + * @outstanding_lock: Protects @outstanding_reqs. + * @outstanding_reqs: Bits representing outstanding transfer requests + * @capabilities: UFS Controller Capabilities + * @nutrs: Transfer Request Queue depth supported by controller + * @nutmrs: Task Management Queue depth supported by controller + * @reserved_slot: Used to submit device commands. Protected by @dev_cmd.lock. + * @ufs_version: UFS Version to which controller complies + * @vops: pointer to variant specific operations + * @vps: pointer to variant specific parameters + * @priv: pointer to variant specific private data + * @irq: Irq number of the controller + * @is_irq_enabled: whether or not the UFS controller interrupt is enabled. + * @dev_ref_clk_freq: reference clock frequency + * @quirks: bitmask with information about deviations from the UFSHCI standard. + * @dev_quirks: bitmask with information about deviations from the UFS standard. + * @tmf_tag_set: TMF tag set. + * @tmf_queue: Used to allocate TMF tags. + * @tmf_rqs: array with pointers to TMF requests while these are in progress. + * @active_uic_cmd: handle of active UIC command + * @uic_cmd_mutex: mutex for UIC command + * @uic_async_done: completion used during UIC processing + * @ufshcd_state: UFSHCD state + * @eh_flags: Error handling flags + * @intr_mask: Interrupt Mask Bits + * @ee_ctrl_mask: Exception event control mask + * @ee_drv_mask: Exception event mask for driver + * @ee_usr_mask: Exception event mask for user (set via debugfs) + * @ee_ctrl_mutex: Used to serialize exception event information. + * @is_powered: flag to check if HBA is powered + * @shutting_down: flag to check if shutdown has been invoked + * @host_sem: semaphore used to serialize concurrent contexts + * @eh_wq: Workqueue that eh_work works on + * @eh_work: Worker to handle UFS errors that require s/w attention + * @eeh_work: Worker to handle exception events + * @errors: HBA errors + * @uic_error: UFS interconnect layer error status + * @saved_err: sticky error mask + * @saved_uic_err: sticky UIC error mask + * @ufs_stats: various error counters + * @force_reset: flag to force eh_work perform a full reset + * @force_pmc: flag to force a power mode change + * @silence_err_logs: flag to silence error logs + * @dev_cmd: ufs device management command information + * @last_dme_cmd_tstamp: time stamp of the last completed DME command + * @nop_out_timeout: NOP OUT timeout value + * @dev_info: information about the UFS device + * @auto_bkops_enabled: to track whether bkops is enabled in device + * @vreg_info: UFS device voltage regulator information + * @clk_list_head: UFS host controller clocks list node head + * @req_abort_count: number of times ufshcd_abort() has been called + * @lanes_per_direction: number of lanes per data direction between the UFS + * controller and the UFS device. + * @pwr_info: holds current power mode + * @max_pwr_info: keeps the device max valid pwm + * @clk_gating: information related to clock gating + * @caps: bitmask with information about UFS controller capabilities + * @devfreq: frequency scaling information owned by the devfreq core + * @clk_scaling: frequency scaling information owned by the UFS driver + * @is_sys_suspended: whether or not the entire system has been suspended + * @urgent_bkops_lvl: keeps track of urgent bkops level for device + * @is_urgent_bkops_lvl_checked: keeps track if the urgent bkops level for + * device is known or not. + * @clk_scaling_lock: used to serialize device commands and clock scaling + * @desc_size: descriptor sizes reported by device + * @scsi_block_reqs_cnt: reference counting for scsi block requests + * @bsg_dev: struct device associated with the BSG queue + * @bsg_queue: BSG queue associated with the UFS controller + * @rpm_dev_flush_recheck_work: used to suspend from RPM (runtime power + * management) after the UFS device has finished a WriteBooster buffer + * flush or auto BKOP. + * @ufshpb_dev: information related to HPB (Host Performance Booster). + * @monitor: statistics about UFS commands + * @crypto_capabilities: Content of crypto capabilities register (0x100) + * @crypto_cap_array: Array of crypto capabilities + * @crypto_cfg_register: Start of the crypto cfg array + * @crypto_profile: the crypto profile of this hba (if applicable) + * @debugfs_root: UFS controller debugfs root directory + * @debugfs_ee_work: used to restore ee_ctrl_mask after a delay + * @debugfs_ee_rate_limit_ms: user configurable delay after which to restore + * ee_ctrl_mask + * @luns_avail: number of regular and well known LUNs supported by the UFS + * device + * @complete_put: whether or not to call ufshcd_rpm_put() from inside + * ufshcd_resume_complete() + */ +struct ufs_hba { + void __iomem *mmio_base; + + /* Virtual memory reference */ + struct utp_transfer_cmd_desc *ucdl_base_addr; + struct utp_transfer_req_desc *utrdl_base_addr; + struct utp_task_req_desc *utmrdl_base_addr; + + /* DMA memory reference */ + dma_addr_t ucdl_dma_addr; + dma_addr_t utrdl_dma_addr; + dma_addr_t utmrdl_dma_addr; + + struct Scsi_Host *host; + struct device *dev; + struct scsi_device *ufs_device_wlun; + +#ifdef CONFIG_SCSI_UFS_HWMON + struct device *hwmon_device; +#endif + + enum ufs_dev_pwr_mode curr_dev_pwr_mode; + enum uic_link_state uic_link_state; + /* Desired UFS power management level during runtime PM */ + enum ufs_pm_level rpm_lvl; + /* Desired UFS power management level during system PM */ + enum ufs_pm_level spm_lvl; + int pm_op_in_progress; + + /* Auto-Hibernate Idle Timer register value */ + u32 ahit; + + struct ufshcd_lrb *lrb; + + unsigned long outstanding_tasks; + spinlock_t outstanding_lock; + unsigned long outstanding_reqs; + + u32 capabilities; + int nutrs; + int nutmrs; + u32 reserved_slot; + u32 ufs_version; + const struct ufs_hba_variant_ops *vops; + struct ufs_hba_variant_params *vps; + void *priv; + unsigned int irq; + bool is_irq_enabled; + enum ufs_ref_clk_freq dev_ref_clk_freq; + + unsigned int quirks; /* Deviations from standard UFSHCI spec. */ + + /* Device deviations from standard UFS device spec. */ + unsigned int dev_quirks; + + struct blk_mq_tag_set tmf_tag_set; + struct request_queue *tmf_queue; + struct request **tmf_rqs; + + struct uic_command *active_uic_cmd; + struct mutex uic_cmd_mutex; + struct completion *uic_async_done; + + enum ufshcd_state ufshcd_state; + u32 eh_flags; + u32 intr_mask; + u16 ee_ctrl_mask; + u16 ee_drv_mask; + u16 ee_usr_mask; + struct mutex ee_ctrl_mutex; + bool is_powered; + bool shutting_down; + struct semaphore host_sem; + + /* Work Queues */ + struct workqueue_struct *eh_wq; + struct work_struct eh_work; + struct work_struct eeh_work; + + /* HBA Errors */ + u32 errors; + u32 uic_error; + u32 saved_err; + u32 saved_uic_err; + struct ufs_stats ufs_stats; + bool force_reset; + bool force_pmc; + bool silence_err_logs; + + /* Device management request data */ + struct ufs_dev_cmd dev_cmd; + ktime_t last_dme_cmd_tstamp; + int nop_out_timeout; + + /* Keeps information of the UFS device connected to this host */ + struct ufs_dev_info dev_info; + bool auto_bkops_enabled; + struct ufs_vreg_info vreg_info; + struct list_head clk_list_head; + + /* Number of requests aborts */ + int req_abort_count; + + /* Number of lanes available (1 or 2) for Rx/Tx */ + u32 lanes_per_direction; + struct ufs_pa_layer_attr pwr_info; + struct ufs_pwr_mode_info max_pwr_info; + + struct ufs_clk_gating clk_gating; + /* Control to enable/disable host capabilities */ + u32 caps; + + struct devfreq *devfreq; + struct ufs_clk_scaling clk_scaling; + bool is_sys_suspended; + + enum bkops_status urgent_bkops_lvl; + bool is_urgent_bkops_lvl_checked; + + struct rw_semaphore clk_scaling_lock; + unsigned char desc_size[QUERY_DESC_IDN_MAX]; + atomic_t scsi_block_reqs_cnt; + + struct device bsg_dev; + struct request_queue *bsg_queue; + struct delayed_work rpm_dev_flush_recheck_work; + +#ifdef CONFIG_SCSI_UFS_HPB + struct ufshpb_dev_info ufshpb_dev; +#endif + + struct ufs_hba_monitor monitor; + +#ifdef CONFIG_SCSI_UFS_CRYPTO + union ufs_crypto_capabilities crypto_capabilities; + union ufs_crypto_cap_entry *crypto_cap_array; + u32 crypto_cfg_register; + struct blk_crypto_profile crypto_profile; +#endif +#ifdef CONFIG_DEBUG_FS + struct dentry *debugfs_root; + struct delayed_work debugfs_ee_work; + u32 debugfs_ee_rate_limit_ms; +#endif + u32 luns_avail; + bool complete_put; +}; + +/* Returns true if clocks can be gated. Otherwise false */ +static inline bool ufshcd_is_clkgating_allowed(struct ufs_hba *hba) +{ + return hba->caps & UFSHCD_CAP_CLK_GATING; +} +static inline bool ufshcd_can_hibern8_during_gating(struct ufs_hba *hba) +{ + return hba->caps & UFSHCD_CAP_HIBERN8_WITH_CLK_GATING; +} +static inline int ufshcd_is_clkscaling_supported(struct ufs_hba *hba) +{ + return hba->caps & UFSHCD_CAP_CLK_SCALING; +} +static inline bool ufshcd_can_autobkops_during_suspend(struct ufs_hba *hba) +{ + return hba->caps & UFSHCD_CAP_AUTO_BKOPS_SUSPEND; +} +static inline bool ufshcd_is_rpm_autosuspend_allowed(struct ufs_hba *hba) +{ + return hba->caps & UFSHCD_CAP_RPM_AUTOSUSPEND; +} + +static inline bool ufshcd_is_intr_aggr_allowed(struct ufs_hba *hba) +{ + return (hba->caps & UFSHCD_CAP_INTR_AGGR) && + !(hba->quirks & UFSHCD_QUIRK_BROKEN_INTR_AGGR); +} + +static inline bool ufshcd_can_aggressive_pc(struct ufs_hba *hba) +{ + return !!(ufshcd_is_link_hibern8(hba) && + (hba->caps & UFSHCD_CAP_AGGR_POWER_COLLAPSE)); +} + +static inline bool ufshcd_is_auto_hibern8_supported(struct ufs_hba *hba) +{ + return (hba->capabilities & MASK_AUTO_HIBERN8_SUPPORT) && + !(hba->quirks & UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8); +} + +static inline bool ufshcd_is_auto_hibern8_enabled(struct ufs_hba *hba) +{ + return FIELD_GET(UFSHCI_AHIBERN8_TIMER_MASK, hba->ahit); +} + +static inline bool ufshcd_is_wb_allowed(struct ufs_hba *hba) +{ + return hba->caps & UFSHCD_CAP_WB_EN; +} + +#define ufshcd_writel(hba, val, reg) \ + writel((val), (hba)->mmio_base + (reg)) +#define ufshcd_readl(hba, reg) \ + readl((hba)->mmio_base + (reg)) + +/** + * ufshcd_rmwl - perform read/modify/write for a controller register + * @hba: per adapter instance + * @mask: mask to apply on read value + * @val: actual value to write + * @reg: register address + */ +static inline void ufshcd_rmwl(struct ufs_hba *hba, u32 mask, u32 val, u32 reg) +{ + u32 tmp; + + tmp = ufshcd_readl(hba, reg); + tmp &= ~mask; + tmp |= (val & mask); + ufshcd_writel(hba, tmp, reg); +} + +int ufshcd_alloc_host(struct device *, struct ufs_hba **); +void ufshcd_dealloc_host(struct ufs_hba *); +int ufshcd_hba_enable(struct ufs_hba *hba); +int ufshcd_init(struct ufs_hba *, void __iomem *, unsigned int); +int ufshcd_link_recovery(struct ufs_hba *hba); +int ufshcd_make_hba_operational(struct ufs_hba *hba); +void ufshcd_remove(struct ufs_hba *); +int ufshcd_uic_hibern8_enter(struct ufs_hba *hba); +int ufshcd_uic_hibern8_exit(struct ufs_hba *hba); +void ufshcd_delay_us(unsigned long us, unsigned long tolerance); +void ufshcd_parse_dev_ref_clk_freq(struct ufs_hba *hba, struct clk *refclk); +void ufshcd_update_evt_hist(struct ufs_hba *hba, u32 id, u32 val); +void ufshcd_hba_stop(struct ufs_hba *hba); +void ufshcd_schedule_eh_work(struct ufs_hba *hba); + +static inline void check_upiu_size(void) +{ + BUILD_BUG_ON(ALIGNED_UPIU_SIZE < + GENERAL_UPIU_REQUEST_SIZE + QUERY_DESC_MAX_SIZE); +} + +/** + * ufshcd_set_variant - set variant specific data to the hba + * @hba: per adapter instance + * @variant: pointer to variant specific data + */ +static inline void ufshcd_set_variant(struct ufs_hba *hba, void *variant) +{ + BUG_ON(!hba); + hba->priv = variant; +} + +/** + * ufshcd_get_variant - get variant specific data from the hba + * @hba: per adapter instance + */ +static inline void *ufshcd_get_variant(struct ufs_hba *hba) +{ + BUG_ON(!hba); + return hba->priv; +} + +#ifdef CONFIG_PM +extern int ufshcd_runtime_suspend(struct device *dev); +extern int ufshcd_runtime_resume(struct device *dev); +#endif +#ifdef CONFIG_PM_SLEEP +extern int ufshcd_system_suspend(struct device *dev); +extern int ufshcd_system_resume(struct device *dev); +#endif +extern int ufshcd_shutdown(struct ufs_hba *hba); +extern int ufshcd_dme_configure_adapt(struct ufs_hba *hba, + int agreed_gear, + int adapt_val); +extern int ufshcd_dme_set_attr(struct ufs_hba *hba, u32 attr_sel, + u8 attr_set, u32 mib_val, u8 peer); +extern int ufshcd_dme_get_attr(struct ufs_hba *hba, u32 attr_sel, + u32 *mib_val, u8 peer); +extern int ufshcd_config_pwr_mode(struct ufs_hba *hba, + struct ufs_pa_layer_attr *desired_pwr_mode); + +/* UIC command interfaces for DME primitives */ +#define DME_LOCAL 0 +#define DME_PEER 1 +#define ATTR_SET_NOR 0 /* NORMAL */ +#define ATTR_SET_ST 1 /* STATIC */ + +static inline int ufshcd_dme_set(struct ufs_hba *hba, u32 attr_sel, + u32 mib_val) +{ + return ufshcd_dme_set_attr(hba, attr_sel, ATTR_SET_NOR, + mib_val, DME_LOCAL); +} + +static inline int ufshcd_dme_st_set(struct ufs_hba *hba, u32 attr_sel, + u32 mib_val) +{ + return ufshcd_dme_set_attr(hba, attr_sel, ATTR_SET_ST, + mib_val, DME_LOCAL); +} + +static inline int ufshcd_dme_peer_set(struct ufs_hba *hba, u32 attr_sel, + u32 mib_val) +{ + return ufshcd_dme_set_attr(hba, attr_sel, ATTR_SET_NOR, + mib_val, DME_PEER); +} + +static inline int ufshcd_dme_peer_st_set(struct ufs_hba *hba, u32 attr_sel, + u32 mib_val) +{ + return ufshcd_dme_set_attr(hba, attr_sel, ATTR_SET_ST, + mib_val, DME_PEER); +} + +static inline int ufshcd_dme_get(struct ufs_hba *hba, + u32 attr_sel, u32 *mib_val) +{ + return ufshcd_dme_get_attr(hba, attr_sel, mib_val, DME_LOCAL); +} + +static inline int ufshcd_dme_peer_get(struct ufs_hba *hba, + u32 attr_sel, u32 *mib_val) +{ + return ufshcd_dme_get_attr(hba, attr_sel, mib_val, DME_PEER); +} + +static inline bool ufshcd_is_hs_mode(struct ufs_pa_layer_attr *pwr_info) +{ + return (pwr_info->pwr_rx == FAST_MODE || + pwr_info->pwr_rx == FASTAUTO_MODE) && + (pwr_info->pwr_tx == FAST_MODE || + pwr_info->pwr_tx == FASTAUTO_MODE); +} + +static inline int ufshcd_disable_host_tx_lcc(struct ufs_hba *hba) +{ + return ufshcd_dme_set(hba, UIC_ARG_MIB(PA_LOCAL_TX_LCC_ENABLE), 0); +} + +/* Expose Query-Request API */ +int ufshcd_query_descriptor_retry(struct ufs_hba *hba, + enum query_opcode opcode, + enum desc_idn idn, u8 index, + u8 selector, + u8 *desc_buf, int *buf_len); +int ufshcd_read_desc_param(struct ufs_hba *hba, + enum desc_idn desc_id, + int desc_index, + u8 param_offset, + u8 *param_read_buf, + u8 param_size); +int ufshcd_query_attr_retry(struct ufs_hba *hba, enum query_opcode opcode, + enum attr_idn idn, u8 index, u8 selector, + u32 *attr_val); +int ufshcd_query_attr(struct ufs_hba *hba, enum query_opcode opcode, + enum attr_idn idn, u8 index, u8 selector, u32 *attr_val); +int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode, + enum flag_idn idn, u8 index, bool *flag_res); + +void ufshcd_auto_hibern8_enable(struct ufs_hba *hba); +void ufshcd_auto_hibern8_update(struct ufs_hba *hba, u32 ahit); +void ufshcd_fixup_dev_quirks(struct ufs_hba *hba, + const struct ufs_dev_quirk *fixups); +#define SD_ASCII_STD true +#define SD_RAW false +int ufshcd_read_string_desc(struct ufs_hba *hba, u8 desc_index, + u8 **buf, bool ascii); + +int ufshcd_hold(struct ufs_hba *hba, bool async); +void ufshcd_release(struct ufs_hba *hba); + +void ufshcd_clkgate_delay_set(struct device *dev, unsigned long value); + +void ufshcd_map_desc_id_to_length(struct ufs_hba *hba, enum desc_idn desc_id, + int *desc_length); + +u32 ufshcd_get_local_unipro_ver(struct ufs_hba *hba); + +int ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd); + +int ufshcd_exec_raw_upiu_cmd(struct ufs_hba *hba, + struct utp_upiu_req *req_upiu, + struct utp_upiu_req *rsp_upiu, + int msgcode, + u8 *desc_buff, int *buff_len, + enum query_opcode desc_op); + +int ufshcd_wb_toggle(struct ufs_hba *hba, bool enable); +int ufshcd_suspend_prepare(struct device *dev); +int __ufshcd_suspend_prepare(struct device *dev, bool rpm_ok_for_spm); +void ufshcd_resume_complete(struct device *dev); + +/* Wrapper functions for safely calling variant operations */ +static inline int ufshcd_vops_init(struct ufs_hba *hba) +{ + if (hba->vops && hba->vops->init) + return hba->vops->init(hba); + + return 0; +} + +static inline int ufshcd_vops_phy_initialization(struct ufs_hba *hba) +{ + if (hba->vops && hba->vops->phy_initialization) + return hba->vops->phy_initialization(hba); + + return 0; +} + +extern struct ufs_pm_lvl_states ufs_pm_lvl_states[]; + +int ufshcd_dump_regs(struct ufs_hba *hba, size_t offset, size_t len, + const char *prefix); + +int __ufshcd_write_ee_control(struct ufs_hba *hba, u32 ee_ctrl_mask); +int ufshcd_write_ee_control(struct ufs_hba *hba); +int ufshcd_update_ee_control(struct ufs_hba *hba, u16 *mask, u16 *other_mask, + u16 set, u16 clr); + +#endif /* End of Header */ diff --git a/include/ufs/ufshci.h b/include/ufs/ufshci.h new file mode 100644 index 000000000000..f81aa95ffbc4 --- /dev/null +++ b/include/ufs/ufshci.h @@ -0,0 +1,510 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Universal Flash Storage Host controller driver + * Copyright (C) 2011-2013 Samsung India Software Operations + * + * Authors: + * Santosh Yaraganavi + * Vinayak Holikatti + */ + +#ifndef _UFSHCI_H +#define _UFSHCI_H + +#include + +enum { + TASK_REQ_UPIU_SIZE_DWORDS = 8, + TASK_RSP_UPIU_SIZE_DWORDS = 8, + ALIGNED_UPIU_SIZE = 512, +}; + +/* UFSHCI Registers */ +enum { + REG_CONTROLLER_CAPABILITIES = 0x00, + REG_UFS_VERSION = 0x08, + REG_CONTROLLER_DEV_ID = 0x10, + REG_CONTROLLER_PROD_ID = 0x14, + REG_AUTO_HIBERNATE_IDLE_TIMER = 0x18, + REG_INTERRUPT_STATUS = 0x20, + REG_INTERRUPT_ENABLE = 0x24, + REG_CONTROLLER_STATUS = 0x30, + REG_CONTROLLER_ENABLE = 0x34, + REG_UIC_ERROR_CODE_PHY_ADAPTER_LAYER = 0x38, + REG_UIC_ERROR_CODE_DATA_LINK_LAYER = 0x3C, + REG_UIC_ERROR_CODE_NETWORK_LAYER = 0x40, + REG_UIC_ERROR_CODE_TRANSPORT_LAYER = 0x44, + REG_UIC_ERROR_CODE_DME = 0x48, + REG_UTP_TRANSFER_REQ_INT_AGG_CONTROL = 0x4C, + REG_UTP_TRANSFER_REQ_LIST_BASE_L = 0x50, + REG_UTP_TRANSFER_REQ_LIST_BASE_H = 0x54, + REG_UTP_TRANSFER_REQ_DOOR_BELL = 0x58, + REG_UTP_TRANSFER_REQ_LIST_CLEAR = 0x5C, + REG_UTP_TRANSFER_REQ_LIST_RUN_STOP = 0x60, + REG_UTP_TASK_REQ_LIST_BASE_L = 0x70, + REG_UTP_TASK_REQ_LIST_BASE_H = 0x74, + REG_UTP_TASK_REQ_DOOR_BELL = 0x78, + REG_UTP_TASK_REQ_LIST_CLEAR = 0x7C, + REG_UTP_TASK_REQ_LIST_RUN_STOP = 0x80, + REG_UIC_COMMAND = 0x90, + REG_UIC_COMMAND_ARG_1 = 0x94, + REG_UIC_COMMAND_ARG_2 = 0x98, + REG_UIC_COMMAND_ARG_3 = 0x9C, + + UFSHCI_REG_SPACE_SIZE = 0xA0, + + REG_UFS_CCAP = 0x100, + REG_UFS_CRYPTOCAP = 0x104, + + UFSHCI_CRYPTO_REG_SPACE_SIZE = 0x400, +}; + +/* Controller capability masks */ +enum { + MASK_TRANSFER_REQUESTS_SLOTS = 0x0000001F, + MASK_TASK_MANAGEMENT_REQUEST_SLOTS = 0x00070000, + MASK_AUTO_HIBERN8_SUPPORT = 0x00800000, + MASK_64_ADDRESSING_SUPPORT = 0x01000000, + MASK_OUT_OF_ORDER_DATA_DELIVERY_SUPPORT = 0x02000000, + MASK_UIC_DME_TEST_MODE_SUPPORT = 0x04000000, + MASK_CRYPTO_SUPPORT = 0x10000000, +}; + +#define UFS_MASK(mask, offset) ((mask) << (offset)) + +/* UFS Version 08h */ +#define MINOR_VERSION_NUM_MASK UFS_MASK(0xFFFF, 0) +#define MAJOR_VERSION_NUM_MASK UFS_MASK(0xFFFF, 16) + +/* + * Controller UFSHCI version + * - 2.x and newer use the following scheme: + * major << 8 + minor << 4 + * - 1.x has been converted to match this in + * ufshcd_get_ufs_version() + */ +static inline u32 ufshci_version(u32 major, u32 minor) +{ + return (major << 8) + (minor << 4); +} + +/* + * HCDDID - Host Controller Identification Descriptor + * - Device ID and Device Class 10h + */ +#define DEVICE_CLASS UFS_MASK(0xFFFF, 0) +#define DEVICE_ID UFS_MASK(0xFF, 24) + +/* + * HCPMID - Host Controller Identification Descriptor + * - Product/Manufacturer ID 14h + */ +#define MANUFACTURE_ID_MASK UFS_MASK(0xFFFF, 0) +#define PRODUCT_ID_MASK UFS_MASK(0xFFFF, 16) + +/* AHIT - Auto-Hibernate Idle Timer */ +#define UFSHCI_AHIBERN8_TIMER_MASK GENMASK(9, 0) +#define UFSHCI_AHIBERN8_SCALE_MASK GENMASK(12, 10) +#define UFSHCI_AHIBERN8_SCALE_FACTOR 10 +#define UFSHCI_AHIBERN8_MAX (1023 * 100000) + +/* + * IS - Interrupt Status - 20h + */ +#define UTP_TRANSFER_REQ_COMPL 0x1 +#define UIC_DME_END_PT_RESET 0x2 +#define UIC_ERROR 0x4 +#define UIC_TEST_MODE 0x8 +#define UIC_POWER_MODE 0x10 +#define UIC_HIBERNATE_EXIT 0x20 +#define UIC_HIBERNATE_ENTER 0x40 +#define UIC_LINK_LOST 0x80 +#define UIC_LINK_STARTUP 0x100 +#define UTP_TASK_REQ_COMPL 0x200 +#define UIC_COMMAND_COMPL 0x400 +#define DEVICE_FATAL_ERROR 0x800 +#define CONTROLLER_FATAL_ERROR 0x10000 +#define SYSTEM_BUS_FATAL_ERROR 0x20000 +#define CRYPTO_ENGINE_FATAL_ERROR 0x40000 + +#define UFSHCD_UIC_HIBERN8_MASK (UIC_HIBERNATE_ENTER |\ + UIC_HIBERNATE_EXIT) + +#define UFSHCD_UIC_PWR_MASK (UFSHCD_UIC_HIBERN8_MASK |\ + UIC_POWER_MODE) + +#define UFSHCD_UIC_MASK (UIC_COMMAND_COMPL | UFSHCD_UIC_PWR_MASK) + +#define UFSHCD_ERROR_MASK (UIC_ERROR |\ + DEVICE_FATAL_ERROR |\ + CONTROLLER_FATAL_ERROR |\ + SYSTEM_BUS_FATAL_ERROR |\ + CRYPTO_ENGINE_FATAL_ERROR) + +#define INT_FATAL_ERRORS (DEVICE_FATAL_ERROR |\ + CONTROLLER_FATAL_ERROR |\ + SYSTEM_BUS_FATAL_ERROR |\ + CRYPTO_ENGINE_FATAL_ERROR |\ + UIC_LINK_LOST) + +/* HCS - Host Controller Status 30h */ +#define DEVICE_PRESENT 0x1 +#define UTP_TRANSFER_REQ_LIST_READY 0x2 +#define UTP_TASK_REQ_LIST_READY 0x4 +#define UIC_COMMAND_READY 0x8 +#define HOST_ERROR_INDICATOR 0x10 +#define DEVICE_ERROR_INDICATOR 0x20 +#define UIC_POWER_MODE_CHANGE_REQ_STATUS_MASK UFS_MASK(0x7, 8) + +#define UFSHCD_STATUS_READY (UTP_TRANSFER_REQ_LIST_READY |\ + UTP_TASK_REQ_LIST_READY |\ + UIC_COMMAND_READY) + +enum { + PWR_OK = 0x0, + PWR_LOCAL = 0x01, + PWR_REMOTE = 0x02, + PWR_BUSY = 0x03, + PWR_ERROR_CAP = 0x04, + PWR_FATAL_ERROR = 0x05, +}; + +/* HCE - Host Controller Enable 34h */ +#define CONTROLLER_ENABLE 0x1 +#define CONTROLLER_DISABLE 0x0 +#define CRYPTO_GENERAL_ENABLE 0x2 + +/* UECPA - Host UIC Error Code PHY Adapter Layer 38h */ +#define UIC_PHY_ADAPTER_LAYER_ERROR 0x80000000 +#define UIC_PHY_ADAPTER_LAYER_ERROR_CODE_MASK 0x1F +#define UIC_PHY_ADAPTER_LAYER_LANE_ERR_MASK 0xF +#define UIC_PHY_ADAPTER_LAYER_GENERIC_ERROR 0x10 + +/* UECDL - Host UIC Error Code Data Link Layer 3Ch */ +#define UIC_DATA_LINK_LAYER_ERROR 0x80000000 +#define UIC_DATA_LINK_LAYER_ERROR_CODE_MASK 0xFFFF +#define UIC_DATA_LINK_LAYER_ERROR_TCX_REP_TIMER_EXP 0x2 +#define UIC_DATA_LINK_LAYER_ERROR_AFCX_REQ_TIMER_EXP 0x4 +#define UIC_DATA_LINK_LAYER_ERROR_FCX_PRO_TIMER_EXP 0x8 +#define UIC_DATA_LINK_LAYER_ERROR_RX_BUF_OF 0x20 +#define UIC_DATA_LINK_LAYER_ERROR_PA_INIT 0x2000 +#define UIC_DATA_LINK_LAYER_ERROR_NAC_RECEIVED 0x0001 +#define UIC_DATA_LINK_LAYER_ERROR_TCx_REPLAY_TIMEOUT 0x0002 + +/* UECN - Host UIC Error Code Network Layer 40h */ +#define UIC_NETWORK_LAYER_ERROR 0x80000000 +#define UIC_NETWORK_LAYER_ERROR_CODE_MASK 0x7 +#define UIC_NETWORK_UNSUPPORTED_HEADER_TYPE 0x1 +#define UIC_NETWORK_BAD_DEVICEID_ENC 0x2 +#define UIC_NETWORK_LHDR_TRAP_PACKET_DROPPING 0x4 + +/* UECT - Host UIC Error Code Transport Layer 44h */ +#define UIC_TRANSPORT_LAYER_ERROR 0x80000000 +#define UIC_TRANSPORT_LAYER_ERROR_CODE_MASK 0x7F +#define UIC_TRANSPORT_UNSUPPORTED_HEADER_TYPE 0x1 +#define UIC_TRANSPORT_UNKNOWN_CPORTID 0x2 +#define UIC_TRANSPORT_NO_CONNECTION_RX 0x4 +#define UIC_TRANSPORT_CONTROLLED_SEGMENT_DROPPING 0x8 +#define UIC_TRANSPORT_BAD_TC 0x10 +#define UIC_TRANSPORT_E2E_CREDIT_OVERFOW 0x20 +#define UIC_TRANSPORT_SAFETY_VALUE_DROPPING 0x40 + +/* UECDME - Host UIC Error Code DME 48h */ +#define UIC_DME_ERROR 0x80000000 +#define UIC_DME_ERROR_CODE_MASK 0x1 + +/* UTRIACR - Interrupt Aggregation control register - 0x4Ch */ +#define INT_AGGR_TIMEOUT_VAL_MASK 0xFF +#define INT_AGGR_COUNTER_THRESHOLD_MASK UFS_MASK(0x1F, 8) +#define INT_AGGR_COUNTER_AND_TIMER_RESET 0x10000 +#define INT_AGGR_STATUS_BIT 0x100000 +#define INT_AGGR_PARAM_WRITE 0x1000000 +#define INT_AGGR_ENABLE 0x80000000 + +/* UTRLRSR - UTP Transfer Request Run-Stop Register 60h */ +#define UTP_TRANSFER_REQ_LIST_RUN_STOP_BIT 0x1 + +/* UTMRLRSR - UTP Task Management Request Run-Stop Register 80h */ +#define UTP_TASK_REQ_LIST_RUN_STOP_BIT 0x1 + +/* UICCMD - UIC Command */ +#define COMMAND_OPCODE_MASK 0xFF +#define GEN_SELECTOR_INDEX_MASK 0xFFFF + +#define MIB_ATTRIBUTE_MASK UFS_MASK(0xFFFF, 16) +#define RESET_LEVEL 0xFF + +#define ATTR_SET_TYPE_MASK UFS_MASK(0xFF, 16) +#define CONFIG_RESULT_CODE_MASK 0xFF +#define GENERIC_ERROR_CODE_MASK 0xFF + +/* GenSelectorIndex calculation macros for M-PHY attributes */ +#define UIC_ARG_MPHY_TX_GEN_SEL_INDEX(lane) (lane) +#define UIC_ARG_MPHY_RX_GEN_SEL_INDEX(lane) (PA_MAXDATALANES + (lane)) + +#define UIC_ARG_MIB_SEL(attr, sel) ((((attr) & 0xFFFF) << 16) |\ + ((sel) & 0xFFFF)) +#define UIC_ARG_MIB(attr) UIC_ARG_MIB_SEL(attr, 0) +#define UIC_ARG_ATTR_TYPE(t) (((t) & 0xFF) << 16) +#define UIC_GET_ATTR_ID(v) (((v) >> 16) & 0xFFFF) + +/* Link Status*/ +enum link_status { + UFSHCD_LINK_IS_DOWN = 1, + UFSHCD_LINK_IS_UP = 2, +}; + +/* UIC Commands */ +enum uic_cmd_dme { + UIC_CMD_DME_GET = 0x01, + UIC_CMD_DME_SET = 0x02, + UIC_CMD_DME_PEER_GET = 0x03, + UIC_CMD_DME_PEER_SET = 0x04, + UIC_CMD_DME_POWERON = 0x10, + UIC_CMD_DME_POWEROFF = 0x11, + UIC_CMD_DME_ENABLE = 0x12, + UIC_CMD_DME_RESET = 0x14, + UIC_CMD_DME_END_PT_RST = 0x15, + UIC_CMD_DME_LINK_STARTUP = 0x16, + UIC_CMD_DME_HIBER_ENTER = 0x17, + UIC_CMD_DME_HIBER_EXIT = 0x18, + UIC_CMD_DME_TEST_MODE = 0x1A, +}; + +/* UIC Config result code / Generic error code */ +enum { + UIC_CMD_RESULT_SUCCESS = 0x00, + UIC_CMD_RESULT_INVALID_ATTR = 0x01, + UIC_CMD_RESULT_FAILURE = 0x01, + UIC_CMD_RESULT_INVALID_ATTR_VALUE = 0x02, + UIC_CMD_RESULT_READ_ONLY_ATTR = 0x03, + UIC_CMD_RESULT_WRITE_ONLY_ATTR = 0x04, + UIC_CMD_RESULT_BAD_INDEX = 0x05, + UIC_CMD_RESULT_LOCKED_ATTR = 0x06, + UIC_CMD_RESULT_BAD_TEST_FEATURE_INDEX = 0x07, + UIC_CMD_RESULT_PEER_COMM_FAILURE = 0x08, + UIC_CMD_RESULT_BUSY = 0x09, + UIC_CMD_RESULT_DME_FAILURE = 0x0A, +}; + +#define MASK_UIC_COMMAND_RESULT 0xFF + +#define INT_AGGR_COUNTER_THLD_VAL(c) (((c) & 0x1F) << 8) +#define INT_AGGR_TIMEOUT_VAL(t) (((t) & 0xFF) << 0) + +/* Interrupt disable masks */ +enum { + /* Interrupt disable mask for UFSHCI v1.0 */ + INTERRUPT_MASK_ALL_VER_10 = 0x30FFF, + INTERRUPT_MASK_RW_VER_10 = 0x30000, + + /* Interrupt disable mask for UFSHCI v1.1 */ + INTERRUPT_MASK_ALL_VER_11 = 0x31FFF, + + /* Interrupt disable mask for UFSHCI v2.1 */ + INTERRUPT_MASK_ALL_VER_21 = 0x71FFF, +}; + +/* CCAP - Crypto Capability 100h */ +union ufs_crypto_capabilities { + __le32 reg_val; + struct { + u8 num_crypto_cap; + u8 config_count; + u8 reserved; + u8 config_array_ptr; + }; +}; + +enum ufs_crypto_key_size { + UFS_CRYPTO_KEY_SIZE_INVALID = 0x0, + UFS_CRYPTO_KEY_SIZE_128 = 0x1, + UFS_CRYPTO_KEY_SIZE_192 = 0x2, + UFS_CRYPTO_KEY_SIZE_256 = 0x3, + UFS_CRYPTO_KEY_SIZE_512 = 0x4, +}; + +enum ufs_crypto_alg { + UFS_CRYPTO_ALG_AES_XTS = 0x0, + UFS_CRYPTO_ALG_BITLOCKER_AES_CBC = 0x1, + UFS_CRYPTO_ALG_AES_ECB = 0x2, + UFS_CRYPTO_ALG_ESSIV_AES_CBC = 0x3, +}; + +/* x-CRYPTOCAP - Crypto Capability X */ +union ufs_crypto_cap_entry { + __le32 reg_val; + struct { + u8 algorithm_id; + u8 sdus_mask; /* Supported data unit size mask */ + u8 key_size; + u8 reserved; + }; +}; + +#define UFS_CRYPTO_CONFIGURATION_ENABLE (1 << 7) +#define UFS_CRYPTO_KEY_MAX_SIZE 64 +/* x-CRYPTOCFG - Crypto Configuration X */ +union ufs_crypto_cfg_entry { + __le32 reg_val[32]; + struct { + u8 crypto_key[UFS_CRYPTO_KEY_MAX_SIZE]; + u8 data_unit_size; + u8 crypto_cap_idx; + u8 reserved_1; + u8 config_enable; + u8 reserved_multi_host; + u8 reserved_2; + u8 vsb[2]; + u8 reserved_3[56]; + }; +}; + +/* + * Request Descriptor Definitions + */ + +/* Transfer request command type */ +enum { + UTP_CMD_TYPE_SCSI = 0x0, + UTP_CMD_TYPE_UFS = 0x1, + UTP_CMD_TYPE_DEV_MANAGE = 0x2, +}; + +/* To accommodate UFS2.0 required Command type */ +enum { + UTP_CMD_TYPE_UFS_STORAGE = 0x1, +}; + +enum { + UTP_SCSI_COMMAND = 0x00000000, + UTP_NATIVE_UFS_COMMAND = 0x10000000, + UTP_DEVICE_MANAGEMENT_FUNCTION = 0x20000000, + UTP_REQ_DESC_INT_CMD = 0x01000000, + UTP_REQ_DESC_CRYPTO_ENABLE_CMD = 0x00800000, +}; + +/* UTP Transfer Request Data Direction (DD) */ +enum { + UTP_NO_DATA_TRANSFER = 0x00000000, + UTP_HOST_TO_DEVICE = 0x02000000, + UTP_DEVICE_TO_HOST = 0x04000000, +}; + +/* Overall command status values */ +enum utp_ocs { + OCS_SUCCESS = 0x0, + OCS_INVALID_CMD_TABLE_ATTR = 0x1, + OCS_INVALID_PRDT_ATTR = 0x2, + OCS_MISMATCH_DATA_BUF_SIZE = 0x3, + OCS_MISMATCH_RESP_UPIU_SIZE = 0x4, + OCS_PEER_COMM_FAILURE = 0x5, + OCS_ABORTED = 0x6, + OCS_FATAL_ERROR = 0x7, + OCS_DEVICE_FATAL_ERROR = 0x8, + OCS_INVALID_CRYPTO_CONFIG = 0x9, + OCS_GENERAL_CRYPTO_ERROR = 0xA, + OCS_INVALID_COMMAND_STATUS = 0x0F, +}; + +enum { + MASK_OCS = 0x0F, +}; + +/* The maximum length of the data byte count field in the PRDT is 256KB */ +#define PRDT_DATA_BYTE_COUNT_MAX (256 * 1024) +/* The granularity of the data byte count field in the PRDT is 32-bit */ +#define PRDT_DATA_BYTE_COUNT_PAD 4 + +/** + * struct ufshcd_sg_entry - UFSHCI PRD Entry + * @addr: Physical address; DW-0 and DW-1. + * @reserved: Reserved for future use DW-2 + * @size: size of physical segment DW-3 + */ +struct ufshcd_sg_entry { + __le64 addr; + __le32 reserved; + __le32 size; +}; + +/** + * struct utp_transfer_cmd_desc - UTP Command Descriptor (UCD) + * @command_upiu: Command UPIU Frame address + * @response_upiu: Response UPIU Frame address + * @prd_table: Physical Region Descriptor + */ +struct utp_transfer_cmd_desc { + u8 command_upiu[ALIGNED_UPIU_SIZE]; + u8 response_upiu[ALIGNED_UPIU_SIZE]; + struct ufshcd_sg_entry prd_table[SG_ALL]; +}; + +/** + * struct request_desc_header - Descriptor Header common to both UTRD and UTMRD + * @dword0: Descriptor Header DW0 + * @dword1: Descriptor Header DW1 + * @dword2: Descriptor Header DW2 + * @dword3: Descriptor Header DW3 + */ +struct request_desc_header { + __le32 dword_0; + __le32 dword_1; + __le32 dword_2; + __le32 dword_3; +}; + +/** + * struct utp_transfer_req_desc - UTP Transfer Request Descriptor (UTRD) + * @header: UTRD header DW-0 to DW-3 + * @command_desc_base_addr_lo: UCD base address low DW-4 + * @command_desc_base_addr_hi: UCD base address high DW-5 + * @response_upiu_length: response UPIU length DW-6 + * @response_upiu_offset: response UPIU offset DW-6 + * @prd_table_length: Physical region descriptor length DW-7 + * @prd_table_offset: Physical region descriptor offset DW-7 + */ +struct utp_transfer_req_desc { + + /* DW 0-3 */ + struct request_desc_header header; + + /* DW 4-5*/ + __le32 command_desc_base_addr_lo; + __le32 command_desc_base_addr_hi; + + /* DW 6 */ + __le16 response_upiu_length; + __le16 response_upiu_offset; + + /* DW 7 */ + __le16 prd_table_length; + __le16 prd_table_offset; +}; + +/* + * UTMRD structure. + */ +struct utp_task_req_desc { + /* DW 0-3 */ + struct request_desc_header header; + + /* DW 4-11 - Task request UPIU structure */ + struct { + struct utp_upiu_header req_header; + __be32 input_param1; + __be32 input_param2; + __be32 input_param3; + __be32 __reserved1[2]; + } upiu_req; + + /* DW 12-19 - Task Management Response UPIU structure */ + struct { + struct utp_upiu_header rsp_header; + __be32 output_param1; + __be32 output_param2; + __be32 __reserved2[3]; + } upiu_rsp; +}; + +#endif /* End of Header */ diff --git a/include/ufs/unipro.h b/include/ufs/unipro.h new file mode 100644 index 000000000000..0521f887e3ac --- /dev/null +++ b/include/ufs/unipro.h @@ -0,0 +1,316 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2013 Samsung Electronics Co., Ltd. + */ + +#ifndef _UNIPRO_H_ +#define _UNIPRO_H_ + +/* + * M-TX Configuration Attributes + */ +#define TX_HIBERN8TIME_CAPABILITY 0x000F +#define TX_MODE 0x0021 +#define TX_HSRATE_SERIES 0x0022 +#define TX_HSGEAR 0x0023 +#define TX_PWMGEAR 0x0024 +#define TX_AMPLITUDE 0x0025 +#define TX_HS_SLEWRATE 0x0026 +#define TX_SYNC_SOURCE 0x0027 +#define TX_HS_SYNC_LENGTH 0x0028 +#define TX_HS_PREPARE_LENGTH 0x0029 +#define TX_LS_PREPARE_LENGTH 0x002A +#define TX_HIBERN8_CONTROL 0x002B +#define TX_LCC_ENABLE 0x002C +#define TX_PWM_BURST_CLOSURE_EXTENSION 0x002D +#define TX_BYPASS_8B10B_ENABLE 0x002E +#define TX_DRIVER_POLARITY 0x002F +#define TX_HS_UNTERMINATED_LINE_DRIVE_ENABLE 0x0030 +#define TX_LS_TERMINATED_LINE_DRIVE_ENABLE 0x0031 +#define TX_LCC_SEQUENCER 0x0032 +#define TX_MIN_ACTIVATETIME 0x0033 +#define TX_PWM_G6_G7_SYNC_LENGTH 0x0034 +#define TX_REFCLKFREQ 0x00EB +#define TX_CFGCLKFREQVAL 0x00EC +#define CFGEXTRATTR 0x00F0 +#define DITHERCTRL2 0x00F1 + +/* + * M-RX Configuration Attributes + */ +#define RX_MODE 0x00A1 +#define RX_HSRATE_SERIES 0x00A2 +#define RX_HSGEAR 0x00A3 +#define RX_PWMGEAR 0x00A4 +#define RX_LS_TERMINATED_ENABLE 0x00A5 +#define RX_HS_UNTERMINATED_ENABLE 0x00A6 +#define RX_ENTER_HIBERN8 0x00A7 +#define RX_BYPASS_8B10B_ENABLE 0x00A8 +#define RX_TERMINATION_FORCE_ENABLE 0x00A9 +#define RX_MIN_ACTIVATETIME_CAPABILITY 0x008F +#define RX_HIBERN8TIME_CAPABILITY 0x0092 +#define RX_REFCLKFREQ 0x00EB +#define RX_CFGCLKFREQVAL 0x00EC +#define CFGWIDEINLN 0x00F0 +#define CFGRXCDR8 0x00BA +#define ENARXDIRECTCFG4 0x00F2 +#define CFGRXOVR8 0x00BD +#define RXDIRECTCTRL2 0x00C7 +#define ENARXDIRECTCFG3 0x00F3 +#define RXCALCTRL 0x00B4 +#define ENARXDIRECTCFG2 0x00F4 +#define CFGRXOVR4 0x00E9 +#define RXSQCTRL 0x00B5 +#define CFGRXOVR6 0x00BF +#define RX_HS_G1_SYNC_LENGTH_CAP 0x008B +#define RX_HS_G1_PREP_LENGTH_CAP 0x008C +#define RX_HS_G2_SYNC_LENGTH_CAP 0x0094 +#define RX_HS_G3_SYNC_LENGTH_CAP 0x0095 +#define RX_HS_G2_PREP_LENGTH_CAP 0x0096 +#define RX_HS_G3_PREP_LENGTH_CAP 0x0097 +#define RX_ADV_GRANULARITY_CAP 0x0098 +#define RX_MIN_ACTIVATETIME_CAP 0x008F +#define RX_HIBERN8TIME_CAP 0x0092 +#define RX_ADV_HIBERN8TIME_CAP 0x0099 +#define RX_ADV_MIN_ACTIVATETIME_CAP 0x009A + + +#define is_mphy_tx_attr(attr) (attr < RX_MODE) +#define RX_ADV_FINE_GRAN_STEP(x) ((((x) & 0x3) << 1) | 0x1) +#define SYNC_LEN_FINE(x) ((x) & 0x3F) +#define SYNC_LEN_COARSE(x) ((1 << 6) | ((x) & 0x3F)) +#define PREP_LEN(x) ((x) & 0xF) + +#define RX_MIN_ACTIVATETIME_UNIT_US 100 +#define HIBERN8TIME_UNIT_US 100 + +/* + * Common Block Attributes + */ +#define TX_GLOBALHIBERNATE UNIPRO_CB_OFFSET(0x002B) +#define REFCLKMODE UNIPRO_CB_OFFSET(0x00BF) +#define DIRECTCTRL19 UNIPRO_CB_OFFSET(0x00CD) +#define DIRECTCTRL10 UNIPRO_CB_OFFSET(0x00E6) +#define CDIRECTCTRL6 UNIPRO_CB_OFFSET(0x00EA) +#define RTOBSERVESELECT UNIPRO_CB_OFFSET(0x00F0) +#define CBDIVFACTOR UNIPRO_CB_OFFSET(0x00F1) +#define CBDCOCTRL5 UNIPRO_CB_OFFSET(0x00F3) +#define CBPRGPLL2 UNIPRO_CB_OFFSET(0x00F8) +#define CBPRGTUNING UNIPRO_CB_OFFSET(0x00FB) + +#define UNIPRO_CB_OFFSET(x) (0x8000 | x) + +/* + * PHY Adapter attributes + */ +#define PA_ACTIVETXDATALANES 0x1560 +#define PA_ACTIVERXDATALANES 0x1580 +#define PA_TXTRAILINGCLOCKS 0x1564 +#define PA_PHY_TYPE 0x1500 +#define PA_AVAILTXDATALANES 0x1520 +#define PA_AVAILRXDATALANES 0x1540 +#define PA_MINRXTRAILINGCLOCKS 0x1543 +#define PA_TXPWRSTATUS 0x1567 +#define PA_RXPWRSTATUS 0x1582 +#define PA_TXFORCECLOCK 0x1562 +#define PA_TXPWRMODE 0x1563 +#define PA_LEGACYDPHYESCDL 0x1570 +#define PA_MAXTXSPEEDFAST 0x1521 +#define PA_MAXTXSPEEDSLOW 0x1522 +#define PA_MAXRXSPEEDFAST 0x1541 +#define PA_MAXRXSPEEDSLOW 0x1542 +#define PA_TXLINKSTARTUPHS 0x1544 +#define PA_LOCAL_TX_LCC_ENABLE 0x155E +#define PA_TXSPEEDFAST 0x1565 +#define PA_TXSPEEDSLOW 0x1566 +#define PA_REMOTEVERINFO 0x15A0 +#define PA_TXGEAR 0x1568 +#define PA_TXTERMINATION 0x1569 +#define PA_HSSERIES 0x156A +#define PA_PWRMODE 0x1571 +#define PA_RXGEAR 0x1583 +#define PA_RXTERMINATION 0x1584 +#define PA_MAXRXPWMGEAR 0x1586 +#define PA_MAXRXHSGEAR 0x1587 +#define PA_RXHSUNTERMCAP 0x15A5 +#define PA_RXLSTERMCAP 0x15A6 +#define PA_GRANULARITY 0x15AA +#define PA_PACPREQTIMEOUT 0x1590 +#define PA_PACPREQEOBTIMEOUT 0x1591 +#define PA_HIBERN8TIME 0x15A7 +#define PA_LOCALVERINFO 0x15A9 +#define PA_GRANULARITY 0x15AA +#define PA_TACTIVATE 0x15A8 +#define PA_PACPFRAMECOUNT 0x15C0 +#define PA_PACPERRORCOUNT 0x15C1 +#define PA_PHYTESTCONTROL 0x15C2 +#define PA_PWRMODEUSERDATA0 0x15B0 +#define PA_PWRMODEUSERDATA1 0x15B1 +#define PA_PWRMODEUSERDATA2 0x15B2 +#define PA_PWRMODEUSERDATA3 0x15B3 +#define PA_PWRMODEUSERDATA4 0x15B4 +#define PA_PWRMODEUSERDATA5 0x15B5 +#define PA_PWRMODEUSERDATA6 0x15B6 +#define PA_PWRMODEUSERDATA7 0x15B7 +#define PA_PWRMODEUSERDATA8 0x15B8 +#define PA_PWRMODEUSERDATA9 0x15B9 +#define PA_PWRMODEUSERDATA10 0x15BA +#define PA_PWRMODEUSERDATA11 0x15BB +#define PA_CONNECTEDTXDATALANES 0x1561 +#define PA_CONNECTEDRXDATALANES 0x1581 +#define PA_LOGICALLANEMAP 0x15A1 +#define PA_SLEEPNOCONFIGTIME 0x15A2 +#define PA_STALLNOCONFIGTIME 0x15A3 +#define PA_SAVECONFIGTIME 0x15A4 +#define PA_TXHSADAPTTYPE 0x15D4 + +/* Adpat type for PA_TXHSADAPTTYPE attribute */ +#define PA_REFRESH_ADAPT 0x00 +#define PA_INITIAL_ADAPT 0x01 +#define PA_NO_ADAPT 0x03 + +#define PA_TACTIVATE_TIME_UNIT_US 10 +#define PA_HIBERN8_TIME_UNIT_US 100 + +/*Other attributes*/ +#define VS_MPHYCFGUPDT 0xD085 +#define VS_DEBUGOMC 0xD09E +#define VS_POWERSTATE 0xD083 + +#define PA_GRANULARITY_MIN_VAL 1 +#define PA_GRANULARITY_MAX_VAL 6 + +/* PHY Adapter Protocol Constants */ +#define PA_MAXDATALANES 4 + +#define DL_FC0ProtectionTimeOutVal_Default 8191 +#define DL_TC0ReplayTimeOutVal_Default 65535 +#define DL_AFC0ReqTimeOutVal_Default 32767 +#define DL_FC1ProtectionTimeOutVal_Default 8191 +#define DL_TC1ReplayTimeOutVal_Default 65535 +#define DL_AFC1ReqTimeOutVal_Default 32767 + +#define DME_LocalFC0ProtectionTimeOutVal 0xD041 +#define DME_LocalTC0ReplayTimeOutVal 0xD042 +#define DME_LocalAFC0ReqTimeOutVal 0xD043 + +/* PA power modes */ +enum { + FAST_MODE = 1, + SLOW_MODE = 2, + FASTAUTO_MODE = 4, + SLOWAUTO_MODE = 5, + UNCHANGED = 7, +}; + +#define PWRMODE_MASK 0xF +#define PWRMODE_RX_OFFSET 4 + +/* PA TX/RX Frequency Series */ +enum { + PA_HS_MODE_A = 1, + PA_HS_MODE_B = 2, +}; + +enum ufs_pwm_gear_tag { + UFS_PWM_DONT_CHANGE, /* Don't change Gear */ + UFS_PWM_G1, /* PWM Gear 1 (default for reset) */ + UFS_PWM_G2, /* PWM Gear 2 */ + UFS_PWM_G3, /* PWM Gear 3 */ + UFS_PWM_G4, /* PWM Gear 4 */ + UFS_PWM_G5, /* PWM Gear 5 */ + UFS_PWM_G6, /* PWM Gear 6 */ + UFS_PWM_G7, /* PWM Gear 7 */ +}; + +enum ufs_hs_gear_tag { + UFS_HS_DONT_CHANGE, /* Don't change Gear */ + UFS_HS_G1, /* HS Gear 1 (default for reset) */ + UFS_HS_G2, /* HS Gear 2 */ + UFS_HS_G3, /* HS Gear 3 */ + UFS_HS_G4, /* HS Gear 4 */ +}; + +enum ufs_unipro_ver { + UFS_UNIPRO_VER_RESERVED = 0, + UFS_UNIPRO_VER_1_40 = 1, /* UniPro version 1.40 */ + UFS_UNIPRO_VER_1_41 = 2, /* UniPro version 1.41 */ + UFS_UNIPRO_VER_1_6 = 3, /* UniPro version 1.6 */ + UFS_UNIPRO_VER_1_61 = 4, /* UniPro version 1.61 */ + UFS_UNIPRO_VER_1_8 = 5, /* UniPro version 1.8 */ + UFS_UNIPRO_VER_MAX = 6, /* UniPro unsupported version */ + /* UniPro version field mask in PA_LOCALVERINFO */ + UFS_UNIPRO_VER_MASK = 0xF, +}; + +/* + * Data Link Layer Attributes + */ +#define DL_TC0TXFCTHRESHOLD 0x2040 +#define DL_FC0PROTTIMEOUTVAL 0x2041 +#define DL_TC0REPLAYTIMEOUTVAL 0x2042 +#define DL_AFC0REQTIMEOUTVAL 0x2043 +#define DL_AFC0CREDITTHRESHOLD 0x2044 +#define DL_TC0OUTACKTHRESHOLD 0x2045 +#define DL_TC1TXFCTHRESHOLD 0x2060 +#define DL_FC1PROTTIMEOUTVAL 0x2061 +#define DL_TC1REPLAYTIMEOUTVAL 0x2062 +#define DL_AFC1REQTIMEOUTVAL 0x2063 +#define DL_AFC1CREDITTHRESHOLD 0x2064 +#define DL_TC1OUTACKTHRESHOLD 0x2065 +#define DL_TXPREEMPTIONCAP 0x2000 +#define DL_TC0TXMAXSDUSIZE 0x2001 +#define DL_TC0RXINITCREDITVAL 0x2002 +#define DL_TC0TXBUFFERSIZE 0x2005 +#define DL_PEERTC0PRESENT 0x2046 +#define DL_PEERTC0RXINITCREVAL 0x2047 +#define DL_TC1TXMAXSDUSIZE 0x2003 +#define DL_TC1RXINITCREDITVAL 0x2004 +#define DL_TC1TXBUFFERSIZE 0x2006 +#define DL_PEERTC1PRESENT 0x2066 +#define DL_PEERTC1RXINITCREVAL 0x2067 + +/* + * Network Layer Attributes + */ +#define N_DEVICEID 0x3000 +#define N_DEVICEID_VALID 0x3001 +#define N_TC0TXMAXSDUSIZE 0x3020 +#define N_TC1TXMAXSDUSIZE 0x3021 + +/* + * Transport Layer Attributes + */ +#define T_NUMCPORTS 0x4000 +#define T_NUMTESTFEATURES 0x4001 +#define T_CONNECTIONSTATE 0x4020 +#define T_PEERDEVICEID 0x4021 +#define T_PEERCPORTID 0x4022 +#define T_TRAFFICCLASS 0x4023 +#define T_PROTOCOLID 0x4024 +#define T_CPORTFLAGS 0x4025 +#define T_TXTOKENVALUE 0x4026 +#define T_RXTOKENVALUE 0x4027 +#define T_LOCALBUFFERSPACE 0x4028 +#define T_PEERBUFFERSPACE 0x4029 +#define T_CREDITSTOSEND 0x402A +#define T_CPORTMODE 0x402B +#define T_TC0TXMAXSDUSIZE 0x4060 +#define T_TC1TXMAXSDUSIZE 0x4061 + +/* CPort setting */ +#define E2EFC_ON (1 << 0) +#define E2EFC_OFF (0 << 0) +#define CSD_N_ON (0 << 1) +#define CSD_N_OFF (1 << 1) +#define CSV_N_ON (0 << 2) +#define CSV_N_OFF (1 << 2) +#define CPORT_DEF_FLAGS (CSV_N_OFF | CSD_N_OFF | E2EFC_OFF) + +/* CPort connection state */ +enum { + CPORT_IDLE = 0, + CPORT_CONNECTED, +}; + +#endif /* _UNIPRO_H_ */ -- cgit v1.2.3 From 59df85d5fbae17175c391d89ad03e9e7a01b7a55 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 1 Mar 2022 19:56:53 -0500 Subject: linux/mount.h: trim includes Signed-off-by: Al Viro --- include/linux/mount.h | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/mount.h b/include/linux/mount.h index 7f18a7555dff..b3b149dcbf96 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -11,17 +11,15 @@ #define _LINUX_MOUNT_H #include -#include -#include -#include -#include -#include +#include struct super_block; -struct vfsmount; struct dentry; -struct mnt_namespace; +struct user_namespace; +struct file_system_type; struct fs_context; +struct file; +struct path; #define MNT_NOSUID 0x01 #define MNT_NODEV 0x02 @@ -81,9 +79,6 @@ static inline struct user_namespace *mnt_user_ns(const struct vfsmount *mnt) return smp_load_acquire(&mnt->mnt_userns); } -struct file; /* forward dec */ -struct path; - extern int mnt_want_write(struct vfsmount *mnt); extern int mnt_want_write_file(struct file *file); extern void mnt_drop_write(struct vfsmount *mnt); @@ -94,12 +89,10 @@ extern struct vfsmount *mnt_clone_internal(const struct path *path); extern bool __mnt_is_readonly(struct vfsmount *mnt); extern bool mnt_may_suid(struct vfsmount *mnt); -struct path; extern struct vfsmount *clone_private_mount(const struct path *path); extern int __mnt_want_write(struct vfsmount *); extern void __mnt_drop_write(struct vfsmount *); -struct file_system_type; extern struct vfsmount *fc_mount(struct fs_context *fc); extern struct vfsmount *vfs_create_mount(struct fs_context *fc); extern struct vfsmount *vfs_kern_mount(struct file_system_type *type, -- cgit v1.2.3 From 70f8d9c5750bbb0ca4ef7e23d6abcb05e6061138 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 2 Mar 2022 17:49:09 -0500 Subject: move mount-related externs from fs.h to mount.h Signed-off-by: Al Viro --- include/linux/fs.h | 11 ----------- include/linux/mount.h | 12 ++++++++++++ 2 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index bbde95387a23..14df7c049b43 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2461,22 +2461,11 @@ struct super_block *sget(struct file_system_type *type, extern int register_filesystem(struct file_system_type *); extern int unregister_filesystem(struct file_system_type *); -extern struct vfsmount *kern_mount(struct file_system_type *); -extern void kern_unmount(struct vfsmount *mnt); -extern int may_umount_tree(struct vfsmount *); -extern int may_umount(struct vfsmount *); -extern long do_mount(const char *, const char __user *, - const char *, unsigned long, void *); -extern struct vfsmount *collect_mounts(const struct path *); -extern void drop_collected_mounts(struct vfsmount *); -extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *, - struct vfsmount *); extern int vfs_statfs(const struct path *, struct kstatfs *); extern int user_statfs(const char __user *, struct kstatfs *); extern int fd_statfs(int, struct kstatfs *); extern int freeze_super(struct super_block *super); extern int thaw_super(struct super_block *super); -extern bool our_mnt(struct vfsmount *mnt); extern __printf(2, 3) int super_setup_bdi_name(struct super_block *sb, char *fmt, ...); extern int super_setup_bdi(struct super_block *sb); diff --git a/include/linux/mount.h b/include/linux/mount.h index b3b149dcbf96..55a4abaf6715 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -108,6 +108,18 @@ extern void mark_mounts_for_expiry(struct list_head *mounts); extern dev_t name_to_dev_t(const char *name); extern bool path_is_mountpoint(const struct path *path); +extern bool our_mnt(struct vfsmount *mnt); + +extern struct vfsmount *kern_mount(struct file_system_type *); +extern void kern_unmount(struct vfsmount *mnt); +extern int may_umount_tree(struct vfsmount *); +extern int may_umount(struct vfsmount *); +extern long do_mount(const char *, const char __user *, + const char *, unsigned long, void *); +extern struct vfsmount *collect_mounts(const struct path *); +extern void drop_collected_mounts(struct vfsmount *); +extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *, + struct vfsmount *); extern void kern_unmount_array(struct vfsmount *mnt[], unsigned int num); #endif /* _LINUX_MOUNT_H */ -- cgit v1.2.3 From 58e5bdeb9c2b06895e723c0b1e670f54510ff782 Mon Sep 17 00:00:00 2001 From: Kanchan Joshi Date: Fri, 20 May 2022 14:36:30 +0530 Subject: nvme: enable uring-passthrough for admin commands Add two new opcodes that userspace can use for admin commands: NVME_URING_CMD_ADMIN : non-vectroed NVME_URING_CMD_ADMIN_VEC : vectored variant Wire up support when these are issued on controller node(/dev/nvmeX). Signed-off-by: Kanchan Joshi Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220520090630.70394-3-joshi.k@samsung.com Signed-off-by: Jens Axboe --- include/uapi/linux/nvme_ioctl.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h index 0b1876aa5a59..2f76cba67166 100644 --- a/include/uapi/linux/nvme_ioctl.h +++ b/include/uapi/linux/nvme_ioctl.h @@ -108,5 +108,7 @@ struct nvme_uring_cmd { /* io_uring async commands: */ #define NVME_URING_CMD_IO _IOWR('N', 0x80, struct nvme_uring_cmd) #define NVME_URING_CMD_IO_VEC _IOWR('N', 0x81, struct nvme_uring_cmd) +#define NVME_URING_CMD_ADMIN _IOWR('N', 0x82, struct nvme_uring_cmd) +#define NVME_URING_CMD_ADMIN_VEC _IOWR('N', 0x83, struct nvme_uring_cmd) #endif /* _UAPI_LINUX_NVME_IOCTL_H */ -- cgit v1.2.3 From 84d0940454a3bca6c7c59cf16b6de2f173e81a11 Mon Sep 17 00:00:00 2001 From: Fabio Baltieri Date: Thu, 28 Apr 2022 10:04:18 +0000 Subject: dt-bindings: Add mfd/cros_ec definitions Add a dt-bindings include file for cros_ec devicetree definition, define a pair of special purpose PWM channels in it. Signed-off-by: Fabio Baltieri Acked-by: Rob Herring Signed-off-by: Thierry Reding --- include/dt-bindings/mfd/cros_ec.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 include/dt-bindings/mfd/cros_ec.h (limited to 'include') diff --git a/include/dt-bindings/mfd/cros_ec.h b/include/dt-bindings/mfd/cros_ec.h new file mode 100644 index 000000000000..3b29cd049578 --- /dev/null +++ b/include/dt-bindings/mfd/cros_ec.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * DTS binding definitions used for the Chromium OS Embedded Controller. + * + * Copyright (c) 2022 The Chromium OS Authors. All rights reserved. + */ + +#ifndef _DT_BINDINGS_MFD_CROS_EC_H +#define _DT_BINDINGS_MFD_CROS_EC_H + +/* Typed channel for keyboard backlight. */ +#define CROS_EC_PWM_DT_KB_LIGHT 0 +/* Typed channel for display backlight. */ +#define CROS_EC_PWM_DT_DISPLAY_LIGHT 1 +/* Number of typed channels. */ +#define CROS_EC_PWM_DT_COUNT 2 + +#endif -- cgit v1.2.3 From 3bc253c2e652cf5f12cd8c00d80d8ec55d67d1a7 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Thu, 19 May 2022 16:30:10 -0700 Subject: bpf: Add bpf_skc_to_mptcp_sock_proto This patch implements a new struct bpf_func_proto, named bpf_skc_to_mptcp_sock_proto. Define a new bpf_id BTF_SOCK_TYPE_MPTCP, and a new helper bpf_skc_to_mptcp_sock(), which invokes another new helper bpf_mptcp_sock_from_subflow() in net/mptcp/bpf.c to get struct mptcp_sock from a given subflow socket. v2: Emit BTF type, add func_id checks in verifier.c and bpf_trace.c, remove build check for CONFIG_BPF_JIT v5: Drop EXPORT_SYMBOL (Martin) Co-developed-by: Nicolas Rybowski Co-developed-by: Matthieu Baerts Signed-off-by: Nicolas Rybowski Signed-off-by: Matthieu Baerts Signed-off-by: Geliang Tang Signed-off-by: Mat Martineau Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220519233016.105670-2-mathew.j.martineau@linux.intel.com --- include/linux/bpf.h | 1 + include/linux/btf_ids.h | 3 ++- include/net/mptcp.h | 6 ++++++ include/uapi/linux/bpf.h | 7 +++++++ 4 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c107392b0ba7..a3ef078401cf 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2231,6 +2231,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto; extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto; extern const struct bpf_func_proto bpf_skc_to_unix_sock_proto; +extern const struct bpf_func_proto bpf_skc_to_mptcp_sock_proto; extern const struct bpf_func_proto bpf_copy_from_user_proto; extern const struct bpf_func_proto bpf_snprintf_btf_proto; extern const struct bpf_func_proto bpf_snprintf_proto; diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index bc5d9cc34e4c..335a19092368 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -178,7 +178,8 @@ extern struct btf_id_set name; BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, tcp6_sock) \ BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock) \ BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock) \ - BTF_SOCK_TYPE(BTF_SOCK_TYPE_UNIX, unix_sock) + BTF_SOCK_TYPE(BTF_SOCK_TYPE_UNIX, unix_sock) \ + BTF_SOCK_TYPE(BTF_SOCK_TYPE_MPTCP, mptcp_sock) enum { #define BTF_SOCK_TYPE(name, str) name, diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 8b1afd6f5cc4..2ba09de955c7 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -284,4 +284,10 @@ static inline int mptcpv6_init(void) { return 0; } static inline void mptcpv6_handle_mapped(struct sock *sk, bool mapped) { } #endif +#if defined(CONFIG_MPTCP) && defined(CONFIG_BPF_SYSCALL) +struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk); +#else +static inline struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk) { return NULL; } +#endif + #endif /* __NET_MPTCP_H */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0210f85131b3..56688bee20d9 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5172,6 +5172,12 @@ union bpf_attr { * Return * Map value associated to *key* on *cpu*, or **NULL** if no entry * was found or *cpu* is invalid. + * + * struct mptcp_sock *bpf_skc_to_mptcp_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *mptcp_sock* pointer. + * Return + * *sk* if casting is valid, or **NULL** otherwise. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5370,6 +5376,7 @@ union bpf_attr { FN(ima_file_hash), \ FN(kptr_xchg), \ FN(map_lookup_percpu_elem), \ + FN(skc_to_mptcp_sock), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From b23316aabffa835ecc516cb81daeef5b9155e8a5 Mon Sep 17 00:00:00 2001 From: Yuntao Wang Date: Thu, 19 May 2022 23:06:10 +0800 Subject: selftests/bpf: Add missing trampoline program type to trampoline_count test Currently the trampoline_count test doesn't include any fmod_ret bpf programs, fix it to make the test cover all possible trampoline program types. Since fmod_ret bpf programs can't be attached to __set_task_comm function, as it's neither whitelisted for error injection nor a security hook, change it to bpf_modify_return_test. This patch also does some other cleanups such as removing duplicate code, dropping inconsistent comments, etc. Signed-off-by: Yuntao Wang Signed-off-by: Andrii Nakryiko Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20220519150610.601313-1-ytcoode@gmail.com --- include/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a3ef078401cf..cc4d5e394031 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -724,7 +724,7 @@ struct btf_func_model { #define BPF_TRAMP_F_RET_FENTRY_RET BIT(4) /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 - * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2 + * bytes on x86. */ #define BPF_MAX_TRAMP_LINKS 38 -- cgit v1.2.3 From d5a42de8bdbe25081f07b801d8b35f4d75a791f4 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Thu, 19 May 2022 17:18:33 -0700 Subject: net: Add a second bind table hashed by port and address We currently have one tcp bind table (bhash) which hashes by port number only. In the socket bind path, we check for bind conflicts by traversing the specified port's inet_bind2_bucket while holding the bucket's spinlock (see inet_csk_get_port() and inet_csk_bind_conflict()). In instances where there are tons of sockets hashed to the same port at different addresses, checking for a bind conflict is time-intensive and can cause softirq cpu lockups, as well as stops new tcp connections since __inet_inherit_port() also contests for the spinlock. This patch proposes adding a second bind table, bhash2, that hashes by port and ip address. Searching the bhash2 table leads to significantly faster conflict resolution and less time holding the spinlock. Signed-off-by: Joanne Koong Reviewed-by: Eric Dumazet Acked-by: Kuniyuki Iwashima Signed-off-by: Jakub Kicinski --- include/net/inet_connection_sock.h | 3 ++ include/net/inet_hashtables.h | 68 +++++++++++++++++++++++++++++++++++++- include/net/sock.h | 14 ++++++++ 3 files changed, 84 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 85cd695e7fd1..077cd730ce2f 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -25,6 +25,7 @@ #undef INET_CSK_CLEAR_TIMERS struct inet_bind_bucket; +struct inet_bind2_bucket; struct tcp_congestion_ops; /* @@ -57,6 +58,7 @@ struct inet_connection_sock_af_ops { * * @icsk_accept_queue: FIFO of established children * @icsk_bind_hash: Bind node + * @icsk_bind2_hash: Bind node in the bhash2 table * @icsk_timeout: Timeout * @icsk_retransmit_timer: Resend (no ack) * @icsk_rto: Retransmit timeout @@ -83,6 +85,7 @@ struct inet_connection_sock { struct inet_sock icsk_inet; struct request_sock_queue icsk_accept_queue; struct inet_bind_bucket *icsk_bind_hash; + struct inet_bind2_bucket *icsk_bind2_hash; unsigned long icsk_timeout; struct timer_list icsk_retransmit_timer; struct timer_list icsk_delack_timer; diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index ebfa3df6f8dc..a0887b70967b 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -90,11 +90,32 @@ struct inet_bind_bucket { struct hlist_head owners; }; +struct inet_bind2_bucket { + possible_net_t ib_net; + int l3mdev; + unsigned short port; + union { +#if IS_ENABLED(CONFIG_IPV6) + struct in6_addr v6_rcv_saddr; +#endif + __be32 rcv_saddr; + }; + /* Node in the inet2_bind_hashbucket chain */ + struct hlist_node node; + /* List of sockets hashed to this bucket */ + struct hlist_head owners; +}; + static inline struct net *ib_net(struct inet_bind_bucket *ib) { return read_pnet(&ib->ib_net); } +static inline struct net *ib2_net(struct inet_bind2_bucket *ib) +{ + return read_pnet(&ib->ib_net); +} + #define inet_bind_bucket_for_each(tb, head) \ hlist_for_each_entry(tb, head, node) @@ -103,6 +124,15 @@ struct inet_bind_hashbucket { struct hlist_head chain; }; +/* This is synchronized using the inet_bind_hashbucket's spinlock. + * Instead of having separate spinlocks, the inet_bind2_hashbucket can share + * the inet_bind_hashbucket's given that in every case where the bhash2 table + * is useful, a lookup in the bhash table also occurs. + */ +struct inet_bind2_hashbucket { + struct hlist_head chain; +}; + /* Sockets can be hashed in established or listening table. * We must use different 'nulls' end-of-chain value for all hash buckets : * A socket might transition from ESTABLISH to LISTEN state without @@ -134,6 +164,12 @@ struct inet_hashinfo { */ struct kmem_cache *bind_bucket_cachep; struct inet_bind_hashbucket *bhash; + /* The 2nd binding table hashed by port and address. + * This is used primarily for expediting the resolution of bind + * conflicts. + */ + struct kmem_cache *bind2_bucket_cachep; + struct inet_bind2_hashbucket *bhash2; unsigned int bhash_size; /* The 2nd listener table hashed by local port and address */ @@ -193,6 +229,36 @@ inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net, void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket *tb); +static inline bool check_bind_bucket_match(struct inet_bind_bucket *tb, + struct net *net, + const unsigned short port, + int l3mdev) +{ + return net_eq(ib_net(tb), net) && tb->port == port && + tb->l3mdev == l3mdev; +} + +struct inet_bind2_bucket * +inet_bind2_bucket_create(struct kmem_cache *cachep, struct net *net, + struct inet_bind2_hashbucket *head, + const unsigned short port, int l3mdev, + const struct sock *sk); + +void inet_bind2_bucket_destroy(struct kmem_cache *cachep, + struct inet_bind2_bucket *tb); + +struct inet_bind2_bucket * +inet_bind2_bucket_find(struct inet_hashinfo *hinfo, struct net *net, + const unsigned short port, int l3mdev, + struct sock *sk, + struct inet_bind2_hashbucket **head); + +bool check_bind2_bucket_match_nulladdr(struct inet_bind2_bucket *tb, + struct net *net, + const unsigned short port, + int l3mdev, + const struct sock *sk); + static inline u32 inet_bhashfn(const struct net *net, const __u16 lport, const u32 bhash_size) { @@ -200,7 +266,7 @@ static inline u32 inet_bhashfn(const struct net *net, const __u16 lport, } void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, - const unsigned short snum); + struct inet_bind2_bucket *tb2, const unsigned short snum); /* Caller must disable local BH processing. */ int __inet_inherit_port(const struct sock *sk, struct sock *child); diff --git a/include/net/sock.h b/include/net/sock.h index 72ca97ccb460..c585ef6565d9 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -348,6 +348,7 @@ struct sk_filter; * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags * @ns_tracker: tracker for netns reference + * @sk_bind2_node: bind node in the bhash2 table */ struct sock { /* @@ -537,6 +538,7 @@ struct sock { #endif struct rcu_head sk_rcu; netns_tracker ns_tracker; + struct hlist_node sk_bind2_node; }; enum sk_pacing { @@ -817,6 +819,16 @@ static inline void sk_add_bind_node(struct sock *sk, hlist_add_head(&sk->sk_bind_node, list); } +static inline void __sk_del_bind2_node(struct sock *sk) +{ + __hlist_del(&sk->sk_bind2_node); +} + +static inline void sk_add_bind2_node(struct sock *sk, struct hlist_head *list) +{ + hlist_add_head(&sk->sk_bind2_node, list); +} + #define sk_for_each(__sk, list) \ hlist_for_each_entry(__sk, list, sk_node) #define sk_for_each_rcu(__sk, list) \ @@ -834,6 +846,8 @@ static inline void sk_add_bind_node(struct sock *sk, hlist_for_each_entry_safe(__sk, tmp, list, sk_node) #define sk_for_each_bound(__sk, list) \ hlist_for_each_entry(__sk, list, sk_bind_node) +#define sk_for_each_bound_bhash2(__sk, list) \ + hlist_for_each_entry(__sk, list, sk_bind2_node) /** * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset -- cgit v1.2.3 From 538101dd7ce360f29effeb45aecb1953bc0fd01b Mon Sep 17 00:00:00 2001 From: Chanho Park Date: Fri, 20 May 2022 12:06:25 +0900 Subject: dt-bindings: clock: exynosautov9: correct count of NR_CLK _NR_CLKS which can be used to register clocks via nr_clk_ids. The clock IDs are started from 1. So, _NR_CLKS should be defined to "the last clock id + 1" Fixes: 680e1c8370a2 ("dt-bindings: clock: add clock binding definitions for Exynos Auto v9") Signed-off-by: Chanho Park Link: https://lore.kernel.org/r/20220520030625.145324-1-chanho61.park@samsung.com Reviewed-by: Chanwoo Choi Reviewed-by: Krzysztof Kozlowski Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/samsung,exynosautov9.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/clock/samsung,exynosautov9.h b/include/dt-bindings/clock/samsung,exynosautov9.h index 71ec0a955364..ea9f91b4eb1a 100644 --- a/include/dt-bindings/clock/samsung,exynosautov9.h +++ b/include/dt-bindings/clock/samsung,exynosautov9.h @@ -166,7 +166,7 @@ #define GOUT_CLKCMU_PERIC1_IP 248 #define GOUT_CLKCMU_PERIS_BUS 249 -#define TOP_NR_CLK 249 +#define TOP_NR_CLK 250 /* CMU_BUSMC */ #define CLK_MOUT_BUSMC_BUS_USER 1 @@ -174,7 +174,7 @@ #define CLK_GOUT_BUSMC_PDMA0_PCLK 3 #define CLK_GOUT_BUSMC_SPDMA_PCLK 4 -#define BUSMC_NR_CLK 4 +#define BUSMC_NR_CLK 5 /* CMU_CORE */ #define CLK_MOUT_CORE_BUS_USER 1 @@ -183,7 +183,7 @@ #define CLK_GOUT_CORE_CCI_PCLK 4 #define CLK_GOUT_CORE_CMU_CORE_PCLK 5 -#define CORE_NR_CLK 5 +#define CORE_NR_CLK 6 /* CMU_FSYS2 */ #define CLK_MOUT_FSYS2_BUS_USER 1 @@ -194,7 +194,7 @@ #define CLK_GOUT_FSYS2_UFS_EMBD1_ACLK 6 #define CLK_GOUT_FSYS2_UFS_EMBD1_UNIPRO 7 -#define FSYS2_NR_CLK 7 +#define FSYS2_NR_CLK 8 /* CMU_PERIC0 */ #define CLK_MOUT_PERIC0_BUS_USER 1 @@ -240,7 +240,7 @@ #define CLK_GOUT_PERIC0_PCLK_10 41 #define CLK_GOUT_PERIC0_PCLK_11 42 -#define PERIC0_NR_CLK 42 +#define PERIC0_NR_CLK 43 /* CMU_PERIC1 */ #define CLK_MOUT_PERIC1_BUS_USER 1 @@ -286,7 +286,7 @@ #define CLK_GOUT_PERIC1_PCLK_10 41 #define CLK_GOUT_PERIC1_PCLK_11 42 -#define PERIC1_NR_CLK 42 +#define PERIC1_NR_CLK 43 /* CMU_PERIS */ #define CLK_MOUT_PERIS_BUS_USER 1 @@ -294,6 +294,6 @@ #define CLK_GOUT_WDT_CLUSTER0 3 #define CLK_GOUT_WDT_CLUSTER1 4 -#define PERIS_NR_CLK 4 +#define PERIS_NR_CLK 5 #endif /* _DT_BINDINGS_CLOCK_EXYNOSAUTOV9_H */ -- cgit v1.2.3 From 722dc8a1d5c8691ab9923b723db4354537206f97 Mon Sep 17 00:00:00 2001 From: Gabriel Fernandez Date: Mon, 16 May 2022 09:05:47 +0200 Subject: dt-bindings: rcc: stm32: add new compatible for STM32MP13 SoC New compatible to manage clock and reset of STM32MP13 SoC. Reviewed-by: Krzysztof Kozlowski Signed-off-by: Gabriel Fernandez Link: https://lore.kernel.org/r/20220516070600.7692-2-gabriel.fernandez@foss.st.com Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/stm32mp13-clks.h | 229 +++++++++++++++++++++++++++ include/dt-bindings/reset/stm32mp13-resets.h | 100 ++++++++++++ 2 files changed, 329 insertions(+) create mode 100644 include/dt-bindings/clock/stm32mp13-clks.h create mode 100644 include/dt-bindings/reset/stm32mp13-resets.h (limited to 'include') diff --git a/include/dt-bindings/clock/stm32mp13-clks.h b/include/dt-bindings/clock/stm32mp13-clks.h new file mode 100644 index 000000000000..02befd25edce --- /dev/null +++ b/include/dt-bindings/clock/stm32mp13-clks.h @@ -0,0 +1,229 @@ +/* SPDX-License-Identifier: GPL-2.0+ or BSD-3-Clause */ +/* + * Copyright (C) STMicroelectronics 2020 - All Rights Reserved + * Author: Gabriel Fernandez for STMicroelectronics. + */ + +#ifndef _DT_BINDINGS_STM32MP13_CLKS_H_ +#define _DT_BINDINGS_STM32MP13_CLKS_H_ + +/* OSCILLATOR clocks */ +#define CK_HSE 0 +#define CK_CSI 1 +#define CK_LSI 2 +#define CK_LSE 3 +#define CK_HSI 4 +#define CK_HSE_DIV2 5 + +/* PLL */ +#define PLL1 6 +#define PLL2 7 +#define PLL3 8 +#define PLL4 9 + +/* ODF */ +#define PLL1_P 10 +#define PLL1_Q 11 +#define PLL1_R 12 +#define PLL2_P 13 +#define PLL2_Q 14 +#define PLL2_R 15 +#define PLL3_P 16 +#define PLL3_Q 17 +#define PLL3_R 18 +#define PLL4_P 19 +#define PLL4_Q 20 +#define PLL4_R 21 + +#define PCLK1 22 +#define PCLK2 23 +#define PCLK3 24 +#define PCLK4 25 +#define PCLK5 26 +#define PCLK6 27 + +/* SYSTEM CLOCK */ +#define CK_PER 28 +#define CK_MPU 29 +#define CK_AXI 30 +#define CK_MLAHB 31 + +/* BASE TIMER */ +#define CK_TIMG1 32 +#define CK_TIMG2 33 +#define CK_TIMG3 34 + +/* AUX */ +#define RTC 35 + +/* TRACE & DEBUG clocks */ +#define CK_DBG 36 +#define CK_TRACE 37 + +/* MCO clocks */ +#define CK_MCO1 38 +#define CK_MCO2 39 + +/* IP clocks */ +#define SYSCFG 40 +#define VREF 41 +#define DTS 42 +#define PMBCTRL 43 +#define HDP 44 +#define IWDG2 45 +#define STGENRO 46 +#define USART1 47 +#define RTCAPB 48 +#define TZC 49 +#define TZPC 50 +#define IWDG1 51 +#define BSEC 52 +#define DMA1 53 +#define DMA2 54 +#define DMAMUX1 55 +#define DMAMUX2 56 +#define GPIOA 57 +#define GPIOB 58 +#define GPIOC 59 +#define GPIOD 60 +#define GPIOE 61 +#define GPIOF 62 +#define GPIOG 63 +#define GPIOH 64 +#define GPIOI 65 +#define CRYP1 66 +#define HASH1 67 +#define BKPSRAM 68 +#define MDMA 69 +#define CRC1 70 +#define USBH 71 +#define DMA3 72 +#define TSC 73 +#define PKA 74 +#define AXIMC 75 +#define MCE 76 +#define ETH1TX 77 +#define ETH2TX 78 +#define ETH1RX 79 +#define ETH2RX 80 +#define ETH1MAC 81 +#define ETH2MAC 82 +#define ETH1STP 83 +#define ETH2STP 84 + +/* IP clocks with parents */ +#define SDMMC1_K 85 +#define SDMMC2_K 86 +#define ADC1_K 87 +#define ADC2_K 88 +#define FMC_K 89 +#define QSPI_K 90 +#define RNG1_K 91 +#define USBPHY_K 92 +#define STGEN_K 93 +#define SPDIF_K 94 +#define SPI1_K 95 +#define SPI2_K 96 +#define SPI3_K 97 +#define SPI4_K 98 +#define SPI5_K 99 +#define I2C1_K 100 +#define I2C2_K 101 +#define I2C3_K 102 +#define I2C4_K 103 +#define I2C5_K 104 +#define TIM2_K 105 +#define TIM3_K 106 +#define TIM4_K 107 +#define TIM5_K 108 +#define TIM6_K 109 +#define TIM7_K 110 +#define TIM12_K 111 +#define TIM13_K 112 +#define TIM14_K 113 +#define TIM1_K 114 +#define TIM8_K 115 +#define TIM15_K 116 +#define TIM16_K 117 +#define TIM17_K 118 +#define LPTIM1_K 119 +#define LPTIM2_K 120 +#define LPTIM3_K 121 +#define LPTIM4_K 122 +#define LPTIM5_K 123 +#define USART1_K 124 +#define USART2_K 125 +#define USART3_K 126 +#define UART4_K 127 +#define UART5_K 128 +#define USART6_K 129 +#define UART7_K 130 +#define UART8_K 131 +#define DFSDM_K 132 +#define FDCAN_K 133 +#define SAI1_K 134 +#define SAI2_K 135 +#define ADFSDM_K 136 +#define USBO_K 137 +#define LTDC_PX 138 +#define ETH1CK_K 139 +#define ETH1PTP_K 140 +#define ETH2CK_K 141 +#define ETH2PTP_K 142 +#define DCMIPP_K 143 +#define SAES_K 144 +#define DTS_K 145 + +/* DDR */ +#define DDRC1 146 +#define DDRC1LP 147 +#define DDRC2 148 +#define DDRC2LP 149 +#define DDRPHYC 150 +#define DDRPHYCLP 151 +#define DDRCAPB 152 +#define DDRCAPBLP 153 +#define AXIDCG 154 +#define DDRPHYCAPB 155 +#define DDRPHYCAPBLP 156 +#define DDRPERFM 157 + +#define ADC1 158 +#define ADC2 159 +#define SAI1 160 +#define SAI2 161 + +#define STM32MP1_LAST_CLK 162 + +/* SCMI clock identifiers */ +#define CK_SCMI_HSE 0 +#define CK_SCMI_HSI 1 +#define CK_SCMI_CSI 2 +#define CK_SCMI_LSE 3 +#define CK_SCMI_LSI 4 +#define CK_SCMI_HSE_DIV2 5 +#define CK_SCMI_PLL2_Q 6 +#define CK_SCMI_PLL2_R 7 +#define CK_SCMI_PLL3_P 8 +#define CK_SCMI_PLL3_Q 9 +#define CK_SCMI_PLL3_R 10 +#define CK_SCMI_PLL4_P 11 +#define CK_SCMI_PLL4_Q 12 +#define CK_SCMI_PLL4_R 13 +#define CK_SCMI_MPU 14 +#define CK_SCMI_AXI 15 +#define CK_SCMI_MLAHB 16 +#define CK_SCMI_CKPER 17 +#define CK_SCMI_PCLK1 18 +#define CK_SCMI_PCLK2 19 +#define CK_SCMI_PCLK3 20 +#define CK_SCMI_PCLK4 21 +#define CK_SCMI_PCLK5 22 +#define CK_SCMI_PCLK6 23 +#define CK_SCMI_CKTIMG1 24 +#define CK_SCMI_CKTIMG2 25 +#define CK_SCMI_CKTIMG3 26 +#define CK_SCMI_RTC 27 +#define CK_SCMI_RTCAPB 28 + +#endif /* _DT_BINDINGS_STM32MP13_CLKS_H_ */ diff --git a/include/dt-bindings/reset/stm32mp13-resets.h b/include/dt-bindings/reset/stm32mp13-resets.h new file mode 100644 index 000000000000..934864e90da6 --- /dev/null +++ b/include/dt-bindings/reset/stm32mp13-resets.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 or BSD-3-Clause */ +/* + * Copyright (C) STMicroelectronics 2018 - All Rights Reserved + * Author: Gabriel Fernandez for STMicroelectronics. + */ + +#ifndef _DT_BINDINGS_STM32MP13_RESET_H_ +#define _DT_BINDINGS_STM32MP13_RESET_H_ + +#define TIM2_R 13568 +#define TIM3_R 13569 +#define TIM4_R 13570 +#define TIM5_R 13571 +#define TIM6_R 13572 +#define TIM7_R 13573 +#define LPTIM1_R 13577 +#define SPI2_R 13579 +#define SPI3_R 13580 +#define USART3_R 13583 +#define UART4_R 13584 +#define UART5_R 13585 +#define UART7_R 13586 +#define UART8_R 13587 +#define I2C1_R 13589 +#define I2C2_R 13590 +#define SPDIF_R 13594 +#define TIM1_R 13632 +#define TIM8_R 13633 +#define SPI1_R 13640 +#define USART6_R 13645 +#define SAI1_R 13648 +#define SAI2_R 13649 +#define DFSDM_R 13652 +#define FDCAN_R 13656 +#define LPTIM2_R 13696 +#define LPTIM3_R 13697 +#define LPTIM4_R 13698 +#define LPTIM5_R 13699 +#define SYSCFG_R 13707 +#define VREF_R 13709 +#define DTS_R 13712 +#define PMBCTRL_R 13713 +#define LTDC_R 13760 +#define DCMIPP_R 13761 +#define DDRPERFM_R 13768 +#define USBPHY_R 13776 +#define STGEN_R 13844 +#define USART1_R 13888 +#define USART2_R 13889 +#define SPI4_R 13890 +#define SPI5_R 13891 +#define I2C3_R 13892 +#define I2C4_R 13893 +#define I2C5_R 13894 +#define TIM12_R 13895 +#define TIM13_R 13896 +#define TIM14_R 13897 +#define TIM15_R 13898 +#define TIM16_R 13899 +#define TIM17_R 13900 +#define DMA1_R 13952 +#define DMA2_R 13953 +#define DMAMUX1_R 13954 +#define DMA3_R 13955 +#define DMAMUX2_R 13956 +#define ADC1_R 13957 +#define ADC2_R 13958 +#define USBO_R 13960 +#define GPIOA_R 14080 +#define GPIOB_R 14081 +#define GPIOC_R 14082 +#define GPIOD_R 14083 +#define GPIOE_R 14084 +#define GPIOF_R 14085 +#define GPIOG_R 14086 +#define GPIOH_R 14087 +#define GPIOI_R 14088 +#define TSC_R 14095 +#define PKA_R 14146 +#define SAES_R 14147 +#define CRYP1_R 14148 +#define HASH1_R 14149 +#define RNG1_R 14150 +#define AXIMC_R 14160 +#define MDMA_R 14208 +#define MCE_R 14209 +#define ETH1MAC_R 14218 +#define FMC_R 14220 +#define QSPI_R 14222 +#define SDMMC1_R 14224 +#define SDMMC2_R 14225 +#define CRC1_R 14228 +#define USBH_R 14232 +#define ETH2MAC_R 14238 + +/* SCMI reset domain identifiers */ +#define RST_SCMI_LTDC 0 +#define RST_SCMI_MDMA 1 + +#endif /* _DT_BINDINGS_STM32MP13_RESET_H_ */ -- cgit v1.2.3 From 8d50cdf8b8341770bc6367bce40c0c1bb0e1d5b3 Mon Sep 17 00:00:00 2001 From: Pawan Gupta Date: Thu, 19 May 2022 20:32:13 -0700 Subject: x86/speculation/mmio: Add sysfs reporting for Processor MMIO Stale Data Add the sysfs reporting file for Processor MMIO Stale Data vulnerability. It exposes the vulnerability and mitigation state similar to the existing files for the other hardware vulnerabilities. Signed-off-by: Pawan Gupta Signed-off-by: Borislav Petkov --- include/linux/cpu.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 54dc2f9a2d56..2c7477354744 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -65,6 +65,9 @@ extern ssize_t cpu_show_tsx_async_abort(struct device *dev, extern ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_mmio_stale_data(struct device *dev, + struct device_attribute *attr, + char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, -- cgit v1.2.3 From 1b3418ac6451b771b677e049b8a48d96e258e922 Mon Sep 17 00:00:00 2001 From: Yongqiang Niu Date: Wed, 6 Apr 2022 17:12:13 +0800 Subject: dt-bindings: gce: add the GCE header file for MT8186 Add the GCE header file to define GCE subsys ids, hardware event ids and constants for MT8186. Signed-off-by: Yongqiang Niu Acked-by: Rob Herring Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Jassi Brar --- include/dt-bindings/gce/mt8186-gce.h | 421 +++++++++++++++++++++++++++++++++++ 1 file changed, 421 insertions(+) create mode 100644 include/dt-bindings/gce/mt8186-gce.h (limited to 'include') diff --git a/include/dt-bindings/gce/mt8186-gce.h b/include/dt-bindings/gce/mt8186-gce.h new file mode 100644 index 000000000000..f12e3cb586ce --- /dev/null +++ b/include/dt-bindings/gce/mt8186-gce.h @@ -0,0 +1,421 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (C) 2022 MediaTek Inc. + * Author: Yongqiang Niu + */ + +#ifndef _DT_BINDINGS_GCE_MT8186_H +#define _DT_BINDINGS_GCE_MT8186_H + +/* assign timeout 0 also means default */ +#define CMDQ_NO_TIMEOUT 0xffffffff +#define CMDQ_TIMEOUT_DEFAULT 1000 + +/* GCE thread priority */ +#define CMDQ_THR_PRIO_LOWEST 0 +#define CMDQ_THR_PRIO_1 1 +#define CMDQ_THR_PRIO_2 2 +#define CMDQ_THR_PRIO_3 3 +#define CMDQ_THR_PRIO_4 4 +#define CMDQ_THR_PRIO_5 5 +#define CMDQ_THR_PRIO_6 6 +#define CMDQ_THR_PRIO_HIGHEST 7 + +/* CPR count in 32bit register */ +#define GCE_CPR_COUNT 1312 + +/* GCE subsys table */ +#define SUBSYS_1300XXXX 0 +#define SUBSYS_1400XXXX 1 +#define SUBSYS_1401XXXX 2 +#define SUBSYS_1402XXXX 3 +#define SUBSYS_1502XXXX 4 +#define SUBSYS_1582XXXX 5 +#define SUBSYS_1B00XXXX 6 +#define SUBSYS_1C00XXXX 7 +#define SUBSYS_1C10XXXX 8 +#define SUBSYS_1000XXXX 9 +#define SUBSYS_1001XXXX 10 +#define SUBSYS_1020XXXX 11 +#define SUBSYS_1021XXXX 12 +#define SUBSYS_1022XXXX 13 +#define SUBSYS_1023XXXX 14 +#define SUBSYS_1060XXXX 15 +#define SUBSYS_1602XXXX 16 +#define SUBSYS_1608XXXX 17 +#define SUBSYS_1700XXXX 18 +#define SUBSYS_1701XXXX 19 +#define SUBSYS_1702XXXX 20 +#define SUBSYS_1703XXXX 21 +#define SUBSYS_1706XXXX 22 +#define SUBSYS_1A00XXXX 23 +#define SUBSYS_1A01XXXX 24 +#define SUBSYS_1A02XXXX 25 +#define SUBSYS_1A03XXXX 26 +#define SUBSYS_1A04XXXX 27 +#define SUBSYS_1A05XXXX 28 +#define SUBSYS_1A06XXXX 29 +#define SUBSYS_NO_SUPPORT 99 + +/* GCE General Purpose Register (GPR) support + * Leave note for scenario usage here + */ +/* GCE: write mask */ +#define GCE_GPR_R00 0x00 +#define GCE_GPR_R01 0x01 +/* MDP: P1: JPEG dest */ +#define GCE_GPR_R02 0x02 +#define GCE_GPR_R03 0x03 +/* MDP: PQ color */ +#define GCE_GPR_R04 0x04 +/* MDP: 2D sharpness */ +#define GCE_GPR_R05 0x05 +/* DISP: poll esd */ +#define GCE_GPR_R06 0x06 +#define GCE_GPR_R07 0x07 +/* MDP: P4: 2D sharpness dst */ +#define GCE_GPR_R08 0x08 +#define GCE_GPR_R09 0x09 +/* VCU: poll with timeout for GPR timer */ +#define GCE_GPR_R10 0x0A +#define GCE_GPR_R11 0x0B +/* CMDQ: debug */ +#define GCE_GPR_R12 0x0C +#define GCE_GPR_R13 0x0D +/* CMDQ: P7: debug */ +#define GCE_GPR_R14 0x0E +#define GCE_GPR_R15 0x0F + +/* GCE hardware events */ +/* VDEC */ +#define CMDQ_EVENT_LINE_COUNT_THRESHOLD_INTERRUPT 0 +#define CMDQ_EVENT_VDEC_INT 1 +#define CMDQ_EVENT_VDEC_PAUSE 2 +#define CMDQ_EVENT_VDEC_DEC_ERROR 3 +#define CMDQ_EVENT_MDEC_TIMEOUT 4 +#define CMDQ_EVENT_DRAM_ACCESS_DONE 5 +#define CMDQ_EVENT_INI_FETCH_RDY 6 +#define CMDQ_EVENT_PROCESS_FLAG 7 +#define CMDQ_EVENT_SEARCH_START_CODE_DONE 8 +#define CMDQ_EVENT_REF_REORDER_DONE 9 +#define CMDQ_EVENT_WP_TBLE_DONE 10 +#define CMDQ_EVENT_COUNT_SRAM_CLR_DONE 11 +#define CMDQ_EVENT_GCE_CNT_OP_THRESHOLD 15 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_0 16 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_1 17 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_2 18 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_3 19 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_4 20 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_5 21 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_6 22 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_7 23 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_8 24 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_9 25 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_10 26 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_11 27 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_12 28 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_13 29 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_14 30 +#define CMDQ_EVENT_VDEC_MINI_MDP_EVENT_15 31 +#define CMDQ_EVENT_WPE_GCE_FRAME_DONE 32 + +/* CAM */ +#define CMDQ_EVENT_ISP_FRAME_DONE_A 65 +#define CMDQ_EVENT_ISP_FRAME_DONE_B 66 +#define CMDQ_EVENT_CAMSV1_PASS1_DONE 70 +#define CMDQ_EVENT_CAMSV2_PASS1_DONE 71 +#define CMDQ_EVENT_CAMSV3_PASS1_DONE 72 +#define CMDQ_EVENT_MRAW_0_PASS1_DONE 73 +#define CMDQ_EVENT_SENINF_CAM0_FIFO_FULL 75 +#define CMDQ_EVENT_SENINF_CAM1_FIFO_FULL 76 +#define CMDQ_EVENT_SENINF_CAM2_FIFO_FULL 77 +#define CMDQ_EVENT_SENINF_CAM3_FIFO_FULL 78 +#define CMDQ_EVENT_SENINF_CAM4_FIFO_FULL 79 +#define CMDQ_EVENT_SENINF_CAM5_FIFO_FULL 80 +#define CMDQ_EVENT_SENINF_CAM6_FIFO_FULL 81 +#define CMDQ_EVENT_SENINF_CAM7_FIFO_FULL 82 +#define CMDQ_EVENT_SENINF_CAM8_FIFO_FULL 83 +#define CMDQ_EVENT_SENINF_CAM9_FIFO_FULL 84 +#define CMDQ_EVENT_SENINF_CAM10_FIFO_FULL 85 +#define CMDQ_EVENT_SENINF_CAM11_FIFO_FULL 86 +#define CMDQ_EVENT_SENINF_CAM12_FIFO_FULL 87 +#define CMDQ_EVENT_TG_OVRUN_A_INT 88 +#define CMDQ_EVENT_DMA_R1_ERROR_A_INT 89 +#define CMDQ_EVENT_TG_OVRUN_B_INT 90 +#define CMDQ_EVENT_DMA_R1_ERROR_B_INT 91 +#define CMDQ_EVENT_TG_OVRUN_M0_INT 94 +#define CMDQ_EVENT_R1_ERROR_M0_INT 95 +#define CMDQ_EVENT_TG_GRABERR_M0_INT 96 +#define CMDQ_EVENT_TG_GRABERR_A_INT 98 +#define CMDQ_EVENT_CQ_VR_SNAP_A_INT 99 +#define CMDQ_EVENT_TG_GRABERR_B_INT 100 +#define CMDQ_EVENT_CQ_VR_SNAP_B_INT 101 +/* VENC */ +#define CMDQ_EVENT_VENC_CMDQ_FRAME_DONE 129 +#define CMDQ_EVENT_VENC_CMDQ_PAUSE_DONE 130 +#define CMDQ_EVENT_JPGENC_CMDQ_DONE 131 +#define CMDQ_EVENT_VENC_CMDQ_MB_DONE 132 +#define CMDQ_EVENT_VENC_CMDQ_128BYTE_CNT_DONE 133 +#define CMDQ_EVENT_VENC_CMDQ_PPS_DONE 136 +#define CMDQ_EVENT_VENC_CMDQ_SPS_DONE 137 +#define CMDQ_EVENT_VENC_CMDQ_VPS_DONE 138 +/* IPE */ +#define CMDQ_EVENT_FDVT_DONE 161 +#define CMDQ_EVENT_FE_DONE 162 +#define CMDQ_EVENT_RSC_DONE 163 +#define CMDQ_EVENT_DVS_DONE_ASYNC_SHOT 164 +#define CMDQ_EVENT_DVP_DONE_ASYNC_SHOT 165 +/* IMG2 */ +#define CMDQ_EVENT_GCE_IMG2_EVENT0 193 +#define CMDQ_EVENT_GCE_IMG2_EVENT1 194 +#define CMDQ_EVENT_GCE_IMG2_EVENT2 195 +#define CMDQ_EVENT_GCE_IMG2_EVENT3 196 +#define CMDQ_EVENT_GCE_IMG2_EVENT4 197 +#define CMDQ_EVENT_GCE_IMG2_EVENT5 198 +#define CMDQ_EVENT_GCE_IMG2_EVENT6 199 +#define CMDQ_EVENT_GCE_IMG2_EVENT7 200 +#define CMDQ_EVENT_GCE_IMG2_EVENT8 201 +#define CMDQ_EVENT_GCE_IMG2_EVENT9 202 +#define CMDQ_EVENT_GCE_IMG2_EVENT10 203 +#define CMDQ_EVENT_GCE_IMG2_EVENT11 204 +#define CMDQ_EVENT_GCE_IMG2_EVENT12 205 +#define CMDQ_EVENT_GCE_IMG2_EVENT13 206 +#define CMDQ_EVENT_GCE_IMG2_EVENT14 207 +#define CMDQ_EVENT_GCE_IMG2_EVENT15 208 +#define CMDQ_EVENT_GCE_IMG2_EVENT16 209 +#define CMDQ_EVENT_GCE_IMG2_EVENT17 210 +#define CMDQ_EVENT_GCE_IMG2_EVENT18 211 +#define CMDQ_EVENT_GCE_IMG2_EVENT19 212 +#define CMDQ_EVENT_GCE_IMG2_EVENT20 213 +#define CMDQ_EVENT_GCE_IMG2_EVENT21 214 +#define CMDQ_EVENT_GCE_IMG2_EVENT22 215 +#define CMDQ_EVENT_GCE_IMG2_EVENT23 216 +/* IMG1 */ +#define CMDQ_EVENT_GCE_IMG1_EVENT0 225 +#define CMDQ_EVENT_GCE_IMG1_EVENT1 226 +#define CMDQ_EVENT_GCE_IMG1_EVENT2 227 +#define CMDQ_EVENT_GCE_IMG1_EVENT3 228 +#define CMDQ_EVENT_GCE_IMG1_EVENT4 229 +#define CMDQ_EVENT_GCE_IMG1_EVENT5 230 +#define CMDQ_EVENT_GCE_IMG1_EVENT6 231 +#define CMDQ_EVENT_GCE_IMG1_EVENT7 232 +#define CMDQ_EVENT_GCE_IMG1_EVENT8 233 +#define CMDQ_EVENT_GCE_IMG1_EVENT9 234 +#define CMDQ_EVENT_GCE_IMG1_EVENT10 235 +#define CMDQ_EVENT_GCE_IMG1_EVENT11 236 +#define CMDQ_EVENT_GCE_IMG1_EVENT12 237 +#define CMDQ_EVENT_GCE_IMG1_EVENT13 238 +#define CMDQ_EVENT_GCE_IMG1_EVENT14 239 +#define CMDQ_EVENT_GCE_IMG1_EVENT15 240 +#define CMDQ_EVENT_GCE_IMG1_EVENT16 241 +#define CMDQ_EVENT_GCE_IMG1_EVENT17 242 +#define CMDQ_EVENT_GCE_IMG1_EVENT18 243 +#define CMDQ_EVENT_GCE_IMG1_EVENT19 244 +#define CMDQ_EVENT_GCE_IMG1_EVENT20 245 +#define CMDQ_EVENT_GCE_IMG1_EVENT21 246 +#define CMDQ_EVENT_GCE_IMG1_EVENT22 247 +#define CMDQ_EVENT_GCE_IMG1_EVENT23 248 +/* MDP */ +#define CMDQ_EVENT_MDP_RDMA0_SOF 256 +#define CMDQ_EVENT_MDP_RDMA1_SOF 257 +#define CMDQ_EVENT_MDP_AAL0_SOF 258 +#define CMDQ_EVENT_MDP_AAL1_SOF 259 +#define CMDQ_EVENT_MDP_HDR0_SOF 260 +#define CMDQ_EVENT_MDP_RSZ0_SOF 261 +#define CMDQ_EVENT_MDP_RSZ1_SOF 262 +#define CMDQ_EVENT_MDP_WROT0_SOF 263 +#define CMDQ_EVENT_MDP_WROT1_SOF 264 +#define CMDQ_EVENT_MDP_TDSHP0_SOF 265 +#define CMDQ_EVENT_MDP_TDSHP1_SOF 266 +#define CMDQ_EVENT_IMG_DL_RELAY0_SOF 267 +#define CMDQ_EVENT_IMG_DL_RELAY1_SOF 268 +#define CMDQ_EVENT_MDP_COLOR0_SOF 269 +#define CMDQ_EVENT_MDP_WROT3_FRAME_DONE 288 +#define CMDQ_EVENT_MDP_WROT2_FRAME_DONE 289 +#define CMDQ_EVENT_MDP_WROT1_FRAME_DONE 290 +#define CMDQ_EVENT_MDP_WROT0_FRAME_DONE 291 +#define CMDQ_EVENT_MDP_TDSHP3_FRAME_DONE 292 +#define CMDQ_EVENT_MDP_TDSHP2_FRAME_DONE 293 +#define CMDQ_EVENT_MDP_TDSHP1_FRAME_DONE 294 +#define CMDQ_EVENT_MDP_TDSHP0_FRAME_DONE 295 +#define CMDQ_EVENT_MDP_RSZ3_FRAME_DONE 296 +#define CMDQ_EVENT_MDP_RSZ2_FRAME_DONE 297 +#define CMDQ_EVENT_MDP_RSZ1_FRAME_DONE 298 +#define CMDQ_EVENT_MDP_RSZ0_FRAME_DONE 299 +#define CMDQ_EVENT_MDP_RDMA3_FRAME_DONE 300 +#define CMDQ_EVENT_MDP_RDMA2_FRAME_DONE 301 +#define CMDQ_EVENT_MDP_RDMA1_FRAME_DONE 302 +#define CMDQ_EVENT_MDP_RDMA0_FRAME_DONE 303 +#define CMDQ_EVENT_MDP_HDR1_FRAME_DONE 304 +#define CMDQ_EVENT_MDP_HDR0_FRAME_DONE 305 +#define CMDQ_EVENT_MDP_COLOR0_FRAME_DONE 306 +#define CMDQ_EVENT_MDP_AAL3_FRAME_DONE 307 +#define CMDQ_EVENT_MDP_AAL2_FRAME_DONE 308 +#define CMDQ_EVENT_MDP_AAL1_FRAME_DONE 309 +#define CMDQ_EVENT_MDP_AAL0_FRAME_DONE 310 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_0 320 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_1 321 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_2 322 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_3 323 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_4 324 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_5 325 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_6 326 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_7 327 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_8 328 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_9 329 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_10 330 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_11 331 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_12 332 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_13 333 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_14 334 +#define CMDQ_EVENT_MDP_STREAM_DONE_ENG_EVENT_15 335 +#define CMDQ_EVENT_MDP_WROT3_SW_RST_DONE_ENG_EVENT 336 +#define CMDQ_EVENT_MDP_WROT2_SW_RST_DONE_ENG_EVENT 337 +#define CMDQ_EVENT_MDP_WROT1_SW_RST_DONE_ENG_EVENT 338 +#define CMDQ_EVENT_MDP_WROT0_SW_RST_DONE_ENG_EVENT 339 +#define CMDQ_EVENT_MDP_RDMA3_SW_RST_DONE_ENG_EVENT 340 +#define CMDQ_EVENT_MDP_RDMA2_SW_RST_DONE_ENG_EVENT 341 +#define CMDQ_EVENT_MDP_RDMA1_SW_RST_DONE_ENG_EVENT 342 +#define CMDQ_EVENT_MDP_RDMA0_SW_RST_DONE_ENG_EVENT 343 +/* DISP */ +#define CMDQ_EVENT_DISP_OVL0_SOF 384 +#define CMDQ_EVENT_DISP_OVL0_2L_SOF 385 +#define CMDQ_EVENT_DISP_RDMA0_SOF 386 +#define CMDQ_EVENT_DISP_RSZ0_SOF 387 +#define CMDQ_EVENT_DISP_COLOR0_SOF 388 +#define CMDQ_EVENT_DISP_CCORR0_SOF 389 +#define CMDQ_EVENT_DISP_CCORR1_SOF 390 +#define CMDQ_EVENT_DISP_AAL0_SOF 391 +#define CMDQ_EVENT_DISP_GAMMA0_SOF 392 +#define CMDQ_EVENT_DISP_POSTMASK0_SOF 393 +#define CMDQ_EVENT_DISP_DITHER0_SOF 394 +#define CMDQ_EVENT_DISP_CM0_SOF 395 +#define CMDQ_EVENT_DISP_SPR0_SOF 396 +#define CMDQ_EVENT_DISP_DSC_WRAP0_SOF 397 +#define CMDQ_EVENT_DSI0_SOF 398 +#define CMDQ_EVENT_DISP_WDMA0_SOF 399 +#define CMDQ_EVENT_DISP_PWM0_SOF 400 +#define CMDQ_EVENT_DSI0_FRAME_DONE 410 +#define CMDQ_EVENT_DISP_WDMA0_FRAME_DONE 411 +#define CMDQ_EVENT_DISP_SPR0_FRAME_DONE 412 +#define CMDQ_EVENT_DISP_RSZ0_FRAME_DONE 413 +#define CMDQ_EVENT_DISP_RDMA0_FRAME_DONE 414 +#define CMDQ_EVENT_DISP_POSTMASK0_FRAME_DONE 415 +#define CMDQ_EVENT_DISP_OVL0_FRAME_DONE 416 +#define CMDQ_EVENT_DISP_OVL0_2L_FRAME_DONE 417 +#define CMDQ_EVENT_DISP_GAMMA0_FRAME_DONE 418 +#define CMDQ_EVENT_DISP_DSC_WRAP0_CORE0_FRAME_DONE 420 +#define CMDQ_EVENT_DISP_DITHER0_FRAME_DONE 421 +#define CMDQ_EVENT_DISP_COLOR0_FRAME_DONE 422 +#define CMDQ_EVENT_DISP_CM0_FRAME_DONE 423 +#define CMDQ_EVENT_DISP_CCORR1_FRAME_DONE 424 +#define CMDQ_EVENT_DISP_CCORR0_FRAME_DONE 425 +#define CMDQ_EVENT_DISP_AAL0_FRAME_DONE 426 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_0 434 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_1 435 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_2 436 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_3 437 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_4 438 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_5 439 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_6 440 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_7 441 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_8 442 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_9 443 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_10 444 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_11 445 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_12 446 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_13 447 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_14 448 +#define CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_15 449 +#define CMDQ_EVENT_DSI0_TE_ENG_EVENT 450 +#define CMDQ_EVENT_DSI0_IRQ_ENG_EVENT 451 +#define CMDQ_EVENT_DSI0_DONE_ENG_EVENT 452 +#define CMDQ_EVENT_DISP_WDMA0_SW_RST_DONE_ENG_EVENT 453 +#define CMDQ_EVENT_DISP_SMIASSERT_ENG_EVENT 454 +#define CMDQ_EVENT_DISP_POSTMASK0_RST_DONE_ENG_EVENT 455 +#define CMDQ_EVENT_DISP_OVL0_RST_DONE_ENG_EVENT 456 +#define CMDQ_EVENT_DISP_OVL0_2L_RST_DONE_ENG_EVENT 457 +#define CMDQ_EVENT_BUF_UNDERRUN_ENG_EVENT_0 458 +#define CMDQ_EVENT_BUF_UNDERRUN_ENG_EVENT_1 459 +#define CMDQ_EVENT_BUF_UNDERRUN_ENG_EVENT_2 460 +#define CMDQ_EVENT_BUF_UNDERRUN_ENG_EVENT_3 461 +#define CMDQ_EVENT_BUF_UNDERRUN_ENG_EVENT_4 462 +#define CMDQ_EVENT_BUF_UNDERRUN_ENG_EVENT_5 463 +#define CMDQ_EVENT_BUF_UNDERRUN_ENG_EVENT_6 464 +#define CMDQ_EVENT_BUF_UNDERRUN_ENG_EVENT_7 465 +#define CMDQ_EVENT_OUT_EVENT_0 898 + +/* CMDQ sw tokens + * Following definitions are gce sw token which may use by clients + * event operation API. + * Note that token 512 to 639 may set secure + */ + +/* end of hw event and begin of sw token */ +#define CMDQ_MAX_HW_EVENT 512 + +/* Config thread notify trigger thread */ +#define CMDQ_SYNC_TOKEN_CONFIG_DIRTY 640 +/* Trigger thread notify config thread */ +#define CMDQ_SYNC_TOKEN_STREAM_EOF 641 +/* Block Trigger thread until the ESD check finishes. */ +#define CMDQ_SYNC_TOKEN_ESD_EOF 642 +#define CMDQ_SYNC_TOKEN_STREAM_BLOCK 643 +/* check CABC setup finish */ +#define CMDQ_SYNC_TOKEN_CABC_EOF 644 + +/* Notify normal CMDQ there are some secure task done + * MUST NOT CHANGE, this token sync with secure world + */ +#define CMDQ_SYNC_SECURE_THR_EOF 647 + +/* CMDQ use sw token */ +#define CMDQ_SYNC_TOKEN_USER_0 649 +#define CMDQ_SYNC_TOKEN_USER_1 650 +#define CMDQ_SYNC_TOKEN_POLL_MONITOR 651 +#define CMDQ_SYNC_TOKEN_TPR_LOCK 652 + +/* ISP sw token */ +#define CMDQ_SYNC_TOKEN_MSS 665 +#define CMDQ_SYNC_TOKEN_MSF 666 + +/* DISP sw token */ +#define CMDQ_SYNC_TOKEN_SODI 671 + +/* GPR access tokens (for register backup) + * There are 15 32-bit GPR, 3 GPR form a set + * (64-bit for address, 32-bit for value) + * MUST NOT CHANGE, these tokens sync with MDP + */ +#define CMDQ_SYNC_TOKEN_GPR_SET_0 700 +#define CMDQ_SYNC_TOKEN_GPR_SET_1 701 +#define CMDQ_SYNC_TOKEN_GPR_SET_2 702 +#define CMDQ_SYNC_TOKEN_GPR_SET_3 703 +#define CMDQ_SYNC_TOKEN_GPR_SET_4 704 + +/* Resource lock event to control resource in GCE thread */ +#define CMDQ_SYNC_RESOURCE_WROT0 710 +#define CMDQ_SYNC_RESOURCE_WROT1 711 + +/* event for gpr timer, used in sleep and poll with timeout */ +#define CMDQ_TOKEN_GPR_TIMER_R0 994 +#define CMDQ_TOKEN_GPR_TIMER_R1 995 +#define CMDQ_TOKEN_GPR_TIMER_R2 996 +#define CMDQ_TOKEN_GPR_TIMER_R3 997 +#define CMDQ_TOKEN_GPR_TIMER_R4 998 +#define CMDQ_TOKEN_GPR_TIMER_R5 999 +#define CMDQ_TOKEN_GPR_TIMER_R6 1000 +#define CMDQ_TOKEN_GPR_TIMER_R7 1001 +#define CMDQ_TOKEN_GPR_TIMER_R8 1002 +#define CMDQ_TOKEN_GPR_TIMER_R9 1003 +#define CMDQ_TOKEN_GPR_TIMER_R10 1004 +#define CMDQ_TOKEN_GPR_TIMER_R11 1005 +#define CMDQ_TOKEN_GPR_TIMER_R12 1006 +#define CMDQ_TOKEN_GPR_TIMER_R13 1007 +#define CMDQ_TOKEN_GPR_TIMER_R14 1008 +#define CMDQ_TOKEN_GPR_TIMER_R15 1009 + +#define CMDQ_EVENT_MAX 0x3FF +/* CMDQ sw tokens END */ + +#endif -- cgit v1.2.3 From 58919326e72f63c380dc3271dd1cc8bdf1bbe3e4 Mon Sep 17 00:00:00 2001 From: Kartik Date: Thu, 14 Apr 2022 13:05:56 +0530 Subject: dt-bindings: tegra186-hsp: add type for shared mailboxes Tegra234 supports sending/receiving 32-bit and 128-bit data over a shared mailbox. Based on the data size to be used, clients need to specify the type of shared mailbox in the device tree. Add a macro for 128-bit shared mailbox. Mailbox clients can use this macro as a flag in device tree to enable 128-bit data support for a shared mailbox. Signed-off-by: Kartik Acked-by: Rob Herring Signed-off-by: Jassi Brar --- include/dt-bindings/mailbox/tegra186-hsp.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/mailbox/tegra186-hsp.h b/include/dt-bindings/mailbox/tegra186-hsp.h index 3bdec7a84d35..b9ccae2aa9e2 100644 --- a/include/dt-bindings/mailbox/tegra186-hsp.h +++ b/include/dt-bindings/mailbox/tegra186-hsp.h @@ -15,6 +15,11 @@ #define TEGRA_HSP_MBOX_TYPE_SS 0x2 #define TEGRA_HSP_MBOX_TYPE_AS 0x3 +/* + * These define the types of shared mailbox supported based on data size. + */ +#define TEGRA_HSP_MBOX_TYPE_SM_128BIT (1 << 8) + /* * These defines represent the bit associated with the given master ID in the * doorbell registers. -- cgit v1.2.3 From bb12dd42d20f5513a8d1da225232af0a0743fd79 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 24 Sep 2021 12:56:53 +0200 Subject: powerpc/powermac: constify device_node in of_irq_parse_oldworld() The of_irq_parse_oldworld() does not modify passed device_node so make it a pointer to const for safety. Drop the extern while modifying the line. Signed-off-by: Krzysztof Kozlowski Acked-by: Rob Herring Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20210924105653.46963-2-krzysztof.kozlowski@canonical.com --- include/linux/of_irq.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index aaf219bd0354..83fccd0c9bba 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -20,12 +20,12 @@ typedef int (*of_irq_init_cb_t)(struct device_node *, struct device_node *); #if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC) extern unsigned int of_irq_workarounds; extern struct device_node *of_irq_dflt_pic; -extern int of_irq_parse_oldworld(struct device_node *device, int index, - struct of_phandle_args *out_irq); +int of_irq_parse_oldworld(const struct device_node *device, int index, + struct of_phandle_args *out_irq); #else /* CONFIG_PPC32 && CONFIG_PPC_PMAC */ #define of_irq_workarounds (0) #define of_irq_dflt_pic (NULL) -static inline int of_irq_parse_oldworld(struct device_node *device, int index, +static inline int of_irq_parse_oldworld(const struct device_node *device, int index, struct of_phandle_args *out_irq) { return -EINVAL; -- cgit v1.2.3 From cd705ea857fdd859a9df09e8adda4cb4c906e8a2 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Fri, 1 Apr 2022 23:40:29 +0200 Subject: lib: add generic polynomial calculation Some temperature and voltage sensors use a polynomial to convert between raw data points and actual temperature or voltage. The polynomial is usually the result of a curve fitting of the diode characteristic. The BT1 PVT hwmon driver already uses such a polynonmial calculation which is rather generic. Move it to lib/ so other drivers can reuse it. Signed-off-by: Michael Walle Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20220401214032.3738095-2-michael@walle.cc Signed-off-by: Guenter Roeck --- include/linux/polynomial.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) create mode 100644 include/linux/polynomial.h (limited to 'include') diff --git a/include/linux/polynomial.h b/include/linux/polynomial.h new file mode 100644 index 000000000000..9e074a0bb6fa --- /dev/null +++ b/include/linux/polynomial.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 BAIKAL ELECTRONICS, JSC + */ + +#ifndef _POLYNOMIAL_H +#define _POLYNOMIAL_H + +/* + * struct polynomial_term - one term descriptor of a polynomial + * @deg: degree of the term. + * @coef: multiplication factor of the term. + * @divider: distributed divider per each degree. + * @divider_leftover: divider leftover, which couldn't be redistributed. + */ +struct polynomial_term { + unsigned int deg; + long coef; + long divider; + long divider_leftover; +}; + +/* + * struct polynomial - a polynomial descriptor + * @total_divider: total data divider. + * @terms: polynomial terms, last term must have degree of 0 + */ +struct polynomial { + long total_divider; + struct polynomial_term terms[]; +}; + +long polynomial_calc(const struct polynomial *poly, long data); + +#endif -- cgit v1.2.3 From e5d21072054fbadf41cd56062a3a14e447e8c22b Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Wed, 11 May 2022 06:29:59 -0700 Subject: hwmon: Introduce hwmon_device_register_for_thermal The thermal subsystem registers a hwmon driver without providing chip or sysfs group information. This is for legacy reasons and would be difficult to change. At the same time, we want to enforce that chip information is provided when registering a hwmon device using hwmon_device_register_with_info(). To enable this, introduce a special API for use only by the thermal subsystem. Acked-by: Rafael J . Wysocki Signed-off-by: Guenter Roeck --- include/linux/hwmon.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 4efaf06fd2b8..14325f93c6b2 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -450,6 +450,9 @@ hwmon_device_register_with_info(struct device *dev, const struct hwmon_chip_info *info, const struct attribute_group **extra_groups); struct device * +hwmon_device_register_for_thermal(struct device *dev, const char *name, + void *drvdata); +struct device * devm_hwmon_device_register_with_info(struct device *dev, const char *name, void *drvdata, const struct hwmon_chip_info *info, -- cgit v1.2.3 From 1359fcbe0f4aa2cd6ea684727a5a111eebeeed3a Mon Sep 17 00:00:00 2001 From: Ohad Sharabi Date: Wed, 23 Feb 2022 11:47:05 +0200 Subject: habanalabs: add DRAM default page size to HW info When using the device memory allocation API the user ought to know what is the default allocation page size. Signed-off-by: Ohad Sharabi Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay Signed-off-by: Greg Kroah-Hartman --- include/uapi/misc/habanalabs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 1d6b4f0c4159..ae2441521467 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -409,6 +409,7 @@ enum hl_server_type { * @dram_page_size: The DRAM physical page size. * @number_of_user_interrupts: The number of interrupts that are available to the userspace * application to use. Relevant for Gaudi2 and later. + * @device_mem_alloc_default_page_size: default page size used in device memory allocation. */ struct hl_info_hw_ip_info { __u64 sram_base_address; @@ -436,6 +437,8 @@ struct hl_info_hw_ip_info { __u32 reserved3; __u16 number_of_user_interrupts; __u16 pad2; + __u64 reserved4; + __u64 device_mem_alloc_default_page_size; }; struct hl_info_dram_usage { -- cgit v1.2.3 From 050a6f349a09d3cefb14f4114bfa047b2c5b2a65 Mon Sep 17 00:00:00 2001 From: Ohad Sharabi Date: Wed, 23 Feb 2022 13:37:08 +0200 Subject: habanalabs: add user API to get valid DRAM page sizes Future devices will support multiple device memory page sizes. In addition, an API for the user was added for it to be able to control the device memory allocation page size. This patch is a complementary patch to inform the user of the available page size supported by the device. Signed-off-by: Ohad Sharabi Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay Signed-off-by: Greg Kroah-Hartman --- include/uapi/misc/habanalabs.h | 63 +++++++++++++++++++++++++----------------- 1 file changed, 37 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index ae2441521467..f474e7fb018d 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -348,33 +348,35 @@ enum hl_server_type { * The address which accessing it caused the razwi. * Razwi initiator. * Razwi cause, was it a page fault or MMU access error. + * HL_INFO_DEV_MEM_ALLOC_PAGE_SIZES - Retrieve valid page sizes for device memory allocation */ -#define HL_INFO_HW_IP_INFO 0 -#define HL_INFO_HW_EVENTS 1 -#define HL_INFO_DRAM_USAGE 2 -#define HL_INFO_HW_IDLE 3 -#define HL_INFO_DEVICE_STATUS 4 -#define HL_INFO_DEVICE_UTILIZATION 6 -#define HL_INFO_HW_EVENTS_AGGREGATE 7 -#define HL_INFO_CLK_RATE 8 -#define HL_INFO_RESET_COUNT 9 -#define HL_INFO_TIME_SYNC 10 -#define HL_INFO_CS_COUNTERS 11 -#define HL_INFO_PCI_COUNTERS 12 -#define HL_INFO_CLK_THROTTLE_REASON 13 -#define HL_INFO_SYNC_MANAGER 14 -#define HL_INFO_TOTAL_ENERGY 15 -#define HL_INFO_PLL_FREQUENCY 16 -#define HL_INFO_POWER 17 -#define HL_INFO_OPEN_STATS 18 -#define HL_INFO_DRAM_REPLACED_ROWS 21 -#define HL_INFO_DRAM_PENDING_ROWS 22 -#define HL_INFO_LAST_ERR_OPEN_DEV_TIME 23 -#define HL_INFO_CS_TIMEOUT_EVENT 24 -#define HL_INFO_RAZWI_EVENT 25 - -#define HL_INFO_VERSION_MAX_LEN 128 -#define HL_INFO_CARD_NAME_MAX_LEN 16 +#define HL_INFO_HW_IP_INFO 0 +#define HL_INFO_HW_EVENTS 1 +#define HL_INFO_DRAM_USAGE 2 +#define HL_INFO_HW_IDLE 3 +#define HL_INFO_DEVICE_STATUS 4 +#define HL_INFO_DEVICE_UTILIZATION 6 +#define HL_INFO_HW_EVENTS_AGGREGATE 7 +#define HL_INFO_CLK_RATE 8 +#define HL_INFO_RESET_COUNT 9 +#define HL_INFO_TIME_SYNC 10 +#define HL_INFO_CS_COUNTERS 11 +#define HL_INFO_PCI_COUNTERS 12 +#define HL_INFO_CLK_THROTTLE_REASON 13 +#define HL_INFO_SYNC_MANAGER 14 +#define HL_INFO_TOTAL_ENERGY 15 +#define HL_INFO_PLL_FREQUENCY 16 +#define HL_INFO_POWER 17 +#define HL_INFO_OPEN_STATS 18 +#define HL_INFO_DRAM_REPLACED_ROWS 21 +#define HL_INFO_DRAM_PENDING_ROWS 22 +#define HL_INFO_LAST_ERR_OPEN_DEV_TIME 23 +#define HL_INFO_CS_TIMEOUT_EVENT 24 +#define HL_INFO_RAZWI_EVENT 25 +#define HL_INFO_DEV_MEM_ALLOC_PAGE_SIZES 26 + +#define HL_INFO_VERSION_MAX_LEN 128 +#define HL_INFO_CARD_NAME_MAX_LEN 16 /** * struct hl_info_hw_ip_info - hardware information on various IPs in the ASIC @@ -643,6 +645,15 @@ struct hl_info_razwi_event { __u8 pad[2]; }; +/** + * struct hl_info_dev_memalloc_page_sizes - valid page sizes in device mem alloc information. + * @page_order_bitmask: bitmap in which a set bit represents the order of the supported page size + * (e.g. 0x2100000 means that 1MB and 32MB pages are supported). + */ +struct hl_info_dev_memalloc_page_sizes { + __u64 page_order_bitmask; +}; + enum gaudi_dcores { HL_GAUDI_WS_DCORE, HL_GAUDI_WN_DCORE, -- cgit v1.2.3 From fdec56c1a416c6947b1db22617da15cb89f46c6c Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Thu, 3 Mar 2022 09:43:10 +0200 Subject: habanalabs: expose compute ctx status through info ioctl In order for the user to know if he can try and open device, we expose the compute ctx state. The user can now know if the context is used by another process or whether the device is still ongoing through cleanup or reset and will be available soon. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay Signed-off-by: Greg Kroah-Hartman --- include/uapi/misc/habanalabs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index f474e7fb018d..ca2af5f98056 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -543,10 +543,15 @@ struct hl_pll_frequency_info { * struct hl_open_stats_info - device open statistics information * @open_counter: ever growing counter, increased on each successful dev open * @last_open_period_ms: duration (ms) device was open last time + * @is_compute_ctx_active: Whether there is an active compute context executing + * @compute_ctx_in_release: true if the current compute context is being released */ struct hl_open_stats_info { __u64 open_counter; __u64 last_open_period_ms; + __u8 is_compute_ctx_active; + __u8 compute_ctx_in_release; + __u8 pad[6]; }; /** -- cgit v1.2.3 From 5d1a0de2c778f369970dd50f6713e95068926a8b Mon Sep 17 00:00:00 2001 From: Ohad Sharabi Date: Sun, 10 Apr 2022 11:19:42 +0300 Subject: habanalabs: add prefetch flag to the MAP operation This patch let the user decide whether the translations done in the page tables will be fetched directly to the STLB right after the map. We want to let the user control whether to perform prefetch upon map operation. To do so a memory flag was added, to be used in the MAP ioctl, called HL_MEM_PREFETCH and if set- the mappings will be fetched directly to the STLB after map operation. Signed-off-by: Ohad Sharabi Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay Signed-off-by: Greg Kroah-Hartman --- include/uapi/misc/habanalabs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index ca2af5f98056..3576bf2b4841 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -1134,6 +1134,7 @@ union hl_wait_cs_args { #define HL_MEM_SHARED 0x2 #define HL_MEM_USERPTR 0x4 #define HL_MEM_FORCE_HINT 0x8 +#define HL_MEM_PREFETCH 0x40 /** * structure hl_mem_in - structure that handle input args for memory IOCTL -- cgit v1.2.3 From 422ef171038d4855ffe938137039a8f3b3e84293 Mon Sep 17 00:00:00 2001 From: Tal Cohen Date: Thu, 28 Apr 2022 13:45:18 +0300 Subject: habanalabs: add support for notification via eventfd The driver will be able to send notification events towards a user process, using user's registered event file descriptor. The driver uses the notification mechanism to inform the user about an occurred event. A user thread can wait until a notification is received from the driver. The driver stores the occurred event until the user reads it, using HL_INFO_GET_EVENTS - new ioctl opcode in the INFO ioctl. Gaudi specific implementation includes sending a notification on a TPC assertion event that is received from f/w. Signed-off-by: Tal Cohen Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay Signed-off-by: Greg Kroah-Hartman --- include/uapi/misc/habanalabs.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 3576bf2b4841..52540d5b4fc9 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -349,6 +349,9 @@ enum hl_server_type { * Razwi initiator. * Razwi cause, was it a page fault or MMU access error. * HL_INFO_DEV_MEM_ALLOC_PAGE_SIZES - Retrieve valid page sizes for device memory allocation + * HL_INFO_REGISTER_EVENTFD - Register eventfd for event notifications. + * HL_INFO_UNREGISTER_EVENTFD - Unregister eventfd + * HL_INFO_GET_EVENTS - Retrieve the last occurred events */ #define HL_INFO_HW_IP_INFO 0 #define HL_INFO_HW_EVENTS 1 @@ -374,6 +377,9 @@ enum hl_server_type { #define HL_INFO_CS_TIMEOUT_EVENT 24 #define HL_INFO_RAZWI_EVENT 25 #define HL_INFO_DEV_MEM_ALLOC_PAGE_SIZES 26 +#define HL_INFO_REGISTER_EVENTFD 28 +#define HL_INFO_UNREGISTER_EVENTFD 29 +#define HL_INFO_GET_EVENTS 30 #define HL_INFO_VERSION_MAX_LEN 128 #define HL_INFO_CARD_NAME_MAX_LEN 16 @@ -679,6 +685,7 @@ enum gaudi_dcores { * @period_ms: Period value, in milliseconds, for utilization rate in range 100ms - 1000ms in 100 ms * resolution. Currently not in use. * @pll_index: Index as defined in hl__pll_index enumeration. + * @eventfd: event file descriptor for event notifications. * @pad: Padding to 64 bit. */ struct hl_info_args { @@ -691,6 +698,7 @@ struct hl_info_args { __u32 ctx_id; __u32 period_ms; __u32 pll_index; + __u32 eventfd; }; __u32 pad; @@ -1390,6 +1398,13 @@ struct hl_debug_args { __u32 ctx_id; }; +/* + * Notifier event values - for the notification mechanism and the HL_INFO_GET_EVENTS command + * + * HL_NOTIFIER_EVENT_TPC_ASSERT - Indicates TPC assert event + */ +#define HL_NOTIFIER_EVENT_TPC_ASSERT (1 << 0) + /* * Various information operations such as: * - H/W IP information -- cgit v1.2.3 From cc4e7fa549cb69c18bc2ba7209df373ca06749e3 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Sat, 21 May 2022 13:10:53 +0200 Subject: net: qed: fix typos in comments Spelling mistakes (triple letters) in comments. Detected with the help of Coccinelle. Signed-off-by: Julia Lawall Signed-off-by: David S. Miller --- include/linux/qed/qed_fcoe_if.h | 4 ++-- include/linux/qed/qed_iscsi_if.h | 4 ++-- include/linux/qed/qed_nvmetcp_if.h | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/qed/qed_fcoe_if.h b/include/linux/qed/qed_fcoe_if.h index 16752eca5cbd..90e3045b2dcb 100644 --- a/include/linux/qed/qed_fcoe_if.h +++ b/include/linux/qed/qed_fcoe_if.h @@ -76,7 +76,7 @@ void qed_fcoe_set_pf_params(struct qed_dev *cdev, * @fill_dev_info: fills FCoE specific information * @param cdev * @param info - * @return 0 on sucesss, otherwise error value. + * @return 0 on success, otherwise error value. * @register_ops: register FCoE operations * @param cdev * @param ops - specified using qed_iscsi_cb_ops @@ -96,7 +96,7 @@ void qed_fcoe_set_pf_params(struct qed_dev *cdev, * connection. * @param p_doorbell - qed will fill the address of the * doorbell. - * return 0 on sucesss, otherwise error value. + * return 0 on success, otherwise error value. * @release_conn: release a previously acquired fcoe connection * @param cdev * @param handle - the connection handle. diff --git a/include/linux/qed/qed_iscsi_if.h b/include/linux/qed/qed_iscsi_if.h index 494cdc3cd840..fbf7973ae9ba 100644 --- a/include/linux/qed/qed_iscsi_if.h +++ b/include/linux/qed/qed_iscsi_if.h @@ -133,7 +133,7 @@ struct qed_iscsi_cb_ops { * @fill_dev_info: fills iSCSI specific information * @param cdev * @param info - * @return 0 on sucesss, otherwise error value. + * @return 0 on success, otherwise error value. * @register_ops: register iscsi operations * @param cdev * @param ops - specified using qed_iscsi_cb_ops @@ -152,7 +152,7 @@ struct qed_iscsi_cb_ops { * connection. * @param p_doorbell - qed will fill the address of the * doorbell. - * @return 0 on sucesss, otherwise error value. + * @return 0 on success, otherwise error value. * @release_conn: release a previously acquired iscsi connection * @param cdev * @param handle - the connection handle. diff --git a/include/linux/qed/qed_nvmetcp_if.h b/include/linux/qed/qed_nvmetcp_if.h index 1d51df347560..bbfbfba51f37 100644 --- a/include/linux/qed/qed_nvmetcp_if.h +++ b/include/linux/qed/qed_nvmetcp_if.h @@ -132,7 +132,7 @@ struct nvmetcp_task_params { * connection. * @param p_doorbell - qed will fill the address of the * doorbell. - * @return 0 on sucesss, otherwise error value. + * @return 0 on success, otherwise error value. * @release_conn: release a previously acquired nvmetcp connection * @param cdev * @param handle - the connection handle. -- cgit v1.2.3 From a05754295e01f006a651eec759c5dbe682ef6cef Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 21 May 2022 08:45:22 +0100 Subject: rxrpc: Use refcount_t rather than atomic_t Move to using refcount_t rather than atomic_t for refcounts in rxrpc. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org Signed-off-by: David S. Miller --- include/trace/events/rxrpc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 4a3ab0ed6e06..cdb28976641b 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -583,7 +583,7 @@ TRACE_EVENT(rxrpc_client, TP_fast_assign( __entry->conn = conn ? conn->debug_id : 0; __entry->channel = channel; - __entry->usage = conn ? atomic_read(&conn->usage) : -2; + __entry->usage = conn ? refcount_read(&conn->ref) : -2; __entry->op = op; __entry->cid = conn ? conn->proto.cid : 0; ), -- cgit v1.2.3 From ad25f5cb39872ca14bcbe00816ae65c22fe04b89 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 21 May 2022 08:45:28 +0100 Subject: rxrpc: Fix locking issue There's a locking issue with the per-netns list of calls in rxrpc. The pieces of code that add and remove a call from the list use write_lock() and the calls procfile uses read_lock() to access it. However, the timer callback function may trigger a removal by trying to queue a call for processing and finding that it's already queued - at which point it has a spare refcount that it has to do something with. Unfortunately, if it puts the call and this reduces the refcount to 0, the call will be removed from the list. Unfortunately, since the _bh variants of the locking functions aren't used, this can deadlock. ================================ WARNING: inconsistent lock state 5.18.0-rc3-build4+ #10 Not tainted -------------------------------- inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. ksoftirqd/2/25 [HC0[0]:SC1[1]:HE1:SE0] takes: ffff888107ac4038 (&rxnet->call_lock){+.?.}-{2:2}, at: rxrpc_put_call+0x103/0x14b {SOFTIRQ-ON-W} state was registered at: ... Possible unsafe locking scenario: CPU0 ---- lock(&rxnet->call_lock); lock(&rxnet->call_lock); *** DEADLOCK *** 1 lock held by ksoftirqd/2/25: #0: ffff8881008ffdb0 ((&call->timer)){+.-.}-{0:0}, at: call_timer_fn+0x5/0x23d Changes ======= ver #2) - Changed to using list_next_rcu() rather than rcu_dereference() directly. Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both") Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org Signed-off-by: David S. Miller --- include/linux/list.h | 10 ++++++++++ include/linux/seq_file.h | 4 ++++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/list.h b/include/linux/list.h index c147eeb2d39d..57e8b559cdf6 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -605,6 +605,16 @@ static inline void list_splice_tail_init(struct list_head *list, #define list_for_each(pos, head) \ for (pos = (head)->next; !list_is_head(pos, (head)); pos = pos->next) +/** + * list_for_each_rcu - Iterate over a list in an RCU-safe fashion + * @pos: the &struct list_head to use as a loop cursor. + * @head: the head for your list. + */ +#define list_for_each_rcu(pos, head) \ + for (pos = rcu_dereference((head)->next); \ + !list_is_head(pos, (head)); \ + pos = rcu_dereference(pos->next)) + /** * list_for_each_continue - continue iteration over a list * @pos: the &struct list_head to use as a loop cursor. diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 60820ab511d2..bd023dd38ae6 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -277,6 +277,10 @@ extern struct list_head *seq_list_start_head(struct list_head *head, extern struct list_head *seq_list_next(void *v, struct list_head *head, loff_t *ppos); +extern struct list_head *seq_list_start_rcu(struct list_head *head, loff_t pos); +extern struct list_head *seq_list_start_head_rcu(struct list_head *head, loff_t pos); +extern struct list_head *seq_list_next_rcu(void *v, struct list_head *head, loff_t *ppos); + /* * Helpers for iteration over hlist_head-s in seq_files */ -- cgit v1.2.3 From dc9fd093b2ebabc25a5d7d0dd5bdfdd6c878e0bf Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 21 May 2022 08:45:35 +0100 Subject: rxrpc: Automatically generate trace tag enums Automatically generate trace tag enums from the symbol -> string mapping tables rather than having the enums as well, thereby reducing duplicated data. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org Signed-off-by: David S. Miller --- include/trace/events/rxrpc.h | 261 +++++++------------------------------------ 1 file changed, 42 insertions(+), 219 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index cdb28976641b..66915b872a44 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -13,215 +13,6 @@ #include #include -/* - * Define enums for tracing information. - * - * These should all be kept sorted, making it easier to match the string - * mapping tables further on. - */ -#ifndef __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY -#define __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY - -enum rxrpc_skb_trace { - rxrpc_skb_cleaned, - rxrpc_skb_freed, - rxrpc_skb_got, - rxrpc_skb_lost, - rxrpc_skb_new, - rxrpc_skb_purged, - rxrpc_skb_received, - rxrpc_skb_rotated, - rxrpc_skb_seen, - rxrpc_skb_unshared, - rxrpc_skb_unshared_nomem, -}; - -enum rxrpc_local_trace { - rxrpc_local_got, - rxrpc_local_new, - rxrpc_local_processing, - rxrpc_local_put, - rxrpc_local_queued, -}; - -enum rxrpc_peer_trace { - rxrpc_peer_got, - rxrpc_peer_new, - rxrpc_peer_processing, - rxrpc_peer_put, -}; - -enum rxrpc_conn_trace { - rxrpc_conn_got, - rxrpc_conn_new_client, - rxrpc_conn_new_service, - rxrpc_conn_put_client, - rxrpc_conn_put_service, - rxrpc_conn_queued, - rxrpc_conn_reap_service, - rxrpc_conn_seen, -}; - -enum rxrpc_client_trace { - rxrpc_client_activate_chans, - rxrpc_client_alloc, - rxrpc_client_chan_activate, - rxrpc_client_chan_disconnect, - rxrpc_client_chan_pass, - rxrpc_client_chan_wait_failed, - rxrpc_client_cleanup, - rxrpc_client_discard, - rxrpc_client_duplicate, - rxrpc_client_exposed, - rxrpc_client_replace, - rxrpc_client_to_active, - rxrpc_client_to_idle, -}; - -enum rxrpc_call_trace { - rxrpc_call_connected, - rxrpc_call_error, - rxrpc_call_got, - rxrpc_call_got_kernel, - rxrpc_call_got_timer, - rxrpc_call_got_userid, - rxrpc_call_new_client, - rxrpc_call_new_service, - rxrpc_call_put, - rxrpc_call_put_kernel, - rxrpc_call_put_noqueue, - rxrpc_call_put_notimer, - rxrpc_call_put_timer, - rxrpc_call_put_userid, - rxrpc_call_queued, - rxrpc_call_queued_ref, - rxrpc_call_release, - rxrpc_call_seen, -}; - -enum rxrpc_transmit_trace { - rxrpc_transmit_await_reply, - rxrpc_transmit_end, - rxrpc_transmit_queue, - rxrpc_transmit_queue_last, - rxrpc_transmit_rotate, - rxrpc_transmit_rotate_last, - rxrpc_transmit_wait, -}; - -enum rxrpc_receive_trace { - rxrpc_receive_end, - rxrpc_receive_front, - rxrpc_receive_incoming, - rxrpc_receive_queue, - rxrpc_receive_queue_last, - rxrpc_receive_rotate, -}; - -enum rxrpc_recvmsg_trace { - rxrpc_recvmsg_cont, - rxrpc_recvmsg_data_return, - rxrpc_recvmsg_dequeue, - rxrpc_recvmsg_enter, - rxrpc_recvmsg_full, - rxrpc_recvmsg_hole, - rxrpc_recvmsg_next, - rxrpc_recvmsg_requeue, - rxrpc_recvmsg_return, - rxrpc_recvmsg_terminal, - rxrpc_recvmsg_to_be_accepted, - rxrpc_recvmsg_wait, -}; - -enum rxrpc_rtt_tx_trace { - rxrpc_rtt_tx_cancel, - rxrpc_rtt_tx_data, - rxrpc_rtt_tx_no_slot, - rxrpc_rtt_tx_ping, -}; - -enum rxrpc_rtt_rx_trace { - rxrpc_rtt_rx_cancel, - rxrpc_rtt_rx_lost, - rxrpc_rtt_rx_obsolete, - rxrpc_rtt_rx_ping_response, - rxrpc_rtt_rx_requested_ack, -}; - -enum rxrpc_timer_trace { - rxrpc_timer_begin, - rxrpc_timer_exp_ack, - rxrpc_timer_exp_hard, - rxrpc_timer_exp_idle, - rxrpc_timer_exp_keepalive, - rxrpc_timer_exp_lost_ack, - rxrpc_timer_exp_normal, - rxrpc_timer_exp_ping, - rxrpc_timer_exp_resend, - rxrpc_timer_expired, - rxrpc_timer_init_for_reply, - rxrpc_timer_init_for_send_reply, - rxrpc_timer_restart, - rxrpc_timer_set_for_ack, - rxrpc_timer_set_for_hard, - rxrpc_timer_set_for_idle, - rxrpc_timer_set_for_keepalive, - rxrpc_timer_set_for_lost_ack, - rxrpc_timer_set_for_normal, - rxrpc_timer_set_for_ping, - rxrpc_timer_set_for_resend, - rxrpc_timer_set_for_send, -}; - -enum rxrpc_propose_ack_trace { - rxrpc_propose_ack_client_tx_end, - rxrpc_propose_ack_input_data, - rxrpc_propose_ack_ping_for_check_life, - rxrpc_propose_ack_ping_for_keepalive, - rxrpc_propose_ack_ping_for_lost_ack, - rxrpc_propose_ack_ping_for_lost_reply, - rxrpc_propose_ack_ping_for_params, - rxrpc_propose_ack_processing_op, - rxrpc_propose_ack_respond_to_ack, - rxrpc_propose_ack_respond_to_ping, - rxrpc_propose_ack_retry_tx, - rxrpc_propose_ack_rotate_rx, - rxrpc_propose_ack_terminal_ack, -}; - -enum rxrpc_propose_ack_outcome { - rxrpc_propose_ack_subsume, - rxrpc_propose_ack_update, - rxrpc_propose_ack_use, -}; - -enum rxrpc_congest_change { - rxrpc_cong_begin_retransmission, - rxrpc_cong_cleared_nacks, - rxrpc_cong_new_low_nack, - rxrpc_cong_no_change, - rxrpc_cong_progress, - rxrpc_cong_retransmit_again, - rxrpc_cong_rtt_window_end, - rxrpc_cong_saw_nack, -}; - -enum rxrpc_tx_point { - rxrpc_tx_point_call_abort, - rxrpc_tx_point_call_ack, - rxrpc_tx_point_call_data_frag, - rxrpc_tx_point_call_data_nofrag, - rxrpc_tx_point_call_final_resend, - rxrpc_tx_point_conn_abort, - rxrpc_tx_point_rxkad_challenge, - rxrpc_tx_point_rxkad_response, - rxrpc_tx_point_reject, - rxrpc_tx_point_version_keepalive, - rxrpc_tx_point_version_reply, -}; - -#endif /* end __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY */ - /* * Declare tracing information enums and their string mappings for display. */ @@ -451,6 +242,36 @@ enum rxrpc_tx_point { EM(rxrpc_tx_point_version_keepalive, "VerKeepalive") \ E_(rxrpc_tx_point_version_reply, "VerReply") +/* + * Generate enums for tracing information. + */ +#ifndef __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY +#define __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY + +#undef EM +#undef E_ +#define EM(a, b) a, +#define E_(a, b) a + +enum rxrpc_call_trace { rxrpc_call_traces } __mode(byte); +enum rxrpc_client_trace { rxrpc_client_traces } __mode(byte); +enum rxrpc_congest_change { rxrpc_congest_changes } __mode(byte); +enum rxrpc_conn_trace { rxrpc_conn_traces } __mode(byte); +enum rxrpc_local_trace { rxrpc_local_traces } __mode(byte); +enum rxrpc_peer_trace { rxrpc_peer_traces } __mode(byte); +enum rxrpc_propose_ack_outcome { rxrpc_propose_ack_outcomes } __mode(byte); +enum rxrpc_propose_ack_trace { rxrpc_propose_ack_traces } __mode(byte); +enum rxrpc_receive_trace { rxrpc_receive_traces } __mode(byte); +enum rxrpc_recvmsg_trace { rxrpc_recvmsg_traces } __mode(byte); +enum rxrpc_rtt_rx_trace { rxrpc_rtt_rx_traces } __mode(byte); +enum rxrpc_rtt_tx_trace { rxrpc_rtt_tx_traces } __mode(byte); +enum rxrpc_skb_trace { rxrpc_skb_traces } __mode(byte); +enum rxrpc_timer_trace { rxrpc_timer_traces } __mode(byte); +enum rxrpc_transmit_trace { rxrpc_transmit_traces } __mode(byte); +enum rxrpc_tx_point { rxrpc_tx_points } __mode(byte); + +#endif /* end __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY */ + /* * Export enum symbols via userspace. */ @@ -459,21 +280,21 @@ enum rxrpc_tx_point { #define EM(a, b) TRACE_DEFINE_ENUM(a); #define E_(a, b) TRACE_DEFINE_ENUM(a); -rxrpc_skb_traces; -rxrpc_local_traces; -rxrpc_conn_traces; -rxrpc_client_traces; rxrpc_call_traces; -rxrpc_transmit_traces; +rxrpc_client_traces; +rxrpc_congest_changes; +rxrpc_congest_modes; +rxrpc_conn_traces; +rxrpc_local_traces; +rxrpc_propose_ack_outcomes; +rxrpc_propose_ack_traces; rxrpc_receive_traces; rxrpc_recvmsg_traces; -rxrpc_rtt_tx_traces; rxrpc_rtt_rx_traces; +rxrpc_rtt_tx_traces; +rxrpc_skb_traces; rxrpc_timer_traces; -rxrpc_propose_ack_traces; -rxrpc_propose_ack_outcomes; -rxrpc_congest_modes; -rxrpc_congest_changes; +rxrpc_transmit_traces; rxrpc_tx_points; /* @@ -1574,6 +1395,8 @@ TRACE_EVENT(rxrpc_rx_discard_ack, __entry->call_ackr_prev) ); +#undef EM +#undef E_ #endif /* _TRACE_RXRPC_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 9a3dedcf18096e8f7f22b8777d78c4acfdea1651 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 21 May 2022 09:03:31 +0100 Subject: rxrpc: Fix decision on when to generate an IDLE ACK Fix the decision on when to generate an IDLE ACK by keeping a count of the number of packets we've received, but not yet soft-ACK'd, and the number of packets we've processed, but not yet hard-ACK'd, rather than trying to keep track of which DATA sequence numbers correspond to those points. We then generate an ACK when either counter exceeds 2. The counters are both cleared when we transcribe the information into any sort of ACK packet for transmission. IDLE and DELAY ACKs are skipped if both counters are 0 (ie. no change). Fixes: 805b21b929e2 ("rxrpc: Send an ACK after every few DATA packets we receive") Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org Signed-off-by: David S. Miller --- include/trace/events/rxrpc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 4a3ab0ed6e06..1c714336b863 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -1509,7 +1509,7 @@ TRACE_EVENT(rxrpc_call_reset, __entry->call_serial = call->rx_serial; __entry->conn_serial = call->conn->hi_serial; __entry->tx_seq = call->tx_hard_ack; - __entry->rx_seq = call->ackr_seen; + __entry->rx_seq = call->rx_hard_ack; ), TP_printk("c=%08x %08x:%08x r=%08x/%08x tx=%08x rx=%08x", -- cgit v1.2.3 From c304eddcecfe2513ff98ce3ae97d1c196d82ba08 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 19 May 2022 13:20:54 -0700 Subject: net: wrap the wireless pointers in struct net_device in an ifdef Most protocol-specific pointers in struct net_device are under a respective ifdef. Wireless is the notable exception. Since there's a sizable number of custom-built kernels for datacenter workloads which don't build wireless it seems reasonable to ifdefy those pointers as well. While at it move IPv4 and IPv6 pointers up, those are special for obvious reasons. Acked-by: Johannes Berg Acked-by: Stefan Schmidt # ieee802154 Acked-by: Sven Eckelmann Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++++-- include/net/cfg80211.h | 2 ++ include/net/cfg802154.h | 2 ++ 3 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1ce91cb8074a..f615a66c89e9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2119,6 +2119,8 @@ struct net_device { /* Protocol-specific pointers */ + struct in_device __rcu *ip_ptr; + struct inet6_dev __rcu *ip6_ptr; #if IS_ENABLED(CONFIG_VLAN_8021Q) struct vlan_info __rcu *vlan_info; #endif @@ -2131,16 +2133,18 @@ struct net_device { #if IS_ENABLED(CONFIG_ATALK) void *atalk_ptr; #endif - struct in_device __rcu *ip_ptr; #if IS_ENABLED(CONFIG_DECNET) struct dn_dev __rcu *dn_ptr; #endif - struct inet6_dev __rcu *ip6_ptr; #if IS_ENABLED(CONFIG_AX25) void *ax25_ptr; #endif +#if IS_ENABLED(CONFIG_CFG80211) struct wireless_dev *ieee80211_ptr; +#endif +#if IS_ENABLED(CONFIG_IEEE802154) || IS_ENABLED(CONFIG_6LOWPAN) struct wpan_dev *ieee802154_ptr; +#endif #if IS_ENABLED(CONFIG_MPLS_ROUTING) struct mpls_dev __rcu *mpls_ptr; #endif diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index cc8a9880b9d6..6d02e12e4702 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -8006,7 +8006,9 @@ int cfg80211_register_netdevice(struct net_device *dev); */ static inline void cfg80211_unregister_netdevice(struct net_device *dev) { +#if IS_ENABLED(CONFIG_CFG80211) cfg80211_unregister_wdev(dev->ieee80211_ptr); +#endif } /** diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 85f9e8417688..d8d8719315fd 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -373,6 +373,7 @@ struct wpan_dev { #define to_phy(_dev) container_of(_dev, struct wpan_phy, dev) +#if IS_ENABLED(CONFIG_IEEE802154) || IS_ENABLED(CONFIG_6LOWPAN) static inline int wpan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, const struct ieee802154_addr *daddr, @@ -383,6 +384,7 @@ wpan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, return wpan_dev->header_ops->create(skb, dev, daddr, saddr, len); } +#endif struct wpan_phy * wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size); -- cgit v1.2.3 From 97d6fb1b48f5e6f6d58028593defe8a23641b0b4 Mon Sep 17 00:00:00 2001 From: Yuezhang Mo Date: Tue, 12 Apr 2022 12:23:10 +0900 Subject: block: add sync_blockdev_range() sync_blockdev_range() is to support syncing multiple sectors with as few block device requests as possible, it is helpful to make the block device to give full play to its performance. Signed-off-by: Yuezhang Mo Suggested-by: Christoph Hellwig Reviewed-by: Andy Wu Reviewed-by: Aoyama Wataru Reviewed-by: Christoph Hellwig Reviewed-by: Jens Axboe Acked-by: Sungjong Seo Signed-off-by: Namjae Jeon --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 60d016138997..331cc6918ee9 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1547,6 +1547,7 @@ int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, #ifdef CONFIG_BLOCK void invalidate_bdev(struct block_device *bdev); int sync_blockdev(struct block_device *bdev); +int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend); int sync_blockdev_nowait(struct block_device *bdev); void sync_bdevs(bool wait); void printk_all_partitions(void); -- cgit v1.2.3 From a72e23dd679c632bcf6ab47a3a1a58c1e777713a Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 22 May 2022 00:37:40 +0300 Subject: net: dsa: felix: update bridge fwd mask from ocelot lib when changing tag_8021q CPU Add more logic to ocelot_port_{,un}set_dsa_8021q_cpu() from the ocelot switch lib by encapsulating the ocelot_apply_bridge_fwd_mask() call that felix used to have. This is necessary because the CPU port change procedure will also need to do this, and it's good to reduce code duplication by having an entry point in the ocelot switch lib that does all that is needed. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 3b8c5a54fb00..2c90a24ca064 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -880,7 +880,6 @@ int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, bool enabled, void ocelot_bridge_stp_state_set(struct ocelot *ocelot, int port, u8 state); u32 ocelot_get_dsa_8021q_cpu_mask(struct ocelot *ocelot); u32 ocelot_get_bridge_fwd_mask(struct ocelot *ocelot, int src_port); -void ocelot_apply_bridge_fwd_mask(struct ocelot *ocelot, bool joining); int ocelot_port_pre_bridge_flags(struct ocelot *ocelot, int port, struct switchdev_brport_flags val); void ocelot_port_bridge_flags(struct ocelot *ocelot, int port, -- cgit v1.2.3 From c295f9831f1db12330d6a28a1cb2bd2562535e37 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 22 May 2022 00:37:42 +0300 Subject: net: mscc: ocelot: switch from {,un}set to {,un}assign for tag_8021q CPU ports There is a desire for the felix driver to gain support for multiple tag_8021q CPU ports, but the current model prevents it. This is because ocelot_apply_bridge_fwd_mask() only takes into consideration whether a port is a tag_8021q CPU port, but not whose CPU port it is. We need a model where we can have a direct affinity between an ocelot port and a tag_8021q CPU port. This serves as the basis for multiple CPU ports. Declare a "dsa_8021q_cpu" backpointer in struct ocelot_port which encodes that affinity. Repurpose the "ocelot_set_dsa_8021q_cpu" API to "ocelot_assign_dsa_8021q_cpu" to express the change of paradigm. Note that this change makes the first practical use of the new ocelot_port->index field in ocelot_port_unassign_dsa_8021q_cpu(), where we need to remove the old tag_8021q CPU port from the reserved VLAN range. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 2c90a24ca064..5f88385a7748 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -654,6 +654,8 @@ struct ocelot_mirror { int to; }; +struct ocelot_port; + struct ocelot_port { struct ocelot *ocelot; @@ -662,6 +664,8 @@ struct ocelot_port { struct net_device *bond; struct net_device *bridge; + struct ocelot_port *dsa_8021q_cpu; + /* VLAN that untagged frames are classified to, on ingress */ const struct ocelot_bridge_vlan *pvid_vlan; @@ -865,8 +869,9 @@ void ocelot_deinit(struct ocelot *ocelot); void ocelot_init_port(struct ocelot *ocelot, int port); void ocelot_deinit_port(struct ocelot *ocelot, int port); -void ocelot_port_set_dsa_8021q_cpu(struct ocelot *ocelot, int port); -void ocelot_port_unset_dsa_8021q_cpu(struct ocelot *ocelot, int port); +void ocelot_port_assign_dsa_8021q_cpu(struct ocelot *ocelot, int port, int cpu); +void ocelot_port_unassign_dsa_8021q_cpu(struct ocelot *ocelot, int port); +u32 ocelot_port_assigned_dsa_8021q_cpu_mask(struct ocelot *ocelot, int port); /* DSA callbacks */ void ocelot_get_strings(struct ocelot *ocelot, int port, u32 sset, u8 *data); @@ -878,7 +883,6 @@ void ocelot_set_ageing_time(struct ocelot *ocelot, unsigned int msecs); int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, bool enabled, struct netlink_ext_ack *extack); void ocelot_bridge_stp_state_set(struct ocelot *ocelot, int port, u8 state); -u32 ocelot_get_dsa_8021q_cpu_mask(struct ocelot *ocelot); u32 ocelot_get_bridge_fwd_mask(struct ocelot *ocelot, int src_port); int ocelot_port_pre_bridge_flags(struct ocelot *ocelot, int port, struct switchdev_brport_flags val); -- cgit v1.2.3 From a4e044dc4c5b1e03f4195224c47108dc44122917 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 22 May 2022 00:37:43 +0300 Subject: net: dsa: felix: tag_8021q preparation for multiple CPU ports Update the VCAP filters to support multiple tag_8021q CPU ports. TX works using a filter for VLAN ID on the ingress of the CPU port, with a redirect and a VLAN pop action. This can be updated trivially by amending the ingress port mask of this rule to match on all tag_8021q CPU ports. RX works using a filter for ingress port on the egress of the CPU port, with a VLAN push action. Here we need to replicate these filters for each tag_8021q CPU port, and let them all have the same action. This means that the OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN() cookie needs to encode a unique value for every {user port, CPU port} pair it's given. Do this by encoding the CPU port in the upper 16 bits of the cookie, and the user port in the lower 16 bits. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/soc/mscc/ocelot_vcap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index de26c992f821..c601a4598b0d 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -11,7 +11,7 @@ /* Cookie definitions for private VCAP filters installed by the driver. * Must be unique per VCAP block. */ -#define OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN(ocelot, port) (port) +#define OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN(ocelot, port, upstream) ((upstream) << 16 | (port)) #define OCELOT_VCAP_IS1_TAG_8021Q_TXVLAN(ocelot, port) (port) #define OCELOT_VCAP_IS2_TAG_8021Q_TXVLAN(ocelot, port) (port) #define OCELOT_VCAP_IS2_MRP_REDIRECT(ocelot, port) ((ocelot)->num_phys_ports + (port)) -- cgit v1.2.3 From a13e248ff90e81e9322406c0e618cf2168702f4e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= Date: Fri, 6 May 2022 18:08:11 +0200 Subject: landlock: Fix landlock_add_rule(2) documentation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It is not mandatory to pass a file descriptor obtained with the O_PATH flag. Also, replace rule's accesses with ruleset's accesses. Link: https://lore.kernel.org/r/20220506160820.524344-2-mic@digikod.net Cc: stable@vger.kernel.org Signed-off-by: Mickaël Salaün --- include/uapi/linux/landlock.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index 15c31abb0d76..21c8d58283c9 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -62,8 +62,9 @@ struct landlock_path_beneath_attr { */ __u64 allowed_access; /** - * @parent_fd: File descriptor, open with ``O_PATH``, which identifies - * the parent directory of a file hierarchy, or just a file. + * @parent_fd: File descriptor, preferably opened with ``O_PATH``, + * which identifies the parent directory of a file hierarchy, or just a + * file. */ __s32 parent_fd; /* -- cgit v1.2.3 From 100f59d964050020285f0c8264ce520f0c406c13 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= Date: Fri, 6 May 2022 18:10:56 +0200 Subject: LSM: Remove double path_rename hook calls for RENAME_EXCHANGE MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In order to be able to identify a file exchange with renameat2(2) and RENAME_EXCHANGE, which will be useful for Landlock [1], propagate the rename flags to LSMs. This may also improve performance because of the switch from two set of LSM hook calls to only one, and because LSMs using this hook may optimize the double check (e.g. only one lock, reduce the number of path walks). AppArmor, Landlock and Tomoyo are updated to leverage this change. This should not change the current behavior (same check order), except (different level of) speed boosts. [1] https://lore.kernel.org/r/20220221212522.320243-1-mic@digikod.net Cc: James Morris Cc: Kentaro Takeda Cc: Serge E. Hallyn Acked-by: John Johansen Acked-by: Tetsuo Handa Reviewed-by: Paul Moore Signed-off-by: Mickaël Salaün Link: https://lore.kernel.org/r/20220506161102.525323-7-mic@digikod.net --- include/linux/lsm_hook_defs.h | 2 +- include/linux/lsm_hooks.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index db924fe379c9..eafa1d2489fd 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -100,7 +100,7 @@ LSM_HOOK(int, 0, path_link, struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry) LSM_HOOK(int, 0, path_rename, const struct path *old_dir, struct dentry *old_dentry, const struct path *new_dir, - struct dentry *new_dentry) + struct dentry *new_dentry, unsigned int flags) LSM_HOOK(int, 0, path_chmod, const struct path *path, umode_t mode) LSM_HOOK(int, 0, path_chown, const struct path *path, kuid_t uid, kgid_t gid) LSM_HOOK(int, 0, path_chroot, const struct path *path) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 419b5febc3ca..9acf5e368d73 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -358,6 +358,7 @@ * @old_dentry contains the dentry structure of the old link. * @new_dir contains the path structure for parent of the new link. * @new_dentry contains the dentry structure of the new link. + * @flags may contain rename options such as RENAME_EXCHANGE. * Return 0 if permission is granted. * @path_chmod: * Check for permission to change a mode of the file @path. The new -- cgit v1.2.3 From b91c3e4ea756b12b7d992529226edce1cfd854d7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= Date: Fri, 6 May 2022 18:10:57 +0200 Subject: landlock: Add support for file reparenting with LANDLOCK_ACCESS_FS_REFER MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a new LANDLOCK_ACCESS_FS_REFER access right to enable policy writers to allow sandboxed processes to link and rename files from and to a specific set of file hierarchies. This access right should be composed with LANDLOCK_ACCESS_FS_MAKE_* for the destination of a link or rename, and with LANDLOCK_ACCESS_FS_REMOVE_* for a source of a rename. This lift a Landlock limitation that always denied changing the parent of an inode. Renaming or linking to the same directory is still always allowed, whatever LANDLOCK_ACCESS_FS_REFER is used or not, because it is not considered a threat to user data. However, creating multiple links or renaming to a different parent directory may lead to privilege escalations if not handled properly. Indeed, we must be sure that the source doesn't gain more privileges by being accessible from the destination. This is handled by making sure that the source hierarchy (including the referenced file or directory itself) restricts at least as much the destination hierarchy. If it is not the case, an EXDEV error is returned, making it potentially possible for user space to copy the file hierarchy instead of moving or linking it. Instead of creating different access rights for the source and the destination, we choose to make it simple and consistent for users. Indeed, considering the previous constraint, it would be weird to require such destination access right to be also granted to the source (to make it a superset). Moreover, RENAME_EXCHANGE would also add to the confusion because of paths being both a source and a destination. See the provided documentation for additional details. New tests are provided with a following commit. Reviewed-by: Paul Moore Signed-off-by: Mickaël Salaün Link: https://lore.kernel.org/r/20220506161102.525323-8-mic@digikod.net --- include/uapi/linux/landlock.h | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index 21c8d58283c9..23df4e0e8ace 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -21,8 +21,14 @@ struct landlock_ruleset_attr { /** * @handled_access_fs: Bitmask of actions (cf. `Filesystem flags`_) * that is handled by this ruleset and should then be forbidden if no - * rule explicitly allow them. This is needed for backward - * compatibility reasons. + * rule explicitly allow them: it is a deny-by-default list that should + * contain as much Landlock access rights as possible. Indeed, all + * Landlock filesystem access rights that are not part of + * handled_access_fs are allowed. This is needed for backward + * compatibility reasons. One exception is the + * LANDLOCK_ACCESS_FS_REFER access right, which is always implicitly + * handled, but must still be explicitly handled to add new rules with + * this access right. */ __u64 handled_access_fs; }; @@ -112,6 +118,22 @@ struct landlock_path_beneath_attr { * - %LANDLOCK_ACCESS_FS_MAKE_FIFO: Create (or rename or link) a named pipe. * - %LANDLOCK_ACCESS_FS_MAKE_BLOCK: Create (or rename or link) a block device. * - %LANDLOCK_ACCESS_FS_MAKE_SYM: Create (or rename or link) a symbolic link. + * - %LANDLOCK_ACCESS_FS_REFER: Link or rename a file from or to a different + * directory (i.e. reparent a file hierarchy). This access right is + * available since the second version of the Landlock ABI. This is also the + * only access right which is always considered handled by any ruleset in + * such a way that reparenting a file hierarchy is always denied by default. + * To avoid privilege escalation, it is not enough to add a rule with this + * access right. When linking or renaming a file, the destination directory + * hierarchy must also always have the same or a superset of restrictions of + * the source hierarchy. If it is not the case, or if the domain doesn't + * handle this access right, such actions are denied by default with errno + * set to EXDEV. Linking also requires a LANDLOCK_ACCESS_FS_MAKE_* access + * right on the destination directory, and renaming also requires a + * LANDLOCK_ACCESS_FS_REMOVE_* access right on the source's (file or + * directory) parent. Otherwise, such actions are denied with errno set to + * EACCES. The EACCES errno prevails over EXDEV to let user space + * efficiently deal with an unrecoverable error. * * .. warning:: * @@ -137,6 +159,7 @@ struct landlock_path_beneath_attr { #define LANDLOCK_ACCESS_FS_MAKE_FIFO (1ULL << 10) #define LANDLOCK_ACCESS_FS_MAKE_BLOCK (1ULL << 11) #define LANDLOCK_ACCESS_FS_MAKE_SYM (1ULL << 12) +#define LANDLOCK_ACCESS_FS_REFER (1ULL << 13) /* clang-format on */ #endif /* _UAPI_LINUX_LANDLOCK_H */ -- cgit v1.2.3 From fb70bf124b051d4ded4ce57511dfec6d3ebf2b43 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 30 Mar 2022 10:30:54 -0400 Subject: NFSD: Instantiate a struct file when creating a regular NFSv4 file There have been reports of races that cause NFSv4 OPEN(CREATE) to return an error even though the requested file was created. NFSv4 does not provide a status code for this case. To mitigate some of these problems, reorganize the NFSv4 OPEN(CREATE) logic to allocate resources before the file is actually created, and open the new file while the parent directory is still locked. Two new APIs are added: + Add an API that works like nfsd_file_acquire() but does not open the underlying file. The OPEN(CREATE) path can use this API when it already has an open file. + Add an API that is kin to dentry_open(). NFSD needs to create a file and grab an open "struct file *" atomically. The alloc_empty_file() has to be done before the inode create. If it fails (for example, because the NFS server has exceeded its max_files limit), we avoid creating the file and can still return an error to the NFS client. BugLink: https://bugzilla.linux-nfs.org/show_bug.cgi?id=382 Signed-off-by: Chuck Lever Tested-by: JianHong Yin --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index aa6c1bbdb8c4..b848355b5e6c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2640,6 +2640,8 @@ static inline struct file *file_open_root_mnt(struct vfsmount *mnt, name, flags, mode); } extern struct file * dentry_open(const struct path *, int, const struct cred *); +extern struct file *dentry_create(const struct path *path, int flags, + umode_t mode, const struct cred *cred); extern struct file * open_with_fake_path(const struct path *, int, struct inode*, const struct cred *); static inline struct file *file_clone_open(struct file *file) -- cgit v1.2.3 From 141e523914f72575915dd334fce3cef4fb0f1e91 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= Date: Mon, 12 Jul 2021 19:03:12 +0200 Subject: certs: Factor out the blacklist hash creation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Factor out the blacklist hash creation with the get_raw_hash() helper. This also centralize the "tbs" and "bin" prefixes and make them private, which help to manage them consistently. Cc: David Howells Cc: David S. Miller Cc: David Woodhouse Cc: Eric Snowberg Cc: Herbert Xu Cc: Jarkko Sakkinen Signed-off-by: Mickaël Salaün Link: https://lore.kernel.org/r/20210712170313.884724-5-mic@digikod.net Signed-off-by: Jarkko Sakkinen --- include/keys/system_keyring.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/keys/system_keyring.h b/include/keys/system_keyring.h index 2419a735420f..91e080efb918 100644 --- a/include/keys/system_keyring.h +++ b/include/keys/system_keyring.h @@ -10,6 +10,13 @@ #include +enum blacklist_hash_type { + /* TBSCertificate hash */ + BLACKLIST_HASH_X509_TBS = 1, + /* Raw data hash */ + BLACKLIST_HASH_BINARY = 2, +}; + #ifdef CONFIG_SYSTEM_TRUSTED_KEYRING extern int restrict_link_by_builtin_trusted(struct key *keyring, @@ -54,13 +61,14 @@ static inline void __init set_machine_trusted_keys(struct key *keyring) extern struct pkcs7_message *pkcs7; #ifdef CONFIG_SYSTEM_BLACKLIST_KEYRING -extern int mark_hash_blacklisted(const char *hash); +extern int mark_hash_blacklisted(const u8 *hash, size_t hash_len, + enum blacklist_hash_type hash_type); extern int is_hash_blacklisted(const u8 *hash, size_t hash_len, - const char *type); + enum blacklist_hash_type hash_type); extern int is_binary_blacklisted(const u8 *hash, size_t hash_len); #else static inline int is_hash_blacklisted(const u8 *hash, size_t hash_len, - const char *type) + enum blacklist_hash_type hash_type) { return 0; } -- cgit v1.2.3 From fcd7c26901c83681532c6daac599e53d4df11738 Mon Sep 17 00:00:00 2001 From: Ahmad Fatoum Date: Fri, 13 May 2022 16:57:00 +0200 Subject: KEYS: trusted: allow use of kernel RNG for key material The two existing trusted key sources don't make use of the kernel RNG, but instead let the hardware doing the sealing/unsealing also generate the random key material. However, both users and future backends may want to place less trust into the quality of the trust source's random number generator and instead reuse the kernel entropy pool, which can be seeded from multiple entropy sources. Make this possible by adding a new trusted.rng parameter, that will force use of the kernel RNG. In its absence, it's up to the trust source to decide, which random numbers to use, maintaining the existing behavior. Suggested-by: Jarkko Sakkinen Acked-by: Sumit Garg Acked-by: Pankaj Gupta Reviewed-by: David Gstir Reviewed-by: Pankaj Gupta Reviewed-by: Jarkko Sakkinen Tested-by: Pankaj Gupta Tested-by: Michael Walle # on ls1028a (non-E and E) Tested-by: John Ernberg # iMX8QXP Signed-off-by: Ahmad Fatoum Signed-off-by: Jarkko Sakkinen --- include/keys/trusted-type.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/keys/trusted-type.h b/include/keys/trusted-type.h index d89fa2579ac0..4eb64548a74f 100644 --- a/include/keys/trusted-type.h +++ b/include/keys/trusted-type.h @@ -64,7 +64,7 @@ struct trusted_key_ops { /* Unseal a key. */ int (*unseal)(struct trusted_key_payload *p, char *datablob); - /* Get a randomized key. */ + /* Optional: Get a randomized key. */ int (*get_random)(unsigned char *key, size_t key_len); /* Exit key interface. */ -- cgit v1.2.3 From 007c3ff11f38d83cc95b0f402e432cbf484e3c31 Mon Sep 17 00:00:00 2001 From: Ahmad Fatoum Date: Fri, 13 May 2022 16:57:02 +0200 Subject: crypto: caam - add in-kernel interface for blob generator The NXP Cryptographic Acceleration and Assurance Module (CAAM) can be used to protect user-defined data across system reboot: - When the system is fused and boots into secure state, the master key is a unique never-disclosed device-specific key - random key is encrypted by key derived from master key - data is encrypted using the random key - encrypted data and its encrypted random key are stored alongside - This blob can now be safely stored in non-volatile memory On next power-on: - blob is loaded into CAAM - CAAM writes decrypted data either into memory or key register Add functions to realize encrypting and decrypting into memory alongside the CAAM driver. They will be used in a later commit as a source for the trusted key seal/unseal mechanism. Reviewed-by: David Gstir Reviewed-by: Pankaj Gupta Tested-by: Tim Harvey Tested-by: Matthias Schiffer Tested-by: Pankaj Gupta Tested-by: Michael Walle # on ls1028a (non-E and E) Tested-by: John Ernberg # iMX8QXP Signed-off-by: Steffen Trumtrar Signed-off-by: Ahmad Fatoum Signed-off-by: Jarkko Sakkinen --- include/soc/fsl/caam-blob.h | 103 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 103 insertions(+) create mode 100644 include/soc/fsl/caam-blob.h (limited to 'include') diff --git a/include/soc/fsl/caam-blob.h b/include/soc/fsl/caam-blob.h new file mode 100644 index 000000000000..937cac52f36d --- /dev/null +++ b/include/soc/fsl/caam-blob.h @@ -0,0 +1,103 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Pengutronix, Ahmad Fatoum + */ + +#ifndef __CAAM_BLOB_GEN +#define __CAAM_BLOB_GEN + +#include +#include + +#define CAAM_BLOB_KEYMOD_LENGTH 16 +#define CAAM_BLOB_OVERHEAD (32 + 16) +#define CAAM_BLOB_MAX_LEN 4096 + +struct caam_blob_priv; + +/** + * struct caam_blob_info - information for CAAM blobbing + * @input: pointer to input buffer (must be DMAable) + * @input_len: length of @input buffer in bytes. + * @output: pointer to output buffer (must be DMAable) + * @output_len: length of @output buffer in bytes. + * @key_mod: key modifier + * @key_mod_len: length of @key_mod in bytes. + * May not exceed %CAAM_BLOB_KEYMOD_LENGTH + */ +struct caam_blob_info { + void *input; + size_t input_len; + + void *output; + size_t output_len; + + const void *key_mod; + size_t key_mod_len; +}; + +/** + * caam_blob_gen_init - initialize blob generation + * Return: pointer to new &struct caam_blob_priv instance on success + * and ``ERR_PTR(-ENODEV)`` if CAAM has no hardware blobbing support + * or no job ring could be allocated. + */ +struct caam_blob_priv *caam_blob_gen_init(void); + +/** + * caam_blob_gen_exit - free blob generation resources + * @priv: instance returned by caam_blob_gen_init() + */ +void caam_blob_gen_exit(struct caam_blob_priv *priv); + +/** + * caam_process_blob - encapsulate or decapsulate blob + * @priv: instance returned by caam_blob_gen_init() + * @info: pointer to blobbing info describing key, blob and + * key modifier buffers. + * @encap: true for encapsulation, false for decapsulation + * + * Return: %0 and sets ``info->output_len`` on success and a negative + * error code otherwise. + */ +int caam_process_blob(struct caam_blob_priv *priv, + struct caam_blob_info *info, bool encap); + +/** + * caam_encap_blob - encapsulate blob + * @priv: instance returned by caam_blob_gen_init() + * @info: pointer to blobbing info describing input key, + * output blob and key modifier buffers. + * + * Return: %0 and sets ``info->output_len`` on success and + * a negative error code otherwise. + */ +static inline int caam_encap_blob(struct caam_blob_priv *priv, + struct caam_blob_info *info) +{ + if (info->output_len < info->input_len + CAAM_BLOB_OVERHEAD) + return -EINVAL; + + return caam_process_blob(priv, info, true); +} + +/** + * caam_decap_blob - decapsulate blob + * @priv: instance returned by caam_blob_gen_init() + * @info: pointer to blobbing info describing output key, + * input blob and key modifier buffers. + * + * Return: %0 and sets ``info->output_len`` on success and + * a negative error code otherwise. + */ +static inline int caam_decap_blob(struct caam_blob_priv *priv, + struct caam_blob_info *info) +{ + if (info->input_len < CAAM_BLOB_OVERHEAD || + info->output_len < info->input_len - CAAM_BLOB_OVERHEAD) + return -EINVAL; + + return caam_process_blob(priv, info, false); +} + +#endif -- cgit v1.2.3 From e9c5048c2de1913d0bcd589bc1487810c2e24bc1 Mon Sep 17 00:00:00 2001 From: Ahmad Fatoum Date: Fri, 13 May 2022 16:57:03 +0200 Subject: KEYS: trusted: Introduce support for NXP CAAM-based trusted keys The Cryptographic Acceleration and Assurance Module (CAAM) is an IP core built into many newer i.MX and QorIQ SoCs by NXP. The CAAM does crypto acceleration, hardware number generation and has a blob mechanism for encapsulation/decapsulation of sensitive material. This blob mechanism depends on a device specific random 256-bit One Time Programmable Master Key that is fused in each SoC at manufacturing time. This key is unreadable and can only be used by the CAAM for AES encryption/decryption of user data. This makes it a suitable backend (source) for kernel trusted keys. Previous commits generalized trusted keys to support multiple backends and added an API to access the CAAM blob mechanism. Based on these, provide the necessary glue to use the CAAM for trusted keys. Reviewed-by: David Gstir Reviewed-by: Pankaj Gupta Reviewed-by: Jarkko Sakkinen Tested-by: Tim Harvey Tested-by: Matthias Schiffer Tested-by: Pankaj Gupta Tested-by: Michael Walle # on ls1028a (non-E and E) Tested-by: John Ernberg # iMX8QXP Signed-off-by: Ahmad Fatoum Signed-off-by: Jarkko Sakkinen --- include/keys/trusted_caam.h | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 include/keys/trusted_caam.h (limited to 'include') diff --git a/include/keys/trusted_caam.h b/include/keys/trusted_caam.h new file mode 100644 index 000000000000..73fe2f32f65e --- /dev/null +++ b/include/keys/trusted_caam.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Pengutronix, Ahmad Fatoum + */ + +#ifndef __CAAM_TRUSTED_KEY_H +#define __CAAM_TRUSTED_KEY_H + +extern struct trusted_key_ops trusted_key_caam_ops; + +#endif -- cgit v1.2.3 From bca1a1004615efe141fd78f360ecc48c60bc4ad5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20Ard=C3=B6?= Date: Thu, 31 Mar 2022 09:01:15 +0200 Subject: mailbox: forward the hrtimer if not queued and under a lock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit c7dacf5b0f32957b24ef29df1207dc2cd8307743, "mailbox: avoid timer start from callback" The previous commit was reverted since it lead to a race that caused the hrtimer to not be started at all. The check for hrtimer_active() in msg_submit() will return true if the callback function txdone_hrtimer() is currently running. This function could return HRTIMER_NORESTART and then the timer will not be restarted, and also msg_submit() will not start the timer. This will lead to a message actually being submitted but no timer will start to check for its compleation. The original fix that added checking hrtimer_active() was added to avoid a warning with hrtimer_forward. Looking in the kernel another solution to avoid this warning is to check hrtimer_is_queued() before calling hrtimer_forward_now() instead. This however requires a lock so the timer is not started by msg_submit() inbetween this check and the hrtimer_forward() call. Fixes: c7dacf5b0f32 ("mailbox: avoid timer start from callback") Signed-off-by: Björn Ardö Signed-off-by: Jassi Brar --- include/linux/mailbox_controller.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mailbox_controller.h b/include/linux/mailbox_controller.h index 36d6ce673503..6fee33cb52f5 100644 --- a/include/linux/mailbox_controller.h +++ b/include/linux/mailbox_controller.h @@ -83,6 +83,7 @@ struct mbox_controller { const struct of_phandle_args *sp); /* Internal to API */ struct hrtimer poll_hrt; + spinlock_t poll_hrt_lock; struct list_head node; }; -- cgit v1.2.3 From fe736565efb775620dbcf3c459c1cd80d3e868da Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 20 May 2022 16:57:53 -0700 Subject: bpf: Introduce bpf_arch_text_invalidate for bpf_prog_pack Introduce bpf_arch_text_invalidate and use it to fill unused part of the bpf_prog_pack with illegal instructions when a BPF program is freed. Fixes: 57631054fae6 ("bpf: Introduce bpf_prog_pack allocator") Fixes: 33c9805860e5 ("bpf: Introduce bpf_jit_binary_pack_[alloc|finalize|free]") Reported-by: Linus Torvalds Signed-off-by: Song Liu Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20220520235758.1858153-4-song@kernel.org --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cc4d5e394031..a9b1875212f6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2365,6 +2365,7 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2); void *bpf_arch_text_copy(void *dst, void *src, size_t len); +int bpf_arch_text_invalidate(void *dst, size_t len); struct btf_id_set; bool btf_id_set_contains(const struct btf_id_set *set, u32 id); -- cgit v1.2.3 From 97e03f521050c092919591e668107b3d69c5f426 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Mon, 23 May 2022 14:07:07 -0700 Subject: bpf: Add verifier support for dynptrs This patch adds the bulk of the verifier work for supporting dynamic pointers (dynptrs) in bpf. A bpf_dynptr is opaque to the bpf program. It is a 16-byte structure defined internally as: struct bpf_dynptr_kern { void *data; u32 size; u32 offset; } __aligned(8); The upper 8 bits of *size* is reserved (it contains extra metadata about read-only status and dynptr type). Consequently, a dynptr only supports memory less than 16 MB. There are different types of dynptrs (eg malloc, ringbuf, ...). In this patchset, the most basic one, dynptrs to a bpf program's local memory, is added. For now only local memory that is of reg type PTR_TO_MAP_VALUE is supported. In the verifier, dynptr state information will be tracked in stack slots. When the program passes in an uninitialized dynptr (ARG_PTR_TO_DYNPTR | MEM_UNINIT), the stack slots corresponding to the frame pointer where the dynptr resides at are marked STACK_DYNPTR. For helper functions that take in initialized dynptrs (eg bpf_dynptr_read + bpf_dynptr_write which are added later in this patchset), the verifier enforces that the dynptr has been initialized properly by checking that their corresponding stack slots have been marked as STACK_DYNPTR. The 6th patch in this patchset adds test cases that the verifier should successfully reject, such as for example attempting to use a dynptr after doing a direct write into it inside the bpf program. Signed-off-by: Joanne Koong Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Acked-by: David Vernet Link: https://lore.kernel.org/bpf/20220523210712.3641569-2-joannelkoong@gmail.com --- include/linux/bpf.h | 28 ++++++++++++++++++++++++++++ include/linux/bpf_verifier.h | 18 ++++++++++++++++++ include/uapi/linux/bpf.h | 5 +++++ 3 files changed, 51 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a9b1875212f6..b26c8176b9e0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -392,10 +392,15 @@ enum bpf_type_flag { MEM_UNINIT = BIT(7 + BPF_BASE_TYPE_BITS), + /* DYNPTR points to memory local to the bpf program. */ + DYNPTR_TYPE_LOCAL = BIT(8 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; +#define DYNPTR_TYPE_FLAG_MASK DYNPTR_TYPE_LOCAL + /* Max number of base types. */ #define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS) @@ -438,6 +443,7 @@ enum bpf_arg_type { ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */ ARG_PTR_TO_TIMER, /* pointer to bpf_timer */ ARG_PTR_TO_KPTR, /* pointer to referenced kptr */ + ARG_PTR_TO_DYNPTR, /* pointer to bpf_dynptr. See bpf_type_flag for dynptr type */ __BPF_ARG_TYPE_MAX, /* Extended arg_types. */ @@ -2376,4 +2382,26 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, u32 **bin_buf, u32 num_args); void bpf_bprintf_cleanup(void); +/* the implementation of the opaque uapi struct bpf_dynptr */ +struct bpf_dynptr_kern { + void *data; + /* Size represents the number of usable bytes of dynptr data. + * If for example the offset is at 4 for a local dynptr whose data is + * of type u64, the number of usable bytes is 4. + * + * The upper 8 bits are reserved. It is as follows: + * Bits 0 - 23 = size + * Bits 24 - 30 = dynptr type + * Bit 31 = whether dynptr is read-only + */ + u32 size; + u32 offset; +} __aligned(8); + +enum bpf_dynptr_type { + BPF_DYNPTR_TYPE_INVALID, + /* Points to memory that is local to the bpf program */ + BPF_DYNPTR_TYPE_LOCAL, +}; + #endif /* _LINUX_BPF_H */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 1f1e7f2ea967..af5b2135215e 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -72,6 +72,18 @@ struct bpf_reg_state { u32 mem_size; /* for PTR_TO_MEM | PTR_TO_MEM_OR_NULL */ + /* For dynptr stack slots */ + struct { + enum bpf_dynptr_type type; + /* A dynptr is 16 bytes so it takes up 2 stack slots. + * We need to track which slot is the first slot + * to protect against cases where the user may try to + * pass in an address starting at the second slot of the + * dynptr. + */ + bool first_slot; + } dynptr; + /* Max size from any of the above. */ struct { unsigned long raw1; @@ -174,9 +186,15 @@ enum bpf_stack_slot_type { STACK_SPILL, /* register spilled into stack */ STACK_MISC, /* BPF program wrote some data into this slot */ STACK_ZERO, /* BPF program wrote constant zero */ + /* A dynptr is stored in this stack slot. The type of dynptr + * is stored in bpf_stack_state->spilled_ptr.dynptr.type + */ + STACK_DYNPTR, }; #define BPF_REG_SIZE 8 /* size of eBPF register in bytes */ +#define BPF_DYNPTR_SIZE sizeof(struct bpf_dynptr_kern) +#define BPF_DYNPTR_NR_SLOTS (BPF_DYNPTR_SIZE / BPF_REG_SIZE) struct bpf_stack_state { struct bpf_reg_state spilled_ptr; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 56688bee20d9..610944cb3389 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6528,6 +6528,11 @@ struct bpf_timer { __u64 :64; } __attribute__((aligned(8))); +struct bpf_dynptr { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + struct bpf_sysctl { __u32 write; /* Sysctl is being read (= 0) or written (= 1). * Allows 1,2,4-byte read, but no write. -- cgit v1.2.3 From 263ae152e96253f40c2c276faad8629e096b3bad Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Mon, 23 May 2022 14:07:08 -0700 Subject: bpf: Add bpf_dynptr_from_mem for local dynptrs This patch adds a new api bpf_dynptr_from_mem: long bpf_dynptr_from_mem(void *data, u32 size, u64 flags, struct bpf_dynptr *ptr); which initializes a dynptr to point to a bpf program's local memory. For now only local memory that is of reg type PTR_TO_MAP_VALUE is supported. Signed-off-by: Joanne Koong Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220523210712.3641569-3-joannelkoong@gmail.com --- include/uapi/linux/bpf.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 610944cb3389..9be3644457dd 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5178,6 +5178,17 @@ union bpf_attr { * Dynamically cast a *sk* pointer to a *mptcp_sock* pointer. * Return * *sk* if casting is valid, or **NULL** otherwise. + * + * long bpf_dynptr_from_mem(void *data, u32 size, u64 flags, struct bpf_dynptr *ptr) + * Description + * Get a dynptr to local memory *data*. + * + * *data* must be a ptr to a map value. + * The maximum *size* supported is DYNPTR_MAX_SIZE. + * *flags* is currently unused. + * Return + * 0 on success, -E2BIG if the size exceeds DYNPTR_MAX_SIZE, + * -EINVAL if flags is not 0. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5377,6 +5388,7 @@ union bpf_attr { FN(kptr_xchg), \ FN(map_lookup_percpu_elem), \ FN(skc_to_mptcp_sock), \ + FN(dynptr_from_mem), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From bc34dee65a65e9c920c420005b8a43f2a721a458 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Mon, 23 May 2022 14:07:09 -0700 Subject: bpf: Dynptr support for ring buffers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, our only way of writing dynamically-sized data into a ring buffer is through bpf_ringbuf_output but this incurs an extra memcpy cost. bpf_ringbuf_reserve + bpf_ringbuf_commit avoids this extra memcpy, but it can only safely support reservation sizes that are statically known since the verifier cannot guarantee that the bpf program won’t access memory outside the reserved space. The bpf_dynptr abstraction allows for dynamically-sized ring buffer reservations without the extra memcpy. There are 3 new APIs: long bpf_ringbuf_reserve_dynptr(void *ringbuf, u32 size, u64 flags, struct bpf_dynptr *ptr); void bpf_ringbuf_submit_dynptr(struct bpf_dynptr *ptr, u64 flags); void bpf_ringbuf_discard_dynptr(struct bpf_dynptr *ptr, u64 flags); These closely follow the functionalities of the original ringbuf APIs. For example, all ringbuffer dynptrs that have been reserved must be either submitted or discarded before the program exits. Signed-off-by: Joanne Koong Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Acked-by: David Vernet Link: https://lore.kernel.org/bpf/20220523210712.3641569-4-joannelkoong@gmail.com --- include/linux/bpf.h | 15 ++++++++++++++- include/linux/bpf_verifier.h | 2 ++ include/uapi/linux/bpf.h | 35 +++++++++++++++++++++++++++++++++++ 3 files changed, 51 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b26c8176b9e0..c72321b6f306 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -395,11 +395,14 @@ enum bpf_type_flag { /* DYNPTR points to memory local to the bpf program. */ DYNPTR_TYPE_LOCAL = BIT(8 + BPF_BASE_TYPE_BITS), + /* DYNPTR points to a ringbuf record. */ + DYNPTR_TYPE_RINGBUF = BIT(9 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; -#define DYNPTR_TYPE_FLAG_MASK DYNPTR_TYPE_LOCAL +#define DYNPTR_TYPE_FLAG_MASK (DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF) /* Max number of base types. */ #define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS) @@ -2231,6 +2234,9 @@ extern const struct bpf_func_proto bpf_ringbuf_reserve_proto; extern const struct bpf_func_proto bpf_ringbuf_submit_proto; extern const struct bpf_func_proto bpf_ringbuf_discard_proto; extern const struct bpf_func_proto bpf_ringbuf_query_proto; +extern const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto; +extern const struct bpf_func_proto bpf_ringbuf_submit_dynptr_proto; +extern const struct bpf_func_proto bpf_ringbuf_discard_dynptr_proto; extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; @@ -2402,6 +2408,13 @@ enum bpf_dynptr_type { BPF_DYNPTR_TYPE_INVALID, /* Points to memory that is local to the bpf program */ BPF_DYNPTR_TYPE_LOCAL, + /* Underlying data is a ringbuf record */ + BPF_DYNPTR_TYPE_RINGBUF, }; +void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, + enum bpf_dynptr_type type, u32 offset, u32 size); +void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr); +int bpf_dynptr_check_size(u32 size); + #endif /* _LINUX_BPF_H */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index af5b2135215e..e8439f6cbe57 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -100,6 +100,8 @@ struct bpf_reg_state { * for the purpose of tracking that it's freed. * For PTR_TO_SOCKET this is used to share which pointers retain the * same reference to the socket, to determine proper reference freeing. + * For stack slots that are dynptrs, this is used to track references to + * the dynptr to determine proper reference freeing. */ u32 id; /* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9be3644457dd..081a55540aa5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5189,6 +5189,38 @@ union bpf_attr { * Return * 0 on success, -E2BIG if the size exceeds DYNPTR_MAX_SIZE, * -EINVAL if flags is not 0. + * + * long bpf_ringbuf_reserve_dynptr(void *ringbuf, u32 size, u64 flags, struct bpf_dynptr *ptr) + * Description + * Reserve *size* bytes of payload in a ring buffer *ringbuf* + * through the dynptr interface. *flags* must be 0. + * + * Please note that a corresponding bpf_ringbuf_submit_dynptr or + * bpf_ringbuf_discard_dynptr must be called on *ptr*, even if the + * reservation fails. This is enforced by the verifier. + * Return + * 0 on success, or a negative error in case of failure. + * + * void bpf_ringbuf_submit_dynptr(struct bpf_dynptr *ptr, u64 flags) + * Description + * Submit reserved ring buffer sample, pointed to by *data*, + * through the dynptr interface. This is a no-op if the dynptr is + * invalid/null. + * + * For more information on *flags*, please see + * 'bpf_ringbuf_submit'. + * Return + * Nothing. Always succeeds. + * + * void bpf_ringbuf_discard_dynptr(struct bpf_dynptr *ptr, u64 flags) + * Description + * Discard reserved ring buffer sample through the dynptr + * interface. This is a no-op if the dynptr is invalid/null. + * + * For more information on *flags*, please see + * 'bpf_ringbuf_discard'. + * Return + * Nothing. Always succeeds. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5389,6 +5421,9 @@ union bpf_attr { FN(map_lookup_percpu_elem), \ FN(skc_to_mptcp_sock), \ FN(dynptr_from_mem), \ + FN(ringbuf_reserve_dynptr), \ + FN(ringbuf_submit_dynptr), \ + FN(ringbuf_discard_dynptr), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 13bbbfbea7598ea9f8d9c3d73bf053bb57f9c4b2 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Mon, 23 May 2022 14:07:10 -0700 Subject: bpf: Add bpf_dynptr_read and bpf_dynptr_write This patch adds two helper functions, bpf_dynptr_read and bpf_dynptr_write: long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset); long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len); The dynptr passed into these functions must be valid dynptrs that have been initialized. Signed-off-by: Joanne Koong Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220523210712.3641569-5-joannelkoong@gmail.com --- include/uapi/linux/bpf.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 081a55540aa5..efe2505650e6 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5221,6 +5221,23 @@ union bpf_attr { * 'bpf_ringbuf_discard'. * Return * Nothing. Always succeeds. + * + * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset) + * Description + * Read *len* bytes from *src* into *dst*, starting from *offset* + * into *src*. + * Return + * 0 on success, -E2BIG if *offset* + *len* exceeds the length + * of *src*'s data, -EINVAL if *src* is an invalid dynptr. + * + * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len) + * Description + * Write *len* bytes from *src* into *dst*, starting from *offset* + * into *dst*. + * Return + * 0 on success, -E2BIG if *offset* + *len* exceeds the length + * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst* + * is a read-only dynptr. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5424,6 +5441,8 @@ union bpf_attr { FN(ringbuf_reserve_dynptr), \ FN(ringbuf_submit_dynptr), \ FN(ringbuf_discard_dynptr), \ + FN(dynptr_read), \ + FN(dynptr_write), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 34d4ef5775f776ec4b0d53a02d588bf3195cada6 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Mon, 23 May 2022 14:07:11 -0700 Subject: bpf: Add dynptr data slices This patch adds a new helper function void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len); which returns a pointer to the underlying data of a dynptr. *len* must be a statically known value. The bpf program may access the returned data slice as a normal buffer (eg can do direct reads and writes), since the verifier associates the length with the returned pointer, and enforces that no out of bounds accesses occur. Signed-off-by: Joanne Koong Signed-off-by: Andrii Nakryiko Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20220523210712.3641569-6-joannelkoong@gmail.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 12 ++++++++++++ 2 files changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c72321b6f306..a7080c86fa76 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -488,6 +488,7 @@ enum bpf_return_type { RET_PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK, RET_PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON, RET_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | MEM_ALLOC | RET_PTR_TO_ALLOC_MEM, + RET_PTR_TO_DYNPTR_MEM_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_ALLOC_MEM, RET_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID, /* This must be the last entry. Its purpose is to ensure the enum is diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index efe2505650e6..f4009dbdf62d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5238,6 +5238,17 @@ union bpf_attr { * 0 on success, -E2BIG if *offset* + *len* exceeds the length * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst* * is a read-only dynptr. + * + * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len) + * Description + * Get a pointer to the underlying dynptr data. + * + * *len* must be a statically known value. The returned data slice + * is invalidated whenever the dynptr is invalidated. + * Return + * Pointer to the underlying dynptr data, NULL if the dynptr is + * read-only, if the dynptr is invalid, or if the offset and length + * is out of bounds. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5443,6 +5454,7 @@ union bpf_attr { FN(ringbuf_discard_dynptr), \ FN(dynptr_read), \ FN(dynptr_write), \ + FN(dynptr_data), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 5d7c854593a460706dacf8e1b16c9bdcb1c2d7bb Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 28 Mar 2022 08:26:48 +0200 Subject: livepatch: Remove klp_arch_set_pc() and asm/livepatch.h All three versions of klp_arch_set_pc() do exactly the same: they call ftrace_instruction_pointer_set(). Call ftrace_instruction_pointer_set() directly and remove klp_arch_set_pc(). As klp_arch_set_pc() was the only thing remaining in asm/livepatch.h on x86 and s390, remove asm/livepatch.h livepatch.h remains on powerpc but its content is exclusively used by powerpc specific code. Signed-off-by: Christophe Leroy Acked-by: Petr Mladek Acked-by: Peter Zijlstra (Intel) Acked-by: Miroslav Benes Signed-off-by: Petr Mladek --- include/linux/livepatch.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 2614247a9781..293e29960c6e 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -16,8 +16,6 @@ #if IS_ENABLED(CONFIG_LIVEPATCH) -#include - /* task patch states */ #define KLP_UNDEFINED -1 #define KLP_UNPATCHED 0 -- cgit v1.2.3 From 7b4537199a4a8480b8c3ba37a2d44765ce76cd9b Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 13 May 2022 20:39:22 +0900 Subject: kbuild: link symbol CRCs at final link, removing CONFIG_MODULE_REL_CRCS include/{linux,asm-generic}/export.h defines a weak symbol, __crc_* as a placeholder. Genksyms writes the version CRCs into the linker script, which will be used for filling the __crc_* symbols. The linker script format depends on CONFIG_MODULE_REL_CRCS. If it is enabled, __crc_* holds the offset to the reference of CRC. It is time to get rid of this complexity. Now that modpost parses text files (.*.cmd) to collect all the CRCs, it can generate C code that will be linked to the vmlinux or modules. Generate a new C file, .vmlinux.export.c, which contains the CRCs of symbols exported by vmlinux. It is compiled and linked to vmlinux in scripts/link-vmlinux.sh. Put the CRCs of symbols exported by modules into the existing *.mod.c files. No additional build step is needed for modules. As before, *.mod.c are compiled and linked to *.ko in scripts/Makefile.modfinal. No linker magic is used here. The new C implementation works in the same way, whether CONFIG_RELOCATABLE is enabled or not. CONFIG_MODULE_REL_CRCS is no longer needed. Previously, Kbuild invoked additional $(LD) to update the CRCs in objects, but this step is unneeded too. Signed-off-by: Masahiro Yamada Tested-by: Nathan Chancellor Tested-by: Nicolas Schier Reviewed-by: Nicolas Schier Tested-by: Sedat Dilek # LLVM-14 (x86-64) --- include/asm-generic/export.h | 22 ++++++++-------------- include/linux/export-internal.h | 17 +++++++++++++++++ include/linux/export.h | 30 ++++++++---------------------- 3 files changed, 33 insertions(+), 36 deletions(-) create mode 100644 include/linux/export-internal.h (limited to 'include') diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h index 07a36a874dca..5e4b1f2369d2 100644 --- a/include/asm-generic/export.h +++ b/include/asm-generic/export.h @@ -2,6 +2,14 @@ #ifndef __ASM_GENERIC_EXPORT_H #define __ASM_GENERIC_EXPORT_H +/* + * This comment block is used by fixdep. Please do not remove. + * + * When CONFIG_MODVERSIONS is changed from n to y, all source files having + * EXPORT_SYMBOL variants must be re-compiled because genksyms is run as a + * side effect of the *.o build rule. + */ + #ifndef KSYM_FUNC #define KSYM_FUNC(x) x #endif @@ -12,9 +20,6 @@ #else #define KSYM_ALIGN 4 #endif -#ifndef KCRC_ALIGN -#define KCRC_ALIGN 4 -#endif .macro __put, val, name #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS @@ -43,17 +48,6 @@ __ksymtab_\name: __kstrtab_\name: .asciz "\name" .previous -#ifdef CONFIG_MODVERSIONS - .section ___kcrctab\sec+\name,"a" - .balign KCRC_ALIGN -#if defined(CONFIG_MODULE_REL_CRCS) - .long __crc_\name - . -#else - .long __crc_\name -#endif - .weak __crc_\name - .previous -#endif #endif .endm diff --git a/include/linux/export-internal.h b/include/linux/export-internal.h new file mode 100644 index 000000000000..c2b1d4fd5987 --- /dev/null +++ b/include/linux/export-internal.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Please do not include this explicitly. + * This is used by C files generated by modpost. + */ + +#ifndef __LINUX_EXPORT_INTERNAL_H__ +#define __LINUX_EXPORT_INTERNAL_H__ + +#include +#include + +/* __used is needed to keep __crc_* for LTO */ +#define SYMBOL_CRC(sym, crc, sec) \ + u32 __section("___kcrctab" sec "+" #sym) __used __crc_##sym = crc + +#endif /* __LINUX_EXPORT_INTERNAL_H__ */ diff --git a/include/linux/export.h b/include/linux/export.h index 27d848712b90..565c5ffcb26f 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -11,6 +11,14 @@ * hackers place grumpy comments in header files. */ +/* + * This comment block is used by fixdep. Please do not remove. + * + * When CONFIG_MODVERSIONS is changed from n to y, all source files having + * EXPORT_SYMBOL variants must be re-compiled because genksyms is run as a + * side effect of the *.o build rule. + */ + #ifndef __ASSEMBLY__ #ifdef MODULE extern struct module __this_module; @@ -19,26 +27,6 @@ extern struct module __this_module; #define THIS_MODULE ((struct module *)0) #endif -#ifdef CONFIG_MODVERSIONS -/* Mark the CRC weak since genksyms apparently decides not to - * generate a checksums for some symbols */ -#if defined(CONFIG_MODULE_REL_CRCS) -#define __CRC_SYMBOL(sym, sec) \ - asm(" .section \"___kcrctab" sec "+" #sym "\", \"a\" \n" \ - " .weak __crc_" #sym " \n" \ - " .long __crc_" #sym " - . \n" \ - " .previous \n") -#else -#define __CRC_SYMBOL(sym, sec) \ - asm(" .section \"___kcrctab" sec "+" #sym "\", \"a\" \n" \ - " .weak __crc_" #sym " \n" \ - " .long __crc_" #sym " \n" \ - " .previous \n") -#endif -#else -#define __CRC_SYMBOL(sym, sec) -#endif - #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS #include /* @@ -85,7 +73,6 @@ struct kernel_symbol { /* * For every exported symbol, do the following: * - * - If applicable, place a CRC entry in the __kcrctab section. * - Put the name of the symbol and namespace (empty string "" for none) in * __ksymtab_strings. * - Place a struct kernel_symbol entry in the __ksymtab section. @@ -98,7 +85,6 @@ struct kernel_symbol { extern typeof(sym) sym; \ extern const char __kstrtab_##sym[]; \ extern const char __kstrtabns_##sym[]; \ - __CRC_SYMBOL(sym, sec); \ asm(" .section \"__ksymtab_strings\",\"aMS\",%progbits,1 \n" \ "__kstrtab_" #sym ": \n" \ " .asciz \"" #sym "\" \n" \ -- cgit v1.2.3 From 83567cee0472fb7b57cc6e931ab002aeb69a26d4 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Sat, 21 May 2022 13:11:36 +0200 Subject: RDMA/core: Fix typo in comment Spelling mistake (triple letters) in comment. Detected with the help of Coccinelle. Link: https://lore.kernel.org/r/20220521111145.81697-86-Julia.Lawall@inria.fr Signed-off-by: Julia Lawall Signed-off-by: Jason Gunthorpe --- include/rdma/ib_verbs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index b0bc9de5e9a8..9c6317cf80d5 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -578,7 +578,7 @@ struct rdma_stat_desc { /** * struct rdma_hw_stats * @lock - Mutex to protect parallel write access to lifespan and values - * of counters, which are 64bits and not guaranteeed to be written + * of counters, which are 64bits and not guaranteed to be written * atomicaly on 32bits systems. * @timestamp - Used by the core code to track when the last update was * @lifespan - Used by the core code to determine how old the counters -- cgit v1.2.3 From 421cfe6596f6cb316991c02bf30a93bd81092853 Mon Sep 17 00:00:00 2001 From: Matthew Rosato Date: Thu, 19 May 2022 14:33:11 -0400 Subject: vfio: remove VFIO_GROUP_NOTIFY_SET_KVM Rather than relying on a notifier for associating the KVM with the group, let's assume that the association has already been made prior to device_open. The first time a device is opened associate the group KVM with the device. This fixes a user-triggerable oops in GVT. Reviewed-by: Tony Krowiak Reviewed-by: Kevin Tian Reviewed-by: Christoph Hellwig Signed-off-by: Jason Gunthorpe Signed-off-by: Matthew Rosato Reviewed-by: Jason Gunthorpe Acked-by: Zhi Wang Link: https://lore.kernel.org/r/20220519183311.582380-2-mjrosato@linux.ibm.com Signed-off-by: Alex Williamson --- include/linux/vfio.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 45b287826ce6..aa888cc51757 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -36,6 +36,8 @@ struct vfio_device { struct vfio_device_set *dev_set; struct list_head dev_set_list; unsigned int migration_flags; + /* Driver must reference the kvm during open_device or never touch it */ + struct kvm *kvm; /* Members below here are private, not for driver use */ refcount_t refcount; @@ -155,15 +157,11 @@ extern int vfio_dma_rw(struct vfio_device *device, dma_addr_t user_iova, /* each type has independent events */ enum vfio_notify_type { VFIO_IOMMU_NOTIFY = 0, - VFIO_GROUP_NOTIFY = 1, }; /* events for VFIO_IOMMU_NOTIFY */ #define VFIO_IOMMU_NOTIFY_DMA_UNMAP BIT(0) -/* events for VFIO_GROUP_NOTIFY */ -#define VFIO_GROUP_NOTIFY_SET_KVM BIT(0) - extern int vfio_register_notifier(struct vfio_device *device, enum vfio_notify_type type, unsigned long *required_events, -- cgit v1.2.3 From eadb2f47a3ced5c64b23b90fd2a3463f63726066 Mon Sep 17 00:00:00 2001 From: Daniel Thompson Date: Mon, 23 May 2022 19:11:02 +0100 Subject: lockdown: also lock down previous kgdb use KGDB and KDB allow read and write access to kernel memory, and thus should be restricted during lockdown. An attacker with access to a serial port (for example, via a hypervisor console, which some cloud vendors provide over the network) could trigger the debugger so it is important that the debugger respect the lockdown mode when/if it is triggered. Fix this by integrating lockdown into kdb's existing permissions mechanism. Unfortunately kgdb does not have any permissions mechanism (although it certainly could be added later) so, for now, kgdb is simply and brutally disabled by immediately exiting the gdb stub without taking any action. For lockdowns established early in the boot (e.g. the normal case) then this should be fine but on systems where kgdb has set breakpoints before the lockdown is enacted than "bad things" will happen. CVE: CVE-2022-21499 Co-developed-by: Stephen Brennan Signed-off-by: Stephen Brennan Reviewed-by: Douglas Anderson Signed-off-by: Daniel Thompson Signed-off-by: Linus Torvalds --- include/linux/security.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/security.h b/include/linux/security.h index 25b3ef71f495..7fc4e9f49f54 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -121,10 +121,12 @@ enum lockdown_reason { LOCKDOWN_DEBUGFS, LOCKDOWN_XMON_WR, LOCKDOWN_BPF_WRITE_USER, + LOCKDOWN_DBG_WRITE_KERNEL, LOCKDOWN_INTEGRITY_MAX, LOCKDOWN_KCORE, LOCKDOWN_KPROBES, LOCKDOWN_BPF_READ_KERNEL, + LOCKDOWN_DBG_READ_KERNEL, LOCKDOWN_PERF, LOCKDOWN_TRACEFS, LOCKDOWN_XMON_RW, -- cgit v1.2.3 From e5499dd7253c8382d03f687f19a854adcc688357 Mon Sep 17 00:00:00 2001 From: Sean Young Date: Wed, 25 May 2022 14:08:30 +0100 Subject: media: lirc: revert removal of unused feature flags Commit b2a90f4fcb14 ("media: lirc: remove unused lirc features") removed feature flags which were never implemented, but they are still used by the lirc daemon went built from source. Reinstate these symbols in order not to break the lirc build. Fixes: b2a90f4fcb14 ("media: lirc: remove unused lirc features") Link: https://lore.kernel.org/all/a0470450-ecfd-2918-e04a-7b57c1fd7694@kernel.org/ Reported-by: Jiri Slaby Cc: Mauro Carvalho Chehab Signed-off-by: Sean Young Signed-off-by: Linus Torvalds --- include/uapi/linux/lirc.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/lirc.h b/include/uapi/linux/lirc.h index 23b0f2c8ba81..8d7ca7c6af42 100644 --- a/include/uapi/linux/lirc.h +++ b/include/uapi/linux/lirc.h @@ -84,6 +84,13 @@ #define LIRC_CAN_SEND(x) ((x)&LIRC_CAN_SEND_MASK) #define LIRC_CAN_REC(x) ((x)&LIRC_CAN_REC_MASK) +/* + * Unused features. These features were never implemented, in tree or + * out of tree. These definitions are here so not to break the lircd build. + */ +#define LIRC_CAN_SET_REC_FILTER 0 +#define LIRC_CAN_NOTIFY_DECODE 0 + /*** IOCTL commands for lirc driver ***/ #define LIRC_GET_FEATURES _IOR('i', 0x00000000, __u32) -- cgit v1.2.3 From caa28984163cb63ea0be4cb8dbf05defdc7303f9 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 25 May 2022 09:02:19 -0700 Subject: linux/types.h: reinstate "__bitwise__" macro for user space use Commit c724c866bb70 ("linux/types.h: remove unnecessary __bitwise__") was right that there are no users of __bitwise__ in the kernel, but it turns out there are user space users of it that do expect it. It is, after all, in the uapi directory, so user space usage is to be expected. Instead of reverting the commit completely, let's just clarify the situation so that it doesn't happen again, and have some in-code explanations for why that "__bitwise__" still exists. Reported-by: Jiri Slaby Cc: Bjorn Helgaas Link: https://lore.kernel.org/all/b5c0a68d-8387-4909-beea-f70ab9e6e3d5@kernel.org/ Signed-off-by: Linus Torvalds --- include/uapi/linux/types.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/types.h b/include/uapi/linux/types.h index c4dc597f3dcf..308433be33c2 100644 --- a/include/uapi/linux/types.h +++ b/include/uapi/linux/types.h @@ -26,6 +26,9 @@ #define __bitwise #endif +/* The kernel doesn't use this legacy form, but user space does */ +#define __bitwise__ __bitwise + typedef __u16 __bitwise __le16; typedef __u16 __bitwise __be16; typedef __u32 __bitwise __le32; -- cgit v1.2.3 From 185194f19134716f32b2ab04ac76cf93ea85706a Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Tue, 17 May 2022 09:58:14 +0300 Subject: include/trace/events/mmflags.h: cleanup for "tracing: incorrect gfp_t conversion" Redefines __def_gfpflag_names array according to akpm@, willy@ and Joe Perches recommendations. Link: https://lkml.kernel.org/r/6f811e19-41c6-f3e8-fca6-23a19a62e313@openvz.org Fixes: fe573327ffb1 ("tracing: incorrect gfp_t conversion") Signed-off-by: Vasily Averin Cc: Matthew Wilcox Cc: Joe Perches Cc: Steven Rostedt Signed-off-by: Andrew Morton --- include/trace/events/mmflags.h | 84 +++++++++++++++++++++--------------------- 1 file changed, 43 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index fcb1ffb2cc8d..e87cb2b80ed3 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -13,49 +13,51 @@ * Thus most bits set go first. */ -#define __def_gfpflag_names \ - {(__force unsigned long)GFP_TRANSHUGE, "GFP_TRANSHUGE"}, \ - {(__force unsigned long)GFP_TRANSHUGE_LIGHT, "GFP_TRANSHUGE_LIGHT"}, \ - {(__force unsigned long)GFP_HIGHUSER_MOVABLE, "GFP_HIGHUSER_MOVABLE"},\ - {(__force unsigned long)GFP_HIGHUSER, "GFP_HIGHUSER"}, \ - {(__force unsigned long)GFP_USER, "GFP_USER"}, \ - {(__force unsigned long)GFP_KERNEL_ACCOUNT, "GFP_KERNEL_ACCOUNT"}, \ - {(__force unsigned long)GFP_KERNEL, "GFP_KERNEL"}, \ - {(__force unsigned long)GFP_NOFS, "GFP_NOFS"}, \ - {(__force unsigned long)GFP_ATOMIC, "GFP_ATOMIC"}, \ - {(__force unsigned long)GFP_NOIO, "GFP_NOIO"}, \ - {(__force unsigned long)GFP_NOWAIT, "GFP_NOWAIT"}, \ - {(__force unsigned long)GFP_DMA, "GFP_DMA"}, \ - {(__force unsigned long)__GFP_HIGHMEM, "__GFP_HIGHMEM"}, \ - {(__force unsigned long)GFP_DMA32, "GFP_DMA32"}, \ - {(__force unsigned long)__GFP_HIGH, "__GFP_HIGH"}, \ - {(__force unsigned long)__GFP_ATOMIC, "__GFP_ATOMIC"}, \ - {(__force unsigned long)__GFP_IO, "__GFP_IO"}, \ - {(__force unsigned long)__GFP_FS, "__GFP_FS"}, \ - {(__force unsigned long)__GFP_NOWARN, "__GFP_NOWARN"}, \ - {(__force unsigned long)__GFP_RETRY_MAYFAIL, "__GFP_RETRY_MAYFAIL"}, \ - {(__force unsigned long)__GFP_NOFAIL, "__GFP_NOFAIL"}, \ - {(__force unsigned long)__GFP_NORETRY, "__GFP_NORETRY"}, \ - {(__force unsigned long)__GFP_COMP, "__GFP_COMP"}, \ - {(__force unsigned long)__GFP_ZERO, "__GFP_ZERO"}, \ - {(__force unsigned long)__GFP_NOMEMALLOC, "__GFP_NOMEMALLOC"}, \ - {(__force unsigned long)__GFP_MEMALLOC, "__GFP_MEMALLOC"}, \ - {(__force unsigned long)__GFP_HARDWALL, "__GFP_HARDWALL"}, \ - {(__force unsigned long)__GFP_THISNODE, "__GFP_THISNODE"}, \ - {(__force unsigned long)__GFP_RECLAIMABLE, "__GFP_RECLAIMABLE"}, \ - {(__force unsigned long)__GFP_MOVABLE, "__GFP_MOVABLE"}, \ - {(__force unsigned long)__GFP_ACCOUNT, "__GFP_ACCOUNT"}, \ - {(__force unsigned long)__GFP_WRITE, "__GFP_WRITE"}, \ - {(__force unsigned long)__GFP_RECLAIM, "__GFP_RECLAIM"}, \ - {(__force unsigned long)__GFP_DIRECT_RECLAIM, "__GFP_DIRECT_RECLAIM"},\ - {(__force unsigned long)__GFP_KSWAPD_RECLAIM, "__GFP_KSWAPD_RECLAIM"},\ - {(__force unsigned long)__GFP_ZEROTAGS, "__GFP_ZEROTAGS"} \ +#define gfpflag_string(flag) {(__force unsigned long)flag, #flag} + +#define __def_gfpflag_names \ + gfpflag_string(GFP_TRANSHUGE), \ + gfpflag_string(GFP_TRANSHUGE_LIGHT), \ + gfpflag_string(GFP_HIGHUSER_MOVABLE), \ + gfpflag_string(GFP_HIGHUSER), \ + gfpflag_string(GFP_USER), \ + gfpflag_string(GFP_KERNEL_ACCOUNT), \ + gfpflag_string(GFP_KERNEL), \ + gfpflag_string(GFP_NOFS), \ + gfpflag_string(GFP_ATOMIC), \ + gfpflag_string(GFP_NOIO), \ + gfpflag_string(GFP_NOWAIT), \ + gfpflag_string(GFP_DMA), \ + gfpflag_string(__GFP_HIGHMEM), \ + gfpflag_string(GFP_DMA32), \ + gfpflag_string(__GFP_HIGH), \ + gfpflag_string(__GFP_ATOMIC), \ + gfpflag_string(__GFP_IO), \ + gfpflag_string(__GFP_FS), \ + gfpflag_string(__GFP_NOWARN), \ + gfpflag_string(__GFP_RETRY_MAYFAIL), \ + gfpflag_string(__GFP_NOFAIL), \ + gfpflag_string(__GFP_NORETRY), \ + gfpflag_string(__GFP_COMP), \ + gfpflag_string(__GFP_ZERO), \ + gfpflag_string(__GFP_NOMEMALLOC), \ + gfpflag_string(__GFP_MEMALLOC), \ + gfpflag_string(__GFP_HARDWALL), \ + gfpflag_string(__GFP_THISNODE), \ + gfpflag_string(__GFP_RECLAIMABLE), \ + gfpflag_string(__GFP_MOVABLE), \ + gfpflag_string(__GFP_ACCOUNT), \ + gfpflag_string(__GFP_WRITE), \ + gfpflag_string(__GFP_RECLAIM), \ + gfpflag_string(__GFP_DIRECT_RECLAIM), \ + gfpflag_string(__GFP_KSWAPD_RECLAIM), \ + gfpflag_string(__GFP_ZEROTAGS) #ifdef CONFIG_KASAN_HW_TAGS -#define __def_gfpflag_names_kasan , \ - {(__force unsigned long)__GFP_SKIP_ZERO, "__GFP_SKIP_ZERO"}, \ - {(__force unsigned long)__GFP_SKIP_KASAN_POISON, "__GFP_SKIP_KASAN_POISON"}, \ - {(__force unsigned long)__GFP_SKIP_KASAN_UNPOISON, "__GFP_SKIP_KASAN_UNPOISON"} +#define __def_gfpflag_names_kasan , \ + gfpflag_string(__GFP_SKIP_ZERO), \ + gfpflag_string(__GFP_SKIP_KASAN_POISON), \ + gfpflag_string(__GFP_SKIP_KASAN_UNPOISON) #else #define __def_gfpflag_names_kasan #endif -- cgit v1.2.3 From e5c3f619a04d9e191de66d5f8e069367f73a6487 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Tue, 17 May 2022 09:55:51 +0300 Subject: include/trace/events/percpu.h: cleanup for "percpu: improve percpu_alloc_percpu event trace" Fix sparse warning about incorrect gfp_t cast. Link: https://lkml.kernel.org/r/001979f3-e978-0998-cbed-61a4a2ac87b8@openvz.org Fixes: f67bed134a05 ("percpu: improve percpu_alloc_percpu event trace") Signed-off-by: Vasily Averin Signed-off-by: Andrew Morton --- include/trace/events/percpu.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/percpu.h b/include/trace/events/percpu.h index e989cefc0def..5b8211ca8950 100644 --- a/include/trace/events/percpu.h +++ b/include/trace/events/percpu.h @@ -28,7 +28,7 @@ TRACE_EVENT(percpu_alloc_percpu, __field( int, off ) __field( void __percpu *, ptr ) __field( size_t, bytes_alloc ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->call_site = call_site; @@ -40,7 +40,7 @@ TRACE_EVENT(percpu_alloc_percpu, __entry->off = off; __entry->ptr = ptr; __entry->bytes_alloc = bytes_alloc; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("call_site=%pS reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p bytes_alloc=%zu gfp_flags=%s", -- cgit v1.2.3 From 4934609dda03ec90ca5052deecbe455b09a44e21 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Mon, 23 May 2022 16:17:06 +0000 Subject: amt: fix typo in amt AMT_MSG_TEARDOWM is defined, But it should be AMT_MSG_TEARDOWN. Fixes: b9022b53adad ("amt: add control plane of amt interface") Signed-off-by: Taehee Yoo Signed-off-by: Jakub Kicinski --- include/net/amt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/amt.h b/include/net/amt.h index 7a4db8b903ee..0e40c3d64fcf 100644 --- a/include/net/amt.h +++ b/include/net/amt.h @@ -15,7 +15,7 @@ enum amt_msg_type { AMT_MSG_MEMBERSHIP_QUERY, AMT_MSG_MEMBERSHIP_UPDATE, AMT_MSG_MULTICAST_DATA, - AMT_MSG_TEARDOWM, + AMT_MSG_TEARDOWN, __AMT_MSG_MAX, }; -- cgit v1.2.3 From 50e35bd57c02a584442c0aa917787c858eabe80b Mon Sep 17 00:00:00 2001 From: pengfuyuan Date: Thu, 26 May 2022 14:27:57 +0800 Subject: video: fbdev: radeon: Fix spelling typo in comment Fix spelling typo in comment. Signed-off-by: pengfuyuan Signed-off-by: Helge Deller --- include/video/radeon.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/video/radeon.h b/include/video/radeon.h index 005eae19ec09..72f94ccfa725 100644 --- a/include/video/radeon.h +++ b/include/video/radeon.h @@ -750,7 +750,7 @@ #define WAIT_DMA_GUI_IDLE (1 << 9) #define WAIT_2D_IDLECLEAN (1 << 16) -/* SURFACE_CNTL bit consants */ +/* SURFACE_CNTL bit constants */ #define SURF_TRANSLATION_DIS (1 << 8) #define NONSURF_AP0_SWP_16BPP (1 << 20) #define NONSURF_AP0_SWP_32BPP (1 << 21) -- cgit v1.2.3 From d534ca7128d7bf681ed6d462c09b9d6ffb3bed91 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 23 May 2022 11:24:31 -0400 Subject: drm/amdgpu: differentiate between LP and non-LP DDR memory Some applications want to know whether the memory is LP or not. Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 9a1d210d135d..d9d475d65c76 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -988,6 +988,8 @@ struct drm_amdgpu_info_vbios { #define AMDGPU_VRAM_TYPE_DDR4 8 #define AMDGPU_VRAM_TYPE_GDDR6 9 #define AMDGPU_VRAM_TYPE_DDR5 10 +#define AMDGPU_VRAM_TYPE_LPDDR4 11 +#define AMDGPU_VRAM_TYPE_LPDDR5 12 struct drm_amdgpu_info_device { /** PCI Device ID */ -- cgit v1.2.3 From fab2cc8335839867a3db38f195441b9c7c6460f6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Fri, 6 May 2022 13:08:34 +0200 Subject: drm/amdgpu: add AMDGPU_GEM_CREATE_DISCARDABLE MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a AMDGPU_GEM_CREATE_DISCARDABLE flag to note that the content of a BO doesn't needs to be preserved during eviction. KFD was already using a similar functionality for SVM BOs so replace the internal flag with the new UAPI. Signed-off-by: Christian König Reviewed-by: Alex Deucher Reviewed-by: Marek Olšák Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index d9d475d65c76..a81bef5cfeaa 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -140,6 +140,10 @@ extern "C" { * not require GTT memory accounting */ #define AMDGPU_GEM_CREATE_PREEMPTIBLE (1 << 11) +/* Flag that BO can be discarded under memory pressure without keeping the + * content. + */ +#define AMDGPU_GEM_CREATE_DISCARDABLE (1 << 12) struct drm_amdgpu_gem_create_in { /** the requested memory size */ -- cgit v1.2.3 From b6c65a2c92aa880e8050a91ca83288b85fc32575 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Fri, 6 May 2022 13:11:41 +0200 Subject: drm/amdgpu: add AMDGPU_VM_NOALLOC v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add the AMDGPU_VM_NOALLOC flag to let userspace control MALL allocation. v2: also add the flag to the allowed flags. Signed-off-by: Christian König Reviewed-by: Alex Deucher (v1) Reviewed-by: Marek Olšák Signed-off-by: Alex Deucher --- include/uapi/drm/amdgpu_drm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index a81bef5cfeaa..18d3246d636e 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -533,6 +533,8 @@ struct drm_amdgpu_gem_op { #define AMDGPU_VM_MTYPE_UC (4 << 5) /* Use Read Write MTYPE instead of default MTYPE */ #define AMDGPU_VM_MTYPE_RW (5 << 5) +/* don't allocate MALL */ +#define AMDGPU_VM_PAGE_NOALLOC (1 << 9) struct drm_amdgpu_gem_va { /** GEM object handle */ -- cgit v1.2.3 From 43994049180704fd1faf78623fabd9a5cd443708 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 4 May 2022 12:36:31 +0900 Subject: kprobes: Fix build errors with CONFIG_KRETPROBES=n MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Max Filippov reported: When building kernel with CONFIG_KRETPROBES=n kernel/kprobes.c compilation fails with the following messages: kernel/kprobes.c: In function ‘recycle_rp_inst’: kernel/kprobes.c:1273:32: error: implicit declaration of function ‘get_kretprobe’ kernel/kprobes.c: In function ‘kprobe_flush_task’: kernel/kprobes.c:1299:35: error: ‘struct task_struct’ has no member named ‘kretprobe_instances’ This came from the commit d741bf41d7c7 ("kprobes: Remove kretprobe hash") which introduced get_kretprobe() and kretprobe_instances member in task_struct when CONFIG_KRETPROBES=y, but did not make recycle_rp_inst() and kprobe_flush_task() depending on CONFIG_KRETPORBES. Since those functions are only used for kretprobe, move those functions into #ifdef CONFIG_KRETPROBE area. Link: https://lkml.kernel.org/r/165163539094.74407.3838114721073251225.stgit@devnote2 Reported-by: Max Filippov Fixes: d741bf41d7c7 ("kprobes: Remove kretprobe hash") Cc: "Naveen N . Rao" Cc: Anil S Keshavamurthy Cc: "David S . Miller" Cc: Peter Zijlstra Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu Tested-by: Max Filippov Signed-off-by: Steven Rostedt (Google) --- include/linux/kprobes.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 157168769fc2..55041d2f884d 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -424,7 +424,7 @@ void unregister_kretprobe(struct kretprobe *rp); int register_kretprobes(struct kretprobe **rps, int num); void unregister_kretprobes(struct kretprobe **rps, int num); -#ifdef CONFIG_KRETPROBE_ON_RETHOOK +#if defined(CONFIG_KRETPROBE_ON_RETHOOK) || !defined(CONFIG_KRETPROBES) #define kprobe_flush_task(tk) do {} while (0) #else void kprobe_flush_task(struct task_struct *tk); -- cgit v1.2.3 From 3a2bfec0b02f2226ff3376a5d2ff604d799bd7ea Mon Sep 17 00:00:00 2001 From: Li kunyu Date: Wed, 18 May 2022 10:36:40 +0800 Subject: ftrace: Remove return value of ftrace_arch_modify_*() All instances of the function ftrace_arch_modify_prepare() and ftrace_arch_modify_post_process() return zero. There's no point in checking their return value. Just have them be void functions. Link: https://lkml.kernel.org/r/20220518023639.4065-1-kunyu@nfschina.com Signed-off-by: Li kunyu Signed-off-by: Steven Rostedt (Google) --- include/linux/ftrace.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 4816b7e11047..a5f74f6e7e4e 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -449,8 +449,8 @@ static inline void stack_tracer_enable(void) { } #ifdef CONFIG_DYNAMIC_FTRACE -int ftrace_arch_code_modify_prepare(void); -int ftrace_arch_code_modify_post_process(void); +void ftrace_arch_code_modify_prepare(void); +void ftrace_arch_code_modify_post_process(void); enum ftrace_bug_type { FTRACE_BUG_UNKNOWN, -- cgit v1.2.3 From a54ce3703613e41fe1d98060b62ec09a3984dc28 Mon Sep 17 00:00:00 2001 From: Vincent Ray Date: Wed, 25 May 2022 17:17:46 -0700 Subject: net: sched: fixed barrier to prevent skbuff sticking in qdisc backlog In qdisc_run_begin(), smp_mb__before_atomic() used before test_bit() does not provide any ordering guarantee as test_bit() is not an atomic operation. This, added to the fact that the spin_trylock() call at the beginning of qdisc_run_begin() does not guarantee acquire semantics if it does not grab the lock, makes it possible for the following statement : if (test_bit(__QDISC_STATE_MISSED, &qdisc->state)) to be executed before an enqueue operation called before qdisc_run_begin(). As a result the following race can happen : CPU 1 CPU 2 qdisc_run_begin() qdisc_run_begin() /* true */ set(MISSED) . /* returns false */ . . /* sees MISSED = 1 */ . /* so qdisc not empty */ . __qdisc_run() . . . pfifo_fast_dequeue() ----> /* may be done here */ . | . clear(MISSED) | . . | . smp_mb __after_atomic(); | . . | . /* recheck the queue */ | . /* nothing => exit */ | enqueue(skb1) | . | qdisc_run_begin() | . | spin_trylock() /* fail */ | . | smp_mb__before_atomic() /* not enough */ | . ---- if (test_bit(MISSED)) return false; /* exit */ In the above scenario, CPU 1 and CPU 2 both try to grab the qdisc->seqlock at the same time. Only CPU 2 succeeds and enters the bypass code path, where it emits its skb then calls __qdisc_run(). CPU1 fails, sets MISSED and goes down the traditionnal enqueue() + dequeue() code path. But when executing qdisc_run_begin() for the second time, after enqueuing its skbuff, it sees the MISSED bit still set (by itself) and consequently chooses to exit early without setting it again nor trying to grab the spinlock again. Meanwhile CPU2 has seen MISSED = 1, cleared it, checked the queue and found it empty, so it returned. At the end of the sequence, we end up with skb1 enqueued in the backlog, both CPUs out of __dev_xmit_skb(), the MISSED bit not set, and no __netif_schedule() called made. skb1 will now linger in the qdisc until somebody later performs a full __qdisc_run(). Associated to the bypass capacity of the qdisc, and the ability of the TCP layer to avoid resending packets which it knows are still in the qdisc, this can lead to serious traffic "holes" in a TCP connection. We fix this by replacing the smp_mb__before_atomic() / test_bit() / set_bit() / smp_mb__after_atomic() sequence inside qdisc_run_begin() by a single test_and_set_bit() call, which is more concise and enforces the needed memory barriers. Fixes: 89837eb4b246 ("net: sched: add barrier to ensure correct ordering for lockless qdisc") Signed-off-by: Vincent Ray Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20220526001746.2437669-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/net/sch_generic.h | 36 ++++++++---------------------------- 1 file changed, 8 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 9bab396c1f3b..80973ce820f3 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -187,37 +187,17 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc) if (spin_trylock(&qdisc->seqlock)) return true; - /* Paired with smp_mb__after_atomic() to make sure - * STATE_MISSED checking is synchronized with clearing - * in pfifo_fast_dequeue(). + /* No need to insist if the MISSED flag was already set. + * Note that test_and_set_bit() also gives us memory ordering + * guarantees wrt potential earlier enqueue() and below + * spin_trylock(), both of which are necessary to prevent races */ - smp_mb__before_atomic(); - - /* If the MISSED flag is set, it means other thread has - * set the MISSED flag before second spin_trylock(), so - * we can return false here to avoid multi cpus doing - * the set_bit() and second spin_trylock() concurrently. - */ - if (test_bit(__QDISC_STATE_MISSED, &qdisc->state)) + if (test_and_set_bit(__QDISC_STATE_MISSED, &qdisc->state)) return false; - /* Set the MISSED flag before the second spin_trylock(), - * if the second spin_trylock() return false, it means - * other cpu holding the lock will do dequeuing for us - * or it will see the MISSED flag set after releasing - * lock and reschedule the net_tx_action() to do the - * dequeuing. - */ - set_bit(__QDISC_STATE_MISSED, &qdisc->state); - - /* spin_trylock() only has load-acquire semantic, so use - * smp_mb__after_atomic() to ensure STATE_MISSED is set - * before doing the second spin_trylock(). - */ - smp_mb__after_atomic(); - - /* Retry again in case other CPU may not see the new flag - * after it releases the lock at the end of qdisc_run_end(). + /* Try to take the lock again to make sure that we will either + * grab it or the CPU that still has it will see MISSED set + * when testing it in qdisc_run_end() */ return spin_trylock(&qdisc->seqlock); } -- cgit v1.2.3 From 49f8b459fc1de5e3712b57c8ccefae9ec45270f8 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 24 May 2022 13:46:30 +0200 Subject: xen: switch gnttab_end_foreign_access() to take a struct page pointer Instead of a virtual kernel address use a pointer of the associated struct page as second parameter of gnttab_end_foreign_access(). Most users have that pointer available already and are creating the virtual address from it, risking problems in case the memory is located in highmem. gnttab_end_foreign_access() itself won't need to get the struct page from the address again. Suggested-by: Jan Beulich Signed-off-by: Juergen Gross Reviewed-by: Jan Beulich Signed-off-by: Juergen Gross --- include/xen/grant_table.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index 7d0f2f0037b8..527c9907f99c 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -101,10 +101,10 @@ int gnttab_end_foreign_access_ref(grant_ref_t ref); * Eventually end access through the given grant reference, and once that * access has been ended, free the given page too. Access will be ended * immediately iff the grant entry is not in use, otherwise it will happen - * some time later. page may be 0, in which case no freeing will occur. + * some time later. page may be NULL, in which case no freeing will occur. * Note that the granted page might still be accessed (read or write) by the * other side after gnttab_end_foreign_access() returns, so even if page was - * specified as 0 it is not allowed to just reuse the page for other + * specified as NULL it is not allowed to just reuse the page for other * purposes immediately. gnttab_end_foreign_access() will take an additional * reference to the granted page in this case, which is dropped only after * the grant is no longer in use. @@ -112,7 +112,7 @@ int gnttab_end_foreign_access_ref(grant_ref_t ref); * gnttab_end_foreign_access() are done via alloc_pages_exact() (and freeing * via free_pages_exact()) in order to avoid high order pages. */ -void gnttab_end_foreign_access(grant_ref_t ref, unsigned long page); +void gnttab_end_foreign_access(grant_ref_t ref, struct page *page); /* * End access through the given grant reference, iff the grant entry is -- cgit v1.2.3 From 56b14ecec97f39118bf85c9ac2438c5a949509ed Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 20 May 2022 00:02:04 +0200 Subject: netfilter: conntrack: re-fetch conntrack after insertion In case the conntrack is clashing, insertion can free skb->_nfct and set skb->_nfct to the already-confirmed entry. This wasn't found before because the conntrack entry and the extension space used to free'd after an rcu grace period, plus the race needs events enabled to trigger. Reported-by: Fixes: 71d8c47fc653 ("netfilter: conntrack: introduce clash resolution on insertion race") Fixes: 2ad9d7747c10 ("netfilter: conntrack: free extension area immediately") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_core.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 6406cfee34c2..37866c8386e2 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -58,8 +58,13 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb) int ret = NF_ACCEPT; if (ct) { - if (!nf_ct_is_confirmed(ct)) + if (!nf_ct_is_confirmed(ct)) { ret = __nf_conntrack_confirm(skb); + + if (ret == NF_ACCEPT) + ct = (struct nf_conn *)skb_nfct(skb); + } + if (ret == NF_ACCEPT && nf_ct_ecache_exist(ct)) nf_ct_deliver_cached_events(ct); } -- cgit v1.2.3 From 656d054e0a15ec327bd82801ccd58201e59f6896 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 2 May 2022 12:30:20 +0200 Subject: jump_label,noinstr: Avoid instrumentation for JUMP_LABEL=n builds When building x86_64 with JUMP_LABEL=n it's possible for instrumentation to sneak into noinstr: vmlinux.o: warning: objtool: exit_to_user_mode+0x14: call to static_key_count.constprop.0() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_exit_to_user_mode+0x2d: call to static_key_count.constprop.0() leaves .noinstr.text section vmlinux.o: warning: objtool: irqentry_exit_to_user_mode+0x1b: call to static_key_count.constprop.0() leaves .noinstr.text section Switch to arch_ prefixed atomic to avoid the explicit instrumentation. Reported-by: kernel test robot Signed-off-by: Peter Zijlstra (Intel) --- include/linux/jump_label.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 107751cc047b..bf1eef337a07 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -256,9 +256,9 @@ extern void static_key_disable_cpuslocked(struct static_key *key); #include #include -static inline int static_key_count(struct static_key *key) +static __always_inline int static_key_count(struct static_key *key) { - return atomic_read(&key->enabled); + return arch_atomic_read(&key->enabled); } static __always_inline void jump_label_init(void) -- cgit v1.2.3 From 620f8d3bd3d5e82dff8cc591c831827d4beeae2e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sat, 7 May 2022 13:35:37 +0200 Subject: context_tracking: Always inline empty stubs Because GCC is seriously challenged.. vmlinux.o: warning: objtool: enter_from_user_mode+0x85: call to context_tracking_enabled() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_enter_from_user_mode+0x8f: call to context_tracking_enabled() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_enter_from_user_mode_prepare+0x85: call to context_tracking_enabled() leaves .noinstr.text section vmlinux.o: warning: objtool: irqentry_enter_from_user_mode+0x85: call to context_tracking_enabled() leaves .noinstr.text section Signed-off-by: Peter Zijlstra (Intel) Acked-by: Mark Rutland Link: https://lkml.kernel.org/r/20220526105958.134113388@infradead.org --- include/linux/context_tracking_state.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index 65a60d3313b0..ae1e63e26947 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -46,10 +46,10 @@ static __always_inline bool context_tracking_in_user(void) return __this_cpu_read(context_tracking.state) == CONTEXT_USER; } #else -static inline bool context_tracking_in_user(void) { return false; } -static inline bool context_tracking_enabled(void) { return false; } -static inline bool context_tracking_enabled_cpu(int cpu) { return false; } -static inline bool context_tracking_enabled_this_cpu(void) { return false; } +static __always_inline bool context_tracking_in_user(void) { return false; } +static __always_inline bool context_tracking_enabled(void) { return false; } +static __always_inline bool context_tracking_enabled_cpu(int cpu) { return false; } +static __always_inline bool context_tracking_enabled_this_cpu(void) { return false; } #endif /* CONFIG_CONTEXT_TRACKING */ #endif -- cgit v1.2.3 From b9684a71fca793213378dd410cd11675d973eaa1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 27 May 2022 07:58:06 +0200 Subject: block, loop: support partitions without scanning Historically we did distinguish between a flag that surpressed partition scanning, and a combinations of the minors variable and another flag if any partitions were supported. This was generally confusing and doesn't make much sense, but some corner case uses of the loop driver actually do want to support manually added partitions on a device that does not actively scan for partitions. To make things worsee the loop driver also wants to dynamically toggle the scanning for partitions on a live gendisk, which makes the disk->flags updates non-atomic. Introduce a new GD_SUPPRESS_PART_SCAN bit in disk->state that disables just scanning for partitions, and toggle that instead of GENHD_FL_NO_PART in the loop driver. Fixes: 1ebe2e5f9d68 ("block: remove GENHD_FL_EXT_DEVT") Reported-by: Ming Lei Signed-off-by: Christoph Hellwig Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20220527055806.1972352-1-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index afad3d1d0dac..691b4c15b8ce 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -147,6 +147,7 @@ struct gendisk { #define GD_DEAD 2 #define GD_NATIVE_CAPACITY 3 #define GD_ADDED 4 +#define GD_SUPPRESS_PART_SCAN 5 struct mutex open_mutex; /* open/close mutex */ unsigned open_partitions; /* number of open partitions */ -- cgit v1.2.3 From 3e35142ef99fe6b4fe5d834ad43ee13cca10a2dc Mon Sep 17 00:00:00 2001 From: "Naveen N. Rao" Date: Thu, 19 May 2022 14:42:37 +0530 Subject: kexec_file: drop weak attribute from arch_kexec_apply_relocations[_add] Since commit d1bcae833b32f1 ("ELF: Don't generate unused section symbols") [1], binutils (v2.36+) started dropping section symbols that it thought were unused. This isn't an issue in general, but with kexec_file.c, gcc is placing kexec_arch_apply_relocations[_add] into a separate .text.unlikely section and the section symbol ".text.unlikely" is being dropped. Due to this, recordmcount is unable to find a non-weak symbol in .text.unlikely to generate a relocation record against. Address this by dropping the weak attribute from these functions. Instead, follow the existing pattern of having architectures #define the name of the function they want to override in their headers. [1] https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=d1bcae833b32f1 [akpm@linux-foundation.org: arch/s390/include/asm/kexec.h needs linux/module.h] Link: https://lkml.kernel.org/r/20220519091237.676736-1-naveen.n.rao@linux.vnet.ibm.com Signed-off-by: Michael Ellerman Signed-off-by: Naveen N. Rao Cc: "Eric W. Biederman" Cc: Signed-off-by: Andrew Morton --- include/linux/kexec.h | 46 ++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 38 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 58d1b58a971e..fcd5035209f1 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -193,14 +193,6 @@ void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name); int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, unsigned long buf_len); void *arch_kexec_kernel_image_load(struct kimage *image); -int arch_kexec_apply_relocations_add(struct purgatory_info *pi, - Elf_Shdr *section, - const Elf_Shdr *relsec, - const Elf_Shdr *symtab); -int arch_kexec_apply_relocations(struct purgatory_info *pi, - Elf_Shdr *section, - const Elf_Shdr *relsec, - const Elf_Shdr *symtab); int arch_kimage_file_post_load_cleanup(struct kimage *image); #ifdef CONFIG_KEXEC_SIG int arch_kexec_kernel_verify_sig(struct kimage *image, void *buf, @@ -229,6 +221,44 @@ extern int crash_exclude_mem_range(struct crash_mem *mem, unsigned long long mend); extern int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map, void **addr, unsigned long *sz); + +#ifndef arch_kexec_apply_relocations_add +/* + * arch_kexec_apply_relocations_add - apply relocations of type RELA + * @pi: Purgatory to be relocated. + * @section: Section relocations applying to. + * @relsec: Section containing RELAs. + * @symtab: Corresponding symtab. + * + * Return: 0 on success, negative errno on error. + */ +static inline int +arch_kexec_apply_relocations_add(struct purgatory_info *pi, Elf_Shdr *section, + const Elf_Shdr *relsec, const Elf_Shdr *symtab) +{ + pr_err("RELA relocation unsupported.\n"); + return -ENOEXEC; +} +#endif + +#ifndef arch_kexec_apply_relocations +/* + * arch_kexec_apply_relocations - apply relocations of type REL + * @pi: Purgatory to be relocated. + * @section: Section relocations applying to. + * @relsec: Section containing RELs. + * @symtab: Corresponding symtab. + * + * Return: 0 on success, negative errno on error. + */ +static inline int +arch_kexec_apply_relocations(struct purgatory_info *pi, Elf_Shdr *section, + const Elf_Shdr *relsec, const Elf_Shdr *symtab) +{ + pr_err("REL relocation unsupported.\n"); + return -ENOEXEC; +} +#endif #endif /* CONFIG_KEXEC_FILE */ #ifdef CONFIG_KEXEC_ELF -- cgit v1.2.3 From 9f186f9e5fa9ebdaef909fd45f825a6ce281f13c Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 19 May 2022 20:50:26 +0800 Subject: mm/swapfile: unuse_pte can map random data if swap read fails Patch series "A few fixup patches for mm", v4. This series contains a few patches to avoid mapping random data if swap read fails and fix lost swap bits in unuse_pte. Also we free hwpoison and swapin error entry in madvise_free_pte_range and so on. More details can be found in the respective changelogs. This patch (of 5): There is a bug in unuse_pte(): when swap page happens to be unreadable, page filled with random data is mapped into user address space. In case of error, a special swap entry indicating swap read fails is set to the page table. So the swapcache page can be freed and the user won't end up with a permanently mounted swap because a sector is bad. And if the page is accessed later, the user process will be killed so that corrupted data is never consumed. On the other hand, if the page is never accessed, the user won't even notice it. Link: https://lkml.kernel.org/r/20220519125030.21486-1-linmiaohe@huawei.com Link: https://lkml.kernel.org/r/20220519125030.21486-2-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Acked-by: David Hildenbrand Cc: Hugh Dickins Cc: Matthew Wilcox (Oracle) Cc: Vlastimil Babka Cc: David Howells Cc: NeilBrown Cc: Alistair Popple Cc: Suren Baghdasaryan Cc: Peter Xu Cc: Ralph Campbell Cc: Naoya Horiguchi Signed-off-by: Andrew Morton --- include/linux/swap.h | 7 ++++++- include/linux/swapops.h | 10 ++++++++++ 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index f3ae17b43f20..0c0fed1b348f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -55,6 +55,10 @@ static inline int current_is_kswapd(void) * actions on faults. */ +#define SWP_SWAPIN_ERROR_NUM 1 +#define SWP_SWAPIN_ERROR (MAX_SWAPFILES + SWP_HWPOISON_NUM + \ + SWP_MIGRATION_NUM + SWP_DEVICE_NUM + \ + SWP_PTE_MARKER_NUM) /* * PTE markers are used to persist information onto PTEs that are mapped with * file-backed memories. As its name "PTE" hints, it should only be applied to @@ -120,7 +124,8 @@ static inline int current_is_kswapd(void) #define MAX_SWAPFILES \ ((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \ - SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - SWP_PTE_MARKER_NUM) + SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - \ + SWP_PTE_MARKER_NUM - SWP_SWAPIN_ERROR_NUM) /* * Magic header for a swap area. The first part of the union is diff --git a/include/linux/swapops.h b/include/linux/swapops.h index fe220df499f1..f24775b41880 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -108,6 +108,16 @@ static inline void *swp_to_radix_entry(swp_entry_t entry) return xa_mk_value(entry.val); } +static inline swp_entry_t make_swapin_error_entry(struct page *page) +{ + return swp_entry(SWP_SWAPIN_ERROR, page_to_pfn(page)); +} + +static inline int is_swapin_error_entry(swp_entry_t entry) +{ + return swp_type(entry) == SWP_SWAPIN_ERROR; +} + #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { -- cgit v1.2.3 From 1c563432588dbffa71e67ca6e37c826f9fa86e04 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Tue, 24 May 2022 10:15:25 -0700 Subject: mm: fix is_pinnable_page against a cma page Pages in the CMA area could have MIGRATE_ISOLATE as well as MIGRATE_CMA so the current is_pinnable_page() could miss CMA pages which have MIGRATE_ISOLATE. It ends up pinning CMA pages as longterm for the pin_user_pages() API so CMA allocations keep failing until the pin is released. CPU 0 CPU 1 - Task B cma_alloc alloc_contig_range pin_user_pages_fast(FOLL_LONGTERM) change pageblock as MIGRATE_ISOLATE internal_get_user_pages_fast lockless_pages_from_mm gup_pte_range try_grab_folio is_pinnable_page return true; So, pinned the page successfully. page migration failure with pinned page .. .. After 30 sec unpin_user_page(page) CMA allocation succeeded after 30 sec. The CMA allocation path protects the migration type change race using zone->lock but what GUP path need to know is just whether the page is on CMA area or not rather than exact migration type. Thus, we don't need zone->lock but just checks migration type in either of (MIGRATE_ISOLATE and MIGRATE_CMA). Adding the MIGRATE_ISOLATE check in is_pinnable_page could cause rejecting of pinning pages on MIGRATE_ISOLATE pageblocks even though it's neither CMA nor movable zone if the page is temporarily unmovable. However, such a migration failure by unexpected temporal refcount holding is general issue, not only come from MIGRATE_ISOLATE and the MIGRATE_ISOLATE is also transient state like other temporal elevated refcount problem. Link: https://lkml.kernel.org/r/20220524171525.976723-1-minchan@kernel.org Signed-off-by: Minchan Kim Reviewed-by: John Hubbard Acked-by: Paul E. McKenney Cc: David Hildenbrand Signed-off-by: Andrew Morton --- include/linux/mm.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index de32c0383387..93a46ff33dc2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1594,8 +1594,13 @@ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, #ifdef CONFIG_MIGRATION static inline bool is_pinnable_page(struct page *page) { - return !(is_zone_movable_page(page) || is_migrate_cma_page(page)) || - is_zero_pfn(page_to_pfn(page)); +#ifdef CONFIG_CMA + int mt = get_pageblock_migratetype(page); + + if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE) + return false; +#endif + return !(is_zone_movable_page(page) || is_zero_pfn(page_to_pfn(page))); } #else static inline bool is_pinnable_page(struct page *page) -- cgit v1.2.3 From 98d40e76652e9aeb3aec4065f600d633ed335e94 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Tue, 24 May 2022 07:56:30 +0200 Subject: block: document BLK_STS_AGAIN usage BLK_STS_AGAIN should only be used if RQF_NOWAIT is set and the bio would block. So we'd better document that to avoid accidental misuse. Signed-off-by: Hannes Reinecke Reviewed-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220524055631.85480-2-hare@suse.de Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 40e815400611..8b38367d1bc7 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -105,6 +105,10 @@ typedef u16 blk_short_t; /* hack for device mapper, don't use elsewhere: */ #define BLK_STS_DM_REQUEUE ((__force blk_status_t)11) +/* + * BLK_STS_AGAIN should only be returned if RQF_NOWAIT is set + * and the bio would block (cf bio_wouldblock_error()) + */ #define BLK_STS_AGAIN ((__force blk_status_t)12) /* -- cgit v1.2.3 From e2e530867245d051dc7800b0d07193b3e581f5b9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 24 May 2022 14:15:30 +0200 Subject: blk-mq: remove the done argument to blk_execute_rq_nowait Let the caller set it together with the end_io_data instead of passing a pointless argument. Note the the target code did in fact already set it and then just overrode it again by calling blk_execute_rq_nowait. Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Reviewed-by: Kanchan Joshi Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20220524121530.943123-4-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 9f07061418db..e2d9daf7e8dd 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -969,8 +969,7 @@ int blk_rq_unmap_user(struct bio *); int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t); int blk_rq_append_bio(struct request *rq, struct bio *bio); -void blk_execute_rq_nowait(struct request *rq, bool at_head, - rq_end_io_fn *end_io); +void blk_execute_rq_nowait(struct request *rq, bool at_head); blk_status_t blk_execute_rq(struct request *rq, bool at_head); struct req_iterator { -- cgit v1.2.3 From 47f15561b69e226bfc034e94ff6dbec51a4662af Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 28 May 2022 11:08:48 -0700 Subject: drm: fix EDID struct for old ARM OABI format When building the kernel for arm with the "-mabi=apcs-gnu" option, gcc will force alignment of all structures and unions to a word boundary (see also STRUCTURE_SIZE_BOUNDARY and the "-mstructure-size-boundary=XX" option if you're a gcc person), even when the members of said structures do not want or need said alignment. This completely messes up the structure alignment of 'struct edid' on those targets, because even though all the embedded structures are marked with "__attribute__((packed))", the unions that contain them are not. This was exposed by commit f1e4c916f97f ("drm/edid: add EDID block count and size helpers"), but the bug is pre-existing. That commit just made the structure layout problem cause a build failure due to the addition of the BUILD_BUG_ON(sizeof(*edid) != EDID_LENGTH); sanity check in drivers/gpu/drm/drm_edid.c:edid_block_data(). This legacy union alignment should probably not be used in the first place, but we can fix the layout by adding the packed attribute to the union entries even when each member is already packed and it shouldn't matter in a sane build environment. You can see this issue with a trivial test program: union { struct { char c[5]; }; struct { char d; unsigned e; } __attribute__((packed)); } a = { "1234" }; where building this with a normal "gcc -S" will result in the expected 5-byte size of said union: .type a, @object .size a, 5 but with an ARM compiler and the old ABI: arm-linux-gnu-gcc -mabi=apcs-gnu -mfloat-abi=soft -S t.c you get .type a, %object .size a, 8 instead, because even though each member of the union is packed, the union itself still gets aligned. This was reported by Sudip for the spear3xx_defconfig target. Link: https://lore.kernel.org/lkml/YpCUzStDnSgQLNFN@debian/ Reported-by: Sudip Mukherjee Acked-by: Arnd Bergmann Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Thomas Zimmermann Cc: David Airlie Cc: Daniel Vetter Signed-off-by: Linus Torvalds --- include/drm/drm_edid.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h index c3204a58fb09..b2756753370b 100644 --- a/include/drm/drm_edid.h +++ b/include/drm/drm_edid.h @@ -121,7 +121,7 @@ struct detailed_data_monitor_range { u8 supported_scalings; u8 preferred_refresh; } __attribute__((packed)) cvt; - } formula; + } __attribute__((packed)) formula; } __attribute__((packed)); struct detailed_data_wpindex { @@ -154,7 +154,7 @@ struct detailed_non_pixel { struct detailed_data_wpindex color; struct std_timing timings[6]; struct cvt_timing cvt[4]; - } data; + } __attribute__((packed)) data; } __attribute__((packed)); #define EDID_DETAIL_EST_TIMINGS 0xf7 @@ -172,7 +172,7 @@ struct detailed_timing { union { struct detailed_pixel_timing pixel_data; struct detailed_non_pixel other_data; - } data; + } __attribute__((packed)) data; } __attribute__((packed)); #define DRM_EDID_INPUT_SERRATION_VSYNC (1 << 0) -- cgit v1.2.3 From a7c41b4687f5902af70cd559806990930c8a307b Mon Sep 17 00:00:00 2001 From: Xiaoguang Wang Date: Mon, 30 May 2022 21:15:20 +0800 Subject: io_uring: let IORING_OP_FILES_UPDATE support choosing fixed file slots One big issue with the file registration feature is that it needs user space apps to maintain free slot info about io_uring's fixed file table, which really is a burden for development. io_uring now supports choosing free file slot for user space apps by using IORING_FILE_INDEX_ALLOC flag in accept, open, and socket operations, but they need the app to use direct accept or direct open, which not all apps are prepared to use yet. To support apps that still need real fds, make use of the registration feature easier. Let IORING_OP_FILES_UPDATE support choosing fixed file slots, which will store picked fixed files slots in fd array and let cqe return the number of slots allocated. Suggested-by: Hao Xu Signed-off-by: Xiaoguang Wang [axboe: move flag to uapi io_uring header, change goto to break, init] Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 53e7dae92e42..776e0278f9dd 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -47,6 +47,7 @@ struct io_uring_sqe { __u32 unlink_flags; __u32 hardlink_flags; __u32 xattr_flags; + __u32 close_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -258,6 +259,11 @@ enum io_uring_op { */ #define IORING_ACCEPT_MULTISHOT (1U << 0) +/* + * close flags, store in sqe->close_flags + */ +#define IORING_CLOSE_FD_AND_FILE_SLOT (1U << 0) + /* * IO completion data structure (Completion Queue Entry) */ -- cgit v1.2.3 From 3e0b8f529c10037ae0b369fc892e524eae5a5485 Mon Sep 17 00:00:00 2001 From: Arun Ajith S Date: Mon, 30 May 2022 10:14:14 +0000 Subject: net/ipv6: Expand and rename accept_unsolicited_na to accept_untracked_na RFC 9131 changes default behaviour of handling RX of NA messages when the corresponding entry is absent in the neighbour cache. The current implementation is limited to accept just unsolicited NAs. However, the RFC is more generic where it also accepts solicited NAs. Both types should result in adding a STALE entry for this case. Expand accept_untracked_na behaviour to also accept solicited NAs to be compliant with the RFC and rename the sysctl knob to accept_untracked_na. Fixes: f9a2fb73318e ("net/ipv6: Introduce accept_unsolicited_na knob to implement router-side changes for RFC9131") Signed-off-by: Arun Ajith S Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20220530101414.65439-1-aajith@arista.com Signed-off-by: Paolo Abeni --- include/linux/ipv6.h | 2 +- include/uapi/linux/ipv6.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 38c8203d52cb..37dfdcfcdd54 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -61,7 +61,7 @@ struct ipv6_devconf { __s32 suppress_frag_ndisc; __s32 accept_ra_mtu; __s32 drop_unsolicited_na; - __s32 accept_unsolicited_na; + __s32 accept_untracked_na; struct ipv6_stable_secret { bool initialized; struct in6_addr secret; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 549ddeaf788b..03cdbe798fe3 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -194,7 +194,7 @@ enum { DEVCONF_IOAM6_ID, DEVCONF_IOAM6_ID_WIDE, DEVCONF_NDISC_EVICT_NOCARRIER, - DEVCONF_ACCEPT_UNSOLICITED_NA, + DEVCONF_ACCEPT_UNTRACKED_NA, DEVCONF_MAX }; -- cgit v1.2.3 From 13b00b135665c92065a27c0c39dd97e0f380bd4f Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 18 May 2022 16:38:00 +0300 Subject: vdpa: Add support for querying vendor statistics Allows to read vendor statistics of a vdpa device. The specific statistics data are received from the upstream driver in the form of an (attribute name, attribute value) pairs. An example of statistics for mlx5_vdpa device are: received_desc - number of descriptors received by the virtqueue completed_desc - number of descriptors completed by the virtqueue A descriptor using indirect buffers is still counted as 1. In addition, N chained descriptors are counted correctly N times as one would expect. A new callback was added to vdpa_config_ops which provides the means for the vdpa driver to return statistics results. The interface allows for reading all the supported virtqueues, including the control virtqueue if it exists. Below are some examples taken from mlx5_vdpa which are introduced in the following patch: 1. Read statistics for the virtqueue at index 1 $ vdpa dev vstats show vdpa-a qidx 1 vdpa-a: queue_type tx queue_index 1 received_desc 3844836 completed_desc 3844836 2. Read statistics for the virtqueue at index 32 $ vdpa dev vstats show vdpa-a qidx 32 vdpa-a: queue_type control_vq queue_index 32 received_desc 62 completed_desc 62 3. Read statisitics for the virtqueue at index 0 with json output $ vdpa -j dev vstats show vdpa-a qidx 0 {"vstats":{"vdpa-a":{ "queue_type":"rx","queue_index":0,"name":"received_desc","value":417776,\ "name":"completed_desc","value":417548}}} 4. Read statistics for the virtqueue at index 0 with preety json output $ vdpa -jp dev vstats show vdpa-a qidx 0 { "vstats": { "vdpa-a": { "queue_type": "rx", "queue_index": 0, "name": "received_desc", "value": 417776, "name": "completed_desc", "value": 417548 } } } Signed-off-by: Eli Cohen Message-Id: <20220518133804.1075129-3-elic@nvidia.com> Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 3 +++ include/uapi/linux/vdpa.h | 6 ++++++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 8943a209202e..2ae8443331e1 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -276,6 +276,9 @@ struct vdpa_config_ops { const struct vdpa_vq_state *state); int (*get_vq_state)(struct vdpa_device *vdev, u16 idx, struct vdpa_vq_state *state); + int (*get_vendor_vq_stats)(struct vdpa_device *vdev, u16 idx, + struct sk_buff *msg, + struct netlink_ext_ack *extack); struct vdpa_notification_area (*get_vq_notification)(struct vdpa_device *vdev, u16 idx); /* vq irq is not expected to be changed once DRIVER_OK is set */ diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 1061d8d2d09d..25c55cab3d7c 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -18,6 +18,7 @@ enum vdpa_command { VDPA_CMD_DEV_DEL, VDPA_CMD_DEV_GET, /* can dump */ VDPA_CMD_DEV_CONFIG_GET, /* can dump */ + VDPA_CMD_DEV_VSTATS_GET, }; enum vdpa_attr { @@ -46,6 +47,11 @@ enum vdpa_attr { VDPA_ATTR_DEV_NEGOTIATED_FEATURES, /* u64 */ VDPA_ATTR_DEV_MGMTDEV_MAX_VQS, /* u32 */ VDPA_ATTR_DEV_SUPPORTED_FEATURES, /* u64 */ + + VDPA_ATTR_DEV_QUEUE_INDEX, /* u32 */ + VDPA_ATTR_DEV_VENDOR_ATTR_NAME, /* string */ + VDPA_ATTR_DEV_VENDOR_ATTR_VALUE, /* u64 */ + /* new attributes must be added above here */ VDPA_ATTR_MAX, }; -- cgit v1.2.3 From a6a51adc6e8aafebfe0c4beb80e99694ea562b40 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 18 May 2022 16:38:02 +0300 Subject: net/vdpa: Use readers/writers semaphore instead of cf_mutex Replace cf_mutex with rw_semaphore to reflect the fact that some calls could be called concurrently but can suffice with read lock. Suggested-by: Si-Wei Liu Signed-off-by: Eli Cohen Message-Id: <20220518133804.1075129-5-elic@nvidia.com> Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 2ae8443331e1..2cb14847831e 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -66,7 +66,7 @@ struct vdpa_mgmt_dev; * @dma_dev: the actual device that is performing DMA * @driver_override: driver name to force a match * @config: the configuration ops for this device. - * @cf_mutex: Protects get and set access to configuration layout. + * @cf_lock: Protects get and set access to configuration layout. * @index: device index * @features_valid: were features initialized? for legacy guests * @use_va: indicate whether virtual address must be used by this device @@ -79,7 +79,7 @@ struct vdpa_device { struct device *dma_dev; const char *driver_override; const struct vdpa_config_ops *config; - struct mutex cf_mutex; /* Protects get/set config */ + struct rw_semaphore cf_lock; /* Protects get/set config */ unsigned int index; bool features_valid; bool use_va; @@ -398,10 +398,10 @@ static inline int vdpa_reset(struct vdpa_device *vdev) const struct vdpa_config_ops *ops = vdev->config; int ret; - mutex_lock(&vdev->cf_mutex); + down_write(&vdev->cf_lock); vdev->features_valid = false; ret = ops->reset(vdev); - mutex_unlock(&vdev->cf_mutex); + up_write(&vdev->cf_lock); return ret; } @@ -420,9 +420,9 @@ static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features) { int ret; - mutex_lock(&vdev->cf_mutex); + down_write(&vdev->cf_lock); ret = vdpa_set_features_unlocked(vdev, features); - mutex_unlock(&vdev->cf_mutex); + up_write(&vdev->cf_lock); return ret; } -- cgit v1.2.3 From 1892a3d425bf525ac98d6d3534035e6ed2bfab50 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 18 May 2022 16:38:03 +0300 Subject: vdpa/mlx5: Add support for reading descriptor statistics Implement the get_vq_stats calback of vdpa_config_ops to return the statistics for a virtqueue. The statistics are provided as vendor specific statistics where the driver provides a pair of attribute name and attribute value. Currently supported are received descriptors and completed descriptors. Signed-off-by: Eli Cohen Message-Id: <20220518133804.1075129-6-elic@nvidia.com> Signed-off-by: Michael S. Tsirkin --- include/linux/mlx5/mlx5_ifc.h | 1 + include/linux/mlx5/mlx5_ifc_vdpa.h | 39 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 78b3d3465dd7..2a8334bb5f82 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -87,6 +87,7 @@ enum { enum { MLX5_OBJ_TYPE_GENEVE_TLV_OPT = 0x000b, MLX5_OBJ_TYPE_VIRTIO_NET_Q = 0x000d, + MLX5_OBJ_TYPE_VIRTIO_Q_COUNTERS = 0x001c, MLX5_OBJ_TYPE_MATCH_DEFINER = 0x0018, MLX5_OBJ_TYPE_MKEY = 0xff01, MLX5_OBJ_TYPE_QP = 0xff02, diff --git a/include/linux/mlx5/mlx5_ifc_vdpa.h b/include/linux/mlx5/mlx5_ifc_vdpa.h index 1a9c9d94cb59..4414ed5b6ed2 100644 --- a/include/linux/mlx5/mlx5_ifc_vdpa.h +++ b/include/linux/mlx5/mlx5_ifc_vdpa.h @@ -165,4 +165,43 @@ struct mlx5_ifc_modify_virtio_net_q_out_bits { struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; }; +struct mlx5_ifc_virtio_q_counters_bits { + u8 modify_field_select[0x40]; + u8 reserved_at_40[0x40]; + u8 received_desc[0x40]; + u8 completed_desc[0x40]; + u8 error_cqes[0x20]; + u8 bad_desc_errors[0x20]; + u8 exceed_max_chain[0x20]; + u8 invalid_buffer[0x20]; + u8 reserved_at_180[0x280]; +}; + +struct mlx5_ifc_create_virtio_q_counters_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; + struct mlx5_ifc_virtio_q_counters_bits virtio_q_counters; +}; + +struct mlx5_ifc_create_virtio_q_counters_out_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; + struct mlx5_ifc_virtio_q_counters_bits virtio_q_counters; +}; + +struct mlx5_ifc_destroy_virtio_q_counters_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; +}; + +struct mlx5_ifc_destroy_virtio_q_counters_out_bits { + struct mlx5_ifc_general_obj_out_cmd_hdr_bits hdr; +}; + +struct mlx5_ifc_query_virtio_q_counters_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; +}; + +struct mlx5_ifc_query_virtio_q_counters_out_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; + struct mlx5_ifc_virtio_q_counters_bits counters; +}; + #endif /* __MLX5_IFC_VDPA_H_ */ -- cgit v1.2.3 From 175d493c3c3e09a3abaa843068fae0f0ad42c47e Mon Sep 17 00:00:00 2001 From: Gautam Dawar Date: Wed, 30 Mar 2022 23:33:41 +0530 Subject: vhost: move the backend feature bits to vhost_types.h We should store feature bits in vhost_types.h as what has been done for e.g VHOST_F_LOG_ALL. Signed-off-by: Jason Wang Signed-off-by: Gautam Dawar Message-Id: <20220330180436.24644-2-gdawar@xilinx.com> Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/vhost.h | 5 ----- include/uapi/linux/vhost_types.h | 5 +++++ 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 5d99e7c242a2..8f7b4a95d6f9 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -89,11 +89,6 @@ /* Set or get vhost backend capability */ -/* Use message type V2 */ -#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1 -/* IOTLB can accept batching hints */ -#define VHOST_BACKEND_F_IOTLB_BATCH 0x2 - #define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64) #define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64) diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h index f7f6a3a28977..76ee7016c501 100644 --- a/include/uapi/linux/vhost_types.h +++ b/include/uapi/linux/vhost_types.h @@ -153,4 +153,9 @@ struct vhost_vdpa_iova_range { /* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */ #define VHOST_NET_F_VIRTIO_NET_HDR 27 +/* Use message type V2 */ +#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1 +/* IOTLB can accept batching hints */ +#define VHOST_BACKEND_F_IOTLB_BATCH 0x2 + #endif -- cgit v1.2.3 From d4821902e43453b85b31329441a9f6ac071228a8 Mon Sep 17 00:00:00 2001 From: Gautam Dawar Date: Wed, 30 Mar 2022 23:33:45 +0530 Subject: vdpa: introduce virtqueue groups This patch introduces virtqueue groups to vDPA device. The virtqueue group is the minimal set of virtqueues that must share an address space. And the address space identifier could only be attached to a specific virtqueue group. Signed-off-by: Jason Wang Signed-off-by: Gautam Dawar Message-Id: <20220330180436.24644-6-gdawar@xilinx.com> Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 2cb14847831e..e4e53574183e 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -85,6 +85,7 @@ struct vdpa_device { bool use_va; u32 nvqs; struct vdpa_mgmt_dev *mdev; + unsigned int ngroups; }; /** @@ -172,6 +173,10 @@ struct vdpa_map_file { * for the device * @vdev: vdpa device * Returns virtqueue algin requirement + * @get_vq_group: Get the group id for a specific virtqueue + * @vdev: vdpa device + * @idx: virtqueue index + * Returns u32: group id for this virtqueue * @get_device_features: Get virtio features supported by the device * @vdev: vdpa device * Returns the virtio features support by the @@ -286,6 +291,7 @@ struct vdpa_config_ops { /* Device ops */ u32 (*get_vq_align)(struct vdpa_device *vdev); + u32 (*get_vq_group)(struct vdpa_device *vdev, u16 idx); u64 (*get_device_features)(struct vdpa_device *vdev); int (*set_driver_features)(struct vdpa_device *vdev, u64 features); u64 (*get_driver_features)(struct vdpa_device *vdev); @@ -318,6 +324,7 @@ struct vdpa_config_ops { struct vdpa_device *__vdpa_alloc_device(struct device *parent, const struct vdpa_config_ops *config, + unsigned int ngroups, size_t size, const char *name, bool use_va); @@ -328,17 +335,18 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, * @member: the name of struct vdpa_device within the @dev_struct * @parent: the parent device * @config: the bus operations that is supported by this device + * @ngroups: the number of virtqueue groups supported by this device * @name: name of the vdpa device * @use_va: indicate whether virtual address must be used by this device * * Return allocated data structure or ERR_PTR upon error */ -#define vdpa_alloc_device(dev_struct, member, parent, config, name, use_va) \ - container_of(__vdpa_alloc_device( \ - parent, config, \ +#define vdpa_alloc_device(dev_struct, member, parent, config, ngroups, name, use_va) \ + container_of((__vdpa_alloc_device( \ + parent, config, ngroups, \ sizeof(dev_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ - dev_struct, member)), name, use_va), \ + dev_struct, member)), name, use_va)), \ dev_struct, member) int vdpa_register_device(struct vdpa_device *vdev, u32 nvqs); -- cgit v1.2.3 From db9adcbf4286ad1c1fca091a870db6e49bb0df07 Mon Sep 17 00:00:00 2001 From: Gautam Dawar Date: Wed, 30 Mar 2022 23:33:46 +0530 Subject: vdpa: multiple address spaces support This patches introduces the multiple address spaces support for vDPA device. This idea is to identify a specific address space via an dedicated identifier - ASID. During vDPA device allocation, vDPA device driver needs to report the number of address spaces supported by the device then the DMA mapping ops of the vDPA device needs to be extended to support ASID. This helps to isolate the environments for the virtqueue that will not be assigned directly. E.g in the case of virtio-net, the control virtqueue will not be assigned directly to guest. As a start, simply claim 1 virtqueue groups and 1 address spaces for all vDPA devices. And vhost-vDPA will simply reject the device with more than 1 virtqueue groups or address spaces. Signed-off-by: Jason Wang Signed-off-by: Gautam Dawar Message-Id: <20220330180436.24644-7-gdawar@xilinx.com> Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 28 +++++++++++++++++++--------- 1 file changed, 19 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index e4e53574183e..1515748e84ff 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -69,6 +69,8 @@ struct vdpa_mgmt_dev; * @cf_lock: Protects get and set access to configuration layout. * @index: device index * @features_valid: were features initialized? for legacy guests + * @ngroups: the number of virtqueue groups + * @nas: the number of address spaces * @use_va: indicate whether virtual address must be used by this device * @nvqs: maximum number of supported virtqueues * @mdev: management device pointer; caller must setup when registering device as part @@ -86,6 +88,7 @@ struct vdpa_device { u32 nvqs; struct vdpa_mgmt_dev *mdev; unsigned int ngroups; + unsigned int nas; }; /** @@ -241,6 +244,7 @@ struct vdpa_map_file { * Needed for device that using device * specific DMA translation (on-chip IOMMU) * @vdev: vdpa device + * @asid: address space identifier * @iotlb: vhost memory mapping to be * used by the vDPA * Returns integer: success (0) or error (< 0) @@ -249,6 +253,7 @@ struct vdpa_map_file { * specific DMA translation (on-chip IOMMU) * and preferring incremental map. * @vdev: vdpa device + * @asid: address space identifier * @iova: iova to be mapped * @size: size of the area * @pa: physical address for the map @@ -260,6 +265,7 @@ struct vdpa_map_file { * specific DMA translation (on-chip IOMMU) * and preferring incremental unmap. * @vdev: vdpa device + * @asid: address space identifier * @iova: iova to be unmapped * @size: size of the area * Returns integer: success (0) or error (< 0) @@ -313,10 +319,12 @@ struct vdpa_config_ops { struct vdpa_iova_range (*get_iova_range)(struct vdpa_device *vdev); /* DMA ops */ - int (*set_map)(struct vdpa_device *vdev, struct vhost_iotlb *iotlb); - int (*dma_map)(struct vdpa_device *vdev, u64 iova, u64 size, - u64 pa, u32 perm, void *opaque); - int (*dma_unmap)(struct vdpa_device *vdev, u64 iova, u64 size); + int (*set_map)(struct vdpa_device *vdev, unsigned int asid, + struct vhost_iotlb *iotlb); + int (*dma_map)(struct vdpa_device *vdev, unsigned int asid, + u64 iova, u64 size, u64 pa, u32 perm, void *opaque); + int (*dma_unmap)(struct vdpa_device *vdev, unsigned int asid, + u64 iova, u64 size); /* Free device resources */ void (*free)(struct vdpa_device *vdev); @@ -324,7 +332,7 @@ struct vdpa_config_ops { struct vdpa_device *__vdpa_alloc_device(struct device *parent, const struct vdpa_config_ops *config, - unsigned int ngroups, + unsigned int ngroups, unsigned int nas, size_t size, const char *name, bool use_va); @@ -336,17 +344,19 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, * @parent: the parent device * @config: the bus operations that is supported by this device * @ngroups: the number of virtqueue groups supported by this device + * @nas: the number of address spaces * @name: name of the vdpa device * @use_va: indicate whether virtual address must be used by this device * * Return allocated data structure or ERR_PTR upon error */ -#define vdpa_alloc_device(dev_struct, member, parent, config, ngroups, name, use_va) \ +#define vdpa_alloc_device(dev_struct, member, parent, config, ngroups, nas, \ + name, use_va) \ container_of((__vdpa_alloc_device( \ - parent, config, ngroups, \ - sizeof(dev_struct) + \ + parent, config, ngroups, nas, \ + (sizeof(dev_struct) + \ BUILD_BUG_ON_ZERO(offsetof( \ - dev_struct, member)), name, use_va)), \ + dev_struct, member))), name, use_va)), \ dev_struct, member) int vdpa_register_device(struct vdpa_device *vdev, u32 nvqs); -- cgit v1.2.3 From 46d554b1bcd19133401d2d5c0728b85e7bfd1358 Mon Sep 17 00:00:00 2001 From: Gautam Dawar Date: Wed, 30 Mar 2022 23:33:47 +0530 Subject: vdpa: introduce config operations for associating ASID to a virtqueue group This patch introduces a new bus operation to allow the vDPA bus driver to associate an ASID to a virtqueue group. Signed-off-by: Jason Wang Signed-off-by: Gautam Dawar Message-Id: <20220330180436.24644-8-gdawar@xilinx.com> Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 1515748e84ff..f336d253db3d 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -240,6 +240,12 @@ struct vdpa_map_file { * @vdev: vdpa device * Returns the iova range supported by * the device. + * @set_group_asid: Set address space identifier for a + * virtqueue group + * @vdev: vdpa device + * @group: virtqueue group + * @asid: address space id for this group + * Returns integer: success (0) or error (< 0) * @set_map: Set device memory mapping (optional) * Needed for device that using device * specific DMA translation (on-chip IOMMU) @@ -325,6 +331,8 @@ struct vdpa_config_ops { u64 iova, u64 size, u64 pa, u32 perm, void *opaque); int (*dma_unmap)(struct vdpa_device *vdev, unsigned int asid, u64 iova, u64 size); + int (*set_group_asid)(struct vdpa_device *vdev, unsigned int group, + unsigned int asid); /* Free device resources */ void (*free)(struct vdpa_device *vdev); -- cgit v1.2.3 From 1cb108994c6830cc6a6e066ad7d9a22ef59fa167 Mon Sep 17 00:00:00 2001 From: Gautam Dawar Date: Wed, 30 Mar 2022 23:33:48 +0530 Subject: vhost_iotlb: split out IOTLB initialization This patch splits out IOTLB initialization to make sure it could be reused by external modules. Signed-off-by: Jason Wang Signed-off-by: Gautam Dawar Message-Id: <20220330180436.24644-9-gdawar@xilinx.com> Signed-off-by: Michael S. Tsirkin --- include/linux/vhost_iotlb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/vhost_iotlb.h b/include/linux/vhost_iotlb.h index 2d0e2f52f938..e79a40838998 100644 --- a/include/linux/vhost_iotlb.h +++ b/include/linux/vhost_iotlb.h @@ -36,6 +36,8 @@ int vhost_iotlb_add_range(struct vhost_iotlb *iotlb, u64 start, u64 last, u64 addr, unsigned int perm); void vhost_iotlb_del_range(struct vhost_iotlb *iotlb, u64 start, u64 last); +void vhost_iotlb_init(struct vhost_iotlb *iotlb, unsigned int limit, + unsigned int flags); struct vhost_iotlb *vhost_iotlb_alloc(unsigned int limit, unsigned int flags); void vhost_iotlb_free(struct vhost_iotlb *iotlb); void vhost_iotlb_reset(struct vhost_iotlb *iotlb); -- cgit v1.2.3 From 91233ad711866f4e375742d84ef3ed6aab9daa96 Mon Sep 17 00:00:00 2001 From: Gautam Dawar Date: Wed, 30 Mar 2022 23:33:49 +0530 Subject: vhost: support ASID in IOTLB API This patches allows userspace to send ASID based IOTLB message to vhost. This idea is to use the reserved u32 field in the existing V2 IOTLB message. Vhost device should advertise this capability via VHOST_BACKEND_F_IOTLB_ASID backend feature. Signed-off-by: Jason Wang Signed-off-by: Gautam Dawar Message-Id: <20220330180436.24644-10-gdawar@xilinx.com> Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/vhost_types.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h index 76ee7016c501..634cee485abb 100644 --- a/include/uapi/linux/vhost_types.h +++ b/include/uapi/linux/vhost_types.h @@ -87,7 +87,7 @@ struct vhost_msg { struct vhost_msg_v2 { __u32 type; - __u32 reserved; + __u32 asid; union { struct vhost_iotlb_msg iotlb; __u8 padding[64]; @@ -157,5 +157,9 @@ struct vhost_vdpa_iova_range { #define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1 /* IOTLB can accept batching hints */ #define VHOST_BACKEND_F_IOTLB_BATCH 0x2 +/* IOTLB can accept address space identifier through V2 type of IOTLB + * message + */ +#define VHOST_BACKEND_F_IOTLB_ASID 0x3 #endif -- cgit v1.2.3 From 3ace88bd37436abc84906312146fe5158a469142 Mon Sep 17 00:00:00 2001 From: Gautam Dawar Date: Wed, 30 Mar 2022 23:33:51 +0530 Subject: vhost-vdpa: introduce uAPI to get the number of virtqueue groups Follows the vDPA support for multiple address spaces, this patch introduce uAPI for the userspace to know the number of virtqueue groups supported by the vDPA device. Signed-off-by: Jason Wang Signed-off-by: Gautam Dawar Message-Id: <20220330180436.24644-12-gdawar@xilinx.com> Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/vhost.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 8f7b4a95d6f9..61317c61d768 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -145,11 +145,13 @@ /* Get the valid iova range */ #define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \ struct vhost_vdpa_iova_range) - /* Get the config size */ #define VHOST_VDPA_GET_CONFIG_SIZE _IOR(VHOST_VIRTIO, 0x79, __u32) /* Get the count of all virtqueues */ #define VHOST_VDPA_GET_VQS_COUNT _IOR(VHOST_VIRTIO, 0x80, __u32) +/* Get the number of virtqueue groups. */ +#define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x81, __u32) + #endif -- cgit v1.2.3 From a0c95f201170bd559737d3cdc8a950aea62f29c6 Mon Sep 17 00:00:00 2001 From: Gautam Dawar Date: Wed, 30 Mar 2022 23:33:52 +0530 Subject: vhost-vdpa: introduce uAPI to get the number of address spaces This patch introduces the uAPI for getting the number of address spaces supported by this vDPA device. Signed-off-by: Jason Wang Signed-off-by: Gautam Dawar Message-Id: <20220330180436.24644-13-gdawar@xilinx.com> Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/vhost.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 61317c61d768..51322008901a 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -154,4 +154,6 @@ /* Get the number of virtqueue groups. */ #define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x81, __u32) +/* Get the number of address spaces. */ +#define VHOST_VDPA_GET_AS_NUM _IOR(VHOST_VIRTIO, 0x7A, unsigned int) #endif -- cgit v1.2.3 From 2d1fcb7758e49fd9caf150f3c70804b95b2ce80c Mon Sep 17 00:00:00 2001 From: Gautam Dawar Date: Wed, 30 Mar 2022 23:33:53 +0530 Subject: vhost-vdpa: uAPI to get virtqueue group id Follows the support for virtqueue group in vDPA. This patches introduces uAPI to get the virtqueue group ID for a specific virtqueue in vhost-vdpa. Signed-off-by: Jason Wang Signed-off-by: Gautam Dawar Message-Id: <20220330180436.24644-14-gdawar@xilinx.com> Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/vhost.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 51322008901a..668914c87f74 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -156,4 +156,12 @@ /* Get the number of address spaces. */ #define VHOST_VDPA_GET_AS_NUM _IOR(VHOST_VIRTIO, 0x7A, unsigned int) + +/* Get the group for a virtqueue: read index, write group in num, + * The virtqueue index is stored in the index field of + * vhost_vring_state. The group for this specific virtqueue is + * returned via num field of vhost_vring_state. + */ +#define VHOST_VDPA_GET_VRING_GROUP _IOWR(VHOST_VIRTIO, 0x7B, \ + struct vhost_vring_state) #endif -- cgit v1.2.3 From 84d7c8fd3aade2fe79313003ed06ede431ec2a6d Mon Sep 17 00:00:00 2001 From: Gautam Dawar Date: Wed, 30 Mar 2022 23:33:54 +0530 Subject: vhost-vdpa: introduce uAPI to set group ASID Follows the vDPA support for associating ASID to a specific virtqueue group. This patch adds a uAPI to support setting them from userspace. Signed-off-by: Jason Wang Signed-off-by: Gautam Dawar Message-Id: <20220330180436.24644-15-gdawar@xilinx.com> Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/vhost.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 668914c87f74..cab645d4a645 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -164,4 +164,11 @@ */ #define VHOST_VDPA_GET_VRING_GROUP _IOWR(VHOST_VIRTIO, 0x7B, \ struct vhost_vring_state) +/* Set the ASID for a virtqueue group. The group index is stored in + * the index field of vhost_vring_state, the ASID associated with this + * group is stored at num field of vhost_vring_state. + */ +#define VHOST_VDPA_SET_GROUP_ASID _IOW(VHOST_VIRTIO, 0x7C, \ + struct vhost_vring_state) + #endif -- cgit v1.2.3 From ffbda8e9df10d1784d5427ec199e7d8308e3763f Mon Sep 17 00:00:00 2001 From: Cindy Lu Date: Fri, 29 Apr 2022 17:10:30 +0800 Subject: vdpa/vp_vdpa : add vdpa tool support in vp_vdpa this patch is to add the support for vdpa tool in vp_vdpa here is the example steps modprobe vp_vdpa modprobe vhost_vdpa echo 0000:00:06.0>/sys/bus/pci/drivers/virtio-pci/unbind echo 1af4 1041 > /sys/bus/pci/drivers/vp-vdpa/new_id vdpa dev add name vdpa1 mgmtdev pci/0000:00:06.0 Signed-off-by: Cindy Lu Message-Id: <20220429091030.547434-1-lulu@redhat.com> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- include/linux/vdpa.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index f336d253db3d..15af802d41c4 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -492,7 +492,7 @@ struct vdpa_mgmtdev_ops { struct vdpa_mgmt_dev { struct device *device; const struct vdpa_mgmtdev_ops *ops; - const struct virtio_device_id *id_table; + struct virtio_device_id *id_table; u64 config_attr_mask; struct list_head list; u64 supported_features; -- cgit v1.2.3 From 48b69959a8559db5df78661d9c6d5138c2f20871 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 27 May 2022 14:01:14 +0800 Subject: virtio: introduce config op to synchronize vring callbacks This patch introduces new virtio config op to vring callbacks. Transport specific method is required to make sure the write before this function is visible to the vring_interrupt() that is called after the return of this function. For the transport that doesn't provide synchronize_vqs(), use synchornize_rcu() which synchronize with IRQ implicitly as a fallback. Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: "Paul E. McKenney" Cc: Marc Zyngier Cc: Halil Pasic Cc: Cornelia Huck Cc: Vineeth Vijayan Cc: Peter Oberparleiter Cc: linux-s390@vger.kernel.org Reviewed-by: Cornelia Huck Signed-off-by: Jason Wang Message-Id: <20220527060120.20964-4-jasowang@redhat.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Xuan Zhuo Reviewed-by: Stefano Garzarella --- include/linux/virtio_config.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index b341dd62aa4d..25be018810a7 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -57,6 +57,11 @@ struct virtio_shm_region { * include a NULL entry for vqs unused by driver * Returns 0 on success or error status * @del_vqs: free virtqueues found by find_vqs(). + * @synchronize_cbs: synchronize with the virtqueue callbacks (optional) + * The function guarantees that all memory operations on the + * queue before it are visible to the vring_interrupt() that is + * called after it. + * vdev: the virtio_device * @get_features: get the array of feature bits for this device. * vdev: the virtio_device * Returns the first 64 feature bits (all we currently need). @@ -89,6 +94,7 @@ struct virtio_config_ops { const char * const names[], const bool *ctx, struct irq_affinity *desc); void (*del_vqs)(struct virtio_device *); + void (*synchronize_cbs)(struct virtio_device *); u64 (*get_features)(struct virtio_device *vdev); int (*finalize_features)(struct virtio_device *vdev); const char *(*bus_name)(struct virtio_device *vdev); @@ -217,6 +223,25 @@ int virtio_find_vqs_ctx(struct virtio_device *vdev, unsigned nvqs, desc); } +/** + * virtio_synchronize_cbs - synchronize with virtqueue callbacks + * @vdev: the device + */ +static inline +void virtio_synchronize_cbs(struct virtio_device *dev) +{ + if (dev->config->synchronize_cbs) { + dev->config->synchronize_cbs(dev); + } else { + /* + * A best effort fallback to synchronize with + * interrupts, preemption and softirq disabled + * regions. See comment above synchronize_rcu(). + */ + synchronize_rcu(); + } +} + /** * virtio_device_ready - enable vq use in probe function * @vdev: the device -- cgit v1.2.3 From be83f04d2529e8dc4273efdd1ccf7b7502741071 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 27 May 2022 14:01:18 +0800 Subject: virtio: allow to unbreak virtqueue This patch allows the new introduced __virtio_break_device() to unbreak the virtqueue. Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: "Paul E. McKenney" Cc: Marc Zyngier Cc: Halil Pasic Cc: Cornelia Huck Cc: Vineeth Vijayan Cc: Peter Oberparleiter Cc: linux-s390@vger.kernel.org Signed-off-by: Jason Wang Message-Id: <20220527060120.20964-8-jasowang@redhat.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Xuan Zhuo --- include/linux/virtio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 5464f398912a..d8fdf170637c 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -131,6 +131,7 @@ void unregister_virtio_device(struct virtio_device *dev); bool is_virtio_device(struct device *dev); void virtio_break_device(struct virtio_device *dev); +void __virtio_unbreak_device(struct virtio_device *dev); void virtio_config_changed(struct virtio_device *dev); #ifdef CONFIG_PM_SLEEP -- cgit v1.2.3 From 8b4ec69d7e098a7ddf832e1e7840de53ed474c77 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 27 May 2022 14:01:19 +0800 Subject: virtio: harden vring IRQ This is a rework on the previous IRQ hardening that is done for virtio-pci where several drawbacks were found and were reverted: 1) try to use IRQF_NO_AUTOEN which is not friendly to affinity managed IRQ that is used by some device such as virtio-blk 2) done only for PCI transport The vq->broken is re-used in this patch for implementing the IRQ hardening. The vq->broken is set to true during both initialization and reset. And the vq->broken is set to false in virtio_device_ready(). Then vring_interrupt() can check and return when vq->broken is true. And in this case, switch to return IRQ_NONE to let the interrupt core aware of such invalid interrupt to prevent IRQ storm. The reason of using a per queue variable instead of a per device one is that we may need it for per queue reset hardening in the future. Note that the hardening is only done for vring interrupt since the config interrupt hardening is already done in commit 22b7050a024d7 ("virtio: defer config changed notifications"). But the method that is used by config interrupt can't be reused by the vring interrupt handler because it uses spinlock to do the synchronization which is expensive. Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: "Paul E. McKenney" Cc: Marc Zyngier Cc: Halil Pasic Cc: Cornelia Huck Cc: Vineeth Vijayan Cc: Peter Oberparleiter Cc: linux-s390@vger.kernel.org Signed-off-by: Jason Wang Message-Id: <20220527060120.20964-9-jasowang@redhat.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Xuan Zhuo --- include/linux/virtio_config.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 25be018810a7..d4edfd7d91bb 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -256,6 +256,26 @@ void virtio_device_ready(struct virtio_device *dev) unsigned status = dev->config->get_status(dev); BUG_ON(status & VIRTIO_CONFIG_S_DRIVER_OK); + + /* + * The virtio_synchronize_cbs() makes sure vring_interrupt() + * will see the driver specific setup if it sees vq->broken + * as false (even if the notifications come before DRIVER_OK). + */ + virtio_synchronize_cbs(dev); + __virtio_unbreak_device(dev); + /* + * The transport should ensure the visibility of vq->broken + * before setting DRIVER_OK. See the comments for the transport + * specific set_status() method. + * + * A well behaved device will only notify a virtqueue after + * DRIVER_OK, this means the device should "see" the coherenct + * memory write that set vq->broken as false which is done by + * the driver when it sees DRIVER_OK, then the following + * driver's vring_interrupt() will see vq->broken as false so + * we won't lose any notification. + */ dev->config->set_status(dev, status | VIRTIO_CONFIG_S_DRIVER_OK); } -- cgit v1.2.3 From 619e9e14ba3c97a80776c0b5a68a01caa41dd148 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 27 May 2022 14:01:20 +0800 Subject: virtio: use WARN_ON() to warning illegal status value We used to use BUG_ON() in virtio_device_ready() to detect illegal status value, this seems sub-optimal since the value is under the control of the device. Switch to use WARN_ON() instead. Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: "Paul E. McKenney" Cc: Marc Zyngier Cc: Halil Pasic Cc: Cornelia Huck Cc: Vineeth Vijayan Cc: Peter Oberparleiter Cc: linux-s390@vger.kernel.org Signed-off-by: Jason Wang Message-Id: <20220527060120.20964-10-jasowang@redhat.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Xuan Zhuo --- include/linux/virtio_config.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index d4edfd7d91bb..9a36051ceb76 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -255,7 +255,7 @@ void virtio_device_ready(struct virtio_device *dev) { unsigned status = dev->config->get_status(dev); - BUG_ON(status & VIRTIO_CONFIG_S_DRIVER_OK); + WARN_ON(status & VIRTIO_CONFIG_S_DRIVER_OK); /* * The virtio_synchronize_cbs() makes sure vring_interrupt() -- cgit v1.2.3 From 3fc2a9e89b3508a5cc0c324f26d7b4740ba8c456 Mon Sep 17 00:00:00 2001 From: Changcheng Liu Date: Tue, 26 Apr 2022 21:28:14 +0800 Subject: net/mlx5: correct ECE offset in query qp output ECE field should be after opt_param_mask in query qp output. Fixes: 6b646a7e4af6 ("net/mlx5: Add ability to read and write ECE options") Signed-off-by: Changcheng Liu Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 78b3d3465dd7..2cd7d611e7b3 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5176,12 +5176,11 @@ struct mlx5_ifc_query_qp_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x20]; - u8 ece[0x20]; + u8 reserved_at_40[0x40]; u8 opt_param_mask[0x20]; - u8 reserved_at_a0[0x20]; + u8 ece[0x20]; struct mlx5_ifc_qpc_bits qpc; -- cgit v1.2.3 From c3ed222745d9ad7b69299b349a64ba533c64a34f Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Sat, 14 May 2022 07:05:13 -0400 Subject: NFSv4: Fix free of uninitialized nfs4_label on referral lookup. Send along the already-allocated fattr along with nfs4_fs_locations, and drop the memcpy of fattr. We end up growing two more allocations, but this fixes up a crash as: PID: 790 TASK: ffff88811b43c000 CPU: 0 COMMAND: "ls" #0 [ffffc90000857920] panic at ffffffff81b9bfde #1 [ffffc900008579c0] do_trap at ffffffff81023a9b #2 [ffffc90000857a10] do_error_trap at ffffffff81023b78 #3 [ffffc90000857a58] exc_stack_segment at ffffffff81be1f45 #4 [ffffc90000857a80] asm_exc_stack_segment at ffffffff81c009de #5 [ffffc90000857b08] nfs_lookup at ffffffffa0302322 [nfs] #6 [ffffc90000857b70] __lookup_slow at ffffffff813a4a5f #7 [ffffc90000857c60] walk_component at ffffffff813a86c4 #8 [ffffc90000857cb8] path_lookupat at ffffffff813a9553 #9 [ffffc90000857cf0] filename_lookup at ffffffff813ab86b Suggested-by: Trond Myklebust Fixes: 9558a007dbc3 ("NFS: Remove the label from the nfs4_lookup_res struct") Signed-off-by: Benjamin Coddington Signed-off-by: Anna Schumaker --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 4a8ba84f848e..0e3aa0f5f324 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1222,7 +1222,7 @@ struct nfs4_fs_location { #define NFS4_FS_LOCATIONS_MAXENTRIES 10 struct nfs4_fs_locations { - struct nfs_fattr fattr; + struct nfs_fattr *fattr; const struct nfs_server *server; struct nfs4_pathname fs_path; int nlocations; -- cgit v1.2.3 From 118f09eda21d392e1eeb9f8a4bee044958cccf20 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Wed, 25 May 2022 12:12:59 -0400 Subject: NFSv4.1 mark qualified async operations as MOVEABLE tasks Mark async operations such as RENAME, REMOVE, COMMIT MOVEABLE for the nfsv4.1+ sessions. Fixes: 85e39feead948 ("NFSv4.1 identify and mark RPC tasks that can move between transports") Signed-off-by: Olga Kornievskaia Signed-off-by: Anna Schumaker --- include/linux/nfs_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 157d2bd6b241..ea2f7e6b1b0b 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -287,4 +287,5 @@ struct nfs_server { #define NFS_CAP_XATTR (1U << 28) #define NFS_CAP_READ_PLUS (1U << 29) #define NFS_CAP_FS_LOCATIONS (1U << 30) +#define NFS_CAP_MOVEABLE (1U << 31) #endif -- cgit v1.2.3 From 2e8728c955ce0624b958eee6e030a37aca3a5d86 Mon Sep 17 00:00:00 2001 From: Guoju Fang Date: Sat, 28 May 2022 18:16:28 +0800 Subject: net: sched: add barrier to fix packet stuck problem for lockless qdisc In qdisc_run_end(), the spin_unlock() only has store-release semantic, which guarantees all earlier memory access are visible before it. But the subsequent test_bit() has no barrier semantics so may be reordered ahead of the spin_unlock(). The store-load reordering may cause a packet stuck problem. The concurrent operations can be described as below, CPU 0 | CPU 1 qdisc_run_end() | qdisc_run_begin() . | . ----> /* may be reorderd here */ | . | . | . | spin_unlock() | set_bit() | . | smp_mb__after_atomic() ---- test_bit() | spin_trylock() . | . Consider the following sequence of events: CPU 0 reorder test_bit() ahead and see MISSED = 0 CPU 1 calls set_bit() CPU 1 calls spin_trylock() and return fail CPU 0 executes spin_unlock() At the end of the sequence, CPU 0 calls spin_unlock() and does nothing because it see MISSED = 0. The skb on CPU 1 has beed enqueued but no one take it, until the next cpu pushing to the qdisc (if ever ...) will notice and dequeue it. This patch fix this by adding one explicit barrier. As spin_unlock() and test_bit() ordering is a store-load ordering, a full memory barrier smp_mb() is needed here. Fixes: a90c57f2cedd ("net: sched: fix packet stuck problem for lockless qdisc") Signed-off-by: Guoju Fang Link: https://lore.kernel.org/r/20220528101628.120193-1-gjfang@linux.alibaba.com Signed-off-by: Jakub Kicinski --- include/net/sch_generic.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 80973ce820f3..d6cf5116b5f9 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -209,6 +209,12 @@ static inline void qdisc_run_end(struct Qdisc *qdisc) if (qdisc->flags & TCQ_F_NOLOCK) { spin_unlock(&qdisc->seqlock); + /* spin_unlock() only has store-release semantic. The unlock + * and test_bit() ordering is a store-load ordering, so a full + * memory barrier is needed here. + */ + smp_mb(); + if (unlikely(test_bit(__QDISC_STATE_MISSED, &qdisc->state))) __netif_schedule(qdisc); -- cgit v1.2.3 From 41925b105e345ebc84cedb64f59d20cb14a62613 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 30 May 2022 10:26:34 +0200 Subject: xen: replace xen_remap() with memremap() xen_remap() is used to establish mappings for frames not under direct control of the kernel: for Xenstore and console ring pages, and for grant pages of non-PV guests. Today xen_remap() is defined to use ioremap() on x86 (doing uncached mappings), and ioremap_cache() on Arm (doing cached mappings). Uncached mappings for those use cases are bad for performance, so they should be avoided if possible. As all use cases of xen_remap() don't require uncached mappings (the mapped area is always physical RAM), a mapping using the standard WB cache mode is fine. As sparse is flagging some of the xen_remap() use cases to be not appropriate for iomem(), as the result is not annotated with the __iomem modifier, eliminate xen_remap() completely and replace all use cases with memremap() specifying the MEMREMAP_WB caching mode. xen_unmap() can be replaced with memunmap(). Reported-by: kernel test robot Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Acked-by: Stefano Stabellini Link: https://lore.kernel.org/r/20220530082634.6339-1-jgross@suse.com Signed-off-by: Juergen Gross --- include/xen/arm/page.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/xen/arm/page.h b/include/xen/arm/page.h index ac1b65470563..f831cfeca000 100644 --- a/include/xen/arm/page.h +++ b/include/xen/arm/page.h @@ -109,9 +109,6 @@ static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) return __set_phys_to_machine(pfn, mfn); } -#define xen_remap(cookie, size) ioremap_cache((cookie), (size)) -#define xen_unmap(cookie) iounmap((cookie)) - bool xen_arch_need_swiotlb(struct device *dev, phys_addr_t phys, dma_addr_t dev_addr); -- cgit v1.2.3 From c4caa500ffebf64795d1c0f6f9d6f179b502c6b7 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Tue, 31 May 2022 14:37:27 +0800 Subject: bonding: guard ns_targets by CONFIG_IPV6 Guard ns_targets in struct bond_params by CONFIG_IPV6, which could save 256 bytes if IPv6 not configed. Also add this protection for function bond_is_ip6_target_ok() and bond_get_targets_ip6(). Remove the IS_ENABLED() check for bond_opts[] as this will make BOND_OPT_NS_TARGETS uninitialized if CONFIG_IPV6 not enabled. Add a dummy bond_option_ns_ip6_targets_set() for this situation. Fixes: 4e24be018eb9 ("bonding: add new parameter ns_targets") Signed-off-by: Hangbin Liu Acked-by: Jonathan Toppins Link: https://lore.kernel.org/r/20220531063727.224043-1-liuhangbin@gmail.com Signed-off-by: Paolo Abeni --- include/net/bonding.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/bonding.h b/include/net/bonding.h index b14f4c0b4e9e..cb904d356e31 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -149,7 +149,9 @@ struct bond_params { struct reciprocal_value reciprocal_packets_per_slave; u16 ad_actor_sys_prio; u16 ad_user_port_key; +#if IS_ENABLED(CONFIG_IPV6) struct in6_addr ns_targets[BOND_MAX_NS_TARGETS]; +#endif /* 2 bytes of padding : see ether_addr_equal_64bits() */ u8 ad_actor_system[ETH_ALEN + 2]; @@ -503,12 +505,14 @@ static inline int bond_is_ip_target_ok(__be32 addr) return !ipv4_is_lbcast(addr) && !ipv4_is_zeronet(addr); } +#if IS_ENABLED(CONFIG_IPV6) static inline int bond_is_ip6_target_ok(struct in6_addr *addr) { return !ipv6_addr_any(addr) && !ipv6_addr_loopback(addr) && !ipv6_addr_is_multicast(addr); } +#endif /* Get the oldest arp which we've received on this slave for bond's * arp_targets. @@ -746,6 +750,7 @@ static inline int bond_get_targets_ip(__be32 *targets, __be32 ip) return -1; } +#if IS_ENABLED(CONFIG_IPV6) static inline int bond_get_targets_ip6(struct in6_addr *targets, struct in6_addr *ip) { int i; @@ -758,6 +763,7 @@ static inline int bond_get_targets_ip6(struct in6_addr *targets, struct in6_addr return -1; } +#endif /* exported from bond_main.c */ extern unsigned int bond_net_id; -- cgit v1.2.3 From 597b89d30b42dcc8e6b262e6876b42dde66f97f0 Mon Sep 17 00:00:00 2001 From: Mikko Perttunen Date: Mon, 16 May 2022 11:52:51 +0300 Subject: gpu: host1x: Add context bus The context bus is a "dummy" bus that contains struct devices that correspond to IOMMU contexts assigned through Host1x to processes. Even when host1x itself is built as a module, the bus is registered in built-in code so that the built-in ARM SMMU driver is able to reference it. Signed-off-by: Mikko Perttunen Signed-off-by: Thierry Reding --- include/linux/host1x_context_bus.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) create mode 100644 include/linux/host1x_context_bus.h (limited to 'include') diff --git a/include/linux/host1x_context_bus.h b/include/linux/host1x_context_bus.h new file mode 100644 index 000000000000..72462737a6db --- /dev/null +++ b/include/linux/host1x_context_bus.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (c) 2021, NVIDIA Corporation. All rights reserved. + */ + +#ifndef __LINUX_HOST1X_CONTEXT_BUS_H +#define __LINUX_HOST1X_CONTEXT_BUS_H + +#include + +#ifdef CONFIG_TEGRA_HOST1X_CONTEXT_BUS +extern struct bus_type host1x_context_device_bus_type; +#endif + +#endif -- cgit v1.2.3 From 662ce1dc9caf493c309200edbe38d186f1ea20d0 Mon Sep 17 00:00:00 2001 From: Yang Yang Date: Wed, 1 Jun 2022 15:55:25 -0700 Subject: delayacct: track delays from write-protect copy Delay accounting does not track the delay of write-protect copy. When tasks trigger many write-protect copys(include COW and unsharing of anonymous pages[1]), it may spend a amount of time waiting for them. To get the delay of tasks in write-protect copy, could help users to evaluate the impact of using KSM or fork() or GUP. Also update tools/accounting/getdelays.c: / # ./getdelays -dl -p 231 print delayacct stats ON listen forever PID 231 CPU count real total virtual total delay total delay average 6247 1859000000 2154070021 1674255063 0.268ms IO count delay total delay average 0 0 0ms SWAP count delay total delay average 0 0 0ms RECLAIM count delay total delay average 0 0 0ms THRASHING count delay total delay average 0 0 0ms COMPACT count delay total delay average 3 72758 0ms WPCOPY count delay total delay average 3635 271567604 0ms [1] commit 31cc5bc4af70("mm: support GUP-triggered unsharing of anonymous pages") Link: https://lkml.kernel.org/r/20220409014342.2505532-1-yang.yang29@zte.com.cn Signed-off-by: Yang Yang Reviewed-by: David Hildenbrand Reviewed-by: Jiang Xuexin Reviewed-by: Ran Xiaokai Reviewed-by: wangyong Cc: Jonathan Corbet Cc: Balbir Singh Cc: Mike Kravetz Cc: Stephen Rothwell Signed-off-by: Andrew Morton --- include/linux/delayacct.h | 28 ++++++++++++++++++++++++++++ include/uapi/linux/taskstats.h | 6 +++++- 2 files changed, 33 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 6b16a6930a19..58aea2d7385c 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -45,9 +45,13 @@ struct task_delay_info { u64 compact_start; u64 compact_delay; /* wait for memory compact */ + u64 wpcopy_start; + u64 wpcopy_delay; /* wait for write-protect copy */ + u32 freepages_count; /* total count of memory reclaim */ u32 thrashing_count; /* total count of thrash waits */ u32 compact_count; /* total count of memory compact */ + u32 wpcopy_count; /* total count of write-protect copy */ }; #endif @@ -75,6 +79,8 @@ extern void __delayacct_swapin_start(void); extern void __delayacct_swapin_end(void); extern void __delayacct_compact_start(void); extern void __delayacct_compact_end(void); +extern void __delayacct_wpcopy_start(void); +extern void __delayacct_wpcopy_end(void); static inline void delayacct_tsk_init(struct task_struct *tsk) { @@ -191,6 +197,24 @@ static inline void delayacct_compact_end(void) __delayacct_compact_end(); } +static inline void delayacct_wpcopy_start(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_wpcopy_start(); +} + +static inline void delayacct_wpcopy_end(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_wpcopy_end(); +} + #else static inline void delayacct_init(void) {} @@ -225,6 +249,10 @@ static inline void delayacct_compact_start(void) {} static inline void delayacct_compact_end(void) {} +static inline void delayacct_wpcopy_start(void) +{} +static inline void delayacct_wpcopy_end(void) +{} #endif /* CONFIG_TASK_DELAY_ACCT */ diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index 736154171489..a7f5b11a8f1b 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 12 +#define TASKSTATS_VERSION 13 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -194,6 +194,10 @@ struct taskstats { __u64 ac_exe_dev; /* program binary device ID */ __u64 ac_exe_inode; /* program binary inode number */ /* v12 end */ + + /* v13: Delay waiting for write-protect copy */ + __u64 wpcopy_count; + __u64 wpcopy_delay_total; }; -- cgit v1.2.3 From 8d3398ba2a0d1e25690f830192b7834acab003ec Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Tue, 31 May 2022 11:43:45 +0200 Subject: socket: Don't use u8 type in uapi socket.h Use plain 255 instead, which also avoid introducing an additional header dependency on Fixes: 26859240e4ee ("txhash: Add socket option to control TX hash rethink behavior") Signed-off-by: Tobias Klauser Link: https://lore.kernel.org/r/20220531094345.13801-1-tklauser@distanz.ch Signed-off-by: Jakub Kicinski --- include/uapi/linux/socket.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/socket.h b/include/uapi/linux/socket.h index 51d6bb2f6765..d3fcd3b5ec53 100644 --- a/include/uapi/linux/socket.h +++ b/include/uapi/linux/socket.h @@ -31,7 +31,7 @@ struct __kernel_sockaddr_storage { #define SOCK_BUF_LOCK_MASK (SOCK_SNDBUF_LOCK | SOCK_RCVBUF_LOCK) -#define SOCK_TXREHASH_DEFAULT ((u8)-1) +#define SOCK_TXREHASH_DEFAULT 255 #define SOCK_TXREHASH_DISABLED 0 #define SOCK_TXREHASH_ENABLED 1 -- cgit v1.2.3 From b6d9014a3335194590abdd2a2471ef5147a67645 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 30 May 2022 18:40:06 +0200 Subject: netfilter: nf_tables: delete flowtable hooks via transaction list Remove inactive bool field in nft_hook object that was introduced in abadb2f865d7 ("netfilter: nf_tables: delete devices from flowtable"). Move stale flowtable hooks to transaction list instead. Deleting twice the same device does not result in ENOENT. Fixes: abadb2f865d7 ("netfilter: nf_tables: delete devices from flowtable") Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 20af9d3557b9..279ae0fff7ad 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1090,7 +1090,6 @@ struct nft_stats { struct nft_hook { struct list_head list; - bool inactive; struct nf_hook_ops ops; struct rcu_head rcu; }; -- cgit v1.2.3 From 7d8a3a477b3e25ada8dc71d22048c2ea417209a0 Mon Sep 17 00:00:00 2001 From: Duoming Zhou Date: Mon, 30 May 2022 23:21:58 +0800 Subject: ax25: Fix ax25 session cleanup problems There are session cleanup problems in ax25_release() and ax25_disconnect(). If we setup a session and then disconnect, the disconnected session is still in "LISTENING" state that is shown below. Active AX.25 sockets Dest Source Device State Vr/Vs Send-Q Recv-Q DL9SAU-4 DL9SAU-3 ??? LISTENING 000/000 0 0 DL9SAU-3 DL9SAU-4 ??? LISTENING 000/000 0 0 The first reason is caused by del_timer_sync() in ax25_release(). The timers of ax25 are used for correct session cleanup. If we use ax25_release() to close ax25 sessions and ax25_dev is not null, the del_timer_sync() functions in ax25_release() will execute. As a result, the sessions could not be cleaned up correctly, because the timers have stopped. In order to solve this problem, this patch adds a device_up flag in ax25_dev in order to judge whether the device is up. If there are sessions to be cleaned up, the del_timer_sync() in ax25_release() will not execute. What's more, we add ax25_cb_del() in ax25_kill_by_device(), because the timers have been stopped and there are no functions that could delete ax25_cb if we do not call ax25_release(). Finally, we reorder the position of ax25_list_lock in ax25_cb_del() in order to synchronize among different functions that call ax25_cb_del(). The second reason is caused by improper check in ax25_disconnect(). The incoming ax25 sessions which ax25->sk is null will close heartbeat timer, because the check "if(!ax25->sk || ..)" is satisfied. As a result, the session could not be cleaned up properly. In order to solve this problem, this patch changes the improper check to "if(ax25->sk && ..)" in ax25_disconnect(). What`s more, the ax25_disconnect() may be called twice, which is not necessary. For example, ax25_kill_by_device() calls ax25_disconnect() and sets ax25->state to AX25_STATE_0, but ax25_release() calls ax25_disconnect() again. In order to solve this problem, this patch add a check in ax25_release(). If the flag of ax25->sk equals to SOCK_DEAD, the ax25_disconnect() in ax25_release() should not be executed. Fixes: 82e31755e55f ("ax25: Fix UAF bugs in ax25 timers") Fixes: 8a367e74c012 ("ax25: Fix segfault after sock connection timeout") Reported-and-tested-by: Thomas Osterried Signed-off-by: Duoming Zhou Link: https://lore.kernel.org/r/20220530152158.108619-1-duoming@zju.edu.cn Signed-off-by: Paolo Abeni --- include/net/ax25.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/ax25.h b/include/net/ax25.h index 0f9790c455bb..a427a05672e2 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -228,6 +228,7 @@ typedef struct ax25_dev { ax25_dama_info dama; #endif refcount_t refcount; + bool device_up; } ax25_dev; typedef struct ax25_cb { -- cgit v1.2.3 From 8cc5b032240ae5220b62c689c20459d3e1825b2d Mon Sep 17 00:00:00 2001 From: Carlos Llamas Date: Wed, 1 Jun 2022 01:00:17 +0000 Subject: binder: fix sender_euid type in uapi header The {pid,uid}_t fields of struct binder_transaction were recently replaced to use kernel types in commit 169adc2b6b3c ("android/binder.h: add linux/android/binder(fs).h to UAPI compile-test coverage"). However, using __kernel_uid_t here breaks backwards compatibility in architectures using 16-bits for this type, since glibc and some others still expect a 32-bit uid_t. Instead, let's use __kernel_uid32_t which avoids this compatibility problem. Fixes: 169adc2b6b3c ("android/binder.h: add linux/android/binder(fs).h to UAPI compile-test coverage") Reported-by: Christopher Ferris Signed-off-by: Carlos Llamas Acked-by: Todd Kjos Signed-off-by: Arnd Bergmann --- include/uapi/linux/android/binder.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index 11157fae8a8e..688bcdaeed53 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -289,7 +289,7 @@ struct binder_transaction_data { /* General information about the transaction. */ __u32 flags; __kernel_pid_t sender_pid; - __kernel_uid_t sender_euid; + __kernel_uid32_t sender_euid; binder_size_t data_size; /* number of bytes of data */ binder_size_t offsets_size; /* number of bytes of offsets */ -- cgit v1.2.3 From 22296a5c0cd35aaf62e1af3266f82cdf6b0b9b78 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 2 Jun 2022 09:18:58 -0700 Subject: net: add debug info to __skb_pull() While analyzing yet another syzbot report, I found the following patch very useful. It allows to better understand what went wrong. This debug info is only enabled if CONFIG_DEBUG_NET=y, which is the case for syzbot builds. Signed-off-by: Eric Dumazet Acked-by: Willem de Bruijn Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index da96f0d3e753..d3d10556f0fa 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2696,7 +2696,14 @@ void *skb_pull(struct sk_buff *skb, unsigned int len); static inline void *__skb_pull(struct sk_buff *skb, unsigned int len) { skb->len -= len; - BUG_ON(skb->len < skb->data_len); + if (unlikely(skb->len < skb->data_len)) { +#if defined(CONFIG_DEBUG_NET) + skb->len += len; + pr_err("__skb_pull(len=%u)\n", len); + skb_dump(KERN_ERR, skb, false); +#endif + BUG(); + } return skb->data += len; } -- cgit v1.2.3 From 08145b087e4481458f6075f3af58021a3cf8a940 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Tue, 31 May 2022 18:04:10 +0800 Subject: LoongArch: Add ELF-related definitions Add ELF-related definitions for LoongArch, including: EM_LOONGARCH, KEXEC_ARCH_LOONGARCH, AUDIT_ARCH_LOONGARCH32, AUDIT_ARCH_LOONGARCH64 and NT_LOONGARCH_*. Reviewed-by: WANG Xuerui Reviewed-by: Jiaxun Yang Signed-off-by: Huacai Chen --- include/uapi/linux/audit.h | 2 ++ include/uapi/linux/elf-em.h | 1 + include/uapi/linux/elf.h | 5 +++++ include/uapi/linux/kexec.h | 1 + 4 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index 8eda133ca4c1..7c1dc818b1d5 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -439,6 +439,8 @@ enum { #define AUDIT_ARCH_UNICORE (EM_UNICORE|__AUDIT_ARCH_LE) #define AUDIT_ARCH_X86_64 (EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE) #define AUDIT_ARCH_XTENSA (EM_XTENSA) +#define AUDIT_ARCH_LOONGARCH32 (EM_LOONGARCH|__AUDIT_ARCH_LE) +#define AUDIT_ARCH_LOONGARCH64 (EM_LOONGARCH|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE) #define AUDIT_PERM_EXEC 1 #define AUDIT_PERM_WRITE 2 diff --git a/include/uapi/linux/elf-em.h b/include/uapi/linux/elf-em.h index f47e853546fa..ef38c2bc5ab7 100644 --- a/include/uapi/linux/elf-em.h +++ b/include/uapi/linux/elf-em.h @@ -51,6 +51,7 @@ #define EM_RISCV 243 /* RISC-V */ #define EM_BPF 247 /* Linux BPF - in-kernel virtual machine */ #define EM_CSKY 252 /* C-SKY */ +#define EM_LOONGARCH 258 /* LoongArch */ #define EM_FRV 0x5441 /* Fujitsu FR-V */ /* diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index c4abd09c3da9..2b9f5e9985e5 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -438,6 +438,11 @@ typedef struct elf64_shdr { #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ #define NT_MIPS_FP_MODE 0x801 /* MIPS floating-point mode */ #define NT_MIPS_MSA 0x802 /* MIPS SIMD registers */ +#define NT_LOONGARCH_CPUCFG 0xa00 /* LoongArch CPU config registers */ +#define NT_LOONGARCH_CSR 0xa01 /* LoongArch control and status registers */ +#define NT_LOONGARCH_LSX 0xa02 /* LoongArch Loongson SIMD Extension registers */ +#define NT_LOONGARCH_LASX 0xa03 /* LoongArch Loongson Advanced SIMD Extension registers */ +#define NT_LOONGARCH_LBT 0xa04 /* LoongArch Loongson Binary Translation registers */ /* Note types with note name "GNU" */ #define NT_GNU_PROPERTY_TYPE_0 5 diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h index fb7e2ef60825..981016e05cfa 100644 --- a/include/uapi/linux/kexec.h +++ b/include/uapi/linux/kexec.h @@ -43,6 +43,7 @@ #define KEXEC_ARCH_MIPS ( 8 << 16) #define KEXEC_ARCH_AARCH64 (183 << 16) #define KEXEC_ARCH_RISCV (243 << 16) +#define KEXEC_ARCH_LOONGARCH (258 << 16) /* The artificial cap on the number of segments passed to kexec_load. */ #define KEXEC_SEGMENT_MAX 16 -- cgit v1.2.3 From 439057ec3b748b1ff61855d09859f369493e22d8 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Tue, 31 May 2022 18:04:10 +0800 Subject: LoongArch: Add writecombine support for drm LoongArch maintains cache coherency in hardware, but its WUC attribute (Weak-ordered UnCached, which is similar to WC) is out of the scope of cache coherency machanism. This means WUC can only used for write-only memory regions. Cc: Daniel Vetter Cc: dri-devel@lists.freedesktop.org Reviewed-by: WANG Xuerui Reviewed-by: Jiaxun Yang Signed-off-by: Huacai Chen --- include/drm/drm_cache.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/drm/drm_cache.h b/include/drm/drm_cache.h index 22deb216b59c..08e0e3ffad13 100644 --- a/include/drm/drm_cache.h +++ b/include/drm/drm_cache.h @@ -67,6 +67,14 @@ static inline bool drm_arch_can_wc_memory(void) * optimization entirely for ARM and arm64. */ return false; +#elif defined(CONFIG_LOONGARCH) + /* + * LoongArch maintains cache coherency in hardware, but its WUC attribute + * (Weak-ordered UnCached, which is similar to WC) is out of the scope of + * cache coherency machanism. This means WUC can only used for write-only + * memory regions. + */ + return false; #else return true; #endif -- cgit v1.2.3 From 46859ac8af52ae599e1b51992ddef3eb43f295fc Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Tue, 31 May 2022 18:04:12 +0800 Subject: LoongArch: Add multi-processor (SMP) support LoongArch-based procesors have 4, 8 or 16 cores per package. This patch adds multi-processor (SMP) support for LoongArch. Reviewed-by: WANG Xuerui Reviewed-by: Jiaxun Yang Signed-off-by: Huacai Chen --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index b66c5f389159..19f0dbfdd7fe 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -130,6 +130,7 @@ enum cpuhp_state { CPUHP_ZCOMP_PREPARE, CPUHP_TIMERS_PREPARE, CPUHP_MIPS_SOC_PREPARE, + CPUHP_LOONGARCH_SOC_PREPARE, CPUHP_BP_PREPARE_DYN, CPUHP_BP_PREPARE_DYN_END = CPUHP_BP_PREPARE_DYN + 20, CPUHP_BRINGUP_CPU, -- cgit v1.2.3 From 6d7131bd52b3e0dd068a0067e5584b3f36cf17eb Mon Sep 17 00:00:00 2001 From: Anna-Maria Behnsen Date: Mon, 11 Apr 2022 17:05:55 +0200 Subject: include/linux/find: Fix documentation The order of the arguments in function documentation doesn't fit the implementation. Change the documentation so that it corresponds to the code. This prevent people to get confused when reading the documentation. Signed-off-by: Anna-Maria Behnsen Reviewed-by: Andy Shevchenko Signed-off-by: Yury Norov --- include/linux/find.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/find.h b/include/linux/find.h index 5bb6db213bcb..424ef67d4a42 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -21,8 +21,8 @@ extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long siz /** * find_next_bit - find the next set bit in a memory region * @addr: The address to base the search on - * @offset: The bitnumber to start searching at * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. @@ -50,8 +50,8 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, * find_next_and_bit - find the next set bit in both memory regions * @addr1: The first address to base the search on * @addr2: The second address to base the search on - * @offset: The bitnumber to start searching at * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at * * Returns the bit number for the next set bit * If no bits are set, returns @size. @@ -79,8 +79,8 @@ unsigned long find_next_and_bit(const unsigned long *addr1, /** * find_next_zero_bit - find the next cleared bit in a memory region * @addr: The address to base the search on - * @offset: The bitnumber to start searching at * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at * * Returns the bit number of the next zero bit * If no bits are zero, returns @size. -- cgit v1.2.3 From e041e0ac53dd52d2d201aa87edc3adaca1085299 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 28 Apr 2022 13:51:12 -0700 Subject: lib/bitmap: extend comment for bitmap_(from,to)_arr32() On LE systems bitmaps are naturally ordered, therefore we can potentially use bitmap_copy routines when converting from 32-bit arrays, even if host system is 64-bit. But it may lead to out-of-bond access due to unsafe typecast, and the bitmap_(from,to)_arr32 comment doesn't explain that clearly CC: Alexander Gordeev CC: Andy Shevchenko CC: Christian Borntraeger CC: Claudio Imbrenda CC: David Hildenbrand CC: Heiko Carstens CC: Janosch Frank CC: Rasmus Villemoes CC: Sven Schnelle CC: Vasily Gorbik Signed-off-by: Yury Norov --- include/linux/bitmap.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 7dba0847510c..afcf7b8dddd1 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -264,8 +264,12 @@ static inline void bitmap_copy_clear_tail(unsigned long *dst, } /* - * On 32-bit systems bitmaps are represented as u32 arrays internally, and - * therefore conversion is not needed when copying data from/to arrays of u32. + * On 32-bit systems bitmaps are represented as u32 arrays internally. On LE64 + * machines the order of hi and lo parts of numbers match the bitmap structure. + * In both cases conversion is not needed when copying data from/to arrays of + * u32. But in LE64 case, typecast in bitmap_copy_clear_tail() may lead + * to out-of-bound access. To avoid that, both LE and BE variants of 64-bit + * architectures are not using bitmap_copy_clear_tail(). */ #if BITS_PER_LONG == 64 void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf, -- cgit v1.2.3 From 0a97953fd2210d0ac8eb5c76f8bd08fb53b6d3d6 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 28 Apr 2022 13:51:13 -0700 Subject: lib: add bitmap_{from,to}_arr64 Manipulating 64-bit arrays with bitmap functions is potentially dangerous because on 32-bit BE machines the order of halfwords doesn't match. Another issue is that compiler may throw a warning about out-of-boundary access. This patch adds bitmap_{from,to}_arr64 functions in addition to existing bitmap_{from,to}_arr32. CC: Alexander Gordeev CC: Andy Shevchenko CC: Christian Borntraeger CC: Claudio Imbrenda CC: David Hildenbrand CC: Heiko Carstens CC: Janosch Frank CC: Rasmus Villemoes CC: Sven Schnelle CC: Vasily Gorbik Signed-off-by: Yury Norov --- include/linux/bitmap.h | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index afcf7b8dddd1..71147b7d721b 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -72,6 +72,8 @@ struct device; * bitmap_allocate_region(bitmap, pos, order) Allocate specified bit region * bitmap_from_arr32(dst, buf, nbits) Copy nbits from u32[] buf to dst * bitmap_to_arr32(buf, src, nbits) Copy nbits from buf to u32[] dst + * bitmap_to_arr64(buf, src, nbits) Copy nbits from buf to u64[] dst + * bitmap_to_arr64(buf, src, nbits) Copy nbits from buf to u64[] dst * bitmap_get_value8(map, start) Get 8bit value from map at start * bitmap_set_value8(map, value, start) Set 8bit value to map at start * @@ -285,6 +287,22 @@ void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, (const unsigned long *) (bitmap), (nbits)) #endif +/* + * On 64-bit systems bitmaps are represented as u64 arrays internally. On LE32 + * machines the order of hi and lo parts of numbers match the bitmap structure. + * In both cases conversion is not needed when copying data from/to arrays of + * u64. + */ +#if (BITS_PER_LONG == 32) && defined(__BIG_ENDIAN) +void bitmap_from_arr64(unsigned long *bitmap, const u64 *buf, unsigned int nbits); +void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits); +#else +#define bitmap_from_arr64(bitmap, buf, nbits) \ + bitmap_copy_clear_tail((unsigned long *)(bitmap), (const unsigned long *)(buf), (nbits)) +#define bitmap_to_arr64(buf, bitmap, nbits) \ + bitmap_copy_clear_tail((unsigned long *)(buf), (const unsigned long *)(bitmap), (nbits)) +#endif + static inline int bitmap_and(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { @@ -518,10 +536,7 @@ static inline void bitmap_next_set_region(unsigned long *bitmap, */ static inline void bitmap_from_u64(unsigned long *dst, u64 mask) { - dst[0] = mask & ULONG_MAX; - - if (sizeof(mask) > sizeof(unsigned long)) - dst[1] = mask >> 32; + bitmap_from_arr64(dst, &mask, 64); } /** -- cgit v1.2.3 From 005f17007f47495dbbb659aa5db7e581065d16e7 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 18 May 2022 13:52:22 -0700 Subject: bitmap: Fix return values to be unsigned Both nodemask and bitmap routines had mixed return values that provided potentially signed return values that could never happen. This was leading to the compiler getting confusing about the range of possible return values (it was thinking things could be negative where they could not be). In preparation for fixing nodemask, fix all the bitmap routines that should be returning unsigned (or bool) values. Cc: Yury Norov Cc: Rasmus Villemoes Cc: Christophe de Dinechin Cc: Alexey Dobriyan Cc: Andy Shevchenko Cc: Andrew Morton Cc: Zhen Lei Signed-off-by: Kees Cook Signed-off-by: Yury Norov --- include/linux/bitmap.h | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 71147b7d721b..2e6cd5681040 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -134,8 +134,8 @@ unsigned long *devm_bitmap_zalloc(struct device *dev, * lib/bitmap.c provides these functions: */ -int __bitmap_equal(const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int nbits); +bool __bitmap_equal(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); bool __pure __bitmap_or_equal(const unsigned long *src1, const unsigned long *src2, const unsigned long *src3, @@ -159,10 +159,10 @@ int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, void __bitmap_replace(unsigned long *dst, const unsigned long *old, const unsigned long *new, const unsigned long *mask, unsigned int nbits); -int __bitmap_intersects(const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int nbits); -int __bitmap_subset(const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int nbits); +bool __bitmap_intersects(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); +bool __bitmap_subset(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); void __bitmap_set(unsigned long *map, unsigned int start, int len); void __bitmap_clear(unsigned long *map, unsigned int start, int len); @@ -353,8 +353,8 @@ static inline void bitmap_complement(unsigned long *dst, const unsigned long *sr #endif #define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1) -static inline int bitmap_equal(const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static inline bool bitmap_equal(const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); @@ -384,8 +384,9 @@ static inline bool bitmap_or_equal(const unsigned long *src1, return !(((*src1 | *src2) ^ *src3) & BITMAP_LAST_WORD_MASK(nbits)); } -static inline int bitmap_intersects(const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static inline bool bitmap_intersects(const unsigned long *src1, + const unsigned long *src2, + unsigned int nbits) { if (small_const_nbits(nbits)) return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0; @@ -393,8 +394,8 @@ static inline int bitmap_intersects(const unsigned long *src1, return __bitmap_intersects(src1, src2, nbits); } -static inline int bitmap_subset(const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static inline bool bitmap_subset(const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits)); -- cgit v1.2.3 From 0dfe54071d7c828a02917b595456bfde1afdddc9 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 18 May 2022 13:52:23 -0700 Subject: nodemask: Fix return values to be unsigned MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The nodemask routines had mixed return values that provided potentially signed return values that could never happen. This was leading to the compiler getting confusing about the range of possible return values (it was thinking things could be negative where they could not be). Fix all the nodemask routines that should be returning unsigned (or bool) values. Silences: mm/swapfile.c: In function ‘setup_swap_info’: mm/swapfile.c:2291:47: error: array subscript -1 is below array bounds of ‘struct plist_node[]’ [-Werror=array-bounds] 2291 | p->avail_lists[i].prio = 1; | ~~~~~~~~~~~~~~^~~ In file included from mm/swapfile.c:16: ./include/linux/swap.h:292:27: note: while referencing ‘avail_lists’ 292 | struct plist_node avail_lists[]; /* | ^~~~~~~~~~~ Reported-by: Christophe de Dinechin Link: https://lore.kernel.org/lkml/20220414150855.2407137-3-dinechin@redhat.com/ Cc: Alexey Dobriyan Cc: Yury Norov Cc: Andy Shevchenko Cc: Rasmus Villemoes Cc: Andrew Morton Cc: Zhen Lei Signed-off-by: Kees Cook Signed-off-by: Yury Norov --- include/linux/nodemask.h | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 567c3ddba2c4..2c39663c3407 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -42,11 +42,11 @@ * void nodes_shift_right(dst, src, n) Shift right * void nodes_shift_left(dst, src, n) Shift left * - * int first_node(mask) Number lowest set bit, or MAX_NUMNODES - * int next_node(node, mask) Next node past 'node', or MAX_NUMNODES - * int next_node_in(node, mask) Next node past 'node', or wrap to first, + * unsigned int first_node(mask) Number lowest set bit, or MAX_NUMNODES + * unsigend int next_node(node, mask) Next node past 'node', or MAX_NUMNODES + * unsigned int next_node_in(node, mask) Next node past 'node', or wrap to first, * or MAX_NUMNODES - * int first_unset_node(mask) First node not set in mask, or + * unsigned int first_unset_node(mask) First node not set in mask, or * MAX_NUMNODES * * nodemask_t nodemask_of_node(node) Return nodemask with bit 'node' set @@ -153,7 +153,7 @@ static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) #define node_test_and_set(node, nodemask) \ __node_test_and_set((node), &(nodemask)) -static inline int __node_test_and_set(int node, nodemask_t *addr) +static inline bool __node_test_and_set(int node, nodemask_t *addr) { return test_and_set_bit(node, addr->bits); } @@ -200,7 +200,7 @@ static inline void __nodes_complement(nodemask_t *dstp, #define nodes_equal(src1, src2) \ __nodes_equal(&(src1), &(src2), MAX_NUMNODES) -static inline int __nodes_equal(const nodemask_t *src1p, +static inline bool __nodes_equal(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_equal(src1p->bits, src2p->bits, nbits); @@ -208,7 +208,7 @@ static inline int __nodes_equal(const nodemask_t *src1p, #define nodes_intersects(src1, src2) \ __nodes_intersects(&(src1), &(src2), MAX_NUMNODES) -static inline int __nodes_intersects(const nodemask_t *src1p, +static inline bool __nodes_intersects(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_intersects(src1p->bits, src2p->bits, nbits); @@ -216,20 +216,20 @@ static inline int __nodes_intersects(const nodemask_t *src1p, #define nodes_subset(src1, src2) \ __nodes_subset(&(src1), &(src2), MAX_NUMNODES) -static inline int __nodes_subset(const nodemask_t *src1p, +static inline bool __nodes_subset(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_subset(src1p->bits, src2p->bits, nbits); } #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES) -static inline int __nodes_empty(const nodemask_t *srcp, unsigned int nbits) +static inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits) { return bitmap_empty(srcp->bits, nbits); } #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES) -static inline int __nodes_full(const nodemask_t *srcp, unsigned int nbits) +static inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits) { return bitmap_full(srcp->bits, nbits); } @@ -260,15 +260,15 @@ static inline void __nodes_shift_left(nodemask_t *dstp, > MAX_NUMNODES, then the silly min_ts could be dropped. */ #define first_node(src) __first_node(&(src)) -static inline int __first_node(const nodemask_t *srcp) +static inline unsigned int __first_node(const nodemask_t *srcp) { - return min_t(int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES)); + return min_t(unsigned int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES)); } #define next_node(n, src) __next_node((n), &(src)) -static inline int __next_node(int n, const nodemask_t *srcp) +static inline unsigned int __next_node(int n, const nodemask_t *srcp) { - return min_t(int,MAX_NUMNODES,find_next_bit(srcp->bits, MAX_NUMNODES, n+1)); + return min_t(unsigned int, MAX_NUMNODES, find_next_bit(srcp->bits, MAX_NUMNODES, n+1)); } /* @@ -276,7 +276,7 @@ static inline int __next_node(int n, const nodemask_t *srcp) * the first node in src if needed. Returns MAX_NUMNODES if src is empty. */ #define next_node_in(n, src) __next_node_in((n), &(src)) -int __next_node_in(int node, const nodemask_t *srcp); +unsigned int __next_node_in(int node, const nodemask_t *srcp); static inline void init_nodemask_of_node(nodemask_t *mask, int node) { @@ -296,9 +296,9 @@ static inline void init_nodemask_of_node(nodemask_t *mask, int node) }) #define first_unset_node(mask) __first_unset_node(&(mask)) -static inline int __first_unset_node(const nodemask_t *maskp) +static inline unsigned int __first_unset_node(const nodemask_t *maskp) { - return min_t(int,MAX_NUMNODES, + return min_t(unsigned int, MAX_NUMNODES, find_first_zero_bit(maskp->bits, MAX_NUMNODES)); } @@ -436,11 +436,11 @@ static inline int num_node_state(enum node_states state) #define first_online_node first_node(node_states[N_ONLINE]) #define first_memory_node first_node(node_states[N_MEMORY]) -static inline int next_online_node(int nid) +static inline unsigned int next_online_node(int nid) { return next_node(nid, node_states[N_ONLINE]); } -static inline int next_memory_node(int nid) +static inline unsigned int next_memory_node(int nid) { return next_node(nid, node_states[N_MEMORY]); } -- cgit v1.2.3 From e1cff7002b716bd0b5f5f4afd4273c99aa8644be Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 5 Jun 2022 11:51:48 -0700 Subject: bluetooth: don't use bitmaps for random flag accesses The bluetooth code uses our bitmap infrastructure for the two bits (!) of connection setup flags, and in the process causes odd problems when it converts between a bitmap and just the regular values of said bits. It's completely pointless to do things like bitmap_to_arr32() to convert a bitmap into a u32. It shoudln't have been a bitmap in the first place. The reason to use bitmaps is if you have arbitrary number of bits you want to manage (not two!), or if you rely on the atomicity guarantees of the bitmap setting and clearing. The code could use an "atomic_t" and use "atomic_or/andnot()" to set and clear the bit values, but considering that it then copies the bitmaps around with "bitmap_to_arr32()" and friends, there clearly cannot be a lot of atomicity requirements. So just use a regular integer. In the process, this avoids the warnings about erroneous use of bitmap_from_u64() which were triggered on 32-bit architectures when conversion from a u64 would access two words (and, surprise, surprise, only one word is needed - and indeed overkill - for a 2-bit bitmap). That was always problematic, but the compiler seems to notice it and warn about the invalid pattern only after commit 0a97953fd221 ("lib: add bitmap_{from,to}_arr64") changed the exact implementation details of 'bitmap_from_u64()', as reported by Sudip Mukherjee and Stephen Rothwell. Fixes: fe92ee6425a2 ("Bluetooth: hci_core: Rework hci_conn_params flags") Link: https://lore.kernel.org/all/YpyJ9qTNHJzz0FHY@debian/ Link: https://lore.kernel.org/all/20220606080631.0c3014f2@canb.auug.org.au/ Link: https://lore.kernel.org/all/20220605162537.1604762-1-yury.norov@gmail.com/ Reported-by: Stephen Rothwell Reported-by: Sudip Mukherjee Reviewed-by: Yury Norov Cc: Luiz Augusto von Dentz Cc: Marcel Holtmann Signed-off-by: Linus Torvalds --- include/net/bluetooth/hci_core.h | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 5a52a2018b56..c0ea2a4892b1 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -155,21 +155,18 @@ struct bdaddr_list_with_irk { u8 local_irk[16]; }; +/* Bitmask of connection flags */ enum hci_conn_flags { - HCI_CONN_FLAG_REMOTE_WAKEUP, - HCI_CONN_FLAG_DEVICE_PRIVACY, - - __HCI_CONN_NUM_FLAGS, + HCI_CONN_FLAG_REMOTE_WAKEUP = 1, + HCI_CONN_FLAG_DEVICE_PRIVACY = 2, }; - -/* Make sure number of flags doesn't exceed sizeof(current_flags) */ -static_assert(__HCI_CONN_NUM_FLAGS < 32); +typedef u8 hci_conn_flags_t; struct bdaddr_list_with_flags { struct list_head list; bdaddr_t bdaddr; u8 bdaddr_type; - DECLARE_BITMAP(flags, __HCI_CONN_NUM_FLAGS); + hci_conn_flags_t flags; }; struct bt_uuid { @@ -576,7 +573,7 @@ struct hci_dev { struct rfkill *rfkill; DECLARE_BITMAP(dev_flags, __HCI_NUM_FLAGS); - DECLARE_BITMAP(conn_flags, __HCI_CONN_NUM_FLAGS); + hci_conn_flags_t conn_flags; __s8 adv_tx_power; __u8 adv_data[HCI_MAX_EXT_AD_LENGTH]; @@ -775,7 +772,7 @@ struct hci_conn_params { struct hci_conn *conn; bool explicit_connect; - DECLARE_BITMAP(flags, __HCI_CONN_NUM_FLAGS); + hci_conn_flags_t flags; u8 privacy_mode; }; -- cgit v1.2.3 From a734510fa8b4e61e6a37176f0da01f4c55fa52de Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 25 May 2022 13:49:42 +0200 Subject: ata: libata: drop 'sas_last_tag' Unused now. Fixes: 4f1a22ee7b57 ("libata: Improve ATA queued command allocation") Cc: John Garry Signed-off-by: Hannes Reinecke Reviewed-by: John Garry Signed-off-by: Damien Le Moal --- include/linux/libata.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/libata.h b/include/linux/libata.h index 732de9014626..0f2a59c9c735 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -822,7 +822,6 @@ struct ata_port { struct ata_queued_cmd qcmd[ATA_MAX_QUEUE + 1]; u64 qc_active; int nr_active_links; /* #links with active qcs */ - unsigned int sas_last_tag; /* track next tag hw expects */ struct ata_link link; /* host default link */ struct ata_link *slave_link; /* see ata_slave_link_init() */ -- cgit v1.2.3 From 2130a790ca49763f724ec45cf93b9dd765e2023e Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 2 Jun 2022 15:05:26 +0200 Subject: kernel: add platform_has() infrastructure Add a simple infrastructure for setting, resetting and querying platform feature flags. Flags can be either global or architecture specific. Signed-off-by: Juergen Gross Reviewed-by: Oleksandr Tyshchenko Tested-by: Oleksandr Tyshchenko # Arm64 only Reviewed-by: Christoph Hellwig Acked-by: Borislav Petkov Signed-off-by: Juergen Gross --- include/asm-generic/Kbuild | 1 + include/asm-generic/platform-feature.h | 8 ++++++++ include/linux/platform-feature.h | 15 +++++++++++++++ 3 files changed, 24 insertions(+) create mode 100644 include/asm-generic/platform-feature.h create mode 100644 include/linux/platform-feature.h (limited to 'include') diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild index 302506bbc2a4..8e47d483b524 100644 --- a/include/asm-generic/Kbuild +++ b/include/asm-generic/Kbuild @@ -44,6 +44,7 @@ mandatory-y += msi.h mandatory-y += pci.h mandatory-y += percpu.h mandatory-y += pgalloc.h +mandatory-y += platform-feature.h mandatory-y += preempt.h mandatory-y += rwonce.h mandatory-y += sections.h diff --git a/include/asm-generic/platform-feature.h b/include/asm-generic/platform-feature.h new file mode 100644 index 000000000000..4b0af3d51588 --- /dev/null +++ b/include/asm-generic/platform-feature.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_GENERIC_PLATFORM_FEATURE_H +#define _ASM_GENERIC_PLATFORM_FEATURE_H + +/* Number of arch specific feature flags. */ +#define PLATFORM_ARCH_FEAT_N 0 + +#endif /* _ASM_GENERIC_PLATFORM_FEATURE_H */ diff --git a/include/linux/platform-feature.h b/include/linux/platform-feature.h new file mode 100644 index 000000000000..6ed859928b97 --- /dev/null +++ b/include/linux/platform-feature.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _PLATFORM_FEATURE_H +#define _PLATFORM_FEATURE_H + +#include +#include + +/* The platform features are starting with the architecture specific ones. */ +#define PLATFORM_FEAT_N (0 + PLATFORM_ARCH_FEAT_N) + +void platform_set(unsigned int feature); +void platform_clear(unsigned int feature); +bool platform_has(unsigned int feature); + +#endif /* _PLATFORM_FEATURE_H */ -- cgit v1.2.3 From 3f9dfbebdc48cebfbda738f6f3d1dbf6d7232f90 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 6 Jun 2022 08:09:16 +0200 Subject: virtio: replace arch_has_restricted_virtio_memory_access() Instead of using arch_has_restricted_virtio_memory_access() together with CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS, replace those with platform_has() and a new platform feature PLATFORM_VIRTIO_RESTRICTED_MEM_ACCESS. Signed-off-by: Juergen Gross Reviewed-by: Oleksandr Tyshchenko Tested-by: Oleksandr Tyshchenko # Arm64 only Reviewed-by: Christoph Hellwig Acked-by: Borislav Petkov --- include/linux/platform-feature.h | 6 +++++- include/linux/virtio_config.h | 9 --------- 2 files changed, 5 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/platform-feature.h b/include/linux/platform-feature.h index 6ed859928b97..b2f48be999fa 100644 --- a/include/linux/platform-feature.h +++ b/include/linux/platform-feature.h @@ -6,7 +6,11 @@ #include /* The platform features are starting with the architecture specific ones. */ -#define PLATFORM_FEAT_N (0 + PLATFORM_ARCH_FEAT_N) + +/* Used to enable platform specific DMA handling for virtio devices. */ +#define PLATFORM_VIRTIO_RESTRICTED_MEM_ACCESS (0 + PLATFORM_ARCH_FEAT_N) + +#define PLATFORM_FEAT_N (1 + PLATFORM_ARCH_FEAT_N) void platform_set(unsigned int feature); void platform_clear(unsigned int feature); diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 9a36051ceb76..49c7c32815f1 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -604,13 +604,4 @@ static inline void virtio_cwrite64(struct virtio_device *vdev, _r; \ }) -#ifdef CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS -int arch_has_restricted_virtio_memory_access(void); -#else -static inline int arch_has_restricted_virtio_memory_access(void) -{ - return 0; -} -#endif /* CONFIG_ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS */ - #endif /* _LINUX_VIRTIO_CONFIG_H */ -- cgit v1.2.3 From 9bf22421dc8a69cade3c994771637e9693ff0216 Mon Sep 17 00:00:00 2001 From: Oleksandr Tyshchenko Date: Thu, 2 Jun 2022 22:23:46 +0300 Subject: arm/xen: Introduce xen_setup_dma_ops() This patch introduces new helper and places it in new header. The helper's purpose is to assign any Xen specific DMA ops in a single place. For now, we deal with xen-swiotlb DMA ops only. The one of the subsequent commits in current series will add xen-grant DMA ops case. Also re-use the xen_swiotlb_detect() check on Arm32. Signed-off-by: Oleksandr Tyshchenko Reviewed-by: Stefano Stabellini [For arm64] Acked-by: Catalin Marinas Link: https://lore.kernel.org/r/1654197833-25362-2-git-send-email-olekstysh@gmail.com Signed-off-by: Juergen Gross --- include/xen/arm/xen-ops.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) create mode 100644 include/xen/arm/xen-ops.h (limited to 'include') diff --git a/include/xen/arm/xen-ops.h b/include/xen/arm/xen-ops.h new file mode 100644 index 000000000000..288deb1c3ac9 --- /dev/null +++ b/include/xen/arm/xen-ops.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_ARM_XEN_OPS_H +#define _ASM_ARM_XEN_OPS_H + +#include + +static inline void xen_setup_dma_ops(struct device *dev) +{ +#ifdef CONFIG_XEN + if (xen_swiotlb_detect()) + dev->dma_ops = &xen_swiotlb_dma_ops; +#endif +} + +#endif /* _ASM_ARM_XEN_OPS_H */ -- cgit v1.2.3 From 02a9e681a3f7998074f39ec265080bf934871530 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 2 Jun 2022 22:23:47 +0300 Subject: xen/grants: support allocating consecutive grants For support of virtio via grant mappings in rare cases larger mappings using consecutive grants are needed. Support those by adding a bitmap of free grants. As consecutive grants will be needed only in very rare cases (e.g. when configuring a virtio device with a multi-page ring), optimize for the normal case of non-consecutive allocations. Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Link: https://lore.kernel.org/r/1654197833-25362-3-git-send-email-olekstysh@gmail.com Signed-off-by: Juergen Gross --- include/xen/grant_table.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index 527c9907f99c..e279be353e3f 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -127,10 +127,14 @@ int gnttab_try_end_foreign_access(grant_ref_t ref); */ int gnttab_alloc_grant_references(u16 count, grant_ref_t *pprivate_head); +int gnttab_alloc_grant_reference_seq(unsigned int count, grant_ref_t *first); + void gnttab_free_grant_reference(grant_ref_t ref); void gnttab_free_grant_references(grant_ref_t head); +void gnttab_free_grant_reference_seq(grant_ref_t head, unsigned int count); + int gnttab_empty_grant_references(const grant_ref_t *pprivate_head); int gnttab_claim_grant_reference(grant_ref_t *pprivate_head); -- cgit v1.2.3 From d6aca3504c7ded5f4f46957e3685b9344d9743dd Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 2 Jun 2022 22:23:48 +0300 Subject: xen/grant-dma-ops: Add option to restrict memory access under Xen Introduce Xen grant DMA-mapping layer which contains special DMA-mapping routines for providing grant references as DMA addresses to be used by frontends (e.g. virtio) in Xen guests. Add the needed functionality by providing a special set of DMA ops handling the needed grant operations for the I/O pages. The subsequent commit will introduce the use case for xen-grant DMA ops layer to enable using virtio devices in Xen guests in a safe manner. Signed-off-by: Juergen Gross Signed-off-by: Oleksandr Tyshchenko Reviewed-by: Stefano Stabellini Link: https://lore.kernel.org/r/1654197833-25362-4-git-send-email-olekstysh@gmail.com Signed-off-by: Juergen Gross --- include/xen/xen-ops.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index c7c1b46ff4cd..afd586d717a4 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -214,4 +214,12 @@ static inline void xen_preemptible_hcall_end(void) { } #endif /* CONFIG_XEN_PV && !CONFIG_PREEMPTION */ +#ifdef CONFIG_XEN_GRANT_DMA_OPS +void xen_grant_setup_dma_ops(struct device *dev); +#else +static inline void xen_grant_setup_dma_ops(struct device *dev) +{ +} +#endif /* CONFIG_XEN_GRANT_DMA_OPS */ + #endif /* INCLUDE_XEN_OPS_H */ -- cgit v1.2.3 From fa1f57421e0b1c57843902c89728f823abc32f02 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Thu, 2 Jun 2022 22:23:49 +0300 Subject: xen/virtio: Enable restricted memory access using Xen grant mappings In order to support virtio in Xen guests add a config option XEN_VIRTIO enabling the user to specify whether in all Xen guests virtio should be able to access memory via Xen grant mappings only on the host side. Also set PLATFORM_VIRTIO_RESTRICTED_MEM_ACCESS feature from the guest initialization code on Arm and x86 if CONFIG_XEN_VIRTIO is enabled. Signed-off-by: Juergen Gross Signed-off-by: Oleksandr Tyshchenko Reviewed-by: Stefano Stabellini Reviewed-by: Boris Ostrovsky Link: https://lore.kernel.org/r/1654197833-25362-5-git-send-email-olekstysh@gmail.com Signed-off-by: Juergen Gross --- include/xen/xen.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/xen/xen.h b/include/xen/xen.h index a99bab817523..0780a81e140d 100644 --- a/include/xen/xen.h +++ b/include/xen/xen.h @@ -52,6 +52,14 @@ bool xen_biovec_phys_mergeable(const struct bio_vec *vec1, extern u64 xen_saved_max_mem_size; #endif +#include + +static inline void xen_set_restricted_virtio_memory_access(void) +{ + if (IS_ENABLED(CONFIG_XEN_VIRTIO) && xen_domain()) + platform_set(PLATFORM_VIRTIO_RESTRICTED_MEM_ACCESS); +} + #ifdef CONFIG_XEN_UNPOPULATED_ALLOC int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages); void xen_free_unpopulated_pages(unsigned int nr_pages, struct page **pages); -- cgit v1.2.3 From 625ab90ecdf7770bda7ae21c4d5c938aa9b43bb4 Mon Sep 17 00:00:00 2001 From: Oleksandr Tyshchenko Date: Thu, 2 Jun 2022 22:23:52 +0300 Subject: xen/grant-dma-ops: Retrieve the ID of backend's domain for DT devices Use the presence of "iommus" property pointed to the IOMMU node with recently introduced "xen,grant-dma" compatible as a clear indicator of enabling Xen grant mappings scheme for that device and read the ID of Xen domain where the corresponding backend is running. The domid (domain ID) is used as an argument to the Xen grant mapping APIs. To avoid the deferred probe timeout which takes place after reusing generic IOMMU device tree bindings (because the IOMMU device never becomes available) enable recently introduced stub IOMMU driver by selecting XEN_GRANT_DMA_IOMMU. Also introduce xen_is_grant_dma_device() to check whether xen-grant DMA ops need to be set for a passed device. Remove the hardcoded domid 0 in xen_grant_setup_dma_ops(). Signed-off-by: Oleksandr Tyshchenko Reviewed-by: Stefano Stabellini Link: https://lore.kernel.org/r/1654197833-25362-8-git-send-email-olekstysh@gmail.com Signed-off-by: Juergen Gross --- include/xen/xen-ops.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index afd586d717a4..80546960f8b7 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -216,10 +216,15 @@ static inline void xen_preemptible_hcall_end(void) { } #ifdef CONFIG_XEN_GRANT_DMA_OPS void xen_grant_setup_dma_ops(struct device *dev); +bool xen_is_grant_dma_device(struct device *dev); #else static inline void xen_grant_setup_dma_ops(struct device *dev) { } +static inline bool xen_is_grant_dma_device(struct device *dev) +{ + return false; +} #endif /* CONFIG_XEN_GRANT_DMA_OPS */ #endif /* INCLUDE_XEN_OPS_H */ -- cgit v1.2.3 From fea981610c25173e6e5d63ccd4fce49739663ab0 Mon Sep 17 00:00:00 2001 From: Oleksandr Tyshchenko Date: Thu, 2 Jun 2022 22:23:53 +0300 Subject: arm/xen: Assign xen-grant DMA ops for xen-grant DMA devices By assigning xen-grant DMA ops we will restrict memory access for passed device using Xen grant mappings. This is needed for using any virtualized device (e.g. virtio) in Xen guests in a safe manner. Please note, for the virtio devices the XEN_VIRTIO config should be enabled (it forces ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS). Signed-off-by: Oleksandr Tyshchenko Reviewed-by: Stefano Stabellini Link: https://lore.kernel.org/r/1654197833-25362-9-git-send-email-olekstysh@gmail.com Signed-off-by: Juergen Gross --- include/xen/arm/xen-ops.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/xen/arm/xen-ops.h b/include/xen/arm/xen-ops.h index 288deb1c3ac9..b0766a660338 100644 --- a/include/xen/arm/xen-ops.h +++ b/include/xen/arm/xen-ops.h @@ -3,11 +3,14 @@ #define _ASM_ARM_XEN_OPS_H #include +#include static inline void xen_setup_dma_ops(struct device *dev) { #ifdef CONFIG_XEN - if (xen_swiotlb_detect()) + if (xen_is_grant_dma_device(dev)) + xen_grant_setup_dma_ops(dev); + else if (xen_swiotlb_detect()) dev->dma_ops = &xen_swiotlb_dma_ops; #endif } -- cgit v1.2.3 From 3a41c64d9c1185a2f3a184015e2a9b78bfc99c71 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 6 Jun 2022 17:31:29 +0200 Subject: netfilter: nf_tables: bail out early if hardware offload is not supported If user requests for NFT_CHAIN_HW_OFFLOAD, then check if either device provides the .ndo_setup_tc interface or there is an indirect flow block that has been registered. Otherwise, bail out early from the preparation phase. Moreover, validate that family == NFPROTO_NETDEV and hook is NF_NETDEV_INGRESS. Fixes: c9626a2cbdb2 ("netfilter: nf_tables: add hardware offload support") Signed-off-by: Pablo Neira Ayuso --- include/net/flow_offload.h | 1 + include/net/netfilter/nf_tables_offload.h | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 021778a7e1af..6484095a8c01 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -612,5 +612,6 @@ int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch, enum tc_setup_type type, void *data, struct flow_block_offload *bo, void (*cleanup)(struct flow_block_cb *block_cb)); +bool flow_indr_dev_exists(void); #endif /* _NET_FLOW_OFFLOAD_H */ diff --git a/include/net/netfilter/nf_tables_offload.h b/include/net/netfilter/nf_tables_offload.h index 797147843958..3568b6a2f5f0 100644 --- a/include/net/netfilter/nf_tables_offload.h +++ b/include/net/netfilter/nf_tables_offload.h @@ -92,7 +92,7 @@ int nft_flow_rule_offload_commit(struct net *net); NFT_OFFLOAD_MATCH(__key, __base, __field, __len, __reg) \ memset(&(__reg)->mask, 0xff, (__reg)->len); -int nft_chain_offload_priority(struct nft_base_chain *basechain); +bool nft_chain_offload_support(const struct nft_base_chain *basechain); int nft_offload_init(void); void nft_offload_exit(void); -- cgit v1.2.3 From 7b6c7a877cc616bc7dc9cd39646fe454acbed48b Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 3 Jun 2022 08:04:44 -0700 Subject: x86/ftrace: Remove OBJECT_FILES_NON_STANDARD usage The file-wide OBJECT_FILES_NON_STANDARD annotation is used with CONFIG_FRAME_POINTER to tell objtool to skip the entire file when frame pointers are enabled. However that annotation is now deprecated because it doesn't work with IBT, where objtool runs on vmlinux.o instead of individual translation units. Instead, use more fine-grained function-specific annotations: - The 'save_mcount_regs' macro does funny things with the frame pointer. Use STACK_FRAME_NON_STANDARD_FP to tell objtool to ignore the functions using it. - The return_to_handler() "function" isn't actually a callable function. Instead of being called, it's returned to. The real return address isn't on the stack, so unwinding is already doomed no matter which unwinder is used. So just remove the STT_FUNC annotation, telling objtool to ignore it. That also removes the implicit ANNOTATE_NOENDBR, which now needs to be made explicit. Fixes the following warning: vmlinux.o: warning: objtool: __fentry__+0x16: return with modified stack frame Fixes: ed53a0d97192 ("x86/alternative: Use .ibt_endbr_seal to seal indirect calls") Reported-by: kernel test robot Signed-off-by: Josh Poimboeuf Link: https://lore.kernel.org/r/b7a7a42fe306aca37826043dac89e113a1acdbac.1654268610.git.jpoimboe@kernel.org --- include/linux/objtool.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 6491fa8fba6d..15b940ec1eac 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -143,6 +143,12 @@ struct unwind_hint { .popsection .endm +.macro STACK_FRAME_NON_STANDARD_FP func:req +#ifdef CONFIG_FRAME_POINTER + STACK_FRAME_NON_STANDARD \func +#endif +.endm + .macro ANNOTATE_NOENDBR .Lhere_\@: .pushsection .discard.noendbr -- cgit v1.2.3 From 77991645952c21962a095910c51fe0f73d35bf91 Mon Sep 17 00:00:00 2001 From: Roger Knecht Date: Sat, 21 May 2022 14:47:45 +0200 Subject: crc-itu-t: fix typo in CRC ITU-T polynomial comment The code comment says that the polynomial is x^16 + x^12 + x^15 + 1, but the correct polynomial is x^16 + x^12 + x^5 + 1. Quoting from page 2 in the ITU-T V.41 specification [1]: 2 Encoding and checking process The service bits and information bits, taken in conjunction, correspond to the coefficients of a message polynomial having terms from x^(n-1) (n = total number of bits in a block or sequence) down to x^16. This polynomial is divided, modulo 2, by the generating polynomial x^16 + x^12 + x^5 + 1. The hex (truncated) polynomial 0x1021 and CRC code implementation are correct, however. [1] https://www.itu.int/rec/T-REC-V.41-198811-I/en Signed-off-by: Roger Knecht Acked-by: Randy Dunlap Signed-off-by: Jason A. Donenfeld --- include/linux/crc-itu-t.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/crc-itu-t.h b/include/linux/crc-itu-t.h index a4367051e192..2f991a427ade 100644 --- a/include/linux/crc-itu-t.h +++ b/include/linux/crc-itu-t.h @@ -4,7 +4,7 @@ * * Implements the standard CRC ITU-T V.41: * Width 16 - * Poly 0x1021 (x^16 + x^12 + x^15 + 1) + * Poly 0x1021 (x^16 + x^12 + x^5 + 1) * Init 0 */ -- cgit v1.2.3 From c4f135d643823a869becfa87539f7820ef9d5bfa Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Wed, 1 Jun 2022 16:32:47 +0900 Subject: workqueue: Wrap flush_workqueue() using a macro Since flush operation synchronously waits for completion, flushing system-wide WQs (e.g. system_wq) might introduce possibility of deadlock due to unexpected locking dependency. Tejun Heo commented at [1] that it makes no sense at all to call flush_workqueue() on the shared WQs as the caller has no idea what it's gonna end up waiting for. Although there is flush_scheduled_work() which flushes system_wq WQ with "Think twice before calling this function! It's very easy to get into trouble if you don't take great care." warning message, syzbot found a circular locking dependency caused by flushing system_wq WQ [2]. Therefore, let's change the direction to that developers had better use their local WQs if flush_scheduled_work()/flush_workqueue(system_*_wq) is inevitable. Steps for converting system-wide WQs into local WQs are explained at [3], and a conversion to stop flushing system-wide WQs is in progress. Now we want some mechanism for preventing developers who are not aware of this conversion from again start flushing system-wide WQs. Since I found that WARN_ON() is complete but awkward approach for teaching developers about this problem, let's use __compiletime_warning() for incomplete but handy approach. For completeness, we will also insert WARN_ON() into __flush_workqueue() after all in-tree users stopped calling flush_scheduled_work(). Link: https://lore.kernel.org/all/YgnQGZWT%2Fn3VAITX@slm.duckdns.org/ [1] Link: https://syzkaller.appspot.com/bug?extid=bde0f89deacca7c765b8 [2] Link: https://lkml.kernel.org/r/49925af7-78a8-a3dd-bce6-cfc02e1a9236@I-love.SAKURA.ne.jp [3] Signed-off-by: Tetsuo Handa Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 64 +++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 56 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 7fee9b6cfede..e1f1c8b1121b 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -445,7 +445,7 @@ extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay); extern bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork); -extern void flush_workqueue(struct workqueue_struct *wq); +extern void __flush_workqueue(struct workqueue_struct *wq); extern void drain_workqueue(struct workqueue_struct *wq); extern int schedule_on_each_cpu(work_func_t func); @@ -563,15 +563,23 @@ static inline bool schedule_work(struct work_struct *work) return queue_work(system_wq, work); } +/* + * Detect attempt to flush system-wide workqueues at compile time when possible. + * + * See https://lkml.kernel.org/r/49925af7-78a8-a3dd-bce6-cfc02e1a9236@I-love.SAKURA.ne.jp + * for reasons and steps for converting system-wide workqueues into local workqueues. + */ +extern void __warn_flushing_systemwide_wq(void) + __compiletime_warning("Please avoid flushing system-wide workqueues."); + /** * flush_scheduled_work - ensure that any scheduled work has run to completion. * * Forces execution of the kernel-global workqueue and blocks until its * completion. * - * Think twice before calling this function! It's very easy to get into - * trouble if you don't take great care. Either of the following situations - * will lead to deadlock: + * It's very easy to get into trouble if you don't take great care. + * Either of the following situations will lead to deadlock: * * One of the work items currently on the workqueue needs to acquire * a lock held by your code or its caller. @@ -586,11 +594,51 @@ static inline bool schedule_work(struct work_struct *work) * need to know that a particular work item isn't queued and isn't running. * In such cases you should use cancel_delayed_work_sync() or * cancel_work_sync() instead. + * + * Please stop calling this function! A conversion to stop flushing system-wide + * workqueues is in progress. This function will be removed after all in-tree + * users stopped calling this function. */ -static inline void flush_scheduled_work(void) -{ - flush_workqueue(system_wq); -} +/* + * The background of commit 771c035372a036f8 ("deprecate the + * '__deprecated' attribute warnings entirely and for good") is that, + * since Linus builds all modules between every single pull he does, + * the standard kernel build needs to be _clean_ in order to be able to + * notice when new problems happen. Therefore, don't emit warning while + * there are in-tree users. + */ +#define flush_scheduled_work() \ +({ \ + if (0) \ + __warn_flushing_systemwide_wq(); \ + __flush_workqueue(system_wq); \ +}) + +/* + * Although there is no longer in-tree caller, for now just emit warning + * in order to give out-of-tree callers time to update. + */ +#define flush_workqueue(wq) \ +({ \ + struct workqueue_struct *_wq = (wq); \ + \ + if ((__builtin_constant_p(_wq == system_wq) && \ + _wq == system_wq) || \ + (__builtin_constant_p(_wq == system_highpri_wq) && \ + _wq == system_highpri_wq) || \ + (__builtin_constant_p(_wq == system_long_wq) && \ + _wq == system_long_wq) || \ + (__builtin_constant_p(_wq == system_unbound_wq) && \ + _wq == system_unbound_wq) || \ + (__builtin_constant_p(_wq == system_freezable_wq) && \ + _wq == system_freezable_wq) || \ + (__builtin_constant_p(_wq == system_power_efficient_wq) && \ + _wq == system_power_efficient_wq) || \ + (__builtin_constant_p(_wq == system_freezable_power_efficient_wq) && \ + _wq == system_freezable_power_efficient_wq)) \ + __warn_flushing_systemwide_wq(); \ + __flush_workqueue(_wq); \ +}) /** * schedule_delayed_work_on - queue work in global workqueue on CPU after delay -- cgit v1.2.3 From 873a400938b31a1e443c4d94b560b78300787540 Mon Sep 17 00:00:00 2001 From: Wonhyuk Yang Date: Wed, 4 May 2022 11:32:03 +0900 Subject: workqueue: Fix type of cpu in trace event The trace event "workqueue_queue_work" use unsigned int type for req_cpu, cpu. This casue confusing cpu number like below log. $ cat /sys/kernel/debug/tracing/trace cat-317 [001] ...: workqueue_queue_work: ... req_cpu=8192 cpu=4294967295 So, change unsigned type to signed type in the trace event. After applying this patch, cpu number will be printed as -1 instead of 4294967295 as folllows. $ cat /sys/kernel/debug/tracing/trace cat-1338 [002] ...: workqueue_queue_work: ... req_cpu=8192 cpu=-1 Cc: Baik Song An Cc: Hong Yeon Kim Cc: Taeung Song Cc: linuxgeek@linuxgeek.io Signed-off-by: Wonhyuk Yang Signed-off-by: Tejun Heo --- include/trace/events/workqueue.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h index 6154a2e72bce..262d52021c23 100644 --- a/include/trace/events/workqueue.h +++ b/include/trace/events/workqueue.h @@ -22,7 +22,7 @@ struct pool_workqueue; */ TRACE_EVENT(workqueue_queue_work, - TP_PROTO(unsigned int req_cpu, struct pool_workqueue *pwq, + TP_PROTO(int req_cpu, struct pool_workqueue *pwq, struct work_struct *work), TP_ARGS(req_cpu, pwq, work), @@ -31,8 +31,8 @@ TRACE_EVENT(workqueue_queue_work, __field( void *, work ) __field( void *, function) __string( workqueue, pwq->wq->name) - __field( unsigned int, req_cpu ) - __field( unsigned int, cpu ) + __field( int, req_cpu ) + __field( int, cpu ) ), TP_fast_assign( @@ -43,7 +43,7 @@ TRACE_EVENT(workqueue_queue_work, __entry->cpu = pwq->pool->cpu; ), - TP_printk("work struct=%p function=%ps workqueue=%s req_cpu=%u cpu=%u", + TP_printk("work struct=%p function=%ps workqueue=%s req_cpu=%d cpu=%d", __entry->work, __entry->function, __get_str(workqueue), __entry->req_cpu, __entry->cpu) ); -- cgit v1.2.3 From 62ed448cc53b654036f7d7f3c99f299d79ad14c3 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 7 Jun 2022 16:47:58 -0400 Subject: SUNRPC: Optimize xdr_reserve_space() Transitioning between encode buffers is quite infrequent. It happens about 1 time in 400 calls to xdr_reserve_space(), measured on NFSD with a typical build/test workload. Force the compiler to remove that code from xdr_reserve_space(), which is a hot path on both the server and the client. This change reduces the size of xdr_reserve_space() from 10 cache lines to 2 when compiled with -Os. Signed-off-by: Chuck Lever Reviewed-by: J. Bruce Fields --- include/linux/sunrpc/xdr.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 4417f667c757..5860f32e3958 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -243,7 +243,7 @@ extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes); extern int xdr_reserve_space_vec(struct xdr_stream *xdr, struct kvec *vec, size_t nbytes); -extern void xdr_commit_encode(struct xdr_stream *xdr); +extern void __xdr_commit_encode(struct xdr_stream *xdr); extern void xdr_truncate_encode(struct xdr_stream *xdr, size_t len); extern int xdr_restrict_buflen(struct xdr_stream *xdr, int newbuflen); extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, @@ -306,6 +306,20 @@ xdr_reset_scratch_buffer(struct xdr_stream *xdr) xdr_set_scratch_buffer(xdr, NULL, 0); } +/** + * xdr_commit_encode - Ensure all data is written to xdr->buf + * @xdr: pointer to xdr_stream + * + * Handle encoding across page boundaries by giving the caller a + * temporary location to write to, then later copying the data into + * place. __xdr_commit_encode() does that copying. + */ +static inline void xdr_commit_encode(struct xdr_stream *xdr) +{ + if (unlikely(xdr->scratch.iov_len)) + __xdr_commit_encode(xdr); +} + /** * xdr_stream_remaining - Return the number of bytes remaining in the stream * @xdr: pointer to struct xdr_stream -- cgit v1.2.3 From f93431c86b631bbca5614c66f966bf3ddb3c2803 Mon Sep 17 00:00:00 2001 From: Wang Yufen Date: Tue, 7 Jun 2022 20:00:27 +0800 Subject: ipv6: Fix signed integer overflow in __ip6_append_data Resurrect ubsan overflow checks and ubsan report this warning, fix it by change the variable [length] type to size_t. UBSAN: signed-integer-overflow in net/ipv6/ip6_output.c:1489:19 2147479552 + 8567 cannot be represented in type 'int' CPU: 0 PID: 253 Comm: err Not tainted 5.16.0+ #1 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace+0x214/0x230 show_stack+0x30/0x78 dump_stack_lvl+0xf8/0x118 dump_stack+0x18/0x30 ubsan_epilogue+0x18/0x60 handle_overflow+0xd0/0xf0 __ubsan_handle_add_overflow+0x34/0x44 __ip6_append_data.isra.48+0x1598/0x1688 ip6_append_data+0x128/0x260 udpv6_sendmsg+0x680/0xdd0 inet6_sendmsg+0x54/0x90 sock_sendmsg+0x70/0x88 ____sys_sendmsg+0xe8/0x368 ___sys_sendmsg+0x98/0xe0 __sys_sendmmsg+0xf4/0x3b8 __arm64_sys_sendmmsg+0x34/0x48 invoke_syscall+0x64/0x160 el0_svc_common.constprop.4+0x124/0x300 do_el0_svc+0x44/0xc8 el0_svc+0x3c/0x1e8 el0t_64_sync_handler+0x88/0xb0 el0t_64_sync+0x16c/0x170 Changes since v1: -Change the variable [length] type to unsigned, as Eric Dumazet suggested. Changes since v2: -Don't change exthdrlen type in ip6_make_skb, as Paolo Abeni suggested. Changes since v3: -Don't change ulen type in udpv6_sendmsg and l2tp_ip6_sendmsg, as Jakub Kicinski suggested. Reported-by: Hulk Robot Signed-off-by: Wang Yufen Link: https://lore.kernel.org/r/20220607120028.845916-1-wangyufen@huawei.com Signed-off-by: Jakub Kicinski --- include/net/ipv6.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 5b38bf1a586b..de9dcc5652c4 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1063,7 +1063,7 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr); int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), - void *from, int length, int transhdrlen, + void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags); @@ -1079,7 +1079,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, struct sk_buff_head *queue, struct sk_buff *ip6_make_skb(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), - void *from, int length, int transhdrlen, + void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct rt6_info *rt, unsigned int flags, struct inet_cork_full *cork); -- cgit v1.2.3 From d5a37b19983725d2045588cfa3a4699f5b39ae26 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 8 Jun 2022 08:34:07 +0200 Subject: block: remove bioset_init_from_src Unused now, and the interface never really made a whole lot of sense to start with. Signed-off-by: Christoph Hellwig Signed-off-by: Mike Snitzer --- include/linux/bio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 1cf3738ef1ea..992ee987f273 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -403,7 +403,6 @@ enum { extern int bioset_init(struct bio_set *, unsigned int, unsigned int, int flags); extern void bioset_exit(struct bio_set *); extern int biovec_init_pool(mempool_t *pool, int pool_entries); -extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src); struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, unsigned int opf, gfp_t gfp_mask, -- cgit v1.2.3 From 00d1f546470d89e072dd3cda12b5c794341e7268 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Thu, 9 Jun 2022 12:19:01 +0800 Subject: vdpa: make get_vq_group and set_group_asid optional This patch makes get_vq_group and set_group_asid optional. This is needed to unbreak the vDPA parent that doesn't support multiple address spaces. Cc: Gautam Dawar Fixes: aaca8373c4b1 ("vhost-vdpa: support ASID based IOTLB API") Signed-off-by: Jason Wang Message-Id: <20220609041901.2029-1-jasowang@redhat.com> Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 4700a88a28f6..7b4a13d3bd91 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -178,7 +178,8 @@ struct vdpa_map_file { * for the device * @vdev: vdpa device * Returns virtqueue algin requirement - * @get_vq_group: Get the group id for a specific virtqueue + * @get_vq_group: Get the group id for a specific + * virtqueue (optional) * @vdev: vdpa device * @idx: virtqueue index * Returns u32: group id for this virtqueue @@ -243,7 +244,7 @@ struct vdpa_map_file { * Returns the iova range supported by * the device. * @set_group_asid: Set address space identifier for a - * virtqueue group + * virtqueue group (optional) * @vdev: vdpa device * @group: virtqueue group * @asid: address space id for this group -- cgit v1.2.3 From 4527d47bb63a134c4483a1a478d0ff5874b466c7 Mon Sep 17 00:00:00 2001 From: "GONG, Ruiqi" Date: Tue, 7 Jun 2022 19:08:48 +0800 Subject: drm/atomic: fix warning of unused variable Fix the `unused-but-set-variable` warning as how other iteration wrappers do. Link: https://lore.kernel.org/all/202206071049.pofHsRih-lkp@intel.com/ Reported-by: kernel test robot Signed-off-by: GONG, Ruiqi Signed-off-by: Maxime Ripard Link: https://patchwork.freedesktop.org/patch/msgid/20220607110848.941486-1-gongruiqi1@huawei.com --- include/drm/drm_atomic.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h index 0777725085df..10b1990bc1f6 100644 --- a/include/drm/drm_atomic.h +++ b/include/drm/drm_atomic.h @@ -1022,6 +1022,7 @@ void drm_state_dump(struct drm_device *dev, struct drm_printer *p); for ((__i) = 0; \ (__i) < (__state)->num_private_objs && \ ((obj) = (__state)->private_objs[__i].ptr, \ + (void)(obj) /* Only to avoid unused-but-set-variable warning */, \ (new_obj_state) = (__state)->private_objs[__i].new_state, 1); \ (__i)++) -- cgit v1.2.3 From 69a37a8ba1b408a1c7616494aa7018e4b3844cbe Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 8 Jun 2022 15:18:34 -0400 Subject: mm/huge_memory: Fix xarray node memory leak If xas_split_alloc() fails to allocate the necessary nodes to complete the xarray entry split, it sets the xa_state to -ENOMEM, which xas_nomem() then interprets as "Please allocate more memory", not as "Please free any unnecessary memory" (which was the intended outcome). It's confusing to use xas_nomem() to free memory in this context, so call xas_destroy() instead. Reported-by: syzbot+9e27a75a8c24f3fe75c1@syzkaller.appspotmail.com Fixes: 6b24ca4a1a8d ("mm: Use multi-index entries in the page cache") Cc: stable@vger.kernel.org Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/xarray.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 72feab5ea8d4..c29e11b2c073 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -1508,6 +1508,7 @@ void *xas_find_marked(struct xa_state *, unsigned long max, xa_mark_t); void xas_init_marks(const struct xa_state *); bool xas_nomem(struct xa_state *, gfp_t); +void xas_destroy(struct xa_state *); void xas_pause(struct xa_state *); void xas_create_range(struct xa_state *); -- cgit v1.2.3 From 334f6f53abcf57782bd2fe81da1cbd893e4ef05c Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 9 Jun 2022 09:13:57 -0400 Subject: mm: Add kernel-doc for folio->mlock_count Fix "./include/linux/mm_types.h:279: warning: Function parameter or member 'mlock_count' not described in 'folio'". Also neaten the html by hiding the anon struct. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/mm_types.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index b34ff2cdbc4f..c29ab4c0cd5c 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -227,6 +227,7 @@ struct page { * struct folio - Represents a contiguous set of bytes. * @flags: Identical to the page flags. * @lru: Least Recently Used list; tracks how recently this folio was used. + * @mlock_count: Number of times this folio has been pinned by mlock(). * @mapping: The file this page belongs to, or refers to the anon_vma for * anonymous memory. * @index: Offset within the file, in units of pages. For anonymous memory, @@ -255,10 +256,14 @@ struct folio { unsigned long flags; union { struct list_head lru; + /* private: avoid cluttering the output */ struct { void *__filler; + /* public: */ unsigned int mlock_count; + /* private: */ }; + /* public: */ }; struct address_space *mapping; pgoff_t index; -- cgit v1.2.3 From 874c8ca1e60b2c564a48f7e7acc40d328d5c8733 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 9 Jun 2022 21:46:04 +0100 Subject: netfs: Fix gcc-12 warning by embedding vfs inode in netfs_i_context While randstruct was satisfied with using an open-coded "void *" offset cast for the netfs_i_context <-> inode casting, __builtin_object_size() as used by FORTIFY_SOURCE was not as easily fooled. This was causing the following complaint[1] from gcc v12: In file included from include/linux/string.h:253, from include/linux/ceph/ceph_debug.h:7, from fs/ceph/inode.c:2: In function 'fortify_memset_chk', inlined from 'netfs_i_context_init' at include/linux/netfs.h:326:2, inlined from 'ceph_alloc_inode' at fs/ceph/inode.c:463:2: include/linux/fortify-string.h:242:25: warning: call to '__write_overflow_field' declared with attribute warning: detected write beyond size of field (1st parameter); maybe use struct_group()? [-Wattribute-warning] 242 | __write_overflow_field(p_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Fix this by embedding a struct inode into struct netfs_i_context (which should perhaps be renamed to struct netfs_inode). The struct inode vfs_inode fields are then removed from the 9p, afs, ceph and cifs inode structs and vfs_inode is then simply changed to "netfs.inode" in those filesystems. Further, rename netfs_i_context to netfs_inode, get rid of the netfs_inode() function that converted a netfs_i_context pointer to an inode pointer (that can now be done with &ctx->inode) and rename the netfs_i_context() function to netfs_inode() (which is now a wrapper around container_of()). Most of the changes were done with: perl -p -i -e 's/vfs_inode/netfs.inode/'g \ `git grep -l 'vfs_inode' -- fs/{9p,afs,ceph,cifs}/*.[ch]` Kees suggested doing it with a pair structure[2] and a special declarator to insert that into the network filesystem's inode wrapper[3], but I think it's cleaner to embed it - and then it doesn't matter if struct randomisation reorders things. Dave Chinner suggested using a filesystem-specific VFS_I() function in each filesystem to convert that filesystem's own inode wrapper struct into the VFS inode struct[4]. Version #2: - Fix a couple of missed name changes due to a disabled cifs option. - Rename nfs_i_context to nfs_inode - Use "netfs" instead of "nic" as the member name in per-fs inode wrapper structs. [ This also undoes commit 507160f46c55 ("netfs: gcc-12: temporarily disable '-Wattribute-warning' for now") that is no longer needed ] Fixes: bc899ee1c898 ("netfs: Add a netfs inode context") Reported-by: Jeff Layton Signed-off-by: David Howells Reviewed-by: Jeff Layton Reviewed-by: Kees Cook Reviewed-by: Xiubo Li cc: Jonathan Corbet cc: Eric Van Hensbergen cc: Latchesar Ionkov cc: Dominique Martinet cc: Christian Schoenebeck cc: Marc Dionne cc: Ilya Dryomov cc: Steve French cc: William Kucharski cc: "Matthew Wilcox (Oracle)" cc: Dave Chinner cc: linux-doc@vger.kernel.org cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cifs@vger.kernel.org cc: samba-technical@lists.samba.org cc: linux-fsdevel@vger.kernel.org cc: linux-hardening@vger.kernel.org Link: https://lore.kernel.org/r/d2ad3a3d7bdd794c6efb562d2f2b655fb67756b9.camel@kernel.org/ [1] Link: https://lore.kernel.org/r/20220517210230.864239-1-keescook@chromium.org/ [2] Link: https://lore.kernel.org/r/20220518202212.2322058-1-keescook@chromium.org/ [3] Link: https://lore.kernel.org/r/20220524101205.GI2306852@dread.disaster.area/ [4] Link: https://lore.kernel.org/r/165296786831.3591209.12111293034669289733.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/165305805651.4094995.7763502506786714216.stgit@warthog.procyon.org.uk # v2 Signed-off-by: Linus Torvalds --- include/linux/netfs.h | 41 ++++++++++++++++------------------------- 1 file changed, 16 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 77fa6a61706a..6dbb4c9ce50d 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -119,9 +119,10 @@ typedef void (*netfs_io_terminated_t)(void *priv, ssize_t transferred_or_error, bool was_async); /* - * Per-inode description. This must be directly after the inode struct. + * Per-inode context. This wraps the VFS inode. */ -struct netfs_i_context { +struct netfs_inode { + struct inode inode; /* The VFS inode */ const struct netfs_request_ops *ops; #if IS_ENABLED(CONFIG_FSCACHE) struct fscache_cookie *cache; @@ -256,7 +257,7 @@ struct netfs_cache_ops { * boundary as appropriate. */ enum netfs_io_source (*prepare_read)(struct netfs_io_subrequest *subreq, - loff_t i_size); + loff_t i_size); /* Prepare a write operation, working out what part of the write we can * actually do. @@ -288,45 +289,35 @@ extern void netfs_put_subrequest(struct netfs_io_subrequest *subreq, extern void netfs_stats_show(struct seq_file *); /** - * netfs_i_context - Get the netfs inode context from the inode + * netfs_inode - Get the netfs inode context from the inode * @inode: The inode to query * * Get the netfs lib inode context from the network filesystem's inode. The * context struct is expected to directly follow on from the VFS inode struct. */ -static inline struct netfs_i_context *netfs_i_context(struct inode *inode) +static inline struct netfs_inode *netfs_inode(struct inode *inode) { - return (void *)inode + sizeof(*inode); + return container_of(inode, struct netfs_inode, inode); } /** - * netfs_inode - Get the netfs inode from the inode context - * @ctx: The context to query - * - * Get the netfs inode from the netfs library's inode context. The VFS inode - * is expected to directly precede the context struct. - */ -static inline struct inode *netfs_inode(struct netfs_i_context *ctx) -{ - return (void *)ctx - sizeof(struct inode); -} - -/** - * netfs_i_context_init - Initialise a netfs lib context + * netfs_inode_init - Initialise a netfslib inode context * @inode: The inode with which the context is associated * @ops: The netfs's operations list * * Initialise the netfs library context struct. This is expected to follow on * directly from the VFS inode struct. */ -static inline void netfs_i_context_init(struct inode *inode, - const struct netfs_request_ops *ops) +static inline void netfs_inode_init(struct inode *inode, + const struct netfs_request_ops *ops) { - struct netfs_i_context *ctx = netfs_i_context(inode); + struct netfs_inode *ctx = netfs_inode(inode); - memset(ctx, 0, sizeof(*ctx)); ctx->ops = ops; ctx->remote_i_size = i_size_read(inode); +#if IS_ENABLED(CONFIG_FSCACHE) + ctx->cache = NULL; +#endif } /** @@ -338,7 +329,7 @@ static inline void netfs_i_context_init(struct inode *inode, */ static inline void netfs_resize_file(struct inode *inode, loff_t new_i_size) { - struct netfs_i_context *ctx = netfs_i_context(inode); + struct netfs_inode *ctx = netfs_inode(inode); ctx->remote_i_size = new_i_size; } @@ -352,7 +343,7 @@ static inline void netfs_resize_file(struct inode *inode, loff_t new_i_size) static inline struct fscache_cookie *netfs_i_cookie(struct inode *inode) { #if IS_ENABLED(CONFIG_FSCACHE) - struct netfs_i_context *ctx = netfs_i_context(inode); + struct netfs_inode *ctx = netfs_inode(inode); return ctx->cache; #else return NULL; -- cgit v1.2.3 From b489a6e5871690735752f8875f411e4d0cd8e5df Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Wed, 8 Jun 2022 18:34:25 +0300 Subject: tls: Rename TLS_INFO_ZC_SENDFILE to TLS_INFO_ZC_TX To embrace possible future optimizations of TLS, rename zerocopy sendfile definitions to more generic ones: * setsockopt: TLS_TX_ZEROCOPY_SENDFILE- > TLS_TX_ZEROCOPY_RO * sock_diag: TLS_INFO_ZC_SENDFILE -> TLS_INFO_ZC_RO_TX RO stands for readonly and emphasizes that the application shouldn't modify the data being transmitted with zerocopy to avoid potential disconnection. Fixes: c1318b39c7d3 ("tls: Add opt-in zerocopy mode of sendfile()") Signed-off-by: Maxim Mikityanskiy Link: https://lore.kernel.org/r/20220608153425.3151146-1-maximmi@nvidia.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/tls.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h index ac39328eabe7..bb8f80812b0b 100644 --- a/include/uapi/linux/tls.h +++ b/include/uapi/linux/tls.h @@ -39,7 +39,7 @@ /* TLS socket options */ #define TLS_TX 1 /* Set transmit parameters */ #define TLS_RX 2 /* Set receive parameters */ -#define TLS_TX_ZEROCOPY_SENDFILE 3 /* transmit zerocopy sendfile */ +#define TLS_TX_ZEROCOPY_RO 3 /* TX zerocopy (only sendfile now) */ /* Supported versions */ #define TLS_VERSION_MINOR(ver) ((ver) & 0xFF) @@ -161,7 +161,7 @@ enum { TLS_INFO_CIPHER, TLS_INFO_TXCONF, TLS_INFO_RXCONF, - TLS_INFO_ZC_SENDFILE, + TLS_INFO_ZC_RO_TX, __TLS_INFO_MAX, }; #define TLS_INFO_MAX (__TLS_INFO_MAX - 1) -- cgit v1.2.3 From 39e0f991a62ed5efabd20711a7b6e7da92603170 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Tue, 7 Jun 2022 17:00:16 +0200 Subject: random: mark bootloader randomness code as __init add_bootloader_randomness() and the variables it touches are only used during __init and not after, so mark these as __init. At the same time, unexport this, since it's only called by other __init code that's built-in. Cc: stable@vger.kernel.org Fixes: 428826f5358c ("fdt: add support for rng-seed") Signed-off-by: Jason A. Donenfeld --- include/linux/random.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index fae0c84027fd..223b4bd584e7 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -13,7 +13,7 @@ struct notifier_block; void add_device_randomness(const void *buf, size_t len); -void add_bootloader_randomness(const void *buf, size_t len); +void __init add_bootloader_randomness(const void *buf, size_t len); void add_input_randomness(unsigned int type, unsigned int code, unsigned int value) __latent_entropy; void add_interrupt_randomness(int irq) __latent_entropy; -- cgit v1.2.3 From e052a478a7daeca67664f7addd308ff51dd40654 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 8 Jun 2022 10:31:25 +0200 Subject: random: remove rng_has_arch_random() With arch randomness being used by every distro and enabled in defconfigs, the distinction between rng_has_arch_random() and rng_is_initialized() is now rather small. In fact, the places where they differ are now places where paranoid users and system builders really don't want arch randomness to be used, in which case we should respect that choice, or places where arch randomness is known to be broken, in which case that choice is all the more important. So this commit just removes the function and its one user. Reviewed-by: Petr Mladek # for vsprintf.c Signed-off-by: Jason A. Donenfeld --- include/linux/random.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/random.h b/include/linux/random.h index 223b4bd584e7..20e389a14e5c 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -74,7 +74,6 @@ static inline unsigned long get_random_canary(void) int __init random_init(const char *command_line); bool rng_is_initialized(void); -bool rng_has_arch_random(void); int wait_for_random_bytes(void); /* Calls wait_for_random_bytes() and then calls get_random_bytes(buf, nbytes). -- cgit v1.2.3 From cfab87c2c2715763dc7e43d9968bdaa01cde4bc3 Mon Sep 17 00:00:00 2001 From: Vijaya Krishna Nivarthi Date: Wed, 8 Jun 2022 00:22:44 +0530 Subject: serial: core: Introduce callback for start_rx and do stop_rx in suspend only if this callback implementation is present. In suspend sequence there is a need to perform stop_rx during suspend sequence to prevent any asynchronous data over rx line. However this can cause problem to drivers which dont do re-start_rx during set_termios. Add new callback start_rx and perform stop_rx only when implementation of start_rx is present. Also add call to start_rx in resume sequence so that drivers who come across this problem can make use of this framework. Fixes: c9d2325cdb92 ("serial: core: Do stop_rx in suspend path for console if console_suspend is disabled") Reviewed-by: Douglas Anderson Signed-off-by: Vijaya Krishna Nivarthi Link: https://lore.kernel.org/r/1654627965-1461-2-git-send-email-quic_vnivarth@quicinc.com Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index cbd5070bc87f..657a0fc68a3f 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -45,6 +45,7 @@ struct uart_ops { void (*unthrottle)(struct uart_port *); void (*send_xchar)(struct uart_port *, char ch); void (*stop_rx)(struct uart_port *); + void (*start_rx)(struct uart_port *); void (*enable_ms)(struct uart_port *); void (*break_ctl)(struct uart_port *, int ctl); int (*startup)(struct uart_port *); -- cgit v1.2.3 From cd756dafd86ee3a4969906086f3c2537e0c6d9d0 Mon Sep 17 00:00:00 2001 From: Peter Robinson Date: Mon, 6 Jun 2022 14:22:00 +0100 Subject: staging: Also remove the Unisys visorbus.h The commit that removed the Unisys s-Par and visorbus drivers left around the include/linux/visorbus.h file mentioned in the MAINTAINERS entry, we can also remove that too. Fixes: e5f45b011e4a ("staging: Remove the drivers for the Unisys s-Par") Reviewed-by: Fabio M. De Francesco Signed-off-by: Peter Robinson Link: https://lore.kernel.org/r/20220606132200.2873243-1-pbrobinson@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/visorbus.h | 344 ----------------------------------------------- 1 file changed, 344 deletions(-) delete mode 100644 include/linux/visorbus.h (limited to 'include') diff --git a/include/linux/visorbus.h b/include/linux/visorbus.h deleted file mode 100644 index 0d8bd6769b13..000000000000 --- a/include/linux/visorbus.h +++ /dev/null @@ -1,344 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * Copyright (C) 2010 - 2013 UNISYS CORPORATION - * All rights reserved. - */ - -/* - * This header file is to be included by other kernel mode components that - * implement a particular kind of visor_device. Each of these other kernel - * mode components is called a visor device driver. Refer to visortemplate - * for a minimal sample visor device driver. - * - * There should be nothing in this file that is private to the visorbus - * bus implementation itself. - */ - -#ifndef __VISORBUS_H__ -#define __VISORBUS_H__ - -#include - -#define VISOR_CHANNEL_SIGNATURE ('L' << 24 | 'N' << 16 | 'C' << 8 | 'E') - -/* - * enum channel_serverstate - * @CHANNELSRV_UNINITIALIZED: Channel is in an undefined state. - * @CHANNELSRV_READY: Channel has been initialized by server. - */ -enum channel_serverstate { - CHANNELSRV_UNINITIALIZED = 0, - CHANNELSRV_READY = 1 -}; - -/* - * enum channel_clientstate - * @CHANNELCLI_DETACHED: - * @CHANNELCLI_DISABLED: Client can see channel but is NOT allowed to use it - * unless given TBD* explicit request - * (should actually be < DETACHED). - * @CHANNELCLI_ATTACHING: Legacy EFI client request for EFI server to attach. - * @CHANNELCLI_ATTACHED: Idle, but client may want to use channel any time. - * @CHANNELCLI_BUSY: Client either wants to use or is using channel. - * @CHANNELCLI_OWNED: "No worries" state - client can access channel - * anytime. - */ -enum channel_clientstate { - CHANNELCLI_DETACHED = 0, - CHANNELCLI_DISABLED = 1, - CHANNELCLI_ATTACHING = 2, - CHANNELCLI_ATTACHED = 3, - CHANNELCLI_BUSY = 4, - CHANNELCLI_OWNED = 5 -}; - -/* - * Values for VISOR_CHANNEL_PROTOCOL.Features: This define exists so that - * a guest can look at the FeatureFlags in the io channel, and configure the - * driver to use interrupts or not based on this setting. All feature bits for - * all channels should be defined here. The io channel feature bits are defined - * below. - */ -#define VISOR_DRIVER_ENABLES_INTS (0x1ULL << 1) -#define VISOR_CHANNEL_IS_POLLING (0x1ULL << 3) -#define VISOR_IOVM_OK_DRIVER_DISABLING_INTS (0x1ULL << 4) -#define VISOR_DRIVER_DISABLES_INTS (0x1ULL << 5) -#define VISOR_DRIVER_ENHANCED_RCVBUF_CHECKING (0x1ULL << 6) - -/* - * struct channel_header - Common Channel Header - * @signature: Signature. - * @legacy_state: DEPRECATED - being replaced by. - * @header_size: sizeof(struct channel_header). - * @size: Total size of this channel in bytes. - * @features: Flags to modify behavior. - * @chtype: Channel type: data, bus, control, etc.. - * @partition_handle: ID of guest partition. - * @handle: Device number of this channel in client. - * @ch_space_offset: Offset in bytes to channel specific area. - * @version_id: Struct channel_header Version ID. - * @partition_index: Index of guest partition. - * @zone_uuid: Guid of Channel's zone. - * @cli_str_offset: Offset from channel header to null-terminated - * ClientString (0 if ClientString not present). - * @cli_state_boot: CHANNEL_CLIENTSTATE of pre-boot EFI client of this - * channel. - * @cmd_state_cli: CHANNEL_COMMANDSTATE (overloaded in Windows drivers, see - * ServerStateUp, ServerStateDown, etc). - * @cli_state_os: CHANNEL_CLIENTSTATE of Guest OS client of this channel. - * @ch_characteristic: CHANNEL_CHARACTERISTIC_. - * @cmd_state_srv: CHANNEL_COMMANDSTATE (overloaded in Windows drivers, see - * ServerStateUp, ServerStateDown, etc). - * @srv_state: CHANNEL_SERVERSTATE. - * @cli_error_boot: Bits to indicate err states for boot clients, so err - * messages can be throttled. - * @cli_error_os: Bits to indicate err states for OS clients, so err - * messages can be throttled. - * @filler: Pad out to 128 byte cacheline. - * @recover_channel: Please add all new single-byte values below here. - */ -struct channel_header { - u64 signature; - u32 legacy_state; - /* SrvState, CliStateBoot, and CliStateOS below */ - u32 header_size; - u64 size; - u64 features; - guid_t chtype; - u64 partition_handle; - u64 handle; - u64 ch_space_offset; - u32 version_id; - u32 partition_index; - guid_t zone_guid; - u32 cli_str_offset; - u32 cli_state_boot; - u32 cmd_state_cli; - u32 cli_state_os; - u32 ch_characteristic; - u32 cmd_state_srv; - u32 srv_state; - u8 cli_error_boot; - u8 cli_error_os; - u8 filler[1]; - u8 recover_channel; -} __packed; - -#define VISOR_CHANNEL_ENABLE_INTS (0x1ULL << 0) - -/* - * struct signal_queue_header - Subheader for the Signal Type variation of the - * Common Channel. - * @version: SIGNAL_QUEUE_HEADER Version ID. - * @chtype: Queue type: storage, network. - * @size: Total size of this queue in bytes. - * @sig_base_offset: Offset to signal queue area. - * @features: Flags to modify behavior. - * @num_sent: Total # of signals placed in this queue. - * @num_overflows: Total # of inserts failed due to full queue. - * @signal_size: Total size of a signal for this queue. - * @max_slots: Max # of slots in queue, 1 slot is always empty. - * @max_signals: Max # of signals in queue (MaxSignalSlots-1). - * @head: Queue head signal #. - * @num_received: Total # of signals removed from this queue. - * @tail: Queue tail signal. - * @reserved1: Reserved field. - * @reserved2: Reserved field. - * @client_queue: - * @num_irq_received: Total # of Interrupts received. This is incremented by the - * ISR in the guest windows driver. - * @num_empty: Number of times that visor_signal_remove is called and - * returned Empty Status. - * @errorflags: Error bits set during SignalReinit to denote trouble with - * client's fields. - * @filler: Pad out to 64 byte cacheline. - */ -struct signal_queue_header { - /* 1st cache line */ - u32 version; - u32 chtype; - u64 size; - u64 sig_base_offset; - u64 features; - u64 num_sent; - u64 num_overflows; - u32 signal_size; - u32 max_slots; - u32 max_signals; - u32 head; - /* 2nd cache line */ - u64 num_received; - u32 tail; - u32 reserved1; - u64 reserved2; - u64 client_queue; - u64 num_irq_received; - u64 num_empty; - u32 errorflags; - u8 filler[12]; -} __packed; - -/* VISORCHANNEL Guids */ -/* {414815ed-c58c-11da-95a9-00e08161165f} */ -#define VISOR_VHBA_CHANNEL_GUID \ - GUID_INIT(0x414815ed, 0xc58c, 0x11da, \ - 0x95, 0xa9, 0x0, 0xe0, 0x81, 0x61, 0x16, 0x5f) -#define VISOR_VHBA_CHANNEL_GUID_STR \ - "414815ed-c58c-11da-95a9-00e08161165f" -struct visorchipset_state { - u32 created:1; - u32 attached:1; - u32 configured:1; - u32 running:1; - /* Remaining bits in this 32-bit word are reserved. */ -}; - -/** - * struct visor_device - A device type for things "plugged" into the visorbus - * bus - * @visorchannel: Points to the channel that the device is - * associated with. - * @channel_type_guid: Identifies the channel type to the bus driver. - * @device: Device struct meant for use by the bus driver - * only. - * @list_all: Used by the bus driver to enumerate devices. - * @timer: Timer fired periodically to do interrupt-type - * activity. - * @being_removed: Indicates that the device is being removed from - * the bus. Private bus driver use only. - * @visordriver_callback_lock: Used by the bus driver to lock when adding and - * removing devices. - * @pausing: Indicates that a change towards a paused state. - * is in progress. Only modified by the bus driver. - * @resuming: Indicates that a change towards a running state - * is in progress. Only modified by the bus driver. - * @chipset_bus_no: Private field used by the bus driver. - * @chipset_dev_no: Private field used the bus driver. - * @state: Used to indicate the current state of the - * device. - * @inst: Unique GUID for this instance of the device. - * @name: Name of the device. - * @pending_msg_hdr: For private use by bus driver to respond to - * hypervisor requests. - * @vbus_hdr_info: A pointer to header info. Private use by bus - * driver. - * @partition_guid: Indicates client partion id. This should be the - * same across all visor_devices in the current - * guest. Private use by bus driver only. - */ -struct visor_device { - struct visorchannel *visorchannel; - guid_t channel_type_guid; - /* These fields are for private use by the bus driver only. */ - struct device device; - struct list_head list_all; - struct timer_list timer; - bool timer_active; - bool being_removed; - struct mutex visordriver_callback_lock; /* synchronize probe/remove */ - bool pausing; - bool resuming; - u32 chipset_bus_no; - u32 chipset_dev_no; - struct visorchipset_state state; - guid_t inst; - u8 *name; - struct controlvm_message_header *pending_msg_hdr; - void *vbus_hdr_info; - guid_t partition_guid; - struct dentry *debugfs_dir; - struct dentry *debugfs_bus_info; -}; - -#define to_visor_device(x) container_of(x, struct visor_device, device) - -typedef void (*visorbus_state_complete_func) (struct visor_device *dev, - int status); - -/* - * This struct describes a specific visor channel, by providing its GUID, name, - * and sizes. - */ -struct visor_channeltype_descriptor { - const guid_t guid; - const char *name; - u64 min_bytes; - u32 version; -}; - -/** - * struct visor_driver - Information provided by each visor driver when it - * registers with the visorbus driver - * @name: Name of the visor driver. - * @owner: The module owner. - * @channel_types: Types of channels handled by this driver, ending with - * a zero GUID. Our specialized BUS.match() method knows - * about this list, and uses it to determine whether this - * driver will in fact handle a new device that it has - * detected. - * @probe: Called when a new device comes online, by our probe() - * function specified by driver.probe() (triggered - * ultimately by some call to driver_register(), - * bus_add_driver(), or driver_attach()). - * @remove: Called when a new device is removed, by our remove() - * function specified by driver.remove() (triggered - * ultimately by some call to device_release_driver()). - * @channel_interrupt: Called periodically, whenever there is a possiblity - * that "something interesting" may have happened to the - * channel. - * @pause: Called to initiate a change of the device's state. If - * the return valu`e is < 0, there was an error and the - * state transition will NOT occur. If the return value - * is >= 0, then the state transition was INITIATED - * successfully, and complete_func() will be called (or - * was just called) with the final status when either the - * state transition fails or completes successfully. - * @resume: Behaves similar to pause. - * @driver: Private reference to the device driver. For use by bus - * driver only. - */ -struct visor_driver { - const char *name; - struct module *owner; - struct visor_channeltype_descriptor *channel_types; - int (*probe)(struct visor_device *dev); - void (*remove)(struct visor_device *dev); - void (*channel_interrupt)(struct visor_device *dev); - int (*pause)(struct visor_device *dev, - visorbus_state_complete_func complete_func); - int (*resume)(struct visor_device *dev, - visorbus_state_complete_func complete_func); - - /* These fields are for private use by the bus driver only. */ - struct device_driver driver; -}; - -#define to_visor_driver(x) (container_of(x, struct visor_driver, driver)) - -int visor_check_channel(struct channel_header *ch, struct device *dev, - const guid_t *expected_uuid, char *chname, - u64 expected_min_bytes, u32 expected_version, - u64 expected_signature); - -int visorbus_register_visor_driver(struct visor_driver *drv); -void visorbus_unregister_visor_driver(struct visor_driver *drv); -int visorbus_read_channel(struct visor_device *dev, - unsigned long offset, void *dest, - unsigned long nbytes); -int visorbus_write_channel(struct visor_device *dev, - unsigned long offset, void *src, - unsigned long nbytes); -int visorbus_enable_channel_interrupts(struct visor_device *dev); -void visorbus_disable_channel_interrupts(struct visor_device *dev); - -int visorchannel_signalremove(struct visorchannel *channel, u32 queue, - void *msg); -int visorchannel_signalinsert(struct visorchannel *channel, u32 queue, - void *msg); -bool visorchannel_signalempty(struct visorchannel *channel, u32 queue); -const guid_t *visorchannel_get_guid(struct visorchannel *channel); - -#define BUS_ROOT_DEVICE UINT_MAX -struct visor_device *visorbus_get_device_by_id(u32 bus_no, u32 dev_no, - struct visor_device *from); -#endif -- cgit v1.2.3 From 4314f9f4f85832b5082f4e38b07b63b11baa538c Mon Sep 17 00:00:00 2001 From: Cristian Marussi Date: Wed, 8 Jun 2022 10:55:28 +0100 Subject: firmware: arm_scmi: Avoid using extended string-buffers sizes if not necessary Commit b260fccaebdc2 ("firmware: arm_scmi: Add SCMI v3.1 protocol extended names support") moved all the name string buffers to use the extended buffer size of 64 instead of the required 16 bytes. While that should be fine if the firmware terminates the string before 16 bytes, there is possibility of copying random data if the name is not NULL terminated by the firmware. SCMI base protocol agent_name/vendor_id/sub_vendor_id are defined by the specification as NULL-terminated ASCII strings up to 16-bytes in length. The underlying buffers and message descriptors are currently bigger than needed; resize them to fit only the strictly needed 16 bytes to avoid any possible leaks when reading data from the firmware. Change the size argument of strlcpy to use SCMI_SHORT_NAME_MAX_SIZE always when dealing with short domain names, so as to limit the possibility that an ill-formed non-NULL terminated short reply from the SCMI platform firmware can leak stale content laying in the underlying transport shared memory area. While at that, convert all strings handling routines to use the preferred strscpy. Link: https://lore.kernel.org/r/20220608095530.497879-1-cristian.marussi@arm.com Fixes: b260fccaebdc2 ("firmware: arm_scmi: Add SCMI v3.1 protocol extended names support") Signed-off-by: Cristian Marussi Signed-off-by: Sudeep Holla --- include/linux/scmi_protocol.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 1c58646ba381..704111f63993 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -13,8 +13,9 @@ #include #include -#define SCMI_MAX_STR_SIZE 64 -#define SCMI_MAX_NUM_RATES 16 +#define SCMI_MAX_STR_SIZE 64 +#define SCMI_SHORT_NAME_MAX_SIZE 16 +#define SCMI_MAX_NUM_RATES 16 /** * struct scmi_revision_info - version information structure @@ -36,8 +37,8 @@ struct scmi_revision_info { u8 num_protocols; u8 num_agents; u32 impl_ver; - char vendor_id[SCMI_MAX_STR_SIZE]; - char sub_vendor_id[SCMI_MAX_STR_SIZE]; + char vendor_id[SCMI_SHORT_NAME_MAX_SIZE]; + char sub_vendor_id[SCMI_SHORT_NAME_MAX_SIZE]; }; struct scmi_clock_info { -- cgit v1.2.3 From e81fb4198e27925b151aad1450e0fd607d6733f8 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 9 Jun 2022 15:04:01 -0700 Subject: netfs: Further cleanups after struct netfs_inode wrapper introduced Change the signature of netfs helper functions to take a struct netfs_inode pointer rather than a struct inode pointer where appropriate, thereby relieving the need for the network filesystem to convert its internal inode format down to the VFS inode only for netfslib to bounce it back up. For type safety, it's better not to do that (and it's less typing too). Give netfs_write_begin() an extra argument to pass in a pointer to the netfs_inode struct rather than deriving it internally from the file pointer. Note that the ->write_begin() and ->write_end() ops are intended to be replaced in the future by netfslib code that manages this without the need to call in twice for each page. netfs_readpage() and similar are intended to be pointed at directly by the address_space_operations table, so must stick to the signature dictated by the function pointers there. Changes ======= - Updated the kerneldoc comments and documentation [DH]. Signed-off-by: David Howells cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/CAHk-=wgkwKyNmNdKpQkqZ6DnmUL-x9hp0YBnUGjaPFEAdxDTbw@mail.gmail.com/ --- include/linux/netfs.h | 22 +++++++++------------- 1 file changed, 9 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 6dbb4c9ce50d..a62739f3726b 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -277,7 +277,8 @@ struct netfs_cache_ops { struct readahead_control; extern void netfs_readahead(struct readahead_control *); int netfs_read_folio(struct file *, struct folio *); -extern int netfs_write_begin(struct file *, struct address_space *, +extern int netfs_write_begin(struct netfs_inode *, + struct file *, struct address_space *, loff_t, unsigned int, struct folio **, void **); @@ -302,19 +303,17 @@ static inline struct netfs_inode *netfs_inode(struct inode *inode) /** * netfs_inode_init - Initialise a netfslib inode context - * @inode: The inode with which the context is associated + * @inode: The netfs inode to initialise * @ops: The netfs's operations list * * Initialise the netfs library context struct. This is expected to follow on * directly from the VFS inode struct. */ -static inline void netfs_inode_init(struct inode *inode, +static inline void netfs_inode_init(struct netfs_inode *ctx, const struct netfs_request_ops *ops) { - struct netfs_inode *ctx = netfs_inode(inode); - ctx->ops = ops; - ctx->remote_i_size = i_size_read(inode); + ctx->remote_i_size = i_size_read(&ctx->inode); #if IS_ENABLED(CONFIG_FSCACHE) ctx->cache = NULL; #endif @@ -322,28 +321,25 @@ static inline void netfs_inode_init(struct inode *inode, /** * netfs_resize_file - Note that a file got resized - * @inode: The inode being resized + * @ctx: The netfs inode being resized * @new_i_size: The new file size * * Inform the netfs lib that a file got resized so that it can adjust its state. */ -static inline void netfs_resize_file(struct inode *inode, loff_t new_i_size) +static inline void netfs_resize_file(struct netfs_inode *ctx, loff_t new_i_size) { - struct netfs_inode *ctx = netfs_inode(inode); - ctx->remote_i_size = new_i_size; } /** * netfs_i_cookie - Get the cache cookie from the inode - * @inode: The inode to query + * @ctx: The netfs inode to query * * Get the caching cookie (if enabled) from the network filesystem's inode. */ -static inline struct fscache_cookie *netfs_i_cookie(struct inode *inode) +static inline struct fscache_cookie *netfs_i_cookie(struct netfs_inode *ctx) { #if IS_ENABLED(CONFIG_FSCACHE) - struct netfs_inode *ctx = netfs_inode(inode); return ctx->cache; #else return NULL; -- cgit v1.2.3 From 40a81101202300df7db273f77dda9fbe6271b1d2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 25 Feb 2022 11:19:14 +0000 Subject: netfs: Rename the netfs_io_request cleanup op and give it an op pointer The netfs_io_request cleanup op is now always in a position to be given a pointer to a netfs_io_request struct, so this can be passed in instead of the mapping and private data arguments (both of which are included in the struct). So rename the ->cleanup op to ->free_request (to match ->init_request) and pass in the I/O pointer. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com --- include/linux/netfs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index a62739f3726b..097cdd644665 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -206,7 +206,9 @@ struct netfs_io_request { */ struct netfs_request_ops { int (*init_request)(struct netfs_io_request *rreq, struct file *file); + void (*free_request)(struct netfs_io_request *rreq); int (*begin_cache_operation)(struct netfs_io_request *rreq); + void (*expand_readahead)(struct netfs_io_request *rreq); bool (*clamp_length)(struct netfs_io_subrequest *subreq); void (*issue_read)(struct netfs_io_subrequest *subreq); @@ -214,7 +216,6 @@ struct netfs_request_ops { int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, struct folio *folio, void **_fsdata); void (*done)(struct netfs_io_request *rreq); - void (*cleanup)(struct address_space *mapping, void *netfs_priv); }; /* -- cgit v1.2.3 From 8bee9dd953b69c634d1c9a3241a8b357469ad4aa Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jonathan=20Neusch=C3=A4fer?= Date: Fri, 10 Jun 2022 01:41:10 +0200 Subject: workqueue: Switch to new kerneldoc syntax for named variable macro argument MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The syntax without dots is available since commit 43756e347f21 ("scripts/kernel-doc: Add support for named variable macro arguments"). The same HTML output is produced with and without this patch. Signed-off-by: Jonathan Neuschäfer Acked-by: Tejun Heo Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index e1f1c8b1121b..62e75dd40d9a 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -406,7 +406,7 @@ alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...); * alloc_ordered_workqueue - allocate an ordered workqueue * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful) - * @args...: args for @fmt + * @args: args for @fmt * * Allocate an ordered workqueue. An ordered workqueue executes at * most one work item at any given time in the queued order. They are -- cgit v1.2.3 From 993d0b287e2ef7bee2e8b13b0ce4d2b5066f278e Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 12 Jun 2022 22:32:25 +0100 Subject: usercopy: Handle vm_map_ram() areas vmalloc does not allocate a vm_struct for vm_map_ram() areas. That causes us to deny usercopies from those areas. This affects XFS which uses vm_map_ram() for its directories. Fix this by calling find_vmap_area() instead of find_vm_area(). Fixes: 0aef499f3172 ("mm/usercopy: Detect vmalloc overruns") Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Uladzislau Rezki (Sony) Tested-by: Zorro Lang Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220612213227.3881769-2-willy@infradead.org --- include/linux/vmalloc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index b159c2789961..096d48aa3437 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -215,6 +215,7 @@ extern struct vm_struct *__get_vm_area_caller(unsigned long size, void free_vm_area(struct vm_struct *area); extern struct vm_struct *remove_vm_area(const void *addr); extern struct vm_struct *find_vm_area(const void *addr); +struct vmap_area *find_vmap_area(unsigned long addr); static inline bool is_vm_area_hugepages(const void *addr) { -- cgit v1.2.3 From 0f9cd1ea10d307cad221d6693b648a8956e812b0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Mon, 13 Jun 2022 09:37:03 +0200 Subject: drm/ttm: fix bulk move handling v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The resource must be on the LRU before ttm_lru_bulk_move_add() is called and we need to check if the BO is pinned or not before adding it. Additional to that we missed taking the LRU spinlock in ttm_bo_unpin(). Signed-off-by: Christian König Reviewed-by: Arunpravin Paneer Selvam Acked-by: Luben Tuikov Link: https://patchwork.freedesktop.org/patch/msgid/20220613080816.4965-1-christian.koenig@amd.com Fixes: fee2ede15542 ("drm/ttm: rework bulk move handling v5") --- include/drm/ttm/ttm_resource.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index 441653693970..ca89a48c2460 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -311,12 +311,12 @@ ttm_resource_manager_cleanup(struct ttm_resource_manager *man) } void ttm_lru_bulk_move_init(struct ttm_lru_bulk_move *bulk); -void ttm_lru_bulk_move_add(struct ttm_lru_bulk_move *bulk, - struct ttm_resource *res); -void ttm_lru_bulk_move_del(struct ttm_lru_bulk_move *bulk, - struct ttm_resource *res); void ttm_lru_bulk_move_tail(struct ttm_lru_bulk_move *bulk); +void ttm_resource_add_bulk_move(struct ttm_resource *res, + struct ttm_buffer_object *bo); +void ttm_resource_del_bulk_move(struct ttm_resource *res, + struct ttm_buffer_object *bo); void ttm_resource_move_to_lru_tail(struct ttm_resource *res); void ttm_resource_init(struct ttm_buffer_object *bo, -- cgit v1.2.3 From d884b6498d2f022098502e106d5a45ab635f2e9a Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 14 Jun 2022 17:51:18 +0100 Subject: io_uring: remove IORING_CLOSE_FD_AND_FILE_SLOT This partially reverts a7c41b4687f5902af70cd559806990930c8a307b Even though IORING_CLOSE_FD_AND_FILE_SLOT might save cycles for some users, but it tries to do two things at a time and it's not clear how to handle errors and what to return in a single result field when one part fails and another completes well. Kill it for now. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/837c745019b3795941eee4fcfd7de697886d645b.1655224415.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 776e0278f9dd..53e7dae92e42 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -47,7 +47,6 @@ struct io_uring_sqe { __u32 unlink_flags; __u32 hardlink_flags; __u32 xattr_flags; - __u32 close_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -259,11 +258,6 @@ enum io_uring_op { */ #define IORING_ACCEPT_MULTISHOT (1U << 0) -/* - * close flags, store in sqe->close_flags - */ -#define IORING_CLOSE_FD_AND_FILE_SLOT (1U << 0) - /* * IO completion data structure (Completion Queue Entry) */ -- cgit v1.2.3 From 018ab4fabddd94f1c96f3b59e180691b9e88d5d8 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 14 Jun 2022 10:36:11 -0700 Subject: netfs: fix up netfs_inode_init() docbook comment Commit e81fb4198e27 ("netfs: Further cleanups after struct netfs_inode wrapper introduced") changed the argument types and names, and actually updated the comment too (although that was thanks to David Howells, not me: my original patch only changed the code). But the comment fixup didn't go quite far enough, and didn't change the argument name in the comment, resulting in include/linux/netfs.h:314: warning: Function parameter or member 'ctx' not described in 'netfs_inode_init' include/linux/netfs.h:314: warning: Excess function parameter 'inode' description in 'netfs_inode_init' during htmldoc generation. Fixes: e81fb4198e27 ("netfs: Further cleanups after struct netfs_inode wrapper introduced") Reported-by: Stephen Rothwell Signed-off-by: Linus Torvalds --- include/linux/netfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 097cdd644665..1773e5df8e65 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -304,7 +304,7 @@ static inline struct netfs_inode *netfs_inode(struct inode *inode) /** * netfs_inode_init - Initialise a netfslib inode context - * @inode: The netfs inode to initialise + * @ctx: The netfs inode to initialise * @ops: The netfs's operations list * * Initialise the netfs library context struct. This is expected to follow on -- cgit v1.2.3 From b87f02307d3cfbda768520f0687c51ca77e14fc3 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Wed, 15 Jun 2022 18:28:05 +0200 Subject: printk: Wait for the global console lock when the system is going down There are reports that the console kthreads block the global console lock when the system is going down, for example, reboot, panic. First part of the solution was to block kthreads in these problematic system states so they stopped handling newly added messages. Second part of the solution is to wait when for the kthreads when they are actively printing. It solves the problem when a message was printed before the system entered the problematic state and the kthreads managed to step in. A busy waiting has to be used because panic() can be called in any context and in an unknown state of the scheduler. There must be a timeout because the kthread might get stuck or sleeping and never release the lock. The timeout 10s is an arbitrary value inspired by the softlockup timeout. Link: https://lore.kernel.org/r/20220610205038.GA3050413@paulmck-ThinkPad-P17-Gen-1 Link: https://lore.kernel.org/r/CAMdYzYpF4FNTBPZsEFeWRuEwSies36QM_As8osPWZSr2q-viEA@mail.gmail.com Signed-off-by: Petr Mladek Tested-by: Paul E. McKenney Link: https://lore.kernel.org/r/20220615162805.27962-3-pmladek@suse.com --- include/linux/printk.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index cd26aab0ab2a..c1e07c0652c7 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -174,6 +174,7 @@ extern void printk_prefer_direct_enter(void); extern void printk_prefer_direct_exit(void); extern bool pr_flush(int timeout_ms, bool reset_on_progress); +extern void try_block_console_kthreads(int timeout_ms); /* * Please don't use printk_ratelimit(), because it shares ratelimiting state @@ -238,6 +239,10 @@ static inline bool pr_flush(int timeout_ms, bool reset_on_progress) return true; } +static inline void try_block_console_kthreads(int timeout_ms) +{ +} + static inline int printk_ratelimit(void) { return 0; -- cgit v1.2.3 From 4bca7e80b6455772b4bf3f536dcbc19aac424d6a Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 15 Jun 2022 15:22:29 +0200 Subject: init: Initialize noop_backing_dev_info early noop_backing_dev_info is used by superblocks of various pseudofilesystems such as kdevtmpfs. After commit 10e14073107d ("writeback: Fix inode->i_io_list not be protected by inode->i_lock error") this broke because __mark_inode_dirty() started to access more fields from noop_backing_dev_info and this led to crashes inside locked_inode_to_wb_and_lock_list() called from __mark_inode_dirty(). Fix the problem by initializing noop_backing_dev_info before the filesystems get mounted. Fixes: 10e14073107d ("writeback: Fix inode->i_io_list not be protected by inode->i_lock error") Reported-and-tested-by: Suzuki K Poulose Reported-and-tested-by: Alexandru Elisei Reported-and-tested-by: Guenter Roeck Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/linux/backing-dev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 2bd073fa6bb5..d452071db572 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -119,6 +119,8 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); extern struct backing_dev_info noop_backing_dev_info; +int bdi_init(struct backing_dev_info *bdi); + /** * writeback_in_progress - determine whether there is writeback in progress * @wb: bdi_writeback of interest -- cgit v1.2.3 From 593d1ebe00a45af5cb7bda1235c0790987c2a2b2 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Wed, 15 Jun 2022 12:32:13 -0700 Subject: Revert "net: Add a second bind table hashed by port and address" This reverts: commit d5a42de8bdbe ("net: Add a second bind table hashed by port and address") commit 538aaf9b2383 ("selftests: Add test for timing a bind request to a port with a populated bhash entry") Link: https://lore.kernel.org/netdev/20220520001834.2247810-1-kuba@kernel.org/ There are a few things that need to be fixed here: * Updating bhash2 in cases where the socket's rcv saddr changes * Adding bhash2 hashbucket locks Links to syzbot reports: https://lore.kernel.org/netdev/00000000000022208805e0df247a@google.com/ https://lore.kernel.org/netdev/0000000000003f33bc05dfaf44fe@google.com/ Fixes: d5a42de8bdbe ("net: Add a second bind table hashed by port and address") Reported-by: syzbot+015d756bbd1f8b5c8f09@syzkaller.appspotmail.com Reported-by: syzbot+98fd2d1422063b0f8c44@syzkaller.appspotmail.com Reported-by: syzbot+0a847a982613c6438fba@syzkaller.appspotmail.com Signed-off-by: Joanne Koong Link: https://lore.kernel.org/r/20220615193213.2419568-1-joannelkoong@gmail.com Signed-off-by: Jakub Kicinski --- include/net/inet_connection_sock.h | 3 -- include/net/inet_hashtables.h | 68 +------------------------------------- include/net/sock.h | 14 -------- 3 files changed, 1 insertion(+), 84 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 077cd730ce2f..85cd695e7fd1 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -25,7 +25,6 @@ #undef INET_CSK_CLEAR_TIMERS struct inet_bind_bucket; -struct inet_bind2_bucket; struct tcp_congestion_ops; /* @@ -58,7 +57,6 @@ struct inet_connection_sock_af_ops { * * @icsk_accept_queue: FIFO of established children * @icsk_bind_hash: Bind node - * @icsk_bind2_hash: Bind node in the bhash2 table * @icsk_timeout: Timeout * @icsk_retransmit_timer: Resend (no ack) * @icsk_rto: Retransmit timeout @@ -85,7 +83,6 @@ struct inet_connection_sock { struct inet_sock icsk_inet; struct request_sock_queue icsk_accept_queue; struct inet_bind_bucket *icsk_bind_hash; - struct inet_bind2_bucket *icsk_bind2_hash; unsigned long icsk_timeout; struct timer_list icsk_retransmit_timer; struct timer_list icsk_delack_timer; diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index a0887b70967b..ebfa3df6f8dc 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -90,32 +90,11 @@ struct inet_bind_bucket { struct hlist_head owners; }; -struct inet_bind2_bucket { - possible_net_t ib_net; - int l3mdev; - unsigned short port; - union { -#if IS_ENABLED(CONFIG_IPV6) - struct in6_addr v6_rcv_saddr; -#endif - __be32 rcv_saddr; - }; - /* Node in the inet2_bind_hashbucket chain */ - struct hlist_node node; - /* List of sockets hashed to this bucket */ - struct hlist_head owners; -}; - static inline struct net *ib_net(struct inet_bind_bucket *ib) { return read_pnet(&ib->ib_net); } -static inline struct net *ib2_net(struct inet_bind2_bucket *ib) -{ - return read_pnet(&ib->ib_net); -} - #define inet_bind_bucket_for_each(tb, head) \ hlist_for_each_entry(tb, head, node) @@ -124,15 +103,6 @@ struct inet_bind_hashbucket { struct hlist_head chain; }; -/* This is synchronized using the inet_bind_hashbucket's spinlock. - * Instead of having separate spinlocks, the inet_bind2_hashbucket can share - * the inet_bind_hashbucket's given that in every case where the bhash2 table - * is useful, a lookup in the bhash table also occurs. - */ -struct inet_bind2_hashbucket { - struct hlist_head chain; -}; - /* Sockets can be hashed in established or listening table. * We must use different 'nulls' end-of-chain value for all hash buckets : * A socket might transition from ESTABLISH to LISTEN state without @@ -164,12 +134,6 @@ struct inet_hashinfo { */ struct kmem_cache *bind_bucket_cachep; struct inet_bind_hashbucket *bhash; - /* The 2nd binding table hashed by port and address. - * This is used primarily for expediting the resolution of bind - * conflicts. - */ - struct kmem_cache *bind2_bucket_cachep; - struct inet_bind2_hashbucket *bhash2; unsigned int bhash_size; /* The 2nd listener table hashed by local port and address */ @@ -229,36 +193,6 @@ inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net, void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket *tb); -static inline bool check_bind_bucket_match(struct inet_bind_bucket *tb, - struct net *net, - const unsigned short port, - int l3mdev) -{ - return net_eq(ib_net(tb), net) && tb->port == port && - tb->l3mdev == l3mdev; -} - -struct inet_bind2_bucket * -inet_bind2_bucket_create(struct kmem_cache *cachep, struct net *net, - struct inet_bind2_hashbucket *head, - const unsigned short port, int l3mdev, - const struct sock *sk); - -void inet_bind2_bucket_destroy(struct kmem_cache *cachep, - struct inet_bind2_bucket *tb); - -struct inet_bind2_bucket * -inet_bind2_bucket_find(struct inet_hashinfo *hinfo, struct net *net, - const unsigned short port, int l3mdev, - struct sock *sk, - struct inet_bind2_hashbucket **head); - -bool check_bind2_bucket_match_nulladdr(struct inet_bind2_bucket *tb, - struct net *net, - const unsigned short port, - int l3mdev, - const struct sock *sk); - static inline u32 inet_bhashfn(const struct net *net, const __u16 lport, const u32 bhash_size) { @@ -266,7 +200,7 @@ static inline u32 inet_bhashfn(const struct net *net, const __u16 lport, } void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, - struct inet_bind2_bucket *tb2, const unsigned short snum); + const unsigned short snum); /* Caller must disable local BH processing. */ int __inet_inherit_port(const struct sock *sk, struct sock *child); diff --git a/include/net/sock.h b/include/net/sock.h index c585ef6565d9..72ca97ccb460 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -348,7 +348,6 @@ struct sk_filter; * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags * @ns_tracker: tracker for netns reference - * @sk_bind2_node: bind node in the bhash2 table */ struct sock { /* @@ -538,7 +537,6 @@ struct sock { #endif struct rcu_head sk_rcu; netns_tracker ns_tracker; - struct hlist_node sk_bind2_node; }; enum sk_pacing { @@ -819,16 +817,6 @@ static inline void sk_add_bind_node(struct sock *sk, hlist_add_head(&sk->sk_bind_node, list); } -static inline void __sk_del_bind2_node(struct sock *sk) -{ - __hlist_del(&sk->sk_bind2_node); -} - -static inline void sk_add_bind2_node(struct sock *sk, struct hlist_head *list) -{ - hlist_add_head(&sk->sk_bind2_node, list); -} - #define sk_for_each(__sk, list) \ hlist_for_each_entry(__sk, list, sk_node) #define sk_for_each_rcu(__sk, list) \ @@ -846,8 +834,6 @@ static inline void sk_add_bind2_node(struct sock *sk, struct hlist_head *list) hlist_for_each_entry_safe(__sk, tmp, list, sk_node) #define sk_for_each_bound(__sk, list) \ hlist_for_each_entry(__sk, list, sk_bind_node) -#define sk_for_each_bound_bhash2(__sk, list) \ - hlist_for_each_entry(__sk, list, sk_bind2_node) /** * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset -- cgit v1.2.3 From 4d337cebcb1c27d9b48c48b9a98e939d4552d584 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 16 Jun 2022 09:44:00 +0800 Subject: blk-mq: avoid to touch q->elevator without any protection q->elevator is referred in blk_mq_has_sqsched() without any protection, no .q_usage_counter is held, no queue srcu and rcu read lock is held, so potential use-after-free may be triggered. Fix the issue by adding one queue flag for checking if the elevator uses single queue style dispatch. Meantime the elevator feature flag of ELEVATOR_F_MQ_AWARE isn't needed any more. Cc: Jan Kara Signed-off-by: Ming Lei Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220616014401.817001-3-ming.lei@redhat.com Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 608d577734c2..bb6e3c31b3b7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -575,6 +575,7 @@ struct request_queue { #define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */ #define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */ #define QUEUE_FLAG_NOWAIT 29 /* device supports NOWAIT */ +#define QUEUE_FLAG_SQ_SCHED 30 /* single queue style io dispatch */ #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_SAME_COMP) | \ @@ -616,6 +617,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) #define blk_queue_nowait(q) test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags) +#define blk_queue_sq_sched(q) test_bit(QUEUE_FLAG_SQ_SCHED, &(q)->queue_flags) extern void blk_set_pm_only(struct request_queue *q); extern void blk_clear_pm_only(struct request_queue *q); @@ -1006,8 +1008,6 @@ void disk_set_independent_access_ranges(struct gendisk *disk, */ /* Supports zoned block devices sequential write constraint */ #define ELEVATOR_F_ZBD_SEQ_WRITE (1U << 0) -/* Supports scheduling on multiple hardware queues */ -#define ELEVATOR_F_MQ_AWARE (1U << 1) extern void blk_queue_required_elevator_features(struct request_queue *q, unsigned int features); -- cgit v1.2.3 From 034e5afad921f1c08c001bf147fb1ba76ae33498 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Fri, 10 Jun 2022 16:35:13 -0600 Subject: mm: re-allow pinning of zero pfns The commit referenced below subtly and inadvertently changed the logic to disallow pinning of zero pfns. This breaks device assignment with vfio and potentially various other users of gup. Exclude the zero page test from the negation. Link: https://lkml.kernel.org/r/165490039431.944052.12458624139225785964.stgit@omen Fixes: 1c563432588d ("mm: fix is_pinnable_page against a cma page") Signed-off-by: Alex Williamson Acked-by: Minchan Kim Acked-by: David Hildenbrand Reported-by: Yishai Hadas Cc: Paul E. McKenney Cc: John Hubbard Cc: John Dias Cc: Jason Gunthorpe Cc: Zhangfei Gao Cc: Matthew Wilcox Cc: Joao Martins Cc: Yi Liu Signed-off-by: Andrew Morton --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index bc8f326be0ce..781fae17177d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1600,7 +1600,7 @@ static inline bool is_pinnable_page(struct page *page) if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE) return false; #endif - return !(is_zone_movable_page(page) || is_zero_pfn(page_to_pfn(page))); + return !is_zone_movable_page(page) || is_zero_pfn(page_to_pfn(page)); } #else static inline bool is_pinnable_page(struct page *page) -- cgit v1.2.3 From 67f22ba7750f940bcd7e1b12720896c505c2d63f Mon Sep 17 00:00:00 2001 From: zhenwei pi Date: Wed, 15 Jun 2022 17:32:09 +0800 Subject: mm/memory-failure: disable unpoison once hw error happens Currently unpoison_memory(unsigned long pfn) is designed for soft poison(hwpoison-inject) only. Since 17fae1294ad9d, the KPTE gets cleared on a x86 platform once hardware memory corrupts. Unpoisoning a hardware corrupted page puts page back buddy only, the kernel has a chance to access the page with *NOT PRESENT* KPTE. This leads BUG during accessing on the corrupted KPTE. Suggested by David&Naoya, disable unpoison mechanism when a real HW error happens to avoid BUG like this: Unpoison: Software-unpoisoned page 0x61234 BUG: unable to handle page fault for address: ffff888061234000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 2c01067 P4D 2c01067 PUD 107267063 PMD 10382b063 PTE 800fffff9edcb062 Oops: 0002 [#1] PREEMPT SMP NOPTI CPU: 4 PID: 26551 Comm: stress Kdump: loaded Tainted: G M OE 5.18.0.bm.1-amd64 #7 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) ... RIP: 0010:clear_page_erms+0x7/0x10 Code: ... RSP: 0000:ffffc90001107bc8 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000901 RCX: 0000000000001000 RDX: ffffea0001848d00 RSI: ffffea0001848d40 RDI: ffff888061234000 RBP: ffffea0001848d00 R08: 0000000000000901 R09: 0000000000001276 R10: 0000000000000003 R11: 0000000000000000 R12: 0000000000000001 R13: 0000000000000000 R14: 0000000000140dca R15: 0000000000000001 FS: 00007fd8b2333740(0000) GS:ffff88813fd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff888061234000 CR3: 00000001023d2005 CR4: 0000000000770ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: prep_new_page+0x151/0x170 get_page_from_freelist+0xca0/0xe20 ? sysvec_apic_timer_interrupt+0xab/0xc0 ? asm_sysvec_apic_timer_interrupt+0x1b/0x20 __alloc_pages+0x17e/0x340 __folio_alloc+0x17/0x40 vma_alloc_folio+0x84/0x280 __handle_mm_fault+0x8d4/0xeb0 handle_mm_fault+0xd5/0x2a0 do_user_addr_fault+0x1d0/0x680 ? kvm_read_and_reset_apf_flags+0x3b/0x50 exc_page_fault+0x78/0x170 asm_exc_page_fault+0x27/0x30 Link: https://lkml.kernel.org/r/20220615093209.259374-2-pizhenwei@bytedance.com Fixes: 847ce401df392 ("HWPOISON: Add unpoisoning support") Fixes: 17fae1294ad9d ("x86/{mce,mm}: Unmap the entire page if the whole page is affected and poisoned") Signed-off-by: zhenwei pi Acked-by: David Hildenbrand Acked-by: Naoya Horiguchi Reviewed-by: Miaohe Lin Reviewed-by: Oscar Salvador Cc: Greg Kroah-Hartman Cc: [5.8+] Signed-off-by: Andrew Morton --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 781fae17177d..cf3d0d673f6b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3232,6 +3232,7 @@ enum mf_flags { MF_MUST_KILL = 1 << 2, MF_SOFT_OFFLINE = 1 << 3, MF_UNPOISON = 1 << 4, + MF_SW_SIMULATED = 1 << 5, }; extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue(unsigned long pfn, int flags); -- cgit v1.2.3 From 540a92bfe6dab7310b9df2e488ba247d784d0163 Mon Sep 17 00:00:00 2001 From: Edward Wu Date: Fri, 17 Jun 2022 11:32:20 +0800 Subject: ata: libata: add qc->flags in ata_qc_complete_template tracepoint Add flags value to check the result of ata completion Fixes: 255c03d15a29 ("libata: Add tracepoints") Cc: stable@vger.kernel.org Signed-off-by: Edward Wu Signed-off-by: Damien Le Moal --- include/trace/events/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/trace/events/libata.h b/include/trace/events/libata.h index d4e631aa976f..6025dd8ba4aa 100644 --- a/include/trace/events/libata.h +++ b/include/trace/events/libata.h @@ -288,6 +288,7 @@ DECLARE_EVENT_CLASS(ata_qc_complete_template, __entry->hob_feature = qc->result_tf.hob_feature; __entry->nsect = qc->result_tf.nsect; __entry->hob_nsect = qc->result_tf.hob_nsect; + __entry->flags = qc->flags; ), TP_printk("ata_port=%u ata_dev=%u tag=%d flags=%s status=%s " \ -- cgit v1.2.3 From 5cf9c91ba927119fc6606b938b1895bb2459d3bc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Jun 2022 09:48:25 +0200 Subject: block: serialize all debugfs operations using q->debugfs_mutex Various places like I/O schedulers or the QOS infrastructure try to register debugfs files on demans, which can race with creating and removing the main queue debugfs directory. Use the existing debugfs_mutex to serialize all debugfs operations that rely on q->debugfs_dir or the directories hanging off it. To make the teardown code a little simpler declare all debugfs dentry pointers and not just the main one uncoditionally in blkdev.h. Move debugfs_mutex next to the dentries that it protects and document what it is used for. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220614074827.458955-3-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bb6e3c31b3b7..73c886eba8e1 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -482,7 +482,6 @@ struct request_queue { #endif /* CONFIG_BLK_DEV_ZONED */ int node; - struct mutex debugfs_mutex; #ifdef CONFIG_BLK_DEV_IO_TRACE struct blk_trace __rcu *blk_trace; #endif @@ -526,11 +525,12 @@ struct request_queue { struct bio_set bio_split; struct dentry *debugfs_dir; - -#ifdef CONFIG_BLK_DEBUG_FS struct dentry *sched_debugfs_dir; struct dentry *rqos_debugfs_dir; -#endif + /* + * Serializes all debugfs metadata operations using the above dentries. + */ + struct mutex debugfs_mutex; bool mq_sysfs_init_done; -- cgit v1.2.3 From c01d4d0a82b71857be7449380338bc53dde2da92 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Thu, 16 Jun 2022 15:00:51 +0200 Subject: random: quiet urandom warning ratelimit suppression message random.c ratelimits how much it warns about uninitialized urandom reads using __ratelimit(). When the RNG is finally initialized, it prints the number of missed messages due to ratelimiting. It has been this way since that functionality was introduced back in 2018. Recently, cc1e127bfa95 ("random: remove ratelimiting for in-kernel unseeded randomness") put a bit more stress on the urandom ratelimiting, which teased out a bug in the implementation. Specifically, when under pressure, __ratelimit() will print its own message and reset the count back to 0, making the final message at the end less useful. Secondly, it does so as a pr_warn(), which apparently is undesirable for people's CI. Fortunately, __ratelimit() has the RATELIMIT_MSG_ON_RELEASE flag exactly for this purpose, so we set the flag. Fixes: 4e00b339e264 ("random: rate limit unseeded randomness warnings") Cc: stable@vger.kernel.org Reported-by: Jon Hunter Reported-by: Ron Economos Tested-by: Ron Economos Signed-off-by: Jason A. Donenfeld --- include/linux/ratelimit_types.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ratelimit_types.h b/include/linux/ratelimit_types.h index c21c7f8103e2..002266693e50 100644 --- a/include/linux/ratelimit_types.h +++ b/include/linux/ratelimit_types.h @@ -23,12 +23,16 @@ struct ratelimit_state { unsigned long flags; }; -#define RATELIMIT_STATE_INIT(name, interval_init, burst_init) { \ - .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ - .interval = interval_init, \ - .burst = burst_init, \ +#define RATELIMIT_STATE_INIT_FLAGS(name, interval_init, burst_init, flags_init) { \ + .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ + .interval = interval_init, \ + .burst = burst_init, \ + .flags = flags_init, \ } +#define RATELIMIT_STATE_INIT(name, interval_init, burst_init) \ + RATELIMIT_STATE_INIT_FLAGS(name, interval_init, burst_init, 0) + #define RATELIMIT_STATE_INIT_DISABLED \ RATELIMIT_STATE_INIT(ratelimit_state, 0, DEFAULT_RATELIMIT_BURST) -- cgit v1.2.3 From 9243fc4cd28c8bdddd7fe0abd5bbec3c4fdf5052 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 3 Jun 2022 14:35:29 +0900 Subject: block: remove queue from struct blk_independent_access_range The request queue pointer in struct blk_independent_access_range is unused. Remove it. Signed-off-by: Damien Le Moal Fixes: 41e46b3c2aa2 ("block: Fix potential deadlock in blk_ia_range_sysfs_show()") Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220603053529.76405-1-damien.lemoal@opensource.wdc.com Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 73c886eba8e1..2f7b43444c5f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -342,7 +342,6 @@ static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev, */ struct blk_independent_access_range { struct kobject kobj; - struct request_queue *queue; sector_t sector; sector_t nr_sectors; }; -- cgit v1.2.3 From 60050ffe3d770dd1df5b641aa48f49d07a54bd84 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 18 May 2022 23:48:09 +0100 Subject: certs: Move load_certificate_list() to be with the asymmetric keys code Move load_certificate_list(), which loads a series of binary X.509 certificates from a blob and inserts them as keys into a keyring, to be with the asymmetric keys code that it drives. This makes it easier to add FIPS selftest code in which we need to load up a private keyring for the tests to use. Signed-off-by: David Howells Reviewed-by: Simo Sorce Reviewed-by: Herbert Xu cc: keyrings@vger.kernel.org cc: linux-crypto@vger.kernel.org Link: https://lore.kernel.org/r/165515742145.1554877.13488098107542537203.stgit@warthog.procyon.org.uk/ --- include/keys/asymmetric-type.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/keys/asymmetric-type.h b/include/keys/asymmetric-type.h index 6c5d4963e15b..69a13e1e5b2e 100644 --- a/include/keys/asymmetric-type.h +++ b/include/keys/asymmetric-type.h @@ -84,6 +84,9 @@ extern struct key *find_asymmetric_key(struct key *keyring, const struct asymmetric_key_id *id_2, bool partial); +int x509_load_certificate_list(const u8 cert_list[], const unsigned long list_size, + const struct key *keyring); + /* * The payload is at the discretion of the subtype. */ -- cgit v1.2.3 From e34a07c0ae3906f97eb18df50902e2a01c1015b6 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 20 Jun 2022 12:13:53 -0700 Subject: sock: redo the psock vs ULP protection check Commit 8a59f9d1e3d4 ("sock: Introduce sk->sk_prot->psock_update_sk_prot()") has moved the inet_csk_has_ulp(sk) check from sk_psock_init() to the new tcp_bpf_update_proto() function. I'm guessing that this was done to allow creating psocks for non-inet sockets. Unfortunately the destruction path for psock includes the ULP unwind, so we need to fail the sk_psock_init() itself. Otherwise if ULP is already present we'll notice that later, and call tcp_update_ulp() with the sk_proto of the ULP itself, which will most likely result in the ULP looping its callbacks. Fixes: 8a59f9d1e3d4 ("sock: Introduce sk->sk_prot->psock_update_sk_prot()") Signed-off-by: Jakub Kicinski Reviewed-by: John Fastabend Reviewed-by: Jakub Sitnicki Tested-by: Jakub Sitnicki Link: https://lore.kernel.org/r/20220620191353.1184629-2-kuba@kernel.org Signed-off-by: Paolo Abeni --- include/net/inet_sock.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index c1b5dcd6597c..daead5fb389a 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -253,6 +253,11 @@ struct inet_sock { #define IP_CMSG_CHECKSUM BIT(7) #define IP_CMSG_RECVFRAGSIZE BIT(8) +static inline bool sk_is_inet(struct sock *sk) +{ + return sk->sk_family == AF_INET || sk->sk_family == AF_INET6; +} + /** * sk_to_full_sk - Access to a full socket * @sk: pointer to a socket -- cgit v1.2.3 From 23c9cd56007e90b2c2317c5eab6ab12921b4314a Mon Sep 17 00:00:00 2001 From: Joel Granados Date: Tue, 21 Jun 2022 09:05:00 +0200 Subject: nvme: fix the CRIMS and CRWMS definitions to match the spec Adjust the values of NVME_CAP_CRMS_CRIMS and NVME_CAP_CRMS_CRWMS masks as they are different from the ones in TP4084 - Time-to-ready. Fixes: 354201c53e61 ("nvme: add support for TP4084 - Time-to-Ready Enhancements"). Signed-off-by: Joel Granados Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 29ec3e3481ff..e3934003f239 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -233,8 +233,8 @@ enum { }; enum { - NVME_CAP_CRMS_CRIMS = 1ULL << 59, - NVME_CAP_CRMS_CRWMS = 1ULL << 60, + NVME_CAP_CRMS_CRWMS = 1ULL << 59, + NVME_CAP_CRMS_CRIMS = 1ULL << 60, }; struct nvme_id_power_state { -- cgit v1.2.3 From e70b64a3f28b9f54602ae3e706b1dc1338de3df7 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Thu, 23 Jun 2022 01:37:43 -0700 Subject: io_uring: move io_uring_get_opcode out of TP_printk The TP_printk macro's are not supposed to use custom code ([1]) or else tools such as perf cannot use these events. Convert the opcode string representation to use the __string wiring that the event framework provides ([2]). [1]: https://lwn.net/Articles/379903/ [2]: https://lwn.net/Articles/381064/ Fixes: 033b87d24f72 ("io_uring: use the text representation of ops in trace") Signed-off-by: Dylan Yudaken Link: https://lore.kernel.org/r/20220623083743.2648321-1-dylany@fb.com [axboe: fixup spurious removal of sq_thread assignment] Signed-off-by: Jens Axboe --- include/trace/events/io_uring.h | 42 ++++++++++++++++++++++++++++++++++------- 1 file changed, 35 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 66fcc5a1a5b1..aa2f951b07cd 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -158,6 +158,8 @@ TRACE_EVENT(io_uring_queue_async_work, __field( unsigned int, flags ) __field( struct io_wq_work *, work ) __field( int, rw ) + + __string( op_str, io_uring_get_opcode(opcode) ) ), TP_fast_assign( @@ -168,11 +170,13 @@ TRACE_EVENT(io_uring_queue_async_work, __entry->opcode = opcode; __entry->work = work; __entry->rw = rw; + + __assign_str(op_str, io_uring_get_opcode(opcode)); ), TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, flags 0x%x, %s queue, work %p", __entry->ctx, __entry->req, __entry->user_data, - io_uring_get_opcode(__entry->opcode), + __get_str(op_str), __entry->flags, __entry->rw ? "hashed" : "normal", __entry->work) ); @@ -198,6 +202,8 @@ TRACE_EVENT(io_uring_defer, __field( void *, req ) __field( unsigned long long, data ) __field( u8, opcode ) + + __string( op_str, io_uring_get_opcode(opcode) ) ), TP_fast_assign( @@ -205,11 +211,13 @@ TRACE_EVENT(io_uring_defer, __entry->req = req; __entry->data = user_data; __entry->opcode = opcode; + + __assign_str(op_str, io_uring_get_opcode(opcode)); ), TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s", __entry->ctx, __entry->req, __entry->data, - io_uring_get_opcode(__entry->opcode)) + __get_str(op_str)) ); /** @@ -298,6 +306,8 @@ TRACE_EVENT(io_uring_fail_link, __field( unsigned long long, user_data ) __field( u8, opcode ) __field( void *, link ) + + __string( op_str, io_uring_get_opcode(opcode) ) ), TP_fast_assign( @@ -306,11 +316,13 @@ TRACE_EVENT(io_uring_fail_link, __entry->user_data = user_data; __entry->opcode = opcode; __entry->link = link; + + __assign_str(op_str, io_uring_get_opcode(opcode)); ), TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, link %p", __entry->ctx, __entry->req, __entry->user_data, - io_uring_get_opcode(__entry->opcode), __entry->link) + __get_str(op_str), __entry->link) ); /** @@ -390,6 +402,8 @@ TRACE_EVENT(io_uring_submit_sqe, __field( u32, flags ) __field( bool, force_nonblock ) __field( bool, sq_thread ) + + __string( op_str, io_uring_get_opcode(opcode) ) ), TP_fast_assign( @@ -400,11 +414,13 @@ TRACE_EVENT(io_uring_submit_sqe, __entry->flags = flags; __entry->force_nonblock = force_nonblock; __entry->sq_thread = sq_thread; + + __assign_str(op_str, io_uring_get_opcode(opcode)); ), TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, flags 0x%x, " "non block %d, sq_thread %d", __entry->ctx, __entry->req, - __entry->user_data, io_uring_get_opcode(__entry->opcode), + __entry->user_data, __get_str(op_str), __entry->flags, __entry->force_nonblock, __entry->sq_thread) ); @@ -435,6 +451,8 @@ TRACE_EVENT(io_uring_poll_arm, __field( u8, opcode ) __field( int, mask ) __field( int, events ) + + __string( op_str, io_uring_get_opcode(opcode) ) ), TP_fast_assign( @@ -444,11 +462,13 @@ TRACE_EVENT(io_uring_poll_arm, __entry->opcode = opcode; __entry->mask = mask; __entry->events = events; + + __assign_str(op_str, io_uring_get_opcode(opcode)); ), TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, mask 0x%x, events 0x%x", __entry->ctx, __entry->req, __entry->user_data, - io_uring_get_opcode(__entry->opcode), + __get_str(op_str), __entry->mask, __entry->events) ); @@ -474,6 +494,8 @@ TRACE_EVENT(io_uring_task_add, __field( unsigned long long, user_data ) __field( u8, opcode ) __field( int, mask ) + + __string( op_str, io_uring_get_opcode(opcode) ) ), TP_fast_assign( @@ -482,11 +504,13 @@ TRACE_EVENT(io_uring_task_add, __entry->user_data = user_data; __entry->opcode = opcode; __entry->mask = mask; + + __assign_str(op_str, io_uring_get_opcode(opcode)); ), TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, mask %x", __entry->ctx, __entry->req, __entry->user_data, - io_uring_get_opcode(__entry->opcode), + __get_str(op_str), __entry->mask) ); @@ -523,6 +547,8 @@ TRACE_EVENT(io_uring_req_failed, __field( u64, pad1 ) __field( u64, addr3 ) __field( int, error ) + + __string( op_str, io_uring_get_opcode(sqe->opcode) ) ), TP_fast_assign( @@ -542,6 +568,8 @@ TRACE_EVENT(io_uring_req_failed, __entry->pad1 = sqe->__pad2[0]; __entry->addr3 = sqe->addr3; __entry->error = error; + + __assign_str(op_str, io_uring_get_opcode(sqe->opcode)); ), TP_printk("ring %p, req %p, user_data 0x%llx, " @@ -550,7 +578,7 @@ TRACE_EVENT(io_uring_req_failed, "personality=%d, file_index=%d, pad=0x%llx, addr3=%llx, " "error=%d", __entry->ctx, __entry->req, __entry->user_data, - io_uring_get_opcode(__entry->opcode), + __get_str(op_str), __entry->flags, __entry->ioprio, (unsigned long long)__entry->off, (unsigned long long) __entry->addr, __entry->len, -- cgit v1.2.3 From 20fb0c8272bbb102d15bdd11aa64f828619dd7cc Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Thu, 23 Jun 2022 16:51:52 +0200 Subject: Revert "printk: Wait for the global console lock when the system is going down" This reverts commit b87f02307d3cfbda768520f0687c51ca77e14fc3. The testing of 5.19 release candidates revealed missing synchronization between early and regular console functionality. It would be possible to start the console kthreads later as a workaround. But it is clear that console lock serialized console drivers between each other. It opens a big area of possible problems that were not considered by people involved in the development and review. printk() is crucial for debugging kernel issues and console output is very important part of it. The number of consoles is huge and a proper review would take some time. As a result it need to be reverted for 5.19. Link: https://lore.kernel.org/r/YrBdjVwBOVgLfHyb@alley Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220623145157.21938-2-pmladek@suse.com --- include/linux/printk.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index c1e07c0652c7..cd26aab0ab2a 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -174,7 +174,6 @@ extern void printk_prefer_direct_enter(void); extern void printk_prefer_direct_exit(void); extern bool pr_flush(int timeout_ms, bool reset_on_progress); -extern void try_block_console_kthreads(int timeout_ms); /* * Please don't use printk_ratelimit(), because it shares ratelimiting state @@ -239,10 +238,6 @@ static inline bool pr_flush(int timeout_ms, bool reset_on_progress) return true; } -static inline void try_block_console_kthreads(int timeout_ms) -{ -} - static inline int printk_ratelimit(void) { return 0; -- cgit v1.2.3 From 2d9ef940f89e0ab4fde7ba6f769d82f2a450c35a Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Thu, 23 Jun 2022 16:51:55 +0200 Subject: Revert "printk: extend console_lock for per-console locking" This reverts commit 8e274732115f63c1d09136284431b3555bd5cc56. The testing of 5.19 release candidates revealed missing synchronization between early and regular console functionality. It would be possible to start the console kthreads later as a workaround. But it is clear that console lock serialized console drivers between each other. It opens a big area of possible problems that were not considered by people involved in the development and review. printk() is crucial for debugging kernel issues and console output is very important part of it. The number of consoles is huge and a proper review would take some time. As a result it need to be reverted for 5.19. Link: https://lore.kernel.org/r/YrBdjVwBOVgLfHyb@alley Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220623145157.21938-5-pmladek@suse.com --- include/linux/console.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include') diff --git a/include/linux/console.h b/include/linux/console.h index 143653090c48..9a251e70c090 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -16,7 +16,6 @@ #include #include -#include struct vc_data; struct console_font_op; @@ -155,20 +154,6 @@ struct console { u64 seq; unsigned long dropped; struct task_struct *thread; - bool blocked; - - /* - * The per-console lock is used by printing kthreads to synchronize - * this console with callers of console_lock(). This is necessary in - * order to allow printing kthreads to run in parallel to each other, - * while each safely accessing the @blocked field and synchronizing - * against direct printing via console_lock/console_unlock. - * - * Note: For synchronizing against direct printing via - * console_trylock/console_unlock, see the static global - * variable @console_kthreads_active. - */ - struct mutex lock; void *data; struct console *next; -- cgit v1.2.3 From 5831788afb17b89c5b531fb60cbd798613ccbb63 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Thu, 23 Jun 2022 16:51:56 +0200 Subject: Revert "printk: add kthread console printers" This reverts commit 09c5ba0aa2fcfdadb17d045c3ee6f86d69270df7. This reverts commit b87f02307d3cfbda768520f0687c51ca77e14fc3. The testing of 5.19 release candidates revealed missing synchronization between early and regular console functionality. It would be possible to start the console kthreads later as a workaround. But it is clear that console lock serialized console drivers between each other. It opens a big area of possible problems that were not considered by people involved in the development and review. printk() is crucial for debugging kernel issues and console output is very important part of it. The number of consoles is huge and a proper review would take some time. As a result it need to be reverted for 5.19. Link: https://lore.kernel.org/r/YrBdjVwBOVgLfHyb@alley Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220623145157.21938-6-pmladek@suse.com --- include/linux/console.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/console.h b/include/linux/console.h index 9a251e70c090..8c1686e2c233 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -153,8 +153,6 @@ struct console { uint ospeed; u64 seq; unsigned long dropped; - struct task_struct *thread; - void *data; struct console *next; }; -- cgit v1.2.3 From 07a22b61946f0b80065b0ddcc703b715f84355f5 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Thu, 23 Jun 2022 16:51:57 +0200 Subject: Revert "printk: add functions to prefer direct printing" This reverts commit 2bb2b7b57f81255c13f4395ea911d6bdc70c9fe2. The testing of 5.19 release candidates revealed missing synchronization between early and regular console functionality. It would be possible to start the console kthreads later as a workaround. But it is clear that console lock serialized console drivers between each other. It opens a big area of possible problems that were not considered by people involved in the development and review. printk() is crucial for debugging kernel issues and console output is very important part of it. The number of consoles is huge and a proper review would take some time. As a result it need to be reverted for 5.19. Link: https://lore.kernel.org/r/YrBdjVwBOVgLfHyb@alley Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20220623145157.21938-7-pmladek@suse.com --- include/linux/printk.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index cd26aab0ab2a..091fba7283e1 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -170,9 +170,6 @@ extern void __printk_safe_exit(void); #define printk_deferred_enter __printk_safe_enter #define printk_deferred_exit __printk_safe_exit -extern void printk_prefer_direct_enter(void); -extern void printk_prefer_direct_exit(void); - extern bool pr_flush(int timeout_ms, bool reset_on_progress); /* @@ -225,14 +222,6 @@ static inline void printk_deferred_exit(void) { } -static inline void printk_prefer_direct_enter(void) -{ -} - -static inline void printk_prefer_direct_exit(void) -{ -} - static inline bool pr_flush(int timeout_ms, bool reset_on_progress) { return true; -- cgit v1.2.3 From c7e1c443584ddd7facffca00e9e23b0d084e5bb3 Mon Sep 17 00:00:00 2001 From: Akira Yokosawa Date: Mon, 6 Jun 2022 13:44:24 +0900 Subject: gpio: Fix kernel-doc comments to nested union Commit 48ec13d36d3f ("gpio: Properly document parent data union") is supposed to have fixed a warning from "make htmldocs" regarding kernel-doc comments to union members. However, the same warning still remains [1]. Fix the issue by following the example found in section "Nested structs/unions" of Documentation/doc-guide/kernel-doc.rst. Signed-off-by: Akira Yokosawa Reported-by: Stephen Rothwell Fixes: 48ec13d36d3f ("gpio: Properly document parent data union") Link: https://lore.kernel.org/r/20220606093302.21febee3@canb.auug.org.au/ [1] Cc: Linus Walleij Cc: Bartosz Golaszewski Cc: Joey Gouly Cc: Marc Zyngier Tested-by: Stephen Rothwell Reviewed-by: Mauro Carvalho Chehab Signed-off-by: Bartosz Golaszewski --- include/linux/gpio/driver.h | 29 ++++++++++++++++------------- 1 file changed, 16 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index b1e0f1f8ee2e..54c3c6506503 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -167,21 +167,24 @@ struct gpio_irq_chip { */ irq_flow_handler_t parent_handler; - /** - * @parent_handler_data: - * - * If @per_parent_data is false, @parent_handler_data is a single - * pointer used as the data associated with every parent interrupt. - * - * @parent_handler_data_array: - * - * If @per_parent_data is true, @parent_handler_data_array is - * an array of @num_parents pointers, and is used to associate - * different data for each parent. This cannot be NULL if - * @per_parent_data is true. - */ union { + /** + * @parent_handler_data: + * + * If @per_parent_data is false, @parent_handler_data is a + * single pointer used as the data associated with every + * parent interrupt. + */ void *parent_handler_data; + + /** + * @parent_handler_data_array: + * + * If @per_parent_data is true, @parent_handler_data_array is + * an array of @num_parents pointers, and is used to associate + * different data for each parent. This cannot be NULL if + * @per_parent_data is true. + */ void **parent_handler_data_array; }; -- cgit v1.2.3 From c346dae4f3fbce51bbd4f2ec5e8c6f9b91e93163 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Wed, 22 Jun 2022 09:29:40 +0800 Subject: virtio: disable notification hardening by default We try to harden virtio device notifications in 8b4ec69d7e09 ("virtio: harden vring IRQ"). It works with the assumption that the driver or core can properly call virtio_device_ready() at the right place. Unfortunately, this seems to be not true and uncover various bugs of the existing drivers, mainly the issue of using virtio_device_ready() incorrectly. So let's add a Kconfig option and disable it by default. It gives us time to fix the drivers and then we can consider re-enabling it. Signed-off-by: Jason Wang Message-Id: <20220622012940.21441-1-jasowang@redhat.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Cornelia Huck --- include/linux/virtio_config.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 49c7c32815f1..b47c2e7ed0ee 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -257,6 +257,7 @@ void virtio_device_ready(struct virtio_device *dev) WARN_ON(status & VIRTIO_CONFIG_S_DRIVER_OK); +#ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION /* * The virtio_synchronize_cbs() makes sure vring_interrupt() * will see the driver specific setup if it sees vq->broken @@ -264,6 +265,7 @@ void virtio_device_ready(struct virtio_device *dev) */ virtio_synchronize_cbs(dev); __virtio_unbreak_device(dev); +#endif /* * The transport should ensure the visibility of vq->broken * before setting DRIVER_OK. See the comments for the transport -- cgit v1.2.3 From 3b89b511ea0c705cc418440e2abf9d692a556d84 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 23 Jun 2022 16:32:32 +0300 Subject: net: fix IFF_TX_SKB_NO_LINEAR definition The "1<<31" shift has a sign extension bug so IFF_TX_SKB_NO_LINEAR is 0xffffffff80000000 instead of 0x0000000080000000. Fixes: c2ff53d8049f ("net: Add priv_flags for allow tx skb without linear") Signed-off-by: Dan Carpenter Reviewed-by: Xuan Zhuo Link: https://lore.kernel.org/r/YrRrcGttfEVnf85Q@kili Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f615a66c89e9..2563d30736e9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1671,7 +1671,7 @@ enum netdev_priv_flags { IFF_FAILOVER_SLAVE = 1<<28, IFF_L3MDEV_RX_HANDLER = 1<<29, IFF_LIVE_RENAME_OK = 1<<30, - IFF_TX_SKB_NO_LINEAR = 1<<31, + IFF_TX_SKB_NO_LINEAR = BIT_ULL(31), IFF_CHANGE_PROTO_DOWN = BIT_ULL(32), }; -- cgit v1.2.3 From e34b9ed96ce3b06c79bf884009b16961ca478f87 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 22 Jun 2022 16:43:57 +0200 Subject: netfilter: nf_tables: avoid skb access on nf_stolen When verdict is NF_STOLEN, the skb might have been freed. When tracing is enabled, this can result in a use-after-free: 1. access to skb->nf_trace 2. access to skb->mark 3. computation of trace id 4. dump of packet payload To avoid 1, keep a cached copy of skb->nf_trace in the trace state struct. Refresh this copy whenever verdict is != STOLEN. Avoid 2 by skipping skb->mark access if verdict is STOLEN. 3 is avoided by precomputing the trace id. Only dump the packet when verdict is not "STOLEN". Reported-by: Pablo Neira Ayuso Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 279ae0fff7ad..5c4e5a96a984 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1338,24 +1338,28 @@ void nft_unregister_flowtable_type(struct nf_flowtable_type *type); /** * struct nft_traceinfo - nft tracing information and state * + * @trace: other struct members are initialised + * @nf_trace: copy of skb->nf_trace before rule evaluation + * @type: event type (enum nft_trace_types) + * @skbid: hash of skb to be used as trace id + * @packet_dumped: packet headers sent in a previous traceinfo message * @pkt: pktinfo currently processed * @basechain: base chain currently processed * @chain: chain currently processed * @rule: rule that was evaluated * @verdict: verdict given by rule - * @type: event type (enum nft_trace_types) - * @packet_dumped: packet headers sent in a previous traceinfo message - * @trace: other struct members are initialised */ struct nft_traceinfo { + bool trace; + bool nf_trace; + bool packet_dumped; + enum nft_trace_types type:8; + u32 skbid; const struct nft_pktinfo *pkt; const struct nft_base_chain *basechain; const struct nft_chain *chain; const struct nft_rule_dp *rule; const struct nft_verdict *verdict; - enum nft_trace_types type; - bool packet_dumped; - bool trace; }; void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt, -- cgit v1.2.3 From 8698e3bab4dd7968666e84e111d0bfd17c040e77 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 27 Jun 2022 20:47:19 +0300 Subject: fanotify: refine the validation checks on non-dir inode mask Commit ceaf69f8eadc ("fanotify: do not allow setting dirent events in mask of non-dir") added restrictions about setting dirent events in the mask of a non-dir inode mark, which does not make any sense. For backward compatibility, these restictions were added only to new (v5.17+) APIs. It also does not make any sense to set the flags FAN_EVENT_ON_CHILD or FAN_ONDIR in the mask of a non-dir inode. Add these flags to the dir-only restriction of the new APIs as well. Move the check of the dir-only flags for new APIs into the helper fanotify_events_supported(), which is only called for FAN_MARK_ADD, because there is no need to error on an attempt to remove the dir-only flags from non-dir inode. Fixes: ceaf69f8eadc ("fanotify: do not allow setting dirent events in mask of non-dir") Link: https://lore.kernel.org/linux-fsdevel/20220627113224.kr2725conevh53u4@quack3.lan/ Link: https://lore.kernel.org/r/20220627174719.2838175-1-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fanotify.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index edc28555814c..e517dbcf74ed 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -111,6 +111,10 @@ FANOTIFY_PERM_EVENTS | \ FAN_Q_OVERFLOW | FAN_ONDIR) +/* Events and flags relevant only for directories */ +#define FANOTIFY_DIRONLY_EVENT_BITS (FANOTIFY_DIRENT_EVENTS | \ + FAN_EVENT_ON_CHILD | FAN_ONDIR) + #define ALL_FANOTIFY_EVENT_BITS (FANOTIFY_OUTGOING_EVENTS | \ FANOTIFY_EVENT_FLAGS) -- cgit v1.2.3 From 0fe3dbbefb74a8575f61d7801b08dbc50523d60d Mon Sep 17 00:00:00 2001 From: Tao Liu Date: Mon, 27 Jun 2022 22:00:04 +0800 Subject: linux/dim: Fix divide by 0 in RDMA DIM Fix a divide 0 error in rdma_dim_stats_compare() when prev->cpe_ratio == 0. CallTrace: Hardware name: H3C R4900 G3/RS33M2C9S, BIOS 2.00.37P21 03/12/2020 task: ffff880194b78000 task.stack: ffffc90006714000 RIP: 0010:backport_rdma_dim+0x10e/0x240 [mlx_compat] RSP: 0018:ffff880c10e83ec0 EFLAGS: 00010202 RAX: 0000000000002710 RBX: ffff88096cd7f780 RCX: 0000000000000064 RDX: 0000000000000000 RSI: 0000000000000002 RDI: 0000000000000001 RBP: 0000000000000001 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 000000001d7c6c09 R13: ffff88096cd7f780 R14: ffff880b174fe800 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff880c10e80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000a0965b00 CR3: 000000000200a003 CR4: 00000000007606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: ib_poll_handler+0x43/0x80 [ib_core] irq_poll_softirq+0xae/0x110 __do_softirq+0xd1/0x28c irq_exit+0xde/0xf0 do_IRQ+0x54/0xe0 common_interrupt+0x8f/0x8f ? cpuidle_enter_state+0xd9/0x2a0 ? cpuidle_enter_state+0xc7/0x2a0 ? do_idle+0x170/0x1d0 ? cpu_startup_entry+0x6f/0x80 ? start_secondary+0x1b9/0x210 ? secondary_startup_64+0xa5/0xb0 Code: 0f 87 e1 00 00 00 8b 4c 24 14 44 8b 43 14 89 c8 4d 63 c8 44 29 c0 99 31 d0 29 d0 31 d2 48 98 48 8d 04 80 48 8d 04 80 48 c1 e0 02 <49> f7 f1 48 83 f8 0a 0f 86 c1 00 00 00 44 39 c1 7f 10 48 89 df RIP: backport_rdma_dim+0x10e/0x240 [mlx_compat] RSP: ffff880c10e83ec0 Fixes: f4915455dcf0 ("linux/dim: Implement RDMA adaptive moderation (DIM)") Link: https://lore.kernel.org/r/20220627140004.3099-1-thomas.liu@ucloud.cn Signed-off-by: Tao Liu Reviewed-by: Max Gurtovoy Acked-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- include/linux/dim.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dim.h b/include/linux/dim.h index b698266d0035..6c5733981563 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -21,7 +21,7 @@ * We consider 10% difference as significant. */ #define IS_SIGNIFICANT_DIFF(val, ref) \ - (((100UL * abs((val) - (ref))) / (ref)) > 10) + ((ref) && (((100UL * abs((val) - (ref))) / (ref)) > 10)) /* * Calculate the gap between two values. -- cgit v1.2.3 From 06e445f740c1a0fe5d16b3dff8a4ef18e124e54e Mon Sep 17 00:00:00 2001 From: Ossama Othman Date: Mon, 27 Jun 2022 18:02:42 -0700 Subject: mptcp: fix conflict with Including before the C library header causes symbol redefinition errors at compile-time due to duplicate declarations and definitions in the header included by . Explicitly include before in when __KERNEL__ is not defined so that the C library compatibility logic in is enabled when including in user space code. Fixes: c11c5906bc0a ("mptcp: add MPTCP_SUBFLOW_ADDRS getsockopt support") Signed-off-by: Ossama Othman Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 921963589904..dfe19bf13f4c 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -2,16 +2,17 @@ #ifndef _UAPI_MPTCP_H #define _UAPI_MPTCP_H +#ifndef __KERNEL__ +#include /* for sockaddr_in and sockaddr_in6 */ +#include /* for struct sockaddr */ +#endif + #include #include #include /* for sockaddr_in */ #include /* for sockaddr_in6 */ #include /* for sockaddr_storage and sa_family */ -#ifndef __KERNEL__ -#include /* for struct sockaddr */ -#endif - #define MPTCP_SUBFLOW_FLAG_MCAP_REM _BITUL(0) #define MPTCP_SUBFLOW_FLAG_MCAP_LOC _BITUL(1) #define MPTCP_SUBFLOW_FLAG_JOIN_REM _BITUL(2) -- cgit v1.2.3 From 9e121040e54abef9ed5542e5fdfa87911cd96204 Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Tue, 7 Jun 2022 20:23:34 +0200 Subject: firmware: sysfb: Make sysfb_create_simplefb() return a pdev pointer This function just returned 0 on success or an errno code on error, but it could be useful for sysfb_init() callers to have a pointer to the device. Signed-off-by: Javier Martinez Canillas Reviewed-by: Daniel Vetter Reviewed-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20220607182338.344270-2-javierm@redhat.com --- include/linux/sysfb.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/sysfb.h b/include/linux/sysfb.h index b0dcfa26d07b..708152e9037b 100644 --- a/include/linux/sysfb.h +++ b/include/linux/sysfb.h @@ -72,8 +72,8 @@ static inline void sysfb_apply_efi_quirks(struct platform_device *pd) bool sysfb_parse_mode(const struct screen_info *si, struct simplefb_platform_data *mode); -int sysfb_create_simplefb(const struct screen_info *si, - const struct simplefb_platform_data *mode); +struct platform_device *sysfb_create_simplefb(const struct screen_info *si, + const struct simplefb_platform_data *mode); #else /* CONFIG_SYSFB_SIMPLE */ @@ -83,10 +83,10 @@ static inline bool sysfb_parse_mode(const struct screen_info *si, return false; } -static inline int sysfb_create_simplefb(const struct screen_info *si, - const struct simplefb_platform_data *mode) +static inline struct platform_device *sysfb_create_simplefb(const struct screen_info *si, + const struct simplefb_platform_data *mode) { - return -EINVAL; + return ERR_PTR(-EINVAL); } #endif /* CONFIG_SYSFB_SIMPLE */ -- cgit v1.2.3 From bde376e9de3c0bc55eedc8956b0f114c05531595 Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Tue, 7 Jun 2022 20:23:35 +0200 Subject: firmware: sysfb: Add sysfb_disable() helper function This can be used by subsystems to unregister a platform device registered by sysfb and also to disable future platform device registration in sysfb. Suggested-by: Daniel Vetter Signed-off-by: Javier Martinez Canillas Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220607182338.344270-3-javierm@redhat.com --- include/linux/sysfb.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/sysfb.h b/include/linux/sysfb.h index 708152e9037b..8ba8b5be5567 100644 --- a/include/linux/sysfb.h +++ b/include/linux/sysfb.h @@ -55,6 +55,18 @@ struct efifb_dmi_info { int flags; }; +#ifdef CONFIG_SYSFB + +void sysfb_disable(void); + +#else /* CONFIG_SYSFB */ + +static inline void sysfb_disable(void) +{ +} + +#endif /* CONFIG_SYSFB */ + #ifdef CONFIG_EFI extern struct efifb_dmi_info efifb_dmi_list[]; -- cgit v1.2.3 From 20b8264394b33adb1640a485a62a84bc1388b6a3 Mon Sep 17 00:00:00 2001 From: Carlos Llamas Date: Tue, 21 Jun 2022 20:39:21 +0000 Subject: drm/fourcc: fix integer type usage in uapi header MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Kernel uapi headers are supposed to use __[us]{8,16,32,64} types defined by as opposed to 'uint32_t' and similar. See [1] for the relevant discussion about this topic. In this particular case, the usage of 'uint64_t' escaped headers_check as these macros are not being called here. However, the following program triggers a compilation error: #include int main() { unsigned long x = AMD_FMT_MOD_CLEAR(RB); return 0; } gcc error: drm.c:5:27: error: ‘uint64_t’ undeclared (first use in this function) 5 | unsigned long x = AMD_FMT_MOD_CLEAR(RB); | ^~~~~~~~~~~~~~~~~ This patch changes AMD_FMT_MOD_{SET,CLEAR} macros to use the correct integer types, which fixes the above issue. [1] https://lkml.org/lkml/2019/6/5/18 Fixes: 8ba16d599374 ("drm/fourcc: Add AMD DRM modifiers.") Signed-off-by: Carlos Llamas Reviewed-by: Simon Ser Signed-off-by: Alex Deucher --- include/uapi/drm/drm_fourcc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index f1972154a594..0980678d502d 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -1444,11 +1444,11 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier) #define AMD_FMT_MOD_PIPE_MASK 0x7 #define AMD_FMT_MOD_SET(field, value) \ - ((uint64_t)(value) << AMD_FMT_MOD_##field##_SHIFT) + ((__u64)(value) << AMD_FMT_MOD_##field##_SHIFT) #define AMD_FMT_MOD_GET(field, value) \ (((value) >> AMD_FMT_MOD_##field##_SHIFT) & AMD_FMT_MOD_##field##_MASK) #define AMD_FMT_MOD_CLEAR(field) \ - (~((uint64_t)AMD_FMT_MOD_##field##_MASK << AMD_FMT_MOD_##field##_SHIFT)) + (~((__u64)AMD_FMT_MOD_##field##_MASK << AMD_FMT_MOD_##field##_SHIFT)) #if defined(__cplusplus) } -- cgit v1.2.3 From b5d281f6c16dd432b618bdfd36ddba1a58d5b603 Mon Sep 17 00:00:00 2001 From: Christian Marangi Date: Mon, 20 Jun 2022 00:03:51 +0200 Subject: PM / devfreq: Rework freq_table to be local to devfreq struct On a devfreq PROBE_DEFER, the freq_table in the driver profile struct, is never reset and may be leaved in an undefined state. This comes from the fact that we store the freq_table in the driver profile struct that is commonly defined as static and not reset on PROBE_DEFER. We currently skip the reinit of the freq_table if we found it's already defined since a driver may declare his own freq_table. This logic is flawed in the case devfreq core generate a freq_table, set it in the profile struct and then PROBE_DEFER, freeing the freq_table. In this case devfreq will found a NOT NULL freq_table that has been freed, skip the freq_table generation and probe the driver based on the wrong table. To fix this and correctly handle PROBE_DEFER, use a local freq_table and max_state in the devfreq struct and never modify the freq_table present in the profile struct if it does provide it. Fixes: 0ec09ac2cebe ("PM / devfreq: Set the freq_table of devfreq device") Cc: stable@vger.kernel.org Signed-off-by: Christian Marangi Signed-off-by: Chanwoo Choi --- include/linux/devfreq.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index dc10bee75a72..34aab4dd336c 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -148,6 +148,8 @@ struct devfreq_stats { * reevaluate operable frequencies. Devfreq users may use * devfreq.nb to the corresponding register notifier call chain. * @work: delayed work for load monitoring. + * @freq_table: current frequency table used by the devfreq driver. + * @max_state: count of entry present in the frequency table. * @previous_freq: previously configured frequency value. * @last_status: devfreq user device info, performance statistics * @data: Private data of the governor. The devfreq framework does not @@ -185,6 +187,9 @@ struct devfreq { struct notifier_block nb; struct delayed_work work; + unsigned long *freq_table; + unsigned int max_state; + unsigned long previous_freq; struct devfreq_dev_status last_status; -- cgit v1.2.3 From 1758bde2e4aa5ff188d53e7d9d388bbb7e12eebb Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Tue, 28 Jun 2022 12:15:08 +0200 Subject: net: phy: Don't trigger state machine while in suspend Upon system sleep, mdio_bus_phy_suspend() stops the phy_state_machine(), but subsequent interrupts may retrigger it: They may have been left enabled to facilitate wakeup and are not quiesced until the ->suspend_noirq() phase. Unwanted interrupts may hence occur between mdio_bus_phy_suspend() and dpm_suspend_noirq(), as well as between dpm_resume_noirq() and mdio_bus_phy_resume(). Retriggering the phy_state_machine() through an interrupt is not only undesirable for the reason given in mdio_bus_phy_suspend() (freezing it midway with phydev->lock held), but also because the PHY may be inaccessible after it's suspended: Accesses to USB-attached PHYs are blocked once usb_suspend_both() clears the can_submit flag and PHYs on PCI network cards may become inaccessible upon suspend as well. Amend phy_interrupt() to avoid triggering the state machine if the PHY is suspended. Signal wakeup instead if the attached net_device or its parent has been configured as a wakeup source. (Those conditions are identical to mdio_bus_phy_may_suspend().) Postpone handling of the interrupt until the PHY has resumed. Before stopping the phy_state_machine() in mdio_bus_phy_suspend(), wait for a concurrent phy_interrupt() to run to completion. That is necessary because phy_interrupt() may have checked the PHY's suspend status before the system sleep transition commenced and it may thus retrigger the state machine after it was stopped. Likewise, after re-enabling interrupt handling in mdio_bus_phy_resume(), wait for a concurrent phy_interrupt() to complete to ensure that interrupts which it postponed are properly rerun. The issue was exposed by commit 1ce8b37241ed ("usbnet: smsc95xx: Forward PHY interrupts to PHY driver to avoid polling"), but has existed since forever. Fixes: 541cd3ee00a4 ("phylib: Fix deadlock on resume") Link: https://lore.kernel.org/netdev/a5315a8a-32c2-962f-f696-de9a26d30091@samsung.com/ Reported-by: Marek Szyprowski Tested-by: Marek Szyprowski Signed-off-by: Lukas Wunner Acked-by: Rafael J. Wysocki Cc: stable@vger.kernel.org # v2.6.33+ Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/b7f386d04e9b5b0e2738f0125743e30676f309ef.1656410895.git.lukas@wunner.de Signed-off-by: Jakub Kicinski --- include/linux/phy.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index 508f1149665b..b09f7d36cff2 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -572,6 +572,10 @@ struct macsec_ops; * @mdix_ctrl: User setting of crossover * @pma_extable: Cached value of PMA/PMD Extended Abilities Register * @interrupts: Flag interrupts have been enabled + * @irq_suspended: Flag indicating PHY is suspended and therefore interrupt + * handling shall be postponed until PHY has resumed + * @irq_rerun: Flag indicating interrupts occurred while PHY was suspended, + * requiring a rerun of the interrupt handler after resume * @interface: enum phy_interface_t value * @skb: Netlink message for cable diagnostics * @nest: Netlink nest used for cable diagnostics @@ -626,6 +630,8 @@ struct phy_device { /* Interrupts are enabled */ unsigned interrupts:1; + unsigned irq_suspended:1; + unsigned irq_rerun:1; enum phy_state state; -- cgit v1.2.3 From 29c1ac230e6056b26846c66881802b581a78ad72 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 30 Jun 2022 13:25:57 +0100 Subject: io_uring: keep sendrecv flags in ioprio We waste a u64 SQE field for flags even though we don't need as many bits and it can be used for something more useful later. Store io_uring specific send/recv flags in sqe->ioprio instead of ->addr2. Signed-off-by: Pavel Begunkov Fixes: 0455d4ccec54 ("io_uring: add POLL_FIRST support for send/sendmsg and recv/recvmsg") [axboe: change comment in io_uring.h as well] Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 53e7dae92e42..f10b59d6693e 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -244,7 +244,7 @@ enum io_uring_op { #define IORING_ASYNC_CANCEL_ANY (1U << 2) /* - * send/sendmsg and recv/recvmsg flags (sqe->addr2) + * send/sendmsg and recv/recvmsg flags (sqe->ioprio) * * IORING_RECVSEND_POLL_FIRST If set, instead of first attempting to send * or receive and arm poll if that yields an -- cgit v1.2.3 From 4a557a5d1a6145ea586dc9b17a9b4e5190c9c017 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 30 Jun 2022 09:34:10 -0700 Subject: sparse: introduce conditional lock acquire function attribute The kernel tends to try to avoid conditional locking semantics because it makes it harder to think about and statically check locking rules, but we do have a few fundamental locking primitives that take locks conditionally - most obviously the 'trylock' functions. That has always been a problem for 'sparse' checking for locking imbalance, and we've had a special '__cond_lock()' macro that we've used to let sparse know how the locking works: # define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) so that you can then use this to tell sparse that (for example) the spinlock trylock macro ends up acquiring the lock when it succeeds, but not when it fails: #define raw_spin_trylock(lock) __cond_lock(lock, _raw_spin_trylock(lock)) and then sparse can follow along the locking rules when you have code like if (!spin_trylock(&dentry->d_lock)) return LRU_SKIP; .. sparse sees that the lock is held here.. spin_unlock(&dentry->d_lock); and sparse ends up happy about the lock contexts. However, this '__cond_lock()' use does result in very ugly header files, and requires you to basically wrap the real function with that macro that uses '__cond_lock'. Which has made PeterZ NAK things that try to fix sparse warnings over the years [1]. To solve this, there is now a very experimental patch to sparse that basically does the exact same thing as '__cond_lock()' did, but using a function attribute instead. That seems to make PeterZ happy [2]. Note that this does not replace existing use of '__cond_lock()', but only exposes the new proposed attribute and uses it for the previously unannotated 'refcount_dec_and_lock()' family of functions. For existing sparse installations, this will make no difference (a negative output context was ignored), but if you have the experimental sparse patch it will make sparse now understand code that uses those functions, the same way '__cond_lock()' makes sparse understand the very similar 'atomic_dec_and_lock()' uses that have the old '__cond_lock()' annotations. Note that in some cases this will silence existing context imbalance warnings. But in other cases it may end up exposing new sparse warnings for code that sparse just didn't see the locking for at all before. This is a trial, in other words. I'd expect that if it ends up being successful, and new sparse releases end up having this new attribute, we'll migrate the old-style '__cond_lock()' users to use the new-style '__cond_acquires' function attribute. The actual experimental sparse patch was posted in [3]. Link: https://lore.kernel.org/all/20130930134434.GC12926@twins.programming.kicks-ass.net/ [1] Link: https://lore.kernel.org/all/Yr60tWxN4P568x3W@worktop.programming.kicks-ass.net/ [2] Link: https://lore.kernel.org/all/CAHk-=wjZfO9hGqJ2_hGQG3U_XzSh9_XaXze=HgPdvJbgrvASfA@mail.gmail.com/ [3] Acked-by: Peter Zijlstra Cc: Alexander Aring Cc: Luc Van Oostenryck Signed-off-by: Linus Torvalds --- include/linux/compiler_types.h | 2 ++ include/linux/refcount.h | 6 +++--- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index d08dfcb0ac68..4f2a819fd60a 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -24,6 +24,7 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } /* context/locking */ # define __must_hold(x) __attribute__((context(x,1,1))) # define __acquires(x) __attribute__((context(x,0,1))) +# define __cond_acquires(x) __attribute__((context(x,0,-1))) # define __releases(x) __attribute__((context(x,1,0))) # define __acquire(x) __context__(x,1) # define __release(x) __context__(x,-1) @@ -50,6 +51,7 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } /* context/locking */ # define __must_hold(x) # define __acquires(x) +# define __cond_acquires(x) # define __releases(x) # define __acquire(x) (void)0 # define __release(x) (void)0 diff --git a/include/linux/refcount.h b/include/linux/refcount.h index b8a6e387f8f9..a62fcca97486 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -361,9 +361,9 @@ static inline void refcount_dec(refcount_t *r) extern __must_check bool refcount_dec_if_one(refcount_t *r); extern __must_check bool refcount_dec_not_one(refcount_t *r); -extern __must_check bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock); -extern __must_check bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock); +extern __must_check bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock) __cond_acquires(lock); +extern __must_check bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock) __cond_acquires(lock); extern __must_check bool refcount_dec_and_lock_irqsave(refcount_t *r, spinlock_t *lock, - unsigned long *flags); + unsigned long *flags) __cond_acquires(lock); #endif /* _LINUX_REFCOUNT_H */ -- cgit v1.2.3 From b8d5109f50969ead9d49c3e8bd78ec1f82e548e3 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 3 Jul 2022 14:40:28 -0700 Subject: lockref: remove unused 'lockref_get_or_lock()' function Looking at the conditional lock acquire functions in the kernel due to the new sparse support (see commit 4a557a5d1a61 "sparse: introduce conditional lock acquire function attribute"), it became obvious that the lockref code has a couple of them, but they don't match the usual naming convention for the other ones, and their return value logic is also reversed. In the other very similar places, the naming pattern is '*_and_lock()' (eg 'atomic_put_and_lock()' and 'refcount_dec_and_lock()'), and the function returns true when the lock is taken. The lockref code is superficially very similar to the refcount code, only with the special "atomic wrt the embedded lock" semantics. But instead of the '*_and_lock()' naming it uses '*_or_lock()'. And instead of returning true in case it took the lock, it returns true if it *didn't* take the lock. Now, arguably the reflock code is quite logical: it really is a "either decrement _or_ lock" kind of situation - and the return value is about whether the operation succeeded without any special care needed. So despite the similarities, the differences do make some sense, and maybe it's not worth trying to unify the different conditional locking primitives in this area. But while looking at this all, it did become obvious that the 'lockref_get_or_lock()' function hasn't actually had any users for almost a decade. The only user it ever had was the shortlived 'd_rcu_to_refcount()' function, and it got removed and replaced with 'lockref_get_not_dead()' back in 2013 in commits 0d98439ea3c6 ("vfs: use lockred 'dead' flag to mark unrecoverably dead dentries") and e5c832d55588 ("vfs: fix dentry RCU to refcounting possibly sleeping dput()") In fact, that single use was removed less than a week after the whole function was introduced in commit b3abd80250c1 ("lockref: add 'lockref_get_or_lock() helper") so this function has been around for a decade, but only had a user for six days. Let's just put this mis-designed and unused function out of its misery. We can think about the naming and semantic oddities of the remaining 'lockref_put_or_lock()' later, but at least that function has users. And while the naming is different and the return value doesn't match, that function matches the whole '{atomic,refcount}_dec_and_test()' pattern much better (ie the magic happens when the count goes down to zero, not when it is incremented from zero). Signed-off-by: Linus Torvalds --- include/linux/lockref.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/lockref.h b/include/linux/lockref.h index 99f17cc8e163..c3a1f78bc884 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -38,7 +38,6 @@ extern void lockref_get(struct lockref *); extern int lockref_put_return(struct lockref *); extern int lockref_get_not_zero(struct lockref *); extern int lockref_put_not_zero(struct lockref *); -extern int lockref_get_or_lock(struct lockref *); extern int lockref_put_or_lock(struct lockref *); extern void lockref_mark_dead(struct lockref *); -- cgit v1.2.3